From 3378323bbb9e77643a645f6b1ff10f7bdb9d61e4 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 25 May 2022 16:40:12 +0200 Subject: locking/lockref: Use try_cmpxchg64 in CMPXCHG_LOOP macro 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 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 [ Michael Ellerman and Mark Rutland confirm that code generation on powerpc and arm64 respectively is also ok, even though they do not have a native arch_try_cmpxchg() implementation, and rely on the default fallback case - Linus ] Signed-off-by: Uros Bizjak Tested-by: Michael Ellerman Tested-by: Mark Rutland Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman.Long@hp.com Cc: paulmck@linux.vnet.ibm.com Signed-off-by: Linus Torvalds --- lib/lockref.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'lib') 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) \ -- cgit v1.2.3