[Intel-gfx] [PATCH] drm/i915: Fix fallout of fake reset along resume

[Chris Wilson]

commit b2209e62a450 ("drm/i915/execlists: Reset the CSB head tracking on
reset/sanitization") and commit 1288786b18f7 ("drm/i915: Move GEM sanitize
from resume_early to resume") show the conflicting requirements on the
code. We must reset the GPU before trashing live state on a fast resume
(hibernation debug, or error paths), but we must only reset our state
tracking iff the GPU is reset (or power cycled). This is tricky if we
are disabling GPU reset to simulate broken hardware; we reset our state
tracking but the GPU is left intact and recovers from its stale state.

Fixes: b2209e62a450 ("drm/i915/execlists: Reset the CSB head tracking on reset/sanitization")
Fixes: 1288786b18f7 ("drm/i915: Move GEM sanitize from resume_early to resume")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c         |  2 ++
 drivers/gpu/drm/i915/i915_gem.c         | 14 +++++---------
 drivers/gpu/drm/i915/intel_engine_cs.c  | 22 ++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 ++
 4 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 7423d78f38f4..beb0951001ce 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1841,6 +1841,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
 	else
 		intel_display_set_init_power(dev_priv, true);
 
+	intel_engines_sanitize(dev_priv);
+
 	enable_rpm_wakeref_asserts(dev_priv);
 
 out:
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5155e458b11e..822abf444378 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4990,8 +4990,7 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	int err;
 
 	GEM_TRACE("\n");
 
@@ -5017,14 +5016,11 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	 * it may impact the display and we are uncertain about the stability
 	 * of the reset, so this could be applied to even earlier gen.
 	 */
+	err = -ENODEV;
 	if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915))
-		WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
-
-	/* Reset the submission backend after resume as well as the GPU reset */
-	for_each_engine(engine, i915, id) {
-		if (engine->reset.reset)
-			engine->reset.reset(engine, NULL);
-	}
+		err = WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
+	if (!err)
+		intel_engines_sanitize(i915);
 
 	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
 	intel_runtime_pm_put(i915);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 13bb8c7d2621..32bf3a408d46 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1077,6 +1077,28 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 		engine->set_default_submission(engine);
 }
 
+/**
+ * intel_engines_sanitize: called after the GPU has lost power
+ * @i915: the i915 device
+ *
+ * Anytime we reset the GPU, either with an explicit GPU reset or through a
+ * PCI power cycle, the GPU loses state and we must reset our state tracking
+ * to match. Note that calling intel_engines_sanitize() if the GPU has not
+ * been reset results in much confusion!
+ */
+void intel_engines_sanitize(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	GEM_TRACE("\n");
+
+	for_each_engine(engine, i915, id) {
+		if (engine->reset.reset)
+			engine->reset.reset(engine, NULL);
+	}
+}
+
 /**
  * intel_engines_park: called when the GT is transitioning from busy->idle
  * @i915: the i915 device
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 4003f3ebe3d1..a0bc7a8222b4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -1052,6 +1052,8 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset)
 	return cs;
 }
 
+void intel_engines_sanitize(struct drm_i915_private *i915);
+
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 
-- 
2.17.1