This function allows to replace fences from the shared fence list when we can gurantee that the operation represented by the original fence has finished or no accesses to the resources protected by the dma_resv object any more when the new fence finishes.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 38 +++++++++++++++ .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 47 ++----------------- include/linux/dma-resv.h | 2 + 3 files changed, 44 insertions(+), 43 deletions(-)
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 49f3c1009821..5703e328b8ac 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -281,6 +281,44 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) } EXPORT_SYMBOL(dma_resv_add_shared_fence);
+/** + * dma_resv_replace_shared - replace shared fences + * @obj: the reservation object + * @context: the context of the fences to replace + * @fence: the new fence to use instead + * + * Replace fences with a specified context with a new fence. Only valid if the + * operation represented by the original fences is completed or has no longer + * access to the resources protected by the dma_resv object when the new fence + * completes. Takes the reference to the new fence. + */ +void dma_resv_replace_shared(struct dma_resv *obj, uint64_t context, + struct dma_fence *fence) +{ + struct dma_resv_list *list; + unsigned int i; + + list = dma_resv_shared(obj); + if (!list) { + dma_fence_put(fence); + return; + } + + write_seqcount_begin(&obj->seq); + for (i = 0; i < list->shared_count; ++i) { + struct dma_fence *old = dma_resv_list_fence(obj, list, i); + + if (old->context != context) + continue; + + rcu_assign_pointer(list->shared[i], dma_fence_get(fence)); + dma_fence_put(old); + } + write_seqcount_end(&obj->seq); + dma_fence_put(fence); +} +EXPORT_SYMBOL(dma_resv_replace_shared); + /** * dma_resv_add_excl_fence - Add an exclusive fence. * @obj: the reservation object diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 88da0e400406..3e5a681a5482 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -238,53 +238,14 @@ void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo) static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, struct amdgpu_amdkfd_fence *ef) { - struct dma_resv *resv = bo->tbo.base.resv; - struct dma_resv_list *old, *new; - unsigned int i, j, k; - if (!ef) return -EINVAL;
- old = dma_resv_shared(resv); - if (!old) - return 0; - - new = kmalloc(struct_size(new, shared, old->shared_max), GFP_KERNEL); - if (!new) - return -ENOMEM; - - /* Go through all the shared fences in the resevation object and sort - * the interesting ones to the end of the list. + /* TODO: Instead of block before we should use the fence of the page + * table update and TLB flush here directly. */ - for (i = 0, j = old->shared_count, k = 0; i < old->shared_count; ++i) { - struct dma_fence *f; - - f = rcu_dereference_protected(old->shared[i], - dma_resv_held(resv)); - - if (f->context == ef->base.context) - RCU_INIT_POINTER(new->shared[--j], f); - else - RCU_INIT_POINTER(new->shared[k++], f); - } - new->shared_max = old->shared_max; - new->shared_count = k; - - /* Install the new fence list, seqcount provides the barriers */ - write_seqcount_begin(&resv->seq); - RCU_INIT_POINTER(resv->fence, new); - write_seqcount_end(&resv->seq); - - /* Drop the references to the removed fences or move them to ef_list */ - for (i = j, k = 0; i < old->shared_count; ++i) { - struct dma_fence *f; - - f = rcu_dereference_protected(new->shared[i], - dma_resv_held(resv)); - dma_fence_put(f); - } - kfree_rcu(old, rcu); - + dma_resv_replace_shared(bo->tbo.base.resv, ef->base.context, + dma_fence_get_stub()); return 0; }
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 98ac66fecb71..74b217b82f39 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -268,6 +268,8 @@ void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); +void dma_resv_replace_shared(struct dma_resv *obj, uint64_t context, + struct dma_fence *fence);
void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence);