[Intel-gfx] [PATCH 1/4] drm/i915: Teach hangcheck about long operations on rings

[Mika Kuoppala]

Some operations that happen in ringbuffer, like flushing,
can take significant amounts of time. After some intense
shader tests, the PIPE_CONTROL with flush can apparently last
longer time than what is our hangcheck tick (1500ms). If
this happens twice in a row, even with subsequent batches,
the hangcheck score decaying mechanism can't cope and
hang is declared.

Strip out actual head checking to a separate function and if
actual head has not moved, check if it is lingering inside the
ringbuffer as opposed to batch. If so, treat it as if it would be
inside loop to only slightly increment the hangcheck score.

References: https://bugs.freedesktop.org/show_bug.cgi?id=93029
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e88d692..6ed6571 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2914,11 +2914,11 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
 }
 
 static enum intel_ring_hangcheck_action
-ring_stuck(struct intel_engine_cs *ring, u64 acthd)
+head_stuck(struct intel_engine_cs *ring, u64 acthd)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 tmp;
+	u32 head;
 
 	if (acthd != ring->hangcheck.acthd) {
 		if (acthd > ring->hangcheck.max_acthd) {
@@ -2929,6 +2929,30 @@ ring_stuck(struct intel_engine_cs *ring, u64 acthd)
 		return HANGCHECK_ACTIVE_LOOP;
 	}
 
+	head = I915_READ_HEAD(ring) & HEAD_ADDR;
+
+	/* Some operations, like pipe flush, can take a long time.
+	 * Detect if we are inside ringbuffer and treat these as if
+	 * the ring would be busy.
+	 */
+	if (lower_32_bits(acthd) == head)
+		return HANGCHECK_ACTIVE_LOOP;
+
+	return HANGCHECK_HUNG;
+}
+
+static enum intel_ring_hangcheck_action
+ring_stuck(struct intel_engine_cs *ring, u64 acthd)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_ring_hangcheck_action ha;
+	u32 tmp;
+
+	ha = head_stuck(ring, acthd);
+	if (ha != HANGCHECK_HUNG)
+		return ha;
+
 	if (IS_GEN2(dev))
 		return HANGCHECK_HUNG;
 
-- 
2.5.0