From 380ca1300affcd5385d43d2c933c393346295531 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Apr 2019 13:38:23 +0200 Subject: x86/atomic: Fix smp_mb__{before,after}_atomic() [ Upstream commit 69d927bba39517d0980462efc051875b7f4db185 ] Recent probing at the Linux Kernel Memory Model uncovered a 'surprise'. Strongly ordered architectures where the atomic RmW primitive implies full memory ordering and smp_mb__{before,after}_atomic() are a simple barrier() (such as x86) fail for: *x = 1; atomic_inc(u); smp_mb__after_atomic(); r0 = *y; Because, while the atomic_inc() implies memory order, it (surprisingly) does not provide a compiler barrier. This then allows the compiler to re-order like so: atomic_inc(u); *x = 1; smp_mb__after_atomic(); r0 = *y; Which the CPU is then allowed to re-order (under TSO rules) like: atomic_inc(u); r0 = *y; *x = 1; And this very much was not intended. Therefore strengthen the atomic RmW ops to include a compiler barrier. NOTE: atomic_{or,and,xor} and the bitops already had the compiler barrier. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar Signed-off-by: Sasha Levin --- arch/x86/include/asm/atomic.h | 8 ++++---- arch/x86/include/asm/atomic64_64.h | 8 ++++---- arch/x86/include/asm/barrier.h | 4 ++-- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index ea3d95275b43..115127c7ad28 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -54,7 +54,7 @@ static __always_inline void arch_atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) - : "ir" (i)); + : "ir" (i) : "memory"); } /** @@ -68,7 +68,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) - : "ir" (i)); + : "ir" (i) : "memory"); } /** @@ -95,7 +95,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" - : "+m" (v->counter)); + : "+m" (v->counter) :: "memory"); } #define arch_atomic_inc arch_atomic_inc @@ -108,7 +108,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v) static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" - : "+m" (v->counter)); + : "+m" (v->counter) :: "memory"); } #define arch_atomic_dec arch_atomic_dec diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index dadc20adba21..5e86c0d68ac1 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -45,7 +45,7 @@ static __always_inline void arch_atomic64_add(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "addq %1,%0" : "=m" (v->counter) - : "er" (i), "m" (v->counter)); + : "er" (i), "m" (v->counter) : "memory"); } /** @@ -59,7 +59,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "subq %1,%0" : "=m" (v->counter) - : "er" (i), "m" (v->counter)); + : "er" (i), "m" (v->counter) : "memory"); } /** @@ -87,7 +87,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) - : "m" (v->counter)); + : "m" (v->counter) : "memory"); } #define arch_atomic64_inc arch_atomic64_inc @@ -101,7 +101,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) - : "m" (v->counter)); + : "m" (v->counter) : "memory"); } #define arch_atomic64_dec arch_atomic64_dec diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 14de0432d288..84f848c2541a 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -80,8 +80,8 @@ do { \ }) /* Atomic operations are already serializing on x86 */ -#define __smp_mb__before_atomic() barrier() -#define __smp_mb__after_atomic() barrier() +#define __smp_mb__before_atomic() do { } while (0) +#define __smp_mb__after_atomic() do { } while (0) #include -- cgit v1.2.3