drm/i915: Better reset handling for contexts

This patch adds to changes for contexts on reset:
Sets last context to default - this will prevent the context switch
happening after a reset. That switch is not possible because the
rings are hung during reset and context switch requires reset. This
behavior will need to be reworked in the future, but this is what we
want for now.

In the future, we'll also want to reset the guilty context to
uninitialized. We should wait for ARB_Robustness related code to land
for that.

This is somewhat for paranoia.  Because we really don't know what the
GPU was doing when it hung, or the state it was in (mid context write,
for example), later restoring the context is a bad idea. By setting the
flag to not initialized, the next load of that context will not restore
the state, and thus on the subsequent switch away from the context will
overwrite the old data.

NOTE: This code needs a fixup when we actually have multiple VMs. The
issue that can occur is inactive objects in a VM will need to be
destroyed before the last context unref. This can now happen via the
fake switch introduced in this patch (and it other ways in the future)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

3 files changed, 46 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2b16c29ea571..40acdde5f224 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2225,6 +2225,7 @@ i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
 /* i915_gem_context.c */
 int __must_check i915_gem_context_init(struct drm_device *dev);
 void i915_gem_context_fini(struct drm_device *dev);
+void i915_gem_context_reset(struct drm_device *dev);
 int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
 void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
 int i915_switch_context(struct intel_ring_buffer *ring,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 254f575b259c..fe17c62c7b09 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2412,6 +2412,8 @@ void i915_gem_reset(struct drm_device *dev)
 
 	i915_gem_cleanup_ringbuffer(dev);
 
+	i915_gem_context_reset(dev);
+
 	i915_gem_restore_fences(dev);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 5f8bc06e8594..509e460e982e 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -255,6 +255,49 @@ err_destroy:
 	return ret;
 }
 
+void i915_gem_context_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *ring;
+	int i;
+
+	if (!HAS_HW_CONTEXTS(dev))
+		return;
+
+	/* Prevent the hardware from restoring the last context (which hung) on
+	 * the next switch */
+	for (i = 0; i < I915_NUM_RINGS; i++) {
+		struct i915_hw_context *dctx;
+		if (!(INTEL_INFO(dev)->ring_mask & (1<<i)))
+			continue;
+
+		/* Do a fake switch to the default context */
+		ring = &dev_priv->ring[i];
+		dctx = ring->default_context;
+		if (WARN_ON(!dctx))
+			continue;
+
+		if (!ring->last_context)
+			continue;
+
+		if (ring->last_context == dctx)
+			continue;
+
+		if (i == RCS) {
+			WARN_ON(i915_gem_obj_ggtt_pin(dctx->obj,
+						      get_context_alignment(dev),
+						      false, false));
+			/* Fake a finish/inactive */
+			dctx->obj->base.write_domain = 0;
+			dctx->obj->active = 0;
+		}
+
+		i915_gem_context_unreference(ring->last_context);
+		i915_gem_context_reference(dctx);
+		ring->last_context = dctx;
+	}
+}
+
 int i915_gem_context_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;