[Intel-gfx] [PATCH 084/190] drm/i915: Track active vma requests

Chris Wilson chris at chris-wilson.co.uk
Mon Jan 11 01:17:35 PST 2016


Hook the vma itself into the i915_gem_request_retire() so that we can
accurately track when a solitary vma is inactive (as opposed to having
to wait for the entire object to be idle). This improves the interaction
when using multiple contexts (with full-ppgtt) and eliminates some
frequent list walking when retiring objects after a completed request.

A side-effect is that we get an active vma reference for free. The
consequence of this is shown in the next patch...

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c        |  2 +-
 drivers/gpu/drm/i915/i915_gem.c            | 15 +++++----------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 10 +++++++++-
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 21 +++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.h        |  5 +++++
 5 files changed, 41 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e2b1242e369b..378bc73296aa 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -357,7 +357,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 				continue;
 		}
 
-		if (obj->active) /* XXX per-vma statistic */
+		if (vma->active)
 			stats->active += vma->node.size;
 		else
 			stats->inactive += vma->node.size;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 95e69dc47fc8..7e4f7f2d18e4 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2070,7 +2070,6 @@ i915_gem_object_retire__read(struct i915_gem_active *active,
 	int ring = request->engine->id;
 	struct drm_i915_gem_object *obj =
 		container_of(active, struct drm_i915_gem_object, last_read[ring]);
-	struct i915_vma *vma;
 
 	GEM_BUG_ON((obj->active & (1 << ring)) == 0);
 
@@ -2082,12 +2081,9 @@ i915_gem_object_retire__read(struct i915_gem_active *active,
 	 * so that we don't steal from recently used but inactive objects
 	 * (unless we are forced to ofc!)
 	 */
-	list_move_tail(&obj->global_list, &request->i915->mm.bound_list);
-
-	list_for_each_entry(vma, &obj->vma_list, obj_link) {
-		if (!list_empty(&vma->vm_link))
-			list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
-	}
+	if (obj->bind_count)
+		list_move_tail(&obj->global_list,
+			       &request->i915->mm.bound_list);
 
 	drm_gem_object_unreference(&obj->base);
 }
@@ -3034,9 +3030,8 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 
 	/* And bump the LRU for this access */
 	vma = i915_gem_obj_to_ggtt(obj);
-	if (vma && drm_mm_node_allocated(&vma->node) && !obj->active)
-		list_move_tail(&vma->vm_link,
-			       &to_i915(obj->base.dev)->gtt.base.inactive_list);
+	if (vma && drm_mm_node_allocated(&vma->node) && !vma->active)
+		list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 9e549bded186..19d32f22f85d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1115,7 +1115,13 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 
 	obj->dirty = 1; /* be paranoid  */
 
-	/* Add a reference if we're newly entering the active list. */
+	/* Add a reference if we're newly entering the active list.
+	 * The order in which we add operations to the retirement queue is
+	 * vital here: mark_active adds to the start of the callback list,
+	 * such that subsequent callbacks are called first. Therefore we
+	 * add the active reference first and queue for it to be dropped
+	 * *last*.
+	 */
 	if (obj->active == 0)
 		drm_gem_object_reference(&obj->base);
 	obj->active |= 1 << engine;
@@ -1139,6 +1145,8 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 		}
 	}
 
+	vma->active |= 1 << engine;
+	i915_gem_request_mark_active(req, &vma->last_read[engine]);
 	list_move_tail(&vma->vm_link, &vma->vm->active_list);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3a07ff622bd6..fd42b6491d28 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3241,12 +3241,31 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	i915_ggtt_flush(dev_priv);
 }
 
+static void
+i915_vma_retire(struct i915_gem_active *active,
+		struct drm_i915_gem_request *rq)
+{
+	const unsigned engine = rq->engine->id;
+	struct i915_vma *vma =
+		container_of(active, struct i915_vma, last_read[engine]);
+
+	GEM_BUG_ON((vma->active & (1 << engine)) == 0);
+	GEM_BUG_ON((vma->obj->active & vma->active) != vma->active);
+
+	vma->active &= ~(1 << engine);
+	if (vma->active)
+		return;
+
+	list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
+}
+
 static struct i915_vma *
 __i915_gem_vma_create(struct drm_i915_gem_object *obj,
 		      struct i915_address_space *vm,
 		      const struct i915_ggtt_view *ggtt_view)
 {
 	struct i915_vma *vma;
+	int i;
 
 	if (WARN_ON(i915_is_ggtt(vm) != !!ggtt_view))
 		return ERR_PTR(-EINVAL);
@@ -3258,6 +3277,8 @@ __i915_gem_vma_create(struct drm_i915_gem_object *obj,
 	INIT_LIST_HEAD(&vma->vm_link);
 	INIT_LIST_HEAD(&vma->obj_link);
 	INIT_LIST_HEAD(&vma->exec_list);
+	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
+		init_request_active(&vma->last_read[i], i915_vma_retire);
 	vma->vm = vm;
 	vma->obj = obj;
 	vma->is_ggtt = i915_is_ggtt(vm);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 9d3984602d34..0a7867fa5a1f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -34,6 +34,8 @@
 #ifndef __I915_GEM_GTT_H__
 #define __I915_GEM_GTT_H__
 
+#include "i915_gem_request.h"
+
 struct drm_i915_file_private;
 
 typedef uint32_t gen6_pte_t;
@@ -180,10 +182,13 @@ struct i915_vma {
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm;
 
+	struct i915_gem_active last_read[I915_NUM_RINGS];
+
 	/** Flags and address space this VMA is bound to */
 #define GLOBAL_BIND	(1<<0)
 #define LOCAL_BIND	(1<<1)
 	unsigned int bound : 4;
+	unsigned int active : I915_NUM_RINGS;
 	bool is_ggtt : 1;
 
 	/**
-- 
2.7.0.rc3



More information about the Intel-gfx mailing list