diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 28 |
1 files changed, 22 insertions, 6 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index dbb551762805..69e105fa41f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -109,14 +109,22 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p, if (p->unlocked) { struct dma_fence *tmp = dma_fence_get(f); - swap(p->vm->last_unlocked, f); + swap(p->vm->last_unlocked, tmp); dma_fence_put(tmp); } else { - amdgpu_bo_fence(p->vm->root.bo, f, true); + dma_resv_add_fence(p->vm->root.bo->tbo.base.resv, f, + DMA_RESV_USAGE_BOOKKEEP); } - if (fence && !p->immediate) + if (fence && !p->immediate) { + /* + * Most hw generations now have a separate queue for page table + * updates, but when the queue is shared with userspace we need + * the extra CPU round trip to correctly flush the TLB. + */ + set_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &f->flags); swap(*fence, f); + } dma_fence_put(f); return 0; @@ -204,14 +212,22 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, struct amdgpu_bo *bo = &vmbo->bo; enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE : AMDGPU_IB_POOL_DELAYED; + struct dma_resv_iter cursor; unsigned int i, ndw, nptes; + struct dma_fence *fence; uint64_t *pte; int r; /* Wait for PD/PT moves to be completed */ - r = amdgpu_sync_fence(&p->job->sync, bo->tbo.moving); - if (r) - return r; + dma_resv_iter_begin(&cursor, bo->tbo.base.resv, DMA_RESV_USAGE_KERNEL); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + r = amdgpu_sync_fence(&p->job->sync, fence); + if (r) { + dma_resv_iter_end(&cursor); + return r; + } + } + dma_resv_iter_end(&cursor); do { ndw = p->num_dw_left; |