drm/i915/gt: Drop the timeline->mutex as we wait for retirement

As we have pinned the timeline (using tl->active_count), we can safely
drop the tl->mutex as we wait for what we believe to be the final
request on that timeline. This is useful for ensuring that we do not
block the engine heartbeat by hogging the kernel_context's timeline on a
dead GPU.

References: https://gitlab.freedesktop.org/drm/intel/issues/1364
Fixes: 058179e72e09 ("drm/i915/gt: Replace hangcheck by heartbeats")
Fixes: f33a8a51602c ("drm/i915: Merge wait_for_timelines with retire_request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200303140009.1494819-1-chris@chris-wilson.co.uk
(cherry picked from commit 82126e596d8519baac416aee83cad938f1d23cf8)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 8a5054f..24c99d0 100644 (file)
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -147,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
                        fence = i915_active_fence_get(&tl->last_request);
                        if (fence) {
+                               mutex_unlock(&tl->mutex);
+
                                timeout = dma_fence_wait_timeout(fence,
                                                                 interruptible,
                                                                 timeout);
                                dma_fence_put(fence);
+
+                               /* Retirement is best effort */
+                               if (!mutex_trylock(&tl->mutex)) {
+                                       active_count++;
+                                       goto out_active;
+                               }
                        }
                }
 
                if (!retire_requests(tl) || flush_submission(gt))
                        active_count++;
+               mutex_unlock(&tl->mutex);
 
-               spin_lock(&timelines->lock);
+out_active:    spin_lock(&timelines->lock);
 
-               /* Resume iteration after dropping lock */
+               /* Resume list iteration after reacquiring spinlock */
                list_safe_reset_next(tl, tn, link);
                if (atomic_dec_and_test(&tl->active_count))
                        list_del(&tl->link);
 
-               mutex_unlock(&tl->mutex);
 
                /* Defer the final release to after the spinlock */
                if (refcount_dec_and_test(&tl->kref.refcount)) {