[Intel-gfx] [PATCH v2 1/3] drm/i915: Wait for all engines to be idle as part of i915_gem_wait_for_idle()

[Chris Wilson]

Make i915_gem_wait_for_idle() be a little heavier in order to try and
guarantee that the GPU is indeed idle (by checking each engine
individually is idle, i.e. all writes are complete and the rings
stopped) after waiting for in-flight requests to be completed.

v2: And return the final error.
v3: Break the wait_for() out from under the WARN -- the macro expansion
is hideous and unreadable in the warning message
v4: If wait_for_engine() fails the result is catastrophic, mark the
device as wedged and wait for the repair team.

References: https://bugs.freedesktop.org/show_bug.cgi?id=98836
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 84ea249c6f4f..c6b68eaeb71e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3268,6 +3268,29 @@ static int wait_for_timeline(struct i915_gem_timeline *tl, unsigned int flags)
 	return 0;
 }
 
+static int wait_for_engine(struct intel_engine_cs *engine, int timeout_ms)
+{
+	return wait_for(intel_engine_is_idle(engine), timeout_ms);
+}
+
+static int wait_for_engines(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, i915, id) {
+		if (GEM_WARN_ON(wait_for_engine(engine, 50))) {
+			i915_gem_set_wedged(i915);
+			return -EIO;
+		}
+
+		GEM_BUG_ON(intel_engine_get_seqno(engine) !=
+			   intel_engine_last_submit(engine));
+	}
+
+	return 0;
+}
+
 int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 {
 	int ret;
@@ -3282,13 +3305,13 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 			if (ret)
 				return ret;
 		}
+
+		ret = wait_for_engines(i915);
 	} else {
 		ret = wait_for_timeline(&i915->gt.global_timeline, flags);
-		if (ret)
-			return ret;
 	}
 
-	return 0;
+	return ret;
 }
 
 /** Flushes the GTT write domain for the object if it's dirty. */
-- 
2.11.0