Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Uros Bizjak <ubizjak@gmail.com>
To:     x86@kernel.org, linux-kernel@vger.kernel.org
Cc:     Uros Bizjak <ubizjak@gmail.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH v2] locking/lockref/x86: Enable ARCH_USE_CMPXCHG_LOCKREF for X86_CMPXCHG64
Date:   Thu, 26 May 2022 20:54:30 +0200
Message-Id: <20220526185430.59120-1-ubizjak@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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 cmpxchg()
in CMPXCHG_LOOP macro, the compiler actually produces sane code,
improving lockref_get_or_lock main loop from:

 2a5:	8d 48 01             	lea    0x1(%eax),%ecx
 2a8:	85 c0                	test   %eax,%eax
 2aa:	7e 3c                	jle    2e8 <lockref_get_or_lock+0x78>
 2ac:	8b 44 24 08          	mov    0x8(%esp),%eax
 2b0:	8b 54 24 0c          	mov    0xc(%esp),%edx
 2b4:	8b 74 24 04          	mov    0x4(%esp),%esi
 2b8:	f0 0f c7 0e          	lock cmpxchg8b (%esi)
 2bc:	8b 4c 24 0c          	mov    0xc(%esp),%ecx
 2c0:	89 c3                	mov    %eax,%ebx
 2c2:	89 d0                	mov    %edx,%eax
 2c4:	8b 74 24 08          	mov    0x8(%esp),%esi
 2c8:	31 ca                	xor    %ecx,%edx
 2ca:	31 de                	xor    %ebx,%esi
 2cc:	09 f2                	or     %esi,%edx
 2ce:	75 40                	jne    310 <lockref_get_or_lock+0xa0>

to:

  2d:	8d 4f 01             	lea    0x1(%edi),%ecx
  30:	85 ff                	test   %edi,%edi
  32:	7e 1c                	jle    50 <lockref_get_or_lock+0x50>
  34:	f0 0f c7 0e          	lock cmpxchg8b (%esi)
  38:	75 36                	jne    70 <lockref_get_or_lock+0x70>

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
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 6f59517c4356..cfc42f370419 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,7 +27,6 @@ config X86_64
 	# Options that are inherently 64-bit kernel only:
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
-	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE
@@ -111,6 +110,7 @@ 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
-- 
2.35.3