[PATCH v2 2/2] locking/rwsem: Optimize down_read_trylock()

[Waiman Long]

Modify __down_read_trylock() to make it generate slightly better code
(smaller and maybe a tiny bit faster).

Before this patch, down_read_trylock:

   0x0000000000000000 <+0>:     callq  0x5 <down_read_trylock+5>
   0x0000000000000005 <+5>:     jmp    0x18 <down_read_trylock+24>
   0x0000000000000007 <+7>:     lea    0x1(%rdx),%rcx
   0x000000000000000b <+11>:    mov    %rdx,%rax
   0x000000000000000e <+14>:    lock cmpxchg %rcx,(%rdi)
   0x0000000000000013 <+19>:    cmp    %rax,%rdx
   0x0000000000000016 <+22>:    je     0x23 <down_read_trylock+35>
   0x0000000000000018 <+24>:    mov    (%rdi),%rdx
   0x000000000000001b <+27>:    test   %rdx,%rdx
   0x000000000000001e <+30>:    jns    0x7 <down_read_trylock+7>
   0x0000000000000020 <+32>:    xor    %eax,%eax
   0x0000000000000022 <+34>:    retq
   0x0000000000000023 <+35>:    mov    %gs:0x0,%rax
   0x000000000000002c <+44>:    or     $0x3,%rax
   0x0000000000000030 <+48>:    mov    %rax,0x20(%rdi)
   0x0000000000000034 <+52>:    mov    $0x1,%eax
   0x0000000000000039 <+57>:    retq

After patch, down_read_trylock:

   0x0000000000000000 <+0>:     callq  0x5 <down_read_trylock+5>
   0x0000000000000005 <+5>:     mov    (%rdi),%rax
   0x0000000000000008 <+8>:     test   %rax,%rax
   0x000000000000000b <+11>:    js     0x2f <down_read_trylock+47>
   0x000000000000000d <+13>:    lea    0x1(%rax),%rdx
   0x0000000000000011 <+17>:    lock cmpxchg %rdx,(%rdi)
   0x0000000000000016 <+22>:    jne    0x8 <down_read_trylock+8>
   0x0000000000000018 <+24>:    mov    %gs:0x0,%rax
   0x0000000000000021 <+33>:    or     $0x3,%rax
   0x0000000000000025 <+37>:    mov    %rax,0x20(%rdi)
   0x0000000000000029 <+41>:    mov    $0x1,%eax
   0x000000000000002e <+46>:    retq
   0x000000000000002f <+47>:    xor    %eax,%eax
   0x0000000000000031 <+49>:    retq

By using a rwsem microbenchmark, the down_read_trylock() rate on a
x86-64 system before and after the patch were:

                 Before Patch    After Patch
   # of Threads     rlock           rlock
   ------------     -----           -----
        1           27,787          28,259
        2            8,359           9,234

On a ARM64 system, the performance results were:

                 Before Patch    After Patch
   # of Threads     rlock           rlock
   ------------     -----           -----
        1           24,155          25,000
        2            6,820           8,699

Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/locking/rwsem.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 067e265..028bc33 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -175,11 +175,11 @@ static inline int __down_read_killable(struct rw_semaphore *sem)
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-	long tmp;
+	long tmp = atomic_long_read(&sem->count);
 
-	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
-		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
+	while (tmp >= 0) {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					tmp + RWSEM_ACTIVE_READ_BIAS)) {
 			return 1;
 		}
 	}
-- 
1.8.3.1