[PATCH AUTOSEL 4.19 077/158] x86/atomic: Fix smp_mb__{before,after}_atomic()

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

[ 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) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 Documentation/atomic_t.txt         | 3 +++
 arch/x86/include/asm/atomic.h      | 8 ++++----
 arch/x86/include/asm/atomic64_64.h | 8 ++++----
 arch/x86/include/asm/barrier.h     | 4 ++--
 4 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/Documentation/atomic_t.txt b/Documentation/atomic_t.txt
index 913396ac5824..ed0d814df7e0 100644
--- a/Documentation/atomic_t.txt
+++ b/Documentation/atomic_t.txt
@@ -177,6 +177,9 @@ These helper barriers exist because architectures have varying implicit
 ordering on their SMP atomic primitives. For example our TSO architectures
 provide full ordered atomics and these barriers are no-ops.
 
+NOTE: when the atomic RmW ops are fully ordered, they should also imply a
+compiler barrier.
+
 Thus:
 
   atomic_fetch_add();
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ce84388e540c..d266a4066289 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 5f851d92eecd..55ca027f8c1c 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 <asm-generic/barrier.h>
 
-- 
2.20.1




[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux