[Intel-gfx] [PATCH v2] drm/i915/execlists: Use coherent writes into the context image

[Chris Wilson]

That we use a WB mapping for updating the RING_TAIL register inside the
context image even on !llc machines has been a source of consternation
for every reader. It appears to work on bsw+, but it may just have been
that we have been incredibly bad at detecting the errors.

v2: With extra enthusiasm.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h         | 6 ++++++
 drivers/gpu/drm/i915/i915_gem.c         | 2 ++
 drivers/gpu/drm/i915/i915_perf.c        | 3 ++-
 drivers/gpu/drm/i915/intel_engine_cs.c  | 2 +-
 drivers/gpu/drm/i915/intel_lrc.c        | 8 +++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +-
 6 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 74482753a04e..28973e692045 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3069,6 +3069,12 @@ enum i915_map_type {
 	I915_MAP_FORCE_WC = I915_MAP_WC | I915_MAP_OVERRIDE,
 };
 
+static inline enum i915_map_type
+i915_coherent_map_type(struct drm_i915_private *i915)
+{
+	return HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC;
+}
+
 /**
  * i915_gem_object_pin_map - return a contiguous mapping of the entire object
  * @obj: the object to map into kernel address space
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0453eb42a1a3..71832e2c85ad 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5404,6 +5404,8 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	for_each_engine(engine, i915, id) {
 		struct i915_vma *state;
 
+		GEM_BUG_ON(to_intel_context(ctx, engine)->pin_count);
+
 		state = to_intel_context(ctx, engine)->state;
 		if (!state)
 			continue;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0376338d1f8d..d2ba7a641866 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1849,7 +1849,8 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv,
 		if (!ce->state)
 			continue;
 
-		regs = i915_gem_object_pin_map(ce->state->obj, I915_MAP_WB);
+		regs = i915_gem_object_pin_map(ce->state->obj,
+					      i915_coherent_map_type(dev_priv));
 		if (IS_ERR(regs)) {
 			ret = PTR_ERR(regs);
 			goto out;
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 8628567d8f6e..2579151c1e05 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1157,7 +1157,7 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 		map = NULL;
 		if (engine->default_state)
 			map = i915_gem_object_pin_map(engine->default_state,
-						      I915_MAP_WB);
+						      I915_MAP_FORCE_WB);
 		if (!IS_ERR_OR_NULL(map))
 			engine->pinned_default_state = map;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3632521a5fb2..7718836c2ada 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1292,7 +1292,7 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 	 * on an active context (which by nature is already on the GPU).
 	 */
 	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
-		err = i915_gem_object_set_to_gtt_domain(vma->obj, true);
+		err = i915_gem_object_set_to_wc_domain(vma->obj, true);
 		if (err)
 			return err;
 	}
@@ -1320,7 +1320,9 @@ __execlists_context_pin(struct intel_engine_cs *engine,
 	if (ret)
 		goto err;
 
-	vaddr = i915_gem_object_pin_map(ce->state->obj, I915_MAP_WB);
+	vaddr = i915_gem_object_pin_map(ce->state->obj,
+					i915_coherent_map_type(ctx->i915) |
+					I915_MAP_OVERRIDE);
 	if (IS_ERR(vaddr)) {
 		ret = PTR_ERR(vaddr);
 		goto unpin_vma;
@@ -2685,7 +2687,7 @@ populate_lr_context(struct i915_gem_context *ctx,
 		void *defaults;
 
 		defaults = i915_gem_object_pin_map(engine->default_state,
-						   I915_MAP_WB);
+						   I915_MAP_FORCE_WB);
 		if (IS_ERR(defaults)) {
 			ret = PTR_ERR(defaults);
 			goto err_unpin_ctx;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d40f55a8dc34..3d82f6b5c229 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1285,7 +1285,7 @@ alloc_context_vma(struct intel_engine_cs *engine)
 		}
 
 		defaults = i915_gem_object_pin_map(engine->default_state,
-						   I915_MAP_WB);
+						   I915_MAP_FORCE_WB);
 		if (IS_ERR(defaults)) {
 			err = PTR_ERR(defaults);
 			goto err_map;
-- 
2.18.0