From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Apr 2012 16:00:41 +0000 (+0100)
Subject: drm/i915: Trigger hangcheck if we detect more a repeating missed IRQ
X-Git-Url: https://openfabrics.org/gitweb/?a=commitdiff_plain;h=d1e61e7fc4456c4cb9a33ed182edf40e34ddedea;p=~shefty%2Frdma-dev.git

drm/i915: Trigger hangcheck if we detect more a repeating missed IRQ

On the first instance we just wish to kick the waiters and see if that
terminates the wait conditions. If it does not, then we do not want to
keep retrying without ever making any forward progress and becoming
stuck in a hangcheck loop.

Reported-and-tested-by: Lukas Hejtmanek <xhejtman@fi.muni.cz>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=48209
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index febddc2952f..39663f51e10 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1875,6 +1875,36 @@ static bool kick_ring(struct intel_ring_buffer *ring)
 	return false;
 }
 
+static bool i915_hangcheck_hung(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	if (dev_priv->hangcheck_count++ > 1) {
+		DRM_ERROR("Hangcheck timer elapsed... GPU hung\n");
+		i915_handle_error(dev, true);
+
+		if (!IS_GEN2(dev)) {
+			/* Is the chip hanging on a WAIT_FOR_EVENT?
+			 * If so we can simply poke the RB_WAIT bit
+			 * and break the hang. This should work on
+			 * all but the second generation chipsets.
+			 */
+			if (kick_ring(&dev_priv->ring[RCS]))
+				return false;
+
+			if (HAS_BSD(dev) && kick_ring(&dev_priv->ring[VCS]))
+				return false;
+
+			if (HAS_BLT(dev) && kick_ring(&dev_priv->ring[BCS]))
+				return false;
+		}
+
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * This is called when the chip hasn't reported back with completed
  * batchbuffers in a long time. The first time this is called we simply record
@@ -1895,9 +1925,14 @@ void i915_hangcheck_elapsed(unsigned long data)
 	if (i915_hangcheck_ring_idle(&dev_priv->ring[RCS], &err) &&
 	    i915_hangcheck_ring_idle(&dev_priv->ring[VCS], &err) &&
 	    i915_hangcheck_ring_idle(&dev_priv->ring[BCS], &err)) {
-		dev_priv->hangcheck_count = 0;
-		if (err)
+		if (err) {
+			if (i915_hangcheck_hung(dev))
+				return;
+
 			goto repeat;
+		}
+
+		dev_priv->hangcheck_count = 0;
 		return;
 	}
 
@@ -1919,30 +1954,8 @@ void i915_hangcheck_elapsed(unsigned long data)
 	    dev_priv->last_acthd_blt == acthd_blt &&
 	    dev_priv->last_instdone == instdone &&
 	    dev_priv->last_instdone1 == instdone1) {
-		if (dev_priv->hangcheck_count++ > 1) {
-			DRM_ERROR("Hangcheck timer elapsed... GPU hung\n");
-			i915_handle_error(dev, true);
-
-			if (!IS_GEN2(dev)) {
-				/* Is the chip hanging on a WAIT_FOR_EVENT?
-				 * If so we can simply poke the RB_WAIT bit
-				 * and break the hang. This should work on
-				 * all but the second generation chipsets.
-				 */
-				if (kick_ring(&dev_priv->ring[RCS]))
-					goto repeat;
-
-				if (HAS_BSD(dev) &&
-				    kick_ring(&dev_priv->ring[VCS]))
-					goto repeat;
-
-				if (HAS_BLT(dev) &&
-				    kick_ring(&dev_priv->ring[BCS]))
-					goto repeat;
-			}
-
+		if (i915_hangcheck_hung(dev))
 			return;
-		}
 	} else {
 		dev_priv->hangcheck_count = 0;