Skip to contentSkip to conversation

drm/i915: More use of the cached LRC state

PATCH In review Tvrtko Ursulin 3 participants 3 messages Jan 22, 2016

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 drm/i915: More use of the cached LRC state

From: Tvrtko Ursulin <[email protected]>

Since:

commit 82352e908acd36d7244c75a008c9f27a2ced44d5

Author: Tvrtko Ursulin <[email protected]>
Date:   Fri Jan 15 17:12:45 2016 +0000

drm/i915: Cache LRC state page in the context

and:

commit 0eb973d31d0aadb6bc801fd6d796afecbbfc3d5b

Author: Tvrtko Ursulin <[email protected]>
Date:   Fri Jan 15 15:10:28 2016 +0000

drm/i915: Cache ringbuffer GTT VMA

We can also remove the ring buffer start updates on every context update since the address will not change for the duration of the LRC pin.

For GuC we can remove the update altogether because it only cares about the ring buffer start.

Cc Alex Dai <[email protected]>
Cc Dave Gordon <[email protected]>
Cc Chris Wilson <[email protected]>
---
 drivers/gpu/drm/i915/i915_guc_submission.c | 27 ---------------------------
 drivers/gpu/drm/i915/intel_lrc.c           |  6 ++++--
 2 files changed, 4 insertions(+), 29 deletions(-)
drivers/gpu/drm/i915/i915_guc_submission.c +0 -27
index 068315fc7404..ea15e2d9285e 100644
@@ -560,29 +560,6 @@ static int guc_add_workqueue_item(struct i915_guc_client *gc,
 	return 0;
 }
 
-#define CTX_RING_BUFFER_START		0x08
-
-/* Update the ringbuffer pointer in a saved context image */
-static void lr_context_update(struct drm_i915_gem_request *rq)
-{
-	enum intel_ring_id ring_id = rq->ring->id;
-	struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring_id].state;
-	struct drm_i915_gem_object *rb_obj = rq->ringbuf->obj;
-	struct page *page;
-	uint32_t *reg_state;
-
-	BUG_ON(!ctx_obj);
-	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj));
-	WARN_ON(!i915_gem_obj_is_pinned(rb_obj));
-
-	page = i915_gem_object_get_dirty_page(ctx_obj, LRC_STATE_PN);
-	reg_state = kmap_atomic(page);
-
-	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
-
-	kunmap_atomic(reg_state);
-}
-
 /**
  * i915_guc_submit() - Submit commands through GuC
  * @client:	the guc client where commands will go through
@@ -597,10 +574,6 @@ int i915_guc_submit(struct i915_guc_client *client,
 	enum intel_ring_id ring_id = rq->ring->id;
 	int q_ret, b_ret;
 
-	/* Need this because of the deferred pin ctx and ring */
-	/* Shall we move this right after ring is pinned? */
-	lr_context_update(rq);
-
 	q_ret = guc_add_workqueue_item(client, rq);
 	if (q_ret == 0)
 		b_ret = guc_ring_doorbell(client);
drivers/gpu/drm/i915/intel_lrc.c +4 -2
index 7f47948d5c40..43c94af4b81c 100644
@@ -393,7 +393,6 @@ static int execlists_update_context(struct drm_i915_gem_request *rq)
 	uint32_t *reg_state = rq->ctx->engine[ring->id].lrc_reg_state;
 
 	reg_state[CTX_RING_TAIL+1] = rq->tail;
-	reg_state[CTX_RING_BUFFER_START+1] = rq->ringbuf->vma->node.start;
 
 	if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
 		/* True 32b PPGTT with dynamic page allocation: update PDP
@@ -1067,6 +1066,7 @@ static int intel_lr_context_do_pin(struct intel_engine_cs *ring,
 	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
 	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
 	struct page *lrc_state_page;
+	uint32_t *lrc_reg_state;
 	int ret;
 
 	WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
@@ -1088,7 +1088,9 @@ static int intel_lr_context_do_pin(struct intel_engine_cs *ring,
 
 	ctx->engine[ring->id].lrc_vma = i915_gem_obj_to_ggtt(ctx_obj);
 	intel_lr_context_descriptor_update(ctx, ring);
-	ctx->engine[ring->id].lrc_reg_state = kmap(lrc_state_page);
+	lrc_reg_state = kmap(lrc_state_page);
+	lrc_reg_state[CTX_RING_BUFFER_START+1] = ringbuf->vma->node.start;
+	ctx->engine[ring->id].lrc_reg_state = lrc_reg_state;
 	ctx_obj->dirty = true;
 
 	/* Invalidate GuC TLB. */
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Reviewed-by on v1 1/1
#1 lore raw
Quoted 22 lines · Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

Since:

commit 82352e908acd36d7244c75a008c9f27a2ced44d5

Author: Tvrtko Ursulin <[email protected]>
Date:   Fri Jan 15 17:12:45 2016 +0000

drm/i915: Cache LRC state page in the context

and:

commit 0eb973d31d0aadb6bc801fd6d796afecbbfc3d5b

Author: Tvrtko Ursulin <[email protected]>
Date:   Fri Jan 15 15:10:28 2016 +0000

drm/i915: Cache ringbuffer GTT VMA

We can also remove the ring buffer start updates on every context update since the address will not change for the duration of the LRC pin.

Quoted 7 lines

For GuC we can remove the update altogether because it only cares about the ring buffer start.

Cc Alex Dai <[email protected]>
Cc Dave Gordon <[email protected]>
Cc Chris Wilson <[email protected]>

Finally starting to reduce my delta at last :-p

-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#2 lore raw

✓ Fi.CI.BAT: success for drm/i915: More use of the cached LRC state

In reply to Tvrtko Ursulin
== Summary ==

== Summary ==

Built on 8fe9e785ae04fa7c37f7935cff12d62e38054b60 drm-intel-nightly: 2016y-01m-21d-11h-02m-42s UTC integration manifest

bdw-nuci7        total:140  pass:131  dwarn:0   dfail:0   fail:0   skip:9  
bdw-ultra        total:143  pass:137  dwarn:0   dfail:0   fail:0   skip:6  
bsw-nuc-2        total:143  pass:119  dwarn:0   dfail:0   fail:0   skip:24 
byt-nuc          total:143  pass:128  dwarn:0   dfail:0   fail:0   skip:15 
hsw-brixbox      total:143  pass:136  dwarn:0   dfail:0   fail:0   skip:7  
hsw-gt2          total:143  pass:139  dwarn:0   dfail:0   fail:0   skip:4  
ilk-hp8440p      total:143  pass:104  dwarn:1   dfail:0   fail:0   skip:38 
ivb-t430s        total:143  pass:137  dwarn:0   dfail:0   fail:0   skip:6  
skl-i5k-2        total:143  pass:134  dwarn:1   dfail:0   fail:0   skip:8  
snb-dellxps      total:143  pass:129  dwarn:0   dfail:0   fail:0   skip:14 
snb-x220t        total:143  pass:129  dwarn:0   dfail:0   fail:1   skip:13 

Results at /archive/results/CI_IGT_test/Patchwork_1250/

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