drm/amdgpu: move vram usage tracking into the vram manager v2
Looks like a better place for this. v2: use atomic64_t members instead Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
parent
9255d77d8c
commit
3c848bb38a
|
@ -1482,8 +1482,6 @@ struct amdgpu_device {
|
|||
struct amdgpu_mman mman;
|
||||
struct amdgpu_vram_scratch vram_scratch;
|
||||
struct amdgpu_wb wb;
|
||||
atomic64_t vram_usage;
|
||||
atomic64_t vram_vis_usage;
|
||||
atomic64_t num_bytes_moved;
|
||||
atomic64_t num_evictions;
|
||||
atomic64_t num_vram_cpu_page_faults;
|
||||
|
|
|
@ -246,7 +246,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
|
|||
}
|
||||
|
||||
total_vram = adev->mc.real_vram_size - adev->vram_pin_size;
|
||||
used_vram = atomic64_read(&adev->vram_usage);
|
||||
used_vram = amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
|
||||
free_vram = used_vram >= total_vram ? 0 : total_vram - used_vram;
|
||||
|
||||
spin_lock(&adev->mm_stats.lock);
|
||||
|
@ -292,7 +292,8 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
|
|||
/* Do the same for visible VRAM if half of it is free */
|
||||
if (adev->mc.visible_vram_size < adev->mc.real_vram_size) {
|
||||
u64 total_vis_vram = adev->mc.visible_vram_size;
|
||||
u64 used_vis_vram = atomic64_read(&adev->vram_vis_usage);
|
||||
u64 used_vis_vram =
|
||||
amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
|
||||
|
||||
if (used_vis_vram < total_vis_vram) {
|
||||
u64 free_vis_vram = total_vis_vram - used_vis_vram;
|
||||
|
|
|
@ -455,10 +455,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
|
|||
ui64 = atomic64_read(&adev->num_vram_cpu_page_faults);
|
||||
return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
|
||||
case AMDGPU_INFO_VRAM_USAGE:
|
||||
ui64 = atomic64_read(&adev->vram_usage);
|
||||
ui64 = amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
|
||||
return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
|
||||
case AMDGPU_INFO_VIS_VRAM_USAGE:
|
||||
ui64 = atomic64_read(&adev->vram_vis_usage);
|
||||
ui64 = amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
|
||||
return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0;
|
||||
case AMDGPU_INFO_GTT_USAGE:
|
||||
ui64 = amdgpu_gtt_mgr_usage(&adev->mman.bdev.man[TTM_PL_TT]);
|
||||
|
@ -497,7 +497,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
|
|||
mem.vram.total_heap_size = adev->mc.real_vram_size;
|
||||
mem.vram.usable_heap_size =
|
||||
adev->mc.real_vram_size - adev->vram_pin_size;
|
||||
mem.vram.heap_usage = atomic64_read(&adev->vram_usage);
|
||||
mem.vram.heap_usage =
|
||||
amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
|
||||
mem.vram.max_allocation = mem.vram.usable_heap_size * 3 / 4;
|
||||
|
||||
mem.cpu_accessible_vram.total_heap_size =
|
||||
|
@ -506,7 +507,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
|
|||
adev->mc.visible_vram_size -
|
||||
(adev->vram_pin_size - adev->invisible_pin_size);
|
||||
mem.cpu_accessible_vram.heap_usage =
|
||||
atomic64_read(&adev->vram_vis_usage);
|
||||
amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
|
||||
mem.cpu_accessible_vram.max_allocation =
|
||||
mem.cpu_accessible_vram.usable_heap_size * 3 / 4;
|
||||
|
||||
|
|
|
@ -37,53 +37,6 @@
|
|||
#include "amdgpu.h"
|
||||
#include "amdgpu_trace.h"
|
||||
|
||||
|
||||
|
||||
static u64 amdgpu_get_vis_part_size(struct amdgpu_device *adev,
|
||||
struct ttm_mem_reg *mem)
|
||||
{
|
||||
if (mem->start << PAGE_SHIFT >= adev->mc.visible_vram_size)
|
||||
return 0;
|
||||
|
||||
return ((mem->start << PAGE_SHIFT) + mem->size) >
|
||||
adev->mc.visible_vram_size ?
|
||||
adev->mc.visible_vram_size - (mem->start << PAGE_SHIFT) :
|
||||
mem->size;
|
||||
}
|
||||
|
||||
static void amdgpu_update_memory_usage(struct amdgpu_device *adev,
|
||||
struct ttm_mem_reg *old_mem,
|
||||
struct ttm_mem_reg *new_mem)
|
||||
{
|
||||
u64 vis_size;
|
||||
if (!adev)
|
||||
return;
|
||||
|
||||
if (new_mem) {
|
||||
switch (new_mem->mem_type) {
|
||||
case TTM_PL_TT:
|
||||
break;
|
||||
case TTM_PL_VRAM:
|
||||
atomic64_add(new_mem->size, &adev->vram_usage);
|
||||
vis_size = amdgpu_get_vis_part_size(adev, new_mem);
|
||||
atomic64_add(vis_size, &adev->vram_vis_usage);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (old_mem) {
|
||||
switch (old_mem->mem_type) {
|
||||
case TTM_PL_TT:
|
||||
break;
|
||||
case TTM_PL_VRAM:
|
||||
atomic64_sub(old_mem->size, &adev->vram_usage);
|
||||
vis_size = amdgpu_get_vis_part_size(adev, old_mem);
|
||||
atomic64_sub(vis_size, &adev->vram_vis_usage);
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
|
||||
{
|
||||
struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
|
||||
|
@ -92,7 +45,6 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
|
|||
bo = container_of(tbo, struct amdgpu_bo, tbo);
|
||||
|
||||
amdgpu_bo_kunmap(bo);
|
||||
amdgpu_update_memory_usage(adev, &bo->tbo.mem, NULL);
|
||||
|
||||
drm_gem_object_release(&bo->gem_base);
|
||||
amdgpu_bo_unref(&bo->parent);
|
||||
|
@ -990,8 +942,6 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
|
|||
return;
|
||||
|
||||
/* move_notify is called before move happens */
|
||||
amdgpu_update_memory_usage(adev, &bo->mem, new_mem);
|
||||
|
||||
trace_amdgpu_ttm_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
|
||||
}
|
||||
|
||||
|
|
|
@ -68,6 +68,9 @@ int amdgpu_gtt_mgr_alloc(struct ttm_mem_type_manager *man,
|
|||
struct ttm_mem_reg *mem);
|
||||
uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
|
||||
|
||||
uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
|
||||
uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
|
||||
|
||||
int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
|
||||
uint64_t dst_offset, uint32_t byte_count,
|
||||
struct reservation_object *resv,
|
||||
|
|
|
@ -28,6 +28,8 @@
|
|||
struct amdgpu_vram_mgr {
|
||||
struct drm_mm mm;
|
||||
spinlock_t lock;
|
||||
atomic64_t usage;
|
||||
atomic64_t vis_usage;
|
||||
};
|
||||
|
||||
/**
|
||||
|
@ -78,6 +80,27 @@ static int amdgpu_vram_mgr_fini(struct ttm_mem_type_manager *man)
|
|||
return 0;
|
||||
}
|
||||
|
||||
/**
|
||||
* amdgpu_vram_mgr_vis_size - Calculate visible node size
|
||||
*
|
||||
* @adev: amdgpu device structure
|
||||
* @node: MM node structure
|
||||
*
|
||||
* Calculate how many bytes of the MM node are inside visible VRAM
|
||||
*/
|
||||
static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
|
||||
struct drm_mm_node *node)
|
||||
{
|
||||
uint64_t start = node->start << PAGE_SHIFT;
|
||||
uint64_t end = (node->size + node->start) << PAGE_SHIFT;
|
||||
|
||||
if (start >= adev->mc.visible_vram_size)
|
||||
return 0;
|
||||
|
||||
return (end > adev->mc.visible_vram_size ?
|
||||
adev->mc.visible_vram_size : end) - start;
|
||||
}
|
||||
|
||||
/**
|
||||
* amdgpu_vram_mgr_new - allocate new ranges
|
||||
*
|
||||
|
@ -93,11 +116,13 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
|
|||
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;
|
||||
|
||||
|
@ -142,6 +167,9 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
|
|||
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.
|
||||
*/
|
||||
|
@ -155,6 +183,9 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
|
|||
}
|
||||
spin_unlock(&mgr->lock);
|
||||
|
||||
atomic64_add(usage, &mgr->usage);
|
||||
atomic64_add(vis_usage, &mgr->vis_usage);
|
||||
|
||||
mem->mm_node = nodes;
|
||||
|
||||
return 0;
|
||||
|
@ -181,8 +212,10 @@ error:
|
|||
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)
|
||||
|
@ -192,14 +225,47 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
|
|||
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;
|
||||
}
|
||||
|
||||
/**
|
||||
* amdgpu_vram_mgr_usage - how many bytes are used in this domain
|
||||
*
|
||||
* @man: TTM memory type manager
|
||||
*
|
||||
* Returns how many bytes are used in this domain.
|
||||
*/
|
||||
uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man)
|
||||
{
|
||||
struct amdgpu_vram_mgr *mgr = man->priv;
|
||||
|
||||
return atomic64_read(&mgr->usage);
|
||||
}
|
||||
|
||||
/**
|
||||
* amdgpu_vram_mgr_vis_usage - how many bytes are used in the visible part
|
||||
*
|
||||
* @man: TTM memory type manager
|
||||
*
|
||||
* Returns how many bytes are used in the visible part of VRAM
|
||||
*/
|
||||
uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man)
|
||||
{
|
||||
struct amdgpu_vram_mgr *mgr = man->priv;
|
||||
|
||||
return atomic64_read(&mgr->vis_usage);
|
||||
}
|
||||
|
||||
/**
|
||||
* amdgpu_vram_mgr_debug - dump VRAM table
|
||||
*
|
||||
|
@ -211,7 +277,6 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
|
|||
static void amdgpu_vram_mgr_debug(struct ttm_mem_type_manager *man,
|
||||
struct drm_printer *printer)
|
||||
{
|
||||
struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
|
||||
struct amdgpu_vram_mgr *mgr = man->priv;
|
||||
|
||||
spin_lock(&mgr->lock);
|
||||
|
@ -219,9 +284,8 @@ static void amdgpu_vram_mgr_debug(struct ttm_mem_type_manager *man,
|
|||
spin_unlock(&mgr->lock);
|
||||
|
||||
drm_printf(printer, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n",
|
||||
adev->mman.bdev.man[TTM_PL_VRAM].size,
|
||||
(u64)atomic64_read(&adev->vram_usage) >> 20,
|
||||
(u64)atomic64_read(&adev->vram_vis_usage) >> 20);
|
||||
man->size, amdgpu_vram_mgr_usage(man) >> 20,
|
||||
amdgpu_vram_mgr_vis_usage(man) >> 20);
|
||||
}
|
||||
|
||||
const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func = {
|
||||
|
|
Loading…
Reference in New Issue