diff mbox

[10/14] drm/i915: Extending i915_gem_check_wedge to check engine reset in progress

Message ID 1460480381-8777-11-git-send-email-arun.siluvery@linux.intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

arun.siluvery@linux.intel.com April 12, 2016, 4:59 p.m. UTC 
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.

Also, i915_wait_request was updated to take advantage of this new
functionality. This is important since the TDR hang recovery mechanism needs a
way to force waiting threads that hold the struct_mutex to give up the
struct_mutex and try again after the hang recovery has completed. 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@intel.com>
Signed-off-by: Ian Lister <ian.lister@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem.c         | 39 +++++++++++++++++++++++++++------
 drivers/gpu/drm/i915/intel_lrc.c        |  1 +
 drivers/gpu/drm/i915/intel_ringbuffer.c |  1 +
 4 files changed, 35 insertions(+), 7 deletions(-)
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index eda531f..682bf207 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3052,6 +3052,7 @@  i915_gem_find_active_request(struct intel_engine_cs *engine);
 bool i915_gem_retire_requests(struct drm_device *dev);
 void i915_gem_retire_requests_ring(struct intel_engine_cs *engine);
 int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
+				      struct intel_engine_cs *engine,
 				      bool interruptible);
 
 static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4c62583..5ca8bd5 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -80,12 +80,29 @@  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;
 
 #define EXIT_COND (!i915_reset_in_progress(error) || \
+		   !i915_engine_reset_pending(error, NULL) ||	\
 		   i915_terminally_wedged(error))
 	if (EXIT_COND)
 		return 0;
@@ -1112,9 +1129,11 @@  put_rpm:
 
 int
 i915_gem_check_wedge(struct i915_gpu_error *error,
+		     struct intel_engine_cs *engine,
 		     bool interruptible)
 {
-	if (i915_reset_in_progress(error)) {
+	if (i915_reset_in_progress(error) ||
+	    i915_engine_reset_pending(error, engine)) {
 		/* Non-interruptible callers can't handle -EAGAIN, hence return
 		 * -EIO unconditionally for these. */
 		if (!interruptible)
@@ -1296,16 +1315,22 @@  int __i915_wait_request(struct drm_i915_gem_request *req,
 
 	for (;;) {
 		struct timer_list timer;
+		int reset_in_progress;
 
 		prepare_to_wait(&engine->irq_queue, &wait, state);
 
 		/* We need to check whether any gpu reset happened in between
 		 * the caller grabbing the seqno and now ... */
-		if (reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter)) {
+		reset_in_progress = i915_gem_check_wedge(&dev_priv->gpu_error,
+							 NULL,
+							 interruptible);
+		if (reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter) ||
+		    reset_in_progress) {
 			/* ... but upgrade the -EAGAIN to an -EIO if the gpu
 			 * is truely gone. */
-			ret = i915_gem_check_wedge(&dev_priv->gpu_error, interruptible);
-			if (ret == 0)
+			if (reset_in_progress)
+				ret = reset_in_progress;
+			else
 				ret = -EAGAIN;
 			break;
 		}
@@ -1471,7 +1496,7 @@  i915_wait_request(struct drm_i915_gem_request *req)
 
 	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
 
-	ret = i915_gem_check_wedge(&dev_priv->gpu_error, interruptible);
+	ret = i915_gem_check_wedge(&dev_priv->gpu_error, NULL, interruptible);
 	if (ret)
 		return ret;
 
@@ -1561,7 +1586,7 @@  i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj,
 	if (!obj->active)
 		return 0;
 
-	ret = i915_gem_check_wedge(&dev_priv->gpu_error, true);
+	ret = i915_gem_check_wedge(&dev_priv->gpu_error, NULL, true);
 	if (ret)
 		return ret;
 
@@ -4138,7 +4163,7 @@  i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 	if (ret)
 		return ret;
 
-	ret = i915_gem_check_wedge(&dev_priv->gpu_error, false);
+	ret = i915_gem_check_wedge(&dev_priv->gpu_error, NULL, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 86d5e18..72e5b70 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -941,6 +941,7 @@  int intel_logical_ring_begin(struct drm_i915_gem_request *req, int num_dwords)
 	dev_priv = req->i915;
 
 	ret = i915_gem_check_wedge(&dev_priv->gpu_error,
+				   req->engine,
 				   dev_priv->mm.interruptible);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e144f4f..3b087f0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2518,6 +2518,7 @@  int intel_ring_begin(struct drm_i915_gem_request *req,
 	dev_priv = req->i915;
 
 	ret = i915_gem_check_wedge(&dev_priv->gpu_error,
+				   engine,
 				   dev_priv->mm.interruptible);
 	if (ret)
 		return ret;