Re: [PATCH net-next v3 5/6] net: devmem: Implement TX path

[Willem de Bruijn]

Mina Almasry wrote:
> Augment dmabuf binding to be able to handle TX. Additional to all the RX
> binding, we also create tx_vec 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.
> - 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 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@xxxxxxxxxxx>. 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@xxxxxxxxxxx>
> Signed-off-by: Kaiyuan Zhang <kaiyuanz@xxxxxxxxxx>
> Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
> 
> 
> ---
> 
> v3:
> - Use kvmalloc_array instead of kcalloc (Stan).
> - Fix unreachable code warning (Simon).
> 
> v2:
> - Remove dmabuf_offset from the dmabuf cmsg.
> - Update zerocopy_fill_skb_from_devmem to interpret the
>   iov_base/iter_iov_addr as the offset into the dmabuf to send from
>   (Stan).
> - Remove the confusing binding->tx_iter which is not needed if we
>   interpret the iov_base/iter_iov_addr as offset into the dmabuf (Stan).
> - Remove check for binding->sgt and binding->sgt->nents in dmabuf
>   binding.
> - Simplify the calculation of binding->tx_vec.
> - Check in net_devmem_get_binding that the binding we're returning
>   has ifindex matching the sending socket (Willem).
> ---
>  include/linux/skbuff.h                  | 15 +++-
>  include/net/sock.h                      |  1 +
>  include/uapi/linux/uio.h                |  6 +-
>  net/core/datagram.c                     | 41 ++++++++++-
>  net/core/devmem.c                       | 97 +++++++++++++++++++++++--
>  net/core/devmem.h                       | 42 ++++++++++-
>  net/core/netdev-genl.c                  | 64 +++++++++++++++-
>  net/core/skbuff.c                       |  6 +-
>  net/core/sock.c                         |  8 ++
>  net/ipv4/tcp.c                          | 36 ++++++---
>  net/vmw_vsock/virtio_transport_common.c |  3 +-
>  11 files changed, 285 insertions(+), 34 deletions(-)
> 
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index bb2b751d274a..3ff8f568c382 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -1711,9 +1711,12 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
>  
>  void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
>  
> +struct net_devmem_dmabuf_binding;
> +
>  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,
> +			    struct net_devmem_dmabuf_binding *binding);
>  
>  int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
>  				struct iov_iter *from, size_t length);
> @@ -1721,12 +1724,14 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
>  static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
>  					  struct msghdr *msg, int len)
>  {
> -	return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len);
> +	return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len,
> +				       NULL);
>  }
>  
>  int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
>  			     struct msghdr *msg, int len,
> -			     struct ubuf_info *uarg);
> +			     struct ubuf_info *uarg,
> +			     struct net_devmem_dmabuf_binding *binding);
>  
>  /* Internal */
>  #define skb_shinfo(SKB)	((struct skb_shared_info *)(skb_end_pointer(SKB)))
> @@ -3697,6 +3702,10 @@ static inline dma_addr_t __skb_frag_dma_map(struct device *dev,
>  					    size_t offset, size_t size,
>  					    enum dma_data_direction dir)
>  {
> +	if (skb_frag_is_net_iov(frag)) {
> +		return netmem_to_net_iov(frag->netmem)->dma_addr + offset +
> +		       frag->offset;
> +	}
>  	return dma_map_page(dev, skb_frag_page(frag),
>  			    skb_frag_off(frag) + offset, size, dir);
>  }
> diff --git a/include/net/sock.h b/include/net/sock.h
> index 8036b3b79cd8..09eb918525b6 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -1822,6 +1822,7 @@ struct sockcm_cookie {
>  	u32 tsflags;
>  	u32 ts_opt_id;
>  	u32 priority;
> +	u32 dmabuf_id;
>  };
>  
>  static inline void sockcm_init(struct sockcm_cookie *sockc,
> diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
> index 649739e0c404..866bd5dfe39f 100644
> --- a/include/uapi/linux/uio.h
> +++ b/include/uapi/linux/uio.h
> @@ -38,10 +38,14 @@ struct dmabuf_token {
>  	__u32 token_count;
>  };
>  
> +struct dmabuf_tx_cmsg {
> +	__u32 dmabuf_id;
> +};
> +

Why a wrapper struct instead of just __u32?