mfence appears to be way slower than a locked instruction - let's use lock+add unconditionally, as we always did on old 32-bit.
Just poking at SP would be the most natural, but if we then read the value from SP, we get a false dependency which will slow us down. This was noted in this article: http://shipilev.net/blog/2014/on-the-fence-with-dependencies/ And is easy to reproduce by sticking a barrier in a small non-inline function. So let's use a negative offset - which avoids this problem since we build with the red zone disabled. Unfortunately there's some code that wants to order clflush instructions using mb(), so we can't replace that - but smp_mb should be safe to replace. Update mb/rmb/wmb on 32 bit to use the negative offset, too, for consistency. Suggested-by: Andy Lutomirski <l...@amacapital.net> Signed-off-by: Michael S. Tsirkin <m...@redhat.com> --- arch/x86/include/asm/barrier.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index bfb28ca..3c6ba1e 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -11,11 +11,11 @@ */ #ifdef CONFIG_X86_32 -#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \ +#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") -#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \ +#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") -#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \ +#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") #else #define mb() asm volatile("mfence":::"memory") @@ -30,7 +30,11 @@ #endif #define dma_wmb() barrier() -#define __smp_mb() mb() +#ifdef CONFIG_X86_32 +#define __smp_mb() asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc") +#else +#define __smp_mb() asm volatile("lock; addl $0,-4(%%rsp)" ::: "memory", "cc") +#endif #define __smp_rmb() dma_rmb() #define __smp_wmb() barrier() #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) -- MST
