forked from Minki/linux
450cbdd012
MFENCE appears to be way slower than a locked instruction - let's use
LOCK ADD unconditionally, as we always did on old 32-bit.
Performance testing results:
perf stat -r 10 -- ./virtio_ring_0_9 --sleep --host-affinity 0 --guest-affinity 0
Before:
0.922565990 seconds time elapsed ( +- 1.15% )
After:
0.578667024 seconds time elapsed ( +- 1.21% )
i.e. about ~60% faster.
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.
For userspace, use an address just below the redzone.
The one difference between LOCK ADD and MFENCE is that LOCK ADD does
not affect CLFLUSH, previous patches converted all uses of CLFLUSH to
call mb(), such that changes to smp_mb() won't affect it.
Update mb/rmb/wmb() on 32-bit to use the negative offset, too, for
consistency.
As a follow-up, it might be worth considering switching users
of CLFLUSH to another API (e.g. clflush_mb()?) - we will
then be able to convert mb() to smp_mb() again.
Also arguably, GCC should switch to use LOCK ADD for __sync_synchronize().
This might be worth pursuing separately.
Suggested-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: qemu-devel@nongnu.org
Cc: virtualization@lists.linux-foundation.org
Link: http://lkml.kernel.org/r/1509118355-4890-1-git-send-email-mst@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
91 lines
2.3 KiB
C
91 lines
2.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_X86_BARRIER_H
|
|
#define _ASM_X86_BARRIER_H
|
|
|
|
#include <asm/alternative.h>
|
|
#include <asm/nops.h>
|
|
|
|
/*
|
|
* Force strict CPU ordering.
|
|
* And yes, this might be required on UP too when we're talking
|
|
* to devices.
|
|
*/
|
|
|
|
#ifdef CONFIG_X86_32
|
|
#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \
|
|
X86_FEATURE_XMM2) ::: "memory", "cc")
|
|
#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \
|
|
X86_FEATURE_XMM2) ::: "memory", "cc")
|
|
#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
|
|
X86_FEATURE_XMM2) ::: "memory", "cc")
|
|
#else
|
|
#define mb() asm volatile("mfence":::"memory")
|
|
#define rmb() asm volatile("lfence":::"memory")
|
|
#define wmb() asm volatile("sfence" ::: "memory")
|
|
#endif
|
|
|
|
#ifdef CONFIG_X86_PPRO_FENCE
|
|
#define dma_rmb() rmb()
|
|
#else
|
|
#define dma_rmb() barrier()
|
|
#endif
|
|
#define dma_wmb() barrier()
|
|
|
|
#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)
|
|
|
|
#if defined(CONFIG_X86_PPRO_FENCE)
|
|
|
|
/*
|
|
* For this option x86 doesn't have a strong TSO memory
|
|
* model and we should fall back to full barriers.
|
|
*/
|
|
|
|
#define __smp_store_release(p, v) \
|
|
do { \
|
|
compiletime_assert_atomic_type(*p); \
|
|
__smp_mb(); \
|
|
WRITE_ONCE(*p, v); \
|
|
} while (0)
|
|
|
|
#define __smp_load_acquire(p) \
|
|
({ \
|
|
typeof(*p) ___p1 = READ_ONCE(*p); \
|
|
compiletime_assert_atomic_type(*p); \
|
|
__smp_mb(); \
|
|
___p1; \
|
|
})
|
|
|
|
#else /* regular x86 TSO memory ordering */
|
|
|
|
#define __smp_store_release(p, v) \
|
|
do { \
|
|
compiletime_assert_atomic_type(*p); \
|
|
barrier(); \
|
|
WRITE_ONCE(*p, v); \
|
|
} while (0)
|
|
|
|
#define __smp_load_acquire(p) \
|
|
({ \
|
|
typeof(*p) ___p1 = READ_ONCE(*p); \
|
|
compiletime_assert_atomic_type(*p); \
|
|
barrier(); \
|
|
___p1; \
|
|
})
|
|
|
|
#endif
|
|
|
|
/* Atomic operations are already serializing on x86 */
|
|
#define __smp_mb__before_atomic() barrier()
|
|
#define __smp_mb__after_atomic() barrier()
|
|
|
|
#include <asm-generic/barrier.h>
|
|
|
|
#endif /* _ASM_X86_BARRIER_H */
|