[Intel-gfx] [PATCH 1/9] drm/i915: Wait for concurrent global resets to complete

[Chris Wilson]

If we enter i915_handle_error() a second time and a global reset is
already in progress, we can simply wait for completion of the first
reset. Currently we exit early prior to the actual reset being
performed -- the worst of both worlds!

v2: Plug into the existing reset_queue, and remember that kselftests is
playing games with I915_RESET_BACKOFF to prevent hangcheck from screwing
up.
v3: Rename to i915_reset_device to fit in better with i915_reset_engine

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Michel Thierry <michel.thierry at intel.com>
Reviewed-by: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c                  | 23 +++++++++++------------
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c |  4 ++++
 2 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4cd9ee1ba332..8e9f4378b5a7 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2600,13 +2600,13 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 }
 
 /**
- * i915_reset_and_wakeup - do process context error handling work
+ * i915_reset_device - do process context error handling work
  * @dev_priv: i915 device private
  *
  * Fire an error uevent so userspace can see that a hang or error
  * was detected.
  */
-static void i915_reset_and_wakeup(struct drm_i915_private *dev_priv)
+static void i915_reset_device(struct drm_i915_private *dev_priv)
 {
 	struct kobject *kobj = &dev_priv->drm.primary->kdev->kobj;
 	char *error_event[] = { I915_ERROR_UEVENT "=1", NULL };
@@ -2646,13 +2646,6 @@ static void i915_reset_and_wakeup(struct drm_i915_private *dev_priv)
 	if (!test_bit(I915_WEDGED, &dev_priv->gpu_error.flags))
 		kobject_uevent_env(kobj,
 				   KOBJ_CHANGE, reset_done_event);
-
-	/*
-	 * Note: The wake_up also serves as a memory barrier so that
-	 * waiters see the updated value of the dev_priv->gpu_error.
-	 */
-	clear_bit(I915_RESET_BACKOFF, &dev_priv->gpu_error.flags);
-	wake_up_all(&dev_priv->gpu_error.reset_queue);
 }
 
 static inline void
@@ -2744,11 +2737,17 @@ void i915_handle_error(struct drm_i915_private *dev_priv,
 	if (!engine_mask)
 		goto out;
 
-	if (test_and_set_bit(I915_RESET_BACKOFF,
-			     &dev_priv->gpu_error.flags))
+	if (test_and_set_bit(I915_RESET_BACKOFF, &dev_priv->gpu_error.flags)) {
+		wait_event(dev_priv->gpu_error.reset_queue,
+			   !test_bit(I915_RESET_BACKOFF,
+				     &dev_priv->gpu_error.flags));
 		goto out;
+	}
+
+	i915_reset_device(dev_priv);
 
-	i915_reset_and_wakeup(dev_priv);
+	clear_bit(I915_RESET_BACKOFF, &dev_priv->gpu_error.flags);
+	wake_up_all(&dev_priv->gpu_error.reset_queue);
 
 out:
 	intel_runtime_pm_put(dev_priv);
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index aa31d6c0cdfb..cc00a361f0fa 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -316,6 +316,8 @@ static int igt_global_reset(void *arg)
 
 	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
 	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
+
 	if (i915_terminally_wedged(&i915->gpu_error))
 		err = -EIO;
 
@@ -404,6 +406,7 @@ static int igt_wait_reset(void *arg)
 unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
 
 	if (i915_terminally_wedged(&i915->gpu_error))
 		return -EIO;
@@ -519,6 +522,7 @@ static int igt_reset_queue(void *arg)
 unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
+	wake_up_all(&i915->gpu_error.reset_queue);
 
 	if (i915_terminally_wedged(&i915->gpu_error))
 		return -EIO;
-- 
2.11.0