bpf: Hooks for sys_connect

== The problem ==

See description of the problem in the initial patch of this patch set.

== The solution ==

The patch provides much more reliable in-kernel solution for the 2nd
part of the problem: making outgoing connecttion from desired IP.

It adds new attach types `BPF_CGROUP_INET4_CONNECT` and
`BPF_CGROUP_INET6_CONNECT` for program type
`BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that can be used to override both
source and destination of a connection at connect(2) time.

Local end of connection can be bound to desired IP using newly
introduced BPF-helper `bpf_bind()`. It allows to bind to only IP though,
and doesn't support binding to port, i.e. leverages
`IP_BIND_ADDRESS_NO_PORT` socket option. There are two reasons for this:
* looking for a free port is expensive and can affect performance
  significantly;
* there is no use-case for port.

As for remote end (`struct sockaddr *` passed by user), both parts of it
can be overridden, remote IP and remote port. It's useful if an
application inside cgroup wants to connect to another application inside
same cgroup or to itself, but knows nothing about IP assigned to the
cgroup.

Support is added for IPv4 and IPv6, for TCP and UDP.

IPv4 and IPv6 have separate attach types for same reason as sys_bind
hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields
when user passes sockaddr_in since it'd be out-of-bound.

== Implementation notes ==

The patch introduces new field in `struct proto`: `pre_connect` that is
a pointer to a function with same signature as `connect` but is called
before it. The reason is in some cases BPF hooks should be called way
before control is passed to `sk->sk_prot->connect`. Specifically
`inet_dgram_connect` autobinds socket before calling
`sk->sk_prot->connect` and there is no way to call `bpf_bind()` from
hooks from e.g. `ip4_datagram_connect` or `ip6_datagram_connect` since
it'd cause double-bind. On the other hand `proto.pre_connect` provides a
flexible way to add BPF hooks for connect only for necessary `proto` and
call them at desired time before `connect`. Since `bpf_bind()` is
allowed to bind only to IP and autobind in `inet_dgram_connect` binds
only port there is no chance of double-bind.

bpf_bind() sets `force_bind_address_no_port` to bind to only IP despite
of value of `bind_address_no_port` socket field.

bpf_bind() sets `with_lock` to `false` when calling to __inet_bind()
and __inet6_bind() since all call-sites, where bpf_bind() is called,
already hold socket lock.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

5 files changed, 53 insertions, 1 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 67dc4a6471ad..c6ab295e6dcb 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -116,12 +116,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 	__ret;								       \
 })
 
+#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)	{					       \
+		lock_sock(sk);						       \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type);    \
+		release_sock(sk);					       \
+	}								       \
+	__ret;								       \
+})
+
 #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr)			       \
 	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_BIND)
 
 #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr)			       \
 	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_BIND)
 
+#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \
+					    sk->sk_prot->pre_connect)
+
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr)			       \
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr)		       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr)		       \
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT)
+
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops)				       \
 ({									       \
 	int __ret = 0;							       \
@@ -151,11 +177,16 @@ struct cgroup_bpf {};
 static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 
+#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
 
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 132e5b95167a..378d601258be 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -231,6 +231,13 @@ struct ipv6_stub {
 };
 extern const struct ipv6_stub *ipv6_stub __read_mostly;
 
+/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */
+struct ipv6_bpf_stub {
+	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+			  bool force_bind_address_no_port, bool with_lock);
+};
+extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
+
 /*
  * identify MLD packets for MLD filter exceptions
  */
diff --git a/include/net/sock.h b/include/net/sock.h
index b8ff435fa96e..49bd2c1796b0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1026,6 +1026,9 @@ static inline void sk_prot_clear_nulls(struct sock *sk, int size)
 struct proto {
 	void			(*close)(struct sock *sk,
 					long timeout);
+	int			(*pre_connect)(struct sock *sk,
+					struct sockaddr *uaddr,
+					int addr_len);
 	int			(*connect)(struct sock *sk,
 					struct sockaddr *uaddr,
 					int addr_len);
diff --git a/include/net/udp.h b/include/net/udp.h
index 850a8e581cce..0676b272f6ac 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -273,6 +273,7 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
 int udp_rcv(struct sk_buff *skb);
 int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 int udp_init_sock(struct sock *sk);
+int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int __udp_disconnect(struct sock *sk, int flags);
 int udp_disconnect(struct sock *sk, int flags);
 __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ce3e69e3c793..77afaf1ba556 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -150,6 +150,8 @@ enum bpf_attach_type {
 	BPF_SK_MSG_VERDICT,
 	BPF_CGROUP_INET4_BIND,
 	BPF_CGROUP_INET6_BIND,
+	BPF_CGROUP_INET4_CONNECT,
+	BPF_CGROUP_INET6_CONNECT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -744,6 +746,13 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: SK_PASS
  *
+ * int bpf_bind(ctx, addr, addr_len)
+ *     Bind socket to address. Only binding to IP is supported, no port can be
+ *     set in addr.
+ *     @ctx: pointer to context of type bpf_sock_addr
+ *     @addr: pointer to struct sockaddr to bind socket to
+ *     @addr_len: length of sockaddr structure
+ *     Return: 0 on success or negative error code
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -809,7 +818,8 @@ union bpf_attr {
 	FN(msg_redirect_map),		\
 	FN(msg_apply_bytes),		\
 	FN(msg_cork_bytes),		\
-	FN(msg_pull_data),
+	FN(msg_pull_data),		\
+	FN(bind),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call