Re: [PATCH v2 3/4] Move libio lock single-thread optimization to generic libc-lock (BZ #27842)

[Adhemerval Zanella <adhemerval.zanella@linaro.org>]

On 27/04/2022 10:30, Florian Weimer wrote:
> * Adhemerval Zanella via Libc-alpha:
> 
>> diff --git a/sysdeps/nptl/libc-lock.h b/sysdeps/nptl/libc-lock.h
>> index 6c2d6acfd1..abd84e71b4 100644
>> --- a/sysdeps/nptl/libc-lock.h
>> +++ b/sysdeps/nptl/libc-lock.h
>> @@ -86,7 +86,7 @@ typedef struct { int lock; int cnt; void *owner; } __libc_lock_recursive_t;
>>  # define __libc_lock_lock_recursive(NAME) \
>>    do {									      \
>>      void *self = THREAD_SELF;						      \
>> -    if ((NAME).owner != self)						      \
>> +    if (!SINGLE_THREAD_P && (NAME).owner != self)						      \
>>        {									      \
>>  	lll_lock ((NAME).lock, LLL_PRIVATE);				      \
>>  	(NAME).owner = self;						      \
>> @@ -104,7 +104,7 @@ typedef struct { int lock; int cnt; void *owner; } __libc_lock_recursive_t;
>>    ({									      \
>>      int result = 0;							      \
>>      void *self = THREAD_SELF;						      \
>> -    if ((NAME).owner != self)						      \
>> +    if (!SINGLE_THREAD_P && (NAME).owner != self)						      \
>>        {									      \
>>  	if (lll_trylock ((NAME).lock) == 0)				      \
>>  	  {								      \
>> @@ -131,7 +131,8 @@ typedef struct { int lock; int cnt; void *owner; } __libc_lock_recursive_t;
>>      if (--(NAME).cnt == 0)						      \
>>        {									      \
>>  	(NAME).owner = NULL;						      \
>> -	lll_unlock ((NAME).lock, LLL_PRIVATE);				      \
>> +        if (!SINGLE_THREAD_P)                                                 \
>> +	  lll_unlock ((NAME).lock, LLL_PRIVATE);			      \
>>        }									      \
>>    } while (0)
>>  #else
> 
> I don't think this is correct if threads are created in the lock region.

I was not sure about this one and I think we the main issue in fact there is
we can't use the single-thread optimization on unlock.  Maybe a better option
would to use a different scheme as proposed by 
https://hal.inria.fr/hal-01236734/document, where we can embedded lock and
cnt in only one variable (as the lll_lock already does).