From 8a59f9d1e3d4340659fdfee8879dc09a6f2546e1 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 30 Mar 2021 19:32:31 -0700 Subject: sock: Introduce sk->sk_prot->psock_update_sk_prot() Currently sockmap calls into each protocol to update the struct proto and replace it. This certainly won't work when the protocol is implemented as a module, for example, AF_UNIX. Introduce a new ops sk->sk_prot->psock_update_sk_prot(), so each protocol can implement its own way to replace the struct proto. This also helps get rid of symbol dependencies on CONFIG_INET. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210331023237.41094-11-xiyou.wangcong@gmail.com --- include/net/sock.h | 3 +++ include/net/tcp.h | 1 + include/net/udp.h | 1 + 3 files changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 0b6266fd6bf6..8b4155e756c2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1184,6 +1184,9 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); +#ifdef CONFIG_BPF_SYSCALL + int (*psock_update_sk_prot)(struct sock *sk, bool restore); +#endif /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS diff --git a/include/net/tcp.h b/include/net/tcp.h index 075de26f449d..2efa4e5ea23d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2203,6 +2203,7 @@ struct sk_psock; #ifdef CONFIG_BPF_SYSCALL struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); +int tcp_bpf_update_proto(struct sock *sk, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ diff --git a/include/net/udp.h b/include/net/udp.h index d4d064c59232..df7cc1edc200 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -518,6 +518,7 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, #ifdef CONFIG_BPF_SYSCALL struct sk_psock; struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); +int udp_bpf_update_proto(struct sock *sk, bool restore); #endif #endif /* _UDP_H */ -- cgit v1.3-14-g43fede From d7f571188ecf25c244789b883c878ec7c64b5b08 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 30 Mar 2021 19:32:32 -0700 Subject: udp: Implement ->read_sock() for sockmap 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(), and UDP still does not support splice() due to lack of ->splice_read(), so users can not reach udp_read_sock() directly. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210331023237.41094-12-xiyou.wangcong@gmail.com --- include/net/udp.h | 2 ++ net/ipv4/af_inet.c | 1 + net/ipv4/udp.c | 29 +++++++++++++++++++++++++++++ net/ipv6/af_inet6.c | 1 + 4 files changed, 33 insertions(+) (limited to 'include/net') 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..4d02f6839e38 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1782,6 +1782,35 @@ 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 copied = 0; + + while (1) { + struct sk_buff *skb; + int err, used; + + skb = skb_recv_udp(sk, 0, 1, &err); + if (!skb) + return err; + used = recv_actor(desc, skb, 0, skb->len); + if (used <= 0) { + if (!copied) + copied = used; + break; + } else if (used <= skb->len) { + copied += used; + } + + 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, -- cgit v1.3-14-g43fede From 2bc793e3272a13e337416c057cb81c5396ad91d1 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 30 Mar 2021 19:32:33 -0700 Subject: skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 4 ++ include/net/tcp.h | 2 - net/core/skmsg.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_bpf.c | 100 +------------------------------------------------- net/tls/tls_sw.c | 4 +- 5 files changed, 106 insertions(+), 102 deletions(-) (limited to 'include/net') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 5e800ddc2dc6..f78e90a04a69 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -125,6 +125,10 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); +int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, + long timeo, int *err); +int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, + int len, int flags); static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 2efa4e5ea23d..31b1696c62ba 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2209,8 +2209,6 @@ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, int flags); -int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, - struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 9fc83f7cc1a0..92a83c02562a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -399,6 +399,104 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); +int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, + long timeo, int *err) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = sk_wait_event(sk, &timeo, + !list_empty(&psock->ingress_msg) || + !skb_queue_empty(&sk->sk_receive_queue), &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} +EXPORT_SYMBOL_GPL(sk_msg_wait_data); + +/* Receive sk_msg from psock->ingress_msg to @msg. */ +int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, + int len, int flags) +{ + struct iov_iter *iter = &msg->msg_iter; + int peek = flags & MSG_PEEK; + struct sk_msg *msg_rx; + int i, copied = 0; + + msg_rx = sk_psock_peek_msg(psock); + while (copied != len) { + struct scatterlist *sge; + + if (unlikely(!msg_rx)) + break; + + i = msg_rx->sg.start; + do { + struct page *page; + int copy; + + sge = sk_msg_elem(msg_rx, i); + copy = sge->length; + page = sg_page(sge); + if (copied + copy > len) + copy = len - copied; + copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (!copy) + return copied ? copied : -EFAULT; + + copied += copy; + if (likely(!peek)) { + sge->offset += copy; + sge->length -= copy; + if (!msg_rx->skb) + sk_mem_uncharge(sk, copy); + msg_rx->sg.size -= copy; + + if (!sge->length) { + sk_msg_iter_var_next(i); + if (!msg_rx->skb) + put_page(page); + } + } else { + /* Lets not optimize peek case if copy_page_to_iter + * didn't copy the entire length lets just break. + */ + if (copy != sge->length) + return copied; + sk_msg_iter_var_next(i); + } + + if (copied == len) + break; + } while (i != msg_rx->sg.end); + + if (unlikely(peek)) { + msg_rx = sk_psock_next_msg(psock, msg_rx); + if (!msg_rx) + break; + continue; + } + + msg_rx->sg.start = i; + if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) { + msg_rx = sk_psock_dequeue_msg(psock); + kfree_sk_msg(msg_rx); + } + msg_rx = sk_psock_peek_msg(psock); + } + + return copied; +} +EXPORT_SYMBOL_GPL(sk_msg_recvmsg); + static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, struct sk_buff *skb) { diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ac8cfbaeacd2..3d622a0d0753 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -10,80 +10,6 @@ #include #include -int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, - struct msghdr *msg, int len, int flags) -{ - struct iov_iter *iter = &msg->msg_iter; - int peek = flags & MSG_PEEK; - struct sk_msg *msg_rx; - int i, copied = 0; - - msg_rx = sk_psock_peek_msg(psock); - while (copied != len) { - struct scatterlist *sge; - - if (unlikely(!msg_rx)) - break; - - i = msg_rx->sg.start; - do { - struct page *page; - int copy; - - sge = sk_msg_elem(msg_rx, i); - copy = sge->length; - page = sg_page(sge); - if (copied + copy > len) - copy = len - copied; - copy = copy_page_to_iter(page, sge->offset, copy, iter); - if (!copy) - return copied ? copied : -EFAULT; - - copied += copy; - if (likely(!peek)) { - sge->offset += copy; - sge->length -= copy; - if (!msg_rx->skb) - sk_mem_uncharge(sk, copy); - msg_rx->sg.size -= copy; - - if (!sge->length) { - sk_msg_iter_var_next(i); - if (!msg_rx->skb) - put_page(page); - } - } else { - /* Lets not optimize peek case if copy_page_to_iter - * didn't copy the entire length lets just break. - */ - if (copy != sge->length) - return copied; - sk_msg_iter_var_next(i); - } - - if (copied == len) - break; - } while (i != msg_rx->sg.end); - - if (unlikely(peek)) { - msg_rx = sk_psock_next_msg(psock, msg_rx); - if (!msg_rx) - break; - continue; - } - - msg_rx->sg.start = i; - if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) { - msg_rx = sk_psock_dequeue_msg(psock); - kfree_sk_msg(msg_rx); - } - msg_rx = sk_psock_peek_msg(psock); - } - - return copied; -} -EXPORT_SYMBOL_GPL(__tcp_bpf_recvmsg); - static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -237,28 +163,6 @@ static bool tcp_bpf_stream_read(const struct sock *sk) return !empty; } -static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock, - int flags, long timeo, int *err) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret = 0; - - if (sk->sk_shutdown & RCV_SHUTDOWN) - return 1; - - if (!timeo) - return ret; - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - ret = sk_wait_event(sk, &timeo, - !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - return ret; -} - static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -278,13 +182,13 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } lock_sock(sk); msg_bytes_ready: - copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); + copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { int data, err = 0; long timeo; timeo = sock_rcvtimeo(sk, nonblock); - data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err); + data = sk_msg_wait_data(sk, psock, flags, timeo, &err); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 01d933ae5f16..1dcb34dfd56b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1789,8 +1789,8 @@ int tls_sw_recvmsg(struct sock *sk, skb = tls_wait_data(sk, psock, flags, timeo, &err); if (!skb) { if (psock) { - int ret = __tcp_bpf_recvmsg(sk, psock, - msg, len, flags); + int ret = sk_msg_recvmsg(sk, psock, msg, len, + flags); if (ret > 0) { decrypted += ret; -- cgit v1.3-14-g43fede