From: Cong Wang <xiyou.wangcong@gmail.com>
To: netdev@vger.kernel.org
Cc: bpf@vger.kernel.org, duanxiongchun@bytedance.com,
wangdongdong.6@bytedance.com, jiang.wang@bytedance.com,
Cong Wang <cong.wang@bytedance.com>,
John Fastabend <john.fastabend@gmail.com>,
Daniel Borkmann <daniel@iogearbox.net>,
Jakub Sitnicki <jakub@cloudflare.com>,
Lorenz Bauer <lmb@cloudflare.com>
Subject: [Patch bpf-next 06/19] sock: introduce sk_prot->update_proto()
Date: Tue, 2 Feb 2021 20:16:23 -0800 [thread overview]
Message-ID: <20210203041636.38555-7-xiyou.wangcong@gmail.com> (raw)
In-Reply-To: <20210203041636.38555-1-xiyou.wangcong@gmail.com>
From: Cong Wang <cong.wang@bytedance.com>
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->update_proto(), so each protocol
can implement its own way to replace the struct proto.
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/linux/skmsg.h | 18 +++---------------
include/net/sock.h | 3 +++
include/net/tcp.h | 2 +-
include/net/udp.h | 2 +-
net/core/sock_map.c | 22 +++-------------------
net/ipv4/tcp_bpf.c | 20 +++++++++++++++++---
net/ipv4/tcp_ipv4.c | 3 +++
net/ipv4/udp.c | 3 +++
net/ipv4/udp_bpf.c | 14 ++++++++++++--
net/ipv6/tcp_ipv6.c | 3 +++
net/ipv6/udp.c | 3 +++
11 files changed, 52 insertions(+), 41 deletions(-)
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index cb79b1afa556..cb94d0f89c08 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -97,6 +97,7 @@ struct sk_psock {
void (*saved_close)(struct sock *sk, long timeout);
void (*saved_write_space)(struct sock *sk);
void (*saved_data_ready)(struct sock *sk);
+ int (*saved_update_proto)(struct sock *sk, bool restore);
struct proto *sk_proto;
struct sk_psock_work_state work_state;
struct work_struct work;
@@ -335,25 +336,12 @@ static inline void sk_psock_cork_free(struct sk_psock *psock)
}
}
-static inline void sk_psock_update_proto(struct sock *sk,
- struct sk_psock *psock,
- struct proto *ops)
-{
- /* Pairs with lockless read in sk_clone_lock() */
- WRITE_ONCE(sk->sk_prot, ops);
-}
-
static inline void sk_psock_restore_proto(struct sock *sk,
struct sk_psock *psock)
{
sk->sk_prot->unhash = psock->saved_unhash;
- if (inet_csk_has_ulp(sk)) {
- tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
- } else {
- sk->sk_write_space = psock->saved_write_space;
- /* Pairs with lockless read in sk_clone_lock() */
- WRITE_ONCE(sk->sk_prot, psock->sk_proto);
- }
+ if (psock->saved_update_proto)
+ psock->saved_update_proto(sk, true);
}
static inline void sk_psock_set_state(struct sk_psock *psock,
diff --git a/include/net/sock.h b/include/net/sock.h
index 7644ea64a376..e474a9202be8 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_SOCK_MAP
+ int (*update_proto)(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 f7591768525d..c2fff35859b6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2183,7 +2183,7 @@ struct sk_msg;
struct sk_psock;
#ifdef CONFIG_BPF_SOCK_MAP
-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);
#else
static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
diff --git a/include/net/udp.h b/include/net/udp.h
index 0ff921e6b866..e3e5dfc8e0f0 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -513,7 +513,7 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
#ifdef CONFIG_BPF_SOCK_MAP
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 /* CONFIG_BPF_SOCK_MAP */
#endif /* _UDP_H */
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index f827f1ecefcc..255067e5c73a 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -181,26 +181,10 @@ static void sock_map_unref(struct sock *sk, void *link_raw)
static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock)
{
- struct proto *prot;
-
- switch (sk->sk_type) {
- case SOCK_STREAM:
- prot = tcp_bpf_get_proto(sk, psock);
- break;
-
- case SOCK_DGRAM:
- prot = udp_bpf_get_proto(sk, psock);
- break;
-
- default:
+ if (!sk->sk_prot->update_proto)
return -EINVAL;
- }
-
- if (IS_ERR(prot))
- return PTR_ERR(prot);
-
- sk_psock_update_proto(sk, psock, prot);
- return 0;
+ psock->saved_update_proto = sk->sk_prot->update_proto;
+ return sk->sk_prot->update_proto(sk, false);
}
static struct sk_psock *sock_map_psock_get_checked(struct sock *sk)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 2252f1d90676..16e00802ccba 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -601,19 +601,33 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP;
}
-struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
+int tcp_bpf_update_proto(struct sock *sk, bool restore)
{
+ struct sk_psock *psock = sk_psock(sk);
int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE;
+ if (restore) {
+ if (inet_csk_has_ulp(sk)) {
+ tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
+ } else {
+ sk->sk_write_space = psock->saved_write_space;
+ /* Pairs with lockless read in sk_clone_lock() */
+ WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ }
+ return 0;
+ }
+
if (sk->sk_family == AF_INET6) {
if (tcp_bpf_assert_proto_ops(psock->sk_proto))
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
tcp_bpf_check_v6_needs_rebuild(psock->sk_proto);
}
- return &tcp_bpf_prots[family][config];
+ /* Pairs with lockless read in sk_clone_lock() */
+ WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
+ return 0;
}
/* If a child got cloned from a listening socket that had tcp_bpf
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 62b6fd385a47..d7c30b762cc3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2803,6 +2803,9 @@ struct proto tcp_prot = {
.hash = inet_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
+#ifdef CONFIG_BPF_SOCK_MAP
+ .update_proto = tcp_bpf_update_proto,
+#endif
.enter_memory_pressure = tcp_enter_memory_pressure,
.leave_memory_pressure = tcp_leave_memory_pressure,
.stream_memory_free = tcp_stream_memory_free,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c67e483fce41..84ab4f2e874a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2843,6 +2843,9 @@ struct proto udp_prot = {
.unhash = udp_lib_unhash,
.rehash = udp_v4_rehash,
.get_port = udp_v4_get_port,
+#ifdef CONFIG_BPF_SOCK_MAP
+ .update_proto = udp_bpf_update_proto,
+#endif
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 7a94791efc1a..595836088e85 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -41,12 +41,22 @@ static int __init udp_bpf_v4_build_proto(void)
}
core_initcall(udp_bpf_v4_build_proto);
-struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
+int udp_bpf_update_proto(struct sock *sk, bool restore)
{
int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
+ struct sk_psock *psock = sk_psock(sk);
+
+ if (restore) {
+ sk->sk_write_space = psock->saved_write_space;
+ /* Pairs with lockless read in sk_clone_lock() */
+ WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ return 0;
+ }
if (sk->sk_family == AF_INET6)
udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
- return &udp_bpf_prots[family];
+ /* Pairs with lockless read in sk_clone_lock() */
+ WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]);
+ return 0;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8539715ff035..77b11799a3fe 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2131,6 +2131,9 @@ struct proto tcpv6_prot = {
.hash = inet6_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
+#ifdef CONFIG_BPF_SOCK_MAP
+ .update_proto = tcp_bpf_update_proto,
+#endif
.enter_memory_pressure = tcp_enter_memory_pressure,
.leave_memory_pressure = tcp_leave_memory_pressure,
.stream_memory_free = tcp_stream_memory_free,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a02ac875a923..66ebdfc83c95 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1711,6 +1711,9 @@ struct proto udpv6_prot = {
.unhash = udp_lib_unhash,
.rehash = udp_v6_rehash,
.get_port = udp_v6_get_port,
+#ifdef CONFIG_BPF_SOCK_MAP
+ .update_proto = udp_bpf_update_proto,
+#endif
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
--
2.25.1
next prev parent reply other threads:[~2021-02-03 4:20 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-03 4:16 [Patch bpf-next 00/19] sock_map: add non-TCP and cross-protocol support Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 01/19] bpf: rename BPF_STREAM_PARSER to BPF_SOCK_MAP Cong Wang
2021-02-05 10:32 ` Jakub Sitnicki
2021-02-09 1:40 ` Cong Wang
2021-02-08 8:21 ` John Fastabend
2021-02-08 9:50 ` Lorenz Bauer
2021-02-09 1:45 ` Cong Wang
2021-02-09 6:48 ` John Fastabend
2021-02-03 4:16 ` [Patch bpf-next 02/19] skmsg: get rid of struct sk_psock_parser Cong Wang
2021-02-05 11:25 ` Jakub Sitnicki
2021-02-08 8:39 ` John Fastabend
2021-02-09 0:19 ` Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 03/19] skmsg: use skb ext instead of TCP_SKB_CB Cong Wang
2021-02-05 22:09 ` Jakub Sitnicki
2021-02-08 18:56 ` Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 04/19] sock_map: rename skb_parser and skb_verdict Cong Wang
2021-02-08 8:27 ` John Fastabend
2021-02-03 4:16 ` [Patch bpf-next 05/19] sock_map: introduce BPF_SK_SKB_VERDICT Cong Wang
2021-02-08 8:31 ` John Fastabend
2021-02-03 4:16 ` Cong Wang [this message]
2021-02-03 4:16 ` [Patch bpf-next 07/19] udp: implement ->sendmsg_locked() Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 08/19] udp: implement ->read_sock() for sockmap Cong Wang
2021-02-08 9:48 ` Lorenz Bauer
2021-02-09 1:35 ` Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 09/19] udp: add ->read_sock() and ->sendmsg_locked() to ipv6 Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 10/19] af_unix: implement ->sendmsg_locked for dgram socket Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 11/19] af_unix: implement ->read_sock() for sockmap Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 12/19] af_unix: implement ->update_proto() Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 13/19] af_unix: set TCP_ESTABLISHED for datagram sockets too Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 14/19] skmsg: extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 15/19] udp: implement udp_bpf_recvmsg() for sockmap Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 16/19] af_unix: implement unix_dgram_bpf_recvmsg() Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 17/19] sock_map: update sock type checks Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 18/19] selftests/bpf: add test cases for unix and udp sockmap Cong Wang
2021-02-05 10:53 ` Jakub Sitnicki
2021-02-08 18:43 ` Cong Wang
2021-02-03 4:16 ` [Patch bpf-next 19/19] selftests/bpf: add test case for redirection between udp and unix Cong Wang
2021-02-03 17:48 ` [Patch bpf-next 00/19] sock_map: add non-TCP and cross-protocol support Alexei Starovoitov
2021-02-03 19:22 ` Cong Wang
2021-02-03 20:29 ` John Fastabend
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210203041636.38555-7-xiyou.wangcong@gmail.com \
--to=xiyou.wangcong@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=cong.wang@bytedance.com \
--cc=daniel@iogearbox.net \
--cc=duanxiongchun@bytedance.com \
--cc=jakub@cloudflare.com \
--cc=jiang.wang@bytedance.com \
--cc=john.fastabend@gmail.com \
--cc=lmb@cloudflare.com \
--cc=netdev@vger.kernel.org \
--cc=wangdongdong.6@bytedance.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).