From a9ebf306f52c756c4f9e50ee9a60cd6389d71344 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 1 Feb 2017 16:39:38 +0100 Subject: locking/atomic: Introduce atomic_try_cmpxchg() Add a new cmpxchg interface: bool try_cmpxchg(u{8,16,32,64} *ptr, u{8,16,32,64} *val, u{8,16,32,64} new); Where the boolean returns the result of the compare; and thus if the exchange happened; and in case of failure, the new value of *ptr is returned in *val. This allows simplification/improvement of loops like: for (;;) { new = val $op $imm; old = cmpxchg(ptr, val, new); if (old == val) break; val = old; } into: do { } while (!try_cmpxchg(ptr, &val, val $op $imm)); while also generating better code (GCC6 and onwards). Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cmpxchg.h | 69 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) (limited to 'arch/x86/include/asm/cmpxchg.h') diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 97848cdfcb1a..fb961db51a2a 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -153,6 +153,75 @@ extern void __add_wrong_size(void) #define cmpxchg_local(ptr, old, new) \ __cmpxchg_local(ptr, old, new, sizeof(*(ptr))) + +#define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock) \ +({ \ + bool success; \ + __typeof__(_ptr) _old = (_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(_ptr); \ + asm volatile(lock "cmpxchgb %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "q" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(_ptr); \ + asm volatile(lock "cmpxchgw %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(_ptr); \ + asm volatile(lock "cmpxchgl %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(_ptr); \ + asm volatile(lock "cmpxchgq %[new], %[ptr]" \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + *_old = __old; \ + success; \ +}) + +#define __try_cmpxchg(ptr, pold, new, size) \ + __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX) + +#define try_cmpxchg(ptr, pold, new) \ + __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) + /* * xadd() adds "inc" to "*ptr" and atomically returns the previous * value of "*ptr". -- cgit v1.2.1 From 44fe84459faf1a7781595b7c64cd36daf2f2827d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 27 Mar 2017 13:54:38 +0200 Subject: locking/atomic: Fix atomic_try_cmpxchg() semantics Dmitry noted that the new atomic_try_cmpxchg() primitive is broken when the old pointer doesn't point to the local stack. He writes: "Consider a classical lock-free stack push: node->next = atomic_read(&head); do { } while (!atomic_try_cmpxchg(&head, &node->next, node)); This code is broken with the current implementation, the problem is with unconditional update of *__po. In case of success it writes the same value back into *__po, but in case of cmpxchg success we might have lose ownership of some memory locations and potentially over what __po has pointed to. The same holds for the re-read of *__po. " He also points out that this makes it surprisingly different from the similar C/C++ atomic operation. After investigating the code-gen differences caused by this patch; and a number of alternatives (Linus dislikes this interface lots), we arrived at these results (size x86_64-defconfig/vmlinux): GCC-6.3.0: 10735757 cmpxchg 10726413 try_cmpxchg 10730509 try_cmpxchg + patch 10730445 try_cmpxchg-linus GCC-7 (20170327): 10709514 cmpxchg 10704266 try_cmpxchg 10704266 try_cmpxchg + patch 10704394 try_cmpxchg-linus From this we see that the patch has the advantage of better code-gen on GCC-7 and keeps the interface roughly consistent with the C language variant. Reported-by: Dmitry Vyukov Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Fixes: a9ebf306f52c ("locking/atomic: Introduce atomic_try_cmpxchg()") Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cmpxchg.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/asm/cmpxchg.h') diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index fb961db51a2a..d90296d061e8 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -212,8 +212,9 @@ extern void __add_wrong_size(void) default: \ __cmpxchg_wrong_size(); \ } \ - *_old = __old; \ - success; \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); \ }) #define __try_cmpxchg(ptr, pold, new, size) \ -- cgit v1.2.1