[Intel-gfx] [PATCH 3/5] drm/i915: Cache LRCA in the context

Tvrtko Ursulin tvrtko.ursulin at linux.intel.com
Tue Nov 10 02:59:43 PST 2015


From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

LRCA is static while the context is pinned so we can avoid looking
up the VMA in question several times per interrupt handled.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 15 ++++++---------
 drivers/gpu/drm/i915/i915_drv.h     |  1 +
 drivers/gpu/drm/i915/intel_lrc.c    | 28 +++++++++++++++-------------
 drivers/gpu/drm/i915/intel_lrc.h    |  3 ++-
 4 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 5659d4c6c2c3..2b1598c8e01f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1973,12 +1973,13 @@ static int i915_context_status(struct seq_file *m, void *unused)
 }
 
 static void i915_dump_lrc_obj(struct seq_file *m,
-			      struct intel_engine_cs *ring,
-			      struct drm_i915_gem_object *ctx_obj)
+			      struct intel_context *ctx,
+			      struct intel_engine_cs *ring)
 {
 	struct page *page;
 	uint32_t *reg_state;
 	int j;
+	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
 	unsigned long ggtt_offset = 0;
 
 	if (ctx_obj == NULL) {
@@ -1988,7 +1989,7 @@ static void i915_dump_lrc_obj(struct seq_file *m,
 	}
 
 	seq_printf(m, "CONTEXT: %s %u\n", ring->name,
-		   intel_execlists_ctx_id(ctx_obj));
+		   intel_execlists_ctx_id(ctx, ring));
 
 	if (!i915_gem_obj_ggtt_bound(ctx_obj))
 		seq_puts(m, "\tNot bound in GGTT\n");
@@ -2037,8 +2038,7 @@ static int i915_dump_lrc(struct seq_file *m, void *unused)
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		for_each_ring(ring, dev_priv, i) {
 			if (ring->default_context != ctx)
-				i915_dump_lrc_obj(m, ring,
-						  ctx->engine[i].state);
+				i915_dump_lrc_obj(m, ctx, ring);
 		}
 	}
 
@@ -2112,11 +2112,8 @@ static int i915_execlists(struct seq_file *m, void *data)
 
 		seq_printf(m, "\t%d requests in queue\n", count);
 		if (head_req) {
-			struct drm_i915_gem_object *ctx_obj;
-
-			ctx_obj = head_req->ctx->engine[ring_id].state;
 			seq_printf(m, "\tHead request id: %u\n",
-				   intel_execlists_ctx_id(ctx_obj));
+				   intel_execlists_ctx_id(head_req->ctx, ring));
 			seq_printf(m, "\tHead request tail: %u\n",
 				   head_req->tail);
 		}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d2a546a66203..f97bb4d27996 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -885,6 +885,7 @@ struct intel_context {
 		struct drm_i915_gem_object *state;
 		struct intel_ringbuffer *ringbuf;
 		int pin_count;
+		u32 lrca;
 	} engine[I915_NUM_RINGS];
 
 	struct list_head link;
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3f9b981cc226..1f8566b1f072 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -260,7 +260,8 @@ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists
 
 /**
  * intel_execlists_ctx_id() - get the Execlists Context ID
- * @ctx_obj: Logical Ring Context backing object.
+ * @ctx: User context we are interested in
+ * @ring: Engine to get the Context ID for
  *
  * Do not confuse with ctx->id! Unfortunately we have a name overload
  * here: the old context ID we pass to userspace as a handler so that
@@ -270,14 +271,12 @@ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists
  *
  * Return: 20-bits globally unique context ID.
  */
-u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)
+u32 intel_execlists_ctx_id(struct intel_context *ctx,
+			   struct intel_engine_cs *ring)
 {
-	u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj) +
-			LRC_PPHWSP_PN * PAGE_SIZE;
-
 	/* LRCA is required to be 4K aligned so the more significant 20 bits
 	 * are globally unique */
-	return lrca >> 12;
+	return ctx->engine[ring->id].lrca >> 12;
 }
 
 static bool disable_lite_restore_wa(struct intel_engine_cs *ring)
@@ -292,13 +291,11 @@ static bool disable_lite_restore_wa(struct intel_engine_cs *ring)
 uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
 				     struct intel_engine_cs *ring)
 {
-	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
 	uint64_t desc = ring->ctx_desc_template;
-	uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj) +
-			LRC_PPHWSP_PN * PAGE_SIZE;
+	uint64_t lrca = ctx->engine[ring->id].lrca;
 
 	desc |= lrca;
-	desc |= (u64)intel_execlists_ctx_id(ctx_obj) << GEN8_CTX_ID_SHIFT;
+	desc |= (u64)intel_execlists_ctx_id(ctx, ring) << GEN8_CTX_ID_SHIFT;
 
 	return desc;
 }
@@ -457,9 +454,7 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring,
 					    execlist_link);
 
 	if (head_req != NULL) {
-		struct drm_i915_gem_object *ctx_obj =
-				head_req->ctx->engine[ring->id].state;
-		if (intel_execlists_ctx_id(ctx_obj) == request_id) {
+		if (intel_execlists_ctx_id(head_req->ctx, ring) == request_id) {
 			WARN(head_req->elsp_submitted == 0,
 			     "Never submitted head request\n");
 
@@ -1041,6 +1036,8 @@ static int intel_lr_context_pin(struct drm_i915_gem_request *rq)
 		ret = intel_lr_context_do_pin(ring, ctx_obj, ringbuf);
 		if (ret)
 			goto reset_pin_count;
+		rq->ctx->engine[ring->id].lrca =
+		  i915_gem_obj_ggtt_offset(ctx_obj) + LRC_PPHWSP_PN * PAGE_SIZE;
 	}
 	return ret;
 
@@ -1060,6 +1057,7 @@ void intel_lr_context_unpin(struct drm_i915_gem_request *rq)
 		if (--rq->ctx->engine[ring->id].pin_count == 0) {
 			intel_unpin_ringbuffer_obj(ringbuf);
 			i915_gem_object_ggtt_unpin(ctx_obj);
+			rq->ctx->engine[ring->id].lrca = 0;
 		}
 	}
 }
@@ -1939,6 +1937,10 @@ static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *rin
 		return ret;
 	}
 
+	ring->default_context->engine[ring->id].lrca =
+		i915_gem_obj_ggtt_offset(ring->default_context->engine[ring->id].state)
+					 + LRC_PPHWSP_PN * PAGE_SIZE;
+
 	ring->disable_lite_restore_wa = disable_lite_restore_wa(ring);
 
 	ring->ctx_desc_template = GEN8_CTX_VALID;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 4e60d54ba66d..cb68bfe91ecd 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -86,6 +86,8 @@ void intel_lr_context_reset(struct drm_device *dev,
 			struct intel_context *ctx);
 uint64_t intel_lr_context_descriptor(struct intel_context *ctx,
 				     struct intel_engine_cs *ring);
+u32 intel_execlists_ctx_id(struct intel_context *ctx,
+			   struct intel_engine_cs *ring);
 
 /* Execlists */
 int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
@@ -93,7 +95,6 @@ struct i915_execbuffer_params;
 int intel_execlists_submission(struct i915_execbuffer_params *params,
 			       struct drm_i915_gem_execbuffer2 *args,
 			       struct list_head *vmas);
-u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
 
 void intel_lrc_irq_handler(struct intel_engine_cs *ring);
 void intel_execlists_retire_requests(struct intel_engine_cs *ring);
-- 
1.9.1



More information about the Intel-gfx mailing list