From 7bb5da0d490b2d836c5218f5186ee588d2145310 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 30 Jun 2022 23:32:57 +0100 Subject: kexec: turn all kexec_mutex acquisitions into trylocks Patch series "kexec, panic: Making crash_kexec() NMI safe", v4. This patch (of 2): Most acquistions of kexec_mutex are done via mutex_trylock() - those were a direct "translation" from: 8c5a1cf0ad3a ("kexec: use a mutex for locking rather than xchg()") there have however been two additions since then that use mutex_lock(): crash_get_memory_size() and crash_shrink_memory(). A later commit will replace said mutex with an atomic variable, and locking operations will become atomic_cmpxchg(). Rather than having those mutex_lock() become while (atomic_cmpxchg(&lock, 0, 1)), turn them into trylocks that can return -EBUSY on acquisition failure. This does halve the printable size of the crash kernel, but that's still neighbouring 2G for 32bit kernels which should be ample enough. Link: https://lkml.kernel.org/r/20220630223258.4144112-1-vschneid@redhat.com Link: https://lkml.kernel.org/r/20220630223258.4144112-2-vschneid@redhat.com Signed-off-by: Valentin Schneider Cc: Arnd Bergmann Cc: "Eric W . Biederman" Cc: Juri Lelli Cc: Luis Claudio R. Goncalves Cc: Miaohe Lin Cc: Petr Mladek Cc: Sebastian Andrzej Siewior Cc: Thomas Gleixner Cc: Baoquan He Signed-off-by: Andrew Morton --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 13e6c4b58f07..41a686996aaa 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -427,7 +427,7 @@ extern int kexec_load_disabled; extern bool kexec_in_progress; int crash_shrink_memory(unsigned long new_size); -size_t crash_get_memory_size(void); +ssize_t crash_get_memory_size(void); #ifndef arch_kexec_protect_crashkres /* -- cgit v1.2.3 From 2be9880dc87342dc7ae459c9ea5c9ee2a45b33d8 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 19 Aug 2022 09:44:06 +0800 Subject: kernel: exit: cleanup release_thread() Only x86 has own release_thread(), introduce a new weak release_thread() function to clean empty definitions in other ARCHs. Link: https://lkml.kernel.org/r/20220819014406.32266-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Guo Ren [csky] Acked-by: Russell King (Oracle) Acked-by: Geert Uytterhoeven Acked-by: Brian Cain Acked-by: Michael Ellerman [powerpc] Acked-by: Stafford Horne [openrisc] Acked-by: Catalin Marinas [arm64] Acked-by: Huacai Chen [LoongArch] Cc: Alexander Gordeev Cc: Anton Ivanov Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Chris Zankel Cc: Dave Hansen Cc: "David S. Miller" Cc: Dinh Nguyen Cc: Guo Ren [csky] Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Bottomley Cc: Johannes Berg Cc: Jonas Bonn Cc: Matt Turner Cc: Max Filippov Cc: Michal Simek Cc: Nicholas Piggin Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Richard Henderson Cc: Richard Weinberger Cc: Rich Felker Cc: Stefan Kristiansson Cc: Sven Schnelle Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Xuerui Wang Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/alpha/include/asm/processor.h | 2 -- arch/alpha/kernel/process.c | 5 ----- arch/arc/include/asm/processor.h | 3 --- arch/arm/include/asm/processor.h | 3 --- arch/arm/kernel/process.c | 4 ---- arch/arm64/include/asm/processor.h | 3 --- arch/arm64/kernel/process.c | 4 ---- arch/csky/include/asm/processor.h | 5 ----- arch/hexagon/include/asm/processor.h | 4 ---- arch/hexagon/kernel/process.c | 7 ------- arch/ia64/include/asm/processor.h | 7 ------- arch/loongarch/include/asm/processor.h | 3 --- arch/m68k/include/asm/processor.h | 5 ----- arch/microblaze/include/asm/processor.h | 5 ----- arch/mips/include/asm/processor.h | 3 --- arch/nios2/include/asm/processor.h | 5 ----- arch/openrisc/include/asm/processor.h | 1 - arch/openrisc/kernel/process.c | 4 ---- arch/parisc/include/asm/processor.h | 3 --- arch/parisc/kernel/process.c | 4 ---- arch/powerpc/include/asm/processor.h | 1 - arch/powerpc/kernel/process.c | 5 ----- arch/riscv/include/asm/processor.h | 5 ----- arch/s390/include/asm/processor.h | 3 --- arch/sh/include/asm/processor_32.h | 3 --- arch/sh/kernel/process_32.c | 5 ----- arch/sparc/include/asm/processor_32.h | 3 --- arch/sparc/include/asm/processor_64.h | 3 --- arch/um/include/asm/processor-generic.h | 4 ---- arch/x86/include/asm/processor.h | 3 --- arch/xtensa/include/asm/processor.h | 3 --- include/linux/sched/task.h | 3 +++ kernel/exit.c | 4 ++++ 33 files changed, 7 insertions(+), 118 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index 43e234c518b1..714abe494e5f 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -36,8 +36,6 @@ extern void start_thread(struct pt_regs *, unsigned long, unsigned long); /* Free all resources held by a thread. */ struct task_struct; -extern void release_thread(struct task_struct *); - unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index e2e25f8b5e76..dbf1bc5e2ad2 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -225,11 +225,6 @@ flush_thread(void) current_thread_info()->pcb.unique = 0; } -void -release_thread(struct task_struct *dead_task) -{ -} - /* * Copy architecture-specific thread state */ diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 54db9d7bb562..fb844fce1ab6 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -43,9 +43,6 @@ struct task_struct; #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1) -/* Free all resources held by a thread */ -#define release_thread(thread) do { } while (0) - /* * A lot of busy-wait loops in SMP are based off of non-volatile data otherwise * get optimised away by gcc diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index bdc35c0e8dfb..326864f79d18 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -81,9 +81,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, /* Forward declaration, a strange C thing */ struct task_struct; -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - unsigned long __get_wchan(struct task_struct *p); #define task_pt_regs(p) \ diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 3d9cace63884..712d3e6d9be9 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -232,10 +232,6 @@ void flush_thread(void) thread_notify(THREAD_NOTIFY_FLUSH, thread); } -void release_thread(struct task_struct *dead_task) -{ -} - asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 86eb0bfe3b38..4cfb4cd1d475 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -323,9 +323,6 @@ static inline bool is_ttbr1_addr(unsigned long addr) /* Forward declaration, a strange C thing */ struct task_struct; -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - unsigned long __get_wchan(struct task_struct *p); void update_sctlr_el1(u64 sctlr); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 92bcc1768f0b..9015f49c206e 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -279,10 +279,6 @@ void flush_thread(void) flush_tagged_addr_state(); } -void release_thread(struct task_struct *dead_task) -{ -} - void arch_release_task_struct(struct task_struct *tsk) { fpsimd_release_task(tsk); diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h index 9638206bc44f..63ad71fab30d 100644 --- a/arch/csky/include/asm/processor.h +++ b/arch/csky/include/asm/processor.h @@ -69,11 +69,6 @@ do { \ /* Forward declaration, a strange C thing */ struct task_struct; -/* Free all resources held by a thread. */ -static inline void release_thread(struct task_struct *dead_task) -{ -} - /* Prepare to copy thread state - unlazy all lazy status */ #define prepare_to_copy(tsk) do { } while (0) diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h index 615f7e49968e..0cd39c2cdf8f 100644 --- a/arch/hexagon/include/asm/processor.h +++ b/arch/hexagon/include/asm/processor.h @@ -60,10 +60,6 @@ struct thread_struct { #define KSTK_EIP(tsk) (pt_elr(task_pt_regs(tsk))) #define KSTK_ESP(tsk) (pt_psp(task_pt_regs(tsk))) -/* Free all resources held by a thread; defined in process.c */ -extern void release_thread(struct task_struct *dead_task); - -/* Get wait channel for task P. */ extern unsigned long __get_wchan(struct task_struct *p); /* The following stuff is pretty HEXAGON specific. */ diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index f0552f98a7ba..e15eeaebd785 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -112,13 +112,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) return 0; } -/* - * Release any architecture-specific resources locked by thread - */ -void release_thread(struct task_struct *dead_task) -{ -} - /* * Some archs flush debug and FPU info here */ diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index 757c2f6d8d4b..d1978e004054 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -318,13 +318,6 @@ struct thread_struct { struct mm_struct; struct task_struct; -/* - * Free all resources held by a thread. This is called after the - * parent of DEAD_TASK has collected the exit status of the task via - * wait(). - */ -#define release_thread(dead_task) - /* Get wait channel for task P. */ extern unsigned long __get_wchan (struct task_struct *p); diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h index 1c4b4308378d..6954dc5d24e9 100644 --- a/arch/loongarch/include/asm/processor.h +++ b/arch/loongarch/include/asm/processor.h @@ -176,9 +176,6 @@ struct thread_struct { struct task_struct; -/* Free all resources held by a thread. */ -#define release_thread(thread) do { } while (0) - enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_HALT, IDLE_NOMWAIT, IDLE_POLL}; extern unsigned long boot_option_idle_override; diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index d86b4009880b..7a2da780830b 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -145,11 +145,6 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc, /* Forward declaration, a strange C thing */ struct task_struct; -/* Free all resources held by a thread. */ -static inline void release_thread(struct task_struct *dead_task) -{ -} - unsigned long __get_wchan(struct task_struct *p); void show_registers(struct pt_regs *regs); diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 7e9e92670df3..4e193c7550df 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -63,11 +63,6 @@ struct thread_struct { .pgdir = swapper_pg_dir, \ } -/* Free all resources held by a thread. */ -static inline void release_thread(struct task_struct *dead_task) -{ -} - unsigned long __get_wchan(struct task_struct *p); /* The size allocated for kernel stacks. This _must_ be a power of two! */ diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 4bb24579d12e..3fde1ff72bd1 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -344,9 +344,6 @@ struct thread_struct { struct task_struct; -/* Free all resources held by a thread. */ -#define release_thread(thread) do { } while(0) - /* * Do necessary setup to start up a newly executed thread. */ diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h index b8125dfbcad2..8916d93d5c2d 100644 --- a/arch/nios2/include/asm/processor.h +++ b/arch/nios2/include/asm/processor.h @@ -64,11 +64,6 @@ extern void start_thread(struct pt_regs *regs, unsigned long pc, struct task_struct; -/* Free all resources held by a thread. */ -static inline void release_thread(struct task_struct *dead_task) -{ -} - extern unsigned long __get_wchan(struct task_struct *p); #define task_pt_regs(p) \ diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index aa1699c18add..ed9efb430afa 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -72,7 +72,6 @@ struct thread_struct { void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp); -void release_thread(struct task_struct *); unsigned long __get_wchan(struct task_struct *p); #define cpu_relax() barrier() diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 52dc983ddeba..f94b5ec06786 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -125,10 +125,6 @@ void show_regs(struct pt_regs *regs) show_registers(regs); } -void release_thread(struct task_struct *dead_task) -{ -} - /* * Copy the thread-specific (arch specific) info from the current * process to the new one p diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 4621ceb51314..a608970b249a 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -266,9 +266,6 @@ on downward growing arches, it looks like this: struct mm_struct; -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - extern unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.regs.iaoq[0]) diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 7c37e09c92da..3db0e97e6c06 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -146,10 +146,6 @@ void flush_thread(void) */ } -void release_thread(struct task_struct *dead_task) -{ -} - /* * Idle thread support * diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index fdfaae194ddd..92e332415d02 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -75,7 +75,6 @@ extern int _chrp_type; struct task_struct; void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp); -void release_thread(struct task_struct *); #define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET] #define TS_CKFPR(i) ckfp_state.fpr[i][TS_FPROFFSET] diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 0fbda89cd1bb..991cda25b9a9 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1655,11 +1655,6 @@ EXPORT_SYMBOL_GPL(set_thread_tidr); #endif /* CONFIG_PPC64 */ -void -release_thread(struct task_struct *t) -{ -} - /* * this gets called so that we can store coprocessor state into memory and * copy the current task into the new thread. diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 19eedd4af4cd..94a0590c6971 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -65,11 +65,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, extern void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp); -/* Free all resources held by a thread. */ -static inline void release_thread(struct task_struct *dead_task) -{ -} - extern unsigned long __get_wchan(struct task_struct *p); diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index bd66f8e34949..c52fe651eeba 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -186,9 +186,6 @@ struct pt_regs; void show_registers(struct pt_regs *regs); void show_cacheinfo(struct seq_file *m); -/* Free all resources held by a thread. */ -static inline void release_thread(struct task_struct *tsk) { } - /* Free guarded storage control block */ void guarded_storage_release(struct task_struct *tsk); void gs_load_bc_cb(struct pt_regs *regs); diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 45240ec6b85a..27aebf1e75a2 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -127,9 +127,6 @@ struct task_struct; extern void start_thread(struct pt_regs *regs, unsigned long new_pc, unsigned long new_sp); -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - /* * FPU lazy state save handling. */ diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index a808843375e7..92b6649d4929 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -84,11 +84,6 @@ void flush_thread(void) #endif } -void release_thread(struct task_struct *dead_task) -{ - /* do nothing */ -} - asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index b26c35336b51..ba8b70ffec08 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -80,9 +80,6 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc, : "memory"); } -/* Free all resources held by a thread. */ -#define release_thread(tsk) do { } while(0) - unsigned long __get_wchan(struct task_struct *); #define task_pt_regs(tsk) ((tsk)->thread.kregs) diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index 89850dff6b03..2667f35d5ea5 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -176,9 +176,6 @@ do { \ regs->tstate &= ~TSTATE_PEF; \ } while (0) -/* Free all resources held by a thread. */ -#define release_thread(tsk) do { } while (0) - unsigned long __get_wchan(struct task_struct *task); #define task_pt_regs(tsk) (task_thread_info(tsk)->kregs) diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index d0fc1862da95..bb5f06480da9 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -55,10 +55,6 @@ struct thread_struct { .request = { 0 } \ } -static inline void release_thread(struct task_struct *task) -{ -} - /* * User space process size: 3GB (default). */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 356308c73951..67c9d73b31fa 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -587,9 +587,6 @@ static inline void load_sp0(unsigned long sp0) #endif /* CONFIG_PARAVIRT_XXL */ -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - unsigned long __get_wchan(struct task_struct *p); /* diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 76bc63127c66..5abde43c570c 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -221,9 +221,6 @@ struct thread_struct { struct task_struct; struct mm_struct; -/* Free all resources held by a thread. */ -#define release_thread(thread) do { } while(0) - extern unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 81cab4b01edc..d6c48163c6de 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -127,6 +127,9 @@ static inline void put_task_struct_many(struct task_struct *t, int nr) void put_task_struct_rcu_user(struct task_struct *task); +/* Free all architecture-specific resources held by a thread. */ +void release_thread(struct task_struct *dead_task); + #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else diff --git a/kernel/exit.c b/kernel/exit.c index 84021b24f79e..f4b7b058f4e6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -183,6 +183,10 @@ void put_task_struct_rcu_user(struct task_struct *task) call_rcu(&task->rcu, delayed_put_task_struct); } +void __weak release_thread(struct task_struct *dead_task) +{ +} + void release_task(struct task_struct *p) { struct task_struct *leader; -- cgit v1.2.3 From da3f52ba359590d8eb465ae0d8b6e11d6fd9432f Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 21 Aug 2022 21:30:11 +0200 Subject: iversion: use atomic64_try_cmpxchg) Use atomic64_try_cmpxchg instead of atomic64_cmpxchg (*ptr, old, new) == old in inode_set_max_iversion_raw, inode_maybe_inc_version and inode_query_iversion. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails, enabling further code simplifications. The loop in inode_maybe_inc_iversion improves from: 5563: 48 89 ca mov %rcx,%rdx 5566: 48 89 c8 mov %rcx,%rax 5569: 48 83 e2 fe and $0xfffffffffffffffe,%rdx 556d: 48 83 c2 02 add $0x2,%rdx 5571: f0 48 0f b1 16 lock cmpxchg %rdx,(%rsi) 5576: 48 39 c1 cmp %rax,%rcx 5579: 0f 84 85 fc ff ff je 5204 <...> 557f: 48 89 c1 mov %rax,%rcx 5582: eb df jmp 5563 <...> to: 5563: 48 89 c2 mov %rax,%rdx 5566: 48 83 e2 fe and $0xfffffffffffffffe,%rdx 556a: 48 83 c2 02 add $0x2,%rdx 556e: f0 48 0f b1 11 lock cmpxchg %rdx,(%rcx) 5573: 0f 84 8b fc ff ff je 5204 <...> 5579: eb e8 jmp 5563 <...> Link: https://lkml.kernel.org/r/20220821193011.88208-1-ubizjak@gmail.com Signed-off-by: Uros Bizjak Signed-off-by: Andrew Morton --- include/linux/iversion.h | 32 +++++++++----------------------- 1 file changed, 9 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/iversion.h b/include/linux/iversion.h index 3bfebde5a1a6..eb5a15810169 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -123,17 +123,12 @@ inode_peek_iversion_raw(const struct inode *inode) static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { - u64 cur, old; + u64 cur = inode_peek_iversion_raw(inode); - cur = inode_peek_iversion_raw(inode); - for (;;) { + do { if (cur > val) break; - old = atomic64_cmpxchg(&inode->i_version, cur, val); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** @@ -197,7 +192,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val) static inline bool inode_maybe_inc_iversion(struct inode *inode, bool force) { - u64 cur, old, new; + u64 cur, new; /* * The i_version field is not strictly ordered with any other inode @@ -211,19 +206,14 @@ inode_maybe_inc_iversion(struct inode *inode, bool force) */ smp_mb(); cur = inode_peek_iversion_raw(inode); - for (;;) { + do { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; - - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return true; } @@ -304,10 +294,10 @@ inode_peek_iversion(const struct inode *inode) static inline u64 inode_query_iversion(struct inode *inode) { - u64 cur, old, new; + u64 cur, new; cur = inode_peek_iversion_raw(inode); - for (;;) { + do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* @@ -320,11 +310,7 @@ inode_query_iversion(struct inode *inode) } new = cur | I_VERSION_QUERIED; - old = atomic64_cmpxchg(&inode->i_version, cur, new); - if (likely(old == cur)) - break; - cur = old; - } + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } -- cgit v1.2.3 From e1d7c7609ae0933b59840390c1b207ac0a925c8b Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 22 Aug 2022 16:38:51 +0200 Subject: bitops: use try_cmpxchg in set_mask_bits and bit_clear_unless Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in set_mask_bits and bit_clear_unless. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails, enabling further code simplifications. Link: https://lkml.kernel.org/r/20220822143851.3290-1-ubizjak@gmail.com Signed-off-by: Uros Bizjak Signed-off-by: Andrew Morton --- include/linux/bitops.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 3b89c64bcfd8..fb24a513d917 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -328,10 +328,10 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ new__ = (old__ & ~mask__) | bits__; \ - } while (cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ old__; \ }) @@ -343,11 +343,12 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ typeof(*(ptr)) old__, new__; \ \ + old__ = READ_ONCE(*(ptr)); \ do { \ - old__ = READ_ONCE(*(ptr)); \ + if (old__ & test__) \ + break; \ new__ = old__ & ~clear__; \ - } while (!(old__ & test__) && \ - cmpxchg(ptr, old__, new__) != old__); \ + } while (!try_cmpxchg(ptr, &old__, new__)); \ \ !(old__ & test__); \ }) -- cgit v1.2.3 From 7b9e664beb237d90bc600f117668227af5ce53ae Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 30 Aug 2022 20:27:13 +0300 Subject: asm-generic: make parameter types consistent in _unaligned_be48() There is a convention to use internal kernel types, so replace __u8 by u8. Link: https://lkml.kernel.org/r/20220830172713.43686-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Keith Busch Cc: Arnd Bergmann Signed-off-by: Andrew Morton --- include/asm-generic/unaligned.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index df30f11b4a46..699650f81970 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -126,7 +126,7 @@ static inline void put_unaligned_le24(const u32 val, void *p) __put_unaligned_le24(val, p); } -static inline void __put_unaligned_be48(const u64 val, __u8 *p) +static inline void __put_unaligned_be48(const u64 val, u8 *p) { *p++ = val >> 40; *p++ = val >> 32; -- cgit v1.2.3 From 8f824b4abd31c5ea32ae1d6725c47bdb247d18da Mon Sep 17 00:00:00 2001 From: Jiangshan Yi Date: Mon, 5 Sep 2022 10:10:34 +0800 Subject: init.h: fix spelling typo in comment Fix spelling typo in comment. Link: https://lkml.kernel.org/r/20220905021034.947701-1-13667453960@163.com Signed-off-by: Jiangshan Yi Reported-by: k2ci Signed-off-by: Andrew Morton --- include/linux/init.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index baf0b29a7010..3254766ebbf2 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -134,7 +134,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -/* Used for contructor calls. */ +/* Used for constructor calls. */ typedef void (*ctor_fn_t)(void); struct file_system_type; -- cgit v1.2.3 From 5ca14835dc429c09fefb290f60343fe266382760 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 9 Sep 2022 13:57:41 -0700 Subject: fs: uninline inode_maybe_inc_iversion() It has many callsites and is large. text data bss dec hex filename 91796 15984 512 108292 1a704 mm/shmem.o-before 91180 15984 512 107676 1a49c mm/shmem.o-after Acked-by: Jeff Layton Cc: Chuck Lever Cc: Alexander Viro Cc: Hugh Dickins Signed-off-by: Andrew Morton --- fs/libfs.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/iversion.h | 46 +--------------------------------------------- 2 files changed, 47 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/fs/libfs.c b/fs/libfs.c index 31b0ddf01c31..682d56345a1c 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include /* sync_mapping_buffers */ #include @@ -1520,3 +1521,48 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) #endif } EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops); + +/** + * inode_maybe_inc_iversion - increments i_version + * @inode: inode with the i_version that should be updated + * @force: increment the counter even if it's not necessary? + * + * Every time the inode is modified, the i_version field must be seen to have + * changed by any observer. + * + * If "force" is set or the QUERIED flag is set, then ensure that we increment + * the value, and clear the queried flag. + * + * In the common case where neither is set, then we can return "false" without + * updating i_version. + * + * If this function returns false, and no other metadata has changed, then we + * can avoid logging the metadata. + */ +bool inode_maybe_inc_iversion(struct inode *inode, bool force) +{ + u64 cur, new; + + /* + * The i_version field is not strictly ordered with any other inode + * information, but the legacy inode_inc_iversion code used a spinlock + * to serialize increments. + * + * Here, we add full memory barriers to ensure that any de-facto + * ordering with other info is preserved. + * + * This barrier pairs with the barrier in inode_query_iversion() + */ + smp_mb(); + cur = inode_peek_iversion_raw(inode); + do { + /* If flag is clear then we needn't do anything */ + if (!force && !(cur & I_VERSION_QUERIED)) + return false; + + /* Since lowest bit is flag, add 2 to avoid it */ + new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; + } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); + return true; +} +EXPORT_SYMBOL(inode_maybe_inc_iversion); diff --git a/include/linux/iversion.h b/include/linux/iversion.h index eb5a15810169..e27bd4f55d84 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -172,51 +172,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val) I_VERSION_QUERIED); } -/** - * inode_maybe_inc_iversion - increments i_version - * @inode: inode with the i_version that should be updated - * @force: increment the counter even if it's not necessary? - * - * Every time the inode is modified, the i_version field must be seen to have - * changed by any observer. - * - * If "force" is set or the QUERIED flag is set, then ensure that we increment - * the value, and clear the queried flag. - * - * In the common case where neither is set, then we can return "false" without - * updating i_version. - * - * If this function returns false, and no other metadata has changed, then we - * can avoid logging the metadata. - */ -static inline bool -inode_maybe_inc_iversion(struct inode *inode, bool force) -{ - u64 cur, new; - - /* - * The i_version field is not strictly ordered with any other inode - * information, but the legacy inode_inc_iversion code used a spinlock - * to serialize increments. - * - * Here, we add full memory barriers to ensure that any de-facto - * ordering with other info is preserved. - * - * This barrier pairs with the barrier in inode_query_iversion() - */ - smp_mb(); - cur = inode_peek_iversion_raw(inode); - do { - /* If flag is clear then we needn't do anything */ - if (!force && !(cur & I_VERSION_QUERIED)) - return false; - - /* Since lowest bit is flag, add 2 to avoid it */ - new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; - } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); - return true; -} - +bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version -- cgit v1.2.3 From 5d0ce3595ab75330a15cec914096efbbb8b41e4a Mon Sep 17 00:00:00 2001 From: Jiebin Sun Date: Wed, 14 Sep 2022 03:25:37 +0800 Subject: percpu: add percpu_counter_add_local and percpu_counter_sub_local Patch series "/msg: mitigate the lock contention in ipc/msg", v6. Here are two patches to mitigate the lock contention in ipc/msg. The 1st patch is to add the new interface percpu_counter_add_local and percpu_counter_sub_local. The batch size in percpu_counter_add_batch should be very large in heavy writing and rare reading case. Add the "_local" version, and mostly it will do local adding, reduce the global updating and mitigate lock contention in writing. The 2nd patch is to use percpu_counter instead of atomic update in ipc/msg. The msg_bytes and msg_hdrs atomic counters are frequently updated when IPC msg queue is in heavy use, causing heavy cache bounce and overhead. Change them to percpu_counter greatly improve the performance. Since there is one percpu struct per namespace, additional memory cost is minimal. Reading of the count done in msgctl call, which is infrequent. So the need to sum up the counts in each CPU is infrequent. This patch (of 2): The batch size in percpu_counter_add_batch should be very large in heavy writing and rare reading case. Add the "_local" version, and mostly it will do local adding, reduce the global updating and mitigate lock contention in writing. Link: https://lkml.kernel.org/r/20220913192538.3023708-1-jiebin.sun@intel.com Link: https://lkml.kernel.org/r/20220913192538.3023708-2-jiebin.sun@intel.com Signed-off-by: Jiebin Sun Reviewed-by: Tim Chen Cc: Alexander Mikhalitsyn Cc: Alexey Gladkov Cc: Christoph Lameter Cc: Dennis Zhou Cc: "Eric W . Biederman" Cc: Manfred Spraul Cc: Shakeel Butt Cc: Tejun Heo Cc: Vasily Averin Cc: Davidlohr Bueso Signed-off-by: Andrew Morton --- include/linux/percpu_counter.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 01861eebed79..8ed5fba6d156 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -15,6 +15,9 @@ #include #include +/* percpu_counter batch for local add or sub */ +#define PERCPU_COUNTER_LOCAL_BATCH INT_MAX + #ifdef CONFIG_SMP struct percpu_counter { @@ -56,6 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } +/* + * With percpu_counter_add_local() and percpu_counter_sub_local(), counts + * are accumulated in local per cpu counter and not in fbc->count until + * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter + * write efficient. + * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be + * used to add up the counts from each CPU to account for all the local + * counts. So percpu_counter_add_local() and percpu_counter_sub_local() + * should be used when a counter is updated frequently and read rarely. + */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH); +} + static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); @@ -138,6 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) preempt_enable(); } +/* non-SMP percpu_counter_add_local is the same with percpu_counter_add */ +static inline void +percpu_counter_add_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add(fbc, amount); +} + static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { @@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) percpu_counter_add(fbc, -amount); } +static inline void +percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount) +{ + percpu_counter_add_local(fbc, -amount); +} + #endif /* _LINUX_PERCPU_COUNTER_H */ -- cgit v1.2.3 From 72d1e611082eda18689106a0c192f2827072713c Mon Sep 17 00:00:00 2001 From: Jiebin Sun Date: Wed, 14 Sep 2022 03:25:38 +0800 Subject: ipc/msg: mitigate the lock contention with percpu counter The msg_bytes and msg_hdrs atomic counters are frequently updated when IPC msg queue is in heavy use, causing heavy cache bounce and overhead. Change them to percpu_counter greatly improve the performance. Since there is one percpu struct per namespace, additional memory cost is minimal. Reading of the count done in msgctl call, which is infrequent. So the need to sum up the counts in each CPU is infrequent. Apply the patch and test the pts/stress-ng-1.4.0 -- system v message passing (160 threads). Score gain: 3.99x CPU: ICX 8380 x 2 sockets Core number: 40 x 2 physical cores Benchmark: pts/stress-ng-1.4.0 -- system v message passing (160 threads) [akpm@linux-foundation.org: coding-style cleanups] [jiebin.sun@intel.com: avoid negative value by overflow in msginfo] Link: https://lkml.kernel.org/r/20220920150809.4014944-1-jiebin.sun@intel.com [akpm@linux-foundation.org: fix min() warnings] Link: https://lkml.kernel.org/r/20220913192538.3023708-3-jiebin.sun@intel.com Signed-off-by: Jiebin Sun Reviewed-by: Tim Chen Cc: Alexander Mikhalitsyn Cc: Alexey Gladkov Cc: Christoph Lameter Cc: Davidlohr Bueso Cc: Dennis Zhou Cc: "Eric W . Biederman" Cc: Manfred Spraul Cc: Shakeel Butt Cc: Tejun Heo Cc: Vasily Averin Signed-off-by: Andrew Morton --- include/linux/ipc_namespace.h | 5 +++-- ipc/msg.c | 48 ++++++++++++++++++++++++++++++------------- ipc/namespace.c | 5 ++++- ipc/util.h | 4 ++-- 4 files changed, 43 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e3e8c8662b49..e8240cf2611a 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -11,6 +11,7 @@ #include #include #include +#include struct user_namespace; @@ -36,8 +37,8 @@ struct ipc_namespace { unsigned int msg_ctlmax; unsigned int msg_ctlmnb; unsigned int msg_ctlmni; - atomic_t msg_bytes; - atomic_t msg_hdrs; + struct percpu_counter percpu_msg_bytes; + struct percpu_counter percpu_msg_hdrs; size_t shm_ctlmax; size_t shm_ctlall; diff --git a/ipc/msg.c b/ipc/msg.c index a0d05775af2c..e4e0990e08f7 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -285,10 +286,10 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) rcu_read_unlock(); list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { - atomic_dec(&ns->msg_hdrs); + percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); free_msg(msg); } - atomic_sub(msq->q_cbytes, &ns->msg_bytes); + percpu_counter_sub_local(&ns->percpu_msg_bytes, msq->q_cbytes); ipc_update_pid(&msq->q_lspid, NULL); ipc_update_pid(&msq->q_lrpid, NULL); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); @@ -495,17 +496,22 @@ static int msgctl_info(struct ipc_namespace *ns, int msqid, msginfo->msgssz = MSGSSZ; msginfo->msgseg = MSGSEG; down_read(&msg_ids(ns).rwsem); - if (cmd == MSG_INFO) { + if (cmd == MSG_INFO) msginfo->msgpool = msg_ids(ns).in_use; - msginfo->msgmap = atomic_read(&ns->msg_hdrs); - msginfo->msgtql = atomic_read(&ns->msg_bytes); + max_idx = ipc_get_maxidx(&msg_ids(ns)); + up_read(&msg_ids(ns).rwsem); + if (cmd == MSG_INFO) { + msginfo->msgmap = min_t(int, + percpu_counter_sum(&ns->percpu_msg_hdrs), + INT_MAX); + msginfo->msgtql = min_t(int, + percpu_counter_sum(&ns->percpu_msg_bytes), + INT_MAX); } else { msginfo->msgmap = MSGMAP; msginfo->msgpool = MSGPOOL; msginfo->msgtql = MSGTQL; } - max_idx = ipc_get_maxidx(&msg_ids(ns)); - up_read(&msg_ids(ns).rwsem); return (max_idx < 0) ? 0 : max_idx; } @@ -935,8 +941,8 @@ static long do_msgsnd(int msqid, long mtype, void __user *mtext, list_add_tail(&msg->m_list, &msq->q_messages); msq->q_cbytes += msgsz; msq->q_qnum++; - atomic_add(msgsz, &ns->msg_bytes); - atomic_inc(&ns->msg_hdrs); + percpu_counter_add_local(&ns->percpu_msg_bytes, msgsz); + percpu_counter_add_local(&ns->percpu_msg_hdrs, 1); } err = 0; @@ -1159,8 +1165,8 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in msq->q_rtime = ktime_get_real_seconds(); ipc_update_pid(&msq->q_lrpid, task_tgid(current)); msq->q_cbytes -= msg->m_ts; - atomic_sub(msg->m_ts, &ns->msg_bytes); - atomic_dec(&ns->msg_hdrs); + percpu_counter_sub_local(&ns->percpu_msg_bytes, msg->m_ts); + percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); ss_wakeup(msq, &wake_q, false); goto out_unlock0; @@ -1297,20 +1303,34 @@ COMPAT_SYSCALL_DEFINE5(msgrcv, int, msqid, compat_uptr_t, msgp, } #endif -void msg_init_ns(struct ipc_namespace *ns) +int msg_init_ns(struct ipc_namespace *ns) { + int ret; + ns->msg_ctlmax = MSGMAX; ns->msg_ctlmnb = MSGMNB; ns->msg_ctlmni = MSGMNI; - atomic_set(&ns->msg_bytes, 0); - atomic_set(&ns->msg_hdrs, 0); + ret = percpu_counter_init(&ns->percpu_msg_bytes, 0, GFP_KERNEL); + if (ret) + goto fail_msg_bytes; + ret = percpu_counter_init(&ns->percpu_msg_hdrs, 0, GFP_KERNEL); + if (ret) + goto fail_msg_hdrs; ipc_init_ids(&ns->ids[IPC_MSG_IDS]); + return 0; + +fail_msg_hdrs: + percpu_counter_destroy(&ns->percpu_msg_bytes); +fail_msg_bytes: + return ret; } #ifdef CONFIG_IPC_NS void msg_exit_ns(struct ipc_namespace *ns) { + percpu_counter_destroy(&ns->percpu_msg_bytes); + percpu_counter_destroy(&ns->percpu_msg_hdrs); free_ipcs(ns, &msg_ids(ns), freeque); idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_MSG_IDS].key_ht); diff --git a/ipc/namespace.c b/ipc/namespace.c index e1fcaedba4fa..8316ea585733 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -66,8 +66,11 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, if (!setup_ipc_sysctls(ns)) goto fail_mq; + err = msg_init_ns(ns); + if (err) + goto fail_put; + sem_init_ns(ns); - msg_init_ns(ns); shm_init_ns(ns); return ns; diff --git a/ipc/util.h b/ipc/util.h index 2dd7ce0416d8..b2906e366539 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -64,7 +64,7 @@ static inline void mq_put_mnt(struct ipc_namespace *ns) { } #ifdef CONFIG_SYSVIPC void sem_init_ns(struct ipc_namespace *ns); -void msg_init_ns(struct ipc_namespace *ns); +int msg_init_ns(struct ipc_namespace *ns); void shm_init_ns(struct ipc_namespace *ns); void sem_exit_ns(struct ipc_namespace *ns); @@ -72,7 +72,7 @@ void msg_exit_ns(struct ipc_namespace *ns); void shm_exit_ns(struct ipc_namespace *ns); #else static inline void sem_init_ns(struct ipc_namespace *ns) { } -static inline void msg_init_ns(struct ipc_namespace *ns) { } +static inline int msg_init_ns(struct ipc_namespace *ns) { return 0; } static inline void shm_init_ns(struct ipc_namespace *ns) { } static inline void sem_exit_ns(struct ipc_namespace *ns) { } -- cgit v1.2.3 From 6a961bffd1c3505c13b4d33bbb8385fe08239cb8 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 2 Sep 2022 11:41:46 +0800 Subject: include/linux/entry-common.h: remove has_signal comment of arch_do_signal_or_restart() prototype The argument has_signal of arch_do_signal_or_restart() has been removed in commit 8ba62d37949e ("task_work: Call tracehook_notify_signal from get_signal on all architectures"), let us remove the related comment. Link: https://lkml.kernel.org/r/1662090106-5545-1-git-send-email-yangtiezhu@loongson.cn Fixes: 8ba62d37949e ("task_work: Call tracehook_notify_signal from get_signal on all architectures") Signed-off-by: Tiezhu Yang Reviewed-by: Kees Cook Signed-off-by: Andrew Morton --- include/linux/entry-common.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 84a466b176cf..d95ab85f96ba 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -253,7 +253,6 @@ static __always_inline void arch_exit_to_user_mode(void) { } /** * arch_do_signal_or_restart - Architecture specific signal delivery function * @regs: Pointer to currents pt_regs - * @has_signal: actual signal to handle * * Invoked from exit_to_user_mode_loop(). */ -- cgit v1.2.3