[Intel-gfx] [PATCH] drm/i915: Always try to reset the GPU on takeover

[Chris Wilson]

When we first introduced the reset to sanitize the GPU on taking over
from the BIOS and before returning control to third parties (the BIOS!),
we restricted it to only systems utilizing HW contexts as we were
uncertain of how stable our reset mechanism truly was. We now have
reasonable coverage across all machines that expose a GPU reset method,
and so we should be safe to sanitize the GPU state everywhere.

v2: We _have_ to skip the reset if it would clobber the display.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem.c          | 11 ++---------
 drivers/gpu/drm/i915/i915_pci.c          |  5 +++++
 drivers/gpu/drm/i915/intel_device_info.h |  1 +
 drivers/gpu/drm/i915/intel_display.c     |  4 ++--
 drivers/gpu/drm/i915/intel_engine_cs.c   |  4 ++++
 5 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7d45e71100bc..50a87272af12 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3441,8 +3441,7 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915)
 	i915_retire_requests(i915);
 	GEM_BUG_ON(i915->gt.active_requests);
 
-	if (!intel_gpu_reset(i915, ALL_ENGINES))
-		intel_engines_sanitize(i915);
+	intel_engines_sanitize(i915);
 
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
@@ -5034,8 +5033,6 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
-	int err;
-
 	GEM_TRACE("\n");
 
 	mutex_lock(&i915->drm.struct_mutex);
@@ -5060,11 +5057,7 @@ 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))
-		err = WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
-	if (!err)
-		intel_engines_sanitize(i915);
+	intel_engines_sanitize(i915);
 
 	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
 	intel_runtime_pm_put(i915);
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 9ddd2db906ce..be0ae8a96fe9 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -69,6 +69,7 @@
 	GEN(2), \
 	.num_pipes = 1, \
 	.has_overlay = 1, .overlay_needs_physical = 1, \
+	.gpu_reset_clobbers_display = true, \
 	.has_gmch_display = 1, \
 	.hws_needs_physical = 1, \
 	.unfenced_needs_alignment = 1, \
@@ -109,6 +110,7 @@ static const struct intel_device_info intel_i865g_info = {
 	GEN(3), \
 	.num_pipes = 2, \
 	.has_gmch_display = 1, \
+	.gpu_reset_clobbers_display = true, \
 	.ring_mask = RENDER_RING, \
 	.has_snoop = true, \
 	.has_coherent_ggtt = true, \
@@ -179,6 +181,7 @@ static const struct intel_device_info intel_pineview_info = {
 	.num_pipes = 2, \
 	.has_hotplug = 1, \
 	.has_gmch_display = 1, \
+	.gpu_reset_clobbers_display = true, \
 	.ring_mask = RENDER_RING, \
 	.has_snoop = true, \
 	.has_coherent_ggtt = true, \
@@ -208,6 +211,7 @@ static const struct intel_device_info intel_g45_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_G45),
 	.ring_mask = RENDER_RING | BSD_RING,
+	.gpu_reset_clobbers_display = false,
 };
 
 static const struct intel_device_info intel_gm45_info = {
@@ -216,6 +220,7 @@ static const struct intel_device_info intel_gm45_info = {
 	.is_mobile = 1, .has_fbc = 1,
 	.supports_tv = 1,
 	.ring_mask = RENDER_RING | BSD_RING,
+	.gpu_reset_clobbers_display = false,
 };
 
 #define GEN5_FEATURES \
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index af7002640cdf..a80a4627032e 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -92,6 +92,7 @@ enum intel_ppgtt {
 	func(has_csr); \
 	func(has_ddi); \
 	func(has_dp_mst); \
+	func(gpu_reset_clobbers_display); \
 	func(has_reset_engine); \
 	func(has_fbc); \
 	func(has_fpga_dbg); \
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 36434c5359b1..9774a6b3a313 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3778,8 +3778,8 @@ __intel_display_resume(struct drm_device *dev,
 
 static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv)
 {
-	return intel_has_gpu_reset(dev_priv) &&
-		INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv);
+	return (INTEL_INFO(dev_priv)->gpu_reset_clobbers_display &&
+		intel_has_gpu_reset(dev_priv));
 }
 
 void intel_prepare_reset(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 1c6143bdf5a4..d5f7e1f6720b 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1081,6 +1081,10 @@ void intel_engines_sanitize(struct drm_i915_private *i915)
 
 	GEM_TRACE("\n");
 
+	if (INTEL_INFO(i915)->gpu_reset_clobbers_display ||
+	    intel_gpu_reset(i915, ALL_ENGINES))
+		return;
+
 	for_each_engine(engine, i915, id) {
 		if (engine->reset.reset)
 			engine->reset.reset(engine, NULL);
-- 
2.19.0