[Intel-gfx] [PATCH 4/4] [v4] drm/i915: Convert execbuf code to use vmas
Ben Widawsky
benjamin.widawsky at intel.com
Wed Aug 14 03:09:09 CEST 2013
From: Ben Widawsky <ben at bwidawsk.net>
In order to transition more of our code over to using a VMA instead of
an <OBJ, VM> pair - we must have the vma accessible at execbuf time. Up
until now, we've only had a VMA when actually binding an object.
The previous patch helped handle the distinction on bound vs. unbound.
This patch will help us catch leaks, and other issues before we actually
shuffle a bunch of stuff around.
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.
WARNING: This patch makes an already hotly profiled path slower. The cost is
unavoidable. In reply to this mail, I will attach the extra data.
v2: Release table lock early, and two a 2 phase vma lookup to avoid
having to use a GFP_ATOMIC. (Chris)
v3: s/obj_exec_list/obj_exec_link/
Updates to address
commit 6d2b888569d366beb4be72cacfde41adee2c25e1
Author: Chris Wilson <chris at chris-wilson.co.uk>
Date: Wed Aug 7 18:30:54 2013 +0100
drm/i915: List objects allocated from stolen memory in debugfs
v4: Use obj = vma->obj for neatness in some places (Chris)
need_reloc_mappable() should return false if ppgtt (Chris)
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
drivers/gpu/drm/i915/i915_debugfs.c | 12 +-
drivers/gpu/drm/i915/i915_drv.h | 25 ++-
drivers/gpu/drm/i915/i915_gem.c | 28 ++-
drivers/gpu/drm/i915/i915_gem_evict.c | 31 ++-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 319 ++++++++++++++++-------------
5 files changed, 232 insertions(+), 183 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index eb87865..4785d8c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -195,9 +195,9 @@ static int obj_rank_by_stolen(void *priv,
struct list_head *A, struct list_head *B)
{
struct drm_i915_gem_object *a =
- container_of(A, struct drm_i915_gem_object, exec_list);
+ container_of(A, struct drm_i915_gem_object, obj_exec_link);
struct drm_i915_gem_object *b =
- container_of(B, struct drm_i915_gem_object, exec_list);
+ container_of(B, struct drm_i915_gem_object, obj_exec_link);
return a->stolen->start - b->stolen->start;
}
@@ -221,7 +221,7 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
if (obj->stolen == NULL)
continue;
- list_add(&obj->exec_list, &stolen);
+ list_add(&obj->obj_exec_link, &stolen);
total_obj_size += obj->base.size;
total_gtt_size += i915_gem_obj_ggtt_size(obj);
@@ -231,7 +231,7 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
if (obj->stolen == NULL)
continue;
- list_add(&obj->exec_list, &stolen);
+ list_add(&obj->obj_exec_link, &stolen);
total_obj_size += obj->base.size;
count++;
@@ -239,11 +239,11 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
list_sort(NULL, &stolen, obj_rank_by_stolen);
seq_puts(m, "Stolen:\n");
while (!list_empty(&stolen)) {
- obj = list_first_entry(&stolen, typeof(*obj), exec_list);
+ obj = list_first_entry(&stolen, typeof(*obj), obj_exec_link);
seq_puts(m, " ");
describe_obj(m, obj);
seq_putc(m, '\n');
- list_del_init(&obj->exec_list);
+ list_del_init(&obj->obj_exec_link);
}
mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 3fc4324..2147e4d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -563,6 +563,17 @@ 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 {
@@ -1312,8 +1323,8 @@ 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_link;
/**
* This is set if the object is on the active lists (has pending
@@ -1399,13 +1410,6 @@ 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. */
@@ -1907,6 +1911,9 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
struct i915_address_space *vm);
struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
struct i915_address_space *vm);
+struct i915_vma *
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm);
/* Some GGTT VM helpers */
#define obj_to_ggtt(obj) \
(&((struct drm_i915_private *)(obj)->base.dev->dev_private)->gtt.base)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 01cc016..6bd341a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3111,8 +3111,7 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
struct i915_vma *vma;
int ret;
- if (WARN_ON(!list_empty(&obj->vma_list)))
- return -EBUSY;
+ BUG_ON(!i915_is_ggtt(vm));
fence_size = i915_gem_get_gtt_size(dev,
obj->base.size,
@@ -3152,16 +3151,15 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
i915_gem_object_pin_pages(obj);
- /* FIXME: For now we only ever use 1 VMA per object */
- BUG_ON(!i915_is_ggtt(vm));
- WARN_ON(!list_empty(&obj->vma_list));
-
- vma = i915_gem_vma_create(obj, vm);
+ vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto err_unpin;
}
+ /* For now we only ever use 1 vma per object */
+ WARN_ON(!list_is_singular(&obj->vma_list));
+
search_free:
ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
size, alignment,
@@ -3981,7 +3979,7 @@ 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_link);
INIT_LIST_HEAD(&obj->vma_list);
obj->ops = ops;
@@ -4121,6 +4119,7 @@ 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;
@@ -4870,3 +4869,16 @@ struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
return NULL;
}
+
+struct i915_vma *
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm)
+{
+ struct i915_vma *vma;
+
+ vma = i915_gem_obj_to_vma(obj, vm);
+ if (!vma)
+ vma = i915_gem_vma_create(obj, vm);
+
+ return vma;
+}
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 7dcf78c..3ca18bc 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;
@@ -70,64 +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 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)
{
- int i;
+ struct drm_i915_gem_object *obj;
+ 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++) {
- struct drm_i915_gem_object *obj;
-
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_link)) {
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_link, &objects);
+ }
+ spin_unlock(&file->table_lock);
- obj->exec_entry = &exec[i];
+ i = 0;
+ list_for_each_entry(obj, &objects, obj_exec_link) {
+ struct i915_vma *vma;
+
+ vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
+ 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);
+
+ 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;
}
- spin_unlock(&file->table_lock);
- return 0;
+
+out:
+ while (!list_empty(&objects)) {
+ obj = list_first_entry(&objects,
+ struct drm_i915_gem_object,
+ obj_exec_link);
+ list_del_init(&obj->obj_exec_link);
+ 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)
@@ -139,27 +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);
}
@@ -173,22 +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
@@ -297,14 +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);
@@ -323,8 +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;
@@ -345,17 +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;
}
@@ -364,10 +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
@@ -378,8 +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;
}
@@ -392,31 +423,32 @@ 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) &&
+ i915_is_ggtt(vma->vm);
}
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;
@@ -444,8 +476,8 @@ 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;
}
@@ -462,14 +494,15 @@ 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;
+ struct drm_i915_gem_object *obj = vma->obj;
- 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);
@@ -482,41 +515,40 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
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:
@@ -535,47 +567,47 @@ 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);
WARN_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;
@@ -591,24 +623,27 @@ 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);
@@ -672,20 +707,19 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
/* reacquire the objects */
eb_reset(eb);
- ret = eb_lookup_objects(eb, exec, args, 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;
}
@@ -704,14 +738,15 @@ 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;
bool flush_chipset = false;
int ret;
- list_for_each_entry(obj, objects, exec_list) {
+ list_for_each_entry(vma, vmas, exec_list) {
+ struct drm_i915_gem_object *obj = vma->obj;
ret = i915_gem_object_sync(obj, ring);
if (ret)
return ret;
@@ -786,13 +821,13 @@ 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;
@@ -803,7 +838,7 @@ 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;
@@ -862,7 +897,7 @@ 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;
@@ -1002,7 +1037,7 @@ 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;
@@ -1010,18 +1045,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
}
/* Look up object handles */
- ret = eb_lookup_objects(eb, exec, args, 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;
@@ -1031,7 +1064,7 @@ 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)
@@ -1053,7 +1086,7 @@ 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;
@@ -1108,7 +1141,7 @@ 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