From 25559c22cef879c5cf7119540bfe21fb379d29f3 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 9 Jul 2018 08:15:49 +0200 Subject: tee: add kernel internal client interface Adds a kernel internal TEE client interface to be used by other drivers. Reviewed-by: Sumit Garg Tested-by: Sumit Garg Tested-by: Zeng Tao Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 73 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a2b3dfcee0b5..6cfe05893a76 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -453,6 +453,79 @@ static inline int tee_shm_get_id(struct tee_shm *shm) */ struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); +/** + * tee_client_open_context() - Open a TEE context + * @start: if not NULL, continue search after this context + * @match: function to check TEE device + * @data: data for match function + * @vers: if not NULL, version data of TEE device of the context returned + * + * This function does an operation similar to open("/dev/teeX") in user space. + * A returned context must be released with tee_client_close_context(). + * + * Returns a TEE context of the first TEE device matched by the match() + * callback or an ERR_PTR. + */ +struct tee_context * +tee_client_open_context(struct tee_context *start, + int (*match)(struct tee_ioctl_version_data *, + const void *), + const void *data, struct tee_ioctl_version_data *vers); + +/** + * tee_client_close_context() - Close a TEE context + * @ctx: TEE context to close + * + * Note that all sessions previously opened with this context will be + * closed when this function is called. + */ +void tee_client_close_context(struct tee_context *ctx); + +/** + * tee_client_get_version() - Query version of TEE + * @ctx: TEE context to TEE to query + * @vers: Pointer to version data + */ +void tee_client_get_version(struct tee_context *ctx, + struct tee_ioctl_version_data *vers); + +/** + * tee_client_open_session() - Open a session to a Trusted Application + * @ctx: TEE context + * @arg: Open session arguments, see description of + * struct tee_ioctl_open_session_arg + * @param: Parameters passed to the Trusted Application + * + * Returns < 0 on error else see @arg->ret for result. If @arg->ret + * is TEEC_SUCCESS the session identifier is available in @arg->session. + */ +int tee_client_open_session(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + +/** + * tee_client_close_session() - Close a session to a Trusted Application + * @ctx: TEE Context + * @session: Session id + * + * Return < 0 on error else 0, regardless the session will not be + * valid after this function has returned. + */ +int tee_client_close_session(struct tee_context *ctx, u32 session); + +/** + * tee_client_invoke_func() - Invoke a function in a Trusted Application + * @ctx: TEE Context + * @arg: Invoke arguments, see description of + * struct tee_ioctl_invoke_arg + * @param: Parameters passed to the Trusted Application + * + * Returns < 0 on error else see @arg->ret for result. + */ +int tee_client_invoke_func(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + static inline bool tee_param_is_memref(struct tee_param *param) { switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { -- cgit v1.2.3 From 0c4a1049cf298721eaec4553d3d5039798086e12 Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Fri, 27 Jul 2018 14:44:13 +0530 Subject: soundwire: Add support to lock across bus instances Currently, the stream concept is limited to single Master and one or more Codecs. This patch extends the concept to support multiple Master(s) sharing the same reference clock and synchronized in the hardware. Modify sdw_stream_runtime to support a list of sdw_master_runtime for the same. The existing reference to a single m_rt is removed in the next patch. Typically to lock, one would acquire a global lock and then lock bus instances. In this case, the caller framework(ASoC DPCM) guarantees that stream operations on a card are always serialized. So, there is no race condition and hence no need for global lock. Bus lock(s) are acquired to reconfigure the bus while the stream is set-up. So, we add sdw_acquire_bus_lock()/sdw_release_bus_lock() APIs which are used only to reconfigure the bus. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 962971e6a9c7..ccd8dcdf06ab 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -769,6 +769,9 @@ struct sdw_stream_params { * @state: Current state of the stream * @type: Stream type PCM or PDM * @m_rt: Master runtime + * @master_list: List of Master runtime(s) in this stream. + * master_list can contain only one m_rt per Master instance + * for a stream */ struct sdw_stream_runtime { char *name; @@ -776,6 +779,7 @@ struct sdw_stream_runtime { enum sdw_stream_state state; enum sdw_stream_type type; struct sdw_master_runtime *m_rt; + struct list_head master_list; }; struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); -- cgit v1.2.3 From 48949722ced4daacfa32f13c221f173b87231ead Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 27 Jul 2018 14:44:14 +0530 Subject: soundwire: Handle multiple master instances in a stream For each SoundWire stream operation, we need to parse master list and operate upon all master runtime. This is a preparatory patch to do the boilerplate conversion of stream handling from single master runtime to handle a list of master runtime. The code to support bank switch for multiple master instances is added in the next patch. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index ccd8dcdf06ab..03df709fb8ef 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -768,7 +768,6 @@ struct sdw_stream_params { * @params: Stream parameters * @state: Current state of the stream * @type: Stream type PCM or PDM - * @m_rt: Master runtime * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance * for a stream @@ -778,7 +777,6 @@ struct sdw_stream_runtime { struct sdw_stream_params params; enum sdw_stream_state state; enum sdw_stream_type type; - struct sdw_master_runtime *m_rt; struct list_head master_list; }; -- cgit v1.2.3 From ce6e74d008ff5c8b43e3bafaa7343bf7eb69593e Mon Sep 17 00:00:00 2001 From: Shreyas NC Date: Fri, 27 Jul 2018 14:44:16 +0530 Subject: soundwire: Add support for multi link bank switch In cases of multiple Masters in a stream, synchronization between multiple Master(s) is achieved by performing bank switch together and using Master methods. Add sdw_ml_bank_switch() to wait for completion of bank switch. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 03df709fb8ef..c6aa2bf847c7 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -678,6 +678,9 @@ struct sdw_master_ops { * @defer_msg: Defer message * @clk_stop_timeout: Clock stop timeout computed * @bank_switch_timeout: Bank switch timeout computed + * @multi_link: Store bus property that indicates if multi links + * are supported. This flag is populated by drivers after reading + * appropriate firmware (ACPI/DT). */ struct sdw_bus { struct device *dev; @@ -694,6 +697,7 @@ struct sdw_bus { struct sdw_defer defer_msg; unsigned int clk_stop_timeout; u32 bank_switch_timeout; + bool multi_link; }; int sdw_add_bus_master(struct sdw_bus *bus); -- cgit v1.2.3 From 9b5c132a1ec98895fe40ba73a19e0a17293122e5 Mon Sep 17 00:00:00 2001 From: Shreyas NC Date: Fri, 27 Jul 2018 14:44:15 +0530 Subject: soundwire: keep track of Masters in a stream A multi link bankswitch can be done if the hardware supports and the stream is handled by multiple Master(s). This preparatory patch adds support to track m_rt in a stream. Modifying m_rt_count and usage is added as part of the next patch. Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart 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 c6aa2bf847c7..df313913e856 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -775,6 +775,7 @@ struct sdw_stream_params { * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance * for a stream + * @m_rt_count: Count of Master runtime(s) in this stream */ struct sdw_stream_runtime { char *name; @@ -782,6 +783,7 @@ struct sdw_stream_runtime { enum sdw_stream_state state; enum sdw_stream_type type; struct list_head master_list; + int m_rt_count; }; struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); -- cgit v1.2.3 From 976516404ff3fab2a8caa8bd6f5efc1437fed0b8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 14 Aug 2018 14:02:57 +0200 Subject: y2038: remove unused time interfaces After many small patches, at least some of the deprecated interfaces have no remaining users any more and can be removed: current_kernel_time do_settimeofday get_monotonic_boottime get_monotonic_boottime64 get_monotonic_coarse get_monotonic_coarse64 getrawmonotonic64 ktime_get_real_ts timekeeping_clocktai timespec_trunc timespec_valid_strict time_to_tm For many of the remaining time functions, we are missing one or two patches that failed to make it into 4.19, they will be removed in the following merge window. The replacement functions for the removed interfaces are documented in Documentation/core-api/timekeeping.rst. Signed-off-by: Arnd Bergmann --- include/linux/time32.h | 25 ---------------------- include/linux/timekeeping.h | 12 ----------- include/linux/timekeeping32.h | 50 ------------------------------------------- 3 files changed, 87 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time32.h b/include/linux/time32.h index d1ae43c13e25..92c0ca092d93 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -105,16 +105,6 @@ static inline bool timespec_valid(const struct timespec *ts) return true; } -static inline bool timespec_valid_strict(const struct timespec *ts) -{ - if (!timespec_valid(ts)) - return false; - /* Disallow values that could overflow ktime_t */ - if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) - return false; - return true; -} - /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted @@ -149,19 +139,6 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } -/** - * time_to_tm - converts the calendar time to local broken-down time - * - * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, - * Coordinated Universal Time (UTC). - * @offset offset seconds adding to totalsecs. - * @result pointer to struct tm variable to receive broken-down time - */ -static inline void time_to_tm(time_t totalsecs, int offset, struct tm *result) -{ - time64_to_tm(totalsecs, offset, result); -} - static inline unsigned long mktime(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, const unsigned int min, @@ -183,8 +160,6 @@ static inline bool timeval_valid(const struct timeval *tv) return true; } -extern struct timespec timespec_trunc(struct timespec t, unsigned int gran); - /** * timeval_to_ns - Convert timeval to nanoseconds * @ts: pointer to the timeval variable to be converted diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..3faba06411aa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -266,9 +266,6 @@ extern int update_persistent_clock64(struct timespec64 now); * deprecated aliases, don't use in new code */ #define getnstimeofday64(ts) ktime_get_real_ts64(ts) -#define get_monotonic_boottime64(ts) ktime_get_boottime_ts64(ts) -#define getrawmonotonic64(ts) ktime_get_raw_ts64(ts) -#define timekeeping_clocktai64(ts) ktime_get_clocktai_ts64(ts) static inline struct timespec64 current_kernel_time64(void) { @@ -279,13 +276,4 @@ static inline struct timespec64 current_kernel_time64(void) return ts; } -static inline struct timespec64 get_monotonic_coarse64(void) -{ - struct timespec64 ts; - - ktime_get_coarse_ts64(&ts); - - return ts; -} - #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index 8762c2f45f8b..a4a4991160fb 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -9,26 +9,6 @@ extern void do_gettimeofday(struct timeval *tv); unsigned long get_seconds(void); -static inline struct timespec current_kernel_time(void) -{ - struct timespec64 ts64; - - ktime_get_coarse_real_ts64(&ts64); - - return timespec64_to_timespec(ts64); -} - -/** - * Deprecated. Use do_settimeofday64(). - */ -static inline int do_settimeofday(const struct timespec *ts) -{ - struct timespec64 ts64; - - ts64 = timespec_to_timespec64(*ts); - return do_settimeofday64(&ts64); -} - static inline void getnstimeofday(struct timespec *ts) { struct timespec64 ts64; @@ -45,14 +25,6 @@ static inline void ktime_get_ts(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -static inline void ktime_get_real_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_real_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - static inline void getrawmonotonic(struct timespec *ts) { struct timespec64 ts64; @@ -61,15 +33,6 @@ static inline void getrawmonotonic(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -static inline struct timespec get_monotonic_coarse(void) -{ - struct timespec64 ts64; - - ktime_get_coarse_ts64(&ts64); - - return timespec64_to_timespec(ts64); -} - static inline void getboottime(struct timespec *ts) { struct timespec64 ts64; @@ -78,19 +41,6 @@ static inline void getboottime(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -/* - * Timespec interfaces utilizing the ktime based ones - */ -static inline void get_monotonic_boottime(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_boottime()); -} - -static inline void timekeeping_clocktai(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_clocktai()); -} - /* * Persistent clock related interfaces */ -- cgit v1.2.3 From 33e26418193f58d1895f2f968e1953b1caf8deb7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 14 Aug 2018 15:18:20 +0200 Subject: y2038: make do_gettimeofday() and get_seconds() inline get_seconds() and do_gettimeofday() are only used by a few modules now any more (waiting for the respective patches to get accepted), and they are among the last holdouts of code that is not y2038 safe in the core kernel. Move the implementation into the timekeeping32.h header to clean up the core kernel and isolate the old interfaces further. Signed-off-by: Arnd Bergmann --- include/linux/timekeeping32.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index a4a4991160fb..a502616f7e1c 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -6,8 +6,19 @@ * over time so we can remove the file here. */ -extern void do_gettimeofday(struct timeval *tv); -unsigned long get_seconds(void); +static inline void do_gettimeofday(struct timeval *tv) +{ + struct timespec64 now; + + ktime_get_real_ts64(&now); + tv->tv_sec = now.tv_sec; + tv->tv_usec = now.tv_nsec/1000; +} + +static inline unsigned long get_seconds(void) +{ + return ktime_get_real_seconds(); +} static inline void getnstimeofday(struct timespec *ts) { -- cgit v1.2.3 From 9afc5eee65ca7d717a99d6fe8f4adfe32a40940a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Jul 2018 12:52:28 +0200 Subject: y2038: globally rename compat_time to old_time32 Christoph Hellwig suggested a slightly different path for handling backwards compatibility with the 32-bit time_t based system calls: Rather than simply reusing the compat_sys_* entry points on 32-bit architectures unchanged, we get rid of those entry points and the compat_time types by renaming them to something that makes more sense on 32-bit architectures (which don't have a compat mode otherwise), and then share the entry points under the new name with the 64-bit architectures that use them for implementing the compatibility. The following types and interfaces are renamed here, and moved from linux/compat_time.h to linux/time32.h: old new --- --- compat_time_t old_time32_t struct compat_timeval struct old_timeval32 struct compat_timespec struct old_timespec32 struct compat_itimerspec struct old_itimerspec32 ns_to_compat_timeval() ns_to_old_timeval32() get_compat_itimerspec64() get_old_itimerspec32() put_compat_itimerspec64() put_old_itimerspec32() compat_get_timespec64() get_old_timespec32() compat_put_timespec64() put_old_timespec32() As we already have aliases in place, this patch addresses only the instances that are relevant to the system call interface in particular, not those that occur in device drivers and other modules. Those will get handled separately, while providing the 64-bit version of the respective interfaces. I'm not renaming the timex, rusage and itimerval structures, as we are still debating what the new interface will look like, and whether we will need a replacement at all. This also doesn't change the names of the syscall entry points, which can be done more easily when we actually switch over the 32-bit architectures to use them, at that point we need to change COMPAT_SYSCALL_DEFINEx to SYSCALL_DEFINEx with a new name, e.g. with a _time32 suffix. Suggested-by: Christoph Hellwig Link: https://lore.kernel.org/lkml/20180705222110.GA5698@infradead.org/ Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 96 +++++++++++++++++++++--------------------- include/linux/compat_time.h | 32 -------------- include/linux/elfcore-compat.h | 8 ++-- include/linux/restart_block.h | 4 +- include/linux/syscalls.h | 2 +- include/linux/time32.h | 48 +++++++++++++++------ 6 files changed, 91 insertions(+), 99 deletions(-) delete mode 100644 include/linux/compat_time.h (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..0e058792ecf6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -7,7 +7,7 @@ */ #include -#include +#include #include #include /* for HZ */ @@ -116,13 +116,13 @@ struct compat_sel_arg_struct; struct rusage; struct compat_utimbuf { - compat_time_t actime; - compat_time_t modtime; + old_time32_t actime; + old_time32_t modtime; }; struct compat_itimerval { - struct compat_timeval it_interval; - struct compat_timeval it_value; + struct old_timeval32 it_interval; + struct old_timeval32 it_value; }; struct itimerval; @@ -146,7 +146,7 @@ struct compat_timex { compat_long_t constant; compat_long_t precision; compat_long_t tolerance; - struct compat_timeval time; + struct old_timeval32 time; compat_long_t tick; compat_long_t ppsfreq; compat_long_t jitter; @@ -307,8 +307,8 @@ struct compat_rlimit { }; struct compat_rusage { - struct compat_timeval ru_utime; - struct compat_timeval ru_stime; + struct old_timeval32 ru_utime; + struct old_timeval32 ru_stime; compat_long_t ru_maxrss; compat_long_t ru_ixrss; compat_long_t ru_idrss; @@ -457,8 +457,8 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -static inline int compat_timeval_compare(struct compat_timeval *lhs, - struct compat_timeval *rhs) +static inline int old_timeval32_compare(struct old_timeval32 *lhs, + struct old_timeval32 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; @@ -467,8 +467,8 @@ static inline int compat_timeval_compare(struct compat_timeval *lhs, return lhs->tv_usec - rhs->tv_usec; } -static inline int compat_timespec_compare(struct compat_timespec *lhs, - struct compat_timespec *rhs) +static inline int old_timespec32_compare(struct old_timespec32 *lhs, + struct old_timespec32 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; @@ -552,12 +552,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, - struct compat_timespec __user *timeout); + struct old_timespec32 __user *timeout); asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, - struct compat_timespec __user *timeout, + struct old_timespec32 __user *timeout, const struct __compat_aio_sigset __user *usig); /* fs/cookies.c */ @@ -642,11 +642,11 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timespec __user *tsp, + struct old_timespec32 __user *tsp, void __user *sig); asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, - struct compat_timespec __user *tsp, + struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); @@ -671,15 +671,15 @@ asmlinkage long compat_sys_newfstat(unsigned int fd, /* fs/timerfd.c */ asmlinkage long compat_sys_timerfd_gettime(int ufd, - struct compat_itimerspec __user *otmr); + struct old_itimerspec32 __user *otmr); asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, - const struct compat_itimerspec __user *utmr, - struct compat_itimerspec __user *otmr); + const struct old_itimerspec32 __user *utmr, + struct old_itimerspec32 __user *otmr); /* fs/utimes.c */ asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, - struct compat_timespec __user *t, + struct old_timespec32 __user *t, int flags); /* kernel/exit.c */ @@ -691,7 +691,7 @@ asmlinkage long compat_sys_waitid(int, compat_pid_t, /* kernel/futex.c */ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, - struct compat_timespec __user *utime, u32 __user *uaddr2, + struct old_timespec32 __user *utime, u32 __user *uaddr2, u32 val3); asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, @@ -701,8 +701,8 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); /* kernel/hrtimer.c */ -asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp); +asmlinkage long compat_sys_nanosleep(struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/itimer.c */ asmlinkage long compat_sys_getitimer(int which, @@ -722,19 +722,19 @@ asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); asmlinkage long compat_sys_timer_gettime(timer_t timer_id, - struct compat_itimerspec __user *setting); + struct old_itimerspec32 __user *setting); asmlinkage long compat_sys_timer_settime(timer_t timer_id, int flags, - struct compat_itimerspec __user *new, - struct compat_itimerspec __user *old); + struct old_itimerspec32 __user *new, + struct old_itimerspec32 __user *old); asmlinkage long compat_sys_clock_settime(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_gettime(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_getres(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_nanosleep(clockid_t which_clock, int flags, - struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp); + struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/ptrace.c */ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, @@ -748,7 +748,7 @@ asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, - struct compat_timespec __user *interval); + struct old_timespec32 __user *interval); /* kernel/signal.c */ asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, @@ -768,7 +768,7 @@ asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, - struct compat_timespec __user *uts, compat_size_t sigsetsize); + struct old_timespec32 __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); /* No generic prototype for rt_sigreturn */ @@ -782,9 +782,9 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource, asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); /* kernel/time.c */ -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, +asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, +asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); @@ -798,11 +798,11 @@ asmlinkage long compat_sys_mq_open(const char __user *u_name, asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, compat_size_t msg_len, unsigned int msg_prio, - const struct compat_timespec __user *u_abs_timeout); + const struct old_timespec32 __user *u_abs_timeout); asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, compat_size_t msg_len, unsigned int __user *u_msg_prio, - const struct compat_timespec __user *u_abs_timeout); + const struct old_timespec32 __user *u_abs_timeout); asmlinkage long compat_sys_mq_notify(mqd_t mqdes, const struct compat_sigevent __user *u_notification); asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, @@ -819,7 +819,7 @@ asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, /* ipc/sem.c */ asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); asmlinkage long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, - unsigned nsems, const struct compat_timespec __user *timeout); + unsigned nsems, const struct old_timespec32 __user *timeout); /* ipc/shm.c */ asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); @@ -876,7 +876,7 @@ asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, struct compat_siginfo __user *uinfo); asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, - struct compat_timespec __user *timeout); + struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, struct compat_rusage __user *ru); @@ -928,7 +928,7 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd, asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); asmlinkage long compat_sys_utimes(const char __user *filename, - struct compat_timeval __user *t); + struct old_timeval32 __user *t); /* __ARCH_WANT_SYSCALL_NO_FLAGS */ asmlinkage long compat_sys_signalfd(int ufd, @@ -942,15 +942,15 @@ asmlinkage long compat_sys_newlstat(const char __user *filename, struct compat_stat __user *statbuf); /* __ARCH_WANT_SYSCALL_DEPRECATED */ -asmlinkage long compat_sys_time(compat_time_t __user *tloc); +asmlinkage long compat_sys_time(old_time32_t __user *tloc); asmlinkage long compat_sys_utime(const char __user *filename, struct compat_utimbuf __user *t); asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, - struct compat_timeval __user *t); + struct old_timeval32 __user *t); asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timeval __user *tvp); + struct old_timeval32 __user *tvp); 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); @@ -983,7 +983,7 @@ asmlinkage long compat_sys_sigaction(int sig, #endif /* obsolete: kernel/time/time.c */ -asmlinkage long compat_sys_stime(compat_time_t __user *tptr); +asmlinkage long compat_sys_stime(old_time32_t __user *tptr); /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); @@ -1002,15 +1002,15 @@ static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif /** - * ns_to_compat_timeval - Compat version of ns_to_timeval + * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted * - * Returns the compat_timeval representation of the nsec parameter. + * Returns the old_timeval32 representation of the nsec parameter. */ -static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) +static inline struct old_timeval32 ns_to_old_timeval32(s64 nsec) { struct timeval tv; - struct compat_timeval ctv; + struct old_timeval32 ctv; tv = ns_to_timeval(nsec); ctv.tv_sec = tv.tv_sec; diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h deleted file mode 100644 index e70bfd1d2c3f..000000000000 --- a/include/linux/compat_time.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_COMPAT_TIME_H -#define _LINUX_COMPAT_TIME_H - -#include -#include - -typedef s32 compat_time_t; - -struct compat_timespec { - compat_time_t tv_sec; - s32 tv_nsec; -}; - -struct compat_timeval { - compat_time_t tv_sec; - s32 tv_usec; -}; - -struct compat_itimerspec { - struct compat_timespec it_interval; - struct compat_timespec it_value; -}; - -extern int compat_get_timespec64(struct timespec64 *, const void __user *); -extern int compat_put_timespec64(const struct timespec64 *, void __user *); -extern int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits); -extern int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits); - -#endif /* _LINUX_COMPAT_TIME_H */ diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index b5f2efdd05e0..7a37f4ce9fd2 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -27,10 +27,10 @@ struct compat_elf_prstatus compat_pid_t pr_ppid; compat_pid_t pr_pgrp; compat_pid_t pr_sid; - struct compat_timeval pr_utime; - struct compat_timeval pr_stime; - struct compat_timeval pr_cutime; - struct compat_timeval pr_cstime; + struct old_timeval32 pr_utime; + struct old_timeval32 pr_stime; + 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; diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 5d83d0c1d06c..bba2920e9c05 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -10,7 +10,7 @@ #include struct timespec; -struct compat_timespec; +struct old_timespec32; struct pollfd; enum timespec_type { @@ -40,7 +40,7 @@ struct restart_block { enum timespec_type type; union { struct __kernel_timespec __user *rmtp; - struct compat_timespec __user *compat_rmtp; + struct old_timespec32 __user *compat_rmtp; }; u64 expires; } nanosleep; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2ff814c92f7f..b3e27e5ee322 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -60,7 +60,7 @@ struct tms; struct utimbuf; struct mq_attr; struct compat_stat; -struct compat_timeval; +struct old_timeval32; struct robust_list_head; struct getcpu_cache; struct old_linux_dirent; diff --git a/include/linux/time32.h b/include/linux/time32.h index 92c0ca092d93..0e0d7304d1a8 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -13,6 +13,31 @@ #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) +typedef s32 old_time32_t; + +struct old_timespec32 { + old_time32_t tv_sec; + s32 tv_nsec; +}; + +struct old_timeval32 { + old_time32_t tv_sec; + s32 tv_usec; +}; + +struct old_itimerspec32 { + struct old_timespec32 it_interval; + struct old_timespec32 it_value; +}; + +extern int get_old_timespec32(struct timespec64 *, const void __user *); +extern int put_old_timespec32(const struct timespec64 *, void __user *); +extern int get_old_itimerspec32(struct itimerspec64 *its, + const struct old_itimerspec32 __user *uits); +extern int put_old_itimerspec32(const struct itimerspec64 *its, + struct old_itimerspec32 __user *uits); + + #if __BITS_PER_LONG == 64 /* timespec64 is defined as timespec here */ @@ -183,18 +208,17 @@ extern struct timeval ns_to_timeval(const s64 nsec); extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); /* - * New aliases for compat time functions. These will be used to replace - * the compat code so it can be shared between 32-bit and 64-bit builds - * both of which provide compatibility with old 32-bit tasks. + * Old names for the 32-bit time_t interfaces, these will be removed + * when everything uses the new names. */ -#define old_time32_t compat_time_t -#define old_timeval32 compat_timeval -#define old_timespec32 compat_timespec -#define old_itimerspec32 compat_itimerspec -#define ns_to_old_timeval32 ns_to_compat_timeval -#define get_old_itimerspec32 get_compat_itimerspec64 -#define put_old_itimerspec32 put_compat_itimerspec64 -#define get_old_timespec32 compat_get_timespec64 -#define put_old_timespec32 compat_put_timespec64 +#define compat_time_t old_time32_t +#define compat_timeval old_timeval32 +#define compat_timespec old_timespec32 +#define compat_itimerspec old_itimerspec32 +#define ns_to_compat_timeval ns_to_old_timeval32 +#define get_compat_itimerspec64 get_old_itimerspec32 +#define put_compat_itimerspec64 put_old_itimerspec32 +#define compat_get_timespec64 get_old_timespec32 +#define compat_put_timespec64 put_old_timespec32 #endif -- cgit v1.2.3 From eeaceb8b7d1fb64b6030249ca0dd1d902ef3069e Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 16 Aug 2018 20:54:49 +0800 Subject: spi: Introduce one new field to set word delay For some SPI controllers, after each word size (specified by bits_per_word) transimission, the hardware need some delay to make sure the slave has enough time to receive the whole data. So introducing one new 'word_delay' field of struct spi_tansfer for slave devices to set this inter word delay time. Signed-off-by: Baolin Wang Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a64235e05321..d698f9db3484 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -711,6 +711,8 @@ extern void spi_res_release(struct spi_controller *ctlr, * @delay_usecs: microseconds to delay after this transfer before * (optionally) changing the chipselect status, then starting * the next transfer or completing this @spi_message. + * @word_delay: clock cycles to inter word delay after each word size + * (set by bits_per_word) transmission. * @transfer_list: transfers are sequenced through @spi_message.transfers * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use @@ -793,6 +795,7 @@ struct spi_transfer { u8 bits_per_word; u16 delay_usecs; u32 speed_hz; + u16 word_delay; struct list_head transfer_list; }; -- cgit v1.2.3 From fb3739759474d150a9927b920a80ea2afb4c2a51 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 22:01:26 +0200 Subject: asm-generic: Move common compat types to asm-generic/compat.h While converting compat system call handlers to work on 32-bit architectures, I found a number of types used in those handlers that are identical between all architectures. Let's move all the identical ones into asm-generic/compat.h to avoid having to add even more identical definitions of those types. For unknown reasons, mips defines __compat_gid32_t, __compat_uid32_t and compat_caddr_t as signed, while all others have them unsigned. This seems to be a mistake, but I'm leaving it alone here. The other types all differ by size or alignment on at least on architecture. compat_aio_context_t is currently defined in linux/compat.h but also needed for compat_sys_io_getevents(), so let's move it into the same place. While we still have not decided whether the 32-bit time handling will always use the compat syscalls, or in which form, I think this is a useful cleanup that we can merge regardless. Reviewed-by: Christoph Hellwig Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 0e058792ecf6..d376fa8be00d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -110,8 +110,6 @@ typedef struct compat_sigaltstack { typedef __compat_uid32_t compat_uid_t; typedef __compat_gid32_t compat_gid_t; -typedef compat_ulong_t compat_aio_context_t; - struct compat_sel_arg_struct; struct rusage; -- cgit v1.2.3 From a4f7a3004630f1a0fb130ab1824942a49ce33140 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 09:11:58 +0200 Subject: y2038: Change sys_utimensat() to use __kernel_timespec When 32-bit architectures get changed to support 64-bit time_t, utimensat() needs to use the new __kernel_timespec structure as its argument. The older utime(), utimes() and futimesat() system calls don't need a corresponding change as they are no longer used on C libraries that have 64-bit time support. As we do for the other syscalls that have timespec arguments, we reuse the 'compat' syscall entry points to implement the traditional four interfaces, and only leave the new utimensat() as a native handler, so that the same code gets used on both 32-bit and 64-bit kernels on each syscall. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b3e27e5ee322..420ac881a610 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -513,7 +513,8 @@ asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user * /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, - struct timespec __user *utimes, int flags); + struct __kernel_timespec __user *utimes, + int flags); /* kernel/acct.c */ asmlinkage long sys_acct(const char __user *name); -- cgit v1.2.3 From 185cfaf7641e14af85635bb2750da302e32b04e3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 09:11:58 +0200 Subject: y2038: Compile utimes()/futimesat() conditionally There are four generations of utimes() syscalls: utime(), utimes(), futimesat() and utimensat(), each one being a superset of the previous one. For y2038 support, we have to add another one, which is the same as the existing utimensat() but always passes 64-bit times_t based timespec values. There are currently 10 architectures that only use utimensat(), two that use utimes(), futimesat() and utimensat() but not utime(), and 11 architectures that have all four, and those define __ARCH_WANT_SYS_UTIME in order to get a sys_utime implementation. Since all the new architectures only want utimensat(), moving all the legacy entry points into a common __ARCH_WANT_SYS_UTIME guard simplifies the logic. Only alpha and ia64 grow a tiny bit as they now also get an unused sys_utime(), but it didn't seem worth the extra complexity of adding yet another ifdef for those. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 420ac881a610..95e795fb0593 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -955,8 +955,6 @@ asmlinkage long sys_access(const char __user *filename, int mode); asmlinkage long sys_rename(const char __user *oldname, const char __user *newname); asmlinkage long sys_symlink(const char __user *old, const char __user *new); -asmlinkage long sys_utimes(char __user *filename, - struct timeval __user *utimes); #if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) asmlinkage long sys_stat64(const char __user *filename, struct stat64 __user *statbuf); @@ -986,14 +984,18 @@ asmlinkage long sys_alarm(unsigned int seconds); asmlinkage long sys_getpgrp(void); asmlinkage long sys_pause(void); asmlinkage long sys_time(time_t __user *tloc); +#ifdef __ARCH_WANT_SYS_UTIME asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times); +asmlinkage long sys_utimes(char __user *filename, + struct timeval __user *utimes); +asmlinkage long sys_futimesat(int dfd, const char __user *filename, + struct timeval __user *utimes); +#endif asmlinkage long sys_creat(const char __user *pathname, umode_t mode); asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user *dirent, unsigned int count); -asmlinkage long sys_futimesat(int dfd, const char __user *filename, - struct timeval __user *utimes); asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, -- cgit v1.2.3 From 4faea239e529d1d6b3b93fbf08d5e90427961a41 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 12:03:19 +0200 Subject: y2038: utimes: Rework #ifdef guards for compat syscalls After changing over to 64-bit time_t syscalls, many architectures will want compat_sys_utimensat() but not respective handlers for utime(), utimes() and futimesat(). This adds a new __ARCH_WANT_SYS_UTIME32 to complement __ARCH_WANT_SYS_UTIME. For now, all 64-bit architectures that support CONFIG_COMPAT set it, but future 64-bit architectures will not (tile would not have needed it either, but got removed). As older 32-bit architectures get converted to using CONFIG_64BIT_TIME, they will have to use __ARCH_WANT_SYS_UTIME32 instead of __ARCH_WANT_SYS_UTIME. Architectures using the generic syscall ABI don't need either of them as they never had a utime syscall. Since the compat_utimbuf structure is now required outside of CONFIG_COMPAT, I'm moving it into compat_time.h. Signed-off-by: Arnd Bergmann --- changed from last version: - renamed __ARCH_WANT_COMPAT_SYS_UTIME to __ARCH_WANT_SYS_UTIME32 --- include/linux/compat.h | 7 +------ include/linux/time32.h | 5 +++++ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d376fa8be00d..6fb5abdb87be 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -113,11 +113,6 @@ typedef __compat_gid32_t compat_gid_t; struct compat_sel_arg_struct; struct rusage; -struct compat_utimbuf { - old_time32_t actime; - old_time32_t modtime; -}; - struct compat_itimerval { struct old_timeval32 it_interval; struct old_timeval32 it_value; @@ -942,7 +937,7 @@ asmlinkage long compat_sys_newlstat(const char __user *filename, /* __ARCH_WANT_SYSCALL_DEPRECATED */ asmlinkage long compat_sys_time(old_time32_t __user *tloc); asmlinkage long compat_sys_utime(const char __user *filename, - struct compat_utimbuf __user *t); + struct old_utimbuf32 __user *t); asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct old_timeval32 __user *t); diff --git a/include/linux/time32.h b/include/linux/time32.h index 0e0d7304d1a8..61904a6c098f 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -30,6 +30,11 @@ struct old_itimerspec32 { struct old_timespec32 it_value; }; +struct old_utimbuf32 { + old_time32_t actime; + old_time32_t modtime; +}; + extern int get_old_timespec32(struct timespec64 *, const void __user *); extern int put_old_timespec32(const struct timespec64 *, void __user *); extern int get_old_itimerspec32(struct itimerspec64 *its, -- cgit v1.2.3 From 474b9c777b20b8340a6ee0f7ba6ebbd6a4bf47e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 21:59:47 +0200 Subject: y2038: sched: Change sched_rr_get_interval to use __kernel_timespec This is a preparation patch for converting sys_sched_rr_get_interval to work with 64-bit time_t on 32-bit architectures. The 'interval' argument is changed to struct __kernel_timespec, which will be redefined using 64-bit time_t in the future. The compat version of the system call in turn is enabled for compilation with CONFIG_COMPAT_32BIT_TIME so the individual 32-bit architectures can share the handling of the traditional argument with 64-bit architectures providing it for their compat mode. Signed-off-by: Arnd Bergmann --- 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 95e795fb0593..5642016a312d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -614,7 +614,7 @@ asmlinkage long sys_sched_yield(void); asmlinkage long sys_sched_get_priority_max(int policy); asmlinkage long sys_sched_get_priority_min(int policy); asmlinkage long sys_sched_rr_get_interval(pid_t pid, - struct timespec __user *interval); + struct __kernel_timespec __user *interval); /* kernel/signal.c */ asmlinkage long sys_restart_syscall(void); -- cgit v1.2.3 From c2e6c8567acdba8db1055b242c34ceb123c6a253 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 13:42:25 +0200 Subject: y2038: socket: Change recvmmsg to use __kernel_timespec This converts the recvmmsg() system call in all its variations to use 'timespec64' internally for its timeout, and have a __kernel_timespec64 argument in the native entry point. This lets us change the type to use 64-bit time_t at a later point while using the 32-bit compat system call emulation for existing user space. Signed-off-by: Arnd Bergmann --- include/linux/socket.h | 4 ++-- include/linux/syscalls.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7ed4713d5337..8b571e9b9f76 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -348,7 +348,7 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); -struct timespec; +struct timespec64; /* The __sys_...msg variants allow MSG_CMSG_COMPAT iff * forbid_cmsg_compat==false @@ -358,7 +358,7 @@ extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat); extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags, struct timespec *timeout); + unsigned int flags, struct timespec64 *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5642016a312d..fb3a05fab8aa 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -830,7 +830,7 @@ asmlinkage long sys_perf_event_open( asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, unsigned int vlen, unsigned flags, - struct timespec __user *timeout); + struct __kernel_timespec __user *timeout); asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, int options, struct rusage __user *ru); -- cgit v1.2.3 From 49c39f8464a9af702e9d45800c00a572753aeb06 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 15:56:13 +0200 Subject: y2038: signal: Change rt_sigtimedwait to use __kernel_timespec This changes sys_rt_sigtimedwait() to use get_timespec64(), changing the timeout type to __kernel_timespec, which will be changed to use a 64-bit time_t in the future. Since the do_sigtimedwait() core function changes, we also have to modify the compat version of this system call in the same way. Signed-off-by: Arnd Bergmann --- 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 fb3a05fab8aa..2ac3d13a915b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -635,7 +635,7 @@ asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, siginfo_t __user *uinfo, - const struct timespec __user *uts, + const struct __kernel_timespec __user *uts, size_t sigsetsize); asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo); -- cgit v1.2.3 From 823f18f8b860526fc099c222619a126d57d2ad8c Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 29 Aug 2018 15:36:10 +0300 Subject: regulator: bd71837: Disable voltage monitoring for LDO3/4 There is a HW quirk in BD71837. The shutdown sequence timings for bucks/LDOs which are enabled via register interface are changed. At PMIC poweroff the voltage for BUCK6/7 is cut immediately at the beginning of shut-down sequence. This causes LDO5/6 voltage monitoring to detect under voltage and force PMIC to emergency state instead of poweroff. Disable voltage monitoring for LDO5 and LDO6 at probe to avoid this. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/mfd/rohm-bd718x7.h | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index a528747f8aed..e8338e5dc10b 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -78,9 +78,9 @@ enum { BD71837_REG_TRANS_COND0 = 0x1F, BD71837_REG_TRANS_COND1 = 0x20, BD71837_REG_VRFAULTEN = 0x21, - BD71837_REG_MVRFLTMASK0 = 0x22, - BD71837_REG_MVRFLTMASK1 = 0x23, - BD71837_REG_MVRFLTMASK2 = 0x24, + BD718XX_REG_MVRFLTMASK0 = 0x22, + BD718XX_REG_MVRFLTMASK1 = 0x23, + BD718XX_REG_MVRFLTMASK2 = 0x24, BD71837_REG_RCVCFG = 0x25, BD71837_REG_RCVNUM = 0x26, BD71837_REG_PWRONCONFIG0 = 0x27, @@ -159,6 +159,33 @@ enum { #define BUCK8_MASK 0x3F #define BUCK8_DEFAULT 0x1E +/* BD718XX Voltage monitoring masks */ +#define BD718XX_BUCK1_VRMON80 0x1 +#define BD718XX_BUCK1_VRMON130 0x2 +#define BD718XX_BUCK2_VRMON80 0x4 +#define BD718XX_BUCK2_VRMON130 0x8 +#define BD718XX_1ST_NODVS_BUCK_VRMON80 0x1 +#define BD718XX_1ST_NODVS_BUCK_VRMON130 0x2 +#define BD718XX_2ND_NODVS_BUCK_VRMON80 0x4 +#define BD718XX_2ND_NODVS_BUCK_VRMON130 0x8 +#define BD718XX_3RD_NODVS_BUCK_VRMON80 0x10 +#define BD718XX_3RD_NODVS_BUCK_VRMON130 0x20 +#define BD718XX_4TH_NODVS_BUCK_VRMON80 0x40 +#define BD718XX_4TH_NODVS_BUCK_VRMON130 0x80 +#define BD718XX_LDO1_VRMON80 0x1 +#define BD718XX_LDO2_VRMON80 0x2 +#define BD718XX_LDO3_VRMON80 0x4 +#define BD718XX_LDO4_VRMON80 0x8 +#define BD718XX_LDO5_VRMON80 0x10 +#define BD718XX_LDO6_VRMON80 0x20 + +/* BD71837 specific voltage monitoring masks */ +#define BD71837_BUCK3_VRMON80 0x10 +#define BD71837_BUCK3_VRMON130 0x20 +#define BD71837_BUCK4_VRMON80 0x40 +#define BD71837_BUCK4_VRMON130 0x80 +#define BD71837_LDO7_VRMON80 0x40 + /* BD71837_REG_IRQ bits */ #define IRQ_SWRST 0x40 #define IRQ_PWRON_S 0x20 -- cgit v1.2.3 From 1b27291b1ea4f1f2090fb07c3425db474cdb99ba Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 18 Jul 2018 14:32:31 -0700 Subject: rcutorture: Add forward-progress tests for RCU grace periods This commit adds a kthread that loops going into and out of RCU read-side critical sections, but also including a cond_resched(), optionally guarded by a check of need_resched(), in that same loop. This commit relies solely on rcu_torture_writer() progress to judge the forward progress of grace periods. Note that Tasks RCU and SRCU are exempted from forward-progress testing due their (intentionally) less-robust forward-progress guarantees. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 8d9a0ea8f0b5..a6353f3d6094 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -108,6 +108,7 @@ static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) */ static inline void rcu_virt_note_context_switch(int cpu) { } static inline void rcu_cpu_stall_reset(void) { } +static inline int rcu_jiffies_till_stall_check(void) { return 21 * HZ; } static inline void rcu_idle_enter(void) { } static inline void rcu_idle_exit(void) { } static inline void rcu_irq_enter(void) { } -- cgit v1.2.3 From 474e59b476b3390ef9f730515439f21640b61623 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 7 Aug 2018 14:34:44 -0700 Subject: rcutorture: Check GP completion at stutter end The rcu_torture_writer() function invokes stutter_wait() at the end of each writer pass, which occasionally blocks for an extended time period in order to ensure that RCU can handle intermittent loads. But part of handling a busy period is invoking all the callbacks before the end of the idle period induced by stutter_wait(). This commit therefore adds a return value to stutter_wait() indicating whether stutter_wait() actually waited. In addition, this commit causes rcu_torture_writer() to test this value and if set, checks that all the elements of the rcu_tortures[] array have been freed up. 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 61dfd93b6ee4..48fad21109fc 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -77,7 +77,7 @@ void torture_shutdown_absorb(const char *title); int torture_shutdown_init(int ssecs, void (*cleanup)(void)); /* Task stuttering, which forces load/no-load transitions. */ -void stutter_wait(const char *title); +bool stutter_wait(const char *title); int torture_stutter_init(int s); /* Initialization and cleanup. */ -- cgit v1.2.3 From 6c5c9581044dd6e0cd284ab653502fb9264f08b6 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Tue, 28 Aug 2018 14:44:28 +0200 Subject: net: add napi_if_scheduled_mark_missed The function napi_if_scheduled_mark_missed is used to check if the NAPI context is scheduled, if so set NAPIF_STATE_MISSED and return true. Used by the AF_XDP zero-copy i40e Tx code implementation in order to make sure that irq affinity is honored by the napi context. Signed-off-by: Magnus Karlsson Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5ab98053c8..4271f6b4e419 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -535,6 +535,32 @@ static inline void napi_synchronize(const struct napi_struct *n) barrier(); } +/** + * napi_if_scheduled_mark_missed - if napi is running, set the + * NAPIF_STATE_MISSED + * @n: NAPI context + * + * If napi is running, set the NAPIF_STATE_MISSED, and return true if + * NAPI is scheduled. + **/ +static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + if (val & NAPIF_STATE_DISABLE) + return true; + + if (!(val & NAPIF_STATE_SCHED)) + return false; + + new = val | NAPIF_STATE_MISSED; + } while (cmpxchg(&n->state, val, new) != val); + + return true; +} + enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, -- cgit v1.2.3 From 679c782de14bd48c19dd74cd1af20a2bc05dd936 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 22 Aug 2018 20:02:19 +0100 Subject: bpf/verifier: per-register parent pointers By giving each register its own liveness chain, we elide the skip_callee() logic. Instead, each register's parent is the state it inherits from; both check_func_call() and prepare_func_exit() automatically connect reg states to the correct chain since when they copy the reg state across (r1-r5 into the callee as args, and r0 out as the return value) they also copy the parent pointer. Signed-off-by: Edward Cree Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 38b04f559ad3..b42b60a83e19 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -41,6 +41,7 @@ enum bpf_reg_liveness { }; struct bpf_reg_state { + /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; union { /* valid when type == PTR_TO_PACKET */ @@ -59,7 +60,6 @@ struct bpf_reg_state { * came from, when one is tested for != NULL. */ u32 id; - /* Ordering of fields matters. See states_equal() */ /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset @@ -76,15 +76,15 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* parentage chain for liveness checking */ + struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' * is used which is an index in bpf_verifier_state->frame[] array * pointing to bpf_func_state. - * This field must be second to last, for states_equal() reasons. */ u32 frameno; - /* This field must be last, for states_equal() reasons. */ enum bpf_reg_liveness live; }; @@ -107,7 +107,6 @@ struct bpf_stack_state { */ struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; - struct bpf_verifier_state *parent; /* index of call instruction that called into this func */ int callsite; /* stack frame number of this function state from pov of @@ -129,7 +128,6 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; - struct bpf_verifier_state *parent; u32 curframe; }; -- cgit v1.2.3 From 9b3004953503462a4fab31b85e44ae446d48f0bd Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Tue, 28 Aug 2018 19:56:58 +0200 Subject: ethtool: drop get_settings and set_settings callbacks Since [gs]et_settings ethtool_ops callbacks have been deprecated in February 2016, all in tree NIC drivers have been converted to provide [gs]et_link_ksettings() and out of tree drivers have had enough time to do the same. Drop get_settings() and set_settings() and implement both ETHTOOL_[GS]SET and ETHTOOL_[GS]LINKSETTINGS only using [gs]et_link_ksettings(). Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- include/linux/ethtool.h | 33 ++++++++++----------------------- 1 file changed, 10 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index f8a2245b70ac..afd9596ce636 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -183,14 +183,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, /** * struct ethtool_ops - optional netdev operations - * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Get various device settings including Ethernet link - * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code - * or zero. - * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Set various device settings including Ethernet link - * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -297,19 +289,16 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. - * @get_link_ksettings: When defined, takes precedence over the - * %get_settings method. Get various device settings - * including Ethernet link settings. The %cmd and - * %link_mode_masks_nwords fields should be ignored (use - * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any - * change to them will be overwritten by kernel. Returns a - * negative error code or zero. - * @set_link_ksettings: When defined, takes precedence over the - * %set_settings method. Set various device settings including - * Ethernet link settings. The %cmd and %link_mode_masks_nwords - * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS - * instead of the latter), any change to them will be overwritten - * by kernel. Returns a negative error code or zero. + * @get_link_ksettings: Get various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. + * @set_link_ksettings: Set various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. * @get_fecparam: Get the network device Forward Error Correction parameters. * @set_fecparam: Set the network device Forward Error Correction parameters. * @get_ethtool_phy_stats: Return extended statistics about the PHY device. @@ -329,8 +318,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * of the generic netdev features interface. */ struct ethtool_ops { - int (*get_settings)(struct net_device *, struct ethtool_cmd *); - int (*set_settings)(struct net_device *, struct ethtool_cmd *); void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); -- cgit v1.2.3 From 45cd0faae3715e305bc46e23b34c5ed4d185ceb8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 27 Aug 2018 15:56:02 +0300 Subject: vfs: add the fadvise() file operation This is going to be used by overlayfs and possibly useful for other filesystems. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..6c0b4a1c22ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1763,6 +1763,7 @@ struct file_operations { u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { @@ -3459,4 +3460,8 @@ static inline bool dir_relax_shared(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + #endif /* _LINUX_FS_H */ -- cgit v1.2.3 From a4e0109a19c554e44c832958e426303781e1ad30 Mon Sep 17 00:00:00 2001 From: Harshitha Ramamurthy Date: Mon, 20 Aug 2018 08:12:32 -0700 Subject: virtchnl: use u8 type for a field in the virtchnl_filter struct The virtchnl_filter struct has a field called field_flags. A previous commit mistakenly had the type to be a __u8. What we want is for the field to be an unsigned 8 bit value, so let's just use the existing kernel type u8 for that. Signed-off-by: Harshitha Ramamurthy Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 212b3822d180..b41f7bc958ef 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -573,7 +573,7 @@ struct virtchnl_filter { enum virtchnl_flow_type flow_type; enum virtchnl_action action; u32 action_meta; - __u8 field_flags; + u8 field_flags; }; VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); -- cgit v1.2.3 From 3e31009898699dfca823893054748d85048dc7b3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 21 Jun 2018 12:50:01 -0700 Subject: rcu: Defer reporting RCU-preempt quiescent states when disabled This commit defers reporting of RCU-preempt quiescent states at rcu_read_unlock_special() time when any of interrupts, softirq, or preemption are disabled. These deferred quiescent states are reported at a later RCU_SOFTIRQ, context switch, idle entry, or CPU-hotplug offline operation. Of course, if another RCU read-side critical section has started in the meantime, the reporting of the quiescent state will be further deferred. This also means that disabling preemption, interrupts, and/or softirqs will act as an RCU-preempt read-side critical section. This is enforced by checking preempt_count() as needed. Some special cases must be handled on an ad-hoc basis, for example, context switch is a quiescent state even though both the scheduler and do_exit() disable preemption. In these cases, additional calls to rcu_preempt_deferred_qs() override the preemption disabling. Similar logic overrides disabled interrupts in rcu_preempt_check_callbacks() because in this case the quiescent state happened just before the corresponding scheduling-clock interrupt. In theory, this change lifts a long-standing restriction that required that if interrupts were disabled across a call to rcu_read_unlock() that the matching rcu_read_lock() also be contained within that interrupts-disabled region of code. Because the reporting of the corresponding RCU-preempt quiescent state is now deferred until after interrupts have been enabled, it is no longer possible for this situation to result in deadlocks involving the scheduler's runqueue and priority-inheritance locks. This may allow some code simplification that might reduce interrupt latency a bit. Unfortunately, in practice this would also defer deboosting a low-priority task that had been subjected to RCU priority boosting, so real-time-response considerations might well force this restriction to remain in place. Because RCU-preempt grace periods are now blocked not only by RCU read-side critical sections, but also by disabling of interrupts, preemption, and softirqs, it will be possible to eliminate RCU-bh and RCU-sched in favor of RCU-preempt in CONFIG_PREEMPT=y kernels. This may require some additional plumbing to provide the network denial-of-service guarantees that have been traditionally provided by RCU-bh. Once these are in place, CONFIG_PREEMPT=n kernels will be able to fold RCU-bh into RCU-sched. This would mean that all kernels would have but one flavor of RCU, which would open the door to significant code cleanup. Moving to a single flavor of RCU would also have the beneficial effect of reducing the NOCB kthreads by at least a factor of two. Signed-off-by: Paul E. McKenney [ paulmck: Apply rcu_read_unlock_special() preempt_count() feedback from Joel Fernandes. ] [ paulmck: Adjust rcu_eqs_enter() call to rcu_preempt_deferred_qs() in response to bug reports from kbuild test robot. ] [ paulmck: Fix bug located by kbuild test robot involving recursion via rcu_preempt_deferred_qs(). ] --- include/linux/rcutiny.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 8d9a0ea8f0b5..f617ab19bb51 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -115,6 +115,11 @@ 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 exit_rcu(void) { } +static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) +{ + return false; +} +static inline void rcu_preempt_deferred_qs(struct task_struct *t) { } #ifdef CONFIG_SRCU void rcu_scheduler_starting(void); #else /* #ifndef CONFIG_SRCU */ -- cgit v1.2.3 From fcc878e4dfb70128a73857c609d70570629b0d9e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 28 Jun 2018 07:39:59 -0700 Subject: rcu: Remove now-unused ->b.exp_need_qs field from the rcu_special union The ->b.exp_need_qs field is now set only to false, so this commit removes it. The job this field used to do is now done by the rcu_data structure's ->deferred_qs field, which is a consequence of a better split between task-based (the rcu_node structure's ->exp_tasks field) and CPU-based (the aforementioned rcu_data structure's ->deferred_qs field) tracking of quiescent states for RCU-preempt expedited grace periods. Signed-off-by: Paul E. McKenney --- include/linux/sched.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..004ca21f7e80 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -571,12 +571,8 @@ union rcu_special { struct { u8 blocked; u8 need_qs; - u8 exp_need_qs; - - /* Otherwise the compiler can store garbage here: */ - u8 pad; } b; /* Bits. */ - u32 s; /* Set of bits. */ + u16 s; /* Set of bits. */ }; enum perf_event_task_context { -- cgit v1.2.3 From d28139c4e96713d52a300fb9036c5be2f45e0741 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 28 Jun 2018 14:45:25 -0700 Subject: rcu: Apply RCU-bh QSes to RCU-sched and RCU-preempt when safe One necessary step towards consolidating the three flavors of RCU is to make sure that the resulting consolidated "one flavor to rule them all" correctly handles networking denial-of-service attacks. One thing that allows RCU-bh to do so is that __do_softirq() invokes rcu_bh_qs() every so often, and so something similar has to happen for consolidated RCU. This must be done carefully. For example, if a preemption-disabled region of code takes an interrupt which does softirq processing before returning, consolidated RCU must ignore the resulting rcu_bh_qs() invocations -- preemption is still disabled, and that means an RCU reader for the consolidated flavor. This commit therefore creates a new rcu_softirq_qs() that is called only from the ksoftirqd task, thus avoiding the interrupted-a-preempted-region problem. This new rcu_softirq_qs() function invokes rcu_sched_qs(), rcu_preempt_qs(), and rcu_preempt_deferred_qs(). The latter call handles any deferred quiescent states. Note that __do_softirq() still invokes rcu_bh_qs(). It will continue to do so until a later stage of cleanup when the RCU-bh flavor is removed. Signed-off-by: Paul E. McKenney [ paulmck: Fix !SMP issue located by kbuild test robot. ] --- include/linux/rcutiny.h | 5 +++++ include/linux/rcutree.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index f617ab19bb51..bcfbc40a7239 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -90,6 +90,11 @@ static inline void kfree_call_rcu(struct rcu_head *head, call_rcu(head, func); } +static inline void rcu_softirq_qs(void) +{ + rcu_sched_qs(); +} + #define rcu_note_context_switch(preempt) \ do { \ rcu_sched_qs(); \ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 914655848ef6..664b580695d6 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -30,6 +30,7 @@ #ifndef __LINUX_RCUTREE_H #define __LINUX_RCUTREE_H +void rcu_softirq_qs(void); void rcu_note_context_switch(bool preempt); int rcu_needs_cpu(u64 basem, u64 *nextevt); void rcu_cpu_stall_reset(void); -- cgit v1.2.3 From 65cfe3583b612a22e12fba9a7bbd2d37ca5ad941 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 1 Jul 2018 07:40:52 -0700 Subject: rcu: Define RCU-bh update API in terms of RCU Now that the main RCU API knows about softirq disabling and softirq's quiescent states, the RCU-bh update code can be dispensed with. This commit therefore removes the RCU-bh update-side implementation and defines RCU-bh's update-side API in terms of that of either RCU-preempt or RCU-sched, depending on the setting of the CONFIG_PREEMPT Kconfig option. In kernels built with CONFIG_RCU_NOCB_CPU=y this has the knock-on effect of reducing by one the number of rcuo kthreads per CPU. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 10 ++++++---- include/linux/rcutiny.h | 10 +++++++--- include/linux/rcutree.h | 8 ++++++-- 3 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 75e5b393cf44..9ebfd436cec7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -55,11 +55,15 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); #define call_rcu call_rcu_sched #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ -void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); void rcu_barrier_tasks(void); +static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); @@ -104,7 +108,6 @@ static inline int rcu_preempt_depth(void) void rcu_init(void); extern int rcu_scheduler_active __read_mostly; void rcu_sched_qs(void); -void rcu_bh_qs(void); void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); @@ -326,8 +329,7 @@ static inline void rcu_preempt_sleep_check(void) { } * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple flavors of pointers to match the multiple flavors of RCU - * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in - * the future. + * (e.g., __rcu_sched, and __srcu), should this make sense in the future. */ #ifdef __CHECKER__ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index bcfbc40a7239..ac26c27ccde8 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -56,19 +56,23 @@ static inline void cond_synchronize_sched(unsigned long oldstate) might_sleep(); } -extern void rcu_barrier_bh(void); -extern void rcu_barrier_sched(void); - static inline void synchronize_rcu_expedited(void) { synchronize_sched(); /* Only one CPU, so pretty fast anyway!!! */ } +extern void rcu_barrier_sched(void); + static inline void rcu_barrier(void) { rcu_barrier_sched(); /* Only one CPU, so only one list of callbacks! */ } +static inline void rcu_barrier_bh(void) +{ + rcu_barrier(); +} + static inline void synchronize_rcu_bh(void) { synchronize_sched(); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 664b580695d6..c789c302a2c9 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,7 +45,11 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } -void synchronize_rcu_bh(void); +static inline void synchronize_rcu_bh(void) +{ + synchronize_rcu(); +} + void synchronize_sched_expedited(void); void synchronize_rcu_expedited(void); @@ -69,7 +73,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); */ static inline void synchronize_rcu_bh_expedited(void) { - synchronize_sched_expedited(); + synchronize_rcu_expedited(); } void rcu_barrier(void); -- cgit v1.2.3 From 82fcecfa81855924cc69f3078113cf63dd6c2964 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 Jul 2018 09:04:27 -0700 Subject: rcu: Update comments and help text for no more RCU-bh updaters This commit updates comments and help text to account for the fact that RCU-bh update-side functions are now simple wrappers for their RCU or RCU-sched counterparts. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 12 ++++-------- include/linux/rcupdate_wait.h | 6 +++--- include/linux/rcutree.h | 14 ++------------ 3 files changed, 9 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9ebfd436cec7..8d5740edd63c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -688,14 +688,10 @@ static inline void rcu_read_unlock(void) /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * - * This is equivalent of rcu_read_lock(), but to be used when updates - * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since - * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a - * softirq handler to be a quiescent state, a process in RCU read-side - * critical section must be protected by disabling softirqs. Read-side - * critical sections in interrupt context can use just rcu_read_lock(), - * though this should at least be commented to avoid confusing people - * reading the code. + * This is equivalent of rcu_read_lock(), but also disables softirqs. + * Note that synchronize_rcu() and friends may be used for the update + * side, although synchronize_rcu_bh() is available as a wrapper in the + * short term. Longer term, the _bh update-side API will be eliminated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index 57f371344152..bc104699560e 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -36,13 +36,13 @@ do { \ * @...: List of call_rcu() functions for the flavors to wait on. * * This macro waits concurrently for multiple flavors of RCU grace periods. - * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait - * on concurrent RCU and RCU-bh grace periods. Waiting on a give SRCU + * For example, synchronize_rcu_mult(call_rcu, call_rcu_sched) would wait + * on concurrent RCU and RCU-sched grace periods. Waiting on a give SRCU * domain requires you to write a wrapper function for that SRCU domain's * call_srcu() function, supplying the corresponding srcu_struct. * * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU - * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called + * or RCU-sched, given that anywhere synchronize_rcu_mult() can be called * is automatically a grace period. */ #define synchronize_rcu_mult(...) \ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index c789c302a2c9..f7a41323aa54 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -58,18 +58,8 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); /** * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period * - * Wait for an RCU-bh grace period to elapse, but use a "big hammer" - * approach to force the grace period to end quickly. This consumes - * significant time on all CPUs and is unfriendly to real-time workloads, - * so is thus not recommended for any sort of common-case code. In fact, - * if you are using synchronize_rcu_bh_expedited() in a loop, please - * restructure your code to batch your updates, and then use a single - * synchronize_rcu_bh() instead. - * - * Note that it is illegal to call this function while holding any lock - * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal - * to call this function from a CPU-hotplug notifier. Failing to observe - * these restriction will result in deadlock. + * This is a transitional API and will soon be removed, with all + * callers converted to synchronize_rcu_expedited(). */ static inline void synchronize_rcu_bh_expedited(void) { -- cgit v1.2.3 From 45975c7d21a1c0aba97e3d8007e2a7c123145748 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 Jul 2018 14:30:37 -0700 Subject: rcu: Define RCU-sched API in terms of RCU for Tree RCU PREEMPT builds Now that RCU-preempt knows about preemption disabling, its implementation of synchronize_rcu() works for synchronize_sched(), and likewise for the other RCU-sched update-side API members. This commit therefore confines the RCU-sched update-side code to CONFIG_PREEMPT=n builds, and defines RCU-sched's update-side API members in terms of those of RCU-preempt. This means that any given build of the Linux kernel has only one update-side flavor of RCU, namely RCU-preempt for CONFIG_PREEMPT=y builds and RCU-sched for CONFIG_PREEMPT=n builds. This in turn means that kernels built with CONFIG_RCU_NOCB_CPU=y have only one rcuo kthread per CPU. Signed-off-by: Paul E. McKenney Cc: Andi Kleen --- include/linux/rcupdate.h | 14 ++++---------- include/linux/rcutiny.h | 7 +++++++ include/linux/rcutree.h | 7 ++++++- 3 files changed, 17 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8d5740edd63c..94474bb6b5c4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -49,11 +49,11 @@ /* Exported common interfaces */ -#ifdef CONFIG_PREEMPT_RCU -void call_rcu(struct rcu_head *head, rcu_callback_t func); -#else /* #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_TINY_RCU #define call_rcu call_rcu_sched -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +#else +void call_rcu(struct rcu_head *head, rcu_callback_t func); +#endif void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); @@ -92,11 +92,6 @@ static inline void __rcu_read_unlock(void) preempt_enable(); } -static inline void synchronize_rcu(void) -{ - synchronize_sched(); -} - static inline int rcu_preempt_depth(void) { return 0; @@ -107,7 +102,6 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active __read_mostly; -void rcu_sched_qs(void); void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ac26c27ccde8..df2c0895c5e7 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -36,6 +36,11 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } +static inline void synchronize_rcu(void) +{ + synchronize_sched(); +} + static inline unsigned long get_state_synchronize_rcu(void) { return 0; @@ -94,6 +99,8 @@ static inline void kfree_call_rcu(struct rcu_head *head, call_rcu(head, func); } +void rcu_sched_qs(void); + static inline void rcu_softirq_qs(void) { rcu_sched_qs(); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index f7a41323aa54..0c44720f0e84 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,14 +45,19 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } +void synchronize_rcu(void); static inline void synchronize_rcu_bh(void) { synchronize_rcu(); } -void synchronize_sched_expedited(void); void synchronize_rcu_expedited(void); +static inline void synchronize_sched_expedited(void) +{ + synchronize_rcu_expedited(); +} + void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); /** -- cgit v1.2.3 From 709fdce7545c978e69f52eb19082ea3af44332f5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 3 Jul 2018 10:44:44 -0700 Subject: rcu: Express Tiny RCU updates in terms of RCU rather than RCU-sched This commit renames Tiny RCU functions so that the lowest level of functionality is RCU (e.g., synchronize_rcu()) rather than RCU-sched (e.g., synchronize_sched()). This provides greater naming compatibility with Tree RCU, which will in turn permit more LoC removal once the RCU-sched and RCU-bh update-side API is removed. Signed-off-by: Paul E. McKenney [ paulmck: Fix Tiny call_rcu()'s EXPORT_SYMBOL() in response to a bug report from kbuild test robot. ] --- include/linux/rcupdate.h | 12 +++++------- include/linux/rcutiny.h | 34 +++++++++++++++++++--------------- include/linux/rcutree.h | 1 - 3 files changed, 24 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 94474bb6b5c4..1207c6c9bd8b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -49,15 +49,14 @@ /* Exported common interfaces */ -#ifdef CONFIG_TINY_RCU -#define call_rcu call_rcu_sched -#else -void call_rcu(struct rcu_head *head, rcu_callback_t func); +#ifndef CONFIG_TINY_RCU +void synchronize_sched(void); +void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); #endif -void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); -void synchronize_sched(void); +void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); +void synchronize_rcu(void); static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) { @@ -68,7 +67,6 @@ static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) void __rcu_read_lock(void); void __rcu_read_unlock(void); -void synchronize_rcu(void); /* * Defined as a macro as it is a very low level header included from diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index df2c0895c5e7..e66fb8bc2127 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -36,9 +36,9 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } -static inline void synchronize_rcu(void) +static inline void synchronize_sched(void) { - synchronize_sched(); + synchronize_rcu(); } static inline unsigned long get_state_synchronize_rcu(void) @@ -61,16 +61,11 @@ static inline void cond_synchronize_sched(unsigned long oldstate) might_sleep(); } -static inline void synchronize_rcu_expedited(void) -{ - synchronize_sched(); /* Only one CPU, so pretty fast anyway!!! */ -} +extern void rcu_barrier(void); -extern void rcu_barrier_sched(void); - -static inline void rcu_barrier(void) +static inline void rcu_barrier_sched(void) { - rcu_barrier_sched(); /* Only one CPU, so only one list of callbacks! */ + rcu_barrier(); /* Only one CPU, so only one list of callbacks! */ } static inline void rcu_barrier_bh(void) @@ -88,27 +83,36 @@ static inline void synchronize_rcu_bh_expedited(void) synchronize_sched(); } +static inline void synchronize_rcu_expedited(void) +{ + synchronize_sched(); +} + static inline void synchronize_sched_expedited(void) { synchronize_sched(); } -static inline void kfree_call_rcu(struct rcu_head *head, - rcu_callback_t func) +static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + +static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } -void rcu_sched_qs(void); +void rcu_qs(void); static inline void rcu_softirq_qs(void) { - rcu_sched_qs(); + rcu_qs(); } #define rcu_note_context_switch(preempt) \ do { \ - rcu_sched_qs(); \ + rcu_qs(); \ rcu_tasks_qs(current); \ } while (0) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 0c44720f0e84..6d30a0809300 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,7 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } -void synchronize_rcu(void); static inline void synchronize_rcu_bh(void) { synchronize_rcu(); -- cgit v1.2.3 From 4c7e9c1434c6fc960774a5475f2fbccbf557fdeb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Jul 2018 09:54:25 -0700 Subject: rcu: Consolidate RCU-bh update-side function definitions This commit saves a few lines by consolidating the RCU-bh function definitions at the end of include/linux/rcupdate.h. This consolidation also makes it easier to remove them all when the time comes. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 27 ++++++++++++++++++++++----- include/linux/rcutiny.h | 15 --------------- include/linux/rcutree.h | 17 ----------------- 3 files changed, 22 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 1207c6c9bd8b..e530f5739033 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -58,11 +58,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); -static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) -{ - call_rcu(head, func); -} - #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); @@ -875,4 +870,26 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ +/* Transitional pre-consolidation compatibility definitions. */ + +static inline void synchronize_rcu_bh(void) +{ + synchronize_rcu(); +} + +static inline void synchronize_rcu_bh_expedited(void) +{ + synchronize_rcu_expedited(); +} + +static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + +static inline void rcu_barrier_bh(void) +{ + rcu_barrier(); +} + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index e66fb8bc2127..df82bada9b19 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -68,21 +68,6 @@ static inline void rcu_barrier_sched(void) rcu_barrier(); /* Only one CPU, so only one list of callbacks! */ } -static inline void rcu_barrier_bh(void) -{ - rcu_barrier(); -} - -static inline void synchronize_rcu_bh(void) -{ - synchronize_sched(); -} - -static inline void synchronize_rcu_bh_expedited(void) -{ - synchronize_sched(); -} - static inline void synchronize_rcu_expedited(void) { synchronize_sched(); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 6d30a0809300..94820156aa62 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,11 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(false); } -static inline void synchronize_rcu_bh(void) -{ - synchronize_rcu(); -} - void synchronize_rcu_expedited(void); static inline void synchronize_sched_expedited(void) @@ -59,19 +54,7 @@ static inline void synchronize_sched_expedited(void) void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); -/** - * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period - * - * This is a transitional API and will soon be removed, with all - * callers converted to synchronize_rcu_expedited(). - */ -static inline void synchronize_rcu_bh_expedited(void) -{ - synchronize_rcu_expedited(); -} - void rcu_barrier(void); -void rcu_barrier_bh(void); void rcu_barrier_sched(void); bool rcu_eqs_special_set(int cpu); unsigned long get_state_synchronize_rcu(void); -- cgit v1.2.3 From a8bb74acd8efe2eb934d524ae20859980975b602 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Jul 2018 11:46:47 -0700 Subject: rcu: Consolidate RCU-sched update-side function definitions This commit saves a few lines by consolidating the RCU-sched function definitions at the end of include/linux/rcupdate.h. This consolidation also makes it easier to remove them all when the time comes. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 38 +++++++++++++++++++++++++++++++------- include/linux/rcutiny.h | 32 +------------------------------- include/linux/rcutree.h | 9 --------- 3 files changed, 32 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e530f5739033..12103e1bbe67 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -48,12 +48,6 @@ #define ulong2long(a) (*(long *)(&(a))) /* Exported common interfaces */ - -#ifndef CONFIG_TINY_RCU -void synchronize_sched(void); -void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); -#endif - void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); @@ -170,7 +164,7 @@ void exit_tasks_rcu_finish(void); #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() #define call_rcu_tasks call_rcu_sched -#define synchronize_rcu_tasks synchronize_sched +#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 */ @@ -892,4 +886,34 @@ static inline void rcu_barrier_bh(void) rcu_barrier(); } +static inline void synchronize_sched(void) +{ + synchronize_rcu(); +} + +static inline void synchronize_sched_expedited(void) +{ + synchronize_rcu_expedited(); +} + +static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} + +static inline void rcu_barrier_sched(void) +{ + rcu_barrier(); +} + +static inline unsigned long get_state_synchronize_sched(void) +{ + return get_state_synchronize_rcu(); +} + +static inline void cond_synchronize_sched(unsigned long oldstate) +{ + cond_synchronize_rcu(oldstate); +} + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index df82bada9b19..7fa4fb9e899e 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -36,11 +36,6 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } -static inline void synchronize_sched(void) -{ - synchronize_rcu(); -} - static inline unsigned long get_state_synchronize_rcu(void) { return 0; @@ -51,36 +46,11 @@ static inline void cond_synchronize_rcu(unsigned long oldstate) might_sleep(); } -static inline unsigned long get_state_synchronize_sched(void) -{ - return 0; -} - -static inline void cond_synchronize_sched(unsigned long oldstate) -{ - might_sleep(); -} - extern void rcu_barrier(void); -static inline void rcu_barrier_sched(void) -{ - rcu_barrier(); /* Only one CPU, so only one list of callbacks! */ -} - static inline void synchronize_rcu_expedited(void) { - synchronize_sched(); -} - -static inline void synchronize_sched_expedited(void) -{ - synchronize_sched(); -} - -static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) -{ - call_rcu(head, func); + synchronize_rcu(); } static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 94820156aa62..d09a9abe9440 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -46,21 +46,12 @@ static inline void rcu_virt_note_context_switch(int cpu) } void synchronize_rcu_expedited(void); - -static inline void synchronize_sched_expedited(void) -{ - synchronize_rcu_expedited(); -} - void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); -void rcu_barrier_sched(void); bool rcu_eqs_special_set(int cpu); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); -unsigned long get_state_synchronize_sched(void); -void cond_synchronize_sched(unsigned long oldstate); void rcu_idle_enter(void); void rcu_idle_exit(void); -- cgit v1.2.3 From 2bd8b1a2afc4463cc503665e98faa5909d1ac462 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 7 Jul 2018 18:12:26 -0700 Subject: rcu: Clean up flavor-related definitions and comments in rcupdate.h Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 12103e1bbe67..d6d543b60a9f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -119,11 +119,10 @@ static inline void rcu_init_nohz(void) { } * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. * - * RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden - * in the inner idle loop, that is, between the rcu_idle_enter() and - * the rcu_idle_exit() -- RCU will happily ignore any such read-side - * critical sections. However, things like powertop need tracepoints - * in the inner idle loop. + * RCU read-side critical sections are forbidden in the inner idle loop, + * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU + * will happily ignore any such read-side critical sections. However, + * things like powertop need tracepoints in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) * will tell RCU that it needs to pay attention, invoke its argument @@ -163,7 +162,7 @@ void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() -#define call_rcu_tasks call_rcu_sched +#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) { } @@ -309,8 +308,8 @@ static inline void rcu_preempt_sleep_check(void) { } * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of - * multiple flavors of pointers to match the multiple flavors of RCU - * (e.g., __rcu_sched, and __srcu), should this make sense in the future. + * multiple pointers markings to match different RCU implementations + * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ @@ -670,9 +669,8 @@ static inline void rcu_read_unlock(void) * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but also disables softirqs. - * Note that synchronize_rcu() and friends may be used for the update - * side, although synchronize_rcu_bh() is available as a wrapper in the - * short term. Longer term, the _bh update-side API will be eliminated. + * Note that anything else that disables softirqs can also serve as + * an RCU read-side critical section. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke @@ -705,10 +703,9 @@ static inline void rcu_read_unlock_bh(void) /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * - * This is equivalent of rcu_read_lock(), but to be used when updates - * are being done using call_rcu_sched() or synchronize_rcu_sched(). - * Read-side critical sections can also be introduced by anything that - * disables preemption, including local_irq_disable() and friends. + * This is equivalent of rcu_read_lock(), but disables preemption. + * Read-side critical sections can also be introduced by anything else + * that disables preemption, including local_irq_disable() and friends. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke -- cgit v1.2.3 From aff5f0369e312b0ab0ca7a2a12dd64b7e39c7091 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 7 Jul 2018 18:12:26 -0700 Subject: rcu: Clean up flavor-related definitions and comments in rculist.h Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 4786c2235b98..e91ec9ddcd30 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -182,7 +182,7 @@ static inline void list_replace_rcu(struct list_head *old, * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list - * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. @@ -240,7 +240,7 @@ static inline void __list_splice_init_rcu(struct list_head *list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into - * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, @@ -255,7 +255,7 @@ static inline void list_splice_init_rcu(struct list_head *list, * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into - * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, @@ -359,13 +359,12 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * - * This primitive may safely run concurrently with the _rcu list-mutation - * primitives such as list_add_rcu(), but requires some implicit RCU - * read-side guarding. One example is running within a special - * exception-time environment where preemption is disabled and where - * lockdep cannot be invoked (in which case updaters must use RCU-sched, - * as in synchronize_sched(), call_rcu_sched(), and friends). Another - * example is when items are added to the list, but never deleted. + * This primitive may safely run concurrently with the _rcu + * list-mutation primitives such as list_add_rcu(), but requires some + * implicit RCU read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where lockdep + * cannot be invoked. Another example is when items are added to the list, + * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) @@ -376,13 +375,12 @@ static inline void list_splice_tail_init_rcu(struct list_head *list, * @head: the head for your list. * @member: the name of the list_struct within the struct. * - * This primitive may safely run concurrently with the _rcu list-mutation - * primitives such as list_add_rcu(), but requires some implicit RCU - * read-side guarding. One example is running within a special - * exception-time environment where preemption is disabled and where - * lockdep cannot be invoked (in which case updaters must use RCU-sched, - * as in synchronize_sched(), call_rcu_sched(), and friends). Another - * example is when items are added to the list, but never deleted. + * This primitive may safely run concurrently with the _rcu + * list-mutation primitives such as list_add_rcu(), but requires some + * implicit RCU read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where lockdep + * cannot be invoked. Another example is when items are added to the list, + * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ -- cgit v1.2.3 From df8561a0d7e4f5cb72d0aa6be43e154b2027bba6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 7 Jul 2018 18:12:26 -0700 Subject: rcu: Clean up flavor-related definitions and comments in rcupdate_wait.h Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_wait.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index bc104699560e..8a16c3eb3dd0 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -33,17 +33,17 @@ do { \ /** * synchronize_rcu_mult - Wait concurrently for multiple grace periods - * @...: List of call_rcu() functions for the flavors to wait on. + * @...: List of call_rcu() functions for different grace periods to wait on * - * This macro waits concurrently for multiple flavors of RCU grace periods. - * For example, synchronize_rcu_mult(call_rcu, call_rcu_sched) would wait - * on concurrent RCU and RCU-sched grace periods. Waiting on a give SRCU + * 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 give SRCU * domain requires you to write a wrapper function for that SRCU domain's * call_srcu() function, supplying the corresponding srcu_struct. * - * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU - * or RCU-sched, given that anywhere synchronize_rcu_mult() can be called - * is automatically a grace period. + * If Tiny RCU, tell _wait_rcu_gp() does not bother waiting for RCU, + * given that anywhere synchronize_rcu_mult() can be called is automatically + * a grace period. */ #define synchronize_rcu_mult(...) \ _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) -- cgit v1.2.3 From 4d232dfe1df35254298e7986c4de8c9f63f58c79 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 10 Jul 2018 12:53:40 -0700 Subject: rcu: Remove !PREEMPT code from rcu_note_voluntary_context_switch() Because RCU-tasks exists only in PREEMPT kernels and because RCU-sched no longer exists in PREEMPT kernels, it is no longer necessary for the rcu_note_voluntary_context_switch() macro to do anything for !PREEMPT kernels. This commit therefore removes !PREEMPT-related code from this macro, namely, the rcu_all_qs(). Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d6d543b60a9f..e4f821165d0b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -150,18 +150,14 @@ static inline void rcu_init_nohz(void) { } if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) -#define rcu_note_voluntary_context_switch(t) \ - do { \ - rcu_all_qs(); \ - rcu_tasks_qs(t); \ - } 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); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ #define rcu_tasks_qs(t) do { } while (0) -#define rcu_note_voluntary_context_switch(t) rcu_all_qs() +#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) { } -- cgit v1.2.3 From 395a2f097ebdddf2bfa286b6119f1b231025c2f1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 10 Jul 2018 14:00:14 -0700 Subject: rcu: Define rcu_all_qs() only in !PREEMPT builds Now that rcu_all_qs() is used only in !PREEMPT builds, move it to tree_plugin.h so that it is defined only in those builds. This in turn means that rcu_momentary_dyntick_idle() is only used in !PREEMPT builds, but it is simply marked __maybe_unused in order to keep it near the rest of the dyntick-idle code. Signed-off-by: Paul E. McKenney --- include/linux/rcutree.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index d09a9abe9440..7f83179177d1 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -66,7 +66,9 @@ void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; void rcu_end_inkernel_boot(void); bool rcu_is_watching(void); +#ifndef CONFIG_PREEMPT void rcu_all_qs(void); +#endif /* RCUtree hotplug events */ int rcutree_prepare_cpu(unsigned int cpu); -- cgit v1.2.3 From 74de6960c99d8df0d09fb29a7b014cb9c5571e2b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 24 Jul 2018 15:28:09 -0700 Subject: rcu: Provide functions for determining if call_rcu() has been invoked This commit adds rcu_head_init() and rcu_head_after_call_rcu() functions to help RCU users detect when another CPU has passed the specified rcu_head structure and function to call_rcu(). The rcu_head_init() should be invoked before making the structure visible to RCU readers, and then the rcu_head_after_call_rcu() may be invoked from within an RCU read-side critical section on an rcu_head structure that was obtained during a traversal of the data structure in question. The rcu_head_after_call_rcu() function will return true if the rcu_head structure has already been passed (with the specified function) to call_rcu(), otherwise it will return false. If rcu_head_init() has not been invoked on the rcu_head structure or if the rcu_head (AKA callback) has already been invoked, then rcu_head_after_call_rcu() will do WARN_ON_ONCE(). Reported-by: NeilBrown Signed-off-by: Paul E. McKenney [ paulmck: Apply neilb naming feedback. ] --- include/linux/rcupdate.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e4f821165d0b..4db8bcacc51a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -857,6 +857,46 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ +/* Has the specified rcu_head structure been handed to call_rcu()? */ + +/* + * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() + * @rhp: The rcu_head structure to initialize. + * + * If you intend to invoke rcu_head_after_call_rcu() to test whether a + * given rcu_head structure has already been passed to call_rcu(), then + * you must also invoke this rcu_head_init() function on it just after + * allocating that structure. Calls to this function must not race with + * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. + */ +static inline void rcu_head_init(struct rcu_head *rhp) +{ + rhp->func = (rcu_callback_t)~0L; +} + +/* + * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()? + * @rhp: The rcu_head structure to test. + * @func: The function passed to call_rcu() along with @rhp. + * + * Returns @true if the @rhp has been passed to call_rcu() with @func, + * and @false otherwise. Emits a warning in any other case, including + * the case where @rhp has already been invoked after a grace period. + * Calls to this function must not race with callback invocation. One way + * to avoid such races is to enclose the call to rcu_head_after_call_rcu() + * in an RCU read-side critical section that includes a read-side fetch + * of the pointer to the structure containing @rhp. + */ +static inline bool +rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) +{ + if (READ_ONCE(rhp->func) == f) + return true; + WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L); + return false; +} + + /* Transitional pre-consolidation compatibility definitions. */ static inline void synchronize_rcu_bh(void) -- cgit v1.2.3 From 31ab604bf3232374e6471a2df9a83c4e75538390 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 3 Aug 2018 16:15:54 -0700 Subject: rcu: Remove unused rcu_dynticks_snap() from Tiny RCU The rcu_dynticks_snap() function is defined in include/linux/rcutiny.h, but is no longer used by Tiny RCU. This commit therefore removes it. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 7fa4fb9e899e..f183683bdf79 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,12 +27,6 @@ #include -struct rcu_dynticks; -static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp) -{ - return 0; -} - /* Never flag non-existent other CPUs! */ static inline bool rcu_eqs_special_set(int cpu) { return false; } -- cgit v1.2.3 From e0fcba9ac02af5aeb1e1c3e842eab987f817c309 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 14 Aug 2018 08:45:54 -0700 Subject: srcu: Make call_srcu() available during very early boot Event tracing is moving to SRCU in order to take advantage of the fact that SRCU may be safely used from idle and even offline CPUs. However, event tracing can invoke call_srcu() very early in the boot process, even before workqueue_init_early() is invoked (let alone rcu_init()). Therefore, call_srcu()'s attempts to queue work fail miserably. This commit therefore detects this situation, and refrains from attempting to queue work before rcu_init() time, but does everything else that it would have done, and in addition, adds the srcu_struct to a global list. The rcu_init() function now invokes a new srcu_init() function, which is empty if CONFIG_SRCU=n. Otherwise, srcu_init() queues work for each srcu_struct on the list. This all happens early enough in boot that there is but a single CPU with interrupts disabled, which allows synchronization to be dispensed with. Of course, the queued work won't actually be invoked until after workqueue_init() is invoked, which happens shortly after the scheduler is up and running. This means that although call_srcu() may be invoked any time after per-CPU variables have been set up, there is still a very narrow window when synchronize_srcu() won't work, and this window extends from the time that the scheduler starts until the time that workqueue_init() returns. This can be fixed in a manner similar to the fix for synchronize_rcu_expedited() and friends, but until someone actually needs to use synchronize_srcu() during this window, this fix is added churn for no benefit. Finally, note that Tree SRCU's new srcu_init() function invokes queue_work() rather than the queue_delayed_work() function that is invoked post-boot. The reason is that queue_delayed_work() will (as you would expect) post a timer, and timers have not yet been initialized. So use of queue_work() avoids the complaints about use of uninitialized spinlocks that would otherwise result. Besides, some delay is already provide by the aforementioned fact that the queued work won't actually be invoked until after the scheduler is up and running. Requested-by: Steven Rostedt Signed-off-by: Paul E. McKenney Tested-by: Steven Rostedt (VMware) --- include/linux/srcutiny.h | 2 ++ include/linux/srcutree.h | 14 ++++++++------ 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index f41d2fb09f87..2b5c0822e683 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -36,6 +36,7 @@ struct srcu_struct { struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ + struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -48,6 +49,7 @@ void srcu_drive_gp(struct work_struct *wp); .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ + .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ __SRCU_DEP_MAP_INIT(name) \ } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 745d4ca4dd50..9cfa4610113a 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -94,6 +94,7 @@ struct srcu_struct { /* callback for the barrier */ /* operation. */ struct delayed_work work; + struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -105,12 +106,13 @@ struct srcu_struct { #define SRCU_STATE_SCAN2 2 #define __SRCU_STRUCT_INIT(name, pcpu_name) \ - { \ - .sda = &pcpu_name, \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .srcu_gp_seq_needed = 0 - 1, \ - __SRCU_DEP_MAP_INIT(name) \ - } +{ \ + .sda = &pcpu_name, \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .srcu_gp_seq_needed = -1UL, \ + .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ + __SRCU_DEP_MAP_INIT(name) \ +} /* * Define and initialize a srcu struct at build time. -- cgit v1.2.3 From 4e6ea4ef56f9425cd239ffdb6be45b3aeeb347fd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 14 Aug 2018 14:41:49 -0700 Subject: srcu: Make early-boot call_srcu() reuse workqueue lists Allocating a list_head structure that is almost never used, and, when used, is used only during early boot (rcu_init() and earlier), is a bit wasteful. This commit therefore eliminates that list_head in favor of the one in the work_struct structure. This is safe because the work_struct structure cannot be used until after rcu_init() returns. Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney Cc: Tejun Heo Cc: Lai Jiangshan Tested-by: Steven Rostedt (VMware) --- include/linux/srcutiny.h | 2 -- include/linux/srcutree.h | 3 +-- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 2b5c0822e683..f41d2fb09f87 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -36,7 +36,6 @@ struct srcu_struct { struct rcu_head *srcu_cb_head; /* Pending callbacks: Head. */ struct rcu_head **srcu_cb_tail; /* Pending callbacks: Tail. */ struct work_struct srcu_work; /* For driving grace periods. */ - struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -49,7 +48,6 @@ void srcu_drive_gp(struct work_struct *wp); .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \ - .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ __SRCU_DEP_MAP_INIT(name) \ } diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 9cfa4610113a..0ae91b3a7406 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -94,7 +94,6 @@ struct srcu_struct { /* callback for the barrier */ /* operation. */ struct delayed_work work; - struct list_head srcu_boot_entry; /* Early-boot callbacks. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -110,7 +109,7 @@ struct srcu_struct { .sda = &pcpu_name, \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .srcu_gp_seq_needed = -1UL, \ - .srcu_boot_entry = LIST_HEAD_INIT(name.srcu_boot_entry), \ + .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ __SRCU_DEP_MAP_INIT(name) \ } -- cgit v1.2.3 From ef394f3fbecbe61d69450ad8cf0fa8f713c8ce8f Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 31 Aug 2018 14:34:02 +0200 Subject: regulator: da9063: fix DT probing with constraints Commit 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") reordered the da9063_regulator_info[] array, but not the DA9063_ID_* regulator ids and not the da9063_matches[] array, because ids are used as indices in the array initializer. This mismatch between regulator id and da9063_regulator_info[] array index causes the driver probe to fail because constraints from DT are not applied to the correct regulator: da9063 0-0058: Device detected (chip-ID: 0x61, var-ID: 0x50) DA9063_BMEM: Bringing 900000uV into 3300000-3300000uV DA9063_LDO9: Bringing 3300000uV into 2500000-2500000uV DA9063_LDO1: Bringing 900000uV into 3300000-3300000uV DA9063_LDO1: failed to apply 3300000-3300000uV constraint(-22) This patch reorders the DA9063_ID_* as apparently intended, and with them the entries in the da90630_matches[] array. Fixes: 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") Signed-off-by: Philipp Zabel Reviewed-by: Geert Uytterhoeven Reviewed-by: Marek Vasut Signed-off-by: Mark Brown --- include/linux/mfd/da9063/pdata.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 8a125701ef7b..50bed4f89c1a 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -21,7 +21,7 @@ /* * Regulator configuration */ -/* DA9063 regulator IDs */ +/* DA9063 and DA9063L regulator IDs */ enum { /* BUCKs */ DA9063_ID_BCORE1, @@ -37,18 +37,20 @@ enum { DA9063_ID_BMEM_BIO_MERGED, /* When two BUCKs are merged, they cannot be reused separately */ - /* LDOs */ + /* LDOs on both DA9063 and DA9063L */ + DA9063_ID_LDO3, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO11, + + /* DA9063-only LDOs */ DA9063_ID_LDO1, DA9063_ID_LDO2, - DA9063_ID_LDO3, DA9063_ID_LDO4, DA9063_ID_LDO5, DA9063_ID_LDO6, - DA9063_ID_LDO7, - DA9063_ID_LDO8, - DA9063_ID_LDO9, DA9063_ID_LDO10, - DA9063_ID_LDO11, }; /* Regulators platform data */ -- cgit v1.2.3 From 6b06546206868f723f2061d703a3c3c378dcbf4c Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Fri, 31 Aug 2018 16:22:42 -0400 Subject: Revert "blk-throttle: fix race between blkcg_bio_issue_check() and cgroup_rmdir()" This reverts commit 4c6994806f708559c2812b73501406e21ae5dcd0. Destroying blkgs is tricky because of the nature of the relationship. A blkg should go away when either a blkcg or a request_queue goes away. However, blkg's pin the blkcg to ensure they remain valid. To break this cycle, when a blkcg is offlined, blkgs put back their css ref. This eventually lets css_free() get called which frees the blkcg. The above commit (4c6994806f70) breaks this order of events by trying to destroy blkgs in css_free(). As the blkgs still hold references to the blkcg, css_free() is never called. The race between blkcg_bio_issue_check() and cgroup_rmdir() will be addressed in the following patch by delaying destruction of a blkg until all writeback associated with the blkcg has been finished. Fixes: 4c6994806f70 ("blk-throttle: fix race between blkcg_bio_issue_check() and cgroup_rmdir()") Reviewed-by: Josef Bacik Signed-off-by: Dennis Zhou Cc: Jiufei Xue Cc: Joseph Qi Cc: Tejun Heo Cc: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 34aec30e06c7..1615cdd4c797 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -89,7 +89,6 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; - bool offline; }; /* -- cgit v1.2.3 From 59b57717fff8b562825d9d25e0180ad7e8048ca9 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Fri, 31 Aug 2018 16:22:43 -0400 Subject: blkcg: delay blkg destruction until after writeback has finished Currently, blkcg destruction relies on a sequence of events: 1. Destruction starts. blkcg_css_offline() is called and blkgs release their reference to the blkcg. This immediately destroys the cgwbs (writeback). 2. With blkgs giving up their reference, the blkcg ref count should become zero and eventually call blkcg_css_free() which finally frees the blkcg. Jiufei Xue reported that there is a race between blkcg_bio_issue_check() and cgroup_rmdir(). To remedy this, blkg destruction becomes contingent on the completion of all writeback associated with the blkcg. A count of the number of cgwbs is maintained and once that goes to zero, blkg destruction can follow. This should prevent premature blkg destruction related to writeback. The new process for blkcg cleanup is as follows: 1. Destruction starts. blkcg_css_offline() is called which offlines writeback. Blkg destruction is delayed on the cgwb_refcnt count to avoid punting potentially large amounts of outstanding writeback to root while maintaining any ongoing policies. Here, the base cgwb_refcnt is put back. 2. When the cgwb_refcnt becomes zero, blkcg_destroy_blkgs() is called and handles destruction of blkgs. This is where the css reference held by each blkg is released. 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. This finally frees the blkg. It seems in the past blk-throttle didn't do the most understandable things with taking data from a blkg while associating with current. So, the simplification and unification of what blk-throttle is doing caused this. Fixes: 08e18eab0c579 ("block: add bi_blkg to the bio for cgroups") Reviewed-by: Josef Bacik Signed-off-by: Dennis Zhou Cc: Jiufei Xue Cc: Joseph Qi Cc: Tejun Heo Cc: Josef Bacik Cc: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1615cdd4c797..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -56,6 +56,7 @@ struct blkcg { struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; + refcount_t cgwb_refcnt; #endif }; @@ -386,6 +387,49 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) return cpd ? cpd->blkcg : NULL; } +extern void blkcg_destroy_blkgs(struct blkcg *blkcg); + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * blkcg_cgwb_get - get a reference for blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + */ +static inline void blkcg_cgwb_get(struct blkcg *blkcg) +{ + refcount_inc(&blkcg->cgwb_refcnt); +} + +/** + * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + * When this count goes to zero, all active wb has finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. + */ +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + if (refcount_dec_and_test(&blkcg->cgwb_refcnt)) + blkcg_destroy_blkgs(blkcg); +} + +#else + +static inline void blkcg_cgwb_get(struct blkcg *blkcg) { } + +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + /* wb isn't being accounted, so trigger destruction right away */ + blkcg_destroy_blkgs(blkcg); +} + +#endif + /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest -- cgit v1.2.3 From c43c5e9f524ec914e7e202f9c5ab91779629ccc6 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 3 Sep 2018 10:15:33 +0200 Subject: timekeeping: Fix declaration of read_persistent_wall_and_boot_offset() It is read_persistent_wall_and_boot_offset() and not read_persistent_clock_and_boot_offset() Fixes: 3eca993740b8eb40f51 ("timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset()") Signed-off-by: Christian Borntraeger Signed-off-by: Thomas Gleixner Cc: Pavel Tatashin Link: https://lkml.kernel.org/r/20180903081533.34366-1-borntraeger@de.ibm.com --- include/linux/timekeeping.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..a5a3cfc3c2fa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -258,8 +258,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, - struct timespec64 *boot_offset); +void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* -- cgit v1.2.3 From 4ac695464763ecf696eaba563eff1c2ab994f6d8 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Tue, 28 Aug 2018 19:09:07 +0800 Subject: dmaengine: sprd: Support DMA link-list mode The Spreadtrum DMA can support the link-list transaction mode, which means DMA controller can do transaction one by one automatically once we linked these transaction by link-list register. Signed-off-by: Eric Long Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- include/linux/dma/sprd-dma.h | 69 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h index b0115e340fbc..b42b80e52cc2 100644 --- a/include/linux/dma/sprd-dma.h +++ b/include/linux/dma/sprd-dma.h @@ -58,4 +58,73 @@ enum sprd_dma_int_type { SPRD_DMA_CFGERR_INT, }; +/* + * struct sprd_dma_linklist - DMA link-list address structure + * @virt_addr: link-list virtual address to configure link-list node + * @phy_addr: link-list physical address to link DMA transfer + * + * The Spreadtrum DMA controller supports the link-list mode, that means slaves + * can supply several groups configurations (each configuration represents one + * DMA transfer) saved in memory, and DMA controller will link these groups + * configurations by writing the physical address of each configuration into the + * link-list register. + * + * Just as shown below, the link-list pointer register will be pointed to the + * physical address of 'configuration 1', and the 'configuration 1' link-list + * pointer will be pointed to 'configuration 2', and so on. + * Once trigger the DMA transfer, the DMA controller will load 'configuration + * 1' to its registers automatically, after 'configuration 1' transaction is + * done, DMA controller will load 'configuration 2' automatically, until all + * DMA transactions are done. + * + * Note: The last link-list pointer should point to the physical address + * of 'configuration 1', which can avoid DMA controller loads incorrect + * configuration when the last configuration transaction is done. + * + * DMA controller linklist memory + * ====================== ----------------------- + *| | | configuration 1 |<--- + *| DMA controller | ------->| | | + *| | | | | | + *| | | | | | + *| | | | | | + *| linklist pointer reg |---- ----| linklist pointer | | + * ====================== | ----------------------- | + * | | + * | ----------------------- | + * | | configuration 2 | | + * --->| | | + * | | | + * | | | + * | | | + * ----| linklist pointer | | + * | ----------------------- | + * | | + * | ----------------------- | + * | | configuration 3 | | + * --->| | | + * | | | + * | . | | + * . | + * . | + * . | + * | . | + * | ----------------------- | + * | | configuration n | | + * --->| | | + * | | | + * | | | + * | | | + * | linklist pointer |---- + * ----------------------- + * + * To support the link-list mode, DMA slaves should allocate one segment memory + * from always-on IRAM or dma coherent memory to store these groups of DMA + * configuration, and pass the virtual and physical address to DMA controller. + */ +struct sprd_dma_linklist { + unsigned long virt_addr; + phys_addr_t phy_addr; +}; + #endif -- cgit v1.2.3 From 9da3f2b74054406f87dff7101a569217ffceb29b Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 28 Aug 2018 22:14:20 +0200 Subject: x86/fault: BUG() when uaccess helpers fault on kernel addresses There have been multiple kernel vulnerabilities that permitted userspace to pass completely unchecked pointers through to userspace accessors: - the waitid() bug - commit 96ca579a1ecc ("waitid(): Add missing access_ok() checks") - the sg/bsg read/write APIs - the infiniband read/write APIs These don't happen all that often, but when they do happen, it is hard to test for them properly; and it is probably also hard to discover them with fuzzing. Even when an unmapped kernel address is supplied to such buggy code, it just returns -EFAULT instead of doing a proper BUG() or at least WARN(). Try to make such misbehaving code a bit more visible by refusing to do a fixup in the pagefault handler code when a userspace accessor causes a #PF on a kernel address and the current context isn't whitelisted. Signed-off-by: Jann Horn Signed-off-by: Thomas Gleixner Tested-by: Kees Cook Cc: Andy Lutomirski Cc: kernel-hardening@lists.openwall.com Cc: dvyukov@google.com Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Anil S Keshavamurthy Cc: "David S. Miller" Cc: Alexander Viro Cc: linux-fsdevel@vger.kernel.org Cc: Borislav Petkov Link: https://lkml.kernel.org/r/20180828201421.157735-7-jannh@google.com --- 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 977cb57d7bc9..56dd65f1be4f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -739,6 +739,12 @@ struct task_struct { unsigned use_memdelay:1; #endif + /* + * May usercopy functions fault on kernel addresses? + * This is not just a single bit because this can potentially nest. + */ + unsigned int kernel_uaccess_faults_ok; + unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; -- cgit v1.2.3 From 1e6cb72399fd58b38a1c11055ef18fe01f535cda Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 1 Sep 2018 10:41:11 +0300 Subject: fsnotify: add super block object type Add the infrastructure to attach a mark to a super_block struct and detach all attached marks when super block is destroyed. This is going to be used by fanotify backend to setup super block marks. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fs.h | 5 +++++ include/linux/fsnotify_backend.h | 17 ++++++++++++++--- 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..2c14801d0aa3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1464,6 +1464,11 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ + +#ifdef CONFIG_FSNOTIFY + __u32 s_fsnotify_mask; + struct fsnotify_mark_connector __rcu *s_fsnotify_marks; +#endif } __randomize_layout; /* Helper functions so that in most cases filesystems will diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b8f4182f42f1..81b88fc9df31 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -206,12 +206,14 @@ struct fsnotify_group { enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, + FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; #define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) #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) static inline bool fsnotify_valid_obj_type(unsigned int type) @@ -255,6 +257,7 @@ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) +FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_obj_type(type) \ for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) @@ -267,8 +270,8 @@ struct fsnotify_mark_connector; typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; /* - * Inode / vfsmount point to this structure which tracks all marks attached to - * the inode / vfsmount. The reference to inode / vfsmount is held by this + * Inode/vfsmount/sb point to this structure which tracks all marks attached to + * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ @@ -335,6 +338,7 @@ extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int dat extern int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); 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 int fsnotify_inode_watches_children(struct inode *inode) @@ -455,9 +459,13 @@ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *gr { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); } +/* run all the marks in a group, and clear all of the sn marks */ +static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) +{ + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); +} extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); -extern void fsnotify_unmount_inodes(struct super_block *sb); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); @@ -484,6 +492,9 @@ static inline void __fsnotify_inode_delete(struct inode *inode) static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} +static inline void fsnotify_sb_delete(struct super_block *sb) +{} + static inline void fsnotify_update_flags(struct dentry *dentry) {} -- cgit v1.2.3 From 3edd79cf5a44b12dbb13bc320f5788aed6562b36 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 3 Sep 2018 16:49:37 +0200 Subject: regulator: Fix 'do-nothing' value for regulators without suspend state Some regulators don't have all states defined and in such cases regulator core should not assume anything. However in current implementation of of_get_regulation_constraints() DO_NOTHING_IN_SUSPEND enable value was set only for regulators which had suspend node defined, otherwise the default 0 value was used, what means DISABLE_IN_SUSPEND. This lead to broken system suspend/resume on boards, which had simple regulator constraints definition (without suspend state nodes). To avoid further mismatches between the default and uninitialized values of the suspend enabled/disabled states, change the values of the them, so default '0' means DO_NOTHING_IN_SUSPEND. Fixes: 72069f9957a1: regulator: leave one item to record whether regulator is enabled Signed-off-by: Marek Szyprowski Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/linux/regulator/machine.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 3468703d663a..a459a5e973a7 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -48,9 +48,9 @@ struct regulator; * DISABLE_IN_SUSPEND - turn off regulator in suspend states * ENABLE_IN_SUSPEND - keep regulator on in suspend states */ -#define DO_NOTHING_IN_SUSPEND (-1) -#define DISABLE_IN_SUSPEND 0 -#define ENABLE_IN_SUSPEND 1 +#define DO_NOTHING_IN_SUSPEND 0 +#define DISABLE_IN_SUSPEND 1 +#define ENABLE_IN_SUSPEND 2 /* Regulator active discharge flags */ enum regulator_active_discharge { -- cgit v1.2.3 From 4d18975c78f2d5c91792356501cf369e67594241 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Sat, 1 Sep 2018 16:08:45 +0200 Subject: fbdev: add remove_conflicting_pci_framebuffers() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Almost all PCI drivers using remove_conflicting_framebuffers() wrap it with the same code. v2: add kerneldoc for DRM helper v3: propagate remove_conflicting_framebuffers() return value + move kerneldoc to where function is implemented Signed-off-by: Michał Mirosław Acked-by: Bartlomiej Zolnierkiewicz Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/7db1c278276de420eb45a1b71d06b5eb6bbd49ef.1535810304.git.mirq-linux@rere.qmqm.pl --- include/linux/fb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 3e7e75383d32..3cd375dafd0e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -632,6 +632,8 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, extern int register_framebuffer(struct fb_info *fb_info); extern int unregister_framebuffer(struct fb_info *fb_info); extern int unlink_framebuffer(struct fb_info *fb_info); +extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, + const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); -- cgit v1.2.3 From 9fd0e09a4e86499639653243edfcb417a05c5c46 Mon Sep 17 00:00:00 2001 From: Anthony Wong Date: Fri, 31 Aug 2018 20:06:42 +0800 Subject: r8169: add support for NCube 8168 network card This card identifies itself as: Ethernet controller [0200]: NCube Device [10ff:8168] (rev 06) Subsystem: TP-LINK Technologies Co., Ltd. Device [7470:3468] Adding a new entry to rtl8169_pci_tbl makes the card work. Link: http://launchpad.net/bugs/1788730 Signed-off-by: Anthony Wong Signed-off-by: David S. Miller --- 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 99d366cb0e9f..d157983b84cf 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3084,4 +3084,6 @@ #define PCI_VENDOR_ID_OCZ 0x1b85 +#define PCI_VENDOR_ID_NCUBE 0x10ff + #endif /* _LINUX_PCI_IDS_H */ -- cgit v1.2.3 From f3569fd613f669c95ad187208ad281995f30cc2a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 7 Aug 2018 14:18:42 -0700 Subject: crypto: shash - Remove VLA usage in unaligned hashing In the quest to remove all stack VLA usage from the kernel[1], this uses the newly defined max alignment to perform unaligned hashing to avoid VLAs, and drops the helper function while adding sanity checks on the resulting buffer sizes. Additionally, the __aligned_largest macro is removed since this helper was the only user. [1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com Signed-off-by: Kees Cook Signed-off-by: Herbert Xu --- include/linux/compiler_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..13fee5fe734b 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -198,7 +198,6 @@ struct ftrace_likely_data { */ #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) -#define __aligned_largest __attribute__((aligned)) #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) #define __maybe_unused __attribute__((unused)) -- cgit v1.2.3 From b76377543b738a6b58b0a7b0a42dd9e16436fee1 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 30 Aug 2018 11:00:15 -0400 Subject: crc-t10dif: Pick better transform if one becomes available T10 CRC library is linked into the kernel thanks to block and SCSI. The crypto accelerators are typically loaded later as modules and are therefore not available when the T10 CRC library is initialized. Use the crypto notifier facility to trigger a switch to a better algorithm if one becomes available after the initial hash has been registered. Use RCU to protect the original transform while the new one is being set up. Suggested-by: Ard Biesheuvel Signed-off-by: Martin K. Petersen Signed-off-by: Herbert Xu --- include/linux/crc-t10dif.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index 1fe0cfcdea30..6bb0c0bf357b 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -6,6 +6,7 @@ #define CRC_T10DIF_DIGEST_SIZE 2 #define CRC_T10DIF_BLOCK_SIZE 1 +#define CRC_T10DIF_STRING "crct10dif" extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len); -- cgit v1.2.3 From bf97279079be21fc843d90489846d2c73c77ed09 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 29 Aug 2018 17:08:53 +0200 Subject: gpio: ts5500: Use SPDX header Cut some boilerplate, use the SPDX license identifier. Cc: kernel@savoirfairelinux.com Cc: Vivien Didelot Cc: Jerome Oufella Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-ts5500.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-ts5500.h b/include/linux/platform_data/gpio-ts5500.h index b10d11c9bb49..94346d4504cb 100644 --- a/include/linux/platform_data/gpio-ts5500.h +++ b/include/linux/platform_data/gpio-ts5500.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * GPIO (DIO) header for Technologic Systems TS-5500 * * Copyright (c) 2012 Savoir-faire Linux Inc. * Vivien Didelot - * - * 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. */ #ifndef _PDATA_GPIO_TS5500_H -- cgit v1.2.3 From 97feacc05dfb601273fd680d7b805b8e09c1bec7 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 29 Aug 2018 17:16:18 +0200 Subject: gpio: ts5500: Delete platform data handling The TS5500 GPIO driver apparently supports platform data without making any use of it whatsoever. Delete this code, last chance to speak up if you think it is needed. Cc: kernel@savoirfairelinux.com Cc: Vivien Didelot Cc: Jerome Oufella Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-ts5500.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/platform_data/gpio-ts5500.h (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-ts5500.h b/include/linux/platform_data/gpio-ts5500.h deleted file mode 100644 index 94346d4504cb..000000000000 --- a/include/linux/platform_data/gpio-ts5500.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * GPIO (DIO) header for Technologic Systems TS-5500 - * - * Copyright (c) 2012 Savoir-faire Linux Inc. - * Vivien Didelot - */ - -#ifndef _PDATA_GPIO_TS5500_H -#define _PDATA_GPIO_TS5500_H - -/** - * struct ts5500_dio_platform_data - TS-5500 pin block configuration - * @base: The GPIO base number to use. - * @strap: The only pin connected to an interrupt in a block is input-only. - * If you need a bidirectional line which can trigger an IRQ, you - * may strap it with an in/out pin. This flag indicates this case. - */ -struct ts5500_dio_platform_data { - int base; - bool strap; -}; - -#endif /* _PDATA_GPIO_TS5500_H */ -- cgit v1.2.3 From aa7e80b220f3a543eefbe4b7e2c5d2b73e2e2ef7 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Mon, 3 Sep 2018 20:19:28 +0300 Subject: net/mlx5: Fix atomic_mode enum values The field atomic_mode is 4 bits wide and therefore can hold values from 0x0 to 0xf. Remove the unnecessary 20 bit shift that made the values be incorrect. While that, remove unused enum values. Fixes: 57cda166bbe0 ("net/mlx5: Add DCT command interface") Signed-off-by: Moni Shoua Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..d885e9f0e054 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -163,10 +163,7 @@ enum mlx5_dcbx_oper_mode { }; enum mlx5_dct_atomic_mode { - MLX5_ATOMIC_MODE_DCT_OFF = 20, - MLX5_ATOMIC_MODE_DCT_NONE = 0 << MLX5_ATOMIC_MODE_DCT_OFF, - MLX5_ATOMIC_MODE_DCT_IB_COMP = 1 << MLX5_ATOMIC_MODE_DCT_OFF, - MLX5_ATOMIC_MODE_DCT_CX = 2 << MLX5_ATOMIC_MODE_DCT_OFF, + MLX5_ATOMIC_MODE_DCT_CX = 2, }; enum { -- cgit v1.2.3 From afaef01c001537fa97a25092d7f54d764dc7d8c1 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:16:58 +0300 Subject: x86/entry: Add STACKLEAK erasing the kernel stack at the end of syscalls The STACKLEAK feature (initially developed by PaX Team) has the following benefits: 1. Reduces the information that can be revealed through kernel stack leak bugs. The idea of erasing the thread stack at the end of syscalls is similar to CONFIG_PAGE_POISONING and memzero_explicit() in kernel crypto, which all comply with FDP_RIP.2 (Full Residual Information Protection) of the Common Criteria standard. 2. Blocks some uninitialized stack variable attacks (e.g. CVE-2017-17712, CVE-2010-2963). That kind of bugs should be killed by improving C compilers in future, which might take a long time. This commit introduces the code filling the used part of the kernel stack with a poison value before returning to userspace. Full STACKLEAK feature also contains the gcc plugin which comes in a separate commit. The STACKLEAK feature is ported from grsecurity/PaX. More information at: https://grsecurity.net/ https://pax.grsecurity.net/ This code is modified from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on our understanding of the code. Changes or omissions from the original code are ours and don't reflect the original grsecurity/PaX code. Performance impact: Hardware: Intel Core i7-4770, 16 GB RAM Test #1: building the Linux kernel on a single core 0.91% slowdown Test #2: hackbench -s 4096 -l 2000 -g 15 -f 25 -P 4.2% slowdown So the STACKLEAK description in Kconfig includes: "The tradeoff is the performance impact: on a single CPU system kernel compilation sees a 1% slowdown, other systems and workloads may vary and you are advised to test this feature on your expected workload before deploying it". Signed-off-by: Alexander Popov Acked-by: Thomas Gleixner Reviewed-by: Dave Hansen Acked-by: Ingo Molnar Signed-off-by: Kees Cook --- include/linux/sched.h | 4 ++++ include/linux/stackleak.h | 26 ++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) create mode 100644 include/linux/stackleak.h (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..c1a23acd24e7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1192,6 +1192,10 @@ struct task_struct { void *security; #endif +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + unsigned long lowest_stack; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h new file mode 100644 index 000000000000..628c2b947b89 --- /dev/null +++ b/include/linux/stackleak.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_STACKLEAK_H +#define _LINUX_STACKLEAK_H + +#include +#include + +/* + * Check that the poison value points to the unused hole in the + * virtual memory map for your platform. + */ +#define STACKLEAK_POISON -0xBEEF +#define STACKLEAK_SEARCH_DEPTH 128 + +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#include + +static inline void stackleak_task_init(struct task_struct *t) +{ + t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +} +#else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ +static inline void stackleak_task_init(struct task_struct *t) { } +#endif + +#endif -- cgit v1.2.3 From c8d126275a5fa59394fe17109bdb9812fed296b8 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:01 +0300 Subject: fs/proc: Show STACKLEAK metrics in the /proc file system Introduce CONFIG_STACKLEAK_METRICS providing STACKLEAK information about tasks via the /proc file system. In particular, /proc//stack_depth shows the maximum kernel stack consumption for the current and previous syscalls. Although this information is not precise, it can be useful for estimating the STACKLEAK performance impact for your workloads. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- include/linux/sched.h | 1 + include/linux/stackleak.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c1a23acd24e7..ae9d10e14b82 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1194,6 +1194,7 @@ struct task_struct { #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; + unsigned long prev_lowest_stack; #endif /* diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 628c2b947b89..b911b973d328 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -18,6 +18,9 @@ static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +# ifdef CONFIG_STACKLEAK_METRICS + t->prev_lowest_stack = t->lowest_stack; +# endif } #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } -- cgit v1.2.3 From 964c9dff0091893a9a74a88edf984c6da0b779f7 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:03 +0300 Subject: stackleak: Allow runtime disabling of kernel stack erasing Introduce CONFIG_STACKLEAK_RUNTIME_DISABLE option, which provides 'stack_erasing' sysctl. It can be used in runtime to control kernel stack erasing for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- include/linux/stackleak.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index b911b973d328..3d5c3271a9a8 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -22,6 +22,12 @@ static inline void stackleak_task_init(struct task_struct *t) t->prev_lowest_stack = t->lowest_stack; # endif } + +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif -- cgit v1.2.3 From 0d6c3011409135ea84e2a231b013a22017ff999a Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 4 Sep 2018 15:31:14 +0200 Subject: HID: core: fix grouping by application commit f07b3c1da92d ("HID: generic: create one input report per application type") was effectively the same as MULTI_INPUT: hidinput->report was never set, so hidinput_match_application() always returned null. Fix that by testing against the real application. Note that this breaks some old eGalax touchscreens that expect MULTI_INPUT instead of HID_QUIRK_INPUT_PER_APP. Enable this quirk for backward compatibility on all non-Win8 touchscreens. link: https://bugzilla.kernel.org/show_bug.cgi?id=200847 link: https://bugzilla.kernel.org/show_bug.cgi?id=200849 link: https://bugs.archlinux.org/task/59699 link: https://github.com/NixOS/nixpkgs/issues/45165 Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..d44a78362942 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,6 +526,7 @@ struct hid_input { const char *name; bool registered; struct list_head reports; /* the list of reports */ + unsigned int application; /* application usage for this input */ }; enum hid_type { -- cgit v1.2.3 From 7525c9518ea6feabc8154956df0891a59a69d289 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 27 Jul 2018 23:05:42 +0200 Subject: mtd: rawnand: Get rid of the ->read_word() hook Commit c120e75e0e7d ("mtd: nand: use read_oob() instead of cmdfunc() for bad block check") removed this only user of the ->read_word() method but kept the hook in place. Remove it now. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index efb2345359bb..d155470f53c8 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1182,7 +1182,6 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the * flash device. * @read_byte: [REPLACEABLE] read one byte from the chip - * @read_word: [REPLACEABLE] read one word from the chip * @write_byte: [REPLACEABLE] write a single byte to the chip on the * low 8 I/O lines * @write_buf: [REPLACEABLE] write data from the buffer to the chip @@ -1287,7 +1286,6 @@ struct nand_chip { void __iomem *IO_ADDR_W; uint8_t (*read_byte)(struct mtd_info *mtd); - u16 (*read_word)(struct mtd_info *mtd); void (*write_byte)(struct mtd_info *mtd, uint8_t byte); void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); -- cgit v1.2.3 From ff8648f29fe58c2d94d32a076d2de7b92be4b485 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Mon, 13 Aug 2018 09:18:46 +0200 Subject: mtd: rawnand: fsl_ifc: fixup SRAM init for newer ctrl versions Newer versions of the IFC controller use a different method of initializing the internal SRAM: Instead of reading from flash, a bit in the NAND configuration register has to be set in order to trigger the self-initializing process. Signed-off-by: Kurt Kanzenbach Signed-off-by: Miquel Raynal --- include/linux/fsl_ifc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h index 3fdfede2f0f3..5f343b796ad9 100644 --- a/include/linux/fsl_ifc.h +++ b/include/linux/fsl_ifc.h @@ -274,6 +274,8 @@ */ /* Auto Boot Mode */ #define IFC_NAND_NCFGR_BOOT 0x80000000 +/* SRAM Initialization */ +#define IFC_NAND_NCFGR_SRAM_INIT_EN 0x20000000 /* Addressing Mode-ROW0+n/COL0 */ #define IFC_NAND_NCFGR_ADDR_MODE_RC0 0x00000000 /* Addressing Mode-ROW0+n/COL0+n */ -- cgit v1.2.3 From 8ce78257965e6cd49720e653867e766ecd38883f Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:41 +0300 Subject: net/mlx5: Add proper NIC TX steering flow tables support Extend the ability to add steering rules to NIC TX flow tables. For now, we are only adding TX bypass (egress) which is used by the RDMA side. This will allow to shape outgoing traffic and tweak it if needed, for example performing encapsulation or rewriting headers. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 11fa4e66afc5..f2281e69ab39 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1120,6 +1120,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \ MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap) +#define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap) + +#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \ + MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap) + #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap) -- cgit v1.2.3 From 90c1d1b8da67330b09893d749401a45328b51704 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:42 +0300 Subject: net/mlx5: Export modify header alloc/dealloc functions Those functions will be used by the RDMA side to create modify header actions to be attached to flow steering rules via verbs. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 804516e4f483..0cbf4d5cb1ab 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -196,4 +196,10 @@ int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); +int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 namespace, u8 num_actions, + void *modify_actions, u32 *modify_header_id); +void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, + u32 modify_header_id); + #endif -- cgit v1.2.3 From 61444b458b01c95e55003d6f0b4d4c936fde51cb Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:44 +0300 Subject: net/mlx5: Break encap/decap into two separated flow table creation flags Today we are able to attach encap and decap actions only to the FDB. In preparation to enable those actions on the NIC flow tables, break the single flag into two. Those flags control whatever a decap or encap operations can be attached to the flow table created. For FDB, if encapsulation is required, we set both of them. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Reviewed-by: Or Gerlitz Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0cbf4d5cb1ab..0194e62ad66a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -45,7 +45,8 @@ enum { }; enum { - MLX5_FLOW_TABLE_TUNNEL_EN = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), }; #define LEFTOVERS_RULE_NUM 2 -- cgit v1.2.3 From e0e7a3861b6c6b673dc93e291ef11cf5e746b0c2 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:45 +0300 Subject: net/mlx5: Move header encap type to IFC header file Those bits are hardware specification and should be defined in the IFC header file. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f043d65b9bac..bd725e0924e5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4848,6 +4848,11 @@ struct mlx5_ifc_alloc_encap_header_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_HEADER_TYPE_VXLAN = 0x0, + MLX5_HEADER_TYPE_NVGRE = 0x1, +}; + struct mlx5_ifc_alloc_encap_header_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; -- cgit v1.2.3 From 60786f0987c0d9354e5330ee11615b16cdb448fe Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:46 +0300 Subject: {net, RDMA}/mlx5: Rename encap to reformat packet Renames all encap mlx5_{core,ib} code to use the new naming of packet reformat. This change doesn't introduce any function change and is needed to properly reflect the operation being done by this action. For example not only can we encapsulate a packet, but also decapsulate it. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 4 ++-- include/linux/mlx5/mlx5_ifc.h | 50 +++++++++++++++++++++---------------------- 2 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0194e62ad66a..37d0c08d0966 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -45,7 +45,7 @@ enum { }; enum { - MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0), MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), }; @@ -160,7 +160,7 @@ struct mlx5_flow_act { u32 action; bool has_flow_tag; u32 flow_tag; - u32 encap_id; + u32 reformat_id; u32 modify_id; uintptr_t esp_id; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bd725e0924e5..c79eaae28e59 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -243,8 +243,8 @@ enum { MLX5_CMD_OP_DEALLOC_FLOW_COUNTER = 0x93a, MLX5_CMD_OP_QUERY_FLOW_COUNTER = 0x93b, MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c, - MLX5_CMD_OP_ALLOC_ENCAP_HEADER = 0x93d, - MLX5_CMD_OP_DEALLOC_ENCAP_HEADER = 0x93e, + MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT = 0x93d, + MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT = 0x93e, MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT = 0x942, @@ -336,7 +336,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 modify_root[0x1]; u8 identified_miss_table_mode[0x1]; u8 flow_table_modify[0x1]; - u8 encap[0x1]; + u8 reformat[0x1]; u8 decap[0x1]; u8 reserved_at_9[0x1]; u8 pop_vlan[0x1]; @@ -599,7 +599,7 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vxlan_encap_decap[0x1]; u8 nvgre_encap_decap[0x1]; u8 reserved_at_22[0x9]; - u8 log_max_encap_headers[0x5]; + u8 log_max_packet_reformat_context[0x5]; u8 reserved_2b[0x6]; u8 max_encap_header_size[0xa]; @@ -2394,7 +2394,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_DROP = 0x2, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST = 0x4, MLX5_FLOW_CONTEXT_ACTION_COUNT = 0x8, - MLX5_FLOW_CONTEXT_ACTION_ENCAP = 0x10, + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT = 0x10, MLX5_FLOW_CONTEXT_ACTION_DECAP = 0x20, MLX5_FLOW_CONTEXT_ACTION_MOD_HDR = 0x40, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP = 0x80, @@ -2427,7 +2427,7 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_a0[0x8]; u8 flow_counter_list_size[0x18]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 modify_header_id[0x20]; @@ -4802,19 +4802,19 @@ struct mlx5_ifc_query_eq_in_bits { u8 reserved_at_60[0x20]; }; -struct mlx5_ifc_encap_header_in_bits { +struct mlx5_ifc_packet_reformat_context_in_bits { u8 reserved_at_0[0x5]; - u8 header_type[0x3]; + u8 reformat_type[0x3]; u8 reserved_at_8[0xe]; - u8 encap_header_size[0xa]; + u8 reformat_data_size[0xa]; u8 reserved_at_20[0x10]; - u8 encap_header[2][0x8]; + u8 reformat_data[2][0x8]; - u8 more_encap_header[0][0x8]; + u8 more_reformat_data[0][0x8]; }; -struct mlx5_ifc_query_encap_header_out_bits { +struct mlx5_ifc_query_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4822,38 +4822,38 @@ struct mlx5_ifc_query_encap_header_out_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_encap_header_in_bits encap_header[0]; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context[0]; }; -struct mlx5_ifc_query_encap_header_in_bits { +struct mlx5_ifc_query_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_at_60[0xa0]; }; -struct mlx5_ifc_alloc_encap_header_out_bits { +struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_at_60[0x20]; }; enum { - MLX5_HEADER_TYPE_VXLAN = 0x0, - MLX5_HEADER_TYPE_NVGRE = 0x1, + MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, + MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, }; -struct mlx5_ifc_alloc_encap_header_in_bits { +struct mlx5_ifc_alloc_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -4862,10 +4862,10 @@ struct mlx5_ifc_alloc_encap_header_in_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_encap_header_in_bits encap_header; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context; }; -struct mlx5_ifc_dealloc_encap_header_out_bits { +struct mlx5_ifc_dealloc_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4874,14 +4874,14 @@ struct mlx5_ifc_dealloc_encap_header_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_dealloc_encap_header_in_bits { +struct mlx5_ifc_dealloc_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; u8 reserved_20[0x10]; u8 op_mod[0x10]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_60[0x20]; }; @@ -6983,7 +6983,7 @@ struct mlx5_ifc_create_flow_table_out_bits { }; struct mlx5_ifc_flow_table_context_bits { - u8 encap_en[0x1]; + u8 reformat_en[0x1]; u8 decap_en[0x1]; u8 reserved_at_2[0x2]; u8 table_miss_action[0x4]; -- cgit v1.2.3 From bea4e1f6c6c5744d467ebf8b0699f5e391835130 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:47 +0300 Subject: net/mlx5: Expose new packet reformat capabilities Expose new abilities when creating a packet reformat context. The new types which can be created are: MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: Ability to create generic encap operation to be done by the HW. MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: Ability to create generic decap operation where the inner packet doesn't contain L2. MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: Ability to create generic encap operation to be done by the HW. The L2 of the original packet is dropped. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c79eaae28e59..3a4a2e0567e9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -344,8 +344,12 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_c[0x1]; u8 pop_vlan_2[0x1]; u8 push_vlan_2[0x1]; - u8 reserved_at_f[0x11]; - + u8 reformat_and_vlan_action[0x1]; + u8 reserved_at_10[0x2]; + u8 reformat_l3_tunnel_to_l2[0x1]; + u8 reformat_l2_to_l3_tunnel[0x1]; + u8 reformat_and_modify_action[0x1]; + u8 reserved_at_14[0xb]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; @@ -554,7 +558,13 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 nic_rx_multi_path_tirs[0x1]; u8 nic_rx_multi_path_tirs_fts[0x1]; u8 allow_sniffer_and_nic_rx_shared_tir[0x1]; - u8 reserved_at_3[0x1fd]; + u8 reserved_at_3[0x1d]; + u8 encap_general_header[0x1]; + u8 reserved_at_21[0xa]; + u8 log_max_packet_reformat_context[0x5]; + u8 reserved_at_30[0x6]; + u8 max_encap_header_size[0xa]; + u8 reserved_at_40[0x1c0]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; @@ -4851,6 +4861,9 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { enum { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, + MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, + MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, + MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { -- cgit v1.2.3 From 50acec06f3928fc29647aecf1270e54cae583afb Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:49 +0300 Subject: net/mlx5: Export packet reformat alloc/dealloc functions This will allow for the RDMA side to allocate packet reformat context. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/fs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 37d0c08d0966..b1c026f1c8ba 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -203,4 +203,13 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id); +int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + u32 *packet_reformat_id); +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + u32 packet_reformat_id); + #endif -- cgit v1.2.3 From 03512ceb60ae4be71ed3129dabb8625224c8ec40 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Fri, 31 Aug 2018 11:31:09 +0300 Subject: ieee80211: remove redundant leading zeroes The defines of IEEE80211_HE_OPERATION_VHT_OPER_INFO and IEEE80211_HE_OPERATION_MULTI_BSSID_AP have leading zeroes that makes the number look like it is bigger than 32 bit. This is misleading, remove it. Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9c03a7d5e400..17ea51d088ae 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1963,8 +1963,8 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10 -#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000 -#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x00100000 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00200000 #define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000 #define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000 -- cgit v1.2.3 From b0aa75f0b1b2e6bc77128fab36c8ed87e84917cc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 31 Aug 2018 11:31:16 +0300 Subject: ieee80211: add new VHT capability fields/parsing IEEE 802.11-2016 extended the VHT capability fields to allow indicating the number of spatial streams depending on the actually used bandwidth, add support for decoding this. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 17ea51d088ae..280600a10111 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1460,13 +1460,16 @@ struct ieee80211_ht_operation { * STA can receive. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. - * The top 3 bits of this field are reserved. + * The top 3 bits of this field indicate the Maximum NSTS,total + * (a beamformee capability.) * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams * @tx_highest: Indicates highest long GI VHT PPDU data rate * STA can transmit. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest TX data rate supported. - * The top 3 bits of this field are reserved. + * The top 2 bits of this field are reserved, the + * 3rd bit from the top indiciates VHT Extended NSS BW + * Capability. */ struct ieee80211_vht_mcs_info { __le16 rx_mcs_map; @@ -1475,6 +1478,13 @@ struct ieee80211_vht_mcs_info { __le16 tx_highest; } __packed; +/* for rx_highest */ +#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 +#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) + +/* for tx_highest */ +#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) + /** * enum ieee80211_vht_mcs_support - VHT MCS support definitions * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the @@ -1650,6 +1660,7 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 #define IEEE80211_VHT_CAP_RXLDPC 0x00000010 #define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 #define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 @@ -1678,6 +1689,26 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 + +/** + * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS + * @cap: VHT capabilities of the peer + * @bw: bandwidth to use + * @mcs: MCS index to use + * @ext_nss_bw_capable: indicates whether or not the local transmitter + * (rate scaling algorithm) can deal with the new logic + * (dot11VHTExtendedNSSBWCapable) + * + * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can + * vary for a given BW/MCS. This function parses the data. + * + * Note: This function is exported by cfg80211. + */ +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable); /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 -- cgit v1.2.3 From add7453ad62f05c8f1a48675bb4dfed52e6ac878 Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Wed, 5 Sep 2018 08:06:08 +0300 Subject: wireless: align to draft 11ax D3.0 Align to new 11ax draft D3.0. Change/add new MAC and PHY capabilities and update drivers' 11ax capabilities and mac80211's debugfs accordingly. Signed-off-by: Shaul Triebitz Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 72 ++++++++++++++++++++++++++++++----------------- 1 file changed, 46 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 280600a10111..c4809ad8ab46 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1555,11 +1555,11 @@ struct ieee80211_vht_operation { * struct ieee80211_he_cap_elem - HE capabilities element * * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3 + * described in P802.11ax_D3.0 section 9.4.2.237.2 and 9.4.2.237.3 */ struct ieee80211_he_cap_elem { - u8 mac_cap_info[5]; - u8 phy_cap_info[9]; + u8 mac_cap_info[6]; + u8 phy_cap_info[11]; } __packed; #define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 @@ -1738,15 +1738,15 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 /* Link adaptation is split between byte HE_MAC_CAP1 and * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE @@ -1760,14 +1760,13 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 #define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 -#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04 +#define IEEE80211_HE_MAC_CAP2_TRS 0x04 #define IEEE80211_HE_MAC_CAP2_BSR 0x08 #define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 #define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 #define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 #define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 -#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01 #define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 #define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 @@ -1775,25 +1774,34 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the * same field in the HE capabilities. */ -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18 -#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_USE_VHT 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_RESERVED 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 #define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 #define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 #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 -#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_SRP_RESP 0x08 #define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 #define IEEE80211_HE_MAC_CAP4_OPS 0x20 #define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40 +/* Multi TID agg TX is split between byte #4 and #5 + * The value is a combination of B39,B40,B41 + */ +#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 + +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 +#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECVITE_TRANSMISSION 0x04 +#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 +#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 /* 802.11ax HE PHY capabilities */ -#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01 #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 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 @@ -1810,10 +1818,10 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 #define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 #define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 -/* Midamble RX Max NSTS is split between byte #2 and byte #3 */ -#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80 +/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 -#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 #define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 #define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 #define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 @@ -1914,7 +1922,19 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 #define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 #define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 -#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_20MHZ 0x00 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_40MHZ 0x40 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_80MHZ 0x80 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ 0xc0 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 +#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 +#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 +#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) -- cgit v1.2.3 From 1ff2e1a44e02d4bdbb9be67c7d9acc240a67141f Mon Sep 17 00:00:00 2001 From: Harry Cutts Date: Thu, 30 Aug 2018 14:56:19 -0700 Subject: HID: input: Create a utility class for counting scroll events To avoid code duplication, this class counts high-resolution scroll movements and emits the legacy low-resolution events when appropriate. Drivers should be able to create one instance for each scroll wheel that they need to handle. Signed-off-by: Harry Cutts Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..037e37b0b0e6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1138,6 +1138,34 @@ static inline u32 hid_report_len(struct hid_report *report) int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt); + +/** + * struct hid_scroll_counter - Utility class for processing high-resolution + * scroll events. + * @dev: the input device for which events should be reported. + * @microns_per_hi_res_unit: the amount moved by the user's finger for each + * high-resolution unit reported by the mouse, in + * microns. + * @resolution_multiplier: the wheel's resolution in high-resolution mode as a + * multiple of its lower resolution. For example, if + * moving the wheel by one "notch" would result in a + * value of 1 in low-resolution mode but 8 in + * high-resolution, the multiplier is 8. + * @remainder: counts the number of high-resolution units moved since the last + * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should + * only be used by class methods. + */ +struct hid_scroll_counter { + struct input_dev *dev; + int microns_per_hi_res_unit; + int resolution_multiplier; + + int remainder; +}; + +void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, + int hi_res_value); + /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); int hid_quirks_init(char **quirks_param, __u16 bus, int count); -- cgit v1.2.3 From d23df2dc56325c72b51670b1fb400ddd23dc17cd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Sep 2018 12:51:59 -0700 Subject: linux/mod_devicetable.h: fix kernel-doc missing notation for typec_device_id Fix kernel-doc warning for missing struct member description: ../include/linux/mod_devicetable.h:763: warning: Function parameter or member 'driver_data' not described in 'typec_device_id' Fixes: 8a37d87d72f0c ("usb: typec: Bus type for alternate modes") Signed-off-by: Randy Dunlap Cc: Heikki Krogerus Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1298a7daa57d..01797cb4587e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -754,6 +754,7 @@ struct tb_service_id { * struct typec_device_id - USB Type-C alternate mode identifiers * @svid: Standard or Vendor ID * @mode: Mode index + * @driver_data: Driver specific data */ struct typec_device_id { __u16 svid; -- cgit v1.2.3 From 865e63b04e9b2a658d7f26bd13a71dcd964a9118 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 4 Sep 2018 16:26:11 -0400 Subject: tracing: Add back in rcu_irq_enter/exit_irqson() for rcuidle tracepoints Borislav reported the following splat: ============================= WARNING: suspicious RCU usage 4.19.0-rc1+ #1 Not tainted ----------------------------- ./include/linux/rcupdate.h:631 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 2, debug_locks = 1 RCU used illegally from extended quiescent state! 1 lock held by swapper/0/0: #0: 000000004557ee0e (rcu_read_lock){....}, at: perf_event_output_forward+0x0/0x130 stack backtrace: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.19.0-rc1+ #1 Hardware name: LENOVO 2320CTO/2320CTO, BIOS G2ET86WW (2.06 ) 11/13/2012 Call Trace: dump_stack+0x85/0xcb perf_event_output_forward+0xf6/0x130 __perf_event_overflow+0x52/0xe0 perf_swevent_overflow+0x91/0xb0 perf_tp_event+0x11a/0x350 ? find_held_lock+0x2d/0x90 ? __lock_acquire+0x2ce/0x1350 ? __lock_acquire+0x2ce/0x1350 ? retint_kernel+0x2d/0x2d ? find_held_lock+0x2d/0x90 ? tick_nohz_get_sleep_length+0x83/0xb0 ? perf_trace_cpu+0xbb/0xd0 ? perf_trace_buf_alloc+0x5a/0xa0 perf_trace_cpu+0xbb/0xd0 cpuidle_enter_state+0x185/0x340 do_idle+0x1eb/0x260 cpu_startup_entry+0x5f/0x70 start_kernel+0x49b/0x4a6 secondary_startup_64+0xa4/0xb0 This is due to the tracepoints moving to SRCU usage which does not require RCU to be "watching". But perf uses these tracepoints with RCU and expects it to be. Hence, we still need to add in the rcu_irq_enter/exit_irqson() calls for "rcuidle" tracepoints. This is a temporary fix until we have SRCU working in NMI context, and then perf can be converted to use that instead of normal RCU. Link: http://lkml.kernel.org/r/20180904162611.6a120068@gandalf.local.home Cc: x86-ml Cc: Peter Zijlstra Reported-by: Borislav Petkov Tested-by: Borislav Petkov Reviewed-by: "Paul E. McKenney" Fixes: e6753f23d961d ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 7f2e16e76ac4..041f7e56a289 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -158,8 +158,10 @@ extern void syscall_unregfunc(void); * For rcuidle callers, use srcu since sched-rcu \ * doesn't work from the idle path. \ */ \ - if (rcuidle) \ + if (rcuidle) { \ idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + rcu_irq_enter_irqson(); \ + } \ \ it_func_ptr = rcu_dereference_raw((tp)->funcs); \ \ @@ -171,8 +173,10 @@ extern void syscall_unregfunc(void); } while ((++it_func_ptr)->func); \ } \ \ - if (rcuidle) \ + if (rcuidle) { \ + rcu_irq_exit_irqson(); \ srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + } \ \ preempt_enable_notrace(); \ } while (0) -- cgit v1.2.3 From 76d5581c870454be5f1f1a106c57985902e7ea20 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sun, 5 Aug 2018 09:19:33 +0300 Subject: net/mlx5: Fix use-after-free in self-healing flow When the mlx5 health mechanism detects a problem while the driver is in the middle of init_one or remove_one, the driver needs to prevent the health mechanism from scheduling future work; if future work is scheduled, there is a problem with use-after-free: the system WQ tries to run the work item (which has been freed) at the scheduled future time. Prevent this by disabling work item scheduling in the health mechanism when the driver is in the middle of init_one() or remove_one(). Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Jack Morgenstein Reviewed-by: Feras Daoud 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 7a452716de4b..aa65f58c6610 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1052,7 +1052,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -void mlx5_stop_health_poll(struct mlx5_core_dev *dev); +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 8d71e818506718e8d7032ce824b5c74a17d4f7a5 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 16:04:41 +0300 Subject: net/mlx5: Use u16 for Work Queue buffer fragment size Minimal stride size is 16. Hence, the number of strides in a fragment (of PAGE_SIZE) is <= PAGE_SIZE / 16 <= 4K. u16 is sufficient to represent this. Fixes: 388ca8be0037 ("IB/mlx5: Implement fragmented completion queue (CQ)") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha 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 aa65f58c6610..3a1258fd8ac3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -362,7 +362,7 @@ struct mlx5_frag_buf { struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; - u32 frag_sz_m1; + u16 frag_sz_m1; u32 strides_offset; u8 log_sz; u8 log_stride; -- cgit v1.2.3 From a09036221092989b88c55d24d1f12ceb1d7d361f Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 16:07:58 +0300 Subject: net/mlx5: Use u16 for Work Queue buffer strides offset Minimal stride size is 16. Hence, the number of strides in a fragment (of PAGE_SIZE) is <= PAGE_SIZE / 16 <= 4K. u16 is sufficient to represent this. Fixes: d7037ad73daa ("net/mlx5: Fix QP fragmented buffer allocation") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3a1258fd8ac3..66d94b4557cf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -363,7 +363,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u16 frag_sz_m1; - u32 strides_offset; + u16 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -995,7 +995,7 @@ static inline u32 mlx5_base_mkey(const u32 key) } static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, - u32 strides_offset, + u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; -- cgit v1.2.3 From 83033688b7ade18d2dbbcefa810f02ff66ba549d Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 23 Jul 2018 10:55:39 +0300 Subject: net/mlx5: Change flow counters addlist type to single linked list In order to prevent flow counters stats work function from traversing whole flow counters tree while searching for deleted flow counters, new list to store deleted flow counters will be added to struct mlx5_fc_stats. However, the flow counter structure itself has no space left to store any more data in first cache line. To free space that is needed to store additional list node, convert current addlist double linked list (two pointers per node) to atomic single linked list (one pointer per node). Lockless NULL-terminated single linked list data type doesn't require any additional external synchronization for operations used by flow counters module (add single new element, remove all elements from list and traverse them). Remove addlist_lock that is no longer needed. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..c00549293982 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -584,9 +584,7 @@ struct mlx5_irq_info { struct mlx5_fc_stats { struct rb_root counters; - struct list_head addlist; - /* protect addlist add/splice operations */ - spinlock_t addlist_lock; + struct llist_head addlist; struct workqueue_struct *wq; struct delayed_work work; -- cgit v1.2.3 From 6e5e22839136fdb466af0aa46ff2404713dff974 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 23 Jul 2018 11:32:05 +0300 Subject: net/mlx5: Add new list to store deleted flow counters In order to prevent flow counters stats work function from traversing whole flow counters tree while searching for deleted flow counters, new list to store deleted flow counters is added to struct mlx5_fc_stats. Lockless NULL-terminated single linked list data type is used due to following reasons: - This use case only needs to add single element to list and remove/iterate whole list. Lockless list doesn't require any additional synchronization for these operations. - First cache line of flow counter data structure only has space to store single additional pointer, which precludes usage of double linked list. Remove flow counter 'deleted' flag that is no longer needed. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey 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 c00549293982..4b53ac64004b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -585,6 +585,7 @@ struct mlx5_irq_info { struct mlx5_fc_stats { struct rb_root counters; struct llist_head addlist; + struct llist_head dellist; struct workqueue_struct *wq; struct delayed_work work; -- cgit v1.2.3 From 9aff93d7d0d4b3f3076d7bd12a4ad06ef1cf9804 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 24 Jul 2018 09:52:11 +0300 Subject: net/mlx5: Store flow counters in a list In order to improve performance of flow counter stats query loop that traverses all configured flow counters, replace rb_tree with double-linked list. This change improves performance of traversing flow counters by removing the tree traversal. (profiling data showed that call to rb_next was most top CPU consumer) However, lookup of flow flow counter in list becomes linear, instead of logarithmic. This problem is fixed by next patch in series, which adds idr for fast lookup. Idr is to be used because it is not an intrusive data structure and doesn't require adding any new members to struct mlx5_fc, which allows its control data part to stay <= 1 cache line in size. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey 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 4b53ac64004b..61bed33e6675 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,7 +583,7 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { - struct rb_root counters; + struct list_head counters; struct llist_head addlist; struct llist_head dellist; -- cgit v1.2.3 From 12d6066c3b29c5606c4a2466f964fbd9ede803c5 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 24 Jul 2018 16:37:40 +0300 Subject: net/mlx5: Add flow counters idr Previous patch in series changed flow counter storage structure from rb_tree to linked list in order to improve flow counter traversal performance. The drawback of such solution is that flow counter lookup by id becomes linear in complexity. Store pointers to flow counters in idr in order to improve lookup performance to logarithmic again. Idr is non-intrusive data structure and doesn't require extending flow counter struct with new elements. This means that idr can be used for lookup, while linked list from previous patch is used for traversal, and struct mlx5_fc size is <= 2 cache lines. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey 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 61bed33e6675..2a0c845f6bdb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,6 +583,8 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { + spinlock_t counters_idr_lock; /* protects counters_idr */ + struct idr counters_idr; struct list_head counters; struct llist_head addlist; struct llist_head dellist; -- cgit v1.2.3 From 64109f1dc41f25f4a9c6b114e04b6266bf4128ad Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Tue, 5 Jun 2018 09:22:18 +0300 Subject: net/mlx5e: Replace PTP clock lock from RW lock to seq lock Changed "priv.clock.lock" lock from 'rw_lock' to 'seq_lock' in order to improve packet rate performance. Tested on Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz. Sent 64b packets between two peers connected by ConnectX-5, and measured packet rate for the receiver in three modes: no time-stamping (base rate) time-stamping using rw_lock (old lock) for critical region time-stamping using seq_lock (new lock) for critical region Only the receiver time stamped its packets. The measured packet rate improvements are: Single flow (multiple TX rings to single RX ring): without timestamping: 4.26 (M packets)/sec with rw-lock (old lock): 4.1 (M packets)/sec with seq-lock (new lock): 4.16 (M packets)/sec 1.46% improvement Multiple flows (multiple TX rings to six RX rings): without timestamping: 22 (M packets)/sec with rw-lock (old lock): 11.7 (M packets)/sec with seq-lock (new lock): 21.3 (M packets)/sec 82.05% improvement The packet rate improvement is due to the lack of atomic operations for the 'readers' by the seq-lock. Since there are much more 'readers' than 'writers' contention on this lock, almost all atomic operations are saved. this results in a dramatic decrease in overall cache misses. Signed-off-by: Shay Agroskin 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 2a0c845f6bdb..b7fce2c9443d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -805,7 +805,7 @@ struct mlx5_pps { }; struct mlx5_clock { - rwlock_t lock; + seqlock_t lock; struct cyclecounter cycles; struct timecounter tc; struct hwtstamp_config hwtstamp_config; -- cgit v1.2.3 From fa788d986a3aac5069378ed04697bd06f83d3488 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Mon, 3 Sep 2018 16:23:36 +0200 Subject: packet: add sockopt to ignore outgoing packets Currently, the only way to ignore outgoing packets on a packet socket is via the BPF filter. With MSG_ZEROCOPY, packets that are looped into AF_PACKET are copied in dev_queue_xmit_nit(), and this copy happens even if the filter run from packet_rcv() would reject them. So the presence of a packet socket on the interface takes away the benefits of MSG_ZEROCOPY, even if the packet socket is not interested in outgoing packets. (Even when MSG_ZEROCOPY is not used, the skb is unnecessarily cloned, but the cost for that is much lower.) Add a socket option to allow AF_PACKET sockets to ignore outgoing packets to solve this. Note that the *BSDs already have something similar: BIOCSSEESENT/BIOCSDIRECTION and BIOCSDIRFILT. The first intended user is lldpd. Signed-off-by: Vincent Whitchurch Signed-off-by: David S. Miller --- 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 4271f6b4e419..e2b3bd750c98 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2343,6 +2343,7 @@ static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, struct packet_type { __be16 type; /* This is really htons(ether_type). */ + bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ int (*func) (struct sk_buff *, struct net_device *, -- cgit v1.2.3 From a3f723079df85eafc10c628dabdfcf374b8e1523 Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Wed, 5 Sep 2018 18:35:55 +0300 Subject: qed*: Utilize FW 8.37.7.0 This patch adds a new qed firmware with fixes and support for new features. Fixes: - Fix a rare case of device crash with iWARP, iSCSI or FCoE offload. - Fix GRE tunneled traffic when iWARP offload is enabled. - Fix RoCE failure in ib_send_bw when using inline data. - Fix latency optimization flow for inline WQEs. - BigBear 100G fix RDMA: - Reduce task context size. - Application page sizes above 2GB support. - Performance improvements. ETH: - Tenant DCB support. - Replace RSS indirection table update interface. Misc: - Debug Tools changes. Signed-off-by: Denis Bolotin Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 10 +++++----- include/linux/qed/iscsi_common.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 0081fa6d1268..03f59a28fefd 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -110,7 +110,7 @@ #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 37 -#define FW_REVISION_VERSION 2 +#define FW_REVISION_VERSION 7 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -931,12 +931,12 @@ struct db_rdma_dpm_params { #define DB_RDMA_DPM_PARAMS_WQE_SIZE_SHIFT 16 #define DB_RDMA_DPM_PARAMS_RESERVED0_MASK 0x1 #define DB_RDMA_DPM_PARAMS_RESERVED0_SHIFT 27 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_SHIFT 28 #define DB_RDMA_DPM_PARAMS_S_FLG_MASK 0x1 #define DB_RDMA_DPM_PARAMS_S_FLG_SHIFT 29 -#define DB_RDMA_DPM_PARAMS_RESERVED1_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 30 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index b34c573f2b30..66aba505ec56 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -896,7 +896,7 @@ struct e4_ustorm_iscsi_task_ag_ctx { __le32 exp_cont_len; __le32 total_data_acked; __le32 exp_data_acked; - u8 next_tid_valid; + u8 byte2; u8 byte3; __le16 word1; __le16 next_tid; -- cgit v1.2.3 From 7759eb23fd9808a2e4498cf36a798ed65cde78ae Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 5 Sep 2018 15:45:54 -0600 Subject: block: remove bio_rewind_iter() It is pointed that bio_rewind_iter() is one very bad API[1]: 1) bio size may not be restored after rewinding 2) it causes some bogus change, such as 5151842b9d8732 (block: reset bi_iter.bi_done after splitting bio) 3) rewinding really makes things complicated wrt. bio splitting 4) unnecessary updating of .bi_done in fast path [1] https://marc.info/?t=153549924200005&r=1&w=2 So this patch takes Kent's suggestion to restore one bio into its original state via saving bio iterator(struct bvec_iter) in bio_integrity_prep(), given now bio_rewind_iter() is only used by bio integrity code. Cc: Dmitry Monakhov Cc: Hannes Reinecke Suggested-by: Kent Overstreet Acked-by: Kent Overstreet Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 22 ++++------------------ include/linux/bvec.h | 3 --- 2 files changed, 4 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 51371740d2a8..14b4fa266357 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -170,27 +170,11 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, { iter->bi_sector += bytes >> 9; - if (bio_no_advance_iter(bio)) { + if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; - iter->bi_done += bytes; - } else { + else bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ - } -} - -static inline bool bio_rewind_iter(struct bio *bio, struct bvec_iter *iter, - unsigned int bytes) -{ - iter->bi_sector -= bytes >> 9; - - if (bio_no_advance_iter(bio)) { - iter->bi_size += bytes; - iter->bi_done -= bytes; - return true; - } - - return bvec_iter_rewind(bio->bi_io_vec, iter, bytes); } #define __bio_for_each_segment(bvl, bio, iter, start) \ @@ -353,6 +337,8 @@ struct bio_integrity_payload { unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ + struct bvec_iter bio_iter; /* for rewinding parent bio */ + struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; diff --git a/include/linux/bvec.h b/include/linux/bvec.h index fe7a22dd133b..02c73c6aa805 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -40,8 +40,6 @@ struct bvec_iter { unsigned int bi_idx; /* current index into bvl_vec */ - unsigned int bi_done; /* number of bytes completed */ - unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; @@ -85,7 +83,6 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, bytes -= len; iter->bi_size -= len; iter->bi_bvec_done += len; - iter->bi_done += len; if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { iter->bi_bvec_done = 0; -- cgit v1.2.3 From cc8a4ea182efac95ad4582053f8a51271fab734d Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 18 Jul 2018 18:09:55 +0200 Subject: platform/chrome: Move mfd/cros_ec_lpc* includes to drivers/platform. The cros-ec-lpc driver lives in drivers/platform because is platform specific, however there are two includes (cros_ec_lpc_mec.h and cros_ec_lpc_reg.h) that lives in include/linux/mfd. These two includes are only used for the platform driver and are not really related to the MFD subsystem, so move the includes from include/linux/mfd to drivers/platform/chrome. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec_lpc_mec.h | 90 ------------------------------------- include/linux/mfd/cros_ec_lpc_reg.h | 61 ------------------------- 2 files changed, 151 deletions(-) delete mode 100644 include/linux/mfd/cros_ec_lpc_mec.h delete mode 100644 include/linux/mfd/cros_ec_lpc_reg.h (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_lpc_mec.h b/include/linux/mfd/cros_ec_lpc_mec.h deleted file mode 100644 index 176496ddc66c..000000000000 --- a/include/linux/mfd/cros_ec_lpc_mec.h +++ /dev/null @@ -1,90 +0,0 @@ -/* - * cros_ec_lpc_mec - LPC variant I/O for Microchip EC - * - * Copyright (C) 2016 Google, Inc - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver uses the Chrome OS EC byte-level message-based protocol for - * communicating the keyboard state (which keys are pressed) from a keyboard EC - * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, - * but everything else (including deghosting) is done here. The main - * motivation for this is to keep the EC firmware as simple as possible, since - * it cannot be easily upgraded and EC flash/IRAM space is relatively - * expensive. - */ - -#ifndef __LINUX_MFD_CROS_EC_MEC_H -#define __LINUX_MFD_CROS_EC_MEC_H - -#include - -enum cros_ec_lpc_mec_emi_access_mode { - /* 8-bit access */ - ACCESS_TYPE_BYTE = 0x0, - /* 16-bit access */ - ACCESS_TYPE_WORD = 0x1, - /* 32-bit access */ - ACCESS_TYPE_LONG = 0x2, - /* - * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the - * EC data register to be incremented. - */ - ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3, -}; - -enum cros_ec_lpc_mec_io_type { - MEC_IO_READ, - MEC_IO_WRITE, -}; - -/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */ -#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0 -#define MEC_EMI_RANGE_END (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE) - -/* EMI registers are relative to base */ -#define MEC_EMI_BASE 0x800 -#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0) -#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1) -#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2) -#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3) -#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4) -#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5) -#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6) -#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7) - -/* - * cros_ec_lpc_mec_init - * - * Initialize MEC I/O. - */ -void cros_ec_lpc_mec_init(void); - -/* - * cros_ec_lpc_mec_destroy - * - * Cleanup MEC I/O. - */ -void cros_ec_lpc_mec_destroy(void); - -/** - * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port - * - * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request - * @offset: Base read / write address - * @length: Number of bytes to read / write - * @buf: Destination / source buffer - * - * @return 8-bit checksum of all bytes read / written - */ -u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type, - unsigned int offset, unsigned int length, u8 *buf); - -#endif /* __LINUX_MFD_CROS_EC_MEC_H */ diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h deleted file mode 100644 index 5560bef63c2b..000000000000 --- a/include/linux/mfd/cros_ec_lpc_reg.h +++ /dev/null @@ -1,61 +0,0 @@ -/* - * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller - * - * Copyright (C) 2016 Google, Inc - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver uses the Chrome OS EC byte-level message-based protocol for - * communicating the keyboard state (which keys are pressed) from a keyboard EC - * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, - * but everything else (including deghosting) is done here. The main - * motivation for this is to keep the EC firmware as simple as possible, since - * it cannot be easily upgraded and EC flash/IRAM space is relatively - * expensive. - */ - -#ifndef __LINUX_MFD_CROS_EC_REG_H -#define __LINUX_MFD_CROS_EC_REG_H - -/** - * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address. - * Returns 8-bit checksum of all bytes read. - * - * @offset: Base read address - * @length: Number of bytes to read - * @dest: Destination buffer - */ -u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest); - -/** - * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address. - * Returns 8-bit checksum of all bytes written. - * - * @offset: Base write address - * @length: Number of bytes to write - * @msg: Write data buffer - */ -u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg); - -/** - * cros_ec_lpc_reg_init - * - * Initialize register I/O. - */ -void cros_ec_lpc_reg_init(void); - -/** - * cros_ec_lpc_reg_destroy - * - * Cleanup reg I/O. - */ -void cros_ec_lpc_reg_destroy(void); - -#endif /* __LINUX_MFD_CROS_EC_REG_H */ -- cgit v1.2.3 From e2bbf91cad09118d7500f1fdaaa83d7741d30395 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 18 Jul 2018 18:09:56 +0200 Subject: mfd: cros_ec: Fix and improve kerneldoc comments. cros-ec includes inside the MFD subsystem, specially the file cros_ec_commands.h, has been modified several times and it has grown a lot, unfortunately, we didn't have care too much about the documentation. This patch tries to improve the documentation and also fixes all the issues reported by kerneldoc script. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec.h | 214 +++++++++++++------------ include/linux/mfd/cros_ec_commands.h | 295 ++++++++++++++++++++++------------- 2 files changed, 303 insertions(+), 206 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 20949dde35cd..e44e3ec8a9c7 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -36,7 +36,7 @@ * I2C requires 1 additional byte for requests. * I2C requires 2 additional bytes for responses. * SPI requires up to 32 additional bytes for responses. - * */ + */ #define EC_PROTO_VERSION_UNKNOWN 0 #define EC_MAX_REQUEST_OVERHEAD 1 #define EC_MAX_RESPONSE_OVERHEAD 32 @@ -58,13 +58,14 @@ enum { EC_MAX_MSG_BYTES = 64 * 1024, }; -/* - * @version: Command version number (often 0) - * @command: Command to send (EC_CMD_...) - * @outsize: Outgoing length in bytes - * @insize: Max number of bytes to accept from EC - * @result: EC's response to the command (separate from communication failure) - * @data: Where to put the incoming data from EC and outgoing data to EC +/** + * struct cros_ec_command - Information about a ChromeOS EC command. + * @version: Command version number (often 0). + * @command: Command to send (EC_CMD_...). + * @outsize: Outgoing length in bytes. + * @insize: Max number of bytes to accept from the EC. + * @result: EC's response to the command (separate from communication failure). + * @data: Where to put the incoming data from EC and outgoing data to EC. */ struct cros_ec_command { uint32_t version; @@ -76,48 +77,55 @@ struct cros_ec_command { }; /** - * struct cros_ec_device - Information about a ChromeOS EC device - * - * @phys_name: name of physical comms layer (e.g. 'i2c-4') + * struct cros_ec_device - Information about a ChromeOS EC device. + * @phys_name: Name of physical comms layer (e.g. 'i2c-4'). * @dev: Device pointer for physical comms device - * @was_wake_device: true if this device was set to wake the system from - * sleep at the last suspend - * @cmd_readmem: direct read of the EC memory-mapped region, if supported - * @offset is within EC_LPC_ADDR_MEMMAP region. - * @bytes: number of bytes to read. zero means "read a string" (including - * the trailing '\0'). At most only EC_MEMMAP_SIZE bytes can be read. - * Caller must ensure that the buffer is large enough for the result when - * reading a string. - * - * @priv: Private data - * @irq: Interrupt to use - * @id: Device id - * @din: input buffer (for data from EC) - * @dout: output buffer (for data to EC) - * \note - * These two buffers will always be dword-aligned and include enough - * space for up to 7 word-alignment bytes also, so we can ensure that - * the body of the message is always dword-aligned (64-bit). - * We use this alignment to keep ARM and x86 happy. Probably word - * alignment would be OK, there might be a small performance advantage - * to using dword. - * @din_size: size of din buffer to allocate (zero to use static din) - * @dout_size: size of dout buffer to allocate (zero to use static dout) - * @wake_enabled: true if this device can wake the system from sleep - * @suspended: true if this device had been suspended - * @cmd_xfer: send command to EC and get response - * Returns the number of bytes received if the communication succeeded, but - * that doesn't mean the EC was happy with the command. The caller - * should check msg.result for the EC's result code. - * @pkt_xfer: send packet to EC and get response - * @lock: one transaction at a time - * @mkbp_event_supported: true if this EC supports the MKBP event protocol. - * @event_notifier: interrupt event notifier for transport devices. - * @event_data: raw payload transferred with the MKBP event. - * @event_size: size in bytes of the event data. + * @was_wake_device: True if this device was set to wake the system from + * sleep at the last suspend. + * @cros_class: The class structure for this device. + * @cmd_readmem: Direct read of the EC memory-mapped region, if supported. + * @offset: Is within EC_LPC_ADDR_MEMMAP region. + * @bytes: Number of bytes to read. zero means "read a string" (including + * the trailing '\0'). At most only EC_MEMMAP_SIZE bytes can be + * read. Caller must ensure that the buffer is large enough for the + * result when reading a string. + * @max_request: Max size of message requested. + * @max_response: Max size of message response. + * @max_passthru: Max sice of passthru message. + * @proto_version: The protocol version used for this device. + * @priv: Private data. + * @irq: Interrupt to use. + * @id: Device id. + * @din: Input buffer (for data from EC). This buffer will always be + * dword-aligned and include enough space for up to 7 word-alignment + * bytes also, so we can ensure that the body of the message is always + * dword-aligned (64-bit). We use this alignment to keep ARM and x86 + * happy. Probably word alignment would be OK, there might be a small + * performance advantage to using dword. + * @dout: Output buffer (for data to EC). This buffer will always be + * dword-aligned and include enough space for up to 7 word-alignment + * bytes also, so we can ensure that the body of the message is always + * dword-aligned (64-bit). We use this alignment to keep ARM and x86 + * happy. Probably word alignment would be OK, there might be a small + * performance advantage to using dword. + * @din_size: Size of din buffer to allocate (zero to use static din). + * @dout_size: Size of dout buffer to allocate (zero to use static dout). + * @wake_enabled: True if this device can wake the system from sleep. + * @suspended: True if this device had been suspended. + * @cmd_xfer: Send command to EC and get response. + * Returns the number of bytes received if the communication + * succeeded, but that doesn't mean the EC was happy with the + * command. The caller should check msg.result for the EC's result + * code. + * @pkt_xfer: Send packet to EC and get response. + * @lock: One transaction at a time. + * @mkbp_event_supported: True if this EC supports the MKBP event protocol. + * @event_notifier: Interrupt event notifier for transport devices. + * @event_data: Raw payload transferred with the MKBP event. + * @event_size: Size in bytes of the event data. + * @host_event_wake_mask: Mask of host events that cause wake from suspend. */ struct cros_ec_device { - /* These are used by other drivers that want to talk to the EC */ const char *phys_name; struct device *dev; @@ -153,20 +161,19 @@ struct cros_ec_device { }; /** - * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information - * + * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information. * @sensor_num: Id of the sensor, as reported by the EC. */ struct cros_ec_sensor_platform { u8 sensor_num; }; -/* struct cros_ec_platform - ChromeOS EC platform information - * - * @ec_name: name of EC device (e.g. 'cros-ec', 'cros-pd', ...) - * used in /dev/ and sysfs. - * @cmd_offset: offset to apply for each command. Set when - * registering a devicde behind another one. +/** + * struct cros_ec_platform - ChromeOS EC platform information. + * @ec_name: Name of EC device (e.g. 'cros-ec', 'cros-pd', ...) + * used in /dev/ and sysfs. + * @cmd_offset: Offset to apply for each command. Set when + * registering a device behind another one. */ struct cros_ec_platform { const char *ec_name; @@ -175,16 +182,16 @@ struct cros_ec_platform { struct cros_ec_debugfs; -/* - * struct cros_ec_dev - ChromeOS EC device entry point - * - * @class_dev: Device structure used in sysfs - * @cdev: Character device structure in /dev - * @ec_dev: cros_ec_device structure to talk to the physical device - * @dev: pointer to the platform device - * @debug_info: cros_ec_debugfs structure for debugging information - * @has_kb_wake_angle: true if at least 2 accelerometer are connected to the EC. - * @cmd_offset: offset to apply for each command. +/** + * struct cros_ec_dev - ChromeOS EC device entry point. + * @class_dev: Device structure used in sysfs. + * @cdev: Character device structure in /dev. + * @ec_dev: cros_ec_device structure to talk to the physical device. + * @dev: Pointer to the platform device. + * @debug_info: cros_ec_debugfs structure for debugging information. + * @has_kb_wake_angle: True if at least 2 accelerometer are connected to the EC. + * @cmd_offset: Offset to apply for each command. + * @features: Features supported by the EC. */ struct cros_ec_dev { struct device class_dev; @@ -200,124 +207,129 @@ struct cros_ec_dev { #define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) /** - * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device + * cros_ec_suspend() - Handle a suspend operation for the ChromeOS EC device. + * @ec_dev: Device to suspend. * * This can be called by drivers to handle a suspend event. * - * ec_dev: Device to suspend - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_suspend(struct cros_ec_device *ec_dev); /** - * cros_ec_resume - Handle a resume operation for the ChromeOS EC device + * cros_ec_resume() - Handle a resume operation for the ChromeOS EC device. + * @ec_dev: Device to resume. * * This can be called by drivers to handle a resume event. * - * @ec_dev: Device to resume - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_resume(struct cros_ec_device *ec_dev); /** - * cros_ec_prepare_tx - Prepare an outgoing message in the output buffer + * cros_ec_prepare_tx() - Prepare an outgoing message in the output buffer. + * @ec_dev: Device to register. + * @msg: Message to write. * * This is intended to be used by all ChromeOS EC drivers, but at present * only SPI uses it. Once LPC uses the same protocol it can start using it. * I2C could use it now, with a refactor of the existing code. * - * @ec_dev: Device to register - * @msg: Message to write + * Return: 0 on success or negative error code. */ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_check_result - Check ec_msg->result + * cros_ec_check_result() - Check ec_msg->result. + * @ec_dev: EC device. + * @msg: Message to check. * * This is used by ChromeOS EC drivers to check the ec_msg->result for * errors and to warn about them. * - * @ec_dev: EC device - * @msg: Message to check + * Return: 0 on success or negative error code. */ int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_cmd_xfer - Send a command to the ChromeOS EC + * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. * * Call this to send a command to the ChromeOS EC. This should be used * instead of calling the EC's cmd_xfer() callback directly. * - * @ec_dev: EC device - * @msg: Message to write + * Return: 0 on success or negative error code. */ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_cmd_xfer_status - Send a command to the ChromeOS EC + * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. * * This function is identical to cros_ec_cmd_xfer, except it returns success * status only if both the command was transmitted successfully and the EC * replied with success status. It's not necessary to check msg->result when * using this function. * - * @ec_dev: EC device - * @msg: Message to write - * @return: Num. of bytes transferred on success, <0 on failure + * Return: The number of bytes transferred on success or negative error code. */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_remove - Remove a ChromeOS EC + * cros_ec_remove() - Remove a ChromeOS EC. + * @ec_dev: Device to register. * * Call this to deregister a ChromeOS EC, then clean up any private data. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_remove(struct cros_ec_device *ec_dev); /** - * cros_ec_register - Register a new ChromeOS EC, using the provided info + * cros_ec_register() - Register a new ChromeOS EC, using the provided info. + * @ec_dev: Device to register. * * Before calling this, allocate a pointer to a new device and then fill * in all the fields up to the --private-- marker. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_register(struct cros_ec_device *ec_dev); /** - * cros_ec_query_all - Query the protocol version supported by the ChromeOS EC + * cros_ec_query_all() - Query the protocol version supported by the + * ChromeOS EC. + * @ec_dev: Device to register. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_query_all(struct cros_ec_device *ec_dev); /** - * cros_ec_get_next_event - Fetch next event from the ChromeOS EC - * - * @ec_dev: Device to fetch event from + * cros_ec_get_next_event() - Fetch next event from the ChromeOS EC. + * @ec_dev: Device to fetch event from. * @wake_event: Pointer to a bool set to true upon return if the event might be * treated as a wake event. Ignored if null. * - * Returns: 0 on success, Linux error number on failure + * Return: 0 on success or negative error code. */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); /** - * cros_ec_get_host_event - Return a mask of event set by the EC. + * cros_ec_get_host_event() - Return a mask of event set by the ChromeOS EC. + * @ec_dev: Device to fetch event from. * - * When MKBP is supported, when the EC raises an interrupt, - * We collect the events raised and call the functions in the ec notifier. + * When MKBP is supported, when the EC raises an interrupt, we collect the + * events raised and call the functions in the ec notifier. This function + * is a helper to know which events are raised. * - * This function is a helper to know which events are raised. + * Return: 0 on success or negative error code. */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..88100bddf1ab 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -306,15 +306,18 @@ enum host_event_code { /* Host event mask */ #define EC_HOST_EVENT_MASK(event_code) (1UL << ((event_code) - 1)) -/* Arguments at EC_LPC_ADDR_HOST_ARGS */ +/** + * struct ec_lpc_host_args - Arguments at EC_LPC_ADDR_HOST_ARGS + * @flags: The host argument flags. + * @command_version: Command version. + * @data_size: The length of data. + * @checksum: Checksum; sum of command + flags + command_version + data_size + + * all params/response data bytes. + */ struct ec_lpc_host_args { uint8_t flags; uint8_t command_version; uint8_t data_size; - /* - * Checksum; sum of command + flags + command_version + data_size + - * all params/response data bytes. - */ uint8_t checksum; } __packed; @@ -468,54 +471,43 @@ struct ec_lpc_host_args { #define EC_HOST_REQUEST_VERSION 3 -/* Version 3 request from host */ +/** + * struct ec_host_request - Version 3 request from host. + * @struct_version: Should be 3. The EC will return EC_RES_INVALID_HEADER if it + * receives a header with a version it doesn't know how to + * parse. + * @checksum: Checksum of request and data; sum of all bytes including checksum + * should total to 0. + * @command: Command to send (EC_CMD_...) + * @command_version: Command version. + * @reserved: Unused byte in current protocol version; set to 0. + * @data_len: Length of data which follows this header. + */ struct ec_host_request { - /* Struct version (=3) - * - * EC will return EC_RES_INVALID_HEADER if it receives a header with a - * version it doesn't know how to parse. - */ uint8_t struct_version; - - /* - * Checksum of request and data; sum of all bytes including checksum - * should total to 0. - */ uint8_t checksum; - - /* Command code */ uint16_t command; - - /* Command version */ uint8_t command_version; - - /* Unused byte in current protocol version; set to 0 */ uint8_t reserved; - - /* Length of data which follows this header */ uint16_t data_len; } __packed; #define EC_HOST_RESPONSE_VERSION 3 -/* Version 3 response from EC */ +/** + * struct ec_host_response - Version 3 response from EC. + * @struct_version: Struct version (=3). + * @checksum: Checksum of response and data; sum of all bytes including + * checksum should total to 0. + * @result: EC's response to the command (separate from communication failure) + * @data_len: Length of data which follows this header. + * @reserved: Unused bytes in current protocol version; set to 0. + */ struct ec_host_response { - /* Struct version (=3) */ uint8_t struct_version; - - /* - * Checksum of response and data; sum of all bytes including checksum - * should total to 0. - */ uint8_t checksum; - - /* Result code (EC_RES_*) */ uint16_t result; - - /* Length of data which follows this header */ uint16_t data_len; - - /* Unused bytes in current protocol version; set to 0 */ uint16_t reserved; } __packed; @@ -540,6 +532,10 @@ struct ec_host_response { */ #define EC_CMD_PROTO_VERSION 0x00 +/** + * struct ec_response_proto_version - Response to the proto version command. + * @version: The protocol version. + */ struct ec_response_proto_version { uint32_t version; } __packed; @@ -550,12 +546,20 @@ struct ec_response_proto_version { */ #define EC_CMD_HELLO 0x01 +/** + * struct ec_params_hello - Parameters to the hello command. + * @in_data: Pass anything here. + */ struct ec_params_hello { - uint32_t in_data; /* Pass anything here */ + uint32_t in_data; } __packed; +/** + * struct ec_response_hello - Response to the hello command. + * @out_data: Output will be in_data + 0x01020304. + */ struct ec_response_hello { - uint32_t out_data; /* Output will be in_data + 0x01020304 */ + uint32_t out_data; } __packed; /* Get version number */ @@ -567,22 +571,37 @@ enum ec_current_image { EC_IMAGE_RW }; +/** + * struct ec_response_get_version - Response to the get version command. + * @version_string_ro: Null-terminated RO firmware version string. + * @version_string_rw: Null-terminated RW firmware version string. + * @reserved: Unused bytes; was previously RW-B firmware version string. + * @current_image: One of ec_current_image. + */ struct ec_response_get_version { - /* Null-terminated version strings for RO, RW */ char version_string_ro[32]; char version_string_rw[32]; - char reserved[32]; /* Was previously RW-B string */ - uint32_t current_image; /* One of ec_current_image */ + char reserved[32]; + uint32_t current_image; } __packed; /* Read test */ #define EC_CMD_READ_TEST 0x03 +/** + * struct ec_params_read_test - Parameters for the read test command. + * @offset: Starting value for read buffer. + * @size: Size to read in bytes. + */ struct ec_params_read_test { - uint32_t offset; /* Starting value for read buffer */ - uint32_t size; /* Size to read in bytes */ + uint32_t offset; + uint32_t size; } __packed; +/** + * struct ec_response_read_test - Response to the read test command. + * @data: Data returned by the read test command. + */ struct ec_response_read_test { uint32_t data[32]; } __packed; @@ -597,18 +616,27 @@ struct ec_response_read_test { /* Get chip info */ #define EC_CMD_GET_CHIP_INFO 0x05 +/** + * struct ec_response_get_chip_info - Response to the get chip info command. + * @vendor: Null-terminated string for chip vendor. + * @name: Null-terminated string for chip name. + * @revision: Null-terminated string for chip mask version. + */ struct ec_response_get_chip_info { - /* Null-terminated strings */ char vendor[32]; char name[32]; - char revision[32]; /* Mask version */ + char revision[32]; } __packed; /* Get board HW version */ #define EC_CMD_GET_BOARD_VERSION 0x06 +/** + * struct ec_response_board_version - Response to the board version command. + * @board_version: A monotonously incrementing number. + */ struct ec_response_board_version { - uint16_t board_version; /* A monotonously incrementing number. */ + uint16_t board_version; } __packed; /* @@ -621,27 +649,42 @@ struct ec_response_board_version { */ #define EC_CMD_READ_MEMMAP 0x07 +/** + * struct ec_params_read_memmap - Parameters for the read memory map command. + * @offset: Offset in memmap (EC_MEMMAP_*). + * @size: Size to read in bytes. + */ struct ec_params_read_memmap { - uint8_t offset; /* Offset in memmap (EC_MEMMAP_*) */ - uint8_t size; /* Size to read in bytes */ + uint8_t offset; + uint8_t size; } __packed; /* Read versions supported for a command */ #define EC_CMD_GET_CMD_VERSIONS 0x08 +/** + * struct ec_params_get_cmd_versions - Parameters for the get command versions. + * @cmd: Command to check. + */ struct ec_params_get_cmd_versions { - uint8_t cmd; /* Command to check */ + uint8_t cmd; } __packed; +/** + * struct ec_params_get_cmd_versions_v1 - Parameters for the get command + * versions (v1) + * @cmd: Command to check. + */ struct ec_params_get_cmd_versions_v1 { - uint16_t cmd; /* Command to check */ + uint16_t cmd; } __packed; +/** + * struct ec_response_get_cmd_version - Response to the get command versions. + * @version_mask: Mask of supported versions; use EC_VER_MASK() to compare with + * a desired version. + */ struct ec_response_get_cmd_versions { - /* - * Mask of supported versions; use EC_VER_MASK() to compare with a - * desired version. - */ uint32_t version_mask; } __packed; @@ -659,6 +702,11 @@ enum ec_comms_status { EC_COMMS_STATUS_PROCESSING = 1 << 0, /* Processing cmd */ }; +/** + * struct ec_response_get_comms_status - Response to the get comms status + * command. + * @flags: Mask of enum ec_comms_status. + */ struct ec_response_get_comms_status { uint32_t flags; /* Mask of enum ec_comms_status */ } __packed; @@ -685,19 +733,19 @@ struct ec_response_test_protocol { /* EC_RES_IN_PROGRESS may be returned if a command is slow */ #define EC_PROTOCOL_INFO_IN_PROGRESS_SUPPORTED (1 << 0) +/** + * struct ec_response_get_protocol_info - Response to the get protocol info. + * @protocol_versions: Bitmask of protocol versions supported (1 << n means + * version n). + * @max_request_packet_size: Maximum request packet size in bytes. + * @max_response_packet_size: Maximum response packet size in bytes. + * @flags: see EC_PROTOCOL_INFO_* + */ struct ec_response_get_protocol_info { /* Fields which exist if at least protocol version 3 supported */ - - /* Bitmask of protocol versions supported (1 << n means version n)*/ uint32_t protocol_versions; - - /* Maximum request packet size, in bytes */ uint16_t max_request_packet_size; - - /* Maximum response packet size, in bytes */ uint16_t max_response_packet_size; - - /* Flags; see EC_PROTOCOL_INFO_* */ uint32_t flags; } __packed; @@ -708,8 +756,10 @@ struct ec_response_get_protocol_info { /* The upper byte of .flags tells what to do (nothing means "get") */ #define EC_GSV_SET 0x80000000 -/* The lower three bytes of .flags identifies the parameter, if that has - meaning for an individual command. */ +/* + * The lower three bytes of .flags identifies the parameter, if that has + * meaning for an individual command. + */ #define EC_GSV_PARAM_MASK 0x00ffffff struct ec_params_get_set_value { @@ -810,6 +860,7 @@ enum ec_feature_code { #define EC_FEATURE_MASK_0(event_code) (1UL << (event_code % 32)) #define EC_FEATURE_MASK_1(event_code) (1UL << (event_code - 32)) + struct ec_response_get_features { uint32_t flags[2]; } __packed; @@ -820,24 +871,22 @@ struct ec_response_get_features { /* Get flash info */ #define EC_CMD_FLASH_INFO 0x10 -/* Version 0 returns these fields */ +/** + * struct ec_response_flash_info - Response to the flash info command. + * @flash_size: Usable flash size in bytes. + * @write_block_size: Write block size. Write offset and size must be a + * multiple of this. + * @erase_block_size: Erase block size. Erase offset and size must be a + * multiple of this. + * @protect_block_size: Protection block size. Protection offset and size + * must be a multiple of this. + * + * Version 0 returns these fields. + */ struct ec_response_flash_info { - /* Usable flash size, in bytes */ uint32_t flash_size; - /* - * Write block size. Write offset and size must be a multiple - * of this. - */ uint32_t write_block_size; - /* - * Erase block size. Erase offset and size must be a multiple - * of this. - */ uint32_t erase_block_size; - /* - * Protection block size. Protection offset and size must be a - * multiple of this. - */ uint32_t protect_block_size; } __packed; @@ -845,7 +894,22 @@ struct ec_response_flash_info { /* EC flash erases bits to 0 instead of 1 */ #define EC_FLASH_INFO_ERASE_TO_0 (1 << 0) -/* +/** + * struct ec_response_flash_info_1 - Response to the flash info v1 command. + * @flash_size: Usable flash size in bytes. + * @write_block_size: Write block size. Write offset and size must be a + * multiple of this. + * @erase_block_size: Erase block size. Erase offset and size must be a + * multiple of this. + * @protect_block_size: Protection block size. Protection offset and size + * must be a multiple of this. + * @write_ideal_size: Ideal write size in bytes. Writes will be fastest if + * size is exactly this and offset is a multiple of this. + * For example, an EC may have a write buffer which can do + * half-page operations if data is aligned, and a slower + * word-at-a-time write mode. + * @flags: Flags; see EC_FLASH_INFO_* + * * Version 1 returns the same initial fields as version 0, with additional * fields following. * @@ -860,15 +924,7 @@ struct ec_response_flash_info_1 { uint32_t protect_block_size; /* Version 1 adds these fields: */ - /* - * Ideal write size in bytes. Writes will be fastest if size is - * exactly this and offset is a multiple of this. For example, an EC - * may have a write buffer which can do half-page operations if data is - * aligned, and a slower word-at-a-time write mode. - */ uint32_t write_ideal_size; - - /* Flags; see EC_FLASH_INFO_* */ uint32_t flags; } __packed; @@ -879,9 +935,14 @@ struct ec_response_flash_info_1 { */ #define EC_CMD_FLASH_READ 0x11 +/** + * struct ec_params_flash_read - Parameters for the flash read command. + * @offset: Byte offset to read. + * @size: Size to read in bytes. + */ struct ec_params_flash_read { - uint32_t offset; /* Byte offset to read */ - uint32_t size; /* Size to read in bytes */ + uint32_t offset; + uint32_t size; } __packed; /* Write flash */ @@ -891,18 +952,28 @@ struct ec_params_flash_read { /* Version 0 of the flash command supported only 64 bytes of data */ #define EC_FLASH_WRITE_VER0_SIZE 64 +/** + * struct ec_params_flash_write - Parameters for the flash write command. + * @offset: Byte offset to write. + * @size: Size to write in bytes. + */ struct ec_params_flash_write { - uint32_t offset; /* Byte offset to write */ - uint32_t size; /* Size to write in bytes */ + uint32_t offset; + uint32_t size; /* Followed by data to write */ } __packed; /* Erase flash */ #define EC_CMD_FLASH_ERASE 0x13 +/** + * struct ec_params_flash_erase - Parameters for the flash erase command. + * @offset: Byte offset to erase. + * @size: Size to erase in bytes. + */ struct ec_params_flash_erase { - uint32_t offset; /* Byte offset to erase */ - uint32_t size; /* Size to erase in bytes */ + uint32_t offset; + uint32_t size; } __packed; /* @@ -941,21 +1012,28 @@ struct ec_params_flash_erase { /* Entile flash code protected when the EC boots */ #define EC_FLASH_PROTECT_ALL_AT_BOOT (1 << 6) +/** + * struct ec_params_flash_protect - Parameters for the flash protect command. + * @mask: Bits in flags to apply. + * @flags: New flags to apply. + */ struct ec_params_flash_protect { - uint32_t mask; /* Bits in flags to apply */ - uint32_t flags; /* New flags to apply */ + uint32_t mask; + uint32_t flags; } __packed; +/** + * struct ec_response_flash_protect - Response to the flash protect command. + * @flags: Current value of flash protect flags. + * @valid_flags: Flags which are valid on this platform. This allows the + * caller to distinguish between flags which aren't set vs. flags + * which can't be set on this platform. + * @writable_flags: Flags which can be changed given the current protection + * state. + */ struct ec_response_flash_protect { - /* Current value of flash protect flags */ uint32_t flags; - /* - * Flags which are valid on this platform. This allows the caller - * to distinguish between flags which aren't set vs. flags which can't - * be set on this platform. - */ uint32_t valid_flags; - /* Flags which can be changed given the current protection state */ uint32_t writable_flags; } __packed; @@ -982,8 +1060,13 @@ enum ec_flash_region { EC_FLASH_REGION_COUNT, }; +/** + * struct ec_params_flash_region_info - Parameters for the flash region info + * command. + * @region: Flash region; see EC_FLASH_REGION_* + */ struct ec_params_flash_region_info { - uint32_t region; /* enum ec_flash_region */ + uint32_t region; } __packed; struct ec_response_flash_region_info { @@ -1094,7 +1177,9 @@ struct rgb_s { }; #define LB_BATTERY_LEVELS 4 -/* List of tweakable parameters. NOTE: It's __packed so it can be sent in a + +/* + * List of tweakable parameters. NOTE: It's __packed so it can be sent in a * host command, but the alignment is the same regardless. Keep it that way. */ struct lightbar_params_v0 { -- cgit v1.2.3 From 1c96a2f67cd9b617b013f0a7580d76aae7dcd0d7 Mon Sep 17 00:00:00 2001 From: David Frey Date: Sat, 1 Sep 2018 09:50:41 -0700 Subject: regmap: split up regmap_config.use_single_rw Split regmap_config.use_single_rw into use_single_read and use_single_write. This change enables drivers of devices which only support bulk operations in one direction to use the regmap_bulk_*() functions for both directions and have their bulk operation split into single operations only when necessary. Update all struct regmap_config instances where use_single_rw==true to instead set both use_single_read and use_single_write. No attempt was made to evaluate whether it is possible to set only one of use_single_read or use_single_write. Signed-off-by: David Frey Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 379505a53722..6ea9bf9377cb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -315,9 +315,12 @@ typedef void (*regmap_unlock)(void *); * masks are used. * @zero_flag_mask: If set, read_flag_mask and write_flag_mask are used even * if they are both empty. - * @use_single_rw: If set, converts the bulk read and write operations into - * a series of single read and write operations. This is useful - * for device that does not support bulk read and write. + * @use_single_read: If set, converts the bulk read operation into a series of + * single read operations. This is useful for a device that + * does not support bulk read. + * @use_single_write: If set, converts the bulk write operation into a series of + * single write operations. This is useful for a device that + * does not support bulk write. * @can_multi_write: If set, the device supports the multi write mode of bulk * write operations, if clear multi write requests will be * split into individual write operations @@ -380,7 +383,8 @@ struct regmap_config { unsigned long write_flag_mask; bool zero_flag_mask; - bool use_single_rw; + bool use_single_read; + bool use_single_write; bool can_multi_write; enum regmap_endian reg_format_endian; -- cgit v1.2.3 From 00b7d1cf46676ad5e6338e80dc6230e1b6e71b86 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Aug 2018 17:21:45 -0500 Subject: of: make default address and size cells sizes private Only some old OpenFirmware implementations rely on default sizes. Any FDT and modern implementation should have explicit properties. Make the OF_ROOT_NODE_*_CELLS_DEFAULT defines private so we don't get any outside users. This also gets us one step closer to removing the asm/prom.h dependency on Sparc. Cc: "David S. Miller" Cc: Frank Rowand Cc: sparclinux@vger.kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..2141490b368f 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -247,12 +247,6 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #include #endif -/* Default #address and #size cells. Allow arch asm/prom.h to override */ -#if !defined(OF_ROOT_NODE_ADDR_CELLS_DEFAULT) -#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 1 -#define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 -#endif - #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) -- cgit v1.2.3 From ccf640f4c9988653ef884672381b03b9be247bec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 09:40:24 +0200 Subject: dma-mapping: remove dma_configure There is no good reason for this indirection given that the method always exists. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-mapping.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1db6a6b46d0d..1c6c7c09bcf2 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -754,14 +754,8 @@ dma_mark_declared_memory_occupied(struct device *dev, #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ #ifdef CONFIG_HAS_DMA -int dma_configure(struct device *dev); void dma_deconfigure(struct device *dev); #else -static inline int dma_configure(struct device *dev) -{ - return 0; -} - static inline void dma_deconfigure(struct device *dev) {} #endif -- cgit v1.2.3 From dc3c05504d38849f77149cb962caeaedd1efa127 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 10:28:18 +0200 Subject: dma-mapping: remove dma_deconfigure This goes through a lot of hooks just to call arch_teardown_dma_ops. Replace it with a direct call instead. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/acpi.h | 2 -- include/linux/dma-mapping.h | 6 ------ include/linux/of_device.h | 3 --- 3 files changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index de8d3d3fa651..af4628979d13 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -831,8 +831,6 @@ static inline int acpi_dma_configure(struct device *dev, return 0; } -static inline void acpi_dma_deconfigure(struct device *dev) { } - #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1c6c7c09bcf2..1423b69f3cc9 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -753,12 +753,6 @@ dma_mark_declared_memory_occupied(struct device *dev, } #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */ -#ifdef CONFIG_HAS_DMA -void dma_deconfigure(struct device *dev); -#else -static inline void dma_deconfigure(struct device *dev) {} -#endif - /* * Managed DMA API */ diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 165fd302b442..8d31e39dd564 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -58,7 +58,6 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma); -void of_dma_deconfigure(struct device *dev); #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -113,8 +112,6 @@ static inline int of_dma_configure(struct device *dev, { return 0; } -static inline void of_dma_deconfigure(struct device *dev) -{} #endif /* CONFIG_OF */ #endif /* _LINUX_OF_DEVICE_H */ -- cgit v1.2.3 From 46053c73685411915d3de50c5a0045beef32806b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Aug 2018 10:29:02 +0200 Subject: dma-mapping: clear dev->dma_ops in arch_teardown_dma_ops There is no reason to leave the per-device dma_ops around when deconfiguring a device, so move this code from arm64 into the common code. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-mapping.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 1423b69f3cc9..eafd6f318e78 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -664,7 +664,10 @@ static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, #endif #ifndef arch_teardown_dma_ops -static inline void arch_teardown_dma_ops(struct device *dev) { } +static inline void arch_teardown_dma_ops(struct device *dev) +{ + dev->dma_ops = NULL; +} #endif static inline unsigned int dma_get_max_seg_size(struct device *dev) -- cgit v1.2.3 From 02ad0437decf2e5dba975c23b1a89775f4b211e1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Sep 2018 12:55:30 -0700 Subject: gpio: fix kernel-doc notation warning for 'request_key' Fix kernel-doc warning for missing struct member 'request_key': ../include/linux/gpio/driver.h:142: warning: Function parameter or member 'request_key' not described in 'gpio_irq_chip' Fixes: 39c3fd58952d ("kernel/irq: Extend lockdep class for request mutex") Signed-off-by: Randy Dunlap Cc: Andrew Lunn Cc: Thomas Gleixner Cc: Linus Walleij Cc: linux-gpio@vger.kernel.org Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 0ea328e71ec9..4a4f410b5285 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -66,9 +66,15 @@ struct gpio_irq_chip { /** * @lock_key: * - * Per GPIO IRQ chip lockdep classes. + * Per GPIO IRQ chip lockdep class for IRQ lock. */ struct lock_class_key *lock_key; + + /** + * @request_key: + * + * Per GPIO IRQ chip lockdep class for IRQ request. + */ struct lock_class_key *request_key; /** -- cgit v1.2.3 From 4e6b823867e2b8afc2b33740ba930e50b1f92421 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 8 Sep 2018 11:23:14 +0200 Subject: gpiolib: export gpiochip_irq_reqres/relres() GPIO drivers that do not use GPIOLIB_IRQCHIP can hook these into the irq_request_resource and irq_release_resource callbacks of the irq_chip so they correctly 'get' the module and lock the gpio line for IRQ use. This will simplify driver code. Signed-off-by: Hans Verkuil Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 4a4f410b5285..479f1ccaaebd 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -401,6 +401,8 @@ extern struct gpio_chip *gpiochip_find(void *data, int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset); void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); +int gpiochip_reqres_irq(struct gpio_chip *chip, unsigned int offset); +void gpiochip_relres_irq(struct gpio_chip *chip, unsigned int offset); /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *chip, unsigned int offset); -- cgit v1.2.3 From 4e9439ddacea06f35acce4d374bf6bd0acf99bc8 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 8 Sep 2018 11:23:16 +0200 Subject: gpiolib: add flag to indicate if the irq is disabled GPIO drivers call gpiochip_(un)lock_as_irq whenever they want to use a gpio as an interrupt. This is done when the irq is requested and it marks the gpio as in use by an interrupt. This is problematic for cases where a gpio pin is used as an interrupt pin, then, after the irq is disabled, is used as a regular gpio pin. Currently it is not possible to do this other than by first freeing the interrupt so gpiochip_unlock_as_irq is called, since an attempt to switch the gpio direction for output will fail since gpiolib believes that the gpio is in use for an interrupt and it does not know that it the irq is actually disabled. There are currently two drivers that would like to be able to do this: the tda998x_drv.c driver where a regular gpio pin needs to be temporarily reconfigured as an interrupt pin during CEC calibration, and the cec-gpio driver where you want to configure the gpio pin as an interrupt while waiting for traffic over the CEC bus, or as a regular pin when receiving or transmitting a CEC message. The solution is to add a new flag that is set when the irq is enabled, and have gpiod_direction_output check for that flag. We also add functions that drivers that do not use GPIOLIB_IRQCHIP can call when they enable/disable the irq. Signed-off-by: Hans Verkuil Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 479f1ccaaebd..9052ccd399fd 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -403,6 +403,8 @@ void gpiochip_unlock_as_irq(struct gpio_chip *chip, unsigned int offset); bool gpiochip_line_is_irq(struct gpio_chip *chip, unsigned int offset); int gpiochip_reqres_irq(struct gpio_chip *chip, unsigned int offset); void gpiochip_relres_irq(struct gpio_chip *chip, unsigned int offset); +void gpiochip_disable_irq(struct gpio_chip *chip, unsigned int offset); +void gpiochip_enable_irq(struct gpio_chip *chip, unsigned int offset); /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *chip, unsigned int offset); -- cgit v1.2.3 From 461c1a7d4733d1dfd5c47b040cf32a5e7eefbc6c Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 8 Sep 2018 11:23:17 +0200 Subject: gpiolib: override irq_enable/disable When using the gpiolib irqchip helpers install irq_enable/disable hooks for the irqchip to ensure that gpiolib knows when the irq is enabled or disabled, allowing drivers to disable the irq and then use it as an output pin, and later switch the direction to input and re-enable the irq. Signed-off-by: Hans Verkuil Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 9052ccd399fd..d8dcd0e44cab 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -144,6 +144,20 @@ struct gpio_irq_chip { * will allocate and map all IRQs during initialization. */ unsigned int first; + + /** + * @irq_enable: + * + * Store old irq_chip irq_enable callback + */ + void (*irq_enable)(struct irq_data *data); + + /** + * @irq_disable: + * + * Store old irq_chip irq_disable callback + */ + void (*irq_disable)(struct irq_data *data); }; static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *chip) -- cgit v1.2.3 From 05484e0984487d42e97c417cbb0697fa9d16e7e9 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Fri, 20 Jul 2018 14:32:31 +0100 Subject: sched/topology: Add SD_ASYM_CPUCAPACITY flag detection The SD_ASYM_CPUCAPACITY sched_domain flag is supposed to mark the sched_domain in the hierarchy where all CPU capacities are visible for any CPU's point of view on asymmetric CPU capacity systems. The scheduler can then take to take capacity asymmetry into account when balancing at this level. It also serves as an indicator for how wide task placement heuristics have to search to consider all available CPU capacities as asymmetric systems might often appear symmetric at smallest level(s) of the sched_domain hierarchy. The flag has been around for while but so far only been set by out-of-tree code in Android kernels. One solution is to let each architecture provide the flag through a custom sched_domain topology array and associated mask and flag functions. However, SD_ASYM_CPUCAPACITY is special in the sense that it depends on the capacity and presence of all CPUs in the system, i.e. when hotplugging all CPUs out except those with one particular CPU capacity the flag should disappear even if the sched_domains don't collapse. Similarly, the flag is affected by cpusets where load-balancing is turned off. Detecting when the flags should be set therefore depends not only on topology information but also the cpuset configuration and hotplug state. The arch code doesn't have easy access to the cpuset configuration. Instead, this patch implements the flag detection in generic code where cpusets and hotplug state is already taken care of. All the arch is responsible for is to implement arch_scale_cpu_capacity() and force a full rebuild of the sched_domain hierarchy if capacities are updated, e.g. later in the boot process when cpufreq has initialized. Signed-off-by: Morten Rasmussen Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dietmar.eggemann@arm.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1532093554-30504-2-git-send-email-morten.rasmussen@arm.com [ Fixed 'CPU' capitalization. ] Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 26347741ba50..6b9976180c1e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -23,10 +23,10 @@ #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 /* Groups have different max cpu capacities */ -#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */ +#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_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 */ -- cgit v1.2.3 From bb1fbdd3c3fd12b612c7d8cdf13bd6bfeebdefa3 Mon Sep 17 00:00:00 2001 From: Morten Rasmussen Date: Fri, 20 Jul 2018 14:32:32 +0100 Subject: sched/topology, drivers/base/arch_topology: Rebuild the sched_domain hierarchy when capacities change The setting of SD_ASYM_CPUCAPACITY depends on the per-CPU capacities. These might not have their final values when the hierarchy is initially built as the values depend on cpufreq to be initialized or the values being set through sysfs. To ensure that the flags are set correctly we need to rebuild the sched_domain hierarchy whenever the reported per-CPU capacity (arch_scale_cpu_capacity()) changes. This patch ensure that a full sched_domain rebuild happens when CPU capacity changes occur. Signed-off-by: Morten Rasmussen Signed-off-by: Peter Zijlstra (Intel) Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dietmar.eggemann@arm.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1532093554-30504-3-git-send-email-morten.rasmussen@arm.com Signed-off-by: Ingo Molnar --- include/linux/arch_topology.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 2b709416de05..d9bdc1a7f4e7 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -9,6 +9,7 @@ #include void topology_normalize_cpu_scale(void); +int topology_update_cpu_topology(void); struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); -- cgit v1.2.3 From 925b9cd1b89a94b7124d128c80dfc48f78a63098 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 6 Sep 2018 16:18:34 -0400 Subject: locking/rwsem: Make owner store task pointer of last owning reader Currently, when a reader acquires a lock, it only sets the RWSEM_READER_OWNED bit in the owner field. The other bits are simply not used. When debugging hanging cases involving rwsems and readers, the owner value does not provide much useful information at all. This patch modifies the current behavior to always store the task_struct pointer of the last rwsem-acquiring reader in a reader-owned rwsem. This may be useful in debugging rwsem hanging cases especially if only one reader is involved. However, the task in the owner field may not the real owner or one of the real owners at all when the owner value is examined, for example, in a crash dump. So it is just an additional hint about the past history. If CONFIG_DEBUG_RWSEMS=y is enabled, the owner field will be checked at unlock time too to make sure the task pointer value is valid. That does have a slight performance cost and so is only enabled as part of that debug option. From the performance point of view, it is expected that the changes shouldn't have any noticeable performance impact. A rwsem microbenchmark (with 48 worker threads and 1:1 reader/writer ratio) was ran on a 2-socket 24-core 48-thread Haswell system. The locking rates on a 4.19-rc1 based kernel were as follows: 1) Unpatched kernel: 543.3 kops/s 2) Patched kernel: 549.2 kops/s 3) Patched kernel (CONFIG_DEBUG_RWSEMS on): 546.6 kops/s There was actually a slight increase in performance (1.1%) in this particular case. Maybe it was caused by the elimination of a branch or just a testing noise. Turning on the CONFIG_DEBUG_RWSEMS option also had less than the expected impact on performance. The least significant 2 bits of the owner value are now used to designate the rwsem is readers owned and the owners are anonymous. Signed-off-by: Waiman Long Acked-by: Peter Zijlstra Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/1536265114-10842-1-git-send-email-longman@redhat.com Signed-off-by: Ingo Molnar --- include/linux/rwsem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index ab93b6eae696..67dbb57508b1 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -45,10 +45,10 @@ struct rw_semaphore { }; /* - * Setting bit 0 of the owner field with other non-zero bits will indicate + * Setting bit 1 of the owner field but not bit 0 will indicate * that the rwsem is writer-owned with an unknown owner. */ -#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-1L) +#define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-2L) extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); -- cgit v1.2.3 From 719cf71cada1abc4f8727eac918b639a4a502a59 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 20 Aug 2018 16:45:41 +0300 Subject: ACPI / glue: Split dev_is_platform() out of module for wide use There would be useful to have in future the similar API in platform core, as we have, for example, for PCI subsystem, to check if device belongs to it. Thus, split out conditional to a macro dev_is_platform() for wide use. No functional change intended. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/platform_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 1a9f38f27f65..c7c081dc6034 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -40,6 +40,7 @@ struct platform_device { #define platform_get_device_id(pdev) ((pdev)->id_entry) +#define dev_is_platform(dev) ((dev)->bus == &platform_bus_type) #define to_platform_device(x) container_of((x), struct platform_device, dev) extern int platform_device_register(struct platform_device *); -- cgit v1.2.3 From d31ca7e5d0fa066d59540859af32ab6f95adb519 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 30 Aug 2018 14:20:04 +0100 Subject: mfd: madera: Add irqchip data pointer into struct madera Put the pointer to struct regmap_irq_chip_data into the parent mfd structure so that the child irqchip driver does not need a trivial private structure to store only this pointer. As the irqchip child driver already has a pointer to the parent struct madera it can use that to store the pointer. This also means that the irqchip driver does not need a double-indirection from its local struct to get at the parent struct madera. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index c332681848ef..fe69c0f4398f 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -148,6 +148,7 @@ struct snd_soc_dapm_context; * @internal_dcvdd: true if DCVDD is supplied from the internal LDO1 * @pdata: our pdata * @irq_dev: the irqchip child driver device + * @irq_data: pointer to irqchip data for the child irqchip driver * @irq: host irq number from SPI or I2C configuration * @out_clamp: indicates output clamp state for each analogue output * @out_shorted: indicates short circuit state for each analogue output @@ -175,6 +176,7 @@ struct madera { struct madera_pdata pdata; struct device *irq_dev; + struct regmap_irq_chip_data *irq_data; int irq; unsigned int num_micbias; -- cgit v1.2.3 From a318c2432218d3cd189ec8228b8a795666899c2a Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 31 Aug 2018 14:34:02 +0200 Subject: mfd: da9063: Fix DT probing with constraints Commit 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") reordered the da9063_regulator_info[] array, but not the DA9063_ID_* regulator ids and not the da9063_matches[] array, because ids are used as indices in the array initializer. This mismatch between regulator id and da9063_regulator_info[] array index causes the driver probe to fail because constraints from DT are not applied to the correct regulator: da9063 0-0058: Device detected (chip-ID: 0x61, var-ID: 0x50) DA9063_BMEM: Bringing 900000uV into 3300000-3300000uV DA9063_LDO9: Bringing 3300000uV into 2500000-2500000uV DA9063_LDO1: Bringing 900000uV into 3300000-3300000uV DA9063_LDO1: failed to apply 3300000-3300000uV constraint(-22) This patch reorders the DA9063_ID_* as apparently intended, and with them the entries in the da90630_matches[] array. Fixes: 1c892e38ce59 ("regulator: da9063: Handle less LDOs on DA9063L") Signed-off-by: Philipp Zabel Reviewed-by: Marek Vasut Reviewed-by: Geert Uytterhoeven Signed-off-by: Lee Jones --- include/linux/mfd/da9063/pdata.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 8a125701ef7b..50bed4f89c1a 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -21,7 +21,7 @@ /* * Regulator configuration */ -/* DA9063 regulator IDs */ +/* DA9063 and DA9063L regulator IDs */ enum { /* BUCKs */ DA9063_ID_BCORE1, @@ -37,18 +37,20 @@ enum { DA9063_ID_BMEM_BIO_MERGED, /* When two BUCKs are merged, they cannot be reused separately */ - /* LDOs */ + /* LDOs on both DA9063 and DA9063L */ + DA9063_ID_LDO3, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO11, + + /* DA9063-only LDOs */ DA9063_ID_LDO1, DA9063_ID_LDO2, - DA9063_ID_LDO3, DA9063_ID_LDO4, DA9063_ID_LDO5, DA9063_ID_LDO6, - DA9063_ID_LDO7, - DA9063_ID_LDO8, - DA9063_ID_LDO9, DA9063_ID_LDO10, - DA9063_ID_LDO11, }; /* Regulators platform data */ -- cgit v1.2.3 From 1a63fe9a2b1f47af5b2b7436b41824b14999c17a Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 10 Sep 2018 17:28:10 +0100 Subject: firmware: arm_scmi: add a getter for power of performance states The SCMI protocol can be used to get power estimates from firmware corresponding to each performance state of a device. Although these power costs are already managed by the SCMI firmware driver, they are not exposed to any external subsystem yet. Fix this by adding a new get_power() interface to the exisiting perf_ops defined for the SCMI protocol. Signed-off-by: Quentin Perret Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index f4c9fc0fc755..3105055c00a7 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -91,6 +91,8 @@ struct scmi_clk_ops { * to sustained performance level mapping * @freq_get: gets the frequency for a given device using sustained frequency * to sustained performance level mapping + * @est_power_get: gets the estimated power cost for a given performance domain + * at a given frequency */ struct scmi_perf_ops { int (*limits_set)(const struct scmi_handle *handle, u32 domain, @@ -110,6 +112,8 @@ struct scmi_perf_ops { unsigned long rate, bool poll); int (*freq_get)(const struct scmi_handle *handle, u32 domain, unsigned long *rate, bool poll); + int (*est_power_get)(const struct scmi_handle *handle, u32 domain, + unsigned long *rate, unsigned long *power); }; /** -- cgit v1.2.3 From 8b69bd7d8a8927d537f134c37bcca6cbfa58e1b2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 11 Aug 2018 18:43:38 -0700 Subject: ppp: Remove direct skb_queue_head list pointer access. Add a helper, __skb_peek(), and use it in ppp_mp_reconstruct(). Signed-off-by: David S. Miller --- include/linux/skbuff.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17a13e4785fc..89283b77294d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1592,6 +1592,17 @@ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) return skb; } +/** + * __skb_peek - peek at the head of a non-empty &sk_buff_head + * @list_: list to peek at + * + * Like skb_peek(), but the caller knows that the list is not empty. + */ +static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) +{ + return list_->next; +} + /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from -- cgit v1.2.3 From a8305bff685252e80b7c60f4f5e7dd2e63e38218 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 29 Jul 2018 20:42:53 -0700 Subject: net: Add and use skb_mark_not_on_list(). An SKB is not on a list if skb->next is NULL. Codify this convention into a helper function and use it where we are dequeueing an SKB and need to mark it as such. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 89283b77294d..c4c9e3f5cd9a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1339,6 +1339,11 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) } } +static inline void skb_mark_not_on_list(struct sk_buff *skb) +{ + skb->next = NULL; +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head -- cgit v1.2.3 From 992cba7e276d438ac8b0a8c17b147b37c8c286f7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 31 Jul 2018 15:27:56 -0700 Subject: net: Add and use skb_list_del_init(). It documents what is happening, and eliminates the spurious list pointer poisoning. In the long term, in order to get proper list head debugging, we might want to use the list poison value as the indicator that an SKB is a singleton and not on a list. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c4c9e3f5cd9a..e3a53ca4a9b5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1344,6 +1344,12 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb) skb->next = NULL; } +static inline void skb_list_del_init(struct sk_buff *skb) +{ + __list_del_entry(&skb->list); + skb_mark_not_on_list(skb); +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head -- cgit v1.2.3 From 4e69817b106e4fb98f7af463d2f951e7b3603c12 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 6 Aug 2018 02:29:53 +0000 Subject: usb: ehci-sh: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/ehci-sh.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ehci-sh.h b/include/linux/platform_data/ehci-sh.h index 5c15a738e116..219bd79dabfc 100644 --- a/include/linux/platform_data/ehci-sh.h +++ b/include/linux/platform_data/ehci-sh.h @@ -1,21 +1,9 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * EHCI SuperH driver platform data * * Copyright (C) 2012 Nobuhiro Iwamatsu * Copyright (C) 2012 Renesas Solutions Corp. - * - * 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; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __USB_EHCI_SH_H -- cgit v1.2.3 From e7a3ff92eaf19eab14e8149758428e680c61706b Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Sun, 19 Aug 2018 19:27:16 +0200 Subject: dmaengine: fsl-edma: add ColdFire mcf5441x edma support This patch adds support for ColdFire mcf5441x-family edma module. The ColdFire edma module is slightly different from fsl-edma, so a new driver is added. But most of the code is common between fsl-edma and mcf-edma so it has been collected into a separate common module fsl-edma-common (patch 1/3). Signed-off-by: Angelo Dureghello Tested-by: Krzysztof Kozlowski Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-mcf-edma.h | 38 ++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/platform_data/dma-mcf-edma.h (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-mcf-edma.h b/include/linux/platform_data/dma-mcf-edma.h new file mode 100644 index 000000000000..d718ccfa3421 --- /dev/null +++ b/include/linux/platform_data/dma-mcf-edma.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Freescale eDMA platform data, ColdFire SoC's family. + * + * Copyright (c) 2017 Angelo Dureghello + * + * 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 in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_PLATFORM_DATA_MCF_EDMA_H__ +#define __LINUX_PLATFORM_DATA_MCF_EDMA_H__ + +struct dma_slave_map; + +bool mcf_edma_filter_fn(struct dma_chan *chan, void *param); + +#define MCF_EDMA_FILTER_PARAM(ch) ((void *)ch) + +/** + * struct mcf_edma_platform_data - platform specific data for eDMA engine + * + * @ver The eDMA module version. + * @dma_channels The number of eDMA channels. + */ +struct mcf_edma_platform_data { + int dma_channels; + const struct dma_slave_map *slave_map; + int slavecnt; +}; + +#endif /* __LINUX_PLATFORM_DATA_MCF_EDMA_H__ */ -- cgit v1.2.3 From 04cfcc7ab358e331b32cabde1e853a125f3f8735 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:02 +0200 Subject: fbdev: Drop FBINFO_CAN_FORCE_OUTPUT flag This was only added for the drm's fbdev emulation support, so that it would try harder to show the Oops. Unfortunately this never really worked reliably, and in practice ended up pushing the real Oops off the screen due to plentyfull locking, sleep-while-atomic and other issues. So we removed all that support from the fbdev emulation a while back. Aside: We've also removed the kgdb support, for similar reasons. Since it's such a small patch I figured I don't split this up into the usual 3-phase removal. Acked-by: Bartlomiej Zolnierkiewicz Cc: Ben Skeggs Cc: Bartlomiej Zolnierkiewicz Cc: Greg Kroah-Hartman Cc: Hans de Goede Cc: Daniel Vetter Cc: Alexander Kapshuk Cc: Kees Cook Cc: Thierry Reding Cc: David Lechner Cc: nouveau@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-1-daniel.vetter@ffwll.ch --- include/linux/fb.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 3cd375dafd0e..b1db5c5eb671 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -457,10 +457,6 @@ struct fb_tile_ops { */ #define FBINFO_BE_MATH 0x100000 -/* report to the VT layer that this fb driver can accept forced console - output like oopses */ -#define FBINFO_CAN_FORCE_OUTPUT 0x200000 - struct fb_info { atomic_t count; int node; -- cgit v1.2.3 From 8d7fc2994f4d1f431e280c9e21a139c18dc435ec Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:03 +0200 Subject: vt: Remove vc_panic_force_write It was only used by the panic support in fbcon, which is now gone. Remove this now dead code too. Acked-by: Greg Kroah-Hartman Cc: Greg Kroah-Hartman Cc: Kees Cook Cc: Joe Perches Cc: Daniel Vetter Cc: Meng Xu Cc: Nicolas Pitre Cc: Thomas Meyer Cc: Mike Frysinger Cc: Bartlomiej Zolnierkiewicz Cc: Hans de Goede Cc: Thierry Reding Cc: David Lechner Cc: Philippe Ombredanne Cc: Thomas Gleixner Cc: Kate Stewart Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-2-daniel.vetter@ffwll.ch --- include/linux/console_struct.h | 1 - include/linux/vt_kern.h | 7 ------- 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index fea64f2692a0..ab137f97ecbd 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -141,7 +141,6 @@ struct vc_data { struct uni_pagedir *vc_uni_pagedir; struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ struct uni_screen *vc_uni_screen; /* unicode screen content */ - bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */ /* additional information is in vt_kern.h */ }; diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 3fd07912909c..8dc77e40bc03 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -135,13 +135,6 @@ extern int do_unbind_con_driver(const struct consw *csw, int first, int last, int deflt); int vty_init(const struct file_operations *console_fops); -static inline bool vt_force_oops_output(struct vc_data *vc) -{ - if (oops_in_progress && vc->vc_panic_force_write && panic_timeout >= 0) - return true; - return false; -} - extern char vt_dont_switch; extern int default_utf8; extern int global_cursor_default; -- cgit v1.2.3 From da6c7707caf3736c1cf968606bd97c07e79625d4 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:04 +0200 Subject: fbdev: Add FBINFO_HIDE_SMEM_START flag DRM drivers really, really, really don't want random userspace to share buffer behind it's back, bypassing the dma-buf buffer sharing machanism. For that reason we've ruthlessly rejected any IOCTL exposing the physical address of any graphics buffer. Unfortunately fbdev comes with that built-in. We could just set smem_start to 0, but that means we'd have to hand-roll our own fb_mmap implementation. For good reasons many drivers do that, but smem_start/length is still super convenient. Hence instead just stop the leak in the ioctl, to keep fb mmap working as-is. A second patch will set this flag for all drm drivers. Acked-by: Bartlomiej Zolnierkiewicz Cc: Bartlomiej Zolnierkiewicz Cc: Kees Cook Cc: Daniel Vetter Cc: linux-fbdev@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-3-daniel.vetter@ffwll.ch --- include/linux/fb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index b1db5c5eb671..a3cab6dc9b44 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -456,6 +456,13 @@ struct fb_tile_ops { * and host endianness. Drivers should not use this flag. */ #define FBINFO_BE_MATH 0x100000 +/* + * Hide smem_start in the FBIOGET_FSCREENINFO IOCTL. This is used by modern DRM + * drivers to stop userspace from trying to share buffers behind the kernel's + * back. Instead dma-buf based buffer sharing should be used. + */ +#define FBINFO_HIDE_SMEM_START 0x200000 + struct fb_info { atomic_t count; -- cgit v1.2.3 From 56df612afb606dcefba8ab38ab32e052218b6050 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Sep 2018 14:41:28 +0200 Subject: spi: davinci: Remove chip select GPIO pdata The DaVinci SPI can use either: - Internal chip selects (inside the SPI host) - External chip selects (using GPIO) - External chip selects passed in pdata The last way of passing external chip selects through platform data is not used in the kernel. Delete it to make the code simpler when refactoring GPIO. Cc: Sekhar Nori Cc: Kevin Hilman Cc: Michele Dionisio Cc: Frode Isaksen Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/platform_data/spi-davinci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-davinci.h b/include/linux/platform_data/spi-davinci.h index f4edcb03c40c..0638fb6353bc 100644 --- a/include/linux/platform_data/spi-davinci.h +++ b/include/linux/platform_data/spi-davinci.h @@ -36,9 +36,6 @@ enum { * @num_chipselect: number of chipselects supported by this SPI master * @intr_line: interrupt line used to connect the SPI IP to the ARM interrupt * controller withn the SoC. Possible values are 0 and 1. - * @chip_sel: list of GPIOs which can act as chip-selects for the SPI. - * SPI_INTERN_CS denotes internal SPI chip-select. Not necessary - * to populate if all chip-selects are internal. * @cshold_bug: set this to true if the SPI controller on your chip requires * a write to CSHOLD bit in between transfers (like in DM355). * @dma_event_q: DMA event queue to use if SPI_IO_TYPE_DMA is used for any @@ -48,7 +45,6 @@ struct davinci_spi_platform_data { u8 version; u8 num_chipselect; u8 intr_line; - u8 *chip_sel; u8 prescaler_limit; bool cshold_bug; enum dma_event_q dma_event_q; -- cgit v1.2.3 From 01c5f85aebaaddfd7e6051fb2ec80c1d4b463554 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Sep 2018 10:59:53 -0600 Subject: blk-cgroup: increase number of supported policies After merging the iolatency policy, we potentially now have 4 policies being registered, but only support 3. This causes one of them to fail loading. Takashi reports that BFQ no longer works for him, because it fails to load due to policy registration failure. Bump to 5 policies, and also add a warning for when we have exceeded the global amount. If we have to touch this again, we should switch to a dynamic scheme instead. Reported-by: Takashi Iwai Reviewed-by: Jeff Moyer Tested-by: Takashi Iwai 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 d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); -- cgit v1.2.3 From 961366a01904d460066d65a609c3c2e3051c7903 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 19 Jul 2018 21:31:13 -0500 Subject: signal: Remove the siginfo paramater from kernel_dqueue_signal None of the callers use the it so remove it. Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 1be35729c2c5..9b6968cbde14 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -272,14 +272,14 @@ extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); -static inline int kernel_dequeue_signal(siginfo_t *info) +static inline int kernel_dequeue_signal(void) { struct task_struct *tsk = current; siginfo_t __info; int ret; spin_lock_irq(&tsk->sighand->siglock); - ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); + ret = dequeue_signal(tsk, &tsk->blocked, &__info); spin_unlock_irq(&tsk->sighand->siglock); return ret; -- cgit v1.2.3 From 4ff4c31a6e85f4c49fbeebeaa28018d002884b5a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 3 Sep 2018 10:39:04 +0200 Subject: signal: Remove SEND_SIG_FORCED There are no more users of SEND_SIG_FORCED so it may be safely removed. Remove the definition of SEND_SIG_FORCED, it's use in is_si_special, it's use in TP_STORE_SIGINFO, and it's use in __send_signal as without any users the uses of SEND_SIG_FORCED are now unncessary. This makes the code simpler, easier to understand and use. Users of signal sending functions now no longer need to ask themselves do I need to use SEND_SIG_FORCED. Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 9b6968cbde14..9e07f3521549 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -477,7 +477,6 @@ static inline int kill_cad_pid(int sig, int priv) /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct siginfo *) 0) #define SEND_SIG_PRIV ((struct siginfo *) 1) -#define SEND_SIG_FORCED ((struct siginfo *) 2) /* * True if we are on the alternate signal stack. -- cgit v1.2.3 From bfc456060d0cbcf6902a436d358b60cb1534668c Mon Sep 17 00:00:00 2001 From: Dennis Dalessandro Date: Fri, 31 Aug 2018 10:34:14 -0700 Subject: IB/hfi1,PCI: Allow bus reset while probing Calling into the new API to reset the secondary bus results in a deadlock. This occurs because the device/bus is already locked at probe time. Reverting back to the old behavior while the API is improved. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200985 Fixes: c6a44ba950d1 ("PCI: Rename pci_try_reset_bus() to pci_reset_bus()") Fixes: 409888e0966e ("IB/hfi1: Use pci_try_reset_bus() for initiating PCI Secondary Bus Reset") Signed-off-by: Dennis Dalessandro Signed-off-by: Bjorn Helgaas Reviewed-by: Michael J. Ruhl Cc: Sinan Kaya --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..6925828f9f25 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1235,6 +1235,9 @@ void pci_bus_remove_resources(struct pci_bus *bus); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); +/* Temporary until new and working PCI SBR API in place */ +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); + #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ -- cgit v1.2.3 From d765edbb301c0e196015a59b17420558088ea33f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 10 Aug 2018 23:06:08 +0000 Subject: vmbus: add driver_override support Add support for overriding the default driver for a VMBus device in the same way that it can be done for PCI devices. This patch adds the /sys/bus/vmbus/devices/.../driver_override file and the logic for matching. This is used by driverctl tool to do driver override. https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitlab.com%2Fdriverctl%2Fdriverctl&data=02%7C01%7Ckys%40microsoft.com%7C42e803feb2c544ef6ea908d5fd538878%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636693457619960040&sdata=kEyYHRIjNZCk%2B37moCSqbrZL426YccNQrsWpENcrZdw%3D&reserved=0 Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index efda23cf32c7..2c3798bcb01c 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1125,6 +1125,7 @@ struct hv_device { u16 device_id; struct device device; + char *driver_override; /* Driver name to force a match */ struct vmbus_channel *channel; struct kset *channels_kset; -- cgit v1.2.3 From cdc3d7f346476b4a4d1c4738b7dcdda4b3d5d870 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Sun, 5 Aug 2018 23:18:05 -0400 Subject: media: drm: shmobile: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Reviewed-by: Simon Horman Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/shmob_drm.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h index ee495d707f17..fe815d7d9f58 100644 --- a/include/linux/platform_data/shmob_drm.h +++ b/include/linux/platform_data/shmob_drm.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm.h -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.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 - * (at your option) any later version. */ #ifndef __SHMOB_DRM_H__ -- cgit v1.2.3 From 7c1a000d466235c875a989971cfda344e6bb1166 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 12 Sep 2018 09:16:07 +0800 Subject: f2fs: add SPDX license identifiers Remove the verbose license text from f2fs files and replace them with SPDX tags. This does not change the license of any of the code. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f70f8ac9c4f4..1d4b196291d6 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /** * include/linux/f2fs_fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.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 - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_FS_H #define _LINUX_F2FS_FS_H -- cgit v1.2.3 From dfb06cba8c73c0704710b2e3fbe2c35ac66a01b4 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 5 Sep 2018 13:31:40 -0700 Subject: uaccess: Fix is_source param for check_copy_size() in copy_to_iter_mcsafe() copy_to_iter_mcsafe() is passing in the is_source parameter as "false" to check_copy_size(). This is different than what copy_to_iter() does. Also, the addr parameter passed to check_copy_size() is the source so therefore we should be passing in "true" instead. Fixes: 8780356ef630 ("x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe()") Cc: Reported-by: Fan Du Signed-off-by: Dave Jiang Reviewed-by: Vishal Verma Reported-by: Wenwei Tao Signed-off-by: Dan Williams --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 409c845d4cd3..422b1c01ee0d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -172,7 +172,7 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) static __always_inline __must_check size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(!check_copy_size(addr, bytes, false))) + if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_to_iter_mcsafe(addr, bytes, i); -- cgit v1.2.3 From 41124fa64d4b298b82266b7ddbefc43540b77b44 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:14 +0200 Subject: net: ethernet: Add helper to remove a supported link mode Some MAC hardware cannot support a subset of link modes. e.g. often 1Gbps Full duplex is supported, but Half duplex is not. Add a helper to remove such a link mode. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli 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 cd6f637cbbfb..9c4c3eca8cf2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1049,6 +1049,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From af8d9bb2f2f405ad541794b46f9d7bc70f13e5cb Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:15 +0200 Subject: net: ethernet: Add helper for MACs which support asym pause Rather than have the MAC drivers manipulate phydev members to indicate they support Asym Pause, add a helper function. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli 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 9c4c3eca8cf2..e2db819807c1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1050,6 +1050,7 @@ int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_asym_pause(struct phy_device *phydev); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From c306ad36184fb7d0bd53f45441f45c1810e88a53 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:16 +0200 Subject: net: ethernet: Add helper for MACs which support pause Rather than have the MAC drivers manipulate phydev members, add a helper function for MACs supporting Pause, but not Asym Pause. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli 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 e2db819807c1..bc5d6c3f1388 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1050,6 +1050,7 @@ int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, -- cgit v1.2.3 From 70814e819c1139e5e7faacb3700eab5eac559272 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:17 +0200 Subject: net: ethernet: Add helper for set_pauseparam for Asym Pause ethtool can be used to enable/disable pause. Add a helper to configure the PHY when asym pause is supported. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli 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 bc5d6c3f1388..e4062ba7472f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1052,6 +1052,7 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From 0c122405d4c3ec638ba00865c872ec5a3ed1a6c0 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:18 +0200 Subject: net: ethernet: Add helper for set_pauseparam for Pause ethtool can be used to enable/disable pause. Add a helper to configure the PHY when Pause is supported. Signed-off-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 e4062ba7472f..8521391ebb20 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1052,6 +1052,8 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, -- cgit v1.2.3 From 22b7d29926b577ff4f480611380d03268545b787 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:19 +0200 Subject: net: ethernet: Add helper to determine if pause configuration is supported Rather than have MAC drivers open code the test, add a helper in phylib. This will help when we change the type of phydev->supported. Signed-off-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 8521391ebb20..192a1fa0c73b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1055,6 +1055,8 @@ void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); 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); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From 0789724f86a59fa7078d67dfeb1ee4a15ae3c693 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Thu, 26 Jul 2018 15:59:16 +0200 Subject: firmware: meson_sm: Add serial number sysfs entry The Amlogic Meson SoC Secure Monitor implements a call to retrieve an unique SoC ID starting from the GX Family and all new families. The serial number is simply exposed as a sysfs entry under the firmware sysfs directory. Signed-off-by: Neil Armstrong Signed-off-by: Kevin Hilman --- include/linux/firmware/meson/meson_sm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h index 37a5eaea69dd..f98c20dd266e 100644 --- a/include/linux/firmware/meson/meson_sm.h +++ b/include/linux/firmware/meson/meson_sm.h @@ -17,6 +17,7 @@ enum { SM_EFUSE_READ, SM_EFUSE_WRITE, SM_EFUSE_USER_MAX, + SM_GET_CHIP_ID, }; struct meson_sm_firmware; -- cgit v1.2.3 From d4983983d98710e4927fdb8de8e987c303b3fba3 Mon Sep 17 00:00:00 2001 From: Maxime Jourdan Date: Thu, 23 Aug 2018 13:49:53 +0200 Subject: soc: amlogic: add meson-canvas driver Amlogic SoCs have a repository of 256 canvas which they use to describe pixel buffers. They contain metadata like width, height, block mode, endianness [..] Many IPs within those SoCs like vdec/vpu rely on those canvas to read/write pixels. Reviewed-by: Jerome Brunet Tested-by: Neil Armstrong Signed-off-by: Maxime Jourdan Signed-off-by: Kevin Hilman --- include/linux/soc/amlogic/meson-canvas.h | 65 ++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/soc/amlogic/meson-canvas.h (limited to 'include/linux') diff --git a/include/linux/soc/amlogic/meson-canvas.h b/include/linux/soc/amlogic/meson-canvas.h new file mode 100644 index 000000000000..b4dde2fbeb3f --- /dev/null +++ b/include/linux/soc/amlogic/meson-canvas.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2018 BayLibre, SAS + */ +#ifndef __SOC_MESON_CANVAS_H +#define __SOC_MESON_CANVAS_H + +#include + +#define MESON_CANVAS_WRAP_NONE 0x00 +#define MESON_CANVAS_WRAP_X 0x01 +#define MESON_CANVAS_WRAP_Y 0x02 + +#define MESON_CANVAS_BLKMODE_LINEAR 0x00 +#define MESON_CANVAS_BLKMODE_32x32 0x01 +#define MESON_CANVAS_BLKMODE_64x64 0x02 + +#define MESON_CANVAS_ENDIAN_SWAP16 0x1 +#define MESON_CANVAS_ENDIAN_SWAP32 0x3 +#define MESON_CANVAS_ENDIAN_SWAP64 0x7 +#define MESON_CANVAS_ENDIAN_SWAP128 0xf + +struct meson_canvas; + +/** + * meson_canvas_get() - get a canvas provider instance + * + * @dev: consumer device pointer + */ +struct meson_canvas *meson_canvas_get(struct device *dev); + +/** + * meson_canvas_alloc() - take ownership of a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: will be filled with the canvas ID + */ +int meson_canvas_alloc(struct meson_canvas *canvas, u8 *canvas_index); + +/** + * meson_canvas_free() - remove ownership from a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: canvas ID that was obtained via meson_canvas_alloc() + */ +int meson_canvas_free(struct meson_canvas *canvas, u8 canvas_index); + +/** + * meson_canvas_config() - configure a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: canvas ID that was obtained via meson_canvas_alloc() + * @addr: physical address to the pixel buffer + * @stride: width of the buffer + * @height: height of the buffer + * @wrap: undocumented + * @blkmode: block mode (linear, 32x32, 64x64) + * @endian: byte swapping (swap16, swap32, swap64, swap128) + */ +int meson_canvas_config(struct meson_canvas *canvas, u8 canvas_index, + u32 addr, u32 stride, u32 height, + unsigned int wrap, unsigned int blkmode, + unsigned int endian); + +#endif -- cgit v1.2.3 From b9762bebc6332b40c33e03dea03e30fa12d9e3ed Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 5 Sep 2018 23:50:05 +0200 Subject: gpiolib: Pass bitmaps, not integer arrays, to get/set array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Most users of get/set array functions iterate consecutive bits of data, usually a single integer, while processing array of results obtained from, or building an array of values to be passed to those functions. Save time wasted on those iterations by changing the functions' API to accept bitmaps. All current users are updated as well. More benefits from the change are expected as soon as planned support for accepting/passing those bitmaps directly from/to respective GPIO chip callbacks if applicable is implemented. Cc: Jonathan Corbet Cc: Miguel Ojeda Sandonis Cc: Sebastien Bourdelin Cc: Lukas Wunner Cc: Peter Korsgaard Cc: Peter Rosin Cc: Andrew Lunn Cc: Florian Fainelli Cc: "David S. Miller" Cc: Rojhalat Ibrahim Cc: Dominik Brodowski Cc: Russell King Cc: Kishon Vijay Abraham I Cc: Tony Lindgren Cc: Lars-Peter Clausen Cc: Michael Hennerich Cc: Jonathan Cameron Cc: Hartmut Knaack Cc: Peter Meerwald-Stadler Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Yegor Yefremov Cc: Uwe Kleine-König Signed-off-by: Janusz Krzysztofik Acked-by: Ulf Hansson Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 21ddbe440030..2b0389f0bec4 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -104,36 +104,38 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); int gpiod_get_array_value(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); + struct gpio_desc **desc_array, + unsigned long *value_bitmap); void gpiod_set_value(struct gpio_desc *desc, int value); void gpiod_set_array_value(unsigned int array_size, - struct gpio_desc **desc_array, int *value_array); + struct gpio_desc **desc_array, + unsigned long *value_bitmap); int gpiod_get_raw_value(const struct gpio_desc *desc); int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); void gpiod_set_raw_value(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array); + unsigned long *value_bitmap); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); int gpiod_set_transitory(struct gpio_desc *desc, bool transitory); @@ -330,7 +332,7 @@ static inline int gpiod_get_value(const struct gpio_desc *desc) } static inline int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -343,7 +345,7 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -356,7 +358,7 @@ static inline int gpiod_get_raw_value(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -369,7 +371,7 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) } static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -384,7 +386,7 @@ static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -397,7 +399,7 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -410,7 +412,7 @@ static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); @@ -424,7 +426,7 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, } static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, - int *value_array) + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); -- cgit v1.2.3 From bf9346f5d47b4506aafbc384dfb5796b0adc3f8d Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 5 Sep 2018 23:50:06 +0200 Subject: gpiolib: Identify arrays matching GPIO hardware Certain GPIO array lookup results may map directly to GPIO pins of a single GPIO chip in hardware order. If that condition is recognized and handled efficiently, significant performance gain of get/set array functions may be possible. While processing a request for an array of GPIO descriptors, identify those which represent corresponding pins of a single GPIO chip. Skip over pins which require open source or open drain special processing. Moreover, identify pins which require inversion. Pass a pointer to that information with the array to the caller so it can benefit from enhanced performance as soon as get/set array functions can accept and make efficient use of it. Cc: Jonathan Corbet Signed-off-by: Janusz Krzysztofik Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 2b0389f0bec4..0ffd71c0a77c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -17,11 +17,20 @@ struct device; */ struct gpio_desc; +/** + * Opaque descriptor for a structure of GPIO array attributes. This structure + * is attached to struct gpiod_descs obtained from gpiod_get_array() and can be + * passed back to get/set array functions in order to activate fast processing + * path if applicable. + */ +struct gpio_array; + /** * Struct containing an array of descriptors that can be obtained using * gpiod_get_array(). */ struct gpio_descs { + struct gpio_array *info; unsigned int ndescs; struct gpio_desc *desc[]; }; -- cgit v1.2.3 From 77588c14ac868caece82fddbfae7de03b2cec941 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 5 Sep 2018 23:50:07 +0200 Subject: gpiolib: Pass array info to get/set array functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to make use of array info obtained from gpiod_get_array() and speed up processing of arrays matching single GPIO chip layout, that information must be passed to get/set array functions. Extend the functions' API with that additional parameter and update all users. Pass NULL if a user builds an array itself from single GPIOs. Cc: Jonathan Corbet Cc: Miguel Ojeda Sandonis Cc: Geert Uytterhoeven Cc: Sebastien Bourdelin Cc: Lukas Wunner Cc: Peter Korsgaard Cc: Peter Rosin Cc: Andrew Lunn Cc: Florian Fainelli Cc: "David S. Miller" Cc: Rojhalat Ibrahim Cc: Dominik Brodowski Cc: Russell King Cc: Kishon Vijay Abraham I Cc: Tony Lindgren Cc: Lars-Peter Clausen Cc: Michael Hennerich Cc: Jonathan Cameron Cc: Hartmut Knaack Cc: Peter Meerwald-Stadler Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Yegor Yefremov Cc: Uwe Kleine-König Signed-off-by: Janusz Krzysztofik Acked-by: Ulf Hansson Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 0ffd71c0a77c..d7fbe30ece84 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -114,36 +114,44 @@ int gpiod_direction_output_raw(struct gpio_desc *desc, int value); int gpiod_get_value(const struct gpio_desc *desc); int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value(struct gpio_desc *desc, int value); void gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); int gpiod_get_raw_value(const struct gpio_desc *desc); int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_raw_value(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); @@ -341,6 +349,7 @@ static inline int gpiod_get_value(const struct gpio_desc *desc) } static inline int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -354,6 +363,7 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -367,6 +377,7 @@ static inline int gpiod_get_raw_value(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -380,6 +391,7 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) } static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -395,6 +407,7 @@ static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -408,6 +421,7 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) } static inline void gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -421,6 +435,7 @@ static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) } static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ @@ -435,6 +450,7 @@ static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, } static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, + struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ -- cgit v1.2.3 From 1e479c619b2ac983fdea1a8212c7b822b5098da0 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 12 Sep 2018 22:22:45 +0200 Subject: rtc: unexport non devm managed registration Ensure the non managed version of the un/registration functions is not used anymore. No driver is using it anymore and they should not be necessary. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 6aedc30003e7..faf00a1472d4 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -167,17 +167,12 @@ struct rtc_device { #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ -extern struct rtc_device *rtc_device_register(const char *name, - struct device *dev, - const struct rtc_class_ops *ops, - struct module *owner); extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); struct rtc_device *devm_rtc_allocate_device(struct device *dev); int __rtc_register_device(struct module *owner, struct rtc_device *rtc); -extern void rtc_device_unregister(struct rtc_device *rtc); extern void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc); -- cgit v1.2.3 From 15033f0457dca569b284bef0c8d3ad55fb37eacb Mon Sep 17 00:00:00 2001 From: Andre Naujoks Date: Mon, 10 Sep 2018 10:27:15 +0200 Subject: ipv6: Add sockopt IPV6_MULTICAST_ALL analogue to IP_MULTICAST_ALL The socket option will be enabled by default to ensure current behaviour is not changed. This is the same for the IPv4 version. A socket bound to in6addr_any and a specific port will receive all traffic on that port. Analogue to IP_MULTICAST_ALL, disable this behaviour, if one or more multicast groups were joined (using said socket) and only pass on multicast traffic from groups, which were explicitly joined via this socket. Without this option disabled a socket (system even) joined to multiple multicast groups is very hard to get right. Filtering by destination address has to take place in user space to avoid receiving multicast traffic from other multicast groups, which might have traffic on the same port. The extension of the IP_MULTICAST_ALL socketoption to just apply to ipv6, too, is not done to avoid changing the behaviour of current applications. Signed-off-by: Andre Naujoks Acked-By: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8415bf1a9776..495e834c1367 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -274,7 +274,8 @@ struct ipv6_pinfo { */ dontfrag:1, autoflowlabel:1, - autoflowlabel_set:1; + autoflowlabel_set:1, + mc_all:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; -- cgit v1.2.3 From 37a3a98ef601f89100e3bb657fb0e190b857028c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 10 Sep 2018 16:20:25 +0200 Subject: ALSA: hda - Enable runtime PM only for discrete GPU The recent change of vga_switcheroo allowed the runtime PM for HD-audio on AMD GPUs, but this also resulted in a regression. When the HD-audio controller driver gets runtime-suspended, HD-audio link is turned off, and the hotplug notification is ignored. This leads to the inconsistent audio state (the connection isn't notified and ELD is ignored). The best fix would be to implement the proper ELD notification via the audio component, but it's still not ready. As a quick workaround, this patch adds the check of runtime_idle and allows the runtime suspend only when the vga_switcheroo is bound with discrete GPU. That is, a system with a single GPU and APU would be again without runtime PM to keep the HD-audio link for the hotplug notification and ELD read out. Also, the codec->auto_runtime_pm flag is set only for the discrete GPU at the time GPU gets bound via vga_switcheroo (i.e. only dGPU is forcibly runtime-PM enabled), so that APU can still get the ELD notification. For identifying which GPU is bound, a new vga_switcheroo client callback, gpu_bound, is implemented. The vga_switcheroo simply calls this when GPU is bound, and tells whether it's dGPU or APU. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=200945 Fixes: 07f4f97d7b4b ("vga_switcheroo: Use device link for HDA controller") Reported-by: Jian-Hong Pan Tested-by: Jian-Hong Pan Acked-by: Lukas Wunner Signed-off-by: Takashi Iwai --- include/linux/vga_switcheroo.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index a34539b7f750..7e6ac0114d55 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -133,15 +133,18 @@ struct vga_switcheroo_handler { * @can_switch: check if the device is in a position to switch now. * Mandatory. The client should return false if a user space process * has one of its device files open + * @gpu_bound: notify the client id to audio client when the GPU is bound. * * Client callbacks. A client can be either a GPU or an audio device on a GPU. * The @set_gpu_state and @can_switch methods are mandatory, @reprobe may be * set to NULL. For audio clients, the @reprobe member is bogus. + * OTOH, @gpu_bound is only for audio clients, and not used for GPU clients. */ struct vga_switcheroo_client_ops { void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state); void (*reprobe)(struct pci_dev *dev); bool (*can_switch)(struct pci_dev *dev); + void (*gpu_bound)(struct pci_dev *dev, enum vga_switcheroo_client_id); }; #if defined(CONFIG_VGA_SWITCHEROO) -- cgit v1.2.3 From fe8dd45bb7556246c6b76277b1ba4296c91c2505 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 12 Sep 2018 11:17:06 +0800 Subject: tun: switch to new type of msg_control This patch introduces to a new tun/tap specific msg_control: #define TUN_MSG_UBUF 1 #define TUN_MSG_PTR 2 struct tun_msg_ctl { int type; void *ptr; }; This allows us to pass different kinds of msg_control through sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will be used by the existed vhost_net zerocopy code. The second is XDP buff, which allows vhost_net to pass XDP buff to TUN. This could be used to implement accepting an array of XDP buffs from vhost_net in the following patches. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/if_tun.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 3d2996dc7d85..12e3eebf0ce6 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -16,9 +16,23 @@ #define __IF_TUN_H #include +#include #define TUN_XDP_FLAG 0x1UL +#define TUN_MSG_UBUF 1 +#define TUN_MSG_PTR 2 +struct tun_msg_ctl { + unsigned short type; + unsigned short num; + void *ptr; +}; + +struct tun_xdp_hdr { + int buflen; + struct virtio_net_hdr gso; +}; + #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -- cgit v1.2.3 From 7f9c136216c745099f36a4e0c3b2e63eedeb442f Mon Sep 17 00:00:00 2001 From: Venkata Narendra Kumar Gutta Date: Wed, 12 Sep 2018 11:06:32 -0700 Subject: soc: qcom: Add broadcast base for Last Level Cache Controller (LLCC) Currently, broadcast base is set to end of the LLCC banks, which may not be correct always. As the number of banks may vary for each chipset and the broadcast base could be at a different address as well. This info depends on the chipset, so get the broadcast base info from the device tree (DT). Add broadcast base in LLCC driver and use this for broadcast writes. Signed-off-by: Venkata Narendra Kumar Gutta Reviewed-by: Evan Green Signed-off-by: Andy Gross --- include/linux/soc/qcom/llcc-qcom.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 7e3b9c605ab2..c681e795b587 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -70,22 +70,22 @@ struct llcc_slice_config { /** * llcc_drv_data - Data associated with the llcc driver * @regmap: regmap associated with the llcc device + * @bcast_regmap: regmap associated with llcc broadcast offset * @cfg: pointer to the data structure for slice configuration * @lock: mutex associated with each slice * @cfg_size: size of the config data table * @max_slices: max slices as read from device tree - * @bcast_off: Offset of the broadcast bank * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array */ struct llcc_drv_data { struct regmap *regmap; + struct regmap *bcast_regmap; const struct llcc_slice_config *cfg; struct mutex lock; u32 cfg_size; u32 max_slices; - u32 bcast_off; u32 num_banks; unsigned long *bitmap; u32 *offsets; -- cgit v1.2.3 From c081f3060fab316fcf103967a24e502d58488849 Mon Sep 17 00:00:00 2001 From: Venkata Narendra Kumar Gutta Date: Wed, 12 Sep 2018 11:06:33 -0700 Subject: soc: qcom: Add support to register LLCC EDAC driver Cache error reporting controller detects and reports single and double bit errors on Last Level Cache Controller (LLCC) cache. Add required support to register LLCC EDAC driver as platform driver, from LLCC driver. Signed-off-by: Venkata Narendra Kumar Gutta Reviewed-by: Evan Green Signed-off-by: Andy Gross --- include/linux/soc/qcom/llcc-qcom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index c681e795b587..2e4b34d2617e 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -78,6 +78,7 @@ struct llcc_slice_config { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array + * @ecc_irq: interrupt for llcc cache error detection and reporting */ struct llcc_drv_data { struct regmap *regmap; @@ -89,6 +90,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; u32 *offsets; + int ecc_irq; }; #if IS_ENABLED(CONFIG_QCOM_LLCC) -- cgit v1.2.3 From 27450653f1db0b9d5b5048a246c850c52ee4aa61 Mon Sep 17 00:00:00 2001 From: Channagoud Kadabi Date: Wed, 12 Sep 2018 11:06:34 -0700 Subject: drivers: edac: Add EDAC driver support for QCOM SoCs Add error reporting driver for Single Bit Errors (SBEs) and Double Bit Errors (DBEs). As of now, this driver supports error reporting for Last Level Cache Controller (LLCC) of Tag RAM and Data RAM. Interrupts are triggered when the errors happen in the cache, the driver handles those interrupts and dumps the syndrome registers. Signed-off-by: Channagoud Kadabi Signed-off-by: Venkata Narendra Kumar Gutta Co-developed-by: Venkata Narendra Kumar Gutta Acked-by: Borislav Petkov Signed-off-by: Andy Gross --- include/linux/soc/qcom/llcc-qcom.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 2e4b34d2617e..69c285b1c990 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -93,6 +93,30 @@ struct llcc_drv_data { int ecc_irq; }; +/** + * llcc_edac_reg_data - llcc edac registers data for each error type + * @name: Name of the error + * @synd_reg: Syndrome register address + * @count_status_reg: Status register address to read the error count + * @ways_status_reg: Status register address to read the error ways + * @reg_cnt: Number of registers + * @count_mask: Mask value to get the error count + * @ways_mask: Mask value to get the error ways + * @count_shift: Shift value to get the error count + * @ways_shift: Shift value to get the error ways + */ +struct llcc_edac_reg_data { + char *name; + u64 synd_reg; + u64 count_status_reg; + u64 ways_status_reg; + u32 reg_cnt; + u32 count_mask; + u32 ways_mask; + u8 count_shift; + u8 ways_shift; +}; + #if IS_ENABLED(CONFIG_QCOM_LLCC) /** * llcc_slice_getd - get llcc slice descriptor -- cgit v1.2.3 From f4926ef76e23e291fcd38bd107c0a9bb8e2db505 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 18 May 2018 15:47:50 -0700 Subject: soc: qcom: geni: Make version macros simpler This macro doesn't work, because it hides a local variable inside of the macro to hold the version and that variable name is called 'ver' and 'version' sometimes. Let's change this to be more explicit. Introduce three macros for the major, minor, and step of the version, and require callers to pass the version in to get the part of the version out. This way we don't hide local variables inside macros and things are less evil overall. Cc: Karthikeyan Ramasubramanian Cc: Sagar Dharia Cc: Girish Mahadevan Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom-geni-se.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 5d6144977828..3bcd67fd5548 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -225,19 +225,14 @@ struct geni_se { #define HW_VER_MINOR_SHFT 16 #define HW_VER_STEP_MASK GENMASK(15, 0) +#define GENI_SE_VERSION_MAJOR(ver) ((ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT) +#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) + #if IS_ENABLED(CONFIG_QCOM_GENI_SE) u32 geni_se_get_qup_hw_version(struct geni_se *se); -#define geni_se_get_wrapper_version(se, major, minor, step) do { \ - u32 ver; \ -\ - ver = geni_se_get_qup_hw_version(se); \ - major = (ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT; \ - minor = (ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT; \ - step = version & HW_VER_STEP_MASK; \ -} while (0) - /** * geni_se_read_proto() - Read the protocol configured for a serial engine * @se: Pointer to the concerned serial engine. -- cgit v1.2.3 From 7a9cdebdcc17e426fb5287e4a82db1dfe86339b2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 12 Sep 2018 23:57:48 -1000 Subject: mm: get rid of vmacache_flush_all() entirely Jann Horn points out that the vmacache_flush_all() function is not only potentially expensive, it's buggy too. It also happens to be entirely unnecessary, because the sequence number overflow case can be avoided by simply making the sequence number be 64-bit. That doesn't even grow the data structures in question, because the other adjacent fields are already 64-bit. So simplify the whole thing by just making the sequence number overflow case go away entirely, which gets rid of all the complications and makes the code faster too. Win-win. [ Oleg Nesterov points out that the VMACACHE_FULL_FLUSHES statistics also just goes away entirely with this ] Reported-by: Jann Horn Suggested-by: Will Deacon Acked-by: Davidlohr Bueso Cc: Oleg Nesterov Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 2 +- include/linux/vm_event_item.h | 1 - include/linux/vmacache.h | 5 ----- 4 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cd2bc939efd0..5ed8f6292a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5fe87687664c..d7016dcb245e 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -32,7 +32,7 @@ #define VMACACHE_MASK (VMACACHE_SIZE - 1) struct vmacache { - u32 seqnum; + u64 seqnum; struct vm_area_struct *vmas[VMACACHE_SIZE]; }; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5c7f010676a7..47a3441cf4c4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,7 +105,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_DEBUG_VM_VMACACHE VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, - VMACACHE_FULL_FLUSHES, #endif #ifdef CONFIG_SWAP SWAP_RA, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index 3e9a963edd6a..6fce268a4588 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -10,7 +10,6 @@ static inline void vmacache_flush(struct task_struct *tsk) memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } -extern void vmacache_flush_all(struct mm_struct *mm); extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); @@ -24,10 +23,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; - - /* deal with overflows */ - if (unlikely(mm->vmacache_seqnum == 0)) - vmacache_flush_all(mm); } #endif /* __LINUX_VMACACHE_H */ -- cgit v1.2.3 From 59104f239b9ed6cf3986e4228173ff2f4c95039e Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 26 Jul 2018 02:37:49 +0000 Subject: drm: shmobile: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Acked-by: Laurent Pinchart Reviewed-by: Simon Horman Signed-off-by: Laurent Pinchart --- include/linux/platform_data/shmob_drm.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h index ee495d707f17..fe815d7d9f58 100644 --- a/include/linux/platform_data/shmob_drm.h +++ b/include/linux/platform_data/shmob_drm.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm.h -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.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 - * (at your option) any later version. */ #ifndef __SHMOB_DRM_H__ -- cgit v1.2.3 From e21120383f2dce32312f63ffca145ff8a87d41f5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 19:47:09 -0400 Subject: move compat handling of tty ioctls to tty_compat_ioctl() ioctls that are * callable only via tty_ioctl() * not driver-specific * not demand data structure conversions * either always need passing arg as is or always demand compat_ptr() get intercepted in tty_compat_ioctl() from the very beginning and redirecter to tty_ioctl(). As the result, their entries in fs/compat_ioctl.c (some of those had been missing, BTW) got removed, as well as n_tty_compat_ioctl_helper() (now it's never called with any cmd it would accept). Signed-off-by: Al Viro --- include/linux/tty.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index c56e3978b00f..414db2bce715 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -746,8 +746,6 @@ static inline int tty_audit_push(void) /* tty_ioctl.c */ extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); -extern long n_tty_compat_ioctl_helper(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); /* vt.c */ -- cgit v1.2.3 From 2f46a2c1d4eb982b82c199e1bd5cddab12681275 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 21:53:32 -0400 Subject: tty_ioctl(): start taking TIOC[SG]SERIAL into separate methods ->set_serial() and ->get_serial() resp., both taking tty and a kernel pointer to serial_struct. Signed-off-by: Al Viro --- include/linux/tty_driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 71dbc891851a..358446247ccd 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -249,6 +249,7 @@ struct tty_struct; struct tty_driver; struct serial_icounter_struct; +struct serial_struct; struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, @@ -287,6 +288,8 @@ struct tty_operations { int (*set_termiox)(struct tty_struct *tty, struct termiox *tnew); int (*get_icount)(struct tty_struct *tty, struct serial_icounter_struct *icount); + int (*get_serial)(struct tty_struct *tty, struct serial_struct *p); + int (*set_serial)(struct tty_struct *tty, struct serial_struct *p); void (*show_fdinfo)(struct tty_struct *tty, struct seq_file *m); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct tty_driver *driver, int line, char *options); -- cgit v1.2.3 From 52bb6677d530d37055092d86b4eab69dce6c166a Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Fri, 14 Sep 2018 16:00:51 +0800 Subject: net: move definition of pcpu_lstats to header file pcpu_lstats is defined in several files, so unify them as one and move to header file Signed-off-by: Zhang Yu Signed-off-by: Li RongQing 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 e2b3bd750c98..baed5d5088c5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2382,6 +2382,12 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; +struct pcpu_lstats { + u64 packets; + u64 bytes; + struct u64_stats_sync syncp; +}; + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ -- cgit v1.2.3 From d58e468b1112dcd1d5193c0a89ff9f98b5a3e8b9 Mon Sep 17 00:00:00 2001 From: Petar Penkov Date: Fri, 14 Sep 2018 07:46:18 -0700 Subject: flow_dissector: implements flow dissector BPF hook Adds a hook for programs of type BPF_PROG_TYPE_FLOW_DISSECTOR and attach type BPF_FLOW_DISSECTOR that is executed in the flow dissector path. The BPF program is per-network namespace. Signed-off-by: Petar Penkov Signed-off-by: Willem de Bruijn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/linux/skbuff.h | 7 +++++++ 3 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 523481a3471b..988a00797bcd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -212,6 +212,7 @@ enum bpf_reg_type { PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ + PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ }; /* The information passed from prog-specific *_is_valid_access diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index cd26c090e7c0..22083712dd18 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -32,6 +32,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) #endif +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17a13e4785fc..ce0e863f02a2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -243,6 +243,8 @@ struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; +struct bpf_prog; +union bpf_attr; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack { @@ -1192,6 +1194,11 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); +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); + bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, -- cgit v1.2.3 From 36f47383c7f9fa0fdc20a92635435ff77ff71a6f Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Fri, 10 Aug 2018 15:13:47 +0200 Subject: mfd: cros: add charger port count command definition A new more command has been added to the ChromeOS embedded controller that allows to get the number of charger port count. Unlike EC_CMD_USB_PD_PORTS, this new command also includes the dedicated port if present. This command will be used to expose the dedicated charger port in the ChromeOS charger driver. Signed-off-by: Fabien Parent Acked-for-MFD-by: Lee Jones Reviewed-by: Enric Balletbo i Serra Signed-off-by: Sebastian Reichel --- include/linux/mfd/cros_ec_commands.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..20ee71f10865 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -3102,6 +3102,16 @@ struct ec_params_usb_pd_info_request { uint8_t port; } __packed; +/* + * This command will return the number of USB PD charge port + the number + * of dedicated port present. + * EC_CMD_USB_PD_PORTS does NOT include the dedicated ports + */ +#define EC_CMD_CHARGE_PORT_COUNT 0x0105 +struct ec_response_charge_port_count { + uint8_t port_count; +} __packed; + /* Read USB-PD Device discovery info */ #define EC_CMD_USB_PD_DISCOVERY 0x0113 struct ec_params_usb_pd_discovery_entry { -- cgit v1.2.3 From 8f5be0ec23bb9ef3f96659c8dff1340b876600bf Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 13 Aug 2018 09:52:09 +0300 Subject: kernfs: update comment about kernfs_path() return value Now it returns the length of the full path or error code. Signed-off-by: Konstantin Khlebnikov Fixes: 3abb1d90f5d9 ("kernfs: make kernfs_path*() behave in the style of strlcpy()") Acked-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 814643f7ee52..5b36b1287a5a 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -477,10 +477,11 @@ static inline void kernfs_init(void) { } * @buf: buffer to copy @kn's name into * @buflen: size of @buf * - * Builds and returns the full path of @kn in @buf of @buflen bytes. The - * path is built from the end of @buf so the returned pointer usually - * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated - * and %NULL is returned. + * If @kn is NULL result will be "(null)". + * + * Returns the length of the full path. If the full length is equal to or + * greater than @buflen, @buf contains the truncated path with the trailing + * '\0'. On error, -errno is returned. */ static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { -- cgit v1.2.3 From 2953d80ff04862b26a2e628fb3948868f54d753d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 31 Aug 2018 20:29:37 +0200 Subject: netfilter: remove obsolete need_conntrack stub as of a0ae2562c6c4b27 ("netfilter: conntrack: remove l3proto abstraction") there are no users anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 03097fa70975..e142b2b5f1ea 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -19,7 +19,4 @@ struct ip_conntrack_stat { unsigned int search_restart; }; -/* call to create an explicit dependency on nf_conntrack. */ -void need_conntrack(void); - #endif /* _NF_CONNTRACK_COMMON_H */ -- cgit v1.2.3 From 0baf9eb25572eea0cf48249c1d152d8373956a7c Mon Sep 17 00:00:00 2001 From: David Lechner Date: Wed, 12 Sep 2018 19:39:17 -0500 Subject: spi: add new SPI_CS_WORD flag This adds a new SPI mode flag, SPI_CS_WORD, that is used to indicate that a SPI device requires the chip select to be toggled after each word that is transferred. Signed-off-by: David Lechner Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a64235e05321..7cc1466111f5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -163,6 +163,7 @@ struct spi_device { #define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ #define SPI_RX_DUAL 0x400 /* receive with 2 wires */ #define SPI_RX_QUAD 0x800 /* receive with 4 wires */ +#define SPI_CS_WORD 0x1000 /* toggle cs after each word */ int irq; void *controller_state; void *controller_data; @@ -177,7 +178,6 @@ struct spi_device { * the controller talks to each chip, like: * - memory packing (12 bit samples into low bits, others zeroed) * - priority - * - drop chipselect after each word * - chipselect delays * - ... */ -- cgit v1.2.3 From efdfeb079cc3b6c7d9c19959c5ed65ce2510dd1d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 6 Sep 2018 14:24:36 +0200 Subject: regulator: fixed: Convert to use GPIO descriptor only As we augmented the regulator core to accept a GPIO descriptor instead of a GPIO number, we can augment the fixed GPIO regulator to look up and pass that descriptor directly from device tree or board GPIO descriptor look up tables. Some boards just auto-enumerate their fixed regulator platform devices and I have assumed they get names like "fixed-regulator.0" but it's pretty hard to guess this. I need some testing from board maintainers to be sure. Other boards are straight forward, using just plain "fixed-regulator" (ID -1) or "fixed-regulator.1" hammering down the device ID. It seems the da9055 and da9211 has never got around to actually passing any enable gpio into its platform data (not the in-tree code anyway) so we can just decide to simply pass a descriptor instead. The fixed GPIO-controlled regulator in mach-pxa/ezx.c was confusingly named "*_dummy_supply_device" while it is a very real device backed by a GPIO line. There is nothing dummy about it at all, so I renamed it with the infix *_regulator_* as part of this patch set. Intel MID portions tested by Andy. Tested-by: Andy Shevchenko # Check the x86 BCM stuff Acked-by: Tony Lindgren # OMAP1,2,3 maintainer Signed-off-by: Linus Walleij Reviewed-by: Janusz Krzysztofik Reviewed-by: Mike Rapoport Signed-off-by: Mark Brown --- include/linux/regulator/fixed.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index 48918be649d4..1a4340ed8e2b 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -24,8 +24,6 @@ struct regulator_init_data; * @supply_name: Name of the regulator supply * @input_supply: Name of the input regulator supply * @microvolts: Output voltage of regulator - * @gpio: GPIO to use for enable control - * set to -EINVAL if not used * @startup_delay: Start-up time in microseconds * @gpio_is_open_drain: Gpio pin is open drain or normal type. * If it is open drain type then HIGH will be set @@ -49,7 +47,6 @@ struct fixed_voltage_config { const char *supply_name; const char *input_supply; int microvolts; - int gpio; unsigned startup_delay; unsigned gpio_is_open_drain:1; unsigned enable_high:1; -- cgit v1.2.3 From 1ccce46c5e8b8a0d2606fb8bb72bff069ffdc3ab Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 14 Aug 2018 17:14:30 -0700 Subject: PCI: Remove unused NFP32xx IDs Defines for NFP32xx are no longer used anywhere, remove them. Signed-off-by: Jakub Kicinski Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d157983b84cf..f4e278493f5b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2539,8 +2539,6 @@ #define PCI_VENDOR_ID_HUAWEI 0x19e5 #define PCI_VENDOR_ID_NETRONOME 0x19ee -#define PCI_DEVICE_ID_NETRONOME_NFP3200 0x3200 -#define PCI_DEVICE_ID_NETRONOME_NFP3240 0x3240 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 #define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 -- cgit v1.2.3 From 6a5f95b5a4f4ff29e4071bc5b95f8f3a2aef046b Mon Sep 17 00:00:00 2001 From: Fieah Lim Date: Tue, 11 Sep 2018 03:59:01 +0800 Subject: cpuidle: Remove unnecessary wrapper cpuidle_get_last_residency() cpuidle_get_last_residency() is just a wrapper for retrieving the last_residency member of struct cpuidle_device. It's also weirdly the only wrapper function for accessing cpuidle_* struct member (by my best guess is it could be a leftover from v2.x). Anyhow, since the only two users (the ladder and menu governors) can access dev->last_residency directly, and it's more intuitive to do it that way, let's just get rid of the wrapper. This patch tidies up CPU idle code a bit without functional changes. Signed-off-by: Fieah Lim [ rjw: Changelog cleanup ] Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 4325d6fdde9b..d262f620890e 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -99,16 +99,6 @@ struct cpuidle_device { DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices); DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev); -/** - * cpuidle_get_last_residency - retrieves the last state's residency time - * @dev: the target CPU - */ -static inline int cpuidle_get_last_residency(struct cpuidle_device *dev) -{ - return dev->last_residency; -} - - /**************************** * CPUIDLE DRIVER INTERFACE * ****************************/ -- cgit v1.2.3 From 10c63443b74d1ef5c1b3bb104a9e6e40dc2437ff Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Aug 2018 14:54:03 +0200 Subject: Revert "serial: sh-sci: Remove SCIx_RZ_SCIFA_REGTYPE" This reverts commit 7acece71a517cad83a0842a94d94c13f271b680c. Signed-off-by: Geert Uytterhoeven Acked-by: Chris Brandt Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_sci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index c0e795d95477..1c89611e0e06 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -36,6 +36,7 @@ enum { SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, + SCIx_RZ_SCIFA_REGTYPE, SCIx_NR_REGTYPES, }; -- cgit v1.2.3 From 76f99ae5b54d48430d1f0c5512a84da0ff9761e0 Mon Sep 17 00:00:00 2001 From: Dou Liyang Date: Sun, 9 Sep 2018 01:58:38 +0800 Subject: irq/matrix: Spread managed interrupts on allocation Linux spreads out the non managed interrupt across the possible target CPUs to avoid vector space exhaustion. Managed interrupts are treated differently, as for them the vectors are reserved (with guarantee) when the interrupt descriptors are initialized. When the interrupt is requested a real vector is assigned. The assignment logic uses the first CPU in the affinity mask for assignment. If the interrupt has more than one CPU in the affinity mask, which happens when a multi queue device has less queues than CPUs, then doing the same search as for non managed interrupts makes sense as it puts the interrupt on the least interrupt plagued CPU. For single CPU affine vectors that's obviously a NOOP. Restructre the matrix allocation code so it does the 'best CPU' search, add the sanity check for an empty affinity mask and adapt the call site in the x86 vector management code. [ tglx: Added the empty mask check to the core and improved change log ] Signed-off-by: Dou Liyang Signed-off-by: Thomas Gleixner Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/20180908175838.14450-2-dou_liyang@163.com --- include/linux/irq.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 201de12a9957..c9bffda04a45 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1151,7 +1151,8 @@ void irq_matrix_offline(struct irq_matrix *m); void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace); int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk); void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk); -int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu); +int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, + unsigned int *mapped_cpu); void irq_matrix_reserve(struct irq_matrix *m); void irq_matrix_remove_reserved(struct irq_matrix *m); int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, -- cgit v1.2.3 From 4372ea94d40c5676814fc6d815a64caed963cb9f Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Wed, 18 Apr 2018 10:00:47 -0500 Subject: ipmi: Finally get rid of ipmi_user_t and ipmi_smi_t All the users have been removed, we can remove the typedefs. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 2 +- include/linux/ipmi_smi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 41f5c086f670..ef61676cfe05 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -27,7 +27,7 @@ struct device; * Opaque type for a IPMI message user. One of these is needed to * send and receive messages. */ -typedef struct ipmi_user *ipmi_user_t; +struct ipmi_user; /* * Stuff coming from the receive interface comes as one of these. diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 7d5fd38d5282..8c4e2ab696c3 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -28,7 +28,7 @@ struct device; */ /* Structure for the low-level drivers. */ -typedef struct ipmi_smi *ipmi_smi_t; +struct ipmi_smi; /* * Messages to/from the lower layer. The smi interface will take one -- cgit v1.2.3 From 05c3d056086a6217a77937b7fa0df35ec75715e6 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Mon, 26 Feb 2018 12:49:16 -0600 Subject: pci:ipmi: Move IPMI PCI class id defines to pci_ids.h Signed-off-by: Corey Minyard Acked-by: Bjorn Helgaas --- include/linux/pci_ids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d157983b84cf..d4afd8086ed9 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -117,6 +117,10 @@ #define PCI_CLASS_SERIAL_USB_DEVICE 0x0c03fe #define PCI_CLASS_SERIAL_FIBER 0x0c04 #define PCI_CLASS_SERIAL_SMBUS 0x0c05 +#define PCI_CLASS_SERIAL_IPMI 0x0c07 +#define PCI_CLASS_SERIAL_IPMI_SMIC 0x0c0700 +#define PCI_CLASS_SERIAL_IPMI_KCS 0x0c0701 +#define PCI_CLASS_SERIAL_IPMI_BT 0x0c0702 #define PCI_BASE_CLASS_WIRELESS 0x0d #define PCI_CLASS_WIRELESS_RF_CONTROLLER 0x0d10 -- cgit v1.2.3 From 81c4b5bf30de01a0f6b43ccaa1d220f4a0a5d99c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Constify hotplug_slot_ops Hotplug drivers cannot declare their hotplug_slot_ops const, making them attractive targets for attackers, because upon registration of a hotplug slot, __pci_hp_initialize() writes to the "owner" and "mod_name" members in that struct. Fix by moving these members to struct hotplug_slot and constify every driver's hotplug_slot_ops except for pciehp. pciehp constructs its hotplug_slot_ops at runtime based on the PCIe port's capabilities, hence cannot declare them const. It can be converted to __write_rarely once that's mainlined: http://www.openwall.com/lists/kernel-hardening/2016/11/16/3 Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Sebastian Ott Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- include/linux/pci_hotplug.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index a6d6650a0490..372dbe95c207 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -16,8 +16,6 @@ /** * struct hotplug_slot_ops -the callbacks that the hotplug pci core can use - * @owner: The module owner of this structure - * @mod_name: The module name (KBUILD_MODNAME) of this structure * @enable_slot: Called when the user wants to enable a specific pci slot * @disable_slot: Called when the user wants to disable a specific pci slot * @set_attention_status: Called to set the specific slot's attention LED to @@ -46,8 +44,6 @@ * set an LED, enable / disable power, etc.) */ struct hotplug_slot_ops { - struct module *owner; - const char *mod_name; int (*enable_slot) (struct hotplug_slot *slot); int (*disable_slot) (struct hotplug_slot *slot); int (*set_attention_status) (struct hotplug_slot *slot, u8 value); @@ -82,15 +78,19 @@ struct hotplug_slot_info { * this slot. * @private: used by the hotplug pci controller driver to store whatever it * needs. + * @owner: The module owner of this structure + * @mod_name: The module name (KBUILD_MODNAME) of this structure */ struct hotplug_slot { - struct hotplug_slot_ops *ops; + const struct hotplug_slot_ops *ops; struct hotplug_slot_info *info; void *private; /* Variables below this are for use only by the hotplug pci core. */ struct list_head slot_list; struct pci_slot *pci_slot; + struct module *owner; + const char *mod_name; }; static inline const char *hotplug_slot_name(const struct hotplug_slot *slot) -- cgit v1.2.3 From a7da21613c4efcd4cc0235e6a30bec96ae47c619 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Drop hotplug_slot_info Ever since the PCI hotplug core was introduced in 2002, drivers had to allocate and register a struct hotplug_slot_info for every slot: https://git.kernel.org/tglx/history/c/a8a2069f432c Apparently the idea was that drivers furnish the hotplug core with an up-to-date card presence status, power status, latch status and attention indicator status as well as notify the hotplug core of changes thereof. However only 4 out of 12 hotplug drivers bother to notify the hotplug core with pci_hp_change_slot_info() and the hotplug core never made any use of the information: There is just a single macro in pci_hotplug_core.c, GET_STATUS(), which uses the hotplug_slot_info if the driver lacks the corresponding callback in hotplug_slot_ops. The macro is called when the user reads the attribute via sysfs. Now, if the callback isn't defined, the attribute isn't exposed in sysfs in the first place (see e.g. has_power_file()). There are only two situations when the hotplug_slot_info would actually be accessed: * If the driver defines ->enable_slot or ->disable_slot but not ->get_power_status. * If the driver defines ->set_attention_status but not ->get_attention_status. There is no driver doing the former and just a single driver doing the latter, namely pnv_php.c. Amend it with a ->get_attention_status callback. With that, the hotplug_slot_info becomes completely unused by the PCI hotplug core. But a few drivers use it internally as a cache: cpcihp uses it to cache the latch_status and adapter_status. cpqhp uses it to cache the adapter_status. pnv_php and rpaphp use it to cache the attention_status. shpchp uses it to cache all four values. Amend these drivers to cache the information in their private slot struct. shpchp's slot struct already contains members to cache the power_status and adapter_status, so additional members are only needed for the other two values. In the case of cpqphp, the cached value is only accessed in a single place, so instead of caching it, read the current value from the hardware. Caution: acpiphp, cpci, cpqhp, shpchp, asus-wmi and eeepc-laptop populate the hotplug_slot_info with initial values on probe. That code is herewith removed. There is a theoretical chance that the code has side effects without which the driver fails to function, e.g. if the ACPI method to read the adapter status needs to be executed at least once on probe. That seems unlikely to me, still maintainers should review the changes carefully for this possibility. Rafael adds: "I'm not aware of any case in which it will break anything, [...] but if that happens, it may be necessary to add the execution of the control methods in question directly to the initialization part." Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Sebastian Ott # drivers/pci/hotplug/s390* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- include/linux/pci_hotplug.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 372dbe95c207..6f07a4e1de8d 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -23,17 +23,9 @@ * @hardware_test: Called to run a specified hardware test on the specified * slot. * @get_power_status: Called to get the current power status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_attention_status: Called to get the current attention status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_latch_status: Called to get the current latch status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_adapter_status: Called to get see if an adapter is present in the slot or not. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @reset_slot: Optional interface to allow override of a bus reset for the * slot for cases where a secondary bus reset can result in spurious * hotplug events or where a slot can be reset independent of the bus. @@ -55,27 +47,9 @@ struct hotplug_slot_ops { int (*reset_slot) (struct hotplug_slot *slot, int probe); }; -/** - * struct hotplug_slot_info - used to notify the hotplug pci core of the state of the slot - * @power_status: if power is enabled or not (1/0) - * @attention_status: if the attention light is enabled or not (1/0) - * @latch_status: if the latch (if any) is open or closed (1/0) - * @adapter_status: if there is a pci board present in the slot or not (1/0) - * - * Used to notify the hotplug pci core of the status of a specific slot. - */ -struct hotplug_slot_info { - u8 power_status; - u8 attention_status; - u8 latch_status; - u8 adapter_status; -}; - /** * struct hotplug_slot - used to register a physical slot with the hotplug pci core * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot - * @info: pointer to the &struct hotplug_slot_info for the initial values for - * this slot. * @private: used by the hotplug pci controller driver to store whatever it * needs. * @owner: The module owner of this structure @@ -83,7 +57,6 @@ struct hotplug_slot_info { */ struct hotplug_slot { const struct hotplug_slot_ops *ops; - struct hotplug_slot_info *info; void *private; /* Variables below this are for use only by the hotplug pci core. */ @@ -110,9 +83,6 @@ void pci_hp_del(struct hotplug_slot *slot); void pci_hp_destroy(struct hotplug_slot *slot); void pci_hp_deregister(struct hotplug_slot *slot); -int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot, - struct hotplug_slot_info *info); - /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define pci_hp_register(slot, pbus, devnr, name) \ __pci_hp_register(slot, pbus, devnr, name, THIS_MODULE, KBUILD_MODNAME) -- cgit v1.2.3 From 125450f814418b9f889c9885831467d1b2e25a7d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Embed hotplug_slot When the PCI hotplug core and its first user, cpqphp, were introduced in February 2002 with historic commit a8a2069f432c, cpqphp allocated a slot struct for its internal use plus a hotplug_slot struct to be registered with the hotplug core and linked the two with pointers: https://git.kernel.org/tglx/history/c/a8a2069f432c Nowadays, the predominant pattern in the tree is to embed ("subclass") such structures in one another and cast to the containing struct with container_of(). But it wasn't until July 2002 that container_of() was introduced with historic commit ec4f214232cf: https://git.kernel.org/tglx/history/c/ec4f214232cf pnv_php, introduced in 2016, did the right thing and embedded struct hotplug_slot in its internal struct pnv_php_slot, but all other drivers cargo-culted cpqphp's design and linked separate structs with pointers. Embedding structs is preferrable to linking them with pointers because it requires fewer allocations, thereby reducing overhead and simplifying error paths. Casting an embedded struct to the containing struct becomes a cheap subtraction rather than a dereference. And having fewer pointers reduces the risk of them pointing nowhere either accidentally or due to an attack. Convert all drivers to embed struct hotplug_slot in their internal slot struct. The "private" pointer in struct hotplug_slot thereby becomes unused, so drop it. Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Sebastian Ott # drivers/pci/hotplug/s390* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- include/linux/pci_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 6f07a4e1de8d..7acc9f91e72b 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -50,14 +50,11 @@ struct hotplug_slot_ops { /** * struct hotplug_slot - used to register a physical slot with the hotplug pci core * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot - * @private: used by the hotplug pci controller driver to store whatever it - * needs. * @owner: The module owner of this structure * @mod_name: The module name (KBUILD_MODNAME) of this structure */ struct hotplug_slot { const struct hotplug_slot_ops *ops; - void *private; /* Variables below this are for use only by the hotplug pci core. */ struct list_head slot_list; -- cgit v1.2.3 From 8fce3331702316d4bcfeb0771c09ac75d2192bbc Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 17 Sep 2018 09:22:56 +0100 Subject: net: stmmac: Rework coalesce timer and fix multi-queue races This follows David Miller advice and tries to fix coalesce timer in multi-queue scenarios. We are now using per-queue coalesce values and per-queue TX timer. Coalesce timer default values was changed to 1ms and the coalesce frames to 25. Tested in B2B setup between XGMAC2 and GMAC5. Signed-off-by: Jose Abreu Fixes: ce736788e8a ("net: stmmac: adding multiple buffers for TX") Cc: Florian Fainelli Cc: Neil Armstrong Cc: Jerome Brunet Cc: Martin Blumenstingl Cc: David S. Miller Cc: Joao Pinto Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c43e9a01b892..7ddfc65586b0 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -30,6 +30,7 @@ #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 +#define STMMAC_CH_MAX 8 #define STMMAC_RX_COE_NONE 0 #define STMMAC_RX_COE_TYPE1 1 -- cgit v1.2.3 From 14d73416792afa84f6a7245ee474d2432069da56 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Mon, 17 Sep 2018 18:46:55 +0800 Subject: veth: rename pcpu_vstats as pcpu_lstats struct pcpu_vstats and pcpu_lstats have same members and usage, and pcpu_lstats is used in many files, so rename pcpu_vstats as pcpu_lstats to reduce duplicate definition Signed-off-by: Zhang Yu Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index baed5d5088c5..1cbbf77a685f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2000,7 +2000,6 @@ struct net_device { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; - struct pcpu_vstats __percpu *vstats; }; #if IS_ENABLED(CONFIG_GARP) -- cgit v1.2.3 From efc463adbccf709c5dbaf6cfbf84b7e94b62810a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 16 Apr 2018 14:18:26 -0500 Subject: signal: Simplify tracehook_report_syscall_exit Replace user_single_step_siginfo with user_single_step_report that allocates siginfo structure on the stack and sends it. This allows tracehook_report_syscall_exit to become a simple if statement that calls user_single_step_report or ptrace_report_syscall depending on the value of step. Update the default helper function now called user_single_step_report to explicitly set si_code to SI_USER and to set si_uid and si_pid to 0. The default helper has always been doing this (using memset) but it was far from obvious. The powerpc helper can now just call force_sig_fault. The x86 helper can now just call send_sigtrap. Unfortunately the default implementation of user_single_step_report can not use force_sig_fault as it does not use a SIGTRAP si_code. So it has to carefully setup the siginfo and use use force_sig_info. The net result is code that is easier to understand and simpler to maintain. Ref: 85ec7fd9f8e5 ("ptrace: introduce user_single_step_siginfo() helper") Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 17 +++++++++++------ include/linux/tracehook.h | 13 ++++--------- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4f36431c380b..1de2235511c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -336,14 +336,19 @@ static inline void user_enable_block_step(struct task_struct *task) extern void user_enable_block_step(struct task_struct *); #endif /* arch_has_block_step */ -#ifdef ARCH_HAS_USER_SINGLE_STEP_INFO -extern void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, siginfo_t *info); +#ifdef ARCH_HAS_USER_SINGLE_STEP_REPORT +extern void user_single_step_report(struct pt_regs *regs); #else -static inline void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, siginfo_t *info) +static inline void user_single_step_report(struct pt_regs *regs) { - info->si_signo = SIGTRAP; + siginfo_t info; + clear_siginfo(&info); + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = SI_USER; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info(info.si_signo, &info, current); } #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 05589a3e37f4..40b0b4c1bf7b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -123,15 +123,10 @@ static inline __must_check int tracehook_report_syscall_entry( */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { - if (step) { - siginfo_t info; - clear_siginfo(&info); - user_single_step_siginfo(current, regs, &info); - force_sig_info(SIGTRAP, &info, current); - return; - } - - ptrace_report_syscall(regs); + if (step) + user_single_step_report(regs); + else + ptrace_report_syscall(regs); } /** -- cgit v1.2.3 From 2dfd184abd38fd72d80715fa8b00c9de78490200 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 18 Sep 2018 16:20:18 -0400 Subject: flow_dissector: fix build failure without CONFIG_NET If boolean CONFIG_BPF_SYSCALL is enabled, kernel/bpf/syscall.c will call flow_dissector functions from net/core/flow_dissector.c. This causes this build failure if CONFIG_NET is disabled: kernel/bpf/syscall.o: In function `__x64_sys_bpf': syscall.c:(.text+0x3278): undefined reference to `skb_flow_dissector_bpf_prog_attach' syscall.c:(.text+0x3310): undefined reference to `skb_flow_dissector_bpf_prog_detach' kernel/bpf/syscall.o:(.rodata+0x3f0): undefined reference to `flow_dissector_prog_ops' kernel/bpf/verifier.o:(.rodata+0x250): undefined reference to `flow_dissector_verifier_ops' Analogous to other optional BPF program types in syscall.c, add stubs if the relevant functions are not compiled and move the BPF_PROG_TYPE definition in the #ifdef CONFIG_NET block. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Reported-by: Randy Dunlap Signed-off-by: Willem de Bruijn Acked-by: Randy Dunlap # build-tested Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 2 +- include/linux/skbuff.h | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 22083712dd18..c9bd6fb765b0 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -16,6 +16,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) @@ -32,7 +33,6 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) #endif -BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ce0e863f02a2..76be85ea392a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1194,10 +1194,23 @@ 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_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_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 bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, -- cgit v1.2.3 From eb7c8743d6cf489e30091e6656fd4d3306621e9a Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 5 Sep 2018 16:17:14 +0530 Subject: OPP: Pass index to _of_init_opp_table() This is a preparatory patch required for the next commit which will start using OPP table's node pointer in _of_init_opp_table(), which requires the index in order to read the OPP table's phandle. This commit adds the index argument in the call chains in order to get it delivered to _of_init_opp_table(). Tested-by: Niklas Cassel 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 099b31960dec..5d399eeef172 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -79,6 +79,7 @@ struct dev_pm_set_opp_data { #if defined(CONFIG_PM_OPP) struct opp_table *dev_pm_opp_get_opp_table(struct device *dev); +struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index); void dev_pm_opp_put_opp_table(struct opp_table *opp_table); unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); @@ -136,6 +137,11 @@ static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) return ERR_PTR(-ENOTSUPP); } +static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) -- cgit v1.2.3 From 53dd9dce6979bc54d64a3a09a2fb20187a025be7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 13 Sep 2018 15:16:22 -0500 Subject: libfdt: Ensure INT_MAX is defined in libfdt_env.h The next update of libfdt has a new dependency on INT_MAX. Update the instances of libfdt_env.h in the kernel to either include the necessary header with the definition or define it locally. Cc: Russell King Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Rob Herring --- include/linux/libfdt_env.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index c6ac1fe7ec68..edb0f0c30904 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -2,6 +2,7 @@ #ifndef LIBFDT_ENV_H #define LIBFDT_ENV_H +#include /* For INT_MAX */ #include #include -- cgit v1.2.3 From 822f312d47f0200dc0999c9f006fe94aa43bd0bd Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 12 Sep 2018 15:33:45 +0200 Subject: kvm: x86: make kvm_{load|put}_guest_fpu() static The functions kvm_load_guest_fpu() kvm_put_guest_fpu() are only used locally, make them static. This requires also that both functions are moved because they are used before their implementation. Those functions were exported (via EXPORT_SYMBOL) before commit e5bb40251a920 ("KVM: Drop kvm_{load,put}_guest_fpu() exports"). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0205aee44ded..c926698040e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -733,8 +733,6 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); -- cgit v1.2.3 From f3ecc0ff0457eae93503792c6fc35921fa8a6204 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 19 Aug 2018 14:53:20 +0200 Subject: dma-mapping: move the dma_coherent flag to struct device Various architectures support both coherent and non-coherent dma on a per-device basis. Move the dma_noncoherent flag from the mips archdata field to struct device proper to prepare the infrastructure for reuse on other architectures. Signed-off-by: Christoph Hellwig Acked-by: Paul Burton Acked-by: Greg Kroah-Hartman --- include/linux/device.h | 7 +++++++ include/linux/dma-noncoherent.h | 16 ++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..983506789402 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -927,6 +927,8 @@ struct dev_links_info { * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. + * @dma_coherent: this particular device is dma coherent, even if the + * architecture supports non-coherent devices. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -1016,6 +1018,11 @@ struct device { bool offline_disabled:1; bool offline:1; bool of_node_reused:1; +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) + bool dma_coherent:1; +#endif }; static inline struct device *kobj_to_dev(struct kobject *kobj) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index a0aa00cc909d..ce9732506ef4 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -4,6 +4,22 @@ #include +#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H +#include +#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) +static inline bool dev_is_dma_coherent(struct device *dev) +{ + return dev->dma_coherent; +} +#else +static inline bool dev_is_dma_coherent(struct device *dev) +{ + return true; +} +#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ + void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, -- cgit v1.2.3 From bc3ec75de5452db59b683487867ba562b950708a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 8 Sep 2018 11:22:43 +0200 Subject: dma-mapping: merge direct and noncoherent ops All the cache maintainance is already stubbed out when not enabled, but merging the two allows us to nicely handle the case where cache maintainance is required for some devices, but not others. Signed-off-by: Christoph Hellwig Acked-by: Paul Burton # MIPS parts --- include/linux/dma-direct.h | 4 ++++ include/linux/dma-mapping.h | 1 - include/linux/dma-noncoherent.h | 5 ----- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 8d9f33febde5..86a59ba5a7f3 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -59,6 +59,10 @@ 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, dma_addr_t dma_addr, unsigned long attrs); +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); 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); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index eafd6f318e78..8f2001181cd1 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -136,7 +136,6 @@ struct dma_map_ops { }; extern const struct dma_map_ops dma_direct_ops; -extern const struct dma_map_ops dma_noncoherent_ops; extern const struct dma_map_ops dma_virt_ops; #define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index ce9732506ef4..3f503025a0cd 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -24,14 +24,9 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); - -#ifdef CONFIG_DMA_NONCOHERENT_MMAP int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); -#else -#define arch_dma_mmap NULL -#endif /* CONFIG_DMA_NONCOHERENT_MMAP */ #ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, -- cgit v1.2.3 From 58b0440663ec11372befb8ead0ee7099d8878590 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Sep 2018 08:55:28 +0200 Subject: dma-mapping: consolidate the dma mmap implementations The only functional differences (modulo a few missing fixes in the arch code) is that architectures without coherent caches need a hook to convert a virtual or dma address into a pfn, given that we don't have the kernel linear mapping available for the otherwise easy virt_to_page call. As a side effect we can support mmap of the per-device coherent area even on architectures not providing the callback, and we make previous dangerous default methods dma_common_mmap actually save for non-coherent architectures by rejecting it without the right helper. In addition to that we need a hook so that some architectures can override the protection bits when mmaping a dma coherent allocations. Signed-off-by: Christoph Hellwig Acked-by: Paul Burton # MIPS parts --- include/linux/dma-mapping.h | 5 +++-- include/linux/dma-noncoherent.h | 10 ++++++++-- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 8f2001181cd1..c3378d4e0d57 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -444,7 +444,8 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size, } extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size); + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); void *dma_common_contiguous_remap(struct page *page, size_t size, unsigned long vm_flags, @@ -476,7 +477,7 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, BUG_ON(!ops); if (ops->mmap) return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs); - return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size); + return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); } #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index 3f503025a0cd..9051b055beec 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -24,9 +24,15 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); -int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, +long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, + dma_addr_t dma_addr); + +#ifdef CONFIG_ARCH_HAS_DMA_MMAP_PGPROT +pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs); +#else +# define arch_dma_mmap_pgprot(dev, prot, attrs) pgprot_noncached(prot) +#endif #ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size, -- cgit v1.2.3 From 9406a49fd1f4379409ed87b29fdaa259b0441912 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 23 Aug 2018 09:39:38 +0200 Subject: dma-mapping: support non-coherent devices in dma_common_get_sgtable We can use the arch_dma_coherent_to_pfn hook to provide a ->get_sgtable implementation. Note that this isn't an endorsement of this interface (which is a horrible bad idea), but it is required to move arm64 over to the generic code without a loss of functionality. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index c3378d4e0d57..bd81e74cca7b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -483,8 +483,8 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) int -dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t dma_addr, size_t size); +dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, + dma_addr_t dma_addr, size_t size, unsigned long attrs); static inline int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, @@ -496,7 +496,8 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, if (ops->get_sgtable) return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); - return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size); + return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size, + attrs); } #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) -- cgit v1.2.3 From 16caf1fa37db4722d8d8c7bc26177279949d75a6 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 4 Sep 2018 17:18:55 +0200 Subject: usb: chipidea: Add dynamic pinctrl selection Some hardware implementations require to configure pins differently according to the USB role (host/device), this can be an update of the pins routing or a simple GPIO value change. This patch introduces new optional "host" and "device" pinctrls. If these pinctrls are defined by the device, they are respectively selected on host/device role start. If a default pinctrl exist, it is restored on host/device role stop. Signed-off-by: Loic Poulain Signed-off-by: Peter Chen --- include/linux/usb/chipidea.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 07f99362bc90..63758c399e4e 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -77,6 +77,12 @@ struct ci_hdrc_platform_data { struct ci_hdrc_cable vbus_extcon; struct ci_hdrc_cable id_extcon; u32 phy_clkgate_delay_us; + + /* pins */ + struct pinctrl *pctl; + struct pinctrl_state *pins_default; + struct pinctrl_state *pins_host; + struct pinctrl_state *pins_device; }; /* Default offset of capability registers */ -- cgit v1.2.3 From 457b42f0aa1c397745ada6083bf81b9479ab19fe Mon Sep 17 00:00:00 2001 From: Liu Xiang Date: Sun, 22 Jul 2018 21:33:56 +0800 Subject: power: supply: bq27xxx: Add support for BQ27411 According to the datasheet, bq27411 is similar to bq27421. Signed-off-by: Liu Xiang Reviewed-by: Andrew F. Davis 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 d6355f49fbae..507c5e214c42 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -24,6 +24,7 @@ enum bq27xxx_chip { BQ27546, BQ27742, BQ27545, /* bq27545 */ + BQ27411, BQ27421, /* bq27421, bq27441, bq27621 */ BQ27425, BQ27426, -- cgit v1.2.3 From bd93227897007bac09c44fe67626035303905900 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 22 Aug 2018 22:43:00 +0200 Subject: USB: EHCI: ehci-mv: remove private_init It's unused. Signed-off-by: Lubomir Rintel Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/mv_usb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mv_usb.h b/include/linux/platform_data/mv_usb.h index 98b7925f1a2d..c0f624aca81c 100644 --- a/include/linux/platform_data/mv_usb.h +++ b/include/linux/platform_data/mv_usb.h @@ -48,6 +48,5 @@ struct mv_usb_platform_data { int (*phy_init)(void __iomem *regbase); void (*phy_deinit)(void __iomem *regbase); int (*set_vbus)(unsigned int vbus); - int (*private_init)(void __iomem *opregs, void __iomem *phyregs); }; #endif -- cgit v1.2.3 From cd7753d371388e712e3ee52b693459f9b71aaac2 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 20 Sep 2018 14:23:40 +0300 Subject: drivers: base: Helpers for adding device connection descriptions Introducing helpers for adding and removing multiple device connection descriptions at once. Acked-by: Hans de Goede Tested-by: Hans de Goede Signed-off-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..3f1066a9e1c3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -773,6 +773,30 @@ struct device *device_connection_find(struct device *dev, const char *con_id); void device_connection_add(struct device_connection *con); void device_connection_remove(struct device_connection *con); +/** + * device_connections_add - Add multiple device connections at once + * @cons: Zero terminated array of device connection descriptors + */ +static inline void device_connections_add(struct device_connection *cons) +{ + struct device_connection *c; + + for (c = cons; c->endpoint[0]; c++) + device_connection_add(c); +} + +/** + * device_connections_remove - Remove multiple device connections at once + * @cons: Zero terminated array of device connection descriptors + */ +static inline void device_connections_remove(struct device_connection *cons) +{ + struct device_connection *c; + + for (c = cons; c->endpoint[0]; c++) + device_connection_remove(c); +} + /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. -- cgit v1.2.3 From b1078c355d76769b5ddefc67d143fbd9b6e52c05 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Thu, 20 Sep 2018 13:41:52 +0200 Subject: of: base: Introduce of_alias_get_alias_list() to check alias IDs The function travels the lookup table to record alias ids for the given device match structures and alias stem. This function will be used by serial drivers to check if requested alias is allocated or free to use. Signed-off-by: Michal Simek Reviewed-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- include/linux/of.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..d51457b40725 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -392,6 +392,9 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); +extern int of_alias_get_alias_list(const struct of_device_id *matches, + const char *stem, unsigned long *bitmap, + unsigned int nbits); extern int of_machine_is_compatible(const char *compat); @@ -893,6 +896,13 @@ static inline int of_alias_get_highest_id(const char *stem) return -ENOSYS; } +static inline int of_alias_get_alias_list(const struct of_device_id *matches, + const char *stem, unsigned long *bitmap, + unsigned int nbits) +{ + return -ENOSYS; +} + static inline int of_machine_is_compatible(const char *compat) { return 0; -- cgit v1.2.3 From d124b44f09cab67fc6da4a4513417e3e54b01efc Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 18 Sep 2018 18:55:41 +0200 Subject: Compiler Attributes: naked was fixed in gcc 4.6 Commit 9c695203a7dd ("compiler-gcc.h: gcc-4.5 needs noclone and noinline on __naked functions") added noinline and noclone as a workaround for a gcc 4.5 bug, which was resolved in 4.6.0. Since now the minimum gcc supported version is 4.6, we can clean it up. See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=44290 and https://godbolt.org/z/h6NMIL Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Rasmus Villemoes Cc: Eli Friedman Cc: Christopher Li Cc: Kees Cook Cc: Ingo Molnar Cc: Geert Uytterhoeven Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Cc: Joe Perches Cc: Dominique Martinet Cc: Linus Torvalds Cc: linux-sparse@vger.kernel.org Tested-by: Stefan Agner Reviewed-by: Stefan Agner Reviewed-by: Luc Van Oostenryck Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler-gcc.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 763bbad1e258..25d3dd6b2702 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -84,14 +84,8 @@ * to trace naked functions because then mcount is called without * stack and frame pointer being set up and there is no chance to * restore the lr register to the value before mcount was called. - * - * The asm() bodies of naked functions often depend on standard calling - * conventions, therefore they must be noinline and noclone. - * - * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. - * See GCC PR44290. */ -#define __naked __attribute__((naked)) noinline __noclone notrace +#define __naked __attribute__((naked)) notrace #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -- cgit v1.2.3 From ae596de1a0c8c2c924dc99d23c026259372ab234 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 18 Sep 2018 18:55:42 +0200 Subject: Compiler Attributes: naked can be shared The naked attribute is supported by at least gcc >= 4.6 (for ARM, which is the only current user), gcc >= 8 (for x86), clang >= 3.1 and icc >= 13. See https://godbolt.org/z/350Dyc Therefore, move it out of compiler-gcc.h so that the definition is shared by all compilers. This also fixes Clang support for ARM32 --- 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"). Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Rasmus Villemoes Cc: Eli Friedman Cc: Christopher Li Cc: Kees Cook Cc: Ingo Molnar Cc: Geert Uytterhoeven Cc: Greg Kroah-Hartman Cc: Masahiro Yamada Cc: Joe Perches Cc: Dominique Martinet Cc: Linus Torvalds Cc: linux-sparse@vger.kernel.org Suggested-by: Arnd Bergmann Tested-by: Stefan Agner Reviewed-by: Stefan Agner Reviewed-by: Luc Van Oostenryck Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda Signed-off-by: Greg Kroah-Hartman --- include/linux/compiler-gcc.h | 8 -------- include/linux/compiler_types.h | 8 ++++++++ 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 25d3dd6b2702..4d36b27214fd 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -79,14 +79,6 @@ #define __noretpoline __attribute__((indirect_branch("keep"))) #endif -/* - * it doesn't make sense on ARM (currently the only user of __naked) - * to trace naked functions because then mcount is called without - * stack and frame pointer being set up and there is no chance to - * restore the lr register to the value before mcount was called. - */ -#define __naked __attribute__((naked)) notrace - #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) #define __optimize(level) __attribute__((__optimize__(level))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..db192becfec4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -226,6 +226,14 @@ struct ftrace_likely_data { #define notrace __attribute__((no_instrument_function)) #endif +/* + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + */ +#define __naked __attribute__((naked)) notrace + #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) /* -- cgit v1.2.3 From 329357723f5e8e2d7fc3144fb79936b51ce63b76 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 31 Aug 2018 14:13:22 -0500 Subject: gpio: davinci: Remove unused member of davinci_gpio_controller This was added as part of the patch in the fixes below, but was not needed or used, remove this here. Fixes: 8e11047b8f3c ("gpio: davinci: Add support for multiple GPIO controllers") Tested-by: Keerthy Acked-by: Keerthy Signed-off-by: Andrew F. Davis Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-davinci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index 57a5a35e0073..b8e4957e7568 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -43,7 +43,6 @@ struct davinci_gpio_controller { void __iomem *regs[MAX_REGS_BANKS]; int gpio_unbanked; int irqs[MAX_INT_PER_BANK]; - unsigned int base; }; /* -- cgit v1.2.3 From c36219d9d8df11641d28c6bd0698459485b1709b Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 31 Aug 2018 14:13:25 -0500 Subject: gpio: davinci: Remove unneeded GPIO macro This macro does nothing and has only one user, remove it. Signed-off-by: Andrew F. Davis Tested-by: Keerthy Acked-by: Keerthy Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-davinci.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index b8e4957e7568..47695b342883 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -45,11 +45,6 @@ struct davinci_gpio_controller { int irqs[MAX_INT_PER_BANK]; }; -/* - * basic gpio routines - */ -#define GPIO(X) (X) /* 0 <= X <= (DAVINCI_N_GPIO - 1) */ - /* Convert GPIO signal to GPIO pin number */ #define GPIO_TO_PIN(bank, gpio) (16 * (bank) + (gpio)) -- cgit v1.2.3 From 79b73ff9b2a3ef312d8fa30894fd963c80ded466 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Fri, 31 Aug 2018 14:13:26 -0500 Subject: gpio: davinci: Move driver local definitions to driver These defines, structs and inline functions are used only internally by the driver, they do not belong in platform_data. Move them. Signed-off-by: Andrew F. Davis Tested-by: Keerthy Acked-by: Keerthy Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-davinci.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index 47695b342883..f92a47e18034 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -16,40 +16,12 @@ #ifndef __DAVINCI_GPIO_PLATFORM_H #define __DAVINCI_GPIO_PLATFORM_H -#include -#include - -#include - -#define MAX_REGS_BANKS 5 -#define MAX_INT_PER_BANK 32 - struct davinci_gpio_platform_data { u32 ngpio; u32 gpio_unbanked; }; -struct davinci_gpio_irq_data { - void __iomem *regs; - struct davinci_gpio_controller *chip; - int bank_num; -}; - -struct davinci_gpio_controller { - struct gpio_chip chip; - struct irq_domain *irq_domain; - /* Serialize access to GPIO registers */ - spinlock_t lock; - void __iomem *regs[MAX_REGS_BANKS]; - int gpio_unbanked; - int irqs[MAX_INT_PER_BANK]; -}; - /* Convert GPIO signal to GPIO pin number */ #define GPIO_TO_PIN(bank, gpio) (16 * (bank) + (gpio)) -static inline u32 __gpio_mask(unsigned gpio) -{ - return 1 << (gpio % 32); -} #endif -- cgit v1.2.3 From 60489f085574157c343fc62a32f997fe7346a659 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 20 Sep 2018 09:31:10 +0200 Subject: spi: spi-mem: Add missing description for data.nbytes field Add a description for spi_mem_op.data.nbytes to the kerneldoc header. Fixes: c36ff266dc82 ("spi: Extend the core to ease integration of SPI memory controllers") Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 62722fb7472d..0cfbb1ad8d96 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -79,6 +79,8 @@ enum spi_mem_data_dir { * @dummy.buswidth: number of IO lanes used to transmit the dummy bytes * @data.buswidth: number of IO lanes used to send/receive the data * @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 * @data.buf.in: input buffer * @data.buf.out: output buffer */ -- cgit v1.2.3 From c949a8e8b43f2c75567269bcc9a50d704ae3c420 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 20 Sep 2018 09:31:11 +0200 Subject: spi: spi-mem: Move the DMA-able constraint doc to the kerneldoc header We'd better have that documented in the kerneldoc header, so that it's exposed to the doc generated by Sphinx. Signed-off-by: Boris Brezillon Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 0cfbb1ad8d96..7195fbc234aa 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -81,8 +81,8 @@ enum spi_mem_data_dir { * @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 - * @data.buf.in: input buffer - * @data.buf.out: output buffer + * @data.buf.in: input buffer (must be DMA-able) + * @data.buf.out: output buffer (must be DMA-able) */ struct spi_mem_op { struct { @@ -105,7 +105,6 @@ struct spi_mem_op { u8 buswidth; enum spi_mem_data_dir dir; unsigned int nbytes; - /* buf.{in,out} must be DMA-able. */ union { void *in; const void *out; -- cgit v1.2.3 From 26683316c92ab2d1b330a3a38548328c9b136ad1 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 10 Sep 2018 19:47:22 +0200 Subject: ARM: OMAP1: ams-delta-fiq: Use Instead of defining symbols already defined in linux/platform_data/gpio-omap.h, use that header file. Since we include the header into an assembler code, prevent C only bits from being read in. Signed-off-by: Janusz Krzysztofik Signed-off-by: Tony Lindgren --- include/linux/platform_data/gpio-omap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index 8612855691b2..ed071f76b642 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -24,8 +24,10 @@ #ifndef __ASM_ARCH_OMAP_GPIO_H #define __ASM_ARCH_OMAP_GPIO_H +#ifndef __ASSEMBLER__ #include #include +#endif #define OMAP1_MPUIO_BASE 0xfffb5000 @@ -157,6 +159,7 @@ #define OMAP_MPUIO(nr) (OMAP_MAX_GPIO_LINES + (nr)) #define OMAP_GPIO_IS_MPUIO(nr) ((nr) >= OMAP_MAX_GPIO_LINES) +#ifndef __ASSEMBLER__ struct omap_gpio_reg_offs { u16 revision; u16 direction; @@ -215,5 +218,6 @@ static inline void omap2_gpio_resume_after_idle(void) { } #endif +#endif /* __ASSEMBLER__ */ #endif -- cgit v1.2.3 From e9158b35ef9afb3bf24e0404c8fd4cd723eafa5b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Horia=20Geant=C4=83?= Date: Wed, 12 Sep 2018 11:59:26 +0300 Subject: bus: fsl-mc: add support for dpseci device type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Horia Geantă Acked-by: Laurentiu Tudor Signed-off-by: Herbert Xu --- include/linux/fsl/mc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index f27cb14088a4..5160f06ffbac 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -405,6 +405,7 @@ extern struct device_type fsl_mc_bus_dpcon_type; 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; static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev) { @@ -451,6 +452,11 @@ static inline bool is_fsl_mc_bus_dprtc(const struct fsl_mc_device *mc_dev) return mc_dev->dev.type == &fsl_mc_bus_dprtc_type; } +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; +} + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From c785896b21dd8e156326ff660050b0074d3431df Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Sat, 15 Sep 2018 21:38:24 -0700 Subject: cpufeature: avoid warning when compiling with clang The table id (second) argument to MODULE_DEVICE_TABLE is often referenced otherwise. This is not the case for CPU features. This leads to warnings when building the kernel with Clang: arch/arm/crypto/aes-ce-glue.c:450:1: warning: variable 'cpu_feature_match_AES' is not needed and will not be emitted [-Wunneeded-internal-declaration] module_cpu_feature_match(AES, aes_init); ^ Avoid warnings by using __maybe_unused, similar to commit 1f318a8bafcf ("modules: mark __inittest/__exittest as __maybe_unused"). Fixes: 67bad2fdb754 ("cpu: add generic support for CPU feature based module autoloading") Signed-off-by: Stefan Agner Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/linux/cpufeature.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h index 986c06c88d81..84d3c81b5978 100644 --- a/include/linux/cpufeature.h +++ b/include/linux/cpufeature.h @@ -45,7 +45,7 @@ * 'asm/cpufeature.h' of your favorite architecture. */ #define module_cpu_feature_match(x, __initfunc) \ -static struct cpu_feature const cpu_feature_match_ ## x[] = \ +static struct cpu_feature const __maybe_unused cpu_feature_match_ ## x[] = \ { { .feature = cpu_feature(x) }, { } }; \ MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x); \ \ -- cgit v1.2.3 From 5d773ff41a7cdf0ef6cc6647435d59f0cf53e7b1 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Mon, 17 Sep 2018 13:30:46 +0300 Subject: net/mlx5: Rename incorrect naming in IFC file Remove a trailing underscore from the multicast/unicast names. Signed-off-by: Mark Bloch Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3a4a2e0567e9..4c7a1d25d73b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2559,8 +2559,8 @@ enum { }; enum { - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_ = 0x1, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST_ = 0x2, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST = 0x1, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST = 0x2, }; struct mlx5_ifc_tirc_bits { -- cgit v1.2.3 From b57e99b4b8b0ebdf9707424e7ddc0c392bdc5fe6 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 21 Sep 2018 16:44:34 -0700 Subject: block: use nanosecond resolution for iostat Klaus Kusche reported that the I/O busy time in /proc/diskstats was not updating properly on 4.18. This is because we started using ktime to track elapsed time, and we convert nanoseconds to jiffies when we update the partition counter. However, this gets rounded down, so any I/Os that take less than a jiffy are not accounted for. Previously in this case, the value of jiffies would sometimes increment while we were doing I/O, so at least some I/Os were accounted for. Let's convert the stats to use nanoseconds internally. We still report milliseconds as before, now more accurately than ever. The value is still truncated to 32 bits for backwards compatibility. Fixes: 522a777566f5 ("block: consolidate struct request timestamp fields") Cc: stable@vger.kernel.org Reported-by: Klaus Kusche Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/genhd.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 57864422a2c8..25c08c6c7f99 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -83,10 +83,10 @@ struct partition { } __attribute__((packed)); 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 ticks[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; }; @@ -354,6 +354,9 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ +#define part_stat_read_msecs(part, which) \ + div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC) + #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 27e6fa996c534c32702aa4d32db0ffa383acd050 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:26 -0400 Subject: blkcg: fix ref count issue with bio_blkcg using task_css The accessor function bio_blkcg either returns the blkcg associated with the bio or finds one in the current context. This can cause an issue when trying to associate a bio with a blkcg. Particularly, it's the third case that is problematic: return css_to_blkcg(task_css(current, io_cgrp_id)); As the above may race against task migration and the cgroup exiting, it is not always ok to take a reference on the blkcg returned from bio_blkcg. This patch adds association ahead of calling bio_blkcg rather than after. This makes association a required and explicit step along the code paths for calling bio_blkcg. blk_get_rl is modified as well to get a reference to the blkcg it may use and blk_put_rl will always put the reference back. Association is also moved above the bio_blkcg call to ensure it will not return NULL in blk-iolatency. BFQ and CFQ utilize this flaw, but due to the complexity, I do not want to address this in this series. I've created a private version of the function with notes not to use it describing the flaw. Hopefully soon, that code can be cleaned up. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 101 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 93 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6d766a19f2bb..24067a1f8b36 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -230,22 +230,100 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); +/** + * blkcg_css - find the current css + * + * Find the css associated with either the kthread or the current task. + * This may return a dying css, so it is up to the caller to use tryget logic + * to confirm it is alive and well. + */ +static inline struct cgroup_subsys_state *blkcg_css(void) +{ + struct cgroup_subsys_state *css; + + css = kthread_blkcg(); + if (css) + return css; + return task_css(current, io_cgrp_id); +} + +/** + * blkcg_get_css - find and get a reference to the css + * + * Find the css associated with either the kthread or the current task. + * This takes a reference on the blkcg which will need to be managed by the + * caller. + */ +static inline struct cgroup_subsys_state *blkcg_get_css(void) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + + css = kthread_blkcg(); + if (css) { + css_get(css); + } else { + /* + * This is a bit complicated. It is possible task_css is seeing + * an old css pointer here. This is caused by the current + * thread migrating away from this cgroup and this cgroup dying. + * css_tryget() will fail when trying to take a ref on a cgroup + * that's ref count has hit 0. + * + * Therefore, if it does fail, this means current must have + * been swapped away already and this is waiting for it to + * propagate on the polling cpu. Hence the use of cpu_relax(). + */ + while (true) { + css = task_css(current, io_cgrp_id); + if (likely(css_tryget(css))) + break; + cpu_relax(); + } + } + + rcu_read_unlock(); + + return css; +} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -static inline struct blkcg *bio_blkcg(struct bio *bio) +/** + * __bio_blkcg - internal version of bio_blkcg for bfq and cfq + * + * DO NOT USE. + * There is a flaw using this version of the function. In particular, this was + * used in a broken paradigm where association was called on the given css. It + * is possible though that the returned css from task_css() is in the process + * of dying due to migration of the current task. So it is improper to assume + * *_get() is going to succeed. Both BFQ and CFQ rely on this logic and will + * take additional work to handle more gracefully. + */ +static inline struct blkcg *__bio_blkcg(struct bio *bio) { - struct cgroup_subsys_state *css; + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + return css_to_blkcg(blkcg_css()); +} +/** + * bio_blkcg - grab the blkcg associated with a bio + * @bio: target bio + * + * This returns the blkcg associated with a bio, NULL if not associated. + * Callers are expected to either handle NULL or know association has been + * done prior to calling this. + */ +static inline struct blkcg *bio_blkcg(struct bio *bio) +{ if (bio && bio->bi_css) return css_to_blkcg(bio->bi_css); - css = kthread_blkcg(); - if (css) - return css_to_blkcg(css); - return css_to_blkcg(task_css(current, io_cgrp_id)); + return NULL; } static inline bool blk_cgroup_congested(void) @@ -534,6 +612,10 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); blkcg = bio_blkcg(bio); + if (blkcg) + css_get(&blkcg->css); + else + blkcg = css_to_blkcg(blkcg_get_css()); /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) @@ -565,6 +647,8 @@ root_rl: */ static inline void blk_put_rl(struct request_list *rl) { + /* an additional ref is always taken for rl */ + css_put(&rl->blkg->blkcg->css); if (rl->blkg->blkcg != &blkcg_root) blkg_put(rl->blkg); } @@ -805,10 +889,10 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, bool throtl = false; rcu_read_lock(); - blkcg = bio_blkcg(bio); /* associate blkcg if bio hasn't attached one */ - bio_associate_blkcg(bio, &blkcg->css); + bio_associate_blkcg(bio, NULL); + blkcg = bio_blkcg(bio); blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { @@ -930,6 +1014,7 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } +static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, -- cgit v1.2.3 From 49f4c2dc2b5066e9211101c59cc0828e81d41614 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:27 -0400 Subject: blkcg: update blkg_lookup_create to do locking To know when to create a blkg, the general pattern is to do a blkg_lookup and if that fails, lock and then do a lookup again and if that fails finally create. It doesn't make much sense for everyone who wants to do creation to write this themselves. This changes blkg_lookup_create to do locking and implement this pattern. The old blkg_lookup_create is renamed to __blkg_lookup_create. If a call site wants to do its own error handling or already owns the queue lock, they can use __blkg_lookup_create. This will be used in upcoming patches. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Reviewed-by: Liu Bo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 24067a1f8b36..cc0f238530f6 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -184,6 +184,8 @@ extern struct cgroup_subsys_state * const blkcg_root_css; 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); @@ -897,7 +899,7 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { spin_lock_irq(q->queue_lock); - blkg = blkg_lookup_create(blkcg, q); + blkg = __blkg_lookup_create(blkcg, q); if (IS_ERR(blkg)) blkg = NULL; spin_unlock_irq(q->queue_lock); -- cgit v1.2.3 From 07b05bcc3213ac9f8c28c9d835b4bf3d5798cc60 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:28 -0400 Subject: blkcg: convert blkg_lookup_create to find closest blkg There are several scenarios where blkg_lookup_create can fail. Examples include the blkcg dying, request_queue is dying, or simply being OOM. At the end of the day, most handle this by simply falling back to the q->root_blkg and calling it a day. This patch implements the notion of closest blkg. During blkg_lookup_create, if it fails to create, return the closest blkg found or the q->root_blkg. blkg_try_get_closest is introduced and used during association so a bio is always attached to a blkg. Acked-by: Tejun Heo Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index cc0f238530f6..1fbff1bbb651 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -549,6 +549,20 @@ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) return NULL; } +/** + * blkg_try_get_closest - try and get a blkg ref on the closet blkg + * @blkg: blkg to get + * + * This walks up the blkg tree to find the closest non-dying blkg and returns + * the blkg that it did association with as it may not be the passed in blkg. + */ +static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) +{ + while (!atomic_inc_not_zero(&blkg->refcnt)) + blkg = blkg->parent; + + return blkg; +} void __blkg_release_rcu(struct rcu_head *rcu); -- cgit v1.2.3 From a7b39b4e961c4e2b3ed837803a7441a65c90ce33 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:29 -0400 Subject: blkcg: always associate a bio with a blkg Previously, blkg's were only assigned as needed by blk-iolatency and blk-throttle. bio->css was also always being associated while blkg was being looked up and then thrown away in blkcg_bio_issue_check. This patch begins the cleanup of bio->css and bio->bi_blkg by always associating a blkg in blkcg_bio_issue_check. This tries to create the blkg, but if it is not possible, falls back to using the root_blkg of the request_queue. Therefore, a bio will always be associated with a blkg. The duplicate association logic is removed from blk-throttle and blk-iolatency. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 +++ include/linux/blk-cgroup.h | 16 ++-------------- 2 files changed, 5 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 14b4fa266357..829cd0bb407d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -542,11 +542,14 @@ static inline int bio_associate_blkcg_from_page(struct bio *bio, #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); +int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } +static inline int bio_associate_create_blkg(struct request_queue *q, + struct bio *bio) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1fbff1bbb651..6e33ad1d92b4 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -900,29 +900,17 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { - struct blkcg *blkcg; struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); - /* associate blkcg if bio hasn't attached one */ - bio_associate_blkcg(bio, NULL); - blkcg = bio_blkcg(bio); - - blkg = blkg_lookup(blkcg, q); - if (unlikely(!blkg)) { - spin_lock_irq(q->queue_lock); - blkg = __blkg_lookup_create(blkcg, q); - if (IS_ERR(blkg)) - blkg = NULL; - spin_unlock_irq(q->queue_lock); - } + bio_associate_create_blkg(q, bio); + blkg = bio->bi_blkg; throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { - blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the -- cgit v1.2.3 From 5bf9a1f3b4efef7e463105dde8bba4d2397909c2 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:30 -0400 Subject: blkcg: consolidate bio_issue_init to be a part of core bio_issue_init among other things initializes the timestamp for an IO. Rather than have this logic handled by policies, this consolidates it to be on the init paths (normal, clone, bounce clone). Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Reviewed-by: Liu Bo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6e33ad1d92b4..a6b6e741a75e 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -897,6 +897,12 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif + +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) { @@ -922,6 +928,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } + blkcg_bio_issue_init(bio); + rcu_read_unlock(); return !throtl; } @@ -1034,6 +1042,7 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } +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; } -- cgit v1.2.3 From 74b7c02a9bc124ee3df0d77880ee26db0a325516 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:31 -0400 Subject: blkcg: associate a blkg for pages being evicted by swap A prior patch in this series added blkg association to bios issued by cgroups. There are two other paths that we want to attribute work back to the appropriate cgroup: swap and writeback. Here we modify the way swap tags bios to include the blkg. Writeback will be tackle in the next patch. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 829cd0bb407d..c73a870ebc0e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -533,21 +533,26 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkcg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); +int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css); int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } +static inline int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ return 0; } static inline int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -- cgit v1.2.3 From bdc2491708c47601603918a9a20acddef6e1d814 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:32 -0400 Subject: blkcg: associate writeback bios with a blkg One of the goals of this series is to remove a separate reference to the css of the bio. This can and should be accessed via bio_blkcg. In this patch, the wbc_init_bio call is changed such that it must be called after a queue has been associated with the bio. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/writeback.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fdfd04e348f6..738a0c24874f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,7 +246,8 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. + * writeback context. Must be called after the bio has been associated with + * a device. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -257,7 +258,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkcg(bio, wbc->wb->blkcg_css); + bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ -- cgit v1.2.3 From c839e7a03f92bafd71fd145b470dcdc7f43f2d4c Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:33 -0400 Subject: blkcg: remove bio->bi_css and instead use bio->bi_blkg Prior patches ensured that all bios are now associated with some blkg. This now makes bio->bi_css unnecessary as blkg maintains a reference to the blkcg already. This patch removes the field bi_css and transfers corresponding uses to access via bi_blkg. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 9 +++------ include/linux/blk-cgroup.h | 8 ++++---- include/linux/blk_types.h | 1 - 3 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index c73a870ebc0e..e973876625a8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -540,24 +540,21 @@ static inline int bio_associate_blkg_from_page(struct bio *bio, #endif #ifdef CONFIG_BLK_CGROUP -int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); int bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkcg_association(struct bio *dst, struct bio *src); +void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkcg(struct bio *bio, - struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { return 0; } static inline int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkcg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a6b6e741a75e..c41cfcc2b4d8 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -308,8 +308,8 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) */ static inline struct blkcg *__bio_blkcg(struct bio *bio) { - if (bio && bio->bi_css) - return css_to_blkcg(bio->bi_css); + if (bio && bio->bi_blkg) + return bio->bi_blkg->blkcg; return css_to_blkcg(blkcg_css()); } @@ -323,8 +323,8 @@ static inline struct blkcg *__bio_blkcg(struct bio *bio) */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_css) - return css_to_blkcg(bio->bi_css); + if (bio && bio->bi_blkg) + return bio->bi_blkg->blkcg; return NULL; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f6dfb30737d8..9578c7ab1eb6 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -178,7 +178,6 @@ struct bio { * release. Read comment on top of bio_associate_current(). */ struct io_context *bi_ioc; - struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif -- cgit v1.2.3 From f0fcb3ec89f37167810e660b0595d9a6155d9807 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:34 -0400 Subject: blkcg: remove additional reference to the css The previous patch in this series removed carrying around a pointer to the css in blkg. However, the blkg association logic still relied on taking a reference on the css to ensure we wouldn't fail in getting a reference for the blkg. Here the implicit dependency on the css is removed. The association continues to rely on the tryget logic walking up the blkg tree. This streamlines the three ways that association can happen: normal, swap, and writeback. Acked-by: Tejun Heo Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 52 ++++------------------------------------------ include/linux/cgroup.h | 2 ++ 2 files changed, 6 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index c41cfcc2b4d8..2951ea3541b1 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -249,47 +249,6 @@ static inline struct cgroup_subsys_state *blkcg_css(void) return task_css(current, io_cgrp_id); } -/** - * blkcg_get_css - find and get a reference to the css - * - * Find the css associated with either the kthread or the current task. - * This takes a reference on the blkcg which will need to be managed by the - * caller. - */ -static inline struct cgroup_subsys_state *blkcg_get_css(void) -{ - struct cgroup_subsys_state *css; - - rcu_read_lock(); - - css = kthread_blkcg(); - if (css) { - css_get(css); - } else { - /* - * This is a bit complicated. It is possible task_css is seeing - * an old css pointer here. This is caused by the current - * thread migrating away from this cgroup and this cgroup dying. - * css_tryget() will fail when trying to take a ref on a cgroup - * that's ref count has hit 0. - * - * Therefore, if it does fail, this means current must have - * been swapped away already and this is waiting for it to - * propagate on the polling cpu. Hence the use of cpu_relax(). - */ - while (true) { - css = task_css(current, io_cgrp_id); - if (likely(css_tryget(css))) - break; - cpu_relax(); - } - } - - rcu_read_unlock(); - - return css; -} - static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; @@ -628,10 +587,8 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); blkcg = bio_blkcg(bio); - if (blkcg) - css_get(&blkcg->css); - else - blkcg = css_to_blkcg(blkcg_get_css()); + if (!blkcg) + blkcg = css_to_blkcg(blkcg_css()); /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) @@ -646,7 +603,8 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, if (unlikely(!blkg)) goto root_rl; - blkg_get(blkg); + if (!blkg_try_get(blkg)) + goto root_rl; rcu_read_unlock(); return &blkg->rl; root_rl: @@ -663,8 +621,6 @@ root_rl: */ static inline void blk_put_rl(struct request_list *rl) { - /* an additional ref is always taken for rl */ - css_put(&rl->blkg->blkcg->css); if (rl->blkg->blkcg != &blkcg_root) blkg_put(rl->blkg); } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 32c553556bbd..b8bcbdeb2eac 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,6 +93,8 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); +struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, + struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, -- cgit v1.2.3 From e2b0989954ae7c80609f77e7ce203bea6d2c54e1 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:35 -0400 Subject: blkcg: cleanup and make blk_get_rl use blkg_lookup_create blk_get_rl is responsible for identifying which request_list a request should be allocated to. Try get logic was added earlier, but semantically the logic was not changed. This patch makes better use of the bio already having a reference to the blkg in the hot path. The cold path uses a better fallback of blkg_lookup_create rather than just blkg_lookup and then falling back to the q->root_rl. If lookup_create fails with anything but -ENODEV, it falls back to q->root_rl. A clarifying comment is added to explain why q->root_rl is used rather than the root blkg's rl. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 2951ea3541b1..d2f7f1b00fcf 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -586,28 +586,36 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); - blkcg = bio_blkcg(bio); - if (!blkcg) - blkcg = css_to_blkcg(blkcg_css()); + if (bio && bio->bi_blkg) { + blkcg = bio->bi_blkg->blkcg; + if (blkcg == &blkcg_root) + goto rl_use_root; + + blkg_get(bio->bi_blkg); + rcu_read_unlock(); + return &bio->bi_blkg->rl; + } - /* bypass blkg lookup and use @q->root_rl directly for root */ + blkcg = css_to_blkcg(blkcg_css()); if (blkcg == &blkcg_root) - goto root_rl; + goto rl_use_root; - /* - * Try to use blkg->rl. blkg lookup may fail under memory pressure - * or if either the blkcg or queue is going away. Fall back to - * root_rl in such cases. - */ blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) - goto root_rl; + blkg = __blkg_lookup_create(blkcg, q); if (!blkg_try_get(blkg)) - goto root_rl; + goto rl_use_root; + rcu_read_unlock(); return &blkg->rl; -root_rl: + + /* + * Each blkg has its own request_list, however, the root blkcg + * uses the request_queue's root_rl. This is to avoid most + * overhead for the root blkcg. + */ +rl_use_root: rcu_read_unlock(); return &q->root_rl; } -- cgit v1.2.3 From b3b9f24f5fcc099c41f7dc1d02350635830888e5 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:36 -0400 Subject: blkcg: change blkg reference counting to use percpu_ref Now that every bio is associated with a blkg, this puts the use of blkg_get, blkg_try_get, and blkg_put on the hot path. This switches over the refcnt in blkg to use percpu_ref. Signed-off-by: Dennis Zhou Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index d2f7f1b00fcf..7ff5d8ba8c7a 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -126,7 +126,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - atomic_t refcnt; + struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -490,8 +490,7 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); - atomic_inc(&blkg->refcnt); + percpu_ref_get(&blkg->refcnt); } /** @@ -503,7 +502,7 @@ static inline void blkg_get(struct blkcg_gq *blkg) */ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - if (atomic_inc_not_zero(&blkg->refcnt)) + if (percpu_ref_tryget(&blkg->refcnt)) return blkg; return NULL; } @@ -517,23 +516,19 @@ static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) */ static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) { - while (!atomic_inc_not_zero(&blkg->refcnt)) + while (!percpu_ref_tryget(&blkg->refcnt)) blkg = blkg->parent; return blkg; } -void __blkg_release_rcu(struct rcu_head *rcu); - /** * blkg_put - put a blkg reference * @blkg: blkg to put */ static inline void blkg_put(struct blkcg_gq *blkg) { - WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); - if (atomic_dec_and_test(&blkg->refcnt)) - call_rcu(&blkg->rcu_head, __blkg_release_rcu); + percpu_ref_put(&blkg->refcnt); } /** -- cgit v1.2.3 From 101246ec02b54adf6a77180a01ccbe310add2c32 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:37 -0400 Subject: blkcg: rename blkg_try_get to blkg_tryget blkg reference counting now uses percpu_ref rather than atomic_t. Let's make this consistent with css_tryget. This renames blkg_try_get to blkg_tryget and now returns a bool rather than the blkg or NULL. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 7ff5d8ba8c7a..b7fd08013de2 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -494,27 +494,25 @@ static inline void blkg_get(struct blkcg_gq *blkg) } /** - * blkg_try_get - try and get a blkg reference + * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) +static inline bool blkg_tryget(struct blkcg_gq *blkg) { - if (percpu_ref_tryget(&blkg->refcnt)) - return blkg; - return NULL; + return percpu_ref_tryget(&blkg->refcnt); } /** - * blkg_try_get_closest - try and get a blkg ref on the closet blkg + * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @blkg: blkg to get * * This walks up the blkg tree to find the closest non-dying blkg and returns * the blkg that it did association with as it may not be the passed in blkg. */ -static inline struct blkcg_gq *blkg_try_get_closest(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) { while (!percpu_ref_tryget(&blkg->refcnt)) blkg = blkg->parent; @@ -599,7 +597,7 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, if (unlikely(!blkg)) blkg = __blkg_lookup_create(blkcg, q); - if (!blkg_try_get(blkg)) + if (!blkg_tryget(blkg)) goto rl_use_root; rcu_read_unlock(); -- cgit v1.2.3 From 9799ccb0e984a5c1311b22a212e7ff96e8b736de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 08:51:49 -0700 Subject: tcp: add tcp_wstamp_ns socket field TCP will soon provide earliest departure time on TX skbs. It needs to track this in a new variable. tcp_mstamp_refresh() needs to update this variable, and became too big to stay an inline. Signed-off-by: Eric Dumazet 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 263e37271afd..848f5b25e178 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -248,6 +248,8 @@ struct tcp_sock { syn_smc:1; /* SYN includes SMC */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + /* RTT measurement */ u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ -- cgit v1.2.3 From d3edd06ea8ea9e03de6567fda80b8be57e21a537 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 08:51:50 -0700 Subject: tcp: provide earliest departure time in skb->tstamp Switch internal TCP skb->skb_mstamp to skb->skb_mstamp_ns, from usec units to nsec units. Do not clear skb->tstamp before entering IP stacks in TX, so that qdisc or devices can implement pacing based on the earliest departure time instead of socket sk->sk_pacing_rate Packets are fed with tcp_wstamp_ns, and following patch will update tcp_wstamp_ns when both TCP and sch_fq switch to the earliest departure time mechanism. Signed-off-by: Eric Dumazet 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 e3a53ca4a9b5..86f337e9a81d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -689,7 +689,7 @@ struct sk_buff { union { ktime_t tstamp; - u64 skb_mstamp; + u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every -- cgit v1.2.3 From c798c88f3962ddff89c7aa818986caeecd46ab4c Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Wed, 19 Sep 2018 01:59:00 +0000 Subject: EDAC, ghes: Use CPER module handles to locate DIMMs Use SMBIOS module handle type 17, on platforms which provide valid ones, to locate the corresponding DIMM and thus have per-DIMM error counter updates. Signed-off-by: Fan Wu [ Massage commit message. ] Signed-off-by: Borislav Petkov Reviewed-by: Tyler Baicar Reviewed-by: James Morse Tested-by: Toshi Kani Cc: Mauro Carvalho Chehab Cc: baicar.tyler@gmail.com Cc: john.garry@huawei.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-edac Cc: shiju.jose@huawei.com Cc: tanxiaofei@huawei.com Cc: wanghuiqiang@huawei.com Link: http://lkml.kernel.org/r/1537322340-1860-1-git-send-email-wufan@codeaurora.org --- include/linux/edac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index bffb97828ed6..a45ce1f84bfc 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -451,6 +451,8 @@ struct dimm_info { u32 nr_pages; /* number of pages on this dimm */ unsigned csrow, cschannel; /* Points to the old API data */ + + u16 smbios_handle; /* Handle for SMBIOS type 17 */ }; /** -- cgit v1.2.3 From 65a272642ce13aab911f68279c8994cde3282b0a Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 18 May 2018 15:47:50 -0700 Subject: soc: qcom: geni: Make version macros simpler This macro doesn't work, because it hides a local variable inside of the macro to hold the version and that variable name is called 'ver' and 'version' sometimes. Let's change this to be more explicit. Introduce three macros for the major, minor, and step of the version, and require callers to pass the version in to get the part of the version out. This way we don't hide local variables inside macros and things are less evil overall. Cc: Karthikeyan Ramasubramanian Cc: Sagar Dharia Cc: Girish Mahadevan Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom-geni-se.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 5d6144977828..3bcd67fd5548 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -225,19 +225,14 @@ struct geni_se { #define HW_VER_MINOR_SHFT 16 #define HW_VER_STEP_MASK GENMASK(15, 0) +#define GENI_SE_VERSION_MAJOR(ver) ((ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT) +#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) + #if IS_ENABLED(CONFIG_QCOM_GENI_SE) u32 geni_se_get_qup_hw_version(struct geni_se *se); -#define geni_se_get_wrapper_version(se, major, minor, step) do { \ - u32 ver; \ -\ - ver = geni_se_get_qup_hw_version(se); \ - major = (ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT; \ - minor = (ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT; \ - step = version & HW_VER_STEP_MASK; \ -} while (0) - /** * geni_se_read_proto() - Read the protocol configured for a serial engine * @se: Pointer to the concerned serial engine. -- cgit v1.2.3 From ac3d9dd034e565df2c034ab2ca71f0a9f69153c1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 15:27:38 -0700 Subject: netpoll: make ndo_poll_controller() optional As diagnosed by Song Liu, ndo_poll_controller() can be very dangerous on loaded hosts, since the cpu calling ndo_poll_controller() might steal all NAPI contexts (for all RX/TX queues of the NIC). This capture can last for unlimited amount of time, since one cpu is generally not able to drain all the queues under load. It seems that all networking drivers that do use NAPI for their TX completions, should not provide a ndo_poll_controller(). NAPI drivers have netpoll support already handled in core networking stack, since netpoll_poll_dev() uses poll_napi(dev) to iterate through registered NAPI contexts for a device. This patch allows netpoll_poll_dev() to process NAPI contexts even for drivers not providing ndo_poll_controller(), allowing for following patches in NAPI drivers. Also we export netpoll_poll_dev() so that it can be called by bonding/team drivers in following patches. Reported-by: Song Liu Signed-off-by: Eric Dumazet Tested-by: Song Liu Signed-off-by: David S. Miller --- include/linux/netpoll.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 67662d01130a..3ef82d3a78db 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -49,8 +49,9 @@ struct netpoll_info { }; #ifdef CONFIG_NETPOLL -extern void netpoll_poll_disable(struct net_device *dev); -extern void netpoll_poll_enable(struct net_device *dev); +void netpoll_poll_dev(struct net_device *dev); +void netpoll_poll_disable(struct net_device *dev); +void netpoll_poll_enable(struct net_device *dev); #else static inline void netpoll_poll_disable(struct net_device *dev) { return; } static inline void netpoll_poll_enable(struct net_device *dev) { return; } -- cgit v1.2.3 From 1cc33161a83d20b5462b1e93f95d3ce6388079ee Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 20 Aug 2018 10:12:47 +0530 Subject: uprobes: Support SDT markers having reference count (semaphore) Userspace Statically Defined Tracepoints[1] are dtrace style markers inside userspace applications. Applications like PostgreSQL, MySQL, Pthread, Perl, Python, Java, Ruby, Node.js, libvirt, QEMU, glib etc have these markers embedded in them. These markers are added by developer at important places in the code. Each marker source expands to a single nop instruction in the compiled code but there may be additional overhead for computing the marker arguments which expands to couple of instructions. In case the overhead is more, execution of it can be omitted by runtime if() condition when no one is tracing on the marker: if (reference_counter > 0) { Execute marker instructions; } Default value of reference counter is 0. Tracer has to increment the reference counter before tracing on a marker and decrement it when done with the tracing. Implement the reference counter logic in core uprobe. User will be able to use it from trace_uprobe as well as from kernel module. New trace_uprobe definition with reference counter will now be: :[(ref_ctr_offset)] where ref_ctr_offset is an optional field. For kernel module, new variant of uprobe_register() has been introduced: uprobe_register_refctr(inode, offset, ref_ctr_offset, consumer) No new variant for uprobe_unregister() because it's assumed to have only one reference counter for one uprobe. [1] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation Note: 'reference counter' is called as 'semaphore' in original Dtrace (or Systemtap, bcc and even in ELF) documentation and code. But the term 'semaphore' is misleading in this context. This is just a counter used to hold number of tracers tracing on a marker. This is not really used for any synchronization. So we are calling it a 'reference counter' in kernel / perf code. Link: http://lkml.kernel.org/r/20180820044250.11659-2-ravi.bangoria@linux.ibm.com Reviewed-by: Masami Hiramatsu [Only trace_uprobe.c] Reviewed-by: Oleg Nesterov Reviewed-by: Song Liu Tested-by: Song Liu Signed-off-by: Ravi Bangoria Signed-off-by: Steven Rostedt (VMware) --- include/linux/uprobes.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index bb9d2084af03..103a48a48872 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -123,6 +123,7 @@ extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); @@ -160,6 +161,10 @@ uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { return -ENOSYS; } +static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) +{ + return -ENOSYS; +} static inline int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) { -- cgit v1.2.3 From a725356b6659469d182d662f22d770d83d3bc7b5 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Tue, 18 Sep 2018 16:34:34 +0300 Subject: vfs: swap names of {do,vfs}_clone_file_range() Commit 031a072a0b8a ("vfs: call vfs_clone_file_range() under freeze protection") created a wrapper do_clone_file_range() around vfs_clone_file_range() moving the freeze protection to former, so overlayfs could call the latter. The more common vfs practice is to call do_xxx helpers from vfs_xxx helpers, where freeze protecction is taken in the vfs_xxx helper, so this anomality could be a source of confusion. It seems that commit 8ede205541ff ("ovl: add reflink/copyfile/dedup support") may have fallen a victim to this confusion - ovl_clone_file_range() calls the vfs_clone_file_range() helper in the hope of getting freeze protection on upper fs, but in fact results in overlayfs allowing to bypass upper fs freeze protection. Swap the names of the two helpers to conform to common vfs practice and call the correct helpers from overlayfs and nfsd. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 17 +++-------------- 1 file changed, 3 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c0b4a1c22ff..897eae8faee1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1828,8 +1828,10 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, struct inode *inode_out, loff_t pos_out, u64 *len, bool is_dedupe); +extern int do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + struct file *file_out, loff_t pos_out, u64 len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); @@ -2773,19 +2775,6 @@ static inline void file_end_write(struct file *file) __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); } -static inline int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len) -{ - int ret; - - file_start_write(file_out); - ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len); - file_end_write(file_out); - - return ret; -} - /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. -- cgit v1.2.3 From ec0daae685b20f3bee196719f64d79d1cc40457e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 20 Sep 2018 12:35:30 -0700 Subject: gpio: omap: Add level wakeup handling for omap4 based SoCs I noticed that unlike omap2 and 3 based SoCs, omap4 based SoCs keep the GPIO clocks enabled for GPIO level interrupts with wakeup enabled. This blocks deeper idle states as the whole domain will stay busy. The GPIO functional clock seems to stay enabled if the wakeup register is enabled and a level interrupt is triggered. In that case the only way to have the GPIO module idle is to reset it. It is possible this has gone unnoticed with OSWR (Open SWitch Retention) and off mode during idle resetting GPIO context most GPIO instances in the earlier Android trees for example. Looks like the way to deal with this is to have omap4 based SoCs only set wake for the duration of idle for level interrupts, and clear level registers for the idle. With level interrupts we can do this as the level interrupt from device will be still there on resume. I've taken the long path to fixing this to avoid yet more hard to read code. I've set up a quirks flag, and a struct for function pointers so we can use these to clean up other quirk handling easier in the later patches. The current level quirk handling is moved to the new functions. Cc: Aaro Koskinen Cc: Ladislav Michl Cc: Tero Kristo Signed-off-by: Tony Lindgren Acked-by: Grygorii Strashko Tested-by: Keerthy Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-omap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index 8612855691b2..d952151b6e33 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -197,6 +197,8 @@ struct omap_gpio_platform_data { bool is_mpuio; /* whether the bank is of type MPUIO */ u32 non_wakeup_gpios; + u32 quirks; /* Version specific quirks mask */ + struct omap_gpio_reg_offs *regs; /* Return context loss count due to PM states changing */ -- cgit v1.2.3 From b764a5863fd834836e65e258303e3a4a81c20f38 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 20 Sep 2018 12:35:31 -0700 Subject: gpio: omap: Remove custom PM calls and use cpu_pm instead For a long time the gpio-omap custom PM calls have been annoying me so let's replace them with cpu_pm instead. This will enable GPIO PM for deeper idle states on omap4. And we can handle GPIO PM for omap2/3/4 in the same way. Note that with this patch we are also slightly changing GPIO PM to be less aggressive for omap3 and only will idle GPIO when PER context may be lost. For omap2, we don't need to save context and don't want to remove any triggering so let's add a quirk flag for that. Let's do this all in a single patch to avoid a situation where old custom calls still are used with new code. Cc: Aaro Koskinen Cc: Keerthy Cc: Ladislav Michl Cc: Tero Kristo Signed-off-by: Tony Lindgren Acked-by: Grygorii Strashko Signed-off-by: Linus Walleij --- include/linux/platform_data/gpio-omap.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index d952151b6e33..8485c6a9a383 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -205,17 +205,4 @@ struct omap_gpio_platform_data { int (*get_context_loss_count)(struct device *dev); }; -#if IS_BUILTIN(CONFIG_GPIO_OMAP) -extern void omap2_gpio_prepare_for_idle(int off_mode); -extern void omap2_gpio_resume_after_idle(void); -#else -static inline void omap2_gpio_prepare_for_idle(int off_mode) -{ -} - -static inline void omap2_gpio_resume_after_idle(void) -{ -} -#endif - #endif -- cgit v1.2.3 From 463659a08d7999d5461fa45b35b17686189a70ca Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 13 Sep 2018 07:47:29 -0400 Subject: media: hdmi.h: rename ADOBE_RGB to OPRGB and ADOBE_YCC to OPYCC These names have been renamed in the CTA-861 standard due to trademark issues. Replace them here as well so they are in sync with the standard. Signed-off-by: Hans Verkuil Cc: stable@vger.kernel.org Acked-by: Daniel Vetter Signed-off-by: Mauro Carvalho Chehab --- include/linux/hdmi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index d271ff23984f..4f3febc0f971 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -101,8 +101,8 @@ enum hdmi_extended_colorimetry { HDMI_EXTENDED_COLORIMETRY_XV_YCC_601, HDMI_EXTENDED_COLORIMETRY_XV_YCC_709, HDMI_EXTENDED_COLORIMETRY_S_YCC_601, - HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601, - HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB, + HDMI_EXTENDED_COLORIMETRY_OPYCC_601, + HDMI_EXTENDED_COLORIMETRY_OPRGB, /* The following EC values are only defined in CEA-861-F. */ HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM, -- cgit v1.2.3 From 808c43b7c7f70360ed7b9e43e2cf980f388e71fa Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 21 Sep 2018 17:03:27 -0700 Subject: cgroup: Simplify cgroup_ancestor Simplify cgroup_ancestor function. This is follow-up for commit 7723628101aa ("bpf: Introduce bpf_skb_ancestor_cgroup_id helper") Suggested-by: Tejun Heo Signed-off-by: Andrey Ignatov Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 32c553556bbd..e03a92430383 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -567,20 +567,11 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { - struct cgroup *ptr; - if (cgrp->level < ancestor_level) return NULL; - - for (ptr = cgrp; - ptr && ptr->level > ancestor_level; - ptr = cgroup_parent(ptr)) - ; - - if (ptr && ptr->level == ancestor_level) - return ptr; - - return NULL; + while (cgrp && cgrp->level > ancestor_level) + cgrp = cgroup_parent(cgrp); + return cgrp; } /** -- cgit v1.2.3 From 43b729bfe9cf30ad11499a66e3b7bd300c716d44 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:47 +0200 Subject: block: move integrity_req_gap_{back,front}_merge to blk.h No need to expose these to drivers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..bc534c857344 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1843,26 +1843,6 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) -{ - struct bio_integrity_payload *bip = bio_integrity(req->bio); - struct bio_integrity_payload *bip_next = bio_integrity(next); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); -} - -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) -{ - struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_integrity_payload *bip_next = bio_integrity(req->bio); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); -} - /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device @@ -1947,17 +1927,6 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq, return true; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) -{ - return false; -} -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) -{ - return false; -} - static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { -- cgit v1.2.3 From e9907009cbfc0c93d987d5a8fdf3d6c3c7b89717 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:48 +0200 Subject: block: move req_gap_{back,front}_merge to blk-merge.c Keep it close to the actual users instead of exposing the function to all drivers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 69 -------------------------------------------------- 1 file changed, 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bc534c857344..b7e676bb01bc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1695,75 +1695,6 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, return __bvec_gap_to_prev(q, bprv, offset); } -/* - * Check if the two bvecs from two bios can be merged to one segment. - * If yes, no need to check gap between the two bios since the 1st bio - * and the 1st bvec in the 2nd bio can be handled in one segment. - */ -static inline bool bios_segs_mergeable(struct request_queue *q, - struct bio *prev, struct bio_vec *prev_last_bv, - struct bio_vec *next_first_bv) -{ - if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv)) - return false; - if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv)) - return false; - if (prev->bi_seg_back_size + next_first_bv->bv_len > - queue_max_segment_size(q)) - return false; - return true; -} - -static inline bool bio_will_gap(struct request_queue *q, - struct request *prev_rq, - struct bio *prev, - struct bio *next) -{ - if (bio_has_data(prev) && queue_virt_boundary(q)) { - struct bio_vec pb, nb; - - /* - * don't merge if the 1st bio starts with non-zero - * offset, otherwise it is quite difficult to respect - * sg gap limit. We work hard to merge a huge number of small - * single bios in case of mkfs. - */ - if (prev_rq) - bio_get_first_bvec(prev_rq->bio, &pb); - else - bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) - return true; - - /* - * We don't need to worry about the situation that the - * merged segment ends in unaligned virt boundary: - * - * - if 'pb' ends aligned, the merged segment ends aligned - * - if 'pb' ends unaligned, the next bio must include - * one single bvec of 'nb', otherwise the 'nb' can't - * merge with 'pb' - */ - bio_get_last_bvec(prev, &pb); - bio_get_first_bvec(next, &nb); - - if (!bios_segs_mergeable(q, prev, &pb, &nb)) - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); - } - - return false; -} - -static inline bool req_gap_back_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, req, req->biotail, bio); -} - -static inline bool req_gap_front_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, NULL, bio, req->bio); -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From 27ca1d4ed04ea29dc77b47190a3cc82697023e76 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:49 +0200 Subject: block: move req_gap_back_merge to blk.h No need to expose these helpers outside the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b7e676bb01bc..1d5e14139795 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1676,25 +1676,6 @@ static inline void put_dev_sector(Sector p) put_page(p.v); } -static inline bool __bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); -} - -/* - * Check if adding a bio_vec after bprv with offset would create a gap in - * the SG list. Most drivers don't care about this, but some do. - */ -static inline bool bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - if (!queue_virt_boundary(q)) - return false; - return __bvec_gap_to_prev(q, bprv, offset); -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); -- cgit v1.2.3 From 6a9f5f240adfdced863a098d34f8f05ca6ab9d5f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:50 +0200 Subject: block: simplify BIOVEC_PHYS_MERGEABLE Turn the macro into an inline, move it to blk.h and simplify the arch hooks a bit. Also rename the function to biovec_phys_mergeable as there is no need to shout. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e973876625a8..e2adb96346f0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -140,19 +140,6 @@ static inline bool bio_full(struct bio *bio) /* * merge helpers etc */ - -/* Default implementation of BIOVEC_PHYS_MERGEABLE */ -#define __BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) - -/* - * allow arch override, for eg virtualized architectures (put in asm/io.h) - */ -#ifndef BIOVEC_PHYS_MERGEABLE -#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - __BIOVEC_PHYS_MERGEABLE(vec1, vec2) -#endif - #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \ (((addr1) | (mask)) == (((addr2) - 1) | (mask))) #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ -- cgit v1.2.3 From 3dccdae54fe836a22cee9dc6df9fd1708ae075ce Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:52 +0200 Subject: block: merge BIOVEC_SEG_BOUNDARY into biovec_phys_mergeable These two checks should always be performed together, so merge them into a single helper. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e2adb96346f0..9b580e1cb2e8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -137,14 +137,6 @@ static inline bool bio_full(struct bio *bio) */ #define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) -/* - * merge helpers etc - */ -#define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \ - (((addr1) | (mask)) == (((addr2) - 1) | (mask))) -#define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ - __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q))) - /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it -- cgit v1.2.3 From 6e768461c215eaf8912e6c23e40fdff1cd962aca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:53 +0200 Subject: block: remove bvec_to_phys We only use it in biovec_phys_mergeable and a m68k paravirt driver, so just opencode it there. Also remove the pointless unsigned long cast for the offset in the opencoded instances. Signed-off-by: Christoph Hellwig Reviewed-by: Geert Uytterhoeven Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9b580e1cb2e8..9ad4b0a487a4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -132,11 +132,6 @@ static inline bool bio_full(struct bio *bio) return bio->bi_vcnt >= bio->bi_max_vecs; } -/* - * will die - */ -#define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) - /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it -- cgit v1.2.3 From bceacbfa48bf132d8d88058904cf5859eeb4f3e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:54 +0200 Subject: block: don't include io.h from bio.h Now that we don't need an override for BIOVEC_PHYS_MERGEABLE there is no need to drag this header in. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9ad4b0a487a4..b3d47862b1b4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -24,9 +24,6 @@ #include #ifdef CONFIG_BLOCK - -#include - /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include -- cgit v1.2.3 From 65969e5cb249b765cee261c8f0458ec778b0c22f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 09:43:55 +0200 Subject: block: don't include bug.h from bio.h No need to pull in the BUG() defintion. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b3d47862b1b4..f447b0ebb288 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -21,7 +21,6 @@ #include #include #include -#include #ifdef CONFIG_BLOCK /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ -- cgit v1.2.3 From 40d9f9124822013331367fb4ab59936c3ac944d6 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 24 Sep 2018 12:16:54 -0700 Subject: bus: ti-sysc: Defer suspend as needed We don't care when we suspend but some our children do. In order to avoid tagging various modules with SYSC_QUIRK_RESOURCE_PROVIDER, let's do it automatically by tagging modules that are busy on suspend for noirq suspend. This way we can just do module detection on define DEBUG. Note that we still need to keep SYSC_QUIRK_LEGACY_IDLE flag around so the our legacy single-child devices that set pm_runtime_irq_safe() can manage the interconnect target module themselves. Signed-off-by: Tony Lindgren --- include/linux/platform_data/ti-sysc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 2efa3470a451..1ea3aab972b4 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -46,7 +46,6 @@ struct sysc_regbits { s8 emufree_shift; }; -#define SYSC_QUIRK_RESOURCE_PROVIDER BIT(9) #define SYSC_QUIRK_LEGACY_IDLE BIT(8) #define SYSC_QUIRK_RESET_STATUS BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) -- cgit v1.2.3 From 9ba481e2eb3b932ae5b6278342b256e4f92d2793 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:20 +0300 Subject: net/mlx5: Set uid as part of CQ commands Set uid as part of CQ commands so that the firmware can manage the CQ object in a secured way. The firmware should mark this CQ with the given uid so that it can be used later on only by objects with the same uid. Upon DEVX flows that use this CQ (e.g. create QP command), the pointed CQ must have the same uid as of the issuer uid command. When a command is issued with uid=0 it means that the issuer of the command is trusted (i.e. kernel), in that case any pointed object can be used regardless of its uid. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/cq.h | 1 + include/linux/mlx5/mlx5_ifc.h | 6 +++--- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 0ef6138eca49..31a750570c38 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -61,6 +61,7 @@ struct mlx5_core_cq { int reset_notify_added; struct list_head reset_notify; struct mlx5_eq *eq; + u16 uid; }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4c7a1d25d73b..1a412b355054 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5629,7 +5629,7 @@ enum { struct mlx5_ifc_modify_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6404,7 +6404,7 @@ struct mlx5_ifc_destroy_cq_out_bits { struct mlx5_ifc_destroy_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7164,7 +7164,7 @@ struct mlx5_ifc_create_cq_out_bits { struct mlx5_ifc_create_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 4ac63ec72587f7426aae15ddfe78e8ab785724dc Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:21 +0300 Subject: net/mlx5: Set uid as part of QP commands Set uid as part of QP commands so that the firmware can manage the QP object in a secured way. That will enable using a QP that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 22 +++++++++++----------- include/linux/mlx5/qp.h | 1 + 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1a412b355054..3b6a612787ac 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3394,7 +3394,7 @@ struct mlx5_ifc_sqerr2rts_qp_out_bits { struct mlx5_ifc_sqerr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3424,7 +3424,7 @@ struct mlx5_ifc_sqd2rts_qp_out_bits { struct mlx5_ifc_sqd2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3629,7 +3629,7 @@ struct mlx5_ifc_rts2rts_qp_out_bits { struct mlx5_ifc_rts2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3659,7 +3659,7 @@ struct mlx5_ifc_rtr2rts_qp_out_bits { struct mlx5_ifc_rtr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3689,7 +3689,7 @@ struct mlx5_ifc_rst2init_qp_out_bits { struct mlx5_ifc_rst2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5192,7 +5192,7 @@ struct mlx5_ifc_qp_2rst_out_bits { struct mlx5_ifc_qp_2rst_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5214,7 +5214,7 @@ struct mlx5_ifc_qp_2err_out_bits { struct mlx5_ifc_qp_2err_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5789,7 +5789,7 @@ struct mlx5_ifc_init2rtr_qp_out_bits { struct mlx5_ifc_init2rtr_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5819,7 +5819,7 @@ struct mlx5_ifc_init2init_qp_out_bits { struct mlx5_ifc_init2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6230,7 +6230,7 @@ struct mlx5_ifc_destroy_qp_out_bits { struct mlx5_ifc_destroy_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6895,7 +6895,7 @@ struct mlx5_ifc_create_qp_out_bits { struct mlx5_ifc_create_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 4778d41085d4..fbe322c966bc 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -471,6 +471,7 @@ struct mlx5_core_qp { int qpn; struct mlx5_rsc_debug *dbg; int pid; + u16 uid; }; struct mlx5_core_dct { -- cgit v1.2.3 From d269b3afffcb107375d9cf73127fc2e0181bc90b Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:22 +0300 Subject: net/mlx5: Set uid as part of RQ commands Set uid as part of RQ commands so that the firmware can manage the RQ object in a secured way. That will enable using an RQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3b6a612787ac..689631ca27b8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5488,7 +5488,7 @@ enum { struct mlx5_ifc_modify_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6164,7 +6164,7 @@ struct mlx5_ifc_destroy_rq_out_bits { struct mlx5_ifc_destroy_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6847,7 +6847,7 @@ struct mlx5_ifc_create_rq_out_bits { struct mlx5_ifc_create_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 430ae0d5a3ce1350375690cb6ab29ab6fae4a9ac Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:23 +0300 Subject: net/mlx5: Set uid as part of SQ commands Set uid as part of SQ commands so that the firmware can manage the SQ object in a secured way. That will enable using an SQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 689631ca27b8..72dd1e49a799 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5381,7 +5381,7 @@ struct mlx5_ifc_modify_sq_out_bits { struct mlx5_ifc_modify_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6096,7 +6096,7 @@ struct mlx5_ifc_destroy_sq_out_bits { struct mlx5_ifc_destroy_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6769,7 +6769,7 @@ struct mlx5_ifc_create_sq_out_bits { struct mlx5_ifc_create_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From a0d8c054318976927493ffd26055d9d183c9beec Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:24 +0300 Subject: net/mlx5: Set uid as part of SRQ commands Set uid as part of SRQ commands so that the firmware can manage the SRQ object in a secured way. That will enable using an SRQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 22 +++++++++++----------- include/linux/mlx5/srq.h | 1 + 3 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d885e9f0e054..8fb072aa8671 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -474,6 +474,7 @@ struct mlx5_core_srq { atomic_t refcount; struct completion free; + u16 uid; }; struct mlx5_eq_table { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 72dd1e49a799..85f1237d80db 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5524,7 +5524,7 @@ struct mlx5_ifc_rmp_bitmask_bits { struct mlx5_ifc_modify_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5986,7 +5986,7 @@ struct mlx5_ifc_destroy_xrq_out_bits { struct mlx5_ifc_destroy_xrq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6008,7 +6008,7 @@ struct mlx5_ifc_destroy_xrc_srq_out_bits { struct mlx5_ifc_destroy_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6074,7 +6074,7 @@ struct mlx5_ifc_destroy_srq_out_bits { struct mlx5_ifc_destroy_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6208,7 +6208,7 @@ struct mlx5_ifc_destroy_rmp_out_bits { struct mlx5_ifc_destroy_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6641,7 +6641,7 @@ struct mlx5_ifc_create_xrq_out_bits { struct mlx5_ifc_create_xrq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6665,7 +6665,7 @@ struct mlx5_ifc_create_xrc_srq_out_bits { struct mlx5_ifc_create_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6741,7 +6741,7 @@ struct mlx5_ifc_create_srq_out_bits { struct mlx5_ifc_create_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6871,7 +6871,7 @@ struct mlx5_ifc_create_rmp_out_bits { struct mlx5_ifc_create_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7272,7 +7272,7 @@ enum { struct mlx5_ifc_arm_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7300,7 +7300,7 @@ enum { struct mlx5_ifc_arm_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 24ff23e27c8a..1b1f3c20c6a3 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -61,6 +61,7 @@ struct mlx5_srq_attr { u32 tm_next_tag; u32 tm_hw_phase_cnt; u32 tm_sw_phase_cnt; + u16 uid; }; struct mlx5_core_dev; -- cgit v1.2.3 From 774ea6eea29025218f75bc94c764df9a641db471 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:25 +0300 Subject: net/mlx5: Set uid as part of DCT commands Set uid as part of DCT commands so that the firmware can manage the DCT object in a secured way. That will enable using a DCT that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 85f1237d80db..62c0592a9fdb 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5918,7 +5918,7 @@ struct mlx5_ifc_drain_dct_out_bits { struct mlx5_ifc_drain_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6382,7 +6382,7 @@ struct mlx5_ifc_destroy_dct_out_bits { struct mlx5_ifc_destroy_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7138,7 +7138,7 @@ struct mlx5_ifc_create_dct_out_bits { struct mlx5_ifc_create_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From bd37197554eb28a7fc38e44e005e303c77f788ed Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 20 Sep 2018 21:35:26 +0300 Subject: net/mlx5: Update mlx5_ifc with DEVX UID bits Add DEVX information to WQ, SRQ, CQ, TIR, TIS, QP, RQ, XRCD, PD, MKEY and MCG. Each object that is created/destroyed/modified via verbs will be stamped with a UID based on its user context. This is already done for DEVX objects commands. This will enable the firmware to enforce the usage of kernel objects from the DEVX flow by validating that the same UID is used and the resources are really related to the same user. The addition of *_valid fields are needed to distinguish how various addresses are passed. For non-DEVX callers, all those fields will be zero. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 67 +++++++++++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 62c0592a9fdb..68f4d5f9d929 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1290,7 +1290,9 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_118[0x3]; u8 log_wq_sz[0x5]; - u8 reserved_at_120[0x3]; + u8 dbr_umem_valid[0x1]; + u8 wq_umem_valid[0x1]; + u8 reserved_at_122[0x1]; u8 log_hairpin_num_packets[0x5]; u8 reserved_at_128[0x3]; u8 log_hairpin_data_sz[0x5]; @@ -2364,7 +2366,10 @@ struct mlx5_ifc_qpc_bits { u8 dc_access_key[0x40]; - u8 reserved_at_680[0xc0]; + u8 reserved_at_680[0x3]; + u8 dbr_umem_valid[0x1]; + + u8 reserved_at_684[0xbc]; }; struct mlx5_ifc_roce_addr_layout_bits { @@ -2464,7 +2469,7 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 reserved_at_22[0x1]; + u8 dbr_umem_valid[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; @@ -3128,7 +3133,9 @@ enum { struct mlx5_ifc_cqc_bits { u8 status[0x4]; - u8 reserved_at_4[0x4]; + u8 reserved_at_4[0x2]; + u8 dbr_umem_valid[0x1]; + u8 reserved_at_7[0x1]; u8 cqe_sz[0x3]; u8 cc[0x1]; u8 reserved_at_c[0x1]; @@ -5314,7 +5321,7 @@ struct mlx5_ifc_modify_tis_bitmask_bits { struct mlx5_ifc_modify_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5353,7 +5360,7 @@ struct mlx5_ifc_modify_tir_out_bits { struct mlx5_ifc_modify_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5454,7 +5461,7 @@ struct mlx5_ifc_rqt_bitmask_bits { struct mlx5_ifc_modify_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5641,7 +5648,10 @@ struct mlx5_ifc_modify_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x40]; + + u8 cq_umem_valid[0x1]; + u8 reserved_at_2c1[0x5bf]; u8 pas[0][0x40]; }; @@ -5962,7 +5972,7 @@ struct mlx5_ifc_detach_from_mcg_out_bits { struct mlx5_ifc_detach_from_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6030,7 +6040,7 @@ struct mlx5_ifc_destroy_tis_out_bits { struct mlx5_ifc_destroy_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6052,7 +6062,7 @@ struct mlx5_ifc_destroy_tir_out_bits { struct mlx5_ifc_destroy_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6142,7 +6152,7 @@ struct mlx5_ifc_destroy_rqt_out_bits { struct mlx5_ifc_destroy_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6507,7 +6517,7 @@ struct mlx5_ifc_dealloc_xrcd_out_bits { struct mlx5_ifc_dealloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6595,7 +6605,7 @@ struct mlx5_ifc_dealloc_pd_out_bits { struct mlx5_ifc_dealloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6674,7 +6684,9 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x40]; + u8 xrc_srq_umem_valid[0x1]; + u8 reserved_at_2c1[0x5bf]; u8 pas[0][0x40]; }; @@ -6693,7 +6705,7 @@ struct mlx5_ifc_create_tis_out_bits { struct mlx5_ifc_create_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6717,7 +6729,7 @@ struct mlx5_ifc_create_tir_out_bits { struct mlx5_ifc_create_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6823,7 +6835,7 @@ struct mlx5_ifc_create_rqt_out_bits { struct mlx5_ifc_create_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6908,7 +6920,10 @@ struct mlx5_ifc_create_qp_in_bits { struct mlx5_ifc_qpc_bits qpc; - u8 reserved_at_800[0x80]; + u8 reserved_at_800[0x60]; + + u8 wq_umem_valid[0x1]; + u8 reserved_at_861[0x1f]; u8 pas[0][0x40]; }; @@ -6970,7 +6985,8 @@ struct mlx5_ifc_create_mkey_in_bits { u8 reserved_at_40[0x20]; u8 pg_access[0x1]; - u8 reserved_at_61[0x1f]; + u8 mkey_umem_valid[0x1]; + u8 reserved_at_62[0x1e]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; @@ -7173,7 +7189,10 @@ struct mlx5_ifc_create_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x60]; + + u8 cq_umem_valid[0x1]; + u8 reserved_at_2e1[0x59f]; u8 pas[0][0x40]; }; @@ -7221,7 +7240,7 @@ struct mlx5_ifc_attach_to_mcg_out_bits { struct mlx5_ifc_attach_to_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7348,7 +7367,7 @@ struct mlx5_ifc_alloc_xrcd_out_bits { struct mlx5_ifc_alloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7436,7 +7455,7 @@ struct mlx5_ifc_alloc_pd_out_bits { struct mlx5_ifc_alloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 2a6db719c92dbfe43c9eea7e4358ea2e51b5004e Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 10 Sep 2018 19:19:16 +0530 Subject: iommu/of: make of_pci_map_rid() available for other devices too iommu-map property is also used by devices with fsl-mc. This patch moves the of_pci_map_rid to generic location, so that it can be used by other busses too. 'of_pci_map_rid' is renamed here to 'of_map_rid' and there is no functional change done in the API. Signed-off-by: Nipun Gupta Reviewed-by: Rob Herring Reviewed-by: Robin Murphy Acked-by: Bjorn Helgaas Signed-off-by: Joerg Roedel --- include/linux/of.h | 11 +++++++++++ include/linux/of_pci.h | 10 ---------- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..bf577ca3c8e7 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -550,6 +550,10 @@ 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, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out); + #else /* CONFIG_OF */ static inline void of_core_init(void) @@ -952,6 +956,13 @@ 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, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out) +{ + return -EINVAL; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index e83d87fc5673..21a89c4880fa 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -14,9 +14,6 @@ struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); void of_pci_check_probe_only(void); -int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out); #else static inline struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn) @@ -29,13 +26,6 @@ static inline int of_pci_get_devfn(struct device_node *np) return -EINVAL; } -static inline int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out) -{ - return -EINVAL; -} - static inline void of_pci_check_probe_only(void) { } #endif -- cgit v1.2.3 From eab03e2a1a3d9d354943aff5ae5e4254ee1ec967 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 10 Sep 2018 19:19:18 +0530 Subject: iommu/arm-smmu: Add support for the fsl-mc bus Implement bus specific support for the fsl-mc bus including registering arm_smmu_ops and bus specific device add operations. Signed-off-by: Nipun Gupta Reviewed-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/fsl/mc.h | 8 ++++++++ include/linux/iommu.h | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index f27cb14088a4..dddaca17d684 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -351,6 +351,14 @@ int mc_send_command(struct fsl_mc_io *mc_io, struct fsl_mc_command *cmd); #define dev_is_fsl_mc(_dev) (0) #endif +/* Macro to check if a device is a container device */ +#define fsl_mc_is_cont_dev(_dev) (to_fsl_mc_device(_dev)->flags & \ + FSL_MC_IS_DPRC) + +/* Macro to get the container device of a MC device */ +#define fsl_mc_cont_dev(_dev) (fsl_mc_is_cont_dev(_dev) ? \ + (_dev) : (_dev)->parent) + /* * module_fsl_mc_driver() - Helper macro for drivers that don't do * anything special in module init/exit. This eliminates a lot of diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 87994c265bf5..70102df4b994 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -377,6 +377,8 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain) extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ extern struct iommu_group *generic_device_group(struct device *dev); +/* FSL-MC device grouping function */ +struct iommu_group *fsl_mc_device_group(struct device *dev); /** * struct iommu_fwspec - per-device IOMMU instance data -- cgit v1.2.3 From e48d194d1204b19655c1a9d78a67f2f01d2fe432 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 25 Sep 2018 09:54:14 +0200 Subject: gpio: Add comments on single direction chips A patch from Ricardo got me thinking about some gpio chip semantics so let's drop in some comments to make things more clear around that. Cc: Ricardo Ribalda Delgado Cc: Bartosz Golaszewski Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index d8dcd0e44cab..f6b95734073f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -178,9 +178,13 @@ static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *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 + * (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. * @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 + * This can be omitted on input-only or output-only gpio chips. * @get: returns value for signal "offset", 0=low, 1=high, or negative error * @get_multiple: reads values for multiple signals defined by "mask" and * stores them in "bits", returns 0 on success or negative error -- cgit v1.2.3 From bee60e94a1e20ec0b8ffdafae270731d8fda4551 Mon Sep 17 00:00:00 2001 From: Ganapatrao Kulkarni Date: Wed, 5 Sep 2018 09:57:36 +0530 Subject: iommu/iova: Optimise attempts to allocate iova from 32bit address range As an optimisation for PCI devices, there is always first attempt been made to allocate iova from SAC address range. This will lead to unnecessary attempts, when there are no free ranges available. Adding fix to track recently failed iova address size and allow further attempts, only if requested size is lesser than a failed size. The size is updated when any replenish happens. Reviewed-by: Robin Murphy Signed-off-by: Ganapatrao Kulkarni Signed-off-by: Joerg Roedel --- include/linux/iova.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 928442dda565..0b93bf96693e 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -75,6 +75,7 @@ struct iova_domain { unsigned long granule; /* pfn granularity for this domain */ unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; + unsigned long max32_alloc_size; /* Size of last failed allocation */ struct iova anchor; /* rbtree lookup anchor */ struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ -- cgit v1.2.3 From 6af588fed39178c8e118fcf9cb6664e58a1fbe88 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 12 Sep 2018 16:24:12 +0100 Subject: iommu: Add fast hook for getting DMA domains While iommu_get_domain_for_dev() is the robust way for arbitrary IOMMU API callers to retrieve the domain pointer, for DMA ops domains it doesn't scale well for large systems and multi-queue devices, since the momentary refcount adjustment will lead to exclusive cacheline contention when multiple CPUs are operating in parallel on different mappings for the same device. In the case of DMA ops domains, however, this refcounting is actually unnecessary, since they already imply that the group exists and is managed by platform code and IOMMU internals (by virtue of iommu_group_get_for_dev()) such that a reference will already be held for the lifetime of the device. Thus we can avoid the bottleneck by providing a fast lookup specifically for the DMA code to retrieve the default domain it already knows it has set up - a simple read-only dereference plays much nicer with cache-coherency protocols. Signed-off-by: Robin Murphy Tested-by: Will Deacon 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 87994c265bf5..c783648d4060 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -293,6 +293,7 @@ extern int iommu_attach_device(struct iommu_domain *domain, extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); +extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, -- cgit v1.2.3 From 26b86092c4650311256fa2372ced7e1e17d97d7b Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:36 -0700 Subject: iommu/vt-d: Relocate struct/function declarations to its header files To reuse the static functions and the struct declarations, move them to corresponding header files and export the needed functions. Cc: Lu Baolu Cc: Fenghua Yu Cc: Jacob Pan Cc: Ashok Raj Reviewed-by: Andy Shevchenko Signed-off-by: Gayatri Kammela Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 28004d74ae04..b7cf32e8ae1f 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -389,6 +389,33 @@ struct pasid_entry; struct pasid_state_entry; struct page_req_dsc; +/* + * 0: Present + * 1-11: Reserved + * 12-63: Context Ptr (12 - (haw-1)) + * 64-127: Reserved + */ +struct root_entry { + u64 lo; + u64 hi; +}; + +/* + * low 64 bits: + * 0: present + * 1: fault processing disable + * 2-3: translation type + * 12-63: address space root + * high 64 bits: + * 0-2: address width + * 3-6: aval + * 8-23: domain id + */ +struct context_entry { + u64 lo; + u64 hi; +}; + struct dmar_domain { int nid; /* node id */ @@ -559,5 +586,8 @@ extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #endif extern const struct attribute_group *intel_iommu_groups[]; +bool context_present(struct context_entry *context); +struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, + u8 devfn, int alloc); #endif -- cgit v1.2.3 From 4a2d80dbadb72b998641af32d8dd4b7b39e72aa0 Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:37 -0700 Subject: iommu/vt-d: Update register definitions to VT-d 3.0 specification Add new register definitions added in the VT-d 3.0 specification. Also include registers that were missing previously. Cc: Lu Baolu Cc: Fenghua Yu Cc: Jacob Pan Cc: Ashok Raj Cc: Gayatri Kammela Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b7cf32e8ae1f..3bdb9aa198af 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -72,6 +72,42 @@ #define DMAR_PEDATA_REG 0xe4 /* Page request event interrupt data register */ #define DMAR_PEADDR_REG 0xe8 /* Page request event interrupt addr register */ #define DMAR_PEUADDR_REG 0xec /* Page request event Upper address register */ +#define DMAR_MTRRCAP_REG 0x100 /* MTRR capability register */ +#define DMAR_MTRRDEF_REG 0x108 /* MTRR default type register */ +#define DMAR_MTRR_FIX64K_00000_REG 0x120 /* MTRR Fixed range registers */ +#define DMAR_MTRR_FIX16K_80000_REG 0x128 +#define DMAR_MTRR_FIX16K_A0000_REG 0x130 +#define DMAR_MTRR_FIX4K_C0000_REG 0x138 +#define DMAR_MTRR_FIX4K_C8000_REG 0x140 +#define DMAR_MTRR_FIX4K_D0000_REG 0x148 +#define DMAR_MTRR_FIX4K_D8000_REG 0x150 +#define DMAR_MTRR_FIX4K_E0000_REG 0x158 +#define DMAR_MTRR_FIX4K_E8000_REG 0x160 +#define DMAR_MTRR_FIX4K_F0000_REG 0x168 +#define DMAR_MTRR_FIX4K_F8000_REG 0x170 +#define DMAR_MTRR_PHYSBASE0_REG 0x180 /* MTRR Variable range registers */ +#define DMAR_MTRR_PHYSMASK0_REG 0x188 +#define DMAR_MTRR_PHYSBASE1_REG 0x190 +#define DMAR_MTRR_PHYSMASK1_REG 0x198 +#define DMAR_MTRR_PHYSBASE2_REG 0x1a0 +#define DMAR_MTRR_PHYSMASK2_REG 0x1a8 +#define DMAR_MTRR_PHYSBASE3_REG 0x1b0 +#define DMAR_MTRR_PHYSMASK3_REG 0x1b8 +#define DMAR_MTRR_PHYSBASE4_REG 0x1c0 +#define DMAR_MTRR_PHYSMASK4_REG 0x1c8 +#define DMAR_MTRR_PHYSBASE5_REG 0x1d0 +#define DMAR_MTRR_PHYSMASK5_REG 0x1d8 +#define DMAR_MTRR_PHYSBASE6_REG 0x1e0 +#define DMAR_MTRR_PHYSMASK6_REG 0x1e8 +#define DMAR_MTRR_PHYSBASE7_REG 0x1f0 +#define DMAR_MTRR_PHYSMASK7_REG 0x1f8 +#define DMAR_MTRR_PHYSBASE8_REG 0x200 +#define DMAR_MTRR_PHYSMASK8_REG 0x208 +#define DMAR_MTRR_PHYSBASE9_REG 0x210 +#define DMAR_MTRR_PHYSMASK9_REG 0x218 +#define DMAR_VCCAP_REG 0xe00 /* Virtual command capability register */ +#define DMAR_VCMD_REG 0xe10 /* Virtual command register */ +#define DMAR_VCRSP_REG 0xe20 /* Virtual command response register */ #define OFFSET_STRIDE (9) -- cgit v1.2.3 From ee2636b8670b1ab2a02a65923a9bef59e9199c37 Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:38 -0700 Subject: iommu/vt-d: Enable base Intel IOMMU debugfs support Add a new config option CONFIG_INTEL_IOMMU_DEBUGFS and do the base enabling for Intel IOMMU debugfs. Cc: Lu Baolu Cc: Fenghua Yu Cc: Ashok Raj Cc: Jacob Pan Co-Developed-by: Gayatri Kammela Signed-off-by: Gayatri Kammela Reviewed-by: Andy Shevchenko Reviewed-by: Lu Baolu Signed-off-by: Sohil Mehta 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 3bdb9aa198af..b0ae25837361 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -621,6 +621,12 @@ extern int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_ extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #endif +#ifdef CONFIG_INTEL_IOMMU_DEBUGFS +void intel_iommu_debugfs_init(void); +#else +static inline void intel_iommu_debugfs_init(void) {} +#endif /* CONFIG_INTEL_IOMMU_DEBUGFS */ + extern const struct attribute_group *intel_iommu_groups[]; bool context_present(struct context_entry *context); struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, -- cgit v1.2.3 From 5131e08cd0f8a3faa30c1cdaf53940d6bce1715a Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 19 Sep 2018 11:12:58 +0100 Subject: iommu: Remove .domain_{get,set}_windows Since these are trivially handled by the .domain_{get,set}_attr callbacks when relevant, we can streamline struct iommu_ops for everyone. Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- 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 c783648d4060..c08ba5d2d451 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -181,8 +181,6 @@ struct iommu_resv_region { * @apply_resv_region: Temporary helper call-back for iova reserved ranges * @domain_window_enable: Configure and enable a particular window for a domain * @domain_window_disable: Disable a particular window for a domain - * @domain_set_windows: Set the number of windows for a domain - * @domain_get_windows: Return the number of windows for a domain * @of_xlate: add OF master IDs to iommu grouping * @pgsize_bitmap: bitmap of all possible supported page sizes */ @@ -223,10 +221,6 @@ struct iommu_ops { int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); - /* Set the number of windows per domain */ - int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); - /* Get the number of windows per domain */ - u32 (*domain_get_windows)(struct iommu_domain *domain); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); -- cgit v1.2.3 From c2c729415b2d21329104fecaa86878d295f1041f Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:42 -0600 Subject: coresight: platform: Cleanup coresight connection handling The platform code parses the component connections and populates a platform-description of the output connections in arrays of fields (which is never freed). This is later copied in the coresight_register to a newly allocated area, represented by coresight_connection(s). This patch cleans up the code dealing with connections by making use of the "coresight_connection" structure right at the platform code and lets the generic driver simply re-use information provided by the platform. Thus making it reader friendly as well as avoiding the wastage of unused memory. Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index d828a6efe0b1..41e1f4333bf2 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -94,20 +94,15 @@ union coresight_dev_subtype { * @cpu: the CPU a source belongs to. Only applicable for ETM/PTMs. * @name: name of the component as shown under sysfs. * @nr_inport: number of input ports for this component. - * @outports: list of remote endpoint port number. - * @child_names:name of all child components connected to this device. - * @child_ports:child component port number the current component is - connected to. * @nr_outport: number of output ports for this component. + * @conns: Array of nr_outport connections from this component */ struct coresight_platform_data { int cpu; const char *name; int nr_inport; - int *outports; - const char **child_names; - int *child_ports; int nr_outport; + struct coresight_connection *conns; }; /** -- cgit v1.2.3 From 7ec786ad193beb5579223174e119805569a7af3b Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:54 -0600 Subject: coresight: perf: Remove reset_buffer call back for sinks Right now we issue an update_buffer() and reset_buffer() call backs in succession when we stop tracing an event. The update_buffer is supposed to check the status of the buffer and make sure the ring buffer is updated with the trace data. And we store information about the size of the data collected only to be consumed by the reset_buffer callback which always follows the update_buffer. This was originally designed for handling future IPs which could trigger a buffer overflow interrupt. This patch gets rid of the reset_buffer callback altogether and performs the actions in update_buffer, making it return the size collected. We can always add the support for handling the overflow interrupt case later. This removes some not-so pretty hack (storing the new head in the size field for snapshot mode) and cleans it up a little bit. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 41e1f4333bf2..8e52682b1e90 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -186,7 +186,6 @@ struct coresight_device { * @alloc_buffer: initialises perf's ring buffer for trace collection. * @free_buffer: release memory allocated in @get_config. * @set_buffer: initialises buffer mechanic before a trace session. - * @reset_buffer: finalises buffer mechanic after a trace session. * @update_buffer: update buffer pointers after a trace session. */ struct coresight_ops_sink { @@ -198,10 +197,7 @@ struct coresight_ops_sink { int (*set_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); - unsigned long (*reset_buffer)(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config); - void (*update_buffer)(struct coresight_device *csdev, + unsigned long (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); }; -- cgit v1.2.3 From 3d6e8935758392179645e1b105789b3da329ad38 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:56 -0600 Subject: coresight: perf: Remove set_buffer call back In coresight perf mode, we need to prepare the sink before starting a session, which is done via set_buffer call back. We then proceed to enable the tracing. If we fail to start the session successfully, we leave the sink configuration unchanged. In order to make the operation atomic and to avoid yet another call back to clear the buffer, we get rid of the "set_buffer" call back and pass the buffer details via enable() call back to the sink. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 8e52682b1e90..53535821dc25 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -185,18 +185,14 @@ struct coresight_device { * @disable: disables the sink. * @alloc_buffer: initialises perf's ring buffer for trace collection. * @free_buffer: release memory allocated in @get_config. - * @set_buffer: initialises buffer mechanic before a trace session. * @update_buffer: update buffer pointers after a trace session. */ struct coresight_ops_sink { - int (*enable)(struct coresight_device *csdev, u32 mode); + int (*enable)(struct coresight_device *csdev, u32 mode, void *data); void (*disable)(struct coresight_device *csdev); void *(*alloc_buffer)(struct coresight_device *csdev, int cpu, void **pages, int nr_pages, bool overwrite); void (*free_buffer)(void *config); - int (*set_buffer)(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config); unsigned long (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); -- cgit v1.2.3 From 2478a6ae4a6a4c8e3f7e9f6f849dffe92e5238e1 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:18:11 -0600 Subject: coresight: Add support for CLAIM tag protocol Coresight architecture defines CLAIM tags for a device to negotiate control of the components (external agent vs self-hosted). Each device has a pair of registers (CLAIMSET & CLAIMCLR) for managing the CLAIM tags. However, the protocol for the CLAIM tags is IMPLEMENTATION DEFINED. PSCI has recommendations for the use of the CLAIM tags to negotiate controls for external agent vs self-hosted use. This patch implements the recommended protocol by PSCI. The claim/disclaim operations are performed from the device specific drivers. The disadvantage is that the calls are sprinkled in each driver, but this makes the operation much simpler. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier 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 53535821dc25..46c67a764877 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -257,6 +257,13 @@ extern int coresight_enable(struct coresight_device *csdev); extern void coresight_disable(struct coresight_device *csdev); extern int coresight_timeout(void __iomem *addr, u32 offset, int position, int value); + +extern int coresight_claim_device(void __iomem *base); +extern int coresight_claim_device_unlocked(void __iomem *base); + +extern void coresight_disclaim_device(void __iomem *base); +extern void coresight_disclaim_device_unlocked(void __iomem *base); + #else static inline struct coresight_device * coresight_register(struct coresight_desc *desc) { return NULL; } @@ -266,6 +273,19 @@ coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } static inline void coresight_disable(struct coresight_device *csdev) {} static inline int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) { return 1; } +static inline int coresight_claim_device_unlocked(void __iomem *base) +{ + return -EINVAL; +} + +static inline int coresight_claim_device(void __iomem *base) +{ + return -EINVAL; +} + +static inline void coresight_disclaim_device(void __iomem *base) {} +static inline void coresight_disclaim_device_unlocked(void __iomem *base) {} + #endif #ifdef CONFIG_OF -- cgit v1.2.3 From 800b932969c53c4044ff9f9fd1ee793a87fa8ef0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:15 -0700 Subject: vmbus: pass channel to hv_process_channel_removal Rather than passing relid and then looking up the channel. Pass the channel directly, since caller already knows it. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- 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 2c3798bcb01c..6c4575c7f46b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1443,7 +1443,7 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -void hv_process_channel_removal(u32 relid); +void hv_process_channel_removal(struct vmbus_channel *channel); void vmbus_setevent(struct vmbus_channel *channel); /* -- cgit v1.2.3 From 52a42c2a90226dc61c99bbd0cb096deeb52c334b Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:16 -0700 Subject: vmbus: keep pointer to ring buffer page Avoid going from struct page to virt address (and back) by just keeping pointer to the allocated pages instead of virt address. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- 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 6c4575c7f46b..a6c32d2d090b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -739,7 +739,7 @@ struct vmbus_channel { u32 ringbuffer_gpadlhandle; /* Allocated memory for ring buffer */ - void *ringbuffer_pages; + struct page *ringbuffer_page; u32 ringbuffer_pagecount; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ -- cgit v1.2.3 From ae6935ed7d424ffa74d634da00767e7b03c98fd3 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:17 -0700 Subject: vmbus: split ring buffer allocation from open The UIO driver needs the ring buffer to be persistent(reused) across open/close. Split the allocation and setup of ring buffer out of vmbus_open. For normal usage vmbus_open/vmbus_close there are no changes; only impacts uio_hv_generic which needs to keep ring buffer memory and reuse when application restarts. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a6c32d2d090b..b3e24368930a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -741,6 +741,7 @@ struct vmbus_channel { /* Allocated memory for ring buffer */ struct page *ringbuffer_page; u32 ringbuffer_pagecount; + u32 ringbuffer_send_offset; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ @@ -1021,6 +1022,14 @@ struct vmbus_packet_mpb_array { struct hv_mpb_array range; } __packed; +int vmbus_alloc_ring(struct vmbus_channel *channel, + u32 send_size, u32 recv_size); +void vmbus_free_ring(struct vmbus_channel *channel); + +int vmbus_connect_ring(struct vmbus_channel *channel, + void (*onchannel_callback)(void *context), + void *context); +int vmbus_disconnect_ring(struct vmbus_channel *channel); extern int vmbus_open(struct vmbus_channel *channel, u32 send_ringbuffersize, -- cgit v1.2.3 From bfddabfa230452cea32aae82f9cd85ab22601acf Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:18 -0700 Subject: uio: introduce UIO_MEM_IOVA Introduce the concept of mapping physical memory locations that are normal memory. The new type UIO_MEM_IOVA are similar to existing UIO_MEM_PHYS but the backing memory is not marked as uncached. Also, indent related switch to the currently used style. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 6f8b68cd460f..a3cd7cb67a69 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -133,6 +133,7 @@ extern void uio_event_notify(struct uio_info *info); #define UIO_MEM_PHYS 1 #define UIO_MEM_LOGICAL 2 #define UIO_MEM_VIRTUAL 3 +#define UIO_MEM_IOVA 4 /* defines for uio_port->porttype */ #define UIO_PORT_NONE 0 -- cgit v1.2.3 From 1a0afc14b5da329765d6ecd4a79f546b9363ad8c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 25 Sep 2018 13:16:55 -0700 Subject: Revert "dma-mapping: clear dev->dma_ops in arch_teardown_dma_ops" This reverts commit 46053c73685411915d3de50c5a0045beef32806b. This change breaks architectures setting up dma_ops in their own magic way and not using arch_setup_dma_ops, so revert it. Reported-by: Guenter Roeck Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index bd81e74cca7b..d23fc45c8208 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -665,10 +665,7 @@ static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, #endif #ifndef arch_teardown_dma_ops -static inline void arch_teardown_dma_ops(struct device *dev) -{ - dev->dma_ops = NULL; -} +static inline void arch_teardown_dma_ops(struct device *dev) { } #endif static inline unsigned int dma_get_max_seg_size(struct device *dev) -- cgit v1.2.3 From 6f99528e9797794b91b43321fbbc93fe772b0803 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 24 Sep 2018 19:22:49 +0300 Subject: net: core: netlink: add helper refcount dec and lock function Rtnl lock is encapsulated in netlink and cannot be accessed by other modules directly. This means that reference counted objects that rely on rtnl lock cannot use it with refcounter helper function that atomically releases decrements reference and obtains mutex. This patch implements simple wrapper function around refcount_dec_and_lock that obtains rtnl lock if reference counter value reached 0. Signed-off-by: Vlad Buslov Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 5225832bd6ff..9cdd76348d9a 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -6,6 +6,7 @@ #include #include #include +#include #include extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -34,6 +35,7 @@ extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); +extern bool refcount_dec_and_rtnl_lock(refcount_t *r); extern wait_queue_head_t netdev_unregistering_wq; extern struct rw_semaphore pernet_ops_rwsem; -- cgit v1.2.3 From 3a7d0d07a386716b459b00783b11a8211cefcc0f Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 24 Sep 2018 19:22:51 +0300 Subject: net: sched: extend Qdisc with rcu Currently, Qdisc API functions assume that users have rtnl lock taken. To implement rtnl unlocked classifiers update interface, Qdisc API must be extended with functions that do not require rtnl lock. Extend Qdisc structure with rcu. Implement special version of put function qdisc_put_unlocked() that is called without rtnl lock taken. This function only takes rtnl lock if Qdisc reference counter reached zero and is intended to be used as optimization. Signed-off-by: Vlad Buslov Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 9cdd76348d9a..bb9cb84114c1 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -85,6 +85,11 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) return rtnl_dereference(dev->ingress_queue); } +static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev) +{ + return rcu_dereference(dev->ingress_queue); +} + struct netdev_queue *dev_ingress_queue_create(struct net_device *dev); #ifdef CONFIG_NET_INGRESS -- cgit v1.2.3 From 76582671eb5d006a78420776cc5f73195b867e81 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:36 -0700 Subject: firmware: xilinx: Add Zynqmp firmware driver This patch is adding communication layer with firmware. Firmware driver provides an interface to firmware APIs. Interface APIs can be used by any driver to communicate to PMUFW(Platform Management Unit). All requests go through ATF. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 63 ++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) create mode 100644 include/linux/firmware/xlnx-zynqmp.h (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h new file mode 100644 index 000000000000..cb63bedf3dcf --- /dev/null +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Xilinx Zynq MPSoC Firmware layer + * + * Copyright (C) 2014-2018 Xilinx + * + * Michal Simek + * Davorin Mista + * Jolly Shah + * Rajan Vaja + */ + +#ifndef __FIRMWARE_ZYNQMP_H__ +#define __FIRMWARE_ZYNQMP_H__ + +#define ZYNQMP_PM_VERSION_MAJOR 1 +#define ZYNQMP_PM_VERSION_MINOR 0 + +#define ZYNQMP_PM_VERSION ((ZYNQMP_PM_VERSION_MAJOR << 16) | \ + ZYNQMP_PM_VERSION_MINOR) + +#define ZYNQMP_TZ_VERSION_MAJOR 1 +#define ZYNQMP_TZ_VERSION_MINOR 0 + +#define ZYNQMP_TZ_VERSION ((ZYNQMP_TZ_VERSION_MAJOR << 16) | \ + ZYNQMP_TZ_VERSION_MINOR) + +/* SMC SIP service Call Function Identifier Prefix */ +#define PM_SIP_SVC 0xC2000000 +#define PM_GET_TRUSTZONE_VERSION 0xa03 + +/* Number of 32bits values in payload */ +#define PAYLOAD_ARG_CNT 4U + +enum pm_api_id { + PM_GET_API_VERSION = 1, +}; + +/* PMU-FW return status codes */ +enum pm_ret_status { + XST_PM_SUCCESS = 0, + XST_PM_INTERNAL = 2000, + XST_PM_CONFLICT, + XST_PM_NO_ACCESS, + XST_PM_INVALID_NODE, + XST_PM_DOUBLE_REQ, + XST_PM_ABORT_SUSPEND, +}; + +struct zynqmp_eemi_ops { + int (*get_api_version)(u32 *version); +}; + +#if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) +const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); +#else +static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) +{ + return NULL; +} +#endif + +#endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 59ecdd778879f171072b663f91de6c3a595e2ed4 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:37 -0700 Subject: firmware: xilinx: Add query data API Add ZynqMP firmware query data API to query platform specific information(clocks, pins) from firmware. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index cb63bedf3dcf..287f42caa623 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -34,6 +34,7 @@ enum pm_api_id { PM_GET_API_VERSION = 1, + PM_QUERY_DATA = 35, }; /* PMU-FW return status codes */ @@ -47,8 +48,27 @@ enum pm_ret_status { XST_PM_ABORT_SUSPEND, }; +enum pm_query_id { + PM_QID_INVALID, +}; + +/** + * struct zynqmp_pm_query_data - PM query data + * @qid: query ID + * @arg1: Argument 1 of query data + * @arg2: Argument 2 of query data + * @arg3: Argument 3 of query data + */ +struct zynqmp_pm_query_data { + u32 qid; + u32 arg1; + u32 arg2; + u32 arg3; +}; + struct zynqmp_eemi_ops { int (*get_api_version)(u32 *version); + int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3 From f9627312e20721681ea326bd2b7935bf8034b288 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:38 -0700 Subject: firmware: xilinx: Add clock APIs Add clock APIs to control clocks through firmware interface. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 287f42caa623..015e130431e6 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -35,6 +35,15 @@ enum pm_api_id { PM_GET_API_VERSION = 1, PM_QUERY_DATA = 35, + PM_CLOCK_ENABLE, + PM_CLOCK_DISABLE, + PM_CLOCK_GETSTATE, + PM_CLOCK_SETDIVIDER, + PM_CLOCK_GETDIVIDER, + PM_CLOCK_SETRATE, + PM_CLOCK_GETRATE, + PM_CLOCK_SETPARENT, + PM_CLOCK_GETPARENT, }; /* PMU-FW return status codes */ @@ -48,8 +57,20 @@ enum pm_ret_status { XST_PM_ABORT_SUSPEND, }; +enum pm_ioctl_id { + IOCTL_SET_PLL_FRAC_MODE = 8, + IOCTL_GET_PLL_FRAC_MODE, + IOCTL_SET_PLL_FRAC_DATA, + IOCTL_GET_PLL_FRAC_DATA, +}; + enum pm_query_id { PM_QID_INVALID, + PM_QID_CLOCK_GET_NAME, + PM_QID_CLOCK_GET_TOPOLOGY, + PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, + PM_QID_CLOCK_GET_PARENTS, + PM_QID_CLOCK_GET_ATTRIBUTES, }; /** @@ -69,6 +90,15 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*get_api_version)(u32 *version); 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); + 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); + int (*clock_setparent)(u32 clock_id, u32 parent_id); + int (*clock_getparent)(u32 clock_id, u32 *parent_id); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3 From 2ba3c43f09c50eb1c0472decdfba71010d8694dc Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Tue, 4 Sep 2018 15:47:17 +0530 Subject: phy: qcom-ufs: Remove stale methods that handle ref clk Remove ufs_qcom_phy_enable/(disable)_dev_ref_clk() that are not being used by any code. Signed-off-by: Vivek Gautam Reviewed-by: Bjorn Andersson Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy-qcom-ufs.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h index 0a2c18a9771d..9dd85071bcce 100644 --- a/include/linux/phy/phy-qcom-ufs.h +++ b/include/linux/phy/phy-qcom-ufs.h @@ -17,20 +17,6 @@ #include "phy.h" -/** - * ufs_qcom_phy_enable_dev_ref_clk() - Enable the device - * ref clock. - * @phy: reference to a generic phy. - */ -void ufs_qcom_phy_enable_dev_ref_clk(struct phy *phy); - -/** - * ufs_qcom_phy_disable_dev_ref_clk() - Disable the device - * ref clock. - * @phy: reference to a generic phy. - */ -void ufs_qcom_phy_disable_dev_ref_clk(struct phy *phy); - int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); void ufs_qcom_phy_save_controller_version(struct phy *phy, u8 major, u16 minor, u16 step); -- cgit v1.2.3 From 1e1e465c6d23aa7d1858eb2894408f15770af16c Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Tue, 4 Sep 2018 15:47:18 +0530 Subject: scsi/ufs: qcom: Remove ufs_qcom_phy_*() calls from host The host makes direct calls into phy using ufs_qcom_phy_*() APIs. These APIs are only defined for 20nm qcom-ufs-qmp phy which is not being used by any architecture as yet. Future architectures too are not going to use 20nm ufs phy. So remove these ufs_qcom_phy_*() calls from host to let further change declare the 20nm phy as broken. Also remove couple of stale enum defines for ufs phy. Signed-off-by: Vivek Gautam Acked-by: Martin K. Petersen Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy-qcom-ufs.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/phy/phy-qcom-ufs.h (limited to 'include/linux') diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h deleted file mode 100644 index 9dd85071bcce..000000000000 --- a/include/linux/phy/phy-qcom-ufs.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Copyright (c) 2013-2015, Linux Foundation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef PHY_QCOM_UFS_H_ -#define PHY_QCOM_UFS_H_ - -#include "phy.h" - -int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); -void ufs_qcom_phy_save_controller_version(struct phy *phy, - u8 major, u16 minor, u16 step); - -#endif /* PHY_QCOM_UFS_H_ */ -- cgit v1.2.3 From 71e0940d52e107748b270213a01d3b1546657d74 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 21 Sep 2018 09:32:44 -0700 Subject: efi: honour memory reservations passed via a linux specific config table In order to allow the OS to reserve memory persistently across a kexec, introduce a Linux-specific UEFI configuration table that points to the head of a linked list in memory, allowing each kernel to add list items describing memory regions that the next kernel should treat as reserved. This is useful, e.g., for GICv3 based ARM systems that cannot disable DMA access to the LPI tables, forcing them to reuse the same memory region again after a kexec reboot. Tested-by: Jeremy Linton Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 401e4b254e30..a5cb580472c5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -672,6 +672,7 @@ void efi_native_runtime_setup(void); #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) +#define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) typedef struct { efi_guid_t guid; @@ -957,6 +958,7 @@ extern struct efi { unsigned long mem_attr_table; /* memory attributes table */ unsigned long rng_seed; /* UEFI firmware random seed */ unsigned long tpm_log; /* TPM2 Event Log table */ + unsigned long mem_reserve; /* Linux EFI memreserve table */ efi_get_time_t *get_time; efi_set_time_t *set_time; efi_get_wakeup_time_t *get_wakeup_time; @@ -1662,4 +1664,10 @@ extern int efi_tpm_eventlog_init(void); /* Workqueue to queue EFI Runtime Services */ extern struct workqueue_struct *efi_rts_wq; +struct linux_efi_memreserve { + phys_addr_t next; + phys_addr_t base; + phys_addr_t size; +}; + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From a23d3bb05ccbd815c79293d2207fedede0b3515d Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 21 Sep 2018 09:32:46 -0700 Subject: efi: add API to reserve memory persistently across kexec reboot Add kernel plumbing to reserve memory regions persistently on a EFI system by adding entries to the MEMRESERVE linked list. Tested-by: Jeremy Linton 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 a5cb580472c5..22e4de9d3700 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1043,6 +1043,7 @@ extern int __init efi_uart_console_only (void); extern u64 efi_mem_desc_end(efi_memory_desc_t *md); extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern void efi_mem_reserve(phys_addr_t addr, u64 size); +extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); extern void efi_reserve_boot_services(void); -- cgit v1.2.3 From 9dbbedaa6171247c4c7c40b83f05b200a117c2e0 Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Tue, 11 Sep 2018 12:15:21 -0700 Subject: efi: Make efi_rts_work accessible to efi page fault handler After the kernel has booted, if any accesses by firmware causes a page fault, the efi page fault handler would freeze efi_rts_wq and schedules a new process. To do this, the efi page fault handler needs efi_rts_work. Hence, make it accessible. There will be no race conditions in accessing this structure, because all the calls to efi runtime services are already serialized. Tested-by: Bhupesh Sharma Suggested-by: Matt Fleming Based-on-code-from: Ricardo Neri Signed-off-by: Sai Praneeth Prakhya Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 22e4de9d3700..a929d2bf41fa 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1662,6 +1662,42 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); +/* efi_runtime_service() function identifiers */ +enum efi_rts_ids { + GET_TIME, + SET_TIME, + GET_WAKEUP_TIME, + SET_WAKEUP_TIME, + GET_VARIABLE, + GET_NEXT_VARIABLE, + SET_VARIABLE, + QUERY_VARIABLE_INFO, + GET_NEXT_HIGH_MONO_COUNT, + UPDATE_CAPSULE, + QUERY_CAPSULE_CAPS, +}; + +/* + * efi_runtime_work: Details of EFI Runtime Service work + * @arg<1-5>: EFI Runtime Service function arguments + * @status: Status of executing EFI Runtime Service + * @efi_rts_id: EFI Runtime Service function identifier + * @efi_rts_comp: Struct used for handling completions + */ +struct efi_runtime_work { + void *arg1; + void *arg2; + void *arg3; + void *arg4; + void *arg5; + efi_status_t status; + struct work_struct work; + enum efi_rts_ids efi_rts_id; + struct completion efi_rts_comp; +}; + +extern struct efi_runtime_work efi_rts_work; + /* Workqueue to queue EFI Runtime Services */ extern struct workqueue_struct *efi_rts_wq; -- cgit v1.2.3 From 3425d934fc0312f62024163736a7afe4de20c10f Mon Sep 17 00:00:00 2001 From: Sai Praneeth Date: Tue, 11 Sep 2018 12:15:22 -0700 Subject: efi/x86: Handle page faults occurring while running EFI runtime services Memory accesses performed by UEFI runtime services should be limited to: - reading/executing from EFI_RUNTIME_SERVICES_CODE memory regions - reading/writing from/to EFI_RUNTIME_SERVICES_DATA memory regions - reading/writing by-ref arguments - reading/writing from/to the stack. Accesses outside these regions may cause the kernel to hang because the memory region requested by the firmware isn't mapped in efi_pgd, which causes a page fault in ring 0 and the kernel fails to handle it, leading to die(). To save kernel from hanging, add an EFI specific page fault handler which recovers from such faults by 1. If the efi runtime service is efi_reset_system(), reboot the machine through BIOS. 2. If the efi runtime service is _not_ efi_reset_system(), then freeze efi_rts_wq and schedule a new process. The EFI page fault handler offers us two advantages: 1. Avoid potential hangs caused by buggy firmware. 2. Shout loud that the firmware is buggy and hence is not a kernel bug. Tested-by: Bhupesh Sharma Suggested-by: Matt Fleming Based-on-code-from: Ricardo Neri Signed-off-by: Sai Praneeth Prakhya Reviewed-by: Thomas Gleixner [ardb: clarify commit log] Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index a929d2bf41fa..845174e113ce 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1662,8 +1662,13 @@ struct linux_efi_tpm_eventlog { extern int efi_tpm_eventlog_init(void); -/* efi_runtime_service() function identifiers */ +/* + * efi_runtime_service() function identifiers. + * "NONE" is used by efi_recover_from_page_fault() to check if the page + * fault happened while executing an efi runtime service. + */ enum efi_rts_ids { + NONE, GET_TIME, SET_TIME, GET_WAKEUP_TIME, @@ -1673,6 +1678,7 @@ enum efi_rts_ids { SET_VARIABLE, QUERY_VARIABLE_INFO, GET_NEXT_HIGH_MONO_COUNT, + RESET_SYSTEM, UPDATE_CAPSULE, QUERY_CAPSULE_CAPS, }; -- cgit v1.2.3 From dbfe2953f63c640463c630746cd5d9de8b2f63ae Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 25 Sep 2018 14:38:18 +0200 Subject: x86/speculation: Apply IBPB more strictly to avoid cross-process data leak Currently, IBPB is only issued in cases when switching into a non-dumpable process, the rationale being to protect such 'important and security sensitive' processess (such as GPG) from data leaking into a different userspace process via spectre v2. This is however completely insufficient to provide proper userspace-to-userpace spectrev2 protection, as any process can poison branch buffers before being scheduled out, and the newly scheduled process immediately becomes spectrev2 victim. In order to minimize the performance impact (for usecases that do require spectrev2 protection), issue the barrier only in cases when switching between processess where the victim can't be ptraced by the potential attacker (as in such cases, the attacker doesn't have to bother with branch buffers at all). [ tglx: Split up PTRACE_MODE_NOACCESS_CHK into PTRACE_MODE_SCHED and PTRACE_MODE_IBPB to be able to do ptrace() context tracking reasonably fine-grained ] Fixes: 18bf3c3ea8 ("x86/speculation: Use Indirect Branch Prediction Barrier in context switch") Originally-by: Tim Chen Signed-off-by: Jiri Kosina Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: "WoodhouseDavid" Cc: Andi Kleen Cc: "SchauflerCasey" Link: https://lkml.kernel.org/r/nycvar.YFH.7.76.1809251437340.15880@cbobk.fhfr.pm --- include/linux/ptrace.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4f36431c380b..e5e5ef513df3 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -62,14 +62,17 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 -#define PTRACE_MODE_FSCREDS 0x08 -#define PTRACE_MODE_REALCREDS 0x10 +#define PTRACE_MODE_FSCREDS 0x08 +#define PTRACE_MODE_REALCREDS 0x10 +#define PTRACE_MODE_SCHED 0x20 +#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) +#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -87,6 +90,20 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); +/** + * ptrace_may_access - check whether the caller is permitted to access + * a target task. + * @task: target task + * @mode: selects type of access and caller credentials + * + * Returns true on success, false on denial. + * + * Similar to ptrace_may_access(). Only to be called from context switch + * code. Does not call into audit and the regular LSM hooks due to locking + * constraints. + */ +extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); + static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); -- cgit v1.2.3 From bca6b067b0b269a7b8ba129e2a918309ca8b4a55 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:03 -0700 Subject: block: Move power management code into a new source file Move the code for runtime power management from blk-core.c into the new source file blk-pm.c. Move the corresponding declarations from into . For CONFIG_PM=n, leave out the declarations of the functions that are not used in that mode. This patch not only reduces the number of #ifdefs in the block layer core code but also reduces the size of header file and hence should help to reduce the build time of the Linux kernel if CONFIG_PM is not defined. Signed-off-by: Bart Van Assche Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Cc: Jianchao Wang Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blk-pm.h | 24 ++++++++++++++++++++++++ include/linux/blkdev.h | 23 ----------------------- 2 files changed, 24 insertions(+), 23 deletions(-) create mode 100644 include/linux/blk-pm.h (limited to 'include/linux') diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h new file mode 100644 index 000000000000..b80c65aba249 --- /dev/null +++ b/include/linux/blk-pm.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BLK_PM_H_ +#define _BLK_PM_H_ + +struct device; +struct request_queue; + +/* + * block layer runtime pm functions + */ +#ifdef CONFIG_PM +extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); +extern int blk_pre_runtime_suspend(struct request_queue *q); +extern void blk_post_runtime_suspend(struct request_queue *q, int err); +extern void blk_pre_runtime_resume(struct request_queue *q); +extern void blk_post_runtime_resume(struct request_queue *q, int err); +extern void blk_set_runtime_active(struct request_queue *q); +#else +static inline void blk_pm_runtime_init(struct request_queue *q, + struct device *dev) {} +#endif + +#endif /* _BLK_PM_H_ */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1d5e14139795..cd863511dedb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1280,29 +1280,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); -/* - * block layer runtime pm functions - */ -#ifdef CONFIG_PM -extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); -extern int blk_pre_runtime_suspend(struct request_queue *q); -extern void blk_post_runtime_suspend(struct request_queue *q, int err); -extern void blk_pre_runtime_resume(struct request_queue *q); -extern void blk_post_runtime_resume(struct request_queue *q, int err); -extern void blk_set_runtime_active(struct request_queue *q); -#else -static inline void blk_pm_runtime_init(struct request_queue *q, - struct device *dev) {} -static inline int blk_pre_runtime_suspend(struct request_queue *q) -{ - return -ENOSYS; -} -static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} -static inline void blk_pre_runtime_resume(struct request_queue *q) {} -static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} -static inline void blk_set_runtime_active(struct request_queue *q) {} -#endif - /* * 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 -- cgit v1.2.3 From cd84a62e0078dce09f4ed349bec84f86c9d54b30 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:04 -0700 Subject: block, scsi: Change the preempt-only flag into a counter The RQF_PREEMPT flag is used for three purposes: - In the SCSI core, for making sure that power management requests are executed even if a device is in the "quiesced" state. - For domain validation by SCSI drivers that use the parallel port. - In the IDE driver, for IDE preempt requests. Rename "preempt-only" into "pm-only" because the primary purpose of this mode is power management. Since the power management core may but does not have to resume a runtime suspended device before performing system-wide suspend and since a later patch will set "pm-only" mode as long as a block device is runtime suspended, make it possible to set "pm-only" mode from more than one context. Since with this change scsi_device_quiesce() is no longer idempotent, make that function return early if it is called for a quiesced queue. Signed-off-by: Bart Van Assche Acked-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Ming Lei Cc: Jianchao Wang Cc: Johannes Thumshirn Cc: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cd863511dedb..13bb54f26736 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -504,6 +504,12 @@ struct request_queue { * various queue flags, see QUEUE_* below */ unsigned long queue_flags; + /* + * Number of contexts that have called blk_set_pm_only(). If this + * counter is above zero then only RQF_PM and RQF_PREEMPT requests are + * processed. + */ + atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from @@ -698,7 +704,6 @@ struct request_queue { #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ -#define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -736,12 +741,11 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) -#define blk_queue_preempt_only(q) \ - test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags) +#define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) -extern int blk_set_preempt_only(struct request_queue *q); -extern void blk_clear_preempt_only(struct request_queue *q); +extern void blk_set_pm_only(struct request_queue *q); +extern void blk_clear_pm_only(struct request_queue *q); static inline int queue_in_flight(struct request_queue *q) { -- cgit v1.2.3 From 18c9a6bbe0645a05172a900740b9d2d379d54320 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 26 Sep 2018 14:01:07 -0700 Subject: percpu-refcount: Introduce percpu_ref_resurrect() This function will be used in a later patch to switch the struct request_queue q_usage_counter from killed back to live. In contrast to percpu_ref_reinit(), this new function does not require that the refcount is zero. Signed-off-by: Bart Van Assche Acked-by: Tejun Heo Reviewed-by: Ming Lei Cc: Christoph Hellwig Cc: Jianchao Wang Cc: Hannes Reinecke Cc: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/percpu-refcount.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 009cdf3d65b6..b297cd1cd4f1 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -108,6 +108,7 @@ void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); +void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); /** -- cgit v1.2.3 From 6194114324139dc16f3251c67ed853bd6d4ae056 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 24 Sep 2018 21:58:59 +0200 Subject: net: core: add member wol_enabled to struct net_device Add flag wol_enabled to struct net_device indicating whether Wake-on-LAN is enabled. As first user phy_suspend() will use it to decide whether PHY can be suspended or not. Fixes: f1e911d5d0df ("r8169: add basic phylib support") Fixes: e8cfd9d6c772 ("net: phy: call state machine synchronously in phy_stop") Signed-off-by: Heiner Kallweit Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5ab98053c8..c7861e4b402c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1730,6 +1730,8 @@ enum netdev_priv_flags { * switch driver and used to set the phys state of the * switch port. * + * @wol_enabled: Wake-on-LAN is enabled + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2014,6 +2016,7 @@ struct net_device { struct lock_class_key *qdisc_tx_busylock; struct lock_class_key *qdisc_running_key; bool proto_down; + unsigned wol_enabled:1; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 6b58859419554fb824e09cfdd73151a195473cbc Mon Sep 17 00:00:00 2001 From: Justin Ernst Date: Tue, 25 Sep 2018 09:34:49 -0500 Subject: EDAC: Raise the maximum number of memory controllers We observe an oops in the skx_edac module during boot: EDAC MC0: Giving out device to module skx_edac controller Skylake Socket#0 IMC#0 EDAC MC1: Giving out device to module skx_edac controller Skylake Socket#0 IMC#1 EDAC MC2: Giving out device to module skx_edac controller Skylake Socket#1 IMC#0 ... EDAC MC13: Giving out device to module skx_edac controller Skylake Socket#0 IMC#1 EDAC MC14: Giving out device to module skx_edac controller Skylake Socket#1 IMC#0 EDAC MC15: Giving out device to module skx_edac controller Skylake Socket#1 IMC#1 Too many memory controllers: 16 EDAC MC: Removed device 0 for skx_edac Skylake Socket#0 IMC#0 We observe there are two memory controllers per socket, with a limit of 16. Raise the maximum number of memory controllers from 16 to 2 * MAX_NUMNODES (1024). [ bp: This is just a band-aid fix until we've sorted out the whole issue with the bus_type association and handling in EDAC and can get rid of this arbitrary limit. ] Signed-off-by: Justin Ernst Signed-off-by: Borislav Petkov Acked-by: Russ Anderson Cc: Mauro Carvalho Chehab Cc: linux-edac@vger.kernel.org Link: https://lkml.kernel.org/r/20180925143449.284634-1-justin.ernst@hpe.com --- include/linux/edac.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index a45ce1f84bfc..1d0c9ea8825d 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -17,6 +17,7 @@ #include #include #include +#include #define EDAC_DEVICE_NAME_LEN 31 @@ -672,6 +673,6 @@ struct mem_ctl_info { /* * Maximum number of memory controllers in the coherent fabric. */ -#define EDAC_MAX_MCS 16 +#define EDAC_MAX_MCS 2 * MAX_NUMNODES #endif -- cgit v1.2.3 From 96a71f21ef1fcc32bea07c612a332a89a213f054 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 21 Sep 2018 21:20:30 +0300 Subject: fanotify: store fanotify_init() flags in group's fanotify_data This averts the need to re-generate flags in fanotify_show_fdinfo() and sets the scene for addition of more upcoming flags without growing new members to the fanotify_data struct. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 4 ++++ include/linux/fsnotify_backend.h | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 096c96f4f16a..9c5ea3bdfaa0 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -6,4 +6,8 @@ /* not valid from userspace, only kernel internal */ #define FAN_MARK_ONDIR 0x00000100 + +#define FAN_GROUP_FLAG(group, flag) \ + ((group)->fanotify_data.flags & (flag)) + #endif /* _LINUX_FANOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 81b88fc9df31..8e91341cbd8a 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -189,10 +189,10 @@ struct fsnotify_group { /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; - int f_flags; + int flags; /* flags from fanotify_init() */ + int f_flags; /* event_f_flags from fanotify_init() */ unsigned int max_marks; struct user_struct *user; - bool audit; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; -- cgit v1.2.3 From 9ae033aca8d600e36034d4d0743aad624cec92ed Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Sep 2018 23:51:36 -0700 Subject: jump_label: Abstract jump_entry member accessors In preparation of allowing architectures to use relative references in jump_label entries [which can dramatically reduce the memory footprint], introduce abstractions for references to the 'code' and 'key' members of struct jump_entry. Signed-off-by: Ard Biesheuvel Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Kees Cook Cc: Will Deacon Cc: Catalin Marinas Cc: Steven Rostedt Cc: Martin Schwidefsky Cc: Jessica Yu Link: https://lkml.kernel.org/r/20180919065144.25010-2-ard.biesheuvel@linaro.org --- include/linux/jump_label.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 1a0b6f17a5d6..2eadff9b3b90 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -119,6 +119,40 @@ struct static_key { #ifdef HAVE_JUMP_LABEL #include + +#ifndef __ASSEMBLY__ + +static inline unsigned long jump_entry_code(const struct jump_entry *entry) +{ + return entry->code; +} + +static inline unsigned long jump_entry_target(const struct jump_entry *entry) +{ + return entry->target; +} + +static inline struct static_key *jump_entry_key(const struct jump_entry *entry) +{ + return (struct static_key *)((unsigned long)entry->key & ~1UL); +} + +static inline bool jump_entry_is_branch(const struct jump_entry *entry) +{ + return (unsigned long)entry->key & 1UL; +} + +static inline bool jump_entry_is_init(const struct jump_entry *entry) +{ + return entry->code == 0; +} + +static inline void jump_entry_set_init(struct jump_entry *entry) +{ + entry->code = 0; +} + +#endif #endif #ifndef __ASSEMBLY__ -- cgit v1.2.3 From 50ff18ab497aa22f6a59444625df7508c8918237 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Sep 2018 23:51:37 -0700 Subject: jump_label: Implement generic support for relative references To reduce the size taken up by absolute references in jump label entries themselves and the associated relocation records in the .init segment, add support for emitting them as relative references instead. Note that this requires some extra care in the sorting routine, given that the offsets change when entries are moved around in the jump_entry table. Signed-off-by: Ard Biesheuvel Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Kees Cook Cc: Will Deacon Cc: Catalin Marinas Cc: Steven Rostedt Cc: Martin Schwidefsky Cc: Jessica Yu Link: https://lkml.kernel.org/r/20180919065144.25010-3-ard.biesheuvel@linaro.org --- include/linux/jump_label.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 2eadff9b3b90..2768a925bafa 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -121,6 +121,32 @@ struct static_key { #include #ifndef __ASSEMBLY__ +#ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE + +struct jump_entry { + s32 code; + s32 target; + long key; // key may be far away from the core kernel under KASLR +}; + +static inline unsigned long jump_entry_code(const struct jump_entry *entry) +{ + return (unsigned long)&entry->code + entry->code; +} + +static inline unsigned long jump_entry_target(const struct jump_entry *entry) +{ + return (unsigned long)&entry->target + entry->target; +} + +static inline struct static_key *jump_entry_key(const struct jump_entry *entry) +{ + long offset = entry->key & ~1L; + + return (struct static_key *)((unsigned long)&entry->key + offset); +} + +#else static inline unsigned long jump_entry_code(const struct jump_entry *entry) { @@ -137,6 +163,8 @@ static inline struct static_key *jump_entry_key(const struct jump_entry *entry) return (struct static_key *)((unsigned long)entry->key & ~1UL); } +#endif + static inline bool jump_entry_is_branch(const struct jump_entry *entry) { return (unsigned long)entry->key & 1UL; -- cgit v1.2.3 From 19483677684b6ca01606f58503cb79cdfbbc7c72 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Sep 2018 23:51:42 -0700 Subject: jump_label: Annotate entries that operate on __init code earlier Jump table entries are mostly read-only, with the exception of the init and module loader code that defuses entries that point into init code when the code being referred to is freed. For robustness, it would be better to move these entries into the ro_after_init section, but clearing the 'code' member of each jump table entry referring to init code at module load time races with the module_enable_ro() call that remaps the ro_after_init section read only, so we'd like to do it earlier. So given that whether such an entry refers to init code can be decided much earlier, we can pull this check forward. Since we may still need the code entry at this point, let's switch to setting a low bit in the 'key' member just like we do to annotate the default state of a jump table entry. Signed-off-by: Ard Biesheuvel Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Acked-by: Peter Zijlstra (Intel) Cc: linux-arm-kernel@lists.infradead.org Cc: linux-s390@vger.kernel.org Cc: Arnd Bergmann Cc: Heiko Carstens Cc: Will Deacon Cc: Catalin Marinas Cc: Steven Rostedt Cc: Martin Schwidefsky Cc: Jessica Yu Link: https://lkml.kernel.org/r/20180919065144.25010-8-ard.biesheuvel@linaro.org --- include/linux/jump_label.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 2768a925bafa..5df6a621e464 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -141,7 +141,7 @@ static inline unsigned long jump_entry_target(const struct jump_entry *entry) static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { - long offset = entry->key & ~1L; + long offset = entry->key & ~3L; return (struct static_key *)((unsigned long)&entry->key + offset); } @@ -160,7 +160,7 @@ static inline unsigned long jump_entry_target(const struct jump_entry *entry) static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { - return (struct static_key *)((unsigned long)entry->key & ~1UL); + return (struct static_key *)((unsigned long)entry->key & ~3UL); } #endif @@ -172,12 +172,12 @@ static inline bool jump_entry_is_branch(const struct jump_entry *entry) static inline bool jump_entry_is_init(const struct jump_entry *entry) { - return entry->code == 0; + return (unsigned long)entry->key & 2UL; } static inline void jump_entry_set_init(struct jump_entry *entry) { - entry->code = 0; + entry->key |= 2; } #endif @@ -213,7 +213,6 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); -extern void jump_label_invalidate_initmem(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -261,8 +260,6 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } -static inline void jump_label_invalidate_initmem(void) {} - static __always_inline bool static_key_false(struct static_key *key) { if (unlikely(static_key_count(key) > 0)) -- cgit v1.2.3 From c6babb5806b77c6ca7078c3487bb0a29704a4e38 Mon Sep 17 00:00:00 2001 From: Pu Wen Date: Tue, 25 Sep 2018 22:46:11 +0800 Subject: x86/pci, x86/amd_nb: Add Hygon Dhyana support to PCI and northbridge Hygon's PCI vendor ID is 0x1d94, and there are PCI devices 0x1450/0x1463/0x1464 for the host bridge on the Hygon Dhyana platform. Add Hygon Dhyana support to the PCI and northbridge subsystems by using the code path of AMD family 17h. [ bp: Massage commit message, sort local vars into reverse xmas tree order and move the amd_northbridges.num check up. ] Signed-off-by: Pu Wen Signed-off-by: Borislav Petkov Acked-by: Bjorn Helgaas # pci_ids.h Cc: tglx@linutronix.de Cc: mingo@redhat.com Cc: hpa@zytor.com Cc: x86@kernel.org Cc: thomas.lendacky@amd.com Cc: helgaas@kernel.org Cc: linux-pci@vger.kernel.org Link: https://lkml.kernel.org/r/5f8877bd413f2ea0833378dd5454df0720e1c0df.1537885177.git.puwen@hygon.cn --- 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 d157983b84cf..8a0841c73f81 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2561,6 +2561,8 @@ #define PCI_VENDOR_ID_AMAZON 0x1d0f +#define PCI_VENDOR_ID_HYGON 0x1d94 + #define PCI_VENDOR_ID_TEKRAM 0x1de1 #define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29 -- cgit v1.2.3 From b445bfcb9081ae90fec90b828f3aacc565776901 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 25 Sep 2018 11:42:28 +0200 Subject: spi: switch to SPDX license identifier Use the appropriate SPDX license identifier and drop the previous license text. Signed-off-by: Marco Felsch Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7bb36145e2ba..f08824ea1968 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1,15 +1,6 @@ -/* - * Copyright (C) 2005 David Brownell +/* SPDX-License-Identifier: GPL-2.0-or-later * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. + * Copyright (C) 2005 David Brownell */ #ifndef __LINUX_SPI_H -- cgit v1.2.3 From 5f143af7501e7c435c56e181a655493edaa92509 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 25 Sep 2018 11:42:29 +0200 Subject: spi: make OF helper available for others The of_find_spi_device_by_node() helper function is useful for other modules too. Export the funciton as GPL like all other spi helper functions and make it available if CONFIG_OF is enabled, because it isn't related to the CONFIG_OF_DYNAMIC context. Finally add a stub if CONFIG_OF isn't enabled, so others must not care about it. Signed-off-by: Marco Felsch Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a64235e05321..e9ebfcd2e932 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1277,7 +1277,6 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) { return 0; } #endif - /* If you're hotplugging an adapter with devices (parport, usb, etc) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but @@ -1309,6 +1308,22 @@ spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer) return list_is_last(&xfer->transfer_list, &ctlr->cur_msg->transfers); } +/* OF support code */ +#if IS_ENABLED(CONFIG_OF) + +/* must call put_device() when done with returned spi_device device */ +extern struct spi_device * +of_find_spi_device_by_node(struct device_node *node); + +#else + +static inline struct spi_device * +of_find_spi_device_by_node(struct device_node *node) +{ + return NULL; +} + +#endif /* IS_ENABLED(CONFIG_OF) */ /* Compatibility layer */ #define spi_master spi_controller -- cgit v1.2.3 From ed88660a5372faa67c168c3db5201e33e488c9fd Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 27 Sep 2018 15:55:51 -0700 Subject: block: move call of scheduler's ->completed_request() hook Commit 4bc6339a583c ("block: move blk_stat_add() to __blk_mq_end_request()") consolidated some calls using ktime_get() so we'd only need to call it once. Kyber's ->completed_request() hook also calls ktime_get(), so let's move it to the same place, too. Signed-off-by: Omar Sandoval 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 a02deea30185..015bb59c0331 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -111,7 +111,7 @@ struct elevator_mq_ops { void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); bool (*has_work)(struct blk_mq_hw_ctx *); - void (*completed_request)(struct request *); + void (*completed_request)(struct request *, u64); void (*started_request)(struct request *); void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); -- cgit v1.2.3 From e9e575b8f29445bcde67f421891efa4d6527d987 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Sep 2018 19:10:39 -0700 Subject: gss_krb5: Remove VLA usage of skcipher In the quest to remove all stack VLA usage from the kernel[1], this replaces struct crypto_skcipher and SKCIPHER_REQUEST_ON_STACK() usage with struct crypto_sync_skcipher and SYNC_SKCIPHER_REQUEST_ON_STACK(), which uses a fixed stack size. [1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com Cc: Trond Myklebust Cc: Anna Schumaker Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: YueHaibing Cc: linux-nfs@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Herbert Xu --- include/linux/sunrpc/gss_krb5.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 7df625d41e35..f6e8ceafafd8 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -71,10 +71,10 @@ struct gss_krb5_enctype { const u32 keyed_cksum; /* is it a keyed cksum? */ const u32 keybytes; /* raw key len, in bytes */ const u32 keylength; /* final key len, in bytes */ - u32 (*encrypt) (struct crypto_skcipher *tfm, + u32 (*encrypt) (struct crypto_sync_skcipher *tfm, void *iv, void *in, void *out, int length); /* encryption function */ - u32 (*decrypt) (struct crypto_skcipher *tfm, + u32 (*decrypt) (struct crypto_sync_skcipher *tfm, void *iv, void *in, void *out, int length); /* decryption function */ u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, @@ -98,12 +98,12 @@ struct krb5_ctx { u32 enctype; u32 flags; const struct gss_krb5_enctype *gk5e; /* enctype-specific info */ - struct crypto_skcipher *enc; - struct crypto_skcipher *seq; - struct crypto_skcipher *acceptor_enc; - struct crypto_skcipher *initiator_enc; - struct crypto_skcipher *acceptor_enc_aux; - struct crypto_skcipher *initiator_enc_aux; + struct crypto_sync_skcipher *enc; + struct crypto_sync_skcipher *seq; + struct crypto_sync_skcipher *acceptor_enc; + struct crypto_sync_skcipher *initiator_enc; + struct crypto_sync_skcipher *acceptor_enc_aux; + struct crypto_sync_skcipher *initiator_enc_aux; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; @@ -262,24 +262,24 @@ gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, u32 -krb5_encrypt(struct crypto_skcipher *key, +krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); u32 -krb5_decrypt(struct crypto_skcipher *key, +krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); int -gss_encrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *outbuf, +gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *outbuf, int offset, struct page **pages); int -gss_decrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *inbuf, +gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *inbuf, int offset); s32 krb5_make_seq_num(struct krb5_ctx *kctx, - struct crypto_skcipher *key, + struct crypto_sync_skcipher *key, int direction, u32 seqnum, unsigned char *cksum, unsigned char *buf); @@ -320,12 +320,12 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, int krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, - struct crypto_skcipher *cipher, + struct crypto_sync_skcipher *cipher, unsigned char *cksum); int krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, - struct crypto_skcipher *cipher, + struct crypto_sync_skcipher *cipher, s32 seqnum); void gss_krb5_make_confounder(char *p, u32 conflen); -- cgit v1.2.3 From cac5818c25d0423bda73e2b6997404ed0a7ed9e3 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Wed, 19 Sep 2018 10:10:54 +0000 Subject: crypto: user - Implement a generic crypto statistics This patch implement a generic way to get statistics about all crypto usages. Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- include/linux/crypto.h | 110 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 108 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index e8839d3a7559..3634ad6fe202 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -454,6 +454,33 @@ struct compress_alg { * @cra_refcnt: internally used * @cra_destroy: internally used * + * All following statistics are for this crypto_alg + * @encrypt_cnt: number of encrypt requests + * @decrypt_cnt: number of decrypt requests + * @compress_cnt: number of compress requests + * @decompress_cnt: number of decompress requests + * @generate_cnt: number of RNG generate requests + * @seed_cnt: number of times the rng was seeded + * @hash_cnt: number of hash requests + * @sign_cnt: number of sign requests + * @setsecret_cnt: number of setsecrey operation + * @generate_public_key_cnt: number of generate_public_key operation + * @verify_cnt: number of verify operation + * @compute_shared_secret_cnt: number of compute_shared_secret operation + * @encrypt_tlen: total data size handled by encrypt requests + * @decrypt_tlen: total data size handled by decrypt requests + * @compress_tlen: total data size handled by compress requests + * @decompress_tlen: total data size handled by decompress requests + * @generate_tlen: total data size of generated data by the RNG + * @hash_tlen: total data size hashed + * @akcipher_err_cnt: number of error for akcipher requests + * @cipher_err_cnt: number of error for akcipher requests + * @compress_err_cnt: number of error for akcipher requests + * @aead_err_cnt: number of error for akcipher requests + * @hash_err_cnt: number of error for akcipher requests + * @rng_err_cnt: number of error for akcipher requests + * @kpp_err_cnt: number of error for akcipher requests + * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. @@ -487,6 +514,45 @@ struct crypto_alg { void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; + + union { + atomic_t encrypt_cnt; + atomic_t compress_cnt; + atomic_t generate_cnt; + atomic_t hash_cnt; + atomic_t setsecret_cnt; + }; + union { + atomic64_t encrypt_tlen; + atomic64_t compress_tlen; + atomic64_t generate_tlen; + atomic64_t hash_tlen; + }; + union { + atomic_t akcipher_err_cnt; + atomic_t cipher_err_cnt; + atomic_t compress_err_cnt; + atomic_t aead_err_cnt; + atomic_t hash_err_cnt; + atomic_t rng_err_cnt; + atomic_t kpp_err_cnt; + }; + union { + atomic_t decrypt_cnt; + atomic_t decompress_cnt; + atomic_t seed_cnt; + atomic_t generate_public_key_cnt; + }; + union { + atomic64_t decrypt_tlen; + atomic64_t decompress_tlen; + }; + union { + atomic_t verify_cnt; + atomic_t compute_shared_secret_cnt; + }; + atomic_t sign_cnt; + } CRYPTO_MINALIGN_ATTR; /* @@ -907,6 +973,38 @@ static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm( return __crypto_ablkcipher_cast(req->base.tfm); } +static inline void crypto_stat_ablkcipher_encrypt(struct ablkcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct ablkcipher_tfm *crt = + crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + } else { + atomic_inc(&crt->base->base.__crt_alg->encrypt_cnt); + atomic64_add(req->nbytes, &crt->base->base.__crt_alg->encrypt_tlen); + } +#endif +} + +static inline void crypto_stat_ablkcipher_decrypt(struct ablkcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct ablkcipher_tfm *crt = + crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + } else { + atomic_inc(&crt->base->base.__crt_alg->decrypt_cnt); + atomic64_add(req->nbytes, &crt->base->base.__crt_alg->decrypt_tlen); + } +#endif +} + /** * crypto_ablkcipher_encrypt() - encrypt plaintext * @req: reference to the ablkcipher_request handle that holds all information @@ -922,7 +1020,11 @@ static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - return crt->encrypt(req); + int ret; + + ret = crt->encrypt(req); + crypto_stat_ablkcipher_encrypt(req, ret); + return ret; } /** @@ -940,7 +1042,11 @@ static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - return crt->decrypt(req); + int ret; + + ret = crt->decrypt(req); + crypto_stat_ablkcipher_decrypt(req, ret); + return ret; } /** -- cgit v1.2.3 From eb2bccb70b979d996ecb769d692b92ff12eabbb7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 19 Sep 2018 03:13:21 +0200 Subject: rtc: move rtc_add_group/s definitions Move rtc_add_group and rtc_add_groups definition to rtc.h that is available for all RTC drivers. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index faf00a1472d4..c8bb4a2b48c3 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -272,4 +272,20 @@ static inline int rtc_nvmem_register(struct rtc_device *rtc, static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {} #endif +#ifdef CONFIG_RTC_INTF_SYSFS +int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp); +int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps); +#else +static inline +int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp) +{ + return 0; +} + +static inline +int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps) +{ + return 0; +} +#endif #endif /* _LINUX_RTC_H_ */ -- cgit v1.2.3 From 421c119f558761556afca6a62ad183bc2d8659e0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 24 Sep 2018 14:10:04 +0200 Subject: netfilter: avoid erronous array bounds warning Unfortunately some versions of gcc emit following warning: $ make net/xfrm/xfrm_output.o linux/compiler.h:252:20: warning: array subscript is above array bounds [-Warray-bounds] hook_head = rcu_dereference(net->nf.hooks_arp[hook]); ^~~~~~~~~~~~~~~~~~~~~ xfrm_output_resume passes skb_dst(skb)->ops->family as its 'pf' arg so compiler can't know that we'll never access hooks_arp[]. (NFPROTO_IPV4 or NFPROTO_IPV6 are only possible cases). Avoid this by adding an explicit WARN_ON_ONCE() check. This patch has no effect if the family is a compile-time constant as gcc will remove the switch() construct entirely. Reported-by: David Ahern Signed-off-by: Florian Westphal Reviewed-by: David Ahern Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 07efffd0c759..bbe99d2b28b4 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -215,6 +215,8 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, break; case NFPROTO_ARP: #ifdef CONFIG_NETFILTER_FAMILY_ARP + if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp))) + break; hook_head = rcu_dereference(net->nf.hooks_arp[hook]); #endif break; -- cgit v1.2.3 From d7b9fd1669d4a4f38281c4e29f1408e1bdce09b3 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:03 -0700 Subject: nvmem: provide nvmem_dev_name() Kernel users don't have any means of checking the names of nvmem devices. Add a routine that returns the name of the nvmem provider. This will be useful for future nvmem notifier subscribers - otherwise they can't check what device is being added/removed. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 4e85447f7860..0389fe00b177 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -55,6 +55,8 @@ ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, int nvmem_device_cell_write(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf); +const char *nvmem_dev_name(struct nvmem_device *nvmem); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -143,6 +145,12 @@ static inline int nvmem_device_write(struct nvmem_device *nvmem, { return -ENOSYS; } + +static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From bf58e8820c48805394ec9e76339f0c4646050432 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:13 -0700 Subject: nvmem: change the signature of nvmem_unregister() We switched the nvmem framework to using kref instead of manually checking the current number of users in nvmem_unregister() so this function can no longer fail. We also converted all remaining users that still checked the return value of nvmem_unregister() to using devm_nvmem_register(). Make the routine return void. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 24def6ad09bb..0f357d0c1e75 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,7 @@ struct nvmem_config { #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); -int nvmem_unregister(struct nvmem_device *nvmem); +void nvmem_unregister(struct nvmem_device *nvmem); struct nvmem_device *devm_nvmem_register(struct device *dev, const struct nvmem_config *cfg); @@ -87,10 +87,7 @@ static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) return ERR_PTR(-ENOSYS); } -static inline int nvmem_unregister(struct nvmem_device *nvmem) -{ - return -ENOSYS; -} +static inline void nvmem_unregister(struct nvmem_device *nvmem) {} static inline struct nvmem_device * devm_nvmem_register(struct device *dev, const struct nvmem_config *c) @@ -101,7 +98,7 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) static inline int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) { - return nvmem_unregister(nvmem); + return -ENOSYS; } -- cgit v1.2.3 From b985f4cba6dbb3b60ad119c6f7e5cbad6f0d7e45 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:15 -0700 Subject: nvmem: add support for cell info Add new structs and routines allowing users to define nvmem cells from machine code. This global list of entries is parsed when a provider is registered and cells are associated with the relevant nvmem_device struct. A possible improvement for the future is to allow users to register cell tables after the nvmem provider has been registered by updating the cell list at each call to nvmem_(add|del)_cell_table(). Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0f357d0c1e75..5c9f205cac8f 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -67,6 +67,25 @@ struct nvmem_config { struct device *base_dev; }; +/** + * struct nvmem_cell_table - NVMEM cell definitions for given provider + * + * @nvmem_name: Provider name. + * @cells: Array of cell definitions. + * @ncells: Number of cell definitions in the array. + * @node: List node. + * + * This structure together with related helper functions is provided for users + * that don't can't access the nvmem provided structure but wish to register + * cell definitions for it e.g. board files registering an EEPROM device. + */ +struct nvmem_cell_table { + const char *nvmem_name; + const struct nvmem_cell_info *cells; + size_t ncells; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); @@ -77,9 +96,9 @@ struct nvmem_device *devm_nvmem_register(struct device *dev, int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem); -int nvmem_add_cells(struct nvmem_device *nvmem, - const struct nvmem_cell_info *info, - int ncells); +void nvmem_add_cell_table(struct nvmem_cell_table *table); +void nvmem_del_cell_table(struct nvmem_cell_table *table); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -102,12 +121,8 @@ devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) } -static inline int nvmem_add_cells(struct nvmem_device *nvmem, - const struct nvmem_cell_info *info, - int ncells) -{ - return -ENOSYS; -} +static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} +static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {} #endif /* CONFIG_NVMEM */ #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- cgit v1.2.3 From 506157be06ba28137b18b7419a4dccfa244f4983 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:17 -0700 Subject: nvmem: add support for cell lookups from machine code Add a way for machine code users to associate devices with nvmem cells. This restores the support for non-DT systems but following a different approach. Cells must now be associated with devices using provided routines and data structures before they can be retrieved using nvmem_cell_get(). It's still possible to define cells statically in nvmem_config but cells created this way still need to be associated with consumers using lookup entries. Note that nvmem_find() must be moved higher in the source file as we want to call it from __nvmem_device_get() for devices that don't have a device node. The signature of __nvmem_device_get() is also changed as it's no longer used to retrieve cells. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 0389fe00b177..27eee3945405 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -29,6 +29,24 @@ struct nvmem_cell_info { unsigned int nbits; }; +/** + * struct nvmem_cell_lookup - cell lookup entry + * + * @nvmem_name: Name of the provider. + * @cell_name: Name of the nvmem cell as defined in the name field of + * struct nvmem_cell_info. + * @dev_id: Name of the consumer device that will be associated with + * this cell. + * @con_id: Connector id for this cell lookup. + */ +struct nvmem_cell_lookup { + const char *nvmem_name; + const char *cell_name; + const char *dev_id; + const char *con_id; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ @@ -57,6 +75,11 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem, const char *nvmem_dev_name(struct nvmem_device *nvmem); +void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, + size_t nentries); +void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, + size_t nentries); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -151,6 +174,11 @@ static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) return NULL; } +static inline void +nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} +static inline void +nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From bee1138bea15a640aaa9e9bb909af5b2762520e0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:19 -0700 Subject: nvmem: add a notifier chain Add a blocking notifier chain with four events (add and remove for both devices and cells) so that users can get notified about the addition of nvmem resources they're waiting for. We'll use this instead of the at24 setup callback in the mityomapl138 board file. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 27eee3945405..0326b52e906b 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -14,6 +14,7 @@ #include #include +#include struct device; struct device_node; @@ -47,6 +48,13 @@ struct nvmem_cell_lookup { struct list_head node; }; +enum { + NVMEM_ADD = 1, + NVMEM_REMOVE, + NVMEM_CELL_ADD, + NVMEM_CELL_REMOVE, +}; + #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ @@ -80,6 +88,9 @@ void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries); +int nvmem_register_notifier(struct notifier_block *nb); +int nvmem_unregister_notifier(struct notifier_block *nb); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -179,6 +190,16 @@ nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} static inline void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} +static inline int nvmem_register_notifier(struct notifier_block *nb) +{ + return -ENOSYS; +} + +static inline int nvmem_unregister_notifier(struct notifier_block *nb) +{ + return -ENOSYS; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From b1c1db9883c276fe41a04e9ce8f89576a64b1ac0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:20 -0700 Subject: nvmem: use SPDX license identifiers Use SPDX license identiefiers to core nvmem files and remove GPL 2.0 license boilerplate. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 5 +---- include/linux/nvmem-provider.h | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 0326b52e906b..d18caae2f7ac 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * nvmem framework consumer. * * Copyright (C) 2015 Srinivas Kandagatla * Copyright (C) 2013 Maxime Ripard - * - * 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 kind, whether express or implied. */ #ifndef _LINUX_NVMEM_CONSUMER_H diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 5c9f205cac8f..8ae012f6545a 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * nvmem framework provider. * * Copyright (C) 2015 Srinivas Kandagatla * Copyright (C) 2013 Maxime Ripard - * - * 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 kind, whether express or implied. */ #ifndef _LINUX_NVMEM_PROVIDER_H -- cgit v1.2.3 From 165589f0cb52b34db12e15676a034b8f83dfa756 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:21 -0700 Subject: nvmem: make the naming of arguments in nvmem_cell_get() consistent The argument representing the cell name in the nvmem_cell_get() family of functions is not consistend between function prototypes and definitions. Name it 'id' in all those routines. This is in line with other frameworks and can represent both the DT cell name from the nvmem-cell-names property as well as the con_id field from cell lookup entries. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index d18caae2f7ac..e17617fa034f 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -55,8 +55,8 @@ enum { #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ -struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *name); -struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *name); +struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *id); +struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *id); 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); @@ -91,13 +91,13 @@ int nvmem_unregister_notifier(struct notifier_block *nb); #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } static inline struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } @@ -201,12 +201,12 @@ static inline int nvmem_unregister_notifier(struct notifier_block *nb) #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, - const char *name); + const char *id); struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name); #else static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } -- cgit v1.2.3 From 20167b70c894f20cd01e2579fad206de440816ef Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:22 -0700 Subject: nvmem: use EOPNOTSUPP instead of ENOSYS Checkpatch emits warnings when using ENOSYS. Some of the frameworks started using EOPNOTSUPP as return values for API functions when given subsystem is disabled in Kconfig. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 30 +++++++++++++++--------------- include/linux/nvmem-provider.h | 5 ++--- 2 files changed, 17 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index e17617fa034f..312bfa5efd80 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -93,13 +93,13 @@ int nvmem_unregister_notifier(struct notifier_block *nb); static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void devm_nvmem_cell_put(struct device *dev, @@ -113,31 +113,31 @@ static inline void nvmem_cell_put(struct nvmem_cell *cell) static inline void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline int nvmem_cell_write(struct nvmem_cell *cell, const char *buf, size_t len) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline struct nvmem_device *nvmem_device_get(struct device *dev, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void nvmem_device_put(struct nvmem_device *nvmem) @@ -153,28 +153,28 @@ static inline ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_cell_write(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_write(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) @@ -189,12 +189,12 @@ nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} static inline int nvmem_register_notifier(struct notifier_block *nb) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_unregister_notifier(struct notifier_block *nb) { - return -ENOSYS; + return -EOPNOTSUPP; } #endif /* CONFIG_NVMEM */ @@ -208,13 +208,13 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NVMEM && CONFIG_OF */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 8ae012f6545a..1e3283c2af77 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -100,7 +100,7 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table); static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void nvmem_unregister(struct nvmem_device *nvmem) {} @@ -114,8 +114,7 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) static inline int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) { - return -ENOSYS; - + return -EOPNOTSUPP; } static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} -- cgit v1.2.3 From 494edd266b945f36908184433dd36eda1719cdb0 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:27:46 +0300 Subject: regulator/mfd: Support ROHM BD71847 power management IC BD71847 is reduced version of BD71837. DVS bucks 3 and 4 are removed as is LDO7. Voltage ranges of some regulators are expanded. Add initial support for BD71847 with BD71837 driver. Signed-off-by: Matti Vaittinen Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 271 ++++++++++++++++++--------------------- 1 file changed, 124 insertions(+), 147 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index e8338e5dc10b..625e3607e069 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -7,106 +7,125 @@ #include enum { - BD71837_BUCK1 = 0, - BD71837_BUCK2, - BD71837_BUCK3, - BD71837_BUCK4, - BD71837_BUCK5, - BD71837_BUCK6, - BD71837_BUCK7, - BD71837_BUCK8, - BD71837_LDO1, - BD71837_LDO2, - BD71837_LDO3, - BD71837_LDO4, - BD71837_LDO5, - BD71837_LDO6, - BD71837_LDO7, - BD71837_REGULATOR_CNT, + BD718XX_TYPE_BD71837 = 0, + BD718XX_TYPE_BD71847, + BD718XX_TYPE_AMOUNT }; -#define BD71837_BUCK1_VOLTAGE_NUM 0x40 -#define BD71837_BUCK2_VOLTAGE_NUM 0x40 -#define BD71837_BUCK3_VOLTAGE_NUM 0x40 -#define BD71837_BUCK4_VOLTAGE_NUM 0x40 +enum { + BD718XX_BUCK1 = 0, + BD718XX_BUCK2, + BD718XX_BUCK3, + BD718XX_BUCK4, + BD718XX_BUCK5, + BD718XX_BUCK6, + BD718XX_BUCK7, + BD718XX_BUCK8, + BD718XX_LDO1, + BD718XX_LDO2, + BD718XX_LDO3, + BD718XX_LDO4, + BD718XX_LDO5, + BD718XX_LDO6, + BD718XX_LDO7, + BD718XX_REGULATOR_AMOUNT, +}; + +/* Common voltage configurations + * + * Note, we support only one range of voltages for each buck/LDO until we + * get pickable ranges support. (See range selection bits for BUCK5 and + * LDO1. On BD71847 also the second no DVS buck and LDO5) + */ + +#define BD718XX_DVS_BUCK_VOLTAGE_NUM 0x3D +#define BD718XX_1ST_NODVS_BUCK_VOLTAGE_NUM 0x08 +#define BD71837_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D + +#define BD718XX_LDO1_VOLTAGE_NUM 0x04 +#define BD718XX_LDO2_VOLTAGE_NUM 0x02 +#define BD718XX_LDO3_VOLTAGE_NUM 0x10 +#define BD718XX_LDO4_VOLTAGE_NUM 0x0A +#define BD718XX_LDO5_VOLTAGE_NUM 0x10 +#define BD718XX_LDO6_VOLTAGE_NUM 0x0A -#define BD71837_BUCK5_VOLTAGE_NUM 0x08 +/* BD71837 specific voltage configurations */ #define BD71837_BUCK6_VOLTAGE_NUM 0x04 #define BD71837_BUCK7_VOLTAGE_NUM 0x08 -#define BD71837_BUCK8_VOLTAGE_NUM 0x40 - -#define BD71837_LDO1_VOLTAGE_NUM 0x04 -#define BD71837_LDO2_VOLTAGE_NUM 0x02 -#define BD71837_LDO3_VOLTAGE_NUM 0x10 -#define BD71837_LDO4_VOLTAGE_NUM 0x10 -#define BD71837_LDO5_VOLTAGE_NUM 0x10 -#define BD71837_LDO6_VOLTAGE_NUM 0x10 #define BD71837_LDO7_VOLTAGE_NUM 0x10 +/* BD71847 specific voltage configurations */ +#define BD71847_BUCK4_VOLTAGE_NUM 0x04 + +/* Registers specific to BD71837 */ enum { - BD71837_REG_REV = 0x00, - BD71837_REG_SWRESET = 0x01, - BD71837_REG_I2C_DEV = 0x02, - BD71837_REG_PWRCTRL0 = 0x03, - BD71837_REG_PWRCTRL1 = 0x04, - BD71837_REG_BUCK1_CTRL = 0x05, - BD71837_REG_BUCK2_CTRL = 0x06, - BD71837_REG_BUCK3_CTRL = 0x07, - BD71837_REG_BUCK4_CTRL = 0x08, - BD71837_REG_BUCK5_CTRL = 0x09, - BD71837_REG_BUCK6_CTRL = 0x0A, - BD71837_REG_BUCK7_CTRL = 0x0B, - BD71837_REG_BUCK8_CTRL = 0x0C, - BD71837_REG_BUCK1_VOLT_RUN = 0x0D, - BD71837_REG_BUCK1_VOLT_IDLE = 0x0E, - BD71837_REG_BUCK1_VOLT_SUSP = 0x0F, - BD71837_REG_BUCK2_VOLT_RUN = 0x10, - BD71837_REG_BUCK2_VOLT_IDLE = 0x11, - BD71837_REG_BUCK3_VOLT_RUN = 0x12, - BD71837_REG_BUCK4_VOLT_RUN = 0x13, - BD71837_REG_BUCK5_VOLT = 0x14, - BD71837_REG_BUCK6_VOLT = 0x15, - BD71837_REG_BUCK7_VOLT = 0x16, - BD71837_REG_BUCK8_VOLT = 0x17, - BD71837_REG_LDO1_VOLT = 0x18, - BD71837_REG_LDO2_VOLT = 0x19, - BD71837_REG_LDO3_VOLT = 0x1A, - BD71837_REG_LDO4_VOLT = 0x1B, - BD71837_REG_LDO5_VOLT = 0x1C, - BD71837_REG_LDO6_VOLT = 0x1D, - BD71837_REG_LDO7_VOLT = 0x1E, - BD71837_REG_TRANS_COND0 = 0x1F, - BD71837_REG_TRANS_COND1 = 0x20, - BD71837_REG_VRFAULTEN = 0x21, - BD718XX_REG_MVRFLTMASK0 = 0x22, - BD718XX_REG_MVRFLTMASK1 = 0x23, - BD718XX_REG_MVRFLTMASK2 = 0x24, - BD71837_REG_RCVCFG = 0x25, - BD71837_REG_RCVNUM = 0x26, - BD71837_REG_PWRONCONFIG0 = 0x27, - BD71837_REG_PWRONCONFIG1 = 0x28, - BD71837_REG_RESETSRC = 0x29, - BD71837_REG_MIRQ = 0x2A, - BD71837_REG_IRQ = 0x2B, - BD71837_REG_IN_MON = 0x2C, - BD71837_REG_POW_STATE = 0x2D, - BD71837_REG_OUT32K = 0x2E, - BD71837_REG_REGLOCK = 0x2F, - BD71837_REG_OTPVER = 0xFF, - BD71837_MAX_REGISTER = 0x100, + BD71837_REG_BUCK3_CTRL = 0x07, + BD71837_REG_BUCK4_CTRL = 0x08, + BD71837_REG_BUCK3_VOLT_RUN = 0x12, + BD71837_REG_BUCK4_VOLT_RUN = 0x13, + BD71837_REG_LDO7_VOLT = 0x1E, +}; + +/* Registers common for BD71837 and BD71847 */ +enum { + BD718XX_REG_REV = 0x00, + BD718XX_REG_SWRESET = 0x01, + BD718XX_REG_I2C_DEV = 0x02, + BD718XX_REG_PWRCTRL0 = 0x03, + BD718XX_REG_PWRCTRL1 = 0x04, + BD718XX_REG_BUCK1_CTRL = 0x05, + BD718XX_REG_BUCK2_CTRL = 0x06, + BD718XX_REG_1ST_NODVS_BUCK_CTRL = 0x09, + BD718XX_REG_2ND_NODVS_BUCK_CTRL = 0x0A, + BD718XX_REG_3RD_NODVS_BUCK_CTRL = 0x0B, + BD718XX_REG_4TH_NODVS_BUCK_CTRL = 0x0C, + BD718XX_REG_BUCK1_VOLT_RUN = 0x0D, + BD718XX_REG_BUCK1_VOLT_IDLE = 0x0E, + BD718XX_REG_BUCK1_VOLT_SUSP = 0x0F, + BD718XX_REG_BUCK2_VOLT_RUN = 0x10, + BD718XX_REG_BUCK2_VOLT_IDLE = 0x11, + BD718XX_REG_1ST_NODVS_BUCK_VOLT = 0x14, + BD718XX_REG_2ND_NODVS_BUCK_VOLT = 0x15, + BD718XX_REG_3RD_NODVS_BUCK_VOLT = 0x16, + BD718XX_REG_4TH_NODVS_BUCK_VOLT = 0x17, + BD718XX_REG_LDO1_VOLT = 0x18, + BD718XX_REG_LDO2_VOLT = 0x19, + BD718XX_REG_LDO3_VOLT = 0x1A, + BD718XX_REG_LDO4_VOLT = 0x1B, + BD718XX_REG_LDO5_VOLT = 0x1C, + BD718XX_REG_LDO6_VOLT = 0x1D, + BD718XX_REG_TRANS_COND0 = 0x1F, + BD718XX_REG_TRANS_COND1 = 0x20, + BD718XX_REG_VRFAULTEN = 0x21, + BD718XX_REG_MVRFLTMASK0 = 0x22, + BD718XX_REG_MVRFLTMASK1 = 0x23, + BD718XX_REG_MVRFLTMASK2 = 0x24, + BD718XX_REG_RCVCFG = 0x25, + BD718XX_REG_RCVNUM = 0x26, + BD718XX_REG_PWRONCONFIG0 = 0x27, + BD718XX_REG_PWRONCONFIG1 = 0x28, + BD718XX_REG_RESETSRC = 0x29, + BD718XX_REG_MIRQ = 0x2A, + BD718XX_REG_IRQ = 0x2B, + BD718XX_REG_IN_MON = 0x2C, + BD718XX_REG_POW_STATE = 0x2D, + BD718XX_REG_OUT32K = 0x2E, + BD718XX_REG_REGLOCK = 0x2F, + BD718XX_REG_OTPVER = 0xFF, + BD718XX_MAX_REGISTER = 0x100, }; #define REGLOCK_PWRSEQ 0x1 #define REGLOCK_VREG 0x10 /* Generic BUCK control masks */ -#define BD71837_BUCK_SEL 0x02 -#define BD71837_BUCK_EN 0x01 -#define BD71837_BUCK_RUN_ON 0x04 +#define BD718XX_BUCK_SEL 0x02 +#define BD718XX_BUCK_EN 0x01 +#define BD718XX_BUCK_RUN_ON 0x04 /* Generic LDO masks */ -#define BD71837_LDO_SEL 0x80 -#define BD71837_LDO_EN 0x40 +#define BD718XX_LDO_SEL 0x80 +#define BD718XX_LDO_EN 0x40 /* BD71837 BUCK ramp rate CTRL reg bits */ #define BUCK_RAMPRATE_MASK 0xC0 @@ -115,49 +134,27 @@ enum { #define BUCK_RAMPRATE_2P50MV 0x2 #define BUCK_RAMPRATE_1P25MV 0x3 -/* BD71837_REG_BUCK1_VOLT_RUN bits */ -#define BUCK1_RUN_MASK 0x3F -#define BUCK1_RUN_DEFAULT 0x14 - -/* BD71837_REG_BUCK1_VOLT_SUSP bits */ -#define BUCK1_SUSP_MASK 0x3F -#define BUCK1_SUSP_DEFAULT 0x14 +#define DVS_BUCK_RUN_MASK 0x3F +#define DVS_BUCK_SUSP_MASK 0x3F +#define DVS_BUCK_IDLE_MASK 0x3F -/* BD71837_REG_BUCK1_VOLT_IDLE bits */ -#define BUCK1_IDLE_MASK 0x3F -#define BUCK1_IDLE_DEFAULT 0x14 +#define BD718XX_1ST_NODVS_BUCK_MASK 0x07 +#define BD71847_BUCK4_MASK 0x03 +#define BD71837_BUCK6_MASK 0x03 +#define BD718XX_3RD_NODVS_BUCK_MASK 0x07 +#define BD718XX_4TH_NODVS_BUCK_MASK 0x3F -/* BD71837_REG_BUCK2_VOLT_RUN bits */ -#define BUCK2_RUN_MASK 0x3F -#define BUCK2_RUN_DEFAULT 0x1E +#define BD718XX_LDO1_MASK 0x03 +#define BD718XX_LDO2_MASK 0x20 +#define BD718XX_LDO3_MASK 0x0F +#define BD718XX_LDO4_MASK 0x0F +#define BD718XX_LDO6_MASK 0x0F -/* BD71837_REG_BUCK2_VOLT_IDLE bits */ -#define BUCK2_IDLE_MASK 0x3F -#define BUCK2_IDLE_DEFAULT 0x14 +#define BD71837_LDO5_MASK 0x0F +#define BD71847_LDO5_MASK 0x0F -/* BD71837_REG_BUCK3_VOLT_RUN bits */ -#define BUCK3_RUN_MASK 0x3F -#define BUCK3_RUN_DEFAULT 0x1E +#define BD71837_LDO7_MASK 0x0F -/* BD71837_REG_BUCK4_VOLT_RUN bits */ -#define BUCK4_RUN_MASK 0x3F -#define BUCK4_RUN_DEFAULT 0x1E - -/* BD71837_REG_BUCK5_VOLT bits */ -#define BUCK5_MASK 0x07 -#define BUCK5_DEFAULT 0x02 - -/* BD71837_REG_BUCK6_VOLT bits */ -#define BUCK6_MASK 0x03 -#define BUCK6_DEFAULT 0x03 - -/* BD71837_REG_BUCK7_VOLT bits */ -#define BUCK7_MASK 0x07 -#define BUCK7_DEFAULT 0x03 - -/* BD71837_REG_BUCK8_VOLT bits */ -#define BUCK8_MASK 0x3F -#define BUCK8_DEFAULT 0x1E /* BD718XX Voltage monitoring masks */ #define BD718XX_BUCK1_VRMON80 0x1 @@ -221,27 +218,6 @@ enum { #define BD71837_INT_ON_REQ_MASK 0x2 #define BD71837_INT_STBY_REQ_MASK 0x1 -/* BD71837_REG_LDO1_VOLT bits */ -#define LDO1_MASK 0x03 - -/* BD71837_REG_LDO1_VOLT bits */ -#define LDO2_MASK 0x20 - -/* BD71837_REG_LDO3_VOLT bits */ -#define LDO3_MASK 0x0F - -/* BD71837_REG_LDO4_VOLT bits */ -#define LDO4_MASK 0x0F - -/* BD71837_REG_LDO5_VOLT bits */ -#define LDO5_MASK 0x0F - -/* BD71837_REG_LDO6_VOLT bits */ -#define LDO6_MASK 0x0F - -/* BD71837_REG_LDO7_VOLT bits */ -#define LDO7_MASK 0x0F - /* Register write induced reset settings */ /* @@ -341,10 +317,11 @@ enum { BD718XX_PWRBTN_LONG_PRESS_15S }; -struct bd71837_pmic; -struct bd71837_clk; +struct bd718xx_pmic; +struct bd718xx_clk; struct bd71837 { + unsigned int chip_type; struct device *dev; struct regmap *regmap; unsigned long int id; @@ -352,8 +329,8 @@ struct bd71837 { int chip_irq; struct regmap_irq_chip_data *irq_data; - struct bd71837_pmic *pmic; - struct bd71837_clk *clk; + struct bd718xx_pmic *pmic; + struct bd718xx_clk *clk; }; #endif /* __LINUX_MFD_BD71837_H__ */ -- cgit v1.2.3 From 18e4b55fbd2069cee51ef9660b35c65ec13bee6d Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:31:36 +0300 Subject: regulator: Support regulators where voltage ranges are selectable For example ROHM BD71837 and ROHM BD71847 Power management ICs have regulators which provide multiple linear ranges. Ranges can be selected by individual non contagious bit in vsel register. Add regmap helper functions for selecting ranges. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 0fd8fbb74763..a9c030192147 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -271,9 +271,16 @@ enum regulator_type { * @ramp_delay: Time to settle down after voltage change (unit: uV/us) * @min_dropout_uV: The minimum dropout voltage this regulator can handle * @linear_ranges: A constant table of possible voltage ranges. - * @n_linear_ranges: Number of entries in the @linear_ranges table. + * @linear_range_selectors: A constant table of voltage range selectors. + * If pickable ranges are used each range must + * have corresponding selector here. + * @n_linear_ranges: Number of entries in the @linear_ranges (and in + * linear_range_selectors if used) table(s). * @volt_table: Voltage mapping table (if table based mapping) * + * @vsel_range_reg: Register for range selector when using pickable ranges + * and regulator_regmap_X_voltage_X_pickable functions. + * @vsel_range_mask: Mask for register bitfield used for range selector * @vsel_reg: Register for selector when using regulator_regmap_X_voltage_ * @vsel_mask: Mask for register bitfield used for selector * @csel_reg: Register for TPS65218 LS3 current regulator @@ -338,10 +345,14 @@ struct regulator_desc { int min_dropout_uV; const struct regulator_linear_range *linear_ranges; + const unsigned int *linear_range_selectors; + int n_linear_ranges; const unsigned int *volt_table; + unsigned int vsel_range_reg; + unsigned int vsel_range_mask; unsigned int vsel_reg; unsigned int vsel_mask; unsigned int csel_reg; @@ -498,18 +509,25 @@ int regulator_mode_to_status(unsigned int); int regulator_list_voltage_linear(struct regulator_dev *rdev, unsigned int selector); +int regulator_list_voltage_pickable_linear_range(struct regulator_dev *rdev, + unsigned int selector); int regulator_list_voltage_linear_range(struct regulator_dev *rdev, unsigned int selector); int regulator_list_voltage_table(struct regulator_dev *rdev, unsigned int selector); int regulator_map_voltage_linear(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_map_voltage_pickable_linear_range(struct regulator_dev *rdev, + int min_uV, int max_uV); int regulator_map_voltage_linear_range(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_iterate(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_ascend(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_get_voltage_sel_pickable_regmap(struct regulator_dev *rdev); +int regulator_set_voltage_sel_pickable_regmap(struct regulator_dev *rdev, + unsigned int sel); int regulator_get_voltage_sel_regmap(struct regulator_dev *rdev); int regulator_set_voltage_sel_regmap(struct regulator_dev *rdev, unsigned sel); int regulator_is_enabled_regmap(struct regulator_dev *rdev); -- cgit v1.2.3 From dd2be639f4a918b335818bf22a937956e552b957 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:32:26 +0300 Subject: regulator/mfd: bd718xx: rename bd71837/bd71847 common instances Rename parts of code that support both BD71837 and BD71847 to BD718XX. Signed-off-by: Matti Vaittinen Acked-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 64 ++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index 625e3607e069..fed5fed75732 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Copyright (C) 2018 ROHM Semiconductors */ -#ifndef __LINUX_MFD_BD71837_H__ -#define __LINUX_MFD_BD71837_H__ +#ifndef __LINUX_MFD_BD718XX_H__ +#define __LINUX_MFD_BD718XX_H__ #include @@ -40,7 +40,7 @@ enum { #define BD718XX_DVS_BUCK_VOLTAGE_NUM 0x3D #define BD718XX_1ST_NODVS_BUCK_VOLTAGE_NUM 0x08 -#define BD71837_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D +#define BD718XX_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D #define BD718XX_LDO1_VOLTAGE_NUM 0x04 #define BD718XX_LDO2_VOLTAGE_NUM 0x02 @@ -183,7 +183,7 @@ enum { #define BD71837_BUCK4_VRMON130 0x80 #define BD71837_LDO7_VRMON80 0x40 -/* BD71837_REG_IRQ bits */ +/* BD718XX_REG_IRQ bits */ #define IRQ_SWRST 0x40 #define IRQ_PWRON_S 0x20 #define IRQ_PWRON_L 0x10 @@ -192,31 +192,31 @@ enum { #define IRQ_ON_REQ 0x02 #define IRQ_STBY_REQ 0x01 -/* BD71837_REG_OUT32K bits */ -#define BD71837_OUT32K_EN 0x01 +/* BD718XX_REG_OUT32K bits */ +#define BD718XX_OUT32K_EN 0x01 -/* BD71837 gated clock rate */ -#define BD71837_CLK_RATE 32768 +/* BD7183XX gated clock rate */ +#define BD718XX_CLK_RATE 32768 -/* ROHM BD71837 irqs */ +/* ROHM BD718XX irqs */ enum { - BD71837_INT_STBY_REQ, - BD71837_INT_ON_REQ, - BD71837_INT_WDOG, - BD71837_INT_PWRBTN, - BD71837_INT_PWRBTN_L, - BD71837_INT_PWRBTN_S, - BD71837_INT_SWRST + BD718XX_INT_STBY_REQ, + BD718XX_INT_ON_REQ, + BD718XX_INT_WDOG, + BD718XX_INT_PWRBTN, + BD718XX_INT_PWRBTN_L, + BD718XX_INT_PWRBTN_S, + BD718XX_INT_SWRST }; -/* ROHM BD71837 interrupt masks */ -#define BD71837_INT_SWRST_MASK 0x40 -#define BD71837_INT_PWRBTN_S_MASK 0x20 -#define BD71837_INT_PWRBTN_L_MASK 0x10 -#define BD71837_INT_PWRBTN_MASK 0x8 -#define BD71837_INT_WDOG_MASK 0x4 -#define BD71837_INT_ON_REQ_MASK 0x2 -#define BD71837_INT_STBY_REQ_MASK 0x1 +/* ROHM BD718XX interrupt masks */ +#define BD718XX_INT_SWRST_MASK 0x40 +#define BD718XX_INT_PWRBTN_S_MASK 0x20 +#define BD718XX_INT_PWRBTN_L_MASK 0x10 +#define BD718XX_INT_PWRBTN_MASK 0x8 +#define BD718XX_INT_WDOG_MASK 0x4 +#define BD718XX_INT_ON_REQ_MASK 0x2 +#define BD718XX_INT_STBY_REQ_MASK 0x1 /* Register write induced reset settings */ @@ -226,13 +226,13 @@ enum { * write 1 to it we will trigger the action. So always write 0 to it when * changning SWRESET action - no matter what we read from it. */ -#define BD71837_SWRESET_TYPE_MASK 7 -#define BD71837_SWRESET_TYPE_DISABLED 0 -#define BD71837_SWRESET_TYPE_COLD 4 -#define BD71837_SWRESET_TYPE_WARM 6 +#define BD718XX_SWRESET_TYPE_MASK 7 +#define BD718XX_SWRESET_TYPE_DISABLED 0 +#define BD718XX_SWRESET_TYPE_COLD 4 +#define BD718XX_SWRESET_TYPE_WARM 6 -#define BD71837_SWRESET_RESET_MASK 1 -#define BD71837_SWRESET_RESET 1 +#define BD718XX_SWRESET_RESET_MASK 1 +#define BD718XX_SWRESET_RESET 1 /* Poweroff state transition conditions */ @@ -320,7 +320,7 @@ enum { struct bd718xx_pmic; struct bd718xx_clk; -struct bd71837 { +struct bd718xx { unsigned int chip_type; struct device *dev; struct regmap *regmap; @@ -333,4 +333,4 @@ struct bd71837 { struct bd718xx_clk *clk; }; -#endif /* __LINUX_MFD_BD71837_H__ */ +#endif /* __LINUX_MFD_BD718XX_H__ */ -- cgit v1.2.3 From a4bfc2c28a21f4d5274d813b20fd015a9dc9bcfa Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 14 Sep 2018 11:33:11 +0300 Subject: regulator: bd718XX use pickable ranges Few regulators in BD71837 and BD71847 can output voltages from different voltage ranges. Register interface is arranged so that used range is selected by toggling bits which are not next to actual voltage selection bits. Then the voltage inside selected range is determined by voltage selection bits (as usual). Support BD71837 and BD71847 selectible range voltages using new pickable ranges helpers. Signed-off-by: Matti Vaittinen Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index fed5fed75732..26acf9a92498 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -31,31 +31,27 @@ enum { BD718XX_REGULATOR_AMOUNT, }; -/* Common voltage configurations - * - * Note, we support only one range of voltages for each buck/LDO until we - * get pickable ranges support. (See range selection bits for BUCK5 and - * LDO1. On BD71847 also the second no DVS buck and LDO5) - */ - +/* Common voltage configurations */ #define BD718XX_DVS_BUCK_VOLTAGE_NUM 0x3D -#define BD718XX_1ST_NODVS_BUCK_VOLTAGE_NUM 0x08 #define BD718XX_4TH_NODVS_BUCK_VOLTAGE_NUM 0x3D -#define BD718XX_LDO1_VOLTAGE_NUM 0x04 +#define BD718XX_LDO1_VOLTAGE_NUM 0x08 #define BD718XX_LDO2_VOLTAGE_NUM 0x02 #define BD718XX_LDO3_VOLTAGE_NUM 0x10 #define BD718XX_LDO4_VOLTAGE_NUM 0x0A -#define BD718XX_LDO5_VOLTAGE_NUM 0x10 #define BD718XX_LDO6_VOLTAGE_NUM 0x0A /* BD71837 specific voltage configurations */ +#define BD71837_BUCK5_VOLTAGE_NUM 0x10 #define BD71837_BUCK6_VOLTAGE_NUM 0x04 #define BD71837_BUCK7_VOLTAGE_NUM 0x08 +#define BD71837_LDO5_VOLTAGE_NUM 0x10 #define BD71837_LDO7_VOLTAGE_NUM 0x10 /* BD71847 specific voltage configurations */ -#define BD71847_BUCK4_VOLTAGE_NUM 0x04 +#define BD71847_BUCK3_VOLTAGE_NUM 0x18 +#define BD71847_BUCK4_VOLTAGE_NUM 0x08 +#define BD71847_LDO5_VOLTAGE_NUM 0x20 /* Registers specific to BD71837 */ enum { @@ -139,12 +135,20 @@ enum { #define DVS_BUCK_IDLE_MASK 0x3F #define BD718XX_1ST_NODVS_BUCK_MASK 0x07 -#define BD71847_BUCK4_MASK 0x03 -#define BD71837_BUCK6_MASK 0x03 #define BD718XX_3RD_NODVS_BUCK_MASK 0x07 #define BD718XX_4TH_NODVS_BUCK_MASK 0x3F +#define BD71847_BUCK3_MASK 0x07 +#define BD71847_BUCK3_RANGE_MASK 0xC0 +#define BD71847_BUCK4_MASK 0x03 +#define BD71847_BUCK4_RANGE_MASK 0x40 + +#define BD71837_BUCK5_MASK 0x07 +#define BD71837_BUCK5_RANGE_MASK 0x80 +#define BD71837_BUCK6_MASK 0x03 + #define BD718XX_LDO1_MASK 0x03 +#define BD718XX_LDO1_RANGE_MASK 0x20 #define BD718XX_LDO2_MASK 0x20 #define BD718XX_LDO3_MASK 0x0F #define BD718XX_LDO4_MASK 0x0F @@ -152,10 +156,10 @@ enum { #define BD71837_LDO5_MASK 0x0F #define BD71847_LDO5_MASK 0x0F +#define BD71847_LDO5_RANGE_MASK 0x20 #define BD71837_LDO7_MASK 0x0F - /* BD718XX Voltage monitoring masks */ #define BD718XX_BUCK1_VRMON80 0x1 #define BD718XX_BUCK1_VRMON130 0x2 -- cgit v1.2.3 From fef912bf860e8e7e48a2bfb978a356bba743a8b7 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 28 Sep 2018 08:17:19 +0200 Subject: block: genhd: add 'groups' argument to device_add_disk Update device_add_disk() to take an 'groups' argument so that individual drivers can register a device with additional sysfs attributes. This avoids race condition the driver would otherwise have if these groups were to be created with sysfs_add_groups(). Signed-off-by: Martin Wilck Signed-off-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/genhd.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 57864422a2c8..0b820ff05839 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -399,10 +399,11 @@ static inline void free_part_info(struct hd_struct *part) extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part); /* block/genhd.c */ -extern void device_add_disk(struct device *parent, struct gendisk *disk); +extern void device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); static inline void add_disk(struct gendisk *disk) { - device_add_disk(NULL, disk); + device_add_disk(NULL, disk, NULL); } extern void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk); static inline void add_disk_no_queue_reg(struct gendisk *disk) -- cgit v1.2.3 From d6112f8def514e019658bcc9b57d53acdb71ca3f Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Fri, 7 Sep 2018 09:16:51 +0300 Subject: PCI: Add support for Immediate Readiness MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe r4.0, sec 7.5.1.1.4 defines a new bit in the Status Register: Immediate Readiness – This optional bit, when Set, indicates the Function is guaranteed to be ready to successfully complete valid configuration accesses at any time following any reset that the host is capable of issuing Configuration Requests to this Function. When this bit is Set, for accesses to this Function, software is exempt from all requirements to delay configuration accesses following any type of reset, including but not limited to the timing requirements defined in Section 6.6. This means that all delays after a Conventional or Function Reset can be skipped. This patch reads such bit and caches its value in a flag inside struct pci_dev to be checked later if we should delay or can skip delays after a reset. While at that, also move the explicit msleep(100) call from pcie_flr() and pci_af_flr() to pci_dev_wait(). Signed-off-by: Felipe Balbi [bhelgaas: rename PCI_STATUS_IMMEDIATE to PCI_STATUS_IMM_READY] 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 6925828f9f25..60da5d7d4310 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -325,6 +325,7 @@ struct pci_dev { pci_power_t current_state; /* Current operating state. In ACPI, this is D0-D3, D0 being fully functional, and D3 being off. */ + unsigned int imm_ready:1; /* Supports Immediate Readiness */ u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ -- cgit v1.2.3 From f1f207e43b8a49ac2ee3c36a64de1f84651c6079 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 22 Aug 2018 15:04:40 -0500 Subject: of: Add cpu node iterator for_each_of_cpu_node() Iterating thru cpu nodes is a common pattern. Create a common iterator which can find child nodes either by node name or device_type == cpu. Using the former will allow for eventually dropping device_type properties which are deprecated for FDT. Cc: Frank Rowand Reviewed-by: Geert Uytterhoeven Signed-off-by: Rob Herring --- include/linux/of.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..1aca0dbd35df 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -353,6 +353,8 @@ extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +extern struct device_node *of_get_next_cpu_node(struct device_node *prev); + #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) @@ -754,6 +756,11 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline struct device_node *of_get_next_cpu_node(struct device_node *prev) +{ + return NULL; +} + static inline int of_n_addr_cells(struct device_node *np) { return 0; @@ -1217,6 +1224,10 @@ static inline int of_property_read_s32(const struct device_node *np, for (child = of_get_next_available_child(parent, NULL); child != NULL; \ child = of_get_next_available_child(parent, child)) +#define for_each_of_cpu_node(cpu) \ + for (cpu = of_get_next_cpu_node(NULL); cpu != NULL; \ + cpu = of_get_next_cpu_node(cpu)) + #define for_each_node_with_property(dn, prop_name) \ for (dn = of_find_node_with_property(NULL, prop_name); dn; \ dn = of_find_node_with_property(dn, prop_name)) -- cgit v1.2.3 From 9e288cefcc551c7b5b04f8abc7099d3451a70f5f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 25 Sep 2018 09:34:05 +0200 Subject: clk: renesas: Convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto [rebased against clk-spdx] Signed-off-by: Geert Uytterhoeven Reviewed-by: Simon Horman Signed-off-by: Stephen Boyd --- include/linux/clk/renesas.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h index 9ebf1f8243bb..0ebbe2f0b45e 100644 --- a/include/linux/clk/renesas.h +++ b/include/linux/clk/renesas.h @@ -1,14 +1,10 @@ -/* +/* SPDX-License-Identifier: GPL-2.0+ + * * Copyright 2013 Ideas On Board SPRL * Copyright 2013, 2014 Horms Solutions Ltd. * * Contact: Laurent Pinchart * Contact: Simon Horman - * - * 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 - * (at your option) any later version. */ #ifndef __LINUX_CLK_RENESAS_H_ -- cgit v1.2.3 From 3d0186bb068e6cc6c23dc1d2f0b1cf64894c40ea Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 16 Jun 2018 17:32:07 -0400 Subject: Update email address Redirect some older email addresses that are in the git logs. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2dfc8006fe64..9e4c86853fa4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -4,7 +4,7 @@ /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation - * Author: Matthew Wilcox + * Author: Matthew Wilcox */ #include -- cgit v1.2.3 From 3159f943aafdbacb2f94c38fdaadabf2bbde2a14 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 3 Nov 2017 13:30:42 -0400 Subject: xarray: Replace exceptional entries Introduce xarray value entries and tagged pointers to replace radix tree exceptional entries. This is a slight change in encoding to allow the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a value entry). It is also a change in emphasis; exceptional entries are intimidating and different. As the comment explains, you can choose to store values or pointers in the xarray and they are both first-class citizens. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 36 ++++------------ include/linux/swapops.h | 19 ++++----- include/linux/xarray.h | 102 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 117 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 34149e8b5f73..e9e76ab4fbbf 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -28,34 +28,26 @@ #include #include #include +#include /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer - * 01 - internal entry - * 10 - exceptional entry - * 11 - this bit combination is currently unused/reserved + * 10 - internal entry + * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). - * This means that you cannot store NULL in the tree as a value for the index. + * This means that storing a NULL entry in the tree is the same as deleting + * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL -#define RADIX_TREE_INTERNAL_NODE 1UL - -/* - * Most users of the radix tree store pointers but shmem/tmpfs stores swap - * entries in the same tree. They are marked as exceptional entries to - * distinguish them from pointers to struct page. - * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it. - */ -#define RADIX_TREE_EXCEPTIONAL_ENTRY 2 -#define RADIX_TREE_EXCEPTIONAL_SHIFT 2 +#define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { @@ -83,11 +75,10 @@ static inline bool radix_tree_is_internal_node(void *ptr) /* * @count is the count of every non-NULL element in the ->slots array - * whether that is an exceptional entry, a retry entry, a user pointer, + * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @exceptional is the count of every element in ->slots which is - * either radix_tree_exceptional_entry() or is a sibling entry for an - * exceptional entry. + * either a value entry or a sibling of a value entry. */ struct radix_tree_node { unsigned char shift; /* Bits remaining in each slot */ @@ -268,17 +259,6 @@ static inline int radix_tree_deref_retry(void *arg) return unlikely(radix_tree_is_internal_node(arg)); } -/** - * radix_tree_exceptional_entry - radix_tree_deref_slot gave exceptional entry? - * @arg: value returned by radix_tree_deref_slot - * Returns: 0 if well-aligned pointer, non-0 if exceptional entry. - */ -static inline int radix_tree_exceptional_entry(void *arg) -{ - /* Not unlikely because radix_tree_exception often tested first */ - return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY; -} - /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 22af9d8a84ae..4d961668e5fc 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -18,9 +18,8 @@ * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ -#define SWP_TYPE_SHIFT(e) ((sizeof(e.val) * 8) - \ - (MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT)) -#define SWP_OFFSET_MASK(e) ((1UL << SWP_TYPE_SHIFT(e)) - 1) +#define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) +#define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Store a type+offset into a swp_entry_t in an arch-independent format @@ -29,8 +28,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; - ret.val = (type << SWP_TYPE_SHIFT(ret)) | - (offset & SWP_OFFSET_MASK(ret)); + ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } @@ -40,7 +38,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) */ static inline unsigned swp_type(swp_entry_t entry) { - return (entry.val >> SWP_TYPE_SHIFT(entry)); + return (entry.val >> SWP_TYPE_SHIFT); } /* @@ -49,7 +47,7 @@ static inline unsigned swp_type(swp_entry_t entry) */ static inline pgoff_t swp_offset(swp_entry_t entry) { - return entry.val & SWP_OFFSET_MASK(entry); + return entry.val & SWP_OFFSET_MASK; } #ifdef CONFIG_MMU @@ -90,16 +88,13 @@ static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; - entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { - unsigned long value; - - value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT; - return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); + return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9e4c86853fa4..5c8acfc4ff55 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -5,9 +5,111 @@ * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox + * + * See Documentation/core-api/xarray.rst for how to use the XArray. */ +#include #include +#include + +/* + * The bottom two bits of the entry determine how the XArray interprets + * the contents: + * + * 00: Pointer entry + * 10: Internal entry + * x1: Value entry or tagged pointer + * + * Attempting to store internal entries in the XArray is a bug. + */ + +#define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) + +/** + * xa_mk_value() - Create an XArray entry from an integer. + * @v: Value to store in XArray. + * + * Context: Any context. + * Return: An entry suitable for storing in the XArray. + */ +static inline void *xa_mk_value(unsigned long v) +{ + WARN_ON((long)v < 0); + return (void *)((v << 1) | 1); +} + +/** + * xa_to_value() - Get value stored in an XArray entry. + * @entry: XArray entry. + * + * Context: Any context. + * Return: The value stored in the XArray entry. + */ +static inline unsigned long xa_to_value(const void *entry) +{ + return (unsigned long)entry >> 1; +} + +/** + * xa_is_value() - Determine if an entry is a value. + * @entry: XArray entry. + * + * Context: Any context. + * Return: True if the entry is a value, false if it is a pointer. + */ +static inline bool xa_is_value(const void *entry) +{ + return (unsigned long)entry & 1; +} + +/** + * xa_tag_pointer() - Create an XArray entry for a tagged pointer. + * @p: Plain pointer. + * @tag: Tag value (0, 1 or 3). + * + * If the user of the XArray prefers, they can tag their pointers instead + * of storing value entries. Three tags are available (0, 1 and 3). + * These are distinct from the xa_mark_t as they are not replicated up + * through the array and cannot be searched for. + * + * Context: Any context. + * Return: An XArray entry. + */ +static inline void *xa_tag_pointer(void *p, unsigned long tag) +{ + return (void *)((unsigned long)p | tag); +} + +/** + * xa_untag_pointer() - Turn an XArray entry into a plain pointer. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the untagged version of the pointer. + * + * Context: Any context. + * Return: A pointer. + */ +static inline void *xa_untag_pointer(void *entry) +{ + return (void *)((unsigned long)entry & ~3UL); +} + +/** + * xa_pointer_tag() - Get the tag stored in an XArray entry. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the tag of that pointer. + * + * Context: Any context. + * Return: A tag. + */ +static inline unsigned int xa_pointer_tag(void *entry) +{ + return (unsigned long)entry & 3UL; +} #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) -- cgit v1.2.3 From 02c02bf12c5d838603eed44195d3e91f094e2ab2 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 3 Nov 2017 23:09:45 -0400 Subject: xarray: Change definition of sibling entries Instead of storing a pointer to the slot containing the canonical entry, store the offset of the slot. Produces slightly more efficient code (~300 bytes) and simplifies the implementation. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 5 +-- include/linux/xarray.h | 92 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 93 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index e9e76ab4fbbf..60f3d8eb2cb7 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -59,10 +59,7 @@ static inline bool radix_tree_is_internal_node(void *ptr) #define RADIX_TREE_MAX_TAGS 3 -#ifndef RADIX_TREE_MAP_SHIFT -#define RADIX_TREE_MAP_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) -#endif - +#define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5c8acfc4ff55..4d1cd7a083e8 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -22,6 +22,12 @@ * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. + * + * Most internal entries are pointers to the next node in the tree. + * The following internal entries have a special meaning: + * + * 0-62: Sibling entries + * 256: Retry entry */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) @@ -111,6 +117,42 @@ static inline unsigned int xa_pointer_tag(void *entry) return (unsigned long)entry & 3UL; } +/* + * xa_mk_internal() - Create an internal entry. + * @v: Value to turn into an internal entry. + * + * Context: Any context. + * Return: An XArray internal entry corresponding to this value. + */ +static inline void *xa_mk_internal(unsigned long v) +{ + return (void *)((v << 2) | 2); +} + +/* + * xa_to_internal() - Extract the value from an internal entry. + * @entry: XArray entry. + * + * Context: Any context. + * Return: The value which was stored in the internal entry. + */ +static inline unsigned long xa_to_internal(const void *entry) +{ + return (unsigned long)entry >> 2; +} + +/* + * xa_is_internal() - Is the entry an internal entry? + * @entry: XArray entry. + * + * Context: Any context. + * Return: %true if the entry is an internal entry. + */ +static inline bool xa_is_internal(const void *entry) +{ + return ((unsigned long)entry & 3) == 2; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -123,4 +165,54 @@ static inline unsigned int xa_pointer_tag(void *entry) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +/* Everything below here is the Advanced API. Proceed with caution. */ + +/* + * The xarray is constructed out of a set of 'chunks' of pointers. Choosing + * the best chunk size requires some tradeoffs. A power of two recommends + * itself so that we can walk the tree based purely on shifts and masks. + * Generally, the larger the better; as the number of slots per level of the + * tree increases, the less tall the tree needs to be. But that needs to be + * balanced against the memory consumption of each node. On a 64-bit system, + * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we + * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. + */ +#ifndef XA_CHUNK_SHIFT +#define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) +#endif +#define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) +#define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) + +/* Private */ +static inline bool xa_is_node(const void *entry) +{ + return xa_is_internal(entry) && (unsigned long)entry > 4096; +} + +/* Private */ +static inline void *xa_mk_sibling(unsigned int offset) +{ + return xa_mk_internal(offset); +} + +/* Private */ +static inline unsigned long xa_to_sibling(const void *entry) +{ + return xa_to_internal(entry); +} + +/** + * xa_is_sibling() - Is the entry a sibling entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a sibling entry. + */ +static inline bool xa_is_sibling(const void *entry) +{ + return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && + (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); +} + +#define XA_RETRY_ENTRY xa_mk_internal(256) + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 492ecf6d6598e7c3b0b1372653ed21da50ddfb09 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Wed, 12 Sep 2018 09:43:25 -0500 Subject: docs: fpga: document fpga manager flags Add flags #defines to kerneldoc documentation in a useful place. Signed-off-by: Alan Tull Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 8942e61f0028..8ab5df769923 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -53,12 +53,20 @@ enum fpga_mgr_states { FPGA_MGR_STATE_OPERATING, }; -/* - * FPGA Manager flags - * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported - * FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting - * FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first - * FPGA_MGR_COMPRESSED_BITSTREAM: FPGA bitstream is compressed +/** + * DOC: FPGA Manager flags + * + * Flags used in the &fpga_image_info->flags field + * + * %FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported + * + * %FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting + * + * %FPGA_MGR_ENCRYPTED_BITSTREAM: indicates bitstream is encrypted + * + * %FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first + * + * %FPGA_MGR_COMPRESSED_BITSTREAM: FPGA bitstream is compressed */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) #define FPGA_MGR_EXTERNAL_CONFIG BIT(1) -- cgit v1.2.3 From 29efbc6aea9d9bd9aa9870a9afc1882046303cf9 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:07:27 +0200 Subject: Compiler Attributes: remove unused attributes __optimize and __deprecate_for_modules are unused in the whole kernel tree. Simply drop them. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 2 -- include/linux/compiler.h | 4 ---- include/linux/compiler_types.h | 1 - 3 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 4d36b27214fd..1302b425e625 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -81,8 +81,6 @@ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#define __optimize(level) __attribute__((__optimize__(level))) - #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #ifndef __CHECKER__ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..7c0157d50964 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -301,10 +301,6 @@ static inline void *offset_to_ptr(const int *off) #endif /* __ASSEMBLY__ */ -#ifndef __optimize -# define __optimize(level) -#endif - /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index db192becfec4..a19562cb047c 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -108,7 +108,6 @@ struct ftrace_likely_data { /* Don't. Just don't. */ #define __deprecated -#define __deprecated_for_modules #endif /* __KERNEL__ */ -- cgit v1.2.3 From 5c67a52f3da0f0d22764f2daec417702695a8112 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:13:37 +0200 Subject: Compiler Attributes: always use the extra-underscores syntax The attribute syntax optionally allows to surround attribute names with "__" in order to avoid collisions with macros of the same name (see https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html). This homogenizes all attributes to use the syntax with underscores. While there are currently only a handful of cases of some TUs defining macros like "error" which may collide with the attributes, this should prevent futures surprises. This has been done only for "standard" attributes supported by the major compilers. In other words, those of third-party tools (e.g. sparse, plugins...) have not been changed for the moment. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 2 +- include/linux/compiler-gcc.h | 12 ++++++------ include/linux/compiler-intel.h | 2 +- include/linux/compiler.h | 8 ++++---- include/linux/compiler_types.h | 42 +++++++++++++++++++++--------------------- 5 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index b1ce500fe8b3..d11cad61ba5c 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -21,7 +21,7 @@ #define __SANITIZE_ADDRESS__ #endif -#define __no_sanitize_address __attribute__((no_sanitize("address"))) +#define __no_sanitize_address __attribute__((__no_sanitize__("address"))) /* * Not all versions of clang implement the the type-generic versions diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1302b425e625..7a1de7683df5 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -76,7 +76,7 @@ #endif #ifdef RETPOLINE -#define __noretpoline __attribute__((indirect_branch("keep"))) +#define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) @@ -84,8 +84,8 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #ifndef __CHECKER__ -#define __compiletime_warning(message) __attribute__((warning(message))) -#define __compiletime_error(message) __attribute__((error(message))) +#define __compiletime_warning(message) __attribute__((__warning__(message))) +#define __compiletime_error(message) __attribute__((__error__(message))) #ifdef LATENT_ENTROPY_PLUGIN #define __latent_entropy __attribute__((latent_entropy)) @@ -134,7 +134,7 @@ * optimizer that something else uses this function or variable, thus preventing * this. */ -#define __visible __attribute__((externally_visible)) +#define __visible __attribute__((__externally_visible__)) /* gcc version specific checks */ @@ -191,7 +191,7 @@ * should not be applied to that function. * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 */ -#define __no_sanitize_address __attribute__((no_sanitize_address)) +#define __no_sanitize_address __attribute__((__no_sanitize_address__)) #endif #if GCC_VERSION >= 50100 @@ -199,7 +199,7 @@ * Mark structures as requiring designated initializers. * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html */ -#define __designated_init __attribute__((designated_init)) +#define __designated_init __attribute__((__designated_init__)) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 4c7f9befa9f6..fef8bb3e53ef 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -42,4 +42,4 @@ * and may be redefined here because they should not be shared with other * compilers, like clang. */ -#define __visible __attribute__((externally_visible)) +#define __visible __attribute__((__externally_visible__)) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 7c0157d50964..ec4a28bad2c6 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -24,7 +24,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, long ______r; \ static struct ftrace_likely_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_annotated_branch"))) \ + __attribute__((__section__("_ftrace_annotated_branch"))) \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -60,7 +60,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, int ______r; \ static struct ftrace_branch_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_branch"))) \ + __attribute__((__section__("_ftrace_branch"))) \ ______f = { \ .func = __func__, \ .file = __FILE__, \ @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((section("___kentry" "+" #sym ), used)) \ + __attribute__((__section__("___kentry" "+" #sym ), used)) \ = (unsigned long)&sym; #endif @@ -287,7 +287,7 @@ unsigned long read_word_at_a_time(const void *addr) * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __attribute__((section(".discard.addressable"), used)) \ + static void * __attribute__((__section__(".discard.addressable"), used)) \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a19562cb047c..8fbdd47dd3d0 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -195,26 +195,26 @@ struct ftrace_likely_data { * would be. * [...] */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __aligned_largest __attribute__((aligned)) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) -#define __mode(x) __attribute__((mode(x))) +#define __pure __attribute__((__pure__)) +#define __aligned(x) __attribute__((__aligned__(x))) +#define __aligned_largest __attribute__((__aligned__)) +#define __printf(a, b) __attribute__((__format__(printf, a, b))) +#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) +#define __maybe_unused __attribute__((__unused__)) +#define __always_unused __attribute__((__unused__)) +#define __mode(x) __attribute__((__mode__(x))) #define __malloc __attribute__((__malloc__)) #define __used __attribute__((__used__)) -#define __noreturn __attribute__((noreturn)) -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) -#define __cold __attribute__((cold)) +#define __noreturn __attribute__((__noreturn__)) +#define __packed __attribute__((__packed__)) +#define __weak __attribute__((__weak__)) +#define __alias(symbol) __attribute__((__alias__(#symbol))) +#define __cold __attribute__((__cold__)) #define __section(S) __attribute__((__section__(#S))) #ifdef CONFIG_ENABLE_MUST_CHECK -#define __must_check __attribute__((warn_unused_result)) +#define __must_check __attribute__((__warn_unused_result__)) #else #define __must_check #endif @@ -222,7 +222,7 @@ struct ftrace_likely_data { #if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) #define notrace __attribute__((hotpatch(0, 0))) #else -#define notrace __attribute__((no_instrument_function)) +#define notrace __attribute__((__no_instrument_function__)) #endif /* @@ -231,7 +231,7 @@ struct ftrace_likely_data { * stack and frame pointer being set up and there is no chance to * restore the lr register to the value before mcount was called. */ -#define __naked __attribute__((naked)) notrace +#define __naked __attribute__((__naked__)) notrace #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) @@ -242,7 +242,7 @@ struct ftrace_likely_data { * defined so the gnu89 semantics are the default. */ #ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((gnu_inline)) +# define __gnu_inline __attribute__((__gnu_inline__)) #else # define __gnu_inline #endif @@ -262,17 +262,17 @@ struct ftrace_likely_data { #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) #define inline \ - inline __attribute__((always_inline, unused)) notrace __gnu_inline + inline __attribute__((__always_inline__, __unused__)) notrace __gnu_inline #else -#define inline inline __attribute__((unused)) notrace __gnu_inline +#define inline inline __attribute__((__unused__)) notrace __gnu_inline #endif #define __inline__ inline #define __inline inline -#define noinline __attribute__((noinline)) +#define noinline __attribute__((__noinline__)) #ifndef __always_inline -#define __always_inline inline __attribute__((always_inline)) +#define __always_inline inline __attribute__((__always_inline__)) #endif /* -- cgit v1.2.3 From c2c640aa04cc4e6caf0ff17ff18b3784e0c99566 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:45:01 +0200 Subject: Compiler Attributes: remove unneeded tests Attributes const and always_inline have tests around them which are unneeded, since they are supported by gcc >= 4.6, clang >= 3 and icc >= 13. https://godbolt.org/z/DFPq37 In the case of gnu_inline, we do not need to test for __GNUC_STDC_INLINE__ because, regardless of the current inlining behavior, we can simply always force the old GCC inlining behavior by using the attribute in all cases. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 8fbdd47dd3d0..5ff9cda893f4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -158,10 +158,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#ifndef __attribute_const__ -#define __attribute_const__ __attribute__((__const__)) -#endif - #ifndef __noclone #define __noclone #endif @@ -196,6 +192,7 @@ struct ftrace_likely_data { * [...] */ #define __pure __attribute__((__pure__)) +#define __attribute_const__ __attribute__((__const__)) #define __aligned(x) __attribute__((__aligned__(x))) #define __aligned_largest __attribute__((__aligned__)) #define __printf(a, b) __attribute__((__format__(printf, a, b))) @@ -211,6 +208,8 @@ struct ftrace_likely_data { #define __alias(symbol) __attribute__((__alias__(#symbol))) #define __cold __attribute__((__cold__)) #define __section(S) __attribute__((__section__(#S))) +#define __always_inline inline __attribute__((__always_inline__)) +#define __gnu_inline __attribute__((__gnu_inline__)) #ifdef CONFIG_ENABLE_MUST_CHECK @@ -235,18 +234,6 @@ struct ftrace_likely_data { #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) -/* - * Feature detection for gnu_inline (gnu89 extern inline semantics). Either - * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, - * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not - * defined so the gnu89 semantics are the default. - */ -#ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((__gnu_inline__)) -#else -# define __gnu_inline -#endif - /* * Force always-inline if the user requests it so via the .config. * GCC does not warn about unused static inline functions for @@ -271,10 +258,6 @@ struct ftrace_likely_data { #define __inline inline #define noinline __attribute__((__noinline__)) -#ifndef __always_inline -#define __always_inline inline __attribute__((__always_inline__)) -#endif - /* * Rather then using noinline to prevent stack consumption, use * noinline_for_stack instead. For documentation reasons. -- cgit v1.2.3 From ec0bbef66f867854691d5af18c2231d746958e0e Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:25:14 +0200 Subject: Compiler Attributes: homogenize __must_be_array Different definitions of __must_be_array: * gcc: disabled for __CHECKER__ * clang: same definition as gcc's, but without __CHECKER__ * intel: the comment claims __builtin_types_compatible_p() is unsupported; but icc seems to support it since 13.0.1 (released in 2012). See https://godbolt.org/z/S0l6QQ Therefore, we can remove all of them and have a single definition in compiler.h Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 1 - include/linux/compiler-gcc.h | 7 ------- include/linux/compiler-intel.h | 3 --- include/linux/compiler.h | 7 +++++++ 4 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d11cad61ba5c..fa9532f8d885 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -41,6 +41,5 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #define __assume_aligned(a, ...) \ __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7a1de7683df5..3b32bbfa5a49 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -68,13 +68,6 @@ */ #define uninitialized_var(x) x = x -#ifdef __CHECKER__ -#define __must_be_array(a) 0 -#else -/* &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])) -#endif - #ifdef RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index fef8bb3e53ef..6004b4588bd4 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -29,9 +29,6 @@ */ #define OPTIMIZER_HIDE_VAR(var) barrier() -/* Intel ECC compiler doesn't support __builtin_types_compatible_p() */ -#define __must_be_array(a) 0 - #endif /* icc has this, but it's called _bswap16 */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ec4a28bad2c6..165b1d5683ed 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -357,4 +357,11 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +#ifdef __CHECKER__ +#define __must_be_array(a) 0 +#else +/* &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])) +#endif + #endif /* __LINUX_COMPILER_H */ -- cgit v1.2.3 From 989bd5000f36052df604888ed12bb6ef390786b7 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 31 Aug 2018 18:00:16 +0200 Subject: Compiler Attributes: remove unneeded sparse (__CHECKER__) tests Sparse knows about a few more attributes now, so we can remove the __CHECKER__ conditions from them (which, in turn, allow us to move some of them later on to compiler_attributes.h). * assume_aligned: since sparse's commit ffc860b ("sparse: ignore __assume_aligned__ attribute"), included in 0.5.1 * error: since sparse's commit 0a04210 ("sparse: Add 'error' to ignored attributes"), included in 0.5.0 * hotpatch: since sparse's commit 6043210 ("sparse/parse.c: ignore hotpatch attribute"), included in 0.5.1 * warning: since sparse's commit 977365d ("Avoid "attribute 'warning': unknown attribute" warning"), included in 0.4.2 On top of that, __must_be_array does not need it either because: * Even ancient versions of sparse do not have a problem * BUILD_BUG_ON_ZERO() is currently disabled for __CHECKER__ Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 6 ++---- include/linux/compiler.h | 4 ---- include/linux/compiler_types.h | 2 +- 3 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3b32bbfa5a49..1ca6a51cfaa9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -76,14 +76,12 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#ifndef __CHECKER__ #define __compiletime_warning(message) __attribute__((__warning__(message))) #define __compiletime_error(message) __attribute__((__error__(message))) -#ifdef LATENT_ENTROPY_PLUGIN +#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) #define __latent_entropy __attribute__((latent_entropy)) #endif -#endif /* __CHECKER__ */ /* * calling noreturn functions, __builtin_unreachable() and __builtin_trap() @@ -131,7 +129,7 @@ /* gcc version specific checks */ -#if GCC_VERSION >= 40900 && !defined(__CHECKER__) +#if GCC_VERSION >= 40900 /* * __assume_aligned(n, k): Tell the optimizer that the returned * pointer can be assumed to be k modulo n. The second argument is diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 165b1d5683ed..4030a2940d6b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -357,11 +357,7 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") -#ifdef __CHECKER__ -#define __must_be_array(a) 0 -#else /* &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])) -#endif #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 5ff9cda893f4..a3eceb3ad1b3 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -218,7 +218,7 @@ struct ftrace_likely_data { #define __must_check #endif -#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) +#if defined(CC_USING_HOTPATCH) #define notrace __attribute__((hotpatch(0, 0))) #else #define notrace __attribute__((__no_instrument_function__)) -- cgit v1.2.3 From 66dbeef915f275dad6c8656b31667ef9640f5639 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 18:34:18 +0200 Subject: Compiler Attributes: add missing SPDX ID in compiler_types.h Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a3eceb3ad1b3..ed7c0e4a180e 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COMPILER_TYPES_H #define __LINUX_COMPILER_TYPES_H -- cgit v1.2.3 From a3f8a30f3f0079c7edfc72e329eee8594fb3e3cb Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 20:36:59 +0200 Subject: Compiler Attributes: use feature checks instead of version checks Instead of using version checks per-compiler to define (or not) each attribute, use __has_attribute to test for them, following the cleanup started with commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"), which 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. All the attributes that can be unconditionally defined and directly map to compiler attribute(s) (even if optional) have been moved to a new file include/linux/compiler_attributes.h In an effort to make the file as regular as possible, comments stating the purpose of attributes have been removed. Instead, links to the compiler docs have been added (i.e. to gcc and, if available, to clang as well). In addition, they have been sorted. Finally, if an attribute is optional (i.e. if it is guarded by __has_attribute), the reason has been stated for future reference. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 4 - include/linux/compiler-gcc.h | 51 -------- include/linux/compiler-intel.h | 6 - include/linux/compiler_attributes.h | 244 ++++++++++++++++++++++++++++++++++++ include/linux/compiler_types.h | 74 ++--------- 5 files changed, 254 insertions(+), 125 deletions(-) create mode 100644 include/linux/compiler_attributes.h (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index fa9532f8d885..3e7dafb3ea80 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -21,8 +21,6 @@ #define __SANITIZE_ADDRESS__ #endif -#define __no_sanitize_address __attribute__((__no_sanitize__("address"))) - /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements @@ -41,5 +39,3 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") -#define __assume_aligned(a, ...) \ - __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1ca6a51cfaa9..cfac027e1625 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -108,9 +108,6 @@ __builtin_unreachable(); \ } while (0) -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) - #if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) #define __randomize_layout __attribute__((randomize_layout)) #define __no_randomize_layout __attribute__((no_randomize_layout)) @@ -119,32 +116,6 @@ #define randomized_struct_fields_end } __randomize_layout; #endif -/* - * When used with Link Time Optimization, gcc can optimize away C functions or - * variables which are referenced only from assembly code. __visible tells the - * optimizer that something else uses this function or variable, thus preventing - * this. - */ -#define __visible __attribute__((__externally_visible__)) - -/* gcc version specific checks */ - -#if GCC_VERSION >= 40900 -/* - * __assume_aligned(n, k): Tell the optimizer that the returned - * pointer can be assumed to be k modulo n. The second argument is - * optional (default 0), so we use a variadic macro to make the - * shorthand. - * - * Beware: Do not apply this to functions which may return - * ERR_PTRs. Also, it is probably unwise to apply it to functions - * returning extra information in the low bits (but in that case the - * compiler should see some alignment anyway, when the return value is - * massaged by 'flags = ptr & 3; ptr &= ~3;'). - */ -#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) -#endif - /* * GCC 'asm goto' miscompiles certain code sequences: * @@ -176,32 +147,10 @@ #define KASAN_ABI_VERSION 3 #endif -#if GCC_VERSION >= 40902 -/* - * Tell the compiler that address safety instrumentation (KASAN) - * should not be applied to that function. - * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - */ -#define __no_sanitize_address __attribute__((__no_sanitize_address__)) -#endif - #if GCC_VERSION >= 50100 -/* - * Mark structures as requiring designated initializers. - * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html - */ -#define __designated_init __attribute__((__designated_init__)) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -#if !defined(__noclone) -#define __noclone /* not needed */ -#endif - -#if !defined(__no_sanitize_address) -#define __no_sanitize_address -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 6004b4588bd4..517bd14e1222 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -34,9 +34,3 @@ /* icc has this, but it's called _bswap16 */ #define __HAVE_BUILTIN_BSWAP16__ #define __builtin_bswap16 _bswap16 - -/* The following are for compatibility with GCC, from compiler-gcc.h, - * and may be redefined here because they should not be shared with other - * compilers, like clang. - */ -#define __visible __attribute__((__externally_visible__)) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h new file mode 100644 index 000000000000..f0f9fc398440 --- /dev/null +++ b/include/linux/compiler_attributes.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_COMPILER_ATTRIBUTES_H +#define __LINUX_COMPILER_ATTRIBUTES_H + +/* + * The attributes in this file are unconditionally defined and they directly + * map to compiler attribute(s) -- except those that are optional. + * + * Any other "attributes" (i.e. those that depend on a configuration option, + * on a compiler, on an architecture, on plugins, on other attributes...) + * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * + * This file is meant to be sorted (by actual attribute name, + * not by #define identifier). Use the __attribute__((__name__)) syntax + * (i.e. with underscores) to avoid future collisions with other macros. + * If an attribute is optional, state the reason in the comment. + */ + +/* + * To check for optional attributes, we use __has_attribute, which 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 +# define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___designated_init__ 0 +# define __GCC4_has_attribute___externally_visible__ 1 +# define __GCC4_has_attribute___noclone__ 1 +# define __GCC4_has_attribute___optimize__ 1 +# define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute + */ +#define __alias(symbol) __attribute__((__alias__(#symbol))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-aligned-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-aligned-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-aligned-variable-attribute + */ +#define __aligned(x) __attribute__((__aligned__(x))) +#define __aligned_largest __attribute__((__aligned__)) + +/* + * Note: users of __always_inline currently do not write "inline" themselves, + * which seems to be required by gcc to apply the attribute according + * to its docs (and also "warning: always_inline function might not be + * inlinable [-Wattributes]" is emitted). + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-always_005finline-function-attribute + * clang: mentioned + */ +#define __always_inline inline __attribute__((__always_inline__)) + +/* + * The second argument is optional (default 0), so we use a variadic macro + * to make the shorthand. + * + * Beware: Do not apply this to functions which may return + * ERR_PTRs. Also, it is probably unwise to apply it to functions + * returning extra information in the low bits (but in that case the + * compiler should see some alignment anyway, when the return value is + * massaged by 'flags = ptr & 3; ptr &= ~3;'). + * + * Optional: only supported since gcc >= 4.9 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#assume-aligned + */ +#if __has_attribute(__assume_aligned__) +# define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) +#else +# define __assume_aligned(a, ...) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute + */ +#define __cold __attribute__((__cold__)) + +/* + * Note the long name. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-const-function-attribute + */ +#define __attribute_const__ __attribute__((__const__)) + +/* + * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' + * attribute warnings entirely and for good") for more information. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-deprecated-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-deprecated-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-deprecated-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Enumerator-Attributes.html#index-deprecated-enumerator-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#deprecated + */ +#define __deprecated + +/* + * Optional: only supported since gcc >= 5.1 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-designated_005finit-type-attribute + */ +#if __has_attribute(__designated_init__) +# define __designated_init __attribute__((__designated_init__)) +#else +# define __designated_init +#endif + +/* + * Optional: not supported by clang + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-externally_005fvisible-function-attribute + */ +#if __has_attribute(__externally_visible__) +# define __visible __attribute__((__externally_visible__)) +#else +# define __visible +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-format-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#format + */ +#define __printf(a, b) __attribute__((__format__(printf, a, b))) +#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-gnu_005finline-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#gnu-inline + */ +#define __gnu_inline __attribute__((__gnu_inline__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute + */ +#define __malloc __attribute__((__malloc__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-mode-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-mode-variable-attribute + */ +#define __mode(x) __attribute__((__mode__(x))) + +/* + * Optional: not supported by clang + * Note: icc does not recognize gcc's no-tracer + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noclone-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-optimize-function-attribute + */ +#if __has_attribute(__noclone__) +# if __has_attribute(__optimize__) +# define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) +# else +# define __noclone __attribute__((__noclone__)) +# endif +#else +# define __noclone +#endif + +/* + * Note the missing underscores. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noinline-function-attribute + * clang: mentioned + */ +#define noinline __attribute__((__noinline__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn + * clang: https://clang.llvm.org/docs/AttributeReference.html#id1 + */ +#define __noreturn __attribute__((__noreturn__)) + +/* + * Optional: only supported since gcc >= 4.8 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fsanitize_005faddress-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-sanitize-address-no-address-safety-analysis + */ +#if __has_attribute(__no_sanitize_address__) +# define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#else +# define __no_sanitize_address +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute + * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute + */ +#define __packed __attribute__((__packed__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-pure-function-attribute + */ +#define __pure __attribute__((__pure__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-section-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate + */ +#define __section(S) __attribute__((__section__(#S))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-unused-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-unused-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-unused-label-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#maybe-unused-unused + */ +#define __always_unused __attribute__((__unused__)) +#define __maybe_unused __attribute__((__unused__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-used-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-used-variable-attribute + */ +#define __used __attribute__((__used__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute + */ +#define __weak __attribute__((__weak__)) + +#endif /* __LINUX_COMPILER_ATTRIBUTES_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index ed7c0e4a180e..3439d7d0249a 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -55,6 +55,9 @@ extern void __chk_io_ptr(const volatile void __iomem *); #ifdef __KERNEL__ +/* Attributes */ +#include + /* Compiler specific macros. */ #ifdef __clang__ #include @@ -79,12 +82,6 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include #endif -/* - * Generic compiler-independent macros required for kernel - * build go below this comment. Actual compiler/compiler version - * specific implementations come from the above header files - */ - struct ftrace_branch_data { const char *func; const char *file; @@ -107,9 +104,6 @@ struct ftrace_likely_data { unsigned long constant; }; -/* Don't. Just don't. */ -#define __deprecated - #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ @@ -119,10 +113,6 @@ struct ftrace_likely_data { * compilers. We don't consider that to be an error, so set them to nothing. * For example, some of them are for compiler specific plugins. */ -#ifndef __designated_init -# define __designated_init -#endif - #ifndef __latent_entropy # define __latent_entropy #endif @@ -140,17 +130,6 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif -#ifndef __visible -#define __visible -#endif - -/* - * Assume alignment of return value. - */ -#ifndef __assume_aligned -#define __assume_aligned(a, ...) -#endif - /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) @@ -159,10 +138,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#ifndef __noclone -#define __noclone -#endif - /* Helpers for emitting diagnostics in pragmas. */ #ifndef __diag #define __diag(string) @@ -182,37 +157,6 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) -/* - * From the GCC manual: - * - * Many functions have no effects except the return value and their - * return value depends only on the parameters and/or global - * variables. Such a function can be subject to common subexpression - * elimination and loop optimization just as an arithmetic operator - * would be. - * [...] - */ -#define __pure __attribute__((__pure__)) -#define __attribute_const__ __attribute__((__const__)) -#define __aligned(x) __attribute__((__aligned__(x))) -#define __aligned_largest __attribute__((__aligned__)) -#define __printf(a, b) __attribute__((__format__(printf, a, b))) -#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) -#define __maybe_unused __attribute__((__unused__)) -#define __always_unused __attribute__((__unused__)) -#define __mode(x) __attribute__((__mode__(x))) -#define __malloc __attribute__((__malloc__)) -#define __used __attribute__((__used__)) -#define __noreturn __attribute__((__noreturn__)) -#define __packed __attribute__((__packed__)) -#define __weak __attribute__((__weak__)) -#define __alias(symbol) __attribute__((__alias__(#symbol))) -#define __cold __attribute__((__cold__)) -#define __section(S) __attribute__((__section__(#S))) -#define __always_inline inline __attribute__((__always_inline__)) -#define __gnu_inline __attribute__((__gnu_inline__)) - - #ifdef CONFIG_ENABLE_MUST_CHECK #define __must_check __attribute__((__warn_unused_result__)) #else @@ -246,18 +190,20 @@ struct ftrace_likely_data { * semantics rather than c99. This prevents multiple symbol definition errors * of extern inline functions at link time. * A lot of inline functions can cause havoc with function tracing. + * Do not use __always_inline here, since currently it expands to inline again + * (which would break users of __always_inline). */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) -#define inline \ - inline __attribute__((__always_inline__, __unused__)) notrace __gnu_inline +#define inline inline __attribute__((__always_inline__)) __gnu_inline \ + __maybe_unused notrace #else -#define inline inline __attribute__((__unused__)) notrace __gnu_inline +#define inline inline __gnu_inline \ + __maybe_unused notrace #endif #define __inline__ inline -#define __inline inline -#define noinline __attribute__((__noinline__)) +#define __inline inline /* * Rather then using noinline to prevent stack consumption, use -- cgit v1.2.3 From 06e3727e02f9ee9cf571692cd5c74fc5a8a2af52 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 19:22:13 +0200 Subject: Compiler Attributes: KENTRY used twice the "used" attribute Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- 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 4030a2940d6b..17ee9165ca51 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((__section__("___kentry" "+" #sym ), used)) \ + __attribute__((__section__("___kentry" "+" #sym ))) \ = (unsigned long)&sym; #endif -- cgit v1.2.3 From e04462fb82f8dd98288c0e7ab1eec79c92537d25 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 19:17:50 +0200 Subject: Compiler Attributes: remove uses of __attribute__ from compiler.h Suggested-by: Nick Desaulniers Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 17ee9165ca51..b5fb034fa6fa 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -23,8 +23,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __branch_check__(x, expect, is_constant) ({ \ long ______r; \ static struct ftrace_likely_data \ - __attribute__((__aligned__(4))) \ - __attribute__((__section__("_ftrace_annotated_branch"))) \ + __aligned(4) \ + __section("_ftrace_annotated_branch") \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -59,8 +59,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, ({ \ int ______r; \ static struct ftrace_branch_data \ - __attribute__((__aligned__(4))) \ - __attribute__((__section__("_ftrace_branch"))) \ + __aligned(4) \ + __section("_ftrace_branch") \ ______f = { \ .func = __func__, \ .file = __FILE__, \ @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((__section__("___kentry" "+" #sym ))) \ + __section("___kentry" "+" #sym ) \ = (unsigned long)&sym; #endif @@ -287,7 +287,7 @@ unsigned long read_word_at_a_time(const void *addr) * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __attribute__((__section__(".discard.addressable"), used)) \ + static void * __section(".discard.addressable") __used \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** -- cgit v1.2.3 From 92676236917d8e2e0de1d8612686d3d04a6a245b Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Wed, 19 Sep 2018 01:06:24 +0200 Subject: Compiler Attributes: add support for __nonstring (gcc >= 8) From the GCC manual: nonstring The nonstring variable attribute specifies that an object or member declaration with type array of char, signed char, or unsigned char, or pointer to such a type is intended to store character arrays that do not necessarily contain a terminating NUL. This is useful in detecting uses of such arrays or pointers with functions that expect NUL-terminated strings, and to avoid warnings when such an array or pointer is used as an argument to a bounded string manipulation function such as strncpy. https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html This attribute can be used for documentation purposes (i.e. replacing comments), but it is most helpful when the following warnings are enabled: -Wstringop-overflow Warn for calls to string manipulation functions such as memcpy and strcpy that are determined to overflow the destination buffer. [...] -Wstringop-truncation Warn for calls to bounded string manipulation functions such as strncat, strncpy, and stpncpy that may either truncate the copied string or leave the destination unchanged. [...] In situations where a character array is intended to store a sequence of bytes with no terminating NUL such an array may be annotated with attribute nonstring to avoid this warning. Such arrays, however, are not suitable arguments to functions that expect NUL-terminated strings. To help detect accidental misuses of such arrays GCC issues warnings unless it can prove that the use is safe. https://gcc.gnu.org/onlinedocs/gcc/Warning-Options.html Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index f0f9fc398440..6b28c1b7310c 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -34,6 +34,7 @@ # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___optimize__ 1 +# define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) #endif @@ -181,6 +182,19 @@ */ #define noinline __attribute__((__noinline__)) +/* + * Optional: only supported since gcc >= 8 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute + */ +#if __has_attribute(__nonstring__) +# define __nonstring __attribute__((__nonstring__)) +#else +# define __nonstring +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn -- cgit v1.2.3 From 9dc6edcf676fe188430e8b119f91280bbf285163 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Aug 2018 14:24:16 -0400 Subject: SUNRPC: Clean up initialisation of the struct rpc_rqst Move the initialisation back into xprt.c. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 336fd1a19cca..3d80524e92d6 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -325,7 +325,6 @@ struct xprt_class { struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); -void xprt_request_init(struct rpc_task *task); void xprt_retry_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); -- cgit v1.2.3 From 3021a5bbbf0aa0252f2993b84ee903a0eca0b690 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2018 13:50:21 -0400 Subject: SUNRPC: The transmitted message must lie in the RPCSEC window of validity If a message has been encoded using RPCSEC_GSS, the server is maintaining a window of sequence numbers that it considers valid. The client should normally be tracking that window, and needs to verify that the sequence number used by the message being transmitted still lies inside the window of validity. So far, we've been able to assume this condition would be realised automatically, since the client has been encoding the message only after taking the socket lock. Once we change that condition, we will need the explicit check. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 ++ include/linux/sunrpc/auth_gss.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 58a6765c1c5e..2c97a3933ef9 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -157,6 +157,7 @@ struct rpc_credops { int (*crkey_timeout)(struct rpc_cred *); bool (*crkey_to_expire)(struct rpc_cred *); char * (*crstringify_acceptor)(struct rpc_cred *); + bool (*crneed_reencode)(struct rpc_task *); }; extern const struct rpc_authops authunix_ops; @@ -192,6 +193,7 @@ __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); __be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); int rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj); int rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj); +bool rpcauth_xmit_need_reencode(struct rpc_task *task); int rpcauth_refreshcred(struct rpc_task *); void rpcauth_invalcred(struct rpc_task *); int rpcauth_uptodatecred(struct rpc_task *); diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 0c9eac351aab..30427b729070 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -70,6 +70,7 @@ struct gss_cl_ctx { refcount_t count; enum rpc_gss_proc gc_proc; u32 gc_seq; + u32 gc_seq_xmit; spinlock_t gc_seq_lock; struct gss_ctx *gc_gss_ctx; struct xdr_netobj gc_wire_ctx; -- cgit v1.2.3 From 7ebbbc6e7bd023903daa5bd95726edf2d60b559c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 28 Aug 2018 09:00:27 -0400 Subject: SUNRPC: Simplify identification of when the message send/receive is complete Add states to indicate that the message send and receive are not yet complete. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 592653becd91..9e655df70131 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -140,8 +140,10 @@ struct rpc_task_setup { #define RPC_TASK_RUNNING 0 #define RPC_TASK_QUEUED 1 #define RPC_TASK_ACTIVE 2 -#define RPC_TASK_MSG_RECV 3 -#define RPC_TASK_MSG_RECV_WAIT 4 +#define RPC_TASK_NEED_XMIT 3 +#define RPC_TASK_NEED_RECV 4 +#define RPC_TASK_MSG_RECV 5 +#define RPC_TASK_MSG_RECV_WAIT 6 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -- cgit v1.2.3 From d1109aa56c71e19fc117e75bff11384fc7279a3b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Aug 2018 15:48:42 -0400 Subject: SUNRPC: Rename TCP receive-specific state variables Since we will want to introduce similar TCP state variables for the transmission of requests, let's rename the existing ones to label that they are for the receive side. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index ae0f99b9b965..90d5ca8e65f4 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -30,15 +30,17 @@ struct sock_xprt { /* * State of TCP reply receive */ - __be32 tcp_fraghdr, - tcp_xid, - tcp_calldir; + struct { + __be32 fraghdr, + xid, + calldir; - u32 tcp_offset, - tcp_reclen; + u32 offset, + len; - unsigned long tcp_copied, - tcp_flags; + unsigned long copied, + flags; + } recv; /* * Connection of transports -- cgit v1.2.3 From 6c7a64e5a44dbc6d073b83a56a48d0a4099f1dd2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Aug 2018 16:54:57 -0400 Subject: SUNRPC: Add socket transmit queue offset tracking Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 90d5ca8e65f4..005cfb6e7238 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -42,6 +42,13 @@ struct sock_xprt { flags; } recv; + /* + * State of TCP transmit queue + */ + struct { + u32 offset; + } xmit; + /* * Connection of transports */ -- cgit v1.2.3 From cf9946cd6144410ced00d52586ff5a2cb4868fc5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 6 Aug 2018 12:55:34 -0400 Subject: SUNRPC: Refactor the transport request pinning We are going to need to pin for both send and receive. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 +-- include/linux/sunrpc/xprt.h | 1 + 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 9e655df70131..8062ce6b18e5 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -142,8 +142,7 @@ struct rpc_task_setup { #define RPC_TASK_ACTIVE 2 #define RPC_TASK_NEED_XMIT 3 #define RPC_TASK_NEED_RECV 4 -#define RPC_TASK_MSG_RECV 5 -#define RPC_TASK_MSG_RECV_WAIT 6 +#define RPC_TASK_MSG_PIN_WAIT 5 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 3d80524e92d6..bd743c51a865 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -103,6 +103,7 @@ struct rpc_rqst { /* A cookie used to track the state of the transport connection */ + atomic_t rq_pin; /* * Partial send handling -- cgit v1.2.3 From 359c48c04af25397ecefec1ccf200ddd199617ce Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 29 Aug 2018 09:22:28 -0400 Subject: SUNRPC: Add a helper to wake up a sleeping rpc_task and set its status Add a helper that will wake up a task that is sleeping on a specific queue, and will set the value of task->tk_status. This is mainly intended for use by the transport layer to notify the task of an error condition. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8062ce6b18e5..8840a420cf4c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -235,6 +235,9 @@ void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq, struct rpc_task *task); void rpc_wake_up_queued_task(struct rpc_wait_queue *, struct rpc_task *); +void rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *, + struct rpc_task *, + int); void rpc_wake_up(struct rpc_wait_queue *); struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *); struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq, -- cgit v1.2.3 From 75c84151a9dc7a755c607e6761d8f14a1690dbf0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 31 Aug 2018 10:21:00 -0400 Subject: SUNRPC: Rename xprt->recv_lock to xprt->queue_lock We will use the same lock to protect both the transmit and receive queues. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index bd743c51a865..c25d0a5fda69 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -235,7 +235,7 @@ struct rpc_xprt { */ spinlock_t transport_lock; /* lock transport info */ spinlock_t reserve_lock; /* lock slot table */ - spinlock_t recv_lock; /* lock receive list */ + spinlock_t queue_lock; /* send/receive queue lock */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ -- cgit v1.2.3 From edc81dcd5b7f699c4049042b35c904396642032e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Aug 2018 17:55:46 -0400 Subject: SUNRPC: Refactor xprt_transmit() to remove the reply queue code Separate out the action of adding a request to the reply queue so that the backchannel code can simply skip calling it altogether. 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 c25d0a5fda69..0250294c904a 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -334,6 +334,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); +void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -- cgit v1.2.3 From 7f3a1d1e1806a0eb9b200e3aed2a04431f2bcc6a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 23 Aug 2018 00:03:43 -0400 Subject: SUNRPC: Refactor xprt_transmit() to remove wait for reply code Allow the caller in clnt.c to call into the code to wait for a reply after calling xprt_transmit(). Again, the reason is that the backchannel code does not need this functionality. 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 0250294c904a..4fa2af087cff 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -335,6 +335,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); +void xprt_request_wait_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -- cgit v1.2.3 From ef3f54347f690d06649c0d7a1f63d3410b3d08d3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 8 Aug 2018 09:23:32 -0400 Subject: SUNRPC: Distinguish between the slot allocation list and receive queue When storing a struct rpc_rqst on the slot allocation list, we currently use the same field 'rq_list' as we use to store the request on the receive queue. Since the structure is never on both lists at the same time, this is OK. However, for clarity, let's make that a union with different names for the different lists so that we can more easily distinguish between the two states. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 4fa2af087cff..9cec2d0811f2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -82,7 +82,11 @@ struct rpc_rqst { struct page **rq_enc_pages; /* scratch pages for use by gss privacy code */ void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */ - struct list_head rq_list; + + union { + struct list_head rq_list; /* Slot allocation list */ + struct list_head rq_recv; /* Receive queue */ + }; void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; @@ -249,7 +253,8 @@ struct rpc_xprt { struct list_head bc_pa_list; /* List of preallocated * backchannel rpc_rqst's */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ - struct list_head recv; + + struct list_head recv_queue; /* Receive queue */ struct { unsigned long bind_count, /* total number of binds */ -- cgit v1.2.3 From 944b042921a17d1a4e51bb05f8edf2b93d26e36f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Aug 2018 23:33:21 -0400 Subject: SUNRPC: Add a transmission queue for RPC requests Add the queue that will enforce the ordering of RPC task transmission. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9cec2d0811f2..81a6c2c8dfc7 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -88,6 +88,8 @@ struct rpc_rqst { struct list_head rq_recv; /* Receive queue */ }; + struct list_head rq_xmit; /* Send queue */ + void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; void *rq_rbuffer; /* Reply XDR decode buffer */ @@ -242,6 +244,9 @@ struct rpc_xprt { spinlock_t queue_lock; /* send/receive queue lock */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ + + struct list_head xmit_queue; /* Send queue */ + struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct svc_serv *bc_serv; /* The RPC service which will */ @@ -339,6 +344,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); +void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); -- cgit v1.2.3 From 762e4e67b356ab7b8fbfc39bc07dc6110121505e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Aug 2018 16:28:28 -0400 Subject: SUNRPC: Refactor RPC call encoding Move the call encoding so that it occurs before the transport connection etc. 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 81a6c2c8dfc7..b8a7de161f67 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -347,6 +347,7 @@ bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); +bool xprt_request_need_retransmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); -- cgit v1.2.3 From 902c58872e1e9a2c146a55b0701c0b26cc5a4b24 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 1 Sep 2018 17:21:01 -0400 Subject: SUNRPC: Fix up the back channel transmit Fix up the back channel code to recognise that it has already been transmitted, so does not need to be called again. Also ensure that we set req->rq_task. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 4397a4824c81..28721cf73ec3 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -34,6 +34,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #ifdef CONFIG_SUNRPC_BACKCHANNEL struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied); +void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs); -- cgit v1.2.3 From 50f484e298218b7271fad8a23bd44c82fb3110e1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 30 Aug 2018 13:27:29 -0400 Subject: SUNRPC: Treat the task and request as separate in the xprt_ops->send_request() When we shift to using the transmit queue, then the task that holds the write lock will not necessarily be the same as the one being transmitted. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index b8a7de161f67..8c2bb078f00c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -140,7 +140,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - int (*send_request)(struct rpc_task *task); + int (*send_request)(struct rpc_rqst *req, struct rpc_task *task); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_request)(struct rpc_task *task); -- cgit v1.2.3 From 918f3c1fe83c5baa4892b943d3f5ac7191d8fb74 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Sep 2018 11:37:22 -0400 Subject: SUNRPC: Improve latency for interactive tasks One of the intentions with the priority queues was to ensure that no single process can hog the transport. The field task->tk_owner therefore identifies the RPC call's origin, and is intended to allow the RPC layer to organise queues for fairness. This commit therefore modifies the transmit queue to group requests by task->tk_owner, and ensures that we round robin among those groups. 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 8c2bb078f00c..e377620b9744 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -89,6 +89,7 @@ struct rpc_rqst { }; struct list_head rq_xmit; /* Send queue */ + struct list_head rq_xmit2; /* Send queue */ void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; -- cgit v1.2.3 From 75891f502f5fc70f52a01af5b924384ed4866907 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 17:37:36 -0400 Subject: SUNRPC: Support for congestion control when queuing is enabled Both RDMA and UDP transports require the request to get a "congestion control" credit before they can be transmitted. Right now, this is done when the request locks the socket. We'd like it to happen when a request attempts to be transmitted for the first time. In order to support retransmission of requests that already hold such credits, we also want to ensure that they get queued first, so that we don't deadlock with requests that have yet to obtain a credit. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index e377620b9744..0d0cc127615e 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -397,6 +397,7 @@ void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_pin_rqst(struct rpc_rqst *req); void xprt_unpin_rqst(struct rpc_rqst *req); void xprt_release_rqst_cong(struct rpc_task *task); +bool xprt_request_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); @@ -415,6 +416,7 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BINDING (5) #define XPRT_CLOSING (6) #define XPRT_CONGESTED (9) +#define XPRT_CWND_WAIT (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From 36bd7de949f41d586ef7794169af75462b67acbc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 18:41:32 -0400 Subject: SUNRPC: Turn off throttling of RPC slots for TCP sockets The theory was that we would need to grab the socket lock anyway, so we might as well use it to gate the allocation of RPC slots for a TCP socket. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 0d0cc127615e..14c9b4d49fb4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -343,7 +343,6 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); -- cgit v1.2.3 From c544577daddb618c7dd5fa7fb98d6a41782f020e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 23:39:27 -0400 Subject: SUNRPC: Clean up transport write space handling Treat socket write space handling in the same way we now treat transport congestion: by denying the XPRT_LOCK until the transport signals that it has free buffer space. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc_xprt.h | 1 - include/linux/sunrpc/xprt.h | 5 +++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index c3d72066d4b1..6b7a86c4d6e6 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -84,7 +84,6 @@ struct svc_xprt { struct sockaddr_storage xpt_remote; /* remote peer's address */ size_t xpt_remotelen; /* length of address */ char xpt_remotebuf[INET6_ADDRSTRLEN + 10]; - struct rpc_wait_queue xpt_bc_pending; /* backchannel wait queue */ struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 14c9b4d49fb4..5600242ccbf9 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -387,8 +387,8 @@ int xprt_load_transport(const char *); void xprt_set_retrans_timeout_def(struct rpc_task *task); void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); -void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action); -void xprt_write_space(struct rpc_xprt *xprt); +void xprt_wait_for_buffer_space(struct rpc_xprt *xprt); +bool xprt_write_space(struct rpc_xprt *xprt); void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_update_rtt(struct rpc_task *task); @@ -416,6 +416,7 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_CLOSING (6) #define XPRT_CONGESTED (9) #define XPRT_CWND_WAIT (10) +#define XPRT_WRITE_SPACE (11) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From adfa71446dd0943ba376eff3e05c7c89582f8038 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 23:58:59 -0400 Subject: SUNRPC: Cleanup: remove the unused 'task' argument from the request_send() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5600242ccbf9..823860cce0bc 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -141,7 +141,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - int (*send_request)(struct rpc_rqst *req, struct rpc_task *task); + int (*send_request)(struct rpc_rqst *req); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_request)(struct rpc_task *task); -- cgit v1.2.3 From 95f7691daa57bbd68caac2bdad79e0b08f4d46c1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 7 Sep 2018 08:35:22 -0400 Subject: SUNRPC: Convert xprt receive queue to use an rbtree If the server is slow, we can find ourselves with quite a lot of entries on the receive queue. Converting the search from an O(n) to O(log(n)) can make a significant difference, particularly since we have to hold a number of locks while searching. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 823860cce0bc..9be399020dab 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -85,7 +85,7 @@ struct rpc_rqst { union { struct list_head rq_list; /* Slot allocation list */ - struct list_head rq_recv; /* Receive queue */ + struct rb_node rq_recv; /* Receive queue */ }; struct list_head rq_xmit; /* Send queue */ @@ -260,7 +260,7 @@ struct rpc_xprt { * backchannel rpc_rqst's */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ - struct list_head recv_queue; /* Receive queue */ + struct rb_root recv_queue; /* Receive queue */ struct { unsigned long bind_count, /* total number of binds */ -- cgit v1.2.3 From f42f7c283078ce3c1e8368b140e270755b1ae313 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 8 Sep 2018 22:09:48 -0400 Subject: SUNRPC: Fix priority queue fairness Fix up the priority queue to not batch by owner, but by queue, so that we allow '1 << priority' elements to be dequeued before switching to the next priority queue. The owner field is still used to wake up requests in round robin order by owner to avoid single processes hogging the RPC layer by loading the queues. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8840a420cf4c..7b540c066594 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -189,7 +189,6 @@ struct rpc_timer { struct rpc_wait_queue { spinlock_t lock; struct list_head tasks[RPC_NR_PRIORITY]; /* task queue for each priority level */ - pid_t owner; /* process id of last task serviced */ unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ @@ -205,7 +204,6 @@ struct rpc_wait_queue { * from a single cookie. The aim is to improve * performance of NFS operations such as read/write. */ -#define RPC_BATCH_COUNT 16 #define RPC_IS_PRIORITY(q) ((q)->maxpriority > 0) /* -- cgit v1.2.3 From 431f6eb3570f286036bc8718a908a283f5d99473 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 16 Sep 2018 00:08:20 -0400 Subject: SUNRPC: Add a label for RPC calls that require allocation on receive If the RPC call relies on the receive call allocating pages as buffers, then let's label it so that we a) Don't leak memory by allocating pages for requests that do not expect this behaviour b) Can optimise for the common case where calls do not require allocation. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 2bd68177a442..431829233392 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -58,6 +58,7 @@ struct xdr_buf { flags; /* Flags for data disposition */ #define XDRBUF_READ 0x01 /* target of file read */ #define XDRBUF_WRITE 0x02 /* source of file write */ +#define XDRBUF_SPARSE_PAGES 0x04 /* Page array is sparse */ unsigned int buflen, /* Total length of storage buffer */ len; /* Length of XDR encoded message */ -- cgit v1.2.3 From 9d96acbc7f376dc1ffcedca0c349dd3389187a38 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 13 Sep 2018 12:22:04 -0400 Subject: SUNRPC: Add a bvec array to struct xdr_buf for use with iovec_iter() Add a bvec array to struct xdr_buf, and have the client allocate it when we need to receive data into pages. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 7 +++++++ include/linux/sunrpc/xprt.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 431829233392..745587132a87 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -18,6 +18,7 @@ #include #include +struct bio_vec; struct rpc_rqst; /* @@ -52,6 +53,7 @@ struct xdr_buf { struct kvec head[1], /* RPC header + non-page data */ tail[1]; /* Appended after page data */ + struct bio_vec *bvec; struct page ** pages; /* Array of pages */ unsigned int page_base, /* Start of page data */ page_len, /* Length of page data */ @@ -70,6 +72,8 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) buf->head[0].iov_base = start; buf->head[0].iov_len = len; buf->tail[0].iov_len = 0; + buf->bvec = NULL; + buf->pages = NULL; buf->page_len = 0; buf->flags = 0; buf->len = 0; @@ -116,6 +120,9 @@ __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *); void xdr_inline_pages(struct xdr_buf *, unsigned int, struct page **, unsigned int, unsigned int); void xdr_terminate_string(struct xdr_buf *, const u32); +size_t xdr_buf_pagecount(struct xdr_buf *buf); +int xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp); +void xdr_free_bvec(struct xdr_buf *buf); static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len) { diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9be399020dab..a4ab4f8d9140 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -141,6 +141,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); + void (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -343,6 +344,7 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); +void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); -- cgit v1.2.3 From 277e4ab7d530bf287e02b65cfcd3ea8f489784f6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 09:49:06 -0400 Subject: SUNRPC: Simplify TCP receive code by switching to using iterators Most of this code should also be reusable with other socket types. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 005cfb6e7238..458bfe0137f5 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -31,15 +31,16 @@ struct sock_xprt { * State of TCP reply receive */ struct { - __be32 fraghdr, + struct { + __be32 fraghdr, xid, calldir; + } __attribute__((packed)); u32 offset, len; - unsigned long copied, - flags; + unsigned long copied; } recv; /* @@ -76,21 +77,9 @@ struct sock_xprt { void (*old_error_report)(struct sock *); }; -/* - * TCP receive state flags - */ -#define TCP_RCV_LAST_FRAG (1UL << 0) -#define TCP_RCV_COPY_FRAGHDR (1UL << 1) -#define TCP_RCV_COPY_XID (1UL << 2) -#define TCP_RCV_COPY_DATA (1UL << 3) -#define TCP_RCV_READ_CALLDIR (1UL << 4) -#define TCP_RCV_COPY_CALLDIR (1UL << 5) - /* * TCP RPC flags */ -#define TCP_RPC_REPLY (1UL << 6) - #define XPRT_SOCK_CONNECTING 1U #define XPRT_SOCK_DATA_READY (2) #define XPRT_SOCK_UPD_TIMEOUT (3) -- cgit v1.2.3 From 550aebfe1c573518c35ae85d6ffbdc2d44c92703 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 14:32:45 -0400 Subject: SUNRPC: Allow AF_LOCAL sockets to use the generic stream receive Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 745587132a87..8815be7cae72 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -185,7 +185,6 @@ struct xdr_skb_reader { typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len); -size_t xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, struct xdr_skb_reader *, xdr_skb_read_actor); -- cgit v1.2.3 From ec846469ba7bdb81e42c04e4e15d8fbf19e426e2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 14:38:05 -0400 Subject: SUNRPC: Unexport xdr_partial_copy_from_skb() It is no longer used outside of net/sunrpc/socklib.c Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 8815be7cae72..43106ffa6788 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -186,8 +186,6 @@ struct xdr_skb_reader { typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); -extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, - struct xdr_skb_reader *, xdr_skb_read_actor); extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32); extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *); -- cgit v1.2.3 From 1db97eaa0b482a738c715da6edb023d6f99e50b0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 2 Sep 2018 15:11:57 -0400 Subject: NFS: Convert lookups of the lock context to RCU Speed up lookups of an existing lock context by avoiding the inode->i_lock, and using RCU instead. 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 a0831e9d19c9..d2f4f88a0e66 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -62,6 +62,7 @@ struct nfs_lock_context { struct nfs_open_context *open_context; fl_owner_t lockowner; atomic_t io_count; + struct rcu_head rcu_head; }; struct nfs4_state; -- cgit v1.2.3 From 0de43976fbe716379084f954b1e370c35aa87bf0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 2 Sep 2018 15:57:01 -0400 Subject: NFS: Convert lookups of the open context to RCU Reduce contention on the inode->i_lock by ensuring that we use RCU when looking up the NFS open context. 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 d2f4f88a0e66..6e0417c02279 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -83,6 +83,7 @@ struct nfs_open_context { struct list_head list; struct nfs4_threshold *mdsthreshold; + struct rcu_head rcu_head; }; struct nfs_open_dir_context { -- cgit v1.2.3 From 8d8928d87960d71f898767185b8c0e4ce3de3cbe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 5 Mar 2018 12:03:00 -0500 Subject: NFSv3: Improve NFSv3 performance when server returns no post-op attributes When the server fails to return post-op attributes, the client's attempt to place read data directly in the page cache fails, and so we have to do an extra copy in order to realign the data with page borders. This patch attempts to detect servers that don't return post-op attributes on read (e.g. for pNFS) and adjusts the placement calculation accordingly. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 3 +++ include/linux/nfs_xdr.h | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index bf39d9c92201..0fc0b9135d46 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -228,6 +228,9 @@ struct nfs_server { unsigned short mountd_port; unsigned short mountd_protocol; struct rpc_wait_queue uoc_rpcwaitq; + + /* XDR related information */ + unsigned int read_hdrsize; }; /* Server capabilities */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bd1c889a9ed9..7f5535e5e852 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -608,6 +608,7 @@ struct nfs_pgio_args { __u32 count; unsigned int pgbase; struct page ** pages; + unsigned int replen; /* used by read */ const u32 * bitmask; /* used by write */ enum nfs3_stable_how stable; /* used by write */ }; @@ -618,9 +619,9 @@ struct nfs_pgio_res { __u32 count; __u32 op_status; int eof; /* used by read */ + unsigned int replen; /* used by read */ struct nfs_writeverf * verf; /* used by write */ const struct nfs_server *server; /* used by write */ - }; /* -- cgit v1.2.3 From 28d52235ee25ba7d843242b4cb3c3f27a8828b5a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 24 Sep 2018 13:15:37 -0400 Subject: NFSv4: Save a few bytes in the nfs_pgio_args/res Save a few bytes by allowing the read/write specific fields of the structures to share storage. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7f5535e5e852..343e44166346 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -608,9 +608,13 @@ struct nfs_pgio_args { __u32 count; unsigned int pgbase; struct page ** pages; - unsigned int replen; /* used by read */ - const u32 * bitmask; /* used by write */ - enum nfs3_stable_how stable; /* used by write */ + union { + unsigned int replen; /* used by read */ + struct { + const u32 * bitmask; /* used by write */ + enum nfs3_stable_how stable; /* used by write */ + }; + }; }; struct nfs_pgio_res { @@ -618,10 +622,16 @@ struct nfs_pgio_res { struct nfs_fattr * fattr; __u32 count; __u32 op_status; - int eof; /* used by read */ - unsigned int replen; /* used by read */ - struct nfs_writeverf * verf; /* used by write */ - const struct nfs_server *server; /* used by write */ + union { + struct { + unsigned int replen; /* used by read */ + int eof; /* used by read */ + }; + struct { + struct nfs_writeverf * verf; /* used by write */ + const struct nfs_server *server; /* used by write */ + }; + }; }; /* -- cgit v1.2.3 From 1c6c4b740df12f2162ae5c3fac337137e2776236 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 25 Sep 2018 12:34:43 -0400 Subject: NFS: Remove private spinlock in struct nfs_pgio_header Now that each struct nfs_pgio_header corresponds to one RPC call, we only have one writer to the struct nfs_pgio_header. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 343e44166346..0e016252cfc6 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1482,11 +1482,10 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; - spinlock_t lock; - /* fields protected by lock */ + int pnfs_error; int error; /* merge with pnfs_error */ - unsigned long good_bytes; /* boundary of good data */ + unsigned int good_bytes; /* boundary of good data */ unsigned long flags; /* -- cgit v1.2.3 From 571ed1fd2390f74e4c1f46994f753fb0d29285e4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 29 Sep 2018 16:00:43 -0400 Subject: SUNRPC: Replace krb5_seq_lock with a lockless scheme Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 7df625d41e35..69f749afa617 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -118,7 +118,8 @@ struct krb5_ctx { u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; -extern spinlock_t krb5_seq_lock; +extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx); +extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx); /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) -- cgit v1.2.3 From aef716fa5e6da3919cca22ac2097a90d73d8177f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 27 Sep 2018 13:55:58 -0700 Subject: RDMA/qedr: Remove enumerated type qed_roce_ll2_tx_dest Clang warns when one enumerated type is explicitly converted to another. drivers/infiniband/hw/qedr/qedr_roce_cm.c:198:28: warning: implicit conversion from enumeration type 'enum qed_roce_ll2_tx_dest' to different enumeration type 'enum qed_ll2_tx_dest' [-Wenum-conversion] ll2_tx_pkt.tx_dest = pkt->tx_dest; ~ ~~~~~^~~~~~~ 1 warning generated. Turns out that QED_ROCE_LL2_TX_DEST_NW and QED_ROCE_LL2_TX_DEST_LB are only used once in the whole tree and QED_ROCE_LL2_TX_DEST_MAX is used nowhere. Remove them and use the equivalent values from qed_ll2_tx_dest in their place. Reported-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Acked-by: Michal Kalderon Signed-off-by: Jason Gunthorpe --- include/linux/qed/qed_rdma_if.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index df4d13f7e191..d15f8e4815e3 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -39,15 +39,6 @@ #include #include -enum qed_roce_ll2_tx_dest { - /* Light L2 TX Destination to the Network */ - QED_ROCE_LL2_TX_DEST_NW, - - /* Light L2 TX Destination to the Loopback */ - QED_ROCE_LL2_TX_DEST_LB, - QED_ROCE_LL2_TX_DEST_MAX -}; - #define QED_RDMA_MAX_CNQ_SIZE (0xFFFF) /* rdma interface */ @@ -581,7 +572,7 @@ struct qed_roce_ll2_packet { int n_seg; struct qed_roce_ll2_buffer payload[RDMA_MAX_SGE_PER_SQ_WQE]; int roce_mode; - enum qed_roce_ll2_tx_dest tx_dest; + enum qed_ll2_tx_dest tx_dest; }; enum qed_rdma_type { -- cgit v1.2.3 From d440c52d3151a28358f4c2d52d8583a0aa54ab83 Mon Sep 17 00:00:00 2001 From: Junling Zheng Date: Fri, 28 Sep 2018 20:25:56 +0800 Subject: f2fs: support superblock checksum Now we support crc32 checksum for superblock. Reviewed-by: Chao Yu Signed-off-by: Junling Zheng Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1d4b196291d6..1db13ff9a3f4 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -109,7 +109,8 @@ struct f2fs_super_block { struct f2fs_device devs[MAX_DEVICES]; /* device list */ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ __u8 hot_ext_count; /* # of hot file extension */ - __u8 reserved[314]; /* valid reserved region */ + __u8 reserved[310]; /* valid reserved region */ + __le32 crc; /* checksum of superblock */ } __packed; /* -- cgit v1.2.3 From cf9af0d5786c008971148f4e06567a98f6a7f9d0 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 27 Sep 2018 13:38:09 +0200 Subject: gpio: Propagate errors from gpiod_set_array_value_complex() Internal helper function gpiod_set_array_value_complex() was changed to return an error value, but not all gpiolib callers were updated to propagate the new error up. Fixes: 3027743f83f867d8 ("gpio: Remove VLA from gpiolib") Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index d7fbe30ece84..136aeca37740 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -117,10 +117,10 @@ int gpiod_get_array_value(unsigned int array_size, struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value(struct gpio_desc *desc, int value); -void gpiod_set_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); +int gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); int gpiod_get_raw_value(const struct gpio_desc *desc); int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -139,10 +139,10 @@ int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_array *array_info, unsigned long *value_bitmap); void gpiod_set_value_cansleep(struct gpio_desc *desc, int value); -void gpiod_set_array_value_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); +int gpiod_set_array_value_cansleep(unsigned int array_size, + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc); int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -361,13 +361,14 @@ static inline void gpiod_set_value(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap) +static inline int gpiod_set_array_value(unsigned int array_size, + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); + return 0; } static inline int gpiod_get_raw_value(const struct gpio_desc *desc) { @@ -419,13 +420,14 @@ static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) /* GPIO can never have been requested */ WARN_ON(1); } -static inline void gpiod_set_array_value_cansleep(unsigned int array_size, +static inline int gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); + return 0; } static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) { -- cgit v1.2.3 From 3c940660cb1ea6c952bb863040cdacafd5077448 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 27 Sep 2018 13:38:10 +0200 Subject: gpio: Restore indentation of continued lines Fixes: 3027743f83f867d8 ("gpio: Remove VLA from gpiolib") Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 136aeca37740..0f350616d372 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -128,9 +128,9 @@ int gpiod_get_raw_array_value(unsigned int array_size, unsigned long *value_bitmap); void gpiod_set_raw_value(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); /* Value get/set from sleeping context */ int gpiod_get_value_cansleep(const struct gpio_desc *desc); @@ -150,9 +150,9 @@ int gpiod_get_raw_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap); void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value); int gpiod_set_raw_array_value_cansleep(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap); + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap); int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce); int gpiod_set_transitory(struct gpio_desc *desc, bool transitory); @@ -391,9 +391,9 @@ static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) WARN_ON(1); } static inline int gpiod_set_raw_array_value(unsigned int array_size, - struct gpio_desc **desc_array, - struct gpio_array *array_info, - unsigned long *value_bitmap) + struct gpio_desc **desc_array, + struct gpio_array *array_info, + unsigned long *value_bitmap) { /* GPIO can never have been requested */ WARN_ON(1); -- cgit v1.2.3 From 22839869f21ab3850fbbac9b425ccc4c0023926f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 5 Sep 2018 15:34:42 +0100 Subject: signal: Introduce COMPAT_SIGMINSTKSZ for use in compat_sys_sigaltstack The sigaltstack(2) system call fails with -ENOMEM if the new alternative signal stack is found to be smaller than SIGMINSTKSZ. On architectures such as arm64, where the native value for SIGMINSTKSZ is larger than the compat value, this can result in an unexpected error being reported to a compat task. See, for example: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=904385 This patch fixes the problem by extending do_sigaltstack to take the minimum signal stack size as an additional parameter, allowing the native and compat system call entry code to pass in their respective values. COMPAT_SIGMINSTKSZ is just defined as SIGMINSTKSZ if it has not been defined by the architecture. Cc: Arnd Bergmann Cc: Dominik Brodowski Cc: "Eric W. Biederman" Cc: Andrew Morton Cc: Al Viro Cc: Oleg Nesterov Reported-by: Steve McIntyre Tested-by: Steve McIntyre <93sam@debian.org> Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- include/linux/compat.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..de0c13bdcd2c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -103,6 +103,9 @@ typedef struct compat_sigaltstack { compat_size_t ss_size; } compat_stack_t; #endif +#ifndef COMPAT_MINSIGSTKSZ +#define COMPAT_MINSIGSTKSZ MINSIGSTKSZ +#endif #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) -- cgit v1.2.3 From 2da274cdf998a1c12afa6b5975db2df1df01edf1 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Thu, 20 Sep 2018 17:10:22 +0100 Subject: iommu/dma: Add support for non-strict mode With the flush queue infrastructure already abstracted into IOVA domains, hooking it up in iommu-dma is pretty simple. Since there is a degree of dependency on the IOMMU driver knowing what to do to play along, we key the whole thing off a domain attribute which will be set on default DMA ops domains to request non-strict invalidation. That way, drivers can indicate the appropriate support by acknowledging the attribute, and we can easily fall back to strict invalidation otherwise. The flush queue callback needs a handle on the iommu_domain which owns our cookie, so we have to add a pointer back to that, but neatly, that's also sufficient to indicate whether we're using a flush queue or not, and thus which way to release IOVAs. The only slight subtlety is switching __iommu_dma_unmap() from calling iommu_unmap() to explicit iommu_unmap_fast()/iommu_tlb_sync() so that we can elide the sync entirely in non-strict mode. Signed-off-by: Zhen Lei [rm: convert to domain attribute, tweak comments and commit message] Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- 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 87994c265bf5..decabe8e8dbe 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -124,6 +124,7 @@ enum iommu_attr { DOMAIN_ATTR_FSL_PAMU_ENABLE, DOMAIN_ATTR_FSL_PAMUV1, DOMAIN_ATTR_NESTING, /* two stages of translation */ + DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, DOMAIN_ATTR_MAX, }; -- cgit v1.2.3 From 8ad50c8985d805923f52a80698010a0a5123c07d Mon Sep 17 00:00:00 2001 From: Kristina Martsenko Date: Wed, 26 Sep 2018 17:32:50 +0100 Subject: vgic: Add support for 52bit guest physical address Add support for handling 52bit guest physical address to the VGIC layer. So far we have limited the guest physical address to 48bits, by explicitly masking the upper bits. This patch removes the restriction. We do not have to check if the host supports 52bit as the gpa is always validated during an access. (e.g, kvm_{read/write}_guest, kvm_is_visible_gfn()). Also, the ITS table save-restore is also not affected with the enhancement. The DTE entries already store the bits[51:8] of the ITT_addr (with a 256byte alignment). Cc: Marc Zyngier Cc: Christoffer Dall Reviewed-by: Eric Auger Signed-off-by: Kristina Martsenko [ Macro clean ups, fix PROPBASER and PENDBASER accesses ] Signed-off-by: Suzuki K Poulose Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 8bdbb5f29494..74b0aa9c7499 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -357,6 +357,8 @@ #define GITS_CBASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt) #define GITS_CBASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb) +#define GITS_CBASER_ADDRESS(cbaser) ((cbaser) & GENMASK_ULL(51, 12)) + #define GITS_BASER_NR_REGS 8 #define GITS_BASER_VALID (1ULL << 63) @@ -388,6 +390,9 @@ #define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48) #define GITS_BASER_PHYS_52_to_48(phys) \ (((phys) & GENMASK_ULL(47, 16)) | (((phys) >> 48) & 0xf) << 12) +#define GITS_BASER_ADDR_48_to_52(baser) \ + (((baser) & GENMASK_ULL(47, 16)) | (((baser) >> 12) & 0xf) << 48) + #define GITS_BASER_SHAREABILITY_SHIFT (10) #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) -- cgit v1.2.3 From 8bad74f9840f87661f20ced3dc80c84ab4fd55a1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:36 +0000 Subject: bpf: extend cgroup bpf core to allow multiple cgroup storage types In order to introduce per-cpu cgroup storage, let's generalize bpf cgroup core to support multiple cgroup storage types. Potentially, per-node cgroup storage can be added later. This commit is mostly a formal change that replaces cgroup_storage pointer with a array of cgroup_storage pointers. It doesn't actually introduce a new storage type, it will be done later. Each bpf program is now able to have one cgroup storage of each type. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++++++++++---------- include/linux/bpf.h | 11 +++++++++-- 2 files changed, 37 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index f91b0f8ff3a9..e9871b012dac 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -2,6 +2,7 @@ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H +#include #include #include #include @@ -22,7 +23,10 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(void*, bpf_cgroup_storage); +DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); + +#define for_each_cgroup_storage_type(stype) \ + for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) struct bpf_cgroup_storage_map; @@ -43,7 +47,7 @@ struct bpf_cgroup_storage { struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; - struct bpf_cgroup_storage *storage; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; struct bpf_prog_array; @@ -101,18 +105,29 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) +static inline enum bpf_cgroup_storage_type cgroup_storage_type( + struct bpf_map *map) { + return BPF_CGROUP_STORAGE_SHARED; +} + +static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage + *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) +{ + enum bpf_cgroup_storage_type stype; struct bpf_storage_buffer *buf; - if (!storage) - return; + for_each_cgroup_storage_type(stype) { + if (!storage[stype]) + continue; - buf = READ_ONCE(storage->buf); - this_cpu_write(bpf_cgroup_storage, &buf->data[0]); + buf = READ_ONCE(storage[stype]->buf); + this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]); + } } -struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog); +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); void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, @@ -265,13 +280,14 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) {} +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 *prog, struct bpf_map *map) { return 0; } static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( - struct bpf_prog *prog) { return 0; } + struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} @@ -293,6 +309,8 @@ static inline void bpf_cgroup_storage_free( #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) +#define for_each_cgroup_storage_type(stype) for (; false; ) + #endif /* CONFIG_CGROUP_BPF */ #endif /* _BPF_CGROUP_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 988a00797bcd..b457fbe7b70b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -272,6 +272,13 @@ struct bpf_prog_offload { u32 jited_len; }; +enum bpf_cgroup_storage_type { + BPF_CGROUP_STORAGE_SHARED, + __BPF_CGROUP_STORAGE_MAX +}; + +#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX + struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; @@ -289,7 +296,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ - struct bpf_map *cgroup_storage; + struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY void *security; @@ -358,7 +365,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, */ struct bpf_prog_array_item { struct bpf_prog *prog; - struct bpf_cgroup_storage *cgroup_storage; + struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; struct bpf_prog_array { -- cgit v1.2.3 From f294b37ec7b24a574884cd157497a3748081c0f0 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:40 +0000 Subject: bpf: rework cgroup storage pointer passing To simplify the following introduction of per-cpu cgroup storage, let's rework a bit a mechanism of passing a pointer to a cgroup storage into the bpf_get_local_storage(). Let's save a pointer to the corresponding bpf_cgroup_storage structure, instead of a pointer to the actual buffer. It will help us to handle per-cpu storage later, which has a different way of accessing to the actual data. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index e9871b012dac..7e0c9a1d48b7 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,7 +23,8 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -115,15 +116,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { enum bpf_cgroup_storage_type stype; - struct bpf_storage_buffer *buf; - - for_each_cgroup_storage_type(stype) { - if (!storage[stype]) - continue; - buf = READ_ONCE(storage[stype]->buf); - this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]); - } + for_each_cgroup_storage_type(stype) + this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); } struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, -- cgit v1.2.3 From b741f1630346defcbc8cc60f1a2bdae8b3b0036f Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:43 +0000 Subject: bpf: introduce per-cpu cgroup local storage This commit introduced per-cpu cgroup local storage. Per-cpu cgroup local storage is very similar to simple cgroup storage (let's call it shared), except all the data is per-cpu. The main goal of per-cpu variant is to implement super fast counters (e.g. packet counters), which don't require neither lookups, neither atomic operations. >From userspace's point of view, accessing a per-cpu cgroup storage is similar to other per-cpu map types (e.g. per-cpu hashmaps and arrays). Writing to a per-cpu cgroup storage is not atomic, but is performed by copying longs, so some minimal atomicity is here, exactly as with other per-cpu maps. Signed-off-by: Roman Gushchin Cc: Daniel Borkmann Cc: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 20 +++++++++++++++++++- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7e0c9a1d48b7..588dd5f0bd85 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -37,7 +37,10 @@ struct bpf_storage_buffer { }; struct bpf_cgroup_storage { - struct bpf_storage_buffer *buf; + union { + struct bpf_storage_buffer *buf; + void __percpu *percpu_buf; + }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; struct list_head list; @@ -109,6 +112,9 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { + if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) + return BPF_CGROUP_STORAGE_PERCPU; + return BPF_CGROUP_STORAGE_SHARED; } @@ -131,6 +137,10 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); void bpf_cgroup_storage_release(struct bpf_prog *prog, 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, + void *value, u64 flags); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -285,6 +295,14 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} +static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, + void *value) { + return 0; +} +static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, + void *key, void *value, u64 flags) { + return 0; +} #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b457fbe7b70b..018299a595c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -274,6 +274,7 @@ struct bpf_prog_offload { enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, + BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index c9bd6fb765b0..5432f4c9f50e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -43,6 +43,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) #endif #ifdef CONFIG_CGROUP_BPF BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, cgroup_storage_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops) -- cgit v1.2.3 From c6d4381220a0087ce19dbf6984d92c451bd6b364 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Sep 2018 19:27:24 -0400 Subject: dma-mapping: make the get_required_mask method available unconditionally This save some duplication for ia64, and makes the interface more general. In the long run we want each dma_map_ops instance to fill this out, but this will take a little more prep work. Signed-off-by: Christoph Hellwig Acked-by: Benjamin Herrenschmidt --- include/linux/dma-mapping.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index d23fc45c8208..562af6b45f23 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -130,9 +130,7 @@ struct dma_map_ops { enum dma_data_direction direction); int (*mapping_error)(struct device *dev, dma_addr_t dma_addr); int (*dma_supported)(struct device *dev, u64 mask); -#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK u64 (*get_required_mask)(struct device *dev); -#endif }; extern const struct dma_map_ops dma_direct_ops; -- cgit v1.2.3 From a20bb058375147cb639c7aa17ef86ad68b32d847 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Sep 2018 13:26:13 +0200 Subject: dma-direct: add an explicit dma_direct_get_required_mask This is somewhat modelled after the powerpc version, and differs from the legacy fallback in use fls64 instead of pointlessly splitting up the address into low and high dwords and in that it takes (__)phys_to_dma into account. Signed-off-by: Christoph Hellwig Acked-by: Benjamin Herrenschmidt Reviewed-by: Robin Murphy --- 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 86a59ba5a7f3..b79496d8c75b 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -55,6 +55,7 @@ static inline void dma_mark_clean(void *addr, size_t size) } #endif /* CONFIG_ARCH_HAS_DMA_MARK_CLEAN */ +u64 dma_direct_get_required_mask(struct device *dev); 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 b4ebe6063204da58e48600b810a97c29ae9e5d12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Sep 2018 14:04:08 +0200 Subject: dma-direct: implement complete bus_dma_mask handling Instead of rejecting devices with a too small bus_dma_mask we can handle by taking the bus dma_mask into account for allocations and bounce buffering decisions. Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index b79496d8c75b..fbca184ff5a0 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -27,7 +27,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) if (!dev->dma_mask) return false; - return addr + size - 1 <= *dev->dma_mask; + return addr + size - 1 <= + min_not_zero(*dev->dma_mask, dev->bus_dma_mask); } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ -- cgit v1.2.3 From 4d8fcf216c90bc25e34ae2200aa8985ee3158898 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Wed, 5 Sep 2018 11:43:23 +0300 Subject: net/mlx5e: Avoid unbounded peer devices when unpairing TC hairpin rules If the peer device was already unbound, then do not attempt to modify it's resources, otherwise we will crash on dereferencing non-existing device. Fixes: 5c65c564c962 ("net/mlx5e: Support offloading TC NIC hairpin flows") Signed-off-by: Alaa Hleihel Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/transobj.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h index 83a33a1873a6..7f5ca2cd3a32 100644 --- a/include/linux/mlx5/transobj.h +++ b/include/linux/mlx5/transobj.h @@ -90,6 +90,8 @@ struct mlx5_hairpin { u32 *rqn; u32 *sqn; + + bool peer_gone; }; struct mlx5_hairpin * -- cgit v1.2.3 From 59c9d35ea9cd73c3a55642ec9a0097770baccb93 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Wed, 5 Sep 2018 17:06:37 +0300 Subject: net/mlx5: Cache the system image guid The system image guid is a read-only field which is used by the TC offloads code to determine if two mlx5 devices belong to the same ASIC while adding flows. Read this once and save it on the core device rather than querying each time an offloaded flow is added. Signed-off-by: Alaa Hleihel Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/vport.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ed73b51f6697..26a92462f4ce 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -838,6 +838,7 @@ struct mlx5_core_dev { u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; } caps; + u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; enum mlx5_device_state state; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 7e7c6dfcfb09..9c694808c212 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -121,4 +121,6 @@ int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status); int mlx5_nic_vport_affiliate_multiport(struct mlx5_core_dev *master_mdev, struct mlx5_core_dev *port_mdev); int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev); + +u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From 783f4a4408e1251d17f333ad56abac24dde988b9 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 27 Sep 2018 16:58:54 -0700 Subject: nvme: call nvme_complete_rq when nvmf_check_ready fails for mpath I/O When an io is rejected by nvmf_check_ready() due to validation of the controller state, the nvmf_fail_nonready_command() will normally return BLK_STS_RESOURCE to requeue and retry. However, if the controller is dying or the I/O is marked for NVMe multipath, the I/O is failed so that the controller can terminate or so that the io can be issued on a different path. Unfortunately, as this reject point is before the transport has accepted the command, blk-mq ends up completing the I/O and never calls nvme_complete_rq(), which is where multipath may preserve or re-route the I/O. The end result is, the device user ends up seeing an EIO error. Example: single path connectivity, controller is under load, and a reset is induced. An I/O is received: a) while the reset state has been set but the queues have yet to be stopped; or b) after queues are started (at end of reset) but before the reconnect has completed. The I/O finishes with an EIO status. This patch makes the following changes: - Adds the HOST_PATH_ERROR pathing status from TP4028 - Modifies the reject point such that it appears to queue successfully, but actually completes the io with the new pathing status and calls nvme_complete_rq(). - nvme_complete_rq() recognizes the new status, avoids resetting the controller (likely was already done in order to get this new status), and calls the multipather to clear the current path that errored. This allows the next command (retry or new command) to select a new path if there is one. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 68e91ef5494c..818dbe9331be 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1241,6 +1241,7 @@ enum { NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_DNR = 0x4000, }; -- cgit v1.2.3 From 684bec1092b6991ff2a7751e8a763898576eb5c2 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Mon, 1 Oct 2018 15:55:22 -0700 Subject: Input: i8042 - enable keyboard wakeups by default when s2idle is used Previously, on typical consumer laptops, pressing a key on the keyboard when the system is in suspend would cause it to wake up (default or unconditional behaviour). This happens because the EC generates a SCI interrupt in this scenario. That is no longer true on modern laptops based on Intel WhiskeyLake, including Acer Swift SF314-55G, Asus UX333FA, Asus UX433FN and Asus UX533FD. We confirmed with Asus EC engineers that the "Modern Standby" design has been modified so that the EC no longer generates a SCI in this case; the keyboard controller itself should be used for wakeup. In order to retain the standard behaviour of being able to use the keyboard to wake up the system, enable serio wakeups by default on platforms that are using s2idle. Link: https://lkml.kernel.org/r/CAB4CAwfQ0mPMqCLp95TVjw4J0r5zKPWkSvvkK4cpZUGE--w8bQ@mail.gmail.com Reviewed-by: Rafael J. Wysocki Signed-off-by: Daniel Drake Signed-off-by: Dmitry Torokhov --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 440b62f7502e..206b735f383f 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -251,6 +251,7 @@ static inline bool idle_should_enter_s2idle(void) return unlikely(s2idle_state == S2IDLE_STATE_ENTER); } +extern bool pm_suspend_via_s2idle(void); extern void __init pm_states_init(void); extern void s2idle_set_ops(const struct platform_s2idle_ops *ops); extern void s2idle_wake(void); @@ -282,6 +283,7 @@ static inline void pm_set_suspend_via_firmware(void) {} static inline void pm_set_resume_via_firmware(void) {} static inline bool pm_suspend_via_firmware(void) { return false; } static inline bool pm_resume_via_firmware(void) { return false; } +static inline bool pm_suspend_via_s2idle(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } -- cgit v1.2.3 From b596d895fa2957e136a6b398b97b06bd42b51291 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Fri, 3 Aug 2018 13:05:11 -0700 Subject: PM / devfreq: Make update_devfreq() public Currently update_devfreq() is only visible to devfreq governors outside of devfreq.c. Make it public to allow drivers that adjust devfreq policies to cause a re-evaluation of the frequency after a policy change. Signed-off-by: Matthias Kaehlcke Reviewed-by: Brian Norris Reviewed-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 3aae5b3af87c..e4963b0f45da 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -198,6 +198,14 @@ extern void devm_devfreq_remove_device(struct device *dev, extern int devfreq_suspend_device(struct devfreq *devfreq); extern int devfreq_resume_device(struct devfreq *devfreq); +/** + * update_devfreq() - Reevaluate the device and configure frequency + * @devfreq: the devfreq device + * + * Note: devfreq->lock must be held + */ +extern int update_devfreq(struct devfreq *devfreq); + /* Helper functions for devfreq user device driver with OPP. */ extern struct dev_pm_opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq, u32 flags); -- cgit v1.2.3 From b31cdffa2329fe330cd304ca26c250dd1520fb0a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:09 +0200 Subject: net: phy: Move linkmode helpers to somewhere public phylink has some useful helpers to working with linkmode bitmaps. Move them to there own header so other code can use them. Signed-off-by: Andrew Lunn Acked-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/linkmode.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mii.h | 1 + include/linux/phy.h | 1 + 3 files changed, 69 insertions(+) create mode 100644 include/linux/linkmode.h (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h new file mode 100644 index 000000000000..014fb86c7114 --- /dev/null +++ b/include/linux/linkmode.h @@ -0,0 +1,67 @@ +#ifndef __LINKMODE_H +#define __LINKMODE_H + +#include +#include +#include + +static inline void linkmode_zero(unsigned long *dst) +{ + bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_copy(unsigned long *dst, const unsigned long *src) +{ + bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_and(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_and(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_or(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_or(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline bool linkmode_empty(const unsigned long *src) +{ + return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) +{ + __set_bit(nr, addr); +} + +static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) +{ + __clear_bit(nr, addr); +} + +static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) +{ + __change_bit(nr, addr); +} + +static inline int linkmode_test_bit(int nr, volatile unsigned long *addr) +{ + return test_bit(nr, addr); +} + +static inline int linkmode_equal(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +#endif /* __LINKMODE_H */ diff --git a/include/linux/mii.h b/include/linux/mii.h index 55000ee5c6ad..567047ef0309 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -10,6 +10,7 @@ #include +#include #include struct ethtool_cmd; diff --git a/include/linux/phy.h b/include/linux/phy.h index 192a1fa0c73b..d24cc46748e2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From ab2a605fa621ecf4ec26603a237822f7772cfa28 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:10 +0200 Subject: net: phy: Add phydev_warn() Not all new style LINK_MODE bits can be converted into old style SUPPORTED bits. We need to warn when such a conversion is attempted. Add a helper for this. Convert all pr_warn() calls to phydev_warn() where possible. Signed-off-by: Andrew Lunn Reviewed-by: Maxime Chevallier 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 d24cc46748e2..0ab9f89773fd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -968,6 +968,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_warn(_phydev, format, args...) \ + dev_warn(&_phydev->mdio.dev, format, ##args) + #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) -- cgit v1.2.3 From c4fabb8b3c0d724eb93dabaf346b0dd8a8be7118 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:11 +0200 Subject: net: phy: Add phydev_info() Add phydev_info() and make use of it within the phy drivers and core code. 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 0ab9f89773fd..0f6e7bf5e9c5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -968,6 +968,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_info(_phydev, format, args...) \ + dev_info(&_phydev->mdio.dev, format, ##args) + #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) -- cgit v1.2.3 From edc7ccbbcf32b97c7d26cd556f364eb4f22c4285 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:12 +0200 Subject: net: phy: Add helper to convert MII ADV register to a linkmode The phy_mii_ioctl can be used to write a value into the MII_ADVERTISE register in the PHY. Since this changes the state of the PHY, we need to make the same change to phydev->advertising. Add a helper which can convert the register value to a linkmode. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 567047ef0309..8c7da9473ad9 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -303,6 +303,37 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) return result | mii_adv_to_ethtool_adv_x(lpa); } +/** + * mii_adv_to_linkmode_adv_t + * @advertising:pointer to destination link mode. + * @adv: value of the MII_ADVERTISE register + * + * A small helper function that translates MII_ADVERTISE bits + * to linkmode advertisement settings. + */ +static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, + u32 adv) +{ + linkmode_zero(advertising); + + if (adv & ADVERTISE_10HALF) + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + advertising); + if (adv & ADVERTISE_10FULL) + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + advertising); + if (adv & ADVERTISE_100HALF) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + advertising); + if (adv & ADVERTISE_100FULL) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + advertising); + if (adv & ADVERTISE_PAUSE_CAP) + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising); + if (adv & ADVERTISE_PAUSE_ASYM) + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); +} + /** * mii_advertise_flowctrl - get flow control advertisement flags * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both) -- cgit v1.2.3 From 5f991f7bddc991ecc3c8a009ffd76fccff4661c7 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:13 +0200 Subject: net: phy: Add helper for advertise to lcl value Add a helper to convert the local advertising to an LCL capabilities, which is then used to resolve pause flow control settings. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 8c7da9473ad9..9ed49c8261d0 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -334,6 +334,25 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); } +/** + * ethtool_adv_to_lcl_adv_t + * @advertising:pointer to ethtool advertising + * + * A small helper function that translates ethtool advertising to LVL + * pause capabilities. + */ +static inline u32 ethtool_adv_to_lcl_adv_t(u32 advertising) +{ + u32 lcl_adv = 0; + + if (advertising & ADVERTISED_Pause) + lcl_adv |= ADVERTISE_PAUSE_CAP; + if (advertising & ADVERTISED_Asym_Pause) + lcl_adv |= ADVERTISE_PAUSE_ASYM; + + return lcl_adv; +} + /** * mii_advertise_flowctrl - get flow control advertisement flags * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both) -- cgit v1.2.3 From f954a04ea18ebfcba1cd2756eaee59eb4978a20e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:14 +0200 Subject: net: phy: Add limkmode equivalents to some of the MII ethtool helpers Add helpers which take a linkmode rather than a u32 ethtool for advertising settings. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 9ed49c8261d0..2da85b02e1c0 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -132,6 +132,34 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv) return result; } +/** + * linkmode_adv_to_mii_adv_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * MII_ADVERTISE register. + */ +static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, advertising)) + result |= ADVERTISE_10HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, advertising)) + result |= ADVERTISE_10FULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, advertising)) + result |= ADVERTISE_100HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, advertising)) + result |= ADVERTISE_100FULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) + result |= ADVERTISE_PAUSE_CAP; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) + result |= ADVERTISE_PAUSE_ASYM; + + return result; +} + /** * mii_adv_to_ethtool_adv_t * @adv: value of the MII_ADVERTISE register @@ -179,6 +207,28 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) return result; } +/** + * linkmode_adv_to_mii_ctrl1000_t + * advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * MII_CTRL1000 register when in 1000T mode. + */ +static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + advertising)) + result |= ADVERTISE_1000HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + advertising)) + result |= ADVERTISE_1000FULL; + + return result; +} + /** * mii_ctrl1000_to_ethtool_adv_t * @adv: value of the MII_CTRL1000 register -- cgit v1.2.3 From 719655a149715f26fc4de904fe0aa83068bd5b9e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:16 +0200 Subject: net: phy: Replace phy driver features u32 with link_mode bitmap This is one step in allowing phylib to make use of link_mode bitmaps, instead of u32 for supported and advertised features. Convert the phy drivers to use bitmaps to indicates the features they support. Build bitmap equivalents of the u32 values at runtime, and have the drivers point to the appropriate bitmap. These bitmaps are shared, and we don't want a driver to modify them. So mark them __ro_after_init. Within phylib, the features bitmap is currently turned back into a u32. This will be removed once the whole of phylib, and the drivers are converted to use bitmaps. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/linkmode.h | 9 +++++++++ include/linux/phy.h | 24 ++++++++++++++++-------- 2 files changed, 25 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 014fb86c7114..22443d7fb5cd 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,6 +43,15 @@ static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) __set_bit(nr, addr); } +static inline void linkmode_set_bit_array(const int *array, int array_size, + unsigned long *addr) +{ + int i; + + for (i = 0; i < array_size; i++) + linkmode_set_bit(array[i], addr); +} + static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) { __clear_bit(nr, addr); diff --git a/include/linux/phy.h b/include/linux/phy.h index 0f6e7bf5e9c5..dff51dd36e52 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -42,13 +42,21 @@ #define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ SUPPORTED_1000baseT_Full) -#define PHY_BASIC_FEATURES (PHY_10BT_FEATURES | \ - PHY_100BT_FEATURES | \ - PHY_DEFAULT_FEATURES) - -#define PHY_GBIT_FEATURES (PHY_BASIC_FEATURES | \ - PHY_1000BT_FEATURES) - +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; + +#define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) +#define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) +#define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) +#define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) +#define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) +#define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) +#define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) /* * Set phydev->irq to PHY_POLL if interrupts are not supported, @@ -510,7 +518,7 @@ struct phy_driver { u32 phy_id; char *name; u32 phy_id_mask; - u32 features; + const unsigned long * const features; u32 flags; const void *driver_data; -- cgit v1.2.3 From 9f2959b6b52d43326b2f6a0e0d7ffe6f4fc3b5ca Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 28 Sep 2018 08:51:09 +0200 Subject: net: phy: improve handling delayed work Using mod_delayed_work() allows to simplify handling delayed work and removes the need for the sync parameter in phy_trigger_machine(). Also introduce a helper phy_queue_state_machine() to encapsulate the low-level delayed work calls. No functional change intended. Signed-off-by: Heiner Kallweit 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 dff51dd36e52..3ea87f774a76 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1054,7 +1054,7 @@ void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -void phy_trigger_machine(struct phy_device *phydev, bool sync); +void phy_trigger_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); -- cgit v1.2.3 From efaffc5e40aeced0bcb497ed7a0a5b8c14abfcdf Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 1 Oct 2018 11:05:24 +0100 Subject: mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration Rate limiting of page migrations due to automatic NUMA balancing was introduced to mitigate the worst-case scenario of migrating at high frequency due to false sharing or slowly ping-ponging between nodes. Since then, a lot of effort was spent on correctly identifying these pages and avoiding unnecessary migrations and the safety net may no longer be required. Jirka Hladky reported a regression in 4.17 due to a scheduler patch that avoids spreading STREAM tasks wide prematurely. However, once the task was properly placed, it delayed migrating the memory due to rate limiting. Increasing the limit fixed the problem for him. Currently, the limit is hard-coded and does not account for the real capabilities of the hardware. Even if an estimate was attempted, it would not properly account for the number of memory controllers and it could not account for the amount of bandwidth used for normal accesses. Rather than fudging, this patch simply eliminates the rate limiting. However, Jirka reports that a STREAM configuration using multiple processes achieved similar performance to 4.16. In local tests, this patch improved performance of STREAM relative to the baseline but it is somewhat machine-dependent. Most workloads show little or not performance difference implying that there is not a heavily reliance on the throttling mechanism and it is safe to remove. STREAM on 2-socket machine 4.19.0-rc5 4.19.0-rc5 numab-v1r1 noratelimit-v1r1 MB/sec copy 43298.52 ( 0.00%) 44673.38 ( 3.18%) MB/sec scale 30115.06 ( 0.00%) 31293.06 ( 3.91%) MB/sec add 32825.12 ( 0.00%) 34883.62 ( 6.27%) MB/sec triad 32549.52 ( 0.00%) 34906.60 ( 7.24% Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Acked-by: Peter Zijlstra Cc: Jirka Hladky Cc: Linus Torvalds Cc: Linux-MM Cc: Srikar Dronamraju Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181001100525.29789-2-mgorman@techsingularity.net Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1e22d96734e0..3f4c0b167333 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -671,12 +671,6 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA_BALANCING /* Lock serializing the migrate rate limiting window */ spinlock_t numabalancing_migrate_lock; - - /* Rate limiting time interval */ - unsigned long numabalancing_migrate_next_window; - - /* Number of pages migrated during the rate limiting time interval */ - unsigned long numabalancing_migrate_nr_pages; #endif /* * This is a per-node reserve of pages that are not available -- cgit v1.2.3 From 11e37d357f6ba7a9af850a872396082cc0a0001f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Jul 2018 13:38:54 +0100 Subject: irqchip/gic-v3-its: Move pending table allocation to init time Pending tables for the redistributors are currently allocated one at a time as each CPU boots. This is causing some grief for Linux/RT (allocation from within a CPU hotplug notifier is frown upon). Let's move this allocation to take place at init time, when we only have a single CPU. It means we're allocating memory for CPUs that are not online yet, but most system will boot all of their CPUs anyway, so that's not completely wasted. Tested-by: Jeremy Linton Tested-by: Bhupesh Sharma Tested-by: Lei Zhang Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 8bdbb5f29494..266093e845bb 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -585,6 +585,7 @@ struct rdists { void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; + bool lpi_enabled; } __percpu *rdist; struct page *prop_page; u64 flags; -- cgit v1.2.3 From e1a2e2010ba9d3c765b2e37a7ae8b332564716f1 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Jul 2018 14:36:00 +0100 Subject: irqchip/gic-v3-its: Keep track of property table's PA and VA We're currently only tracking the page allocated to contain the property table by its struct page. In the future, it is going to be convenient to track both PA and VA for that page instead. Let's do that. Tested-by: Jeremy Linton Tested-by: Bhupesh Sharma Tested-by: Lei Zhang Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 266093e845bb..c2a7b863fc2e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -587,7 +587,8 @@ struct rdists { phys_addr_t phys_base; bool lpi_enabled; } __percpu *rdist; - struct page *prop_page; + phys_addr_t prop_table_pa; + void *prop_table_va; u64 flags; u32 gicd_typer; bool has_vlpis; -- cgit v1.2.3 From 1f83515bebc236d2acda59976a8e852f1a6d50b7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 1 Oct 2018 16:13:45 +0200 Subject: genirq/msi: Allow creation of a tree-based irqdomain for platform-msi platform_msi_create_device_domain() always creates a revmap-based irqdomain, which has the drawback of requiring the number of MSIs that can be allocated ahead of time. This is not always possible, and we sometimes need to use a tree-based irqdomain instead. Add a new platform_msi_create_device_tree_domain() helper to that effect. Reported-by: Miquel Raynal Signed-off-by: Marc Zyngier Signed-off-by: Miquel Raynal Signed-off-by: Marc Zyngier --- include/linux/msi.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 5839d8062dfc..0e9c50052ff3 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -317,11 +317,18 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, int virq, int nvec, msi_alloc_info_t *args); struct irq_domain * -platform_msi_create_device_domain(struct device *dev, - unsigned int nvec, - irq_write_msi_msg_t write_msi_msg, - const struct irq_domain_ops *ops, - void *host_data); +__platform_msi_create_device_domain(struct device *dev, + unsigned int nvec, + bool is_tree, + irq_write_msi_msg_t write_msi_msg, + const struct irq_domain_ops *ops, + void *host_data); + +#define platform_msi_create_device_domain(dev, nvec, write, ops, data) \ + __platform_msi_create_device_domain(dev, nvec, false, write, ops, data) +#define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ + __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) + int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, -- cgit v1.2.3 From 61ce8d8d8a8168a714de80fc31b3d6ac160fc5b0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 1 Oct 2018 16:13:51 +0200 Subject: irqchip/irq-mvebu-sei: Add new driver for Marvell SEI This is a cascaded interrupt controller in the AP806 GIC that collapses SEIs (System Error Interrupt) coming from the AP and the CPs (through the ICU). The SEI handles up to 64 interrupts. The first 21 interrupts are wired from the AP. The next 43 interrupts are from the CPs and are triggered through MSI messages. To handle this complexity, the driver has to declare to the upper layer: one IRQ domain for the wired interrupts, one IRQ domain for the MSIs; and acts as a MSI controller ('parent') by declaring an MSI domain. Suggested-by: Haim Boot Suggested-by: Marc Zyngier Signed-off-by: Miquel Raynal Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index dccfa65aee96..068aa46f0d55 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -75,6 +75,7 @@ struct irq_fwspec { enum irq_domain_bus_token { DOMAIN_BUS_ANY = 0, DOMAIN_BUS_WIRED, + DOMAIN_BUS_GENERIC_MSI, DOMAIN_BUS_PCI_MSI, DOMAIN_BUS_PLATFORM_MSI, DOMAIN_BUS_NEXUS, -- cgit v1.2.3 From 9524d6b265f9b2b9a61fceb2ee2ce1c2a83e39ca Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 11 Sep 2018 16:40:20 -0700 Subject: dmaengine: ep93xx: Return proper enum in ep93xx_dma_chan_direction Clang warns when implicitly converting from one enumerated type to another. Avoid this by using the equivalent value from the expected type. In file included from drivers/dma/ep93xx_dma.c:30: ./include/linux/platform_data/dma-ep93xx.h:88:10: warning: implicit conversion from enumeration type 'enum dma_data_direction' to different enumeration type 'enum dma_transfer_direction' [-Wenum-conversion] return DMA_NONE; ~~~~~~ ^~~~~~~~ 1 warning generated. Reported-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-ep93xx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-ep93xx.h b/include/linux/platform_data/dma-ep93xx.h index f8f1f6b952a6..eb9805bb3fe8 100644 --- a/include/linux/platform_data/dma-ep93xx.h +++ b/include/linux/platform_data/dma-ep93xx.h @@ -85,7 +85,7 @@ static inline enum dma_transfer_direction ep93xx_dma_chan_direction(struct dma_chan *chan) { if (!ep93xx_dma_chan_is_m2p(chan)) - return DMA_NONE; + return DMA_TRANS_NONE; /* even channels are for TX, odd for RX */ return (chan->chan_id % 2 == 0) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; -- cgit v1.2.3 From cc16567e5a8a7bb9439ef61ab80069acdd33f76f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Oct 2018 11:03:40 +0200 Subject: net: drop unused skb_append_datato_frags() This helper is unused since commit 988cf74deb45 ("inet: Stop generating UFO packets.") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 87e29710373f..119d092c6b13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1082,11 +1082,6 @@ static inline int skb_pad(struct sk_buff *skb, int pad) } #define dev_kfree_skb(a) consume_skb(a) -int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, - int getfrag(void *from, char *to, int offset, - int len, int odd, struct sk_buff *skb), - void *from, int length); - int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size); -- cgit v1.2.3 From 5bf0961cc6a180c077793f2615a8fd842c655876 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 2 Oct 2018 06:16:11 -0700 Subject: qed: Add driver support for 20G link speed. Add driver support for configuring/reading the 20G link speed. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8cd34645e892..dee3c9c744f7 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -670,10 +670,11 @@ enum qed_link_mode_bits { QED_LM_1000baseT_Half_BIT = BIT(4), QED_LM_1000baseT_Full_BIT = BIT(5), QED_LM_10000baseKR_Full_BIT = BIT(6), - QED_LM_25000baseKR_Full_BIT = BIT(7), - QED_LM_40000baseLR4_Full_BIT = BIT(8), - QED_LM_50000baseKR2_Full_BIT = BIT(9), - QED_LM_100000baseKR4_Full_BIT = BIT(10), + 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_COUNT = 11 }; -- cgit v1.2.3 From c550f01c810f2197c98e6e3103f81797f5e063be Mon Sep 17 00:00:00 2001 From: Steve Sakoman Date: Thu, 20 Sep 2018 09:20:34 -1000 Subject: serial:serial_core: Allow use of CTS for PPS line discipline Add a "pps_4wire" file to serial ports in sysfs in case the kernel is configured with CONFIG_PPS_CLIENT_LDISC. Writing 1 to the file enables the use of CTS instead of DCD for PPS signal input. This is necessary in case a serial port is not completely wired. Though this affects PPS processing the patch is against the serial core as the source of the serial port PPS event dispatching has to be modified. Furthermore it should be possible to modify the source of serial port PPS event dispatching before changing the line discipline. Signed-off-by: Andreas Steinmetz Signed-off-by: Steve Sakoman Tested-by: Steve Sakoman Tested-by: Eric Gallimore 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 406edae44ca3..079793e5d3fa 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -255,7 +255,8 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char unused[2]; + unsigned char pps_4wire; /* CTS instead of DCD */ + unsigned char unused; 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 ad8c0eaa0a418ae8ef3f9217638bb86439399eac Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Wed, 26 Sep 2018 14:58:47 +0200 Subject: tty/serial_core: add ISO7816 infrastructure Add the ISO7816 ioctl and associated accessors and data structure. Drivers can then use this common implementation to handle ISO7816 (smart cards). Signed-off-by: Nicolas Ferre [ludovic.desroches@microchip.com: squash and rebase, removal of gpios, checkpatch fixes] Signed-off-by: Ludovic Desroches Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 079793e5d3fa..4e2ba4894dcc 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -144,6 +144,8 @@ struct uart_port { void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct serial_rs485 *rs485); + int (*iso7816_config)(struct uart_port *, + struct serial_iso7816 *iso7816); unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ @@ -261,6 +263,7 @@ 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 serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; -- cgit v1.2.3 From f0157160b359b1d263ee9d4e0a435a7ad85bbcea Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 20 Sep 2018 10:27:17 -0600 Subject: PCI: Make link active reporting detection generic The spec has timing requirements when waiting for a link to become active after a conventional reset. Implement those hard delays when waiting for an active link so pciehp and dpc drivers don't need to duplicate this. For devices that don't support data link layer active reporting, wait the fixed time recommended by the PCIe spec. Signed-off-by: Keith Busch [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Reviewed-by: Sinan Kaya --- 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 6925828f9f25..896b42032ec5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -402,6 +402,7 @@ struct pci_dev { unsigned int has_secondary_link:1; unsigned int non_compliant_bars:1; /* Broken BARs; ignore them */ unsigned int is_probed:1; /* Device probing in progress */ + unsigned int link_active_reporting:1;/* Device capable of reporting link active */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From 5f5e4890d57a8af5da72c9d73a4efa9bad43a7a3 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 27 Sep 2018 16:57:05 -0500 Subject: ACPI / property: Allow multiple property compatible _DSD entries It is possible to have _DSD entries where the data is compatible with device properties format but are using different GUID for various reasons. In addition to that there can be many such _DSD entries for a single device such as for PCIe root port used to host a Thunderbolt hierarchy: Scope (\_SB.PCI0.RP21) { Name (_DSD, Package () { ToUUID ("6211e2c0-58a3-4af3-90e1-927a4e0c55a4"), Package () { Package () {"HotPlugSupportInD3", 1} }, ToUUID ("efcc06cc-73ac-4bc3-bff0-76143807c389"), Package () { Package () {"ExternalFacingPort", 1}, Package () {"UID", 0 } } }) } More information about these new _DSD entries can be found in: https://docs.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports To make these available for drivers via unified device property APIs, modify ACPI property core so that it supports multiple _DSD entries organized in a linked list. We also store GUID of each _DSD entry in struct acpi_device_properties in case there is need to differentiate between entries. The supported GUIDs are then listed in prp_guids array. Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Sakari Ailus --- include/linux/acpi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index de8d3d3fa651..51e3c29663fe 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1074,6 +1074,15 @@ static inline int acpi_node_get_property_reference( NR_FWNODE_REFERENCE_ARGS, args); } +static inline bool acpi_dev_has_props(const struct acpi_device *adev) +{ + return !list_empty(&adev->data.properties); +} + +struct acpi_device_properties * +acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, + const union acpi_object *properties); + int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); int acpi_dev_prop_read_single(struct acpi_device *adev, -- cgit v1.2.3 From 10653022456dc77b398777fd8e95126c77954b49 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Aug 2018 14:54:03 +0200 Subject: Revert "serial: sh-sci: Remove SCIx_RZ_SCIFA_REGTYPE" This reverts commit 7acece71a517cad83a0842a94d94c13f271b680c. Signed-off-by: Geert Uytterhoeven Acked-by: Chris Brandt Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_sci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index c0e795d95477..1c89611e0e06 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -36,6 +36,7 @@ enum { SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, + SCIx_RZ_SCIFA_REGTYPE, SCIx_NR_REGTYPES, }; -- cgit v1.2.3 From fd3b339cbb6047dacfa7ccc81c846efcb61032a9 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 1 Oct 2018 12:31:21 +0300 Subject: thunderbolt: Convert rest of the driver files to use SPDX identifier This gets rid of the licence boilerplate duplicated in each file. While there fix doubled space in domain.c author line. No functional changes intended. Signed-off-by: Mika Westerberg Acked-by: Yehezkel Bernat Signed-off-by: Greg Kroah-Hartman --- include/linux/thunderbolt.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index a3ed26082bc1..bf6ec83e60ee 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Thunderbolt service API * @@ -5,10 +6,6 @@ * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * 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. */ #ifndef THUNDERBOLT_H_ -- cgit v1.2.3 From f3709f69b7c5cba6323cc03c29b64293b93be817 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:29 -0700 Subject: bpf: Add iterator for spilled registers Add this iterator for spilled registers, it concentrates the details of how to get the current frame's spilled registers into a single macro while clarifying the intention of the code which is calling the macro. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b42b60a83e19..d0e7f97e8b60 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -131,6 +131,17 @@ struct bpf_verifier_state { u32 curframe; }; +#define bpf_get_spilled_reg(slot, frame) \ + (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ + (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ? &frame->stack[slot].spilled_ptr : NULL) + +/* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ +#define bpf_for_each_spilled_reg(iter, frame, reg) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ + iter < frame->allocated_stack / BPF_REG_SIZE; \ + iter++, reg = bpf_get_spilled_reg(iter, frame)) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; -- cgit v1.2.3 From c64b7983288e636356f7f5f652de4813e1cfedac Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:33 -0700 Subject: bpf: Add PTR_TO_SOCKET verifier type Teach the verifier a little bit about a new type of pointer, a PTR_TO_SOCKET. This pointer type is accessed from BPF through the 'struct bpf_sock' structure. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/bpf_verifier.h | 2 ++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 018299a595c8..027697b6a22f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -154,6 +154,7 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ + ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */ }; /* type of values returned from helper functions */ @@ -162,6 +163,7 @@ enum bpf_return_type { RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ + RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -213,6 +215,8 @@ enum bpf_reg_type { PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ + PTR_TO_SOCKET, /* reg points to struct bpf_sock */ + PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -343,6 +347,11 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); +typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, + const struct bpf_insn *src, + struct bpf_insn *dst, + struct bpf_prog *prog, + u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); @@ -836,4 +845,29 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +#if defined(CONFIG_NET) +bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); +u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); +#else +static inline bool bpf_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} +static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} +#endif + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d0e7f97e8b60..a411363098a5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -58,6 +58,8 @@ 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_SOCKET this is used to share which pointers retain the + * same reference to the socket, to determine proper reference freeing. */ u32 id; /* For scalar types (SCALAR_VALUE), this represents our knowledge of -- cgit v1.2.3 From fd978bf7fd312581a7ca454a991f0ffb34c4204b Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:35 -0700 Subject: bpf: Add reference tracking to verifier Allow helper functions to acquire a reference and return it into a register. Specific pointer types such as the PTR_TO_SOCKET will implicitly represent such a reference. The verifier must ensure that these references are released exactly once in each path through the program. To achieve this, this commit assigns an id to the pointer and tracks it in the 'bpf_func_state', then when the function or program exits, verifies that all of the acquired references have been freed. When the pointer is passed to a function that frees the reference, it is removed from the 'bpf_func_state` and all existing copies of the pointer in registers are marked invalid. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a411363098a5..7b6fd2ab3263 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -104,6 +104,17 @@ struct bpf_stack_state { u8 slot_type[BPF_REG_SIZE]; }; +struct bpf_reference_state { + /* Track each reference created with a unique id, even if the same + * instruction creates the reference multiple times (eg, via CALL). + */ + int id; + /* Instruction where the allocation of this reference occurred. This + * is used purely to inform the user of a reference leak. + */ + int insn_idx; +}; + /* state of the program: * type of all registers and stack info */ @@ -121,7 +132,9 @@ struct bpf_func_state { */ u32 subprogno; - /* should be second to last. See copy_func_state() */ + /* The following fields should be last. See copy_func_state() */ + int acquired_refs; + struct bpf_reference_state *refs; int allocated_stack; struct bpf_stack_state *stack; }; @@ -217,11 +230,16 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); -static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; - return cur->frame[cur->curframe]->regs; + return cur->frame[cur->curframe]; +} + +static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +{ + return cur_func(env)->regs; } int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); -- cgit v1.2.3 From 401b25aa1a75e7fe4e3202a6336604269697d705 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Tue, 2 Oct 2018 22:20:50 -0400 Subject: ext4: convert fault handler to use vm_fault_t type Return type of ext4_page_mkwrite and ext4_filemap_fault are changed to use vm_fault_t type. With this patch all the callers of block_page_mkwrite_return() are changed to handle vm_fault_t. So converting the return type of block_page_mkwrite_return() to vm_fault_t. Signed-off-by: Souptick Joarder Signed-off-by: Theodore Ts'o Reviewed-by: Matthew Wilcox --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 96225a77c112..7b73ef7f902d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -242,7 +242,7 @@ int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ -static inline int block_page_mkwrite_return(int err) +static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; -- cgit v1.2.3 From f3edc2dbe0ad0bbbd8450cd37328f99acf215fd8 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Mon, 1 Oct 2018 17:02:43 +0100 Subject: net: usbnet: make driver_info const The driver_info field that is used for describing each of the usb-net drivers using the usbnet.c core all declare their information as const and the usbnet.c itself does not try and modify the struct. It is therefore a good idea to make this const in the usbnet.c structure in case anyone tries to modify it. Signed-off-by: Ben Dooks Signed-off-by: Ben Dooks Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index e2ec3582e549..d8860f2d0976 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -28,7 +28,7 @@ struct usbnet { /* housekeeping */ struct usb_device *udev; struct usb_interface *intf; - struct driver_info *driver_info; + const struct driver_info *driver_info; const char *driver_name; void *driver_priv; wait_queue_head_t wait; -- cgit v1.2.3 From 47bd59e538d4e7b3ad9c18bef5c1052657bdff59 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:13 +0200 Subject: mtd: rawnand: plat_nand: Pass a nand_chip object to all platform_nand_ctrl hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. In order to do that, we first need to update the platform_nand_ctrl hooks to take a nand_chip object instead of an mtd_info. We add temporary plat_nand_xxx() wrappers to the do the mtd -> chip conversion, but those will be dropped when patching nand_chip hooks to take a nand_chip object. Signed-off-by: Boris Brezillon Reviewed-by: Alexander Sverdlin Acked-by: Alexander Sverdlin Acked-by: Robert Jarzmik Acked-by: Krzysztof Halasa Acked-by: Paul Burton Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index d155470f53c8..818cdc0a4dbb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1595,11 +1595,11 @@ struct platform_device; struct platform_nand_ctrl { int (*probe)(struct platform_device *pdev); void (*remove)(struct platform_device *pdev); - int (*dev_ready)(struct mtd_info *mtd); - void (*select_chip)(struct mtd_info *mtd, int chip); - void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); - void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); - void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); + int (*dev_ready)(struct nand_chip *chip); + void (*select_chip)(struct nand_chip *chip, int cs); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); + void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); + void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void *priv; }; -- cgit v1.2.3 From 00ad378f304a091ab2e2df5f944892a6ed558610 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:14 +0200 Subject: mtd: rawnand: Pass a nand_chip object to nand_scan() Let's make the raw NAND API consistent by patching all helpers to take a nand_chip object instead of an mtd_info one. We start with nand_scan(). Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 818cdc0a4dbb..733b228d94a5 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -24,15 +24,16 @@ #include #include +struct nand_chip; struct nand_flash_dev; /* Scan and identify a NAND device */ -int nand_scan_with_ids(struct mtd_info *mtd, int max_chips, +int nand_scan_with_ids(struct nand_chip *chip, int max_chips, struct nand_flash_dev *ids); -static inline int nand_scan(struct mtd_info *mtd, int max_chips) +static inline int nand_scan(struct nand_chip *chip, int max_chips) { - return nand_scan_with_ids(mtd, max_chips, NULL); + return nand_scan_with_ids(chip, max_chips, NULL); } /* Internal helper for board drivers which need to override command function */ -- cgit v1.2.3 From 59ac276f22270fb2094910f9a734c17f41c25e70 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:15 +0200 Subject: mtd: rawnand: Pass a nand_chip object to nand_release() Let's make the raw NAND API consistent by patching all helpers to take a nand_chip object instead of an mtd_info one. Now is nand_release()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 733b228d94a5..e9c59f0624ad 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1739,7 +1739,7 @@ int nand_write_data_op(struct nand_chip *chip, const void *buf, */ void nand_cleanup(struct nand_chip *chip); /* Unregister the MTD device and calls nand_cleanup() */ -void nand_release(struct mtd_info *mtd); +void nand_release(struct nand_chip *chip); /* Default extended ID decoding function */ void nand_decode_ext_id(struct nand_chip *chip); -- cgit v1.2.3 From 2b356ab46ebe9b1bc63bda6708b81c9200382e78 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:16 +0200 Subject: mtd: rawnand: Pass a nand_chip object to nand_wait_ready() Let's make the raw NAND API consistent by patching all helpers to take a nand_chip object instead of an mtd_info one. Now is nand_wait_ready()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 e9c59f0624ad..55014e42912a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -37,7 +37,7 @@ static inline int nand_scan(struct nand_chip *chip, int max_chips) } /* Internal helper for board drivers which need to override command function */ -void nand_wait_ready(struct mtd_info *mtd); +void nand_wait_ready(struct nand_chip *chip); /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 -- cgit v1.2.3 From ec47636cd7e7b0dd53e526ec832ebb21b67ad9c6 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:17 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->hwctl() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one. Now is ecc->hwctl()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 55014e42912a..029fef900f33 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -647,7 +647,7 @@ struct nand_ecc_ctrl { void *priv; u8 *calc_buf; u8 *code_buf; - void (*hwctl)(struct mtd_info *mtd, int mode); + void (*hwctl)(struct nand_chip *chip, int mode); int (*calculate)(struct mtd_info *mtd, const uint8_t *dat, uint8_t *ecc_code); int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, -- cgit v1.2.3 From af37d2c3a8c7a05cf5b0fe6b61e2a6b9e357928b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:18 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->calculate() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one. Now is ecc->calculate()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/nand_bch.h | 5 +++-- include/linux/mtd/nand_ecc.h | 4 +++- include/linux/mtd/rawnand.h | 4 ++-- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand_bch.h b/include/linux/mtd/nand_bch.h index 98f20ef05d60..6db133508960 100644 --- a/include/linux/mtd/nand_bch.h +++ b/include/linux/mtd/nand_bch.h @@ -12,6 +12,7 @@ #define __MTD_NAND_BCH_H__ struct mtd_info; +struct nand_chip; struct nand_bch_control; #if defined(CONFIG_MTD_NAND_ECC_BCH) @@ -21,7 +22,7 @@ static inline int mtd_nand_has_bch(void) { return 1; } /* * Calculate BCH ecc code */ -int nand_bch_calculate_ecc(struct mtd_info *mtd, const u_char *dat, +int nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, u_char *ecc_code); /* @@ -43,7 +44,7 @@ void nand_bch_free(struct nand_bch_control *nbc); static inline int mtd_nand_has_bch(void) { return 0; } static inline int -nand_bch_calculate_ecc(struct mtd_info *mtd, const u_char *dat, +nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, u_char *ecc_code) { return -1; diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index 8a2decf7462c..a514e62ff54f 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -14,6 +14,7 @@ #define __MTD_NAND_ECC_H__ struct mtd_info; +struct nand_chip; /* * Calculate 3 byte ECC code for eccsize byte block @@ -24,7 +25,8 @@ void __nand_calculate_ecc(const u_char *dat, unsigned int eccsize, /* * Calculate 3 byte ECC code for 256/512 byte block */ -int nand_calculate_ecc(struct mtd_info *mtd, const u_char *dat, u_char *ecc_code); +int nand_calculate_ecc(struct nand_chip *chip, const u_char *dat, + u_char *ecc_code); /* * Detect and correct a 1 bit error for eccsize byte block diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 029fef900f33..b2f51b2fb110 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -648,8 +648,8 @@ struct nand_ecc_ctrl { u8 *calc_buf; u8 *code_buf; void (*hwctl)(struct nand_chip *chip, int mode); - int (*calculate)(struct mtd_info *mtd, const uint8_t *dat, - uint8_t *ecc_code); + int (*calculate)(struct nand_chip *chip, const uint8_t *dat, + uint8_t *ecc_code); int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, uint8_t *calc_ecc); int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From 00da2ea97229946450c8145d680db480b5da1f94 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:19 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->correct() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one. Now is ecc->correct()'s turn. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/nand_bch.h | 6 +++--- include/linux/mtd/nand_ecc.h | 4 ++-- include/linux/mtd/rawnand.h | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand_bch.h b/include/linux/mtd/nand_bch.h index 6db133508960..b8106651f807 100644 --- a/include/linux/mtd/nand_bch.h +++ b/include/linux/mtd/nand_bch.h @@ -28,8 +28,8 @@ int nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, /* * Detect and correct bit errors */ -int nand_bch_correct_data(struct mtd_info *mtd, u_char *dat, u_char *read_ecc, - u_char *calc_ecc); +int nand_bch_correct_data(struct nand_chip *chip, u_char *dat, + u_char *read_ecc, u_char *calc_ecc); /* * Initialize BCH encoder/decoder */ @@ -51,7 +51,7 @@ nand_bch_calculate_ecc(struct nand_chip *chip, const u_char *dat, } static inline int -nand_bch_correct_data(struct mtd_info *mtd, unsigned char *buf, +nand_bch_correct_data(struct nand_chip *chip, unsigned char *buf, unsigned char *read_ecc, unsigned char *calc_ecc) { return -ENOTSUPP; diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index a514e62ff54f..b81fecd5e719 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -13,7 +13,6 @@ #ifndef __MTD_NAND_ECC_H__ #define __MTD_NAND_ECC_H__ -struct mtd_info; struct nand_chip; /* @@ -37,6 +36,7 @@ int __nand_correct_data(u_char *dat, u_char *read_ecc, u_char *calc_ecc, /* * Detect and correct a 1 bit error for 256/512 byte block */ -int nand_correct_data(struct mtd_info *mtd, u_char *dat, u_char *read_ecc, u_char *calc_ecc); +int nand_correct_data(struct nand_chip *chip, u_char *dat, u_char *read_ecc, + u_char *calc_ecc); #endif /* __MTD_NAND_ECC_H__ */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index b2f51b2fb110..24434310d126 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -650,8 +650,8 @@ struct nand_ecc_ctrl { void (*hwctl)(struct nand_chip *chip, int mode); int (*calculate)(struct nand_chip *chip, const uint8_t *dat, uint8_t *ecc_code); - int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, - uint8_t *calc_ecc); + int (*correct)(struct nand_chip *chip, uint8_t *dat, uint8_t *read_ecc, + uint8_t *calc_ecc); int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page); int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From b976168757f7f4adf05215884e8557aaa9f6792c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:20 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->read_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all ecc->read_xxx() hooks at once. Signed-off-by: Boris Brezillon Acked-by: Stefan Agner Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 24434310d126..a5f4a585f749 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -652,14 +652,14 @@ struct nand_ecc_ctrl { uint8_t *ecc_code); int (*correct)(struct nand_chip *chip, uint8_t *dat, uint8_t *read_ecc, uint8_t *calc_ecc); - int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); + int (*read_page_raw)(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); - int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); - int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offs, uint32_t len, uint8_t *buf, int page); + int (*read_page)(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); + int (*read_subpage)(struct nand_chip *chip, uint32_t offs, + uint32_t len, uint8_t *buf, int page); int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offset, uint32_t data_len, const uint8_t *data_buf, int oob_required, int page); @@ -667,9 +667,8 @@ struct nand_ecc_ctrl { const uint8_t *buf, int oob_required, int page); int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, int page); - int (*read_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, - int page); - int (*read_oob)(struct mtd_info *mtd, struct nand_chip *chip, int page); + int (*read_oob_raw)(struct nand_chip *chip, int page); + int (*read_oob)(struct nand_chip *chip, int page); int (*write_oob)(struct mtd_info *mtd, struct nand_chip *chip, int page); }; @@ -1676,11 +1675,10 @@ int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int page); /* Default read_oob implementation */ -int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); +int nand_read_oob_std(struct nand_chip *chip, int page); /* Default read_oob syndrome implementation */ -int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, - int page); +int nand_read_oob_syndrome(struct nand_chip *chip, int page); /* Wrapper to use in order for controllers/vendors to GET/SET FEATURES */ int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param); @@ -1690,10 +1688,10 @@ int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip, int addr, u8 *subfeature_param); /* Default read_page_raw implementation */ -int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); -int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, - u8 *buf, int oob_required, int page); +int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, + int page); +int nand_read_page_raw_notsupp(struct nand_chip *chip, u8 *buf, + int oob_required, int page); /* Default write_page_raw implementation */ int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From 767eb6fbdedb7d8b9c7a87d640a8bc8091eba002 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:21 +0200 Subject: mtd: rawnand: Pass a nand_chip object to ecc->write_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all ecc->write_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index a5f4a585f749..527947e81447 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -654,23 +654,21 @@ struct nand_ecc_ctrl { uint8_t *calc_ecc); int (*read_page_raw)(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); - int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); + int (*write_page_raw)(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); int (*read_page)(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); int (*read_subpage)(struct nand_chip *chip, uint32_t offs, uint32_t len, uint8_t *buf, int page); - int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offset, uint32_t data_len, - const uint8_t *data_buf, int oob_required, int page); - int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); - int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, - int page); + int (*write_subpage)(struct nand_chip *chip, uint32_t offset, + uint32_t data_len, const uint8_t *data_buf, + int oob_required, int page); + int (*write_page)(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); + int (*write_oob_raw)(struct nand_chip *chip, int page); int (*read_oob_raw)(struct nand_chip *chip, int page); int (*read_oob)(struct nand_chip *chip, int page); - int (*write_oob)(struct mtd_info *mtd, struct nand_chip *chip, - int page); + int (*write_oob)(struct nand_chip *chip, int page); }; /** @@ -1668,11 +1666,10 @@ int nand_ecc_choose_conf(struct nand_chip *chip, const struct nand_ecc_caps *caps, int oobavail); /* Default write_oob implementation */ -int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); +int nand_write_oob_std(struct nand_chip *chip, int page); /* Default write_oob syndrome implementation */ -int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, - int page); +int nand_write_oob_syndrome(struct nand_chip *chip, int page); /* Default read_oob implementation */ int nand_read_oob_std(struct nand_chip *chip, int page); @@ -1694,10 +1691,10 @@ int nand_read_page_raw_notsupp(struct nand_chip *chip, u8 *buf, int oob_required, int page); /* Default write_page_raw implementation */ -int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); -int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip, - const u8 *buf, int oob_required, int page); +int nand_write_page_raw(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); +int nand_write_page_raw_notsupp(struct nand_chip *chip, const u8 *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 7e534323c416216e8ac45b5633fb0a5e5137e5b5 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:22 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->read_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all chip->read_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 527947e81447..f324a82fe6a2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1283,10 +1283,10 @@ struct nand_chip { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; - uint8_t (*read_byte)(struct mtd_info *mtd); + uint8_t (*read_byte)(struct nand_chip *chip); void (*write_byte)(struct mtd_info *mtd, uint8_t byte); void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); - void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); + void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct mtd_info *mtd, int chip); int (*block_bad)(struct mtd_info *mtd, loff_t ofs); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); -- cgit v1.2.3 From c0739d85723a381302907f9613392d7ac8515176 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:23 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->write_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all chip->write_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 f324a82fe6a2..cd94cb3b9c2e 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1284,8 +1284,8 @@ struct nand_chip { void __iomem *IO_ADDR_W; uint8_t (*read_byte)(struct nand_chip *chip); - void (*write_byte)(struct mtd_info *mtd, uint8_t byte); - void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); + void (*write_byte)(struct nand_chip *chip, uint8_t byte); + void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct mtd_info *mtd, int chip); int (*block_bad)(struct mtd_info *mtd, loff_t ofs); -- cgit v1.2.3 From 758b56f58b66bebc5bc2e0e180e1904aafa2b523 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:24 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->select_chip() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->select_chip() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 cd94cb3b9c2e..65a25e89b426 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1287,7 +1287,7 @@ struct nand_chip { void (*write_byte)(struct nand_chip *chip, uint8_t byte); void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); - void (*select_chip)(struct mtd_info *mtd, int chip); + void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct mtd_info *mtd, loff_t ofs); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); -- cgit v1.2.3 From c17556f545c0283f53561c8a38d5cd4e91a35fe5 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:25 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->block_xxx() hooks Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle all chip->block_xxx() hooks at once. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 65a25e89b426..0d8e2708e125 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1288,8 +1288,8 @@ struct nand_chip { void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct nand_chip *chip, int cs); - int (*block_bad)(struct mtd_info *mtd, loff_t ofs); - int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); + int (*block_bad)(struct nand_chip *chip, loff_t ofs); + int (*block_markbad)(struct nand_chip *chip, loff_t ofs); void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); int (*dev_ready)(struct mtd_info *mtd); void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, -- cgit v1.2.3 From 0f808c1602bc75c74399989d47842197118f7e72 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:26 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->cmd_ctrl() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->cmd_ctrl() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 0d8e2708e125..b53ccc7139c2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1290,7 +1290,7 @@ struct nand_chip { void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); - void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); int (*dev_ready)(struct mtd_info *mtd); void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, int page_addr); -- cgit v1.2.3 From 50a487e7719caa07e951dfcfd983b2c5517e2f76 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:27 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->dev_ready() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->dev_ready() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 b53ccc7139c2..404ac7d4b279 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1291,7 +1291,7 @@ struct nand_chip { int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); - int (*dev_ready)(struct mtd_info *mtd); + int (*dev_ready)(struct nand_chip *chip); void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, int page_addr); int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); -- cgit v1.2.3 From 5295cf2e047cf60ac1e14d4789cdf698af45cf2f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:28 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->cmdfunc() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->cmdfunc() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 404ac7d4b279..2a74de9012c4 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1292,7 +1292,7 @@ struct nand_chip { int (*block_markbad)(struct nand_chip *chip, loff_t ofs); void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); int (*dev_ready)(struct nand_chip *chip); - void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, + void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, int page_addr); int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); int (*exec_op)(struct nand_chip *chip, -- cgit v1.2.3 From f1d46942e823ffdd8532409c9b1c1f87314bf20f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:29 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->waitfunc() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->waitfunc() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 2a74de9012c4..c00e571d09ca 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1294,7 +1294,7 @@ struct nand_chip { int (*dev_ready)(struct nand_chip *chip); void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, int page_addr); - int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); + int (*waitfunc)(struct nand_chip *chip); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); -- cgit v1.2.3 From a2098a9e4f6704471c32230d48b905e51f0cba32 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:30 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->erase() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->erase() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 c00e571d09ca..8c8315d977de 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1298,7 +1298,7 @@ struct nand_chip { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); - int (*erase)(struct mtd_info *mtd, int page); + int (*erase)(struct nand_chip *chip, int page); int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From aa36ff25ffdea656c3b748a5cf141bc884e6275c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:31 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->{get, set}_features() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->{get,set}_features() hooks. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8c8315d977de..7c639070c512 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1299,10 +1299,10 @@ struct nand_chip { const struct nand_operation *op, bool check_only); int (*erase)(struct nand_chip *chip, int page); - int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip, - int feature_addr, uint8_t *subfeature_para); - int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip, - int feature_addr, uint8_t *subfeature_para); + int (*set_features)(struct nand_chip *chip, int feature_addr, + uint8_t *subfeature_para); + int (*get_features)(struct nand_chip *chip, int feature_addr, + uint8_t *subfeature_para); int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, const struct nand_data_interface *conf); @@ -1681,8 +1681,8 @@ int nand_read_oob_syndrome(struct nand_chip *chip, int page); int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param); int nand_set_features(struct nand_chip *chip, int addr, u8 *subfeature_param); /* Stub used by drivers that do not support GET/SET FEATURES operations */ -int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip, - int addr, u8 *subfeature_param); +int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, + u8 *subfeature_param); /* Default read_page_raw implementation */ int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, -- cgit v1.2.3 From 2e7f1cec271c209128d0535e0cc1c49d3cf03624 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:32 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->setup_read_retry() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->setup_read_retry() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 7c639070c512..14ce2b078206 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1303,7 +1303,7 @@ struct nand_chip { uint8_t *subfeature_para); int (*get_features)(struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); - int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); + int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, const struct nand_data_interface *conf); -- cgit v1.2.3 From 858838b87ef542c35b5401a6469d162d103d1d8f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:33 +0200 Subject: mtd: rawnand: Pass a nand_chip object to chip->setup_data_interface() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the chip->setup_data_interface() hook. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 14ce2b078206..5bfb9d543a8a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1304,7 +1304,7 @@ struct nand_chip { int (*get_features)(struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); - int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, + int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); int chip_delay; -- cgit v1.2.3 From 5740d4c4f9bbc97270993147b4756587f92d44c3 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:34 +0200 Subject: mtd: rawnand: Pass a nand_chip object to all nand_xxx_bbt() helpers Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the nand_xxx_bbt() helpers. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5bfb9d543a8a..e0d98ca7cb45 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1545,9 +1545,9 @@ extern const struct nand_manufacturer_ops amd_nand_manuf_ops; extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; int nand_create_bbt(struct nand_chip *chip); -int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); -int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); -int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); +int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); +int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); +int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, int allowbbt); -- cgit v1.2.3 From e4cdf9cb3254b5b4d9b1064c275d8c40f2d82e03 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 6 Sep 2018 14:05:35 +0200 Subject: mtd: rawnand: Pass a nand_chip object nand_erase_nand() Let's make the raw NAND API consistent by patching all helpers and hooks to take a nand_chip object instead of an mtd_info one or remove the mtd_info object when both are passed. Let's tackle the nand_erase_nand() helper. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 e0d98ca7cb45..e6360e1156e7 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1548,7 +1548,7 @@ int nand_create_bbt(struct nand_chip *chip); int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); -int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, +int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt); /** -- cgit v1.2.3 From 871a4073f438c61cc4cf7471476d9a8a29ccf620 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 4 Aug 2018 22:59:22 +0200 Subject: mtd: rawnand: Make maxchips an unsigned int There's no good reason to make maxchips a signed integer, since only positive values are valid. Make it an unsigned int. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 e6360e1156e7..e3a96ee7e531 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -28,10 +28,10 @@ struct nand_chip; struct nand_flash_dev; /* Scan and identify a NAND device */ -int nand_scan_with_ids(struct nand_chip *chip, int max_chips, +int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, struct nand_flash_dev *ids); -static inline int nand_scan(struct nand_chip *chip, int max_chips) +static inline int nand_scan(struct nand_chip *chip, unsigned int max_chips) { return nand_scan_with_ids(chip, max_chips, NULL); } -- cgit v1.2.3 From 82fc5099744e5f30cd8c9ee13075f28fb37e9518 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:34 +0200 Subject: mtd: rawnand: Create a legacy struct and move ->IO_ADDR_{R, W} there We regularly have new NAND controller drivers that are making use of fields/hooks that we want to get rid of but can't because of all the legacy drivers that we might break if we do. So, instead of removing those fields/hooks, let's move them to a sub-struct which is clearly documented as deprecated. We start with the ->IO_ADDR_{R,W] fields. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e3a96ee7e531..6b1dc8fef89d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1172,13 +1172,27 @@ int nand_op_parser_exec_op(struct nand_chip *chip, const struct nand_op_parser *parser, const struct nand_operation *op, bool check_only); +/** + * struct nand_legacy - NAND chip legacy fields/hooks + * @IO_ADDR_R: address to read the 8 I/O lines of the flash device + * @IO_ADDR_W: address to write the 8 I/O lines of the flash device + * + * If you look at this structure you're already wrong. These fields/hooks are + * all deprecated. + */ +struct nand_legacy { + void __iomem *IO_ADDR_R; + void __iomem *IO_ADDR_W; +}; + /** * struct nand_chip - NAND Private Flash Chip Data * @mtd: MTD device registered to the MTD framework - * @IO_ADDR_R: [BOARDSPECIFIC] address to read the 8 I/O lines of the - * flash device - * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the - * flash device. + * @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. * @read_byte: [REPLACEABLE] read one byte from the chip * @write_byte: [REPLACEABLE] write a single byte to the chip on the * low 8 I/O lines @@ -1280,8 +1294,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, struct nand_chip { struct mtd_info mtd; - void __iomem *IO_ADDR_R; - void __iomem *IO_ADDR_W; + + struct nand_legacy legacy; uint8_t (*read_byte)(struct nand_chip *chip); void (*write_byte)(struct nand_chip *chip, uint8_t byte); -- cgit v1.2.3 From 716bbbabcc68c2b0e1b805d369c0bd58f4fdea30 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:35 +0200 Subject: mtd: rawnand: Deprecate ->{read, write}_{byte, buf}() hooks All those hooks have been replaced by ->exec_op(). Move them to the nand_legacy struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 6b1dc8fef89d..f961efd2eacc 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1176,6 +1176,10 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * struct nand_legacy - NAND chip legacy fields/hooks * @IO_ADDR_R: address to read the 8 I/O lines of the flash device * @IO_ADDR_W: address to write the 8 I/O lines of the flash device + * @read_byte: read one byte from the chip + * @write_byte: write a single byte to the chip on the low 8 I/O lines + * @write_buf: write data from the buffer to the chip + * @read_buf: read data from the chip into the buffer * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1183,6 +1187,10 @@ int nand_op_parser_exec_op(struct nand_chip *chip, struct nand_legacy { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; + u8 (*read_byte)(struct nand_chip *chip); + void (*write_byte)(struct nand_chip *chip, u8 byte); + void (*write_buf)(struct nand_chip *chip, const u8 *buf, int len); + void (*read_buf)(struct nand_chip *chip, u8 *buf, int len); }; /** @@ -1193,11 +1201,6 @@ struct nand_legacy { * you're modifying an existing driver that is using those * fields/hooks, you should consider reworking the driver * avoid using them. - * @read_byte: [REPLACEABLE] read one byte from the chip - * @write_byte: [REPLACEABLE] write a single byte to the chip on the - * low 8 I/O lines - * @write_buf: [REPLACEABLE] write data from the buffer to the chip - * @read_buf: [REPLACEABLE] read data from the chip into the buffer * @select_chip: [REPLACEABLE] select chip nr * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers * @block_markbad: [REPLACEABLE] mark a block bad @@ -1213,8 +1216,8 @@ struct nand_legacy { * ready. * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), - * ->{read,write}_{buf,byte,word}(), ->dev_ready() and - * ->waifunc(). + * ->legacy.{read,write}_{buf,byte,word}(), ->dev_ready() + * and ->waifunc(). * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure @@ -1297,10 +1300,6 @@ struct nand_chip { struct nand_legacy legacy; - uint8_t (*read_byte)(struct nand_chip *chip); - void (*write_byte)(struct nand_chip *chip, uint8_t byte); - void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); - void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); -- cgit v1.2.3 From bf6065c6c08fa3ed7bdf8d28b8062ce8e58c1543 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:36 +0200 Subject: mtd: rawnand: Deprecate ->cmd_ctrl() and ->cmdfunc() Those hooks have been replaced by ->exec_op(). Move them to the nand_legacy struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f961efd2eacc..5ef2004a37a2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -199,10 +199,10 @@ enum nand_ecc_algo { #define NAND_USE_BOUNCE_BUFFER 0x00100000 /* - * In case your controller is implementing ->cmd_ctrl() and is relying on the - * default ->cmdfunc() implementation, you may want to let the core handle the - * tCCS delay which is required when a column change (RNDIN or RNDOUT) is - * requested. + * In case your controller is implementing ->legacy.cmd_ctrl() and is relying + * on the default ->cmdfunc() implementation, you may want to let the core + * handle the tCCS delay which is required when a column change (RNDIN or + * RNDOUT) is requested. * If your controller already takes care of this delay, you don't need to set * this flag. */ @@ -1180,6 +1180,9 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @write_byte: write a single byte to the chip on the low 8 I/O lines * @write_buf: write data from the buffer to the chip * @read_buf: read data from the chip into the buffer + * @cmd_ctrl: hardware specific function for controlling ALE/CLE/nCE. Also used + * to write command and address + * @cmdfunc: hardware specific function for writing commands to the chip. * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1191,6 +1194,9 @@ struct nand_legacy { void (*write_byte)(struct nand_chip *chip, u8 byte); void (*write_buf)(struct nand_chip *chip, const u8 *buf, int len); void (*read_buf)(struct nand_chip *chip, u8 *buf, int len); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); + void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, + int page_addr); }; /** @@ -1204,14 +1210,10 @@ struct nand_legacy { * @select_chip: [REPLACEABLE] select chip nr * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers * @block_markbad: [REPLACEABLE] mark a block bad - * @cmd_ctrl: [BOARDSPECIFIC] hardwarespecific function for controlling - * ALE/CLE/nCE. Also used to write command and address * @dev_ready: [BOARDSPECIFIC] hardwarespecific function for accessing * device ready/busy line. If set to NULL no access to * ready/busy is available and the ready/busy information * is read from the chip status register. - * @cmdfunc: [REPLACEABLE] hardwarespecific function for writing - * commands to the chip. * @waitfunc: [REPLACEABLE] hardwarespecific function for wait on * ready. * @exec_op: controller specific method to execute NAND operations. @@ -1303,10 +1305,7 @@ struct nand_chip { void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); - void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); int (*dev_ready)(struct nand_chip *chip); - void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, - int page_addr); int (*waitfunc)(struct nand_chip *chip); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, -- cgit v1.2.3 From 8395b753d7cad2beb03d374621cc8851f1cb4e01 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:37 +0200 Subject: mtd: rawnand: Deprecate ->dev_ready() and ->waitfunc() Those hooks have been replaced by ->exec_op(). Move them to the nand_legacy struct. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5ef2004a37a2..15642c028da2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1183,6 +1183,10 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @cmd_ctrl: hardware specific function for controlling ALE/CLE/nCE. Also used * to write command and address * @cmdfunc: hardware specific function for writing commands to the chip. + * @dev_ready: hardware specific function for accessing device ready/busy line. + * If set to NULL no access to ready/busy is available and the + * ready/busy information is read from the chip status register. + * @waitfunc: hardware specific function for wait on ready. * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1197,6 +1201,8 @@ struct nand_legacy { void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); void (*cmdfunc)(struct nand_chip *chip, unsigned command, int column, int page_addr); + int (*dev_ready)(struct nand_chip *chip); + int (*waitfunc)(struct nand_chip *chip); }; /** @@ -1210,16 +1216,10 @@ struct nand_legacy { * @select_chip: [REPLACEABLE] select chip nr * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers * @block_markbad: [REPLACEABLE] mark a block bad - * @dev_ready: [BOARDSPECIFIC] hardwarespecific function for accessing - * device ready/busy line. If set to NULL no access to - * ready/busy is available and the ready/busy information - * is read from the chip status register. - * @waitfunc: [REPLACEABLE] hardwarespecific function for wait on - * ready. * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), - * ->legacy.{read,write}_{buf,byte,word}(), ->dev_ready() - * and ->waifunc(). + * ->legacy.{read,write}_{buf,byte,word}(), + * ->legacy.dev_ready() and ->waifunc(). * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure @@ -1305,8 +1305,6 @@ struct nand_chip { void (*select_chip)(struct nand_chip *chip, int cs); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); - int (*dev_ready)(struct nand_chip *chip); - int (*waitfunc)(struct nand_chip *chip); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); -- cgit v1.2.3 From cdc784c743945f445a26f4c0bd60a50a1adb39c4 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:38 +0200 Subject: mtd: rawnand: Deprecate ->block_{bad,markbad}() hooks Those hooks have been overloaded by some drivers for bad reasons: either the driver was not fitting in the NAND framework and should have been an MTD driver (docg4), or it was not properly implementing the OOB read/write request or had a weird layout where BBM are trashed. In any case, we should discourage people from overloading those methods and encourage them to fix their driver instead. Move the ->block_{bad,markbad}() hooks to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 15642c028da2..aa3e931d0206 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1187,6 +1187,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * If set to NULL no access to ready/busy is available and the * ready/busy information is read from the chip status register. * @waitfunc: hardware specific function for wait on ready. + * @block_bad: check if a block is bad, using OOB markers + * @block_markbad: mark a block bad * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1203,6 +1205,8 @@ struct nand_legacy { int page_addr); int (*dev_ready)(struct nand_chip *chip); int (*waitfunc)(struct nand_chip *chip); + int (*block_bad)(struct nand_chip *chip, loff_t ofs); + int (*block_markbad)(struct nand_chip *chip, loff_t ofs); }; /** @@ -1214,8 +1218,6 @@ struct nand_legacy { * fields/hooks, you should consider reworking the driver * avoid using them. * @select_chip: [REPLACEABLE] select chip nr - * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers - * @block_markbad: [REPLACEABLE] mark a block bad * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), * ->legacy.{read,write}_{buf,byte,word}(), @@ -1303,8 +1305,6 @@ struct nand_chip { struct nand_legacy legacy; void (*select_chip)(struct nand_chip *chip, int cs); - int (*block_bad)(struct nand_chip *chip, loff_t ofs); - int (*block_markbad)(struct nand_chip *chip, loff_t ofs); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); @@ -1556,6 +1556,7 @@ extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; int nand_create_bbt(struct nand_chip *chip); int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); +int nand_markbad_bbm(struct nand_chip *chip, loff_t ofs); int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, -- cgit v1.2.3 From f9ebd1bb41031afc162e9acda7ad044a35bccf82 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:39 +0200 Subject: mtd: rawnand: Deprecate ->erase() The ->erase() hook have been overloaded by some drivers for bad reasons: either the driver was not fitting in the NAND framework and should have been an MTD driver (docg4), or the driver uses a specific path for the ERASE operation (denali), instead of implementing it generically. In any case, we should discourage people from overloading this method and encourage them to implement ->exec_op() instead. Move the ->erase() hook to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 aa3e931d0206..97c6ff7d127e 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1189,6 +1189,7 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @waitfunc: hardware specific function for wait on ready. * @block_bad: check if a block is bad, using OOB markers * @block_markbad: mark a block bad + * @erase: erase function * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1207,6 +1208,7 @@ struct nand_legacy { int (*waitfunc)(struct nand_chip *chip); int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); + int (*erase)(struct nand_chip *chip, int page); }; /** @@ -1228,7 +1230,6 @@ struct nand_legacy { * @buf_align: minimum buffer alignment required by a platform * @dummy_controller: dummy controller implementation for drivers that can * only control a single chip - * @erase: [REPLACEABLE] erase function * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring * data from array to read regs (tR). * @state: [INTERN] the current state of the NAND device @@ -1308,7 +1309,6 @@ struct nand_chip { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); - int (*erase)(struct nand_chip *chip, int page); int (*set_features)(struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*get_features)(struct nand_chip *chip, int feature_addr, -- cgit v1.2.3 From 45240367939b071b9957b970379cf64f9a2934ce Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:40 +0200 Subject: mtd: rawnand: Deprecate ->{set,get}_features() hooks Those hooks should be replaced by a proper ->exec_op() implementation. Move them to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 97c6ff7d127e..02ac70a30c63 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1190,6 +1190,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @block_bad: check if a block is bad, using OOB markers * @block_markbad: mark a block bad * @erase: erase function + * @set_features: set the NAND chip features + * @get_features: get the NAND chip features * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1209,6 +1211,10 @@ struct nand_legacy { int (*block_bad)(struct nand_chip *chip, loff_t ofs); int (*block_markbad)(struct nand_chip *chip, loff_t ofs); int (*erase)(struct nand_chip *chip, int page); + int (*set_features)(struct nand_chip *chip, int feature_addr, + u8 *subfeature_para); + int (*get_features)(struct nand_chip *chip, int feature_addr, + u8 *subfeature_para); }; /** @@ -1279,8 +1285,6 @@ struct nand_legacy { * @blocks_per_die: [INTERN] The number of PEBs in a die * @data_interface: [INTERN] NAND interface timing information * @read_retries: [INTERN] the number of read retry modes supported - * @set_features: [REPLACEABLE] set the NAND chip features - * @get_features: [REPLACEABLE] get the NAND chip features * @setup_data_interface: [OPTIONAL] 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 @@ -1309,10 +1313,6 @@ struct nand_chip { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); - int (*set_features)(struct nand_chip *chip, int feature_addr, - uint8_t *subfeature_para); - int (*get_features)(struct nand_chip *chip, int feature_addr, - uint8_t *subfeature_para); int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); -- cgit v1.2.3 From 3cece3abebda068e55e19302a6f0fa60cf553737 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:41 +0200 Subject: mtd: rawnand: Deprecate ->chip_delay The wait timeouts and delays are directly extracted from the NAND timings and ->chip_delay is only used in legacy path, so let's move it to the nand_legacy struct to make it clear. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 02ac70a30c63..992d78d29674 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1192,6 +1192,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * @erase: erase function * @set_features: set the NAND chip features * @get_features: get the NAND chip features + * @chip_delay: chip dependent delay for transferring data from array to read + * regs (tR). * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -1215,6 +1217,7 @@ struct nand_legacy { u8 *subfeature_para); int (*get_features)(struct nand_chip *chip, int feature_addr, u8 *subfeature_para); + int chip_delay; }; /** @@ -1236,8 +1239,6 @@ struct nand_legacy { * @buf_align: minimum buffer alignment required by a platform * @dummy_controller: dummy controller implementation for drivers that can * only control a single chip - * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring - * data from array to read regs (tR). * @state: [INTERN] the current state of the NAND device * @oob_poi: "poison value buffer," used for laying out OOB data * before writing @@ -1317,7 +1318,6 @@ struct nand_chip { int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); - int chip_delay; unsigned int options; unsigned int bbt_options; -- cgit v1.2.3 From 0b4e61c1c26e0f34c9a5f6c35edee16cc26a72fd Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:42 +0200 Subject: mtd: rawnand: Move function prototypes after struct declarations Move nand_scan[_with_ids]() and nand_wait_ready() at the end of the file where all function prototype lies. This will also allow us to get rid of the nand_flash_dev forward declaration. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 992d78d29674..15183b73fed2 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -27,18 +27,6 @@ struct nand_chip; struct nand_flash_dev; -/* Scan and identify a NAND device */ -int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, - struct nand_flash_dev *ids); - -static inline int nand_scan(struct nand_chip *chip, unsigned int max_chips) -{ - return nand_scan_with_ids(chip, max_chips, NULL); -} - -/* Internal helper for board drivers which need to override command function */ -void nand_wait_ready(struct nand_chip *chip); - /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 @@ -1739,6 +1727,18 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); +/* Scan and identify a NAND device */ +int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, + struct nand_flash_dev *ids); + +static inline int nand_scan(struct nand_chip *chip, unsigned int max_chips) +{ + return nand_scan_with_ids(chip, max_chips, NULL); +} + +/* Internal helper for board drivers which need to override command function */ +void nand_wait_ready(struct nand_chip *chip); + /* * Free resources held by the NAND device, must be called on error after a * sucessful nand_scan(). -- cgit v1.2.3 From 394938eadff2b875c099529452ffb7f7303f1547 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:43 +0200 Subject: mtd: rawnand: Get rid of nand_flash_dev forward declation nand_scan[with_ids]() have been moved at the end of the file. We can now get rid of of the nand_flash_dev forward declaration. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 15183b73fed2..768415ed1159 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -25,7 +25,6 @@ #include struct nand_chip; -struct nand_flash_dev; /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 -- cgit v1.2.3 From d16397d57a90d8c35bef3d8104460bf18e111fa7 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:44 +0200 Subject: mtd: rawnand: Get rid of the duplicate nand_chip forward declaration There's already a forward declaration of nand_chip at the beginning of the file. Get rid of this one. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 768415ed1159..608279104aae 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -210,9 +210,6 @@ enum nand_ecc_algo { #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 -/* Keep gcc happy */ -struct nand_chip; - /* ONFI version bits */ #define ONFI_VERSION_1_0 BIT(1) #define ONFI_VERSION_2_0 BIT(2) -- cgit v1.2.3 From 4114f97c41cd3992724f450f595417e4432737a0 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:45 +0200 Subject: mtd: rawnand: Get rid of a few unused definitions Those definitions are not used, let's remove them. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 608279104aae..8aa8b57ca4b1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -119,10 +119,6 @@ enum nand_ecc_algo { #define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) #define NAND_ECC_MAXIMIZE BIT(1) -/* Bit mask for flags passed to do_nand_read_ecc */ -#define NAND_GET_DEVICE 0x80 - - /* * Option constants for bizarre disfunctionality and real * features. @@ -163,9 +159,7 @@ enum nand_ecc_algo { #define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG /* Macros to identify the above */ -#define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) -#define NAND_HAS_SUBPAGE_WRITE(chip) !((chip)->options & NAND_NO_SUBPAGE_WRITE) /* Non chip related options */ /* This option skips the bbt scan during initialization. */ @@ -1649,8 +1643,6 @@ static inline int nand_opcode_8bits(unsigned int command) return 0; } -/* get timing characteristics from ONFI timing mode. */ -const struct nand_sdr_timings *onfi_async_timing_mode_to_sdr_timings(int mode); int nand_check_erased_ecc_chunk(void *data, int datalen, void *ecc, int ecclen, -- cgit v1.2.3 From c7921bb32ab616462cefb9c2f3dd81d85d32b948 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:46 +0200 Subject: mtd: rawnand: Move platform_nand_xxx definitions out of rawnand.h platform_nand_xxx definitions are just used by the plat_nand driver. Let's move those definitions out of the core/driver-agnostic rawnand.h header. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/platnand.h | 74 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 60 ----------------------------------- 2 files changed, 74 insertions(+), 60 deletions(-) create mode 100644 include/linux/mtd/platnand.h (limited to 'include/linux') diff --git a/include/linux/mtd/platnand.h b/include/linux/mtd/platnand.h new file mode 100644 index 000000000000..bc11eb6b593b --- /dev/null +++ b/include/linux/mtd/platnand.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner + * + * Contains all platform NAND related definitions. + */ + +#ifndef __LINUX_MTD_PLATNAND_H +#define __LINUX_MTD_PLATNAND_H + +#include +#include +#include + +/** + * struct platform_nand_chip - chip level device structure + * @nr_chips: max. number of chips to scan for + * @chip_offset: chip number offset + * @nr_partitions: number of partitions pointed to by partitions (or zero) + * @partitions: mtd partition list + * @chip_delay: R/B delay value in us + * @options: Option flags, e.g. 16bit buswidth + * @bbt_options: BBT option flags, e.g. NAND_BBT_USE_FLASH + * @part_probe_types: NULL-terminated array of probe types + */ +struct platform_nand_chip { + int nr_chips; + int chip_offset; + int nr_partitions; + struct mtd_partition *partitions; + int chip_delay; + unsigned int options; + unsigned int bbt_options; + const char **part_probe_types; +}; + +/** + * struct platform_nand_ctrl - controller level device structure + * @probe: platform specific function to probe/setup hardware + * @remove: platform specific function to remove/teardown hardware + * @dev_ready: platform specific function to read ready/busy pin + * @select_chip: platform specific chip select function + * @cmd_ctrl: platform specific function for controlling + * ALE/CLE/nCE. Also used to write command and address + * @write_buf: platform specific function for write buffer + * @read_buf: platform specific function for read buffer + * @priv: private data to transport driver specific settings + * + * All fields are optional and depend on the hardware driver requirements + */ +struct platform_nand_ctrl { + int (*probe)(struct platform_device *pdev); + void (*remove)(struct platform_device *pdev); + int (*dev_ready)(struct nand_chip *chip); + void (*select_chip)(struct nand_chip *chip, int cs); + void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); + void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); + void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); + void *priv; +}; + +/** + * struct platform_nand_data - container structure for platform-specific data + * @chip: chip level chip structure + * @ctrl: controller level device structure + */ +struct platform_nand_data { + struct platform_nand_chip chip; + struct platform_nand_ctrl ctrl; +}; + +#endif /* __LINUX_MTD_PLATNAND_H */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8aa8b57ca4b1..04e11a314e9c 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1540,66 +1540,6 @@ int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt); -/** - * struct platform_nand_chip - chip level device structure - * @nr_chips: max. number of chips to scan for - * @chip_offset: chip number offset - * @nr_partitions: number of partitions pointed to by partitions (or zero) - * @partitions: mtd partition list - * @chip_delay: R/B delay value in us - * @options: Option flags, e.g. 16bit buswidth - * @bbt_options: BBT option flags, e.g. NAND_BBT_USE_FLASH - * @part_probe_types: NULL-terminated array of probe types - */ -struct platform_nand_chip { - int nr_chips; - int chip_offset; - int nr_partitions; - struct mtd_partition *partitions; - int chip_delay; - unsigned int options; - unsigned int bbt_options; - const char **part_probe_types; -}; - -/* Keep gcc happy */ -struct platform_device; - -/** - * struct platform_nand_ctrl - controller level device structure - * @probe: platform specific function to probe/setup hardware - * @remove: platform specific function to remove/teardown hardware - * @dev_ready: platform specific function to read ready/busy pin - * @select_chip: platform specific chip select function - * @cmd_ctrl: platform specific function for controlling - * ALE/CLE/nCE. Also used to write command and address - * @write_buf: platform specific function for write buffer - * @read_buf: platform specific function for read buffer - * @priv: private data to transport driver specific settings - * - * All fields are optional and depend on the hardware driver requirements - */ -struct platform_nand_ctrl { - int (*probe)(struct platform_device *pdev); - void (*remove)(struct platform_device *pdev); - int (*dev_ready)(struct nand_chip *chip); - void (*select_chip)(struct nand_chip *chip, int cs); - void (*cmd_ctrl)(struct nand_chip *chip, int dat, unsigned int ctrl); - void (*write_buf)(struct nand_chip *chip, const uint8_t *buf, int len); - void (*read_buf)(struct nand_chip *chip, uint8_t *buf, int len); - void *priv; -}; - -/** - * struct platform_nand_data - container structure for platform-specific data - * @chip: chip level chip structure - * @ctrl: controller level device structure - */ -struct platform_nand_data { - struct platform_nand_chip chip; - struct platform_nand_ctrl ctrl; -}; - /* return the supported asynchronous timing mode. */ static inline int onfi_get_async_timing_mode(struct nand_chip *chip) { -- cgit v1.2.3 From 462f35d3e5e805657b48c76d3e7dd1c37e0ac62c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:47 +0200 Subject: mtd: rawnand: Inline onfi_get_async_timing_mode() onfi_get_async_timing_mode() is only used in one place inside nand_base.c. Let's inline the code and kill the helper. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- 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 04e11a314e9c..7f0e3dc222ed 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1540,15 +1540,6 @@ int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt); -/* return the supported asynchronous timing mode. */ -static inline int onfi_get_async_timing_mode(struct nand_chip *chip) -{ - if (!chip->parameters.onfi) - return ONFI_TIMING_MODE_UNKNOWN; - - return chip->parameters.onfi->async_timing_mode; -} - int onfi_fill_data_interface(struct nand_chip *chip, enum nand_data_interface_type type, int timing_mode); -- cgit v1.2.3 From 348d56a8c6067f3b2f1799d6f050f3be4bf5904b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:48 +0200 Subject: mtd: rawnand: Keep all internal stuff private A lot of things defined in rawnand.h should not be exposed to NAND controller drivers and should only be shared by core files. Create the drivers/mtd/nand/raw/internals.h header to store such definitions, and move all private defs to this header. Also remove EXPORT_SYMBOLS() on functions that are not supposed to be exposed. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 96 --------------------------------------------- 1 file changed, 96 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 7f0e3dc222ed..fbe7686cfc59 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -775,24 +775,6 @@ nand_get_sdr_timings(const struct nand_data_interface *conf) return &conf->timings.sdr; } -/** - * struct nand_manufacturer_ops - NAND Manufacturer operations - * @detect: detect the NAND memory organization and capabilities - * @init: initialize all vendor specific fields (like the ->read_retry() - * implementation) if any. - * @cleanup: the ->init() function may have allocated resources, ->cleanup() - * is here to let vendor specific code release those resources. - * @fixup_onfi_param_page: apply vendor specific fixups to the ONFI parameter - * page. This is called after the checksum is verified. - */ -struct nand_manufacturer_ops { - void (*detect)(struct nand_chip *chip); - int (*init)(struct nand_chip *chip); - void (*cleanup)(struct nand_chip *chip); - void (*fixup_onfi_param_page)(struct nand_chip *chip, - struct nand_onfi_params *p); -}; - /** * struct nand_op_cmd_instr - Definition of a command instruction * @opcode: the command to issue in one cycle @@ -1403,27 +1385,6 @@ static inline void *nand_get_manufacturer_data(struct nand_chip *chip) return chip->manufacturer.priv; } -/* - * NAND Flash Manufacturer ID Codes - */ -#define NAND_MFR_TOSHIBA 0x98 -#define NAND_MFR_ESMT 0xc8 -#define NAND_MFR_SAMSUNG 0xec -#define NAND_MFR_FUJITSU 0x04 -#define NAND_MFR_NATIONAL 0x8f -#define NAND_MFR_RENESAS 0x07 -#define NAND_MFR_STMICRO 0x20 -#define NAND_MFR_HYNIX 0xad -#define NAND_MFR_MICRON 0x2c -#define NAND_MFR_AMD 0x01 -#define NAND_MFR_MACRONIX 0xc2 -#define NAND_MFR_EON 0x92 -#define NAND_MFR_SANDISK 0x45 -#define NAND_MFR_INTEL 0x89 -#define NAND_MFR_ATO 0x9b -#define NAND_MFR_WINBOND 0xef - - /* * A helper for defining older NAND chips where the second ID byte fully * defined the chip, including the geometry (chip size, eraseblock size, page @@ -1503,46 +1464,7 @@ struct nand_flash_dev { int onfi_timing_mode_default; }; -/** - * struct nand_manufacturer - NAND Flash Manufacturer structure - * @name: Manufacturer name - * @id: manufacturer ID code of device. - * @ops: manufacturer operations -*/ -struct nand_manufacturer { - int id; - char *name; - const struct nand_manufacturer_ops *ops; -}; - -const struct nand_manufacturer *nand_get_manufacturer(u8 id); - -static inline const char * -nand_manufacturer_name(const struct nand_manufacturer *manufacturer) -{ - return manufacturer ? manufacturer->name : "Unknown"; -} - -extern struct nand_flash_dev nand_flash_ids[]; - -extern const struct nand_manufacturer_ops toshiba_nand_manuf_ops; -extern const struct nand_manufacturer_ops samsung_nand_manuf_ops; -extern const struct nand_manufacturer_ops hynix_nand_manuf_ops; -extern const struct nand_manufacturer_ops micron_nand_manuf_ops; -extern const struct nand_manufacturer_ops amd_nand_manuf_ops; -extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; - int nand_create_bbt(struct nand_chip *chip); -int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); -int nand_markbad_bbm(struct nand_chip *chip, loff_t ofs); -int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); -int nand_isbad_bbt(struct nand_chip *chip, loff_t offs, int allowbbt); -int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, - int allowbbt); - -int onfi_fill_data_interface(struct nand_chip *chip, - enum nand_data_interface_type type, - int timing_mode); /* * Check if it is a SLC nand. @@ -1574,7 +1496,6 @@ static inline int nand_opcode_8bits(unsigned int command) return 0; } - int nand_check_erased_ecc_chunk(void *data, int datalen, void *ecc, int ecclen, void *extraoob, int extraooblen, @@ -1586,18 +1507,9 @@ int nand_ecc_choose_conf(struct nand_chip *chip, /* Default write_oob implementation */ int nand_write_oob_std(struct nand_chip *chip, int page); -/* Default write_oob syndrome implementation */ -int nand_write_oob_syndrome(struct nand_chip *chip, int page); - /* Default read_oob implementation */ int nand_read_oob_std(struct nand_chip *chip, int page); -/* Default read_oob syndrome implementation */ -int nand_read_oob_syndrome(struct nand_chip *chip, int page); - -/* Wrapper to use in order for controllers/vendors to GET/SET FEATURES */ -int nand_get_features(struct nand_chip *chip, int addr, u8 *subfeature_param); -int nand_set_features(struct nand_chip *chip, int addr, u8 *subfeature_param); /* Stub used by drivers that do not support GET/SET FEATURES operations */ int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, u8 *subfeature_param); @@ -1605,14 +1517,10 @@ int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, /* Default read_page_raw implementation */ int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); -int nand_read_page_raw_notsupp(struct nand_chip *chip, u8 *buf, - int oob_required, int page); /* Default write_page_raw implementation */ int nand_write_page_raw(struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); -int nand_write_page_raw_notsupp(struct nand_chip *chip, const u8 *buf, - int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); @@ -1622,7 +1530,6 @@ int nand_reset_op(struct nand_chip *chip); int nand_readid_op(struct nand_chip *chip, u8 addr, void *buf, unsigned int len); int nand_status_op(struct nand_chip *chip, u8 *status); -int nand_exit_status_op(struct nand_chip *chip); int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock); int nand_read_page_op(struct nand_chip *chip, unsigned int page, unsigned int offset_in_page, void *buf, unsigned int len); @@ -1666,9 +1573,6 @@ void nand_cleanup(struct nand_chip *chip); /* Unregister the MTD device and calls nand_cleanup() */ void nand_release(struct nand_chip *chip); -/* Default extended ID decoding function */ -void nand_decode_ext_id(struct nand_chip *chip); - /* * External helper for controller drivers that have to implement the WAITRDY * instruction and have no physical pin to check it. -- cgit v1.2.3 From 1c325cc5077a88510afc08b1d2c75bcf18681f21 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:50 +0200 Subject: mtd: rawnand: Move ONFI code to nand_onfi.c This moves ONFI related code to nand_onfi.c and ONFI related struct/macros to include/linux/mtd/onfi.h. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/onfi.h | 178 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 164 +--------------------------------------- 2 files changed, 179 insertions(+), 163 deletions(-) create mode 100644 include/linux/mtd/onfi.h (limited to 'include/linux') diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h new file mode 100644 index 000000000000..339ac798568e --- /dev/null +++ b/include/linux/mtd/onfi.h @@ -0,0 +1,178 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner + * + * Contains all ONFI related definitions + */ + +#ifndef __LINUX_MTD_ONFI_H +#define __LINUX_MTD_ONFI_H + +#include + +/* ONFI version bits */ +#define ONFI_VERSION_1_0 BIT(1) +#define ONFI_VERSION_2_0 BIT(2) +#define ONFI_VERSION_2_1 BIT(3) +#define ONFI_VERSION_2_2 BIT(4) +#define ONFI_VERSION_2_3 BIT(5) +#define ONFI_VERSION_3_0 BIT(6) +#define ONFI_VERSION_3_1 BIT(7) +#define ONFI_VERSION_3_2 BIT(8) +#define ONFI_VERSION_4_0 BIT(9) + +/* ONFI features */ +#define ONFI_FEATURE_16_BIT_BUS (1 << 0) +#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) + +/* ONFI timing mode, used in both asynchronous and synchronous mode */ +#define ONFI_TIMING_MODE_0 (1 << 0) +#define ONFI_TIMING_MODE_1 (1 << 1) +#define ONFI_TIMING_MODE_2 (1 << 2) +#define ONFI_TIMING_MODE_3 (1 << 3) +#define ONFI_TIMING_MODE_4 (1 << 4) +#define ONFI_TIMING_MODE_5 (1 << 5) +#define ONFI_TIMING_MODE_UNKNOWN (1 << 6) + +/* ONFI feature number/address */ +#define ONFI_FEATURE_NUMBER 256 +#define ONFI_FEATURE_ADDR_TIMING_MODE 0x1 + +/* Vendor-specific feature address (Micron) */ +#define ONFI_FEATURE_ADDR_READ_RETRY 0x89 +#define ONFI_FEATURE_ON_DIE_ECC 0x90 +#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) + +/* ONFI subfeature parameters length */ +#define ONFI_SUBFEATURE_PARAM_LEN 4 + +/* ONFI optional commands SET/GET FEATURES supported? */ +#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) + +struct nand_onfi_params { + /* rev info and features block */ + /* 'O' 'N' 'F' 'I' */ + u8 sig[4]; + __le16 revision; + __le16 features; + __le16 opt_cmd; + u8 reserved0[2]; + __le16 ext_param_page_length; /* since ONFI 2.1 */ + u8 num_of_param_pages; /* since ONFI 2.1 */ + u8 reserved1[17]; + + /* manufacturer information block */ + char manufacturer[12]; + char model[20]; + u8 jedec_id; + __le16 date_code; + u8 reserved2[13]; + + /* memory organization block */ + __le32 byte_per_page; + __le16 spare_bytes_per_page; + __le32 data_bytes_per_ppage; + __le16 spare_bytes_per_ppage; + __le32 pages_per_block; + __le32 blocks_per_lun; + u8 lun_count; + u8 addr_cycles; + u8 bits_per_cell; + __le16 bb_per_lun; + __le16 block_endurance; + u8 guaranteed_good_blocks; + __le16 guaranteed_block_endurance; + u8 programs_per_page; + u8 ppage_attr; + u8 ecc_bits; + u8 interleaved_bits; + u8 interleaved_ops; + u8 reserved3[13]; + + /* electrical parameter block */ + u8 io_pin_capacitance_max; + __le16 async_timing_mode; + __le16 program_cache_timing_mode; + __le16 t_prog; + __le16 t_bers; + __le16 t_r; + __le16 t_ccs; + __le16 src_sync_timing_mode; + u8 src_ssync_features; + __le16 clk_pin_capacitance_typ; + __le16 io_pin_capacitance_typ; + __le16 input_pin_capacitance_typ; + u8 input_pin_capacitance_max; + u8 driver_strength_support; + __le16 t_int_r; + __le16 t_adl; + u8 reserved4[8]; + + /* vendor */ + __le16 vendor_revision; + u8 vendor[88]; + + __le16 crc; +} __packed; + +#define ONFI_CRC_BASE 0x4F4E + +/* Extended ECC information Block Definition (since ONFI 2.1) */ +struct onfi_ext_ecc_info { + u8 ecc_bits; + u8 codeword_size; + __le16 bb_per_lun; + __le16 block_endurance; + u8 reserved[2]; +} __packed; + +#define ONFI_SECTION_TYPE_0 0 /* Unused section. */ +#define ONFI_SECTION_TYPE_1 1 /* for additional sections. */ +#define ONFI_SECTION_TYPE_2 2 /* for ECC information. */ +struct onfi_ext_section { + u8 type; + u8 length; +} __packed; + +#define ONFI_EXT_SECTION_MAX 8 + +/* Extended Parameter Page Definition (since ONFI 2.1) */ +struct onfi_ext_param_page { + __le16 crc; + u8 sig[4]; /* 'E' 'P' 'P' 'S' */ + u8 reserved0[10]; + struct onfi_ext_section sections[ONFI_EXT_SECTION_MAX]; + + /* + * The actual size of the Extended Parameter Page is in + * @ext_param_page_length of nand_onfi_params{}. + * The following are the variable length sections. + * So we do not add any fields below. Please see the ONFI spec. + */ +} __packed; + +/** + * struct onfi_params - ONFI specific parameters that will be reused + * @version: ONFI version (BCD encoded), 0 if ONFI is not supported + * @tPROG: Page program time + * @tBERS: Block erase time + * @tR: Page read time + * @tCCS: Change column setup time + * @async_timing_mode: Supported asynchronous timing mode + * @vendor_revision: Vendor specific revision number + * @vendor: Vendor specific data + */ +struct onfi_params { + int version; + u16 tPROG; + u16 tBERS; + u16 tR; + u16 tCCS; + u16 async_timing_mode; + u16 vendor_revision; + u8 vendor[88]; +}; + +#endif /* __LINUX_MTD_ONFI_H */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index fbe7686cfc59..f4fc0cce7c55 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -204,147 +205,6 @@ enum nand_ecc_algo { #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 -/* ONFI version bits */ -#define ONFI_VERSION_1_0 BIT(1) -#define ONFI_VERSION_2_0 BIT(2) -#define ONFI_VERSION_2_1 BIT(3) -#define ONFI_VERSION_2_2 BIT(4) -#define ONFI_VERSION_2_3 BIT(5) -#define ONFI_VERSION_3_0 BIT(6) -#define ONFI_VERSION_3_1 BIT(7) -#define ONFI_VERSION_3_2 BIT(8) -#define ONFI_VERSION_4_0 BIT(9) - -/* ONFI features */ -#define ONFI_FEATURE_16_BIT_BUS (1 << 0) -#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) - -/* ONFI timing mode, used in both asynchronous and synchronous mode */ -#define ONFI_TIMING_MODE_0 (1 << 0) -#define ONFI_TIMING_MODE_1 (1 << 1) -#define ONFI_TIMING_MODE_2 (1 << 2) -#define ONFI_TIMING_MODE_3 (1 << 3) -#define ONFI_TIMING_MODE_4 (1 << 4) -#define ONFI_TIMING_MODE_5 (1 << 5) -#define ONFI_TIMING_MODE_UNKNOWN (1 << 6) - -/* ONFI feature number/address */ -#define ONFI_FEATURE_NUMBER 256 -#define ONFI_FEATURE_ADDR_TIMING_MODE 0x1 - -/* Vendor-specific feature address (Micron) */ -#define ONFI_FEATURE_ADDR_READ_RETRY 0x89 -#define ONFI_FEATURE_ON_DIE_ECC 0x90 -#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) - -/* ONFI subfeature parameters length */ -#define ONFI_SUBFEATURE_PARAM_LEN 4 - -/* ONFI optional commands SET/GET FEATURES supported? */ -#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) - -struct nand_onfi_params { - /* rev info and features block */ - /* 'O' 'N' 'F' 'I' */ - u8 sig[4]; - __le16 revision; - __le16 features; - __le16 opt_cmd; - u8 reserved0[2]; - __le16 ext_param_page_length; /* since ONFI 2.1 */ - u8 num_of_param_pages; /* since ONFI 2.1 */ - u8 reserved1[17]; - - /* manufacturer information block */ - char manufacturer[12]; - char model[20]; - u8 jedec_id; - __le16 date_code; - u8 reserved2[13]; - - /* memory organization block */ - __le32 byte_per_page; - __le16 spare_bytes_per_page; - __le32 data_bytes_per_ppage; - __le16 spare_bytes_per_ppage; - __le32 pages_per_block; - __le32 blocks_per_lun; - u8 lun_count; - u8 addr_cycles; - u8 bits_per_cell; - __le16 bb_per_lun; - __le16 block_endurance; - u8 guaranteed_good_blocks; - __le16 guaranteed_block_endurance; - u8 programs_per_page; - u8 ppage_attr; - u8 ecc_bits; - u8 interleaved_bits; - u8 interleaved_ops; - u8 reserved3[13]; - - /* electrical parameter block */ - u8 io_pin_capacitance_max; - __le16 async_timing_mode; - __le16 program_cache_timing_mode; - __le16 t_prog; - __le16 t_bers; - __le16 t_r; - __le16 t_ccs; - __le16 src_sync_timing_mode; - u8 src_ssync_features; - __le16 clk_pin_capacitance_typ; - __le16 io_pin_capacitance_typ; - __le16 input_pin_capacitance_typ; - u8 input_pin_capacitance_max; - u8 driver_strength_support; - __le16 t_int_r; - __le16 t_adl; - u8 reserved4[8]; - - /* vendor */ - __le16 vendor_revision; - u8 vendor[88]; - - __le16 crc; -} __packed; - -#define ONFI_CRC_BASE 0x4F4E - -/* Extended ECC information Block Definition (since ONFI 2.1) */ -struct onfi_ext_ecc_info { - u8 ecc_bits; - u8 codeword_size; - __le16 bb_per_lun; - __le16 block_endurance; - u8 reserved[2]; -} __packed; - -#define ONFI_SECTION_TYPE_0 0 /* Unused section. */ -#define ONFI_SECTION_TYPE_1 1 /* for additional sections. */ -#define ONFI_SECTION_TYPE_2 2 /* for ECC information. */ -struct onfi_ext_section { - u8 type; - u8 length; -} __packed; - -#define ONFI_EXT_SECTION_MAX 8 - -/* Extended Parameter Page Definition (since ONFI 2.1) */ -struct onfi_ext_param_page { - __le16 crc; - u8 sig[4]; /* 'E' 'P' 'P' 'S' */ - u8 reserved0[10]; - struct onfi_ext_section sections[ONFI_EXT_SECTION_MAX]; - - /* - * The actual size of the Extended Parameter Page is in - * @ext_param_page_length of nand_onfi_params{}. - * The following are the variable length sections. - * So we do not add any fields below. Please see the ONFI spec. - */ -} __packed; - struct jedec_ecc_info { u8 ecc_bits; u8 codeword_size; @@ -423,28 +283,6 @@ struct nand_jedec_params { __le16 crc; } __packed; -/** - * struct onfi_params - ONFI specific parameters that will be reused - * @version: ONFI version (BCD encoded), 0 if ONFI is not supported - * @tPROG: Page program time - * @tBERS: Block erase time - * @tR: Page read time - * @tCCS: Change column setup time - * @async_timing_mode: Supported asynchronous timing mode - * @vendor_revision: Vendor specific revision number - * @vendor: Vendor specific data - */ -struct onfi_params { - int version; - u16 tPROG; - u16 tBERS; - u16 tR; - u16 tCCS; - u16 async_timing_mode; - u16 vendor_revision; - u8 vendor[88]; -}; - /** * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name -- cgit v1.2.3 From 8ae3fbf81b9cfdd1fec0451181213742b73fdf1a Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 7 Sep 2018 00:38:51 +0200 Subject: mtd: rawnand: Move JEDEC code to nand_jedec.c This moves JEDEC related code to nand_jedec.c and JEDEC related struct/macros to include/linux/mtd/jedec.h. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/jedec.h | 91 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 79 +-------------------------------------- 2 files changed, 92 insertions(+), 78 deletions(-) create mode 100644 include/linux/mtd/jedec.h (limited to 'include/linux') diff --git a/include/linux/mtd/jedec.h b/include/linux/mtd/jedec.h new file mode 100644 index 000000000000..0b6b59f7cfbd --- /dev/null +++ b/include/linux/mtd/jedec.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner + * + * Contains all JEDEC related definitions + */ + +#ifndef __LINUX_MTD_JEDEC_H +#define __LINUX_MTD_JEDEC_H + +struct jedec_ecc_info { + u8 ecc_bits; + u8 codeword_size; + __le16 bb_per_lun; + __le16 block_endurance; + u8 reserved[2]; +} __packed; + +/* JEDEC features */ +#define JEDEC_FEATURE_16_BIT_BUS (1 << 0) + +struct nand_jedec_params { + /* rev info and features block */ + /* 'J' 'E' 'S' 'D' */ + u8 sig[4]; + __le16 revision; + __le16 features; + u8 opt_cmd[3]; + __le16 sec_cmd; + u8 num_of_param_pages; + u8 reserved0[18]; + + /* manufacturer information block */ + char manufacturer[12]; + char model[20]; + u8 jedec_id[6]; + u8 reserved1[10]; + + /* memory organization block */ + __le32 byte_per_page; + __le16 spare_bytes_per_page; + u8 reserved2[6]; + __le32 pages_per_block; + __le32 blocks_per_lun; + u8 lun_count; + u8 addr_cycles; + u8 bits_per_cell; + u8 programs_per_page; + u8 multi_plane_addr; + u8 multi_plane_op_attr; + u8 reserved3[38]; + + /* electrical parameter block */ + __le16 async_sdr_speed_grade; + __le16 toggle_ddr_speed_grade; + __le16 sync_ddr_speed_grade; + u8 async_sdr_features; + u8 toggle_ddr_features; + u8 sync_ddr_features; + __le16 t_prog; + __le16 t_bers; + __le16 t_r; + __le16 t_r_multi_plane; + __le16 t_ccs; + __le16 io_pin_capacitance_typ; + __le16 input_pin_capacitance_typ; + __le16 clk_pin_capacitance_typ; + u8 driver_strength_support; + __le16 t_adl; + u8 reserved4[36]; + + /* ECC and endurance block */ + u8 guaranteed_good_blocks; + __le16 guaranteed_block_endurance; + struct jedec_ecc_info ecc_info[4]; + u8 reserved5[29]; + + /* reserved */ + u8 reserved6[148]; + + /* vendor */ + __le16 vendor_rev_num; + u8 reserved7[88]; + + /* CRC for Parameter Page */ + __le16 crc; +} __packed; + +#endif /* __LINUX_MTD_JEDEC_H */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f4fc0cce7c55..68d09e01fa56 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -205,84 +206,6 @@ enum nand_ecc_algo { #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 -struct jedec_ecc_info { - u8 ecc_bits; - u8 codeword_size; - __le16 bb_per_lun; - __le16 block_endurance; - u8 reserved[2]; -} __packed; - -/* JEDEC features */ -#define JEDEC_FEATURE_16_BIT_BUS (1 << 0) - -struct nand_jedec_params { - /* rev info and features block */ - /* 'J' 'E' 'S' 'D' */ - u8 sig[4]; - __le16 revision; - __le16 features; - u8 opt_cmd[3]; - __le16 sec_cmd; - u8 num_of_param_pages; - u8 reserved0[18]; - - /* manufacturer information block */ - char manufacturer[12]; - char model[20]; - u8 jedec_id[6]; - u8 reserved1[10]; - - /* memory organization block */ - __le32 byte_per_page; - __le16 spare_bytes_per_page; - u8 reserved2[6]; - __le32 pages_per_block; - __le32 blocks_per_lun; - u8 lun_count; - u8 addr_cycles; - u8 bits_per_cell; - u8 programs_per_page; - u8 multi_plane_addr; - u8 multi_plane_op_attr; - u8 reserved3[38]; - - /* electrical parameter block */ - __le16 async_sdr_speed_grade; - __le16 toggle_ddr_speed_grade; - __le16 sync_ddr_speed_grade; - u8 async_sdr_features; - u8 toggle_ddr_features; - u8 sync_ddr_features; - __le16 t_prog; - __le16 t_bers; - __le16 t_r; - __le16 t_r_multi_plane; - __le16 t_ccs; - __le16 io_pin_capacitance_typ; - __le16 input_pin_capacitance_typ; - __le16 clk_pin_capacitance_typ; - u8 driver_strength_support; - __le16 t_adl; - u8 reserved4[36]; - - /* ECC and endurance block */ - u8 guaranteed_good_blocks; - __le16 guaranteed_block_endurance; - struct jedec_ecc_info ecc_info[4]; - u8 reserved5[29]; - - /* reserved */ - u8 reserved6[148]; - - /* vendor */ - __le16 vendor_rev_num; - u8 reserved7[88]; - - /* CRC for Parameter Page */ - __le16 crc; -} __packed; - /** * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name -- cgit v1.2.3 From 309600c14e36d0e78c22fe3df58317965b90f4d1 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 4 Sep 2018 16:23:28 +0200 Subject: mtd: rawnand: Allow selection of ECC byte ordering at runtime Currently, the selection of ECC byte ordering for software hamming is done at compilation time, which doesn't make sense when ECC byte calculation is done in hardware and byte ordering is forced by the hardware engine. In this case, only the correction is done in software and we want to force the byte-ordering no matter the value of CONFIG_MTD_NAND_ECC_SMC. This is typically the case for the FSMC (Smart Media ordering), TMIO and TXX9NDFMC (regular byte ordering) blocks. For all other use cases (pure software implementation, SM FTL and nandecctest), we keep selecting the byte ordering based on the CONFIG_MTD_NAND_ECC_SMC value. It might not be ideal for SM FTL (I'd expect Smart Media ordering to be employed by the Smart Media FTL), but this option doesn't seem to be enabled in the existing _defconfig, so I can't tell setting sm_order to true is the right choice. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- include/linux/mtd/nand_ecc.h | 4 ++-- include/linux/mtd/rawnand.h | 6 ++++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand_ecc.h b/include/linux/mtd/nand_ecc.h index b81fecd5e719..0b3bb156c344 100644 --- a/include/linux/mtd/nand_ecc.h +++ b/include/linux/mtd/nand_ecc.h @@ -19,7 +19,7 @@ struct nand_chip; * Calculate 3 byte ECC code for eccsize byte block */ void __nand_calculate_ecc(const u_char *dat, unsigned int eccsize, - u_char *ecc_code); + u_char *ecc_code, bool sm_order); /* * Calculate 3 byte ECC code for 256/512 byte block @@ -31,7 +31,7 @@ int nand_calculate_ecc(struct nand_chip *chip, const u_char *dat, * Detect and correct a 1 bit error for eccsize byte block */ int __nand_correct_data(u_char *dat, u_char *read_ecc, u_char *calc_ecc, - unsigned int eccsize); + unsigned int eccsize, bool sm_order); /* * Detect and correct a 1 bit error for 256/512 byte block diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 68d09e01fa56..e10b126e148f 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -121,6 +121,12 @@ 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. -- cgit v1.2.3 From 2130b789b3ef6a518b9c9c6f245642620e2b0c0c Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Tue, 28 Aug 2018 16:51:18 +0100 Subject: irqchip/gic: Unify GIC priority definitions LPIs use the same priority value as other GIC interrupts. Make the GIC default priority definition visible to ITS implementation and use this same definition for LPI priorities. Tested-by: Daniel Thompson Signed-off-by: Julien Thierry Cc: Thomas Gleixner Cc: Jason Cooper Cc: Marc Zyngier Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-common.h | 6 ++++++ include/linux/irqchip/arm-gic.h | 5 ----- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index 0a83b4379f34..9a1a479a2bf4 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -13,6 +13,12 @@ #include #include +#define GICD_INT_DEF_PRI 0xa0 +#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ + (GICD_INT_DEF_PRI << 16) |\ + (GICD_INT_DEF_PRI << 8) |\ + GICD_INT_DEF_PRI) + enum gic_type { GIC_V2, GIC_V3, diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 6c4aaf04046c..626179077bb0 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -65,11 +65,6 @@ #define GICD_INT_EN_CLR_X32 0xffffffff #define GICD_INT_EN_SET_SGI 0x0000ffff #define GICD_INT_EN_CLR_PPI 0xffff0000 -#define GICD_INT_DEF_PRI 0xa0 -#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ - (GICD_INT_DEF_PRI << 16) |\ - (GICD_INT_DEF_PRI << 8) |\ - GICD_INT_DEF_PRI) #define GICD_IIDR_IMPLEMENTER_SHIFT 0 #define GICD_IIDR_IMPLEMENTER_MASK (0xfff << GICD_IIDR_IMPLEMENTER_SHIFT) -- cgit v1.2.3 From 47b00dcf141172c4c1c583701ec91923672cec39 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 10 Aug 2018 11:29:09 +0300 Subject: clk: ti: clkctrl: support multiple clkctrl nodes under a cm node Currently, only one clkctrl node can be added under a specific CM node due to limitation with the implementation. Modify the code to pick-up clockdomain name from the clkctrl node instead of CM node if provided. Also, add a new flag to the TI clock driver so that both modes can be supported simultaneously. Signed-off-by: Tero Kristo Tested-by: Tony Lindgren --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index a8faa38b1ed6..3301bd025a2c 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -290,6 +290,7 @@ struct ti_clk_features { #define TI_CLK_DPLL4_DENY_REPROGRAM BIT(1) #define TI_CLK_DISABLE_CLKDM_CONTROL BIT(2) #define TI_CLK_ERRATA_I810 BIT(3) +#define TI_CLK_CLKCTRL_COMPAT BIT(4) void ti_clk_setup_features(struct ti_clk_features *features); const struct ti_clk_features *ti_clk_get_features(void); -- cgit v1.2.3 From 8b95d1ce3300c411728954473316bd04d0ba9883 Mon Sep 17 00:00:00 2001 From: Russ Dill Date: Tue, 4 Sep 2018 12:19:35 +0530 Subject: clk: Add functions to save/restore clock context en-masse Deep enough power saving mode can result into losing context of the clock registers also, and they need to be restored once coming back from the power saving mode. Hence add functions to save/restore clock context. Signed-off-by: Keerthy Signed-off-by: Russ Dill Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- include/linux/clk-provider.h | 7 +++++++ include/linux/clk.h | 25 +++++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 08b1aa70a38d..df7379da6269 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -119,6 +119,11 @@ struct clk_duty { * Called with enable_lock held. This function must not * sleep. * + * @save_context: Save the context of the clock in prepration for poweroff. + * + * @restore_context: Restore the context of the clock after a restoration + * of power. + * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to * ensure that the prepare_mutex is held across this call. @@ -223,6 +228,8 @@ struct clk_ops { void (*disable)(struct clk_hw *hw); int (*is_enabled)(struct clk_hw *hw); void (*disable_unused)(struct clk_hw *hw); + int (*save_context)(struct clk_hw *hw); + void (*restore_context)(struct clk_hw *hw); unsigned long (*recalc_rate)(struct clk_hw *hw, unsigned long parent_rate); long (*round_rate)(struct clk_hw *hw, unsigned long rate, diff --git a/include/linux/clk.h b/include/linux/clk.h index 4f750c481b82..7da754d79f9d 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -629,6 +629,23 @@ struct clk *clk_get_parent(struct clk *clk); */ struct clk *clk_get_sys(const char *dev_id, const char *con_id); +/** + * clk_save_context - save clock context for poweroff + * + * Saves the context of the clock register for powerstates in which the + * contents of the registers will be lost. Occurs deep within the suspend + * code so locking is not necessary. + */ +int clk_save_context(void); + +/** + * clk_restore_context - restore clock context after poweroff + * + * This occurs with all clocks enabled. Occurs deep within the resume code + * so locking is not necessary. + */ +void clk_restore_context(void); + #else /* !CONFIG_HAVE_CLK */ static inline struct clk *clk_get(struct device *dev, const char *id) @@ -728,6 +745,14 @@ static inline struct clk *clk_get_sys(const char *dev_id, const char *con_id) { return NULL; } + +static inline int clk_save_context(void) +{ + return 0; +} + +static inline void clk_restore_context(void) {} + #endif /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ -- cgit v1.2.3 From 435365485f40cf12747d1daa2253a4f4b46b8148 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Tue, 4 Sep 2018 12:19:36 +0530 Subject: clk: clk: Add clk_gate_restore_context function The clock gate restore context function enables or disables the gate clocks based on the enable_count. This is done in cases where the clock context is lost and based on the enable_count the clock either needs to be enabled/disabled. Signed-off-by: Keerthy Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- include/linux/clk-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index df7379da6269..60c51871b04b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1018,5 +1018,7 @@ static inline void clk_writel(u32 val, u32 __iomem *reg) #endif /* platform dependent I/O accessors */ +void clk_gate_restore_context(struct clk_hw *hw); + #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ -- cgit v1.2.3 From d6e7bbc148f9fbec8a0117b0d0f420c9710e6d81 Mon Sep 17 00:00:00 2001 From: Russ Dill Date: Tue, 4 Sep 2018 12:19:37 +0530 Subject: clk: ti: Add functions to save/restore clk context SoCs like AM43XX lose clock registers context during RTC-only suspend. Hence add functions to save/restore the clock registers context. Signed-off-by: Keerthy Signed-off-by: Russ Dill Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- include/linux/clk/ti.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 3301bd025a2c..eacc5df57b99 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -159,6 +159,7 @@ struct clk_hw_omap { const char *clkdm_name; struct clockdomain *clkdm; const struct clk_hw_omap_ops *ops; + u32 context; }; /* @@ -294,6 +295,11 @@ struct ti_clk_features { void ti_clk_setup_features(struct ti_clk_features *features); const struct ti_clk_features *ti_clk_get_features(void); +int omap3_noncore_dpll_save_context(struct clk_hw *hw); +void omap3_noncore_dpll_restore_context(struct clk_hw *hw); + +int omap3_core_dpll_save_context(struct clk_hw *hw); +void omap3_core_dpll_restore_context(struct clk_hw *hw); extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll; -- cgit v1.2.3 From 9414229c9c53d3604032aa80f3d2e9ba5770cd4a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 24 Sep 2018 06:08:07 +0200 Subject: clocksource: Remove obsolete CLOCKSOURCE_OF_DECLARE The macro CLOCKSOURCE_OF_DECLARE was renamed more TIMER_OF_DECLARE, and we kept an alias CLOCKSOURCE_OF_DECLARE in order to smooth the transition for drivers. This change was done 1.5 year ago, we can reasonably remove this backward compatible macro as it is no longer used anywhere. Signed-off-by: Daniel Lezcano --- include/linux/clocksource.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 308918928767..4c58c1e64080 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -257,9 +257,6 @@ extern int clocksource_i8253_init(void); #define TIMER_OF_DECLARE(name, compat, fn) \ OF_DECLARE_1_RET(timer, name, compat, fn) -#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ - TIMER_OF_DECLARE(name, compat, fn) - #ifdef CONFIG_TIMER_PROBE extern void timer_probe(void); #else -- cgit v1.2.3 From 16fc087b9cb22c9a97307cc24a5413d0df68fe11 Mon Sep 17 00:00:00 2001 From: Yashaswini Raghuram Prathivadi Bhayankaram Date: Fri, 10 Aug 2018 00:17:44 -0700 Subject: virtchnl: Added support to exchange additional speed values Introduced a new virtchnl capability flag and a struct to support exchange of additional supported speeds. Signed-off-by: Yashaswini Raghuram Prathivadi Bhayankaram Signed-off-by: Anirudh Venkataramanan Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b41f7bc958ef..2c9756bd9c4c 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -252,6 +252,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 #define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 +/* Define below the capability flags that are not offloads */ +#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED 0x00000080 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -596,10 +598,23 @@ enum virtchnl_event_codes { struct virtchnl_pf_event { enum virtchnl_event_codes event; union { + /* If the PF driver does not support the new speed reporting + * capabilities then use link_event else use link_event_adv to + * get the speed and link information. The ability to understand + * new speeds is indicated by setting the capability flag + * VIRTCHNL_VF_CAP_ADV_LINK_SPEED in vf_cap_flags parameter + * in virtchnl_vf_resource struct and can be used to determine + * which link event struct to use below. + */ struct { enum virtchnl_link_speed link_speed; bool link_status; } link_event; + struct { + /* link_speed provided in Mbps */ + u32 link_speed; + u8 link_status; + } link_event_adv; } event_data; int severity; -- cgit v1.2.3 From 4cd2e0e70af6897ca2247fa1ffb1553ca16b4903 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 18 Apr 2018 17:30:19 -0500 Subject: signal: Introduce copy_siginfo_from_user and use it's return value In preparation for using a smaller version of siginfo in the kernel introduce copy_siginfo_from_user and use it when siginfo is copied from userspace. Make the pattern for using copy_siginfo_from_user and copy_siginfo_from_user32 to capture the return value and return that value on error. This is a necessary prerequisite for using a smaller siginfo in the kernel than the kernel exports to userspace. Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 3d4cd5db30a9..de94c159bfb0 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -22,6 +22,7 @@ static inline void clear_siginfo(struct siginfo *info) } int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); +int copy_siginfo_from_user(struct siginfo *to, const struct siginfo __user *from); enum siginfo_layout { SIL_KILL, -- cgit v1.2.3 From ae7795bc6187a15ec51cf258abae656a625f9980 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 25 Sep 2018 11:27:20 +0200 Subject: signal: Distinguish between kernel_siginfo and siginfo Linus recently observed that if we did not worry about the padding member in struct siginfo it is only about 48 bytes, and 48 bytes is much nicer than 128 bytes for allocating on the stack and copying around in the kernel. The obvious thing of only adding the padding when userspace is including siginfo.h won't work as there are sigframe definitions in the kernel that embed struct siginfo. So split siginfo in two; kernel_siginfo and siginfo. Keeping the traditional name for the userspace definition. While the version that is used internally to the kernel and ultimately will not be padded to 128 bytes is called kernel_siginfo. The definition of struct kernel_siginfo I have put in include/signal_types.h A set of buildtime checks has been added to verify the two structures have the same field offsets. To make it easy to verify the change kernel_siginfo retains the same size as siginfo. The reduction in size comes in a following change. Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 2 +- include/linux/compat.h | 4 ++-- include/linux/coredump.h | 4 ++-- include/linux/lsm_hooks.h | 4 ++-- include/linux/posix-timers.h | 2 +- include/linux/ptrace.h | 2 +- include/linux/sched.h | 2 +- include/linux/sched/signal.h | 18 +++++++++--------- include/linux/security.h | 6 +++--- include/linux/signal.h | 15 ++++++++------- include/linux/signal_types.h | 11 +++++++++-- 11 files changed, 39 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c05f24fac4f6..e9f5fe69df31 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -78,7 +78,7 @@ struct linux_binprm { /* Function parameter for binfmt->coredump */ struct coredump_params { - const siginfo_t *siginfo; + const kernel_siginfo_t *siginfo; struct pt_regs *regs; struct file *file; unsigned long limit; diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..4565d65b1776 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -452,8 +452,8 @@ 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(siginfo_t *to, const struct compat_siginfo __user *from); -int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *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); int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 207aed96a5b7..abf4b4e65dbb 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -17,9 +17,9 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); extern void dump_truncate(struct coredump_params *cprm); #ifdef CONFIG_COREDUMP -extern void do_coredump(const siginfo_t *siginfo); +extern void do_coredump(const kernel_siginfo_t *siginfo); #else -static inline void do_coredump(const siginfo_t *siginfo) {} +static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 97a020c616ad..bb40f6d34163 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -672,7 +672,7 @@ * Return 0 if permission is granted. * @task_kill: * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a siginfo structure. If @info is 1 or + * the constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming * from the kernel and should typically be permitted. * SIGIO signals are handled separately by the send_sigiotask hook in @@ -1606,7 +1606,7 @@ union security_list_options { int (*task_setscheduler)(struct task_struct *p); int (*task_getscheduler)(struct task_struct *p); int (*task_movememory)(struct task_struct *p); - int (*task_kill)(struct task_struct *p, struct siginfo *info, + int (*task_kill)(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred); int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index ee7e987ea1b4..e96581ca7c9d 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -126,5 +126,5 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); -void posixtimer_rearm(struct siginfo *info); +void posixtimer_rearm(struct kernel_siginfo *info); #endif diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 1de2235511c8..d19a795100da 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -341,7 +341,7 @@ extern void user_single_step_report(struct pt_regs *regs); #else static inline void user_single_step_report(struct pt_regs *regs) { - siginfo_t info; + kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..2ba88082e1ef 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -960,7 +960,7 @@ struct task_struct { /* Ptrace state: */ unsigned long ptrace_message; - siginfo_t *last_siginfo; + kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_TASK_XACCT diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 9e07f3521549..13789d10a50e 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -270,12 +270,12 @@ static inline int signal_group_exit(const struct signal_struct *sig) extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); +extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info); static inline int kernel_dequeue_signal(void) { struct task_struct *tsk = current; - siginfo_t __info; + kernel_siginfo_t __info; int ret; spin_lock_irq(&tsk->sighand->siglock); @@ -322,12 +322,12 @@ int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_ptrace_errno_trap(int errno, void __user *addr); -extern int send_sig_info(int, struct siginfo *, struct task_struct *); +extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig, struct task_struct *p); -extern int force_sig_info(int, struct siginfo *, struct task_struct *); -extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); -extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); -extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *, +extern int force_sig_info(int, struct kernel_siginfo *, struct task_struct *); +extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); +extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); +extern int kill_pid_info_as_cred(int, struct kernel_siginfo *, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); @@ -475,8 +475,8 @@ static inline int kill_cad_pid(int sig, int priv) } /* These can be the second arg to send_sig_info/send_group_sig_info. */ -#define SEND_SIG_NOINFO ((struct siginfo *) 0) -#define SEND_SIG_PRIV ((struct siginfo *) 1) +#define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) +#define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) /* * True if we are on the alternate signal stack. diff --git a/include/linux/security.h b/include/linux/security.h index 75f4156c84d7..d170a5b031f3 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -35,7 +35,7 @@ struct linux_binprm; struct cred; struct rlimit; -struct siginfo; +struct kernel_siginfo; struct sembuf; struct kern_ipc_perm; struct audit_context; @@ -361,7 +361,7 @@ int security_task_setrlimit(struct task_struct *p, unsigned int resource, int security_task_setscheduler(struct task_struct *p); int security_task_getscheduler(struct task_struct *p); int security_task_movememory(struct task_struct *p); -int security_task_kill(struct task_struct *p, struct siginfo *info, +int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred); int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -1020,7 +1020,7 @@ static inline int security_task_movememory(struct task_struct *p) } static inline int security_task_kill(struct task_struct *p, - struct siginfo *info, int sig, + struct kernel_siginfo *info, int sig, const struct cred *cred) { return 0; diff --git a/include/linux/signal.h b/include/linux/signal.h index de94c159bfb0..70031b10b918 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -11,18 +11,19 @@ struct task_struct; /* for sysctl */ extern int print_fatal_signals; -static inline void copy_siginfo(struct siginfo *to, const struct siginfo *from) +static inline void copy_siginfo(kernel_siginfo_t *to, + const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*to)); } -static inline void clear_siginfo(struct siginfo *info) +static inline void clear_siginfo(kernel_siginfo_t *info) { memset(info, 0, sizeof(*info)); } -int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); -int copy_siginfo_from_user(struct siginfo *to, const struct siginfo __user *from); +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); enum siginfo_layout { SIL_KILL, @@ -258,11 +259,11 @@ struct pt_regs; enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); -extern int do_send_sig_info(int sig, struct siginfo *info, +extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int group_send_sig_info(int sig, struct siginfo *info, +extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); +extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 222ae696000b..2a40a9c5e4ad 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -9,6 +9,13 @@ #include #include +typedef struct kernel_siginfo { + union { + __SIGINFO; + int _si_pad[SI_MAX_SIZE/sizeof(int)]; + }; +} kernel_siginfo_t; + /* * Real Time signals may be queued. */ @@ -16,7 +23,7 @@ struct sigqueue { struct list_head list; int flags; - siginfo_t info; + kernel_siginfo_t info; struct user_struct *user; }; @@ -60,7 +67,7 @@ struct old_sigaction { struct ksignal { struct k_sigaction ka; - siginfo_t info; + kernel_siginfo_t info; int sig; }; -- cgit v1.2.3 From 4ce5f9c9e7546915c559ffae594e6d73f918db00 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 25 Sep 2018 12:59:31 +0200 Subject: signal: Use a smaller struct siginfo in the kernel We reserve 128 bytes for struct siginfo but only use about 48 bytes on 64bit and 32 bytes on 32bit. Someday we might use more but it is unlikely to be anytime soon. Userspace seems content with just enough bytes of siginfo to implement sigqueue. Or in the case of checkpoint/restart reinjecting signals the kernel has sent. Reducing the stack footprint and the work to copy siginfo around from 2 cachelines to 1 cachelines seems worth doing even if I don't have benchmarks to show a performance difference. Suggested-by: Linus Torvalds Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 ++ include/linux/signal_types.h | 5 +---- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 70031b10b918..706a499d1eb1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -22,6 +22,8 @@ static inline void clear_siginfo(kernel_siginfo_t *info) memset(info, 0, sizeof(*info)); } +#define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) + 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); diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 2a40a9c5e4ad..f8a90ae9c6ec 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -10,10 +10,7 @@ #include typedef struct kernel_siginfo { - union { - __SIGINFO; - int _si_pad[SI_MAX_SIZE/sizeof(int)]; - }; + __SIGINFO; } kernel_siginfo_t; /* -- cgit v1.2.3 From 608a0ab2f54ab0e301ad76a41aad979ea0d02670 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:44 -0400 Subject: SUNRPC: Add lockless lookup of the server's auth domain Avoid taking the global auth_domain_lock in most lookups of the auth domain by adding an RCU protected lookup. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svcauth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 04e404a07882..3e53a6e2ada7 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -82,6 +82,7 @@ struct auth_domain { struct hlist_node hash; char *name; struct auth_ops *flavour; + struct rcu_head rcu_head; }; /* -- cgit v1.2.3 From fcd29ad17c6ff885dfae58f557e9323941e63ba2 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Thu, 9 Aug 2018 09:55:21 +0300 Subject: net/mlx5: Add Fast teardown support Today mlx5 devices support two teardown modes: 1- Regular teardown 2- Force teardown This change introduces the enhanced version of the "Force teardown" that allows SW to perform teardown in a faster way without the need to reclaim all the pages. Fast teardown provides the following advantages: 1- Fix a FW race condition that could cause command timeout 2- Avoid moving to polling mode 3- Close the vport to prevent PCI ACK to be sent without been scatter to memory Signed-off-by: Feras Daoud Reviewed-by: Majd Dibbiny Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 4 ++++ include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 11fa4e66afc5..e9b502d5bcc1 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -504,6 +504,10 @@ struct health_buffer { __be16 ext_synd; }; +enum mlx5_cmd_addr_l_sz_offset { + MLX5_NIC_IFC_OFFSET = 8, +}; + struct mlx5_init_seg { __be32 fw_rev; __be32 cmdif_rev_fw_sub; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f043d65b9bac..6e8a882052b1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -896,7 +896,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x8]; u8 dump_fill_mkey[0x1]; - u8 reserved_at_f9[0x3]; + u8 reserved_at_f9[0x2]; + u8 fast_teardown[0x1]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; @@ -3352,12 +3353,13 @@ struct mlx5_ifc_teardown_hca_out_bits { u8 reserved_at_40[0x3f]; - u8 force_state[0x1]; + u8 state[0x1]; }; enum { MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, MLX5_TEARDOWN_HCA_IN_PROFILE_FORCE_CLOSE = 0x1, + MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN = 0x2, }; struct mlx5_ifc_teardown_hca_in_bits { -- cgit v1.2.3 From 5f26bdceb9c0a5e6c696aa2899d077cd3ae93413 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 2 Oct 2018 23:42:02 +0200 Subject: cpuidle: menu: Fix wakeup statistics updates for polling state If the CPU exits the "polling" state due to the time limit in the loop in poll_idle(), this is not a real wakeup and it just means that the "polling" state selection was not adequate. The governor mispredicted short idle duration, but had a more suitable state been selected, the CPU might have spent more time in it. In fact, there is no reason to expect that there would have been a wakeup event earlier than the next timer in that case. Handling such cases as regular wakeups in menu_update() may cause the menu governor to make suboptimal decisions going forward, but ignoring them altogether would not be correct either, because every time menu_select() is invoked, it makes a separate new attempt to predict the idle duration taking distinct time to the closest timer event as input and the outcomes of all those attempts should be recorded. For this reason, make menu_update() always assume that if the "polling" state was exited due to the time limit, the next proper wakeup event for the CPU would be the next timer event (not including the tick). Fixes: a37b969a61c1 "cpuidle: poll_state: Add time limit to poll_idle()" Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Lezcano --- 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 d262f620890e..faed7a8977e8 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -81,6 +81,7 @@ struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; unsigned int use_deepest_state:1; + unsigned int poll_time_limit:1; unsigned int cpu; int last_residency; -- cgit v1.2.3 From c06c4d8090513f2974dfdbed2ac98634357ac475 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Wed, 3 Oct 2018 14:30:53 -0700 Subject: x86/objtool: Use asm macros to work around GCC inlining bugs As described in: 77b0bf55bc67: ("kbuild/Makefile: Prepare for using macros in inline assembly code to work around asm() related GCC inlining bugs") GCC's inlining heuristics are broken with common asm() patterns used in kernel code, resulting in the effective disabling of inlining. In the case of objtool the resulting borkage can be significant, since all the annotations of objtool are discarded during linkage and never inlined, yet GCC bogusly considers most functions affected by objtool annotations as 'too large'. The workaround is to set an assembly macro and call it from the inline assembly block. As a result GCC considers the inline assembly block as a single instruction. (Which it isn't, but that's the best we can get.) This increases the kernel size slightly: text data bss dec hex filename 18140829 10224724 2957312 31322865 1ddf2f1 ./vmlinux before 18140970 10225412 2957312 31323694 1ddf62e ./vmlinux after (+829) The number of static text symbols (i.e. non-inlined functions) is reduced: Before: 40321 After: 40302 (-19) [ mingo: Rewrote the changelog. ] Tested-by: Kees Cook Signed-off-by: Nadav Amit Reviewed-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Christopher Li Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-sparse@vger.kernel.org Link: http://lkml.kernel.org/r/20181003213100.189959-4-namit@vmware.com Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 56 +++++++++++++++++++++++++++++++++++++----------- 1 file changed, 43 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..1921545c6351 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -99,22 +99,13 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * unique, to convince GCC not to merge duplicate inline asm statements. */ #define annotate_reachable() ({ \ - asm volatile("%c0:\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + asm volatile("ANNOTATE_REACHABLE counter=%c0" \ + : : "i" (__COUNTER__)); \ }) #define annotate_unreachable() ({ \ - asm volatile("%c0:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__COUNTER__)); \ + asm volatile("ANNOTATE_UNREACHABLE counter=%c0" \ + : : "i" (__COUNTER__)); \ }) -#define ASM_UNREACHABLE \ - "999:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" #else #define annotate_reachable() #define annotate_unreachable() @@ -299,6 +290,45 @@ static inline void *offset_to_ptr(const int *off) return (void *)((unsigned long)off + *off); } +#else /* __ASSEMBLY__ */ + +#ifdef __KERNEL__ +#ifndef LINKER_SCRIPT + +#ifdef CONFIG_STACK_VALIDATION +.macro ANNOTATE_UNREACHABLE counter:req +\counter: + .pushsection .discard.unreachable + .long \counter\()b -. + .popsection +.endm + +.macro ANNOTATE_REACHABLE counter:req +\counter: + .pushsection .discard.reachable + .long \counter\()b -. + .popsection +.endm + +.macro ASM_UNREACHABLE +999: + .pushsection .discard.unreachable + .long 999b - . + .popsection +.endm +#else /* CONFIG_STACK_VALIDATION */ +.macro ANNOTATE_UNREACHABLE counter:req +.endm + +.macro ANNOTATE_REACHABLE counter:req +.endm + +.macro ASM_UNREACHABLE +.endm +#endif /* CONFIG_STACK_VALIDATION */ + +#endif /* LINKER_SCRIPT */ +#endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ #ifndef __optimize -- cgit v1.2.3 From 34845c939082093354a6ffbb1ebff599e30b9b22 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 26 Sep 2018 15:20:03 +0200 Subject: reset: Grammar s/more then once/more than once/ Fix grammar in reset_control_get_exclusive() documentation comment. Signed-off-by: Geert Uytterhoeven Signed-off-by: Philipp Zabel --- include/linux/reset.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 09732c36f351..29af6d6b2f4b 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -116,7 +116,7 @@ static inline int device_reset_optional(struct device *dev) * @id: reset line name * * Returns a struct reset_control or IS_ERR() condition containing errno. - * If this function is called more then once for the same reset_control it will + * If this function is called more than once for the same reset_control it will * return -EBUSY. * * See reset_control_get_shared for details on shared references to -- cgit v1.2.3 From b723a7911d028fb55f67a63c4c4d895f72e059d4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:32 +0300 Subject: fanotify: fix collision of internal and uapi mark flags The new mark flag FAN_MARK_FILESYSTEMS collides with existing internal flag FAN_MARK_ONDIR. Change internal flag value to avoid the collision. Fixes: d54f4fba889b ("fanotify: add API to attach/detach super block mark") 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 9c5ea3bdfaa0..e70fccc3757e 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -5,7 +5,7 @@ #include /* not valid from userspace, only kernel internal */ -#define FAN_MARK_ONDIR 0x00000100 +#define FAN_MARK_ONDIR 0x80000000 #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) -- cgit v1.2.3 From 007d1e8395eaa59b0e7ad9eb2b53a40859446a88 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:33 +0300 Subject: fsnotify: generalize handling of extra event flags FS_EVENT_ON_CHILD gets a special treatment in fsnotify() because it is not a flag specifying an event type, but rather an extra flags that may be reported along with another event and control the handling of the event by the backend. FS_ISDIR is also an "extra flag" and not an "event type" and therefore desrves the same treatment. With inotify/dnotify backends it was never possible to set FS_ISDIR in mark masks, so it did not matter. With fanotify backend, mark adding code jumps through hoops to avoid setting the FS_ISDIR in the commulative object mask. Separate the constant ALL_FSNOTIFY_EVENTS to ALL_FSNOTIFY_FLAGS and ALL_FSNOTIFY_EVENTS, so the latter can be used to test for specific event types. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8e91341cbd8a..135b973e44d1 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -68,15 +68,20 @@ #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM) +/* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN | \ FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \ FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ - FS_OPEN_PERM | FS_ACCESS_PERM | FS_EXCL_UNLINK | \ - FS_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \ + FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME) + +/* Extra flags that may be reported with event or control handling of events */ +#define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) +#define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) + struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; -- cgit v1.2.3 From a72fd224e37bf6a0630bce302deebbccbc236ba2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:34 +0300 Subject: fanotify: simplify handling of FAN_ONDIR fanotify mark add/remove code jumps through hoops to avoid setting the FS_ISDIR in the commulative object mask. That was just papering over a bug in fsnotify() handling of the FS_ISDIR extra flag. This bug is now fixed, so all the hoops can be removed along with the unneeded internal flag FAN_MARK_ONDIR. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index e70fccc3757e..a8c3fc54276d 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -4,9 +4,6 @@ #include -/* not valid from userspace, only kernel internal */ -#define FAN_MARK_ONDIR 0x80000000 - #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) -- cgit v1.2.3 From 23c9deeb3285d34fd243abb3d6b9f07db60c3cf4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:35 +0300 Subject: fanotify: deprecate uapi FAN_ALL_* constants We do not want to add new bits to the FAN_ALL_* uapi constants because they have been exposed to userspace. If there are programs out there using these constants, those programs could break if re-compiled with modified FAN_ALL_* constants and run on an old kernel. We deprecate the uapi constants FAN_ALL_* and define new FANOTIFY_* constants for internal use to replace them. New feature bits will be added only to the new constants. Cc: Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index a8c3fc54276d..4519b0988afe 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -7,4 +7,51 @@ #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) +/* + * Flags allowed to be passed from/to userspace. + * + * We intentionally do not add new bits to the old FAN_ALL_* constants, because + * they are uapi exposed constants. If there are programs out there using + * these constant, the programs may break if re-compiled with new uapi headers + * and then run on an old kernel. + */ +#define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ + FAN_CLASS_PRE_CONTENT) + +#define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | \ + FAN_CLOEXEC | FAN_NONBLOCK | \ + FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS) + +#define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ + FAN_MARK_FILESYSTEM) + +#define FANOTIFY_MARK_FLAGS (FANOTIFY_MARK_TYPE_BITS | \ + FAN_MARK_ADD | \ + FAN_MARK_REMOVE | \ + FAN_MARK_DONT_FOLLOW | \ + FAN_MARK_ONLYDIR | \ + FAN_MARK_IGNORED_MASK | \ + FAN_MARK_IGNORED_SURV_MODIFY | \ + FAN_MARK_FLUSH) + +/* Events that user can request to be notified on */ +#define FANOTIFY_EVENTS (FAN_ACCESS | FAN_MODIFY | \ + FAN_CLOSE | FAN_OPEN) + +/* Events that require a permission response from user */ +#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) + +/* Events that may be reported to user */ +#define FANOTIFY_OUTGOING_EVENTS (FANOTIFY_EVENTS | \ + FANOTIFY_PERM_EVENTS | \ + FAN_Q_OVERFLOW) + +/* Do not use these old uapi constants internally */ +#undef FAN_ALL_CLASS_BITS +#undef FAN_ALL_INIT_FLAGS +#undef FAN_ALL_MARK_FLAGS +#undef FAN_ALL_EVENTS +#undef FAN_ALL_PERM_EVENTS +#undef FAN_ALL_OUTGOING_EVENTS + #endif /* _LINUX_FANOTIFY_H */ -- cgit v1.2.3 From bdd5a46fe30653cb4d26c7c787a22159bf79eed9 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:37 +0300 Subject: fanotify: add BUILD_BUG_ON() to count the bits of fanotify constants Also define the FANOTIFY_EVENT_FLAGS consisting of the extra flags FAN_ONDIR and FAN_ON_CHILD. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 4519b0988afe..caf55c67fc6c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -41,11 +41,17 @@ /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) +/* Extra flags that may be reported with event or control handling of events */ +#define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) + /* Events that may be reported to user */ #define FANOTIFY_OUTGOING_EVENTS (FANOTIFY_EVENTS | \ FANOTIFY_PERM_EVENTS | \ FAN_Q_OVERFLOW) +#define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ + FANOTIFY_EVENT_FLAGS) + /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS #undef FAN_ALL_INIT_FLAGS -- cgit v1.2.3 From bbb4c4323a4d9cb5ca04db904aa3050a7586839a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 4 Oct 2018 14:27:55 +0100 Subject: dns: Allow the dns resolver to retrieve a server set Allow the DNS resolver to retrieve a set of servers and their associated addresses, ports, preference and weight ratings. In terms of communication with userspace, "srv=1" is added to the callout string (the '1' indicating the maximum data version supported by the kernel) to ask the userspace side for this. If the userspace side doesn't recognise it, it will ignore the option and return the usual text address list. If the userspace side does recognise it, it will return some binary data that begins with a zero byte that would cause the string parsers to give an error. The second byte contains the version of the data in the blob (this may be between 1 and the version specified in the callout data). The remainder of the payload is version-specific. In version 1, the payload looks like (note that this is packed): u8 Non-string marker (ie. 0) u8 Content (0 => Server list) u8 Version (ie. 1) u8 Source (eg. DNS_RECORD_FROM_DNS_SRV) u8 Status (eg. DNS_LOOKUP_GOOD) u8 Number of servers foreach-server { u16 Name length (LE) u16 Priority (as per SRV record) (LE) u16 Weight (as per SRV record) (LE) u16 Port (LE) u8 Source (eg. DNS_RECORD_FROM_NSS) u8 Status (eg. DNS_LOOKUP_GOT_NOT_FOUND) u8 Protocol (eg. DNS_SERVER_PROTOCOL_UDP) u8 Number of addresses char[] Name (not NUL-terminated) foreach-address { u8 Family (AF_INET{,6}) union { u8[4] ipv4_addr u8[16] ipv6_addr } } } This can then be used to fetch a whole cell's VL-server configuration for AFS, for example. Signed-off-by: David Howells Signed-off-by: David S. Miller --- include/linux/dns_resolver.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h index 6ac3cad9aef1..34a744a1bafc 100644 --- a/include/linux/dns_resolver.h +++ b/include/linux/dns_resolver.h @@ -24,11 +24,9 @@ #ifndef _LINUX_DNS_RESOLVER_H #define _LINUX_DNS_RESOLVER_H -#ifdef __KERNEL__ +#include extern int dns_query(const char *type, const char *name, size_t namelen, const char *options, char **_result, time64_t *_expiry); -#endif /* KERNEL */ - #endif /* _LINUX_DNS_RESOLVER_H */ -- cgit v1.2.3 From 817e9bc8cc04e5c70592525b96812c46c1aa1c46 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 4 Oct 2018 09:57:23 -0700 Subject: Revert "serial:serial_core: Allow use of CTS for PPS line discipline" This reverts commit c550f01c810f2197c98e6e3103f81797f5e063be. Turns out the samsung tty driver is mucking around in the "unused" port fields and this patch breaks that code :( So we need to fix that driver up before this can be accepted. Reported-by: Stephen Rothwell Cc: Steve Sakoman Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 4e2ba4894dcc..047fa67d039b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -257,8 +257,7 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char pps_4wire; /* CTS instead of DCD */ - unsigned char unused; + unsigned char unused[2]; 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 5d5a0ab1a7918fce5ca5c0fb1871a3e2000f85de Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 1 Oct 2018 10:54:51 -0500 Subject: of: Fix property name in of_node_get_device_type Commit 0413bedabc88 ("of: Add device_type access helper functions") added a new helper not yet used in preparation for some treewide clean up of accesses to 'device_type' properties. Unfortunately, there's an error and 'type' was used for the property name. Fix this. Fixes: 0413bedabc88 ("of: Add device_type access helper functions") Cc: Frank Rowand Signed-off-by: Rob Herring --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index f581531d797e..04cef4490efc 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -991,7 +991,7 @@ static inline struct device_node *of_find_matching_node( static inline const char *of_node_get_device_type(const struct device_node *np) { - return of_get_property(np, "type", NULL); + return of_get_property(np, "device_type", NULL); } static inline bool of_node_is_type(const struct device_node *np, const char *type) -- cgit v1.2.3 From 479adb89a97b0a33e5a9d702119872cc82ca21aa Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 4 Oct 2018 13:28:08 -0700 Subject: cgroup: Fix dom_cgrp propagation when enabling threaded mode A cgroup which is already a threaded domain may be converted into a threaded cgroup if the prerequisite conditions are met. When this happens, all threaded descendant should also have their ->dom_cgrp updated to the new threaded domain cgroup. Unfortunately, this propagation was missing leading to the following failure. # cd /sys/fs/cgroup/unified # cat cgroup.subtree_control # show that no controllers are enabled # mkdir -p mycgrp/a/b/c # echo threaded > mycgrp/a/b/cgroup.type At this point, the hierarchy looks as follows: mycgrp [d] a [dt] b [t] c [inv] Now let's make node "a" threaded (and thus "mycgrp" s made "domain threaded"): # echo threaded > mycgrp/a/cgroup.type By this point, we now have a hierarchy that looks as follows: mycgrp [dt] a [t] b [t] c [inv] But, when we try to convert the node "c" from "domain invalid" to "threaded", we get ENOTSUP on the write(): # echo threaded > mycgrp/a/b/c/cgroup.type sh: echo: write error: Operation not supported This patch fixes the problem by * Moving the opencoded ->dom_cgrp save and restoration in cgroup_enable_threaded() into cgroup_{save|restore}_control() so that mulitple cgroups can be handled. * Updating all threaded descendants' ->dom_cgrp to point to the new dom_cgrp when enabling threaded mode. Signed-off-by: Tejun Heo Reported-and-tested-by: "Michael Kerrisk (man-pages)" Reported-by: Amin Jamali Reported-by: Joao De Almeida Pereira Link: https://lore.kernel.org/r/CAKgNAkhHYCMn74TCNiMJ=ccLd7DcmXSbvw3CbZ1YREeG7iJM5g@mail.gmail.com Fixes: 454000adaa2a ("cgroup: introduce cgroup->dom_cgrp and threaded css_set handling") Cc: stable@vger.kernel.org # v4.14+ --- include/linux/cgroup-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ff20b677fb9f..22254c1fe1c5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -412,6 +412,7 @@ struct cgroup { * specific task are charged to the dom_cgrp. */ struct cgroup *dom_cgrp; + struct cgroup *old_dom_cgrp; /* used while enabling threaded */ /* per-cpu recursive resource statistics */ struct cgroup_rstat_cpu __percpu *rstat_cpu; -- cgit v1.2.3 From d67f34c19a679436dd2963b588015e119279e7a8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 17 Sep 2018 14:45:34 +0200 Subject: clocksource: Provide clocksource_arch_init() Architectures have extra archdata in the clocksource, e.g. for VDSO support. There are no sanity checks or general initializations for this available. Add support for that. Signed-off-by: Thomas Gleixner Acked-by: Andy Lutomirski Acked-by: John Stultz Cc: Peter Zijlstra Cc: Matt Rickard Cc: Stephen Boyd Cc: Florian Weimer Cc: "K. Y. Srinivasan" Cc: Vitaly Kuznetsov Cc: devel@linuxdriverproject.org Cc: virtualization@lists.linux-foundation.org Cc: Paolo Bonzini Cc: Arnd Bergmann Cc: Juergen Gross Link: https://lkml.kernel.org/r/20180917130706.973042587@linutronix.de --- include/linux/clocksource.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 308918928767..6e6b86f9046d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -241,6 +241,11 @@ static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz __clocksource_update_freq_scale(cs, 1000, khz); } +#ifdef CONFIG_ARCH_CLOCKSOURCE_INIT +extern void clocksource_arch_init(struct clocksource *cs); +#else +static inline void clocksource_arch_init(struct clocksource *cs) { } +#endif extern int timekeeping_notify(struct clocksource *clock); -- cgit v1.2.3 From fae29f135ef4a86228d3ce13b61babf0d3031118 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 25 Sep 2018 12:35:18 -0400 Subject: hwrng: core - document the quality field quality field is currently documented as being 'per mill'. In fact the math involved is: add_hwgenerator_randomness((void *)rng_fillbuf, rc, rc * current_quality * 8 >> 10); thus the actual definition is "bits of entropy per 1024 bits of input". The current documentation seems to have confused multiple people in the past, let's fix the documentation to match code. An alternative is to change core to match driver expectations, replacing rc * current_quality * 8 >> 10 with rc * current_quality / 1000 but that has performance costs, so probably isn't a good option. Fixes: 0f734e6e768 ("hwrng: add per-device entropy derating") Reported-by: "Dr. David Alan Gilbert" Signed-off-by: Michael S. Tsirkin Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index bee0827766a3..c0b93e0ff0c0 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -33,7 +33,8 @@ * and max is a multiple of 4 and >= 32 bytes. * @priv: Private data, for use by the RNG driver. * @quality: Estimation of true entropy in RNG's bitstream - * (per mill). + * (in bits of entropy per 1024 bits of input; + * valid values: 1 to 1024, or 0 for unknown). */ struct hwrng { const char *name; -- cgit v1.2.3 From 9d2f67e43b73e8af7438be219b66a5de0cfa8bd9 Mon Sep 17 00:00:00 2001 From: Jianfeng Tan Date: Sat, 29 Sep 2018 15:41:27 +0000 Subject: net/packet: fix packet drop as of virtio gso When we use raw socket as the vhost backend, a packet from virito with gso offloading information, cannot be sent out in later validaton at xmit path, as we did not set correct skb->protocol which is further used for looking up the gso function. To fix this, we set this field according to virito hdr information. Fixes: e858fae2b0b8f4 ("virtio_net: use common code for virtio_net_hdr and skb GSO conversion") Signed-off-by: Jianfeng Tan Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 9397628a1967..cb462f9ab7dd 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -5,6 +5,24 @@ #include #include +static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, + const struct virtio_net_hdr *hdr) +{ + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + case VIRTIO_NET_HDR_GSO_UDP: + skb->protocol = cpu_to_be16(ETH_P_IP); + break; + case VIRTIO_NET_HDR_GSO_TCPV6: + skb->protocol = cpu_to_be16(ETH_P_IPV6); + break; + default: + return -EINVAL; + } + + return 0; +} + static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) -- cgit v1.2.3 From 661b8d1b0e3a745e25f05adef2ebd00d830eeea7 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 1 Oct 2018 14:51:33 +0200 Subject: net: add umem reference in netdev{_rx}_queue These references to the umem will be used to store information on what kind of AF_XDP umem that is bound to a queue id, if any. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann --- 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 1cbbf77a685f..8318f79586c2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -609,6 +609,9 @@ struct netdev_queue { /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; +#ifdef CONFIG_XDP_SOCKETS + struct xdp_umem *umem; +#endif /* * write-mostly part */ @@ -738,6 +741,9 @@ struct netdev_rx_queue { struct kobject kobj; struct net_device *dev; struct xdp_rxq_info xdp_rxq; +#ifdef CONFIG_XDP_SOCKETS + struct xdp_umem *umem; +#endif } ____cacheline_aligned_in_smp; /* -- cgit v1.2.3 From c2a90025ad09d830c8d8ae69f485eac6aaaa2472 Mon Sep 17 00:00:00 2001 From: Quentin Schulz Date: Thu, 4 Oct 2018 14:22:03 +0200 Subject: phy: add QSGMII and PCIE modes Prepare for upcoming phys that'll handle QSGMII or PCIe. Reviewed-by: Florian Fainelli Signed-off-by: Quentin Schulz Signed-off-by: David S. Miller --- include/linux/phy/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 9713aebdd348..03b319f89a34 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -37,9 +37,11 @@ enum phy_mode { PHY_MODE_USB_OTG, PHY_MODE_SGMII, PHY_MODE_2500SGMII, + PHY_MODE_QSGMII, PHY_MODE_10GKR, PHY_MODE_UFS_HS_A, PHY_MODE_UFS_HS_B, + PHY_MODE_PCIE, }; /** -- cgit v1.2.3 From 017b1660df89f5fb4bfe66c34e35f7d2031100c7 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Oct 2018 15:51:29 -0700 Subject: mm: migration: fix migration of huge PMD shared pages The page migration code employs try_to_unmap() to try and unmap the source page. This is accomplished by using rmap_walk to find all vmas where the page is mapped. This search stops when page mapcount is zero. For shared PMD huge pages, the page map count is always 1 no matter the number of mappings. Shared mappings are tracked via the reference count of the PMD page. Therefore, try_to_unmap stops prematurely and does not completely unmap all mappings of the source page. This problem can result is data corruption as writes to the original source page can happen after contents of the page are copied to the target page. Hence, data is lost. This problem was originally seen as DB corruption of shared global areas after a huge page was soft offlined due to ECC memory errors. DB developers noticed they could reproduce the issue by (hotplug) offlining memory used to back huge pages. A simple testcase can reproduce the problem by creating a shared PMD mapping (note that this must be at least PUD_SIZE in size and PUD_SIZE aligned (1GB on x86)), and using migrate_pages() to migrate process pages between nodes while continually writing to the huge pages being migrated. To fix, have the try_to_unmap_one routine check for huge PMD sharing by calling huge_pmd_unshare for hugetlbfs huge pages. If it is a shared mapping it will be 'unshared' which removes the page table entry and drops the reference on the PMD page. After this, flush caches and TLB. mmu notifiers are called before locking page tables, but we can not be sure of PMD sharing until page tables are locked. Therefore, check for the possibility of PMD sharing before locking so that notifiers can prepare for the worst possible case. Link: http://lkml.kernel.org/r/20180823205917.16297-2-mike.kravetz@oracle.com [mike.kravetz@oracle.com: make _range_in_vma() a static inline] Link: http://lkml.kernel.org/r/6063f215-a5c8-2f0c-465a-2c515ddc952d@oracle.com Fixes: 39dde65c9940 ("shared page table for hugetlb page") Signed-off-by: Mike Kravetz Acked-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Acked-by: Michal Hocko Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Jerome Glisse Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb.h | 14 ++++++++++++++ include/linux/mm.h | 6 ++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6b68e345f0ca..087fd5f48c91 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, 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); +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, int write); struct page *follow_huge_pd(struct vm_area_struct *vma, @@ -170,6 +172,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } +static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..0416a7204be3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2455,6 +2455,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } +static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); -- cgit v1.2.3 From 1bb89893d4fa8275333b3ed74fb0379d63025f9a Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 14 Sep 2018 19:37:23 -0500 Subject: remoteproc: Add missing kernel-doc comment for auto-boot The commit ddf711872c9d ("remoteproc: Introduce auto-boot flag") introduced the auto-boot flag but missed adding the corresponding kernel-doc comment. Add the same. Signed-off-by: Suman Anna 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 e3c5d856b6da..75f9ca05b865 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -439,6 +439,7 @@ struct rproc_dump_segment { * @cached_table: copy of the resource table * @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 * @dump_segments: list of segments in the firmware */ struct rproc { -- cgit v1.2.3 From 992b649a3f013465d8128da02e5449def662a4c3 Mon Sep 17 00:00:00 2001 From: Lianbo Jiang Date: Sun, 30 Sep 2018 16:37:41 +0800 Subject: kdump, proc/vmcore: Enable kdumping encrypted memory with SME enabled In the kdump kernel, the memory of the first kernel needs to be dumped into the vmcore file. If SME is enabled in the first kernel, the old memory has to be remapped with the memory encryption mask in order to access it properly. Split copy_oldmem_page() functionality to handle encrypted memory properly. [ bp: Heavily massage everything. ] Signed-off-by: Lianbo Jiang Signed-off-by: Borislav Petkov Cc: kexec@lists.infradead.org Cc: tglx@linutronix.de Cc: mingo@redhat.com Cc: hpa@zytor.com Cc: akpm@linux-foundation.org Cc: dan.j.williams@intel.com Cc: bhelgaas@google.com Cc: baiyaowei@cmss.chinamobile.com Cc: tiwai@suse.de Cc: brijesh.singh@amd.com Cc: dyoung@redhat.com Cc: bhe@redhat.com Cc: jroedel@suse.de Link: https://lkml.kernel.org/r/be7b47f9-6be6-e0d1-2c2a-9125bc74b818@redhat.com --- include/linux/crash_dump.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 3e4ba9d753c8..f774c5eb9e3c 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -26,6 +26,10 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); +extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, + int userbuf); + void vmcore_cleanup(void); /* Architecture code defines this if there are other possible ELF -- cgit v1.2.3 From 99c65fa7c59ff558e70db8aa61bbdece5d3a9588 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 8 Oct 2018 00:20:07 -0700 Subject: dma-debug: Check for drivers mapping invalid addresses in dma_map_single() I recently debugged a DMA mapping oops where a driver was trying to map a buffer returned from request_firmware() with dma_map_single(). Memory returned from request_firmware() is mapped into the vmalloc region and this isn't a valid region to map with dma_map_single() per the DMA documentation's "What memory is DMA'able?" section. Unfortunately, we don't really check that in the DMA debugging code, so enabling DMA debugging doesn't help catch this problem. Let's add a new DMA debug function to check for a vmalloc address or an invalid virtual address and print a warning if this happens. This makes it a little easier to debug these sorts of problems, instead of seeing odd behavior or crashes when drivers attempt to map the vmalloc space for DMA. Cc: Marek Szyprowski Reviewed-by: Robin Murphy Signed-off-by: Stephen Boyd Signed-off-by: Christoph Hellwig --- include/linux/dma-debug.h | 8 ++++++++ include/linux/dma-mapping.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index a785f2507159..30213adbb6b9 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -32,6 +32,9 @@ extern void dma_debug_add_bus(struct bus_type *bus); extern int dma_debug_resize_entries(u32 num_entries); +extern void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len); + extern void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction, dma_addr_t dma_addr, @@ -103,6 +106,11 @@ static inline int dma_debug_resize_entries(u32 num_entries) return 0; } +static inline void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len) +{ +} + static inline void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction, dma_addr_t dma_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 562af6b45f23..547a48bcfa3d 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -229,6 +229,7 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, dma_addr_t addr; BUG_ON(!valid_dma_direction(dir)); + debug_dma_map_single(dev, ptr, size); addr = ops->map_page(dev, virt_to_page(ptr), offset_in_page(ptr), size, dir, attrs); -- cgit v1.2.3 From c941ce9c282cc606e6517356fcc186a9da2b4ab9 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Sun, 7 Oct 2018 12:56:47 +0100 Subject: bpf: add verifier callback to get stack usage info for offloaded progs In preparation for BPF-to-BPF calls in offloaded programs, add a new function attribute to the struct bpf_prog_offload_ops so that drivers supporting eBPF offload can hook at the end of program verification, and potentially extract information collected by the verifier. Implement a minimal callback (returning 0) in the drivers providing the structs, namely netdevsim and nfp. This will be useful in the nfp driver, in later commits, to extract the number of subprograms as well as the stack depth for those subprograms. Signed-off-by: Quentin Monnet Reviewed-by: Jiong Wang Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 027697b6a22f..9b558713447f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -263,6 +263,7 @@ struct bpf_verifier_ops { struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); + int (*finalize)(struct bpf_verifier_env *env); }; struct bpf_prog_offload { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7b6fd2ab3263..9e8056ec20fa 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -245,5 +245,6 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); +int bpf_prog_offload_finalize(struct bpf_verifier_env *env); #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From cbf6d82cad4a507475d92d380228302fe668dd94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Thu, 30 Aug 2018 01:32:05 +0200 Subject: mmc: core: add helper to see if a host is doing a retune MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a helper to allow host drivers checking if a retune is in progress. Signed-off-by: Niklas Söderlund Reviewed-by: Wolfram Sang Tested-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index beed7121c781..2a5fe75dd082 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -569,6 +569,11 @@ static inline bool mmc_can_retune(struct mmc_host *host) return host->can_retune == 1; } +static inline bool mmc_doing_retune(struct mmc_host *host) +{ + return host->doing_retune == 1; +} + static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) { return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE; -- cgit v1.2.3 From 9ef986a697c6d733d86e76d9870b4f1f60512b7a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 20 Sep 2018 16:01:10 -0700 Subject: mmc: mmci: Drop support for pdata GPIO numbers All the machines using the MMCI are passing GPIOs for the card detect and write protect using the device tree or descriptor table (one single case, Integrator/AP IM-PD1). Drop support for passing global GPIO numbers through platform data, noone is using it. Signed-off-by: Linus Walleij Signed-off-by: Ulf Hansson --- include/linux/amba/mmci.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index da8357ba11bc..c92ebc39fc1f 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -18,20 +18,13 @@ * mask into a value to be binary (or set some other custom bits * in MMCIPWR) or:ed and written into the MMCIPWR register of the * block. May also control external power based on the power_mode. - * @status: if no GPIO read function was given to the block in - * gpio_wp (below) this function will be called to determine - * whether a card is present in the MMC slot or not - * @gpio_wp: read this GPIO pin to see if the card is write protected - * @gpio_cd: read this GPIO pin to detect card insertion - * @cd_invert: true if the gpio_cd pin value is active low + * @status: if no GPIO line was given to the block in this function will + * be called to determine whether a card is present in the MMC slot or not */ struct mmci_platform_data { unsigned int ocr_mask; int (*ios_handler)(struct device *, struct mmc_ios *); unsigned int (*status)(struct device *); - int gpio_wp; - int gpio_cd; - bool cd_invert; }; #endif -- cgit v1.2.3 From 43b7358df63adff21aa81b349d9080954bf1c372 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 23 Sep 2018 09:03:21 +0200 Subject: mmc: sdhci: pxav3: Delete GPIO handling The platform data for the PXAv3 driver allows passing a card detect GPIO, but this code is not used in the kernel. In order to not encourage the use of the old global GPIO numberspace we need to remove this. Card detect (and write protect) GPIO can easily be added into the driver using machine descriptor tables instead, and the descriptor-based (gpiod) variants of the slot GPIO APIs. Cc: Jisheng Zhang Cc: Adrian Hunter Signed-off-by: Linus Walleij Reviewed-by: Jisheng Zhang Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/platform_data/pxa_sdhci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/pxa_sdhci.h b/include/linux/platform_data/pxa_sdhci.h index 9e20c2fb4ffd..4977c06d8a86 100644 --- a/include/linux/platform_data/pxa_sdhci.h +++ b/include/linux/platform_data/pxa_sdhci.h @@ -33,8 +33,6 @@ * 1: choose feedback clk + delay value * 2: choose internal clk * @clk_delay_enable: enable clk_delay or not, used on pxa910 - * @ext_cd_gpio: gpio pin used for external CD line - * @ext_cd_gpio_invert: invert values for external CD gpio line * @max_speed: the maximum speed supported * @host_caps: Standard MMC host capabilities bit field. * @quirks: quirks of platfrom @@ -46,8 +44,6 @@ struct sdhci_pxa_platdata { unsigned int clk_delay_cycles; unsigned int clk_delay_sel; bool clk_delay_enable; - unsigned int ext_cd_gpio; - bool ext_cd_gpio_invert; unsigned int max_speed; u32 host_caps; u32 host_caps2; -- cgit v1.2.3 From 7838a8ddc80b2aa82d364d39042ca422f7748885 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 24 Sep 2018 13:30:50 +0200 Subject: mmc: omap_hsmmc: Kill off cover detection Cover detection appears to be a feature protecting the SD card on mobile phones with a slide-cover, such as some Nokia phones. The idea seems to be to not allow access to the SD card when the cover is open. It is only usable with platform data from board files, but no board file in the kernel is using it, yet it takes up a sizeable chunk of code in the OMAP HSMMC driver. Since we do not add new board files for the OMAPs any target that need this should anyway reimplement it properly using the device tree, so delete this legacy code. The driver is marked as orphan in MAINTAINERS by the way. Cc: Tony Lindgren Cc: linux-omap@vger.kernel.org Signed-off-by: Linus Walleij Acked-by: Tony Lindgren Acked-by: Kishon Vijay Abraham I Signed-off-by: Ulf Hansson --- include/linux/platform_data/hsmmc-omap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h index 73d9098ada2d..c055d7eda085 100644 --- a/include/linux/platform_data/hsmmc-omap.h +++ b/include/linux/platform_data/hsmmc-omap.h @@ -71,7 +71,6 @@ struct omap_hsmmc_platform_data { char *version; int gpio_cd; /* gpio (card detect) */ - int gpio_cod; /* gpio (cover detect) */ int gpio_wp; /* gpio (write protect) */ /* if we have special card, init it using this callback */ void (*init_card)(struct mmc_card *card); -- cgit v1.2.3 From e63201f19438372fcb45977d8e14c6ab5807d55b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 24 Sep 2018 13:30:51 +0200 Subject: mmc: omap_hsmmc: Delete platform data GPIO CD and WP The OMAP HSMMC driver has some elaborate and hairy handling for passing GPIO card detect and write protect lines from a boardfile into the driver: the machine defines a struct omap2_hsmmc_info that is copied into struct omap_hsmmc_platform_data by omap_hsmmc_pdata_init() in arch/arm/mach-omap2/hsmmc.c. However the .gpio_cd and .gpio_wp fields are not copied from omap2_hsmmc_info to omap_hsmmc_platform_data by omap_hsmmc_pdata_init() so they remain unused. The only platform defining omap2_hsmmc_info also define both to -1, unused. It turn out there are no boardfiles passing any valid GPIO lines into the OMAP HSMMC driver at all. And since we are not going to add any more OMAP2 boardfiles, we can delete this card detect and write protect handling altogether. This seems to also fix a bug: the card detect callback mmc_gpio_get_cd() in the slot GPIO core needs to be called by drivers utilizing slot GPIO. It appears the the boardfile quirks were not doing this right, so this would only get called for boardfiles, i.e. since no boardfile was using it, never. Just assign mmc_gpio_get_cd() unconditionally to omap_hsmmc_ops .get_cd() so card detects from the device tree works. AFAICT card detect with GPIO lines assigned from mmc_of_parse() are not working at the moment, but that is no regression since it probably never worked. Cc: Tony Lindgren Cc: linux-omap@vger.kernel.org Signed-off-by: Linus Walleij Acked-by: Tony Lindgren Signed-off-by: Ulf Hansson --- include/linux/platform_data/hsmmc-omap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h index c055d7eda085..85da11916bd5 100644 --- a/include/linux/platform_data/hsmmc-omap.h +++ b/include/linux/platform_data/hsmmc-omap.h @@ -70,8 +70,6 @@ struct omap_hsmmc_platform_data { /* string specifying a particular variant of hardware */ char *version; - int gpio_cd; /* gpio (card detect) */ - int gpio_wp; /* gpio (write protect) */ /* if we have special card, init it using this callback */ void (*init_card)(struct mmc_card *card); -- cgit v1.2.3 From d0a6a87e40da49cfc7954c491d3065a25a641b29 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:38 +0300 Subject: fanotify: support reporting thread id instead of process id In order to identify which thread triggered the event in a multi-threaded program, add the FAN_REPORT_TID flag in fanotify_init to opt-in for reporting the event creator's thread id information. Signed-off-by: nixiaoming Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index caf55c67fc6c..a5a60691e48b 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -19,6 +19,7 @@ FAN_CLASS_PRE_CONTENT) #define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | \ + FAN_REPORT_TID | \ FAN_CLOEXEC | FAN_NONBLOCK | \ FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS) -- cgit v1.2.3 From 0792a2c8e0bbda3605b8d42c6b9635be7b19982a Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 11 Sep 2018 20:18:44 -0400 Subject: macintosh: Use common code to access RTC Now that the 68k Mac port has adopted the via-pmu driver, the same RTC code can be shared between m68k and powerpc. Replace duplicated code in arch/powerpc and arch/m68k with common RTC accessors for Cuda and PMU. Drop the problematic WARN_ON which was introduced in commit 22db552b50fa ("powerpc/powermac: Fix rtc read/write functions"). Tested-by: Stan Johnson Signed-off-by: Finn Thain Cc: Geert Uytterhoeven Cc: Arnd Bergmann Acked-by: Geert Uytterhoeven Signed-off-by: Michael Ellerman --- include/linux/cuda.h | 4 ++++ include/linux/pmu.h | 4 ++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cuda.h b/include/linux/cuda.h index 056867f09a01..45bfe9d61271 100644 --- a/include/linux/cuda.h +++ b/include/linux/cuda.h @@ -8,6 +8,7 @@ #ifndef _LINUX_CUDA_H #define _LINUX_CUDA_H +#include #include @@ -16,4 +17,7 @@ extern int cuda_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); extern void cuda_poll(void); +extern time64_t cuda_get_time(void); +extern int cuda_set_rtc_time(struct rtc_time *tm); + #endif /* _LINUX_CUDA_H */ diff --git a/include/linux/pmu.h b/include/linux/pmu.h index 9ac8fc60ad49..52453a24a24f 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -9,6 +9,7 @@ #ifndef _LINUX_PMU_H #define _LINUX_PMU_H +#include #include @@ -36,6 +37,9 @@ static inline void pmu_resume(void) extern void pmu_enable_irled(int on); +extern time64_t pmu_get_time(void); +extern int pmu_set_rtc_time(struct rtc_time *tm); + extern void pmu_restart(void); extern void pmu_shutdown(void); extern void pmu_unlock(void); -- cgit v1.2.3 From edbee095fafb4b727b51032bdc41e345f95bbc20 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 7 Oct 2018 21:04:42 +0800 Subject: firmware: imx: add SCU firmware driver support The System Controller Firmware (SCFW) is a low-level system function which runs on a dedicated Cortex-M core to provide power, clock, and resource management. It exists on some i.MX8 processors. e.g. i.MX8QM (QM, QP), and i.MX8QX (QXP, DX). This patch implements the SCU firmware IPC function and the common message sending API sc_call_rpc. Cc: Shawn Guo Cc: Fabio Estevam Cc: Jassi Brar Reviewed-by: Sascha Hauer Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- include/linux/firmware/imx/ipc.h | 59 ++++ include/linux/firmware/imx/sci.h | 16 + include/linux/firmware/imx/types.h | 617 +++++++++++++++++++++++++++++++++++++ 3 files changed, 692 insertions(+) create mode 100644 include/linux/firmware/imx/ipc.h create mode 100644 include/linux/firmware/imx/sci.h create mode 100644 include/linux/firmware/imx/types.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/ipc.h b/include/linux/firmware/imx/ipc.h new file mode 100644 index 000000000000..6312c8cb084a --- /dev/null +++ b/include/linux/firmware/imx/ipc.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2018 NXP + * + * Header file for the IPC implementation. + */ + +#ifndef _SC_IPC_H +#define _SC_IPC_H + +#include +#include + +#define IMX_SC_RPC_VERSION 1 +#define IMX_SC_RPC_MAX_MSG 8 + +struct imx_sc_ipc; + +enum imx_sc_rpc_svc { + IMX_SC_RPC_SVC_UNKNOWN = 0, + IMX_SC_RPC_SVC_RETURN = 1, + IMX_SC_RPC_SVC_PM = 2, + IMX_SC_RPC_SVC_RM = 3, + IMX_SC_RPC_SVC_TIMER = 5, + IMX_SC_RPC_SVC_PAD = 6, + IMX_SC_RPC_SVC_MISC = 7, + IMX_SC_RPC_SVC_IRQ = 8, + IMX_SC_RPC_SVC_ABORT = 9 +}; + +struct imx_sc_rpc_msg { + uint8_t ver; + uint8_t size; + uint8_t svc; + uint8_t func; +}; + +/* + * This is an function to send an RPC message over an IPC channel. + * It is called by client-side SCFW API function shims. + * + * @param[in] ipc IPC handle + * @param[in,out] msg handle to a message + * @param[in] have_resp response flag + * + * If have_resp is true then this function waits for a response + * and returns the result in msg. + */ +int imx_scu_call_rpc(struct imx_sc_ipc *ipc, void *msg, bool have_resp); + +/* + * This function gets the default ipc handle used by SCU + * + * @param[out] ipc sc ipc handle + * + * @return Returns an error code (0 = success, failed if < 0) + */ +int imx_scu_get_handle(struct imx_sc_ipc **ipc); +#endif /* _SC_IPC_H */ diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h new file mode 100644 index 000000000000..ff3227ad8d7c --- /dev/null +++ b/include/linux/firmware/imx/sci.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * + * Header file containing the public System Controller Interface (SCI) + * definitions. + */ + +#ifndef _SC_SCI_H +#define _SC_SCI_H + +#include +#include + +#endif /* _SC_SCI_H */ diff --git a/include/linux/firmware/imx/types.h b/include/linux/firmware/imx/types.h new file mode 100644 index 000000000000..9cbf0c4a6069 --- /dev/null +++ b/include/linux/firmware/imx/types.h @@ -0,0 +1,617 @@ +/* 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 resource. Resources include peripherals + * and bus masters (but not memory regions). Note items from list should + * never be changed or removed (only added to at the end of the list). + */ +enum imx_sc_rsrc { + IMX_SC_R_A53 = 0, + IMX_SC_R_A53_0 = 1, + IMX_SC_R_A53_1 = 2, + IMX_SC_R_A53_2 = 3, + IMX_SC_R_A53_3 = 4, + IMX_SC_R_A72 = 5, + IMX_SC_R_A72_0 = 6, + IMX_SC_R_A72_1 = 7, + IMX_SC_R_A72_2 = 8, + IMX_SC_R_A72_3 = 9, + IMX_SC_R_CCI = 10, + IMX_SC_R_DB = 11, + IMX_SC_R_DRC_0 = 12, + IMX_SC_R_DRC_1 = 13, + IMX_SC_R_GIC_SMMU = 14, + IMX_SC_R_IRQSTR_M4_0 = 15, + IMX_SC_R_IRQSTR_M4_1 = 16, + IMX_SC_R_SMMU = 17, + IMX_SC_R_GIC = 18, + IMX_SC_R_DC_0_BLIT0 = 19, + IMX_SC_R_DC_0_BLIT1 = 20, + IMX_SC_R_DC_0_BLIT2 = 21, + IMX_SC_R_DC_0_BLIT_OUT = 22, + IMX_SC_R_DC_0_CAPTURE0 = 23, + IMX_SC_R_DC_0_CAPTURE1 = 24, + IMX_SC_R_DC_0_WARP = 25, + IMX_SC_R_DC_0_INTEGRAL0 = 26, + IMX_SC_R_DC_0_INTEGRAL1 = 27, + IMX_SC_R_DC_0_VIDEO0 = 28, + IMX_SC_R_DC_0_VIDEO1 = 29, + IMX_SC_R_DC_0_FRAC0 = 30, + IMX_SC_R_DC_0_FRAC1 = 31, + IMX_SC_R_DC_0 = 32, + IMX_SC_R_GPU_2_PID0 = 33, + IMX_SC_R_DC_0_PLL_0 = 34, + IMX_SC_R_DC_0_PLL_1 = 35, + IMX_SC_R_DC_1_BLIT0 = 36, + IMX_SC_R_DC_1_BLIT1 = 37, + IMX_SC_R_DC_1_BLIT2 = 38, + IMX_SC_R_DC_1_BLIT_OUT = 39, + IMX_SC_R_DC_1_CAPTURE0 = 40, + IMX_SC_R_DC_1_CAPTURE1 = 41, + IMX_SC_R_DC_1_WARP = 42, + IMX_SC_R_DC_1_INTEGRAL0 = 43, + IMX_SC_R_DC_1_INTEGRAL1 = 44, + IMX_SC_R_DC_1_VIDEO0 = 45, + IMX_SC_R_DC_1_VIDEO1 = 46, + IMX_SC_R_DC_1_FRAC0 = 47, + IMX_SC_R_DC_1_FRAC1 = 48, + IMX_SC_R_DC_1 = 49, + IMX_SC_R_GPU_3_PID0 = 50, + IMX_SC_R_DC_1_PLL_0 = 51, + IMX_SC_R_DC_1_PLL_1 = 52, + IMX_SC_R_SPI_0 = 53, + IMX_SC_R_SPI_1 = 54, + IMX_SC_R_SPI_2 = 55, + IMX_SC_R_SPI_3 = 56, + IMX_SC_R_UART_0 = 57, + IMX_SC_R_UART_1 = 58, + IMX_SC_R_UART_2 = 59, + IMX_SC_R_UART_3 = 60, + IMX_SC_R_UART_4 = 61, + IMX_SC_R_EMVSIM_0 = 62, + IMX_SC_R_EMVSIM_1 = 63, + IMX_SC_R_DMA_0_CH0 = 64, + IMX_SC_R_DMA_0_CH1 = 65, + IMX_SC_R_DMA_0_CH2 = 66, + IMX_SC_R_DMA_0_CH3 = 67, + IMX_SC_R_DMA_0_CH4 = 68, + IMX_SC_R_DMA_0_CH5 = 69, + IMX_SC_R_DMA_0_CH6 = 70, + IMX_SC_R_DMA_0_CH7 = 71, + IMX_SC_R_DMA_0_CH8 = 72, + IMX_SC_R_DMA_0_CH9 = 73, + IMX_SC_R_DMA_0_CH10 = 74, + IMX_SC_R_DMA_0_CH11 = 75, + IMX_SC_R_DMA_0_CH12 = 76, + IMX_SC_R_DMA_0_CH13 = 77, + IMX_SC_R_DMA_0_CH14 = 78, + IMX_SC_R_DMA_0_CH15 = 79, + IMX_SC_R_DMA_0_CH16 = 80, + IMX_SC_R_DMA_0_CH17 = 81, + IMX_SC_R_DMA_0_CH18 = 82, + IMX_SC_R_DMA_0_CH19 = 83, + IMX_SC_R_DMA_0_CH20 = 84, + IMX_SC_R_DMA_0_CH21 = 85, + IMX_SC_R_DMA_0_CH22 = 86, + IMX_SC_R_DMA_0_CH23 = 87, + IMX_SC_R_DMA_0_CH24 = 88, + IMX_SC_R_DMA_0_CH25 = 89, + IMX_SC_R_DMA_0_CH26 = 90, + IMX_SC_R_DMA_0_CH27 = 91, + IMX_SC_R_DMA_0_CH28 = 92, + IMX_SC_R_DMA_0_CH29 = 93, + IMX_SC_R_DMA_0_CH30 = 94, + IMX_SC_R_DMA_0_CH31 = 95, + IMX_SC_R_I2C_0 = 96, + IMX_SC_R_I2C_1 = 97, + IMX_SC_R_I2C_2 = 98, + IMX_SC_R_I2C_3 = 99, + IMX_SC_R_I2C_4 = 100, + IMX_SC_R_ADC_0 = 101, + IMX_SC_R_ADC_1 = 102, + IMX_SC_R_FTM_0 = 103, + IMX_SC_R_FTM_1 = 104, + IMX_SC_R_CAN_0 = 105, + IMX_SC_R_CAN_1 = 106, + IMX_SC_R_CAN_2 = 107, + IMX_SC_R_DMA_1_CH0 = 108, + IMX_SC_R_DMA_1_CH1 = 109, + IMX_SC_R_DMA_1_CH2 = 110, + IMX_SC_R_DMA_1_CH3 = 111, + IMX_SC_R_DMA_1_CH4 = 112, + IMX_SC_R_DMA_1_CH5 = 113, + IMX_SC_R_DMA_1_CH6 = 114, + IMX_SC_R_DMA_1_CH7 = 115, + IMX_SC_R_DMA_1_CH8 = 116, + IMX_SC_R_DMA_1_CH9 = 117, + IMX_SC_R_DMA_1_CH10 = 118, + IMX_SC_R_DMA_1_CH11 = 119, + IMX_SC_R_DMA_1_CH12 = 120, + IMX_SC_R_DMA_1_CH13 = 121, + IMX_SC_R_DMA_1_CH14 = 122, + IMX_SC_R_DMA_1_CH15 = 123, + IMX_SC_R_DMA_1_CH16 = 124, + IMX_SC_R_DMA_1_CH17 = 125, + IMX_SC_R_DMA_1_CH18 = 126, + IMX_SC_R_DMA_1_CH19 = 127, + IMX_SC_R_DMA_1_CH20 = 128, + IMX_SC_R_DMA_1_CH21 = 129, + IMX_SC_R_DMA_1_CH22 = 130, + IMX_SC_R_DMA_1_CH23 = 131, + IMX_SC_R_DMA_1_CH24 = 132, + IMX_SC_R_DMA_1_CH25 = 133, + IMX_SC_R_DMA_1_CH26 = 134, + IMX_SC_R_DMA_1_CH27 = 135, + IMX_SC_R_DMA_1_CH28 = 136, + IMX_SC_R_DMA_1_CH29 = 137, + IMX_SC_R_DMA_1_CH30 = 138, + IMX_SC_R_DMA_1_CH31 = 139, + IMX_SC_R_UNUSED1 = 140, + IMX_SC_R_UNUSED2 = 141, + IMX_SC_R_UNUSED3 = 142, + IMX_SC_R_UNUSED4 = 143, + IMX_SC_R_GPU_0_PID0 = 144, + IMX_SC_R_GPU_0_PID1 = 145, + IMX_SC_R_GPU_0_PID2 = 146, + IMX_SC_R_GPU_0_PID3 = 147, + IMX_SC_R_GPU_1_PID0 = 148, + IMX_SC_R_GPU_1_PID1 = 149, + IMX_SC_R_GPU_1_PID2 = 150, + IMX_SC_R_GPU_1_PID3 = 151, + IMX_SC_R_PCIE_A = 152, + IMX_SC_R_SERDES_0 = 153, + IMX_SC_R_MATCH_0 = 154, + IMX_SC_R_MATCH_1 = 155, + IMX_SC_R_MATCH_2 = 156, + IMX_SC_R_MATCH_3 = 157, + IMX_SC_R_MATCH_4 = 158, + IMX_SC_R_MATCH_5 = 159, + IMX_SC_R_MATCH_6 = 160, + IMX_SC_R_MATCH_7 = 161, + IMX_SC_R_MATCH_8 = 162, + IMX_SC_R_MATCH_9 = 163, + IMX_SC_R_MATCH_10 = 164, + IMX_SC_R_MATCH_11 = 165, + IMX_SC_R_MATCH_12 = 166, + IMX_SC_R_MATCH_13 = 167, + IMX_SC_R_MATCH_14 = 168, + IMX_SC_R_PCIE_B = 169, + IMX_SC_R_SATA_0 = 170, + IMX_SC_R_SERDES_1 = 171, + IMX_SC_R_HSIO_GPIO = 172, + IMX_SC_R_MATCH_15 = 173, + IMX_SC_R_MATCH_16 = 174, + IMX_SC_R_MATCH_17 = 175, + IMX_SC_R_MATCH_18 = 176, + IMX_SC_R_MATCH_19 = 177, + IMX_SC_R_MATCH_20 = 178, + IMX_SC_R_MATCH_21 = 179, + IMX_SC_R_MATCH_22 = 180, + IMX_SC_R_MATCH_23 = 181, + IMX_SC_R_MATCH_24 = 182, + IMX_SC_R_MATCH_25 = 183, + IMX_SC_R_MATCH_26 = 184, + IMX_SC_R_MATCH_27 = 185, + IMX_SC_R_MATCH_28 = 186, + IMX_SC_R_LCD_0 = 187, + IMX_SC_R_LCD_0_PWM_0 = 188, + IMX_SC_R_LCD_0_I2C_0 = 189, + IMX_SC_R_LCD_0_I2C_1 = 190, + IMX_SC_R_PWM_0 = 191, + IMX_SC_R_PWM_1 = 192, + IMX_SC_R_PWM_2 = 193, + IMX_SC_R_PWM_3 = 194, + IMX_SC_R_PWM_4 = 195, + IMX_SC_R_PWM_5 = 196, + IMX_SC_R_PWM_6 = 197, + IMX_SC_R_PWM_7 = 198, + IMX_SC_R_GPIO_0 = 199, + IMX_SC_R_GPIO_1 = 200, + IMX_SC_R_GPIO_2 = 201, + IMX_SC_R_GPIO_3 = 202, + IMX_SC_R_GPIO_4 = 203, + IMX_SC_R_GPIO_5 = 204, + IMX_SC_R_GPIO_6 = 205, + IMX_SC_R_GPIO_7 = 206, + IMX_SC_R_GPT_0 = 207, + IMX_SC_R_GPT_1 = 208, + IMX_SC_R_GPT_2 = 209, + IMX_SC_R_GPT_3 = 210, + IMX_SC_R_GPT_4 = 211, + IMX_SC_R_KPP = 212, + IMX_SC_R_MU_0A = 213, + IMX_SC_R_MU_1A = 214, + IMX_SC_R_MU_2A = 215, + IMX_SC_R_MU_3A = 216, + IMX_SC_R_MU_4A = 217, + IMX_SC_R_MU_5A = 218, + IMX_SC_R_MU_6A = 219, + IMX_SC_R_MU_7A = 220, + IMX_SC_R_MU_8A = 221, + IMX_SC_R_MU_9A = 222, + IMX_SC_R_MU_10A = 223, + IMX_SC_R_MU_11A = 224, + IMX_SC_R_MU_12A = 225, + IMX_SC_R_MU_13A = 226, + IMX_SC_R_MU_5B = 227, + IMX_SC_R_MU_6B = 228, + IMX_SC_R_MU_7B = 229, + IMX_SC_R_MU_8B = 230, + IMX_SC_R_MU_9B = 231, + IMX_SC_R_MU_10B = 232, + IMX_SC_R_MU_11B = 233, + IMX_SC_R_MU_12B = 234, + IMX_SC_R_MU_13B = 235, + IMX_SC_R_ROM_0 = 236, + IMX_SC_R_FSPI_0 = 237, + IMX_SC_R_FSPI_1 = 238, + IMX_SC_R_IEE = 239, + IMX_SC_R_IEE_R0 = 240, + IMX_SC_R_IEE_R1 = 241, + IMX_SC_R_IEE_R2 = 242, + IMX_SC_R_IEE_R3 = 243, + IMX_SC_R_IEE_R4 = 244, + IMX_SC_R_IEE_R5 = 245, + IMX_SC_R_IEE_R6 = 246, + IMX_SC_R_IEE_R7 = 247, + IMX_SC_R_SDHC_0 = 248, + IMX_SC_R_SDHC_1 = 249, + IMX_SC_R_SDHC_2 = 250, + IMX_SC_R_ENET_0 = 251, + IMX_SC_R_ENET_1 = 252, + IMX_SC_R_MLB_0 = 253, + IMX_SC_R_DMA_2_CH0 = 254, + IMX_SC_R_DMA_2_CH1 = 255, + IMX_SC_R_DMA_2_CH2 = 256, + IMX_SC_R_DMA_2_CH3 = 257, + IMX_SC_R_DMA_2_CH4 = 258, + IMX_SC_R_USB_0 = 259, + IMX_SC_R_USB_1 = 260, + IMX_SC_R_USB_0_PHY = 261, + IMX_SC_R_USB_2 = 262, + IMX_SC_R_USB_2_PHY = 263, + IMX_SC_R_DTCP = 264, + IMX_SC_R_NAND = 265, + IMX_SC_R_LVDS_0 = 266, + IMX_SC_R_LVDS_0_PWM_0 = 267, + IMX_SC_R_LVDS_0_I2C_0 = 268, + IMX_SC_R_LVDS_0_I2C_1 = 269, + IMX_SC_R_LVDS_1 = 270, + IMX_SC_R_LVDS_1_PWM_0 = 271, + IMX_SC_R_LVDS_1_I2C_0 = 272, + IMX_SC_R_LVDS_1_I2C_1 = 273, + IMX_SC_R_LVDS_2 = 274, + IMX_SC_R_LVDS_2_PWM_0 = 275, + IMX_SC_R_LVDS_2_I2C_0 = 276, + IMX_SC_R_LVDS_2_I2C_1 = 277, + IMX_SC_R_M4_0_PID0 = 278, + IMX_SC_R_M4_0_PID1 = 279, + IMX_SC_R_M4_0_PID2 = 280, + IMX_SC_R_M4_0_PID3 = 281, + IMX_SC_R_M4_0_PID4 = 282, + IMX_SC_R_M4_0_RGPIO = 283, + IMX_SC_R_M4_0_SEMA42 = 284, + IMX_SC_R_M4_0_TPM = 285, + IMX_SC_R_M4_0_PIT = 286, + IMX_SC_R_M4_0_UART = 287, + IMX_SC_R_M4_0_I2C = 288, + IMX_SC_R_M4_0_INTMUX = 289, + IMX_SC_R_M4_0_SIM = 290, + IMX_SC_R_M4_0_WDOG = 291, + IMX_SC_R_M4_0_MU_0B = 292, + IMX_SC_R_M4_0_MU_0A0 = 293, + IMX_SC_R_M4_0_MU_0A1 = 294, + IMX_SC_R_M4_0_MU_0A2 = 295, + IMX_SC_R_M4_0_MU_0A3 = 296, + IMX_SC_R_M4_0_MU_1A = 297, + IMX_SC_R_M4_1_PID0 = 298, + IMX_SC_R_M4_1_PID1 = 299, + IMX_SC_R_M4_1_PID2 = 300, + IMX_SC_R_M4_1_PID3 = 301, + IMX_SC_R_M4_1_PID4 = 302, + IMX_SC_R_M4_1_RGPIO = 303, + IMX_SC_R_M4_1_SEMA42 = 304, + IMX_SC_R_M4_1_TPM = 305, + IMX_SC_R_M4_1_PIT = 306, + IMX_SC_R_M4_1_UART = 307, + IMX_SC_R_M4_1_I2C = 308, + IMX_SC_R_M4_1_INTMUX = 309, + IMX_SC_R_M4_1_SIM = 310, + IMX_SC_R_M4_1_WDOG = 311, + IMX_SC_R_M4_1_MU_0B = 312, + IMX_SC_R_M4_1_MU_0A0 = 313, + IMX_SC_R_M4_1_MU_0A1 = 314, + IMX_SC_R_M4_1_MU_0A2 = 315, + IMX_SC_R_M4_1_MU_0A3 = 316, + IMX_SC_R_M4_1_MU_1A = 317, + IMX_SC_R_SAI_0 = 318, + IMX_SC_R_SAI_1 = 319, + IMX_SC_R_SAI_2 = 320, + IMX_SC_R_IRQSTR_SCU2 = 321, + IMX_SC_R_IRQSTR_DSP = 322, + IMX_SC_R_UNUSED5 = 323, + IMX_SC_R_UNUSED6 = 324, + IMX_SC_R_AUDIO_PLL_0 = 325, + IMX_SC_R_PI_0 = 326, + IMX_SC_R_PI_0_PWM_0 = 327, + IMX_SC_R_PI_0_PWM_1 = 328, + IMX_SC_R_PI_0_I2C_0 = 329, + IMX_SC_R_PI_0_PLL = 330, + IMX_SC_R_PI_1 = 331, + IMX_SC_R_PI_1_PWM_0 = 332, + IMX_SC_R_PI_1_PWM_1 = 333, + IMX_SC_R_PI_1_I2C_0 = 334, + IMX_SC_R_PI_1_PLL = 335, + IMX_SC_R_SC_PID0 = 336, + IMX_SC_R_SC_PID1 = 337, + IMX_SC_R_SC_PID2 = 338, + IMX_SC_R_SC_PID3 = 339, + IMX_SC_R_SC_PID4 = 340, + IMX_SC_R_SC_SEMA42 = 341, + IMX_SC_R_SC_TPM = 342, + IMX_SC_R_SC_PIT = 343, + IMX_SC_R_SC_UART = 344, + IMX_SC_R_SC_I2C = 345, + IMX_SC_R_SC_MU_0B = 346, + IMX_SC_R_SC_MU_0A0 = 347, + IMX_SC_R_SC_MU_0A1 = 348, + IMX_SC_R_SC_MU_0A2 = 349, + IMX_SC_R_SC_MU_0A3 = 350, + IMX_SC_R_SC_MU_1A = 351, + IMX_SC_R_SYSCNT_RD = 352, + IMX_SC_R_SYSCNT_CMP = 353, + IMX_SC_R_DEBUG = 354, + IMX_SC_R_SYSTEM = 355, + IMX_SC_R_SNVS = 356, + IMX_SC_R_OTP = 357, + IMX_SC_R_VPU_PID0 = 358, + IMX_SC_R_VPU_PID1 = 359, + IMX_SC_R_VPU_PID2 = 360, + IMX_SC_R_VPU_PID3 = 361, + IMX_SC_R_VPU_PID4 = 362, + IMX_SC_R_VPU_PID5 = 363, + IMX_SC_R_VPU_PID6 = 364, + IMX_SC_R_VPU_PID7 = 365, + IMX_SC_R_VPU_UART = 366, + IMX_SC_R_VPUCORE = 367, + IMX_SC_R_VPUCORE_0 = 368, + IMX_SC_R_VPUCORE_1 = 369, + IMX_SC_R_VPUCORE_2 = 370, + IMX_SC_R_VPUCORE_3 = 371, + IMX_SC_R_DMA_4_CH0 = 372, + IMX_SC_R_DMA_4_CH1 = 373, + IMX_SC_R_DMA_4_CH2 = 374, + IMX_SC_R_DMA_4_CH3 = 375, + IMX_SC_R_DMA_4_CH4 = 376, + IMX_SC_R_ISI_CH0 = 377, + IMX_SC_R_ISI_CH1 = 378, + IMX_SC_R_ISI_CH2 = 379, + IMX_SC_R_ISI_CH3 = 380, + IMX_SC_R_ISI_CH4 = 381, + IMX_SC_R_ISI_CH5 = 382, + IMX_SC_R_ISI_CH6 = 383, + IMX_SC_R_ISI_CH7 = 384, + IMX_SC_R_MJPEG_DEC_S0 = 385, + IMX_SC_R_MJPEG_DEC_S1 = 386, + IMX_SC_R_MJPEG_DEC_S2 = 387, + IMX_SC_R_MJPEG_DEC_S3 = 388, + IMX_SC_R_MJPEG_ENC_S0 = 389, + IMX_SC_R_MJPEG_ENC_S1 = 390, + IMX_SC_R_MJPEG_ENC_S2 = 391, + IMX_SC_R_MJPEG_ENC_S3 = 392, + IMX_SC_R_MIPI_0 = 393, + IMX_SC_R_MIPI_0_PWM_0 = 394, + IMX_SC_R_MIPI_0_I2C_0 = 395, + IMX_SC_R_MIPI_0_I2C_1 = 396, + IMX_SC_R_MIPI_1 = 397, + IMX_SC_R_MIPI_1_PWM_0 = 398, + IMX_SC_R_MIPI_1_I2C_0 = 399, + IMX_SC_R_MIPI_1_I2C_1 = 400, + IMX_SC_R_CSI_0 = 401, + IMX_SC_R_CSI_0_PWM_0 = 402, + IMX_SC_R_CSI_0_I2C_0 = 403, + IMX_SC_R_CSI_1 = 404, + IMX_SC_R_CSI_1_PWM_0 = 405, + IMX_SC_R_CSI_1_I2C_0 = 406, + IMX_SC_R_HDMI = 407, + IMX_SC_R_HDMI_I2S = 408, + IMX_SC_R_HDMI_I2C_0 = 409, + IMX_SC_R_HDMI_PLL_0 = 410, + IMX_SC_R_HDMI_RX = 411, + IMX_SC_R_HDMI_RX_BYPASS = 412, + IMX_SC_R_HDMI_RX_I2C_0 = 413, + IMX_SC_R_ASRC_0 = 414, + IMX_SC_R_ESAI_0 = 415, + IMX_SC_R_SPDIF_0 = 416, + IMX_SC_R_SPDIF_1 = 417, + IMX_SC_R_SAI_3 = 418, + IMX_SC_R_SAI_4 = 419, + IMX_SC_R_SAI_5 = 420, + IMX_SC_R_GPT_5 = 421, + IMX_SC_R_GPT_6 = 422, + IMX_SC_R_GPT_7 = 423, + IMX_SC_R_GPT_8 = 424, + IMX_SC_R_GPT_9 = 425, + IMX_SC_R_GPT_10 = 426, + IMX_SC_R_DMA_2_CH5 = 427, + IMX_SC_R_DMA_2_CH6 = 428, + IMX_SC_R_DMA_2_CH7 = 429, + IMX_SC_R_DMA_2_CH8 = 430, + IMX_SC_R_DMA_2_CH9 = 431, + IMX_SC_R_DMA_2_CH10 = 432, + IMX_SC_R_DMA_2_CH11 = 433, + IMX_SC_R_DMA_2_CH12 = 434, + IMX_SC_R_DMA_2_CH13 = 435, + IMX_SC_R_DMA_2_CH14 = 436, + IMX_SC_R_DMA_2_CH15 = 437, + IMX_SC_R_DMA_2_CH16 = 438, + IMX_SC_R_DMA_2_CH17 = 439, + IMX_SC_R_DMA_2_CH18 = 440, + IMX_SC_R_DMA_2_CH19 = 441, + IMX_SC_R_DMA_2_CH20 = 442, + IMX_SC_R_DMA_2_CH21 = 443, + IMX_SC_R_DMA_2_CH22 = 444, + IMX_SC_R_DMA_2_CH23 = 445, + IMX_SC_R_DMA_2_CH24 = 446, + IMX_SC_R_DMA_2_CH25 = 447, + IMX_SC_R_DMA_2_CH26 = 448, + IMX_SC_R_DMA_2_CH27 = 449, + IMX_SC_R_DMA_2_CH28 = 450, + IMX_SC_R_DMA_2_CH29 = 451, + IMX_SC_R_DMA_2_CH30 = 452, + IMX_SC_R_DMA_2_CH31 = 453, + IMX_SC_R_ASRC_1 = 454, + IMX_SC_R_ESAI_1 = 455, + IMX_SC_R_SAI_6 = 456, + IMX_SC_R_SAI_7 = 457, + IMX_SC_R_AMIX = 458, + IMX_SC_R_MQS_0 = 459, + IMX_SC_R_DMA_3_CH0 = 460, + IMX_SC_R_DMA_3_CH1 = 461, + IMX_SC_R_DMA_3_CH2 = 462, + IMX_SC_R_DMA_3_CH3 = 463, + IMX_SC_R_DMA_3_CH4 = 464, + IMX_SC_R_DMA_3_CH5 = 465, + IMX_SC_R_DMA_3_CH6 = 466, + IMX_SC_R_DMA_3_CH7 = 467, + IMX_SC_R_DMA_3_CH8 = 468, + IMX_SC_R_DMA_3_CH9 = 469, + IMX_SC_R_DMA_3_CH10 = 470, + IMX_SC_R_DMA_3_CH11 = 471, + IMX_SC_R_DMA_3_CH12 = 472, + IMX_SC_R_DMA_3_CH13 = 473, + IMX_SC_R_DMA_3_CH14 = 474, + IMX_SC_R_DMA_3_CH15 = 475, + IMX_SC_R_DMA_3_CH16 = 476, + IMX_SC_R_DMA_3_CH17 = 477, + IMX_SC_R_DMA_3_CH18 = 478, + IMX_SC_R_DMA_3_CH19 = 479, + IMX_SC_R_DMA_3_CH20 = 480, + IMX_SC_R_DMA_3_CH21 = 481, + IMX_SC_R_DMA_3_CH22 = 482, + IMX_SC_R_DMA_3_CH23 = 483, + IMX_SC_R_DMA_3_CH24 = 484, + IMX_SC_R_DMA_3_CH25 = 485, + IMX_SC_R_DMA_3_CH26 = 486, + IMX_SC_R_DMA_3_CH27 = 487, + IMX_SC_R_DMA_3_CH28 = 488, + IMX_SC_R_DMA_3_CH29 = 489, + IMX_SC_R_DMA_3_CH30 = 490, + IMX_SC_R_DMA_3_CH31 = 491, + IMX_SC_R_AUDIO_PLL_1 = 492, + IMX_SC_R_AUDIO_CLK_0 = 493, + IMX_SC_R_AUDIO_CLK_1 = 494, + IMX_SC_R_MCLK_OUT_0 = 495, + IMX_SC_R_MCLK_OUT_1 = 496, + IMX_SC_R_PMIC_0 = 497, + IMX_SC_R_PMIC_1 = 498, + IMX_SC_R_SECO = 499, + IMX_SC_R_CAAM_JR1 = 500, + IMX_SC_R_CAAM_JR2 = 501, + IMX_SC_R_CAAM_JR3 = 502, + IMX_SC_R_SECO_MU_2 = 503, + IMX_SC_R_SECO_MU_3 = 504, + IMX_SC_R_SECO_MU_4 = 505, + IMX_SC_R_HDMI_RX_PWM_0 = 506, + IMX_SC_R_A35 = 507, + IMX_SC_R_A35_0 = 508, + IMX_SC_R_A35_1 = 509, + IMX_SC_R_A35_2 = 510, + IMX_SC_R_A35_3 = 511, + IMX_SC_R_DSP = 512, + IMX_SC_R_DSP_RAM = 513, + IMX_SC_R_CAAM_JR1_OUT = 514, + IMX_SC_R_CAAM_JR2_OUT = 515, + IMX_SC_R_CAAM_JR3_OUT = 516, + IMX_SC_R_VPU_DEC_0 = 517, + IMX_SC_R_VPU_ENC_0 = 518, + IMX_SC_R_CAAM_JR0 = 519, + IMX_SC_R_CAAM_JR0_OUT = 520, + IMX_SC_R_PMIC_2 = 521, + IMX_SC_R_DBLOGIC = 522, + IMX_SC_R_HDMI_PLL_1 = 523, + IMX_SC_R_BOARD_R0 = 524, + IMX_SC_R_BOARD_R1 = 525, + IMX_SC_R_BOARD_R2 = 526, + IMX_SC_R_BOARD_R3 = 527, + IMX_SC_R_BOARD_R4 = 528, + IMX_SC_R_BOARD_R5 = 529, + IMX_SC_R_BOARD_R6 = 530, + IMX_SC_R_BOARD_R7 = 531, + IMX_SC_R_MJPEG_DEC_MP = 532, + IMX_SC_R_MJPEG_ENC_MP = 533, + IMX_SC_R_VPU_TS_0 = 534, + IMX_SC_R_VPU_MU_0 = 535, + IMX_SC_R_VPU_MU_1 = 536, + IMX_SC_R_VPU_MU_2 = 537, + IMX_SC_R_VPU_MU_3 = 538, + IMX_SC_R_VPU_ENC_1 = 539, + IMX_SC_R_VPU = 540, + IMX_SC_R_LAST +}; + +/* NOTE - please add by replacing some of the UNUSED from above! */ + +/* + * 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 15e1f2bc8b3b2d238b9e06b128d4a09d28f11733 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 7 Oct 2018 21:04:43 +0800 Subject: firmware: imx: add misc svc support Add SCU MISC SVC support which provides misc control get/set functions. Cc: Shawn Guo Reviewed-by: Sascha Hauer Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- include/linux/firmware/imx/sci.h | 1 + include/linux/firmware/imx/svc/misc.h | 55 +++++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 include/linux/firmware/imx/svc/misc.h (limited to 'include/linux') diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index ff3227ad8d7c..29ada609de03 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -13,4 +13,5 @@ #include #include +#include #endif /* _SC_SCI_H */ diff --git a/include/linux/firmware/imx/svc/misc.h b/include/linux/firmware/imx/svc/misc.h new file mode 100644 index 000000000000..e21c49aba92f --- /dev/null +++ b/include/linux/firmware/imx/svc/misc.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * + * Header file containing the public API for the System Controller (SC) + * Miscellaneous (MISC) function. + * + * MISC_SVC (SVC) Miscellaneous Service + * + * Module for the Miscellaneous (MISC) service. + */ + +#ifndef _SC_MISC_API_H +#define _SC_MISC_API_H + +#include + +/* + * This type is used to indicate RPC MISC function calls. + */ +enum imx_misc_func { + IMX_SC_MISC_FUNC_UNKNOWN = 0, + IMX_SC_MISC_FUNC_SET_CONTROL = 1, + IMX_SC_MISC_FUNC_GET_CONTROL = 2, + IMX_SC_MISC_FUNC_SET_MAX_DMA_GROUP = 4, + IMX_SC_MISC_FUNC_SET_DMA_GROUP = 5, + IMX_SC_MISC_FUNC_SECO_IMAGE_LOAD = 8, + IMX_SC_MISC_FUNC_SECO_AUTHENTICATE = 9, + IMX_SC_MISC_FUNC_DEBUG_OUT = 10, + IMX_SC_MISC_FUNC_WAVEFORM_CAPTURE = 6, + IMX_SC_MISC_FUNC_BUILD_INFO = 15, + IMX_SC_MISC_FUNC_UNIQUE_ID = 19, + IMX_SC_MISC_FUNC_SET_ARI = 3, + IMX_SC_MISC_FUNC_BOOT_STATUS = 7, + IMX_SC_MISC_FUNC_BOOT_DONE = 14, + IMX_SC_MISC_FUNC_OTP_FUSE_READ = 11, + IMX_SC_MISC_FUNC_OTP_FUSE_WRITE = 17, + IMX_SC_MISC_FUNC_SET_TEMP = 12, + IMX_SC_MISC_FUNC_GET_TEMP = 13, + IMX_SC_MISC_FUNC_GET_BOOT_DEV = 16, + IMX_SC_MISC_FUNC_GET_BUTTON_STATUS = 18, +}; + +/* + * Control Functions + */ + +int imx_sc_misc_set_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 val); + +int imx_sc_misc_get_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 *val); + +#endif /* _SC_MISC_API_H */ -- cgit v1.2.3 From 4a19edb60d0203cd5bf95a8b46ea8f63fd41194c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 7 Oct 2018 20:16:22 -0700 Subject: netlink: Pass extack to dump handlers Declare extack in netlink_dump and pass to dump handlers via netlink_callback. Add any extack message after the dump_done_errno allowing error messages to be returned. This will be useful when strict checking is done on dump requests, returning why the dump fails EINVAL. Signed-off-by: David Ahern Acked-by: Christian Brauner Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 71f121b66ca8..88c8a2d83eb3 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -176,6 +176,7 @@ struct netlink_callback { void *data; /* the module that dump function belong to */ struct module *module; + struct netlink_ext_ack *extack; u16 family; u16 min_dump_alloc; unsigned int prev_seq, seq; -- cgit v1.2.3 From 89d35528d17d25819a755a2b52931e911baebc66 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 7 Oct 2018 20:16:27 -0700 Subject: netlink: Add new socket option to enable strict checking on dumps Add a new socket option, NETLINK_DUMP_STRICT_CHK, that userspace can use via setsockopt to request strict checking of headers and attributes on dump requests. To get dump features such as kernel side filtering based on data in the header or attributes appended to the dump request, userspace must call setsockopt() for NETLINK_DUMP_STRICT_CHK and a non-zero value. Since the netlink sock and its flags are private to the af_netlink code, the strict checking flag is passed to dump handlers via a flag in the netlink_callback struct. For old userspace on new kernel there is no impact as all of the data checks in later patches are wrapped in a check on the new strict flag. For new userspace on old kernel, the setsockopt will fail and even if new userspace sets data in the headers and appended attributes the kernel will silently ignore it. Moving forward when the setsockopt succeeds, the new userspace on old kernel means the dump request can pass an attribute the kernel does not understand. The dump will then fail as the older kernel does not understand it. New userspace on new kernel setting the socket option gets the benefit of the improved data dump. Kernel side the NETLINK_DUMP_STRICT_CHK uapi is converted to a generic NETLINK_F_STRICT_CHK flag which can potentially be leveraged for tighter checking on the NEW, DEL, and SET commands. Signed-off-by: David Ahern Acked-by: Christian Brauner Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 88c8a2d83eb3..72580f1a72a2 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -179,6 +179,7 @@ struct netlink_callback { struct netlink_ext_ack *extack; u16 family; u16 min_dump_alloc; + bool strict_check; unsigned int prev_seq, seq; long args[6]; }; -- cgit v1.2.3 From 5390a8df769ec9ba9c995191bb0867430f602ebb Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 11 Sep 2018 18:40:06 +0300 Subject: mtd: spi-nor: add support to non-uniform SFDP SPI NOR flash memories Based on Cyrille Pitchen's patch https://lkml.org/lkml/2017/3/22/935. This patch is a transitional patch in introducing the support of SFDP SPI memories with non-uniform erase sizes like Spansion s25fs512s. Non-uniform erase maps will be used later when initialized based on the SFDP data. Introduce the memory erase map which splits the memory array into one or many erase regions. Each erase region supports up to 4 erase types, as defined by the JEDEC JESD216B (SFDP) specification. To be backward compatible, the erase map of uniform SPI NOR flash memories is initialized so it contains only one erase region and this erase region supports only one erase command. Hence a single size is used to erase any sector/block of the memory. Besides, since the algorithm used to erase sectors on non-uniform SPI NOR flash memories is quite expensive, when possible, the erase map is tuned to come back to the uniform case. The 'erase with the best command, move forward and repeat' approach was suggested by Cristian Birsan in a brainstorm session, so: Suggested-by: Cristian Birsan Signed-off-by: Tudor Ambarus Reviewed-by: Marek Vasut Signed-off-by: Boris Brezillon --- include/linux/mtd/spi-nor.h | 107 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 107 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c922e97f205a..894cbf88bf2e 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -238,6 +238,94 @@ enum spi_nor_option_flags { SNOR_F_BROKEN_RESET = BIT(6), }; +/** + * struct spi_nor_erase_type - Structure to describe a SPI NOR erase type + * @size: the size of the sector/block erased by the erase type. + * JEDEC JESD216B imposes erase sizes to be a power of 2. + * @size_shift: @size is a power of 2, the shift is stored in + * @size_shift. + * @size_mask: the size mask based on @size_shift. + * @opcode: the SPI command op code to erase the sector/block. + * @idx: Erase Type index as sorted in the Basic Flash Parameter + * Table. It will be used to synchronize the supported + * Erase Types with the ones identified in the SFDP + * optional tables. + */ +struct spi_nor_erase_type { + u32 size; + u32 size_shift; + u32 size_mask; + u8 opcode; + u8 idx; +}; + +/** + * struct spi_nor_erase_command - Used for non-uniform erases + * The structure is used to describe a list of erase commands to be executed + * once we validate that the erase can be performed. The elements in the list + * are run-length encoded. + * @list: for inclusion into the list of erase commands. + * @count: how many times the same erase command should be + * consecutively used. + * @size: the size of the sector/block erased by the command. + * @opcode: the SPI command op code to erase the sector/block. + */ +struct spi_nor_erase_command { + struct list_head list; + u32 count; + u32 size; + u8 opcode; +}; + +/** + * struct spi_nor_erase_region - Structure to describe a SPI NOR erase region + * @offset: the offset in the data array of erase region start. + * LSB bits are used as a bitmask encoding flags to + * determine if this region is overlaid, if this region is + * the last in the SPI NOR flash memory and to indicate + * all the supported erase commands inside this region. + * The erase types are sorted in ascending order with the + * smallest Erase Type size being at BIT(0). + * @size: the size of the region in bytes. + */ +struct spi_nor_erase_region { + u64 offset; + u64 size; +}; + +#define SNOR_ERASE_TYPE_MAX 4 +#define SNOR_ERASE_TYPE_MASK GENMASK_ULL(SNOR_ERASE_TYPE_MAX - 1, 0) + +#define SNOR_LAST_REGION BIT(4) +#define SNOR_OVERLAID_REGION BIT(5) + +#define SNOR_ERASE_FLAGS_MAX 6 +#define SNOR_ERASE_FLAGS_MASK GENMASK_ULL(SNOR_ERASE_FLAGS_MAX - 1, 0) + +/** + * struct spi_nor_erase_map - Structure to describe the SPI NOR erase map + * @regions: array of erase regions. The regions are consecutive in + * address space. Walking through the regions is done + * incrementally. + * @uniform_region: a pre-allocated erase region for SPI NOR with a uniform + * sector size (legacy implementation). + * @erase_type: an array of erase types shared by all the regions. + * The erase types are sorted in ascending order, with the + * smallest Erase Type size being the first member in the + * erase_type array. + * @uniform_erase_type: bitmask encoding erase types that can erase the + * entire memory. This member is completed at init by + * uniform and non-uniform SPI NOR flash memories if they + * support at least one erase type that can erase the + * entire memory. + */ +struct spi_nor_erase_map { + struct spi_nor_erase_region *regions; + struct spi_nor_erase_region uniform_region; + struct spi_nor_erase_type erase_type[SNOR_ERASE_TYPE_MAX]; + u8 uniform_erase_type; +}; + /** * struct flash_info - Forward declaration of a structure used internally by * spi_nor_scan() @@ -262,6 +350,7 @@ struct flash_info; * @write_proto: the SPI protocol for write operations * @reg_proto the SPI protocol for read_reg/write_reg/erase operations * @cmd_buf: used by the write_reg + * @erase_map: the erase map of the SPI NOR * @prepare: [OPTIONAL] do some preparations for the * read/write/erase/lock/unlock operations * @unprepare: [OPTIONAL] do some post work after the @@ -297,6 +386,7 @@ struct spi_nor { bool sst_write_second; u32 flags; u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE]; + struct spi_nor_erase_map erase_map; int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); @@ -317,6 +407,23 @@ struct spi_nor { void *priv; }; +static u64 __maybe_unused +spi_nor_region_is_last(const struct spi_nor_erase_region *region) +{ + return region->offset & SNOR_LAST_REGION; +} + +static u64 __maybe_unused +spi_nor_region_end(const struct spi_nor_erase_region *region) +{ + return (region->offset & ~SNOR_ERASE_FLAGS_MASK) + region->size; +} + +static bool __maybe_unused spi_nor_has_uniform_erase(const struct spi_nor *nor) +{ + return !!nor->erase_map.uniform_erase_type; +} + static inline void spi_nor_set_flash_node(struct spi_nor *nor, struct device_node *np) { -- cgit v1.2.3 From b038e8e3be724dd293a0849f5fe267fdddcca9dd Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 11 Sep 2018 18:40:07 +0300 Subject: mtd: spi-nor: parse SFDP Sector Map Parameter Table Add support for the SFDP (JESD216B) Sector Map Parameter Table. This table is optional, but when available, we parse it to identify the location and size of sectors within the main data array of the flash memory device and to identify which Erase Types are supported by each sector. Signed-off-by: Tudor Ambarus Reviewed-by: Marek Vasut Signed-off-by: Boris Brezillon --- include/linux/mtd/spi-nor.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 894cbf88bf2e..7f0c7303575e 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -419,6 +419,18 @@ spi_nor_region_end(const struct spi_nor_erase_region *region) return (region->offset & ~SNOR_ERASE_FLAGS_MASK) + region->size; } +static void __maybe_unused +spi_nor_region_mark_end(struct spi_nor_erase_region *region) +{ + region->offset |= SNOR_LAST_REGION; +} + +static void __maybe_unused +spi_nor_region_mark_overlay(struct spi_nor_erase_region *region) +{ + region->offset |= SNOR_OVERLAID_REGION; +} + static bool __maybe_unused spi_nor_has_uniform_erase(const struct spi_nor *nor) { return !!nor->erase_map.uniform_erase_type; -- cgit v1.2.3 From b8d62f33b7b225935649ab165d901fe8dd7f95e5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 Oct 2018 13:17:26 +0200 Subject: genirq: Fix grammar s/an /a / Fix a grammar mistake in . [ mingo: While at it also fix another similar error in another comment as well. ] Signed-off-by: Geert Uytterhoeven Cc: Jiri Kosina Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181008111726.26286-1-geert%2Brenesas@glider.be Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index eeceac3376fc..1d6711c28271 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -45,7 +45,7 @@ * IRQF_PERCPU - Interrupt is per cpu * IRQF_NOBALANCING - Flag to exclude this interrupt from irq balancing * IRQF_IRQPOLL - Interrupt is used for polling (only the interrupt that is - * registered first in an shared interrupt is considered for + * registered first in a shared interrupt is considered for * performance reasons) * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished. * Used by threaded interrupts which need to keep the -- cgit v1.2.3 From e054637597ba36d3729ba6a3a3dd7aad8e2a3003 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Sat, 6 Oct 2018 16:53:19 +0530 Subject: mm, sched/numa: Remove remaining traces of NUMA rate-limiting Remove the leftover pglist_data::numabalancing_migrate_lock and its initialization, we stopped using this lock with: efaffc5e40ae ("mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration") [ mingo: Rewrote the changelog. ] Signed-off-by: Srikar Dronamraju Acked-by: Mel Gorman Cc: Linus Torvalds Cc: Linux-MM Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1538824999-31230-1-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3f4c0b167333..d4b0c79d2924 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -667,10 +667,6 @@ typedef struct pglist_data { enum zone_type kcompactd_classzone_idx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; -#endif -#ifdef CONFIG_NUMA_BALANCING - /* Lock serializing the migrate rate limiting window */ - spinlock_t numabalancing_migrate_lock; #endif /* * This is a per-node reserve of pages that are not available -- cgit v1.2.3 From 8ca2b56cd7da98fc8f8d787bb706b9d6c8674a3b Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 3 Oct 2018 13:07:18 -0400 Subject: locking/lockdep: Make class->ops a percpu counter and move it under CONFIG_DEBUG_LOCKDEP=y A sizable portion of the CPU cycles spent on the __lock_acquire() is used up by the atomic increment of the class->ops stat counter. By taking it out from the lock_class structure and changing it to a per-cpu per-lock-class counter, we can reduce the amount of cacheline contention on the class structure when multiple CPUs are trying to acquire locks of the same class simultaneously. To limit the increase in memory consumption because of the percpu nature of that counter, it is now put back under the CONFIG_DEBUG_LOCKDEP config option. So the memory consumption increase will only occur if CONFIG_DEBUG_LOCKDEP is defined. The lock_class structure, however, is reduced in size by 16 bytes on 64-bit archs after ops removal and a minor restructuring of the fields. This patch also fixes a bug in the increment code as the counter is of the 'unsigned long' type, but atomic_inc() was used to increment it. Signed-off-by: Waiman Long Acked-by: Peter Zijlstra Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/d66681f3-8781-9793-1dcf-2436a284550b@redhat.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b0d0b51c4d85..1fd82ff99c65 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -99,13 +99,8 @@ struct lock_class { */ unsigned int version; - /* - * Statistics counter: - */ - unsigned long ops; - - const char *name; int name_version; + const char *name; #ifdef CONFIG_LOCK_STAT unsigned long contention_point[LOCKSTAT_POINTS]; -- cgit v1.2.3 From 78d8f8f1a1800cf6068ffcac7a14cda19ae693d8 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 5 Oct 2018 11:41:13 -0700 Subject: mfd: cros: add "base attached" MKBP switch definition This adds a "base attached" switch definition to the MKBP protocol that is used by Whiskers driver to properly determine device state (clamshell vs tablet mode). Signed-off-by: Dmitry Torokhov Acked-by: Lee Jones Signed-off-by: Jiri Kosina --- include/linux/mfd/cros_ec_commands.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..7690f0793965 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -2132,6 +2132,7 @@ struct ec_response_get_next_event_v1 { /* Switches */ #define EC_MKBP_LID_OPEN 0 #define EC_MKBP_TABLET_MODE 1 +#define EC_MKBP_BASE_ATTACHED 2 /*****************************************************************************/ /* Temperature sensor commands */ -- cgit v1.2.3 From 53c99bd665a2649341ed6aed358ab56a3eedcd00 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 31 Aug 2018 10:42:24 +0200 Subject: init: add arch_call_rest_init to allow stack switching With CONFIG_VMAP_STACK=y the kernel stack of all tasks should be allocated in the vmalloc space. The initial stack used for all the early init code is in the init_thread_union. To be able to switch from this early stack to a properly allocated stack from vmalloc the architecture needs a switch-over point. Introduce the arch_call_rest_init() function with a weak definition in init/main.c with the only purpose to call rest_init() from the end of start_kernel(). The architecture override can then do the necessary magic to switch to the new vmalloc'ed stack. Signed-off-by: Martin Schwidefsky --- include/linux/start_kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 4b268d86a784..8b369a41c03c 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -9,5 +9,7 @@ up something else. */ extern asmlinkage void __init start_kernel(void); +extern void __init arch_call_rest_init(void); +extern void __ref rest_init(void); #endif /* _LINUX_START_KERNEL_H */ -- cgit v1.2.3 From dde709d1361ab50d3b9f2824f72b4374f5582e84 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Mon, 20 Nov 2017 11:16:14 +0100 Subject: compiler: introduce __no_sanitize_address_or_inline Due to conflict between kasan instrumentation and inlining https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 functions which are defined as inline could not be called from functions defined with __no_sanitize_address. Introduce __no_sanitize_address_or_inline which would expand to __no_sanitize_address when the kernel is built with kasan support and to inline otherwise. This helps to avoid disabling kasan instrumentation for entire files. Reviewed-by: Martin Schwidefsky Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- include/linux/compiler-gcc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 763bbad1e258..997ade08a79d 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -208,6 +208,12 @@ * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 */ #define __no_sanitize_address __attribute__((no_sanitize_address)) +#ifdef CONFIG_KASAN +#define __no_sanitize_address_or_inline \ + __no_sanitize_address __maybe_unused notrace +#else +#define __no_sanitize_address_or_inline inline +#endif #endif #if GCC_VERSION >= 50100 @@ -225,6 +231,7 @@ #if !defined(__no_sanitize_address) #define __no_sanitize_address +#define __no_sanitize_address_or_inline inline #endif /* -- cgit v1.2.3 From 3b0296b8c893adb17b422179b9e779e4c32aa347 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Mon, 8 Oct 2018 11:21:44 -0700 Subject: firmware: xilinx: Add zynqmp IOCTL API for device control Add ZynqMP firmware IOCTL API to control and configure devices like PLLs, SD, Gem, etc. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Acked-by: Olof Johansson Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 015e130431e6..7a9db0861803 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -34,7 +34,8 @@ enum pm_api_id { PM_GET_API_VERSION = 1, - PM_QUERY_DATA = 35, + PM_IOCTL = 34, + PM_QUERY_DATA, PM_CLOCK_ENABLE, PM_CLOCK_DISABLE, PM_CLOCK_GETSTATE, @@ -99,6 +100,7 @@ struct zynqmp_eemi_ops { 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); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3 From 3fde0e16d016ecb273f0fa404b5d56b947fc0576 Mon Sep 17 00:00:00 2001 From: Jolly Shah Date: Mon, 8 Oct 2018 11:21:46 -0700 Subject: drivers: clk: Add ZynqMP clock driver This patch adds CCF compliant clock driver for ZynqMP. Clock driver queries supported clock information from firmware and regiters pll and output clocks with CCF. Signed-off-by: Rajan Vaja Signed-off-by: Tejas Patel Signed-off-by: Shubhrajyoti Datta Signed-off-by: Jolly Shah Acked-by: Olof Johansson Reviewed-by: Stephen Boyd Signed-off-by: Michal Simek --- include/linux/firmware/xlnx-zynqmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 7a9db0861803..3c3c28eff56a 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -72,6 +72,7 @@ enum pm_query_id { PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, PM_QID_CLOCK_GET_PARENTS, PM_QID_CLOCK_GET_ATTRIBUTES, + PM_QID_CLOCK_GET_NUM_CLOCKS = 12, }; /** -- cgit v1.2.3 From 7ed1d91a9ed61afe438ba51cbf49cb567ab7dca8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Sep 2018 13:06:58 +0200 Subject: dma-mapping: translate __GFP_NOFAIL to DMA_ATTR_NO_WARN This allows all dma_map_ops instances to entirely rely on DMA_ATTR_NO_WARN going forward. Signed-off-by: Christoph Hellwig Acked-by: Robin Murphy --- include/linux/dma-mapping.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 547a48bcfa3d..15bd41447025 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -558,9 +558,11 @@ static inline void dma_free_attrs(struct device *dev, size_t size, } static inline void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag) + dma_addr_t *dma_handle, gfp_t gfp) { - return dma_alloc_attrs(dev, size, dma_handle, flag, 0); + + return dma_alloc_attrs(dev, size, dma_handle, gfp, + (gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0); } static inline void dma_free_coherent(struct device *dev, size_t size, @@ -794,8 +796,12 @@ static inline void dmam_release_declared_memory(struct device *dev) static inline void *dma_alloc_wc(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t gfp) { - return dma_alloc_attrs(dev, size, dma_addr, gfp, - DMA_ATTR_WRITE_COMBINE); + unsigned long attrs = DMA_ATTR_NO_WARN; + + if (gfp & __GFP_NOWARN) + attrs |= DMA_ATTR_NO_WARN; + + return dma_alloc_attrs(dev, size, dma_addr, gfp, attrs); } #ifndef dma_alloc_writecombine #define dma_alloc_writecombine dma_alloc_wc -- cgit v1.2.3 From d7b6801673f95e5f72efd3ffba1bcbb606883049 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Tue, 9 Oct 2018 13:11:32 +0200 Subject: lightnvm: combine 1.2 and 2.0 command flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add nvm_set_flags helper to enable core to appropriately set the command flags for read/write/erase depending on which version a drive supports. The flags arguments can be distilled into the access hint, scrambling, and program/erase suspend. Replace the access hint with a "is_seq" parameter. The rest of the flags are dependent on the command opcode, which is trivial to detect and set. Signed-off-by: Matias Bjørling Reviewed-by: Javier González Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index e9e0d1c7eaf5..8acc2fe277d6 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -305,6 +305,8 @@ struct nvm_rq { u64 ppa_status; /* ppa media status */ int error; + int is_seq; /* Sequential hint flag. 1.2 only */ + void *private; }; -- cgit v1.2.3 From 656e33ca3d405196f94133babc4e38454a49cb73 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Tue, 9 Oct 2018 13:11:34 +0200 Subject: lightnvm: move device L2P detection to core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A 1.2 device is able to manage the logical to physical mapping table internally or leave it to the host. A target only supports one of those approaches, and therefore must check on initialization. Move this check to core to avoid each target implement the check. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 8acc2fe277d6..f4a84694e5e2 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -495,9 +495,15 @@ typedef void (nvm_tgt_exit_fn)(void *, bool); typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *); typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *); +enum { + NVM_TGT_F_DEV_L2P = 0, + NVM_TGT_F_HOST_L2P = 1 << 0, +}; + struct nvm_tgt_type { const char *name; unsigned int version[3]; + int flags; /* target entry points */ nvm_tgt_make_rq_fn *make_rq; -- cgit v1.2.3 From aff3fb18f957de93e629c7d3d2c4ef1f360aa511 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Tue, 9 Oct 2018 13:11:36 +0200 Subject: lightnvm: move bad block and chunk state logic to core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit pblk implements two data paths for recovery line state. One for 1.2 and another for 2.0, instead of having pblk implement these, combine them in the core to reduce complexity and make available to other targets. The new interface will adhere to the 2.0 chunk definition, including managing open chunks with an active write pointer. To provide this interface, a 1.2 device recovers the state of the chunks by manually detecting if a chunk is either free/open/close/offline, and if open, scanning the flash pages sequentially to find the next writeable page. This process takes on average ~10 seconds on a device with 64 dies, 1024 blocks and 60us read access time. The process can be parallelized but is left out for maintenance simplicity, as the 1.2 specification is deprecated. For 2.0 devices, the logic is maintained internally in the drive and retrieved through the 2.0 interface. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index f4a84694e5e2..0106984400bc 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -86,8 +86,8 @@ struct nvm_chk_meta; typedef int (nvm_id_fn)(struct nvm_dev *); typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *); typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int); -typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, struct nvm_chk_meta *, - sector_t, int); +typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, sector_t, int, + struct nvm_chk_meta *); typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *); typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); @@ -532,18 +532,13 @@ extern struct nvm_dev *nvm_alloc_dev(int); extern int nvm_register(struct nvm_dev *); extern void nvm_unregister(struct nvm_dev *); - -extern int nvm_get_chunk_meta(struct nvm_tgt_dev *tgt_dev, - struct nvm_chk_meta *meta, struct ppa_addr ppa, - int nchks); - -extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *, +extern int nvm_get_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr, + int, struct nvm_chk_meta *); +extern int nvm_set_chunk_meta(struct nvm_tgt_dev *, struct ppa_addr *, int, int); extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *); extern void nvm_end_io(struct nvm_rq *); -extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int); -extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *); #else /* CONFIG_NVM */ struct nvm_dev_ops; -- cgit v1.2.3 From 2cf99bbd106f89fc72f778e8ad9d5538f1ef939b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Tue, 9 Oct 2018 13:11:41 +0200 Subject: lightnvm: pblk: add helpers for chunk addresses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement helpers to go from ppas to a chunk within a line and an address within a chunk. These helpers will be used on the patches adding trace support in pblk, which will be sent in this window. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 0106984400bc..77743a02ec0d 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -487,6 +487,25 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, return l; } +static inline u64 dev_to_chunk_addr(struct nvm_dev *dev, void *addrf, + struct ppa_addr p) +{ + struct nvm_geo *geo = &dev->geo; + u64 caddr; + + if (geo->version == NVM_OCSSD_SPEC_12) { + struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)addrf; + + caddr = (u64)p.g.pg << ppaf->pg_offset; + caddr |= (u64)p.g.pl << ppaf->pln_offset; + caddr |= (u64)p.g.sec << ppaf->sec_offset; + } else { + caddr = p.m.sec; + } + + return caddr; +} + 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 *, -- cgit v1.2.3 From d68a9344041b6dd304ff382d0c7805869f09944f Mon Sep 17 00:00:00 2001 From: Hans Holmberg Date: Tue, 9 Oct 2018 13:11:46 +0200 Subject: lightnvm: introduce nvm_rq_to_ppa_list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a number of places in the lightnvm subsystem where the user iterates over the ppa list. Before iterating, the user must know if it is a single or multiple LBAs due to vector commands using either the nvm_rq ->ppa_addr or ->ppa_list fields on command submission, which leads to open-coding the if/else statement. Instead of having multiple if/else's, move it into a function that can be called by its users. A nice side effect of this cleanup is that this patch fixes up a bunch of cases where we don't consider the single-ppa case in pblk. Signed-off-by: Hans Holmberg Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 77743a02ec0d..50ac5b21297c 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -320,6 +320,11 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) return rqdata + 1; } +static inline struct ppa_addr *nvm_rq_to_ppa_list(struct nvm_rq *rqd) +{ + return (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr; +} + enum { NVM_BLK_ST_FREE = 0x1, /* Free block */ NVM_BLK_ST_TGT = 0x2, /* Block in use by target */ -- cgit v1.2.3 From 7f985f9a691dc25ddcfc9dc7ff21199f5ee1569c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Tue, 9 Oct 2018 13:11:56 +0200 Subject: lightnvm: move ppa transformations to core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Continuing the effort of moving 1.2 and 2.0 specific code to core, move 64_to_32 and 32_to_64 ppa helpers from pblk to core. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 83 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 50ac5b21297c..eb7300c20f24 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -511,6 +511,89 @@ static inline u64 dev_to_chunk_addr(struct nvm_dev *dev, void *addrf, return caddr; } +static inline struct ppa_addr nvm_ppa32_to_ppa64(struct nvm_dev *dev, + void *addrf, u32 ppa32) +{ + struct ppa_addr ppa64; + + ppa64.ppa = 0; + + if (ppa32 == -1) { + ppa64.ppa = ADDR_EMPTY; + } else if (ppa32 & (1U << 31)) { + ppa64.c.line = ppa32 & ((~0U) >> 1); + ppa64.c.is_cached = 1; + } else { + struct nvm_geo *geo = &dev->geo; + + if (geo->version == NVM_OCSSD_SPEC_12) { + struct nvm_addrf_12 *ppaf = addrf; + + ppa64.g.ch = (ppa32 & ppaf->ch_mask) >> + ppaf->ch_offset; + ppa64.g.lun = (ppa32 & ppaf->lun_mask) >> + ppaf->lun_offset; + ppa64.g.blk = (ppa32 & ppaf->blk_mask) >> + ppaf->blk_offset; + ppa64.g.pg = (ppa32 & ppaf->pg_mask) >> + ppaf->pg_offset; + ppa64.g.pl = (ppa32 & ppaf->pln_mask) >> + ppaf->pln_offset; + ppa64.g.sec = (ppa32 & ppaf->sec_mask) >> + ppaf->sec_offset; + } else { + struct nvm_addrf *lbaf = addrf; + + ppa64.m.grp = (ppa32 & lbaf->ch_mask) >> + lbaf->ch_offset; + ppa64.m.pu = (ppa32 & lbaf->lun_mask) >> + lbaf->lun_offset; + ppa64.m.chk = (ppa32 & lbaf->chk_mask) >> + lbaf->chk_offset; + ppa64.m.sec = (ppa32 & lbaf->sec_mask) >> + lbaf->sec_offset; + } + } + + return ppa64; +} + +static inline u32 nvm_ppa64_to_ppa32(struct nvm_dev *dev, + void *addrf, struct ppa_addr ppa64) +{ + u32 ppa32 = 0; + + if (ppa64.ppa == ADDR_EMPTY) { + ppa32 = ~0U; + } else if (ppa64.c.is_cached) { + ppa32 |= ppa64.c.line; + ppa32 |= 1U << 31; + } else { + struct nvm_geo *geo = &dev->geo; + + if (geo->version == NVM_OCSSD_SPEC_12) { + struct nvm_addrf_12 *ppaf = addrf; + + ppa32 |= ppa64.g.ch << ppaf->ch_offset; + ppa32 |= ppa64.g.lun << ppaf->lun_offset; + ppa32 |= ppa64.g.blk << ppaf->blk_offset; + ppa32 |= ppa64.g.pg << ppaf->pg_offset; + ppa32 |= ppa64.g.pl << ppaf->pln_offset; + ppa32 |= ppa64.g.sec << ppaf->sec_offset; + } else { + struct nvm_addrf *lbaf = addrf; + + ppa32 |= ppa64.m.grp << lbaf->ch_offset; + ppa32 |= ppa64.m.pu << lbaf->lun_offset; + ppa32 |= ppa64.m.chk << lbaf->chk_offset; + ppa32 |= ppa64.m.sec << lbaf->sec_offset; + } + } + + return ppa32; +} + + 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 *, -- cgit v1.2.3 From bf82fa2f584f1c6e12df8c04fca715d53e7f32d5 Mon Sep 17 00:00:00 2001 From: Hans Holmberg Date: Tue, 9 Oct 2018 13:11:59 +0200 Subject: lightnvm: pblk: fix mapping issue on failed writes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On 1.2-devices, the mapping-out of remaning sectors in the failed-write's block can result in an infinite loop, stalling the write pipeline, fix this. Fixes: 6a3abf5beef6 ("lightnvm: pblk: rework write error recovery path") Signed-off-by: Hans Holmberg Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index eb7300c20f24..2fdeac1a420d 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -593,6 +593,42 @@ static inline u32 nvm_ppa64_to_ppa32(struct nvm_dev *dev, return ppa32; } +static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev, + struct ppa_addr *ppa) +{ + struct nvm_geo *geo = &dev->geo; + int last = 0; + + if (geo->version == NVM_OCSSD_SPEC_12) { + int sec = ppa->g.sec; + + sec++; + if (sec == geo->ws_min) { + int pg = ppa->g.pg; + + sec = 0; + pg++; + if (pg == geo->num_pg) { + int pl = ppa->g.pl; + + pg = 0; + pl++; + if (pl == geo->num_pln) + last = 1; + + ppa->g.pl = pl; + } + ppa->g.pg = pg; + } + ppa->g.sec = sec; + } else { + ppa->m.sec++; + if (ppa->m.sec == geo->clba) + last = 1; + } + + return last; +} typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); -- cgit v1.2.3 From 7d49b28a80b830c3ca876d33bedc58d62a78e16f Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Tue, 25 Sep 2018 23:58:41 -0400 Subject: smp,cpumask: introduce on_each_cpu_cond_mask Introduce a variant of on_each_cpu_cond that iterates only over the CPUs in a cpumask, in order to avoid making callbacks for every single CPU in the system when we only need to test a subset. Cc: npiggin@gmail.com Cc: mingo@kernel.org Cc: will.deacon@arm.com Cc: songliubraving@fb.com Cc: kernel-team@fb.com Cc: hpa@zytor.com Cc: luto@kernel.org Signed-off-by: Rik van Riel Signed-off-by: Peter Zijlstra (Intel) Link: http://lkml.kernel.org/r/20180926035844.1420-5-riel@surriel.com --- include/linux/smp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 9fb239e12b82..a56f08ff3097 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -53,6 +53,10 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), smp_call_func_t func, void *info, bool wait, gfp_t gfp_flags); +void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags, const struct cpumask *mask); + int smp_call_function_single_async(int cpu, call_single_data_t *csd); #ifdef CONFIG_SMP -- cgit v1.2.3 From f2e74abfaad446765ce0350aed1d9c5eed5b1b36 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:38 +0200 Subject: remoteproc: add release ops in rproc_mem_entry struct Memory entry could be allocated in different ways (ioremap, dma_alloc_coherent, internal RAM allocator...). This patch introduces a release ops in rproc_mem_entry structure to associate dedicated release mechanism to each memory entry descriptor in order to keep remoteproc core generic. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson 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 75f9ca05b865..4116e92d4b3d 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -305,12 +305,15 @@ struct fw_rsc_vdev { struct fw_rsc_vdev_vring vring[0]; } __packed; +struct rproc; + /** * struct rproc_mem_entry - memory entry descriptor * @va: virtual address * @dma: dma address * @len: length, in bytes * @da: device address + * @release: release associated memory * @priv: associated data * @node: list node */ @@ -321,9 +324,9 @@ struct rproc_mem_entry { u32 da; void *priv; struct list_head node; + int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; -struct rproc; struct firmware; /** -- cgit v1.2.3 From 3265230c5b05fe919291d09e266a8aedc85ebad0 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:39 +0200 Subject: remoteproc: add name in rproc_mem_entry struct Add name field in struct rproc_mem_entry. This new field will be used to match memory area requested in resource table with pre-registered carveout. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson 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 4116e92d4b3d..19908c930f47 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -315,6 +315,7 @@ struct rproc; * @da: device address * @release: release associated memory * @priv: associated data + * @name: associated memory region name (optional) * @node: list node */ struct rproc_mem_entry { @@ -323,6 +324,7 @@ struct rproc_mem_entry { int len; u32 da; void *priv; + char name[32]; struct list_head node; int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; -- cgit v1.2.3 From 72029c901a0244ca2e1eb09e1c453413a17f5787 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:40 +0200 Subject: remoteproc: add helper function to allocate and init rproc_mem_entry struct This patch introduces rproc_mem_entry_init helper function to simplify rproc_mem_entry structure allocation and filling by client. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 19908c930f47..9e2b84fa2efa 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -559,6 +559,12 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +struct rproc_mem_entry * +rproc_mem_entry_init(struct device *dev, + void *va, dma_addr_t dma, int len, u32 da, + int (*release)(struct rproc *, struct rproc_mem_entry *), + const char *name, ...); + int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); -- cgit v1.2.3 From 15c0b0258e4f1c3c817f34d092d2cc6ff5178bdd Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:41 +0200 Subject: remoteproc: introduce rproc_add_carveout function This patch introduces a new API to allow platform driver to register platform specific carveout regions. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson 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 9e2b84fa2efa..8a350265d883 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -559,6 +559,8 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); + struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, int len, u32 da, -- cgit v1.2.3 From d7c51706d0956472b7c0530b1bf8fba32d82ee6b Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:43 +0200 Subject: remoteproc: add alloc ops in rproc_mem_entry struct Memory entry could be allocated in different ways (ioremap, dma_alloc_coherent, internal RAM allocator...). This patch introduces an alloc ops in rproc_mem_entry structure to associate dedicated allocation mechanism to each memory entry descriptor in order to do remote core agnostic from memory allocators. The introduction of this ops allows to perform allocation of all registered carveout at the same time, just before calling rproc_start(). It simplifies and makes uniform carveout management whatever origin. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8a350265d883..d251c091303c 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -317,6 +317,9 @@ struct rproc; * @priv: associated data * @name: associated memory region name (optional) * @node: list node + * @rsc_offset: offset in resource table + * @flags: iommu protection flags + * @alloc: specific memory allocator function */ struct rproc_mem_entry { void *va; @@ -326,6 +329,9 @@ struct rproc_mem_entry { void *priv; char name[32]; struct list_head node; + u32 rsc_offset; + u32 flags; + int (*alloc)(struct rproc *rproc, struct rproc_mem_entry *mem); int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; @@ -564,6 +570,7 @@ void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, int len, u32 da, + int (*alloc)(struct rproc *, struct rproc_mem_entry *), int (*release)(struct rproc *, struct rproc_mem_entry *), const char *name, ...); -- cgit v1.2.3 From 1429cca1175f4cb64dd5d61ffd6037895a41d672 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:44 +0200 Subject: remoteproc: add helper function to allocate rproc_mem_entry from reserved memory This patch introduces rproc_res_mem_entry_init() helper function to allocate a rproc_mem_entry structure from a reserved memory region. In that case, rproc_mem_entry structure has no alloc and release ops. It will be used to assigned the specified reserved memory to any rproc sub device. Relation between rproc_mem_entry and rproc sub device will be done by name. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index d251c091303c..d4cabe8da507 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -319,6 +319,7 @@ struct rproc; * @node: list node * @rsc_offset: offset in resource table * @flags: iommu protection flags + * @of_resm_idx: reserved memory phandle index * @alloc: specific memory allocator function */ struct rproc_mem_entry { @@ -331,6 +332,7 @@ struct rproc_mem_entry { struct list_head node; u32 rsc_offset; u32 flags; + u32 of_resm_idx; int (*alloc)(struct rproc *rproc, struct rproc_mem_entry *mem); int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; @@ -574,6 +576,10 @@ rproc_mem_entry_init(struct device *dev, int (*release)(struct rproc *, struct rproc_mem_entry *), const char *name, ...); +struct rproc_mem_entry * +rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, int len, + u32 da, const char *name, ...); + int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); -- cgit v1.2.3 From f8ec92a9f63b3b11e399409141b7868bb405e6b5 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Fri, 5 Oct 2018 08:52:58 +0200 Subject: gpiolib: Add init_valid_mask exported function Add a function that allows initializing the valid_mask from gpiochip_add_data. This prevents race conditions during gpiochip initialization. If the function is not exported, then the old behaviour is respected, this is, set all gpios as valid. Signed-off-by: Ricardo Ribalda Delgado Tested-by: Jeffrey Hugo Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f6b95734073f..c5a51af8f76e 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -280,6 +280,9 @@ struct gpio_chip { void (*dbg_show)(struct seq_file *s, struct gpio_chip *chip); + + int (*init_valid_mask)(struct gpio_chip *chip); + int base; u16 ngpio; const char *const *names; @@ -318,7 +321,9 @@ struct gpio_chip { /** * @need_valid_mask: * - * If set core allocates @valid_mask with all bits set to one. + * If set core allocates @valid_mask with all its values initialized + * with init_valid_mask() or set to one if init_valid_mask() is not + * defined */ bool need_valid_mask; -- cgit v1.2.3 From 3e779a2e7f909015f21428b66834127496110b6d Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 8 Oct 2018 09:32:13 -0700 Subject: gpio: Assign gpio_irq_chip::parents to non-stack pointer gpiochip_set_cascaded_irqchip() is passed 'parent_irq' as an argument and then the address of that argument is assigned to the gpio chips gpio_irq_chip 'parents' pointer shortly thereafter. This can't ever work, because we've just assigned some stack address to a pointer that we plan to dereference later in gpiochip_irq_map(). I ran into this issue with the KASAN report below when gpiochip_irq_map() tried to setup the parent irq with a total junk pointer for the 'parents' array. BUG: KASAN: stack-out-of-bounds in gpiochip_irq_map+0x228/0x248 Read of size 4 at addr ffffffc0dde472e0 by task swapper/0/1 CPU: 7 PID: 1 Comm: swapper/0 Not tainted 4.14.72 #34 Call trace: [] dump_backtrace+0x0/0x718 [] show_stack+0x20/0x2c [] __dump_stack+0x20/0x28 [] dump_stack+0x80/0xbc [] print_address_description+0x70/0x238 [] kasan_report+0x1cc/0x260 [] __asan_report_load4_noabort+0x2c/0x38 [] gpiochip_irq_map+0x228/0x248 [] irq_domain_associate+0x114/0x2ec [] irq_create_mapping+0x120/0x234 [] irq_create_fwspec_mapping+0x4c8/0x88c [] irq_create_of_mapping+0x180/0x210 [] of_irq_get+0x138/0x198 [] spi_drv_probe+0x94/0x178 [] driver_probe_device+0x51c/0x824 [] __device_attach_driver+0x148/0x20c [] bus_for_each_drv+0x120/0x188 [] __device_attach+0x19c/0x2dc [] device_initial_probe+0x20/0x2c [] bus_probe_device+0x80/0x154 [] device_add+0x9b8/0xbdc [] spi_add_device+0x1b8/0x380 [] spi_register_controller+0x111c/0x1378 [] spi_geni_probe+0x4dc/0x6f8 [] platform_drv_probe+0xdc/0x130 [] driver_probe_device+0x51c/0x824 [] __driver_attach+0x100/0x194 [] bus_for_each_dev+0x104/0x16c [] driver_attach+0x48/0x54 [] bus_add_driver+0x274/0x498 [] driver_register+0x1ac/0x230 [] __platform_driver_register+0xcc/0xdc [] spi_geni_driver_init+0x1c/0x24 [] do_one_initcall+0x240/0x3dc [] kernel_init_freeable+0x378/0x468 [] kernel_init+0x14/0x110 [] ret_from_fork+0x10/0x18 The buggy address belongs to the page: page:ffffffbf037791c0 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x4000000000000000() raw: 4000000000000000 0000000000000000 0000000000000000 00000000ffffffff raw: ffffffbf037791e0 ffffffbf037791e0 0000000000000000 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffffc0dde47180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc0dde47200: f1 f1 f1 f1 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f2 f2 >ffffffc0dde47280: f2 f2 00 00 00 00 00 00 00 00 00 00 f3 f3 f3 f3 ^ ffffffc0dde47300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc0dde47380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Let's leave around one unsigned int in the gpio_irq_chip struct for the single parent irq case and repoint the 'parents' array at it. This way code is left mostly intact to setup parents and we waste an extra few bytes per structure of which there should be only a handful in a system. Cc: Evan Green Cc: Thierry Reding Cc: Grygorii Strashko Fixes: e0d897289813 ("gpio: Implement tighter IRQ chip integration") Signed-off-by: Stephen Boyd Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 0ea328e71ec9..a4d5eb37744a 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -94,6 +94,13 @@ struct gpio_irq_chip { */ unsigned int num_parents; + /** + * @parent_irq: + * + * For use by gpiochip_set_cascaded_irqchip() + */ + unsigned int parent_irq; + /** * @parents: * -- cgit v1.2.3 From 5039563e7c25eccd7fec1de6706011009d1c5665 Mon Sep 17 00:00:00 2001 From: Trent Piepho Date: Thu, 20 Sep 2018 19:18:32 +0000 Subject: spi: Add driver_override SPI device attribute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This attribute works the same was as the identically named attribute for PCI, AMBA, and platform devices. For reference, see: commit 3cf385713460 ("ARM: 8256/1: driver coamba: add device binding path 'driver_override'") commit 3d713e0e382e ("driver core: platform: add device binding path 'driver_override'") commit 782a985d7af2 ("PCI: Introduce new device binding path using pci_dev.driver_override") If the name of a driver is written to this attribute, then the device will bind to the named driver and only the named driver. The device will bind to the driver even if the driver does not list the device in its id table. This behavior is different than the driver's bind attribute, which only allows binding to devices that are listed as supported by the driver. It can be used to bind a generic driver, like spidev, to a device. Signed-off-by: Trent Piepho Reviewed-by: Jan Kundrát Tested-by: Jan Kundrát Reviewed-by: Geert Uytterhoeven Signed-off-by: Mark Brown --- 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 f08824ea1968..3de9958ca28b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -159,6 +159,7 @@ struct spi_device { void *controller_state; void *controller_data; char modalias[SPI_NAME_SIZE]; + const char *driver_override; int cs_gpio; /* chip select gpio */ /* the statistics */ -- cgit v1.2.3 From 52916982af48d9f9fc01ad825259de1eb3a9b25e Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:35 -0600 Subject: PCI/P2PDMA: Support peer-to-peer memory Some PCI devices may have memory mapped in a BAR space that's intended for use in peer-to-peer transactions. To enable such transactions the memory must be registered with ZONE_DEVICE pages so it can be used by DMA interfaces in existing drivers. Add an interface for other subsystems to find and allocate chunks of P2P memory as necessary to facilitate transfers between two PCI peers: struct pci_dev *pci_p2pmem_find[_many](); int pci_p2pdma_distance[_many](); void *pci_alloc_p2pmem(); The new interface requires a driver to collect a list of client devices involved in the transaction then call pci_p2pmem_find() to obtain any suitable P2P memory. Alternatively, if the caller knows a device which provides P2P memory, they can use pci_p2pdma_distance() to determine if it is usable. With a suitable p2pmem device, memory can then be allocated with pci_alloc_p2pmem() for use in DMA transactions. Depending on hardware, using peer-to-peer memory may reduce the bandwidth of the transfer but can significantly reduce pressure on system memory. This may be desirable in many cases: for example a system could be designed with a small CPU connected to a PCIe switch by a small number of lanes which would maximize the number of lanes available to connect to NVMe devices. The code is designed to only utilize the p2pmem device if all the devices involved in a transfer are behind the same PCI bridge. This is because we have no way of knowing whether peer-to-peer routing between PCIe Root Ports is supported (PCIe r4.0, sec 1.3.1). Additionally, the benefits of P2P transfers that go through the RC is limited to only reducing DRAM usage and, in some cases, coding convenience. The PCI-SIG may be exploring adding a new capability bit to advertise whether this is possible for future hardware. This commit includes significant rework and feedback from Christoph Hellwig. Signed-off-by: Christoph Hellwig Signed-off-by: Logan Gunthorpe [bhelgaas: fold in fix from Keith Busch : https://lore.kernel.org/linux-pci/20181012155920.15418-1-keith.busch@intel.com, to address comment from Dan Carpenter , fold in https://lore.kernel.org/linux-pci/20181017160510.17926-1-logang@deltatee.com] Signed-off-by: Bjorn Helgaas --- include/linux/memremap.h | 5 +++ include/linux/mm.h | 18 +++++++++ include/linux/pci-p2pdma.h | 92 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 4 ++ 4 files changed, 119 insertions(+) create mode 100644 include/linux/pci-p2pdma.h (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f91f9e763557..9553370ebdad 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -53,11 +53,16 @@ struct vmem_altmap { * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). + * + * MEMORY_DEVICE_PCI_P2PDMA: + * Device memory residing in a PCI BAR intended for use with Peer-to-Peer + * transactions. */ enum memory_type { MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_PUBLIC, MEMORY_DEVICE_FS_DAX, + MEMORY_DEVICE_PCI_P2PDMA, }; /* diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..2055df412a77 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -890,6 +890,19 @@ static inline bool is_device_public_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PUBLIC; } +#ifdef CONFIG_PCI_P2PDMA +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; +} +#else /* CONFIG_PCI_P2PDMA */ +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return false; +} +#endif /* CONFIG_PCI_P2PDMA */ + #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline void dev_pagemap_get_ops(void) { @@ -913,6 +926,11 @@ static inline bool is_device_public_page(const struct page *page) { return false; } + +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return false; +} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline void get_page(struct page *page) diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h new file mode 100644 index 000000000000..7bdaacfd5892 --- /dev/null +++ b/include/linux/pci-p2pdma.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCI Peer 2 Peer DMA support. + * + * Copyright (c) 2016-2018, Logan Gunthorpe + * Copyright (c) 2016-2017, Microsemi Corporation + * Copyright (c) 2017, Christoph Hellwig + * Copyright (c) 2018, Eideticom Inc. + */ + +#ifndef _LINUX_PCI_P2PDMA_H +#define _LINUX_PCI_P2PDMA_H + +#include + +struct block_device; +struct scatterlist; + +#ifdef CONFIG_PCI_P2PDMA +int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, + u64 offset); +int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, + int num_clients, bool verbose); +bool pci_has_p2pmem(struct pci_dev *pdev); +struct pci_dev *pci_p2pmem_find_many(struct device **clients, int num_clients); +void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size); +void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size); +pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, void *addr); +struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, + unsigned int *nents, u32 length); +void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); +void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); +#else /* CONFIG_PCI_P2PDMA */ +static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, + size_t size, u64 offset) +{ + return -EOPNOTSUPP; +} +static inline int pci_p2pdma_distance_many(struct pci_dev *provider, + struct device **clients, int num_clients, bool verbose) +{ + return -1; +} +static inline bool pci_has_p2pmem(struct pci_dev *pdev) +{ + return false; +} +static inline struct pci_dev *pci_p2pmem_find_many(struct device **clients, + int num_clients) +{ + return NULL; +} +static inline void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size) +{ + return NULL; +} +static inline void pci_free_p2pmem(struct pci_dev *pdev, void *addr, + size_t size) +{ +} +static inline pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, + void *addr) +{ + return 0; +} +static inline struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, + unsigned int *nents, u32 length) +{ + return NULL; +} +static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev, + struct scatterlist *sgl) +{ +} +static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) +{ +} +#endif /* CONFIG_PCI_P2PDMA */ + + +static inline int pci_p2pdma_distance(struct pci_dev *provider, + struct device *client, bool verbose) +{ + return pci_p2pdma_distance_many(provider, &client, 1, verbose); +} + +static inline struct pci_dev *pci_p2pmem_find(struct device *client) +{ + return pci_p2pmem_find_many(&client, 1); +} + +#endif /* _LINUX_PCI_P2P_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..bf5277768f69 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -281,6 +281,7 @@ struct pcie_link_state; struct pci_vpd; struct pci_sriov; struct pci_ats; +struct pci_p2pdma; /* The pci_dev structure describes PCI devices */ struct pci_dev { @@ -438,6 +439,9 @@ struct pci_dev { #endif #ifdef CONFIG_PCI_PASID u16 pasid_features; +#endif +#ifdef CONFIG_PCI_P2PDMA + struct pci_p2pdma *p2pdma; #endif phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ -- cgit v1.2.3 From df2fc43d09d3ee5ede82cab9299df5e78aa427b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 13 Sep 2018 11:17:23 +0200 Subject: list: introduce list_bulk_move_tail helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move all entries between @first and including @last before @head. This is useful for LRU lists where a whole block of entries should be moved to the end of the list. Used as a band aid in TTM, but better placed in the common list headers. Acked-by: Dave Airlie Signed-off-by: Christian König Reviewed-by: Huang Rui Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher --- include/linux/list.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index de04cc5ed536..edb7628e46ed 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -183,6 +183,29 @@ static inline void list_move_tail(struct list_head *list, list_add_tail(list, head); } +/** + * list_bulk_move_tail - move a subsection of a list to its tail + * @head: the head that will follow our entry + * @first: first entry to move + * @last: last entry to move, can be the same as first + * + * Move all entries between @first and including @last before @head. + * All three entries must belong to the same linked list. + */ +static inline void list_bulk_move_tail(struct list_head *head, + struct list_head *first, + struct list_head *last) +{ + first->prev->next = last->next; + last->next->prev = first->prev; + + head->prev->next = first; + first->prev = head->prev; + + last->next = head; + head->prev = last; +} + /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test -- cgit v1.2.3 From 18b01b16e8bae9cd227909f6e6d2783d74855f65 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:22 +0200 Subject: PCI: Remove pci_unmap_addr() wrappers for DMA API Only some of these were still used by the cxgb4 driver, and that despite the fact that the driver otherwise uses the generic DMA API. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma.h | 12 ------------ include/linux/pci.h | 1 - 2 files changed, 13 deletions(-) delete mode 100644 include/linux/pci-dma.h (limited to 'include/linux') diff --git a/include/linux/pci-dma.h b/include/linux/pci-dma.h deleted file mode 100644 index 0f7aa7353ca3..000000000000 --- a/include/linux/pci-dma.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_PCI_DMA_H -#define _LINUX_PCI_DMA_H - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) DEFINE_DMA_UNMAP_ADDR(ADDR_NAME); -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) DEFINE_DMA_UNMAP_LEN(LEN_NAME); -#define pci_unmap_addr dma_unmap_addr -#define pci_unmap_addr_set dma_unmap_addr_set -#define pci_unmap_len dma_unmap_len -#define pci_unmap_len_set dma_unmap_len_set - -#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..e938e80e59c1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1342,7 +1342,6 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, /* kmem_cache style wrapper around pci_alloc_consistent() */ -#include #include #define pci_pool dma_pool -- cgit v1.2.3 From a6f44cf9f5cc60471cf06f3d5391fc6041eb37a5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:23 +0200 Subject: PCI: Remove pci_set_dma_seg_boundary() The two callers can just use dma_set_seg_boundary() directly. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma-compat.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index c3f1b44ade29..558a109ab497 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -125,12 +125,6 @@ static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, { return dma_set_max_seg_size(&dev->dev, size); } - -static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, - unsigned long mask) -{ - return dma_set_seg_boundary(&dev->dev, mask); -} #else static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } @@ -139,9 +133,6 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size) { return -EIO; } -static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, - unsigned long mask) -{ return -EIO; } #endif #endif -- cgit v1.2.3 From b0da3498c587c20e64799c4c7ba65a31314b2182 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:24 +0200 Subject: PCI: Remove pci_set_dma_max_seg_size() The few callers can just use dma_set_max_seg_size ()directly. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pci-dma-compat.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index 558a109ab497..cb1adf0b78a9 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -119,20 +119,11 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) { return dma_set_coherent_mask(&dev->dev, mask); } - -static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, - unsigned int size) -{ - return dma_set_max_seg_size(&dev->dev, size); -} #else static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } -static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, - unsigned int size) -{ return -EIO; } #endif #endif -- cgit v1.2.3 From f6a8a19bb11b46d60250ddc4e3e1ba6aa166f488 Mon Sep 17 00:00:00 2001 From: Denis Drozdov Date: Tue, 14 Aug 2018 14:08:51 +0300 Subject: RDMA/netdev: Hoist alloc_netdev_mqs out of the driver netdev has several interfaces that expect to call alloc_netdev_mqs from the core code, with the driver only providing the arguments. This is incompatible with the rdma_netdev interface that returns the netdev directly. Thus re-organize the API used by ipoib so that the verbs core code calls alloc_netdev_mqs for the driver. This is done by allowing the drivers to provide the allocation parameters via a 'get_params' callback and then initializing an allocated netdev as a second step. Fixes: cd565b4b51e5 ("IB/IPoIB: Support acceleration options callbacks") Signed-off-by: Jason Gunthorpe Signed-off-by: Denis Drozdov Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 26a92462f4ce..4b75796cac23 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1228,21 +1228,15 @@ 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); -#ifndef CONFIG_MLX5_CORE_IPOIB -static inline -struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, - struct ib_device *ibdev, - const char *name, - void (*setup)(struct net_device *)) -{ - return ERR_PTR(-EOPNOTSUPP); -} -#else +#ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, const char *name, void (*setup)(struct net_device *)); #endif /* CONFIG_MLX5_CORE_IPOIB */ +int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, + struct ib_device *device, + struct rdma_netdev_alloc_params *params); struct mlx5_profile { u64 mask; -- cgit v1.2.3 From 37fdffb217a45609edccbb8b407d031143f551c0 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 21 Aug 2018 14:41:41 +0300 Subject: net/mlx5: WQ, fixes for fragmented WQ buffers API mlx5e netdevice used to calculate fragment edges by a call to mlx5_wq_cyc_get_frag_size(). This calculation did not give the correct indication for queues smaller than a PAGE_SIZE, (broken by default on PowerPC, where PAGE_SIZE == 64KB). Here it is replaced by the correct new calls/API. Since (TX/RX) Work Queues buffers are fragmented, here we introduce changes to the API in core driver, so that it gets a stride index and returns the index of last stride on same fragment, and an additional wrapping function that returns the number of physically contiguous strides that can be written contiguously to the work queue. This obsoletes the following API functions, and their buggy usage in EN driver: * mlx5_wq_cyc_get_frag_size() * mlx5_wq_cyc_ctr2fragix() The new API improves modularity and hides the details of such calculation for mlx5e netdevice and mlx5_ib rdma drivers. New calculation is also more efficient, and improves performance as follows: Packet rate test: pktgen, UDP / IPv4, 64byte, single ring, 8K ring size. Before: 16,477,619 pps After: 17,085,793 pps 3.7% improvement Fixes: 3a2f70331226 ("net/mlx5: Use order-0 allocations for all WQ types") Signed-off-by: Tariq Toukan Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 66d94b4557cf..88a041b73abf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1032,6 +1032,14 @@ static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, ((fbc->frag_sz_m1 & ix) << fbc->log_stride); } +static inline u32 +mlx5_frag_buf_get_idx_last_contig_stride(struct mlx5_frag_buf_ctrl *fbc, u32 ix) +{ + u32 last_frag_stride_idx = (ix + fbc->strides_offset) | fbc->frag_sz_m1; + + return min_t(u32, last_frag_stride_idx - fbc->strides_offset, fbc->sz_m1); +} + int mlx5_cmd_init(struct mlx5_core_dev *dev); void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); void mlx5_cmd_use_events(struct mlx5_core_dev *dev); -- cgit v1.2.3 From a36700589b85443e28170be59fa11c8a104130a5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 10 Oct 2018 20:29:44 -0500 Subject: signal: Guard against negative signal numbers in copy_siginfo_from_user32 While fixing an out of bounds array access in known_siginfo_layout reported by the kernel test robot it became apparent that the same bug exists in siginfo_layout and affects copy_siginfo_from_user32. The straight forward fix that makes guards against making this mistake in the future and should keep the code size small is to just take an unsigned signal number instead of a signed signal number, as I did to fix known_siginfo_layout. Cc: stable@vger.kernel.org Fixes: cc731525f26a ("signal: Remove kernel interal si_code magic") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 706a499d1eb1..200ed96a05af 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -40,7 +40,7 @@ enum siginfo_layout { SIL_SYS, }; -enum siginfo_layout siginfo_layout(int sig, int si_code); +enum siginfo_layout siginfo_layout(unsigned sig, int si_code); /* * Define some primitives to manipulate sigset_t. -- cgit v1.2.3 From a6ca88b241d5e929e6e60b12ad8cd288f0ffa256 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 1 Oct 2018 22:36:36 -0700 Subject: trace_uprobe: support reference counter in fd-based uprobe This patch enables uprobes with reference counter in fd-based uprobe. Highest 32 bits of perf_event_attr.config is used to stored offset of the reference count (semaphore). Format information in /sys/bus/event_source/devices/uprobe/format/ is updated to reflect this new feature. Link: http://lkml.kernel.org/r/20181002053636.1896903-1-songliubraving@fb.com Cc: Oleg Nesterov Acked-by: Peter Zijlstra (Intel) Reviewed-and-tested-by: Ravi Bangoria Signed-off-by: Song Liu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 78a010e19ed4..4130a5497d40 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -575,7 +575,8 @@ extern int bpf_get_kprobe_info(const struct perf_event *event, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS -extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe); +extern int perf_uprobe_init(struct perf_event *event, + unsigned long ref_ctr_offset, bool is_retprobe); extern void perf_uprobe_destroy(struct perf_event *event); extern int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, -- cgit v1.2.3 From 68c0d69dee594e1488aebe12aa50fd79a3e5e5b5 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 5 Oct 2018 16:59:04 -0700 Subject: hwmon: (core) Add hwmon_in_enable attribute According to hwmon ABI, in%d_enable is a sysfs interface that allows user space to enable and disable the input sensor. So this patch just simply adds the attribute to the list. Signed-off-by: Nicolin Chen Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 9493d4a388db..99e0c1b0b5fb 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -118,6 +118,7 @@ enum hwmon_in_attributes { hwmon_in_max_alarm, hwmon_in_lcrit_alarm, hwmon_in_crit_alarm, + hwmon_in_enable, }; #define HWMON_I_INPUT BIT(hwmon_in_input) @@ -135,6 +136,7 @@ enum hwmon_in_attributes { #define HWMON_I_MAX_ALARM BIT(hwmon_in_max_alarm) #define HWMON_I_LCRIT_ALARM BIT(hwmon_in_lcrit_alarm) #define HWMON_I_CRIT_ALARM BIT(hwmon_in_crit_alarm) +#define HWMON_I_ENABLE BIT(hwmon_in_enable) enum hwmon_curr_attributes { hwmon_curr_input, -- cgit v1.2.3 From af7d6cce53694a88d6a1bb60c9a239a6a5144459 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 9 Oct 2018 17:48:14 +0200 Subject: net: ipv4: update fnhe_pmtu when first hop's MTU changes Since commit 5aad1de5ea2c ("ipv4: use separate genid for next hop exceptions"), exceptions get deprecated separately from cached routes. In particular, administrative changes don't clear PMTU anymore. As Stefano described in commit e9fa1495d738 ("ipv6: Reflect MTU changes on PMTU of exceptions for MTU-less routes"), the PMTU discovered before the local MTU change can become stale: - if the local MTU is now lower than the PMTU, that PMTU is now incorrect - if the local MTU was the lowest value in the path, and is increased, we might discover a higher PMTU Similarly to what commit e9fa1495d738 did for IPv6, update PMTU in those cases. If the exception was locked, the discovered PMTU was smaller than the minimal accepted PMTU. In that case, if the new local MTU is smaller than the current PMTU, let PMTU discovery figure out if locking of the exception is still needed. To do this, we need to know the old link MTU in the NETDEV_CHANGEMTU notifier. By the time the notifier is called, dev->mtu has been changed. This patch adds the old MTU as additional information in the notifier structure, and a new call_netdevice_notifiers_u32() function. Fixes: 5aad1de5ea2c ("ipv4: use separate genid for next hop exceptions") Signed-off-by: Sabrina Dubroca Reviewed-by: Stefano Brivio Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c7861e4b402c..d837dad24b4c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2458,6 +2458,13 @@ struct netdev_notifier_info { struct netlink_ext_ack *extack; }; +struct netdev_notifier_info_ext { + struct netdev_notifier_info info; /* must be first */ + union { + u32 mtu; + } ext; +}; + struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; -- cgit v1.2.3 From ce76d938dd98817f998c905e01fbb99b072c0bf6 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 5 Oct 2018 15:43:05 +0300 Subject: lib: Add memcat_p(): paste 2 pointer arrays together This adds a helper to paste 2 pointer arrays together, useful for merging various types of attribute arrays. There are a few places in the kernel tree where this is open coded, and I just added one more in the STM class. The naming is inspired by memset_p() and memcat(), and partial credit for it goes to Andy Shevchenko. This patch adds the function wrapped in a type-enforcing macro and a test module. Signed-off-by: Alexander Shishkin Reviewed-by: Andy Shevchenko Tested-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/string.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 4a5a0eb7df51..27d0482e5e05 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -131,6 +131,13 @@ static inline void *memset_p(void **p, void *v, __kernel_size_t n) return memset64((uint64_t *)p, (uintptr_t)v, n); } +extern void **__memcat_p(void **a, void **b); +#define memcat_p(a, b) ({ \ + BUILD_BUG_ON_MSG(!__same_type(*(a), *(b)), \ + "type mismatch in memcat_p()"); \ + (typeof(*a) *)__memcat_p((void **)(a), (void **)(b)); \ +}) + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif -- cgit v1.2.3 From f458e832ba510f843807fc2c2906a8fb59554c9f Mon Sep 17 00:00:00 2001 From: Chaitanya T K Date: Sat, 6 Oct 2018 19:34:59 +0200 Subject: mac80211: minstrel: Enable STBC and LDPC for VHT Rates If peer support reception of STBC and LDPC, enable them for better performance. Signed-off-by: Chaitanya TK Signed-off-by: Felix Fietkau 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 c4809ad8ab46..0ef67f837ae1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1670,6 +1670,7 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 #define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 #define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 +#define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 #define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 -- cgit v1.2.3 From 55ef8262f2b1b31762b045b14182db3cc8f607d1 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 10 Oct 2018 19:09:28 +0200 Subject: spi: pxa2xx: Use an enum for type That seems to be the correct type. Signed-off-by: Lubomir Rintel Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 13b4244d44c1..262e1f318836 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -217,7 +217,7 @@ struct ssp_device { const char *label; int port_id; - int type; + enum pxa_ssp_type type; int use_count; int irq; -- cgit v1.2.3 From 87ae1d2d70772d661162de03e56c8d1cc5f12650 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 10 Oct 2018 19:09:29 +0200 Subject: spi: pxa2xx: Add devicetree support The MMP2 platform, that uses device tree, has this controller. Let's add devicetree alongside platform & PCI. Signed-off-by: Lubomir Rintel Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 262e1f318836..979087e021f3 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -196,6 +196,7 @@ enum pxa_ssp_type { PXA27x_SSP, PXA3xx_SSP, PXA168_SSP, + MMP2_SSP, PXA910_SSP, CE4100_SSP, QUARK_X1000_SSP, -- cgit v1.2.3 From 81b45683487a51b0f4d3b29d37f20d6d078544e4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 26 Aug 2018 03:16:29 +0900 Subject: compiler.h: give up __compiletime_assert_fallback() __compiletime_assert_fallback() is supposed to stop building earlier by using the negative-array-size method in case the compiler does not support "error" attribute, but has never worked like that. You can simply try: BUILD_BUG_ON(1); GCC immediately terminates the build, but Clang does not report anything because Clang does not support the "error" attribute now. It will later fail at link time, but __compiletime_assert_fallback() is not working at least. The root cause is commit 1d6a0d19c855 ("bug.h: prevent double evaluation of `condition' in BUILD_BUG_ON"). Prior to that commit, BUILD_BUG_ON() was checked by the negative-array-size method *and* the link-time trick. Since that commit, the negative-array-size is not effective because '__cond' is no longer constant. As the comment in says, GCC (and Clang as well) only emits the error for obvious cases. When '__cond' is a variable, ((void)sizeof(char[1 - 2 * __cond])) ... is not obvious for the compiler to know the array size is negative. Reverting that commit would break BUILD_BUG() because negative-size-array is evaluated before the code is optimized out. Let's give up __compiletime_assert_fallback(). This commit does not change the current behavior since it just rips off the useless code. Signed-off-by: Masahiro Yamada Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Signed-off-by: Kees Cook --- include/linux/compiler.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..87c776c3ce73 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -314,29 +314,14 @@ static inline void *offset_to_ptr(const int *off) #endif #ifndef __compiletime_error # define __compiletime_error(message) -/* - * Sparse complains of variable sized arrays due to the temporary variable in - * __compiletime_assert. Unfortunately we can't just expand it out to make - * sparse see a constant array size without breaking compiletime_assert on old - * versions of GCC (e.g. 4.2.4), so hide the array from sparse altogether. - */ -# ifndef __CHECKER__ -# define __compiletime_error_fallback(condition) \ - do { ((void)sizeof(char[1 - 2 * condition])); } while (0) -# endif -#endif -#ifndef __compiletime_error_fallback -# define __compiletime_error_fallback(condition) do { } while (0) #endif #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ - int __cond = !(condition); \ extern void prefix ## suffix(void) __compiletime_error(msg); \ - if (__cond) \ + if (!(condition)) \ prefix ## suffix(); \ - __compiletime_error_fallback(__cond); \ } while (0) #else # define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) -- cgit v1.2.3 From 953923c09fe83255ae11845db1c9eb576ba73df8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 11 Oct 2018 11:06:29 -0400 Subject: dm: rename DM_TYPE_MQ_REQUEST_BASED to DM_TYPE_REQUEST_BASED Now that request-based DM is only using blk-mq, there is no need to differentiate between legacy "rq" and new "mq". We're back to a single request-based DM -- and there was much rejoicing! Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 6fb0808e87c8..8d937754aa0c 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -26,9 +26,8 @@ enum dm_queue_mode { DM_TYPE_NONE = 0, DM_TYPE_BIO_BASED = 1, DM_TYPE_REQUEST_BASED = 2, - DM_TYPE_MQ_REQUEST_BASED = 3, - DM_TYPE_DAX_BIO_BASED = 4, - DM_TYPE_NVME_BIO_BASED = 5, + DM_TYPE_DAX_BIO_BASED = 3, + DM_TYPE_NVME_BIO_BASED = 4, }; typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; -- cgit v1.2.3 From 3f2aa244ee1a0d17ed5b6c86564d2c1b24d1c96b Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 3 Oct 2018 13:21:07 +0100 Subject: TC: Set DMA masks for devices Fix a TURBOchannel support regression with commit 205e1b7f51e4 ("dma-mapping: warn when there is no coherent_dma_mask") that caused coherent DMA allocations to produce a warning such as: defxx: v1.11 2014/07/01 Lawrence V. Stefani and others tc1: DEFTA at MMIO addr = 0x1e900000, IRQ = 20, Hardware addr = 08-00-2b-a3-a3-29 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at ./include/linux/dma-mapping.h:516 dfx_dev_register+0x670/0x678 Modules linked in: CPU: 0 PID: 1 Comm: swapper Not tainted 4.19.0-rc6 #2 Stack : ffffffff8009ffc0 fffffffffffffec0 0000000000000000 ffffffff80647650 0000000000000000 0000000000000000 ffffffff806f5f80 ffffffffffffffff 0000000000000000 0000000000000000 0000000000000001 ffffffff8065d4e8 98000000031b6300 ffffffff80563478 ffffffff805685b0 ffffffffffffffff 0000000000000000 ffffffff805d6720 0000000000000204 ffffffff80388df8 0000000000000000 0000000000000009 ffffffff8053efd0 ffffffff806657d0 0000000000000000 ffffffff803177f8 0000000000000000 ffffffff806d0000 9800000003078000 980000000307b9e0 000000001e900000 ffffffff80067940 0000000000000000 ffffffff805d6720 0000000000000204 ffffffff80388df8 ffffffff805176c0 ffffffff8004dc78 0000000000000000 ffffffff80067940 ... Call Trace: [] show_stack+0xa0/0x130 [] __warn+0x128/0x170 ---[ end trace b1d1e094f67f3bb2 ]--- This is because the TURBOchannel bus driver fails to set the coherent DMA mask for devices enumerated. Set the regular and coherent DMA masks for TURBOchannel devices then, observing that the bus protocol supports a 34-bit (16GiB) DMA address space, by interpreting the value presented in the address cycle across the 32 `ad' lines as a 32-bit word rather than byte address[1]. The architectural size of the TURBOchannel DMA address space exceeds the maximum amount of RAM any actual TURBOchannel system in existence may have, hence both masks are the same. This removes the warning shown above. References: [1] "TURBOchannel Hardware Specification", EK-369AA-OD-007B, Digital Equipment Corporation, January 1993, Section "DMA", pp. 1-15 -- 1-17 Signed-off-by: Maciej W. Rozycki Signed-off-by: Paul Burton Patchwork: https://patchwork.linux-mips.org/patch/20835/ Fixes: 205e1b7f51e4 ("dma-mapping: warn when there is no coherent_dma_mask") Cc: stable@vger.kernel.org # 4.16+ Cc: Ralf Baechle --- include/linux/tc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tc.h b/include/linux/tc.h index f92511e57cdb..a60639f37963 100644 --- a/include/linux/tc.h +++ b/include/linux/tc.h @@ -84,6 +84,7 @@ struct tc_dev { device. */ struct device dev; /* Generic device interface. */ struct resource resource; /* Address space of this device. */ + u64 dma_mask; /* DMA addressable range. */ char vendor[9]; char name[9]; char firmware[9]; -- cgit v1.2.3 From 4822e902f9bdffaea2817471365e000966f0d1a1 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 11 Oct 2018 10:07:06 +0300 Subject: block: describe difference between flags IO_STAT and STATS This adds reasonable comments, but they definitely needs better names. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dee46c20701b..61207560e826 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -108,7 +108,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) -/* account I/O stat */ +/* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* request came from our alloc pool */ #define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) @@ -116,7 +116,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* IO stats tracking on */ +/* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ @@ -685,7 +685,7 @@ struct request_queue { #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ #define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ +#define QUEUE_FLAG_IO_STAT 10 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 11 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 12 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 13 /* Contributes to random pool */ @@ -699,7 +699,7 @@ struct request_queue { #define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ #define QUEUE_FLAG_FLUSH_NQ 22 /* flush not queueuable */ #define QUEUE_FLAG_DAX 23 /* device supports DAX */ -#define QUEUE_FLAG_STATS 24 /* track rq completion times */ +#define QUEUE_FLAG_STATS 24 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ -- cgit v1.2.3 From 5fd752b6b3a2233972ce1726df8bdb40886113a9 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 11 Oct 2018 12:07:14 +0800 Subject: leds: core: Introduce LED pattern trigger This patch adds a new LED trigger that LED device can configure to employ software or hardware pattern engine. Consumers can write 'pattern' file to enable the software pattern which alters the brightness for the specified duration with one software timer. Moreover consumers can write 'hw_pattern' file to enable the hardware pattern for some LED controllers which can autonomously control brightness over time, according to some preprogrammed hardware patterns. Signed-off-by: Raphael Teysseyre Signed-off-by: Baolin Wang Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 834683d603f9..7393a316d9fa 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -22,6 +22,7 @@ #include struct device; +struct led_pattern; /* * LED Core */ @@ -88,6 +89,10 @@ struct led_classdev { unsigned long *delay_on, unsigned long *delay_off); + int (*pattern_set)(struct led_classdev *led_cdev, + struct led_pattern *pattern, u32 len, int repeat); + int (*pattern_clear)(struct led_classdev *led_cdev); + struct device *dev; const struct attribute_group **groups; @@ -472,4 +477,14 @@ static inline void led_classdev_notify_brightness_hw_changed( struct led_classdev *led_cdev, enum led_brightness brightness) { } #endif +/** + * struct led_pattern - pattern interval settings + * @delta_t: pattern interval delay, in milliseconds + * @brightness: pattern interval brightness + */ +struct led_pattern { + u32 delta_t; + int brightness; +}; + #endif /* __LINUX_LEDS_H_INCLUDED */ -- cgit v1.2.3 From ca2b497253ad01c80061a1f3ee9eb91b5d54a849 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 5 Oct 2018 13:24:36 +0100 Subject: arm64: perf: Reject stand-alone CHAIN events for PMUv3 It doesn't make sense for a perf event to be configured as a CHAIN event in isolation, so extend the arm_pmu structure with a ->filter_match() function to allow the backend PMU implementation to reject CHAIN events early. Cc: Reviewed-by: Suzuki K Poulose Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 10f92e1d8e7b..bf309ff6f244 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -99,6 +99,7 @@ struct arm_pmu { void (*stop)(struct arm_pmu *); void (*reset)(void *); int (*map_event)(struct perf_event *event); + int (*filter_match)(struct perf_event *event); int num_events; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 -- cgit v1.2.3 From 9c2120090586d7e509faa885988d4eb2441fabc2 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 10 Oct 2018 19:09:27 +0200 Subject: PCI: Provide pci_match_id() with CONFIG_PCI=n This spares drivers from #ifdef-ing on CONFIG_PCI if the driver can be optionally built on machines without PCI bus. Consistent with acpi_driver_match_device() and similar. Acked-by: Bjorn Helgaas Signed-off-by: Lubomir Rintel Signed-off-by: Mark Brown --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..d2f14eb23ea4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1702,6 +1702,10 @@ static inline int pci_irqd_intx_xlate(struct irq_domain *d, unsigned long *out_hwirq, unsigned int *out_type) { return -EINVAL; } + +static inline const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, + struct pci_dev *dev) +{ return NULL; } #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ -- cgit v1.2.3 From b0ce7b29bfcd090ddba476f45a75ec0a797b048a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 12 Oct 2018 14:54:12 +0200 Subject: regulator/gpio: Allow nonexclusive GPIO access This allows nonexclusive (simultaneous) access to a single GPIO line for the fixed regulator enable line. This happens when several regulators use the same GPIO for enabling and disabling a regulator, and all need a handle on their GPIO descriptor. This solution with a special flag is not entirely elegant and should ideally be replaced by something more careful as this makes it possible for several consumers to enable/disable the same GPIO line to the left and right without any consistency. The current use inside the regulator core should however be fine as it takes special care to handle this. For the state of the GPIO backend, this is still the lesser evil compared to going back to global GPIO numbers. Cc: Marek Szyprowski Cc: Jon Hunter Fixes: efdfeb079cc3 ("regulator: fixed: Convert to use GPIO descriptor only") Reported-by: Marek Szyprowski Tested-by: Jon Hunter Tested-by: Marek Szyprowski Signed-off-by: Linus Walleij Signed-off-by: Mark Brown --- include/linux/gpio/consumer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 21ddbe440030..33695a1d8b35 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -30,6 +30,7 @@ struct gpio_descs { #define GPIOD_FLAGS_BIT_DIR_OUT BIT(1) #define GPIOD_FLAGS_BIT_DIR_VAL BIT(2) #define GPIOD_FLAGS_BIT_OPEN_DRAIN BIT(3) +#define GPIOD_FLAGS_BIT_NONEXCLUSIVE BIT(4) /** * Optional flags that can be passed to one of gpiod_* to configure direction -- cgit v1.2.3 From 81732b26e05994552f347746eb11762e986079a0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 23:28:07 -0400 Subject: usb-serial: begin switching to ->[sg]et_serial() add such methods for usb_serial_driver, provide tty_operations ->[sg]et_serial() calling those. For now the lack of methods in driver means ENOIOCTLCMD from usb-serial ->[sg]et_serial(), making tty_ioctl() fall back to calling ->ioctl(). Once all drivers are converted, we'll be returning -ENOTTY instead, completing the switchover. Reviewed-by: Johan Hovold Signed-off-by: Al Viro --- include/linux/usb/serial.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 106551a5616e..1c19f77ed541 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -285,6 +285,8 @@ struct usb_serial_driver { int (*write_room)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); + int (*get_serial)(struct tty_struct *tty, struct serial_struct *ss); + int (*set_serial)(struct tty_struct *tty, struct serial_struct *ss); void (*set_termios)(struct tty_struct *tty, struct usb_serial_port *port, struct ktermios *old); void (*break_ctl)(struct tty_struct *tty, int break_state); -- cgit v1.2.3 From f0193d3ea73b966b5dbfa272c8228d743b8856ef Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 13 Sep 2018 22:12:15 -0400 Subject: change semantics of ldisc ->compat_ioctl() First of all, make it return int. Returning long when native method had never allowed that is ridiculous and inconvenient. More importantly, change the caller; if ldisc ->compat_ioctl() is NULL or returns -ENOIOCTLCMD, tty_compat_ioctl() will try to feed cmd and compat_ptr(arg) to ldisc's native ->ioctl(). That simplifies ->compat_ioctl() instances quite a bit - they only need to deal with ioctls that are neither generic tty ones (those would get shunted off to tty_ioctl()) nor simple compat pointer ones. Note that something like TCFLSH won't reach ->compat_ioctl(), even if ldisc ->ioctl() does handle it - it will be recognized earlier and passed to tty_ioctl() (and ultimately - ldisc ->ioctl()). For many ldiscs it means that NULL ->compat_ioctl() does the right thing. Those where it won't serve (see e.g. n_r3964.c) are also easily dealt with - we need to handle the numeric-argument ioctls (calling the native instance) and, if such would exist, the ioctls that need layout conversion, etc. All in-tree ldiscs dealt with. Signed-off-by: Al Viro --- include/linux/tty_ldisc.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 840894ca3fc0..b1e6043e9917 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -54,11 +54,17 @@ * low-level driver can "grab" an ioctl request before the line * discpline has a chance to see it. * - * long (*compat_ioctl)(struct tty_struct * tty, struct file * file, + * int (*compat_ioctl)(struct tty_struct * tty, struct file * file, * unsigned int cmd, unsigned long arg); * * Process ioctl calls from 32-bit process on 64-bit system * + * NOTE: only ioctls that are neither "pointer to compatible + * structure" nor tty-generic. Something private that takes + * an integer or a pointer to wordsize-sensitive structure + * belongs here, but most of ldiscs will happily leave + * it NULL. + * * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); * * This function notifies the line discpline that a change has @@ -184,7 +190,7 @@ struct tty_ldisc_ops { const unsigned char *buf, size_t nr); int (*ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); - long (*compat_ioctl)(struct tty_struct *tty, struct file *file, + int (*compat_ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); void (*set_termios)(struct tty_struct *tty, struct ktermios *old); __poll_t (*poll)(struct tty_struct *, struct file *, -- cgit v1.2.3 From cc53aabcc283c36274d3f3ce9adc4b40c21d4838 Mon Sep 17 00:00:00 2001 From: Govind Singh Date: Thu, 11 Oct 2018 13:16:01 +0300 Subject: firmware: qcom: scm: Add WLAN VMID for Qualcomm SCM interface Add WLAN related VMID's to support wlan driver to set up the remote's permissions call via TrustZone. Signed-off-by: Govind Singh Reviewed-by: Bjorn Andersson Acked-by: Niklas Cassel Reviewed-by: Brian Norris Signed-off-by: Kalle Valo --- include/linux/qcom_scm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 5d65521260b3..06996ad4f2bc 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2015, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2015, 2018, The Linux Foundation. All rights reserved. * Copyright (C) 2015 Linaro Ltd. * * This program is free software; you can redistribute it and/or modify @@ -33,6 +33,8 @@ struct qcom_scm_vmperm { #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF +#define QCOM_SCM_VMID_WLAN 0x18 +#define QCOM_SCM_VMID_WLAN_CE 0x19 #define QCOM_SCM_PERM_READ 0x4 #define QCOM_SCM_PERM_WRITE 0x2 #define QCOM_SCM_PERM_EXEC 0x1 -- cgit v1.2.3 From c6aed238b7a9b15a5c90a0c31f1d36577b5d2cbe Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:47 +0200 Subject: remoteproc: modify vring allocation to rely on centralized carveout allocator Current version of rproc_alloc_vring function supports only dynamic vring allocation. This patch allows to allocate vrings based on memory region declatation. Vrings are now manage like memory carveouts, to communize memory management code in rproc_alloc_registered_carveouts(). Allocated buffer is retrieved in rp_find_vq() thanks to rproc_find_carveout_by_name() functions for. This patch sets vrings names to vdev"x"vring"y" with x vdev index in resource table and y vring index in vdev. This will be updated when name will be associated to vdev in firmware resource table. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index d4cabe8da507..8bb0cf0416f1 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -454,6 +454,7 @@ struct rproc_dump_segment { * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started * @dump_segments: list of segments in the firmware + * @nb_vdev: number of vdev currently handled by rproc */ struct rproc { struct list_head node; @@ -486,6 +487,7 @@ struct rproc { bool has_iommu; bool auto_boot; struct list_head dump_segments; + int nb_vdev; }; /** @@ -513,7 +515,6 @@ struct rproc_subdev { /** * struct rproc_vring - remoteproc vring state * @va: virtual address - * @dma: dma address * @len: length, in bytes * @da: device address * @align: vring alignment @@ -523,7 +524,6 @@ struct rproc_subdev { */ struct rproc_vring { void *va; - dma_addr_t dma; int len; u32 da; u32 align; @@ -542,6 +542,7 @@ struct rproc_vring { * @vdev: the virio device * @vring: the vrings for this vdev * @rsc_offset: offset of the vdev's resource entry + * @index: vdev position versus other vdev declared in resource table */ struct rproc_vdev { struct kref refcount; @@ -554,6 +555,7 @@ struct rproc_vdev { struct virtio_device vdev; struct rproc_vring vring[RVDEV_NUM_VRINGS]; u32 rsc_offset; + u32 index; }; struct rproc *rproc_get_by_phandle(phandle phandle); -- cgit v1.2.3 From 722fb61e2ed39473297157839ec7230b77fd6940 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 10 Oct 2018 12:51:32 +0900 Subject: mmc: tmio: remove TMIO_MMC_HAVE_HIGH_REG flag TMIO_MMC_HAVE_HIGH_REG is confusing due to its counter-intuitive name. All the TMIO MMC variants (TMIO MMC, Renesas SDHI, UniPhier SD) actually have high registers. It is just that each of them implements its own registers there. The original IP from Panasonic only defines registers 0x00-0xff in the bus_shift=1 review. The register area above them is platform-dependent. In fact, TMIO_MMC_HAVE_HIGH_REG is set only by tmio-mmc.c and used to test the accessibility of CTL_SDIO_REGS. Because it is specific to the TMIO MFD variant, the right thing to do is to move such registers to tmio_mmc.c and delete the TMIO_MMC_HAVE_HIGH_REG flag. Signed-off-by: Masahiro Yamada Reviewed-by: Wolfram Sang Tested-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 77866214ab51..1e70060c92ce 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -61,13 +61,6 @@ */ #define TMIO_MMC_USE_GPIO_CD BIT(5) -/* - * Some controllers doesn't have over 0x100 register. - * it is used to checking accessibility of - * CTL_SD_CARD_CLK_CTL / CTL_CLK_AND_WAIT_CTL - */ -#define TMIO_MMC_HAVE_HIGH_REG BIT(6) - /* * Some controllers have CMD12 automatically * issue/non-issue register -- cgit v1.2.3 From 18127429a854e7607b859484880b8e26cee9ddab Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 15 Oct 2018 15:43:06 +0200 Subject: bitops: protect variables in set_mask_bits() macro Unprotected naming of local variables within the set_mask_bits() can easily lead to using the wrong scope. Noticed this when "set_mask_bits(&foo->bar, 0, mask)" behaved as no-op. Signed-off-by: Miklos Szeredi Fixes: 00a1a053ebe5 ("ext4: atomically set inode->i_flags in ext4_set_inode_flags()") Cc: Theodore Ts'o --- include/linux/bitops.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 7ddb1349394d..d18ee0e63c32 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -236,17 +236,17 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, #ifdef __KERNEL__ #ifndef set_mask_bits -#define set_mask_bits(ptr, _mask, _bits) \ +#define set_mask_bits(ptr, mask, bits) \ ({ \ - const typeof(*ptr) mask = (_mask), bits = (_bits); \ - typeof(*ptr) old, new; \ + const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ + typeof(*(ptr)) old__, new__; \ \ do { \ - old = READ_ONCE(*ptr); \ - new = (old & ~mask) | bits; \ - } while (cmpxchg(ptr, old, new) != old); \ + old__ = READ_ONCE(*(ptr)); \ + new__ = (old__ & ~mask__) | bits__; \ + } while (cmpxchg(ptr, old__, new__) != old__); \ \ - new; \ + new__; \ }) #endif -- cgit v1.2.3 From edfa87281f4fa1b78a21f6db999935a2faa2f6b8 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 15 Oct 2018 15:43:06 +0200 Subject: bitops: protect variables in bit_clear_unless() macro Unprotected naming of local variables within bit_clear_unless() can easily lead to using the wrong scope. Noticed this by code review after having hit this issue in set_mask_bits() Signed-off-by: Miklos Szeredi Fixes: 85ad1d13ee9b ("md: set MD_CHANGE_PENDING in a atomic region") Cc: Guoqing Jiang --- include/linux/bitops.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index d18ee0e63c32..705f7c442691 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -251,18 +251,18 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, #endif #ifndef bit_clear_unless -#define bit_clear_unless(ptr, _clear, _test) \ +#define bit_clear_unless(ptr, clear, test) \ ({ \ - const typeof(*ptr) clear = (_clear), test = (_test); \ - typeof(*ptr) old, new; \ + const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ + typeof(*(ptr)) old__, new__; \ \ do { \ - old = READ_ONCE(*ptr); \ - new = old & ~clear; \ - } while (!(old & test) && \ - cmpxchg(ptr, old, new) != old); \ + old__ = READ_ONCE(*(ptr)); \ + new__ = old__ & ~clear__; \ + } while (!(old__ & test__) && \ + cmpxchg(ptr, old__, new__) != old__); \ \ - !(old & test); \ + !(old__ & test__); \ }) #endif -- cgit v1.2.3 From 604326b41a6fb9b4a78b6179335decee0365cd8c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 13 Oct 2018 02:45:58 +0200 Subject: bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 33 ++--- include/linux/bpf_types.h | 2 +- include/linux/filter.h | 21 --- include/linux/skmsg.h | 371 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 383 insertions(+), 44 deletions(-) create mode 100644 include/linux/skmsg.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9b558713447f..e60fff48288b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -737,33 +737,18 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) } #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ -#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) -struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); -struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key); -int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); -int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog); +#if defined(CONFIG_BPF_STREAM_PARSER) +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); #else -static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) -{ - return NULL; -} - -static inline struct sock *__sock_hash_lookup_elem(struct bpf_map *map, - void *key) -{ - return NULL; -} - -static inline int sock_map_prog(struct bpf_map *map, - struct bpf_prog *prog, - u32 type) +static inline int sock_map_prog_update(struct bpf_map *map, + struct bpf_prog *prog, u32 which) { return -EOPNOTSUPP; } -static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog) +static inline int sock_map_get_from_fd(const union bpf_attr *attr, + struct bpf_prog *prog) { return -EINVAL; } @@ -839,6 +824,10 @@ extern const struct bpf_func_proto bpf_get_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; +extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; +extern const struct bpf_func_proto bpf_msg_redirect_map_proto; +extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; +extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 5432f4c9f50e..fa48343a5ea1 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -57,7 +57,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) -#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET) +#if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 6791a0ac0139..5771874bc01e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -520,24 +520,6 @@ struct bpf_skb_data_end { void *data_end; }; -struct sk_msg_buff { - void *data; - void *data_end; - __u32 apply_bytes; - __u32 cork_bytes; - int sg_copybreak; - int sg_start; - int sg_curr; - int sg_end; - struct scatterlist sg_data[MAX_SKB_FRAGS]; - bool sg_copy[MAX_SKB_FRAGS]; - __u32 flags; - struct sock *sk_redir; - struct sock *sk; - struct sk_buff *skb; - struct list_head list; -}; - struct bpf_redirect_info { u32 ifindex; u32 flags; @@ -833,9 +815,6 @@ void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); -struct sock *do_sk_redirect_map(struct sk_buff *skb); -struct sock *do_msg_redirect_map(struct sk_msg_buff *md); - #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h new file mode 100644 index 000000000000..95678103c4a0 --- /dev/null +++ b/include/linux/skmsg.h @@ -0,0 +1,371 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ + +#ifndef _LINUX_SKMSG_H +#define _LINUX_SKMSG_H + +#include +#include +#include +#include + +#include +#include +#include + +#define MAX_MSG_FRAGS MAX_SKB_FRAGS + +enum __sk_action { + __SK_DROP = 0, + __SK_PASS, + __SK_REDIRECT, + __SK_NONE, +}; + +struct sk_msg_sg { + u32 start; + u32 curr; + u32 end; + u32 size; + u32 copybreak; + bool copy[MAX_MSG_FRAGS]; + struct scatterlist data[MAX_MSG_FRAGS]; +}; + +struct sk_msg { + struct sk_msg_sg sg; + void *data; + void *data_end; + u32 apply_bytes; + u32 cork_bytes; + u32 flags; + struct sk_buff *skb; + struct sock *sk_redir; + struct sock *sk; + struct list_head list; +}; + +struct sk_psock_progs { + struct bpf_prog *msg_parser; + struct bpf_prog *skb_parser; + struct bpf_prog *skb_verdict; +}; + +enum sk_psock_state_bits { + SK_PSOCK_TX_ENABLED, +}; + +struct sk_psock_link { + struct list_head list; + struct bpf_map *map; + void *link_raw; +}; + +struct sk_psock_parser { + struct strparser strp; + bool enabled; + void (*saved_data_ready)(struct sock *sk); +}; + +struct sk_psock_work_state { + struct sk_buff *skb; + u32 len; + u32 off; +}; + +struct sk_psock { + struct sock *sk; + struct sock *sk_redir; + u32 apply_bytes; + u32 cork_bytes; + u32 eval; + struct sk_msg *cork; + struct sk_psock_progs progs; + struct sk_psock_parser parser; + struct sk_buff_head ingress_skb; + struct list_head ingress_msg; + unsigned long state; + struct list_head link; + spinlock_t link_lock; + refcount_t refcnt; + void (*saved_unhash)(struct sock *sk); + void (*saved_close)(struct sock *sk, long timeout); + void (*saved_write_space)(struct sock *sk); + struct proto *sk_proto; + struct sk_psock_work_state work_state; + struct work_struct work; + union { + struct rcu_head rcu; + struct work_struct gc; + }; +}; + +int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, + int elem_first_coalesce); +void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); +int sk_msg_free(struct sock *sk, struct sk_msg *msg); +int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); +void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes); +void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, + u32 bytes); + +void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); + +int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes); +int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes); + +static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) +{ + WARN_ON(i == msg->sg.end && bytes); +} + +static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) +{ + if (psock->apply_bytes) { + if (psock->apply_bytes < bytes) + psock->apply_bytes = 0; + else + psock->apply_bytes -= bytes; + } +} + +#define sk_msg_iter_var_prev(var) \ + do { \ + if (var == 0) \ + var = MAX_MSG_FRAGS - 1; \ + else \ + var--; \ + } while (0) + +#define sk_msg_iter_var_next(var) \ + do { \ + var++; \ + if (var == MAX_MSG_FRAGS) \ + var = 0; \ + } while (0) + +#define sk_msg_iter_prev(msg, which) \ + sk_msg_iter_var_prev(msg->sg.which) + +#define sk_msg_iter_next(msg, which) \ + sk_msg_iter_var_next(msg->sg.which) + +static inline void sk_msg_clear_meta(struct sk_msg *msg) +{ + memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); +} + +static inline void sk_msg_init(struct sk_msg *msg) +{ + memset(msg, 0, sizeof(*msg)); + sg_init_marker(msg->sg.data, ARRAY_SIZE(msg->sg.data)); +} + +static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, + int which, u32 size) +{ + dst->sg.data[which] = src->sg.data[which]; + dst->sg.data[which].length = size; + src->sg.data[which].length -= size; + src->sg.data[which].offset += size; +} + +static inline u32 sk_msg_elem_used(const struct sk_msg *msg) +{ + return msg->sg.end >= msg->sg.start ? + msg->sg.end - msg->sg.start : + msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); +} + +static inline bool sk_msg_full(const struct sk_msg *msg) +{ + return (msg->sg.end == msg->sg.start) && msg->sg.size; +} + +static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) +{ + return &msg->sg.data[which]; +} + +static inline struct page *sk_msg_page(struct sk_msg *msg, int which) +{ + return sg_page(sk_msg_elem(msg, which)); +} + +static inline bool sk_msg_to_ingress(const struct sk_msg *msg) +{ + return msg->flags & BPF_F_INGRESS; +} + +static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) +{ + struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); + + if (msg->sg.copy[msg->sg.start]) { + msg->data = NULL; + msg->data_end = NULL; + } else { + msg->data = sg_virt(sge); + msg->data_end = msg->data + sge->length; + } +} + +static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, + u32 len, u32 offset) +{ + struct scatterlist *sge; + + get_page(page); + sge = sk_msg_elem(msg, msg->sg.end); + sg_set_page(sge, page, len, offset); + sg_unmark_end(sge); + + msg->sg.copy[msg->sg.end] = true; + msg->sg.size += len; + sk_msg_iter_next(msg, end); +} + +static inline struct sk_psock *sk_psock(const struct sock *sk) +{ + return rcu_dereference_sk_user_data(sk); +} + +static inline bool sk_has_psock(struct sock *sk) +{ + return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg; +} + +static inline void sk_psock_queue_msg(struct sk_psock *psock, + struct sk_msg *msg) +{ + list_add_tail(&msg->list, &psock->ingress_msg); +} + +static inline void sk_psock_report_error(struct sk_psock *psock, int err) +{ + struct sock *sk = psock->sk; + + sk->sk_err = err; + sk->sk_error_report(sk); +} + +struct sk_psock *sk_psock_init(struct sock *sk, int node); + +int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); +void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); +void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); + +int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, + struct sk_msg *msg); + +static inline struct sk_psock_link *sk_psock_init_link(void) +{ + return kzalloc(sizeof(struct sk_psock_link), + GFP_ATOMIC | __GFP_NOWARN); +} + +static inline void sk_psock_free_link(struct sk_psock_link *link) +{ + kfree(link); +} + +struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); +#if defined(CONFIG_BPF_STREAM_PARSER) +void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link); +#else +static inline void sk_psock_unlink(struct sock *sk, + struct sk_psock_link *link) +{ +} +#endif + +void __sk_psock_purge_ingress_msg(struct sk_psock *psock); + +static inline void sk_psock_cork_free(struct sk_psock *psock) +{ + if (psock->cork) { + sk_msg_free(psock->sk, psock->cork); + kfree(psock->cork); + psock->cork = NULL; + } +} + +static inline void sk_psock_update_proto(struct sock *sk, + struct sk_psock *psock, + struct proto *ops) +{ + psock->saved_unhash = sk->sk_prot->unhash; + psock->saved_close = sk->sk_prot->close; + psock->saved_write_space = sk->sk_write_space; + + psock->sk_proto = sk->sk_prot; + sk->sk_prot = ops; +} + +static inline void sk_psock_restore_proto(struct sock *sk, + struct sk_psock *psock) +{ + if (psock->sk_proto) { + sk->sk_prot = psock->sk_proto; + psock->sk_proto = NULL; + } +} + +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static inline struct sk_psock *sk_psock_get(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock && !refcount_inc_not_zero(&psock->refcnt)) + psock = NULL; + rcu_read_unlock(); + return psock; +} + +void sk_psock_stop(struct sock *sk, struct sk_psock *psock); +void sk_psock_destroy(struct rcu_head *rcu); +void sk_psock_drop(struct sock *sk, struct sk_psock *psock); + +static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) +{ + if (refcount_dec_and_test(&psock->refcnt)) + sk_psock_drop(sk, psock); +} + +static inline void psock_set_prog(struct bpf_prog **pprog, + struct bpf_prog *prog) +{ + prog = xchg(pprog, prog); + if (prog) + bpf_prog_put(prog); +} + +static inline void psock_progs_drop(struct sk_psock_progs *progs) +{ + psock_set_prog(&progs->msg_parser, NULL); + psock_set_prog(&progs->skb_parser, NULL); + psock_set_prog(&progs->skb_verdict, NULL); +} + +#endif /* _LINUX_SKMSG_H */ -- cgit v1.2.3 From d829e9c4112b52f4f00195900fd4c685f61365ab Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 13 Oct 2018 02:45:59 +0200 Subject: tls: convert to generic sk_msg interface Convert kTLS over to make use of sk_msg interface for plaintext and encrypted scattergather data, so it reuses all the sk_msg helpers and data structure which later on in a second step enables to glue this to BPF. This also allows to remove quite a bit of open coded helpers which are covered by the sk_msg API. Recent changes in kTLs 80ece6a03aaf ("tls: Remove redundant vars from tls record structure") and 4e6d47206c32 ("tls: Add support for inplace records encryption") changed the data path handling a bit; while we've kept the latter optimization intact, we had to undo the former change to better fit the sk_msg model, hence the sg_aead_in and sg_aead_out have been brought back and are linked into the sk_msg sgs. Now the kTLS record contains a msg_plaintext and msg_encrypted sk_msg each. In the original code, the zerocopy_from_iter() has been used out of TX but also RX path. For the strparser skb-based RX path, we've left the zerocopy_from_iter() in decrypt_internal() mostly untouched, meaning it has been moved into tls_setup_from_iter() with charging logic removed (as not used from RX). Given RX path is not based on sk_msg objects, we haven't pursued setting up a dummy sk_msg to call into sk_msg_zerocopy_from_iter(), but it could be an option to prusue in a later step. Joint work with John. Signed-off-by: Daniel Borkmann Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 95678103c4a0..4e84b3c2eff8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -102,6 +102,8 @@ struct sk_psock { int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce); +int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, + u32 off, u32 len); void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); int sk_msg_free(struct sock *sk, struct sk_msg *msg); int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); -- cgit v1.2.3 From d3b18ad31f93d0b6bae105c679018a1ba7daa9ca Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 13 Oct 2018 02:46:01 +0200 Subject: tls: add bpf support to sk_msg handling This work adds BPF sk_msg verdict program support to kTLS allowing BPF and kTLS to be combined together. Previously kTLS and sk_msg verdict programs were mutually exclusive in the ULP layer which created challenges for the orchestrator when trying to apply TCP based policy, for example. To resolve this, leveraging the work from previous patches that consolidates the use of sk_msg, we can finally enable BPF sk_msg verdict programs so they continue to run after the kTLS socket is created. No change in behavior when kTLS is not used in combination with BPF, the kselftest suite for kTLS also runs successfully. Joint work with Daniel. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 41 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 4e84b3c2eff8..0b919f0bc6d6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,11 @@ struct sk_msg_sg { u32 size; u32 copybreak; bool copy[MAX_MSG_FRAGS]; - struct scatterlist data[MAX_MSG_FRAGS]; + /* The extra element is used for chaining the front and sections when + * the list becomes partitioned (e.g. end < start). The crypto APIs + * require the chaining. + */ + struct scatterlist data[MAX_MSG_FRAGS + 1]; }; struct sk_msg { @@ -112,6 +116,7 @@ void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); +void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes); int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); @@ -161,8 +166,9 @@ static inline void sk_msg_clear_meta(struct sk_msg *msg) static inline void sk_msg_init(struct sk_msg *msg) { + BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS); memset(msg, 0, sizeof(*msg)); - sg_init_marker(msg->sg.data, ARRAY_SIZE(msg->sg.data)); + sg_init_marker(msg->sg.data, MAX_MSG_FRAGS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, @@ -174,6 +180,12 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, src->sg.data[which].offset += size; } +static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) +{ + memcpy(dst, src, sizeof(*src)); + sk_msg_init(src); +} + static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { return msg->sg.end >= msg->sg.start ? @@ -229,6 +241,26 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sk_msg_iter_next(msg, end); } +static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) +{ + do { + msg->sg.copy[i] = copy_state; + sk_msg_iter_var_next(i); + if (i == msg->sg.end) + break; + } while (1); +} + +static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start) +{ + sk_msg_sg_copy(msg, start, true); +} + +static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) +{ + sk_msg_sg_copy(msg, start, false); +} + static inline struct sk_psock *sk_psock(const struct sock *sk) { return rcu_dereference_sk_user_data(sk); @@ -245,6 +277,11 @@ static inline void sk_psock_queue_msg(struct sk_psock *psock, list_add_tail(&msg->list, &psock->ingress_msg); } +static inline bool sk_psock_queue_empty(const struct sk_psock *psock) +{ + return psock ? list_empty(&psock->ingress_msg) : true; +} + static inline void sk_psock_report_error(struct sk_psock *psock, int err) { struct sock *sk = psock->sk; -- cgit v1.2.3 From 9316a9ed6895c4ad2f0cde171d486f80c55d8283 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 15 Oct 2018 08:40:37 -0600 Subject: blk-mq: provide helper for setting up an SQ queue and tag set This pattern is repeated throughout all the blk-mq conversions. Provide a basic helper to get it done. Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1da59c16f637..2286dc12c6bc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -203,6 +203,10 @@ enum { struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); +struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, + unsigned int queue_depth, + unsigned int set_flags); int blk_mq_register_dev(struct device *, struct request_queue *); void blk_mq_unregister_dev(struct device *, struct request_queue *); -- cgit v1.2.3 From 25ab0bc334b43bbbe4eabc255006ce42a9424da2 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Wed, 10 Oct 2018 03:23:09 +0000 Subject: scsi: sched/wait: Add wait_event_lock_irq_timeout for TASK_UNINTERRUPTIBLE usage Short of reverting commit 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") for v4.19, target-core needs a wait_event_t macro can be executed using TASK_UNINTERRUPTIBLE to function correctly with existing fabric drivers that expect to run with signals pending during session shutdown and active se_cmd I/O quiesce. The most notable is iscsi-target/iser-target, while ibmvscsi_tgt invokes session shutdown logic from userspace via configfs attribute that could also potentially have signals pending. So go ahead and introduce wait_event_lock_irq_timeout() to achieve this, and update + rename __wait_event_lock_irq_timeout() to make it accept 'state' as a parameter. Fixes: 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") Cc: # v4.19+ Cc: Bart Van Assche Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Bryant G. Ly Cc: Peter Zijlstra (Intel) Tested-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger Reviewed-by: Bryant G. Ly Acked-by: Peter Zijlstra (Intel) Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/linux/wait.h | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index d9f131ecf708..ed7c122cb31f 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1052,10 +1052,9 @@ do { \ __ret; \ }) -#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition, \ - lock, timeout) \ +#define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ + state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); @@ -1089,8 +1088,19 @@ do { \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_lock_irq_timeout( \ - wq_head, condition, lock, timeout); \ + __ret = __wait_event_lock_irq_timeout( \ + wq_head, condition, lock, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ +}) + +#define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_lock_irq_timeout( \ + wq_head, condition, lock, timeout, \ + TASK_UNINTERRUPTIBLE); \ __ret; \ }) -- cgit v1.2.3 From 9f9a742db40f95f4dc20fc7293de4ea6ddb24e47 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 9 Oct 2018 23:57:49 +0100 Subject: FDDI: defza: Support capturing outgoing SMT traffic DEC FDDIcontroller 700 (DEFZA) uses a Tx/Rx queue pair to communicate SMT frames with adapter's firmware. Any SMT frame received from the RMC via the Rx queue is queued back by the driver to the SMT Rx queue for the firmware to process. Similarly the firmware uses the SMT Tx queue to supply the driver with SMT frames which are queued back to the Tx queue for the RMC to send to the ring. When a network tap is attached to an FDDI interface handled by `defza' any incoming SMT frames captured are queued to our usual processing of network data received, which in turn delivers them to any listening taps. However the outgoing SMT frames produced by the firmware bypass our network protocol stack and are therefore not delivered to taps. This in turn means that taps are missing a part of network traffic sent by the adapter, which may make it more difficult to track down network problems or do general traffic analysis. Call `dev_queue_xmit_nit' then in the SMT Tx path, having checked that a network tap is attached, with a newly-created `dev_nit_active' helper wrapping the usual condition used in the transmit path. Signed-off-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- 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 22e4ef7bb701..dc1d9ed33b31 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3645,6 +3645,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return 0; } +bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; -- cgit v1.2.3 From 5f6188a8003d080e3753b8f14f4a5a2325ae1ff6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Oct 2018 09:37:52 -0700 Subject: tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh In EDT design, I made the mistake of using tcp_wstamp_ns to store the last tcp_clock_ns() sample and to store the pacing virtual timer. This causes major regressions at high speed flows. Introduce tcp_clock_cache to store last tcp_clock_ns(). This is needed because some arches have slow high-resolution kernel time service. tcp_wstamp_ns is only updated when a packet is sent. Note that we can remove tcp_mstamp in the future since tcp_mstamp is essentially tcp_clock_cache/1000, so the apparent socket size increase is temporary. Fixes: 9799ccb0e984 ("tcp: add tcp_wstamp_ns socket field") Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh 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 848f5b25e178..8ed77bb4ed86 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -249,6 +249,7 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ /* RTT measurement */ u64 tcp_mstamp; /* most recent packet received/sent */ -- cgit v1.2.3 From 22e6c58b8c2843337ec4e8464b1ce6e869ca5bf4 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:41 -0700 Subject: netlink: Add answer_flags to netlink_callback With dump filtering we need a way to ensure the NLM_F_DUMP_FILTERED flag is set on a message back to the user if the data returned is influenced by some input attributes. Normally this can be done as messages are added to the skb, but if the filter results in no data being returned, the user could be confused as to why. This patch adds answer_flags to the netlink_callback allowing dump handlers to set the NLM_F_DUMP_FILTERED at a minimum in the NLMSG_DONE message ensuring the flag gets back to the user. The netlink_callback space is initialized to 0 via a memset in __netlink_dump_start, so init of the new answer_flags is covered. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 72580f1a72a2..4da90a6ab536 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -180,6 +180,7 @@ struct netlink_callback { u16 family; u16 min_dump_alloc; bool strict_check; + u16 answer_flags; unsigned int prev_seq, seq; long args[6]; }; -- cgit v1.2.3 From e1cedae1ba6b09ae8376c1486712bf91ea0dfc41 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:46 -0700 Subject: ipmr: Refactor mr_rtm_dumproute Move per-table loops from mr_rtm_dumproute to mr_table_dump and export mr_table_dump for dumps by specific table id. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 6675b9f81979..db85373c8d15 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -283,6 +283,12 @@ void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg); int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm); +int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, + struct netlink_callback *cb, + int (*fill)(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), -- cgit v1.2.3 From cb167893f41e21e6bd283d78e53489289dc0592d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:47 -0700 Subject: net: Plumb support for filtering ipv4 and ipv6 multicast route dumps Implement kernel side filtering of routes by egress device index and table id. If the table id is given in the filter, lookup table and call mr_table_dump directly for it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index db85373c8d15..34de06b426ef 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -7,6 +7,7 @@ #include #include #include +#include /** * struct vif_device - interface representor for multicast routing @@ -288,7 +289,7 @@ int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock); + spinlock_t *lock, struct fib_dump_filter *filter); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), @@ -296,7 +297,7 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock); + spinlock_t *lock, struct fib_dump_filter *filter); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, @@ -346,7 +347,7 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock) + spinlock_t *lock, struct fib_dump_filter *filter) { return -EINVAL; } -- cgit v1.2.3 From a218dc82f0b5c6c8ad3d58c9870ed69e26c08b3e Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 10 Oct 2018 09:57:13 +0200 Subject: netfilter: nft_osf: Add ttl option support Add ttl option support to the nftables "osf" expression. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_osf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h index ecf7dab81e9e..c6000046c966 100644 --- a/include/linux/netfilter/nfnetlink_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -27,6 +27,7 @@ bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, const struct list_head *nf_osf_fingers); const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers); + const struct list_head *nf_osf_fingers, + const int ttl_check); #endif /* _NFOSF_H */ -- cgit v1.2.3 From 4cf841e398503990df640f7a7c5b2ea56f11c08c Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 15 Oct 2018 16:11:31 -0700 Subject: ACPI/ADXL: Add address translation interface using an ACPI DSM Some new Intel servers provide an interface so that the OS can ask the BIOS to translate a system physical address to a memory address (socket, memory controller, channel, rank, dimm, etc.). This is useful for EDAC drivers that want to take the address of an error reported in a machine check bank and let the user know which DIMM may need to be replaced. Specification for this interface is available at: https://cdrdv2.intel.com/v1/dl/getContent/603354 [ Based on earlier code by Qiuxu Zhuo . ] [ bp: Make the first pr_info() in adxl_init() pr_debug() so that it doesn't pollute every dmesg. ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Acked-by: Rafael J. Wysocki Tested-by: Qiuxu Zhuo CC: Len Brown CC: linux-acpi@vger.kernel.org CC: linux-edac@vger.kernel.org Link: http://lkml.kernel.org/r/20181015202620.23610-1-tony.luck@intel.com --- include/linux/adxl.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/adxl.h (limited to 'include/linux') diff --git a/include/linux/adxl.h b/include/linux/adxl.h new file mode 100644 index 000000000000..2a629acb4c3f --- /dev/null +++ b/include/linux/adxl.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Address translation interface via ACPI DSM. + * Copyright (C) 2018 Intel Corporation + */ + +#ifndef _LINUX_ADXL_H +#define _LINUX_ADXL_H + +const char * const *adxl_get_component_names(void); +int adxl_decode(u64 addr, u64 component_values[]); + +#endif /* _LINUX_ADXL_H */ -- cgit v1.2.3 From 084181fe8cc7472695b907f0018f4cd00934cb12 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:01 -0500 Subject: fpga: mgr: add devm_fpga_mgr_create Add devm_fpga_mgr_create() which is the managed version of fpga_mgr_create(). Change current FPGA manager drivers to use devm_fpga_mgr_create() Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 8ab5df769923..e8ca62b2cb5b 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -198,4 +198,8 @@ void fpga_mgr_free(struct fpga_manager *mgr); int fpga_mgr_register(struct fpga_manager *mgr); void fpga_mgr_unregister(struct fpga_manager *mgr); +struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name, + const struct fpga_manager_ops *mops, + void *priv); + #endif /*_LINUX_FPGA_MGR_H */ -- cgit v1.2.3 From 213befe049c70cfcfcbb4f6010bd5276dbc1f7b9 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:02 -0500 Subject: fpga: bridge: add devm_fpga_bridge_create Add devm_fpga_bridge_create() which is the managed version of fpga_bridge_create(). Change current bridge drivers to use devm_fpga_bridge_create(). Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-bridge.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index ce550fcf6360..817600a32c93 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -69,4 +69,8 @@ void fpga_bridge_free(struct fpga_bridge *br); int fpga_bridge_register(struct fpga_bridge *br); void fpga_bridge_unregister(struct fpga_bridge *br); +struct fpga_bridge +*devm_fpga_bridge_create(struct device *dev, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv); + #endif /* _LINUX_FPGA_BRIDGE_H */ -- cgit v1.2.3 From fea82b7f6670002ff36bf1bc77d0345b0b2f2d1c Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:03 -0500 Subject: fpga: add devm_fpga_region_create Add devm_fpga_region_create() which is the managed version of fpga_region_create(). Change current region drivers to use devm_fpga_region_create(). Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-region.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 0521b7f577a4..27cb706275db 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -44,4 +44,8 @@ void fpga_region_free(struct fpga_region *region); int fpga_region_register(struct fpga_region *region); void fpga_region_unregister(struct fpga_region *region); +struct fpga_region +*devm_fpga_region_create(struct device *dev, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)); + #endif /* _FPGA_REGION_H */ -- cgit v1.2.3 From 8514c470dc18e58f27dee10a787175ef8f31162f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jul 2018 15:20:32 +0200 Subject: driver core: add BUS_ATTR_WO() macro Many bus attributes are write-only, so provide a simple macro for that to be able to match the other driver core attribute macros. Cc: "Rafael J. Wysocki" Cc: Ioana Ciornei Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..767cf1938b14 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -55,6 +55,8 @@ struct bus_attribute { struct bus_attribute bus_attr_##_name = __ATTR_RW(_name) #define BUS_ATTR_RO(_name) \ struct bus_attribute bus_attr_##_name = __ATTR_RO(_name) +#define BUS_ATTR_WO(_name) \ + struct bus_attribute bus_attr_##_name = __ATTR_WO(_name) extern int __must_check bus_create_file(struct bus_type *, struct bus_attribute *); -- cgit v1.2.3 From 0571967dfb5d2573c2a06871517d748932a899d1 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sun, 14 Oct 2018 17:20:07 +0200 Subject: devres: constify p in devm_kfree() Make devm_kfree() signature uniform with that of kfree(). To avoid compiler warnings: cast p to (void *) when calling devres_destroy(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Bjorn Andersson Reviewed-by: Geert Uytterhoeven Acked-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 767cf1938b14..c2022c1daef6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -694,7 +694,7 @@ 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, void *p); +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 void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); -- cgit v1.2.3 From 09d1ea1c7309c8ca91151778bb3efe514f2e03ed Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sun, 14 Oct 2018 17:20:09 +0200 Subject: devres: provide devm_kstrdup_const() Provide a resource managed version of kstrdup_const(). This variant internally calls devm_kstrdup() on pointers that are outside of .rodata section and returns the string as is otherwise. Make devm_kfree() check if the passed pointer doesn't point to .rodata and if so - don't actually destroy the resource. Signed-off-by: Bartosz Golaszewski Reviewed-by: Bjorn Andersson Acked-by: Mike Rapoport Acked-by: Rasmus Villemoes Reviewed-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c2022c1daef6..fecd9722400e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -696,6 +696,8 @@ static inline void *devm_kcalloc(struct device *dev, } 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); -- cgit v1.2.3 From 891b7c5fbf619d2a314e424775b3c232eb227e90 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2018 08:09:58 -0600 Subject: mtd_blkdevs: convert to blk-mq Straight forward conversion, using an internal list to enable the driver to pull requests at will. Dynamically allocate the tag set to avoid having to pull in the block headers for blktrans.h, since various mtd drivers use block conflicting names for defines and functions. Cc: David Woodhouse Cc: linux-mtd@lists.infradead.org Tested-by: Richard Weinberger Signed-off-by: Jens Axboe --- include/linux/mtd/blktrans.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index e93837f647de..1d3ade69d39a 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -23,7 +23,6 @@ #include #include #include -#include struct hd_geometry; struct mtd_info; @@ -44,9 +43,9 @@ struct mtd_blktrans_dev { struct kref ref; struct gendisk *disk; struct attribute_group *disk_attributes; - struct workqueue_struct *wq; - struct work_struct work; struct request_queue *rq; + struct list_head rq_list; + struct blk_mq_tag_set *tag_set; spinlock_t queue_lock; void *priv; fmode_t file_mode; -- cgit v1.2.3 From c87228f16f0acdf242dee62f139013212208473f Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 11 Oct 2018 12:20:45 -0700 Subject: amiflop: fold headers into C file amifd.h and amifdreg.h are only used from amiflop.c, and they're pretty small, so move the contents to amiflop.c and get rid of the .h files. This is preparation for adding a struct blk_mq_tag_set to struct amiga_floppy_struct. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/amifd.h | 63 ------------------------------------- include/linux/amifdreg.h | 82 ------------------------------------------------ 2 files changed, 145 deletions(-) delete mode 100644 include/linux/amifd.h delete mode 100644 include/linux/amifdreg.h (limited to 'include/linux') diff --git a/include/linux/amifd.h b/include/linux/amifd.h deleted file mode 100644 index 202a77dbe46d..000000000000 --- a/include/linux/amifd.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _AMIFD_H -#define _AMIFD_H - -/* Definitions for the Amiga floppy driver */ - -#include - -#define FD_MAX_UNITS 4 /* Max. Number of drives */ -#define FLOPPY_MAX_SECTORS 22 /* Max. Number of sectors per track */ - -#ifndef ASSEMBLER - -struct fd_data_type { - char *name; /* description of data type */ - int sects; /* sectors per track */ -#ifdef __STDC__ - int (*read_fkt)(int); - void (*write_fkt)(int); -#else - int (*read_fkt)(); /* read whole track */ - void (*write_fkt)(); /* write whole track */ -#endif -}; - -/* -** Floppy type descriptions -*/ - -struct fd_drive_type { - unsigned long code; /* code returned from drive */ - char *name; /* description of drive */ - unsigned int tracks; /* number of tracks */ - unsigned int heads; /* number of heads */ - unsigned int read_size; /* raw read size for one track */ - unsigned int write_size; /* raw write size for one track */ - unsigned int sect_mult; /* sectors and gap multiplier (HD = 2) */ - unsigned int precomp1; /* start track for precomp 1 */ - unsigned int precomp2; /* start track for precomp 2 */ - unsigned int step_delay; /* time (in ms) for delay after step */ - unsigned int settle_time; /* time to settle after dir change */ - unsigned int side_time; /* time needed to change sides */ -}; - -struct amiga_floppy_struct { - struct fd_drive_type *type; /* type of floppy for this unit */ - struct fd_data_type *dtype; /* type of floppy for this unit */ - int track; /* current track (-1 == unknown) */ - unsigned char *trackbuf; /* current track (kmaloc()'d */ - - int blocks; /* total # blocks on disk */ - - int changed; /* true when not known */ - int disk; /* disk in drive (-1 == unknown) */ - int motor; /* true when motor is at speed */ - int busy; /* true when drive is active */ - int dirty; /* true when trackbuf is not on disk */ - int status; /* current error code for unit */ - struct gendisk *gendisk; -}; -#endif - -#endif diff --git a/include/linux/amifdreg.h b/include/linux/amifdreg.h deleted file mode 100644 index 9b514d05ec70..000000000000 --- a/include/linux/amifdreg.h +++ /dev/null @@ -1,82 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_AMIFDREG_H -#define _LINUX_AMIFDREG_H - -/* -** CIAAPRA bits (read only) -*/ - -#define DSKRDY (0x1<<5) /* disk ready when low */ -#define DSKTRACK0 (0x1<<4) /* head at track zero when low */ -#define DSKPROT (0x1<<3) /* disk protected when low */ -#define DSKCHANGE (0x1<<2) /* low when disk removed */ - -/* -** CIAAPRB bits (read/write) -*/ - -#define DSKMOTOR (0x1<<7) /* motor on when low */ -#define DSKSEL3 (0x1<<6) /* select drive 3 when low */ -#define DSKSEL2 (0x1<<5) /* select drive 2 when low */ -#define DSKSEL1 (0x1<<4) /* select drive 1 when low */ -#define DSKSEL0 (0x1<<3) /* select drive 0 when low */ -#define DSKSIDE (0x1<<2) /* side selection: 0 = upper, 1 = lower */ -#define DSKDIREC (0x1<<1) /* step direction: 0=in, 1=out (to trk 0) */ -#define DSKSTEP (0x1) /* pulse low to step head 1 track */ - -/* -** DSKBYTR bits (read only) -*/ - -#define DSKBYT (1<<15) /* register contains valid byte when set */ -#define DMAON (1<<14) /* disk DMA enabled */ -#define DISKWRITE (1<<13) /* disk write bit in DSKLEN enabled */ -#define WORDEQUAL (1<<12) /* DSKSYNC register match when true */ -/* bits 7-0 are data */ - -/* -** ADKCON/ADKCONR bits -*/ - -#ifndef SETCLR -#define ADK_SETCLR (1<<15) /* control bit */ -#endif -#define ADK_PRECOMP1 (1<<14) /* precompensation selection */ -#define ADK_PRECOMP0 (1<<13) /* 00=none, 01=140ns, 10=280ns, 11=500ns */ -#define ADK_MFMPREC (1<<12) /* 0=GCR precomp., 1=MFM precomp. */ -#define ADK_WORDSYNC (1<<10) /* enable DSKSYNC auto DMA */ -#define ADK_MSBSYNC (1<<9) /* when 1, enable sync on MSbit (for GCR) */ -#define ADK_FAST (1<<8) /* bit cell: 0=2us (GCR), 1=1us (MFM) */ - -/* -** DSKLEN bits -*/ - -#define DSKLEN_DMAEN (1<<15) -#define DSKLEN_WRITE (1<<14) - -/* -** INTENA/INTREQ bits -*/ - -#define DSKINDEX (0x1<<4) /* DSKINDEX bit */ - -/* -** Misc -*/ - -#define MFM_SYNC 0x4489 /* standard MFM sync value */ - -/* Values for FD_COMMAND */ -#define FD_RECALIBRATE 0x07 /* move to track 0 */ -#define FD_SEEK 0x0F /* seek track */ -#define FD_READ 0xE6 /* read with MT, MFM, SKip deleted */ -#define FD_WRITE 0xC5 /* write with MT, MFM */ -#define FD_SENSEI 0x08 /* Sense Interrupt Status */ -#define FD_SPECIFY 0x03 /* specify HUT etc */ -#define FD_FORMAT 0x4D /* format one track */ -#define FD_VERSION 0x10 /* get version code */ -#define FD_CONFIGURE 0x13 /* configure FIFO operation */ -#define FD_PERPENDICULAR 0x12 /* perpendicular r/w mode */ - -#endif /* _LINUX_AMIFDREG_H */ -- cgit v1.2.3 From 4354994f097d068a894aa1a0860da54571df3582 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 20 Aug 2018 19:21:43 -0700 Subject: f2fs: checkpoint disabling Note that, it requires "f2fs: return correct errno in f2fs_gc". This adds a lightweight non-persistent snapshotting scheme to f2fs. To use, mount with the option checkpoint=disable, and to return to normal operation, remount with checkpoint=enable. If the filesystem is shut down before remounting with checkpoint=enable, it will revert back to its apparent state when it was first mounted with checkpoint=disable. This is useful for situations where you wish to be able to roll back the state of the disk in case of some critical failure. Signed-off-by: Daniel Rosenberg [Jaegeuk Kim: use SB_RDONLY instead of MS_RDONLY] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1db13ff9a3f4..8b9c7dc0260c 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -116,6 +116,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_DISABLED_FLAG 0x00001000 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From c56a8be7e7aa855ebcccf0e9d9eba2216514d399 Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Tue, 16 Oct 2018 03:59:20 -0700 Subject: qed: Add supported link and advertise link to display in ethtool. Added transceiver type, speed capability and board types in HSI, are utilizing to display the accurate link information in ethtool. Signed-off-by: Rahul Verma Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index dee3c9c744f7..a47321a0d572 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -667,15 +667,35 @@ enum qed_link_mode_bits { QED_LM_Autoneg_BIT = BIT(1), QED_LM_Asym_Pause_BIT = BIT(2), QED_LM_Pause_BIT = BIT(3), - QED_LM_1000baseT_Half_BIT = BIT(4), - QED_LM_1000baseT_Full_BIT = BIT(5), + 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_COUNT = 11 + QED_LM_2500baseX_Full_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 { -- cgit v1.2.3 From 94a04d1d3d3681adde1a3e022b25dbac7b345b7e Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Tue, 9 Oct 2018 12:05:12 +0300 Subject: net/mlx5: Expose DC scatter to CQE capability bit dc_req_scat_data_cqe capability bit determines if requester scatter to cqe is available for 64 bytes CQE over DC transport type. Signed-off-by: Yonatan Cohen Reviewed-by: Guy Levi Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 68f4d5f9d929..0f460fb22c31 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1005,7 +1005,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 umr_modify_atomic_disabled[0x1]; u8 umr_indirect_mkey_disabled[0x1]; u8 umr_fence[0x2]; - u8 reserved_at_20c[0x3]; + u8 dc_req_scat_data_cqe[0x1]; + u8 reserved_at_20d[0x2]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; -- cgit v1.2.3 From 616e45df7c4aa71279c07cc803a1d51f43f89f37 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Fri, 31 Aug 2018 12:45:54 +0800 Subject: clk: add new APIs to operate on all available clocks This patch introduces of_clk_bulk_get_all and clk_bulk_x_all APIs to users who just want to handle all available clocks from device tree without need to know the detailed clock information likes clock numbers and names. This is useful in writing some generic drivers to handle clock part. Cc: Stephen Boyd Cc: Masahiro Yamada Tested-by: Thor Thayer Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- include/linux/clk.h | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 4f750c481b82..e9433c76757b 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -312,7 +312,26 @@ struct clk *clk_get(struct device *dev, const char *id); */ int __must_check clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks); - +/** + * clk_bulk_get_all - lookup and obtain all available references to clock + * producer. + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * This helper function allows drivers to get all clk consumers in one + * operation. If any of the clk cannot be acquired then any clks + * that were obtained will be freed before returning to the caller. + * + * Returns a positive value for the number of clocks obtained while the + * clock references are stored in the clk_bulk_data table in @clks field. + * Returns 0 if there're none and a negative value if something failed. + * + * Drivers must assume that the clock source is not enabled. + * + * clk_bulk_get should not be called from within interrupt context. + */ +int __must_check clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks); /** * devm_clk_bulk_get - managed get multiple clk consumers * @dev: device for clock "consumer" @@ -487,6 +506,19 @@ void clk_put(struct clk *clk); */ void clk_bulk_put(int num_clks, struct clk_bulk_data *clks); +/** + * clk_bulk_put_all - "free" all the clock source + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Note: drivers must ensure that all clk_bulk_enable calls made on this + * clock source are balanced by clk_bulk_disable calls prior to calling + * this function. + * + * clk_bulk_put_all should not be called from within interrupt context. + */ +void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks); + /** * devm_clk_put - "free" a managed clock source * @dev: device used to acquire the clock @@ -642,6 +674,12 @@ static inline int __must_check clk_bulk_get(struct device *dev, int num_clks, return 0; } +static inline int __must_check clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + return 0; +} + static inline struct clk *devm_clk_get(struct device *dev, const char *id) { return NULL; @@ -663,6 +701,8 @@ static inline void clk_put(struct clk *clk) {} static inline void clk_bulk_put(int num_clks, struct clk_bulk_data *clks) {} +static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {} + static inline void devm_clk_put(struct device *dev, struct clk *clk) {} -- cgit v1.2.3 From f08c2e2865f6f9b172f37d7bbf24716f9ebad553 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Fri, 31 Aug 2018 12:45:55 +0800 Subject: clk: add managed version of clk_bulk_get_all This patch introduces the managed version of clk_bulk_get_all. Cc: Michael Turquette Cc: Stephen Boyd Tested-by: Thor Thayer Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- include/linux/clk.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index e9433c76757b..c705271dc1f2 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -346,6 +346,22 @@ int __must_check clk_bulk_get_all(struct device *dev, */ int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks); +/** + * devm_clk_bulk_get_all - managed get multiple clk consumers + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * Returns a positive value for the number of clocks obtained while the + * clock references are stored in the clk_bulk_data table in @clks field. + * Returns 0 if there're none and a negative value if something failed. + * + * This helper function allows drivers to get several clk + * consumers in one operation with management, the clks will + * automatically be freed when the device is unbound. + */ + +int __must_check devm_clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks); /** * devm_clk_get - lookup and obtain a managed reference to a clock producer. @@ -691,6 +707,13 @@ static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clk return 0; } +static inline int __must_check devm_clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + + return 0; +} + static inline struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { -- cgit v1.2.3 From 3f4c3127d332000530349db4843deece27fe5e0c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Oct 2018 10:36:01 -0700 Subject: bpf: sockmap, fix skmsg recvmsg handler to track size correctly When converting sockmap to new skmsg generic data structures we missed that the recvmsg handler did not correctly use sg.size and instead was using individual elements length. The result is if a sock is closed with outstanding data we omit the call to sk_mem_uncharge() and can get the warning below. [ 66.728282] WARNING: CPU: 6 PID: 5783 at net/core/stream.c:206 sk_stream_kill_queues+0x1fa/0x210 To fix this correct the redirect handler to xfer the size along with the scatterlist and also decrement the size from the recvmsg handler. Now when a sock is closed the remaining 'size' will be decremented with sk_mem_uncharge(). Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 0b919f0bc6d6..31df0d9fa536 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -176,6 +176,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, { dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; + dst->sg.size += size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } -- cgit v1.2.3 From 8734a162c13b1a893e7dff8de0df81fed04c51a6 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Oct 2018 11:07:59 -0700 Subject: bpf: skmsg, improve sk_msg_used_element to work in cork context Currently sk_msg_used_element is only called in zerocopy context where cork is not possible and if this case happens we fallback to copy mode. However the helper is more useful if it works in all contexts. This patch resolved the case where if end == head indicating a full or empty ring the helper always reports an empty ring. To fix this add a test for the full ring case to avoid reporting a full ring has 0 elements. This additional functionality will be used in the next patches from recvmsg context where end = head with a full ring is a valid case. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 31df0d9fa536..22347b08e1f8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -187,18 +187,21 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) sk_msg_init(src); } +static inline bool sk_msg_full(const struct sk_msg *msg) +{ + return (msg->sg.end == msg->sg.start) && msg->sg.size; +} + static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { + if (sk_msg_full(msg)) + return MAX_MSG_FRAGS; + return msg->sg.end >= msg->sg.start ? msg->sg.end - msg->sg.start : msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); } -static inline bool sk_msg_full(const struct sk_msg *msg) -{ - return (msg->sg.end == msg->sg.start) && msg->sg.size; -} - static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) { return &msg->sg.data[which]; -- cgit v1.2.3 From a60109dc9a954ef9eddba6577e2d2e9e7952e487 Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Wed, 10 Oct 2018 09:25:16 +0300 Subject: IB/mlx5: Add support for extended atomic operations Extended atomic operations cmp&swp and fetch&add is a Mellanox feature extending the standard atomic operation to use, varied operand sizes, as apposed to normal atomic operation that use an 8 byte operand only. Extended atomics allows masking the results and arguments. This patch configures QP to support extended atomic operation with the maximum size possible, as exposed by HCA capabilities. Signed-off-by: Yonatan Cohen Reviewed-by: Guy Levi Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8fb072aa8671..a73c701edd16 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -97,14 +97,15 @@ enum { }; enum { - MLX5_ATOMIC_MODE_IB_COMP = 1 << 16, - MLX5_ATOMIC_MODE_CX = 2 << 16, - MLX5_ATOMIC_MODE_8B = 3 << 16, - MLX5_ATOMIC_MODE_16B = 4 << 16, - MLX5_ATOMIC_MODE_32B = 5 << 16, - MLX5_ATOMIC_MODE_64B = 6 << 16, - MLX5_ATOMIC_MODE_128B = 7 << 16, - MLX5_ATOMIC_MODE_256B = 8 << 16, + MLX5_ATOMIC_MODE_OFFSET = 16, + MLX5_ATOMIC_MODE_IB_COMP = 1, + MLX5_ATOMIC_MODE_CX = 2, + MLX5_ATOMIC_MODE_8B = 3, + MLX5_ATOMIC_MODE_16B = 4, + MLX5_ATOMIC_MODE_32B = 5, + MLX5_ATOMIC_MODE_64B = 6, + MLX5_ATOMIC_MODE_128B = 7, + MLX5_ATOMIC_MODE_256B = 8, }; enum { @@ -162,13 +163,11 @@ enum mlx5_dcbx_oper_mode { MLX5E_DCBX_PARAM_VER_OPER_AUTO = 0x3, }; -enum mlx5_dct_atomic_mode { - MLX5_ATOMIC_MODE_DCT_CX = 2, -}; - enum { MLX5_ATOMIC_OPS_CMP_SWAP = 1 << 0, MLX5_ATOMIC_OPS_FETCH_ADD = 1 << 1, + MLX5_ATOMIC_OPS_EXTENDED_CMP_SWAP = 1 << 2, + MLX5_ATOMIC_OPS_EXTENDED_FETCH_ADD = 1 << 3, }; enum mlx5_page_fault_resume_flags { -- cgit v1.2.3 From 977196b8c5b20b901acb0042579e30d7fa55790a Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:37 -0600 Subject: PCI/P2PDMA: Add PCI p2pmem DMA mappings to adjust the bus offset The DMA address used when mapping PCI P2P memory must be the PCI bus address. Thus, introduce pci_p2pmem_map_sg() to map the correct addresses when using P2P memory. Memory mapped in this way does not need to be unmapped and thus if we provided pci_p2pmem_unmap_sg() it would be empty. This breaks the expected balance between map/unmap but was left out as an empty function doesn't really provide any benefit. In the future, if this call becomes necessary it can be added without much difficulty. For this, we assume that an SGL passed to these functions contain all P2P memory or no P2P memory. Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- include/linux/memremap.h | 1 + include/linux/pci-p2pdma.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 9553370ebdad..0ac69ddf5fc4 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -125,6 +125,7 @@ struct dev_pagemap { struct device *dev; void *data; enum memory_type type; + u64 pci_p2pdma_bus_offset; }; #ifdef CONFIG_ZONE_DEVICE diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index 7bdaacfd5892..b6dfb6dc2e53 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -30,6 +30,8 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, unsigned int *nents, u32 length); void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); +int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir); #else /* CONFIG_PCI_P2PDMA */ static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) @@ -75,6 +77,11 @@ static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev, static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) { } +static inline int pci_p2pdma_map_sg(struct device *dev, + struct scatterlist *sg, int nents, enum dma_data_direction dir) +{ + return 0; +} #endif /* CONFIG_PCI_P2PDMA */ -- cgit v1.2.3 From 2d7bc010f450d803db9fed1a25da6144ff6140d3 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:38 -0600 Subject: PCI/P2PDMA: Introduce configfs/sysfs enable attribute helpers Users of the P2PDMA infrastructure will typically need a way for the user to tell the kernel to use P2P resources. Typically this will be a simple on/off boolean operation but sometimes it may be desirable for the user to specify the exact device to use for the P2P operation. Add new helpers for attributes which take a boolean or a PCI device. Any boolean as accepted by strtobool() turn P2P on or off (such as 'y', 'n', '1', '0', etc). Specifying a full PCI device name/BDF will select the specific device. Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- include/linux/pci-p2pdma.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index b6dfb6dc2e53..bca9bc3e5be7 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -32,6 +32,10 @@ void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir); +int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, + bool *use_p2pdma); +ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev, + bool use_p2pdma); #else /* CONFIG_PCI_P2PDMA */ static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) @@ -82,6 +86,17 @@ static inline int pci_p2pdma_map_sg(struct device *dev, { return 0; } +static inline int pci_p2pdma_enable_store(const char *page, + struct pci_dev **p2p_dev, bool *use_p2pdma) +{ + *use_p2pdma = false; + return 0; +} +static inline ssize_t pci_p2pdma_enable_show(char *page, + struct pci_dev *p2p_dev, bool use_p2pdma) +{ + return sprintf(page, "none\n"); +} #endif /* CONFIG_PCI_P2PDMA */ -- cgit v1.2.3 From 49d92c0dd64ae769c2d67fe27ac260ae31259ba6 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:41 -0600 Subject: block: Add PCI P2P flag for request queue Add QUEUE_FLAG_PCI_P2P, meaning a driver's request queue supports targeting P2P memory. This will be used by P2P providers and orchestrators (in subsequent patches) to ensure block devices can support P2P memory before submitting P2P-backed pages to submit_bio(). Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Acked-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6980014357d4..c32f7171899b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -699,6 +699,7 @@ struct request_queue { #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ #define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ +#define QUEUE_FLAG_PCI_P2PDMA 30 /* device supports PCI p2p requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -731,6 +732,8 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) +#define blk_queue_pci_p2pdma(q) \ + test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ -- cgit v1.2.3 From 9c0be3f6b5d776dfe3ed249862c244a4486414dc Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 13 Oct 2018 15:10:50 -0400 Subject: tracepoint: Fix tracepoint array element size mismatch commit 46e0c9be206f ("kernel: tracepoints: add support for relative references") changes the layout of the __tracepoint_ptrs section on architectures supporting relative references. However, it does so without turning struct tracepoint * const into const int elsewhere in the tracepoint code, which has the following side-effect: Setting mod->num_tracepoints is done in by module.c: mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs", sizeof(*mod->tracepoints_ptrs), &mod->num_tracepoints); Basically, since sizeof(*mod->tracepoints_ptrs) is a pointer size (rather than sizeof(int)), num_tracepoints is erroneously set to half the size it should be on 64-bit arch. So a module with an odd number of tracepoints misses the last tracepoint due to effect of integer division. So in the module going notifier: for_each_tracepoint_range(mod->tracepoints_ptrs, mod->tracepoints_ptrs + mod->num_tracepoints, tp_module_going_check_quiescent, NULL); the expression (mod->tracepoints_ptrs + mod->num_tracepoints) actually evaluates to something within the bounds of the array, but miss the last tracepoint if the number of tracepoints is odd on 64-bit arch. Fix this by introducing a new typedef: tracepoint_ptr_t, which is either "const int" on architectures that have PREL32 relocations, or "struct tracepoint * const" on architectures that does not have this feature. Also provide a new tracepoint_ptr_defer() static inline to encapsulate deferencing this type rather than duplicate code and ugly idefs within the for_each_tracepoint_range() implementation. This issue appears in 4.19-rc kernels, and should ideally be fixed before the end of the rc cycle. Acked-by: Ard Biesheuvel Acked-by: Jessica Yu Link: http://lkml.kernel.org/r/20181013191050.22389-1-mathieu.desnoyers@efficios.com Link: http://lkml.kernel.org/r/20180704083651.24360-7-ard.biesheuvel@linaro.org Cc: Michael Ellerman Cc: Ingo Molnar Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: James Morris Cc: James Morris Cc: Josh Poimboeuf Cc: Kees Cook Cc: Nicolas Pitre Cc: Paul Mackerras Cc: Petr Mladek Cc: Russell King Cc: "Serge E. Hallyn" Cc: Sergey Senozhatsky Cc: Thomas Garnier Cc: Thomas Gleixner Cc: Will Deacon Cc: Andrew Morton Cc: Linus Torvalds Cc: Greg Kroah-Hartman Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (VMware) --- include/linux/module.h | 3 ++- include/linux/tracepoint-defs.h | 6 ++++++ include/linux/tracepoint.h | 36 +++++++++++++++++++++++------------- 3 files changed, 31 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index f807f15bebbe..e19ae08c7fb8 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -430,7 +431,7 @@ struct module { #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; - struct tracepoint * const *tracepoints_ptrs; + tracepoint_ptr_t *tracepoints_ptrs; #endif #ifdef HAVE_JUMP_LABEL struct jump_entry *jump_entries; diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h index 22c5a46e9693..49ba9cde7e4b 100644 --- a/include/linux/tracepoint-defs.h +++ b/include/linux/tracepoint-defs.h @@ -35,6 +35,12 @@ struct tracepoint { struct tracepoint_func __rcu *funcs; }; +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +typedef const int tracepoint_ptr_t; +#else +typedef struct tracepoint * const tracepoint_ptr_t; +#endif + struct bpf_raw_event_map { struct tracepoint *tp; void *bpf_func; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 041f7e56a289..538ba1a58f5b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -99,6 +99,29 @@ extern void syscall_unregfunc(void); #define TRACE_DEFINE_ENUM(x) #define TRACE_DEFINE_SIZEOF(x) +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS +static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) +{ + return offset_to_ptr(p); +} + +#define __TRACEPOINT_ENTRY(name) \ + asm(" .section \"__tracepoints_ptrs\", \"a\" \n" \ + " .balign 4 \n" \ + " .long __tracepoint_" #name " - . \n" \ + " .previous \n") +#else +static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) +{ + return *p; +} + +#define __TRACEPOINT_ENTRY(name) \ + static tracepoint_ptr_t __tracepoint_ptr_##name __used \ + __attribute__((section("__tracepoints_ptrs"))) = \ + &__tracepoint_##name +#endif + #endif /* _LINUX_TRACEPOINT_H */ /* @@ -253,19 +276,6 @@ extern void syscall_unregfunc(void); return static_key_false(&__tracepoint_##name.key); \ } -#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define __TRACEPOINT_ENTRY(name) \ - asm(" .section \"__tracepoints_ptrs\", \"a\" \n" \ - " .balign 4 \n" \ - " .long __tracepoint_" #name " - . \n" \ - " .previous \n") -#else -#define __TRACEPOINT_ENTRY(name) \ - static struct tracepoint * const __tracepoint_ptr_##name __used \ - __attribute__((section("__tracepoints_ptrs"))) = \ - &__tracepoint_##name -#endif - /* * We have no guarantee that gcc and the linker won't up-align the tracepoint * structures, so we create an array of pointers that will be used for iteration -- cgit v1.2.3 From f366d322aea782cf786aa821d5accdc1609f9e10 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Sep 2018 10:19:30 +0100 Subject: UAPI: ndctl: Remove use of PAGE_SIZE The macro PAGE_SIZE isn't valid outside of the kernel, so it should not appear in UAPI headers. Furthermore, the actual machine page size could theoretically change from an application's point of view if it's running in a container that gets migrated to another machine (say 4K/ppc64 to 64K/ppc64). Fixes: f2ba5a5baecf ("libnvdimm, namespace: make min namespace size 4K") Signed-off-by: David Howells Signed-off-by: Dan Williams --- include/linux/ndctl.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/ndctl.h (limited to 'include/linux') diff --git a/include/linux/ndctl.h b/include/linux/ndctl.h new file mode 100644 index 000000000000..cd5a293ce3ae --- /dev/null +++ b/include/linux/ndctl.h @@ -0,0 +1,22 @@ +/* + * Copyright (c) 2014-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU Lesser General Public License, + * version 2.1, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT ANY + * WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS + * FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for + * more details. + */ +#ifndef _LINUX_NDCTL_H +#define _LINUX_NDCTL_H + +#include + +enum { + ND_MIN_NAMESPACE_SIZE = PAGE_SIZE, +}; + +#endif /* _LINUX_NDCTL_H */ -- cgit v1.2.3 From b8aee82250b7d90a32b11ba208656f52dbaca342 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 2 Oct 2018 22:57:24 +0000 Subject: net/mlx5: E-Switch, Get counters for offloaded flows from callers There's no real reason for the e-switch logic to manage the creation of counters for offloaded flows. The API already has the directive for the caller to denote they want to attach a counter to the created flow. As such, we go and move the management of flow counters to the mlx5e tc offload logic. This also lets us remove an inelegant interface where the FS layer had to provide a way to retrieve a counter from a flow rule. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index b1c026f1c8ba..74d0ea146c9a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -186,7 +186,6 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_flow_destination *new_dest, struct mlx5_flow_destination *old_dest); -struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler); struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, -- cgit v1.2.3 From 171c7625bef999848ee6032c6dde96e7330c4d15 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Wed, 3 Oct 2018 00:03:35 +0000 Subject: net/mlx5: Use flow counter IDs and not the wrapping cache object Currently, when a flow rule is created using the FS core layer, the caller has to pass the entire flow counter object and not just the counter HW handle (ID). This requires both the FS core and the caller to have knowledge about the inner implementation of the FS layer flow counters cache and limits the possible users. Move to use the counter ID across the place when dealing with flows. Doing this decoupling, now can we privatize the inner implementation of the flow counters. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 74d0ea146c9a..a5fc62184195 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -92,7 +92,7 @@ struct mlx5_flow_destination { u32 tir_num; u32 ft_num; struct mlx5_flow_table *ft; - struct mlx5_fc *counter; + u32 counter_id; struct { u16 num; u16 vhca_id; @@ -192,6 +192,7 @@ void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, u64 *packets, u64 *bytes); +u32 mlx5_fc_id(struct mlx5_fc *counter); int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); -- cgit v1.2.3 From b9aa0ba17af5afa13605eb6ea91f1974da97a2e2 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 31 May 2018 11:50:23 +0300 Subject: net/mlx5: Add cap bits for multi fdb encap If set, the firmware supports creating of flow tables with encap enabled while VFs are configured, if we already created one (restriction still applies on the first creation). Signed-off-by: Paul Blakey Reviewed-by: Or Gerlitz 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 15e36198f85f..963611820006 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -584,7 +584,9 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_at_0[0x1c]; u8 fdb_multi_path_to_table[0x1]; - u8 reserved_at_1d[0x1e3]; + u8 reserved_at_1d[0x1]; + u8 multi_fdb_encap[0x1]; + u8 reserved_at_1e[0x1e1]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; -- cgit v1.2.3 From 328edb499f99126946845ece477c9c1afe8631af Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 3 Jul 2018 11:13:00 +0300 Subject: net/mlx5: Split FDB fast path prio to multiple namespaces Towards supporting multi-chains and priorities, split the FDB fast path to multiple namespaces (sub namespaces), each with multiple priorities. This patch adds a new flow steering type, FS_TYPE_PRIO_CHAINS, which is like current FS_TYPE_PRIO, but may contain only namespaces, and those will be in parallel to one another in terms of managing of the flow tables connections inside them. Meaning, while searching for the next or previous flow table to connect for a new table inside such namespace we skip the parallel namespaces in the same level under the FS_TYPE_PRIO_CHAINS prio we originated from. We use this new type for splitting the fast path prio into multiple parallel namespaces, each containing normal prios. The prios inside them (and their tables) will be connected to one another, but not from one parallel namespace to another, instead the last prio in each namespace will be connected to the next prio in the containing FDB namespace, which is the slow path prio. Signed-off-by: Paul Blakey Acked-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index a5fc62184195..f8d00872c7d3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -101,6 +101,8 @@ struct mlx5_flow_destination { }; }; +struct mlx5_flow_namespace * +mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, int n); struct mlx5_flow_namespace * mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); -- cgit v1.2.3 From d5634fee245f9e92787e3a34ef621fc12b2cbf16 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 20 Sep 2018 12:17:48 +0200 Subject: net/mlx5: Add a no-append flow insertion mode If no-append flag is set, we will add a new FTE, instead of appending the actions of the inserted rule when the same match already exists. While here, move the has_flow_tag boolean indicator to be a flag too. This patch doesn't change any functionality. Signed-off-by: Paul Blakey Reviewed-by: Or Gerlitz Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index f8d00872c7d3..5660f07d3be0 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -158,20 +158,28 @@ struct mlx5_fs_vlan { #define MLX5_FS_VLAN_DEPTH 2 +enum { + FLOW_ACT_HAS_TAG = BIT(0), + FLOW_ACT_NO_APPEND = BIT(1), +}; + struct mlx5_flow_act { u32 action; - bool has_flow_tag; u32 flow_tag; u32 reformat_id; u32 modify_id; uintptr_t esp_id; + u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; }; #define MLX5_DECLARE_FLOW_ACT(name) \ - struct mlx5_flow_act name = {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ - MLX5_FS_DEFAULT_FLOW_TAG, 0, 0} + struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, \ + .reformat_id = 0, \ + .modify_id = 0, \ + .flags = 0, } /* Single destination per rule. * Group ID is implied by the match criteria. -- cgit v1.2.3 From 82385b0d2d2504aee51aa3fb40ebfb03603f64c3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 17 Oct 2018 15:01:37 +0200 Subject: net: skbuff.h: Mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Acked-by: Kees Cook Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 119d092c6b13..0ba687454267 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3505,13 +3505,19 @@ 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 */ case 24: diffs |= __it_diff(a, b, 64); + /* fall through */ case 16: diffs |= __it_diff(a, b, 64); + /* fall through */ case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); + /* fall through */ case 20: diffs |= __it_diff(a, b, 64); + /* fall through */ case 12: diffs |= __it_diff(a, b, 64); + /* fall through */ case 4: diffs |= __it_diff(a, b, 32); break; } -- cgit v1.2.3 From eb66ae030829605d61fbef1909ce310e29f78821 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 12 Oct 2018 15:22:59 -0700 Subject: mremap: properly flush TLB before releasing the page Jann Horn points out that our TLB flushing was subtly wrong for the mremap() case. What makes mremap() special is that we don't follow the usual "add page to list of pages to be freed, then flush tlb, and then free pages". No, mremap() obviously just _moves_ the page from one page table location to another. That matters, because mremap() thus doesn't directly control the lifetime of the moved page with a freelist: instead, the lifetime of the page is controlled by the page table locking, that serializes access to the entry. As a result, we need to flush the TLB not just before releasing the lock for the source location (to avoid any concurrent accesses to the entry), but also before we release the destination page table lock (to avoid the TLB being flushed after somebody else has already done something to that page). This also makes the whole "need_flush" logic unnecessary, since we now always end up flushing the TLB for every valid entry. Reported-and-tested-by: Jann Horn Acked-by: Will Deacon Tested-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- 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 99c19b06d9a4..fdcb45999b26 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -43,7 +43,7 @@ extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, 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, - pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush); + 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, int prot_numa); -- cgit v1.2.3 From e5089c2c73a157997eb6ecca982adea9d0673075 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 3 Oct 2018 16:38:16 +0200 Subject: PM / Domains: Document flags for genpd The current documented description of the GENPD_FLAG_* flags, are too simplified, so let's extend them. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 776c546d581a..3b5d7280e52e 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -17,11 +17,36 @@ #include #include -/* Defines used for the flags field in the struct generic_pm_domain */ -#define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */ -#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */ -#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */ -#define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) /* Keep devices active if wakeup */ +/* + * Flags to control the behaviour of a genpd. + * + * These flags may be set in the struct generic_pm_domain's flags field by a + * genpd backend driver. The flags must be set before it calls pm_genpd_init(), + * which initializes a genpd. + * + * GENPD_FLAG_PM_CLK: Instructs genpd to use the PM clk framework, + * while powering on/off attached devices. + * + * GENPD_FLAG_IRQ_SAFE: This informs genpd that its backend callbacks, + * ->power_on|off(), doesn't sleep. Hence, these + * can be invoked from within atomic context, which + * enables genpd to power on/off the PM domain, + * even when pm_runtime_is_irq_safe() returns true, + * for any of its attached devices. Note that, a + * genpd having this flag set, requires its + * masterdomains to also have it set. + * + * GENPD_FLAG_ALWAYS_ON: Instructs genpd to always keep the PM domain + * powered on. + * + * GENPD_FLAG_ACTIVE_WAKEUP: Instructs genpd to keep the PM domain powered + * on, in case any of its attached devices is used + * in the wakeup path to serve system wakeups. + */ +#define GENPD_FLAG_PM_CLK (1U << 0) +#define GENPD_FLAG_IRQ_SAFE (1U << 1) +#define GENPD_FLAG_ALWAYS_ON (1U << 2) +#define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ -- cgit v1.2.3 From f349b0a3e1f0d184374936f1b2a49352f8a4b1c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Tue, 9 Oct 2018 22:13:42 +0200 Subject: dm: add dm_table_device_name() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a shortcut for dm_device_name(dm_table_get_md(t)). Signed-off-by: Michał Mirosław 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 8d937754aa0c..d7bee8669f10 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -489,6 +489,7 @@ sector_t dm_table_get_size(struct dm_table *t); unsigned int dm_table_get_num_targets(struct dm_table *t); fmode_t dm_table_get_mode(struct dm_table *t); struct mapped_device *dm_table_get_md(struct dm_table *t); +const char *dm_table_device_name(struct dm_table *t); /* * Trigger an event. -- cgit v1.2.3 From 4972e6fa3a04032830bc3d6bb343d08ab3546773 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 12 Sep 2018 15:36:41 +0300 Subject: net/mlx5: Refactor fragmented buffer struct fields and init flow Take struct mlx5_frag_buf out of mlx5_frag_buf_ctrl, as it is not needed to manage and control the datapath of the fragmented buffers API. struct mlx5_frag_buf contains control info to manage the allocation and de-allocation of the fragmented buffer. Its fields are not relevant for datapath, so here I take them out of the struct mlx5_frag_buf_ctrl, except for the fragments array itself. In addition, modified mlx5_fill_fbc to initialise the frags pointers as well. This implies that the buffer must be allocated before the function is called. A set of type-specific *_get_byte_size() functions are replaced by a generic one. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 94ffd02af7cd..e10f61a1f77d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -357,7 +357,7 @@ struct mlx5_frag_buf { }; struct mlx5_frag_buf_ctrl { - struct mlx5_frag_buf frag_buf; + struct mlx5_buf_list *frags; u32 sz_m1; u16 frag_sz_m1; u16 strides_offset; @@ -994,10 +994,12 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, +static inline void mlx5_init_fbc_offset(struct mlx5_buf_list *frags, + u8 log_stride, u8 log_sz, u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { + fbc->frags = frags; fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; @@ -1006,18 +1008,11 @@ static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, fbc->strides_offset = strides_offset; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, +static inline void mlx5_init_fbc(struct mlx5_buf_list *frags, + u8 log_stride, u8 log_sz, struct mlx5_frag_buf_ctrl *fbc) { - mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); -} - -static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, - void *cqc) -{ - mlx5_fill_fbc(6 + MLX5_GET(cqc, cqc, cqe_sz), - MLX5_GET(cqc, cqc, log_cq_size), - fbc); + mlx5_init_fbc_offset(frags, log_stride, log_sz, 0, fbc); } static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, @@ -1028,8 +1023,7 @@ static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, ix += fbc->strides_offset; frag = ix >> fbc->log_frag_strides; - return fbc->frag_buf.frags[frag].buf + - ((fbc->frag_sz_m1 & ix) << fbc->log_stride); + return fbc->frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); } int mlx5_cmd_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 4b5b9c7d972e8a7b1e7691c7c921ec0d6dec33b9 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Tue, 9 Oct 2018 14:16:43 +0300 Subject: net/mlx5: Add FEC fields to Port Phy Link Mode (PPLM) reg Added FEC related fields to PPLM layout. These fields are needed to set and query FEC policy for different link speeds. Signed-off-by: Shay Agroskin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 39 ++++++++++++++++++++++++++++----------- 2 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e10f61a1f77d..696ed3f7f894 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -133,6 +133,7 @@ enum { MLX5_REG_PVLC = 0x500f, MLX5_REG_PCMR = 0x5041, MLX5_REG_PMLP = 0x5002, + MLX5_REG_PPLM = 0x5023, MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 963611820006..47b09a742ae5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -7828,20 +7828,34 @@ struct mlx5_ifc_pplr_reg_bits { struct mlx5_ifc_pplm_reg_bits { u8 reserved_at_0[0x8]; - u8 local_port[0x8]; - u8 reserved_at_10[0x10]; + u8 local_port[0x8]; + u8 reserved_at_10[0x10]; - u8 reserved_at_20[0x20]; + u8 reserved_at_20[0x20]; - u8 port_profile_mode[0x8]; - u8 static_port_profile[0x8]; - u8 active_port_profile[0x8]; - u8 reserved_at_58[0x8]; + u8 port_profile_mode[0x8]; + u8 static_port_profile[0x8]; + u8 active_port_profile[0x8]; + u8 reserved_at_58[0x8]; - u8 retransmission_active[0x8]; - u8 fec_mode_active[0x18]; + u8 retransmission_active[0x8]; + u8 fec_mode_active[0x18]; - u8 reserved_at_80[0x20]; + u8 rs_fec_correction_bypass_cap[0x4]; + u8 reserved_at_84[0x8]; + u8 fec_override_cap_56g[0x4]; + u8 fec_override_cap_100g[0x4]; + u8 fec_override_cap_50g[0x4]; + u8 fec_override_cap_25g[0x4]; + u8 fec_override_cap_10g_40g[0x4]; + + u8 rs_fec_correction_bypass_admin[0x4]; + u8 reserved_at_a4[0x8]; + u8 fec_override_admin_56g[0x4]; + u8 fec_override_admin_100g[0x4]; + u8 fec_override_admin_50g[0x4]; + u8 fec_override_admin_25g[0x4]; + u8 fec_override_admin_10g_40g[0x4]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -8137,7 +8151,10 @@ struct mlx5_ifc_pcam_enhanced_features_bits { struct mlx5_ifc_pcam_regs_5000_to_507f_bits { u8 port_access_reg_cap_mask_127_to_96[0x20]; u8 port_access_reg_cap_mask_95_to_64[0x20]; - u8 port_access_reg_cap_mask_63_to_32[0x20]; + + u8 port_access_reg_cap_mask_63_to_36[0x1c]; + u8 pplm[0x1]; + u8 port_access_reg_cap_mask_34_to_32[0x3]; u8 port_access_reg_cap_mask_31_to_13[0x13]; u8 pbmc[0x1]; -- cgit v1.2.3 From 67daf1186086ad4b2ec09b8078b835936977d06a Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Sun, 30 Sep 2018 09:58:08 +0300 Subject: net/mlx5: Added "per_lane_error_counters" cap bit to PCAM Added "Per lane raw errors" capability bit in Ports Capabilities Mask (PCAM) enhanced features layout. This bit determines if the fields "phy_raw_errors_laneX" in "Physical Layer statistical" counters group are supported. Signed-off-by: Shay Agroskin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 47b09a742ae5..dbff9ff28f2c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8140,7 +8140,8 @@ struct mlx5_ifc_pcam_enhanced_features_bits { u8 rx_icrc_encapsulated_counter[0x1]; u8 reserved_at_6e[0x8]; u8 pfcc_mask[0x1]; - u8 reserved_at_77[0x4]; + u8 reserved_at_77[0x3]; + u8 per_lane_error_counters[0x1]; u8 rx_buffer_fullness_counters[0x1]; u8 ptys_connector_type[0x1]; u8 reserved_at_7d[0x1]; -- cgit v1.2.3 From 01a14bda11add9dcd4a59200f13834d634559935 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 18 Oct 2018 21:45:18 -0400 Subject: locking/lockdep: Make global debug_locks* variables read-mostly Make the frequently used lockdep global variable debug_locks read-mostly. As debug_locks_silent is sometime used together with debug_locks, it is also made read-mostly so that they can be close together. With false cacheline sharing, cacheline contention problem can happen depending on what get put into the same cacheline as debug_locks. Signed-off-by: Waiman Long Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Link: http://lkml.kernel.org/r/1539913518-15598-2-git-send-email-longman@redhat.com Signed-off-by: Ingo Molnar --- include/linux/debug_locks.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 120225e9a366..257ab3c92cb8 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -8,8 +8,8 @@ struct task_struct; -extern int debug_locks; -extern int debug_locks_silent; +extern int debug_locks __read_mostly; +extern int debug_locks_silent __read_mostly; static inline int __debug_locks_off(void) -- cgit v1.2.3 From b65125c6acf38388d3342b37c18c3b6cc97eeb75 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 Apr 2018 14:49:23 +0200 Subject: swiotlb: mark is_swiotlb_buffer static Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 965be92c33b5..7ef541ce8f34 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -121,7 +121,6 @@ static inline unsigned int swiotlb_max_segment(void) { return 0; } #endif extern void swiotlb_print_info(void); -extern int is_swiotlb_buffer(phys_addr_t paddr); extern void swiotlb_set_max_segment(unsigned int); extern const struct dma_map_ops swiotlb_dma_ops; -- cgit v1.2.3 From dff8d6c1ed584de65aac40494d3e7468c50980c3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Aug 2018 15:30:39 +0300 Subject: swiotlb: remove the overflow buffer Like all other dma mapping drivers just return an error code instead of an actual memory buffer. The reason for the overflow buffer was that at the time swiotlb was invented there was no way to check for dma mapping errors, but this has long been fixed. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- include/linux/dma-direct.h | 2 ++ include/linux/swiotlb.h | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index fbca184ff5a0..bd73e7a91410 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,6 +5,8 @@ #include #include +#define DIRECT_MAPPING_ERROR 0 + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 7ef541ce8f34..f847c1b265c4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -106,9 +106,6 @@ extern void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -extern int -swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); - extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); -- cgit v1.2.3 From fe0640eb30b7da261ae84d252ed9ed3c7e68dfd8 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Mon, 15 Oct 2018 10:22:21 -0700 Subject: compiler.h: update definition of unreachable() Fixes the objtool warning seen with Clang: arch/x86/mm/fault.o: warning: objtool: no_context()+0x220: unreachable instruction Fixes commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Josh noted that the fallback definition was meant to work around a pre-gcc-4.6 bug. GCC still needs to work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365, so compiler-gcc.h defines its own version of unreachable(). Clang and ICC can use this shared definition. Link: https://github.com/ClangBuiltLinux/linux/issues/204 Suggested-by: Andy Lutomirski Suggested-by: Josh Poimboeuf Tested-by: Nathan Chancellor Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b5fb034fa6fa..2e0b6322588b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -124,7 +124,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define ASM_UNREACHABLE #endif #ifndef unreachable -# define unreachable() do { annotate_reachable(); do { } while (1); } while (0) +# define unreachable() do { \ + annotate_unreachable(); \ + __builtin_unreachable(); \ +} while (0) #endif /* -- cgit v1.2.3 From 1ff2fea5e30ca15752777441ecb64a169fe22e9e Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Mon, 15 Oct 2018 14:24:27 -0700 Subject: compiler-gcc: remove comment about gcc 4.5 from unreachable() Remove the comment about being unable to detect __builtin_unreachable. __builtin_unreachable was implemented in the GCC 4.5 timeframe. The kernel's minimum supported version of GCC is 4.6 since commit cafa0010cd51 ("Raise the minimum required gcc version to 4.6"). Commit cb984d101b30 ("compiler-gcc: integrate the various compiler-gcc[345].h files") shows that unreachable() had different guards based on GCC version. Suggested-by: Miguel Ojeda Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cfac027e1625..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -96,10 +96,6 @@ * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. */ #define unreachable() \ do { \ -- cgit v1.2.3 From fafadcd16595c1df82df399f62421718ec9bf70a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 30 Sep 2018 16:13:33 -0700 Subject: swiotlb: don't dip into swiotlb pool for coherent allocations All architectures that support swiotlb also have a zone that backs up these less than full addressing allocations (usually ZONE_DMA32). Because of that it is rather pointless to fall back to the global swiotlb buffer if the normal dma direct allocation failed - the only thing this will do is to eat up bounce buffers that would be more useful to serve streaming mappings. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Acked-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index f847c1b265c4..a387b59640a4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -67,11 +67,6 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, /* Accessory functions. */ -void *swiotlb_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs); -void swiotlb_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs); - extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, -- cgit v1.2.3 From cdf6b11daa77d4b55ddf0530842a551cc5562a93 Mon Sep 17 00:00:00 2001 From: Ben Whitten Date: Fri, 19 Oct 2018 10:33:50 +0100 Subject: regmap: Add regmap_noinc_write API The regmap API had a noinc_read function added for instances where devices supported returning data from an internal FIFO in a single read. This commit adds the noinc_write variant to allow writing to a non incrementing register, this is used in devices such as the sx1301 for loading firmware. Signed-off-by: Ben Whitten Signed-off-by: Mark Brown --- include/linux/regmap.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 379505a53722..de04dc46c7a9 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -268,6 +268,13 @@ typedef void (*regmap_unlock)(void *); * field is NULL but precious_table (see below) is not, the * check is performed on such table (a register is precious if * it belongs to one of the ranges specified by precious_table). + * @writeable_noinc_reg: Optional callback returning true if the register + * supports multiple write operations without incrementing + * the register number. If this field is NULL but + * wr_noinc_table (see below) is not, the check is + * performed on such table (a register is no increment + * writeable if it belongs to one of the ranges specified + * by wr_noinc_table). * @readable_noinc_reg: Optional callback returning true if the register * supports multiple read operations without incrementing * the register number. If this field is NULL but @@ -302,6 +309,7 @@ typedef void (*regmap_unlock)(void *); * @rd_table: As above, for read access. * @volatile_table: As above, for volatile registers. * @precious_table: As above, for precious registers. + * @wr_noinc_table: As above, for no increment writeable registers. * @rd_noinc_table: As above, for no increment readable registers. * @reg_defaults: Power on reset values for registers (for use with * register cache support). @@ -352,6 +360,7 @@ struct regmap_config { bool (*readable_reg)(struct device *dev, unsigned int reg); bool (*volatile_reg)(struct device *dev, unsigned int reg); bool (*precious_reg)(struct device *dev, unsigned int reg); + bool (*writeable_noinc_reg)(struct device *dev, unsigned int reg); bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); bool disable_locking; @@ -369,6 +378,7 @@ struct regmap_config { const struct regmap_access_table *rd_table; const struct regmap_access_table *volatile_table; const struct regmap_access_table *precious_table; + const struct regmap_access_table *wr_noinc_table; const struct regmap_access_table *rd_noinc_table; const struct reg_default *reg_defaults; unsigned int num_reg_defaults; @@ -979,6 +989,8 @@ int regmap_write(struct regmap *map, unsigned int reg, unsigned int val); int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val); int regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len); +int regmap_noinc_write(struct regmap *map, unsigned int reg, + const void *val, size_t val_len); int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count); int regmap_multi_reg_write(struct regmap *map, const struct reg_sequence *regs, @@ -1222,6 +1234,13 @@ static inline int regmap_raw_write_async(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_noinc_write(struct regmap *map, unsigned int reg, + const void *val, size_t val_len) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count) { -- cgit v1.2.3 From bcb047ebf28453da56f0265aeeb9edc52b797ea7 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 4 Oct 2018 15:25:58 +0800 Subject: regulator: bd718x7: Remove struct bd718xx_pmic All the fields in struct bd718xx_pmic are not really necessary. Remove struct bd718xx_pmic to simplify the code. Signed-off-by: Axel Lin Reviewed-by: Matti Vaittinen Signed-off-by: Mark Brown --- include/linux/mfd/rohm-bd718x7.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h index 26acf9a92498..fd194bfc836f 100644 --- a/include/linux/mfd/rohm-bd718x7.h +++ b/include/linux/mfd/rohm-bd718x7.h @@ -321,7 +321,6 @@ enum { BD718XX_PWRBTN_LONG_PRESS_15S }; -struct bd718xx_pmic; struct bd718xx_clk; struct bd718xx { @@ -333,7 +332,6 @@ struct bd718xx { int chip_irq; struct regmap_irq_chip_data *irq_data; - struct bd718xx_pmic *pmic; struct bd718xx_clk *clk; }; -- cgit v1.2.3 From 99c228a994ec8b1580c43631866fd2c5440f5bfd Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 18 Oct 2018 14:22:55 +0300 Subject: fs: group frequently accessed fields of struct super_block together Kernel test robot reported [1] a 6% performance regression in a concurrent unlink(2) workload on commit 60f7ed8c7c4d ("fsnotify: send path type events to group with super block marks"). The performance test was run with no fsnotify marks at all on the data set, so the only extra instructions added by the offending commit are tests of the super_block fields s_fsnotify_{marks,mask} and these tests happen on almost every single inode access. When adding those fields to the super_block struct, we did not give much thought of placing them on a hot cache lines (we just placed them at the end of the struct). Re-organize struct super_block to try and keep some frequently accessed fields on the same cache line. Move the frequently accessed fields s_fsnotify_{marks,mask} near the frequently accessed fields s_fs_info,s_time_gran, while filling a 64bit alignment hole after s_time_gran. Move the seldom accessed fields s_id,s_uuid,s_max_links,s_mode near the seldom accessed fields s_vfs_rename_mutex,s_subtype. Rong Chen confirmed that this patch solved the reported problem. [1] https://lkml.org/lkml/2018/9/30/206 Reported-by: kernel test robot Tested-by: kernel test robot Fixes: 1e6cb72399 ("fsnotify: add super block object type") Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fs.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c14801d0aa3..6da94deb957f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1393,17 +1393,26 @@ struct super_block { struct sb_writers s_writers; + /* + * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and + * s_fsnotify_marks together for cache efficiency. They are frequently + * accessed and rarely modified. + */ + void *s_fs_info; /* Filesystem private info */ + + /* Granularity of c/m/atime in ns (cannot be worse than a second) */ + u32 s_time_gran; +#ifdef CONFIG_FSNOTIFY + __u32 s_fsnotify_mask; + struct fsnotify_mark_connector __rcu *s_fsnotify_marks; +#endif + char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ - void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; fmode_t s_mode; - /* Granularity of c/m/atime in ns. - Cannot be worse than a second */ - u32 s_time_gran; - /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. @@ -1464,11 +1473,6 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ - -#ifdef CONFIG_FSNOTIFY - __u32 s_fsnotify_mask; - struct fsnotify_mark_connector __rcu *s_fsnotify_marks; -#endif } __randomize_layout; /* Helper functions so that in most cases filesystems will -- cgit v1.2.3 From 3952105df4723abbd36b57e88c8dad42cf6c8b59 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Wed, 17 Oct 2018 19:25:23 +0530 Subject: remoteproc: Introduce custom dump function for each remoteproc segment Introduce custom dump function and private data per remoteproc dump segment. The dump function is responsible for filling the device memory segment associated with coredump Signed-off-by: Sibi Sankar Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8bb0cf0416f1..2d036adab7ff 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -412,6 +412,9 @@ enum rproc_crash_type { * @node: list node related to the rproc segment list * @da: device address of the segment * @size: size of the segment + * @priv: private data associated with the dump_segment + * @dump: custom dump function to fill device memory segment associated + * with coredump */ struct rproc_dump_segment { struct list_head node; @@ -419,6 +422,9 @@ struct rproc_dump_segment { dma_addr_t da; size_t size; + void *priv; + void (*dump)(struct rproc *rproc, struct rproc_dump_segment *segment, + void *dest); loff_t offset; }; -- cgit v1.2.3 From ab8f873bb90da7bbe40e2f41c92a4971c4f0dc76 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Wed, 17 Oct 2018 19:25:24 +0530 Subject: remoteproc: Add mechanism for custom dump function assignment This patch adds a mechanism for assigning each rproc dump segment with a custom dump function and private data. The dump function is to be called for each rproc segment during coredump if assigned. Signed-off-by: Sibi Sankar [bjorn: reordred arguments to rproc_coredump_add_custom_segment()] Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 2d036adab7ff..507a2b524208 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -592,6 +592,12 @@ int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size); +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 *priv); static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) { -- cgit v1.2.3 From 144991602e6a14d667b295f1b099e609ce857772 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:09 +0200 Subject: bpf: rename stack trace map operations In the following patches queue and stack maps (FIFO and LIFO datastructures) will be implemented. In order to avoid confusion and a possible name clash rename stack_map_ops to stack_trace_map_ops Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa48343a5ea1..7bad4e1947ed 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -51,7 +51,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops) #ifdef CONFIG_PERF_EVENTS -BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) -- cgit v1.2.3 From 2ea864c58f19bf70a0e2415f9f1c53814e07f1b4 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:20 +0200 Subject: bpf/verifier: add ARG_PTR_TO_UNINIT_MAP_VALUE ARG_PTR_TO_UNINIT_MAP_VALUE argument is a pointer to a memory zone used to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. This will be used in the following patch that implements some new helpers that receive a pointer to be filled with a map value. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu 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 e60fff48288b..0f8b863e0229 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -138,6 +138,7 @@ enum bpf_arg_type { ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ + ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack -- cgit v1.2.3 From f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:25 +0200 Subject: bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++++ include/linux/bpf_types.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0f8b863e0229..33014ae73103 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -39,6 +39,9 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); + int (*map_pop_elem)(struct bpf_map *map, void *value); + int (*map_peek_elem)(struct bpf_map *map, void *value); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -811,6 +814,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_map_push_elem_proto; +extern const struct bpf_func_proto bpf_map_pop_elem_proto; +extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 7bad4e1947ed..44d9ab4809bd 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) -- cgit v1.2.3 From b39b5f411dcfce28ff954e5d6acb2c11be3cb0ec Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 19 Oct 2018 09:57:57 -0700 Subject: bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB BPF programs of BPF_PROG_TYPE_CGROUP_SKB need to access headers in the skb. This patch enables direct access of skb for these programs. Two helper functions bpf_compute_and_save_data_end() and bpf_restore_data_end() are introduced. There are used in __cgroup_bpf_run_filter_skb(), to compute proper data_end for the BPF program, and restore original data afterwards. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5771874bc01e..91b4c934f02e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,6 +548,27 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) cb->data_end = skb->data + skb_headlen(skb); } +/* Similar to bpf_compute_data_pointers(), except that save orginal + * data in cb->data and cb->meta_data for restore. + */ +static inline void bpf_compute_and_save_data_end( + struct sk_buff *skb, void **saved_data_end) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + + *saved_data_end = cb->data_end; + cb->data_end = skb->data + skb_headlen(skb); +} + +/* Restore data saved by bpf_compute_data_pointers(). */ +static inline void bpf_restore_data_end( + struct sk_buff *skb, void *saved_data_end) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + + cb->data_end = saved_data_end; +} + static inline u8 *bpf_skb_cb(struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta -- cgit v1.2.3 From 5032d079909d1ac5c2535acc32d5f01cd245d8ea Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 18 Oct 2018 13:58:35 -0700 Subject: bpf: skmsg, fix psock create on existing kcm/tls port Before using the psock returned by sk_psock_get() when adding it to a sockmap we need to ensure it is actually a sockmap based psock. Previously we were only checking this after incrementing the reference counter which was an error. This resulted in a slab-out-of-bounds error when the psock was not actually a sockmap type. This moves the check up so the reference counter is only used if it is a sockmap psock. Eric reported the following KASAN BUG, BUG: KASAN: slab-out-of-bounds in atomic_read include/asm-generic/atomic-instrumented.h:21 [inline] BUG: KASAN: slab-out-of-bounds in refcount_inc_not_zero_checked+0x97/0x2f0 lib/refcount.c:120 Read of size 4 at addr ffff88019548be58 by task syz-executor4/22387 CPU: 1 PID: 22387 Comm: syz-executor4 Not tainted 4.19.0-rc7+ #264 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c4/0x2b4 lib/dump_stack.c:113 print_address_description.cold.8+0x9/0x1ff mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412 check_memory_region_inline mm/kasan/kasan.c:260 [inline] check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267 kasan_check_read+0x11/0x20 mm/kasan/kasan.c:272 atomic_read include/asm-generic/atomic-instrumented.h:21 [inline] refcount_inc_not_zero_checked+0x97/0x2f0 lib/refcount.c:120 sk_psock_get include/linux/skmsg.h:379 [inline] sock_map_link.isra.6+0x41f/0xe30 net/core/sock_map.c:178 sock_hash_update_common+0x19b/0x11e0 net/core/sock_map.c:669 sock_hash_update_elem+0x306/0x470 net/core/sock_map.c:738 map_update_elem+0x819/0xdf0 kernel/bpf/syscall.c:818 Signed-off-by: John Fastabend Reported-by: Eric Dumazet Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 22347b08e1f8..84e18863f6a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -270,11 +270,6 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } -static inline bool sk_has_psock(struct sock *sk) -{ - return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg; -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { @@ -374,6 +369,26 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock, return test_bit(bit, &psock->state); } +static inline struct sk_psock *sk_psock_get_checked(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock) { + if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) { + psock = ERR_PTR(-EBUSY); + goto out; + } + + if (!refcount_inc_not_zero(&psock->refcnt)) + psock = ERR_PTR(-EBUSY); + } +out: + rcu_read_unlock(); + return psock; +} + static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; -- cgit v1.2.3 From c9fbd71f73094311b31ee703a918e9e0df502cef Mon Sep 17 00:00:00 2001 From: Debabrata Banerjee Date: Thu, 18 Oct 2018 11:18:26 -0400 Subject: netpoll: allow cleanup to be synchronous This fixes a problem introduced by: commit 2cde6acd49da ("netpoll: Fix __netpoll_rcu_free so that it can hold the rtnl lock") When using netconsole on a bond, __netpoll_cleanup can asynchronously recurse multiple times, each __netpoll_free_async call can result in more __netpoll_free_async's. This means there is now a race between cleanup_work queues on multiple netpoll_info's on multiple devices and the configuration of a new netpoll. For example if a netconsole is set to enable 0, reconfigured, and enable 1 immediately, this netconsole will likely not work. Given the reason for __netpoll_free_async is it can be called when rtnl is not locked, if it is locked, we should be able to execute synchronously. It appears to be locked everywhere it's called from. Generalize the design pattern from the teaming driver for current callers of __netpoll_free_async. CC: Neil Horman CC: "David S. Miller" Signed-off-by: Debabrata Banerjee Signed-off-by: David S. Miller --- include/linux/netpoll.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 3ef82d3a78db..676f1ff161a9 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -31,8 +31,6 @@ struct netpoll { bool ipv6; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; - - struct work_struct cleanup_work; }; struct netpoll_info { @@ -63,7 +61,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt); int __netpoll_setup(struct netpoll *np, struct net_device *ndev); int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); -void __netpoll_free_async(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); -- cgit v1.2.3 From bff5b4b3737219195ca0caef4ff7884303cb5dc1 Mon Sep 17 00:00:00 2001 From: Yuiko Oshino Date: Thu, 18 Oct 2018 15:06:01 -0400 Subject: net: phy: micrel: add Microchip KSZ9131 initial driver Add support for Microchip Technology KSZ9131 10/100/1000 Ethernet PHY Signed-off-by: Yuiko Oshino Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 472fa4d4ea62..7361cd3fddc1 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,6 +31,7 @@ #define PHY_ID_KSZ8081 0x00221560 #define PHY_ID_KSZ8061 0x00221570 #define PHY_ID_KSZ9031 0x00221620 +#define PHY_ID_KSZ9131 0x00221640 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -- cgit v1.2.3 From 6fff607e2f14bd7c63c06c464a6f93b8efbabe28 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Oct 2018 19:56:49 -0700 Subject: bpf: sk_msg program helper bpf_msg_push_data This allows user to push data into a msg using sk_msg program types. The format is as follows, bpf_msg_push_data(msg, offset, len, flags) this will insert 'len' bytes at offset 'offset'. For example to prepend 10 bytes at the front of the message the user can, bpf_msg_push_data(msg, 0, 10, 0); This will invalidate data bounds so BPF user will have to then recheck data bounds after calling this. After this the msg size will have been updated and the user is free to write into the added bytes. We allow any offset/len as long as it is within the (data, data_end) range. However, a copy will be required if the ring is full and its possible for the helper to fail with ENOMEM or EINVAL errors which need to be handled by the BPF program. This can be used similar to XDP metadata to pass data between sk_msg layer and lower layers. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84e18863f6a4..2a11e9d91dfa 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -207,6 +207,11 @@ static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) return &msg->sg.data[which]; } +static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which) +{ + return msg->sg.data[which]; +} + static inline struct page *sk_msg_page(struct sk_msg *msg, int which) { return sg_page(sk_msg_elem(msg, which)); -- cgit v1.2.3 From b2c3fa546705944e748666b474ffdaebaec0569f Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Sat, 20 Oct 2018 14:56:11 -0400 Subject: blkcg: fix edge case for blk_get_rl() under memory pressure It is possible for blkg creation to fail when in blk_get_rl(). In this situation, the fallback logic returns the nearest created blkg. There is however special handling for the request_list for the root blkcg. This fixes the missing edge case from the earlier series changing blk_get_rl(). Fixes: e2b0989954ae ("blkcg: cleanup and make blk_get_rl use blkg_lookup_create") Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b7fd08013de2..1e76ceebeb5d 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -597,7 +597,7 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, if (unlikely(!blkg)) blkg = __blkg_lookup_create(blkcg, q); - if (!blkg_tryget(blkg)) + if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg)) goto rl_use_root; rcu_read_unlock(); -- cgit v1.2.3 From d459d853c2edc793135e4bfa4e345c758f1cc859 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Sat, 20 Oct 2018 14:56:12 -0400 Subject: blkcg: reassociate bios when make_request() is called recursively When submitting a bio, multiple recursive calls to make_request() may occur. This causes the initial associate done in blkcg_bio_issue_check() to be incorrect and reference the prior request_queue. This introduces a helper to do reassociation when make_request() is recursively called. Fixes: a7b39b4e961c ("blkcg: always associate a bio with a blkg") Reported-by: Valdis Kletnieks Signed-off-by: Dennis Zhou Tested-by: Valdis Kletnieks Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index f447b0ebb288..b47c7f716731 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -514,6 +514,7 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); int bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); +int bio_reassociate_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ @@ -522,6 +523,8 @@ static inline int bio_associate_blkg_from_css(struct bio *bio, { return 0; } static inline int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { return 0; } +static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) +{ return 0; } static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } -- cgit v1.2.3 From f8d5d0cc145cc21bfc56ef807dc28102aebbf228 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 7 Nov 2017 16:30:10 -0500 Subject: xarray: Add definition of struct xarray This is a direct replacement for struct radix_tree_root. Some of the struct members have changed name; convert those, and use a #define so that radix_tree users continue to work without change. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 28 ++++++------------- include/linux/xarray.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 60f3d8eb2cb7..0b080bd88ab7 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -30,6 +30,9 @@ #include #include +/* Keep unconverted code working */ +#define radix_tree_root xarray + /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: @@ -92,36 +95,21 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* The IDR tag is stored in the low bits of the GFP flags */ +/* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) -/* The top bits of gfp_mask are used to store the root tags */ +/* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) -struct radix_tree_root { - spinlock_t xa_lock; - gfp_t gfp_mask; - struct radix_tree_node __rcu *rnode; -}; - -#define RADIX_TREE_INIT(name, mask) { \ - .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ - .gfp_mask = (mask), \ - .rnode = NULL, \ -} +#define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) -#define INIT_RADIX_TREE(root, mask) \ -do { \ - spin_lock_init(&(root)->xa_lock); \ - (root)->gfp_mask = (mask); \ - (root)->rnode = NULL; \ -} while (0) +#define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { - return root->rnode == NULL; + return root->xa_head == NULL; } /** diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4d1cd7a083e8..9122cf8bf52a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -10,6 +10,8 @@ */ #include +#include +#include #include #include @@ -153,6 +155,74 @@ static inline bool xa_is_internal(const void *entry) return ((unsigned long)entry & 3) == 2; } +/** + * struct xarray - The anchor of the XArray. + * @xa_lock: Lock that protects the contents of the XArray. + * + * To use the xarray, define it statically or embed it in your data structure. + * It is a very small data structure, so it does not usually make sense to + * allocate it separately and keep a pointer to it in your data structure. + * + * You may use the xa_lock to protect your own data structures as well. + */ +/* + * If all of the entries in the array are NULL, @xa_head is a NULL pointer. + * If the only non-NULL entry in the array is at index 0, @xa_head is that + * entry. If any other entry in the array is non-NULL, @xa_head points + * to an @xa_node. + */ +struct xarray { + spinlock_t xa_lock; +/* private: The rest of the data structure is not to be used directly. */ + gfp_t xa_flags; + void __rcu * xa_head; +}; + +#define XARRAY_INIT(name, flags) { \ + .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ + .xa_flags = flags, \ + .xa_head = NULL, \ +} + +/** + * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. + * @name: A string that names your XArray. + * @flags: XA_FLAG values. + * + * This is intended for file scope definitions of XArrays. It declares + * and initialises an empty XArray with the chosen name and flags. It is + * equivalent to calling xa_init_flags() on the array, but it does the + * initialisation at compiletime instead of runtime. + */ +#define DEFINE_XARRAY_FLAGS(name, flags) \ + struct xarray name = XARRAY_INIT(name, flags) + +/** + * DEFINE_XARRAY() - Define an XArray. + * @name: A string that names your XArray. + * + * This is intended for file scope definitions of XArrays. It declares + * and initialises an empty XArray with the chosen name. It is equivalent + * to calling xa_init() on the array, but it does the initialisation at + * compiletime instead of runtime. + */ +#define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) + +void xa_init_flags(struct xarray *, gfp_t flags); + +/** + * xa_init() - Initialise an empty XArray. + * @xa: XArray. + * + * An empty XArray is full of NULL entries. + * + * Context: Any context. + */ +static inline void xa_init(struct xarray *xa) +{ + xa_init_flags(xa, 0); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) -- cgit v1.2.3 From 01959dfe771c6893365482ec78dc1d9cbbbe6de8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 9 Nov 2017 09:23:56 -0500 Subject: xarray: Define struct xa_node This is a direct replacement for struct radix_tree_node. A couple of struct members have changed name, so convert those. Use a #define so that radix tree users continue to work without change. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 29 +++-------------------------- include/linux/xarray.h | 27 +++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 0b080bd88ab7..15388b7e38b9 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -32,6 +32,7 @@ /* Keep unconverted code working */ #define radix_tree_root xarray +#define radix_tree_node xa_node /* * The bottom two bits of the slot determine how the remaining bits in the @@ -60,41 +61,17 @@ static inline bool radix_tree_is_internal_node(void *ptr) /*** radix-tree API starts here ***/ -#define RADIX_TREE_MAX_TAGS 3 - #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) -#define RADIX_TREE_TAG_LONGS \ - ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG) +#define RADIX_TREE_MAX_TAGS XA_MAX_MARKS +#define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) -/* - * @count is the count of every non-NULL element in the ->slots array - * whether that is a value entry, a retry entry, a user pointer, - * a sibling entry or a pointer to the next level of the tree. - * @exceptional is the count of every element in ->slots which is - * either a value entry or a sibling of a value entry. - */ -struct radix_tree_node { - unsigned char shift; /* Bits remaining in each slot */ - unsigned char offset; /* Slot offset in parent */ - unsigned char count; /* Total entry count */ - unsigned char exceptional; /* Exceptional entry count */ - struct radix_tree_node *parent; /* Used when ascending tree */ - struct radix_tree_root *root; /* The tree we belong to */ - union { - struct list_head private_list; /* For tree user */ - struct rcu_head rcu_head; /* Used when freeing node */ - }; - void __rcu *slots[RADIX_TREE_MAP_SIZE]; - unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; -}; - /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9122cf8bf52a..52141dfc5a90 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -252,6 +252,33 @@ static inline void xa_init(struct xarray *xa) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) +#define XA_MAX_MARKS 3 +#define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) + +/* + * @count is the count of every non-NULL element in the ->slots array + * whether that is a value entry, a retry entry, a user pointer, + * a sibling entry or a pointer to the next level of the tree. + * @nr_values is the count of every element in ->slots which is + * either a value entry or a sibling of a value entry. + */ +struct xa_node { + unsigned char shift; /* Bits remaining in each slot */ + unsigned char offset; /* Slot offset in parent */ + unsigned char count; /* Total entry count */ + unsigned char nr_values; /* Value entry count */ + struct xa_node __rcu *parent; /* NULL at top of tree */ + struct xarray *array; /* The array we belong to */ + union { + struct list_head private_list; /* For tree user */ + struct rcu_head rcu_head; /* Used when freeing node */ + }; + void __rcu *slots[XA_CHUNK_SIZE]; + union { + unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; + unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; + }; +}; /* Private */ static inline bool xa_is_node(const void *entry) -- cgit v1.2.3 From ad3d6c7263e368abdc151e1cc13dc78aa39cc7a7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 7 Nov 2017 14:57:46 -0500 Subject: xarray: Add XArray load operation The xa_load function brings with it a lot of infrastructure; xa_empty(), xa_is_err(), and large chunks of the XArray advanced API that are used to implement xa_load. As the test-suite demonstrates, it is possible to use the XArray functions on a radix tree. The radix tree functions depend on the GFP flags being stored in the root of the tree, so it's not possible to use the radix tree functions on an XArray. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 336 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 336 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 52141dfc5a90..a0df8217068c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include @@ -30,6 +32,10 @@ * * 0-62: Sibling entries * 256: Retry entry + * + * Errors are also represented as internal entries, but use the negative + * space (-4094 to -2). They're never stored in the slots array; only + * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) @@ -155,6 +161,42 @@ static inline bool xa_is_internal(const void *entry) return ((unsigned long)entry & 3) == 2; } +/** + * xa_is_err() - Report whether an XArray operation returned an error + * @entry: Result from calling an XArray function + * + * If an XArray operation cannot complete an operation, it will return + * a special value indicating an error. This function tells you + * whether an error occurred; xa_err() tells you which error occurred. + * + * Context: Any context. + * Return: %true if the entry indicates an error. + */ +static inline bool xa_is_err(const void *entry) +{ + return unlikely(xa_is_internal(entry)); +} + +/** + * xa_err() - Turn an XArray result into an errno. + * @entry: Result from calling an XArray function. + * + * If an XArray operation cannot complete an operation, it will return + * a special pointer value which encodes an errno. This function extracts + * the errno from the pointer value, or returns 0 if the pointer does not + * represent an errno. + * + * Context: Any context. + * Return: A negative errno or 0. + */ +static inline int xa_err(void *entry) +{ + /* xa_to_internal() would not do sign extension. */ + if (xa_is_err(entry)) + return (long)entry >> 2; + return 0; +} + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -209,6 +251,7 @@ struct xarray { #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) void xa_init_flags(struct xarray *, gfp_t flags); +void *xa_load(struct xarray *, unsigned long index); /** * xa_init() - Initialise an empty XArray. @@ -223,6 +266,18 @@ static inline void xa_init(struct xarray *xa) xa_init_flags(xa, 0); } +/** + * xa_empty() - Determine if an array has any present entries. + * @xa: XArray. + * + * Context: Any context. + * Return: %true if the array contains only NULL pointers. + */ +static inline bool xa_empty(const struct xarray *xa) +{ + return xa->xa_head == NULL; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -280,6 +335,65 @@ struct xa_node { }; }; +void xa_dump(const struct xarray *); +void xa_dump_node(const struct xa_node *); + +#ifdef XA_DEBUG +#define XA_BUG_ON(xa, x) do { \ + if (x) { \ + xa_dump(xa); \ + BUG(); \ + } \ + } while (0) +#define XA_NODE_BUG_ON(node, x) do { \ + if (x) { \ + if (node) xa_dump_node(node); \ + BUG(); \ + } \ + } while (0) +#else +#define XA_BUG_ON(xa, x) do { } while (0) +#define XA_NODE_BUG_ON(node, x) do { } while (0) +#endif + +/* Private */ +static inline void *xa_head(const struct xarray *xa) +{ + return rcu_dereference_check(xa->xa_head, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_head_locked(const struct xarray *xa) +{ + return rcu_dereference_protected(xa->xa_head, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_entry(const struct xarray *xa, + const struct xa_node *node, unsigned int offset) +{ + XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); + return rcu_dereference_check(node->slots[offset], + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_entry_locked(const struct xarray *xa, + const struct xa_node *node, unsigned int offset) +{ + XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); + return rcu_dereference_protected(node->slots[offset], + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline struct xa_node *xa_to_node(const void *entry) +{ + return (struct xa_node *)((unsigned long)entry - 2); +} + /* Private */ static inline bool xa_is_node(const void *entry) { @@ -312,4 +426,226 @@ static inline bool xa_is_sibling(const void *entry) #define XA_RETRY_ENTRY xa_mk_internal(256) +/** + * xa_is_retry() - Is the entry a retry entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a retry entry. + */ +static inline bool xa_is_retry(const void *entry) +{ + return unlikely(entry == XA_RETRY_ENTRY); +} + +/** + * typedef xa_update_node_t - A callback function from the XArray. + * @node: The node which is being processed + * + * This function is called every time the XArray updates the count of + * present and value entries in a node. It allows advanced users to + * maintain the private_list in the node. + * + * Context: The xa_lock is held and interrupts may be disabled. + * Implementations should not drop the xa_lock, nor re-enable + * interrupts. + */ +typedef void (*xa_update_node_t)(struct xa_node *node); + +/* + * The xa_state is opaque to its users. It contains various different pieces + * of state involved in the current operation on the XArray. It should be + * declared on the stack and passed between the various internal routines. + * The various elements in it should not be accessed directly, but only + * through the provided accessor functions. The below documentation is for + * the benefit of those working on the code, not for users of the XArray. + * + * @xa_node usually points to the xa_node containing the slot we're operating + * on (and @xa_offset is the offset in the slots array). If there is a + * single entry in the array at index 0, there are no allocated xa_nodes to + * point to, and so we store %NULL in @xa_node. @xa_node is set to + * the value %XAS_RESTART if the xa_state is not walked to the correct + * position in the tree of nodes for this operation. If an error occurs + * during an operation, it is set to an %XAS_ERROR value. If we run off the + * end of the allocated nodes, it is set to %XAS_BOUNDS. + */ +struct xa_state { + struct xarray *xa; + unsigned long xa_index; + unsigned char xa_shift; + unsigned char xa_sibs; + unsigned char xa_offset; + unsigned char xa_pad; /* Helps gcc generate better code */ + struct xa_node *xa_node; + struct xa_node *xa_alloc; + xa_update_node_t xa_update; +}; + +/* + * We encode errnos in the xas->xa_node. If an error has happened, we need to + * drop the lock to fix it, and once we've done so the xa_state is invalid. + */ +#define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) +#define XAS_BOUNDS ((struct xa_node *)1UL) +#define XAS_RESTART ((struct xa_node *)3UL) + +#define __XA_STATE(array, index, shift, sibs) { \ + .xa = array, \ + .xa_index = index, \ + .xa_shift = shift, \ + .xa_sibs = sibs, \ + .xa_offset = 0, \ + .xa_pad = 0, \ + .xa_node = XAS_RESTART, \ + .xa_alloc = NULL, \ + .xa_update = NULL \ +} + +/** + * XA_STATE() - Declare an XArray operation state. + * @name: Name of this operation state (usually xas). + * @array: Array to operate on. + * @index: Initial index of interest. + * + * Declare and initialise an xa_state on the stack. + */ +#define XA_STATE(name, array, index) \ + struct xa_state name = __XA_STATE(array, index, 0, 0) + +/** + * XA_STATE_ORDER() - Declare an XArray operation state. + * @name: Name of this operation state (usually xas). + * @array: Array to operate on. + * @index: Initial index of interest. + * @order: Order of entry. + * + * Declare and initialise an xa_state on the stack. This variant of + * XA_STATE() allows you to specify the 'order' of the element you + * want to operate on.` + */ +#define XA_STATE_ORDER(name, array, index, order) \ + struct xa_state name = __XA_STATE(array, \ + (index >> order) << order, \ + order - (order % XA_CHUNK_SHIFT), \ + (1U << (order % XA_CHUNK_SHIFT)) - 1) + +#define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) +#define xas_trylock(xas) xa_trylock((xas)->xa) +#define xas_lock(xas) xa_lock((xas)->xa) +#define xas_unlock(xas) xa_unlock((xas)->xa) +#define xas_lock_bh(xas) xa_lock_bh((xas)->xa) +#define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) +#define xas_lock_irq(xas) xa_lock_irq((xas)->xa) +#define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) +#define xas_lock_irqsave(xas, flags) \ + xa_lock_irqsave((xas)->xa, flags) +#define xas_unlock_irqrestore(xas, flags) \ + xa_unlock_irqrestore((xas)->xa, flags) + +/** + * xas_error() - Return an errno stored in the xa_state. + * @xas: XArray operation state. + * + * Return: 0 if no error has been noted. A negative errno if one has. + */ +static inline int xas_error(const struct xa_state *xas) +{ + return xa_err(xas->xa_node); +} + +/** + * xas_set_err() - Note an error in the xa_state. + * @xas: XArray operation state. + * @err: Negative error number. + * + * Only call this function with a negative @err; zero or positive errors + * will probably not behave the way you think they should. If you want + * to clear the error from an xa_state, use xas_reset(). + */ +static inline void xas_set_err(struct xa_state *xas, long err) +{ + xas->xa_node = XA_ERROR(err); +} + +/** + * xas_invalid() - Is the xas in a retry or error state? + * @xas: XArray operation state. + * + * Return: %true if the xas cannot be used for operations. + */ +static inline bool xas_invalid(const struct xa_state *xas) +{ + return (unsigned long)xas->xa_node & 3; +} + +/** + * xas_valid() - Is the xas a valid cursor into the array? + * @xas: XArray operation state. + * + * Return: %true if the xas can be used for operations. + */ +static inline bool xas_valid(const struct xa_state *xas) +{ + return !xas_invalid(xas); +} + +/** + * xas_reset() - Reset an XArray operation state. + * @xas: XArray operation state. + * + * Resets the error or walk state of the @xas so future walks of the + * array will start from the root. Use this if you have dropped the + * xarray lock and want to reuse the xa_state. + * + * Context: Any context. + */ +static inline void xas_reset(struct xa_state *xas) +{ + xas->xa_node = XAS_RESTART; +} + +/** + * xas_retry() - Retry the operation if appropriate. + * @xas: XArray operation state. + * @entry: Entry from xarray. + * + * The advanced functions may sometimes return an internal entry, such as + * a retry entry or a zero entry. This function sets up the @xas to restart + * the walk from the head of the array if needed. + * + * Context: Any context. + * Return: true if the operation needs to be retried. + */ +static inline bool xas_retry(struct xa_state *xas, const void *entry) +{ + if (!xa_is_retry(entry)) + return false; + xas_reset(xas); + return true; +} + +void *xas_load(struct xa_state *); + +/** + * xas_reload() - Refetch an entry from the xarray. + * @xas: XArray operation state. + * + * Use this function to check that a previously loaded entry still has + * the same value. This is useful for the lockless pagecache lookup where + * we walk the array with only the RCU lock to protect us, lock the page, + * then check that the page hasn't moved since we looked it up. + * + * The caller guarantees that @xas is still valid. If it may be in an + * error or restart state, call xas_load() instead. + * + * Return: The entry at this location in the xarray. + */ +static inline void *xas_reload(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (node) + return xa_entry(xas->xa, node, xas->xa_offset); + return xa_head(xas->xa); +} + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 9b89a0355144685a787b0dc5bcf7bdd6f2d02968 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 09:34:31 -0500 Subject: xarray: Add XArray marks XArray marks are like the radix tree tags, only slightly more strongly typed. They are renamed in order to distinguish them from tagged pointers. This commit adds the basic get/set/clear operations. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index a0df8217068c..2de504ae9ba4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -197,6 +198,20 @@ static inline int xa_err(void *entry) return 0; } +typedef unsigned __bitwise xa_mark_t; +#define XA_MARK_0 ((__force xa_mark_t)0U) +#define XA_MARK_1 ((__force xa_mark_t)1U) +#define XA_MARK_2 ((__force xa_mark_t)2U) +#define XA_PRESENT ((__force xa_mark_t)8U) +#define XA_MARK_MAX XA_MARK_2 + +/* + * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, + * and we remain compatible with that. + */ +#define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ + (__force unsigned)(mark))) + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -252,6 +267,9 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); +bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); +void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); +void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_init() - Initialise an empty XArray. @@ -278,6 +296,19 @@ static inline bool xa_empty(const struct xarray *xa) return xa->xa_head == NULL; } +/** + * xa_marked() - Inquire whether any entry in this array has a mark set + * @xa: Array + * @mark: Mark value + * + * Context: Any context. + * Return: %true if any entry has this mark set. + */ +static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) +{ + return xa->xa_flags & XA_FLAGS_MARK(mark); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -290,6 +321,12 @@ static inline bool xa_empty(const struct xarray *xa) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +/* + * Versions of the normal API which require the caller to hold the xa_lock. + */ +void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); +void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); + /* Everything below here is the Advanced API. Proceed with caution. */ /* @@ -388,6 +425,22 @@ static inline void *xa_entry_locked(const struct xarray *xa, lockdep_is_held(&xa->xa_lock)); } +/* Private */ +static inline struct xa_node *xa_parent(const struct xarray *xa, + const struct xa_node *node) +{ + return rcu_dereference_check(node->parent, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline struct xa_node *xa_parent_locked(const struct xarray *xa, + const struct xa_node *node) +{ + return rcu_dereference_protected(node->parent, + lockdep_is_held(&xa->xa_lock)); +} + /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { @@ -588,6 +641,12 @@ static inline bool xas_valid(const struct xa_state *xas) return !xas_invalid(xas); } +/* True if the pointer is something other than a node */ +static inline bool xas_not_node(struct xa_node *node) +{ + return ((unsigned long)node & 3) || !node; +} + /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. @@ -625,6 +684,10 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); +bool xas_get_mark(const struct xa_state *, xa_mark_t); +void xas_set_mark(const struct xa_state *, xa_mark_t); +void xas_clear_mark(const struct xa_state *, xa_mark_t); + /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. -- cgit v1.2.3 From 58d6ea3085f2e53714810a513c61629f6d2be0a6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 15:15:08 -0500 Subject: xarray: Add XArray unconditional store operations xa_store() differs from radix_tree_insert() in that it will overwrite an existing element in the array rather than returning an error. This is the behaviour which most users want, and those that want more complex behaviour generally want to use the xas family of routines anyway. For memory allocation, xa_store() will first attempt to request memory from the slab allocator; if memory is not immediately available, it will drop the xa_lock and allocate memory, keeping a pointer in the xa_state. It does not use the per-CPU cache, although those will continue to exist until all radix tree users are converted to the xarray. This patch also includes xa_erase() and __xa_erase() for a streamlined way to store NULL. Since there is no need to allocate memory in order to store a NULL in the XArray, we do not need to trouble the user with deciding what memory allocation flags to use. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 147 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 145 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2de504ae9ba4..15eab63286ed 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -205,10 +205,17 @@ typedef unsigned __bitwise xa_mark_t; #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 +enum xa_lock_type { + XA_LOCK_IRQ = 1, + XA_LOCK_BH = 2, +}; + /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ +#define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) +#define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) @@ -267,6 +274,7 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); +void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -309,6 +317,23 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) return xa->xa_flags & XA_FLAGS_MARK(mark); } +/** + * xa_erase() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase(struct xarray *xa, unsigned long index) +{ + return xa_store(xa, index, NULL, 0); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -322,11 +347,65 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) spin_unlock_irqrestore(&(xa)->xa_lock, flags) /* - * Versions of the normal API which require the caller to hold the xa_lock. - */ + * Versions of the normal API which require the caller to hold the + * xa_lock. If the GFP flags allow it, they will drop the lock to + * allocate memory, then reacquire it afterwards. These functions + * may also re-enable interrupts if the XArray flags indicate the + * locking should be interrupt safe. + */ +void *__xa_erase(struct xarray *, unsigned long index); +void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +/** + * xa_erase_bh() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) +{ + void *entry; + + xa_lock_bh(xa); + entry = __xa_erase(xa, index); + xa_unlock_bh(xa); + + return entry; +} + +/** + * xa_erase_irq() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) +{ + void *entry; + + xa_lock_irq(xa); + entry = __xa_erase(xa, index); + xa_unlock_irq(xa); + + return entry; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* @@ -441,6 +520,12 @@ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, lockdep_is_held(&xa->xa_lock)); } +/* Private */ +static inline void *xa_mk_node(const struct xa_node *node) +{ + return (void *)((unsigned long)node | 2); +} + /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { @@ -647,6 +732,12 @@ static inline bool xas_not_node(struct xa_node *node) return ((unsigned long)node & 3) || !node; } +/* True if the node represents head-of-tree, RESTART or BOUNDS */ +static inline bool xas_top(struct xa_node *node) +{ + return node <= XAS_RESTART; +} + /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. @@ -683,10 +774,14 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) } void *xas_load(struct xa_state *); +void *xas_store(struct xa_state *, void *entry); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); +void xas_init_marks(const struct xa_state *); + +bool xas_nomem(struct xa_state *, gfp_t); /** * xas_reload() - Refetch an entry from the xarray. @@ -711,4 +806,52 @@ static inline void *xas_reload(struct xa_state *xas) return xa_head(xas->xa); } +/** + * xas_set() - Set up XArray operation state for a different index. + * @xas: XArray operation state. + * @index: New index into the XArray. + * + * Move the operation state to refer to a different index. This will + * have the effect of starting a walk from the top; see xas_next() + * to move to an adjacent index. + */ +static inline void xas_set(struct xa_state *xas, unsigned long index) +{ + xas->xa_index = index; + xas->xa_node = XAS_RESTART; +} + +/** + * xas_set_order() - Set up XArray operation state for a multislot entry. + * @xas: XArray operation state. + * @index: Target of the operation. + * @order: Entry occupies 2^@order indices. + */ +static inline void xas_set_order(struct xa_state *xas, unsigned long index, + unsigned int order) +{ +#ifdef CONFIG_XARRAY_MULTI + xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; + xas->xa_shift = order - (order % XA_CHUNK_SHIFT); + xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; + xas->xa_node = XAS_RESTART; +#else + BUG_ON(order > 0); + xas_set(xas, index); +#endif +} + +/** + * xas_set_update() - Set up XArray operation state for a callback. + * @xas: XArray operation state. + * @update: Function to call when updating a node. + * + * The XArray can notify a caller after it has updated an xa_node. + * This is advanced functionality and is only needed by the page cache. + */ +static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) +{ + xas->xa_update = update; +} + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 41aec91f55985e7f14ee75fe2f6e7bcfff0d0fae Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 15:34:55 -0500 Subject: xarray: Add XArray conditional store operations Like cmpxchg(), xa_cmpxchg will only store to the index if the current entry matches the old entry. It returns the current entry, which is usually more useful than the errno returned by radix_tree_insert(). For the users who really only want the errno, the xa_insert() wrapper provides a more convenient calling convention. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 15eab63286ed..7f740f675b96 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -275,6 +275,8 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *xa_cmpxchg(struct xarray *, unsigned long index, + void *old, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -334,6 +336,34 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) return xa_store(xa, index, NULL, 0); } +/** + * xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Process context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -355,9 +385,39 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, + void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +/** + * __xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use __xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int __xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. -- cgit v1.2.3 From b803b42823d0d9e8b6deccf01ffc2aba5d0738df Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 14 Nov 2017 08:30:11 -0500 Subject: xarray: Add XArray iterators The xa_for_each iterator allows the user to efficiently walk a range of the array, executing the loop body once for each entry in that range that matches the filter. This commit also includes xa_find() and xa_find_after() which are helper functions for xa_for_each() but may also be useful in their own right. In the xas family of functions, we have xas_for_each(), xas_find(), xas_next_entry(), xas_for_each_tagged(), xas_find_tagged(), xas_next_tagged() and xas_pause(). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 165 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 165 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 7f740f675b96..66b10efa5a50 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -280,6 +280,10 @@ void *xa_cmpxchg(struct xarray *, unsigned long index, bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +void *xa_find(struct xarray *xa, unsigned long *index, + unsigned long max, xa_mark_t) __attribute__((nonnull(2))); +void *xa_find_after(struct xarray *xa, unsigned long *index, + unsigned long max, xa_mark_t) __attribute__((nonnull(2))); /** * xa_init() - Initialise an empty XArray. @@ -364,6 +368,35 @@ static inline int xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_for_each() - Iterate over a portion of an XArray. + * @xa: XArray. + * @entry: Entry retrieved from array. + * @index: Index of @entry. + * @max: Maximum index to retrieve from array. + * @filter: Selection criterion. + * + * Initialise @index to the lowest index you want to retrieve from the + * array. During the iteration, @entry will have the value of the entry + * stored in @xa at @index. The iteration will skip all entries in the + * array which do not match @filter. You may modify @index during the + * iteration if you want to skip or reprocess indices. It is safe to modify + * the array during the iteration. At the end of the iteration, @entry will + * be set to NULL and @index will have a value less than or equal to max. + * + * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). xa_for_each() + * will spin if it hits a retry entry; if you intend to see retry entries, + * you should use the xas_for_each() iterator instead. The xas_for_each() + * iterator will expand into more inline code than xa_for_each(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each(xa, entry, index, max, filter) \ + for (entry = xa_find(xa, &index, max, filter); entry; \ + entry = xa_find_after(xa, &index, max, filter)) + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -835,13 +868,16 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); +void *xas_find(struct xa_state *, unsigned long max); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); +void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); +void xas_pause(struct xa_state *); /** * xas_reload() - Refetch an entry from the xarray. @@ -914,4 +950,133 @@ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) xas->xa_update = update; } +/** + * xas_next_entry() - Advance iterator to next present entry. + * @xas: XArray operation state. + * @max: Highest index to return. + * + * xas_next_entry() is an inline function to optimise xarray traversal for + * speed. It is equivalent to calling xas_find(), and will call xas_find() + * for all the hard cases. + * + * Return: The next present entry after the one currently referred to by @xas. + */ +static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) +{ + struct xa_node *node = xas->xa_node; + void *entry; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) + return xas_find(xas, max); + + do { + if (unlikely(xas->xa_index >= max)) + return xas_find(xas, max); + if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) + return xas_find(xas, max); + entry = xa_entry(xas->xa, node, xas->xa_offset + 1); + if (unlikely(xa_is_internal(entry))) + return xas_find(xas, max); + xas->xa_offset++; + xas->xa_index++; + } while (!entry); + + return entry; +} + +/* Private */ +static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, + xa_mark_t mark) +{ + unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; + unsigned int offset = xas->xa_offset; + + if (advance) + offset++; + if (XA_CHUNK_SIZE == BITS_PER_LONG) { + if (offset < XA_CHUNK_SIZE) { + unsigned long data = *addr & (~0UL << offset); + if (data) + return __ffs(data); + } + return XA_CHUNK_SIZE; + } + + return find_next_bit(addr, XA_CHUNK_SIZE, offset); +} + +/** + * xas_next_marked() - Advance iterator to next marked entry. + * @xas: XArray operation state. + * @max: Highest index to return. + * @mark: Mark to search for. + * + * xas_next_marked() is an inline function to optimise xarray traversal for + * speed. It is equivalent to calling xas_find_marked(), and will call + * xas_find_marked() for all the hard cases. + * + * Return: The next marked entry after the one currently referred to by @xas. + */ +static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, + xa_mark_t mark) +{ + struct xa_node *node = xas->xa_node; + unsigned int offset; + + if (unlikely(xas_not_node(node) || node->shift)) + return xas_find_marked(xas, max, mark); + offset = xas_find_chunk(xas, true, mark); + xas->xa_offset = offset; + xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; + if (xas->xa_index > max) + return NULL; + if (offset == XA_CHUNK_SIZE) + return xas_find_marked(xas, max, mark); + return xa_entry(xas->xa, node, offset); +} + +/* + * If iterating while holding a lock, drop the lock and reschedule + * every %XA_CHECK_SCHED loops. + */ +enum { + XA_CHECK_SCHED = 4096, +}; + +/** + * xas_for_each() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * @max: Maximum index to retrieve from array. + * + * The loop body will be executed for each entry present in the xarray + * between the current xas position and @max. @entry will be set to + * the entry retrieved from the xarray. It is safe to delete entries + * from the array in the loop body. You should hold either the RCU lock + * or the xa_lock while iterating. If you need to drop the lock, call + * xas_pause() first. + */ +#define xas_for_each(xas, entry, max) \ + for (entry = xas_find(xas, max); entry; \ + entry = xas_next_entry(xas, max)) + +/** + * xas_for_each_marked() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * @max: Maximum index to retrieve from array. + * @mark: Mark to search for. + * + * The loop body will be executed for each marked entry in the xarray + * between the current xas position and @max. @entry will be set to + * the entry retrieved from the xarray. It is safe to delete entries + * from the array in the loop body. You should hold either the RCU lock + * or the xa_lock while iterating. If you need to drop the lock, call + * xas_pause() first. + */ +#define xas_for_each_marked(xas, entry, max, mark) \ + for (entry = xas_find_marked(xas, max, mark); entry; \ + entry = xas_next_marked(xas, max, mark)) + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 80a0a1a9a3cde9b23851e8eb7160e2786549306a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 14 Nov 2017 16:42:22 -0500 Subject: xarray: Extract entries from an XArray The xa_extract function combines the functionality of radix_tree_gang_lookup() and radix_tree_gang_lookup_tagged(). It extracts entries matching the specified filter into a normal array. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 66b10efa5a50..82ceed981924 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -284,6 +284,8 @@ void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); +unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, + unsigned long max, unsigned int n, xa_mark_t); /** * xa_init() - Initialise an empty XArray. -- cgit v1.2.3 From 687149fca1f37c447e5d161e0a4a04cb2c880cb6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 08:16:34 -0500 Subject: xarray: Destroy an XArray This function frees all the internal memory allocated to the xarray and reinitialises it to be empty. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 82ceed981924..0a758fa3ed2c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -286,6 +286,7 @@ void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); +void xa_destroy(struct xarray *); /** * xa_init() - Initialise an empty XArray. -- cgit v1.2.3 From 64d3e9a9e0cc51957d243dd2b0adc5d74ff5e128 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 00:06:52 -0500 Subject: xarray: Step through an XArray The xas_next and xas_prev functions move the xas index by one position, and adjust the rest of the iterator state to match it. This is more efficient than calling xas_set() as it keeps the iterator at the leaves of the tree instead of walking the iterator from the root each time. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 0a758fa3ed2c..381f94a66762 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -828,6 +828,12 @@ static inline bool xas_not_node(struct xa_node *node) return ((unsigned long)node & 3) || !node; } +/* True if the node represents RESTART or an error */ +static inline bool xas_frozen(struct xa_node *node) +{ + return (unsigned long)node & 2; +} + /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { @@ -1082,4 +1088,65 @@ enum { for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) +void *__xas_next(struct xa_state *); +void *__xas_prev(struct xa_state *); + +/** + * xas_prev() - Move iterator to previous index. + * @xas: XArray operation state. + * + * If the @xas was in an error state, it will remain in an error state + * and this function will return %NULL. If the @xas has never been walked, + * it will have the effect of calling xas_load(). Otherwise one will be + * subtracted from the index and the state will be walked to the correct + * location in the array for the next operation. + * + * If the iterator was referencing index 0, this function wraps + * around to %ULONG_MAX. + * + * Return: The entry at the new index. This may be %NULL or an internal + * entry. + */ +static inline void *xas_prev(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset == 0)) + return __xas_prev(xas); + + xas->xa_index--; + xas->xa_offset--; + return xa_entry(xas->xa, node, xas->xa_offset); +} + +/** + * xas_next() - Move state to next index. + * @xas: XArray operation state. + * + * If the @xas was in an error state, it will remain in an error state + * and this function will return %NULL. If the @xas has never been walked, + * it will have the effect of calling xas_load(). Otherwise one will be + * added to the index and the state will be walked to the correct + * location in the array for the next operation. + * + * If the iterator was referencing index %ULONG_MAX, this function wraps + * around to 0. + * + * Return: The entry at the new index. This may be %NULL or an internal + * entry. + */ +static inline void *xas_next(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset == XA_CHUNK_MASK)) + return __xas_next(xas); + + xas->xa_index++; + xas->xa_offset++; + return xa_entry(xas->xa, node, xas->xa_offset); +} + #endif /* _LINUX_XARRAY_H */ -- cgit v1.2.3 From 4e99d4e9579d3b950bf4b38d0d64eb1b9be78761 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Jun 2018 22:46:02 -0400 Subject: xarray: Add xas_for_each_conflict This iterator iterates over each entry that is stored in the index or indices specified by the xa_state. This is intended for use for a conditional store of a multiindex entry, or to allow entries which are about to be removed from the xarray to be disposed of properly. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 381f94a66762..2664e718dbd3 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -878,6 +878,7 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); +void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); @@ -1088,6 +1089,22 @@ enum { for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) +/** + * xas_for_each_conflict() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * + * The loop body will be executed for each entry in the XArray that lies + * within the range specified by @xas. If the loop completes successfully, + * any entries that lie in this range will be replaced by @entry. The caller + * may break out of the loop; if they do so, the contents of the XArray will + * be unchanged. The operation may fail due to an out of memory condition. + * The caller may also call xa_set_err() to exit the loop while setting an + * error to record the reason. + */ +#define xas_for_each_conflict(xas, entry) \ + while ((entry = xas_find_conflict(xas))) + void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); -- cgit v1.2.3 From 2264f5132fe45571139727ebdeb78696b35d1506 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 00:11:48 -0500 Subject: xarray: Add xas_create_range This hopefully temporary function is useful for users who have not yet been converted to multi-index entries. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2664e718dbd3..deae17aa0ed7 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -822,6 +822,17 @@ static inline bool xas_valid(const struct xa_state *xas) return !xas_invalid(xas); } +/** + * xas_is_node() - Does the xas point to a node? + * @xas: XArray operation state. + * + * Return: %true if the xas currently references a node. + */ +static inline bool xas_is_node(const struct xa_state *xas) +{ + return xas_valid(xas) && xas->xa_node; +} + /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { @@ -889,6 +900,8 @@ void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_pause(struct xa_state *); +void xas_create_range(struct xa_state *); + /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. -- cgit v1.2.3 From 9f14d4f1f1045f161fd4db8a8e194b7825c2874a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 1 Oct 2018 14:54:59 -0400 Subject: xarray: Add xa_reserve and xa_release This function reserves a slot in the XArray for users which need to acquire multiple locks before storing their entry in the tree and so cannot use a plain xa_store(). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 34 ++++++++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index deae17aa0ed7..bed63d3cfea8 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -32,7 +32,8 @@ * The following internal entries have a special meaning: * * 0-62: Sibling entries - * 256: Retry entry + * 256: Zero entry + * 257: Retry entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only @@ -277,6 +278,7 @@ void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int xa_reserve(struct xarray *, unsigned long index, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -371,6 +373,20 @@ static inline int xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_release() - Release a reserved entry. + * @xa: XArray. + * @index: Index of entry. + * + * After calling xa_reserve(), you can call this function to release the + * reservation. If the entry at @index has been stored to, this function + * will do nothing. + */ +static inline void xa_release(struct xarray *xa, unsigned long index) +{ + xa_cmpxchg(xa, index, NULL, NULL, 0); +} + /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. @@ -658,7 +674,19 @@ static inline bool xa_is_sibling(const void *entry) (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } -#define XA_RETRY_ENTRY xa_mk_internal(256) +#define XA_ZERO_ENTRY xa_mk_internal(256) +#define XA_RETRY_ENTRY xa_mk_internal(257) + +/** + * xa_is_zero() - Is the entry a zero entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a zero entry. + */ +static inline bool xa_is_zero(const void *entry) +{ + return unlikely(entry == XA_ZERO_ENTRY); +} /** * xa_is_retry() - Is the entry a retry entry? @@ -880,6 +908,8 @@ static inline void xas_reset(struct xa_state *xas) */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { + if (xa_is_zero(entry)) + return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); -- cgit v1.2.3 From 371c752dc66948714ee3b66c3306f3ff1ff71d2e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jul 2018 10:50:12 -0400 Subject: xarray: Track free entries in an XArray Add the optional ability to track which entries in an XArray are free and provide xa_alloc() to replace most of the functionality of the IDR. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 101 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index bed63d3cfea8..e0b57af52e9b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -205,6 +205,7 @@ typedef unsigned __bitwise xa_mark_t; #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 +#define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, @@ -217,9 +218,12 @@ enum xa_lock_type { */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) +#define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) +#define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -273,6 +277,15 @@ struct xarray { */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) +/** + * DEFINE_XARRAY_ALLOC() - Define an XArray which can allocate IDs. + * @name: A string that names your XArray. + * + * This is intended for file scope definitions of allocating XArrays. + * See also DEFINE_XARRAY(). + */ +#define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) + void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); @@ -439,6 +452,7 @@ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -518,6 +532,93 @@ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) return entry; } +/** + * xa_alloc() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock. May sleep if + * the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock(xa); + + return err; +} + +/** + * xa_alloc_bh() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc_bh(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock_bh(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock_bh(xa); + + return err; +} + +/** + * xa_alloc_irq() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc_irq(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock_irq(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock_irq(xa); + + return err; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* -- cgit v1.2.3 From f32f004cddf86d63a9c42994bbce9f4e2f07c9fa Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jul 2018 15:42:46 -0400 Subject: ida: Convert to XArray Use the XA_TRACK_FREE ability to track which entries have a free bit, similarly to how it uses the radix tree's IDR_FREE tag. This eliminates the per-cpu ida_bitmap preload, and fixes the memory consumption regression I introduced when making the IDR able to store any pointer. Signed-off-by: Matthew Wilcox --- include/linux/idr.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 3ec8628ce17f..60daf34b625d 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -214,8 +214,7 @@ static inline void idr_preload_end(void) ++id, (entry) = idr_get_next((idr), &(id))) /* - * IDA - IDR based id allocator, use when translation from id to - * pointer isn't necessary. + * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ #define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) @@ -225,14 +224,14 @@ struct ida_bitmap { unsigned long bitmap[IDA_BITMAP_LONGS]; }; -DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap); - struct ida { - struct radix_tree_root ida_rt; + struct xarray xa; }; +#define IDA_INIT_FLAGS (XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC) + #define IDA_INIT(name) { \ - .ida_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER | GFP_NOWAIT), \ + .xa = XARRAY_INIT(name, IDA_INIT_FLAGS) \ } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) @@ -292,7 +291,7 @@ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) static inline void ida_init(struct ida *ida) { - INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT); + xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } #define ida_simple_get(ida, start, end, gfp) \ @@ -301,9 +300,6 @@ static inline void ida_init(struct ida *ida) static inline bool ida_is_empty(const struct ida *ida) { - return radix_tree_empty(&ida->ida_rt); + return xa_empty(&ida->xa); } - -/* in lib/radix-tree.c */ -int ida_pre_get(struct ida *ida, gfp_t gfp_mask); #endif /* __IDR_H__ */ -- cgit v1.2.3 From eb797a8ee0ab4cd03df556980ce7bf167cadaa50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Mar 2018 22:46:03 -0500 Subject: page cache: Rearrange address_space Change i_pages from a radix_tree_root to an xarray, convert the documentation into kernel-doc format and change the order of the elements to pack them better on 64-bit systems. Signed-off-by: Matthew Wilcox --- include/linux/fs.h | 46 +++++++++++++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c0b4a1c22ff..d126cad0f621 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -403,24 +403,40 @@ int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); +/** + * struct address_space - Contents of a cacheable, mappable object. + * @host: Owner, either the inode or the block_device. + * @i_pages: Cached pages. + * @gfp_mask: Memory allocation flags to use for allocating pages. + * @i_mmap_writable: Number of VM_SHARED mappings. + * @i_mmap: Tree of private and shared mappings. + * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. + * @nrpages: Number of page entries, protected by the i_pages lock. + * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. + * @writeback_index: Writeback starts here. + * @a_ops: Methods. + * @flags: Error bits and flags (AS_*). + * @wb_err: The most recent error which has occurred. + * @private_lock: For use by the owner of the address_space. + * @private_list: For use by the owner of the address_space. + * @private_data: For use by the owner of the address_space. + */ struct address_space { - struct inode *host; /* owner: inode, block_device */ - struct radix_tree_root i_pages; /* cached pages */ - atomic_t i_mmap_writable;/* count VM_SHARED mappings */ - struct rb_root_cached i_mmap; /* tree of private and shared mappings */ - struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ - /* Protected by the i_pages lock */ - unsigned long nrpages; /* number of total pages */ - /* number of shadow or DAX exceptional entries */ + struct inode *host; + struct xarray i_pages; + gfp_t gfp_mask; + atomic_t i_mmap_writable; + struct rb_root_cached i_mmap; + struct rw_semaphore i_mmap_rwsem; + unsigned long nrpages; unsigned long nrexceptional; - pgoff_t writeback_index;/* writeback starts here */ - const struct address_space_operations *a_ops; /* methods */ - unsigned long flags; /* error bits */ - spinlock_t private_lock; /* for use by the address_space */ - gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* for use by the address_space */ - void *private_data; /* ditto */ + pgoff_t writeback_index; + const struct address_space_operations *a_ops; + unsigned long flags; errseq_t wb_err; + spinlock_t private_lock; + struct list_head private_list; + void *private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but -- cgit v1.2.3 From 0d3f92966629e536b0c5c2355c1ada8e21c245f6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 21 Nov 2017 14:07:06 -0500 Subject: page cache: Convert hole search to XArray The page cache offers the ability to search for a miss in the previous or next N locations. Rather than teach the XArray about the page cache's definition of a miss, use xas_prev() and xas_next() to search the page array. This should be more efficient as it does not have to start the lookup from the top for each index. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b1bd2186e6d2..cf9ad413eee9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -241,9 +241,9 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) typedef int filler_t(void *, struct page *); -pgoff_t page_cache_next_hole(struct address_space *mapping, +pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); -pgoff_t page_cache_prev_hole(struct address_space *mapping, +pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); #define FGP_ACCESSED 0x00000001 -- cgit v1.2.3 From 74d609585d8bd6083bd9d75bc1fd2c0d3851bcc5 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 10:01:45 -0500 Subject: page cache: Add and replace pages using the XArray Use the XArray APIs to add and replace pages in the page cache. This removes two uses of the radix tree preload API and is significantly shorter code. It also removes the last user of __radix_tree_create() outside radix-tree.c itself, so make it static. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 3 --- include/linux/swap.h | 8 ++++++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 15388b7e38b9..d55de428a589 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -231,9 +231,6 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_create(struct radix_tree_root *, unsigned long index, - unsigned order, struct radix_tree_node **nodep, - void __rcu ***slotp); int __radix_tree_insert(struct radix_tree_root *, unsigned long index, unsigned order, void *); static inline int radix_tree_insert(struct radix_tree_root *root, diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..6ea50cf41b4c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -299,8 +299,12 @@ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); -/* Do not use directly, use workingset_lookup_update */ -void workingset_update_node(struct radix_tree_node *node); +/* Only track the nodes of mappings with shadow entries */ +void workingset_update_node(struct xa_node *node); +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + xas_set_update(xas, workingset_update_node); \ +} while (0) /* Returns workingset_update_node() if the mapping has shadow entries. */ #define workingset_lookup_update(mapping) \ -- cgit v1.2.3 From 3ece58a270cd1e5026282abe778bd50db7a11d08 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:00:33 -0400 Subject: page cache: Convert find_get_pages_contig to XArray There's no direct replacement for radix_tree_for_each_contig() in the XArray API as it's an unusual thing to do. Instead, open-code a loop using xas_next(). This removes the only user of radix_tree_for_each_contig() so delete the iterator from the API and the test suite code for it. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index d55de428a589..023e888e1163 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -522,23 +522,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) -/** - * radix_tree_for_each_contig - iterate over contiguous slots - * - * @slot: the void** variable for pointer to slot - * @root: the struct radix_tree_root pointer - * @iter: the struct radix_tree_iter pointer - * @start: iteration starting index - * - * @slot points to radix tree slot, @iter->index contains its index. - */ -#define radix_tree_for_each_contig(slot, root, iter, start) \ - for (slot = radix_tree_iter_init(iter, start) ; \ - slot || (slot = radix_tree_next_chunk(root, iter, \ - RADIX_TREE_ITER_CONTIG)) ; \ - slot = radix_tree_next_slot(slot, iter, \ - RADIX_TREE_ITER_CONTIG)) - /** * radix_tree_for_each_tagged - iterate over tagged slots * -- cgit v1.2.3 From a6906972fe67fb6f73ba04088f7897227fd1cd8f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:12:54 -0400 Subject: page cache; Convert find_get_pages_range_tag to XArray The 'end' parameter of the xas_for_each iterator avoids a useless iteration at the end of the range. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cf9ad413eee9..c9bbb9a05764 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -363,10 +363,10 @@ static inline unsigned find_get_pages(struct address_space *mapping, unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, int tag, unsigned int nr_pages, + pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages_tag(struct address_space *mapping, - pgoff_t *index, int tag, unsigned int nr_pages, + pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, -- cgit v1.2.3 From c1901cd33cf407d77a181f8dd4ffff98041ef480 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 23:56:04 -0400 Subject: page cache: Convert find_get_entries_tag to XArray Slightly shorter and simpler code. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c9bbb9a05764..226f96f0dee0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -373,7 +373,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, nr_pages, pages); } unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, - int tag, unsigned int nr_entries, + xa_mark_t tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices); struct page *grab_cache_page_write_begin(struct address_space *mapping, -- cgit v1.2.3 From ff9c745b81ff1e482167fd73558450e66ad43a33 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 11:41:23 -0500 Subject: mm: Convert page-writeback to XArray Includes moving mapping_tagged() to fs.h as a static inline, and changing it to return bool. Signed-off-by: Matthew Wilcox --- include/linux/fs.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d126cad0f621..e10278e4db66 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -483,15 +483,18 @@ struct block_device { 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 +#define PAGECACHE_TAG_WRITEBACK XA_MARK_1 +#define PAGECACHE_TAG_TOWRITE XA_MARK_2 + /* - * Radix-tree tags, for tagging dirty and writeback pages within the pagecache - * radix trees + * Returns true if any of the pages in the mapping are marked with the tag. */ -#define PAGECACHE_TAG_DIRTY 0 -#define PAGECACHE_TAG_WRITEBACK 1 -#define PAGECACHE_TAG_TOWRITE 2 - -int mapping_tagged(struct address_space *mapping, int tag); +static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) +{ + return xa_marked(&mapping->i_pages, tag); +} static inline void i_mmap_lock_write(struct address_space *mapping) { -- cgit v1.2.3 From a97e7904c0806309fd77103005bb7820c3f1c5e4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Nov 2017 14:24:59 -0500 Subject: mm: Convert workingset to XArray We construct an XA_STATE and use it to delete the node with xas_store() rather than adding a special function for this unique use case. Includes a test that simulates this usage for the test suite. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6ea50cf41b4c..112cebcf0402 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -306,15 +306,6 @@ void workingset_update_node(struct xa_node *node); xas_set_update(xas, workingset_update_node); \ } while (0) -/* Returns workingset_update_node() if the mapping has shadow entries. */ -#define workingset_lookup_update(mapping) \ -({ \ - radix_tree_update_node_t __helper = workingset_update_node; \ - if (dax_mapping(mapping) || shmem_mapping(mapping)) \ - __helper = NULL; \ - __helper; \ -}) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; -- cgit v1.2.3 From 4e17ec250fce0eba9b70a91c9622da2748a3ec50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 29 Nov 2017 08:32:39 -0500 Subject: mm: Convert delete_from_swap_cache to XArray Both callers of __delete_from_swap_cache have the swp_entry_t already, so pass that in to make constructing the XA_STATE easier. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 112cebcf0402..cb479bf5842e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -403,7 +403,7 @@ 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 *); +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 *); extern void free_pages_and_swap_cache(struct page **, int); @@ -557,7 +557,8 @@ static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, return -1; } -static inline void __delete_from_swap_cache(struct page *page) +static inline void __delete_from_swap_cache(struct page *page, + swp_entry_t entry) { } -- cgit v1.2.3 From 10bbd235859bf483f9a8a4ebe95463d700bae394 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 5 Dec 2017 17:30:38 -0500 Subject: pagevec: Use xa_mark_t Removes sparse warnings. Signed-off-by: Matthew Wilcox --- include/linux/pagevec.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 6dc456ac6136..081d934eda64 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -9,6 +9,8 @@ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H +#include + /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 @@ -40,12 +42,12 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec, unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag); + xa_mark_t tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag, unsigned max_pages); + xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, int tag) + struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } -- cgit v1.2.3 From 7b8d046fba91d62beb8a8f78244aaa3c23a60cdd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 22:13:06 -0500 Subject: shmem: Convert shmem_alloc_hugepage to XArray xa_find() is a slightly easier API to use than radix_tree_gang_lookup_slot() because it contains its own RCU locking. This commit removes the last user of radix_tree_gang_lookup_slot() so remove the function too. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 023e888e1163..8a4280bc350f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -147,12 +147,11 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup - * radix_tree_gang_lookup_slot * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * - * The first 8 functions are able to be called locklessly, using RCU. The + * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. @@ -263,9 +262,6 @@ void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, - void __rcu ***results, unsigned long *indices, - unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); -- cgit v1.2.3 From 1cf56f9d670b88b2e947a7ccdb8ba32e6477915d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 9 Apr 2018 16:24:45 -0400 Subject: radix tree: Remove radix_tree_update_node_t The only user of this functionality was the workingset code, and it's now been converted to the XArray. Remove __radix_tree_delete_node() entirely as it was also only used by the workingset code. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 8a4280bc350f..7513d0df984b 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -242,17 +242,12 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); -typedef void (*radix_tree_update_node_t)(struct radix_tree_node *); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, - void __rcu **slot, void *entry, - radix_tree_update_node_t update_node); + void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); -void __radix_tree_delete_node(struct radix_tree_root *, - struct radix_tree_node *, - radix_tree_update_node_t update_node); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); -- cgit v1.2.3 From 2956c6644bfd9aab9f6b21a12e1bd75876d9dd73 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 19 May 2018 16:47:47 -0400 Subject: radix tree: Remove split/join code radix_tree_split and radix_tree_join were never used upstream. Remove them; if they're needed in future they will be replaced by XArray equivalents. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7513d0df984b..44f9abdcb5ab 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -284,12 +284,6 @@ static inline void radix_tree_preload_end(void) preempt_enable(); } -int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t); -int radix_tree_split(struct radix_tree_root *, unsigned long index, - unsigned new_order); -int radix_tree_join(struct radix_tree_root *, unsigned long index, - unsigned new_order, void *); - void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); -- cgit v1.2.3 From 8cf2f98411e3a0865026a1061af637161b16d32b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 19 May 2018 16:47:47 -0400 Subject: radix tree: Remove radix_tree_maybe_preload_order This function was only used by the page cache which is now converted to the XArray. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 44f9abdcb5ab..664d50c5c2ff 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -259,7 +259,6 @@ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); -int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); -- cgit v1.2.3 From adb9d9c4ccb1ff0bf1d376e65f36aa5573c75c1a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 9 Apr 2018 16:52:21 -0400 Subject: radix tree: Remove radix_tree_clear_tags The page cache was the only user of this interface and it has now been converted to the XArray. Transform the test into a test of xas_init_marks(). Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 664d50c5c2ff..7b009af3bb1e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -252,8 +252,6 @@ void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); -void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, - void __rcu **slot); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -- cgit v1.2.3 From 372266ba0267803564824b1c09f1bb7f3f3fc761 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 18 Aug 2018 07:09:22 -0400 Subject: radix tree test suite: Convert tag_tagged_items to XArray The tag_tagged_items() function is supposed to test the page-writeback tagging code. Since that has been converted to the XArray, there's not much point in testing the radix tree's tagging code. This requires using the pthread mutex embedded in the xarray instead of an external lock, so remove the pthread mutexes which protect xarrays/radix trees. Also remove radix_tree_iter_tag_set() as this was the last user. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7b009af3bb1e..9a1460488163 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -264,8 +264,6 @@ void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); -void radix_tree_iter_tag_set(struct radix_tree_root *, - const struct radix_tree_iter *iter, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, -- cgit v1.2.3 From 0e9446c35a80931044b6d8d2d74a9cabd248539f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 15 Aug 2018 14:13:29 -0400 Subject: xarray: Add range store functionality This version of xa_store_range() really only supports load and store. Our only user only needs basic load and store functionality, so there's no need to do the extra work to support marking and overlapping stores correctly yet. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index e0b57af52e9b..d9514928ddac 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -292,6 +292,8 @@ void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int xa_reserve(struct xarray *, unsigned long index, gfp_t); +void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, + void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); -- cgit v1.2.3 From 3a08cd52c37c793ffc199f6fc2ecfc368e284b2d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 22 Sep 2018 16:14:30 -0400 Subject: radix tree: Remove multiorder support All users have now been converted to the XArray. Removing the support reduces code size and ensures new users will use the XArray instead. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 40 ++++------------------------------------ 1 file changed, 4 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 9a1460488163..06c4c7a6c09c 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -96,7 +96,6 @@ static inline bool radix_tree_empty(const struct radix_tree_root *root) * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot - * @shift: shift for the node that holds our slots * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is @@ -110,20 +109,8 @@ struct radix_tree_iter { unsigned long next_index; unsigned long tags; struct radix_tree_node *node; -#ifdef CONFIG_RADIX_TREE_MULTIORDER - unsigned int shift; -#endif }; -static inline unsigned int iter_shift(const struct radix_tree_iter *iter) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - return iter->shift; -#else - return 0; -#endif -} - /** * Radix-tree synchronization * @@ -230,13 +217,8 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_insert(struct radix_tree_root *, unsigned long index, - unsigned order, void *); -static inline int radix_tree_insert(struct radix_tree_root *root, - unsigned long index, void *entry) -{ - return __radix_tree_insert(root, index, 0, entry); -} +int radix_tree_insert(struct radix_tree_root *, unsigned long index, + void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); @@ -384,7 +366,7 @@ void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { - return iter->index + (slots << iter_shift(iter)); + return iter->index + slots; } /** @@ -409,20 +391,8 @@ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { - return (iter->next_index - iter->index) >> iter_shift(iter); -} - -#ifdef CONFIG_RADIX_TREE_MULTIORDER -void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags); -#else -/* Can't happen without sibling entries, but the compiler can't tell that */ -static inline void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags) -{ - return slot; + return iter->next_index - iter->index; } -#endif /** * radix_tree_next_slot - find next slot in chunk @@ -482,8 +452,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, return NULL; found: - if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot)))) - return __radix_tree_next_slot(slot, iter, flags); return slot; } -- cgit v1.2.3 From 94e6992bb560be8bffb47f287194adf070b57695 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 26 Sep 2018 18:03:16 +0200 Subject: libceph: bump CEPH_MSG_MAX_DATA_LEN If the read is large enough, we end up spinning in the messenger: libceph: osd0 192.168.122.1:6801 io error libceph: osd0 192.168.122.1:6801 io error libceph: osd0 192.168.122.1:6801 io error This is a receive side limit, so only reads were affected. Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 49c93b9308d7..68bb09c29ce8 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -81,7 +81,13 @@ struct ceph_options { #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) -#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) + +/* + * Handle the largest possible rbd object in one message. + * There is no limit on the size of cephfs objects, but it has to obey + * rsize and wsize mount options anyway. + */ +#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" -- cgit v1.2.3 From 24639ce56040a8ea890ad8836068c1ad8bd177c7 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 26 Sep 2018 19:12:07 +0200 Subject: libceph: osd_req_op_cls_init() doesn't need to take opcode Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 02096da01845..f3e828460c91 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -444,9 +444,8 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); -extern int osd_req_op_cls_init(struct ceph_osd_request *osd_req, - unsigned int which, u16 opcode, - const char *class, const char *method); +int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, + const char *class, const char *method); extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *name, const void *value, size_t size, u8 cmp_op, u8 cmp_mode); -- cgit v1.2.3 From 33165d472310262d8c79c7e4d1a17dc60cea7e35 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 28 Sep 2018 15:38:34 +0200 Subject: libceph: introduce ceph_pagelist_alloc() struct ceph_pagelist cannot be embedded into anything else because it has its own refcount. Merge allocation and initialization together. Signed-off-by: Ilya Dryomov --- include/linux/ceph/pagelist.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index d0223364349f..5dead8486fd8 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -23,16 +23,7 @@ struct ceph_pagelist_cursor { size_t room; /* room remaining to reset to */ }; -static inline void ceph_pagelist_init(struct ceph_pagelist *pl) -{ - INIT_LIST_HEAD(&pl->head); - pl->mapped_tail = NULL; - pl->length = 0; - pl->room = 0; - INIT_LIST_HEAD(&pl->free_list); - pl->num_pages_free = 0; - refcount_set(&pl->refcnt, 1); -} +struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags); extern void ceph_pagelist_release(struct ceph_pagelist *pl); -- cgit v1.2.3 From 0d9c1ab3be4c0187663096a6a084421d0a1e45c6 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 15 Oct 2018 17:38:23 +0200 Subject: libceph: preallocate message data items Currently message data items are allocated with ceph_msg_data_create() in setup_request_data() inside send_request(). send_request() has never been allowed to fail, so each allocation is followed by a BUG_ON: data = ceph_msg_data_create(...); BUG_ON(!data); It's been this way since support for multiple message data items was added in commit 6644ed7b7e04 ("libceph: make message data be a pointer") in 3.10. There is no reason to delay the allocation of message data items until the last possible moment and we certainly don't need a linked list of them as they are only ever appended to the end and never erased. Make ceph_msg_new2() take max_data_items and adapt the rest of the code. Reported-by: Jerry Lee Signed-off-by: Ilya Dryomov --- include/linux/ceph/messenger.h | 24 +++++------------------- include/linux/ceph/msgpool.h | 11 ++++++----- 2 files changed, 11 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index fc2b4491ee0a..800a2128d411 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -82,22 +82,6 @@ enum ceph_msg_data_type { CEPH_MSG_DATA_BVECS, /* data source/destination is a bio_vec array */ }; -static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) -{ - switch (type) { - case CEPH_MSG_DATA_NONE: - case CEPH_MSG_DATA_PAGES: - case CEPH_MSG_DATA_PAGELIST: -#ifdef CONFIG_BLOCK - case CEPH_MSG_DATA_BIO: -#endif /* CONFIG_BLOCK */ - case CEPH_MSG_DATA_BVECS: - return true; - default: - return false; - } -} - #ifdef CONFIG_BLOCK struct ceph_bio_iter { @@ -181,7 +165,6 @@ struct ceph_bvec_iter { } while (0) struct ceph_msg_data { - struct list_head links; /* ceph_msg->data */ enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK @@ -202,7 +185,6 @@ struct ceph_msg_data { struct ceph_msg_data_cursor { size_t total_resid; /* across all data items */ - struct list_head *data_head; /* = &ceph_msg->data */ struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ @@ -240,7 +222,9 @@ struct ceph_msg { struct ceph_buffer *middle; size_t data_length; - struct list_head data; + struct ceph_msg_data *data; + int num_data_items; + int max_data_items; struct ceph_msg_data_cursor cursor; struct ceph_connection *con; @@ -381,6 +365,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, void ceph_msg_data_add_bvecs(struct ceph_msg *msg, struct ceph_bvec_iter *bvec_pos); +struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, + gfp_t flags, bool can_fail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h index 76c98a512758..729cdf700eae 100644 --- a/include/linux/ceph/msgpool.h +++ b/include/linux/ceph/msgpool.h @@ -13,14 +13,15 @@ struct ceph_msgpool { mempool_t *pool; int type; /* preallocated message type */ int front_len; /* preallocated payload size */ + int max_data_items; }; -extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type, - int front_len, int size, bool blocking, - const char *name); +int ceph_msgpool_init(struct ceph_msgpool *pool, int type, + int front_len, int max_data_items, int size, + const char *name); extern void ceph_msgpool_destroy(struct ceph_msgpool *pool); -extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *, - int front_len); +struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len, + int max_data_items); extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *); #endif -- cgit v1.2.3 From 23ddf9bea900b4ce39e5707e1ddf66062cfe6d91 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Mon, 15 Oct 2018 16:45:58 +0100 Subject: libceph: support the RADOS copy-from operation Add support for performing remote object copies using the 'copy-from' operation. [ Add COPY_FROM to get_num_data_items(). ] Signed-off-by: Luis Henriques Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 17 +++++++++++++++++ include/linux/ceph/rados.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f3e828460c91..7a2af5034278 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,13 @@ struct ceph_osd_req_op { u64 expected_object_size; u64 expected_write_size; } alloc_hint; + struct { + u64 snapid; + u64 src_version; + u8 flags; + u32 src_fadvise_flags; + struct ceph_osd_data osd_data; + } copy_from; }; }; @@ -510,6 +517,16 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct timespec64 *mtime, struct page **pages, int nr_pages); +int ceph_osdc_copy_from(struct ceph_osd_client *osdc, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 dst_fadvise_flags, + u8 copy_from_flags); + /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index f1988387c5ad..3eb0e55665b4 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -410,6 +410,14 @@ enum { enum { CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ CEPH_OSD_OP_FLAG_FAILOK = 2, /* continue despite failure */ + CEPH_OSD_OP_FLAG_FADVISE_RANDOM = 0x4, /* the op is random */ + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL = 0x8, /* the op is sequential */ + CEPH_OSD_OP_FLAG_FADVISE_WILLNEED = 0x10,/* data will be accessed in + the near future */ + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED = 0x20,/* data will not be accessed + in the near future */ + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE = 0x40,/* data will be accessed only + once by this client */ }; #define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ @@ -431,6 +439,15 @@ enum { CEPH_OSD_CMPXATTR_MODE_U64 = 2 }; +enum { + CEPH_OSD_COPY_FROM_FLAG_FLUSH = 1, /* part of a flush operation */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_OVERLAY = 2, /* ignore pool overlay */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_CACHE = 4, /* ignore osd cache logic */ + CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to + * cloneid */ + CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */ +}; + enum { CEPH_OSD_WATCH_OP_UNWATCH = 0, CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1, @@ -497,6 +514,17 @@ struct ceph_osd_op { __le64 expected_object_size; __le64 expected_write_size; } __attribute__ ((packed)) alloc_hint; + struct { + __le64 snapid; + __le64 src_version; + __u8 flags; /* CEPH_OSD_COPY_FROM_FLAG_* */ + /* + * CEPH_OSD_OP_FLAG_FADVISE_*: fadvise flags + * for src object, flags for dest object are in + * ceph_osd_op::flags. + */ + __le32 src_fadvise_flags; + } __attribute__ ((packed)) copy_from; }; __le32 payload_len; } __attribute__ ((packed)); -- cgit v1.2.3 From 1227daa43bce1318ff6fb54e6cd862b4f60245c7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Oct 2018 17:20:35 -0700 Subject: pstore/ram: Clarify resource reservation labels When ramoops reserved a memory region in the kernel, it had an unhelpful label of "persistent_memory". When reading /proc/iomem, it would be repeated many times, did not hint that it was ramoops in particular, and didn't clarify very much about what each was used for: 400000000-407ffffff : Persistent Memory (legacy) 400000000-400000fff : persistent_memory 400001000-400001fff : persistent_memory ... 4000ff000-4000fffff : persistent_memory Instead, this adds meaningful labels for how the various regions are being used: 400000000-407ffffff : Persistent Memory (legacy) 400000000-400000fff : ramoops:dump(0/252) 400001000-400001fff : ramoops:dump(1/252) ... 4000fc000-4000fcfff : ramoops:dump(252/252) 4000fd000-4000fdfff : ramoops:console 4000fe000-4000fe3ff : ramoops:ftrace(0/3) 4000fe400-4000fe7ff : ramoops:ftrace(1/3) 4000fe800-4000febff : ramoops:ftrace(2/3) 4000fec00-4000fefff : ramoops:ftrace(3/3) 4000ff000-4000fffff : ramoops:pmsg Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) Tested-by: Sai Prakash Ranjan Tested-by: Guenter Roeck --- include/linux/pstore_ram.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index e6d226464838..602d64725222 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -46,6 +46,7 @@ struct persistent_ram_zone { phys_addr_t paddr; size_t size; void *vaddr; + char *label; struct persistent_ram_buffer *buffer; size_t buffer_size; u32 flags; @@ -65,7 +66,7 @@ struct persistent_ram_zone { struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype, u32 flags); + unsigned int memtype, u32 flags, char *label); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); -- cgit v1.2.3 From af033b2aa8a874fd5737fafe90d159136527b5b4 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 20 Sep 2018 20:05:00 +0800 Subject: f2fs: guarantee journalled quota data by checkpoint For journalled quota mode, let checkpoint to flush dquot dirty data and quota file data to guarntee persistence of all quota sysfile in last checkpoint, by this way, we can avoid corrupting quota sysfile when encountering SPO. The implementation is as below: 1. add a global state SBI_QUOTA_NEED_FLUSH to indicate that there is cached dquot metadata changes in quota subsystem, and later checkpoint should: a) flush dquot metadata into quota file. b) flush quota file to storage to keep file usage be consistent. 2. add a global state SBI_QUOTA_NEED_REPAIR to indicate that quota operation failed due to -EIO or -ENOSPC, so later, a) checkpoint will skip syncing dquot metadata. b) CP_QUOTA_NEED_FSCK_FLAG will be set in last cp pack to give a hint for fsck repairing. 3. add a global state SBI_QUOTA_SKIP_FLUSH, in checkpoint, if quota data updating is very heavy, it may cause hungtask in block_operation(). To avoid this, if our retry time exceed threshold, let's just skip flushing and retry in next checkpoint(). Signed-off-by: Weichao Guo Signed-off-by: Chao Yu [Jaegeuk Kim: avoid warnings and set fsck flag] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 8b9c7dc0260c..d7711048ef93 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -117,6 +117,7 @@ struct f2fs_super_block { * For checkpoint */ #define CP_DISABLED_FLAG 0x00001000 +#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From 876dcf2f3aaa0f68d437b368b93a4c4b81521191 Mon Sep 17 00:00:00 2001 From: Olivier Brunel Date: Sat, 20 Oct 2018 19:39:56 +0200 Subject: umh: Add command line to user mode helpers User mode helpers were spawned without a command line, and because an empty command line is used by many tools to identify processes as kernel threads, this could cause some issues. Notably during killing spree on shutdown, since such helper would then be skipped (i.e. not killed) which would result in the process remaining alive, and thus preventing unmouting of the rootfs (as experienced with the bpfilter umh). Fixes: 449325b52b7a ("umh: introduce fork_usermode_blob() helper") Signed-off-by: Olivier Brunel Signed-off-by: David S. Miller --- include/linux/umh.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/umh.h b/include/linux/umh.h index 5c812acbb80a..235f51b62c71 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -44,6 +44,7 @@ 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; struct file *pipe_from_umh; pid_t pid; -- cgit v1.2.3 From 39b27ad9c71cb72b07c9cd85191a8fe723e5b21a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 7 Aug 2018 18:11:22 +0200 Subject: mfd: sec-core: Add SPDX license identifiers Replace GPL v2.0+ license statements with SPDX license identifiers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/samsung/core.h | 11 ++--------- include/linux/mfd/samsung/irq.h | 10 ++-------- include/linux/mfd/samsung/rtc.h | 15 ++------------- include/linux/mfd/samsung/s2mpa01.h | 7 +------ include/linux/mfd/samsung/s2mps11.h | 9 +-------- include/linux/mfd/samsung/s2mps13.h | 14 +------------- include/linux/mfd/samsung/s2mps14.h | 14 +------------- include/linux/mfd/samsung/s2mps15.h | 11 +---------- include/linux/mfd/samsung/s2mpu02.h | 14 +------------- include/linux/mfd/samsung/s5m8763.h | 10 ++-------- include/linux/mfd/samsung/s5m8767.h | 10 ++-------- 11 files changed, 16 insertions(+), 109 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 28f4ae76271d..3ca17eb89aa2 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -1,14 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * core.h - * - * copyright (c) 2011 Samsung Electronics Co., Ltd + * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_SEC_CORE_H diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h index 667aa40486dd..6cfe4201a106 100644 --- a/include/linux/mfd/samsung/irq.h +++ b/include/linux/mfd/samsung/irq.h @@ -1,13 +1,7 @@ -/* irq.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2012 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_SEC_IRQ_H diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h index 9ed2871ea335..0204decfc9aa 100644 --- a/include/linux/mfd/samsung/rtc.h +++ b/include/linux/mfd/samsung/rtc.h @@ -1,18 +1,7 @@ -/* rtc.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_SEC_RTC_H diff --git a/include/linux/mfd/samsung/s2mpa01.h b/include/linux/mfd/samsung/s2mpa01.h index 2766108bca2f..0762e9de6f2f 100644 --- a/include/linux/mfd/samsung/s2mpa01.h +++ b/include/linux/mfd/samsung/s2mpa01.h @@ -1,12 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (c) 2013 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S2MPA01_H diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index 2c14eeca46f0..6e7668a389a1 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -1,14 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps11.h - * * Copyright (c) 2012 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S2MPS11_H diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h index 239e977ba45d..b96d8a11dcd3 100644 --- a/include/linux/mfd/samsung/s2mps13.h +++ b/include/linux/mfd/samsung/s2mps13.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps13.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPS13_H diff --git a/include/linux/mfd/samsung/s2mps14.h b/include/linux/mfd/samsung/s2mps14.h index c92f4782afb5..f4afa0cfc24f 100644 --- a/include/linux/mfd/samsung/s2mps14.h +++ b/include/linux/mfd/samsung/s2mps14.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps14.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPS14_H diff --git a/include/linux/mfd/samsung/s2mps15.h b/include/linux/mfd/samsung/s2mps15.h index 36d35287c3c0..eac6bf74b72e 100644 --- a/include/linux/mfd/samsung/s2mps15.h +++ b/include/linux/mfd/samsung/s2mps15.h @@ -1,16 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (c) 2015 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_MFD_S2MPS15_H diff --git a/include/linux/mfd/samsung/s2mpu02.h b/include/linux/mfd/samsung/s2mpu02.h index 47ae9bc583a7..76cd5380cf0f 100644 --- a/include/linux/mfd/samsung/s2mpu02.h +++ b/include/linux/mfd/samsung/s2mpu02.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mpu02.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPU02_H diff --git a/include/linux/mfd/samsung/s5m8763.h b/include/linux/mfd/samsung/s5m8763.h index e025418e5589..c534f086ca16 100644 --- a/include/linux/mfd/samsung/s5m8763.h +++ b/include/linux/mfd/samsung/s5m8763.h @@ -1,13 +1,7 @@ -/* s5m8763.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S5M8763_H diff --git a/include/linux/mfd/samsung/s5m8767.h b/include/linux/mfd/samsung/s5m8767.h index 243b58fec33d..704f8d80e96e 100644 --- a/include/linux/mfd/samsung/s5m8767.h +++ b/include/linux/mfd/samsung/s5m8767.h @@ -1,13 +1,7 @@ -/* s5m8767.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.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 (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S5M8767_H -- cgit v1.2.3 From d7d8d7a2405f8b6296660648e893fc3442269d81 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 7 Aug 2018 18:11:23 +0200 Subject: mfd: maxim: Add SPDX license identifiers Replace GPL v2.0+ license statements with SPDX license identifiers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/max14577-private.h | 11 +---------- include/linux/mfd/max14577.h | 11 +---------- include/linux/mfd/max77686-private.h | 15 +-------------- include/linux/mfd/max77686.h | 15 +-------------- include/linux/mfd/max77693-common.h | 6 +----- include/linux/mfd/max77693-private.h | 15 +-------------- include/linux/mfd/max77693.h | 15 +-------------- include/linux/mfd/max77843-private.h | 6 +----- include/linux/mfd/max8997-private.h | 15 +-------------- include/linux/mfd/max8997.h | 15 +-------------- include/linux/mfd/max8998-private.h | 15 +-------------- include/linux/mfd/max8998.h | 15 +-------------- 12 files changed, 12 insertions(+), 142 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h index df75234f979d..a21374f8ad26 100644 --- a/include/linux/mfd/max14577-private.h +++ b/include/linux/mfd/max14577-private.h @@ -1,19 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max14577-private.h - Common API for the Maxim 14577/77836 internal sub chip * * Copyright (C) 2014 Samsung Electrnoics * Chanwoo Choi * Krzysztof Kozlowski - * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __MAX14577_PRIVATE_H__ diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h index d81b52bb8bee..8b3ef891ba42 100644 --- a/include/linux/mfd/max14577.h +++ b/include/linux/mfd/max14577.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max14577.h - Driver for the Maxim 14577/77836 * @@ -5,16 +6,6 @@ * Chanwoo Choi * Krzysztof Kozlowski * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * This driver is based on max8997.h * * MAX14577 has MUIC, Charger devices. diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index 643dae777b43..833e578e051e 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -1,22 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77686-private.h - Voltage regulator driver for the Maxim 77686/802 * * Copyright (C) 2012 Samsung Electrnoics * Chiwoong Byun - * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX77686_PRIV_H diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h index d4b72d519115..d0fb510875e6 100644 --- a/include/linux/mfd/max77686.h +++ b/include/linux/mfd/max77686.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77686.h - Driver for the Maxim 77686/802 * * Copyright (C) 2012 Samsung Electrnoics * Chiwoong Byun * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8997.h * * MAX77686 has PMIC, RTC devices. diff --git a/include/linux/mfd/max77693-common.h b/include/linux/mfd/max77693-common.h index 095b121aa725..a5bce099f1ed 100644 --- a/include/linux/mfd/max77693-common.h +++ b/include/linux/mfd/max77693-common.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Common data shared between Maxim 77693 and 77843 drivers * * Copyright (C) 2015 Samsung Electronics - * - * 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 - * (at your option) any later version. */ #ifndef __LINUX_MFD_MAX77693_COMMON_H diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 3c7a63b98ad6..e798c81aec31 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77693-private.h - Voltage regulator driver for the Maxim 77693 * @@ -5,20 +6,6 @@ * SangYoung Son * * This program is not provided / owned by Maxim Integrated Products. - * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX77693_PRIV_H diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h index d450f687301b..c67c16ba8649 100644 --- a/include/linux/mfd/max77693.h +++ b/include/linux/mfd/max77693.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77693.h - Driver for the Maxim 77693 * @@ -6,20 +7,6 @@ * * This program is not provided / owned by Maxim Integrated Products. * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8997.h * * MAX77693 has PMIC, Charger, Flash LED, Haptic, MUIC devices. diff --git a/include/linux/mfd/max77843-private.h b/include/linux/mfd/max77843-private.h index b8908bf8d315..0bc7454c4dbe 100644 --- a/include/linux/mfd/max77843-private.h +++ b/include/linux/mfd/max77843-private.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Common variables for the Maxim MAX77843 driver * * Copyright (C) 2015 Samsung Electronics * Author: Jaewon Kim * Author: Beomho Seo - * - * 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 - * (at your option) any later version. */ #ifndef __MAX77843_PRIVATE_H_ diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h index 78c76cd4d37b..a10cd6945232 100644 --- a/include/linux/mfd/max8997-private.h +++ b/include/linux/mfd/max8997-private.h @@ -1,22 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8997-private.h - Voltage regulator driver for the Maxim 8997 * * Copyright (C) 2010 Samsung Electrnoics * MyungJoo Ham - * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8997_PRIV_H diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index cf815577bd68..3c4e920b4727 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8997.h - Driver for the Maxim 8997/8966 * * Copyright (C) 2009-2010 Samsung Electrnoics * MyungJoo Ham * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8998.h * * MAX8997 has PMIC, MUIC, HAPTIC, RTC, FLASH, and Fuel Gauge devices. diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h index d68ada502ff3..6deb5f577602 100644 --- a/include/linux/mfd/max8998-private.h +++ b/include/linux/mfd/max8998-private.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8998-private.h - Voltage regulator driver for the Maxim 8998 * * Copyright (C) 2009-2010 Samsung Electrnoics * Kyungmin Park * Marek Szyprowski - * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8998_PRIV_H diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index e3956a654cbc..061af220dcd3 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8998.h - Voltage regulator driver for the Maxim 8998 * * Copyright (C) 2009-2010 Samsung Electrnoics * Kyungmin Park * Marek Szyprowski - * - * 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 - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8998_H -- cgit v1.2.3 From 3d51ec93a564a0f87d1276f067732be904816a53 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 21 Aug 2018 19:16:12 +0200 Subject: mfd: Add ingenic-tcu.h header This header contains macros for the registers that are present in the regmap shared by all the drivers related to the TCU (Timer Counter Unit) of the Ingenic JZ47xx SoCs. Signed-off-by: Paul Cercueil Signed-off-by: Lee Jones --- include/linux/mfd/ingenic-tcu.h | 56 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/mfd/ingenic-tcu.h (limited to 'include/linux') diff --git a/include/linux/mfd/ingenic-tcu.h b/include/linux/mfd/ingenic-tcu.h new file mode 100644 index 000000000000..ab16ad283def --- /dev/null +++ b/include/linux/mfd/ingenic-tcu.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header file for the Ingenic JZ47xx TCU driver + */ +#ifndef __LINUX_MFD_INGENIC_TCU_H_ +#define __LINUX_MFD_INGENIC_TCU_H_ + +#include + +#define TCU_REG_WDT_TDR 0x00 +#define TCU_REG_WDT_TCER 0x04 +#define TCU_REG_WDT_TCNT 0x08 +#define TCU_REG_WDT_TCSR 0x0c +#define TCU_REG_TER 0x10 +#define TCU_REG_TESR 0x14 +#define TCU_REG_TECR 0x18 +#define TCU_REG_TSR 0x1c +#define TCU_REG_TFR 0x20 +#define TCU_REG_TFSR 0x24 +#define TCU_REG_TFCR 0x28 +#define TCU_REG_TSSR 0x2c +#define TCU_REG_TMR 0x30 +#define TCU_REG_TMSR 0x34 +#define TCU_REG_TMCR 0x38 +#define TCU_REG_TSCR 0x3c +#define TCU_REG_TDFR0 0x40 +#define TCU_REG_TDHR0 0x44 +#define TCU_REG_TCNT0 0x48 +#define TCU_REG_TCSR0 0x4c +#define TCU_REG_OST_DR 0xe0 +#define TCU_REG_OST_CNTL 0xe4 +#define TCU_REG_OST_CNTH 0xe8 +#define TCU_REG_OST_TCSR 0xec +#define TCU_REG_TSTR 0xf0 +#define TCU_REG_TSTSR 0xf4 +#define TCU_REG_TSTCR 0xf8 +#define TCU_REG_OST_CNTHBUF 0xfc + +#define TCU_TCSR_RESERVED_BITS 0x3f +#define TCU_TCSR_PARENT_CLOCK_MASK 0x07 +#define TCU_TCSR_PRESCALE_LSB 3 +#define TCU_TCSR_PRESCALE_MASK 0x38 + +#define TCU_TCSR_PWM_SD BIT(9) /* 0: Shutdown abruptly 1: gracefully */ +#define TCU_TCSR_PWM_INITL_HIGH BIT(8) /* Sets the initial output level */ +#define TCU_TCSR_PWM_EN BIT(7) /* PWM pin output enable */ + +#define TCU_WDT_TCER_TCEN BIT(0) /* Watchdog timer enable */ + +#define TCU_CHANNEL_STRIDE 0x10 +#define TCU_REG_TDFRc(c) (TCU_REG_TDFR0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TDHRc(c) (TCU_REG_TDHR0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TCNTc(c) (TCU_REG_TCNT0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TCSRc(c) (TCU_REG_TCSR0 + ((c) * TCU_CHANNEL_STRIDE)) + +#endif /* __LINUX_MFD_INGENIC_TCU_H_ */ -- cgit v1.2.3 From 6360e40f421fba0a11bbabaa211c9c22c5cf5e61 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 28 Aug 2018 09:41:58 +0100 Subject: mfd: madera: Remove unused forward reference The madera_irqchip_pdata struct was replaced by the irq_flags member of struct madera_pdata so the forward reference is obsolete. Signed-off-by: Richard Fitzgerald 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 0b311f39c8f4..8dc852402dbb 100644 --- a/include/linux/mfd/madera/pdata.h +++ b/include/linux/mfd/madera/pdata.h @@ -24,7 +24,6 @@ struct gpio_desc; struct pinctrl_map; -struct madera_irqchip_pdata; struct madera_codec_pdata; /** -- cgit v1.2.3 From 55143439b7b501882bea9d95a54adfe00ffc79a3 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 28 Aug 2018 17:02:40 -0300 Subject: mfd: mc13xxx-core: Fix PMIC shutdown when reading ADC values When trying to read any MC13892 ADC channel on a imx51-babbage board: The MC13892 PMIC shutdowns completely. After debugging this issue and comparing the MC13892 and MC13783 initializations done in the vendor kernel, it was noticed that the CHRGRAWDIV bit of the ADC0 register was not being set. This bit is set by default after power on, but the driver was clearing it. After setting this bit it is possible to read the ADC values correctly. Signed-off-by: Fabio Estevam Tested-by: Chris Healy Signed-off-by: Lee Jones --- include/linux/mfd/mc13xxx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h index 54a3cd808f9e..2ad9bdc0a5ec 100644 --- a/include/linux/mfd/mc13xxx.h +++ b/include/linux/mfd/mc13xxx.h @@ -249,6 +249,7 @@ struct mc13xxx_platform_data { #define MC13XXX_ADC0_TSMOD0 (1 << 12) #define MC13XXX_ADC0_TSMOD1 (1 << 13) #define MC13XXX_ADC0_TSMOD2 (1 << 14) +#define MC13XXX_ADC0_CHRGRAWDIV (1 << 15) #define MC13XXX_ADC0_ADINC1 (1 << 16) #define MC13XXX_ADC0_ADINC2 (1 << 17) -- cgit v1.2.3 From 9f8ddee1dab836ca758ca8fc555ab5a3aaa5d3fd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 19:52:52 +0300 Subject: mfd: intel_soc_pmic_bxtwc: Chain power button IRQs as well Power button IRQ actually has a second level of interrupts to distinguish between UI and POWER buttons. Moreover, current implementation looks awkward in approach to handle second level IRQs by first level related IRQ chip. To address above issues, split power button IRQ to be chained as well. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Lee Jones --- include/linux/mfd/intel_soc_pmic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 5aacdb017a9f..806a4f095312 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -25,6 +25,7 @@ struct intel_soc_pmic { int irq; struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; + struct regmap_irq_chip_data *irq_chip_data_pwrbtn; struct regmap_irq_chip_data *irq_chip_data_tmu; struct regmap_irq_chip_data *irq_chip_data_bcu; struct regmap_irq_chip_data *irq_chip_data_adc; -- cgit v1.2.3 From 26c7e05a69d3843abb0e5389e7f538cd175c0f09 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 19:52:54 +0300 Subject: mfd: Convert Intel PMIC drivers to use SPDX identifier 1;5201;0c Reduce size of duplicated comments by switching to use SPDX identifier. No functional change. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Lee Jones --- include/linux/mfd/intel_msic.h | 7 ++----- include/linux/mfd/intel_soc_pmic.h | 12 ++---------- include/linux/mfd/intel_soc_pmic_bxtwc.h | 10 +--------- 3 files changed, 5 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/intel_msic.h b/include/linux/mfd/intel_msic.h index 439a7a617bc9..317e8608cf41 100644 --- a/include/linux/mfd/intel_msic.h +++ b/include/linux/mfd/intel_msic.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * include/linux/mfd/intel_msic.h - Core interface for Intel MSIC + * Core interface for Intel MSIC * * Copyright (C) 2011, Intel Corporation * Author: Mika Westerberg - * - * 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. */ #ifndef __LINUX_MFD_INTEL_MSIC_H__ diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 806a4f095312..ed1dfba5e5f9 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * intel_soc_pmic.h - Intel SoC PMIC Driver + * Intel SoC PMIC Driver * * Copyright (C) 2012-2014 Intel Corporation. All rights reserved. * - * 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 in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Author: Yang, Bin * Author: Zhu, Lejun */ diff --git a/include/linux/mfd/intel_soc_pmic_bxtwc.h b/include/linux/mfd/intel_soc_pmic_bxtwc.h index 0c351bc85d2d..9be566cc58c6 100644 --- a/include/linux/mfd/intel_soc_pmic_bxtwc.h +++ b/include/linux/mfd/intel_soc_pmic_bxtwc.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Header file for Intel Broxton Whiskey Cove PMIC * * Copyright (C) 2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef __INTEL_BXTWC_H__ -- cgit v1.2.3 From efddff27c886e729a7f84a7205bd84d7d4af7336 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 5 Sep 2018 13:54:07 +0200 Subject: mfd: max8997: Enale irq-wakeup unconditionally IRQ wake up support for MAX8997 driver was initially configured by respective property in pdata. However, after the driver conversion to device-tree, setting it was left as 'todo'. Nowadays most of other PMIC MFD drivers initialized from device-tree assume that they can be an irq wakeup source, so enable it also for MAX8997. This fixes support for wakeup from MAX8997 RTC alarm. Signed-off-by: Marek Szyprowski Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/max8997.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index 3c4e920b4727..e955e2f0a2cc 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -165,7 +165,6 @@ struct max8997_led_platform_data { struct max8997_platform_data { /* IRQ */ int ono; - int wakeup; /* ---- PMIC ---- */ struct max8997_regulator_data *regulators; -- cgit v1.2.3 From 7a6a395b16c3fdcd2ede2b0ce4bf63f6dafc1fea Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Tue, 11 Sep 2018 23:01:33 +0200 Subject: mfd: ti-lmu: Switch to GPIOD Use new descriptor based API instead of the legacy one. Signed-off-by: Sebastian Reichel Signed-off-by: Pavel Machek Signed-off-by: Lee Jones --- include/linux/mfd/ti-lmu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti-lmu.h b/include/linux/mfd/ti-lmu.h index 09d5f30384e5..1ef51ed36be5 100644 --- a/include/linux/mfd/ti-lmu.h +++ b/include/linux/mfd/ti-lmu.h @@ -16,6 +16,7 @@ #include #include #include +#include /* Notifier event */ #define LMU_EVENT_MONITOR_DONE 0x01 @@ -81,7 +82,7 @@ enum lm363x_regulator_id { struct ti_lmu { struct device *dev; struct regmap *regmap; - int en_gpio; + struct gpio_desc *en_gpio; struct blocking_notifier_head notifier; }; #endif -- cgit v1.2.3 From 07d02a67b7faae56e184f6c35f78de47f06da37f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Oct 2018 13:28:26 -0400 Subject: SUNRPC: Simplify lookup code We no longer need to worry about whether or not the entry is hashed in order to figure out if the contents are valid. We only care whether or not the refcount is non-zero. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 2c97a3933ef9..a7fc8f5a2dad 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -206,11 +206,11 @@ bool rpcauth_cred_key_to_expire(struct rpc_auth *, struct rpc_cred *); char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline -struct rpc_cred * get_rpccred(struct rpc_cred *cred) +struct rpc_cred *get_rpccred(struct rpc_cred *cred) { - if (cred != NULL) - atomic_inc(&cred->cr_count); - return cred; + if (cred != NULL && atomic_inc_not_zero(&cred->cr_count)) + return cred; + return NULL; } /** @@ -226,9 +226,7 @@ struct rpc_cred * get_rpccred(struct rpc_cred *cred) static inline struct rpc_cred * get_rpccred_rcu(struct rpc_cred *cred) { - if (atomic_inc_not_zero(&cred->cr_count)) - return cred; - return NULL; + return get_rpccred(cred); } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 79b181810285a6b9b7a1aed25c365c9e1782e22a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Oct 2018 10:34:31 -0400 Subject: SUNRPC: Convert auth creds to use refcount_t Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a7fc8f5a2dad..a71d4bd191e7 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -67,7 +67,7 @@ struct rpc_cred { const struct rpc_credops *cr_ops; unsigned long cr_expire; /* when to gc */ unsigned long cr_flags; /* various flags */ - atomic_t cr_count; /* ref count */ + refcount_t cr_count; /* ref count */ kuid_t cr_uid; @@ -208,7 +208,7 @@ char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline struct rpc_cred *get_rpccred(struct rpc_cred *cred) { - if (cred != NULL && atomic_inc_not_zero(&cred->cr_count)) + if (cred != NULL && refcount_inc_not_zero(&cred->cr_count)) return cred; return NULL; } -- cgit v1.2.3 From 331bc71cb1751d78f6807ad8e6162b07c67cdd1b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Oct 2018 10:40:29 -0400 Subject: SUNRPC: Convert the auth cred cache to use refcount_t Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a71d4bd191e7..c4db9424b63b 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -100,7 +100,7 @@ struct rpc_auth { * differ from the flavor in * au_ops->au_flavor in gss * case) */ - atomic_t au_count; /* Reference counter */ + refcount_t au_count; /* Reference counter */ struct rpc_cred_cache * au_credcache; /* per-flavor data */ -- cgit v1.2.3 From 00e23707442a75b404392cef1405ab4fd498de6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 22 Oct 2018 13:07:28 +0100 Subject: iov_iter: Use accessor function Use accessor functions to access an iterator's type and direction. This allows for the possibility of using some other method of determining the type of iterator than if-chains with bitwise-AND conditions. Signed-off-by: David Howells --- include/linux/uio.h | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 422b1c01ee0d..fcabc959c794 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -21,7 +21,7 @@ struct kvec { size_t iov_len; }; -enum { +enum iter_type { ITER_IOVEC = 0, ITER_KVEC = 2, ITER_BVEC = 4, @@ -47,6 +47,36 @@ struct iov_iter { }; }; +static inline enum iter_type iov_iter_type(const struct iov_iter *i) +{ + return i->type & ~(READ | WRITE); +} + +static inline bool iter_is_iovec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_IOVEC; +} + +static inline bool iov_iter_is_kvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_KVEC; +} + +static inline bool iov_iter_is_bvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_BVEC; +} + +static inline bool iov_iter_is_pipe(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_PIPE; +} + +static inline unsigned char iov_iter_rw(const struct iov_iter *i) +{ + return i->type & (READ | WRITE); +} + /* * Total number of bytes covered by an iovec. * @@ -74,7 +104,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) } #define iov_for_each(iov, iter, start) \ - if (!((start).type & (ITER_BVEC | ITER_PIPE))) \ + if (iov_iter_type(start) == ITER_IOVEC || \ + iov_iter_type(start) == ITER_KVEC) \ for (iter = (start); \ (iter).count && \ ((iov = iov_iter_iovec(&(iter))), 1); \ @@ -202,19 +233,6 @@ static inline size_t iov_iter_count(const struct iov_iter *i) return i->count; } -static inline bool iter_is_iovec(const struct iov_iter *i) -{ - return !(i->type & (ITER_BVEC | ITER_KVEC | ITER_PIPE)); -} - -/* - * Get one of READ or WRITE out of iter->type without any other flags OR'd in - * with it. - * - * The ?: is just for type safety. - */ -#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & (READ | WRITE)) - /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value -- cgit v1.2.3 From aa563d7bca6e882ec2bdae24603c8f016401a144 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 20 Oct 2018 00:57:56 +0100 Subject: iov_iter: Separate type from direction and use accessor functions In the iov_iter struct, separate the iterator type from the iterator direction and use accessor functions to access them in most places. Convert a bunch of places to use switch-statements to access them rather then chains of bitwise-AND statements. This makes it easier to add further iterator types. Also, this can be more efficient as to implement a switch of small contiguous integers, the compiler can use ~50% fewer compare instructions than it has to use bitwise-and instructions. Further, cease passing the iterator type into the iterator setup function. The iterator function can set that itself. Only the direction is required. Signed-off-by: David Howells --- include/linux/uio.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index fcabc959c794..3d8f1acc142c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -29,7 +29,7 @@ enum iter_type { }; struct iov_iter { - int type; + unsigned int type; size_t iov_offset; size_t count; union { @@ -212,13 +212,13 @@ size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); -void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); -void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); -void iov_iter_pipe(struct iov_iter *i, int direction, struct pipe_inode_info *pipe, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -- cgit v1.2.3 From 9ea9ce0427aab02a2fd88fc608267cf6952119f1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 20 Oct 2018 00:57:56 +0100 Subject: iov_iter: Add I/O discard iterator Add a new iterator, ITER_DISCARD, that can only be used in READ mode and just discards any data copied to it. This is useful in a network filesystem for discarding any unwanted data sent by a server. Signed-off-by: David Howells --- include/linux/uio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 3d8f1acc142c..55ce99ddb912 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -26,6 +26,7 @@ enum iter_type { ITER_KVEC = 2, ITER_BVEC = 4, ITER_PIPE = 8, + ITER_DISCARD = 16, }; struct iov_iter { @@ -72,6 +73,11 @@ static inline bool iov_iter_is_pipe(const struct iov_iter *i) return iov_iter_type(i) == ITER_PIPE; } +static inline bool iov_iter_is_discard(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_DISCARD; +} + static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->type & (READ | WRITE); @@ -220,6 +226,7 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_ unsigned long nr_segs, size_t count); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); +void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, -- cgit v1.2.3 From 721fb6fbfd2132164c2e8777cc837f9b2c1794dc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 17 Oct 2018 13:07:05 +0200 Subject: fsnotify: Fix busy inodes during unmount Detaching of mark connector from fsnotify_put_mark() can race with unmounting of the filesystem like: CPU1 CPU2 fsnotify_put_mark() spin_lock(&conn->lock); ... inode = fsnotify_detach_connector_from_object(conn) spin_unlock(&conn->lock); generic_shutdown_super() fsnotify_unmount_inodes() sees connector detached for inode -> nothing to do evict_inode() barfs on pending inode reference iput(inode); Resulting in "Busy inodes after unmount" message and possible kernel oops. Make fsnotify_unmount_inodes() properly wait for outstanding inode references from detached connectors. Note that the accounting of outstanding inode references in the superblock can cause some cacheline contention on the counter. OTOH it happens only during deletion of the last notification mark from an inode (or during unlinking of watched inode) and that is not too bad. I have measured time to create & delete inotify watch 100000 times from 64 processes in parallel (each process having its own inotify group and its own file on a shared superblock) on a 64 CPU machine. Average and standard deviation of 15 runs look like: Avg Stddev Vanilla 9.817400 0.276165 Fixed 9.710467 0.228294 So there's no statistically significant difference. Fixes: 6b3f05d24d35 ("fsnotify: Detach mark from object list when last reference is dropped") CC: stable@vger.kernel.org Signed-off-by: Jan Kara --- 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 6da94deb957f..00b23b21e78a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1437,6 +1437,9 @@ struct super_block { /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; + /* Pending fsnotify inode refs */ + atomic_long_t s_fsnotify_inode_refs; + /* Being remounted read-only */ int s_readonly_remount; -- cgit v1.2.3 From a7fe5190c03f8137ef08db84a58dd4daf2c4785d Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 4 Oct 2018 14:04:03 +0200 Subject: cpuidle: menu: Remove get_loadavg() from the performance multiplier The function get_loadavg() returns almost always zero. To be more precise, statistically speaking for a total of 1023379 times passing in the function, the load is equal to zero 1020728 times, greater than 100, 610 times, the remaining is between 0 and 5. In 2011, the get_loadavg() was removed from the Android tree because of the above [1]. At this time, the load was: unsigned long this_cpu_load(void) { struct rq *this = this_rq(); return this->cpu_load[0]; } In 2014, the code was changed by commit 372ba8cb46b2 (cpuidle: menu: Lookup CPU runqueues less) and the load is: void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) { struct rq *rq = this_rq(); *nr_waiters = atomic_read(&rq->nr_iowait); *load = rq->load.weight; } with the same result. Both measurements show using the load in this code path does no matter anymore. Removing it. [1] https://android.googlesource.com/kernel/common/+/4dedd9f124703207895777ac6e91dacde0f7cc17 Signed-off-by: Daniel Lezcano Acked-by: Mel Gorman Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rafael J. Wysocki --- include/linux/sched/stat.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index 04f1321d14c4..f30954cc059d 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -20,7 +20,6 @@ extern unsigned long nr_running(void); extern bool single_task_running(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); -extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); static inline int sched_info_on(void) { -- cgit v1.2.3 From a91e138022bc29b5d2bbc56b41de3e0db6261e28 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:43 +0900 Subject: block: Introduce blkdev_nr_zones() helper Introduce the blkdev_nr_zones() helper function to get the total number of zones of a zoned block device. This number is always 0 for a regular block device (q->limits.zoned == BLK_ZONED_NONE case). Replace hard-coded number of zones calculation in dmz_get_zoned_device() with a call to this helper. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d423721b327..ca5fdc1b7745 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -401,6 +401,7 @@ struct blk_zone_report_hdr { u8 padding[60]; }; +extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, unsigned int *nr_zones, gfp_t gfp_mask); @@ -414,6 +415,10 @@ extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blkdev_nr_zones(struct block_device *bdev) +{ + return 0; +} static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From 965b652e901886ea54f93c60027b5be76328d958 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:48 +0900 Subject: block: Expose queue nr_zones in sysfs Expose through sysfs the nr_zones field of struct request_queue. Exposing this value helps in debugging disk issues as well as facilitating scripts based use of the disk (e.g. blktests). For zoned block devices, the nr_zones field indicates the total number of zones of the device calculated using the known disk capacity and zone size. This number of zones is always 0 for regular block devices. Since nr_zones is defined conditionally with CONFIG_BLK_DEV_ZONED, introduce the blk_queue_nr_zones() function to return the correct value for any device, regardless if CONFIG_BLK_DEV_ZONED is set. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal 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 ca5fdc1b7745..6bb845f9601a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -811,6 +811,11 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) } #ifdef CONFIG_BLK_DEV_ZONED +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return blk_queue_is_zoned(q) ? q->nr_zones : 0; +} + static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { @@ -826,6 +831,11 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return false; return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); } +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) -- cgit v1.2.3 From e76239a3748c90a8b0e197f8f4544a8ce52f126e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 Oct 2018 19:08:49 +0900 Subject: block: add a report_zones method Dispatching a report zones command through the request queue is a major pain due to the command reply payload rewriting necessary. Given that blkdev_report_zones() is executing everything synchronously, implement report zones as a block device file operation instead, allowing major simplification of the code in many places. sd, null-blk, dm-linear and dm-flakey being the only block device drivers supporting exposing zoned block devices, these drivers are modified to provide the device side implementation of the report_zones() block device file operation. For device mappers, a new report_zones() target type operation is defined so that the upper block layer calls blkdev_report_zones() can be propagated down to the underlying devices of the dm targets. Implementation for this new operation is added to the dm-linear and dm-flakey targets. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig [Damien] * Changed method block_device argument to gendisk * Various bug fixes and improvements * Added support for null_blk, dm-linear and dm-flakey. Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 -- include/linux/blkdev.h | 8 +++----- include/linux/device-mapper.h | 12 ++++++++++-- 3 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9578c7ab1eb6..093a818c5b68 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -283,8 +283,6 @@ enum req_opf { REQ_OP_FLUSH = 2, /* discard sectors */ REQ_OP_DISCARD = 3, - /* get zone information */ - REQ_OP_ZONE_REPORT = 4, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, /* seset a zone write pointer */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6bb845f9601a..51fe6472ce02 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -396,11 +396,6 @@ struct queue_limits { #ifdef CONFIG_BLK_DEV_ZONED -struct blk_zone_report_hdr { - unsigned int nr_zones; - u8 padding[60]; -}; - extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, @@ -1867,6 +1862,9 @@ struct block_device_operations { int (*getgeo)(struct block_device *, struct hd_geometry *); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); + int (*report_zones)(struct gendisk *, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 6fb0808e87c8..a23b396a8edc 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -92,6 +92,11 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); +typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, + struct blk_zone *zones, + unsigned int *nr_zones, + gfp_t gfp_mask); + /* * These iteration functions are typically used to check (and combine) * properties of underlying devices. @@ -180,6 +185,9 @@ struct target_type { dm_status_fn status; dm_message_fn message; dm_prepare_ioctl_fn prepare_ioctl; +#ifdef CONFIG_BLK_DEV_ZONED + dm_report_zones_fn report_zones; +#endif dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; @@ -420,8 +428,8 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, - sector_t start); +void dm_remap_zone_report(struct dm_target *ti, sector_t start, + struct blk_zone *zones, unsigned int *nr_zones); union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); -- cgit v1.2.3 From bf5054569653c491ece544cc7ee333ae53b47121 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:50 +0900 Subject: block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 51fe6472ce02..4293dc1cd160 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -402,6 +402,7 @@ extern int blkdev_report_zones(struct block_device *bdev, unsigned int *nr_zones, gfp_t gfp_mask); extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); @@ -414,6 +415,12 @@ static inline unsigned int blkdev_nr_zones(struct block_device *bdev) { return 0; } + +static inline int blk_revalidate_disk_zones(struct gendisk *disk) +{ + return 0; +} + static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From ede95a63b5e84ddeea6b0c473b36ab8bfd8c6ce3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 23 Oct 2018 01:11:04 +0200 Subject: bpf: add bpf_jit_limit knob to restrict unpriv allocations Rick reported that the BPF JIT could potentially fill the entire module space with BPF programs from unprivileged users which would prevent later attempts to load normal kernel modules or privileged BPF programs, for example. If JIT was enabled but unsuccessful to generate the image, then before commit 290af86629b2 ("bpf: introduce BPF_JIT_ALWAYS_ON config") we would always fall back to the BPF interpreter. Nowadays in the case where the CONFIG_BPF_JIT_ALWAYS_ON could be set, then the load will abort with a failure since the BPF interpreter was compiled out. Add a global limit and enforce it for unprivileged users such that in case of BPF interpreter compiled out we fail once the limit has been reached or we fall back to BPF interpreter earlier w/o using module mem if latter was compiled in. In a next step, fair share among unprivileged users can be resolved in particular for the case where we would fail hard once limit is reached. Fixes: 290af86629b2 ("bpf: introduce BPF_JIT_ALWAYS_ON config") Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64") Co-Developed-by: Rick Edgecombe Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: Eric Dumazet Cc: Jann Horn Cc: Kees Cook Cc: LKML Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 91b4c934f02e..de629b706d1d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -854,6 +854,7 @@ bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; +extern int bpf_jit_limit; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); -- cgit v1.2.3 From 70025f84e5b79627a6739533c4fe7cef5b605886 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 9 Oct 2018 17:46:51 +0100 Subject: KEYS: Provide key type operations for asymmetric key ops [ver #2] Provide five new operations in the key_type struct that can be used to provide access to asymmetric key operations. These will be implemented for the asymmetric key type in a later patch and may refer to a key retained in RAM by the kernel or a key retained in crypto hardware. int (*asym_query)(const struct kernel_pkey_params *params, struct kernel_pkey_query *info); int (*asym_eds_op)(struct kernel_pkey_params *params, const void *in, void *out); int (*asym_verify_signature)(struct kernel_pkey_params *params, const void *in, const void *in2); Since encrypt, decrypt and sign are identical in their interfaces, they're rolled together in the asym_eds_op() operation and there's an operation ID in the params argument to distinguish them. Verify is different in that we supply the data and the signature instead and get an error value (or 0) as the only result on the expectation that this may well be how a hardware crypto device may work. Signed-off-by: David Howells Tested-by: Marcel Holtmann Reviewed-by: Marcel Holtmann Reviewed-by: Denis Kenzior Tested-by: Denis Kenzior Signed-off-by: James Morris --- include/linux/key-type.h | 11 +++++++++++ include/linux/keyctl.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 include/linux/keyctl.h (limited to 'include/linux') diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 05d8fb5a06c4..bc9af551fc83 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -17,6 +17,9 @@ #ifdef CONFIG_KEYS +struct kernel_pkey_query; +struct kernel_pkey_params; + /* * key under-construction record * - passed to the request_key actor if supplied @@ -155,6 +158,14 @@ struct key_type { */ struct key_restriction *(*lookup_restriction)(const char *params); + /* Asymmetric key accessor functions. */ + int (*asym_query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info); + int (*asym_eds_op)(struct kernel_pkey_params *params, + const void *in, void *out); + int (*asym_verify_signature)(struct kernel_pkey_params *params, + const void *in, const void *in2); + /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h new file mode 100644 index 000000000000..c7c48c79ce0e --- /dev/null +++ b/include/linux/keyctl.h @@ -0,0 +1,46 @@ +/* keyctl kernel bits + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef __LINUX_KEYCTL_H +#define __LINUX_KEYCTL_H + +#include + +struct kernel_pkey_query { + __u32 supported_ops; /* Which ops are supported */ + __u32 key_size; /* Size of the key in bits */ + __u16 max_data_size; /* Maximum size of raw data to sign in bytes */ + __u16 max_sig_size; /* Maximum size of signature in bytes */ + __u16 max_enc_size; /* Maximum size of encrypted blob in bytes */ + __u16 max_dec_size; /* Maximum size of decrypted blob in bytes */ +}; + +enum kernel_pkey_operation { + kernel_pkey_encrypt, + kernel_pkey_decrypt, + kernel_pkey_sign, + kernel_pkey_verify, +}; + +struct kernel_pkey_params { + struct key *key; + const char *encoding; /* Encoding (eg. "oaep" or "raw" for none) */ + const char *hash_algo; /* Digest algorithm used (eg. "sha1") or NULL if N/A */ + char *info; /* Modified info string to be released later */ + __u32 in_len; /* Input data size */ + union { + __u32 out_len; /* Output buffer size (enc/dec/sign) */ + __u32 in2_len; /* 2nd input data size (verify) */ + }; + enum kernel_pkey_operation op : 8; +}; + +#endif /* __LINUX_KEYCTL_H */ -- cgit v1.2.3 From 4d54954a197175c0dcb3c82af0c0740d0c5f827a Mon Sep 17 00:00:00 2001 From: Sebastien Boisvert Date: Fri, 26 Oct 2018 15:02:23 -0700 Subject: include/linux/pfn_t.h: force '~' to be parsed as an unary operator Tracing the event "fs_dax:dax_pmd_insert_mapping" with perf produces this warning: [fs_dax:dax_pmd_insert_mapping] unknown op '~' It is printed in process_op (tools/lib/traceevent/event-parse.c) because '~' is parsed as a binary operator. perf reads the format of fs_dax:dax_pmd_insert_mapping ("print fmt") from /sys/kernel/debug/tracing/events/fs_dax/dax_pmd_insert_mapping/format . The format contains: ~(((u64) ~(~(((1UL) << 12)-1))) ^ \ interpreted as a binary operator by process_op(). This part is generated in the declaration of the event class dax_pmd_insert_mapping_class in include/trace/events/fs_dax.h : __print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|", PFN_FLAGS_TRACE), This patch adds a pair of parentheses in the declaration of PFN_FLAGS_MASK to make sure that '~' is parsed as a unary operator by perf. The part of the format that was problematic is now: ~(((u64) (~(~(((1UL) << 12)-1)))) Now, all the '~' are parsed as unary operators. Link: http://lkml.kernel.org/r/20181021145939.8760-1-sebhtml@videotron.qc.ca Signed-off-by: Sebastien Boisvert Acked-by: Dan Williams Cc: "Steven Rostedt (VMware)" Cc: Arnaldo Carvalho de Melo Cc: "Tzvetomir Stoyanov (VMware)" Cc: Namhyung Kim Cc: Ross Zwisler Cc: Elenie Godzaridis Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 21713dc14ce2..673546ba7342 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -10,7 +10,7 @@ * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver */ -#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) +#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) -- cgit v1.2.3 From 74f213ea25b99fddcf34cbe07dabdb01136bcd86 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:02:27 -0700 Subject: include/linux/linkage.h: align weak symbols Since WEAK() supposed to be used instead of ENTRY() to define weak symbols, but unlike ENTRY() it doesn't have ALIGN directive. It seems there is no actual reason to not have, so let's add ALIGN to WEAK() too. Link: http://lkml.kernel.org/r/20180920135631.23833-1-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Will Deacon , Catalin Marinas Cc: Kyeongdon Kim Cc: Ard Biesheuvel Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/linkage.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index d7618c41f74c..7c47b1a471d4 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -90,6 +90,7 @@ #ifndef WEAK #define WEAK(name) \ .weak name ASM_NL \ + ALIGN ASM_NL \ name: #endif -- cgit v1.2.3 From 5780a02fd1e87641ad6a8dd6891a1e890cf45c5d Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Fri, 26 Oct 2018 15:02:59 -0700 Subject: fs/iomap.c: change return type to vm_fault_t Change iomap_page_mkwrite() return type to vm_fault_t. see commit 1c8f422059ae ("mm: change return type to vm_fault_t") for reference. Link: http://lkml.kernel.org/r/20180827172050.GA18673@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/iomap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3555d54bf79a..9a4258154b25 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -6,6 +6,7 @@ #include #include #include +#include struct address_space; struct fiemap_extent_info; @@ -141,7 +142,8 @@ int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); -int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); +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); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, -- cgit v1.2.3 From 9b6f7e163cd0f468d1b9696b785659d3c27c8667 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:19 -0700 Subject: mm: rework memcg kernel stack accounting If CONFIG_VMAP_STACK is set, kernel stacks are allocated using __vmalloc_node_range() with __GFP_ACCOUNT. So kernel stack pages are charged against corresponding memory cgroups on allocation and uncharged on releasing them. The problem is that we do cache kernel stacks in small per-cpu caches and do reuse them for new tasks, which can belong to different memory cgroups. Each stack page still holds a reference to the original cgroup, so the cgroup can't be released until the vmap area is released. To make this happen we need more than two subsequent exits without forks in between on the current cpu, which makes it very unlikely to happen. As a result, I saw a significant number of dying cgroups (in theory, up to 2 * number_of_cpu + number_of_tasks), which can't be released even by significant memory pressure. As a cgroup structure can take a significant amount of memory (first of all, per-cpu data like memcg statistics), it leads to a noticeable waste of memory. Link: http://lkml.kernel.org/r/20180827162621.30187-1-guro@fb.com Fixes: ac496bf48d97 ("fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y") Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Andy Lutomirski Cc: Konstantin Khlebnikov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 652f602167df..4399cc3f00e4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1268,10 +1268,11 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); void memcg_kmem_put_cache(struct kmem_cache *cachep); int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg); + +#ifdef CONFIG_MEMCG_KMEM int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void memcg_kmem_uncharge(struct page *page, int order); -#ifdef CONFIG_MEMCG_KMEM extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1307,6 +1308,16 @@ extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else + +static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_kmem_uncharge(struct page *page, int order) +{ +} + #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) -- cgit v1.2.3 From 68600f623d69da428c6163275f97ca126e1a8ec5 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:27 -0700 Subject: mm: don't miss the last page because of round-off error I've noticed, that dying memory cgroups are often pinned in memory by a single pagecache page. Even under moderate memory pressure they sometimes stayed in such state for a long time. That looked strange. My investigation showed that the problem is caused by applying the LRU pressure balancing math: scan = div64_u64(scan * fraction[lru], denominator), where denominator = fraction[anon] + fraction[file] + 1. Because fraction[lru] is always less than denominator, if the initial scan size is 1, the result is always 0. This means the last page is not scanned and has no chances to be reclaimed. Fix this by rounding up the result of the division. In practice this change significantly improves the speed of dying cgroups reclaim. [guro@fb.com: prevent double calculation of DIV64_U64_ROUND_UP() arguments] Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle Link: http://lkml.kernel.org/r/20180827162621.30187-3-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Rik van Riel Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/math64.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 837f2f2d1d34..bb2c84afb80c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +#define DIV64_U64_ROUND_UP(ll, d) \ + ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) + #endif /* _LINUX_MATH64_H */ -- cgit v1.2.3 From 33490af3f5c15757448b6c454ca93b48a333aa1b Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:35 -0700 Subject: mm, mmu_notifier: be explicit about range invalition non-blocking mode If invalidate_range_start() is called for !blocking mode then all callbacks have to guarantee they will no block/sleep. The same obviously applies to invalidate_range_end because this operation pairs with the former and they are called from the same context. Make sure this is appropriately documented. Link: http://lkml.kernel.org/r/20180827112623.8992-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Jerome Glisse Cc: Boris Ostrovsky Cc: David Rientjes Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 133ba78820ee..698e371aafe3 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -153,7 +153,9 @@ struct mmu_notifier_ops { * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN. 0 should be returned - * otherwise. + * otherwise. Please note that if invalidate_range_start approves + * a non-blocking behavior then the same applies to + * invalidate_range_end. * */ int (*invalidate_range_start)(struct mmu_notifier *mn, -- cgit v1.2.3 From 4e15a073a168b62311db911a55c4d4f1500c2821 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:39 -0700 Subject: Revert "mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks" Revert 5ff7091f5a2ca ("mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks"). MMU_INVALIDATE_DOES_NOT_BLOCK flags was the only one used and it is no longer needed since 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). We now have a full support for per range !blocking behavior so we can drop the stop gap workaround which the per notifier flag was used for. Link: http://lkml.kernel.org/r/20180827112623.8992-4-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: David Rientjes Cc: Boris Ostrovsky Cc: Jerome Glisse Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 698e371aafe3..9893a6432adf 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -2,7 +2,6 @@ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H -#include #include #include #include @@ -11,9 +10,6 @@ struct mmu_notifier; struct mmu_notifier_ops; -/* mmu_notifier_ops flags */ -#define MMU_INVALIDATE_DOES_NOT_BLOCK (0x01) - #ifdef CONFIG_MMU_NOTIFIER /* @@ -30,15 +26,6 @@ struct mmu_notifier_mm { }; struct mmu_notifier_ops { - /* - * Flags to specify behavior of callbacks for this MMU notifier. - * Used to determine which context an operation may be called. - * - * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not - * block - */ - int flags; - /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are @@ -183,10 +170,6 @@ struct mmu_notifier_ops { * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. - * - * If this callback cannot block, and invalidate_range_{start,end} - * cannot block, mmu_notifier_ops.flags should have - * MMU_INVALIDATE_DOES_NOT_BLOCK set. */ void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -241,7 +224,6 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); -extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm); static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -495,11 +477,6 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, { } -static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - return false; -} - static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } -- cgit v1.2.3 From 5d7476374564645b1a2d299e242ad7b17b1104ee Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:10 -0700 Subject: mm: remove vm_insert_mixed() All callers are now converted to vmf_insert_mixed() so convert vmf_insert_mixed() from being a compatibility wrapper into the real function. Link: http://lkml.kernel.org/r/20180828145728.11873-3-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..ecc6f9347756 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,7 +2506,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn) -{ - int err = vm_insert_mixed(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { -- cgit v1.2.3 From f5e6d1d5f8f3080aa7a51acea1f77085f45abe9c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:13 -0700 Subject: mm: introduce vmf_insert_pfn_prot() Like vm_insert_pfn_prot(), but returns a vm_fault_t instead of an errno. Also unexport vm_insert_pfn_prot as it has no modular users. Link: http://lkml.kernel.org/r/20180828145728.11873-4-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton 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 ecc6f9347756..f1293bdc6de2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,6 +2506,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, -- cgit v1.2.3 From bc12e6ad9617831727e4201e7cbf5c3b868cc8fd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:21 -0700 Subject: mm: make vm_insert_pfn_prot() static Now this is no longer used outside mm/memory.c, make it static. Link: http://lkml.kernel.org/r/20180828145728.11873-6-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 f1293bdc6de2..0f5db0455e61 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2504,8 +2504,6 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.3 From 67fa1666223d7c825f6651add97f0011fe155f36 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:26 -0700 Subject: mm: remove references to vm_insert_pfn() Documentation and comments. Link: http://lkml.kernel.org/r/20180828145728.11873-7-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 4c92e3ba3e16..dde947083d4e 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -107,7 +107,7 @@ enum hmm_pfn_flag_e { * 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 vm_insert_pfn() or vm_insert_page(). Therefore, it should not + * 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. * -- cgit v1.2.3 From ae2b01f37044c10e975d22116755df56252b09d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:29 -0700 Subject: mm: remove vm_insert_pfn() All callers are now converted to vmf_insert_pfn() so convert vmf_insert_pfn() from being a compatibility wrapper around vm_insert_pfn() to being a compatibility wrapper around vmf_insert_pfn_prot(). Link: http://lkml.kernel.org/r/20180828145728.11873-8-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0f5db0455e61..737279bb479c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2502,7 +2502,7 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn) -{ - int err = vm_insert_pfn(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) -- cgit v1.2.3 From cc252eae85e09552f9c1e7ac0c3227f835efdf2d Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:34 -0700 Subject: mm, slab: combine kmalloc_caches and kmalloc_dma_caches Patch series "kmalloc-reclaimable caches", v4. As discussed at LSF/MM [1] here's a patchset that introduces kmalloc-reclaimable caches (more details in the second patch) and uses them for dcache external names. That allows us to repurpose the NR_INDIRECTLY_RECLAIMABLE_BYTES counter later in the series. With patch 3/6, dcache external names are allocated from kmalloc-rcl-* caches, eliminating the need for manual accounting. More importantly, it also ensures the reclaimable kmalloc allocations are grouped in pages separate from the regular kmalloc allocations. The need for proper accounting of dcache external names has shown it's easy for misbehaving process to allocate lots of them, causing premature OOMs. Without the added grouping, it's likely that a similar workload can interleave the dcache external names allocations with regular kmalloc allocations (note: I haven't searched myself for an example of such regular kmalloc allocation, but I would be very surprised if there wasn't some). A pathological case would be e.g. one 64byte regular allocations with 63 external dcache names in a page (64x64=4096), which means the page is not freed even after reclaiming after all dcache names, and the process can thus "steal" the whole page with single 64byte allocation. If other kmalloc users similar to dcache external names become identified, they can also benefit from the new functionality simply by adding __GFP_RECLAIMABLE to the kmalloc calls. Side benefits of the patchset (that could be also merged separately) include removed branch for detecting __GFP_DMA kmalloc(), and shortening kmalloc cache names in /proc/slabinfo output. The latter is potentially an ABI break in case there are tools parsing the names and expecting the values to be in bytes. This is how /proc/slabinfo looks like after booting in virtme: ... kmalloc-rcl-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 ... kmalloc-rcl-96 7 32 128 32 1 : tunables 120 60 8 : slabdata 1 1 0 kmalloc-rcl-64 25 128 64 64 1 : tunables 120 60 8 : slabdata 2 2 0 kmalloc-rcl-32 0 0 32 124 1 : tunables 120 60 8 : slabdata 0 0 0 kmalloc-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-2M 0 0 2097152 1 512 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-1M 0 0 1048576 1 256 : tunables 1 1 0 : slabdata 0 0 0 ... /proc/vmstat with renamed nr_indirectly_reclaimable_bytes counter: ... nr_slab_reclaimable 2817 nr_slab_unreclaimable 1781 ... nr_kernel_misc_reclaimable 0 ... /proc/meminfo with new KReclaimable counter: ... Shmem: 564 kB KReclaimable: 11260 kB Slab: 18368 kB SReclaimable: 11260 kB SUnreclaim: 7108 kB KernelStack: 1248 kB ... This patch (of 6): The kmalloc caches currently mainain separate (optional) array kmalloc_dma_caches for __GFP_DMA allocations. There are tests for __GFP_DMA in the allocation hotpaths. We can avoid the branches by combining kmalloc_caches and kmalloc_dma_caches into a single two-dimensional array where the outer dimension is cache "type". This will also allow to add kmalloc-reclaimable caches as a third type. Link: http://lkml.kernel.org/r/20180731090649.16028-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Johannes Weiner Cc: David Rientjes Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Laura Abbott Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 42 +++++++++++++++++++++++++++++++----------- 1 file changed, 31 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index ed9cbddeb4a6..2a7137043e91 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,12 +295,29 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +enum kmalloc_cache_type { + KMALLOC_NORMAL = 0, +#ifdef CONFIG_ZONE_DMA + KMALLOC_DMA, +#endif + NR_KMALLOC_TYPES +}; + #ifndef CONFIG_SLOB -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; + +static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) +{ + int is_dma = 0; + #ifdef CONFIG_ZONE_DMA -extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; + is_dma = !!(flags & __GFP_DMA); #endif + return is_dma; +} + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. @@ -501,18 +518,20 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { +#ifndef CONFIG_SLOB + unsigned int index; +#endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB - if (!(flags & GFP_DMA)) { - unsigned int index = kmalloc_index(size); + index = kmalloc_index(size); - if (!index) - return ZERO_SIZE_PTR; + if (!index) + return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(kmalloc_caches[index], - flags, size); - } + return kmem_cache_alloc_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, size); #endif } return __kmalloc(size, flags); @@ -542,13 +561,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(kmalloc_caches[i], + return kmem_cache_alloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif -- cgit v1.2.3 From 1291523f2c1d631fea34102fd241fb54a4e8f7a0 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:38 -0700 Subject: mm, slab/slub: introduce kmalloc-reclaimable caches Kmem caches can be created with a SLAB_RECLAIM_ACCOUNT flag, which indicates they contain objects which can be reclaimed under memory pressure (typically through a shrinker). This makes the slab pages accounted as NR_SLAB_RECLAIMABLE in vmstat, which is reflected also the MemAvailable meminfo counter and in overcommit decisions. The slab pages are also allocated with __GFP_RECLAIMABLE, which is good for anti-fragmentation through grouping pages by mobility. The generic kmalloc-X caches are created without this flag, but sometimes are used also for objects that can be reclaimed, which due to varying size cannot have a dedicated kmem cache with SLAB_RECLAIM_ACCOUNT flag. A prominent example are dcache external names, which prompted the creation of a new, manually managed vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES in commit f1782c9bc547 ("dcache: account external names as indirectly reclaimable memory"). To better handle this and any other similar cases, this patch introduces SLAB_RECLAIM_ACCOUNT variants of kmalloc caches, named kmalloc-rcl-X. They are used whenever the kmalloc() call passes __GFP_RECLAIMABLE among gfp flags. They are added to the kmalloc_caches array as a new type. Allocations with both __GFP_DMA and __GFP_RECLAIMABLE will use a dma type cache. This change only applies to SLAB and SLUB, not SLOB. This is fine, since SLOB's target are tiny system and this patch does add some overhead of kmem management objects. Link: http://lkml.kernel.org/r/20180731090649.16028-3-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Laura Abbott Cc: Matthew Wilcox Cc: Michal Hocko Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2a7137043e91..918f374e7156 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,8 +295,13 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +/* + * Whenever changing this, take care of that kmalloc_type() and + * create_kmalloc_caches() still work as intended. + */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, + KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif @@ -310,12 +315,21 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { int is_dma = 0; + int type_dma = 0; + int is_reclaimable; #ifdef CONFIG_ZONE_DMA is_dma = !!(flags & __GFP_DMA); + type_dma = is_dma * KMALLOC_DMA; #endif - return is_dma; + is_reclaimable = !!(flags & __GFP_RECLAIMABLE); + + /* + * If an allocation is both __GFP_DMA and __GFP_RECLAIMABLE, return + * KMALLOC_DMA and effectively ignore __GFP_RECLAIMABLE + */ + return type_dma + (is_reclaimable & !is_dma) * KMALLOC_RECLAIM; } /* -- cgit v1.2.3 From b29940c1abd7a4c3abeb926df0a5ec84d6902d47 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:46 -0700 Subject: mm: rename and change semantics of nr_indirectly_reclaimable_bytes The vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES was introduced by commit eb59254608bc ("mm: introduce NR_INDIRECTLY_RECLAIMABLE_BYTES") with the goal of accounting objects that can be reclaimed, but cannot be allocated via a SLAB_RECLAIM_ACCOUNT cache. This is now possible via kmalloc() with __GFP_RECLAIMABLE flag, and the dcache external names user is converted. The counter is however still useful for accounting direct page allocations (i.e. not slab) with a shrinker, such as the ION page pool. So keep it, and: - change granularity to pages to be more like other counters; sub-page allocations should be able to use kmalloc - rename the counter to NR_KERNEL_MISC_RECLAIMABLE - expose the counter again in vmstat as "nr_kernel_misc_reclaimable"; we can again remove the check for not printing "hidden" counters Link: http://lkml.kernel.org/r/20180731090649.16028-5-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Vijayanand Jitta Cc: Laura Abbott Cc: Sumit Semwal Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d4b0c79d2924..7bbeba21f6a3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -180,7 +180,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */ + NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_VM_NODE_STAT_ITEMS }; -- cgit v1.2.3 From 1899ad18c6072d689896badafb81267b0a1092a4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:04 -0700 Subject: mm: workingset: tell cache transitions from workingset thrashing Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset. During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing. Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing. How many page->flags does this leave us with on 32-bit? 20 bits are always page flags 21 if you have an MMU 23 with the zone bits for DMA, Normal, HighMem, Movable 29 with the sparsemem section bits 30 if PAE is enabled 31 with this patch. So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits. Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 ++++- include/linux/swap.h | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bbeba21f6a3..ba51d5bf7af1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74bee8cecf4c..4d99504f6496 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -69,13 +69,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -280,6 +281,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..b93740d72e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -296,7 +296,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Do not use directly, use workingset_lookup_update */ -- cgit v1.2.3 From b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:08 -0700 Subject: delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ -- cgit v1.2.3 From 8508cf3ffad4defa202b303e5b6379efc4cd9054 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:11 -0700 Subject: sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD There are several definitions of those functions/macros in places that mess with fixed-point load averages. Provide an official version. [akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c] Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/loadavg.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..cc9cc62bb1f8 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,23 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */ -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +#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); -- cgit v1.2.3 From 5c54f5b9edb1aa2eabbb1091c458f1b6776a1896 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:16 -0700 Subject: sched: loadavg: make calc_load_n() public It's going to be used in a later patch. Keep the churn separate. Link: http://lkml.kernel.org/r/20180828172258.3185-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/loadavg.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index cc9cc62bb1f8..4859bea47a7b 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -37,6 +37,9 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return newload / FIXED_1; } +extern unsigned long calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n); + #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) -- cgit v1.2.3 From eb414681d5a07d28d2ff90dc05f69ec6b232ebd2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:27 -0700 Subject: psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/psi.h | 28 +++++++++++++++ include/linux/psi_types.h | 92 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 10 ++++++ 3 files changed, 130 insertions(+) create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b0daf050de58 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include +#include + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include +#include + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index adfb3f9a7597..b8fcc6b3080c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -706,6 +707,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -965,6 +970,10 @@ struct task_struct { kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1391,6 +1400,7 @@ 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_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ -- cgit v1.2.3 From 2ce7135adc9ad081aa3c49744144376ac74fea60 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:31 -0700 Subject: psi: cgroup support On a system that executes multiple cgrouped jobs and independent workloads, we don't just care about the health of the overall system, but also that of individual jobs, so that we can ensure individual job health, fairness between jobs, or prioritize some jobs over others. This patch implements pressure stall tracking for cgroups. In kernels with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure, and io.pressure files that track aggregate pressure stall times for only the tasks inside the cgroup. Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Tejun Heo Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup-defs.h | 4 ++++ include/linux/cgroup.h | 15 +++++++++++++++ include/linux/psi.h | 25 +++++++++++++++++++++++++ 3 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 22254c1fe1c5..5e1694fe035b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -436,6 +437,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + /* used to track pressure stalls */ + struct psi_group psi; + /* used to store eBPF programs */ struct cgroup_bpf bpf; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b622d6608605..9968332cceed 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -650,6 +650,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return &cgrp->psi; +} + static inline void cgroup_init_kthreadd(void) { /* @@ -703,6 +708,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) return NULL; } +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + return NULL; +} + +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return NULL; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { diff --git a/include/linux/psi.h b/include/linux/psi.h index b0daf050de58..8e0725aac0aa 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -4,6 +4,9 @@ #include #include +struct seq_file; +struct css_set; + #ifdef CONFIG_PSI extern bool psi_disabled; @@ -16,6 +19,14 @@ void psi_memstall_tick(struct task_struct *task, int cpu); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); +int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); +#endif + #else /* CONFIG_PSI */ static inline void psi_init(void) {} @@ -23,6 +34,20 @@ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} +#ifdef CONFIG_CGROUPS +static inline int psi_cgroup_alloc(struct cgroup *cgrp) +{ + return 0; +} +static inline void psi_cgroup_free(struct cgroup *cgrp) +{ +} +static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) +{ + rcu_assign_pointer(p->cgroups, to); +} +#endif + #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */ -- cgit v1.2.3 From 68d48e6a2df575b935edd420396c3cb8b6aa6ad3 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:39 -0700 Subject: mm: workingset: add vmstat counter for shadow nodes Make it easier to catch bugs in the shadow node shrinker by adding a counter for the shadow nodes in circulation. [akpm@linux-foundation.org: assert that irqs are disabled, for __inc_lruvec_page_state()] [akpm@linux-foundation.org: s/WARN_ON_ONCE/VM_WARN_ON_ONCE/, per Johannes] Link: http://lkml.kernel.org/r/20181009184732.762-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Rik van Riel Signed-off-by: Andrew Morton 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 ba51d5bf7af1..9f0caccd5833 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -161,6 +161,7 @@ enum node_stat_item { NR_SLAB_UNRECLAIMABLE, 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, -- cgit v1.2.3 From 85cfb245060e45640fa3447f8b0bad5e8bd3bdaf Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 26 Oct 2018 15:07:41 -0700 Subject: memcg: remove memcg_kmem_skip_account The flag memcg_kmem_skip_account was added during the era of opt-out kmem accounting. There is no need for such flag in the opt-in world as there aren't any __GFP_ACCOUNT allocations within memcg_create_cache_enqueue(). Link: http://lkml.kernel.org/r/20180919004501.178023-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b8fcc6b3080c..8f8a5418b627 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -724,9 +724,6 @@ struct task_struct { #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; -#ifdef CONFIG_MEMCG_KMEM - unsigned memcg_kmem_skip_account:1; -#endif #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; -- cgit v1.2.3 From f682a97a00591def7cefbb5003dc04045028e405 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:45 -0700 Subject: mm: provide kernel parameter to allow disabling page init poisoning Patch series "Address issues slowing persistent memory initialization", v5. The main thing this patch set achieves is that it allows us to initialize each node worth of persistent memory independently. As a result we reduce page init time by about 2 minutes because instead of taking 30 to 40 seconds per node and going through each node one at a time, we process all 4 nodes in parallel in the case of a 12TB persistent memory setup spread evenly over 4 nodes. This patch (of 3): On systems with a large amount of memory it can take a significant amount of time to initialize all of the page structs with the PAGE_POISON_PATTERN value. I have seen it take over 2 minutes to initialize a system with over 12TB of RAM. In order to work around the issue I had to disable CONFIG_DEBUG_VM and then the boot time returned to something much more reasonable as the arch_add_memory call completed in milliseconds versus seconds. However in doing that I had to disable all of the other VM debugging on the system. In order to work around a kernel that might have CONFIG_DEBUG_VM enabled on a system that has a large amount of memory I have added a new kernel parameter named "vm_debug" that can be set to "-" in order to disable it. Link: http://lkml.kernel.org/r/20180925201921.3576.84239.stgit@localhost.localdomain Reviewed-by: Pavel Tatashin Signed-off-by: Alexander Duyck Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d99504f6496..934f91ef3f54 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -163,6 +163,14 @@ static inline int PagePoisoned(const struct page *page) return page->flags == PAGE_POISON_PATTERN; } +#ifdef CONFIG_DEBUG_VM +void page_init_poison(struct page *page, size_t size); +#else +static inline void page_init_poison(struct page *page, size_t size) +{ +} +#endif + /* * Page flags policies wrt compound pages * -- cgit v1.2.3 From d483da5bc78b86fe4200d2947f193a745f711713 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:48 -0700 Subject: mm: create non-atomic version of SetPageReserved for init use It doesn't make much sense to use the atomic SetPageReserved at init time when we are using memset to clear the memory and manipulating the page flags via simple "&=" and "|=" operations in __init_single_page. This patch adds a non-atomic version __SetPageReserved that can be used during page init and shows about a 10% improvement in initialization times on the systems I have available for testing. On those systems I saw initialization times drop from around 35 seconds to around 32 seconds to initialize a 3TB block of persistent memory. I believe the main advantage of this is that it allows for more compiler optimization as the __set_bit operation can be reordered whereas the atomic version cannot. I tried adding a bit of documentation based on f1dd2cd13c4 ("mm, memory_hotplug: do not associate hotadded memory to zones until online"). Ideally the reserved flag should be set earlier since there is a brief window where the page is initialization via __init_single_page and we have not set the PG_Reserved flag. I'm leaving that for a future patch set as that will require a more significant refactor. Link: http://lkml.kernel.org/r/20180925202018.3576.11607.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 934f91ef3f54..50ce1bddaf56 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,6 +303,7 @@ PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) -- cgit v1.2.3 From 966cf44f637e6aeea7e3d01ba004bf8b5beac78f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:52 -0700 Subject: mm: defer ZONE_DEVICE page initialization to the point where we init pgmap The ZONE_DEVICE pages were being initialized in two locations. One was with the memory_hotplug lock held and another was outside of that lock. The problem with this is that it was nearly doubling the memory initialization time. Instead of doing this twice, once while holding a global lock and once without, I am opting to defer the initialization to the one outside of the lock. This allows us to avoid serializing the overhead for memory init and we can instead focus on per-node init times. One issue I encountered is that devm_memremap_pages and hmm_devmmem_pages_create were initializing only the pgmap field the same way. One wasn't initializing hmm_data, and the other was initializing it to a poison value. Since this is something that is exposed to the driver in the case of hmm I am opting for a third option and just initializing hmm_data to 0 since this is going to be exposed to unknown third party drivers. [alexander.h.duyck@linux.intel.com: fix reference count for pgmap in devm_memremap_pages] Link: http://lkml.kernel.org/r/20181008233404.1909.37302.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/20180925202053.3576.66039.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Tested-by: Dan Williams Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton 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 737279bb479c..33228a49d7d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -848,6 +848,8 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { -- cgit v1.2.3 From 85a06835f6f1ba79f0f00838ccd5ad840dd1eafb Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:50 -0700 Subject: mm: mremap: downgrade mmap_sem to read when shrinking Other than munmap, mremap might be used to shrink memory mapping too. So, it may hold write mmap_sem for long time when shrinking large mapping, as what commit ("mm: mmap: zap pages with read mmap_sem in munmap") described. The mremap() will not manipulate vmas anymore after __do_munmap() call for the mapping shrink use case, so it is safe to downgrade to read mmap_sem. So, the same optimization, which downgrades mmap_sem to read for zapping pages, is also feasible and reasonable to this case. The period of holding exclusive mmap_sem for shrinking large mapping would be reduced significantly with this optimization. MREMAP_FIXED and MREMAP_MAYMOVE are more complicated to adopt this optimization since they need manipulate vmas after do_munmap(), downgrading mmap_sem may create race window. Simple mapping shrink is the low hanging fruit, and it may cover the most cases of unmap with munmap together. [akpm@linux-foundation.org: tweak comment] [yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue] Link: http://lkml.kernel.org/r/1538687672-17795-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1538067582-60038-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Matthew Wilcox Cc: Laurent Dufour Cc: Colin Ian King Signed-off-by: Andrew Morton 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 33228a49d7d2..a023c5ce71fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2306,6 +2306,8 @@ 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); +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); -- cgit v1.2.3 From cc4b8c794f476076c9ce19f43eb4d98dc4b5e155 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:57 -0700 Subject: mm: dax: add comment for PFN_SPECIAL The comment for PFN_SPECIAL is missed in pfn_t.h. Add comment to get consistent with other pfn flags. Link: http://lkml.kernel.org/r/1538086549-100536-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Suggested-by: Dan Williams Reviewed-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 673546ba7342..7bb77850c65a 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -9,6 +9,8 @@ * PFN_SG_LAST - pfn references a page and is the last scatterlist entry * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver + * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not + * get_user_pages */ #define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) -- cgit v1.2.3 From 1c2d479a119b84feacbe4de782016f1bf1ad16dc Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 26 Oct 2018 15:09:28 -0700 Subject: mm/memcontrol.c: convert mem_cgroup_id::ref to refcount_t type This will allow to use generic refcount_t interfaces to check counters overflow instead of currently existing VM_BUG_ON(). The only difference after the patch is VM_BUG_ON() may cause BUG(), while refcount_t fires with WARN(). But this seems not to be significant here, since such the problems are usually caught by syzbot with panic-on-warn enabled. Link: http://lkml.kernel.org/r/153910718919.7006.13400779039257185427.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reviewed-by: Andrew Morton Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Andrea Parri Signed-off-by: Andrew Morton 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 4399cc3f00e4..7ab2120155a4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -78,7 +78,7 @@ struct mem_cgroup_reclaim_cookie { struct mem_cgroup_id { int id; - atomic_t ref; + refcount_t ref; }; /* -- cgit v1.2.3 From 907ec5fca3dc38d37737de826f06f25b063aa08e Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 26 Oct 2018 15:10:15 -0700 Subject: mm: zero remaining unavailable struct pages Patch series "mm: Fix for movable_node boot option", v3. This patch series contains a fix for the movable_node boot option issue which was introduced by commit 124049decbb1 ("x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"). The commit breaks the option because it changed the memory gap range to reserved memblock. So, the node is marked as Normal zone even if the SRAT has Hot pluggable affinity. First and second patch fix the original issue which the commit tried to fix, then revert the commit. This patch (of 3): There is a kernel panic that is triggered when reading /proc/kpageflags on the kernel booted with kernel parameter 'memmap=nn[KMG]!ss[KMG]': BUG: unable to handle kernel paging request at fffffffffffffffe PGD 9b20e067 P4D 9b20e067 PUD 9b210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 1728 Comm: page-types Not tainted 4.17.0-rc6-mm1-v4.17-rc6-180605-0816-00236-g2dfb086ef02c+ #160 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.fc28 04/01/2014 RIP: 0010:stable_page_flags+0x27/0x3c0 Code: 00 00 00 0f 1f 44 00 00 48 85 ff 0f 84 a0 03 00 00 41 54 55 49 89 fc 53 48 8b 57 08 48 8b 2f 48 8d 42 ff 83 e2 01 48 0f 44 c7 <48> 8b 00 f6 c4 01 0f 84 10 03 00 00 31 db 49 8b 54 24 08 4c 89 e7 RSP: 0018:ffffbbd44111fde0 EFLAGS: 00010202 RAX: fffffffffffffffe RBX: 00007fffffffeff9 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000202 RDI: ffffed1182fff5c0 RBP: ffffffffffffffff R08: 0000000000000001 R09: 0000000000000001 R10: ffffbbd44111fed8 R11: 0000000000000000 R12: ffffed1182fff5c0 R13: 00000000000bffd7 R14: 0000000002fff5c0 R15: ffffbbd44111ff10 FS: 00007efc4335a500(0000) GS:ffff93a5bfc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffffe CR3: 00000000b2a58000 CR4: 00000000001406e0 Call Trace: kpageflags_read+0xc7/0x120 proc_reg_read+0x3c/0x60 __vfs_read+0x36/0x170 vfs_read+0x89/0x130 ksys_pread64+0x71/0x90 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7efc42e75e23 Code: 09 00 ba 9f 01 00 00 e8 ab 81 f4 ff 66 2e 0f 1f 84 00 00 00 00 00 90 83 3d 29 0a 2d 00 00 75 13 49 89 ca b8 11 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 db d3 01 00 48 89 04 24 According to kernel bisection, this problem became visible due to commit f7f99100d8d9 which changes how struct pages are initialized. Memblock layout affects the pfn ranges covered by node/zone. Consider that we have a VM with 2 NUMA nodes and each node has 4GB memory, and the default (no memmap= given) memblock layout is like below: MEMBLOCK configuration: memory size = 0x00000001fff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x4 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000100000000-0x000000013fffffff], 0x0000000040000000 bytes on node 0 flags: 0x0 memory[0x3] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... If you give memmap=1G!4G (so it just covers memory[0x2]), the range [0x100000000-0x13fffffff] is gone: MEMBLOCK configuration: memory size = 0x00000001bff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x3 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... This causes shrinking node 0's pfn range because it is calculated by the address range of memblock.memory. So some of struct pages in the gap range are left uninitialized. We have a function zero_resv_unavail() which does zeroing the struct pages outside memblock.memory, but currently it covers only the reserved unavailable range (i.e. memblock.memory && !memblock.reserved). This patch extends it to cover all unavailable range, which fixes the reported issue. Link: http://lkml.kernel.org/r/20181002143821.5112-2-msys.mizuma@gmail.com Fixes: f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") Signed-off-by: Naoya Horiguchi Signed-off-by-by: Masayoshi Mizuma Tested-by: Oscar Salvador Tested-by: Masayoshi Mizuma Reviewed-by: Pavel Tatashin Cc: Ingo Molnar Cc: Michal Hocko Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 516920549378..2acdd046df2d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -265,21 +265,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -/** - * for_each_resv_unavail_range - iterate through reserved and unavailable memory - * @i: u64 used as loop variable - * @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 - * - * Walks over unavailable but reserved (reserved && !memory) areas of memblock. - * Available as soon as memblock is initialized. - * Note: because this memory does not belong to any physical node, flags and - * nid arguments do not make sense and thus not exported as arguments. - */ -#define for_each_resv_unavail_range(i, p_start, p_end) \ - for_each_mem_range(i, &memblock.reserved, &memblock.memory, \ - NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) - static inline void memblock_set_region_flags(struct memblock_region *r, enum memblock_flags flags) { -- cgit v1.2.3 From df06b37ffe5a442503b7095b77b0a970df515459 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:10:28 -0700 Subject: mm/gup: cache dev_pagemap while pinning pages Getting pages from ZONE_DEVICE memory needs to check the backing device's live-ness, which is tracked in the device's dev_pagemap metadata. This metadata is stored in a radix tree and looking it up adds measurable software overhead. This patch avoids repeating this relatively costly operation when dev_pagemap is used by caching the last dev_pagemap while getting user pages. The gup_benchmark kernel self test reports this reduces time to get user pages to as low as 1/3 of the previous time. Link: http://lkml.kernel.org/r/20181012173040.15669-1-keith.busch@intel.com Signed-off-by: Keith Busch Reviewed-by: Dan Williams Acked-by: Kirill A. Shutemov Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 8 ++++---- include/linux/mm.h | 12 ++---------- 2 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fdcb45999b26..4663ee96cf59 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page) } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); + pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags); + pud_t *pud, int flags, struct dev_pagemap **pgmap); extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); @@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm) } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, int flags) + unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags) + unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index a023c5ce71fa..1e52b8fd1685 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2536,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags, - unsigned int *page_mask); - -static inline struct page *follow_page(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags) -{ - unsigned int unused_page_mask; - return follow_page_mask(vma, address, foll_flags, &unused_page_mask); -} +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ -- cgit v1.2.3 From bc4ae27d817a4e92071ef67cb6368120cfabe7ec Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 26 Oct 2018 15:10:51 -0700 Subject: mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS The SWP_FILE flag serves two purposes: to make swap_{read,write}page() go through the filesystem, and to make swapoff() call ->swap_deactivate(). For Btrfs, we want the latter but not the former, so split this flag into two. This makes us always call ->swap_deactivate() if ->swap_activate() succeeded, not just if it didn't add any swap extents itself. This also resolves the issue of the very misleading name of SWP_FILE, which is only used for swap files over NFS. Link: http://lkml.kernel.org/r/6d63d8668c4287a4f6d203d65696e96f80abdfc7.1536704650.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Nikolay Borisov Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: David Sterba Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index b93740d72e78..38195f5c96b1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -167,13 +167,14 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ - SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ + SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ + SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ + SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL -- cgit v1.2.3 From ae74136b4bb64440a55117e12065b8c282ab6c1a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 3 Oct 2018 12:01:22 -0400 Subject: SUNRPC: Allow cache lookups to use RCU protection rather than the r/w spinlock Instead of the reader/writer spinlock, allow cache lookups to use RCU for looking up entries. This is more efficient since modifications can occur while other entries are being looked up. Note that for now, we keep the reader/writer spinlock until all users have been converted to use RCU-safe freeing of their cache entries. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 40d2822f0e2f..cf3e17ee2786 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -167,6 +167,9 @@ extern const struct file_operations cache_file_operations_pipefs; extern const struct file_operations content_file_operations_pipefs; extern const struct file_operations cache_flush_operations_pipefs; +extern struct cache_head * +sunrpc_cache_lookup_rcu(struct cache_detail *detail, + struct cache_head *key, int hash); extern struct cache_head * sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash); @@ -186,6 +189,12 @@ static inline struct cache_head *cache_get(struct cache_head *h) return h; } +static inline struct cache_head *cache_get_rcu(struct cache_head *h) +{ + if (kref_get_unless_zero(&h->ref)) + return h; + return NULL; +} static inline void cache_put(struct cache_head *h, struct cache_detail *cd) { @@ -227,6 +236,9 @@ extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); extern void *cache_seq_start(struct seq_file *file, loff_t *pos); extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos); extern void cache_seq_stop(struct seq_file *file, void *p); +extern void *cache_seq_start_rcu(struct seq_file *file, loff_t *pos); +extern void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos); +extern void cache_seq_stop_rcu(struct seq_file *file, void *p); extern void qword_add(char **bpp, int *lp, char *str); extern void qword_addhex(char **bpp, int *lp, char *buf, int blen); -- cgit v1.2.3 From d48cf356a13073853f19be6ca5ebbecfc2762ebe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:51 -0400 Subject: SUNRPC: Remove non-RCU protected lookup Clean up the cache code by removing the non-RCU protected lookup. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index cf3e17ee2786..c3d67e893430 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -171,9 +171,6 @@ extern struct cache_head * sunrpc_cache_lookup_rcu(struct cache_detail *detail, struct cache_head *key, int hash); extern struct cache_head * -sunrpc_cache_lookup(struct cache_detail *detail, - struct cache_head *key, int hash); -extern struct cache_head * sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash); @@ -233,9 +230,6 @@ extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); /* Must store cache_detail in seq_file->private if using next three functions */ -extern void *cache_seq_start(struct seq_file *file, loff_t *pos); -extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos); -extern void cache_seq_stop(struct seq_file *file, void *p); extern void *cache_seq_start_rcu(struct seq_file *file, loff_t *pos); extern void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos); extern void cache_seq_stop_rcu(struct seq_file *file, void *p); -- cgit v1.2.3 From 1863d77f15da0addcd293a1719fa5d3ef8cde3ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:52 -0400 Subject: SUNRPC: Replace the cache_detail->hash_lock with a regular spinlock Now that the reader functions are all RCU protected, use a regular spinlock rather than a reader/writer lock. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index c3d67e893430..5a3e95017fc6 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -67,7 +67,7 @@ struct cache_detail { struct module * owner; int hash_size; struct hlist_head * hash_table; - rwlock_t hash_lock; + spinlock_t hash_lock; char *name; void (*cache_put)(struct kref *); -- cgit v1.2.3 From 3ae2cefb613b00d613677c05ffa384b4f660f468 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 1 Oct 2018 14:16:11 -0400 Subject: svcrdma: Increase the default connection credit limit Reduce queuing on clients by allowing more credits by default. 64 is the default NFSv4.1 slot table size on Linux clients. This size prevents the credit limit from putting RPC requests to sleep again after they have already slept waiting for a session slot. Signed-off-by: Chuck Lever Reviewed-by: Sagi Grimberg Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index fd78f78df5c6..e6e26918504c 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -113,13 +113,14 @@ struct svcxprt_rdma { /* sc_flags */ #define RDMAXPRT_CONN_PENDING 3 -#define RPCRDMA_LISTEN_BACKLOG 10 -#define RPCRDMA_MAX_REQUESTS 32 - -/* Typical ULP usage of BC requests is NFSv4.1 backchannel. Our - * current NFSv4.1 implementation supports one backchannel slot. +/* + * Default connection parameters */ -#define RPCRDMA_MAX_BC_REQUESTS 2 +enum { + RPCRDMA_LISTEN_BACKLOG = 10, + RPCRDMA_MAX_REQUESTS = 64, + RPCRDMA_MAX_BC_REQUESTS = 2, +}; #define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD -- cgit v1.2.3 From 1383a7ed67490fb00d793e36c7a4d599ff88a64d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:40:31 +1100 Subject: vfs: check file ranges before cloning files Move the file range checks from vfs_clone_file_prep into a separate generic_remap_checks function so that all the checks are collected in a central location. This forms the basis for adding more checks from generic_write_checks that will make cloning's input checking more consistent with write input checking. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 897eae8faee1..ba93a6e7dac4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe); +extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, @@ -2967,6 +2967,9 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +extern int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *count, bool is_dedupe); 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 a83ab01a62e61616ebb8b97f90f568c1214dc10d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:08 +1100 Subject: vfs: rename vfs_clone_file_prep to be more descriptive The vfs_clone_file_prep is a generic function to be called by filesystem implementations only. Rename the prefix to generic_ and make it more clear that it applies to remap operations, not just clones. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ba93a6e7dac4..55729e1c2e75 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); +extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From 2e5dfc99f2e61c42083ba742395e7a7b353513d1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:21 +1100 Subject: vfs: combine the clone and dedupe into a single remap_file_range Combine the clone_file_range and dedupe_file_range operations into a single remap_file_range file operation dispatch since they're fundamentally the same operation. The differences between the two can be made in the prep functions. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 55729e1c2e75..888cef35c7d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1721,6 +1721,24 @@ struct block_device_operations; #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) +/* + * These flags control the behavior of the remap_file_range function pointer. + * If it is called with len == 0 that means "remap to end of source file". + * See Documentation/filesystems/vfs.txt for more details about this call. + * + * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + */ +#define REMAP_FILE_DEDUP (1 << 0) + +/* + * These flags signal that the caller is ok with altering various aspects of + * the behavior of the remap operation. The changes must be made by the + * implementation; the vfs remap helper functions can take advantage of them. + * Flags in this category exist to preserve the quirky behavior of the hoisted + * btrfs clone/dedupe ioctls. + * There are no flags yet, but subsequent commits will add some. + */ +#define REMAP_FILE_ADVISORY (0) struct iov_iter; @@ -1759,10 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); - int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); + int (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; -- cgit v1.2.3 From a91ae49bbaf43910edb09e03fedf26b23875bd52 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:28 +1100 Subject: vfs: pass remap flags to generic_remap_file_range_prep Plumb the remap flags through the filesystem from the vfs function dispatcher all the way to the prep function to prepare for behavior changes in subsequent patches. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- 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 888cef35c7d7..631c28ce1436 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1844,7 +1844,7 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); + u64 *count, unsigned int remap_flags); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3 From 3d28193e1df043764deb7abdaba5e3a6660bc393 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:34 +1100 Subject: vfs: pass remap flags to generic_remap_checks Pass the same remap flags to generic_remap_checks for consistency. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- 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 631c28ce1436..c5435ca81132 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2986,7 +2986,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, bool is_dedupe); + uint64_t *count, unsigned int remap_flags); 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 42ec3d4c02187a18e27ff94b409ec27234bf2ffd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:49 +1100 Subject: vfs: make remap_file_range functions take and return bytes completed Change the remap_file_range functions to take a number of bytes to operate upon and return the number of bytes they operated on. This is a requirement for allowing fs implementations to return short clone/dedupe results to the user, which will enable us to obey resource limits in a graceful manner. A subsequent patch will enable copy_file_range to signal to the ->clone_file_range implementation that it can handle a short length, which will be returned in the function's return value. For now the short return is not implemented anywhere so the behavior won't change -- either copy_file_range manages to clone the entire range or it tries an alternative. Neither clone ioctl can take advantage of this, alas. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c5435ca81132..c72d8c3c065a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,9 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*remap_file_range)(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; @@ -1844,19 +1844,22 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, unsigned int remap_flags); -extern int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); -extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + loff_t *count, + unsigned int remap_flags); +extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); +extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, - u64 len); +extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len); struct super_operations { @@ -2986,7 +2989,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, unsigned int remap_flags); + loff_t *count, unsigned int remap_flags); 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 452ce65951a2f0719e4e119ecca134c06cfe22ee Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:56 +1100 Subject: vfs: plumb remap flags through the vfs clone functions Plumb a remap_flags argument through the {do,vfs}_clone_file_range functions so that clone can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c72d8c3c065a..1c5e55d2a67d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1848,10 +1848,10 @@ extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); -- cgit v1.2.3 From df3658361951e17364f1e1c3fa92862a990ad8bd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:03 +1100 Subject: vfs: plumb remap flags through the vfs dedupe functions Plumb a remap_flags argument through the vfs_dedupe_file_range_one functions so that dedupe can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- 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 1c5e55d2a67d..544ab5083b48 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1859,7 +1859,7 @@ extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, - loff_t len); + loff_t len, unsigned int remap_flags); struct super_operations { -- cgit v1.2.3 From eca3654e3cc7d93e9734d0fa96cfb15c7f356244 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:10 +1100 Subject: vfs: enable remap callers that can handle short operations Plumb in a remap flag that enables the filesystem remap handler to shorten remapping requests for callers that can handle it. Now copy_file_range can report partial success (in case we run up against alignment problems, resource limits, etc.). We also enable CAN_SHORTEN for fideduperange to maintain existing userspace-visible behavior where xfs/btrfs shorten the dedupe range to avoid stale post-eof data exposure. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 544ab5083b48..34c22d695011 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1727,8 +1727,10 @@ struct block_device_operations; * See Documentation/filesystems/vfs.txt for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) +#define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of @@ -1736,9 +1738,8 @@ struct block_device_operations; * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. - * There are no flags yet, but subsequent commits will add some. */ -#define REMAP_FILE_ADVISORY (0) +#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; -- cgit v1.2.3 From c32e5f39953fa6bbff35c655bdcb7b3128f1e79f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:17 +1100 Subject: vfs: hide file range comparison function There are no callers of vfs_dedupe_file_range_compare, so we might as well make it a static helper and remove the export. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 34c22d695011..346036a84f18 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1853,9 +1853,6 @@ extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); -extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, -- cgit v1.2.3 From 966c37f2d77eb44d47af8e919267b1ba675b2eca Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 26 Oct 2018 11:30:35 +0800 Subject: ipv4/igmp: fix v1/v2 switchback timeout based on rfc3376, 8.12 Similiar with ipv6 mcast commit 89225d1ce6af3 ("net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12.") i) RFC3376 8.12. Older Version Querier Present Timeout says: The Older Version Querier Interval is the time-out for transitioning a host back to IGMPv3 mode once an older version query is heard. When an older version query is received, hosts set their Older Version Querier Present Timer to Older Version Querier Interval. This value MUST be ((the Robustness Variable) times (the Query Interval in the last Query received)) plus (one Query Response Interval). Currently we only use a hardcode value IGMP_V1/v2_ROUTER_PRESENT_TIMEOUT. Fix it by adding two new items mr_qi(Query Interval) and mr_qri(Query Response Interval) in struct in_device. Now we can calculate the switchback time via (mr_qrv * mr_qi) + mr_qri. We need update these values when receive IGMPv3 queries. Reported-by: Ying Xu Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index c759d1cbcedd..a64f21a97369 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -37,7 +37,9 @@ struct in_device { unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; - unsigned char mr_qrv; + unsigned long mr_qi; /* Query Interval */ + unsigned long mr_qri; /* Query Response Interval */ + unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; unsigned char mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ -- cgit v1.2.3 From ffb6ce7086ee2d68d8d6d987882f1c5e923fee7e Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Tue, 9 Oct 2018 14:40:55 +0800 Subject: platform/x86: asus-wmi: export function for evaluating WMI methods Export asus_wmi_evaluate_method() and related headers for use by other drivers. hid-asus is going to use this to avoid advertising that it has a keyboard backlight when the keyboard backlight is controlled via WMI. Signed-off-by: Daniel Drake Signed-off-by: Andy Shevchenko --- include/linux/platform_data/x86/asus-wmi.h | 101 +++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 include/linux/platform_data/x86/asus-wmi.h (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h new file mode 100644 index 000000000000..53dfc2541960 --- /dev/null +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_DATA_X86_ASUS_WMI_H +#define __PLATFORM_DATA_X86_ASUS_WMI_H + +#include +#include + +/* WMI Methods */ +#define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ +#define ASUS_WMI_METHODID_SFBD 0x44424653 /* Set First Boot Device */ +#define ASUS_WMI_METHODID_GLCD 0x44434C47 /* Get LCD status */ +#define ASUS_WMI_METHODID_GPID 0x44495047 /* Get Panel ID?? (Resol) */ +#define ASUS_WMI_METHODID_QMOD 0x444F4D51 /* Quiet MODe */ +#define ASUS_WMI_METHODID_SPLV 0x4C425053 /* Set Panel Light Value */ +#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* FaN? */ +#define ASUS_WMI_METHODID_SFUN 0x4E554653 /* FUNCtionalities */ +#define ASUS_WMI_METHODID_SDSP 0x50534453 /* Set DiSPlay output */ +#define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ +#define ASUS_WMI_METHODID_DEVP 0x50564544 /* DEVice Policy */ +#define ASUS_WMI_METHODID_OSVR 0x5256534F /* OS VeRsion */ +#define ASUS_WMI_METHODID_DSTS 0x53544344 /* Device STatuS */ +#define ASUS_WMI_METHODID_DSTS2 0x53545344 /* Device STatuS #2*/ +#define ASUS_WMI_METHODID_BSTS 0x53545342 /* Bios STatuS ? */ +#define ASUS_WMI_METHODID_DEVS 0x53564544 /* DEVice Set */ +#define ASUS_WMI_METHODID_CFVS 0x53564643 /* CPU Frequency Volt Set */ +#define ASUS_WMI_METHODID_KBFT 0x5446424B /* KeyBoard FilTer */ +#define ASUS_WMI_METHODID_INIT 0x54494E49 /* INITialize */ +#define ASUS_WMI_METHODID_HKEY 0x59454B48 /* Hot KEY ?? */ + +#define ASUS_WMI_UNSUPPORTED_METHOD 0xFFFFFFFE + +/* Wireless */ +#define ASUS_WMI_DEVID_HW_SWITCH 0x00010001 +#define ASUS_WMI_DEVID_WIRELESS_LED 0x00010002 +#define ASUS_WMI_DEVID_CWAP 0x00010003 +#define ASUS_WMI_DEVID_WLAN 0x00010011 +#define ASUS_WMI_DEVID_WLAN_LED 0x00010012 +#define ASUS_WMI_DEVID_BLUETOOTH 0x00010013 +#define ASUS_WMI_DEVID_GPS 0x00010015 +#define ASUS_WMI_DEVID_WIMAX 0x00010017 +#define ASUS_WMI_DEVID_WWAN3G 0x00010019 +#define ASUS_WMI_DEVID_UWB 0x00010021 + +/* Leds */ +/* 0x000200XX and 0x000400XX */ +#define ASUS_WMI_DEVID_LED1 0x00020011 +#define ASUS_WMI_DEVID_LED2 0x00020012 +#define ASUS_WMI_DEVID_LED3 0x00020013 +#define ASUS_WMI_DEVID_LED4 0x00020014 +#define ASUS_WMI_DEVID_LED5 0x00020015 +#define ASUS_WMI_DEVID_LED6 0x00020016 + +/* Backlight and Brightness */ +#define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ +#define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 +#define ASUS_WMI_DEVID_BRIGHTNESS 0x00050012 +#define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 +#define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ +#define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 + +/* Misc */ +#define ASUS_WMI_DEVID_CAMERA 0x00060013 + +/* Storage */ +#define ASUS_WMI_DEVID_CARDREADER 0x00080013 + +/* Input */ +#define ASUS_WMI_DEVID_TOUCHPAD 0x00100011 +#define ASUS_WMI_DEVID_TOUCHPAD_LED 0x00100012 + +/* Fan, Thermal */ +#define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 +#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 + +/* Power */ +#define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 + +/* Deep S3 / Resume on LID open */ +#define ASUS_WMI_DEVID_LID_RESUME 0x00120031 + +/* DSTS masks */ +#define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 +#define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 +#define ASUS_WMI_DSTS_PRESENCE_BIT 0x00010000 +#define ASUS_WMI_DSTS_USER_BIT 0x00020000 +#define ASUS_WMI_DSTS_BIOS_BIT 0x00040000 +#define ASUS_WMI_DSTS_BRIGHTNESS_MASK 0x000000FF +#define ASUS_WMI_DSTS_MAX_BRIGTH_MASK 0x0000FF00 +#define ASUS_WMI_DSTS_LIGHTBAR_MASK 0x0000000F + +#if IS_REACHABLE(CONFIG_ASUS_WMI) +int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, u32 *retval); +#else +static inline int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, + u32 *retval) +{ + return -ENODEV; +} +#endif + +#endif /* __PLATFORM_DATA_X86_ASUS_WMI_H */ -- cgit v1.2.3 From f813f21971b96f61a789dd48151f92220fdd2e0a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Tue, 30 Oct 2018 15:04:06 -0700 Subject: mm/hmm: fix utf8 ... MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "HMM updates, improvements and fixes", v2 Few fixes that only affect HMM users. Improve the synchronization call back so that we match was other mmu_notifier listener do and add proper support to the new blockable flags in the process. For curious folks here are branches to leverage HMM in various existing device drivers: https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-nouveau-v01 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-radeon-v00 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-intel-v00 More to come (amd gpu, Mellanox, ...) I expect more of the preparatory work for nouveau will be merge in 4.20 (like we have been doing since 4.16) and i will wait until this patchset is upstream before pushing the patches that actualy make use of HMM (to avoid complex tree inter-dependency). This patch (of 6): Somehow utf=8 must have been broken. Link: http://lkml.kernel.org/r/20181019160442.18723-2-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 dde947083d4e..42b1ae915915 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Authors: Jérôme Glisse + * Authors: Jérôme Glisse */ /* * Heterogeneous Memory Management (HMM) -- cgit v1.2.3 From 44532d4c591c10d6907ac5030373bc306617d92b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Tue, 30 Oct 2018 15:04:24 -0700 Subject: mm/hmm: use a structure for update callback parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use a structure to gather all the parameters for the update callback. This make it easier when adding new parameters by avoiding having to update all callback function signature. The hmm_update structure is always associated with a mmu_notifier callbacks so we are not planing on grouping multiple updates together. Nor do we care about page size for the range as range will over fully cover the page being invalidated (this is a mmu_notifier property). Link: http://lkml.kernel.org/r/20181019160442.18723-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Ralph Campbell Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 42b1ae915915..c6fb869a81c0 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -274,13 +274,28 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, struct hmm_mirror; /* - * enum hmm_update_type - type of update + * enum hmm_update_event - type of update * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) */ -enum hmm_update_type { +enum hmm_update_event { HMM_UPDATE_INVALIDATE, }; +/* + * struct hmm_update - HMM update informations for callback + * + * @start: virtual start address of the range to update + * @end: virtual end address of the range to update + * @event: event triggering the update (what is happening) + * @blockable: can the callback block/sleep ? + */ +struct hmm_update { + unsigned long start; + unsigned long end; + enum hmm_update_event event; + bool blockable; +}; + /* * struct hmm_mirror_ops - HMM mirror device operations callback * @@ -300,9 +315,9 @@ struct hmm_mirror_ops { /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror - * @update_type: type of update that occurred to the CPU page table - * @start: virtual start address of the range to update - * @end: virtual end address of the range to update + * @update: update informations (see struct hmm_update) + * Returns: -EAGAIN if update.blockable false and callback need to + * block, 0 otherwise. * * This callback ultimately originates from mmu_notifiers when the CPU * page table is updated. The device driver must update its page table @@ -313,10 +328,8 @@ struct hmm_mirror_ops { * page tables are completely updated (TLBs flushed, etc); this is a * synchronous call. */ - void (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - enum hmm_update_type update_type, - unsigned long start, - unsigned long end); + int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, + const struct hmm_update *update); }; /* -- cgit v1.2.3 From 7275b097851a5e2e0dd4da039c7e96b59ac5314e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:04:59 -0700 Subject: linux/bitmap.h: handle constant zero-size bitmaps correctly The static inlines in bitmap.h do not handle a compile-time constant nbits==0 correctly (they dereference the passed src or dst pointers, despite only 0 words being valid to access). I had the 0-day buildbot chew on a patch [1] that would cause build failures for such cases without complaining, suggesting that we don't have any such users currently, at least for the 70 .config/arch combinations that was built. Should any turn up, make sure they use the out-of-line versions, which do handle nbits==0 correctly. This is of course not the most efficient, but it's much less churn than teaching all the static inlines an "if (zero_const_nbits())", and since we don't have any current instances, this doesn't affect existing code at all. [1] lkml.kernel.org/r/20180815085539.27485-1-linux@rasmusvillemoes.dk Link: http://lkml.kernel.org/r/20180818131623.8755-3-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index acf5e8df3504..a9805bacbd7c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -204,8 +204,13 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +/* + * The static inlines below do not handle constant nbits==0 correctly, + * so make such users (should any ever turn up) call the out-of-line + * versions. + */ #define small_const_nbits(nbits) \ - (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) + (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { -- cgit v1.2.3 From c8cebc553368209426f7279736db4f88f1853396 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:02 -0700 Subject: linux/bitmap.h: remove redundant uses of small_const_nbits() In the _zero, _fill and _copy functions, the small_const_nbits branch is redundant. If nbits is small and const, gcc knows full well that BITS_TO_LONGS(nbits) is 1, so len is also a compile-time constant (sizeof(long)), and calling memset or memcpy with a length argument of sizeof(long) makes gcc generate the expected code anyway: #include void a(unsigned long *x) { memset(x, 0, 8); } void b(unsigned long *x) { memset(x, 0xff, 8); } void c(unsigned long *x, const unsigned long *y) { memcpy(x, y, 8); } turns into 0000000000000000 : 0: 48 c7 07 00 00 00 00 movq $0x0,(%rdi) 7: c3 retq 8: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1) f: 00 0000000000000010 : 10: 48 c7 07 ff ff ff ff movq $0xffffffffffffffff,(%rdi) 17: c3 retq 18: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1) 1f: 00 0000000000000020 : 20: 48 8b 06 mov (%rsi),%rax 23: 48 89 07 mov %rax,(%rdi) 26: c3 retq Link: http://lkml.kernel.org/r/20180818131623.8755-4-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a9805bacbd7c..004cd42a3c4d 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -214,33 +214,21 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = 0UL; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = ~0UL; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0xff, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = *src; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memcpy(dst, src, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memcpy(dst, src, len); } /* -- cgit v1.2.3 From d9873969fa8725dc6a5a21ab788c057fd8719751 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:07 -0700 Subject: linux/bitmap.h: fix type of nbits in bitmap_shift_right() Most other bitmap API, including the OOL version __bitmap_shift_right, take unsigned nbits. This was accidentally left out from 2fbad29917c98. Link: http://lkml.kernel.org/r/20180818131623.8755-5-linux@rasmusvillemoes.dk Fixes: 2fbad29917c98 ("lib: bitmap: change bitmap_shift_right to take unsigned parameters") Signed-off-by: Rasmus Villemoes Reported-by: Yury Norov Reviewed-by: Andy Shevchenko Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 004cd42a3c4d..4032680e629d 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -391,7 +391,7 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, } static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, int nbits) + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; -- cgit v1.2.3 From 41e7b1661ffbf562d3aa2b7ce4ad283db50b711a Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:10 -0700 Subject: linux/bitmap.h: relax comment on compile-time constant nbits It's not clear what's so horrible about emitting a function call to handle a run-time sized bitmap. Moreover, gcc also emits a function call for a compile-time-constant-but-huge nbits, so the comment isn't even accurate. Link: http://lkml.kernel.org/r/20180818131623.8755-6-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 4032680e629d..f58e97446abc 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -28,8 +28,8 @@ * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * - * Note that nbits should be always a compile time evaluable constant. - * Otherwise many inlines will generate horrible code. + * The generated code is more efficient when nbits is known at + * compile-time and at most BITS_PER_LONG. * * :: * -- cgit v1.2.3 From 7e5ca363a5a1ec42c54dc1e0644b361a2daf984c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 30 Oct 2018 15:05:42 -0700 Subject: lib/rbtree.c: fix typo in comment of rb_insert_augmented() The function name in the comment is not correct. Link: http://lkml.kernel.org/r/20181010021344.60433-1-richard.weiyang@gmail.com Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree_augmented.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index af8a61be2d8d..9510c677ac70 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -51,8 +51,8 @@ extern void __rb_insert_augmented(struct rb_node *node, * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and - * rb_augment_inserted() instead of the usual rb_insert_color() call. - * If rb_augment_inserted() rebalances the rbtree, it will callback into + * rb_insert_augmented() instead of the usual rb_insert_color() call. + * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ -- cgit v1.2.3 From 89976005536c47a788bdd6cef5a4e9fef3c0de32 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 30 Oct 2018 15:05:49 -0700 Subject: include/linux/compat.h: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Link: http://lkml.kernel.org/r/20181013115048.GA3262@embeddedor.com Signed-off-by: Gustavo A. R. Silva Acked-by: Kees Cook Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d30e4dbd4be2..06e77473f175 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -488,8 +488,11 @@ 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 */ case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + /* fall through */ case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + /* fall through */ case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; -- cgit v1.2.3 From 3819ddec1f8c8a5daf215bec4067f8fd1dc40d6d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 30 Oct 2018 15:07:10 -0700 Subject: include/linux/signal.h: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Link: http://lkml.kernel.org/r/20181013114847.GA3160@embeddedor.com Signed-off-by: Gustavo A. R. Silva Acked-by: Kees Cook Reviewed-by: Michael Ellerman Cc: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 200ed96a05af..f428e86f4800 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -129,9 +129,11 @@ 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 */ \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ + /* fall through */ \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ @@ -161,7 +163,9 @@ 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 */ \ case 2: set->sig[1] = op(set->sig[1]); \ + /* fall through */ \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ @@ -182,6 +186,7 @@ static inline void sigemptyset(sigset_t *set) memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; + /* fall through */ case 1: set->sig[0] = 0; break; } @@ -194,6 +199,7 @@ static inline void sigfillset(sigset_t *set) memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; + /* fall through */ case 1: set->sig[0] = -1; break; } -- cgit v1.2.3 From 69a60bc75fe73511af89328ded1b33bc4a625a5c Mon Sep 17 00:00:00 2001 From: Alexander Pateenok Date: Tue, 30 Oct 2018 15:07:36 -0700 Subject: percpu: remove PER_CPU_DEF_ATTRIBUTES macro The macro is not used: $ grep -r PER_CPU_DEF_ATTRIBUTES include/linux/percpu-defs.h: __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ include/linux/percpu-defs.h: __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ include/asm-generic/percpu.h:#ifndef PER_CPU_DEF_ATTRIBUTES include/asm-generic/percpu.h:#define PER_CPU_DEF_ATTRIBUTES It was added with b01e8dc34379 ("alpha: fix percpu build breakage") and removed in 2009 with b01e8dc34379..6088464cf1ae. Link: http://lkml.kernel.org/r/20180821164904.qqhcduimjznods66@K55DR.localdomain Signed-off-by: Alexander Pateenok Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu-defs.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 2d2096ba1cfe..1ce8e264a269 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -91,8 +91,7 @@ extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ extern __PCPU_ATTRS(sec) __typeof__(type) name; \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ - __typeof__(type) name + __PCPU_ATTRS(sec) __weak __typeof__(type) name #else /* * Normal declaration and definition macros. @@ -101,8 +100,7 @@ extern __PCPU_ATTRS(sec) __typeof__(type) name #define DEFINE_PER_CPU_SECTION(type, name, sec) \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ - __typeof__(type) name + __PCPU_ATTRS(sec) __typeof__(type) name #endif /* -- cgit v1.2.3 From b4a991ec584b3ce333342c431c3cc4fef8a690d7 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:40 -0700 Subject: mm: remove CONFIG_NO_BOOTMEM All achitectures select NO_BOOTMEM which essentially becomes 'Y' for any kernel configuration and therefore it can be removed. [alexander.h.duyck@linux.intel.com: remove now defunct NO_BOOTMEM from depends list for deferred init] Link: http://lkml.kernel.org/r/20180925201814.3576.15105.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/1536927045-23536-3-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Alexander Duyck Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 36 ++---------------------------------- include/linux/mmzone.h | 5 +---- 2 files changed, 3 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 42515195d7d8..1f005b5c1555 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,34 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -#ifndef CONFIG_NO_BOOTMEM -/** - * struct bootmem_data - per-node information used by the bootmem allocator - * @node_min_pfn: the starting physical address of the node's memory - * @node_low_pfn: the end physical address of the directly addressable memory - * @node_bootmem_map: is a bitmap pointer - the bits represent all physical - * memory pages (including holes) on the node. - * @last_end_off: the offset within the page of the end of the last allocation; - * if 0, the page used is full - * @hint_idx: the PFN of the page used with the last allocation; - * together with using this with the @last_end_offset field, - * a test can be made to see if allocations can be merged - * with the page used for the last allocation rather than - * using up a full new page. - * @list: list entry in the linked list ordered by the memory addresses - */ -typedef struct bootmem_data { - unsigned long node_min_pfn; - unsigned long node_low_pfn; - void *node_bootmem_map; - unsigned long last_end_off; - unsigned long hint_idx; - struct list_head list; -} bootmem_data_t; - -extern bootmem_data_t bootmem_node_data[]; -#endif - extern unsigned long bootmem_bootmap_pages(unsigned long); extern unsigned long init_bootmem_node(pg_data_t *pgdat, @@ -125,12 +97,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long align, unsigned long goal) __malloc; -#ifdef CONFIG_NO_BOOTMEM /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 -#else -#define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS) -#endif #ifndef ARCH_LOW_ADDRESS_LIMIT #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL @@ -165,7 +133,7 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -#if defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) +#if defined(CONFIG_HAVE_MEMBLOCK) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 @@ -373,7 +341,7 @@ static inline void __init memblock_free_late( { free_bootmem_late(base, size); } -#endif /* defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) */ +#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9f0caccd5833..847705a6d0ec 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -633,9 +633,6 @@ typedef struct pglist_data { struct page_ext *node_page_ext; #endif #endif -#ifndef CONFIG_NO_BOOTMEM - struct bootmem_data *bdata; -#endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, node_present_pages @@ -869,7 +866,7 @@ static inline int is_highmem_idx(enum zone_type idx) } /** - * is_highmem - helper function to quickly check if a struct zone is a + * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone - pointer to struct zone variable -- cgit v1.2.3 From aca52c39838910605b1063a2243f553aa2a02d5c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:44 -0700 Subject: mm: remove CONFIG_HAVE_MEMBLOCK All architecures use memblock for early memory management. There is no need for the CONFIG_HAVE_MEMBLOCK configuration option. [rppt@linux.vnet.ibm.com: of/fdt: fixup #ifdefs] Link: http://lkml.kernel.org/r/20180919103457.GA20545@rapoport-lnx [rppt@linux.vnet.ibm.com: csky: fixups after bootmem removal] Link: http://lkml.kernel.org/r/20180926112744.GC4628@rapoport-lnx [rppt@linux.vnet.ibm.com: remove stale #else and the code it protects] Link: http://lkml.kernel.org/r/1538067825-24835-1-git-send-email-rppt@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1536927045-23536-4-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Tested-by: Jonathan Cameron Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 112 ----------------------------------------------- include/linux/memblock.h | 7 --- include/linux/mm.h | 2 +- 3 files changed, 1 insertion(+), 120 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 1f005b5c1555..ee61ac355104 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -132,9 +132,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) - -#if defined(CONFIG_HAVE_MEMBLOCK) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) @@ -234,115 +231,6 @@ static inline void __init memblock_free_late( __memblock_free_late(base, size); } -#else - -#define BOOTMEM_ALLOC_ACCESSIBLE 0 - - -/* Fall back to all the existing bootmem APIs */ -static inline void * __init memblock_virt_alloc( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low_nopanic(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return __alloc_bootmem_nopanic(size, align, min_addr); -} - -static inline void * __init memblock_virt_alloc_node( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node(NODE_DATA(nid), size, SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node_nopanic(NODE_DATA(nid), size, - SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_try_nid(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return __alloc_bootmem_node_high(NODE_DATA(nid), size, align, - min_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_raw( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_nopanic( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - free_bootmem_node(NODE_DATA(nid), base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem_late(base, size); -} -#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ - extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, unsigned long numentries, diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 2acdd046df2d..224d27363cca 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -2,7 +2,6 @@ #define _LINUX_MEMBLOCK_H #ifdef __KERNEL__ -#ifdef CONFIG_HAVE_MEMBLOCK /* * Logical memory blocks. * @@ -440,12 +439,6 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) { } #endif -#else -static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) -{ - return 0; -} -#endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1e52b8fd1685..fcf9cc9d535f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2163,7 +2163,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) +#if !defined(CONFIG_FLAT_NODE_MEM_MAP) void zero_resv_unavail(void); #else static inline void zero_resv_unavail(void) {} -- cgit v1.2.3 From 355c45affca7114ab510e296a5b7012943aeea17 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:50 -0700 Subject: mm: remove bootmem allocator implementation. All architectures have been converted to use MEMBLOCK + NO_BOOTMEM. The bootmem allocator implementation can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-5-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index ee61ac355104..fce6278a1724 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,14 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long bootmem_bootmap_pages(unsigned long); - -extern unsigned long init_bootmem_node(pg_data_t *pgdat, - unsigned long freepfn, - unsigned long startpfn, - unsigned long endpfn); -extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); - extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); @@ -55,14 +47,6 @@ extern void free_bootmem_late(unsigned long physaddr, unsigned long size); #define BOOTMEM_DEFAULT 0 #define BOOTMEM_EXCLUSIVE (1<<0) -extern int reserve_bootmem(unsigned long addr, - unsigned long size, - int flags); -extern int reserve_bootmem_node(pg_data_t *pgdat, - unsigned long physaddr, - unsigned long size, - int flags); - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); -- cgit v1.2.3 From b146ada221c178a384fee2a8e2e5b2e8a04476b1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:54 -0700 Subject: mm: nobootmem: remove dead code Several bootmem functions and macros are not used. Remove them. Link: http://lkml.kernel.org/r/1536927045-23536-6-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index fce6278a1724..b74bafd110b9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,17 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -/* - * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, - * the architecture-specific code should honor this). - * - * If flags is BOOTMEM_DEFAULT, then the return value is always 0 (success). - * If flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the memory - * already was reserved. - */ -#define BOOTMEM_DEFAULT 0 -#define BOOTMEM_EXCLUSIVE (1<<0) - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); @@ -73,13 +62,6 @@ void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, extern void *__alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal) __malloc; -void *__alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -92,8 +74,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_align(x, align) \ __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_nopanic(x) \ - __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages(x) \ __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_nopanic(x) \ @@ -104,17 +84,11 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_low(x) \ __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages_nopanic(x) \ - __alloc_bootmem_low_nopanic(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_low(x, PAGE_SIZE, 0) -#define alloc_bootmem_low_pages_node(pgdat, x) \ - __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 -- cgit v1.2.3 From 9a8dd708d547268c899f1cb443c49bd4d8c84eb3 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:59 -0700 Subject: memblock: rename memblock_alloc{_nid,_try_nid} to memblock_phys_alloc* Make it explicit that the caller gets a physical address rather than a virtual one. This will also allow using meblock_alloc prefix for memblock allocations returning virtual address, which is done in the following patches. The conversion is done using the following semantic patch: @@ expression e1, e2, e3; @@ ( - memblock_alloc(e1, e2) + memblock_phys_alloc(e1, e2) | - memblock_alloc_nid(e1, e2, e3) + memblock_phys_alloc_nid(e1, e2, e3) | - memblock_alloc_try_nid(e1, e2, e3) + memblock_phys_alloc_try_nid(e1, e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-7-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 224d27363cca..9d46a7204975 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -300,10 +300,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); +phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); /* * Set the allocation direction to bottom-up or top-down. -- cgit v1.2.3 From eb31d559f1e8390195372cd51cfb198da8bc84b9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:04 -0700 Subject: memblock: remove _virt from APIs returning virtual address The conversion is done using sed -i 's@memblock_virt_alloc@memblock_alloc@g' \ $(git grep -l memblock_virt_alloc) Link: http://lkml.kernel.org/r/1536927045-23536-8-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index b74bafd110b9..7d91f0f5ee44 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -95,78 +95,78 @@ extern void *__alloc_bootmem_low(unsigned long size, #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) /* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_virt_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid_nopanic(phys_addr_t size, +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); void __memblock_free_early(phys_addr_t base, phys_addr_t size); void __memblock_free_late(phys_addr_t base, phys_addr_t size); -static inline void * __init memblock_virt_alloc( +static inline void * __init memblock_alloc( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_raw( +static inline void * __init memblock_alloc_raw( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_nopanic( +static inline void * __init memblock_alloc_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low( +static inline void * __init memblock_alloc_low( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low_nopanic( +static inline void * __init memblock_alloc_low_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_from_nopanic( +static inline void * __init memblock_alloc_from_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) { - return memblock_virt_alloc_try_nid_nopanic(size, align, min_addr, + return memblock_alloc_try_nid_nopanic(size, align, min_addr, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_node( +static inline void * __init memblock_alloc_node( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -static inline void * __init memblock_virt_alloc_node_nopanic( +static inline void * __init memblock_alloc_node_nopanic( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -- cgit v1.2.3 From 3913c8f9f96bb75a062ad16ea10a1cdad48bb716 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:36 -0700 Subject: memblock: add align parameter to memblock_alloc_node() With the align parameter memblock_alloc_node() can be used as drop in replacement for alloc_bootmem_pages_node() and __alloc_bootmem_node(), which is done in the following patches. Link: http://lkml.kernel.org/r/1536927045-23536-15-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7d91f0f5ee44..3896af205303 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -157,9 +157,9 @@ static inline void * __init memblock_alloc_from_nopanic( } static inline void * __init memblock_alloc_node( - phys_addr_t size, int nid) + phys_addr_t size, phys_addr_t align, int nid) { - return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -- cgit v1.2.3 From 4fc4a09e4cc1126c4e8a86c293425cffa2a2eb3c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:03 -0700 Subject: memblock: replace __alloc_bootmem with memblock_alloc_from The functions are equivalent, just the later does not require nobootmem translation layer. The conversion is done using the following semantic patch: @@ expression size, align, goal; @@ - __alloc_bootmem(size, align, goal) + memblock_alloc_from(size, align, goal) Link: http://lkml.kernel.org/r/1536927045-23536-21-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3896af205303..c97c105cfc67 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -122,6 +122,14 @@ static inline void * __init memblock_alloc_raw( NUMA_NO_NODE); } +static inline void * __init memblock_alloc_from( + phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) +{ + return memblock_alloc_try_nid(size, align, min_addr, + BOOTMEM_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + static inline void * __init memblock_alloc_nopanic( phys_addr_t size, phys_addr_t align) { -- cgit v1.2.3 From 6c7835f8d0d1839ca93bd3cf6faa15706f03d604 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:15 -0700 Subject: mm: nobootmem: remove bootmem allocation APIs The bootmem compatibility APIs are not used and can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-23-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 47 ----------------------------------------------- 1 file changed, 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index c97c105cfc67..73f1272fce20 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,33 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -extern void *__alloc_bootmem(unsigned long size, - unsigned long align, - unsigned long goal); -extern void *__alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *__alloc_bootmem_node_high(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) __malloc; -extern void *__alloc_bootmem_low(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -70,26 +43,6 @@ extern void *__alloc_bootmem_low(unsigned long size, #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL #endif -#define alloc_bootmem(x) \ - __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_align(x, align) \ - __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages(x) \ - __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_nopanic(x) \ - __alloc_bootmem_nopanic(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) - -#define alloc_bootmem_low(x) \ - __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_low(x, PAGE_SIZE, 0) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) -- cgit v1.2.3 From 2013288f723887837d2f1cebef5fcf663b2319de Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:21 -0700 Subject: memblock: replace free_bootmem{_node} with memblock_free The free_bootmem and free_bootmem_node are merely wrappers for memblock_free. Replace their usage with a call to memblock_free using the following semantic patch: @@ expression e1, e2, e3; @@ ( - free_bootmem(e1, e2) + memblock_free(e1, e2) | - free_bootmem_node(e1, e2, e3) + memblock_free(e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-24-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 73f1272fce20..706cf8ef6678 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,10 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_node(pg_data_t *pgdat, - unsigned long addr, - unsigned long size); -extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); /* We are using top down, so it is safe to use 0 here */ -- cgit v1.2.3 From 53ab85ebfd27cdf16c8ddc72781c072a63bef3cb Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:25 -0700 Subject: memblock: replace free_bootmem_late with memblock_free_late The free_bootmem_late and memblock_free_late do exactly the same thing: they iterate over a range and give pages to the page allocator. Replace calls to free_bootmem_late with calls to memblock_free_late and remove the bootmem variant. Link: http://lkml.kernel.org/r/1536927045-23536-25-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 706cf8ef6678..bcc7e2fcb6a6 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,8 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_late(unsigned long physaddr, unsigned long size); - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 -- cgit v1.2.3 From c6ffc5ca8fb311a89cb6de5c31b6511308ddac8d Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:30 -0700 Subject: memblock: rename free_all_bootmem to memblock_free_all The conversion is done using sed -i 's@free_all_bootmem@memblock_free_all@' \ $(git grep -l free_all_bootmem) Link: http://lkml.kernel.org/r/1536927045-23536-26-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index bcc7e2fcb6a6..b58873a567b2 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,7 +26,7 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long free_all_bootmem(void); +extern unsigned long memblock_free_all(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -- cgit v1.2.3 From 57c8a661d95dff48dd9c2f2496139082bbaf241a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:49 -0700 Subject: mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include @@ @@ - #include + #include [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 173 ----------------------------------------------- include/linux/memblock.h | 151 +++++++++++++++++++++++++++++++++++++++-- 2 files changed, 147 insertions(+), 177 deletions(-) delete mode 100644 include/linux/bootmem.h (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h deleted file mode 100644 index b58873a567b2..000000000000 --- a/include/linux/bootmem.h +++ /dev/null @@ -1,173 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999 - */ -#ifndef _LINUX_BOOTMEM_H -#define _LINUX_BOOTMEM_H - -#include -#include -#include -#include - -/* - * simple boot-time physical memory area allocator. - */ - -extern unsigned long max_low_pfn; -extern unsigned long min_low_pfn; - -/* - * highest page - */ -extern unsigned long max_pfn; -/* - * highest possible page - */ -extern unsigned long long max_possible_pfn; - -extern unsigned long memblock_free_all(void); -extern void reset_node_managed_pages(pg_data_t *pgdat); -extern void reset_all_zones_managed_pages(void); - -/* We are using top down, so it is safe to use 0 here */ -#define BOOTMEM_LOW_LIMIT 0 - -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif - -/* FIXME: use MEMBLOCK_ALLOC_* variants here */ -#define BOOTMEM_ALLOC_ACCESSIBLE 0 -#define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) - -/* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid_nopanic(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void __memblock_free_early(phys_addr_t base, phys_addr_t size); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); - -static inline void * __init memblock_alloc( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} -static inline void * __init memblock_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid_nopanic(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_node( - phys_addr_t size, phys_addr_t align, int nid) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, nid); -} - -static inline void * __init memblock_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - nid); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - -extern void *alloc_large_system_hash(const char *tablename, - unsigned long bucketsize, - unsigned long numentries, - int scale, - int flags, - unsigned int *_hash_shift, - unsigned int *_hash_mask, - unsigned long low_limit, - unsigned long high_limit); - -#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ -#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min - * shift passed via *_hash_shift */ -#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ - -/* Only NUMA needs hash distribution. 64bit NUMA architectures have - * sufficient vmalloc space. - */ -#ifdef CONFIG_NUMA -#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) -extern int hashdist; /* Distribute hashes across NUMA nodes? */ -#else -#define hashdist (0) -#endif - - -#endif /* _LINUX_BOOTMEM_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9d46a7204975..1b4d85879cbe 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -15,6 +15,19 @@ #include #include +#include + +extern unsigned long max_low_pfn; +extern unsigned long min_low_pfn; + +/* + * highest page + */ +extern unsigned long max_pfn; +/* + * highest possible page + */ +extern unsigned long long max_possible_pfn; #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 @@ -119,6 +132,10 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); enum memblock_flags choose_memblock_flags(void); +unsigned long memblock_free_all(void); +void reset_node_managed_pages(pg_data_t *pgdat); +void reset_all_zones_managed_pages(void); + /* Low level functions */ int memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, @@ -300,11 +317,116 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +/* Flags for memblock allocation APIs */ +#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) +#define MEMBLOCK_ALLOC_ACCESSIBLE 0 + +/* We are using top down, so it is safe to use 0 here */ +#define MEMBLOCK_LOW_LIMIT 0 + +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); + +static inline void * __init memblock_alloc(phys_addr_t size, phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_raw(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_raw(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_low(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); +} +static inline void * __init memblock_alloc_low_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from_nopanic(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid_nopanic(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_node(phys_addr_t size, + phys_addr_t align, int nid) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, + int nid) +{ + return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void __init memblock_free_early(phys_addr_t base, + phys_addr_t size) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_early_nid(phys_addr_t base, + phys_addr_t size, int nid) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_late(phys_addr_t base, phys_addr_t size) +{ + __memblock_free_late(base, size); +} + /* * Set the allocation direction to bottom-up or top-down. */ @@ -323,10 +445,6 @@ static inline bool memblock_bottom_up(void) return memblock.bottom_up; } -/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ -#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) -#define MEMBLOCK_ALLOC_ACCESSIBLE 0 - phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, enum memblock_flags flags); @@ -432,6 +550,31 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) +extern void *alloc_large_system_hash(const char *tablename, + unsigned long bucketsize, + unsigned long numentries, + int scale, + int flags, + unsigned int *_hash_shift, + unsigned int *_hash_mask, + unsigned long low_limit, + unsigned long high_limit); + +#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ +#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min + * shift passed via *_hash_shift */ +#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ + +/* Only NUMA needs hash distribution. 64bit NUMA architectures have + * sufficient vmalloc space. + */ +#ifdef CONFIG_NUMA +#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) +extern int hashdist; /* Distribute hashes across NUMA nodes? */ +#else +#define hashdist (0) +#endif + #ifdef CONFIG_MEMTEST extern void early_memtest(phys_addr_t start, phys_addr_t end); #else -- cgit v1.2.3 From 7e1c4e27928e5f87b9b1eaf06dc31773b2f1e7f1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:57 -0700 Subject: memblock: stop using implicit alignment to SMP_CACHE_BYTES When a memblock allocation APIs are called with align = 0, the alignment is implicitly set to SMP_CACHE_BYTES. Implicit alignment is done deep in the memblock allocator and it can come as a surprise. Not that such an alignment would be wrong even when used incorrectly but it is better to be explicit for the sake of clarity and the prinicple of the least surprise. Replace all such uses of memblock APIs with the 'align' parameter explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment in the memblock internal allocation functions. For the case when memblock APIs are used via helper functions, e.g. like iommu_arena_new_node() in Alpha, the helper functions were detected with Coccinelle's help and then manually examined and updated where appropriate. The direct memblock APIs users were updated using the semantic patch below: @@ expression size, min_addr, max_addr, nid; @@ ( | - memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc(size, 0) + memblock_alloc(size, SMP_CACHE_BYTES) | - memblock_alloc_raw(size, 0) + memblock_alloc_raw(size, SMP_CACHE_BYTES) | - memblock_alloc_from(size, 0, min_addr) + memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_nopanic(size, 0) + memblock_alloc_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_low(size, 0) + memblock_alloc_low(size, SMP_CACHE_BYTES) | - memblock_alloc_low_nopanic(size, 0) + memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_from_nopanic(size, 0, min_addr) + memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_node(size, 0, nid) + memblock_alloc_node(size, SMP_CACHE_BYTES, nid) ) [mhocko@suse.com: changelog update] [akpm@linux-foundation.org: coding-style fixes] [rppt@linux.ibm.com: fix missed uses of implicit alignment] Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Suggested-by: Michal Hocko Acked-by: Paul Burton [MIPS] Acked-by: Michael Ellerman [powerpc] Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: Ingo Molnar Cc: Matt Turner Cc: Michal Simek Cc: Richard Weinberger Cc: Russell King Cc: Thomas Gleixner Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1b4d85879cbe..aee299a6aa76 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -406,7 +406,8 @@ static inline void * __init memblock_alloc_node(phys_addr_t size, static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, int nid) { - return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, + MEMBLOCK_LOW_LIMIT, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -- cgit v1.2.3 From d15e59260f62bd5e0f625cf5f5240f6ffac78ab6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:18 -0700 Subject: mm/memory_hotplug: make remove_memory() take the device_hotplug_lock Patch series "mm: online/offline_pages called w.o. mem_hotplug_lock", v3. Reading through the code and studying how mem_hotplug_lock is to be used, I noticed that there are two places where we can end up calling device_online()/device_offline() - online_pages()/offline_pages() without the mem_hotplug_lock. And there are other places where we call device_online()/device_offline() without the device_hotplug_lock. While e.g. echo "online" > /sys/devices/system/memory/memory9/state is fine, e.g. echo 1 > /sys/devices/system/memory/memory9/online Will not take the mem_hotplug_lock. However the device_lock() and device_hotplug_lock. E.g. via memory_probe_store(), we can end up calling add_memory()->online_pages() without the device_hotplug_lock. So we can have concurrent callers in online_pages(). We e.g. touch in online_pages() basically unprotected zone->present_pages then. Looks like there is a longer history to that (see Patch #2 for details), and fixing it to work the way it was intended is not really possible. We would e.g. have to take the mem_hotplug_lock in device/base/core.c, which sounds wrong. Summary: We had a lock inversion on mem_hotplug_lock and device_lock(). More details can be found in patch 3 and patch 6. I propose the general rules (documentation added in patch 6): 1. add_memory/add_memory_resource() must only be called with device_hotplug_lock. 2. remove_memory() must only be called with device_hotplug_lock. This is already documented and holds for all callers. 3. device_online()/device_offline() must only be called with device_hotplug_lock. This is already documented and true for now in core code. Other callers (related to memory hotplug) have to be fixed up. 4. mem_hotplug_lock is taken inside of add_memory/remove_memory/ online_pages/offline_pages. To me, this looks way cleaner than what we have right now (and easier to verify). And looking at the documentation of remove_memory, using lock_device_hotplug also for add_memory() feels natural. This patch (of 6): remove_memory() is exported right now but requires the device_hotplug_lock, which is not exported. So let's provide a variant that takes the lock and only export that one. The lock is already held in arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c arch/powerpc/platforms/powernv/memtrace.c Apart from that, there are not other users in the tree. Link: http://lkml.kernel.org/r/20180925091457.28651-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Greg Kroah-Hartman Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: Boris Ostrovsky Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Juergen Gross Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 34a28227068d..1f096852f479 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -301,6 +301,7 @@ 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 void 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, @@ -317,6 +318,7 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) } static inline void remove_memory(int nid, u64 start, u64 size) {} +static inline void __remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern void __ref free_area_init_core_hotplug(int nid); @@ -330,7 +332,6 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); -extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn, struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, -- cgit v1.2.3 From 8df1d0e4a265f25dc1e7e7624ccdbcb4a6630c89 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:24 -0700 Subject: mm/memory_hotplug: make add_memory() take the device_hotplug_lock add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Mathieu Malaterre Cc: Pavel Tatashin Cc: YASUAKI ISHIMATSU Cc: Balbir Singh Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Michael Neuling Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- 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 1f096852f479..ffd9cd10fcf3 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -324,6 +324,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {} extern void __ref free_area_init_core_hotplug(int nid); extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); +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, bool online); extern int arch_add_memory(int nid, u64 start, u64 size, -- cgit v1.2.3 From bb58fd7eeffc9bd5d6e2a16cbf0e9e259f8d09f2 Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Fri, 19 Oct 2018 14:11:03 -0700 Subject: i40e: Update status codes Add a few new status code which will be used by the ice driver, and rename a few to make them more consistent. Error code are mapped to similar values as in i40e_status.h, so as to be compatible with older VF drivers not using this status enum. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2c9756bd9c4c..b2488055fd1d 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -62,13 +62,19 @@ /* Error Codes */ enum virtchnl_status_code { VIRTCHNL_STATUS_SUCCESS = 0, - VIRTCHNL_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_NO_MEMORY = -18, VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH = -38, VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR = -39, VIRTCHNL_STATUS_ERR_INVALID_VF_ID = -40, - VIRTCHNL_STATUS_NOT_SUPPORTED = -64, + VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR = -53, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED = -64, }; +/* Backward compatibility */ +#define VIRTCHNL_ERR_PARAM VIRTCHNL_STATUS_ERR_PARAM +#define VIRTCHNL_STATUS_NOT_SUPPORTED VIRTCHNL_STATUS_ERR_NOT_SUPPORTED + #define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 #define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 #define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 @@ -831,7 +837,7 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: default: - return VIRTCHNL_ERR_PARAM; + return VIRTCHNL_STATUS_ERR_PARAM; } /* few more checks */ if (err_msg_format || valid_len != msglen) -- cgit v1.2.3 From a324e9396ca3d00e1101476ba067b412e0aba232 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 31 Oct 2018 19:20:20 +0100 Subject: EDAC, skx: Fix randconfig builds The driver depends on the ADXL component glue and selects it. However, ADXL itself implicitly depends on ACPI and in nonsensical randconfig builds like this: # CONFIG_ACPI is not set CONFIG_ACPI_ADXL=y where ACPI is not enabled, the build fails with: drivers/edac/skx_edac.o: In function `skx_mce_check_error': skx_edac.c:(.text+0xab): undefined reference to `adxl_decode' drivers/edac/skx_edac.o: In function `skx_init': skx_edac.c:(.init.text+0x8bf): undefined reference to `adxl_get_component_names' make: *** [vmlinux] Error 1 Add stubs for that case so that the build succeeds. CONFIG_ACPI=n doesn't make any sense for real configurations but this fix will at least silence randconfig builds. Signed-off-by: Borislav Petkov Acked-by: Tony Luck Cc: "Rafael J. Wysocki" --- include/linux/adxl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/adxl.h b/include/linux/adxl.h index 2a629acb4c3f..2d29f55923e3 100644 --- a/include/linux/adxl.h +++ b/include/linux/adxl.h @@ -7,7 +7,12 @@ #ifndef _LINUX_ADXL_H #define _LINUX_ADXL_H +#ifdef CONFIG_ACPI_ADXL const char * const *adxl_get_component_names(void); int adxl_decode(u64 addr, u64 component_values[]); +#else +static inline const char * const *adxl_get_component_names(void) { return NULL; } +static inline int adxl_decode(u64 addr, u64 component_values[]) { return -EOPNOTSUPP; } +#endif #endif /* _LINUX_ADXL_H */ -- cgit v1.2.3 From 439cd39ea136d2c026805264d58a91f36b6b64ca Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Sat, 14 Jul 2018 21:59:43 +0200 Subject: netfilter: ipset: list:set: Decrease refcount synchronously on deletion and replace Commit 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") postponed decreasing set reference counters to the RCU callback. An 'ipset del' command can terminate before the RCU grace period is elapsed, and if sets are listed before then, the reference counter shown in userspace will be wrong: # ipset create h hash:ip; ipset create l list:set; ipset add l # ipset del l h; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 1 Number of entries: 0 Members: # sleep 1; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 0 Number of entries: 0 Members: Fix this by making the reference count update synchronous again. As a result, when sets are listed, ip_set_name_byindex() might now fetch a set whose reference count is already zero. Instead of relying on the reference count to protect against concurrent set renaming, grab ip_set_ref_lock as reader and copy the name, while holding the same lock in ip_set_rename() as writer instead. Reported-by: Li Shuang Fixes: 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") Signed-off-by: Stefano Brivio Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34fc80f3eb90..1d100efe74ec 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -314,7 +314,7 @@ enum { extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); -extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index); +extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); -- cgit v1.2.3 From 0962590e553331db2cc0aef2dc35c57f6300dbbe Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 1 Nov 2018 00:05:52 +0100 Subject: bpf: fix partial copy of map_ptr when dst is scalar ALU operations on pointers such as scalar_reg += map_value_ptr are handled in adjust_ptr_min_max_vals(). Problem is however that map_ptr and range in the register state share a union, so transferring state through dst_reg->range = ptr_reg->range is just buggy as any new map_ptr in the dst_reg is then truncated (or null) for subsequent checks. Fix this by adding a raw member and use it for copying state over to dst_reg. Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Signed-off-by: Daniel Borkmann Cc: Edward Cree Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 9e8056ec20fa..d93e89761a8b 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -51,6 +51,9 @@ struct bpf_reg_state { * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; + + /* Max size from any of the above. */ + unsigned long raw; }; /* Fixed part of pointer offset, pointer types only */ s32 off; -- cgit v1.2.3 From a846446b1914d1e3d996d657754f43fde89bab51 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Fri, 12 Oct 2018 14:42:52 +0100 Subject: x86/compat: Adjust in_compat_syscall() to generic code under !COMPAT The result of in_compat_syscall() can be pictured as: x86 platform: --------------------------------------------------- | Arch\syscall | 64-bit | ia32 | x32 | |-------------------------------------------------| | x86_64 | false | true | true | |-------------------------------------------------| | i686 | | | | --------------------------------------------------- Other platforms: ------------------------------------------- | Arch\syscall | 64-bit | compat | |-----------------------------------------| | 64-bit | false | true | |-----------------------------------------| | 32-bit(?) | | | ------------------------------------------- As seen, the result of in_compat_syscall() on generic 32-bit platform differs from i686. There is no reason for in_compat_syscall() == true on native i686. It also easy to misread code if the result on native 32-bit platform differs between arches. Because of that non arch-specific code has many places with: if (IS_ENABLED(CONFIG_COMPAT) && in_compat_syscall()) in different variations. It looks-like the only non-x86 code which uses in_compat_syscall() not under CONFIG_COMPAT guard is in amd/amdkfd. But according to the commit a18069c132cb ("amdkfd: Disable support for 32-bit user processes"), it actually should be disabled on native i686. Rename in_compat_syscall() to in_32bit_syscall() for x86-specific code and make in_compat_syscall() false under !CONFIG_COMPAT. A follow on patch will clean up generic users which were forced to check IS_ENABLED(CONFIG_COMPAT) with in_compat_syscall(). Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Ard Biesheuvel Cc: "David S. Miller" Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: John Stultz Cc: "Kirill A. Shutemov" Cc: Oleg Nesterov Cc: Steffen Klassert Cc: Stephen Boyd Cc: Steven Rostedt Cc: linux-efi@vger.kernel.org Cc: netdev@vger.kernel.org Link: https://lkml.kernel.org/r/20181012134253.23266-2-dima@arista.com --- include/linux/compat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d30e4dbd4be2..f1ef24c68fcc 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -1029,9 +1029,9 @@ int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) -#ifndef in_compat_syscall +/* Ensure no one redefines in_compat_syscall() under !CONFIG_COMPAT */ +#define in_compat_syscall in_compat_syscall static inline bool in_compat_syscall(void) { return false; } -#endif #endif /* CONFIG_COMPAT */ -- cgit v1.2.3 From c3be6577d82a9f0163eb1e2c37a477414d12a209 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 1 Nov 2018 17:51:34 +0000 Subject: SUNRPC: Use atomic(64)_t for seq_send(64) The seq_send & seq_send64 fields in struct krb5_ctx are used as atomically incrementing counters. This is implemented using cmpxchg() & cmpxchg64() to implement what amount to custom versions of atomic_fetch_inc() & atomic64_fetch_inc(). Besides the duplication, using cmpxchg64() has another major drawback in that some 32 bit architectures don't provide it. As such commit 571ed1fd2390 ("SUNRPC: Replace krb5_seq_lock with a lockless scheme") resulted in build failures for some architectures. Change seq_send to be an atomic_t and seq_send64 to be an atomic64_t, then use atomic(64)_* functions to manipulate the values. The atomic64_t type & associated functions are provided even on architectures which lack real 64 bit atomic memory access via CONFIG_GENERIC_ATOMIC64 which uses spinlocks to serialize access. This fixes the build failures for architectures lacking cmpxchg64(). A potential alternative that was raised would be to provide cmpxchg64() on the 32 bit architectures that currently lack it, using spinlocks. However this would provide a version of cmpxchg64() with semantics a little different to the implementations on architectures with real 64 bit atomics - the spinlock-based implementation would only work if all access to the memory used with cmpxchg64() is *always* performed using cmpxchg64(). That is not currently a requirement for users of cmpxchg64(), and making it one seems questionable. As such avoiding cmpxchg64() outside of architecture-specific code seems best, particularly in cases where atomic64_t seems like a better fit anyway. The CONFIG_GENERIC_ATOMIC64 implementation of atomic64_* functions will use spinlocks & so faces the same issue, but with the key difference that the memory backing an atomic64_t ought to always be accessed via the atomic64_* functions anyway making the issue moot. Signed-off-by: Paul Burton Fixes: 571ed1fd2390 ("SUNRPC: Replace krb5_seq_lock with a lockless scheme") Cc: Trond Myklebust Cc: Anna Schumaker Cc: J. Bruce Fields Cc: Jeff Layton Cc: David S. Miller Cc: linux-nfs@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 69f749afa617..4162de72e95c 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -107,8 +107,8 @@ struct krb5_ctx { u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; - u32 seq_send; - u64 seq_send64; + atomic_t seq_send; + atomic64_t seq_send64; struct xdr_netobj mech_used; u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; @@ -118,9 +118,6 @@ struct krb5_ctx { u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; -extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx); -extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx); - /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) -- cgit v1.2.3 From b5f2954d30c77649bce9c27e7a0a94299d9cfdf8 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Thu, 1 Nov 2018 17:24:10 -0400 Subject: blkcg: revert blkcg cleanups series This reverts a series committed earlier due to null pointer exception bug report in [1]. It seems there are edge case interactions that I did not consider and will need some time to understand what causes the adverse interactions. The original series can be found in [2] with a follow up series in [3]. [1] https://www.spinics.net/lists/cgroups/msg20719.html [2] https://lore.kernel.org/lkml/20180911184137.35897-1-dennisszhou@gmail.com/ [3] https://lore.kernel.org/lkml/20181020185612.51587-1-dennis@kernel.org/ This reverts the following commits: d459d853c2ed, b2c3fa546705, 101246ec02b5, b3b9f24f5fcc, e2b0989954ae, f0fcb3ec89f3, c839e7a03f92, bdc2491708c4, 74b7c02a9bc1, 5bf9a1f3b4ef, a7b39b4e961c, 07b05bcc3213, 49f4c2dc2b50, 27e6fa996c53 Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- include/linux/bio.h | 26 +++----- include/linux/blk-cgroup.h | 145 ++++++++++++++------------------------------- include/linux/blk_types.h | 1 + include/linux/cgroup.h | 2 - include/linux/writeback.h | 5 +- 5 files changed, 57 insertions(+), 122 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b47c7f716731..056fb627edb3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -503,31 +503,23 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkcg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css); -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkg_association(struct bio *dst, struct bio *src); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ return 0; } -static inline int bio_associate_create_blkg(struct request_queue *q, - struct bio *bio) { return 0; } -static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) -{ return 0; } +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1e76ceebeb5d..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -126,7 +126,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - struct percpu_ref refcnt; + atomic_t refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -184,8 +184,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css; 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); @@ -232,59 +230,22 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -/** - * __bio_blkcg - internal version of bio_blkcg for bfq and cfq - * - * DO NOT USE. - * There is a flaw using this version of the function. In particular, this was - * used in a broken paradigm where association was called on the given css. It - * is possible though that the returned css from task_css() is in the process - * of dying due to migration of the current task. So it is improper to assume - * *_get() is going to succeed. Both BFQ and CFQ rely on this logic and will - * take additional work to handle more gracefully. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, NULL if not associated. - * Callers are expected to either handle NULL or know association has been - * done prior to calling this. - */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; + struct cgroup_subsys_state *css; + + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + css = kthread_blkcg(); + if (css) + return css_to_blkcg(css); + return css_to_blkcg(task_css(current, io_cgrp_id)); } static inline bool blk_cgroup_congested(void) @@ -490,35 +451,26 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - percpu_ref_get(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); } /** - * blkg_tryget - try and get a blkg reference + * blkg_try_get - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - return percpu_ref_tryget(&blkg->refcnt); + if (atomic_inc_not_zero(&blkg->refcnt)) + return blkg; + return NULL; } -/** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This walks up the blkg tree to find the closest non-dying blkg and returns - * the blkg that it did association with as it may not be the passed in blkg. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - while (!percpu_ref_tryget(&blkg->refcnt)) - blkg = blkg->parent; - return blkg; -} +void __blkg_release_rcu(struct rcu_head *rcu); /** * blkg_put - put a blkg reference @@ -526,7 +478,9 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) */ static inline void blkg_put(struct blkcg_gq *blkg) { - percpu_ref_put(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) + call_rcu(&blkg->rcu_head, __blkg_release_rcu); } /** @@ -579,36 +533,25 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); - if (bio && bio->bi_blkg) { - blkcg = bio->bi_blkg->blkcg; - if (blkcg == &blkcg_root) - goto rl_use_root; - - blkg_get(bio->bi_blkg); - rcu_read_unlock(); - return &bio->bi_blkg->rl; - } + blkcg = bio_blkcg(bio); - blkcg = css_to_blkcg(blkcg_css()); + /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) - goto rl_use_root; + goto root_rl; + /* + * Try to use blkg->rl. blkg lookup may fail under memory pressure + * or if either the blkcg or queue is going away. Fall back to + * root_rl in such cases. + */ blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) - blkg = __blkg_lookup_create(blkcg, q); - - if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg)) - goto rl_use_root; + goto root_rl; + blkg_get(blkg); rcu_read_unlock(); return &blkg->rl; - - /* - * Each blkg has its own request_list, however, the root blkcg - * uses the request_queue's root_rl. This is to avoid most - * overhead for the root blkcg. - */ -rl_use_root: +root_rl: rcu_read_unlock(); return &q->root_rl; } @@ -854,26 +797,32 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif - -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 *blkcg; struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); + blkcg = bio_blkcg(bio); + + /* associate blkcg if bio hasn't attached one */ + bio_associate_blkcg(bio, &blkcg->css); - bio_associate_create_blkg(q, bio); - blkg = bio->bi_blkg; + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the @@ -885,8 +834,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } - blkcg_bio_issue_init(bio); - rcu_read_unlock(); return !throtl; } @@ -983,7 +930,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, @@ -999,7 +945,6 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } -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; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 093a818c5b68..1dcf652ba0aa 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -178,6 +178,7 @@ struct bio { * release. Read comment on top of bio_associate_current(). */ struct io_context *bi_ioc; + struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b8bcbdeb2eac..32c553556bbd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,8 +93,6 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 738a0c24874f..fdfd04e348f6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,8 +246,7 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. Must be called after the bio has been associated with - * a device. + * writeback context. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -258,7 +257,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); + bio_associate_blkcg(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ -- cgit v1.2.3 From 6d212db11947ae5464e4717536ed9faf61c01e86 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 10:30:23 +0200 Subject: mm: add mm_pxd_folded checks to pgtable_bytes accounting functions The common mm code calls mm_dec_nr_pmds() and mm_dec_nr_puds() in free_pgtables() if the address range spans a full pud or pmd. If mm_dec_nr_puds/mm_dec_nr_pmds are non-empty due to configuration settings they blindly subtract the size of the pmd or pud table from pgtable_bytes even if the pud or pmd page table layer is folded. Add explicit mm_[pmd|pud]_folded checks to the four pgtable_bytes accounting functions mm_inc_nr_puds, mm_inc_nr_pmds, mm_dec_nr_puds and mm_dec_nr_pmds. As the check for folded page tables can be overwritten by the architecture, this allows to keep a correct pgtable_bytes value for platforms that use a dynamic number of page table levels. Acked-by: Kirill A. Shutemov Signed-off-by: Martin Schwidefsky --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..a3701e91bb57 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1742,11 +1742,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1766,11 +1770,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif -- cgit v1.2.3 From a7ad38b0dd3c1ba8d6e5a55241e875e9db8331ab Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Sat, 3 Nov 2018 00:51:28 +0800 Subject: clocksource/drivers/c-sky: Add C-SKY SMP timer The driver is for C-SKY SMP timer. It only supports oneshot event and 32bit overflow for clocksource. Per cpu core has one timer and all timers share one clock-counter-input from the same clocksource. This use mfcr&mtcr instructions to access the regs. Signed-off-by: Guo Ren Cc: Daniel Lezcano Cc: Thomas Gleixner Signed-off-by: Daniel Lezcano --- 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 caf40ad0bbc6..e0cd2baa8380 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -126,6 +126,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, -- cgit v1.2.3 From 17b8b74c0f8dbf9b9e3301f9ca5b65dd1c079951 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 19 Oct 2018 19:35:19 +0200 Subject: netfilter: ipset: Correct rcu_dereference() call in ip_set_put_comment() The function is called when rcu_read_lock() is held and not when rcu_read_lock_bh() is held. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_comment.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 8e2bab1e8e90..70877f8de7e9 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -43,11 +43,11 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, rcu_assign_pointer(comment->c, c); } -/* Used only when dumping a set, protected by rcu_read_lock_bh() */ +/* Used only when dumping a set, protected by rcu_read_lock() */ static inline int ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) { - struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); if (!c) return 0; -- cgit v1.2.3 From 94e297c50b529f5d01cfd1dbc808d61e95180ab7 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Fri, 2 Nov 2018 15:47:53 -0700 Subject: include/linux/notifier.h: SRCU: fix ctags ctags indexing ("make tags" command) throws this warning: ctags: Warning: include/linux/notifier.h:125: null expansion of name pattern "\1" This is the result of DEFINE_PER_CPU() macro expansion. Fix that by getting rid of line break. Similar fix was already done in commit 25528213fe9f ("tags: Fix DEFINE_PER_CPU expansions"), but this one probably wasn't noticed. Link: http://lkml.kernel.org/r/20181030202808.28027-1-semen.protsenko@linaro.org Fixes: 9c80172b902d ("kernel/SRCU: provide a static initializer") Signed-off-by: Sam Protsenko Cc: Sebastian Andrzej Siewior Cc: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index f35c7bf76143..0096a05395e3 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -122,8 +122,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ - static DEFINE_PER_CPU(struct srcu_data, \ - name##_head_srcu_data); \ + static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) -- cgit v1.2.3 From 89c83fb539f95491be80cdd5158e6f0ce329e317 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Nov 2018 15:48:31 -0700 Subject: mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask THP allocation mode is quite complex and it depends on the defrag mode. This complexity is hidden in alloc_hugepage_direct_gfpmask from a large part currently. The NUMA special casing (namely __GFP_THISNODE) is however independent and placed in alloc_pages_vma currently. This both adds an unnecessary branch to all vma based page allocation requests and it makes the code more complex unnecessarily as well. Not to mention that e.g. shmem THP used to do the node reclaiming unconditionally regardless of the defrag mode until recently. This was not only unexpected behavior but it was also hardly a good default behavior and I strongly suspect it was just a side effect of the code sharing more than a deliberate decision which suggests that such a layering is wrong. Get rid of the thp special casing from alloc_pages_vma and move the logic to alloc_hugepage_direct_gfpmask. __GFP_THISNODE is applied to the resulting gfp mask only when the direct reclaim is not requested and when there is no explicit numa binding to preserve the current logic. Please note that there's also a slight difference wrt MPOL_BIND now. The previous code would avoid using __GFP_THISNODE if the local node was outside of policy_nodemask(). After this patch __GFP_THISNODE is avoided for all MPOL_BIND policies. So there's a difference that if local node is actually allowed by the bind policy's nodemask, previously __GFP_THISNODE would be added, but now it won't be. From the behavior POV this is still correct because the policy nodemask is used. Link: http://lkml.kernel.org/r/20180925120326.24392-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Williamson Cc: Andrea Arcangeli Cc: David Rientjes Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Stefan Priebe - Profihost AG Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++-------- include/linux/mempolicy.h | 2 ++ 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 24bcc5eec6b4..76f8db0b0e71 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af416..bac395f1d00a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); -- cgit v1.2.3 From 3e59020abf0f88182730527ee5b862e786eb485a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Oct 2018 08:39:12 -0700 Subject: net: bql: add __netdev_tx_sent_queue() When qdisc_run() tries to use BQL budget to bulk-dequeue a batch of packets, GSO can later transform this list in another list of skbs, and each skb is sent to device ndo_start_xmit(), one at a time, with skb->xmit_more being set to one but for last skb. Problem is that very often, BQL limit is hit in the middle of the packet train, forcing dev_hard_start_xmit() to stop the bulk send and requeue the end of the list. BQL role is to avoid head of line blocking, making sure a qdisc can deliver high priority packets before low priority ones. But there is no way requeued packets can be bypassed by fresh packets in the qdisc. Aborting the bulk send increases TX softirqs, and hot cache lines (after skb_segment()) are wasted. Note that for TSO packets, we never split a packet in the middle because of BQL limit being hit. Drivers should be able to update BQL counters without flipping/caring about BQL status, if the current skb has xmit_more set. Upper layers are ultimately responsible to stop sending another packet train when BQL limit is hit. Code template in a driver might look like the following : send_doorbell = __netdev_tx_sent_queue(tx_queue, nr_bytes, skb->xmit_more); Note that __netdev_tx_sent_queue() use is not mandatory, since following patch will change dev_hard_start_xmit() to not care about BQL status. But it is highly recommended so that xmit_more full benefits can be reached (less doorbells sent, and less atomic operations as well) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dc1d9ed33b31..857f8abf7b91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3190,6 +3190,26 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/* Variant of netdev_tx_sent_queue() for drivers that are aware + * that they should not test BQL status themselves. + * We do want to change __QUEUE_STATE_STACK_XOFF only for the last + * skb of a batch. + * Returns true if the doorbell must be used to kick the NIC. + */ +static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, + unsigned int bytes, + bool xmit_more) +{ + if (xmit_more) { +#ifdef CONFIG_BQL + dql_queued(&dev_queue->dql, bytes); +#endif + return netif_tx_queue_stopped(dev_queue); + } + netdev_tx_sent_queue(dev_queue, bytes); + return true; +} + /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device -- cgit v1.2.3 From 35b69a420bfb56b7b74cb635ea903db05e357bec Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Nov 2018 03:48:54 +0000 Subject: clockevents/drivers/i8253: Add support for PIT shutdown quirk Add support for platforms where pit_shutdown() doesn't work because of a quirk in the PIT emulation. On these platforms setting the counter register to zero causes the PIT to start running again, negating the shutdown. Provide a global variable that controls whether the counter register is zero'ed, which platform specific code can override. Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Cc: "gregkh@linuxfoundation.org" Cc: "devel@linuxdriverproject.org" Cc: "daniel.lezcano@linaro.org" Cc: "virtualization@lists.linux-foundation.org" Cc: "jgross@suse.com" Cc: "akataria@vmware.com" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: vkuznets Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: KY Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1541303219-11142-2-git-send-email-mikelley@microsoft.com --- include/linux/i8253.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i8253.h b/include/linux/i8253.h index e6bb36a97519..8336b2f6f834 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,6 +21,7 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; +extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); -- cgit v1.2.3 From d098093ba06eb032057d1aca1c2e45889e099d00 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 28 Oct 2018 12:29:55 +0100 Subject: mtd: nand: Fix nanddev_neraseblocks() nanddev_neraseblocks() currently returns the number pages per LUN instead of the total number of eraseblocks. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Cc: Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index abe975c87b90..78b86dea2f29 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand) */ static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand) { - return (u64)nand->memorg.luns_per_target * - nand->memorg.eraseblocks_per_lun * - nand->memorg.pages_per_eraseblock; + return nand->memorg.ntargets * nand->memorg.luns_per_target * + nand->memorg.eraseblocks_per_lun; } /** -- cgit v1.2.3 From 163c8d54a997153ee1a1e07fcac087492ad85b37 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 5 Nov 2018 07:36:28 +0100 Subject: compiler: remove __no_sanitize_address_or_inline again The __no_sanitize_address_or_inline and __no_kasan_or_inline defines are almost identical. The only difference is that __no_kasan_or_inline does not have the 'notrace' attribute. To be able to replace __no_sanitize_address_or_inline with the older definition, add 'notrace' to __no_kasan_or_inline and change to two users of __no_sanitize_address_or_inline in the s390 code. The 'notrace' option is necessary for e.g. the __load_psw_mask function in arch/s390/include/asm/processor.h. Without the option it is possible to trace __load_psw_mask which leads to kernel stack overflow. Signed-off-by: Martin Schwidefsky Pointed-out-by: Andrey Ryabinin Acked-by: Steven Rostedt (VMware) Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 12 ------------ include/linux/compiler.h | 2 +- 2 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c0f5db3a9621..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -143,18 +143,6 @@ #define KASAN_ABI_VERSION 3 #endif -/* - * Because __no_sanitize_address conflicts with inlining: - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * we do one or the other. - */ -#ifdef CONFIG_KASAN -#define __no_sanitize_address_or_inline \ - __no_sanitize_address __maybe_unused notrace -#else -#define __no_sanitize_address_or_inline inline -#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 18c80cfa4fc4..06396c1cf127 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -189,7 +189,7 @@ void __read_once_size(const volatile void *p, void *res, int size) * 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 __maybe_unused +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused #else # define __no_kasan_or_inline __always_inline #endif -- cgit v1.2.3 From aa9b760cec2385ad408bb2e346c7f6dc1be69a79 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 4 Nov 2018 11:32:47 +0100 Subject: HID: fix up .raw_event() documentation The documentation for the .raw_event() callback says that if the driver return 1, there will be no further processing of the event, but this is not true, the actual code in hid-core.c looks like this: if (hdrv && hdrv->raw_event && hid_match_report(hid, report)) { ret = hdrv->raw_event(hid, report, data, size); if (ret < 0) goto unlock; } ret = hid_report_raw_event(hid, type, data, size, interrupt); The only return value that has any effect on the processing is a negative error. Correct this as it seems to confuse people: I found bogus code in the Razer out-of-tree driver attempting to return 1 here. Signed-off-by: Linus Walleij Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 2827b87590d8..387c70df6f29 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -722,8 +722,8 @@ struct hid_usage_id { * input will not be passed to raw_event unless hid_device_io_start is * called. * - * raw_event and event should return 0 on no action performed, 1 when no - * further processing should be done and negative on error + * raw_event and event should return negative on error, any other value will + * pass the event on to .event() typically return 0 for success. * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this -- cgit v1.2.3 From 8bd66d147c88bd441178c7b4c774ae5a185f19b8 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Wed, 31 Oct 2018 12:39:01 -0700 Subject: include/linux/compiler*.h: define asm_volatile_goto asm_volatile_goto should also be defined for other compilers that support asm goto. Fixes commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"). Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3439d7d0249a..4a3f9c09c92d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -130,6 +130,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) -- cgit v1.2.3 From 98ee3fc7ef8395f8b7a379e6608aee91efc66d48 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 6 Nov 2018 17:25:37 +0100 Subject: mtd: nand: Fix nanddev_pos_next_page() kernel-doc header Function name is wrong in the kernel-doc header. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 78b86dea2f29..7f53ece2c039 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -568,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand, } /** - * nanddev_pos_next_eraseblock() - Move a position to the next page + * nanddev_pos_next_page() - Move a position to the next page * @nand: NAND device * @pos: the position to update * -- cgit v1.2.3 From 81bd415c91eb966118d773dddf254aebf3022411 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Wed, 6 Jun 2018 21:42:32 +0200 Subject: watchdog/core: Add missing prototypes for weak functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The split out of the hard lockup detector exposed two new weak functions, but no prototypes for them, which triggers the build warning: kernel/watchdog.c:109:12: warning: no previous prototype for ‘watchdog_nmi_enable’ [-Wmissing-prototypes] kernel/watchdog.c:115:13: warning: no previous prototype for ‘watchdog_nmi_disable’ [-Wmissing-prototypes] Add the prototypes. Fixes: 73ce0511c436 ("kernel/watchdog.c: move hardlockup detector to separate file") Signed-off-by: Mathieu Malaterre Signed-off-by: Thomas Gleixner Cc: Babu Moger Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180606194232.17653-1-malat@debian.org --- include/linux/nmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 08f9247e9827..9003e29cde46 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); +int watchdog_nmi_enable(unsigned int cpu); +void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. -- cgit v1.2.3 From 24efee412c75843755da0ddd7bbc2db2ce9129f5 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 6 Nov 2018 22:52:11 +0100 Subject: Compiler Attributes: improve explanation of header Explain better what "optional" attributes are, and avoid calling them so to avoid confusion. Simply retain "Optional" as a word to look for in the comments. Moreover, add a couple sentences to explain a bit more the intention and the documentation links. Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b28c1b7310c..f8c400ba1929 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -4,22 +4,26 @@ /* * The attributes in this file are unconditionally defined and they directly - * map to compiler attribute(s) -- except those that are optional. + * map to compiler attribute(s), unless one of the compilers does not support + * the attribute. In that case, __has_attribute is used to check for support + * and the reason is stated in its comment ("Optional: ..."). * * Any other "attributes" (i.e. those that depend on a configuration option, * on a compiler, on an architecture, on plugins, on other attributes...) * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * The intention is to keep this file as simple as possible, as well as + * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks). * * This file is meant to be sorted (by actual attribute name, * not by #define identifier). Use the __attribute__((__name__)) syntax * (i.e. with underscores) to avoid future collisions with other macros. - * If an attribute is optional, state the reason in the comment. + * Provide links to the documentation of each supported compiler, if it exists. */ /* - * To check for optional attributes, we use __has_attribute, which 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. + * __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 -- cgit v1.2.3 From 23c625ce3065e40c933a4239efb9b11f1194a343 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 8 Nov 2018 14:55:21 +0100 Subject: libceph: assume argonaut on the server side No one is running pre-argonaut. In addition one of the argonaut features (NOSRCADDR) has been required since day one (and a half, 2.6.34 vs 2.6.35) of the kernel client. Allow for the possibility of reusing these feature bits later. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b92b3395fa9..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif -- cgit v1.2.3