On Mon, Mar 21, 2022 at 02:58:34PM +0100, Christian König wrote:
> 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.
>
> Then use this function in the amdkfd code when BOs are unmapped from the
> process.
>
> v2: add an example when this is usefull.
Yeah this makes a looooot more sense now :-)
Reviewed-by: Daniel Vetter <daniel.vetter@xxxxxxxx>
>
> Signed-off-by: Christian König <christian.koenig@xxxxxxx>
> ---
> drivers/dma-buf/dma-resv.c | 45 +++++++++++++++++
> .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 49 +++----------------
> include/linux/dma-resv.h | 2 +
> 3 files changed, 54 insertions(+), 42 deletions(-)
>
> diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
> index b51416405e86..509060861cf3 100644
> --- a/drivers/dma-buf/dma-resv.c
> +++ b/drivers/dma-buf/dma-resv.c
> @@ -289,6 +289,51 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence)
> }
> EXPORT_SYMBOL(dma_resv_add_shared_fence);
>
> +/**
> + * dma_resv_replace_fences - replace fences in the dma_resv obj
> + * @obj: the reservation object
> + * @context: the context of the fences to replace
> + * @replacement: 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 fence has no longer access to the
> + * resources represented by the dma_resv object when the new fence completes.
> + *
> + * And example for using this is replacing a preemption fence with a page table
> + * update fence which makes the resource inaccessible.
> + */
> +void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context,
> + struct dma_fence *replacement)
> +{
> + struct dma_resv_list *list;
> + struct dma_fence *old;
> + unsigned int i;
> +
> + dma_resv_assert_held(obj);
> +
> + write_seqcount_begin(&obj->seq);
> +
> + old = dma_resv_excl_fence(obj);
> + if (old->context == context) {
> + RCU_INIT_POINTER(obj->fence_excl, dma_fence_get(replacement));
> + dma_fence_put(old);
> + }
> +
> + list = dma_resv_shared_list(obj);
> + for (i = 0; list && i < list->shared_count; ++i) {
> + old = rcu_dereference_protected(list->shared[i],
> + dma_resv_held(obj));
> + if (old->context != context)
> + continue;
> +
> + rcu_assign_pointer(list->shared[i], dma_fence_get(replacement));
> + dma_fence_put(old);
> + }
> +
> + write_seqcount_end(&obj->seq);
> +}
> +EXPORT_SYMBOL(dma_resv_replace_fences);
> +
> /**
> * 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 f9bab963a948..b6f266f612ea 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -253,53 +253,18 @@ void amdgpu_amdkfd_release_notify(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;
> + struct dma_fence *replacement;
>
> if (!ef)
> return -EINVAL;
>
> - old = dma_resv_shared_list(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; 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);
> -
> + replacement = dma_fence_get_stub();
> + dma_resv_replace_fences(bo->tbo.base.resv, ef->base.context,
> + replacement);
> + dma_fence_put(replacement);
> return 0;
> }
>
> diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
> index afdfdfac729f..3f53177bdb46 100644
> --- a/include/linux/dma-resv.h
> +++ b/include/linux/dma-resv.h
> @@ -468,6 +468,8 @@ 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_fences(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);
> int dma_resv_get_fences(struct dma_resv *obj, bool write,
> unsigned int *num_fences, struct dma_fence ***fences);
> --
> 2.25.1
>
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
