Re: [PATCH 2/8] mutex: In mutex_can_spin_on_owner(), return false iftask need_resched()

[Peter Zijlstra]

On Mon, Feb 10, 2014 at 08:58:22PM +0100, Peter Zijlstra wrote:

Bah, I forgot Quilt eats the From: headers and I forgot to re-add them.
They're still present in the queue, just lost in mailing :/

> The mutex_can_spin_on_owner() function should also return false if the
> task needs to be rescheduled to avoid entering the MCS queue when it
> needs to reschedule.
> 
> Cc: chegu_vinod@xxxxxx
> Cc: paulmck@xxxxxxxxxxxxxxxxxx
> Cc: Waiman.Long@xxxxxx
> Cc: torvalds@xxxxxxxxxxxxxxxxxxxx
> Cc: tglx@xxxxxxxxxxxxx
> Cc: riel@xxxxxxxxxx
> Cc: akpm@xxxxxxxxxxxxxxxxxxxx
> Cc: davidlohr@xxxxxx
> Cc: hpa@xxxxxxxxx
> Cc: andi@xxxxxxxxxxxxxx
> Cc: aswin@xxxxxx
> Cc: mingo@xxxxxxxxxx
> Cc: scott.norton@xxxxxx
> Signed-off-by: Jason Low <jason.low2@xxxxxx>
> Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Link: http://lkml.kernel.org/r/1390936396-3962-2-git-send-email-jason.low2@xxxxxx
> ---
>  kernel/locking/mutex.c |    3 +++
>  1 file changed, 3 insertions(+)
> 
> --- a/kernel/locking/mutex.c
> +++ b/kernel/locking/mutex.c
> @@ -166,6 +166,9 @@ static inline int mutex_can_spin_on_owne
>  	struct task_struct *owner;
>  	int retval = 1;
>  
> +	if (need_resched())
> +		return 0;
> +
>  	rcu_read_lock();
>  	owner = ACCESS_ONCE(lock->owner);
>  	if (owner)
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/