summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c83
1 files changed, 66 insertions, 17 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 8db880244324..abdc52b0895a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -24,13 +24,15 @@
#include <linux/dma-mapping.h>
#include <drm/ttm/ttm_range_manager.h>
+#include <drm/drm_drv.h>
#include "amdgpu.h"
#include "amdgpu_vm.h"
#include "amdgpu_res_cursor.h"
-#include "amdgpu_atomfirmware.h"
#include "atom.h"
+#define AMDGPU_MAX_SG_SEGMENT_SIZE (2UL << 30)
+
struct amdgpu_vram_reservation {
u64 start;
u64 size;
@@ -450,16 +452,18 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
{
struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
struct amdgpu_device *adev = to_amdgpu_device(mgr);
+ struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
u64 vis_usage = 0, max_bytes, min_block_size;
struct amdgpu_vram_mgr_resource *vres;
u64 size, remaining_size, lpfn, fpfn;
+ unsigned int adjust_dcc_size = 0;
struct drm_buddy *mm = &mgr->mm;
struct drm_buddy_block *block;
unsigned long pages_per_block;
int r;
lpfn = (u64)place->lpfn << PAGE_SHIFT;
- if (!lpfn)
+ if (!lpfn || lpfn > man->size)
lpfn = man->size;
fpfn = (u64)place->fpfn << PAGE_SHIFT;
@@ -468,7 +472,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
if (tbo->type != ttm_bo_type_kernel)
max_bytes -= AMDGPU_VM_RESERVED_VRAM;
- if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS) {
pages_per_block = ~0ul;
} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -477,7 +481,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
/* default to 2MB */
pages_per_block = 2UL << (20UL - PAGE_SHIFT);
#endif
- pages_per_block = max_t(uint32_t, pages_per_block,
+ pages_per_block = max_t(u32, pages_per_block,
tbo->page_alignment);
}
@@ -498,14 +502,29 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
if (place->flags & TTM_PL_FLAG_TOPDOWN)
vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
- if (place->flags & TTM_PL_FLAG_CONTIGUOUS)
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
vres->flags |= DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED)
+ vres->flags |= DRM_BUDDY_CLEAR_ALLOCATION;
+
if (fpfn || lpfn != mgr->mm.size)
/* Allocate blocks in desired range */
vres->flags |= DRM_BUDDY_RANGE_ALLOCATION;
+ if (bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC &&
+ adev->gmc.gmc_funcs->get_dcc_alignment)
+ adjust_dcc_size = amdgpu_gmc_get_dcc_alignment(adev);
+
remaining_size = (u64)vres->base.size;
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) {
+ unsigned int dcc_size;
+
+ dcc_size = roundup_pow_of_two(vres->base.size + adjust_dcc_size);
+ remaining_size = (u64)dcc_size;
+
+ vres->flags |= DRM_BUDDY_TRIM_DISABLE;
+ }
mutex_lock(&mgr->lock);
while (remaining_size) {
@@ -514,21 +533,32 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
else
min_block_size = mgr->default_page_size;
- BUG_ON(min_block_size < mm->chunk_size);
-
- /* Limit maximum size to 2GiB due to SG table limitations */
- size = min(remaining_size, 2ULL << 30);
+ size = remaining_size;
- if ((size >= (u64)pages_per_block << PAGE_SHIFT) &&
- !(size & (((u64)pages_per_block << PAGE_SHIFT) - 1)))
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size)
+ min_block_size = size;
+ else if ((size >= (u64)pages_per_block << PAGE_SHIFT) &&
+ !(size & (((u64)pages_per_block << PAGE_SHIFT) - 1)))
min_block_size = (u64)pages_per_block << PAGE_SHIFT;
+ BUG_ON(min_block_size < mm->chunk_size);
+
r = drm_buddy_alloc_blocks(mm, fpfn,
lpfn,
size,
min_block_size,
&vres->blocks,
vres->flags);
+
+ if (unlikely(r == -ENOSPC) && pages_per_block == ~0ul &&
+ !(place->flags & TTM_PL_FLAG_CONTIGUOUS)) {
+ vres->flags &= ~DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+ pages_per_block = max_t(u32, 2UL << (20UL - PAGE_SHIFT),
+ tbo->page_alignment);
+
+ continue;
+ }
+
if (unlikely(r))
goto error_free_blocks;
@@ -537,6 +567,22 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
else
remaining_size -= size;
}
+
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) {
+ struct drm_buddy_block *dcc_block;
+ unsigned long dcc_start;
+ u64 trim_start;
+
+ dcc_block = amdgpu_vram_mgr_first_block(&vres->blocks);
+ /* Adjust the start address for DCC buffers only */
+ dcc_start =
+ roundup((unsigned long)amdgpu_vram_mgr_block_start(dcc_block),
+ adjust_dcc_size);
+ trim_start = (u64)dcc_start;
+ drm_buddy_block_trim(mm, &trim_start,
+ (u64)vres->base.size,
+ &vres->blocks);
+ }
mutex_unlock(&mgr->lock);
vres->base.start = 0;
@@ -571,7 +617,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
return 0;
error_free_blocks:
- drm_buddy_free_list(mm, &vres->blocks);
+ drm_buddy_free_list(mm, &vres->blocks, 0);
mutex_unlock(&mgr->lock);
error_fini:
ttm_resource_fini(man, &vres->base);
@@ -604,7 +650,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
amdgpu_vram_mgr_do_reserve(man);
- drm_buddy_free_list(mm, &vres->blocks);
+ drm_buddy_free_list(mm, &vres->blocks, vres->flags);
mutex_unlock(&mgr->lock);
atomic64_sub(vis_usage, &mgr->vis_usage);
@@ -646,7 +692,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
amdgpu_res_first(res, offset, length, &cursor);
while (cursor.remaining) {
num_entries++;
- amdgpu_res_next(&cursor, cursor.size);
+ amdgpu_res_next(&cursor, min(cursor.size, AMDGPU_MAX_SG_SEGMENT_SIZE));
}
r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL);
@@ -666,7 +712,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
amdgpu_res_first(res, offset, length, &cursor);
for_each_sgtable_sg((*sgt), sg, i) {
phys_addr_t phys = cursor.start + adev->gmc.aper_base;
- size_t size = cursor.size;
+ unsigned long size = min(cursor.size, AMDGPU_MAX_SG_SEGMENT_SIZE);
dma_addr_t addr;
addr = dma_map_resource(dev, phys, size, dir,
@@ -679,7 +725,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
sg_dma_address(sg) = addr;
sg_dma_len(sg) = size;
- amdgpu_res_next(&cursor, cursor.size);
+ amdgpu_res_next(&cursor, size);
}
return 0;
@@ -862,6 +908,9 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
struct ttm_resource_manager *man = &mgr->manager;
int err;
+ man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", adev->gmc.real_vram_size);
+ if (IS_ERR(man->cg))
+ return PTR_ERR(man->cg);
ttm_resource_manager_init(man, &adev->mman.bdev,
adev->gmc.real_vram_size);
@@ -912,7 +961,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
kfree(rsv);
list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
- drm_buddy_free_list(&mgr->mm, &rsv->allocated);
+ drm_buddy_free_list(&mgr->mm, &rsv->allocated, 0);
kfree(rsv);
}
if (!adev->gmc.is_app_apu)
generated by cgit (git 2.34.1) at 2025-07-04 04:16:06 +0000