[Intel-gfx] [PATCH 2/2] drm/i915/execlists: Skip nested spinlock for validating pending

[Chris Wilson]

Quoting Tvrtko Ursulin (2019-12-03 15:38:20)
> 
> On 03/12/2019 11:53, Chris Wilson wrote:
> > Only along the submission path can we guarantee that the locked request
> > is indeed from a foreign engine, and so the nesting of engine/rq is
> > permissible. On the submission tasklet (process_csb()), we may find
> > ourselves competing with the normal nesting of rq/engine, invalidating
> > our nesting. As we only use the spinlock for debug purposes, skip the
> > debug if we cannot acquire the spinlock for safe validation - catching
> > 99% of the bugs is better than causing a hard lockup.
> > 
> > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > ---
> >   drivers/gpu/drm/i915/gt/intel_lrc.c | 7 +++----
> >   1 file changed, 3 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> > index 37ab9742abe7..b411e4ce6771 100644
> > --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> > +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> > @@ -1300,7 +1300,6 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
> >       }
> >   
> >       for (port = execlists->pending; (rq = *port); port++) {
> > -             unsigned long flags;
> >               bool ok = true;
> >   
> >               GEM_BUG_ON(!kref_read(&rq->fence.refcount));
> > @@ -1315,8 +1314,8 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
> >               ce = rq->hw_context;
> >   
> >               /* Hold tightly onto the lock to prevent concurrent retires! */
> > -             spin_lock_irqsave_nested(&rq->lock, flags,
> > -                                      SINGLE_DEPTH_NESTING);
> > +             if (!spin_trylock(&rq->lock))
> > +                     continue;
> >   
> >               if (i915_request_completed(rq))
> >                       goto unlock;
> > @@ -1347,7 +1346,7 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
> >               }
> >   
> >   unlock:
> > -             spin_unlock_irqrestore(&rq->lock, flags);
> > +             spin_unlock(&rq->lock);
> >               if (!ok)
> >                       return false;
> >       }
> > 
> 
> With Fixes: and irqsave variant:
> 
> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Predictive patching: https://patchwork.freedesktop.org/patch/343495/?series=70375&rev=1

Ta,
-Chris