@@ -2452,7 +2452,7 @@ int r600_dma_cs_next_reloc(struct radeon_cs_parser *p,
idx, p->nrelocs);
return -EINVAL;
}
- *cs_reloc = p->relocs_ptr[idx];
+ *cs_reloc = &p->relocs[idx];
p->dma_reloc_idx++;
return 0;
}
@@ -1076,7 +1076,6 @@ struct radeon_cs_parser {
/* relocations */
unsigned nrelocs;
struct radeon_bo_list *relocs;
- struct radeon_bo_list **relocs_ptr;
struct radeon_bo_list *vm_bos;
struct list_head validated;
unsigned dma_reloc_idx;
@@ -77,8 +77,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
struct drm_device *ddev = p->rdev->ddev;
struct radeon_cs_chunk *chunk;
struct radeon_cs_buckets buckets;
- unsigned i, j;
- bool duplicate, need_mmap_lock = false;
+ unsigned i;
+ bool need_mmap_lock = false;
int r;
if (p->chunk_relocs_idx == -1) {
@@ -88,10 +88,6 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
p->dma_reloc_idx = 0;
/* FIXME: we assume that each relocs use 4 dwords */
p->nrelocs = chunk->length_dw / 4;
- p->relocs_ptr = kcalloc(p->nrelocs, sizeof(void *), GFP_KERNEL);
- if (p->relocs_ptr == NULL) {
- return -ENOMEM;
- }
p->relocs = kcalloc(p->nrelocs, sizeof(struct radeon_bo_list), GFP_KERNEL);
if (p->relocs == NULL) {
return -ENOMEM;
@@ -104,28 +100,13 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
struct drm_gem_object *gobj;
unsigned priority;
- duplicate = false;
r = (struct drm_radeon_cs_reloc *)&chunk->kdata[i*4];
- for (j = 0; j < i; j++) {
- struct drm_radeon_cs_reloc *other;
- other = (void *)&chunk->kdata[j*4];
- if (r->handle == other->handle) {
- p->relocs_ptr[i] = &p->relocs[j];
- duplicate = true;
- break;
- }
- }
- if (duplicate) {
- continue;
- }
-
gobj = drm_gem_object_lookup(ddev, p->filp, r->handle);
if (gobj == NULL) {
DRM_ERROR("gem object lookup failed 0x%x\n",
r->handle);
return -ENOENT;
}
- p->relocs_ptr[i] = &p->relocs[i];
p->relocs[i].robj = gem_to_radeon_bo(gobj);
/* The userspace buffer priorities are from 0 to 15. A higher
@@ -448,7 +429,6 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo
}
kfree(parser->track);
kfree(parser->relocs);
- kfree(parser->relocs_ptr);
drm_free_large(parser->vm_bos);
for (i = 0; i < parser->nchunks; i++)
drm_free_large(parser->chunks[i].kdata);
@@ -523,10 +503,6 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p,
for (i = 0; i < p->nrelocs; i++) {
struct radeon_bo *bo;
- /* ignore duplicates */
- if (p->relocs_ptr[i] != &p->relocs[i])
- continue;
-
bo = p->relocs[i].robj;
bo_va = radeon_vm_bo_find(vm, bo);
if (bo_va == NULL) {
@@ -871,6 +847,6 @@ int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p,
(u64)relocs_chunk->kdata[idx + 3] << 32;
(*cs_reloc)->gpu_offset |= relocs_chunk->kdata[idx + 0];
} else
- *cs_reloc = p->relocs_ptr[(idx / 4)];
+ *cs_reloc = &p->relocs[(idx / 4)];
return 0;
}
@@ -503,18 +503,19 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
struct list_head *head, int ring)
{
struct radeon_bo_list *lobj;
- struct radeon_bo *bo;
+ struct list_head duplicates;
int r;
u64 bytes_moved = 0, initial_bytes_moved;
u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev);
- r = ttm_eu_reserve_buffers(ticket, head, true, NULL);
+ INIT_LIST_HEAD(&duplicates);
+ r = ttm_eu_reserve_buffers(ticket, head, true, &duplicates);
if (unlikely(r != 0)) {
return r;
}
list_for_each_entry(lobj, head, tv.head) {
- bo = lobj->robj;
+ struct radeon_bo *bo = lobj->robj;
if (!bo->pin_count) {
u32 domain = lobj->prefered_domains;
u32 allowed = lobj->allowed_domains;
@@ -562,6 +563,12 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
lobj->gpu_offset = radeon_bo_gpu_offset(bo);
lobj->tiling_flags = bo->tiling_flags;
}
+
+ list_for_each_entry(lobj, &duplicates, tv.head) {
+ lobj->gpu_offset = radeon_bo_gpu_offset(lobj->robj);
+ lobj->tiling_flags = lobj->robj->tiling_flags;
+ }
+
return 0;
}
@@ -502,7 +502,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
return -EINVAL;
}
- reloc = p->relocs_ptr[(idx / 4)];
+ reloc = &p->relocs[(idx / 4)];
start = reloc->gpu_offset;
end = start + radeon_bo_size(reloc->robj);
start += offset;
@@ -467,7 +467,7 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi,
return -EINVAL;
}
- reloc = p->relocs_ptr[(idx / 4)];
+ reloc = &p->relocs[(idx / 4)];
start = reloc->gpu_offset;
end = start + radeon_bo_size(reloc->robj);
start += offset;