RE: [Patch bpf-next v7 09/13] udp: implement ->read_sock() for sockmap

[John Fastabend <john.fastabend@gmail.com>]

Cong Wang wrote:
> From: Cong Wang <cong.wang@bytedance.com>
> 
> This is similar to tcp_read_sock(), except we do not need
> to worry about connections, we just need to retrieve skb
> from UDP receive queue.
> 
> Note, the return value of ->read_sock() is unused in
> sk_psock_verdict_data_ready().
> 
> Cc: John Fastabend <john.fastabend@gmail.com>
> Cc: Daniel Borkmann <daniel@iogearbox.net>
> Cc: Jakub Sitnicki <jakub@cloudflare.com>
> Cc: Lorenz Bauer <lmb@cloudflare.com>
> Signed-off-by: Cong Wang <cong.wang@bytedance.com>
> ---
>  include/net/udp.h   |  2 ++
>  net/ipv4/af_inet.c  |  1 +
>  net/ipv4/udp.c      | 35 +++++++++++++++++++++++++++++++++++
>  net/ipv6/af_inet6.c |  1 +
>  4 files changed, 39 insertions(+)
> 
> diff --git a/include/net/udp.h b/include/net/udp.h
> index df7cc1edc200..347b62a753c3 100644
> --- a/include/net/udp.h
> +++ b/include/net/udp.h
> @@ -329,6 +329,8 @@ struct sock *__udp6_lib_lookup(struct net *net,
>  			       struct sk_buff *skb);
>  struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
>  				 __be16 sport, __be16 dport);
> +int udp_read_sock(struct sock *sk, read_descriptor_t *desc,
> +		  sk_read_actor_t recv_actor);
>  
>  /* UDP uses skb->dev_scratch to cache as much information as possible and avoid
>   * possibly multiple cache miss on dequeue()
> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
> index 1355e6c0d567..f17870ee558b 100644
> --- a/net/ipv4/af_inet.c
> +++ b/net/ipv4/af_inet.c
> @@ -1070,6 +1070,7 @@ const struct proto_ops inet_dgram_ops = {
>  	.setsockopt	   = sock_common_setsockopt,
>  	.getsockopt	   = sock_common_getsockopt,
>  	.sendmsg	   = inet_sendmsg,
> +	.read_sock	   = udp_read_sock,
>  	.recvmsg	   = inet_recvmsg,
>  	.mmap		   = sock_no_mmap,
>  	.sendpage	   = inet_sendpage,
> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
> index 38952aaee3a1..04620e4d64ab 100644
> --- a/net/ipv4/udp.c
> +++ b/net/ipv4/udp.c
> @@ -1782,6 +1782,41 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
>  }
>  EXPORT_SYMBOL(__skb_recv_udp);
>  
> +int udp_read_sock(struct sock *sk, read_descriptor_t *desc,
> +		  sk_read_actor_t recv_actor)
> +{
> +	int copied = 0;
> +
> +	while (1) {
> +		int offset = 0, err;

Should this be

 int offset = sk_peek_offset()?

MSG_PEEK should work from recv side, at least it does on TCP side. If
its handled in some following patch a comment would be nice. I was
just reading udp_recvmsg() so maybe its not needed.

> +		struct sk_buff *skb;
> +
> +		skb = __skb_recv_udp(sk, 0, 1, &offset, &err);
> +		if (!skb)
> +			return err;
> +		if (offset < skb->len) {
> +			size_t len;
> +			int used;
> +
> +			len = skb->len - offset;
> +			used = recv_actor(desc, skb, offset, len);
> +			if (used <= 0) {
> +				if (!copied)
> +					copied = used;
> +				break;
> +			} else if (used <= len) {
> +				copied += used;
> +				offset += used;

The while loop is going to zero this? What are we trying to do
here with offset?

> +			}
> +		}
> +		if (!desc->count)
> +			break;
> +	}
> +
> +	return copied;
> +}
> +EXPORT_SYMBOL(udp_read_sock);
> +
>  /*
>   * 	This should be easy, if there is something there we
>   * 	return it, otherwise we block.
> diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
> index 802f5111805a..71de739b4a9e 100644
> --- a/net/ipv6/af_inet6.c
> +++ b/net/ipv6/af_inet6.c
> @@ -714,6 +714,7 @@ const struct proto_ops inet6_dgram_ops = {
>  	.getsockopt	   = sock_common_getsockopt,	/* ok		*/
>  	.sendmsg	   = inet6_sendmsg,		/* retpoline's sake */
>  	.recvmsg	   = inet6_recvmsg,		/* retpoline's sake */
> +	.read_sock	   = udp_read_sock,
>  	.mmap		   = sock_no_mmap,
>  	.sendpage	   = sock_no_sendpage,
>  	.set_peek_off	   = sk_set_peek_off,
> -- 
> 2.25.1
>