[Intel-gfx] [PATCH 25/29] drm/i915: Convert execbuf code to use vmas
Ben Widawsky
ben at bwidawsk.net
Thu Aug 1 02:00:18 CEST 2013
This attempts to convert all the execbuf code to speak in vmas. Since
the execbuf code is very self contained it was a nice isolated
conversion.
The meat of the code is about turning eb_objects into eb_vma, and then
wiring up the rest of the code to use vmas instead of obj, vm pairs.
Unfortunately, to do this, we must move the exec_list link from the obj
structure. This list is reused in the eviction code, so we must also
modify the eviction code to make this work.
v2: Release table lock early, and two a 2 phase vma lookup to avoid
having to use a GFP_ATOMIC. (Chris)
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
drivers/gpu/drm/i915/i915_drv.h | 22 +-
drivers/gpu/drm/i915/i915_gem.c | 3 +-
drivers/gpu/drm/i915/i915_gem_evict.c | 31 ++-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 322 +++++++++++++++--------------
4 files changed, 201 insertions(+), 177 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c0eb7fd..ee5164e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -550,6 +550,17 @@ struct i915_vma {
struct list_head mm_list;
struct list_head vma_link; /* Link in the object's VMA list */
+
+ /** This vma's place in the batchbuffer or on the eviction list */
+ struct list_head exec_list;
+
+ /**
+ * Used for performing relocations during execbuffer insertion.
+ */
+ struct hlist_node exec_node;
+ unsigned long exec_handle;
+ struct drm_i915_gem_exec_object2 *exec_entry;
+
};
struct i915_ctx_hang_stats {
@@ -1267,8 +1278,8 @@ struct drm_i915_gem_object {
struct list_head global_list;
struct list_head ring_list;
- /** This object's place in the batchbuffer or on the eviction list */
- struct list_head exec_list;
+ /** Used in execbuf to temporarily hold a ref */
+ struct list_head obj_exec_list;
/**
* This is set if the object is on the active lists (has pending
@@ -1353,13 +1364,6 @@ struct drm_i915_gem_object {
void *dma_buf_vmapping;
int vmapping_count;
- /**
- * Used for performing relocations during execbuffer insertion.
- */
- struct hlist_node exec_node;
- unsigned long exec_handle;
- struct drm_i915_gem_exec_object2 *exec_entry;
-
struct intel_ring_buffer *ring;
/** Breadcrumb of last rendering to the buffer. */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 72bd53c..a4ba819 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3913,7 +3913,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
{
INIT_LIST_HEAD(&obj->global_list);
INIT_LIST_HEAD(&obj->ring_list);
- INIT_LIST_HEAD(&obj->exec_list);
+ INIT_LIST_HEAD(&obj->obj_exec_list);
INIT_LIST_HEAD(&obj->vma_list);
obj->ops = ops;
@@ -4048,6 +4048,7 @@ struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj,
INIT_LIST_HEAD(&vma->vma_link);
INIT_LIST_HEAD(&vma->mm_list);
+ INIT_LIST_HEAD(&vma->exec_list);
vma->vm = vm;
vma->obj = obj;
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 425939b..8787588 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -37,7 +37,7 @@ mark_free(struct i915_vma *vma, struct list_head *unwind)
if (vma->obj->pin_count)
return false;
- list_add(&vma->obj->exec_list, unwind);
+ list_add(&vma->exec_list, unwind);
return drm_mm_scan_add_block(&vma->node);
}
@@ -49,7 +49,6 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
drm_i915_private_t *dev_priv = dev->dev_private;
struct list_head eviction_list, unwind_list;
struct i915_vma *vma;
- struct drm_i915_gem_object *obj;
int ret = 0;
trace_i915_gem_evict(dev, min_size, alignment, mappable);
@@ -104,14 +103,13 @@ i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
none:
/* Nothing found, clean up and bail out! */
while (!list_empty(&unwind_list)) {
- obj = list_first_entry(&unwind_list,
- struct drm_i915_gem_object,
+ vma = list_first_entry(&unwind_list,
+ struct i915_vma,
exec_list);
- vma = i915_gem_obj_to_vma(obj, vm);
ret = drm_mm_scan_remove_block(&vma->node);
BUG_ON(ret);
- list_del_init(&obj->exec_list);
+ list_del_init(&vma->exec_list);
}
/* We expect the caller to unpin, evict all and try again, or give up.
@@ -125,28 +123,27 @@ found:
* temporary list. */
INIT_LIST_HEAD(&eviction_list);
while (!list_empty(&unwind_list)) {
- obj = list_first_entry(&unwind_list,
- struct drm_i915_gem_object,
+ vma = list_first_entry(&unwind_list,
+ struct i915_vma,
exec_list);
- vma = i915_gem_obj_to_vma(obj, vm);
if (drm_mm_scan_remove_block(&vma->node)) {
- list_move(&obj->exec_list, &eviction_list);
- drm_gem_object_reference(&obj->base);
+ list_move(&vma->exec_list, &eviction_list);
+ drm_gem_object_reference(&vma->obj->base);
continue;
}
- list_del_init(&obj->exec_list);
+ list_del_init(&vma->exec_list);
}
/* Unbinding will emit any required flushes */
while (!list_empty(&eviction_list)) {
- obj = list_first_entry(&eviction_list,
- struct drm_i915_gem_object,
+ vma = list_first_entry(&eviction_list,
+ struct i915_vma,
exec_list);
if (ret == 0)
- ret = i915_vma_unbind(i915_gem_obj_to_vma(obj, vm));
+ ret = i915_vma_unbind(vma);
- list_del_init(&obj->exec_list);
- drm_gem_object_unreference(&obj->base);
+ list_del_init(&vma->exec_list);
+ drm_gem_object_unreference(&vma->obj->base);
}
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 3f17a55..1c9d504 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -33,24 +33,24 @@
#include "intel_drv.h"
#include <linux/dma_remapping.h>
-struct eb_objects {
- struct list_head objects;
+struct eb_vmas {
+ struct list_head vmas;
int and;
union {
- struct drm_i915_gem_object *lut[0];
+ struct i915_vma *lut[0];
struct hlist_head buckets[0];
};
};
-static struct eb_objects *
-eb_create(struct drm_i915_gem_execbuffer2 *args)
+static struct eb_vmas *
+eb_create(struct drm_i915_gem_execbuffer2 *args, struct i915_address_space *vm)
{
- struct eb_objects *eb = NULL;
+ struct eb_vmas *eb = NULL;
if (args->flags & I915_EXEC_HANDLE_LUT) {
int size = args->buffer_count;
- size *= sizeof(struct drm_i915_gem_object *);
- size += sizeof(struct eb_objects);
+ size *= sizeof(struct i915_vma *);
+ size += sizeof(struct eb_vmas);
eb = kmalloc(size, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
}
@@ -61,7 +61,7 @@ eb_create(struct drm_i915_gem_execbuffer2 *args)
while (count > 2*size)
count >>= 1;
eb = kzalloc(count*sizeof(struct hlist_head) +
- sizeof(struct eb_objects),
+ sizeof(struct eb_vmas),
GFP_TEMPORARY);
if (eb == NULL)
return eb;
@@ -70,72 +70,97 @@ eb_create(struct drm_i915_gem_execbuffer2 *args)
} else
eb->and = -args->buffer_count;
- INIT_LIST_HEAD(&eb->objects);
+ INIT_LIST_HEAD(&eb->vmas);
return eb;
}
static void
-eb_reset(struct eb_objects *eb)
+eb_reset(struct eb_vmas *eb)
{
if (eb->and >= 0)
memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head));
}
static int
-eb_lookup_objects(struct eb_objects *eb,
- struct drm_i915_gem_exec_object2 *exec,
- const struct drm_i915_gem_execbuffer2 *args,
- struct i915_address_space *vm,
- struct drm_file *file)
+eb_lookup_vmas(struct eb_vmas *eb,
+ struct drm_i915_gem_exec_object2 *exec,
+ const struct drm_i915_gem_execbuffer2 *args,
+ struct i915_address_space *vm,
+ struct drm_file *file)
{
struct drm_i915_gem_object *obj;
- int i;
+ struct list_head objects;
+ int i, ret = 0;
+ INIT_LIST_HEAD(&objects);
spin_lock(&file->table_lock);
+ /* Grab a reference to the object and release the lock so we can lookup
+ * or create the VMA without using GFP_ATOMIC */
for (i = 0; i < args->buffer_count; i++) {
obj = to_intel_bo(idr_find(&file->object_idr, exec[i].handle));
if (obj == NULL) {
spin_unlock(&file->table_lock);
DRM_DEBUG("Invalid object handle %d at index %d\n",
exec[i].handle, i);
- return -ENOENT;
+ ret = -ENOENT;
+ goto out;
}
- if (!list_empty(&obj->exec_list)) {
+ if (!list_empty(&obj->obj_exec_list)) {
spin_unlock(&file->table_lock);
DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n",
obj, exec[i].handle, i);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
drm_gem_object_reference(&obj->base);
- list_add_tail(&obj->exec_list, &eb->objects);
+ list_add_tail(&obj->obj_exec_list, &objects);
}
spin_unlock(&file->table_lock);
- list_for_each_entry(obj, &eb->objects, exec_list) {
+ i = 0;
+ list_for_each_entry(obj, &objects, obj_exec_list) {
struct i915_vma *vma;
vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
- if (IS_ERR(vma))
- return PTR_ERR(vma);
+ if (IS_ERR(vma)) {
+ /* XXX: We don't need an error path fro vma because if
+ * the vma was created just for this execbuf, object
+ * unreference should kill it off.*/
+ DRM_DEBUG("Failed to lookup VMA\n");
+ ret = PTR_ERR(vma);
+ goto out;
+ }
+
+ list_add_tail(&vma->exec_list, &eb->vmas);
- obj->exec_entry = &exec[i];
+ vma->exec_entry = &exec[i];
if (eb->and < 0) {
- eb->lut[i] = obj;
+ eb->lut[i] = vma;
} else {
uint32_t handle = args->flags & I915_EXEC_HANDLE_LUT ? i : exec[i].handle;
- obj->exec_handle = handle;
- hlist_add_head(&obj->exec_node,
+ vma->exec_handle = handle;
+ hlist_add_head(&vma->exec_node,
&eb->buckets[handle & eb->and]);
}
+ ++i;
}
- return 0;
+
+out:
+ while (!list_empty(&objects)) {
+ obj = list_first_entry(&objects,
+ struct drm_i915_gem_object,
+ obj_exec_list);
+ list_del_init(&obj->obj_exec_list);
+ if (ret)
+ drm_gem_object_unreference(&obj->base);
+ }
+ return ret;
}
-static struct drm_i915_gem_object *
-eb_get_object(struct eb_objects *eb, unsigned long handle)
+static struct i915_vma *eb_get_vma(struct eb_vmas *eb, unsigned long handle)
{
if (eb->and < 0) {
if (handle >= -eb->and)
@@ -147,27 +172,25 @@ eb_get_object(struct eb_objects *eb, unsigned long handle)
head = &eb->buckets[handle & eb->and];
hlist_for_each(node, head) {
- struct drm_i915_gem_object *obj;
+ struct i915_vma *vma;
- obj = hlist_entry(node, struct drm_i915_gem_object, exec_node);
- if (obj->exec_handle == handle)
- return obj;
+ vma = hlist_entry(node, struct i915_vma, exec_node);
+ if (vma->exec_handle == handle)
+ return vma;
}
return NULL;
}
}
-static void
-eb_destroy(struct eb_objects *eb)
-{
- while (!list_empty(&eb->objects)) {
- struct drm_i915_gem_object *obj;
+static void eb_destroy(struct eb_vmas *eb) {
+ while (!list_empty(&eb->vmas)) {
+ struct i915_vma *vma;
- obj = list_first_entry(&eb->objects,
- struct drm_i915_gem_object,
+ vma = list_first_entry(&eb->vmas,
+ struct i915_vma,
exec_list);
- list_del_init(&obj->exec_list);
- drm_gem_object_unreference(&obj->base);
+ list_del_init(&vma->exec_list);
+ drm_gem_object_unreference(&vma->obj->base);
}
kfree(eb);
}
@@ -181,22 +204,24 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
static int
i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
- struct eb_objects *eb,
+ struct eb_vmas *eb,
struct drm_i915_gem_relocation_entry *reloc,
struct i915_address_space *vm)
{
struct drm_device *dev = obj->base.dev;
struct drm_gem_object *target_obj;
struct drm_i915_gem_object *target_i915_obj;
+ struct i915_vma *target_vma;
uint32_t target_offset;
int ret = -EINVAL;
/* we've already hold a reference to all valid objects */
- target_obj = &eb_get_object(eb, reloc->target_handle)->base;
- if (unlikely(target_obj == NULL))
+ target_vma = eb_get_vma(eb, reloc->target_handle);
+ if (unlikely(target_vma == NULL))
return -ENOENT;
+ target_i915_obj = target_vma->obj;
+ target_obj = &target_vma->obj->base;
- target_i915_obj = to_intel_bo(target_obj);
target_offset = i915_gem_obj_ggtt_offset(target_i915_obj);
/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
@@ -305,14 +330,13 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
}
static int
-i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
- struct eb_objects *eb,
- struct i915_address_space *vm)
+i915_gem_execbuffer_relocate_vma(struct i915_vma *vma,
+ struct eb_vmas *eb)
{
#define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)];
struct drm_i915_gem_relocation_entry __user *user_relocs;
- struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
+ struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
int remain, ret;
user_relocs = to_user_ptr(entry->relocs_ptr);
@@ -331,8 +355,8 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
do {
u64 offset = r->presumed_offset;
- ret = i915_gem_execbuffer_relocate_entry(obj, eb, r,
- vm);
+ ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r,
+ vma->vm);
if (ret)
return ret;
@@ -353,17 +377,16 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
}
static int
-i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj,
- struct eb_objects *eb,
- struct drm_i915_gem_relocation_entry *relocs,
- struct i915_address_space *vm)
+i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma,
+ struct eb_vmas *eb,
+ struct drm_i915_gem_relocation_entry *relocs)
{
- const struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
+ const struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
int i, ret;
for (i = 0; i < entry->relocation_count; i++) {
- ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i],
- vm);
+ ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i],
+ vma->vm);
if (ret)
return ret;
}
@@ -372,10 +395,10 @@ i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj,
}
static int
-i915_gem_execbuffer_relocate(struct eb_objects *eb,
+i915_gem_execbuffer_relocate(struct eb_vmas *eb,
struct i915_address_space *vm)
{
- struct drm_i915_gem_object *obj;
+ struct i915_vma *vma;
int ret = 0;
/* This is the fast path and we cannot handle a pagefault whilst
@@ -386,8 +409,8 @@ i915_gem_execbuffer_relocate(struct eb_objects *eb,
* lockdep complains vehemently.
*/
pagefault_disable();
- list_for_each_entry(obj, &eb->objects, exec_list) {
- ret = i915_gem_execbuffer_relocate_object(obj, eb, vm);
+ list_for_each_entry(vma, &eb->vmas, exec_list) {
+ ret = i915_gem_execbuffer_relocate_vma(vma, eb);
if (ret)
break;
}
@@ -400,31 +423,31 @@ i915_gem_execbuffer_relocate(struct eb_objects *eb,
#define __EXEC_OBJECT_HAS_FENCE (1<<30)
static int
-need_reloc_mappable(struct drm_i915_gem_object *obj)
+need_reloc_mappable(struct i915_vma *vma)
{
- struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
- return entry->relocation_count && !use_cpu_reloc(obj);
+ struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
+ return entry->relocation_count && !use_cpu_reloc(vma->obj);
}
static int
-i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
- struct intel_ring_buffer *ring,
- struct i915_address_space *vm,
- bool *need_reloc)
+i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
+ struct intel_ring_buffer *ring,
+ bool *need_reloc)
{
- struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
- struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
+ struct drm_i915_private *dev_priv = ring->dev->dev_private;
+ struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
bool need_fence, need_mappable;
+ struct drm_i915_gem_object *obj = vma->obj;
int ret;
need_fence =
has_fenced_gpu_access &&
entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
obj->tiling_mode != I915_TILING_NONE;
- need_mappable = need_fence || need_reloc_mappable(obj);
+ need_mappable = need_fence || need_reloc_mappable(vma);
- ret = i915_gem_object_pin(obj, vm, entry->alignment, need_mappable,
+ ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, need_mappable,
false);
if (ret)
return ret;
@@ -452,8 +475,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
obj->has_aliasing_ppgtt_mapping = 1;
}
- if (entry->offset != i915_gem_obj_offset(obj, vm)) {
- entry->offset = i915_gem_obj_offset(obj, vm);
+ if (entry->offset != vma->node.start) {
+ entry->offset = vma->node.start;
*need_reloc = true;
}
@@ -470,61 +493,60 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
}
static void
-i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
+i915_gem_execbuffer_unreserve_vma(struct i915_vma *vma)
{
struct drm_i915_gem_exec_object2 *entry;
- if (!i915_gem_obj_bound_any(obj))
+ if (!drm_mm_node_allocated(&vma->node))
return;
- entry = obj->exec_entry;
+ entry = vma->exec_entry;
if (entry->flags & __EXEC_OBJECT_HAS_FENCE)
- i915_gem_object_unpin_fence(obj);
+ i915_gem_object_unpin_fence(vma->obj);
if (entry->flags & __EXEC_OBJECT_HAS_PIN)
- i915_gem_object_unpin(obj);
+ i915_gem_object_unpin(vma->obj);
entry->flags &= ~(__EXEC_OBJECT_HAS_FENCE | __EXEC_OBJECT_HAS_PIN);
}
static int
i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
- struct list_head *objects,
- struct i915_address_space *vm,
+ struct list_head *vmas,
bool *need_relocs)
{
struct drm_i915_gem_object *obj;
- struct list_head ordered_objects;
+ struct i915_vma *vma;
+ struct list_head ordered_vmas;
bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
int retry;
- INIT_LIST_HEAD(&ordered_objects);
- while (!list_empty(objects)) {
+ INIT_LIST_HEAD(&ordered_vmas);
+ while (!list_empty(vmas)) {
struct drm_i915_gem_exec_object2 *entry;
bool need_fence, need_mappable;
- obj = list_first_entry(objects,
- struct drm_i915_gem_object,
- exec_list);
- entry = obj->exec_entry;
+ vma = list_first_entry(vmas, struct i915_vma, exec_list);
+ obj = vma->obj;
+ entry = vma->exec_entry;
need_fence =
has_fenced_gpu_access &&
entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
obj->tiling_mode != I915_TILING_NONE;
- need_mappable = need_fence || need_reloc_mappable(obj);
+ need_mappable = need_fence || need_reloc_mappable(vma);
if (need_mappable)
- list_move(&obj->exec_list, &ordered_objects);
+ list_move(&vma->exec_list, &ordered_vmas);
else
- list_move_tail(&obj->exec_list, &ordered_objects);
+ list_move_tail(&vma->exec_list, &ordered_vmas);
obj->base.pending_read_domains = I915_GEM_GPU_DOMAINS & ~I915_GEM_DOMAIN_COMMAND;
obj->base.pending_write_domain = 0;
obj->pending_fenced_gpu_access = false;
}
- list_splice(&ordered_objects, objects);
+ list_splice(&ordered_vmas, vmas);
/* Attempt to pin all of the buffers into the GTT.
* This is done in 3 phases:
@@ -543,47 +565,47 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
int ret = 0;
/* Unbind any ill-fitting objects or pin. */
- list_for_each_entry(obj, objects, exec_list) {
- struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
+ list_for_each_entry(vma, vmas, exec_list) {
+ struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
bool need_fence, need_mappable;
- u32 obj_offset;
- if (!i915_gem_obj_bound(obj, vm))
+ obj = vma->obj;
+
+ if (!drm_mm_node_allocated(&vma->node))
continue;
- obj_offset = i915_gem_obj_offset(obj, vm);
need_fence =
has_fenced_gpu_access &&
entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
obj->tiling_mode != I915_TILING_NONE;
- need_mappable = need_fence || need_reloc_mappable(obj);
+ need_mappable = need_fence || need_reloc_mappable(vma);
BUG_ON((need_mappable || need_fence) &&
- !i915_is_ggtt(vm));
+ !i915_is_ggtt(vma->vm));
if ((entry->alignment &&
- obj_offset & (entry->alignment - 1)) ||
+ vma->node.start & (entry->alignment - 1)) ||
(need_mappable && !obj->map_and_fenceable))
- ret = i915_vma_unbind(i915_gem_obj_to_vma(obj, vm));
+ ret = i915_vma_unbind(vma);
else
- ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs);
+ ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs);
if (ret)
goto err;
}
/* Bind fresh objects */
- list_for_each_entry(obj, objects, exec_list) {
- if (i915_gem_obj_bound(obj, vm))
+ list_for_each_entry(vma, vmas, exec_list) {
+ if (drm_mm_node_allocated(&vma->node))
continue;
- ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs);
+ ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs);
if (ret)
goto err;
}
err: /* Decrement pin count for bound objects */
- list_for_each_entry(obj, objects, exec_list)
- i915_gem_execbuffer_unreserve_object(obj);
+ list_for_each_entry(vma, vmas, exec_list)
+ i915_gem_execbuffer_unreserve_vma(vma);
if (ret != -ENOSPC || retry++)
return ret;
@@ -599,24 +621,27 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
struct drm_i915_gem_execbuffer2 *args,
struct drm_file *file,
struct intel_ring_buffer *ring,
- struct eb_objects *eb,
- struct drm_i915_gem_exec_object2 *exec,
- struct i915_address_space *vm)
+ struct eb_vmas *eb,
+ struct drm_i915_gem_exec_object2 *exec)
{
struct drm_i915_gem_relocation_entry *reloc;
- struct drm_i915_gem_object *obj;
+ struct i915_address_space *vm;
+ struct i915_vma *vma;
bool need_relocs;
int *reloc_offset;
int i, total, ret;
int count = args->buffer_count;
+ if (WARN_ON(list_empty(&eb->vmas)))
+ return 0;
+
+ vm = list_first_entry(&eb->vmas, struct i915_vma, exec_list)->vm;
+
/* We may process another execbuffer during the unlock... */
- while (!list_empty(&eb->objects)) {
- obj = list_first_entry(&eb->objects,
- struct drm_i915_gem_object,
- exec_list);
- list_del_init(&obj->exec_list);
- drm_gem_object_unreference(&obj->base);
+ while (!list_empty(&eb->vmas)) {
+ vma = list_first_entry(&eb->vmas, struct i915_vma, exec_list);
+ list_del_init(&vma->exec_list);
+ drm_gem_object_unreference(&vma->obj->base);
}
mutex_unlock(&dev->struct_mutex);
@@ -680,20 +705,19 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
/* reacquire the objects */
eb_reset(eb);
- ret = eb_lookup_objects(eb, exec, args, vm, file);
+ ret = eb_lookup_vmas(eb, exec, args, vm, file);
if (ret)
goto err;
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
- ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs);
+ ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
if (ret)
goto err;
- list_for_each_entry(obj, &eb->objects, exec_list) {
- int offset = obj->exec_entry - exec;
- ret = i915_gem_execbuffer_relocate_object_slow(obj, eb,
- reloc + reloc_offset[offset],
- vm);
+ list_for_each_entry(vma, &eb->vmas, exec_list) {
+ int offset = vma->exec_entry - exec;
+ ret = i915_gem_execbuffer_relocate_vma_slow(vma, eb,
+ reloc + reloc_offset[offset]);
if (ret)
goto err;
}
@@ -712,21 +736,21 @@ err:
static int
i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
- struct list_head *objects)
+ struct list_head *vmas)
{
- struct drm_i915_gem_object *obj;
+ struct i915_vma *vma;
uint32_t flush_domains = 0;
int ret;
- list_for_each_entry(obj, objects, exec_list) {
- ret = i915_gem_object_sync(obj, ring);
+ list_for_each_entry(vma, vmas, exec_list) {
+ ret = i915_gem_object_sync(vma->obj, ring);
if (ret)
return ret;
- if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
- i915_gem_clflush_object(obj);
+ if (vma->obj->base.write_domain & I915_GEM_DOMAIN_CPU)
+ i915_gem_clflush_object(vma->obj);
- flush_domains |= obj->base.write_domain;
+ flush_domains |= vma->obj->base.write_domain;
}
if (flush_domains & I915_GEM_DOMAIN_CPU)
@@ -793,13 +817,13 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
}
static void
-i915_gem_execbuffer_move_to_active(struct list_head *objects,
- struct i915_address_space *vm,
+i915_gem_execbuffer_move_to_active(struct list_head *vmas,
struct intel_ring_buffer *ring)
{
- struct drm_i915_gem_object *obj;
+ struct i915_vma *vma;
- list_for_each_entry(obj, objects, exec_list) {
+ list_for_each_entry(vma, vmas, exec_list) {
+ struct drm_i915_gem_object *obj = vma->obj;
u32 old_read = obj->base.read_domains;
u32 old_write = obj->base.write_domain;
@@ -810,7 +834,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects,
obj->fenced_gpu_access = obj->pending_fenced_gpu_access;
/* FIXME: This lookup gets fixed later <-- danvet */
- list_move_tail(&i915_gem_obj_to_vma(obj, vm)->mm_list, &vm->active_list);
+ list_move_tail(&vma->mm_list, &vma->vm->active_list);
i915_gem_object_move_to_active(obj, ring);
if (obj->base.write_domain) {
obj->dirty = 1;
@@ -869,7 +893,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
struct i915_address_space *vm)
{
drm_i915_private_t *dev_priv = dev->dev_private;
- struct eb_objects *eb;
+ struct eb_vmas *eb;
struct drm_i915_gem_object *batch_obj;
struct drm_clip_rect *cliprects = NULL;
struct intel_ring_buffer *ring;
@@ -1009,7 +1033,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
goto pre_mutex_err;
}
- eb = eb_create(args);
+ eb = eb_create(args, vm);
if (eb == NULL) {
mutex_unlock(&dev->struct_mutex);
ret = -ENOMEM;
@@ -1017,18 +1041,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
}
/* Look up object handles */
- ret = eb_lookup_objects(eb, exec, args, vm, file);
+ ret = eb_lookup_vmas(eb, exec, args, vm, file);
if (ret)
goto err;
/* take note of the batch buffer before we might reorder the lists */
- batch_obj = list_entry(eb->objects.prev,
- struct drm_i915_gem_object,
- exec_list);
+ batch_obj = list_entry(eb->vmas.prev, struct i915_vma, exec_list)->obj;
/* Move the objects en-masse into the GTT, evicting if necessary. */
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
- ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs);
+ ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
if (ret)
goto err;
@@ -1038,7 +1060,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (ret) {
if (ret == -EFAULT) {
ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring,
- eb, exec, vm);
+ eb, exec);
BUG_ON(!mutex_is_locked(&dev->struct_mutex));
}
if (ret)
@@ -1060,7 +1082,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (flags & I915_DISPATCH_SECURE && !batch_obj->has_global_gtt_mapping)
i915_gem_gtt_bind_object(batch_obj, batch_obj->cache_level);
- ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->objects);
+ ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->vmas);
if (ret)
goto err;
@@ -1115,7 +1137,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags);
- i915_gem_execbuffer_move_to_active(&eb->objects, vm, ring);
+ i915_gem_execbuffer_move_to_active(&eb->vmas, ring);
i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
err:
--
1.8.3.4
More information about the Intel-gfx
mailing list