diff mbox series

[bpf-next,06/19] sock: introduce sk_prot->update_proto()

Message ID 20210203041636.38555-7-xiyou.wangcong@gmail.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series sock_map: add non-TCP and cross-protocol support | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count fail Series longer than 15 patches
netdev/tree_selection success Clearly marked for bpf-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 10 maintainers not CCed: davem@davemloft.net songliubraving@fb.com andrii@kernel.org yoshfuji@linux-ipv6.org edumazet@google.com kpsingh@kernel.org ast@kernel.org kuba@kernel.org kafai@fb.com yhs@fb.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit fail Errors and warnings before: 4415 this patch: 4420
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 86 exceeds 80 columns
netdev/build_allmodconfig_warn fail Errors and warnings before: 4836 this patch: 4841
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Cong Wang Feb. 3, 2021, 4:16 a.m. UTC 
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 mbox series

Patch

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),