diff mbox series

[v5,3/3] locking/rwsem: Optimize down_read_trylock()

Message ID 20190322143008.21313-4-longman@redhat.com (mailing list archive)
State Not Applicable
Headers show
Series locking/rwsem: Rwsem rearchitecture part 0 | expand

Commit Message

Waiman Long March 22, 2019, 2:30 p.m. UTC
Modify __down_read_trylock() to optimize for an unlocked rwsem and make
it generate slightly better code.

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>:	xor    %eax,%eax
   0x0000000000000007 <+7>:	lea    0x1(%rax),%rdx
   0x000000000000000b <+11>:	lock cmpxchg %rdx,(%rdi)
   0x0000000000000010 <+16>:	jne    0x29 <down_read_trylock+41>
   0x0000000000000012 <+18>:	mov    %gs:0x0,%rax
   0x000000000000001b <+27>:	or     $0x3,%rax
   0x000000000000001f <+31>:	mov    %rax,0x20(%rdi)
   0x0000000000000023 <+35>:	mov    $0x1,%eax
   0x0000000000000028 <+40>:	retq
   0x0000000000000029 <+41>:	test   %rax,%rax
   0x000000000000002c <+44>:	jns    0x7 <down_read_trylock+7>
   0x000000000000002e <+46>:	xor    %eax,%eax
   0x0000000000000030 <+48>:	retq

By using a rwsem microbenchmark, the down_read_trylock() rate (with a
load of 10 to lengthen the lock critical section) on a x86-64 system
before and after the patch were:

                 Before Patch    After Patch
   # of Threads     rlock           rlock
   ------------     -----           -----
        1           14,496          14,716
        2            8,644           8,453
	4            6,799           6,983
	8            5,664           7,190

On a ARM64 system, the performance results were:

                 Before Patch    After Patch
   # of Threads     rlock           rlock
   ------------     -----           -----
        1           23,676          24,488
        2            7,697           9,502
        4            4,945           3,440
        8            2,641           1,603

For the uncontended case (1 thread), the new down_read_trylock() is a
little bit faster. For the contended cases, the new down_read_trylock()
perform pretty well in x86-64, but performance degrades at high
contention level on ARM64.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/locking/rwsem.h | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

Comments

Linus Torvalds March 22, 2019, 5:08 p.m. UTC | #1
On Fri, Mar 22, 2019 at 7:30 AM Waiman Long <longman@redhat.com> wrote:
>
> Modify __down_read_trylock() to optimize for an unlocked rwsem and make
> it generate slightly better code.

Oh, that should teach me to read all patches in the series before
starting to comment on them.

So ignore my comment on #1.

                Linus
Russell King (Oracle) March 22, 2019, 5:25 p.m. UTC | #2
On Fri, Mar 22, 2019 at 10:30:08AM -0400, Waiman Long wrote:
> Modify __down_read_trylock() to optimize for an unlocked rwsem and make
> it generate slightly better code.
> 
> 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>:	xor    %eax,%eax
>    0x0000000000000007 <+7>:	lea    0x1(%rax),%rdx
>    0x000000000000000b <+11>:	lock cmpxchg %rdx,(%rdi)
>    0x0000000000000010 <+16>:	jne    0x29 <down_read_trylock+41>
>    0x0000000000000012 <+18>:	mov    %gs:0x0,%rax
>    0x000000000000001b <+27>:	or     $0x3,%rax
>    0x000000000000001f <+31>:	mov    %rax,0x20(%rdi)
>    0x0000000000000023 <+35>:	mov    $0x1,%eax
>    0x0000000000000028 <+40>:	retq
>    0x0000000000000029 <+41>:	test   %rax,%rax
>    0x000000000000002c <+44>:	jns    0x7 <down_read_trylock+7>
>    0x000000000000002e <+46>:	xor    %eax,%eax
>    0x0000000000000030 <+48>:	retq
> 
> By using a rwsem microbenchmark, the down_read_trylock() rate (with a
> load of 10 to lengthen the lock critical section) on a x86-64 system
> before and after the patch were:
> 
>                  Before Patch    After Patch
>    # of Threads     rlock           rlock
>    ------------     -----           -----
>         1           14,496          14,716
>         2            8,644           8,453
> 	4            6,799           6,983
> 	8            5,664           7,190
> 
> On a ARM64 system, the performance results were:
> 
>                  Before Patch    After Patch
>    # of Threads     rlock           rlock
>    ------------     -----           -----
>         1           23,676          24,488
>         2            7,697           9,502
>         4            4,945           3,440
>         8            2,641           1,603
> 
> For the uncontended case (1 thread), the new down_read_trylock() is a
> little bit faster. For the contended cases, the new down_read_trylock()
> perform pretty well in x86-64, but performance degrades at high
> contention level on ARM64.

So, 70% for 4 threads, 61% for 4 threads - does this trend
continue tailing off as the number of threads (and cores)
increase?
Waiman Long March 22, 2019, 5:41 p.m. UTC | #3
On 03/22/2019 01:25 PM, Russell King - ARM Linux admin wrote:
> On Fri, Mar 22, 2019 at 10:30:08AM -0400, Waiman Long wrote:
>> Modify __down_read_trylock() to optimize for an unlocked rwsem and make
>> it generate slightly better code.
>>
>> 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>:	xor    %eax,%eax
>>    0x0000000000000007 <+7>:	lea    0x1(%rax),%rdx
>>    0x000000000000000b <+11>:	lock cmpxchg %rdx,(%rdi)
>>    0x0000000000000010 <+16>:	jne    0x29 <down_read_trylock+41>
>>    0x0000000000000012 <+18>:	mov    %gs:0x0,%rax
>>    0x000000000000001b <+27>:	or     $0x3,%rax
>>    0x000000000000001f <+31>:	mov    %rax,0x20(%rdi)
>>    0x0000000000000023 <+35>:	mov    $0x1,%eax
>>    0x0000000000000028 <+40>:	retq
>>    0x0000000000000029 <+41>:	test   %rax,%rax
>>    0x000000000000002c <+44>:	jns    0x7 <down_read_trylock+7>
>>    0x000000000000002e <+46>:	xor    %eax,%eax
>>    0x0000000000000030 <+48>:	retq
>>
>> By using a rwsem microbenchmark, the down_read_trylock() rate (with a
>> load of 10 to lengthen the lock critical section) on a x86-64 system
>> before and after the patch were:
>>
>>                  Before Patch    After Patch
>>    # of Threads     rlock           rlock
>>    ------------     -----           -----
>>         1           14,496          14,716
>>         2            8,644           8,453
>> 	4            6,799           6,983
>> 	8            5,664           7,190
>>
>> On a ARM64 system, the performance results were:
>>
>>                  Before Patch    After Patch
>>    # of Threads     rlock           rlock
>>    ------------     -----           -----
>>         1           23,676          24,488
>>         2            7,697           9,502
>>         4            4,945           3,440
>>         8            2,641           1,603
>>
>> For the uncontended case (1 thread), the new down_read_trylock() is a
>> little bit faster. For the contended cases, the new down_read_trylock()
>> perform pretty well in x86-64, but performance degrades at high
>> contention level on ARM64.
> So, 70% for 4 threads, 61% for 4 threads - does this trend
> continue tailing off as the number of threads (and cores)
> increase?
>
I didn't try higher number of contending threads. I won't worry too much
about contention as trylock is a one-off event. The chance of having
more than one trylock happening simultaneously is very small.

Cheers,
Longman
Christophe Leroy March 25, 2019, 3:25 p.m. UTC | #4
Hi,

Could you share the microbenchmark you are using ?

I'd like to test the series on powerpc.

Thanks
Christophe

Le 22/03/2019 à 15:30, Waiman Long a écrit :
> Modify __down_read_trylock() to optimize for an unlocked rwsem and make
> it generate slightly better code.
> 
> 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>:	xor    %eax,%eax
>     0x0000000000000007 <+7>:	lea    0x1(%rax),%rdx
>     0x000000000000000b <+11>:	lock cmpxchg %rdx,(%rdi)
>     0x0000000000000010 <+16>:	jne    0x29 <down_read_trylock+41>
>     0x0000000000000012 <+18>:	mov    %gs:0x0,%rax
>     0x000000000000001b <+27>:	or     $0x3,%rax
>     0x000000000000001f <+31>:	mov    %rax,0x20(%rdi)
>     0x0000000000000023 <+35>:	mov    $0x1,%eax
>     0x0000000000000028 <+40>:	retq
>     0x0000000000000029 <+41>:	test   %rax,%rax
>     0x000000000000002c <+44>:	jns    0x7 <down_read_trylock+7>
>     0x000000000000002e <+46>:	xor    %eax,%eax
>     0x0000000000000030 <+48>:	retq
> 
> By using a rwsem microbenchmark, the down_read_trylock() rate (with a
> load of 10 to lengthen the lock critical section) on a x86-64 system
> before and after the patch were:
> 
>                   Before Patch    After Patch
>     # of Threads     rlock           rlock
>     ------------     -----           -----
>          1           14,496          14,716
>          2            8,644           8,453
> 	4            6,799           6,983
> 	8            5,664           7,190
> 
> On a ARM64 system, the performance results were:
> 
>                   Before Patch    After Patch
>     # of Threads     rlock           rlock
>     ------------     -----           -----
>          1           23,676          24,488
>          2            7,697           9,502
>          4            4,945           3,440
>          8            2,641           1,603
> 
> For the uncontended case (1 thread), the new down_read_trylock() is a
> little bit faster. For the contended cases, the new down_read_trylock()
> perform pretty well in x86-64, but performance degrades at high
> contention level on ARM64.
> 
> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
> Signed-off-by: Waiman Long <longman@redhat.com>
> ---
>   kernel/locking/rwsem.h | 13 ++++++++-----
>   1 file changed, 8 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
> index 45ee00236e03..1f5775aa6a1d 100644
> --- a/kernel/locking/rwsem.h
> +++ b/kernel/locking/rwsem.h
> @@ -174,14 +174,17 @@ static inline int __down_read_killable(struct rw_semaphore *sem)
>   
>   static inline int __down_read_trylock(struct rw_semaphore *sem)
>   {
> -	long tmp;
> +	/*
> +	 * Optimize for the case when the rwsem is not locked at all.
> +	 */
> +	long tmp = RWSEM_UNLOCKED_VALUE;
>   
> -	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
> -		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
> -				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
> +	do {
> +		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
> +					tmp + RWSEM_ACTIVE_READ_BIAS)) {
>   			return 1;
>   		}
> -	}
> +	} while (tmp >= 0);
>   	return 0;
>   }
>   
>
diff mbox series

Patch

diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 45ee00236e03..1f5775aa6a1d 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -174,14 +174,17 @@  static inline int __down_read_killable(struct rw_semaphore *sem)
 
 static inline int __down_read_trylock(struct rw_semaphore *sem)
 {
-	long tmp;
+	/*
+	 * Optimize for the case when the rwsem is not locked at all.
+	 */
+	long tmp = RWSEM_UNLOCKED_VALUE;
 
-	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
-		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
+	do {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					tmp + RWSEM_ACTIVE_READ_BIAS)) {
 			return 1;
 		}
-	}
+	} while (tmp >= 0);
 	return 0;
 }