[Intel-gfx] [PATCH v2 10/15] drm/i915: Extending i915_gem_check_wedge to check engine reset in progress

[Arun Siluvery]

i915_gem_check_wedge now returns a non-zero result in three different cases:

1. Legacy: A hang has been detected and full GPU reset is in progress.

2. Per-engine recovery:
   a. A single engine reference can be passed to the function, in which
   case only that engine will be checked. If that particular engine is
   detected to be hung and is to be reset this will yield a non-zero result
   but not if reset is in progress for any other engine.

   b. No engine reference is passed to the function, in which case all
   engines are checked for ongoing per-engine hang recovery.

__i915_wait_request() is updated such that if an engine reset is pending,
we request the waiter to try again so that engine recovery can continue.
If i915_wait_request does not take per-engine hang recovery into account
there is no way for a waiting thread to know that a per-engine recovery is
about to happen and that it needs to back off.

Signed-off-by: Tomas Elf <tomas.elf at intel.com>
Signed-off-by: Ian Lister <ian.lister at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
---

These changes are based on current nightly. I am aware of the changes being
done to wait_request patch in "thundering herd series" but my understanding
is it has other dependencies. We can add incremental changes once that
series is merged.

 drivers/gpu/drm/i915/i915_gem.c | 43 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 38 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6160564..bc404da 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -100,12 +100,31 @@ static void i915_gem_info_remove_obj(struct drm_i915_private *dev_priv,
 	spin_unlock(&dev_priv->mm.object_stat_lock);
 }
 
+static bool i915_engine_reset_pending(struct i915_gpu_error *error,
+				     struct intel_engine_cs *engine)
+{
+	int i;
+
+	if (engine)
+		return i915_engine_reset_in_progress(error, engine->id);
+
+	for (i = 0; i < I915_NUM_ENGINES; ++i) {
+		if (i915_engine_reset_in_progress(error, i))
+			return true;
+	}
+
+	return false;
+}
+
 static int
 i915_gem_wait_for_error(struct i915_gpu_error *error)
 {
 	int ret;
 
-	if (!i915_reset_in_progress(error))
+#define EXIT_COND (!i915_reset_in_progress(error) ||	\
+		   !i915_engine_reset_pending(error, NULL))
+
+	if (EXIT_COND)
 		return 0;
 
 	/*
@@ -114,7 +133,7 @@ i915_gem_wait_for_error(struct i915_gpu_error *error)
 	 * we should simply try to bail out and fail as gracefully as possible.
 	 */
 	ret = wait_event_interruptible_timeout(error->reset_queue,
-					       !i915_reset_in_progress(error),
+					       EXIT_COND,
 					       10*HZ);
 	if (ret == 0) {
 		DRM_ERROR("Timed out waiting for the gpu reset to complete\n");
@@ -1325,12 +1344,18 @@ put_rpm:
 }
 
 static int
-i915_gem_check_wedge(unsigned reset_counter, bool interruptible)
+i915_gem_check_wedge(struct drm_i915_private *dev_priv,
+		     struct intel_engine_cs *engine,
+		     bool interruptible)
 {
+	struct i915_gpu_error *error = &dev_priv->gpu_error;
+	unsigned reset_counter = i915_reset_counter(error);
+
 	if (__i915_terminally_wedged(reset_counter))
 		return -EIO;
 
-	if (__i915_reset_in_progress(reset_counter)) {
+	if (__i915_reset_in_progress(reset_counter) ||
+	    i915_engine_reset_pending(error, engine)) {
 		/* Non-interruptible callers can't handle -EAGAIN, hence return
 		 * -EIO unconditionally for these. */
 		if (!interruptible)
@@ -1500,6 +1525,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 
 	for (;;) {
 		struct timer_list timer;
+		int reset_pending;
 
 		prepare_to_wait(&engine->irq_queue, &wait, state);
 
@@ -1515,6 +1541,13 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 			break;
 		}
 
+		reset_pending = i915_engine_reset_pending(&dev_priv->gpu_error,
+							  NULL);
+		if (reset_pending) {
+			ret = -EAGAIN;
+			break;
+		}
+
 		if (i915_gem_request_completed(req, false)) {
 			ret = 0;
 			break;
@@ -2997,7 +3030,7 @@ __i915_gem_request_alloc(struct intel_engine_cs *engine,
 	 * EIO if the GPU is already wedged, or EAGAIN to drop the struct_mutex
 	 * and restart.
 	 */
-	ret = i915_gem_check_wedge(reset_counter, dev_priv->mm.interruptible);
+	ret = i915_gem_check_wedge(dev_priv, NULL, dev_priv->mm.interruptible);
 	if (ret)
 		return ret;
 
-- 
1.9.1