[163/190] drm/i915: Fix i915_gem_evict_for_vma (soft-pinning)
diff mbox

Message ID 1452510091-6833-22-git-send-email-chris@chris-wilson.co.uk
State New
Headers show

Commit Message

Chris Wilson Jan. 11, 2016, 11:01 a.m. UTC
Soft-pinning depends upon being able to check for availabilty of an
inverval and evict overlapping object fro a drm_mm range manager very
quickly. Currently it uses a linear list which makes performance dire,
and softpinning not a suitable replacement.

It also helps if the routine reports the correct error codes as expected
by its callers and emits a tracepoint upon use.

For posterity since the wrong patch was pushed (i.e. that missed these
key points), this is the changelog that should have been on

commit 506a8e87d8d2746b9e9d2433503fe237c54e4750
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Tue Dec 8 11:55:07 2015 +0000

    drm/i915: Add soft-pinning API for execbuffer

Userspace can pass in an offset that it presumes the object is located
at. The kernel will then do its utmost to fit the object into that
location. The assumption is that userspace is handling its own object
locations (for example along with full-ppgtt) and that the kernel will
rarely have to make space for the user's requests.

This extends the DRM_IOCTL_I915_GEM_EXECBUFFER2 to do the following:
* if the user supplies a virtual address via the execobject->offset
  *and* sets the EXEC_OBJECT_PINNED flag in execobject->flags, then
  that object is placed at that offset in the address space selected
  by the context specifier in execbuffer.
* the location must be aligned to the GTT page size, 4096 bytes
* as the object is placed exactly as specified, it may be used by this
  execbuffer call without relocations pointing to it

It may fail to do so if:
* EINVAL is returned if the object does not have a 4096 byte aligned
  address
* the object conflicts with another pinned object (either pinned by
  hardware in that address space, e.g. scanouts in the aliasing ppgtt)
  or within the same batch.
  EBUSY is returned if the location is pinned by hardware
  EINVAL is returned if the location is already in use by the batch
* EINVAL is returned if the object conflicts with its own alignment (as meets
  the hardware requirements) or if the placement of the object does not fit
  within the address space

All other execbuffer errors apply.

Presence of this execbuf extension may be queried by passing
I915_PARAM_HAS_EXEC_SOFTPIN to DRM_IOCTL_I915_GETPARAM and checking for
a reported value of 1 (or greater).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h       |  2 +-
 drivers/gpu/drm/i915/i915_gem.c       |  2 +-
 drivers/gpu/drm/i915/i915_gem_evict.c | 69 ++++++++++++++++++++++-------------
 drivers/gpu/drm/i915/i915_trace.h     | 23 ++++++++++++
 4 files changed, 69 insertions(+), 27 deletions(-)

Patch
diff mbox

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index addd33bbc847..62a024a7225b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3052,7 +3052,7 @@  int __must_check i915_gem_evict_something(struct drm_device *dev,
 					  unsigned long start,
 					  unsigned long end,
 					  unsigned flags);
-int __must_check i915_gem_evict_for_vma(struct i915_vma *target);
+int __must_check i915_gem_evict_for_vma(struct i915_vma *vma, unsigned flags);
 int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
 
 /* belongs in i915_gem_gtt.h */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 962fd81ce26c..497b68849d09 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2813,7 +2813,7 @@  i915_vma_insert(struct i915_vma *vma,
 		vma->node.color = obj->cache_level;
 		ret = drm_mm_reserve_node(&vma->vm->mm, &vma->node);
 		if (ret) {
-			ret = i915_gem_evict_for_vma(vma);
+			ret = i915_gem_evict_for_vma(vma, flags);
 			if (ret == 0)
 				ret = drm_mm_reserve_node(&vma->vm->mm, &vma->node);
 			if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index fdc4941be15a..b48839fc2996 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -229,42 +229,61 @@  found:
 }
 
 int
-i915_gem_evict_for_vma(struct i915_vma *target)
+i915_gem_evict_for_vma(struct i915_vma *target, unsigned flags)
 {
-	struct drm_mm_node *node, *next;
+	struct list_head eviction_list;
+	struct drm_mm_node *node;
+	u64 end = target->node.start + target->node.size;
+	struct i915_vma *vma, *next;
+	int ret;
 
-	list_for_each_entry_safe(node, next,
-			&target->vm->mm.head_node.node_list,
-			node_list) {
-		struct i915_vma *vma;
-		int ret;
+	trace_i915_gem_evict_vma(target, flags);
 
-		if (node->start + node->size <= target->node.start)
-			continue;
-		if (node->start >= target->node.start + target->node.size)
-			break;
+	node = drm_mm_interval_first(&target->vm->mm,
+				     target->node.start, end - 1);
+	if (node == NULL)
+		return 0;
 
-		vma = container_of(node, typeof(*vma), node);
+	INIT_LIST_HEAD(&eviction_list);
+	vma = container_of(node, typeof(*vma), node);
+	list_for_each_entry_from(vma,
+				 &target->vm->mm.head_node.node_list,
+				 node.node_list) {
+		if (vma->node.start >= end)
+			break;
 
-		if (vma->pin_count) {
-			if (!vma->exec_entry || (vma->pin_count > 1))
-				/* Object is pinned for some other use */
-				return -EBUSY;
+		if (flags & PIN_NONBLOCK && (vma->pin_count | vma->active)) {
+			ret = -ENOSPC;
+			break;
+		}
 
-			/* We need to evict a buffer in the same batch */
-			if (vma->exec_entry->flags & EXEC_OBJECT_PINNED)
-				/* Overlapping fixed objects in the same batch */
-				return -EINVAL;
+		if (vma->exec_entry &&
+		    vma->exec_entry->flags & EXEC_OBJECT_PINNED) {
+			/* Overlapping pinned objects in the same batch */
+			ret = -EINVAL;
+			break;
+		}
 
-			return -ENOSPC;
+		if (vma->pin_count) {
+			/* We may need to evict an buffer in the same batch */
+			ret = vma->exec_entry ? -ENOSPC : -EBUSY;
+			break;
 		}
 
-		ret = i915_vma_unbind(vma);
-		if (ret)
-			return ret;
+		list_add(&vma->exec_list, &eviction_list);
+		drm_gem_object_reference(&vma->obj->base);
 	}
 
-	return 0;
+	ret = 0;
+	list_for_each_entry_safe(vma, next, &eviction_list, exec_list) {
+		struct drm_i915_gem_object *obj = vma->obj;
+		list_del_init(&vma->exec_list);
+		if (ret == 0)
+			ret = i915_vma_unbind(vma);
+		drm_gem_object_unreference(&obj->base);
+	}
+
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index e486dcef508d..396943fa53ea 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -448,6 +448,29 @@  TRACE_EVENT(i915_gem_evict_vm,
 	    TP_printk("dev=%d, vm=%p", __entry->dev, __entry->vm)
 );
 
+TRACE_EVENT(i915_gem_evict_vma,
+	    TP_PROTO(struct i915_vma *vma, unsigned flags),
+	    TP_ARGS(vma, flags),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(struct i915_address_space *, vm)
+			     __field(u64, start)
+			     __field(u64, size)
+			     __field(unsigned, flags)
+			    ),
+
+	    TP_fast_assign(
+			   __entry->dev = vma->vm->dev->primary->index;
+			   __entry->vm = vma->vm;
+			   __entry->start = vma->node.start;
+			   __entry->size = vma->node.size;
+			   __entry->flags = flags;
+			  ),
+
+	    TP_printk("dev=%d, vm=%p, start=%llx size=%llx, flags=%x", __entry->dev, __entry->vm, (long long)__entry->start, (long long)__entry->size, __entry->flags)
+);
+
 TRACE_EVENT(i915_gem_ring_sync_to,
 	    TP_PROTO(struct drm_i915_gem_request *to,
 		     struct drm_i915_gem_request *from),