63,25 → 63,43 |
} |
|
struct eb_objects { |
struct list_head objects; |
int and; |
union { |
struct drm_i915_gem_object *lut[0]; |
struct hlist_head buckets[0]; |
}; |
}; |
|
static struct eb_objects * |
eb_create(int size) |
eb_create(struct drm_i915_gem_execbuffer2 *args) |
{ |
struct eb_objects *eb; |
struct eb_objects *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); |
eb = kmalloc(size, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); |
} |
|
if (eb == NULL) { |
int size = args->buffer_count; |
int count = PAGE_SIZE / sizeof(struct hlist_head) / 2; |
BUILD_BUG_ON(!is_power_of_2(PAGE_SIZE / sizeof(struct hlist_head))); |
while (count > size) |
BUILD_BUG_ON_NOT_POWER_OF_2(PAGE_SIZE / sizeof(struct hlist_head)); |
while (count > 2*size) |
count >>= 1; |
eb = kzalloc(count*sizeof(struct hlist_head) + |
sizeof(struct eb_objects), |
GFP_KERNEL); |
GFP_TEMPORARY); |
if (eb == NULL) |
return eb; |
|
eb->and = count - 1; |
} else |
eb->and = -args->buffer_count; |
|
INIT_LIST_HEAD(&eb->objects); |
return eb; |
} |
|
88,36 → 106,93 |
static void |
eb_reset(struct eb_objects *eb) |
{ |
if (eb->and >= 0) |
memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head)); |
} |
|
static void |
eb_add_object(struct eb_objects *eb, struct drm_i915_gem_object *obj) |
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) |
{ |
int i; |
|
spin_lock(&file->table_lock); |
for (i = 0; i < args->buffer_count; i++) { |
struct drm_i915_gem_object *obj; |
|
if(exec[i].handle == -2) |
obj = get_fb_obj(); |
else |
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; |
} |
|
if (!list_empty(&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; |
} |
|
drm_gem_object_reference(&obj->base); |
list_add_tail(&obj->exec_list, &eb->objects); |
|
obj->exec_entry = &exec[i]; |
if (eb->and < 0) { |
eb->lut[i] = obj; |
} else { |
uint32_t handle = args->flags & I915_EXEC_HANDLE_LUT ? i : exec[i].handle; |
obj->exec_handle = handle; |
hlist_add_head(&obj->exec_node, |
&eb->buckets[obj->exec_handle & eb->and]); |
&eb->buckets[handle & eb->and]); |
} |
} |
spin_unlock(&file->table_lock); |
|
return 0; |
} |
|
static struct drm_i915_gem_object * |
eb_get_object(struct eb_objects *eb, unsigned long handle) |
{ |
if (eb->and < 0) { |
if (handle >= -eb->and) |
return NULL; |
return eb->lut[handle]; |
} else { |
struct hlist_head *head; |
struct hlist_node *node; |
struct drm_i915_gem_object *obj; |
|
head = &eb->buckets[handle & eb->and]; |
hlist_for_each(node, head) { |
struct drm_i915_gem_object *obj; |
|
obj = hlist_entry(node, struct drm_i915_gem_object, exec_node); |
if (obj->exec_handle == handle) |
return obj; |
} |
|
return NULL; |
} |
} |
|
static void |
eb_destroy(struct eb_objects *eb) |
{ |
while (!list_empty(&eb->objects)) { |
struct drm_i915_gem_object *obj; |
|
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); |
} |
kfree(eb); |
} |
|
179,17 → 254,6 |
reloc->write_domain); |
return ret; |
} |
if (unlikely(reloc->write_domain && target_obj->pending_write_domain && |
reloc->write_domain != target_obj->pending_write_domain)) { |
DRM_DEBUG("Write domain conflict: " |
"obj %p target %d offset %d " |
"new %08x old %08x\n", |
obj, reloc->target_handle, |
(int) reloc->offset, |
reloc->write_domain, |
target_obj->pending_write_domain); |
return ret; |
} |
|
target_obj->pending_read_domains |= reloc->read_domains; |
target_obj->pending_write_domain |= reloc->write_domain; |
218,10 → 282,7 |
} |
|
/* We can't wait for rendering with pagefaults disabled */ |
// if (obj->active && in_atomic()) |
// return -EFAULT; |
|
|
reloc->delta += target_offset; |
if (use_cpu_reloc(obj)) { |
uint32_t page_offset = reloc->offset & ~PAGE_MASK; |
324,8 → 385,7 |
|
static int |
i915_gem_execbuffer_relocate(struct drm_device *dev, |
struct eb_objects *eb, |
struct list_head *objects) |
struct eb_objects *eb) |
{ |
struct drm_i915_gem_object *obj; |
int ret = 0; |
338,7 → 398,7 |
* lockdep complains vehemently. |
*/ |
// pagefault_disable(); |
list_for_each_entry(obj, objects, exec_list) { |
list_for_each_entry(obj, &eb->objects, exec_list) { |
ret = i915_gem_execbuffer_relocate_object(obj, eb); |
if (ret) |
break; |
360,7 → 420,8 |
|
static int |
i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, |
struct intel_ring_buffer *ring) |
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; |
409,9 → 470,20 |
obj->has_aliasing_ppgtt_mapping = 1; |
} |
|
if (entry->offset != obj->gtt_offset) { |
entry->offset = obj->gtt_offset; |
// LEAVE(); |
*need_reloc = true; |
} |
|
if (entry->flags & EXEC_OBJECT_WRITE) { |
obj->base.pending_read_domains = I915_GEM_DOMAIN_RENDER; |
obj->base.pending_write_domain = I915_GEM_DOMAIN_RENDER; |
} |
|
if (entry->flags & EXEC_OBJECT_NEEDS_GTT && |
!obj->has_global_gtt_mapping) |
i915_gem_gtt_bind_object(obj, obj->cache_level); |
|
return 0; |
} |
|
437,7 → 509,8 |
static int |
i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, |
struct drm_file *file, |
struct list_head *objects) |
struct list_head *objects, |
bool *need_relocs) |
{ |
struct drm_i915_gem_object *obj; |
struct list_head ordered_objects; |
467,7 → 540,7 |
else |
list_move_tail(&obj->exec_list, &ordered_objects); |
|
obj->base.pending_read_domains = 0; |
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; |
} |
507,7 → 580,7 |
(need_mappable && !obj->map_and_fenceable)) |
ret = i915_gem_object_unbind(obj); |
else |
ret = i915_gem_execbuffer_reserve_object(obj, ring); |
ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs); |
if (ret) |
goto err; |
} |
517,7 → 590,7 |
if (obj->gtt_space) |
continue; |
|
ret = i915_gem_execbuffer_reserve_object(obj, ring); |
ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs); |
if (ret) |
goto err; |
} |
540,21 → 613,22 |
|
static int |
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 list_head *objects, |
struct eb_objects *eb, |
struct drm_i915_gem_exec_object2 *exec, |
int count) |
struct drm_i915_gem_exec_object2 *exec) |
{ |
struct drm_i915_gem_relocation_entry *reloc; |
struct drm_i915_gem_object *obj; |
bool need_relocs; |
int *reloc_offset; |
int i, total, ret; |
int count = args->buffer_count; |
|
/* We may process another execbuffer during the unlock... */ |
while (!list_empty(objects)) { |
obj = list_first_entry(objects, |
while (!list_empty(&eb->objects)) { |
obj = list_first_entry(&eb->objects, |
struct drm_i915_gem_object, |
exec_list); |
list_del_init(&obj->exec_list); |
622,34 → 696,16 |
|
/* reacquire the objects */ |
eb_reset(eb); |
for (i = 0; i < count; i++) { |
|
if(exec[i].handle == -2) |
{ |
obj = get_fb_obj(); |
drm_gem_object_reference(&obj->base); |
} |
else |
obj = to_intel_bo(drm_gem_object_lookup(dev, file, |
exec[i].handle)); |
if (&obj->base == NULL) { |
DRM_DEBUG("Invalid object handle %d at index %d\n", |
exec[i].handle, i); |
ret = -ENOENT; |
ret = eb_lookup_objects(eb, exec, args, file); |
if (ret) |
goto err; |
} |
|
list_add_tail(&obj->exec_list, objects); |
obj->exec_handle = exec[i].handle; |
obj->exec_entry = &exec[i]; |
eb_add_object(eb, obj); |
} |
|
ret = i915_gem_execbuffer_reserve(ring, file, objects); |
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; |
ret = i915_gem_execbuffer_reserve(ring, file, &eb->objects, &need_relocs); |
if (ret) |
goto err; |
|
list_for_each_entry(obj, objects, exec_list) { |
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]); |
670,44 → 726,11 |
} |
|
static int |
i915_gem_execbuffer_wait_for_flips(struct intel_ring_buffer *ring, u32 flips) |
{ |
u32 plane, flip_mask; |
int ret; |
|
/* Check for any pending flips. As we only maintain a flip queue depth |
* of 1, we can simply insert a WAIT for the next display flip prior |
* to executing the batch and avoid stalling the CPU. |
*/ |
|
for (plane = 0; flips >> plane; plane++) { |
if (((flips >> plane) & 1) == 0) |
continue; |
|
if (plane) |
flip_mask = MI_WAIT_FOR_PLANE_B_FLIP; |
else |
flip_mask = MI_WAIT_FOR_PLANE_A_FLIP; |
|
ret = intel_ring_begin(ring, 2); |
if (ret) |
return ret; |
|
intel_ring_emit(ring, MI_WAIT_FOR_EVENT | flip_mask); |
intel_ring_emit(ring, MI_NOOP); |
intel_ring_advance(ring); |
} |
|
return 0; |
} |
|
static int |
i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring, |
struct list_head *objects) |
{ |
struct drm_i915_gem_object *obj; |
uint32_t flush_domains = 0; |
uint32_t flips = 0; |
int ret; |
|
list_for_each_entry(obj, objects, exec_list) { |
718,18 → 741,9 |
if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) |
i915_gem_clflush_object(obj); |
|
if (obj->base.pending_write_domain) |
flips |= atomic_read(&obj->pending_flip); |
|
flush_domains |= obj->base.write_domain; |
} |
|
if (flips) { |
ret = i915_gem_execbuffer_wait_for_flips(ring, flips); |
if (ret) |
return ret; |
} |
|
if (flush_domains & I915_GEM_DOMAIN_CPU) |
i915_gem_chipset_flush(ring->dev); |
|
745,6 → 759,9 |
static bool |
i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) |
{ |
if (exec->flags & __I915_EXEC_UNKNOWN_FLAGS) |
return false; |
|
return ((exec->batch_start_offset | exec->batch_len) & 0x7) == 0; |
} |
|
753,21 → 770,26 |
int count) |
{ |
int i; |
int relocs_total = 0; |
int relocs_max = INT_MAX / sizeof(struct drm_i915_gem_relocation_entry); |
|
for (i = 0; i < count; i++) { |
char __user *ptr = (char __user *)(uintptr_t)exec[i].relocs_ptr; |
int length; /* limited by fault_in_pages_readable() */ |
|
/* First check for malicious input causing overflow */ |
if (exec[i].relocation_count > |
INT_MAX / sizeof(struct drm_i915_gem_relocation_entry)) |
if (exec[i].flags & __EXEC_OBJECT_UNKNOWN_FLAGS) |
return -EINVAL; |
|
/* First check for malicious input causing overflow in |
* the worst case where we need to allocate the entire |
* relocation tree as a single array. |
*/ |
if (exec[i].relocation_count > relocs_max - relocs_total) |
return -EINVAL; |
relocs_total += exec[i].relocation_count; |
|
length = exec[i].relocation_count * |
sizeof(struct drm_i915_gem_relocation_entry); |
// if (!access_ok(VERIFY_READ, ptr, length)) |
// return -EFAULT; |
|
/* we may also need to update the presumed offsets */ |
// if (!access_ok(VERIFY_WRITE, ptr, length)) |
// return -EFAULT; |
789,8 → 811,10 |
u32 old_read = obj->base.read_domains; |
u32 old_write = obj->base.write_domain; |
|
obj->base.write_domain = obj->base.pending_write_domain; |
if (obj->base.write_domain == 0) |
obj->base.pending_read_domains |= obj->base.read_domains; |
obj->base.read_domains = obj->base.pending_read_domains; |
obj->base.write_domain = obj->base.pending_write_domain; |
obj->fenced_gpu_access = obj->pending_fenced_gpu_access; |
|
i915_gem_object_move_to_active(obj, ring); |
849,7 → 873,6 |
struct drm_i915_gem_exec_object2 *exec) |
{ |
drm_i915_private_t *dev_priv = dev->dev_private; |
struct list_head objects; |
struct eb_objects *eb; |
struct drm_i915_gem_object *batch_obj; |
struct drm_clip_rect *cliprects = NULL; |
856,12 → 879,12 |
struct intel_ring_buffer *ring; |
u32 ctx_id = i915_execbuffer2_get_context_id(*args); |
u32 exec_start, exec_len; |
u32 mask; |
u32 flags; |
u32 mask, flags; |
int ret, mode, i; |
bool need_relocs; |
|
if (!i915_gem_check_execbuffer(args)) { |
DRM_DEBUG("execbuf with invalid offset/length\n"); |
if (!i915_gem_check_execbuffer(args)) |
{ |
FAIL(); |
return -EINVAL; |
} |
875,8 → 898,6 |
|
flags = 0; |
if (args->flags & I915_EXEC_SECURE) { |
// if (!file->is_master || !capable(CAP_SYS_ADMIN)) |
// return -EPERM; |
|
flags |= I915_DISPATCH_SECURE; |
} |
989,7 → 1010,7 |
goto pre_mutex_err; |
} |
|
eb = eb_create(args->buffer_count); |
eb = eb_create(args); |
if (eb == NULL) { |
mutex_unlock(&dev->struct_mutex); |
ret = -ENOMEM; |
997,60 → 1018,28 |
} |
|
/* Look up object handles */ |
INIT_LIST_HEAD(&objects); |
for (i = 0; i < args->buffer_count; i++) { |
struct drm_i915_gem_object *obj; |
|
if(exec[i].handle == -2) |
{ |
obj = get_fb_obj(); |
drm_gem_object_reference(&obj->base); |
} |
else |
obj = to_intel_bo(drm_gem_object_lookup(dev, file, |
exec[i].handle)); |
|
// printf("%s object %p handle %d\n", __FUNCTION__, obj, exec[i].handle); |
|
if (&obj->base == NULL) { |
DRM_DEBUG("Invalid object handle %d at index %d\n", |
exec[i].handle, i); |
/* prevent error path from reading uninitialized data */ |
ret = -ENOENT; |
ret = eb_lookup_objects(eb, exec, args, file); |
if (ret) |
goto err; |
} |
|
if (!list_empty(&obj->exec_list)) { |
DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n", |
obj, exec[i].handle, i); |
ret = -EINVAL; |
goto err; |
} |
|
list_add_tail(&obj->exec_list, &objects); |
obj->exec_handle = exec[i].handle; |
obj->exec_entry = &exec[i]; |
eb_add_object(eb, obj); |
} |
|
/* take note of the batch buffer before we might reorder the lists */ |
batch_obj = list_entry(objects.prev, |
batch_obj = list_entry(eb->objects.prev, |
struct drm_i915_gem_object, |
exec_list); |
|
/* Move the objects en-masse into the GTT, evicting if necessary. */ |
ret = i915_gem_execbuffer_reserve(ring, file, &objects); |
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; |
ret = i915_gem_execbuffer_reserve(ring, file, &eb->objects, &need_relocs); |
if (ret) |
goto err; |
|
/* The objects are in their final locations, apply the relocations. */ |
ret = i915_gem_execbuffer_relocate(dev, eb, &objects); |
if (need_relocs) |
ret = i915_gem_execbuffer_relocate(dev, eb); |
if (ret) { |
if (ret == -EFAULT) { |
ret = i915_gem_execbuffer_relocate_slow(dev, file, ring, |
&objects, eb, |
exec, |
args->buffer_count); |
ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring, |
eb, exec); |
BUG_ON(!mutex_is_locked(&dev->struct_mutex)); |
} |
if (ret) |
1072,7 → 1061,7 |
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, &objects); |
ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->objects); |
if (ret) |
goto err; |
|
1104,18 → 1093,7 |
exec_start = batch_obj->gtt_offset + args->batch_start_offset; |
exec_len = args->batch_len; |
if (cliprects) { |
// for (i = 0; i < args->num_cliprects; i++) { |
// ret = i915_emit_box(dev, &cliprects[i], |
// args->DR1, args->DR4); |
// if (ret) |
// goto err; |
|
// ret = ring->dispatch_execbuffer(ring, |
// exec_start, exec_len, |
// flags); |
// if (ret) |
// goto err; |
// } |
} else { |
ret = ring->dispatch_execbuffer(ring, |
exec_start, exec_len, |
1126,30 → 1104,21 |
|
trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags); |
|
i915_gem_execbuffer_move_to_active(&objects, ring); |
i915_gem_execbuffer_move_to_active(&eb->objects, ring); |
i915_gem_execbuffer_retire_commands(dev, file, ring); |
|
err: |
eb_destroy(eb); |
while (!list_empty(&objects)) { |
struct drm_i915_gem_object *obj; |
|
obj = list_first_entry(&objects, |
struct drm_i915_gem_object, |
exec_list); |
list_del_init(&obj->exec_list); |
drm_gem_object_unreference(&obj->base); |
} |
|
mutex_unlock(&dev->struct_mutex); |
|
pre_mutex_err: |
kfree(cliprects); |
|
|
return ret; |
} |
|
|
|
int |
i915_gem_execbuffer2(struct drm_device *dev, void *data, |
struct drm_file *file) |
1167,11 → 1136,8 |
return -EINVAL; |
} |
|
exec2_list = malloc(sizeof(*exec2_list)*args->buffer_count); |
|
// if (exec2_list == NULL) |
// exec2_list = drm_malloc_ab(sizeof(*exec2_list), |
// args->buffer_count); |
exec2_list = kmalloc(sizeof(*exec2_list)*args->buffer_count, |
GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); |
if (exec2_list == NULL) { |
DRM_DEBUG("Failed to allocate exec list for %d buffers\n", |
args->buffer_count); |