Skip to contentSkip to conversation

drm/i915: Untangle execlist tracking

PATCH In review Nick Hoath 2 participants 6 messages Jan 12, 2015

Subsystems (2)
lore
Share & tools
lore

Nick Hoath

author
#0 lore raw

cover drm/i915: Untangle execlist tracking

This patchset merges execlist queue items in to gem requests. It does this by using the reference count added by the "Replace seqno values with request structures" patchset to ensure that the gem request is available for the whole execlist submission lifespan.

v2: merge intel_ctx_submit_request and drm_i915_gem_request, rebase changes &
add cover letter

v3: Rebase over upstreamed "Replace seqno values with request structures" and add overzealous freeing fix.

v4: Removed re-addition of cleanup work queue (found by Daniel Vetter)
v5: Fixed non-building individual patch (0002). Separated out the tail pointer from the postfix pointer (found by Thomas Daniel)
v6: Actual removal of intel_ctx_submit_request. Update both tail and postfix pointer in __i915_add_request (found by Thomas Daniel)

Nick Hoath (4):
drm/i915: execlist request keeps ptr/ref to gem_request drm/i915: Removed duplicate members from submit_request drm/i915: Remove FIXME_lrc_ctx backpointer drm/i915: Subsume intel_ctx_submit_request in to

    drm_i915_gem_request
 drivers/gpu/drm/i915/i915_debugfs.c     |   4 +-
 drivers/gpu/drm/i915/i915_drv.h         |  30 +++++++-
 drivers/gpu/drm/i915/i915_gem.c         |  19 +++--
 drivers/gpu/drm/i915/i915_gpu_error.c   |   2 +-
 drivers/gpu/drm/i915/i915_reg.h         |  32 +++++++++
 drivers/gpu/drm/i915/intel_display.c    |   6 +-
 drivers/gpu/drm/i915/intel_lrc.c        | 123 +++++++++++++++++++-------------
 drivers/gpu/drm/i915/intel_lrc.h        |  41 +++--------
 drivers/gpu/drm/i915/intel_ringbuffer.c |   2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.h |  14 ++--
 10 files changed, 167 insertions(+), 106 deletions(-)
Signature · 6 lines
2.1.1

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
author
#1 lore raw

PATCH 1/4 drm/i915: execlist request keeps ptr/ref to gem_request

Add a reference and pointer from the execlist queue item to the associated gem request. For execlist requests that don't have a request, create one as a placeholder.

Issue: VIZ-4274
v1: Rebase after upstream of "Replace seqno values with request structures" patchset.

---
 drivers/gpu/drm/i915/intel_lrc.c | 31 +++++++++++++++++++++++++------
 drivers/gpu/drm/i915/intel_lrc.h |  6 +++++-
 2 files changed, 30 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/intel_lrc.c +25 -6
index 7670a0f..d9eaf2d 100644
@@ -534,7 +534,8 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring)
 
 static int execlists_context_queue(struct intel_engine_cs *ring,
 				   struct intel_context *to,
-				   u32 tail)
+				   u32 tail,
+				   struct drm_i915_gem_request *request)
 {
 	struct intel_ctx_submit_request *req = NULL, *cursor;
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -553,6 +554,21 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 	req->ring = ring;
 	req->tail = tail;
 
+	if (!request) {
+		/*
+		 * If there isn't a request associated with this submission,
+		 * create one as a temporary holder.
+		 */
+		WARN(1, "execlist context submission without request");
+		request = kzalloc(sizeof(*request), GFP_KERNEL);
+		if (request == NULL)
+			return -ENOMEM;
+		request->ctx = to;
+		request->ring = ring;
+	}
+	req->request = request;
+	i915_gem_request_reference(request);
+
 	intel_runtime_pm_get(dev_priv);
 
 	spin_lock_irqsave(&ring->execlist_lock, flags);
@@ -766,6 +782,7 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring)
 			intel_lr_context_unpin(ring, ctx);
 		intel_runtime_pm_put(dev_priv);
 		i915_gem_context_unreference(req->ctx);
+		i915_gem_request_unreference(req->request);
 		list_del(&req->execlist_link);
 		kfree(req);
 	}
@@ -818,7 +835,8 @@ int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf)
  * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
  * point, the tail *inside* the context is updated and the ELSP written to.
  */
-void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf)
+void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
+					   struct drm_i915_gem_request *request)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	struct intel_context *ctx = ringbuf->FIXME_lrc_ctx;
@@ -828,7 +846,7 @@ void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf)
 	if (intel_ring_stopped(ring))
 		return;
 
-	execlists_context_queue(ring, ctx, ringbuf->tail);
+	execlists_context_queue(ring, ctx, ringbuf->tail, request);
 }
 
 static int intel_lr_context_pin(struct intel_engine_cs *ring,
@@ -972,7 +990,7 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
 		return ret;
 
 	/* Force the context submission in case we have been skipping it */
-	intel_logical_ring_advance_and_submit(ringbuf);
+	intel_logical_ring_advance_and_submit(ringbuf, NULL);
 
 	/* With GEM the hangcheck timer should kick us out of the loop,
 	 * leaving it early runs the risk of corrupting GEM state (due
@@ -1310,7 +1328,8 @@ static void gen8_set_seqno(struct intel_engine_cs *ring, u32 seqno)
 	intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
 }
 
-static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
+static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
+			     struct drm_i915_gem_request *request)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	u32 cmd;
@@ -1332,7 +1351,7 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
 		i915_gem_request_get_seqno(ring->outstanding_lazy_request));
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
-	intel_logical_ring_advance_and_submit(ringbuf);
+	intel_logical_ring_advance_and_submit(ringbuf, request);
 
 	return 0;
 }
drivers/gpu/drm/i915/intel_lrc.h +5 -1
index 960fcbd..7a82bc9 100644
@@ -39,7 +39,9 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
 int intel_logical_rings_init(struct drm_device *dev);
 
 int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf);
-void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf);
+void intel_logical_ring_advance_and_submit(
+				struct intel_ringbuffer *ringbuf,
+				struct drm_i915_gem_request *request);
 /**
  * intel_logical_ring_advance() - advance the ringbuffer tail
  * @ringbuf: Ringbuffer to advance.
@@ -110,6 +112,8 @@ struct intel_ctx_submit_request {
 	struct list_head execlist_link;
 
 	int elsp_submitted;
+
+	struct drm_i915_gem_request *request;
 };
 
 void intel_lrc_irq_handler(struct intel_engine_cs *ring);
Signature · 6 lines
2.1.1

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
author
#2 lore raw

PATCH 2/4 drm/i915: Removed duplicate members from submit_request

In reply to Nick Hoath

Where there were duplicate variables for the tail, context and ring (engine) in the gem request and the execlist queue item, use the one from the request and remove the duplicate from the execlist queue item.

Issue: VIZ-4274

v1: Rebase
v2: Fixed build issues. Keep separate postfix & tail pointers as these are used in different ways. Reinserted missing full tail pointer update.

---
 drivers/gpu/drm/i915/i915_debugfs.c     |  4 ++--
 drivers/gpu/drm/i915/i915_drv.h         |  9 ++++++++-
 drivers/gpu/drm/i915/i915_gem.c         |  8 ++++----
 drivers/gpu/drm/i915/i915_gpu_error.c   |  2 +-
 drivers/gpu/drm/i915/intel_lrc.c        | 25 +++++++++++--------------
 drivers/gpu/drm/i915/intel_lrc.h        |  4 ----
 drivers/gpu/drm/i915/intel_ringbuffer.c |  2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.h |  3 ++-
 8 files changed, 29 insertions(+), 28 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +2 -2
index e515aad..d4cc482 100644
@@ -1968,11 +1968,11 @@ static int i915_execlists(struct seq_file *m, void *data)
 		if (head_req) {
 			struct drm_i915_gem_object *ctx_obj;
 
-			ctx_obj = head_req->ctx->engine[ring_id].state;
+			ctx_obj = head_req->request->ctx->engine[ring_id].state;
 			seq_printf(m, "\tHead request id: %u\n",
 				   intel_execlists_ctx_id(ctx_obj));
 			seq_printf(m, "\tHead request tail: %u\n",
-				   head_req->tail);
+				   head_req->request->tail);
 		}
 
 		seq_putc(m, '\n');
drivers/gpu/drm/i915/i915_drv.h +8 -1
index b521613..af024f2 100644
@@ -2062,7 +2062,14 @@ struct drm_i915_gem_request {
 	/** Position in the ringbuffer of the start of the request */
 	u32 head;
 
-	/** Position in the ringbuffer of the end of the request */
+	/**
+	 * Position in the ringbuffer of the start of the postfix.
+	 * This is required to calculate the maximum available ringbuffer
+	 * space without overwriting the postfix.
+	 */
+	 u32 postfix;
+
+	/** Position in the ringbuffer of the end of the whole request */
 	u32 tail;
 
 	/** Context related to this request */
drivers/gpu/drm/i915/i915_gem.c +4 -4
index 6c40365..e6768d3 100644
@@ -2453,7 +2453,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	request_ring_position = intel_ring_get_tail(ringbuf);
 
 	if (i915.enable_execlists) {
-		ret = ring->emit_request(ringbuf);
+		ret = ring->emit_request(ringbuf, request);
 		if (ret)
 			return ret;
 	} else {
@@ -2463,7 +2463,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	}
 
 	request->head = request_start;
-	request->tail = request_ring_position;
+	request->postfix = request_ring_position;
 
 	/* Whilst this request exists, batch_obj will be on the
 	 * active_list, and so will hold the active reference. Only when this
@@ -2657,7 +2657,7 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 				execlist_link);
 		list_del(&submit_req->execlist_link);
 		intel_runtime_pm_put(dev_priv);
-		i915_gem_context_unreference(submit_req->ctx);
+		i915_gem_context_unreference(submit_req->request->ctx);
 		kfree(submit_req);
 	}
 
@@ -2783,7 +2783,7 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 		 * of tail of the request to update the last known position
 		 * of the GPU head.
 		 */
-		ringbuf->last_retired_head = request->tail;
+		ringbuf->last_retired_head = request->postfix;
 
 		i915_gem_free_request(request);
 	}
drivers/gpu/drm/i915/i915_gpu_error.c +1 -1
index be5c990..48ddbf4 100644
@@ -1052,7 +1052,7 @@ static void i915_gem_record_rings(struct drm_device *dev,
 			erq = &error->ring[i].requests[count++];
 			erq->seqno = request->seqno;
 			erq->jiffies = request->emitted_jiffies;
-			erq->tail = request->tail;
+			erq->tail = request->postfix;
 		}
 	}
 }
drivers/gpu/drm/i915/intel_lrc.c +11 -14
index d9eaf2d..312b8e8 100644
@@ -417,7 +417,7 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring)
 				 execlist_link) {
 		if (!req0) {
 			req0 = cursor;
-		} else if (req0->ctx == cursor->ctx) {
+		} else if (req0->request->ctx == cursor->request->ctx) {
 			/* Same ctx: ignore first request, as second request
 			 * will update tail past first request's workload */
 			cursor->elsp_submitted = req0->elsp_submitted;
@@ -433,9 +433,9 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring)
 
 	WARN_ON(req1 && req1->elsp_submitted);
 
-	execlists_submit_contexts(ring, req0->ctx, req0->tail,
-				  req1 ? req1->ctx : NULL,
-				  req1 ? req1->tail : 0);
+	execlists_submit_contexts(ring, req0->request->ctx, req0->request->tail,
+				  req1 ? req1->request->ctx : NULL,
+				  req1 ? req1->request->tail : 0);
 
 	req0->elsp_submitted++;
 	if (req1)
@@ -455,7 +455,7 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring,
 
 	if (head_req != NULL) {
 		struct drm_i915_gem_object *ctx_obj =
-				head_req->ctx->engine[ring->id].state;
+				head_req->request->ctx->engine[ring->id].state;
 		if (intel_execlists_ctx_id(ctx_obj) == request_id) {
 			WARN(head_req->elsp_submitted == 0,
 			     "Never submitted head request\n");
@@ -545,15 +545,10 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
 	if (req == NULL)
 		return -ENOMEM;
-	req->ctx = to;
-	i915_gem_context_reference(req->ctx);
 
 	if (to != ring->default_context)
 		intel_lr_context_pin(ring, to);
 
-	req->ring = ring;
-	req->tail = tail;
-
 	if (!request) {
 		/*
 		 * If there isn't a request associated with this submission,
@@ -563,11 +558,13 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 		request = kzalloc(sizeof(*request), GFP_KERNEL);
 		if (request == NULL)
 			return -ENOMEM;
-		request->ctx = to;
 		request->ring = ring;
 	}
+	request->ctx = to;
+	request->tail = tail;
 	req->request = request;
 	i915_gem_request_reference(request);
+	i915_gem_context_reference(req->request->ctx);
 
 	intel_runtime_pm_get(dev_priv);
 
@@ -584,7 +581,7 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 					   struct intel_ctx_submit_request,
 					   execlist_link);
 
-		if (to == tail_req->ctx) {
+		if (to == tail_req->request->ctx) {
 			WARN(tail_req->elsp_submitted != 0,
 				"More than 2 already-submitted reqs queued\n");
 			list_del(&tail_req->execlist_link);
@@ -774,14 +771,14 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring)
 	spin_unlock_irqrestore(&ring->execlist_lock, flags);
 
 	list_for_each_entry_safe(req, tmp, &retired_list, execlist_link) {
-		struct intel_context *ctx = req->ctx;
+		struct intel_context *ctx = req->request->ctx;
 		struct drm_i915_gem_object *ctx_obj =
 				ctx->engine[ring->id].state;
 
 		if (ctx_obj && (ctx != ring->default_context))
 			intel_lr_context_unpin(ring, ctx);
 		intel_runtime_pm_put(dev_priv);
-		i915_gem_context_unreference(req->ctx);
+		i915_gem_context_unreference(ctx);
 		i915_gem_request_unreference(req->request);
 		list_del(&req->execlist_link);
 		kfree(req);
drivers/gpu/drm/i915/intel_lrc.h +0 -4
index 7a82bc9..376c307 100644
@@ -105,10 +105,6 @@ u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
  * All accesses to the queue are mediated by a spinlock (ring->execlist_lock).
  */
 struct intel_ctx_submit_request {
-	struct intel_context *ctx;
-	struct intel_engine_cs *ring;
-	u32 tail;
-
 	struct list_head execlist_link;
 
 	int elsp_submitted;
drivers/gpu/drm/i915/intel_ringbuffer.c +1 -1
index 12a36f0..b42e2df 100644
@@ -1931,7 +1931,7 @@ static int intel_ring_wait_request(struct intel_engine_cs *ring, int n)
 		return 0;
 
 	list_for_each_entry(request, &ring->request_list, list) {
-		if (__intel_ring_space(request->tail, ringbuf->tail,
+		if (__intel_ring_space(request->postfix, ringbuf->tail,
 				       ringbuf->size) >= n) {
 			break;
 		}
drivers/gpu/drm/i915/intel_ringbuffer.h +2 -1
index 6dbb6f4..32aa3f3 100644
@@ -239,7 +239,8 @@ struct  intel_engine_cs {
 	struct list_head execlist_retired_req_list;
 	u8 next_context_status_buffer;
 	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
-	int		(*emit_request)(struct intel_ringbuffer *ringbuf);
+	int		(*emit_request)(struct intel_ringbuffer *ringbuf,
+					struct drm_i915_gem_request *request);
 	int		(*emit_flush)(struct intel_ringbuffer *ringbuf,
 				      u32 invalidate_domains,
 				      u32 flush_domains);
Signature · 6 lines
2.1.1

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
author
#3 lore raw

PATCH 3/4 drm/i915: Remove FIXME_lrc_ctx backpointer

In reply to Nick Hoath

The first pass implementation of execlists required a backpointer to the context to be held in the intel_ringbuffer. However the context pointer is available higher in the call stack. Remove the backpointer from the ring buffer structure and instead pass it down through the call stack.

v2: Integrate this changeset with the removal of duplicate request/execlist queue item members.
v3: Rebase
v4: Rebase. Remove passing of context when the request is passed.

---
 drivers/gpu/drm/i915/i915_gem.c         |  5 +--
 drivers/gpu/drm/i915/intel_lrc.c        | 67 ++++++++++++++++++++-------------
 drivers/gpu/drm/i915/intel_lrc.h        |  8 +++-
 drivers/gpu/drm/i915/intel_ringbuffer.h | 11 ++----
 4 files changed, 52 insertions(+), 39 deletions(-)
drivers/gpu/drm/i915/i915_gem.c +2 -3
index e6768d3..0649559 100644
@@ -2422,8 +2422,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 		return -ENOMEM;
 
 	if (i915.enable_execlists) {
-		struct intel_context *ctx = request->ctx;
-		ringbuf = ctx->engine[ring->id].ringbuf;
+		ringbuf = request->ctx->engine[ring->id].ringbuf;
 	} else
 		ringbuf = ring->buffer;
 
@@ -2436,7 +2435,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	 * what.
 	 */
 	if (i915.enable_execlists) {
-		ret = logical_ring_flush_all_caches(ringbuf);
+		ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
 		if (ret)
 			return ret;
 	} else {
drivers/gpu/drm/i915/intel_lrc.c +40 -27

263 lines not on this page · raw message

drivers/gpu/drm/i915/intel_lrc.h +6 -2
index 376c307..80a80ea 100644
@@ -38,9 +38,11 @@ void intel_logical_ring_stop(struct intel_engine_cs *ring);
 void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
 int intel_logical_rings_init(struct drm_device *dev);
 
-int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf);
+int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf,
+				  struct intel_context *ctx);
 void intel_logical_ring_advance_and_submit(
 				struct intel_ringbuffer *ringbuf,
+				struct intel_context *ctx,
 				struct drm_i915_gem_request *request);
 /**
  * intel_logical_ring_advance() - advance the ringbuffer tail
@@ -63,7 +65,9 @@ static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf,
 	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
 	ringbuf->tail += 4;
 }
-int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf, int num_dwords);
+int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf,
+			     struct intel_context *ctx,
+			     int num_dwords);
 
 /* Logical Ring Contexts */
 int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
drivers/gpu/drm/i915/intel_ringbuffer.h +4 -7
index 32aa3f3..714f3fd 100644
@@ -99,13 +99,6 @@ struct intel_ringbuffer {
 
 	struct intel_engine_cs *ring;
 
-	/*
-	 * FIXME: This backpointer is an artifact of the history of how the
-	 * execlist patches came into being. It will get removed once the basic
-	 * code has landed.
-	 */
-	struct intel_context *FIXME_lrc_ctx;
-
 	u32 head;
 	u32 tail;
 	int space;
@@ -123,6 +116,8 @@ struct intel_ringbuffer {
 	u32 last_retired_head;
 };
 
+struct	intel_context;
+
 struct  intel_engine_cs {
 	const char	*name;
 	enum intel_ring_id {
@@ -242,9 +237,11 @@ struct  intel_engine_cs {
 	int		(*emit_request)(struct intel_ringbuffer *ringbuf,
 					struct drm_i915_gem_request *request);
 	int		(*emit_flush)(struct intel_ringbuffer *ringbuf,
+				      struct intel_context *ctx,
 				      u32 invalidate_domains,
 				      u32 flush_domains);
 	int		(*emit_bb_start)(struct intel_ringbuffer *ringbuf,
+					 struct intel_context *ctx,
 					 u64 offset, unsigned flags);
 
 	/**
Signature · 6 lines
2.1.1

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
author
#4 lore raw

PATCH 4/4 drm/i915: Subsume intel_ctx_submit_request in to drm_i915_gem_request

In reply to Nick Hoath

Move all remaining elements that were unique to execlists queue items in to the associated request.

Issue: VIZ-4274

v2: Rebase. Fixed issue of overzealous freeing of request.
v3: Removed re-addition of cleanup work queue (found by Daniel Vetter)
v4: Rebase.
v5: Actual removal of intel_ctx_submit_request. Update both tail and postfix pointer in __i915_add_request (found by Thomas Daniel)

---
 drivers/gpu/drm/i915/i915_debugfs.c  |  8 +++----
 drivers/gpu/drm/i915/i915_drv.h      | 21 +++++++++++++++++
 drivers/gpu/drm/i915/i915_gem.c      | 12 +++++-----
 drivers/gpu/drm/i915/i915_reg.h      | 32 ++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_display.c |  6 ++++-
 drivers/gpu/drm/i915/intel_lrc.c     | 44 ++++++++++++++++--------------------
 drivers/gpu/drm/i915/intel_lrc.h     | 27 ----------------------
 7 files changed, 87 insertions(+), 63 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +4 -4
index d4cc482..b2dfac4 100644
@@ -1928,7 +1928,7 @@ static int i915_execlists(struct seq_file *m, void *data)
 	intel_runtime_pm_get(dev_priv);
 
 	for_each_ring(ring, dev_priv, ring_id) {
-		struct intel_ctx_submit_request *head_req = NULL;
+		struct drm_i915_gem_request *head_req = NULL;
 		int count = 0;
 		unsigned long flags;
 
@@ -1961,18 +1961,18 @@ static int i915_execlists(struct seq_file *m, void *data)
 		list_for_each(cursor, &ring->execlist_queue)
 			count++;
 		head_req = list_first_entry_or_null(&ring->execlist_queue,
-				struct intel_ctx_submit_request, execlist_link);
+				struct drm_i915_gem_request, execlist_link);
 		spin_unlock_irqrestore(&ring->execlist_lock, flags);
 
 		seq_printf(m, "\t%d requests in queue\n", count);
 		if (head_req) {
 			struct drm_i915_gem_object *ctx_obj;
 
-			ctx_obj = head_req->request->ctx->engine[ring_id].state;
+			ctx_obj = head_req->ctx->engine[ring_id].state;
 			seq_printf(m, "\tHead request id: %u\n",
 				   intel_execlists_ctx_id(ctx_obj));
 			seq_printf(m, "\tHead request tail: %u\n",
-				   head_req->request->tail);
+				   head_req->tail);
 		}
 
 		seq_putc(m, '\n');
drivers/gpu/drm/i915/i915_drv.h +21 -0
index af024f2..8c6a207 100644
@@ -2089,6 +2089,27 @@ struct drm_i915_gem_request {
 	struct list_head client_list;
 
 	uint32_t uniq;
+
+	/**
+	 * The ELSP only accepts two elements at a time, so we queue
+	 * context/tail pairs on a given queue (ring->execlist_queue) until the
+	 * hardware is available. The queue serves a double purpose: we also use
+	 * it to keep track of the up to 2 contexts currently in the hardware
+	 * (usually one in execution and the other queued up by the GPU): We
+	 * only remove elements from the head
+	 * of the queue when the hardware informs us that an element has been
+	 * completed.
+	 *
+	 * All accesses to the queue are mediated by a spinlock
+	 * (ring->execlist_lock).
+	 */
+
+	/** Execlist link in the submission queue.*/
+	struct list_head execlist_link;
+
+	/** Execlists no. of times this request has been sent to the ELSP */
+	int elsp_submitted;
+
 };
 
 void i915_gem_request_free(struct kref *req_ref);
drivers/gpu/drm/i915/i915_gem.c +6 -6
index 0649559..0195e3f 100644
@@ -2414,7 +2414,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_request *request;
 	struct intel_ringbuffer *ringbuf;
-	u32 request_ring_position, request_start;
+	u32 request_start;
 	int ret;
 
 	request = ring->outstanding_lazy_request;
@@ -2449,7 +2449,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	 * GPU processing the request, we never over-estimate the
 	 * position of the head.
 	 */
-	request_ring_position = intel_ring_get_tail(ringbuf);
+	request->postfix = intel_ring_get_tail(ringbuf);
 
 	if (i915.enable_execlists) {
 		ret = ring->emit_request(ringbuf, request);
@@ -2462,7 +2462,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	}
 
 	request->head = request_start;
-	request->postfix = request_ring_position;
+	request->tail = intel_ring_get_tail(ringbuf);
 
 	/* Whilst this request exists, batch_obj will be on the
 	 * active_list, and so will hold the active reference. Only when this
@@ -2649,14 +2649,14 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 	 * pinned in place.
 	 */
 	while (!list_empty(&ring->execlist_queue)) {
-		struct intel_ctx_submit_request *submit_req;
+		struct drm_i915_gem_request *submit_req;
 
 		submit_req = list_first_entry(&ring->execlist_queue,
-				struct intel_ctx_submit_request,
+				struct drm_i915_gem_request,
 				execlist_link);
 		list_del(&submit_req->execlist_link);
 		intel_runtime_pm_put(dev_priv);
-		i915_gem_context_unreference(submit_req->request->ctx);
+		i915_gem_context_unreference(submit_req->ctx);
 		kfree(submit_req);
 	}
 
drivers/gpu/drm/i915/i915_reg.h +32 -0
index 0f32fd1a..9ae81db 100644
@@ -5223,6 +5223,10 @@ enum punit_power_well {
 #define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1<<11)
 #define  HDC_FENCE_DEST_SLM_DISABLE		(1<<14)
 
+/* GEN8 chicken */
+#define GEN9_SLICE_COMMON_ECO_CHICKEN0		0x07308
+#define GEN9_DISABLE_PIXEL_MASK_CAMMING		(1<<14)
+
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
@@ -6169,6 +6173,7 @@ enum punit_power_well {
 #define HALF_SLICE_CHICKEN3		0xe184
 #define   HSW_SAMPLE_C_PERFORMANCE	(1<<9)
 #define   GEN8_CENTROID_PIXEL_OPT_DIS	(1<<8)
+#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1<<5)
 #define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1<<1)
 
 /* Audio */
@@ -7145,4 +7150,31 @@ enum punit_power_well {
 #define _PALETTE_A (dev_priv->info.display_mmio_offset + 0xa000)
 #define _PALETTE_B (dev_priv->info.display_mmio_offset + 0xa800)
 
+/*
+ * Chicken Registers for LLC/eLLC Hot Spotting Avoidance Mode for
+ * 3D/Media Compressed Resources
+ */
+#define GEN9_COMMON_SLICE_CHICKEN2_REG			0x7014
+#define GEN9_COMMON_SLICE_CHICKEN2_NEW_HASH_ENABLE	(1<<29 | 1<<13)
+#define GEN9_HALF_SLICE_CHICKEN7_REG			0xE194
+#define GEN9_HALF_SLICE_CHICKEN7_NEW_HASH_ENABLE	(1<<24 | 1<<8)
+#define GEN9_MMCD_MISC_CTRL_REG				0x4DDC
+#define GEN9_MMCD_MISC_CTRL_NEW_HASH_ENABLE		(1<<31 | 1<<27)
+#define GEN9_CHICKEN_MISC1_REG				0x42080
+#define GEN9_CHICKEN_MISC1_NEW_HASH_ENABLE		(1<<15)
+
+/* Unit Level Clock Gating Control */
+#define GEN9_UCGCTL6					0x9430
+#define GEN9_GAPS_UNIT_CLOCK_GATE_DISABLE		(1<<24)
+#define GEN9_HDC_UNIT_CLOCK_GATE_DISABLE		(1<<28)
+
+/* Mirror of EU disable fuses */
+#define MIRROR_EU_DISABLE0				0x9134
+#define MIRROR_EU_DISABLE1				0x9138
+#define MIRROR_EU_DISABLE_SS0				(0x7<<0)
+#define MIRROR_EU_DISABLE_SS1				(0x7<<8)
+#define MIRROR_EU_DISABLE_SS2				(0x7<<16)
+#define MIRROR_EU_DISABLE_SS3				(0x7<<24)
+
+
 #endif /* _I915_REG_H_ */
drivers/gpu/drm/i915/intel_display.c +5 -1
index d1a4de8..2942b11 100644
@@ -9514,9 +9514,13 @@ static int intel_gen9_queue_flip(struct drm_device *dev,
 
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
 	intel_ring_emit(ring, DERRMR);
+	/* WaClearRenderResponseMasks:bxt */
 	intel_ring_emit(ring, ~(DERRMR_PIPEA_PRI_FLIP_DONE |
 				DERRMR_PIPEB_PRI_FLIP_DONE |
-				DERRMR_PIPEC_PRI_FLIP_DONE));
+				DERRMR_PIPEC_PRI_FLIP_DONE |
+				DERRMR_PIPEA_SPR_FLIP_DONE |
+				DERRMR_PIPEB_SPR_FLIP_DONE |
+				DERRMR_PIPEC_SPR_FLIP_DONE));
 	intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8(1) |
 			      MI_SRM_LRM_GLOBAL_GTT);
 	intel_ring_emit(ring, DERRMR);
drivers/gpu/drm/i915/intel_lrc.c +19 -25

132 lines not on this page · raw message

drivers/gpu/drm/i915/intel_lrc.h +0 -27
index 80a80ea..6f2d7da 100644
@@ -89,33 +89,6 @@ int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
 			       u64 exec_start, u32 flags);
 u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
 
-/**
- * struct intel_ctx_submit_request - queued context submission request
- * @ctx: Context to submit to the ELSP.
- * @ring: Engine to submit it to.
- * @tail: how far in the context's ringbuffer this request goes to.
- * @execlist_link: link in the submission queue.
- * @work: workqueue for processing this request in a bottom half.
- * @elsp_submitted: no. of times this request has been sent to the ELSP.
- *
- * The ELSP only accepts two elements at a time, so we queue context/tail
- * pairs on a given queue (ring->execlist_queue) until the hardware is
- * available. The queue serves a double purpose: we also use it to keep track
- * of the up to 2 contexts currently in the hardware (usually one in execution
- * and the other queued up by the GPU): We only remove elements from the head
- * of the queue when the hardware informs us that an element has been
- * completed.
- *
- * All accesses to the queue are mediated by a spinlock (ring->execlist_lock).
- */
-struct intel_ctx_submit_request {
-	struct list_head execlist_link;
-
-	int elsp_submitted;
-
-	struct drm_i915_gem_request *request;
-};
-
 void intel_lrc_irq_handler(struct intel_engine_cs *ring);
 void intel_execlists_retire_requests(struct intel_engine_cs *ring);
 
Signature · 6 lines
2.1.1

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Tested-by on v1 4/4
#5 lore raw

Re: [PATCH 4/4] drm/i915: Subsume intel_ctx_submit_request in to drm_i915_gem_request

-------------------------------------Summary-------------------------------------
Platform Delta drm-intel-nightly Series Applied

PNV                 -2              354/354              352/354
ILK                 -1              354/354              353/354
SNB              +1-1              401/424              401/424
IVB                                  488/488              488/488
BYT                                  278/278              278/278
HSW                                  529/529              529/529
BDW                 -1              405/405              404/405
-------------------------------------Detailed-------------------------------------
Platform  Test                                drm-intel-nightly          Series Applied
*PNV  igt_gen3_mixed_blits      PASS(2, M7M23)      NRUN(1, M23)
*PNV  igt_gen3_render_linear_blits      PASS(2, M7M23)      CRASH(1, M23)
*ILK  igt_gem_unfence_active_buffers      PASS(2, M37M26)      DMESG_WARN(1, M26)
 SNB  igt_kms_flip_flip-vs-dpms-off-vs-modeset-interruptible      NSPT(1, M35)PASS(5, M35M22)      PASS(1, M22)
*SNB  igt_gem_concurrent_blit_gtt-rcs-early-read-interruptible      PASS(6, M35M22)      DMESG_WARN(1, M22)
*BDW  igt_gem_concurrent_blit_gtt-bcs-gpu-read-after-write-interruptible      PASS(5, M30M28)      DMESG_WARN(1, M28)

Note: You need to pay more attention to line start with '*'
_______________________________________________
Intel-gfx mailing list [email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx