diff options
author | Jakub Kicinski <kuba@kernel.org> | 2023-05-26 05:56:10 +0300 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2023-05-26 05:57:39 +0300 |
commit | d4031ec844bc52fe7f2f844e9c476727fd6b8240 (patch) | |
tree | b350f90348c94ccd6e6d5dcd31ad371e3486e177 /net/ipv4/tcp_bpf.c | |
parent | 657d42cf5df64d9f32caab73ba2d2284879a37b0 (diff) | |
parent | ad42a35bdfc6d3c0fc4cb4027d7b2757ce665665 (diff) | |
download | linux-d4031ec844bc52fe7f2f844e9c476727fd6b8240.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR.
Conflicts:
net/ipv4/raw.c
3632679d9e4f ("ipv{4,6}/raw: fix output xfrm lookup wrt protocol")
c85be08fc4fa ("raw: Stop using RTO_ONLINK.")
https://lore.kernel.org/all/20230525110037.2b532b83@canb.auug.org.au/
Adjacent changes:
drivers/net/ethernet/freescale/fec_main.c
9025944fddfe ("net: fec: add dma_wmb to ensure correct descriptor values")
144470c88c5d ("net: fec: using the standard return codes when xdp xmit errors")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/ipv4/tcp_bpf.c')
-rw-r--r-- | net/ipv4/tcp_bpf.c | 79 |
1 files changed, 78 insertions, 1 deletions
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 0291d15acd19..e75023ea052f 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -11,6 +11,24 @@ #include <net/inet_common.h> #include <net/tls.h> +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tcp; + int copied; + + if (!skb || !skb->len || !sk_is_tcp(sk)) + return; + + if (skb_bpf_strparser(skb)) + return; + + tcp = tcp_sk(sk); + copied = tcp->copied_seq + skb->len; + WRITE_ONCE(tcp->copied_seq, copied); + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, skb->len); +} + static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -178,14 +196,34 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, return ret; } +static bool is_next_msg_fin(struct sk_psock *psock) +{ + struct scatterlist *sge; + struct sk_msg *msg_rx; + int i; + + msg_rx = sk_psock_peek_msg(psock); + i = msg_rx->sg.start; + sge = sk_msg_elem(msg_rx, i); + if (!sge->length) { + struct sk_buff *skb = msg_rx->skb; + + if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + return true; + } + return false; +} + static int tcp_bpf_recvmsg_parser(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { + struct tcp_sock *tcp = tcp_sk(sk); + u32 seq = tcp->copied_seq; struct sk_psock *psock; - int copied; + int copied = 0; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -198,8 +236,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return tcp_recvmsg(sk, msg, len, flags, addr_len); lock_sock(sk); + + /* We may have received data on the sk_receive_queue pre-accept and + * then we can not use read_skb in this context because we haven't + * assigned a sk_socket yet so have no link to the ops. The work-around + * is to check the sk_receive_queue and in these cases read skbs off + * queue again. The read_skb hook is not running at this point because + * of lock_sock so we avoid having multiple runners in read_skb. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + tcp_data_ready(sk); + /* This handles the ENOMEM errors if we both receive data + * pre accept and are already under memory pressure. At least + * let user know to retry. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + copied = -EAGAIN; + goto out; + } + } + msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); + /* The typical case for EFAULT is the socket was gracefully + * shutdown with a FIN pkt. So check here the other case is + * some error on copy_page_to_iter which would be unexpected. + * On fin return correct return code to zero. + */ + if (copied == -EFAULT) { + bool is_fin = is_next_msg_fin(psock); + + if (is_fin) { + copied = 0; + seq++; + goto out; + } + } + seq += copied; if (!copied) { long timeo; int data; @@ -237,6 +310,10 @@ msg_bytes_ready: copied = -EAGAIN; } out: + WRITE_ONCE(tcp->copied_seq, seq); + tcp_rcv_space_adjust(sk); + if (copied > 0) + __tcp_cleanup_rbuf(sk, copied); release_sock(sk); sk_psock_put(sk, psock); return copied; |