[RESEND PATCH v3] locking/lockref/x86: Enable ARCH_USE_CMPXCHG_LOCKREF for X86_CMPXCHG64
From: Uros Bizjak
Date: Mon Sep 18 2023 - 14:41:50 EST
Commit bc08b449ee14ace4d869adaa1bb35a44ce68d775 enabled lockless
reference count updates using cmpxchg() only for x86_64 and
left x86_32 behind due to inability to detect support for
cmpxchg8b instruction. Nowadays, we can use CONFIG_X86_CMPXCHG64
for this purpose. Also, by using try_cmpxchg64() instead of cmpxchg64()
in CMPXCHG_LOOP macro, the compiler actually produces sane code,
improving lockref_get_not_zero main loop from:
eb: 8d 48 01 lea 0x1(%eax),%ecx
ee: 85 c0 test %eax,%eax
f0: 7e 2f jle 121 <lockref_get_not_zero+0x71>
f2: 8b 44 24 10 mov 0x10(%esp),%eax
f6: 8b 54 24 14 mov 0x14(%esp),%edx
fa: 8b 74 24 08 mov 0x8(%esp),%esi
fe: f0 0f c7 0e lock cmpxchg8b (%esi)
102: 8b 7c 24 14 mov 0x14(%esp),%edi
106: 89 c1 mov %eax,%ecx
108: 89 c3 mov %eax,%ebx
10a: 8b 74 24 10 mov 0x10(%esp),%esi
10e: 89 d0 mov %edx,%eax
110: 31 fa xor %edi,%edx
112: 31 ce xor %ecx,%esi
114: 09 f2 or %esi,%edx
116: 75 58 jne 170 <lockref_get_not_zero+0xc0>
to:
350: 8d 4f 01 lea 0x1(%edi),%ecx
353: 85 ff test %edi,%edi
355: 7e 79 jle 3d0 <lockref_get_not_zero+0xb0>
357: f0 0f c7 0e lock cmpxchg8b (%esi)
35b: 75 53 jne 3b0 <lockref_get_not_zero+0x90>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Signed-off-by: Uros Bizjak <ubizjak@xxxxxxxxx>
Acked-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
v3:
- Update commit message to refer to lockref_get_not_zero
instead of removed lockref_get_or_lock
v2:
- select ARCH_USE_CMPXCHG_LOCKREF for CONFIG_X86_CMPXCHG which
is unconditionally defined for X86_64
---
arch/x86/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 66bfabae8814..1379603016fd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,7 +28,6 @@ config X86_64
select ARCH_HAS_GIGANTIC_PAGE
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_SUPPORTS_PER_VMA_LOCK
- select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE
@@ -118,6 +117,7 @@ config X86
select ARCH_SUPPORTS_LTO_CLANG
select ARCH_SUPPORTS_LTO_CLANG_THIN
select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if X86_CMPXCHG64
select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
--
2.41.0