Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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>, Waiman.Long@hp.com,
        paulmck@linux.vnet.ibm.com
Subject: [PATCH 1/2] locking/lockref: Use try_cmpxchg64 in CMPXCHG_LOOP macro
Date:   Wed, 25 May 2022 16:40:12 +0200
Message-Id: <20220525144013.6481-2-ubizjak@gmail.com>
In-Reply-To: <20220525144013.6481-1-ubizjak@gmail.com>
References: <20220525144013.6481-1-ubizjak@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Use try_cmpxchg64 instead of cmpxchg64 in CMPXCHG_LOOP macro.
x86 CMPXCHG instruction returns success in ZF flag, so this
change saves a compare after cmpxchg (and related move instruction
in front of cmpxchg). The main loop of lockref_get improves from:

  13:	48 89 c1             	mov    %rax,%rcx
  16:	48 c1 f9 20          	sar    $0x20,%rcx
  1a:	83 c1 01             	add    $0x1,%ecx
  1d:	48 89 ce             	mov    %rcx,%rsi
  20:	89 c1                	mov    %eax,%ecx
  22:	48 89 d0             	mov    %rdx,%rax
  25:	48 c1 e6 20          	shl    $0x20,%rsi
  29:	48 09 f1             	or     %rsi,%rcx
  2c:	f0 48 0f b1 4d 00    	lock cmpxchg %rcx,0x0(%rbp)
  32:	48 39 d0             	cmp    %rdx,%rax
  35:	75 17                	jne    4e <lockref_get+0x4e>

to:

  13:	48 89 ca             	mov    %rcx,%rdx
  16:	48 c1 fa 20          	sar    $0x20,%rdx
  1a:	83 c2 01             	add    $0x1,%edx
  1d:	48 89 d6             	mov    %rdx,%rsi
  20:	89 ca                	mov    %ecx,%edx
  22:	48 c1 e6 20          	shl    $0x20,%rsi
  26:	48 09 f2             	or     %rsi,%rdx
  29:	f0 48 0f b1 55 00    	lock cmpxchg %rdx,0x0(%rbp)
  2f:	75 02                	jne    33 <lockref_get+0x33>

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>
Cc: Waiman.Long@hp.com
Cc: paulmck@linux.vnet.ibm.com
---
 lib/lockref.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/lib/lockref.c b/lib/lockref.c
index 5b34bbd3eba8..c6f0b183b937 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -14,12 +14,11 @@
 	BUILD_BUG_ON(sizeof(old) != 8);						\
 	old.lock_count = READ_ONCE(lockref->lock_count);			\
 	while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) {  	\
-		struct lockref new = old, prev = old;				\
+		struct lockref new = old;					\
 		CODE								\
-		old.lock_count = cmpxchg64_relaxed(&lockref->lock_count,	\
-						   old.lock_count,		\
-						   new.lock_count);		\
-		if (likely(old.lock_count == prev.lock_count)) {		\
+		if (likely(try_cmpxchg64_relaxed(&lockref->lock_count,		\
+						 &old.lock_count,		\
+						 new.lock_count))) {		\
 			SUCCESS;						\
 		}								\
 		if (!--retry)							\
-- 
2.35.3