/**
* amdgpu_bo_placement_from_domain - set buffer's placement
* @abo: &amdgpu_bo buffer object whose placement is to be set
* @domain: requested domain
*
* Sets buffer's placement according to requested domain and the buffer's
* flags.
*/
void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
struct ttm_placement *placement = &abo->placement;
struct ttm_place *places = abo->placements;
u64 flags = abo->flags;
u32 c = 0;
if (domain & AMDGPU_GEM_DOMAIN_VRAM) {
unsigned visible_pfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
places[c].fpfn = 0;
places[c].lpfn = 0;
places[c].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
TTM_PL_FLAG_VRAM;
if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
places[c].lpfn = visible_pfn;
else
places[c].flags |= TTM_PL_FLAG_TOPDOWN;
if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
places[c].flags |= TTM_PL_FLAG_CONTIGUOUS;
c++;
}
/**
* amdgpu_vram_mgr_del - free ranges
*
* @man: TTM memory type manager
* @tbo: TTM BO we need this range for
* @place: placement flags and restrictions
* @mem: TTM memory object
*
* Free the allocated VRAM again.
*/
static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
struct ttm_mem_reg *mem)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
struct amdgpu_vram_mgr *mgr = man->priv;
struct drm_mm_node *nodes = mem->mm_node;
uint64_t usage = 0, vis_usage = 0;
unsigned pages = mem->num_pages;
if (!mem->mm_node)
return;
spin_lock(&mgr->lock);
while (pages) {
pages -= nodes->size;
drm_mm_remove_node(nodes);
usage += nodes->size << PAGE_SHIFT;
vis_usage += amdgpu_vram_mgr_vis_size(adev, nodes);
++nodes;
}
spin_unlock(&mgr->lock);
atomic64_sub(usage, &mgr->usage);
atomic64_sub(vis_usage, &mgr->vis_usage);
kfree(mem->mm_node);
mem->mm_node = NULL;
}
static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
if (bo->pin_count > 0)
amdgpu_bo_subtract_pin_size(bo);
if (bo->kfd_bo)
amdgpu_amdkfd_unreserve_memory_limit(bo);
amdgpu_bo_kunmap(bo);
if (bo->gem_base.import_attach)
drm_prime_gem_destroy(&bo->gem_base, bo->tbo.sg);
drm_gem_object_release(&bo->gem_base);
amdgpu_bo_unref(&bo->parent);
if (!list_empty(&bo->shadow_list)) {
mutex_lock(&adev->shadow_list_lock);
list_del_init(&bo->shadow_list);
mutex_unlock(&adev->shadow_list_lock);
}
kfree(bo->metadata);
kfree(bo);
}
int amdgpu_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
{
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
unsigned asize = amdgpu_bo_size(bo);
int ret;
if (!vma->vm_file)
return -ENODEV;
if (adev == NULL)
return -ENODEV;
/* Check for valid size. */
if (asize < vma->vm_end - vma->vm_start)
return -EINVAL;
if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) ||
(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)) {
return -EPERM;
}
vma->vm_pgoff += amdgpu_bo_mmap_offset(bo) >> PAGE_SHIFT;
/* prime mmap does not need to check access, so allow here */
ret = drm_vma_node_allow(&obj->vma_node, vma->vm_file->private_data);
if (ret)
return ret;
ret = ttm_bo_mmap(vma->vm_file, vma, &adev->mman.bdev);
drm_vma_node_revoke(&obj->vma_node, vma->vm_file->private_data);
return ret;
}
static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
enum dma_data_direction direction)
{
struct amdgpu_bo *bo = gem_to_amdgpu_bo(dma_buf->priv);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
struct ttm_operation_ctx ctx = { true, false };
u32 domain = amdgpu_display_framebuffer_domains(adev);
int ret;
bool reads = (direction == DMA_BIDIRECTIONAL ||
direction == DMA_FROM_DEVICE);
if (!reads || !(domain & AMDGPU_GEM_DOMAIN_GTT))
return 0;
/* move to gtt */
ret = amdgpu_bo_reserve(bo, false);
if (unlikely(ret != 0))
return ret;
if (!bo->pin_count && (bo->allowed_domains & AMDGPU_GEM_DOMAIN_GTT)) {
amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
}
amdgpu_bo_unreserve(bo);
return ret;
}
/**
* amdgpu_bo_subtract_pin_size - Remove BO from pin_size accounting
*
* @bo: &amdgpu_bo buffer object
*
* This function is called when a BO stops being pinned, and updates the
* &amdgpu_device pin_size values accordingly.
*/
static void amdgpu_bo_subtract_pin_size(struct amdgpu_bo *bo)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size);
atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo),
&adev->visible_pin_size);
} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size);
}
}
static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
struct device *target_dev,
struct dma_buf_attachment *attach)
{
struct drm_gem_object *obj = dma_buf->priv;
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
long r;
r = drm_gem_map_attach(dma_buf, target_dev, attach);
if (r)
return r;
r = amdgpu_bo_reserve(bo, false);
if (unlikely(r != 0))
goto error_detach;
if (attach->dev->driver != adev->dev->driver) {
/*
* Wait for all shared fences to complete before we switch to future
* use of exclusive fence on this prime shared bo.
*/
r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
true, false,
MAX_SCHEDULE_TIMEOUT);
if (unlikely(r < 0)) {
DRM_DEBUG_PRIME("Fence wait failed: %li\n", r);
goto error_unreserve;
}
}
/* pin buffer into GTT */
r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
if (r)
goto error_unreserve;
if (attach->dev->driver != adev->dev->driver)
bo->prime_shared_count++;
error_unreserve:
amdgpu_bo_unreserve(bo);
error_detach:
if (r)
drm_gem_map_detach(dma_buf, attach);
return r;
}
static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
struct amdgpu_bo *bo;
bo = container_of(tbo, struct amdgpu_bo, tbo);
amdgpu_update_memory_usage(adev, &bo->tbo.mem, NULL);
drm_gem_object_release(&bo->gem_base);
amdgpu_bo_unref(&bo->parent);
if (!list_empty(&bo->shadow_list)) {
mutex_lock(&adev->shadow_list_lock);
list_del_init(&bo->shadow_list);
mutex_unlock(&adev->shadow_list_lock);
}
kfree(bo->metadata);
kfree(bo);
}
static void amdgpu_gem_map_detach(struct dma_buf *dma_buf,
struct dma_buf_attachment *attach)
{
struct drm_gem_object *obj = dma_buf->priv;
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
int ret = 0;
ret = amdgpu_bo_reserve(bo, true);
if (unlikely(ret != 0))
goto error;
amdgpu_bo_unpin(bo);
if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
bo->prime_shared_count--;
amdgpu_bo_unreserve(bo);
error:
drm_gem_map_detach(dma_buf, attach);
}
/**
* amdgpu_vram_mgr_new - allocate new ranges
*
* @man: TTM memory type manager
* @tbo: TTM BO we need this range for
* @place: placement flags and restrictions
* @mem: the resulting mem object
*
* Allocate VRAM for the given BO.
*/
static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
struct ttm_buffer_object *tbo,
const struct ttm_place *place,
struct ttm_mem_reg *mem)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
struct amdgpu_vram_mgr *mgr = man->priv;
struct drm_mm *mm = &mgr->mm;
struct drm_mm_node *nodes;
enum drm_mm_insert_mode mode;
unsigned long lpfn, num_nodes, pages_per_node, pages_left;
uint64_t usage = 0, vis_usage = 0;
unsigned i;
int r;
lpfn = place->lpfn;
if (!lpfn)
lpfn = man->size;
if (place->flags & TTM_PL_FLAG_CONTIGUOUS ||
amdgpu_vram_page_split == -1) {
pages_per_node = ~0ul;
num_nodes = 1;
} else {
pages_per_node = max((uint32_t)amdgpu_vram_page_split,
mem->page_alignment);
num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node);
}
nodes = kcalloc(num_nodes, sizeof(*nodes), GFP_KERNEL);
if (!nodes)
return -ENOMEM;
mode = DRM_MM_INSERT_BEST;
if (place->flags & TTM_PL_FLAG_TOPDOWN)
mode = DRM_MM_INSERT_HIGH;
mem->start = 0;
pages_left = mem->num_pages;
spin_lock(&mgr->lock);
for (i = 0; i < num_nodes; ++i) {
unsigned long pages = min(pages_left, pages_per_node);
uint32_t alignment = mem->page_alignment;
unsigned long start;
if (pages == pages_per_node)
alignment = pages_per_node;
r = drm_mm_insert_node_in_range(mm, &nodes[i],
pages, alignment, 0,
place->fpfn, lpfn,
mode);
if (unlikely(r))
goto error;
usage += nodes[i].size << PAGE_SHIFT;
vis_usage += amdgpu_vram_mgr_vis_size(adev, &nodes[i]);
/* Calculate a virtual BO start address to easily check if
* everything is CPU accessible.
*/
start = nodes[i].start + nodes[i].size;
if (start > mem->num_pages)
start -= mem->num_pages;
else
start = 0;
mem->start = max(mem->start, start);
pages_left -= pages;
}
spin_unlock(&mgr->lock);
atomic64_add(usage, &mgr->usage);
atomic64_add(vis_usage, &mgr->vis_usage);
mem->mm_node = nodes;
return 0;
error:
while (i--)
drm_mm_remove_node(&nodes[i]);
spin_unlock(&mgr->lock);
kfree(nodes);
return r == -ENOSPC ? 0 : r;
}
