drm/i915: Don't accumulate hangcheck score on forward progress

If the actual head has progressed forward inside a batch (request),
don't accumulate hangcheck score.

As the hangcheck score in increased only by acthd jumping backwards,
the result is that we only declare an active batch as stuck if it is
trapped inside a loop. Or that the looping will dominate the batch
progression so that it overcomes the bonus that forward progress gives.

v2: Improved commit message (Chris Wilson)

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
[danvet: s/active_loop/active (loop)/ as requested by Chris.]
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

3 files changed, 16 insertions, 3 deletions

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0c945e91d542..7c478e6cedae 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -229,6 +229,8 @@ static const char *hangcheck_action_to_str(enum intel_ring_hangcheck_action a)
                 return "wait";
         case HANGCHECK_ACTIVE:
                 return "active";
+        case HANGCHECK_ACTIVE_LOOP:
+                return "active (loop)";
         case HANGCHECK_KICK:
                 return "kick";
         case HANGCHECK_HUNG:
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6ef9d6fabf80..390ccc2a3096 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3189,8 +3189,14 @@ ring_stuck(struct intel_engine_cs *ring, u64 acthd)
         struct drm_i915_private *dev_priv = dev->dev_private;
         u32 tmp;
 
-        if (ring->hangcheck.acthd != acthd)
-                return HANGCHECK_ACTIVE;
+        if (acthd != ring->hangcheck.acthd) {
+                if (acthd > ring->hangcheck.max_acthd) {
+                        ring->hangcheck.max_acthd = acthd;
+                        return HANGCHECK_ACTIVE;
+                }
+
+                return HANGCHECK_ACTIVE_LOOP;
+        }
 
         if (IS_GEN2(dev))
                 return HANGCHECK_HUNG;
@@ -3301,8 +3307,9 @@ static void i915_hangcheck_elapsed(unsigned long data)
                                 switch (ring->hangcheck.action) {
                                 case HANGCHECK_IDLE:
                                 case HANGCHECK_WAIT:
-                                        break;
                                 case HANGCHECK_ACTIVE:
+                                        break;
+                                case HANGCHECK_ACTIVE_LOOP:
                                         ring->hangcheck.score += BUSY;
                                         break;
                                 case HANGCHECK_KICK:
@@ -3322,6 +3329,8 @@ static void i915_hangcheck_elapsed(unsigned long data)
                          */
                         if (ring->hangcheck.score > 0)
                                 ring->hangcheck.score--;
+
+                        ring->hangcheck.acthd = ring->hangcheck.max_acthd = 0;
                 }
 
                 ring->hangcheck.seqno = seqno;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ed5941078f92..70525d0c2c74 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -70,6 +70,7 @@ enum intel_ring_hangcheck_action {
         HANGCHECK_IDLE = 0,
         HANGCHECK_WAIT,
         HANGCHECK_ACTIVE,
+        HANGCHECK_ACTIVE_LOOP,
         HANGCHECK_KICK,
         HANGCHECK_HUNG,
 };
@@ -78,6 +79,7 @@ enum intel_ring_hangcheck_action {
 
 struct intel_ring_hangcheck {
         u64 acthd;
+        u64 max_acthd;
         u32 seqno;
         int score;
         enum intel_ring_hangcheck_action action;