diff options
| author | Cong Wang <cong.wang@bytedance.com> | 2022-06-15 09:20:12 -0700 |
|---|---|---|
| committer | Daniel Borkmann <daniel@iogearbox.net> | 2022-06-20 14:05:52 +0200 |
| commit | 965b57b469a589d64d81b1688b38dcb537011bb0 (patch) | |
| tree | 968209ff361fc86f0f49071cf4817c65e21d10aa /net/ipv4 | |
| parent | 04919bed948dc22a0032a9da867b7dcb8aece4ca (diff) | |
| download | linux-next-965b57b469a589d64d81b1688b38dcb537011bb0.tar.gz | |
net: Introduce a new proto_ops ->read_skb()
Currently both splice() and sockmap use ->read_sock() to
read skb from receive queue, but for sockmap we only read
one entire skb at a time, so ->read_sock() is too conservative
to use. Introduce a new proto_ops ->read_skb() which supports
this sematic, with this we can finally pass the ownership of
skb to recv actors.
For non-TCP protocols, all ->read_sock() can be simply
converted to ->read_skb().
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220615162014.89193-3-xiyou.wangcong@gmail.com
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/af_inet.c | 3 | ||||
| -rw-r--r-- | net/ipv4/tcp.c | 9 | ||||
| -rw-r--r-- | net/ipv4/udp.c | 10 |
3 files changed, 9 insertions, 13 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index da81f56fdd1c..7abd652a558f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1040,6 +1040,7 @@ const struct proto_ops inet_stream_ops = { .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, + .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, .peek_len = tcp_peek_len, @@ -1067,7 +1068,7 @@ const struct proto_ops inet_dgram_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .read_sock = udp_read_sock, + .read_skb = udp_read_skb, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 124f384f8695..9d2fd3ced21b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1734,8 +1734,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, } EXPORT_SYMBOL(tcp_read_sock); -int tcp_read_skb(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor) +int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; @@ -1750,7 +1749,7 @@ int tcp_read_skb(struct sock *sk, read_descriptor_t *desc, int used; __skb_unlink(skb, &sk->sk_receive_queue); - used = recv_actor(desc, skb, 0, skb->len); + used = recv_actor(sk, skb); if (used <= 0) { if (!copied) copied = used; @@ -1765,9 +1764,7 @@ int tcp_read_skb(struct sock *sk, read_descriptor_t *desc, break; } consume_skb(skb); - if (!desc->count) - break; - WRITE_ONCE(tp->copied_seq, seq); + break; } WRITE_ONCE(tp->copied_seq, seq); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6172b4750a88..c660b0bc4d14 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1797,8 +1797,7 @@ busy_check: } EXPORT_SYMBOL(__skb_recv_udp); -int udp_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor) +int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { int copied = 0; @@ -1820,7 +1819,7 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc, continue; } - used = recv_actor(desc, skb, 0, skb->len); + used = recv_actor(sk, skb); if (used <= 0) { if (!copied) copied = used; @@ -1831,13 +1830,12 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc, } kfree_skb(skb); - if (!desc->count) - break; + break; } return copied; } -EXPORT_SYMBOL(udp_read_sock); +EXPORT_SYMBOL(udp_read_skb); /* * This should be easy, if there is something there we |