mirror of https://gitee.com/openkylin/linux.git
drm/radeon: track memory statistics about VRAM and GTT usage and buffer moves v2
The statistics are: - VRAM usage in bytes - GTT usage in bytes - number of bytes moved by TTM The last one is actually a counter, so you need to sample it before and after command submission and take the difference. This is useful for finding performance bottlenecks. Userspace queries are also added. v2: use atomic64_t Signed-off-by: Marek Olšák <marek.olsak@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
This commit is contained in:
parent
bda72d58a2
commit
67e8e3f970
|
@ -2309,6 +2309,10 @@ struct radeon_device {
|
|||
/* virtual memory */
|
||||
struct radeon_vm_manager vm_manager;
|
||||
struct mutex gpu_clock_mutex;
|
||||
/* memory stats */
|
||||
atomic64_t vram_usage;
|
||||
atomic64_t gtt_usage;
|
||||
atomic64_t num_bytes_moved;
|
||||
/* ACPI interface */
|
||||
struct radeon_atif atif;
|
||||
struct radeon_atcs atcs;
|
||||
|
|
|
@ -486,6 +486,21 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file
|
|||
case RADEON_INFO_VCE_FB_VERSION:
|
||||
*value = rdev->vce.fb_version;
|
||||
break;
|
||||
case RADEON_INFO_NUM_BYTES_MOVED:
|
||||
value = (uint32_t*)&value64;
|
||||
value_size = sizeof(uint64_t);
|
||||
value64 = atomic64_read(&rdev->num_bytes_moved);
|
||||
break;
|
||||
case RADEON_INFO_VRAM_USAGE:
|
||||
value = (uint32_t*)&value64;
|
||||
value_size = sizeof(uint64_t);
|
||||
value64 = atomic64_read(&rdev->vram_usage);
|
||||
break;
|
||||
case RADEON_INFO_GTT_USAGE:
|
||||
value = (uint32_t*)&value64;
|
||||
value_size = sizeof(uint64_t);
|
||||
value64 = atomic64_read(&rdev->gtt_usage);
|
||||
break;
|
||||
default:
|
||||
DRM_DEBUG_KMS("Invalid request %d\n", info->request);
|
||||
return -EINVAL;
|
||||
|
|
|
@ -56,11 +56,36 @@ static void radeon_bo_clear_va(struct radeon_bo *bo)
|
|||
}
|
||||
}
|
||||
|
||||
static void radeon_update_memory_usage(struct radeon_bo *bo,
|
||||
unsigned mem_type, int sign)
|
||||
{
|
||||
struct radeon_device *rdev = bo->rdev;
|
||||
u64 size = (u64)bo->tbo.num_pages << PAGE_SHIFT;
|
||||
|
||||
switch (mem_type) {
|
||||
case TTM_PL_TT:
|
||||
if (sign > 0)
|
||||
atomic64_add(size, &rdev->gtt_usage);
|
||||
else
|
||||
atomic64_sub(size, &rdev->gtt_usage);
|
||||
break;
|
||||
case TTM_PL_VRAM:
|
||||
if (sign > 0)
|
||||
atomic64_add(size, &rdev->vram_usage);
|
||||
else
|
||||
atomic64_sub(size, &rdev->vram_usage);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
|
||||
{
|
||||
struct radeon_bo *bo;
|
||||
|
||||
bo = container_of(tbo, struct radeon_bo, tbo);
|
||||
|
||||
radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1);
|
||||
|
||||
mutex_lock(&bo->rdev->gem.mutex);
|
||||
list_del_init(&bo->list);
|
||||
mutex_unlock(&bo->rdev->gem.mutex);
|
||||
|
@ -567,14 +592,23 @@ int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
|
|||
}
|
||||
|
||||
void radeon_bo_move_notify(struct ttm_buffer_object *bo,
|
||||
struct ttm_mem_reg *mem)
|
||||
struct ttm_mem_reg *new_mem)
|
||||
{
|
||||
struct radeon_bo *rbo;
|
||||
|
||||
if (!radeon_ttm_bo_is_radeon_bo(bo))
|
||||
return;
|
||||
|
||||
rbo = container_of(bo, struct radeon_bo, tbo);
|
||||
radeon_bo_check_tiling(rbo, 0, 1);
|
||||
radeon_vm_bo_invalidate(rbo->rdev, rbo);
|
||||
|
||||
/* update statistics */
|
||||
if (!new_mem)
|
||||
return;
|
||||
|
||||
radeon_update_memory_usage(rbo, bo->mem.mem_type, -1);
|
||||
radeon_update_memory_usage(rbo, new_mem->mem_type, 1);
|
||||
}
|
||||
|
||||
int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
|
||||
|
|
|
@ -151,7 +151,7 @@ extern void radeon_bo_get_tiling_flags(struct radeon_bo *bo,
|
|||
extern int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
|
||||
bool force_drop);
|
||||
extern void radeon_bo_move_notify(struct ttm_buffer_object *bo,
|
||||
struct ttm_mem_reg *mem);
|
||||
struct ttm_mem_reg *new_mem);
|
||||
extern int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
|
||||
extern int radeon_bo_get_surface_reg(struct radeon_bo *bo);
|
||||
|
||||
|
|
|
@ -406,8 +406,14 @@ static int radeon_bo_move(struct ttm_buffer_object *bo,
|
|||
if (r) {
|
||||
memcpy:
|
||||
r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
|
||||
if (r) {
|
||||
return r;
|
||||
}
|
||||
}
|
||||
return r;
|
||||
|
||||
/* update statistics */
|
||||
atomic64_add((u64)bo->num_pages << PAGE_SHIFT, &rdev->num_bytes_moved);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
|
||||
|
|
|
@ -1004,6 +1004,9 @@ struct drm_radeon_cs {
|
|||
#define RADEON_INFO_VCE_FW_VERSION 0x1b
|
||||
/* version of VCE feedback */
|
||||
#define RADEON_INFO_VCE_FB_VERSION 0x1c
|
||||
#define RADEON_INFO_NUM_BYTES_MOVED 0x1d
|
||||
#define RADEON_INFO_VRAM_USAGE 0x1e
|
||||
#define RADEON_INFO_GTT_USAGE 0x1f
|
||||
|
||||
|
||||
struct drm_radeon_info {
|
||||
|
|
Loading…
Reference in New Issue