Re: [PATCH 4/4] input: evdev: only wake poll on EV_SYN

[Henrik Rydberg]

On Tue, Mar 22, 2011 at 06:04:04PM -0700, Jeff Brown wrote:
> On SMP systems, it is possible for an evdev client blocked on poll()
> to wake up and read events from the evdev ring buffer at the same
> rate as they are enqueued.  This can result in high CPU usage,
> particularly for MT devices, because the client ends up reading
> events one at a time instead of reading complete packets.  This patch
> ensures that the client only wakes from poll() when a complete packet
> is ready to be read.
> 
> Signed-off-by: jeffbrown@xxxxxxxxxxx
> ---
>  drivers/input/evdev.c |    5 +++--
>  1 files changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
> index 203ed70..7b6770d 100644
> --- a/drivers/input/evdev.c
> +++ b/drivers/input/evdev.c
> @@ -73,7 +73,7 @@ static void evdev_pass_event(struct evdev_client *client,
>  	}
>  	spin_unlock(&client->buffer_lock);
>  
> -	if (event->type == EV_SYN)
> +	if (event->type == EV_SYN && event->code != SYN_MT_REPORT)

It is not clear what should happen at the other SYN events.  Maybe
event->code == SYN_REPORT instead?

>  		kill_fasync(&client->fasync, SIGIO, POLL_IN);
>  }
>  
> @@ -103,7 +103,8 @@ static void evdev_event(struct input_handle *handle,
>  
>  	rcu_read_unlock();
>  
> -	wake_up_interruptible(&evdev->wait);
> +	if (type == EV_SYN && code != SYN_MT_REPORT)
> +		wake_up_interruptible(&evdev->wait);

Ah, this is a good one. Since the code depends on the same logic being
applied in evdev_pass_event as well, a boolean argument to that
function would be good.

Thanks,
Henrik
--
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/