aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_object.c63
1 files changed, 41 insertions, 22 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 010b0cb7693c9..8d8c39be61295 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
@@ -153,8 +154,10 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
else
places[c].flags |= TTM_PL_FLAG_TOPDOWN;
- if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
+ if (abo->tbo.type == ttm_bo_type_kernel &&
+ flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
places[c].flags |= TTM_PL_FLAG_CONTIGUOUS;
+
c++;
}
@@ -173,6 +176,12 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
abo->flags & AMDGPU_GEM_CREATE_PREEMPTIBLE ?
AMDGPU_PL_PREEMPT : TTM_PL_TT;
places[c].flags = 0;
+ /*
+ * When GTT is just an alternative to VRAM make sure that we
+ * only use it as fallback and still try to fill up VRAM first.
+ */
+ if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
+ places[c].flags |= TTM_PL_FLAG_FALLBACK;
c++;
}
@@ -595,8 +604,7 @@ 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 |
@@ -605,6 +613,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
else
amdgpu_bo_placement_from_domain(bo, bp->domain);
if (bp->type == ttm_bo_type_kernel)
+ bo->tbo.priority = 2;
+ else if (!(bp->flags & AMDGPU_GEM_CREATE_DISCARDABLE))
bo->tbo.priority = 1;
if (!bp->destroy)
@@ -617,8 +627,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
return r;
if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
- bo->tbo.resource->mem_type == TTM_PL_VRAM &&
- amdgpu_bo_in_cpu_visible_vram(bo))
+ amdgpu_res_cpu_visible(adev, bo->tbo.resource))
amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
ctx.bytes_moved);
else
@@ -628,7 +637,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
bo->tbo.resource->mem_type == TTM_PL_VRAM) {
struct dma_fence *fence;
- 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;
@@ -758,7 +767,7 @@ int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence)
return amdgpu_copy_buffer(ring, shadow_addr, parent_addr,
amdgpu_bo_size(shadow), NULL, fence,
- true, false, false);
+ true, false, 0);
}
/**
@@ -960,6 +969,10 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
if (!bo->placements[i].lpfn ||
(lpfn && lpfn < bo->placements[i].lpfn))
bo->placements[i].lpfn = lpfn;
+
+ if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS &&
+ bo->placements[i].mem_type == TTM_PL_VRAM)
+ bo->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS;
}
r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
@@ -1242,14 +1255,18 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
* amdgpu_bo_move_notify - notification about a memory move
* @bo: pointer to a buffer object
* @evict: if this move is evicting the buffer from the graphics address space
+ * @new_mem: new resource for backing the BO
*
* Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
* bookkeeping.
* TTM driver callback which is called when ttm moves a buffer.
*/
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+ bool evict,
+ struct ttm_resource *new_mem)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
+ struct ttm_resource *old_mem = bo->resource;
struct amdgpu_bo *abo;
if (!amdgpu_bo_is_amdgpu_bo(bo))
@@ -1261,34 +1278,36 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
amdgpu_bo_kunmap(abo);
if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach &&
- bo->resource->mem_type != TTM_PL_SYSTEM)
+ old_mem && old_mem->mem_type != TTM_PL_SYSTEM)
dma_buf_move_notify(abo->tbo.base.dma_buf);
- /* remember the eviction */
- if (evict)
- atomic64_inc(&adev->num_evictions);
+ /* move_notify is called before move happens */
+ trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1,
+ old_mem ? old_mem->mem_type : -1);
}
void amdgpu_bo_get_memory(struct amdgpu_bo *bo,
struct amdgpu_mem_stats *stats)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+ struct ttm_resource *res = bo->tbo.resource;
uint64_t size = amdgpu_bo_size(bo);
struct drm_gem_object *obj;
unsigned int domain;
bool shared;
/* Abort if the BO doesn't currently have a backing store */
- if (!bo->tbo.resource)
+ if (!res)
return;
obj = &bo->tbo.base;
shared = drm_gem_object_is_shared_for_memory_stats(obj);
- domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type);
+ domain = amdgpu_mem_type_to_domain(res->mem_type);
switch (domain) {
case AMDGPU_GEM_DOMAIN_VRAM:
stats->vram += size;
- if (amdgpu_bo_in_cpu_visible_vram(bo))
+ if (amdgpu_res_cpu_visible(adev, bo->tbo.resource))
stats->visible_vram += size;
if (shared)
stats->vram_shared += size;
@@ -1359,8 +1378,9 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv)))
return;
- r = amdgpu_fill_buffer(abo, AMDGPU_POISON, bo->base.resv, &fence, true);
+ r = amdgpu_fill_buffer(abo, 0, bo->base.resv, &fence, true);
if (!WARN_ON(r)) {
+ amdgpu_vram_mgr_set_cleared(bo->resource);
amdgpu_bo_fence(abo, fence, false);
dma_fence_put(fence);
}
@@ -1389,10 +1409,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
/* Remember that this BO was accessed by the CPU */
abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
- if (bo->resource->mem_type != TTM_PL_VRAM)
- return 0;
-
- if (amdgpu_bo_in_cpu_visible_vram(abo))
+ if (amdgpu_res_cpu_visible(adev, bo->resource))
return 0;
/* Can't move a pinned BO to visible VRAM */
@@ -1415,7 +1432,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
/* this should never happen */
if (bo->resource->mem_type == TTM_PL_VRAM &&
- !amdgpu_bo_in_cpu_visible_vram(abo))
+ !amdgpu_res_cpu_visible(adev, bo->resource))
return VM_FAULT_SIGBUS;
ttm_bo_move_to_lru_tail_unlocked(bo);
@@ -1579,6 +1596,7 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev,
*/
u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
struct dma_buf_attachment *attachment;
struct dma_buf *dma_buf;
const char *placement;
@@ -1587,10 +1605,11 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m)
if (dma_resv_trylock(bo->tbo.base.resv)) {
unsigned int domain;
+
domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type);
switch (domain) {
case AMDGPU_GEM_DOMAIN_VRAM:
- if (amdgpu_bo_in_cpu_visible_vram(bo))
+ if (amdgpu_res_cpu_visible(adev, bo->tbo.resource))
placement = "VRAM VISIBLE";
else
placement = "VRAM";
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-19 23:26:58 +0000