drm/i915: Fix __wait_seqno to use true infinite timeouts

When we switched to always using a timeout in conjunction with
wait_seqno, we lost the ability to detect missed interrupts. Since, we
have had issues with interrupts on a number of generations, and they are
required to be delivered in a timely fashion for a smooth UX, it is
important that we do log errors found in the wild and prevent the
display stalling for upwards of 1s every time the seqno interrupt is
missed.

Rather than continue to fix up the timeouts to work around the interface
impedence in wait_event_*(), open code the combination of
wait_event[_interruptible][_timeout], and use the exposed timer to
poll for seqno should we detect a lost interrupt.

v2: In order to satisfy the debug requirement of logging missed
interrupts with the real world requirments of making machines work even
if interrupts are hosed, we revert to polling after detecting a missed
interrupt.

v3: Throw in a debugfs interface to simulate broken hw not reporting
interrupts.

v4: s/EGAIN/EAGAIN/ (Imre)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
[danvet: Don't use the struct typedef in new code.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 68 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fcfa98844cc..bc5c04d5890 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1897,6 +1897,72 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_ring_stop_fops,
 			i915_ring_stop_get, i915_ring_stop_set,
 			"0x%08llx\n");
 
+static int
+i915_ring_missed_irq_get(void *data, u64 *val)
+{
+	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	*val = dev_priv->gpu_error.missed_irq_rings;
+	return 0;
+}
+
+static int
+i915_ring_missed_irq_set(void *data, u64 val)
+{
+	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	/* Lock against concurrent debugfs callers */
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+	dev_priv->gpu_error.missed_irq_rings = val;
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(i915_ring_missed_irq_fops,
+			i915_ring_missed_irq_get, i915_ring_missed_irq_set,
+			"0x%08llx\n");
+
+static int
+i915_ring_test_irq_get(void *data, u64 *val)
+{
+	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	*val = dev_priv->gpu_error.test_irq_rings;
+
+	return 0;
+}
+
+static int
+i915_ring_test_irq_set(void *data, u64 val)
+{
+	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	DRM_DEBUG_DRIVER("Masking interrupts on rings 0x%08llx\n", val);
+
+	/* Lock against concurrent debugfs callers */
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	dev_priv->gpu_error.test_irq_rings = val;
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(i915_ring_test_irq_fops,
+			i915_ring_test_irq_get, i915_ring_test_irq_set,
+			"0x%08llx\n");
+
 #define DROP_UNBOUND 0x1
 #define DROP_BOUND 0x2
 #define DROP_RETIRE 0x4
@@ -2290,6 +2356,8 @@ static struct i915_debugfs_files {
 	{"i915_min_freq", &i915_min_freq_fops},
 	{"i915_cache_sharing", &i915_cache_sharing_fops},
 	{"i915_ring_stop", &i915_ring_stop_fops},
+	{"i915_ring_missed_irq", &i915_ring_missed_irq_fops},
+	{"i915_ring_test_irq", &i915_ring_test_irq_fops},
 	{"i915_gem_drop_caches", &i915_drop_caches_fops},
 	{"i915_error_state", &i915_error_state_fops},
 	{"i915_next_seqno", &i915_next_seqno_fops},