@@ -1158,7 +1158,7 @@ static int process_sync_pds_resv(struct amdkfd_process_info *process_info,
struct amdgpu_bo *pd = peer_vm->root.bo;
ret = amdgpu_sync_resv(NULL, sync, pd->tbo.base.resv,
- AMDGPU_SYNC_NE_OWNER,
+ AMDGPU_SYNC_NE_OWNER, AMDGPU_SYNC_NE_OWNER,
AMDGPU_FENCE_OWNER_KFD);
if (ret)
return ret;
@@ -675,7 +675,7 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
sync_mode = amdgpu_bo_explicit_sync(bo) ?
AMDGPU_SYNC_EXPLICIT : AMDGPU_SYNC_NE_OWNER;
r = amdgpu_sync_resv(p->adev, &p->job->sync, resv, sync_mode,
- &fpriv->vm);
+ AMDGPU_SYNC_EXPLICIT, &fpriv->vm);
if (r)
return r;
}
@@ -1410,7 +1410,8 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
*
* @adev: amdgpu device pointer
* @resv: reservation object to sync to
- * @sync_mode: synchronization mode
+ * @implicit_sync_mode: synchronization mode for usage <= DMA_RESV_USAGE_READ
+ * @explicit_sync_mode: synchronization mode for usage DMA_RESV_USAGE_BOOKKEEP
* @owner: fence owner
* @intr: Whether the wait is interruptible
*
@@ -1420,14 +1421,15 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
* 0 on success, errno otherwise.
*/
int amdgpu_bo_sync_wait_resv(struct amdgpu_device *adev, struct dma_resv *resv,
- enum amdgpu_sync_mode sync_mode, void *owner,
+ enum amdgpu_sync_mode implicit_sync_mode,
+ enum amdgpu_sync_mode explicit_sync_mode, void *owner,
bool intr)
{
struct amdgpu_sync sync;
int r;
amdgpu_sync_create(&sync);
- amdgpu_sync_resv(adev, &sync, resv, sync_mode, owner);
+ amdgpu_sync_resv(adev, &sync, resv, implicit_sync_mode, explicit_sync_mode, owner);
r = amdgpu_sync_wait(&sync, intr);
amdgpu_sync_free(&sync);
return r;
@@ -1448,7 +1450,8 @@ int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr)
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
return amdgpu_bo_sync_wait_resv(adev, bo->tbo.base.resv,
- AMDGPU_SYNC_NE_OWNER, owner, intr);
+ AMDGPU_SYNC_NE_OWNER, AMDGPU_SYNC_EXPLICIT,
+ owner, intr);
}
/**
@@ -320,7 +320,8 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
bool shared);
int amdgpu_bo_sync_wait_resv(struct amdgpu_device *adev, struct dma_resv *resv,
- enum amdgpu_sync_mode sync_mode, void *owner,
+ enum amdgpu_sync_mode implicit_sync_mode,
+ enum amdgpu_sync_mode explicit_sync_mode, void *owner,
bool intr);
int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr);
u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo);
@@ -225,14 +225,15 @@ static bool amdgpu_sync_test_fence(struct amdgpu_device *adev,
* @adev: amdgpu device
* @sync: sync object to add fences from reservation object to
* @resv: reservation object with embedded fence
- * @mode: how owner affects which fences we sync to
+ * @implicit_mode: how owner affects which fences with usage <= DMA_RESV_USAGE_READ we sync to
+ * @explicit_mode: how owner affects which fences with usage DMA_RESV_USAGE_BOOKKEEP we sync to
* @owner: owner of the planned job submission
*
* Sync to the fence
*/
int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
- struct dma_resv *resv, enum amdgpu_sync_mode mode,
- void *owner)
+ struct dma_resv *resv, enum amdgpu_sync_mode implicit_mode,
+ enum amdgpu_sync_mode explicit_mode, void *owner)
{
struct dma_resv_iter cursor;
struct dma_fence *f;
@@ -245,6 +246,10 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, f) {
dma_fence_chain_for_each(f, f) {
struct dma_fence *tmp = dma_fence_chain_contained(f);
+ enum amdgpu_sync_mode mode = implicit_mode;
+
+ if (dma_resv_iter_usage(&cursor) >= DMA_RESV_USAGE_BOOKKEEP)
+ mode = explicit_mode;
if (amdgpu_sync_test_fence(adev, mode, owner, tmp)) {
r = amdgpu_sync_fence(sync, f);
@@ -48,8 +48,8 @@ struct amdgpu_sync {
void amdgpu_sync_create(struct amdgpu_sync *sync);
int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f);
int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync,
- struct dma_resv *resv, enum amdgpu_sync_mode mode,
- void *owner);
+ struct dma_resv *resv, enum amdgpu_sync_mode implicit_mode,
+ enum amdgpu_sync_mode explicit_mode, void *owner);
struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
struct amdgpu_ring *ring);
struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync);
@@ -1978,6 +1978,7 @@ static int amdgpu_ttm_prepare_job(struct amdgpu_device *adev,
if (resv) {
r = amdgpu_sync_resv(adev, &(*job)->sync, resv,
AMDGPU_SYNC_ALWAYS,
+ AMDGPU_SYNC_EXPLICIT,
AMDGPU_FENCE_OWNER_UNDEFINED);
if (r) {
DRM_ERROR("sync failed (%d).\n", r);
@@ -1176,7 +1176,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
goto err_free;
} else {
r = amdgpu_sync_resv(adev, &job->sync, bo->tbo.base.resv,
- AMDGPU_SYNC_ALWAYS,
+ AMDGPU_SYNC_ALWAYS, AMDGPU_SYNC_ALWAYS,
AMDGPU_FENCE_OWNER_UNDEFINED);
if (r)
goto err_free;
@@ -51,7 +51,7 @@ static int amdgpu_vm_cpu_prepare(struct amdgpu_vm_update_params *p,
if (!resv)
return 0;
- return amdgpu_bo_sync_wait_resv(p->adev, resv, sync_mode, p->vm, true);
+ return amdgpu_bo_sync_wait_resv(p->adev, resv, sync_mode, sync_mode, p->vm, true);
}
/**
@@ -75,7 +75,7 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
if (!resv)
return 0;
- return amdgpu_sync_resv(p->adev, &p->job->sync, resv, sync_mode, p->vm);
+ return amdgpu_sync_resv(p->adev, &p->job->sync, resv, sync_mode, sync_mode, p->vm);
}
/**
To prep for allowing different sync modes in a follow-up patch. Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 11 +++++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 11 ++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 2 +- 10 files changed, 25 insertions(+), 15 deletions(-)