drm/i915: Reset logical ring contexts' head and tail during GPU reset

Work was getting left behind in LRC contexts during reset.  This causes a hang
if the GPU is reset when HEAD==TAIL because the context's ringbuffer head and
tail don't get reset and retiring a request doesn't alter them, so the ring
still appears full.

Added a function intel_lr_context_reset() to reset head and tail on a LRC and
its ringbuffer.

Call intel_lr_context_reset() for each context in i915_gem_context_reset() when
in execlists mode.

Testcase: igt/pm_rps --run-subtest reset #bdw
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88096
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: Dave Gordon <david.s.gordon@intel.com>
[danvet: Flatten control flow in the lrc reset code a notch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

3 files changed, 45 insertions, 4 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 8603bf48d3ee..70346b0028f9 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -296,11 +296,15 @@ void i915_gem_context_reset(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
-	/* In execlists mode we will unreference the context when the execlist
-	 * queue is cleared and the requests destroyed.
-	 */
-	if (i915.enable_execlists)
+	if (i915.enable_execlists) {
+		struct intel_context *ctx;
+
+		list_for_each_entry(ctx, &dev_priv->context_list, link) {
+			intel_lr_context_reset(dev, ctx);
+		}
+
 		return;
+	}
 
 	for (i = 0; i < I915_NUM_RINGS; i++) {
 		struct intel_engine_cs *ring = &dev_priv->ring[i];
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 98c87f617bf2..0bd0a9cfca8c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1991,3 +1991,38 @@ error_unpin_ctx:
 	drm_gem_object_unreference(&ctx_obj->base);
 	return ret;
 }
+
+void intel_lr_context_reset(struct drm_device *dev,
+			struct intel_context *ctx)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring;
+	int i;
+
+	for_each_ring(ring, dev_priv, i) {
+		struct drm_i915_gem_object *ctx_obj =
+				ctx->engine[ring->id].state;
+		struct intel_ringbuffer *ringbuf =
+				ctx->engine[ring->id].ringbuf;
+		uint32_t *reg_state;
+		struct page *page;
+
+		if (!ctx_obj)
+			continue;
+
+		if (i915_gem_object_get_pages(ctx_obj)) {
+			WARN(1, "Failed get_pages for context obj\n");
+			continue;
+		}
+		page = i915_gem_object_get_page(ctx_obj, 1);
+		reg_state = kmap_atomic(page);
+
+		reg_state[CTX_RING_HEAD+1] = 0;
+		reg_state[CTX_RING_TAIL+1] = 0;
+
+		kunmap_atomic(reg_state);
+
+		ringbuf->head = 0;
+		ringbuf->tail = 0;
+	}
+}
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index f635735df8a1..5dd0ecaf6128 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -73,6 +73,8 @@ int intel_lr_context_deferred_create(struct intel_context *ctx,
 				     struct intel_engine_cs *ring);
 void intel_lr_context_unpin(struct intel_engine_cs *ring,
 		struct intel_context *ctx);
+void intel_lr_context_reset(struct drm_device *dev,
+			struct intel_context *ctx);
 
 /* Execlists */
 int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);