From dcb60f9c403e03133363563ac8ea5d8bba6c2be1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 12 Jul 2023 20:08:32 -0700 Subject: cpumask: eliminate kernel-doc warnings Update lib/cpumask.c and to fix all kernel-doc warnings: include/linux/cpumask.h:185: warning: Function parameter or member 'srcp1' not described in 'cpumask_first_and' include/linux/cpumask.h:185: warning: Function parameter or member 'srcp2' not described in 'cpumask_first_and' include/linux/cpumask.h:185: warning: Excess function parameter 'src1p' description in 'cpumask_first_and' include/linux/cpumask.h:185: warning: Excess function parameter 'src2p' description in 'cpumask_first_and' lib/cpumask.c:59: warning: Function parameter or member 'node' not described in 'alloc_cpumask_var_node' lib/cpumask.c:169: warning: Function parameter or member 'src1p' not described in 'cpumask_any_and_distribute' lib/cpumask.c:169: warning: Function parameter or member 'src2p' not described in 'cpumask_any_and_distribute' Fixes: 7b4967c53204 ("cpumask: Add alloc_cpumask_var_node()") Fixes: 839cad5fa54b ("cpumask: fix function description kernel-doc notation") Fixes: 93ba139ba819 ("cpumask: use find_first_and_bit()") Signed-off-by: Randy Dunlap Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- include/linux/cpumask.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 0d2e2a38b92d..f10fb87d49db 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -175,8 +175,8 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 - * @src1p: the first input - * @src2p: the second input + * @srcp1: the first input + * @srcp2: the second input * * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ @@ -1197,6 +1197,10 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus + * @buf: the buffer to copy into + * @mask: the cpumask to copy + * @off: in the string from which we are copying, we copy to @buf + * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. -- cgit v1.2.3 From 80ddce5f2dbd0e83eadc9f9d373439180d599fe5 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Sat, 8 Jul 2023 13:27:19 +0200 Subject: thermal: core: constify params in thermal_zone_device_register Since commit 3d439b1a2ad3 ("thermal/core: Alloc-copy-free the thermal zone parameters structure"), thermal_zone_device_register() allocates a copy of the tzp argument and callers need not explicitly manage its lifetime. This means the function no longer cares about the parameter being mutable, so constify it. No functional change. Signed-off-by: Ahmad Fatoum Acked-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/thermal.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 87837094d549..dee66ade89a0 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -301,14 +301,14 @@ int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp); #ifdef CONFIG_THERMAL struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, void *, struct thermal_zone_device_ops *, - struct thermal_zone_params *, int, int); + const struct thermal_zone_params *, int, int); void thermal_zone_device_unregister(struct thermal_zone_device *); struct thermal_zone_device * thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int, int, void *, struct thermal_zone_device_ops *, - struct thermal_zone_params *, int, int); + const struct thermal_zone_params *, int, int); void *thermal_zone_device_priv(struct thermal_zone_device *tzd); const char *thermal_zone_device_type(struct thermal_zone_device *tzd); @@ -348,7 +348,7 @@ void thermal_zone_device_critical(struct thermal_zone_device *tz); static inline struct thermal_zone_device *thermal_zone_device_register( const char *type, int trips, int mask, void *devdata, struct thermal_zone_device_ops *ops, - struct thermal_zone_params *tzp, + const struct thermal_zone_params *tzp, int passive_delay, int polling_delay) { return ERR_PTR(-ENODEV); } static inline void thermal_zone_device_unregister( -- cgit v1.2.3 From e7b915219baa4b2bf30afe1dbaca7a24ff627ad2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 13 Jul 2023 16:57:40 +0200 Subject: PM: sleep: wakeirq: drop unused enable helpers Drop the wake-irq enable and disable helpers which have not been used since commit bed570307ed7 ("PM / wakeirq: Fix dedicated wakeirq for drivers not using autosuspend"). Note that these functions are essentially just leftovers from the first iteration of the wake-irq implementation where device drivers were supposed to call these functions themselves instead of PM core (as is also indicated by the bogus kernel doc comments). Signed-off-by: Johan Hovold Reviewed-by: Tony Lindgren Signed-off-by: Rafael J. Wysocki --- include/linux/pm_wakeirq.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h index dd42d16945d0..d9642c6cf852 100644 --- a/include/linux/pm_wakeirq.h +++ b/include/linux/pm_wakeirq.h @@ -10,8 +10,6 @@ extern int dev_pm_set_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq); extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq); extern void dev_pm_clear_wake_irq(struct device *dev); -extern void dev_pm_enable_wake_irq(struct device *dev); -extern void dev_pm_disable_wake_irq(struct device *dev); #else /* !CONFIG_PM */ @@ -34,13 +32,5 @@ static inline void dev_pm_clear_wake_irq(struct device *dev) { } -static inline void dev_pm_enable_wake_irq(struct device *dev) -{ -} - -static inline void dev_pm_disable_wake_irq(struct device *dev) -{ -} - #endif /* CONFIG_PM */ #endif /* _LINUX_PM_WAKEIRQ_H */ -- cgit v1.2.3 From c1ed39ec116272935528ca9b348b8ee79b0791da Mon Sep 17 00:00:00 2001 From: Winston Wen Date: Mon, 24 Jul 2023 10:10:56 +0800 Subject: fs/nls: make load_nls() take a const parameter load_nls() take a char * parameter, use it to find nls module in list or construct the module name to load it. This change make load_nls() take a const parameter, so we don't need do some cast like this: ses->local_nls = load_nls((char *)ctx->local_nls->charset); Suggested-by: Stephen Rothwell Signed-off-by: Winston Wen Reviewed-by: Paulo Alcantara Reviewed-by: Christian Brauner Signed-off-by: Steve French --- include/linux/nls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nls.h b/include/linux/nls.h index 499e486b3722..e0bf8367b274 100644 --- a/include/linux/nls.h +++ b/include/linux/nls.h @@ -47,7 +47,7 @@ enum utf16_endian { /* nls_base.c */ extern int __register_nls(struct nls_table *, struct module *); extern int unregister_nls(struct nls_table *); -extern struct nls_table *load_nls(char *); +extern struct nls_table *load_nls(const char *charset); extern void unload_nls(struct nls_table *); extern struct nls_table *load_nls_default(void); #define register_nls(nls) __register_nls((nls), THIS_MODULE) -- cgit v1.2.3 From fb3bd914b3ec28f5fb697ac55c4846ac2d542855 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Wed, 28 Jun 2023 11:02:39 +0200 Subject: x86/srso: Add a Speculative RAS Overflow mitigation Add a mitigation for the speculative return address stack overflow vulnerability found on AMD processors. The mitigation works by ensuring all RET instructions speculate to a controlled location, similar to how speculation is controlled in the retpoline sequence. To accomplish this, the __x86_return_thunk forces the CPU to mispredict every function return using a 'safe return' sequence. To ensure the safety of this mitigation, the kernel must ensure that the safe return sequence is itself free from attacker interference. In Zen3 and Zen4, this is accomplished by creating a BTB alias between the untraining function srso_untrain_ret_alias() and the safe return function srso_safe_ret_alias() which results in evicting a potentially poisoned BTB entry and using that safe one for all function returns. In older Zen1 and Zen2, this is accomplished using a reinterpretation technique similar to Retbleed one: srso_untrain_ret() and srso_safe_ret(). Signed-off-by: Borislav Petkov (AMD) --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 6e6e57ec69e8..23ac87be1ff1 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -70,6 +70,8 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev, char *buf); extern ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From 09eadda27ca4afc3f560efea265bbe7a93ef786d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 19 Mar 2023 22:29:28 +0100 Subject: backlight: corgi_lcd: fix missing prototype The corgi_lcd_limit_intensity() function is called from platform and defined in a driver, but the driver does not see the declaration: drivers/video/backlight/corgi_lcd.c:434:6: error: no previous prototype for 'corgi_lcd_limit_intensity' [-Werror=missing-prototypes] 434 | void corgi_lcd_limit_intensity(int limit) Move the prototype into a header that can be included from both sides to shut up the warning. Reviewed-by: Daniel Thompson Signed-off-by: Arnd Bergmann --- include/linux/spi/corgi_lcd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/corgi_lcd.h b/include/linux/spi/corgi_lcd.h index 0b857616919c..fc6c1515dc54 100644 --- a/include/linux/spi/corgi_lcd.h +++ b/include/linux/spi/corgi_lcd.h @@ -15,4 +15,6 @@ struct corgi_lcd_platform_data { void (*kick_battery)(void); }; +void corgi_lcd_limit_intensity(int limit); + #endif /* __LINUX_SPI_CORGI_LCD_H */ -- cgit v1.2.3 From 71c8f9cf2623d0db79665f876b95afcdd8214aec Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 19 Jul 2023 21:00:25 +0200 Subject: mtd: spi-nor: avoid holes in struct spi_mem_op gcc gets confused when -ftrivial-auto-var-init=pattern is used on sparse bit fields such as 'struct spi_mem_op', which caused the previous false positive warning about an uninitialized variable: drivers/mtd/spi-nor/spansion.c: error: 'op' is used uninitialized [-Werror=uninitialized] In fact, the variable is fully initialized and gcc does not see it being used, so the warning is entirely bogus. The problem appears to be a misoptimization in the initialization of single bit fields when the rest of the bytes are not initialized. A previous workaround added another initialization, which ended up shutting up the warning in spansion.c, though it apparently still happens in other files as reported by Peter Foley in the gcc bugzilla. The workaround of adding a fake initialization seems particularly bad because it would set values that can never be correct but prevent the compiler from warning about actually missing initializations. Revert the broken workaround and instead pad the structure to only have bitfields that add up to full bytes, which should avoid this behavior in all drivers. I also filed a new bug against gcc with what I found, so this can hopefully be addressed in future gcc releases. At the moment, only gcc-12 and gcc-13 are affected. Cc: Peter Foley Cc: Pedro Falcato Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110743 Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108402 Link: https://godbolt.org/z/efMMsG1Kx Fixes: 420c4495b5e56 ("mtd: spi-nor: spansion: make sure local struct does not contain garbage") Signed-off-by: Arnd Bergmann Acked-by: Mark Brown Acked-by: Tudor Ambarus Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20230719190045.4007391-1-arnd@kernel.org --- include/linux/spi/spi-mem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 8e984d75f5b6..6b0a7dc48a4b 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -101,6 +101,7 @@ struct spi_mem_op { u8 nbytes; u8 buswidth; u8 dtr : 1; + u8 __pad : 7; u16 opcode; } cmd; @@ -108,6 +109,7 @@ struct spi_mem_op { u8 nbytes; u8 buswidth; u8 dtr : 1; + u8 __pad : 7; u64 val; } addr; @@ -115,12 +117,14 @@ struct spi_mem_op { u8 nbytes; u8 buswidth; u8 dtr : 1; + u8 __pad : 7; } dummy; struct { u8 buswidth; u8 dtr : 1; u8 ecc : 1; + u8 __pad : 6; enum spi_mem_data_dir dir; unsigned int nbytes; union { -- cgit v1.2.3 From b1f02b95758d05b799731d939e76a0bd6da312db Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Sat, 22 Jul 2023 00:51:07 +0200 Subject: mm: fix memory ordering for mm_lock_seq and vm_lock_seq mm->mm_lock_seq effectively functions as a read/write lock; therefore it must be used with acquire/release semantics. A specific example is the interaction between userfaultfd_register() and lock_vma_under_rcu(). userfaultfd_register() does the following from the point where it changes a VMA's flags to the point where concurrent readers are permitted again (in a simple scenario where only a single private VMA is accessed and no merging/splitting is involved): userfaultfd_register userfaultfd_set_vm_flags vm_flags_reset vma_start_write down_write(&vma->vm_lock->lock) vma->vm_lock_seq = mm_lock_seq [marks VMA as busy] up_write(&vma->vm_lock->lock) vm_flags_init [sets VM_UFFD_* in __vm_flags] vma->vm_userfaultfd_ctx.ctx = ctx mmap_write_unlock vma_end_write_all WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1) [unlocks VMA] There are no memory barriers in between the __vm_flags update and the mm->mm_lock_seq update that unlocks the VMA, so the unlock can be reordered to above the `vm_flags_init()` call, which means from the perspective of a concurrent reader, a VMA can be marked as a userfaultfd VMA while it is not VMA-locked. That's bad, we definitely need a store-release for the unlock operation. The non-atomic write to vma->vm_lock_seq in vma_start_write() is mostly fine because all accesses to vma->vm_lock_seq that matter are always protected by the VMA lock. There is a racy read in vma_start_read() though that can tolerate false-positives, so we should be using WRITE_ONCE() to keep things tidy and data-race-free (including for KCSAN). On the other side, lock_vma_under_rcu() works as follows in the relevant region for locking and userfaultfd check: lock_vma_under_rcu vma_start_read vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq) [early bailout] down_read_trylock(&vma->vm_lock->lock) vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq) [main check] userfaultfd_armed checks vma->vm_flags & __VM_UFFD_FLAGS Here, the interesting aspect is how far down the mm->mm_lock_seq read can be reordered - if this read is reordered down below the vma->vm_flags access, this could cause lock_vma_under_rcu() to partly operate on information that was read while the VMA was supposed to be locked. To prevent this kind of downwards bleeding of the mm->mm_lock_seq read, we need to read it with a load-acquire. Some of the comment wording is based on suggestions by Suren. BACKPORT WARNING: One of the functions changed by this patch (which I've written against Linus' tree) is vma_try_start_write(), but this function no longer exists in mm/mm-everything. I don't know whether the merged version of this patch will be ordered before or after the patch that removes vma_try_start_write(). If you're backporting this patch to a tree with vma_try_start_write(), make sure this patch changes that function. Link: https://lkml.kernel.org/r/20230721225107.942336-1-jannh@google.com Fixes: 5e31275cc997 ("mm: add per-VMA lock and helper functions to control it") Signed-off-by: Jann Horn Reviewed-by: Suren Baghdasaryan Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 29 +++++++++++++++++++++++------ include/linux/mm_types.h | 28 ++++++++++++++++++++++++++++ include/linux/mmap_lock.h | 10 ++++++++-- 3 files changed, 59 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2dd73e4f3d8e..406ab9ea818f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -641,8 +641,14 @@ static inline void vma_numab_state_free(struct vm_area_struct *vma) {} */ static inline bool vma_start_read(struct vm_area_struct *vma) { - /* Check before locking. A race might cause false locked result. */ - if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) + /* + * Check before locking. A race might cause false locked result. + * We can use READ_ONCE() for the mm_lock_seq here, and don't need + * ACQUIRE semantics, because this is just a lockless check whose result + * we don't rely on for anything - the mm_lock_seq read against which we + * need ordering is below. + */ + if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq)) return false; if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) @@ -653,8 +659,13 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * False unlocked result is impossible because we modify and check * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq * modification invalidates all existing locks. + * + * We must use ACQUIRE semantics for the mm_lock_seq so that if we are + * racing with vma_end_write_all(), we only start reading from the VMA + * after it has been unlocked. + * This pairs with RELEASE semantics in vma_end_write_all(). */ - if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { + if (unlikely(vma->vm_lock_seq == smp_load_acquire(&vma->vm_mm->mm_lock_seq))) { up_read(&vma->vm_lock->lock); return false; } @@ -676,7 +687,7 @@ static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ - *mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); + *mm_lock_seq = vma->vm_mm->mm_lock_seq; return (vma->vm_lock_seq == *mm_lock_seq); } @@ -688,7 +699,13 @@ static inline void vma_start_write(struct vm_area_struct *vma) return; down_write(&vma->vm_lock->lock); - vma->vm_lock_seq = mm_lock_seq; + /* + * We should use WRITE_ONCE() here because we can have concurrent reads + * from the early lockless pessimistic check in vma_start_read(). + * We don't really care about the correctness of that early check, but + * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. + */ + WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); up_write(&vma->vm_lock->lock); } @@ -702,7 +719,7 @@ static inline bool vma_try_start_write(struct vm_area_struct *vma) if (!down_write_trylock(&vma->vm_lock->lock)) return false; - vma->vm_lock_seq = mm_lock_seq; + WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); up_write(&vma->vm_lock->lock); return true; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index de10fc797c8e..5e74ce4a28cd 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -514,6 +514,20 @@ struct vm_area_struct { }; #ifdef CONFIG_PER_VMA_LOCK + /* + * Can only be written (using WRITE_ONCE()) while holding both: + * - mmap_lock (in write mode) + * - vm_lock->lock (in write mode) + * Can be read reliably while holding one of: + * - mmap_lock (in read or write mode) + * - vm_lock->lock (in read or write mode) + * Can be read unreliably (using READ_ONCE()) for pessimistic bailout + * while holding nothing (except RCU to keep the VMA struct allocated). + * + * This sequence counter is explicitly allowed to overflow; sequence + * counter reuse can only lead to occasional unnecessary use of the + * slowpath. + */ int vm_lock_seq; struct vma_lock *vm_lock; @@ -679,6 +693,20 @@ struct mm_struct { * by mmlist_lock */ #ifdef CONFIG_PER_VMA_LOCK + /* + * This field has lock-like semantics, meaning it is sometimes + * accessed with ACQUIRE/RELEASE semantics. + * Roughly speaking, incrementing the sequence number is + * equivalent to releasing locks on VMAs; reading the sequence + * number can be part of taking a read lock on a VMA. + * + * Can be modified under write mmap_lock using RELEASE + * semantics. + * Can be read with no other protection when holding write + * mmap_lock. + * Can be read with ACQUIRE semantics if not holding write + * mmap_lock. + */ int mm_lock_seq; #endif diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index aab8f1b28d26..e05e167dbd16 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -76,8 +76,14 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm) static inline void vma_end_write_all(struct mm_struct *mm) { mmap_assert_write_locked(mm); - /* No races during update due to exclusive mmap_lock being held */ - WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1); + /* + * Nobody can concurrently modify mm->mm_lock_seq due to exclusive + * mmap_lock being held. + * We need RELEASE semantics here to ensure that preceding stores into + * the VMA take effect before we unlock it with this store. + * Pairs with ACQUIRE semantics in vma_start_read(). + */ + smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1); } #else static inline void vma_end_write_all(struct mm_struct *mm) {} -- cgit v1.2.3 From 800959e697de0c55613a2ce40bca52520a421c9f Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 25 Jul 2023 21:48:08 +0800 Subject: ftrace: Remove unused extern declarations commit 6a9c981b1e96 ("ftrace: Remove unused function ftrace_arch_read_dyn_info()") left ftrace_arch_read_dyn_info() extern declaration. And commit 1d74f2a0f64b ("ftrace: remove ftrace_ip_converted()") leave ftrace_ip_converted() declaration. Link: https://lore.kernel.org/linux-trace-kernel/20230725134808.9716-1-yuehaibing@huawei.com Cc: Cc: Signed-off-by: YueHaibing Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ce156c7704ee..aad9cf8876b5 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -684,7 +684,6 @@ void __init ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable); /* defined in arch */ -extern int ftrace_ip_converted(unsigned long ip); extern int ftrace_dyn_arch_init(void); extern void ftrace_replace_code(int enable); extern int ftrace_update_ftrace_func(ftrace_func_t func); @@ -859,9 +858,6 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a } #endif -/* May be defined in arch */ -extern int ftrace_arch_read_dyn_info(char *buf, int size); - extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); extern void ftrace_module_enable(struct module *mod); -- cgit v1.2.3 From 16e95a62eed18864aecac404f1e4eed764c363f2 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 25 Jul 2023 13:39:12 +0800 Subject: powercap: intel_rapl: Fix a sparse warning in TPMI interface Depends on the interface used, the RAPL registers can be either MSR indexes or memory mapped IO addresses. Current RAPL common code uses u64 to save both MSR and memory mapped IO registers. With this, when handling register address with an __iomem annotation, it triggers a sparse warning like below: sparse warnings: (new ones prefixed by >>) >> drivers/powercap/intel_rapl_tpmi.c:141:41: sparse: sparse: incorrect type in initializer (different address spaces) @@ expected unsigned long long [usertype] *tpmi_rapl_regs @@ got void [noderef] __iomem * @@ drivers/powercap/intel_rapl_tpmi.c:141:41: sparse: expected unsigned long long [usertype] *tpmi_rapl_regs drivers/powercap/intel_rapl_tpmi.c:141:41: sparse: got void [noderef] __iomem * Fix the problem by using a union to save the registers instead. Suggested-by: David Laight Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202307031405.dy3druuy-lkp@intel.com/ Tested-by: Wang Wendy Signed-off-by: Zhang Rui [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index e6936cb25047..33f21bd85dbf 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -100,10 +100,16 @@ struct rapl_package; #define RAPL_DOMAIN_NAME_LENGTH 16 +union rapl_reg { + void __iomem *mmio; + u32 msr; + u64 val; +}; + struct rapl_domain { char name[RAPL_DOMAIN_NAME_LENGTH]; enum rapl_domain_type id; - u64 regs[RAPL_DOMAIN_REG_MAX]; + union rapl_reg regs[RAPL_DOMAIN_REG_MAX]; struct powercap_zone power_zone; struct rapl_domain_data rdd; struct rapl_power_limit rpl[NR_POWER_LIMITS]; @@ -116,7 +122,7 @@ struct rapl_domain { }; struct reg_action { - u64 reg; + union rapl_reg reg; u64 mask; u64 value; int err; @@ -143,8 +149,8 @@ struct rapl_if_priv { enum rapl_if_type type; struct powercap_control_type *control_type; enum cpuhp_state pcap_rapl_online; - u64 reg_unit; - u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; + union rapl_reg reg_unit; + union rapl_reg regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; int limits[RAPL_DOMAIN_MAX]; int (*read_raw)(int id, struct reg_action *ra); int (*write_raw)(int id, struct reg_action *ra); -- cgit v1.2.3 From 6ad0f2f91ad14ba0a3c2990c054fd6fbe8100429 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 25 Jul 2023 22:21:08 +0800 Subject: Drivers: hv: vmbus: Remove unused extern declaration vmbus_ontimer() Since commit 30fbee49b071 ("Staging: hv: vmbus: Get rid of the unused function vmbus_ontimer()") this is not used anymore, so can remove it. Signed-off-by: YueHaibing Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20230725142108.27280-1-yuehaibing@huawei.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index bfbc37ce223b..3ac3974b3c78 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1239,9 +1239,6 @@ extern int vmbus_recvpacket_raw(struct vmbus_channel *channel, u32 *buffer_actual_len, u64 *requestid); - -extern void vmbus_ontimer(unsigned long data); - /* Base driver object */ struct hv_driver { const char *name; -- cgit v1.2.3 From 3e3271549670783be20e233a2b78a87a0b04c715 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 5 Aug 2023 12:25:01 -0700 Subject: vfs: get rid of old '->iterate' directory operation All users now just use '->iterate_shared()', which only takes the directory inode lock for reading. Filesystems that never got convered to shared mode now instead use a wrapper that drops the lock, re-takes it in write mode, calls the old function, and then downgrades the lock back to read mode. This way the VFS layer and other callers no longer need to care about filesystems that never got converted to the modern era. The filesystems that use the new wrapper are ceph, coda, exfat, jfs, ntfs, ocfs2, overlayfs, and vboxsf. Honestly, several of them look like they really could just iterate their directories in shared mode and skip the wrapper entirely, but the point of this change is to not change semantics or fix filesystems that haven't been fixed in the last 7+ years, but to finally get rid of the dual iterators. Signed-off-by: Linus Torvalds Signed-off-by: Christian Brauner --- include/linux/fs.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6867512907d6..562f2623c9c9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1780,7 +1780,6 @@ struct file_operations { ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); - int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); @@ -1817,6 +1816,13 @@ struct file_operations { unsigned int poll_flags); } __randomize_layout; +/* Wrap a directory iterator that needs exclusive inode access */ +int wrap_directory_iterator(struct file *, struct dir_context *, + int (*) (struct file *, struct dir_context *)); +#define WRAP_DIR_ITER(x) \ + static int shared_##x(struct file *file , struct dir_context *ctx) \ + { return wrap_directory_iterator(file, ctx, x); } + struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); -- cgit v1.2.3 From 554b841d470338a3b1d6335b14ee1cd0c8f5d754 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 2 Aug 2023 07:25:33 -0500 Subject: tpm: Disable RNG for all AMD fTPMs The TPM RNG functionality is not necessary for entropy when the CPU already supports the RDRAND instruction. The TPM RNG functionality was previously disabled on a subset of AMD fTPM series, but reports continue to show problems on some systems causing stutter root caused to TPM RNG functionality. Expand disabling TPM RNG use for all AMD fTPMs whether they have versions that claim to have fixed or not. To accomplish this, move the detection into part of the TPM CRB registration and add a flag indicating that the TPM should opt-out of registration to hwrng. Cc: stable@vger.kernel.org # 6.1.y+ Fixes: b006c439d58d ("hwrng: core - start hwrng kthread also for untrusted sources") Fixes: f1324bbc4011 ("tpm: disable hwrng for fTPM on some AMD designs") Reported-by: daniil.stas@posteo.net Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217719 Reported-by: bitlord0xff@gmail.com Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217212 Signed-off-by: Mario Limonciello Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 6a1e8f157255..4ee9d13749ad 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -283,6 +283,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), + TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -- cgit v1.2.3 From d74f714896fd6268882789ba28e52c9145951403 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Aug 2023 11:03:28 -0600 Subject: block: get rid of unused plug->nowait flag This was introduced to add a plug based way of signaling nowait issues, but we have since moved on from that. Kill the old dead code, nobody is setting it anymore. Reviewed-by: Chaitanya Kulkarni Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ed44a997f629..87d94be7825a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -969,7 +969,6 @@ struct blk_plug { bool multiple_queues; bool has_elevator; - bool nowait; struct list_head cb_list; /* md requires an unplug callback */ }; -- cgit v1.2.3 From 2bc057692599a5b3dc93d75a3dff34f72576355d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Aug 2023 11:06:17 -0600 Subject: block: don't make REQ_POLLED imply REQ_NOWAIT Normally these two flags do go together, as the issuer of polled IO generally cannot wait for resources that will get freed as part of IO completion. This is because that very task is the one that will complete the request and free those resources, hence that would introduce a deadlock. But it is possible to have someone else issue the polled IO, eg via io_uring if the request is punted to io-wq. For that case, it's fine to have the task block on IO submission, as it is not the same task that will be completing the IO. It's completely up to the caller to ask for both polled and nowait IO separately! If we don't allow polled IO where IOCB_NOWAIT isn't set in the kiocb, then we can run into repeated -EAGAIN submissions and not make any progress. Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index c4f5b5228105..11984ed29cb8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -791,7 +791,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page, static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) { bio->bi_opf |= REQ_POLLED; - if (!is_sync_kiocb(kiocb)) + if (kiocb->ki_flags & IOCB_NOWAIT) bio->bi_opf |= REQ_NOWAIT; } -- cgit v1.2.3 From 809e4dc71a0f2b8d2836035d98603694fff11d5d Mon Sep 17 00:00:00 2001 From: Xu Kuohai Date: Fri, 4 Aug 2023 03:37:38 -0400 Subject: bpf, sockmap: Fix bug that strp_done cannot be called strp_done is only called when psock->progs.stream_parser is not NULL, but stream_parser was set to NULL by sk_psock_stop_strp(), called by sk_psock_drop() earlier. So, strp_done can never be called. Introduce SK_PSOCK_RX_ENABLED to mark whether there is strp on psock. Change the condition for calling strp_done from judging whether stream_parser is set to judging whether this flag is set. This flag is only set once when strp_init() succeeds, and will never be cleared later. Fixes: c0d95d3380ee ("bpf, sockmap: Re-evaluate proto ops when psock is removed from sockmap") Signed-off-by: Xu Kuohai Reviewed-by: John Fastabend Link: https://lore.kernel.org/r/20230804073740.194770-3-xukuohai@huaweicloud.com Signed-off-by: Martin KaFai Lau --- 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 054d7911bfc9..c1637515a8a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -62,6 +62,7 @@ struct sk_psock_progs { enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, + SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { -- cgit v1.2.3 From a57c27c7ad85c420b7de44c6ee56692d51709dda Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 9 Aug 2023 15:04:59 +0200 Subject: x86/speculation: Add cpu_show_gds() prototype The newly added function has two definitions but no prototypes: drivers/base/cpu.c:605:16: error: no previous prototype for 'cpu_show_gds' [-Werror=missing-prototypes] Add a declaration next to the other ones for this file to avoid the warning. Fixes: 8974eb588283b ("x86/speculation: Add Gather Data Sampling mitigation") Signed-off-by: Arnd Bergmann Signed-off-by: Dave Hansen Tested-by: Daniel Sneddon Cc: stable@kernel.org Link: https://lore.kernel.org/all/20230809130530.1913368-1-arnd%40kernel.org --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 23ac87be1ff1..e006c719182b 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -72,6 +72,8 @@ extern ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_gds(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From c8afaa1b0f8bc93d013ab2ea6b9649958af3f1d3 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Sat, 12 Aug 2023 18:15:54 +0200 Subject: locking: remove spin_lock_prefetch The only remaining consumer is new_inode, where it showed up in 2001 as commit c37fa164f793 ("v2.4.9.9 -> v2.4.9.10") in a historical repo [1] with a changelog which does not mention it. Since then the line got only touched up to keep compiling. While it may have been of benefit back in the day, it is guaranteed to at best not get in the way in the multicore setting -- as the code performs *a lot* of work between the prefetch and actual lock acquire, any contention means the cacheline is already invalid by the time the routine calls spin_lock(). It adds spurious traffic, for short. On top of it prefetch is notoriously tricky to use for single-threaded purposes, making it questionable from the get go. As such, remove it. I admit upfront I did not see value in benchmarking this change, but I can do it if that is deemed appropriate. Removal from new_inode and of the entire thing are in the same patch as requested by Linus, so whatever weird looks can be directed at that guy. Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/fs/inode.c?id=c37fa164f793735b32aa3f53154ff1a7659e6442 [1] Signed-off-by: Mateusz Guzik Signed-off-by: Linus Torvalds --- include/linux/prefetch.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h index b83a3f944f28..b068e2e60939 100644 --- a/include/linux/prefetch.h +++ b/include/linux/prefetch.h @@ -25,11 +25,10 @@ struct page; prefetch() should be defined by the architecture, if not, the #define below provides a no-op define. - There are 3 prefetch() macros: + There are 2 prefetch() macros: prefetch(x) - prefetches the cacheline at "x" for read prefetchw(x) - prefetches the cacheline at "x" for write - spin_lock_prefetch(x) - prefetches the spinlock *x for taking there is also PREFETCH_STRIDE which is the architecure-preferred "lookahead" size for prefetching streamed operations. @@ -44,10 +43,6 @@ struct page; #define prefetchw(x) __builtin_prefetch(x,1) #endif -#ifndef ARCH_HAS_SPINLOCK_PREFETCH -#define spin_lock_prefetch(x) prefetchw(x) -#endif - #ifndef PREFETCH_STRIDE #define PREFETCH_STRIDE (4*L1_CACHE_BYTES) #endif -- cgit v1.2.3