bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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 v8 10/16] sock: introduce sk->sk_prot->psock_update_sk_prot()
Date: Tue, 30 Mar 2021 19:32:31 -0700	[thread overview]
Message-ID: <20210331023237.41094-11-xiyou.wangcong@gmail.com> (raw)
In-Reply-To: <20210331023237.41094-1-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->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.

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     |  1 +
 include/net/udp.h     |  1 +
 net/core/skmsg.c      |  5 -----
 net/core/sock_map.c   | 24 ++++--------------------
 net/ipv4/tcp_bpf.c    | 24 +++++++++++++++++++++---
 net/ipv4/tcp_ipv4.c   |  3 +++
 net/ipv4/udp.c        |  3 +++
 net/ipv4/udp_bpf.c    | 15 +++++++++++++--
 net/ipv6/tcp_ipv6.c   |  3 +++
 net/ipv6/udp.c        |  3 +++
 12 files changed, 58 insertions(+), 45 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c83dbc2d81d9..5e800ddc2dc6 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -99,6 +99,7 @@ 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  (*psock_update_sk_prot)(struct sock *sk, bool restore);
 	struct proto			*sk_proto;
 	struct mutex			work_mutex;
 	struct sk_psock_work_state	work_state;
@@ -395,25 +396,12 @@ 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->psock_update_sk_prot)
+		psock->psock_update_sk_prot(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 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 */
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index a045812d7c78..9fc83f7cc1a0 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -562,11 +562,6 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 
 	write_lock_bh(&sk->sk_callback_lock);
 
-	if (inet_csk_has_ulp(sk)) {
-		psock = ERR_PTR(-EINVAL);
-		goto out;
-	}
-
 	if (sk->sk_user_data) {
 		psock = ERR_PTR(-EBUSY);
 		goto out;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index c2a0411e08a8..2915c7c8778b 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -185,26 +185,10 @@ 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->psock_update_sk_prot)
 		return -EINVAL;
-	}
-
-	if (IS_ERR(prot))
-		return PTR_ERR(prot);
-
-	sk_psock_update_proto(sk, psock, prot);
-	return 0;
+	psock->psock_update_sk_prot = sk->sk_prot->psock_update_sk_prot;
+	return sk->sk_prot->psock_update_sk_prot(sk, false);
 }
 
 static struct sk_psock *sock_map_psock_get_checked(struct sock *sk)
@@ -556,7 +540,7 @@ static bool sock_map_redirect_allowed(const struct sock *sk)
 
 static bool sock_map_sk_is_suitable(const struct sock *sk)
 {
-	return sk_is_tcp(sk) || sk_is_udp(sk);
+	return !!sk->sk_prot->psock_update_sk_prot;
 }
 
 static bool sock_map_sk_state_allowed(const struct sock *sk)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ae980716d896..ac8cfbaeacd2 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -595,20 +595,38 @@ 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 (inet_csk_has_ulp(sk))
+		return -EINVAL;
+
 	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;
 }
+EXPORT_SYMBOL_GPL(tcp_bpf_update_proto);
 
 /* If a child got cloned from a listening socket that had tcp_bpf
  * protocol callbacks installed, we need to restore the callbacks to
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index daad4f99db32..dfc6d1c0e710 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2806,6 +2806,9 @@ struct proto tcp_prot = {
 	.hash			= inet_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= 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 4a0478b17243..38952aaee3a1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2849,6 +2849,9 @@ struct proto udp_prot = {
 	.unhash			= udp_lib_unhash,
 	.rehash			= udp_v4_rehash,
 	.get_port		= udp_v4_get_port,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= 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..6001f93cd3a0 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -41,12 +41,23 @@ 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;
 }
+EXPORT_SYMBOL_GPL(udp_bpf_update_proto);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d0f007741e8e..bff22d6ef516 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2139,6 +2139,9 @@ struct proto tcpv6_prot = {
 	.hash			= inet6_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= 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 d25e5a9252fd..ef2c75bb4771 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1713,6 +1713,9 @@ struct proto udpv6_prot = {
 	.unhash			= udp_lib_unhash,
 	.rehash			= udp_v6_rehash,
 	.get_port		= udp_v6_get_port,
+#ifdef CONFIG_BPF_SYSCALL
+	.psock_update_sk_prot	= 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


  parent reply	other threads:[~2021-03-31  2:33 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-31  2:32 [Patch bpf-next v8 00/16] sockmap: introduce BPF_SK_SKB_VERDICT and support UDP Cong Wang
2021-03-31  2:32 ` [Patch bpf-next v8 01/16] skmsg: lock ingress_skb when purging Cong Wang
2021-03-31 22:00   ` John Fastabend
2021-03-31  2:32 ` [Patch bpf-next v8 02/16] skmsg: introduce a spinlock to protect ingress_msg Cong Wang
2021-03-31  2:32 ` [Patch bpf-next v8 03/16] net: introduce skb_send_sock() for sock_map Cong Wang
2021-04-01  8:10   ` Jakub Sitnicki
2021-03-31  2:32 ` [Patch bpf-next v8 04/16] skmsg: avoid lock_sock() in sk_psock_backlog() Cong Wang
2021-03-31  2:32 ` [Patch bpf-next v8 05/16] skmsg: use rcu work for destroying psock Cong Wang
2021-03-31  2:32 ` [Patch bpf-next v8 06/16] skmsg: use GFP_KERNEL in sk_psock_create_ingress_msg() Cong Wang
2021-03-31  2:32 ` [Patch bpf-next v8 07/16] sock_map: simplify sock_map_link() a bit Cong Wang
2021-04-01  5:48   ` John Fastabend
2021-03-31  2:32 ` [Patch bpf-next v8 08/16] sock_map: kill sock_map_link_no_progs() Cong Wang
2021-03-31  2:32 ` [Patch bpf-next v8 09/16] sock_map: introduce BPF_SK_SKB_VERDICT Cong Wang
2021-04-01  5:51   ` John Fastabend
2021-03-31  2:32 ` Cong Wang [this message]
2021-04-02 10:16   ` [Patch bpf-next v8 10/16] sock: introduce sk->sk_prot->psock_update_sk_prot() Jakub Sitnicki
2021-04-03  5:13     ` Cong Wang
2021-04-05  8:25   ` Eric Dumazet
2021-04-06 18:12     ` John Fastabend
2021-04-06 18:30     ` Cong Wang
2021-04-06 21:07       ` John Fastabend
2021-03-31  2:32 ` [Patch bpf-next v8 11/16] udp: implement ->read_sock() for sockmap Cong Wang
2021-04-01  6:00   ` John Fastabend
2021-04-03  5:08     ` Cong Wang
2021-04-03  6:45       ` Alexei Starovoitov
2021-03-31  2:32 ` [Patch bpf-next v8 12/16] skmsg: extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Cong Wang
2021-04-01 16:36   ` John Fastabend
2021-03-31  2:32 ` [Patch bpf-next v8 13/16] udp: implement udp_bpf_recvmsg() for sockmap Cong Wang
2021-04-01 16:24   ` John Fastabend
2021-03-31  2:32 ` [Patch bpf-next v8 14/16] sock_map: update sock type checks for UDP Cong Wang
2021-04-01  6:02   ` John Fastabend
2021-03-31  2:32 ` [Patch bpf-next v8 15/16] selftests/bpf: add a test case for udp sockmap Cong Wang
2021-03-31  2:32 ` [Patch bpf-next v8 16/16] selftests/bpf: add a test case for loading BPF_SK_SKB_VERDICT Cong Wang
2021-04-01 16:51 ` [Patch bpf-next v8 00/16] sockmap: introduce BPF_SK_SKB_VERDICT and support UDP John Fastabend
2021-04-01 18:03   ` Alexei Starovoitov

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=20210331023237.41094-11-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).