Re: [PATCH] drm/i915: Lock timeline mutex directly in error path of eb_pin_timeline

[John Harrison <john.c.harrison@xxxxxxxxx>]

On 1/11/2022 08:39, Matthew Brost wrote:
> Don't use the interruptable version of the timeline mutex lock in the
> error path of eb_pin_timeline as the cleanup must always happen.
>
> v2:
>   (John Harrison)
>    - Don't check for interrupt during mutex lock
> v3:
>   (Tvrtko)
>    - A comment explaining why lock helper isn't used
>
> Fixes: 544460c33821 ("drm/i915: Multi-BB execbuf")
> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
Reviewed-by: John Harrison <John.C.Harrison@xxxxxxxxx>

> ---
>   drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 9 +++++++--
>   1 file changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> index 9e221ce427075..4a611d62e991a 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> @@ -2518,9 +2518,14 @@ static int eb_pin_timeline(struct i915_execbuffer *eb, struct intel_context *ce,
>   				      timeout) < 0) {
>   			i915_request_put(rq);
>   
> -			tl = intel_context_timeline_lock(ce);
> +			/*
> +			 * Error path, cannot use intel_context_timeline_lock as
> +			 * that is user interruptable and this clean up step
> +			 * must be done.
> +			 */
> +			mutex_lock(&ce->timeline->mutex);
>   			intel_context_exit(ce);
> -			intel_context_timeline_unlock(tl);
> +			mutex_unlock(&ce->timeline->mutex);
>   
>   			if (nonblock)
>   				return -EWOULDBLOCK;