drm/i915: L3 cache remapping is part of context switching

Move the i915_gem_l3_remap function such that it next to the context
switching, which is where we perform the L3 remap.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1461833819-3991-8-git-send-email-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_gem.c

@@ -4738,37 +4738,6 @@ i915_gem_suspend(struct drm_device *dev)
 	return ret;
 }
 
-int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
-{
-	struct intel_engine_cs *engine = req->engine;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
-	int i, ret;
-
-	if (!HAS_L3_DPF(dev) || !remap_info)
-		return 0;
-
-	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
-	if (ret)
-		return ret;
-
-	/*
-	 * Note: We do not worry about the concurrent register cacheline hang
-	 * here because no other code should access these registers other than
-	 * at initialization time.
-	 */
-	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
-		intel_ring_emit(engine, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit_reg(engine, GEN7_L3LOG(slice, i));
-		intel_ring_emit(engine, remap_info[i]);
-	}
-
-	intel_ring_advance(engine);
-
-	return ret;
-}
-
 void i915_gem_init_swizzling(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;

drivers/gpu/drm/i915/i915_gem_context.c

@@ -601,6 +601,37 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 	return ret;
 }
 
+int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
+{
+	struct intel_engine_cs *engine = req->engine;
+	struct drm_device *dev = engine->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
+	int i, ret;
+
+	if (!HAS_L3_DPF(dev) || !remap_info)
+		return 0;
+
+	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
+	if (ret)
+		return ret;
+
+	/*
+	 * Note: We do not worry about the concurrent register cacheline hang
+	 * here because no other code should access these registers other than
+	 * at initialization time.
+	 */
+	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
+		intel_ring_emit(engine, MI_LOAD_REGISTER_IMM(1));
+		intel_ring_emit_reg(engine, GEN7_L3LOG(slice, i));
+		intel_ring_emit(engine, remap_info[i]);
+	}
+
+	intel_ring_advance(engine);
+
+	return ret;
+}
+
 static inline bool skip_rcs_switch(struct intel_engine_cs *engine,
 				   struct intel_context *to)
 {