Received-SPF: pass (google.com: domain of linux-kernel+bounces-122308-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Message-ID: <38ba7584-3e74-44e3-b1f5-6e42179856a5@redhat.com>
Date: Wed, 27 Mar 2024 21:52:55 -0400
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH 1/2] locking/pvqspinlock: Use try_cmpxchg_acquire() in
 trylock_clear_pending()
Content-Language: en-US
To: Uros Bizjak <ubizjak@gmail.com>, linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>,
 Will Deacon <will@kernel.org>, Boqun Feng <boqun.feng@gmail.com>
References: <20240325140943.815051-1-ubizjak@gmail.com>
From: Waiman Long <longman@redhat.com>
In-Reply-To: <20240325140943.815051-1-ubizjak@gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit

On 3/25/24 10:09, Uros Bizjak wrote:
> Use try_cmpxchg_acquire(*ptr, &old, new) instead of
> cmpxchg_relaxed(*ptr, old, new) == old in trylock_clear_pending().
> x86 CMPXCHG instruction returns success in ZF flag, so this change
> saves a compare after cmpxchg.
>
> Also change the return type of the function to bool.
>
> No functional change intended.
>
> Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Will Deacon <will@kernel.org>
> Cc: Waiman Long <longman@redhat.com>
> Cc: Boqun Feng <boqun.feng@gmail.com>
> ---
>   kernel/locking/qspinlock_paravirt.h | 31 ++++++++++++-----------------
>   1 file changed, 13 insertions(+), 18 deletions(-)
>
> diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
> index 169950fe1aad..77ba80bd95f9 100644
> --- a/kernel/locking/qspinlock_paravirt.h
> +++ b/kernel/locking/qspinlock_paravirt.h
> @@ -116,11 +116,12 @@ static __always_inline void set_pending(struct qspinlock *lock)
>    * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the
>    * lock just to be sure that it will get it.
>    */
> -static __always_inline int trylock_clear_pending(struct qspinlock *lock)
> +static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
>   {
> +	u16 old = _Q_PENDING_VAL;
> +
>   	return !READ_ONCE(lock->locked) &&
> -	       (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL,
> -				_Q_LOCKED_VAL) == _Q_PENDING_VAL);
> +	       try_cmpxchg_acquire(&lock->locked_pending, &old, _Q_LOCKED_VAL);
>   }
>   #else /* _Q_PENDING_BITS == 8 */
>   static __always_inline void set_pending(struct qspinlock *lock)
> @@ -128,27 +129,21 @@ static __always_inline void set_pending(struct qspinlock *lock)
>   	atomic_or(_Q_PENDING_VAL, &lock->val);
>   }
>   
> -static __always_inline int trylock_clear_pending(struct qspinlock *lock)
> +static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
>   {
> -	int val = atomic_read(&lock->val);
> -
> -	for (;;) {
> -		int old, new;
> -
> -		if (val  & _Q_LOCKED_MASK)
> -			break;
> +	int old, new;
>   
> +	old = atomic_read(&lock->val);
> +	do {
> +		if (old & _Q_LOCKED_MASK)
> +			return false;
>   		/*
>   		 * Try to clear pending bit & set locked bit
>   		 */
> -		old = val;
> -		new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
> -		val = atomic_cmpxchg_acquire(&lock->val, old, new);
> +		new = (old & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
> +	} while (!atomic_try_cmpxchg_acquire (&lock->val, &old, new));
>   
> -		if (val == old)
> -			return 1;
> -	}
> -	return 0;
> +	return true;
>   }
>   #endif /* _Q_PENDING_BITS == 8 */
>   
Reviewed-by: Waiman Long <longman@redhat.com>