Re: [RFC PATCH v3 04/12] netdev: support binding dma-buf to netdevice

From: Paolo Abeni <pabeni@redhat.com>
To: Mina Almasry <almasrymina@google.com>,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-arch@vger.kernel.org, linux-kselftest@vger.kernel.org,
	linux-media@vger.kernel.org, dri-devel@lists.freedesktop.org,
	linaro-mm-sig@lists.linaro.org
Cc: "David S. Miller" <davem@davemloft.net>,
	"Eric Dumazet" <edumazet@google.com>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"Jesper Dangaard Brouer" <hawk@kernel.org>,
	"Ilias Apalodimas" <ilias.apalodimas@linaro.org>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"David Ahern" <dsahern@kernel.org>,
	"Willem de Bruijn" <willemdebruijn.kernel@gmail.com>,
	"Shuah Khan" <shuah@kernel.org>,
	"Sumit Semwal" <sumit.semwal@linaro.org>,
	"Christian König" <christian.koenig@amd.com>,
	"Shakeel Butt" <shakeelb@google.com>,
	"Jeroen de Borst" <jeroendb@google.com>,
	"Praveen Kaligineedi" <pkaligineedi@google.com>,
	"Willem de Bruijn" <willemb@google.com>,
	"Kaiyuan Zhang" <kaiyuanz@google.com>
Subject: Re: [RFC PATCH v3 04/12] netdev: support binding dma-buf to netdevice
Date: Thu, 09 Nov 2023 09:29:54 +0100	[thread overview]
Message-ID: <076fa6505f3e1c79cc8acdf9903809fad6c2fd31.camel@redhat.com> (raw)
In-Reply-To: <20231106024413.2801438-5-almasrymina@google.com>

On Sun, 2023-11-05 at 18:44 -0800, Mina Almasry wrote:
[...]
> +int netdev_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
> +		       struct netdev_dmabuf_binding **out)
> +{
> +	struct netdev_dmabuf_binding *binding;
> +	struct scatterlist *sg;
> +	struct dma_buf *dmabuf;
> +	unsigned int sg_idx, i;
> +	unsigned long virtual;
> +	int err;
> +
> +	if (!capable(CAP_NET_ADMIN))
> +		return -EPERM;
> +
> +	dmabuf = dma_buf_get(dmabuf_fd);
> +	if (IS_ERR_OR_NULL(dmabuf))
> +		return -EBADFD;
> +
> +	binding = kzalloc_node(sizeof(*binding), GFP_KERNEL,
> +			       dev_to_node(&dev->dev));
> +	if (!binding) {
> +		err = -ENOMEM;
> +		goto err_put_dmabuf;
> +	}
> +
> +	xa_init_flags(&binding->bound_rxq_list, XA_FLAGS_ALLOC);
> +
> +	refcount_set(&binding->ref, 1);
> +
> +	binding->dmabuf = dmabuf;
> +
> +	binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent);
> +	if (IS_ERR(binding->attachment)) {
> +		err = PTR_ERR(binding->attachment);
> +		goto err_free_binding;
> +	}
> +
> +	binding->sgt = dma_buf_map_attachment(binding->attachment,
> +					      DMA_BIDIRECTIONAL);
> +	if (IS_ERR(binding->sgt)) {
> +		err = PTR_ERR(binding->sgt);
> +		goto err_detach;
> +	}
> +
> +	/* For simplicity we expect to make PAGE_SIZE allocations, but the
> +	 * binding can be much more flexible than that. We may be able to
> +	 * allocate MTU sized chunks here. Leave that for future work...
> +	 */
> +	binding->chunk_pool = gen_pool_create(PAGE_SHIFT,
> +					      dev_to_node(&dev->dev));
> +	if (!binding->chunk_pool) {
> +		err = -ENOMEM;
> +		goto err_unmap;
> +	}
> +
> +	virtual = 0;
> +	for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx) {
> +		dma_addr_t dma_addr = sg_dma_address(sg);
> +		struct dmabuf_genpool_chunk_owner *owner;
> +		size_t len = sg_dma_len(sg);
> +		struct page_pool_iov *ppiov;
> +
> +		owner = kzalloc_node(sizeof(*owner), GFP_KERNEL,
> +				     dev_to_node(&dev->dev));
> +		owner->base_virtual = virtual;
> +		owner->base_dma_addr = dma_addr;
> +		owner->num_ppiovs = len / PAGE_SIZE;
> +		owner->binding = binding;
> +
> +		err = gen_pool_add_owner(binding->chunk_pool, dma_addr,
> +					 dma_addr, len, dev_to_node(&dev->dev),
> +					 owner);
> +		if (err) {
> +			err = -EINVAL;
> +			goto err_free_chunks;
> +		}
> +
> +		owner->ppiovs = kvmalloc_array(owner->num_ppiovs,
> +					       sizeof(*owner->ppiovs),
> +					       GFP_KERNEL);
> +		if (!owner->ppiovs) {
> +			err = -ENOMEM;
> +			goto err_free_chunks;
> +		}
> +
> +		for (i = 0; i < owner->num_ppiovs; i++) {
> +			ppiov = &owner->ppiovs[i];
> +			ppiov->owner = owner;
> +			refcount_set(&ppiov->refcount, 1);
> +		}
> +
> +		dma_addr += len;

I'm trying to wrap my head around the whole infra... the above line is
confusing. Why do you increment dma_addr? it will be re-initialized in
the next iteration.

Cheers,

Paolo