diff mbox

[5/6] drm/i915: Add the CPU mapping of the hw context to the pinned items.

Message ID 1445333036-22164-6-git-send-email-nicholas.hoath@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Nick Hoath Oct. 20, 2015, 9:23 a.m. UTC 
Pin the hw ctx mapping so that it is not mapped/unmapped per bb
when doing GuC submission.

v2: Removed interim development extra mapping. (Daniel Vetter)

Issue: VIZ-4277
Signed-off-by: Nick Hoath <nicholas.hoath@intel.com>
Cc: David Gordon <david.s.gordon@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 14 ++++-------
 drivers/gpu/drm/i915/i915_drv.h     |  4 +++-
 drivers/gpu/drm/i915/intel_lrc.c    | 46 ++++++++++++++++++++++++++-----------
 3 files changed, 40 insertions(+), 24 deletions(-)

Comments

Chris Wilson Oct. 20, 2015, 9:56 a.m. UTC | #1 
On Tue, Oct 20, 2015 at 10:23:55AM +0100, Nick Hoath wrote:
> Pin the hw ctx mapping so that it is not mapped/unmapped per bb
> when doing GuC submission.
> 
> v2: Removed interim development extra mapping. (Daniel Vetter)

You've missed the point here. I've shown how to do kmapping once neatly,
what you need the unbind callback for is to amoritize the cost of the
ioremap.
-Chris
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a3b22bd..f0a172e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1970,10 +1970,9 @@  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 drm_i915_gem_object *ctx_obj,
+			      uint32_t *reg_state)
 {
-	struct page *page;
-	uint32_t *reg_state;
 	int j;
 	unsigned long ggtt_offset = 0;
 
@@ -1996,17 +1995,13 @@  static void i915_dump_lrc_obj(struct seq_file *m,
 		return;
 	}
 
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	if (!WARN_ON(page == NULL)) {
-		reg_state = kmap_atomic(page);
-
+	if (!WARN_ON(reg_state == NULL)) {
 		for (j = 0; j < 0x600 / sizeof(u32) / 4; j += 4) {
 			seq_printf(m, "\t[0x%08lx] 0x%08x 0x%08x 0x%08x 0x%08x\n",
 				   ggtt_offset + 4096 + (j * 4),
 				   reg_state[j], reg_state[j + 1],
 				   reg_state[j + 2], reg_state[j + 3]);
 		}
-		kunmap_atomic(reg_state);
 	}
 
 	seq_putc(m, '\n');
@@ -2034,7 +2029,8 @@  static int i915_dump_lrc(struct seq_file *m, void *unused)
 		for_each_ring(ring, dev_priv, i) {
 			if (ring->default_context != ctx)
 				i915_dump_lrc_obj(m, ring,
-						  ctx->engine[i].state);
+						  ctx->engine[i].state,
+						  ctx->engine[i].reg_state);
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0dd4ace..dc69d67 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -881,8 +881,10 @@  struct intel_context {
 	} legacy_hw_ctx;
 
 	/* Execlists */
-	struct {
+	struct intel_context_engine {
 		struct drm_i915_gem_object *state;
+		uint32_t *reg_state;
+		struct page *page;
 		struct intel_ringbuffer *ringbuf;
 		int pin_count;
 	} engine[I915_NUM_RINGS];
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 069950e..a35efcd 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -360,16 +360,13 @@  static int execlists_update_context(struct drm_i915_gem_request *rq)
 	struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt;
 	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;
+	uint32_t *reg_state = rq->ctx->engine[ring->id].reg_state;
 
 	BUG_ON(!ctx_obj);
+	WARN_ON(!reg_state);
 	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj));
 	WARN_ON(!i915_gem_obj_is_pinned(rb_obj));
 
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	reg_state = kmap_atomic(page);
-
 	reg_state[CTX_RING_TAIL+1] = rq->tail;
 	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj);
 
@@ -385,8 +382,6 @@  static int execlists_update_context(struct drm_i915_gem_request *rq)
 		ASSIGN_CTX_PDP(ppgtt, reg_state, 0);
 	}
 
-	kunmap_atomic(reg_state);
-
 	return 0;
 }
 
@@ -985,7 +980,31 @@  int logical_ring_flush_all_caches(struct drm_i915_gem_request *req)
 	return 0;
 }
 
-static int intel_lr_context_do_pin(struct intel_engine_cs *ring,
+static int intel_mmap_hw_context(struct drm_i915_gem_object *obj,
+		bool unmap)
+{
+	int ret = 0;
+	struct intel_context_engine *ice =
+			(struct intel_context_engine *)obj->mappable;
+	struct page *page;
+	uint32_t *reg_state;
+
+	if (unmap) {
+		kunmap(ice->page);
+		ice->reg_state = NULL;
+		ice->page = NULL;
+	} else {
+		page = i915_gem_object_get_page(obj, LRC_STATE_PN);
+		reg_state = kmap(page);
+		ice->reg_state = reg_state;
+		ice->page = page;
+	}
+	return ret;
+}
+
+static int intel_lr_context_do_pin(
+		struct intel_context *ctx,
+		struct intel_engine_cs *ring,
 		struct drm_i915_gem_object *ctx_obj,
 		struct intel_ringbuffer *ringbuf)
 {
@@ -1032,7 +1051,7 @@  static int intel_lr_context_pin(struct drm_i915_gem_request *rq)
 	struct intel_ringbuffer *ringbuf = rq->ringbuf;
 
 	if (rq->ctx->engine[ring->id].pin_count++ == 0) {
-		ret = intel_lr_context_do_pin(ring, ctx_obj, ringbuf);
+		ret = intel_lr_context_do_pin(rq->ctx, ring, ctx_obj, ringbuf);
 		if (ret)
 			goto reset_pin_count;
 	}
@@ -1921,6 +1940,7 @@  static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *rin
 
 	/* As this is the default context, always pin it */
 	ret = intel_lr_context_do_pin(
+			ring->default_context,
 			ring,
 			ring->default_context->engine[ring->id].state,
 			ring->default_context->engine[ring->id].ringbuf);
@@ -2471,6 +2491,8 @@  int intel_lr_context_deferred_alloc(struct intel_context *ctx,
 		goto error_ringbuf;
 	}
 
+	ctx_obj->mmap = intel_mmap_hw_context;
+	ctx_obj->mappable = &(ctx->engine[ring->id]);
 	ctx->engine[ring->id].ringbuf = ringbuf;
 	ctx->engine[ring->id].state = ctx_obj;
 
@@ -2518,7 +2540,6 @@  void intel_lr_context_reset(struct drm_device *dev,
 		struct intel_ringbuffer *ringbuf =
 				ctx->engine[ring->id].ringbuf;
 		uint32_t *reg_state;
-		struct page *page;
 
 		if (!ctx_obj)
 			continue;
@@ -2527,14 +2548,11 @@  void intel_lr_context_reset(struct drm_device *dev,
 			WARN(1, "Failed get_pages for context obj\n");
 			continue;
 		}
-		page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-		reg_state = kmap_atomic(page);
+		reg_state = ctx->engine[ring->id].reg_state;
 
 		reg_state[CTX_RING_HEAD+1] = 0;
 		reg_state[CTX_RING_TAIL+1] = 0;
 
-		kunmap_atomic(reg_state);
-
 		ringbuf->head = 0;
 		ringbuf->tail = 0;