[Intel-gfx] [PATCH v6 25/25] drm/i915: Unify GPU resets upon shutdown

[Chris Wilson]

Both execlists and legacy need to reset the context (and mode) of the
GPU before we lose control of the system. By resetting the GPU, we
revert back to default settings. This simplifies the life of any
subsequent driver (in particular for virtualized setups) as it does not
then have to try and recover from an unknown condition. As both paths
need to reset for the same reason, move the reset to a common point.

This unifies the resets added in a647828afc (drm/i915: Also perform gpu
reset under execlist mode) and 8e96d9c4d9 (drm/i915: reset the GPU on
context fini).

v2: Restrict the reset to "modern" gen (where we enable HW contexts) to
try and avoid leaving the machine in an unusable state with a risky
reset on older GPU. This should keep the status quo as to who performs
resets (i.e. currently only GPUs with HW contexts perform a reset on
shutdown).

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin at linux.intel.com>
CC: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
Cc: "Niu, Bing" <bing.niu at intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_dma.c         | 45 +++++++++++++++++++++++++++------
 drivers/gpu/drm/i915/i915_gem.c         |  8 ------
 drivers/gpu/drm/i915/i915_gem_context.c | 10 +-------
 3 files changed, 38 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 5c7615041b31..d70f028afadb 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -425,6 +425,41 @@ static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
 	.can_switch = i915_switcheroo_can_switch,
 };
 
+static void i915_gem_fini(struct drm_device *dev)
+{
+	/*
+	 * Neither the BIOS, ourselves or any other kernel
+	 * expects the system to be in execlists mode on startup,
+	 * so we need to reset the GPU back to legacy mode. And the only
+	 * known way to disable logical contexts is through a GPU reset.
+	 *
+	 * So in order to leave the system in a known default configuration,
+	 * always reset the GPU upon unload. Afterwards we then clean up the
+	 * GEM state tracking, flushing off the requests and leaving the
+	 * system in a known idle state.
+	 *
+	 * Note that is of the upmost importance that the GPU is idle and
+	 * all stray writes are flushed *before* we dismantle the backing
+	 * storage for the pinned objects.
+	 *
+	 * However, since we are uncertain that reseting the GPU on older
+	 * machines is a good idea, we don't - just in case it leaves the
+	 * machine in an unusable condition.
+	 */
+	if (HAS_HW_CONTEXTS(dev)) {
+		int reset = intel_gpu_reset(dev, ALL_ENGINES);
+		WARN_ON(reset && reset != -ENODEV);
+	}
+
+	mutex_lock(&dev->struct_mutex);
+	i915_gem_reset(dev);
+	i915_gem_cleanup_engines(dev);
+	i915_gem_context_fini(dev);
+	mutex_unlock(&dev->struct_mutex);
+
+	WARN_ON(!list_empty(&to_i915(dev)->context_list));
+}
+
 static int i915_load_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -506,10 +541,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	return 0;
 
 cleanup_gem:
-	mutex_lock(&dev->struct_mutex);
-	i915_gem_cleanup_engines(dev);
-	i915_gem_context_fini(dev);
-	mutex_unlock(&dev->struct_mutex);
+	i915_gem_fini(dev);
 cleanup_irq:
 	intel_guc_ucode_fini(dev);
 	drm_irq_uninstall(dev);
@@ -1456,10 +1488,7 @@ int i915_driver_unload(struct drm_device *dev)
 	flush_workqueue(dev_priv->wq);
 
 	intel_guc_ucode_fini(dev);
-	mutex_lock(&dev->struct_mutex);
-	i915_gem_cleanup_engines(dev);
-	i915_gem_context_fini(dev);
-	mutex_unlock(&dev->struct_mutex);
+	i915_gem_fini(dev);
 	intel_fbc_cleanup_cfb(dev_priv);
 
 	intel_power_domains_fini(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1174966b3b38..fb5c46dd0219 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4961,14 +4961,6 @@ i915_gem_cleanup_engines(struct drm_device *dev)
 
 	for_each_engine(engine, dev_priv)
 		dev_priv->gt.cleanup_engine(engine);
-
-	if (i915.enable_execlists)
-		/*
-		 * Neither the BIOS, ourselves or any other kernel
-		 * expects the system to be in execlists mode on startup,
-		 * so we need to reset the GPU back to legacy mode.
-		 */
-		intel_gpu_reset(dev, ALL_ENGINES);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 9477af0fcb33..cd39aba09137 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -450,16 +450,8 @@ void i915_gem_context_fini(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_context *dctx = dev_priv->kernel_context;
 
-	i915_gem_context_lost(dev_priv);
-
-	if (dctx->legacy_hw_ctx.rcs_state) {
-		/* The only known way to stop the gpu from accessing the hw context is
-		 * to reset it. Do this as the very last operation to avoid confusing
-		 * other code, leading to spurious errors. */
-		intel_gpu_reset(dev, ALL_ENGINES);
-
+	if (dctx->legacy_hw_ctx.rcs_state)
 		i915_gem_object_ggtt_unpin(dctx->legacy_hw_ctx.rcs_state);
-	}
 
 	i915_gem_context_unreference(dctx);
 	dev_priv->kernel_context = NULL;
-- 
2.8.1