[PATCH v8 4/5] RDMA/mlx5: Support dma-buf based userspace memory region

[Jason Gunthorpe]

On Thu, Nov 05, 2020 at 02:48:08PM -0800, Jianxin Xiong wrote:
> @@ -966,7 +969,10 @@ static struct mlx5_ib_mr *alloc_mr_from_cache(struct ib_pd *pd,
>  	struct mlx5_ib_mr *mr;
>  	unsigned int page_size;
>  
> -	page_size = mlx5_umem_find_best_pgsz(umem, mkc, log_page_size, 0, iova);
> +	if (umem->is_dmabuf)
> +		page_size = ib_umem_find_best_pgsz(umem, PAGE_SIZE, iova);

You said the sgl is not set here, why doesn't this crash? It is
certainly wrong to call this function without a SGL.

> +/**
> + * mlx5_ib_fence_dmabuf_mr - Stop all access to the dmabuf MR
> + * @mr: to fence
> + *
> + * On return no parallel threads will be touching this MR and no DMA will be
> + * active.
> + */
> +void mlx5_ib_fence_dmabuf_mr(struct mlx5_ib_mr *mr)
> +{
> +	struct ib_umem_dmabuf *umem_dmabuf = to_ib_umem_dmabuf(mr->umem);
> +
> +	/* Prevent new page faults and prefetch requests from succeeding */
> +	xa_erase(&mr->dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key));
> +
> +	/* Wait for all running page-fault handlers to finish. */
> +	synchronize_srcu(&mr->dev->odp_srcu);
> +
> +	wait_event(mr->q_deferred_work, !atomic_read(&mr->num_deferred_work));
> +
> +	dma_resv_lock(umem_dmabuf->attach->dmabuf->resv, NULL);
> +	mlx5_mr_cache_invalidate(mr);
> +	umem_dmabuf->private = NULL;
> +	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
> +
> +	if (!mr->cache_ent) {
> +		mlx5_core_destroy_mkey(mr->dev->mdev, &mr->mmkey);
> +		WARN_ON(mr->descs);
> +	}
> +}

I would expect this to call ib_umem_dmabuf_unmap_pages() ?

Who calls it on the dereg path?

This looks quite strange to me, it calls ib_umem_dmabuf_unmap_pages()
only from the invalidate callback?

I feel uneasy how this seems to assume everything works sanely, we can
have parallel page faults so pagefault_dmabuf_mr() can be called
multiple times after an invalidation, and it doesn't protect itself
against calling ib_umem_dmabuf_map_pages() twice.

Perhaps the umem code should keep track of the current map state and
exit if there is already a sgl. NULL or not NULL sgl would do and
seems quite reasonable.

> @@ -810,22 +871,31 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt,
>  			u32 *bytes_mapped, u32 flags)
>  {
>  	struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
> +	struct ib_umem_dmabuf *umem_dmabuf = to_ib_umem_dmabuf(mr->umem);
>  
>  	lockdep_assert_held(&mr->dev->odp_srcu);
>  	if (unlikely(io_virt < mr->mmkey.iova))
>  		return -EFAULT;
>  
> -	if (!odp->is_implicit_odp) {
> +	if (is_dmabuf_mr(mr) || !odp->is_implicit_odp) {
>  		u64 user_va;
> +		u64 end;
>  
>  		if (check_add_overflow(io_virt - mr->mmkey.iova,
> -				       (u64)odp->umem.address, &user_va))
> +				       (u64)mr->umem->address, &user_va))
>  			return -EFAULT;
> -		if (unlikely(user_va >= ib_umem_end(odp) ||
> -			     ib_umem_end(odp) - user_va < bcnt))
> +		if (is_dmabuf_mr(mr))
> +			end = mr->umem->address + mr->umem->length;
> +		else
> +			end = ib_umem_end(odp);
> +		if (unlikely(user_va >= end || end - user_va < bcnt))
>  			return -EFAULT;
> -		return pagefault_real_mr(mr, odp, user_va, bcnt, bytes_mapped,
> -					 flags);
> +		if (is_dmabuf_mr(mr))
> +			return pagefault_dmabuf_mr(mr, umem_dmabuf, user_va,
> +						   bcnt, bytes_mapped, flags);

But this doesn't care about user_va or bcnt it just triggers the whole
thing to be remapped, so why calculate it?

Jason