Message-ID: <676dd022d1388_1d346b2947@willemb.c.googlers.com.notmuch>
Date: Thu, 26 Dec 2024 16:52:34 -0500
From: Willem de Bruijn <willemdebruijn.kernel@...il.com>
To: Mina Almasry <almasrymina@...gle.com>, 
 netdev@...r.kernel.org, 
 linux-kernel@...r.kernel.org, 
 linux-doc@...r.kernel.org, 
 virtualization@...ts.linux.dev, 
 kvm@...r.kernel.org, 
 linux-kselftest@...r.kernel.org
Cc: Mina Almasry <almasrymina@...gle.com>, 
 "David S. Miller" <davem@...emloft.net>, 
 Eric Dumazet <edumazet@...gle.com>, 
 Jakub Kicinski <kuba@...nel.org>, 
 Paolo Abeni <pabeni@...hat.com>, 
 Simon Horman <horms@...nel.org>, 
 Donald Hunter <donald.hunter@...il.com>, 
 Jonathan Corbet <corbet@....net>, 
 Andrew Lunn <andrew+netdev@...n.ch>, 
 David Ahern <dsahern@...nel.org>, 
 "Michael S. Tsirkin" <mst@...hat.com>, 
 Jason Wang <jasowang@...hat.com>, 
 Xuan Zhuo <xuanzhuo@...ux.alibaba.com>, 
 Eugenio Pérez <eperezma@...hat.com>, 
 Stefan Hajnoczi <stefanha@...hat.com>, 
 Stefano Garzarella <sgarzare@...hat.com>, 
 Shuah Khan <shuah@...nel.org>, 
 Kaiyuan Zhang <kaiyuanz@...gle.com>, 
 Pavel Begunkov <asml.silence@...il.com>, 
 Willem de Bruijn <willemb@...gle.com>, 
 Samiullah Khawaja <skhawaja@...gle.com>, 
 Stanislav Fomichev <sdf@...ichev.me>, 
 Joe Damato <jdamato@...tly.com>, 
 dw@...idwei.uk
Subject: Re: [PATCH RFC net-next v1 5/5] net: devmem: Implement TX path

Mina Almasry wrote:
> Augment dmabuf binding to be able to handle TX. Additional to all the RX
> binding, we also create tx_vec and tx_iter needed for the TX path.
> 
> Provide API for sendmsg to be able to send dmabufs bound to this device:
> 
> - Provide a new dmabuf_tx_cmsg which includes the dmabuf to send from,
>   and the offset into the dmabuf to send from.
> - MSG_ZEROCOPY with SCM_DEVMEM_DMABUF cmsg indicates send from dma-buf.
> 
> Devmem is uncopyable, so piggyback off the existing MSG_ZEROCOPY
> implementation, while disabling instances where MSG_ZEROCOPY falls back
> to copying.
> 
> We additionally look up the dmabuf to send from by id, then pipe the
> binding down to the new zerocopy_fill_skb_from_devmem which fills a TX skb
> with net_iov netmems instead of the traditional page netmems.
> 
> We also special case skb_frag_dma_map to return the dma-address of these
> dmabuf net_iovs instead of attempting to map pages.
> 
> Based on work by Stanislav Fomichev <sdf@...ichev.me>. A lot of the meat
> of the implementation came from devmem TCP RFC v1[1], which included the
> TX path, but Stan did all the rebasing on top of netmem/net_iov.
> 
> Cc: Stanislav Fomichev <sdf@...ichev.me>
> Signed-off-by: Kaiyuan Zhang <kaiyuanz@...gle.com>
> Signed-off-by: Mina Almasry <almasrymina@...gle.com>
> 
> ---
>  include/linux/skbuff.h                  | 13 +++-
>  include/net/sock.h                      |  2 +
>  include/uapi/linux/uio.h                |  5 ++
>  net/core/datagram.c                     | 40 ++++++++++-
>  net/core/devmem.c                       | 91 +++++++++++++++++++++++--
>  net/core/devmem.h                       | 40 +++++++++--
>  net/core/netdev-genl.c                  | 65 +++++++++++++++++-
>  net/core/skbuff.c                       |  8 ++-
>  net/core/sock.c                         |  9 +++
>  net/ipv4/tcp.c                          | 36 +++++++---
>  net/vmw_vsock/virtio_transport_common.c |  4 +-
>  11 files changed, 281 insertions(+), 32 deletions(-)
> 

> +static int zerocopy_fill_skb_from_devmem(struct sk_buff *skb,
> +					 struct msghdr *msg,
> +					 struct iov_iter *from, int length)
> +{
> +	int i = skb_shinfo(skb)->nr_frags;
> +	int orig_length = length;
> +	netmem_ref netmem;
> +	size_t size;
> +
> +	while (length && iov_iter_count(from)) {
> +		if (i == MAX_SKB_FRAGS)
> +			return -EMSGSIZE;
> +
> +		size = min_t(size_t, iter_iov_len(from), length);
> +		if (!size)
> +			return -EFAULT;

On error, should caller skb_zerocopy_iter_stream rewind from, rather
than (or as well as) msg->msg_iter?
> +
> +		netmem = net_iov_to_netmem(iter_iov(from)->iov_base);
> +		get_netmem(netmem);
> +		skb_add_rx_frag_netmem(skb, i, netmem, from->iov_offset, size,
> +				       PAGE_SIZE);
> +
> +		iov_iter_advance(from, size);
> +		length -= size;
> +		i++;
> +	}
> +
> +	iov_iter_advance(&msg->msg_iter, orig_length);

What does this do if sendmsg is called with NULL as buffer?
> +
> +	return 0;
> +}
> +
>  int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
>  			    struct sk_buff *skb, struct iov_iter *from,
> -			    size_t length)
> +			    size_t length, bool is_devmem)
>  {
>  	unsigned long orig_size = skb->truesize;
>  	unsigned long truesize;
> @@ -702,6 +736,8 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
>  
>  	if (msg && msg->msg_ubuf && msg->sg_from_iter)
>  		ret = msg->sg_from_iter(skb, from, length);
> +	else if (unlikely(is_devmem))
> +		ret = zerocopy_fill_skb_from_devmem(skb, msg, from, length);
>  	else
>  		ret = zerocopy_fill_skb_from_iter(skb, from, length);
>  
> @@ -735,7 +771,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
>  	if (skb_copy_datagram_from_iter(skb, 0, from, copy))
>  		return -EFAULT;
>  
> -	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U);
> +	return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U, NULL);
>  }
>  EXPORT_SYMBOL(zerocopy_sg_from_iter);

>  struct net_iov *
>  net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
> @@ -109,6 +112,13 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
>  	unsigned long xa_idx;
>  	unsigned int rxq_idx;
>  
> +	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
> +
> +	/* Ensure no tx net_devmem_lookup_dmabuf() are in flight after the
> +	 * erase.
> +	 */
> +	synchronize_net();
> +

What precisely does this protect?

synchronize_net() ensures no packet is in flight inside an rcu
readside section. But a packet can still be in flight, such as posted
to the device or queued in a qdisc.

>  	if (binding->list.next)
>  		list_del(&binding->list);
>  
> @@ -122,8 +132,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
>  		WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx));
>  	}
>  
> -	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
> -
>  	net_devmem_dmabuf_binding_put(binding);
>  }
>  
> @@ -174,8 +182,9 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
>  }
>  
>  struct net_devmem_dmabuf_binding *
> -net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
> -		       struct netlink_ext_ack *extack)
> +net_devmem_bind_dmabuf(struct net_device *dev,
> +		       enum dma_data_direction direction,
> +		       unsigned int dmabuf_fd, struct netlink_ext_ack *extack)
>  {
>  	struct net_devmem_dmabuf_binding *binding;
>  	static u32 id_alloc_next;
> @@ -183,6 +192,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
>  	struct dma_buf *dmabuf;
>  	unsigned int sg_idx, i;
>  	unsigned long virtual;
> +	struct iovec *iov;
>  	int err;
>  
>  	dmabuf = dma_buf_get(dmabuf_fd);
> @@ -218,13 +228,19 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
>  	}
>  
>  	binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment,
> -						       DMA_FROM_DEVICE);
> +						       direction);
>  	if (IS_ERR(binding->sgt)) {
>  		err = PTR_ERR(binding->sgt);
>  		NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment");
>  		goto err_detach;
>  	}
>  
> +	if (!binding->sgt || binding->sgt->nents == 0) {
> +		err = -EINVAL;
> +		NL_SET_ERR_MSG(extack, "Empty dmabuf attachment");
> +		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...
> @@ -236,6 +252,19 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
>  		goto err_unmap;
>  	}
>  
> +	if (direction == DMA_TO_DEVICE) {
> +		virtual = 0;
> +		for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx)
> +			virtual += sg_dma_len(sg);
> +
> +		binding->tx_vec = kcalloc(virtual / PAGE_SIZE + 1,

instead of open coding this computation repeatedly, consider a local
variable. And parentheses and maybe round_up().

> +					  sizeof(struct iovec), GFP_KERNEL);
> +		if (!binding->tx_vec) {
> +			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);
> @@ -277,11 +306,21 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
>  			niov->owner = owner;
>  			page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
>  						      net_devmem_get_dma_addr(niov));
> +
> +			if (direction == DMA_TO_DEVICE) {
> +				iov = &binding->tx_vec[virtual / PAGE_SIZE + i];

why does this start counting at virtual / PAGE_SIZE, rather than 0?

> +				iov->iov_base = niov;
> +				iov->iov_len = PAGE_SIZE;
> +			}
>  		}
>  
>  		virtual += len;
>  	}
>  
> +	if (direction == DMA_TO_DEVICE)
> +		iov_iter_init(&binding->tx_iter, WRITE, binding->tx_vec,
> +			      virtual / PAGE_SIZE + 1, virtual);
> +
>  	return binding;
>  
>  err_free_chunks:
> @@ -302,6 +341,21 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
>  	return ERR_PTR(err);
>  }
>  
> +struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id)
> +{
> +	struct net_devmem_dmabuf_binding *binding;
> +
> +	rcu_read_lock();
> +	binding = xa_load(&net_devmem_dmabuf_bindings, id);
> +	if (binding) {
> +		if (!net_devmem_dmabuf_binding_get(binding))
> +			binding = NULL;
> +	}
> +	rcu_read_unlock();
> +
> +	return binding;
> +}
> +
>  void dev_dmabuf_uninstall(struct net_device *dev)
>  {
>  	struct net_devmem_dmabuf_binding *binding;
> @@ -332,6 +386,33 @@ void net_devmem_put_net_iov(struct net_iov *niov)
>  	net_devmem_dmabuf_binding_put(niov->owner->binding);
>  }
>  
> +struct net_devmem_dmabuf_binding *
> +net_devmem_get_sockc_binding(struct sock *sk, struct sockcm_cookie *sockc)
> +{
> +	struct net_devmem_dmabuf_binding *binding;
> +	int err = 0;
> +
> +	binding = net_devmem_lookup_dmabuf(sockc->dmabuf_id);

This lookup is from global xarray net_devmem_dmabuf_bindings.

Is there a check that the socket is sending out through the device
to which this dmabuf was bound with netlink? Should there be?
(e.g., SO_BINDTODEVICE).

> +	if (!binding || !binding->tx_vec) {
> +		err = -EINVAL;
> +		goto out_err;
> +	}
> +
> +	if (sock_net(sk) != dev_net(binding->dev)) {
> +		err = -ENODEV;
> +		goto out_err;
> +	}
> +
> +	iov_iter_advance(&binding->tx_iter, sockc->dmabuf_offset);
> +	return binding;
> +
> +out_err:
> +	if (binding)
> +		net_devmem_dmabuf_binding_put(binding);
> +
> +	return ERR_PTR(err);
> +}
> +
>  /*** "Dmabuf devmem memory provider" ***/
>  

> @@ -1063,6 +1064,15 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
>  
>  	flags = msg->msg_flags;
>  
> +	sockcm_init(&sockc, sk);
> +	if (msg->msg_controllen) {
> +		err = sock_cmsg_send(sk, msg, &sockc);
> +		if (unlikely(err)) {
> +			err = -EINVAL;
> +			goto out_err;
> +		}
> +	}
> +
>  	if ((flags & MSG_ZEROCOPY) && size) {
>  		if (msg->msg_ubuf) {
>  			uarg = msg->msg_ubuf;
> @@ -1080,6 +1090,15 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
>  			else
>  				uarg_to_msgzc(uarg)->zerocopy = 0;
>  		}
> +
> +		if (sockc.dmabuf_id != 0) {
> +			binding = net_devmem_get_sockc_binding(sk, &sockc);
> +			if (IS_ERR(binding)) {
> +				err = PTR_ERR(binding);
> +				binding = NULL;
> +				goto out_err;
> +			}
> +		}

Powered by blists - more mailing lists