Am 11.12.23 um 08:31 schrieb Arunpravin Paneer Selvam:
Add clear page support in vram memory region.
v1:(Christian)
- Dont handle clear page as TTM flag since when moving the BO back
in from GTT again we don't need that.
- Make a specialized version of amdgpu_fill_buffer() which only
clears the VRAM areas which are not already cleared
- Drop the TTM_PL_FLAG_WIPE_ON_RELEASE check in
amdgpu_object.c
v2:
- Modify the function name amdgpu_ttm_* (Alex)
- Drop the delayed parameter (Christian)
- handle amdgpu_res_cleared(&cursor) just above the size
calculation (Christian)
- Use AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE for clearing the buffers
in the free path to properly wait for fences etc.. (Christian)
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@xxxxxxx>
Suggested-by: Christian König <christian.koenig@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 16 +++---
.../gpu/drm/amd/amdgpu/amdgpu_res_cursor.h | 25 +++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 53 +++++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 3 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 15 +++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h | 5 ++
6 files changed, 109 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index cef920a93924..5a01b6266772 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -39,6 +39,7 @@
#include "amdgpu.h"
#include "amdgpu_trace.h"
#include "amdgpu_amdkfd.h"
+#include "amdgpu_vram_mgr.h"
/**
* DOC: amdgpu_object
@@ -598,8 +599,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
if (!amdgpu_bo_support_uswc(bo->flags))
bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
- if (adev->ras_enabled)
- bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
+ bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
bo->tbo.bdev = &adev->mman.bdev;
if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA |
@@ -629,15 +629,17 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
if (bp->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
bo->tbo.resource->mem_type == TTM_PL_VRAM) {
- struct dma_fence *fence;
+ struct dma_fence *fence = NULL;
- r = amdgpu_fill_buffer(bo, 0, bo->tbo.base.resv, &fence, true);
+ r = amdgpu_ttm_clear_buffer(bo, bo->tbo.base.resv, &fence);
if (unlikely(r))
goto fail_unreserve;
- dma_resv_add_fence(bo->tbo.base.resv, fence,
- DMA_RESV_USAGE_KERNEL);
- dma_fence_put(fence);
+ if (fence) {
+ dma_resv_add_fence(bo->tbo.base.resv, fence,
+ DMA_RESV_USAGE_KERNEL);
+ dma_fence_put(fence);
+ }
}
if (!bp->resv)
amdgpu_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
index 381101d2bf05..50fcd86e1033 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
@@ -164,4 +164,29 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
}
}
+/**
+ * amdgpu_res_cleared - check if blocks are cleared
+ *
+ * @cur: the cursor to extract the block
+ *
+ * Check if the @cur block is cleared
+ */
+static inline bool amdgpu_res_cleared(struct amdgpu_res_cursor *cur)
+{
+ struct drm_buddy_block *block;
+
+ switch (cur->mem_type) {
+ case TTM_PL_VRAM:
+ block = cur->node;
+
+ if (!amdgpu_vram_mgr_is_cleared(block))
+ return false;
+ break;
+ default:
+ return false;
+ }
+
+ return true;
+}
+
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 05991c5c8ddb..252b384194c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2222,6 +2222,59 @@ static int amdgpu_ttm_fill_mem(struct amdgpu_ring *ring, uint32_t src_data,
return 0;
}
+int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
+ struct dma_resv *resv,
+ struct dma_fence **fence)
+{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+ struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
+ struct amdgpu_res_cursor cursor;
+ struct dma_fence *f = NULL;
+ u64 addr;
+ int r;
+
+ if (!adev->mman.buffer_funcs_enabled)
+ return -EINVAL;
+
+ amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor);
+
+ mutex_lock(&adev->mman.gtt_window_lock);
+ while (cursor.remaining) {
+ struct dma_fence *next = NULL;
+ u64 size;
+
+ if (!amdgpu_res_cleared(&cursor)) {
That test here is now inverted. You need to remove the !
+ amdgpu_res_next(&cursor, cursor.size);
+ continue;
+ }
+
+ /* Never clear more than 256MiB at once to avoid timeouts */
+ size = min(cursor.size, 256ULL << 20);
+
+ r = amdgpu_ttm_map_buffer(&bo->tbo, bo->tbo.resource, &cursor,
+ 1, ring, false, &size, &addr);
+ if (r)
+ goto err;
+
+ r = amdgpu_ttm_fill_mem(ring, 0, addr, size, resv,
+ &next, true, true);
+ if (r)
+ goto err;
+
+ dma_fence_put(f);
+ f = next;
+
+ amdgpu_res_next(&cursor, size);
+ }
+err:
+ mutex_unlock(&adev->mman.gtt_window_lock);
+ if (fence)
+ *fence = dma_fence_get(f);
+ dma_fence_put(f);
+
+ return r;
+}
+
int amdgpu_fill_buffer(struct amdgpu_bo *bo,
uint32_t src_data,
struct dma_resv *resv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 65ec82141a8e..cf77489a7adb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -155,6 +155,9 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
uint64_t size, bool tmz,
struct dma_resv *resv,
struct dma_fence **f);
+int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
+ struct dma_resv *resv,
+ struct dma_fence **fence);
int amdgpu_fill_buffer(struct amdgpu_bo *bo,
uint32_t src_data,
struct dma_resv *resv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index d0e199cc8f17..f3d36c345b63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -435,6 +435,7 @@ 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;
@@ -486,6 +487,9 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
if (place->flags & TTM_PL_FLAG_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;
@@ -579,7 +583,9 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res);
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(res->bo);
struct drm_buddy *mm = &mgr->mm;
+ struct dma_fence *fence = NULL;
struct drm_buddy_block *block;
uint64_t vis_usage = 0;
@@ -589,7 +595,14 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
amdgpu_vram_mgr_do_reserve(man);
- drm_buddy_free_list(mm, &vres->blocks, 0);
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) {
+ if (!amdgpu_fill_buffer(bo, 0, NULL, &fence, true)) {
+ vres->flags |= DRM_BUDDY_CLEARED;
+ dma_fence_put(fence);
+ }
+ }
Please completely drop that chunk.
AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE should already be handled elsewhere.
What you might want to do is to change the
AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE handling to set the
DRM_BUDDY_CLEARED flag.
That might be much cleaner and could potentially also handle the case
where we can't execute the AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE flag
because the engine isn't ready.
Regards,
Christian.
+
+ drm_buddy_free_list(mm, &vres->blocks, vres->flags);
mutex_unlock(&mgr->lock);
atomic64_sub(vis_usage, &mgr->vis_usage);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
index 0e04e42cf809..8478522d7366 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
@@ -53,6 +53,11 @@ static inline u64 amdgpu_vram_mgr_block_size(struct drm_buddy_block *block)
return (u64)PAGE_SIZE << drm_buddy_block_order(block);
}
+static inline bool amdgpu_vram_mgr_is_cleared(struct drm_buddy_block *block)
+{
+ return drm_buddy_block_is_clear(block);
+}
+
static inline struct amdgpu_vram_mgr_resource *
to_amdgpu_vram_mgr_resource(struct ttm_resource *res)
{
