bpf: Post-hooks for sys_bind

"Post-hooks" are hooks that are called right before returning from
sys_bind. At this time IP and port are already allocated and no further
changes to `struct sock` can happen before returning from sys_bind but
BPF program has a chance to inspect the socket and change sys_bind
result.

Specifically it can e.g. inspect what port was allocated and if it
doesn't satisfy some policy, BPF program can force sys_bind to fail and
return EPERM to user.

Another example of usage is recording the IP:port pair to some map to
use it in later calls to sys_connect. E.g. if some TCP server inside
cgroup was bound to some IP:port_n, it can be recorded to a map. And
later when some TCP client inside same cgroup is trying to connect to
127.0.0.1:port_n, BPF hook for sys_connect can override the destination
and connect application to IP:port_n instead of 127.0.0.1:port_n. That
helps forcing all applications inside a cgroup to use desired IP and not
break those applications if they e.g. use localhost to communicate
between each other.

== Implementation details ==

Post-hooks are implemented as two new attach types
`BPF_CGROUP_INET4_POST_BIND` and `BPF_CGROUP_INET6_POST_BIND` for
existing prog type `BPF_PROG_TYPE_CGROUP_SOCK`.

Separate attach types for IPv4 and IPv6 are introduced to avoid access
to IPv6 field in `struct sock` from `inet_bind()` and to IPv4 field from
`inet6_bind()` since those fields might not make sense in such cases.

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

3 files changed, 128 insertions, 27 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index bdb9cadd4d27..d31aff93270d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4097,30 +4097,80 @@ static bool lwt_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, prog, info);
 }
 
-static bool sock_filter_is_valid_access(int off, int size,
-					enum bpf_access_type type,
-					const struct bpf_prog *prog,
-					struct bpf_insn_access_aux *info)
+
+/* Attach type specific accesses */
+static bool __sock_filter_check_attach_type(int off,
+					    enum bpf_access_type access_type,
+					    enum bpf_attach_type attach_type)
 {
-	if (type == BPF_WRITE) {
-		switch (off) {
-		case offsetof(struct bpf_sock, bound_dev_if):
-		case offsetof(struct bpf_sock, mark):
-		case offsetof(struct bpf_sock, priority):
-			break;
+	switch (off) {
+	case offsetof(struct bpf_sock, bound_dev_if):
+	case offsetof(struct bpf_sock, mark):
+	case offsetof(struct bpf_sock, priority):
+		switch (attach_type) {
+		case BPF_CGROUP_INET_SOCK_CREATE:
+			goto full_access;
+		default:
+			return false;
+		}
+	case bpf_ctx_range(struct bpf_sock, src_ip4):
+		switch (attach_type) {
+		case BPF_CGROUP_INET4_POST_BIND:
+			goto read_only;
+		default:
+			return false;
+		}
+	case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
+		switch (attach_type) {
+		case BPF_CGROUP_INET6_POST_BIND:
+			goto read_only;
+		default:
+			return false;
+		}
+	case bpf_ctx_range(struct bpf_sock, src_port):
+		switch (attach_type) {
+		case BPF_CGROUP_INET4_POST_BIND:
+		case BPF_CGROUP_INET6_POST_BIND:
+			goto read_only;
 		default:
 			return false;
 		}
 	}
+read_only:
+	return access_type == BPF_READ;
+full_access:
+	return true;
+}
+
+static bool __sock_filter_check_size(int off, int size,
+				     struct bpf_insn_access_aux *info)
+{
+	const int size_default = sizeof(__u32);
 
-	if (off < 0 || off + size > sizeof(struct bpf_sock))
+	switch (off) {
+	case bpf_ctx_range(struct bpf_sock, src_ip4):
+	case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
+		bpf_ctx_record_field_size(info, size_default);
+		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	}
+
+	return size == size_default;
+}
+
+static bool sock_filter_is_valid_access(int off, int size,
+					enum bpf_access_type type,
+					const struct bpf_prog *prog,
+					struct bpf_insn_access_aux *info)
+{
+	if (off < 0 || off >= sizeof(struct bpf_sock))
 		return false;
-	/* The verifier guarantees that size > 0. */
 	if (off % size != 0)
 		return false;
-	if (size != sizeof(__u32))
+	if (!__sock_filter_check_attach_type(off, type,
+					     prog->expected_attach_type))
+		return false;
+	if (!__sock_filter_check_size(off, size, info))
 		return false;
-
 	return true;
 }
 
@@ -4728,6 +4778,7 @@ static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
 					  struct bpf_prog *prog, u32 *target_size)
 {
 	struct bpf_insn *insn = insn_buf;
+	int off;
 
 	switch (si->off) {
 	case offsetof(struct bpf_sock, bound_dev_if):
@@ -4783,6 +4834,43 @@ static u32 sock_filter_convert_ctx_access(enum bpf_access_type type,
 		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
 		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT);
 		break;
+
+	case offsetof(struct bpf_sock, src_ip4):
+		*insn++ = BPF_LDX_MEM(
+			BPF_SIZE(si->code), si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock_common, skc_rcv_saddr,
+				       FIELD_SIZEOF(struct sock_common,
+						    skc_rcv_saddr),
+				       target_size));
+		break;
+
+	case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]):
+#if IS_ENABLED(CONFIG_IPV6)
+		off = si->off;
+		off -= offsetof(struct bpf_sock, src_ip6[0]);
+		*insn++ = BPF_LDX_MEM(
+			BPF_SIZE(si->code), si->dst_reg, si->src_reg,
+			bpf_target_off(
+				struct sock_common,
+				skc_v6_rcv_saddr.s6_addr32[0],
+				FIELD_SIZEOF(struct sock_common,
+					     skc_v6_rcv_saddr.s6_addr32[0]),
+				target_size) + off);
+#else
+		(void)off;
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+		break;
+
+	case offsetof(struct bpf_sock, src_port):
+		*insn++ = BPF_LDX_MEM(
+			BPF_FIELD_SIZEOF(struct sock_common, skc_num),
+			si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock_common, skc_num,
+				       FIELD_SIZEOF(struct sock_common,
+						    skc_num),
+				       target_size));
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 488fe26ac8e5..142d4c35b493 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -519,12 +519,18 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 		inet->inet_saddr = 0;  /* Use device */
 
 	/* Make sure we are allowed to bind here. */
-	if ((snum || !(inet->bind_address_no_port ||
-		       force_bind_address_no_port)) &&
-	    sk->sk_prot->get_port(sk, snum)) {
-		inet->inet_saddr = inet->inet_rcv_saddr = 0;
-		err = -EADDRINUSE;
-		goto out_release_sock;
+	if (snum || !(inet->bind_address_no_port ||
+		      force_bind_address_no_port)) {
+		if (sk->sk_prot->get_port(sk, snum)) {
+			inet->inet_saddr = inet->inet_rcv_saddr = 0;
+			err = -EADDRINUSE;
+			goto out_release_sock;
+		}
+		err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
+		if (err) {
+			inet->inet_saddr = inet->inet_rcv_saddr = 0;
+			goto out_release_sock;
+		}
 	}
 
 	if (inet->inet_rcv_saddr)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 566cec0e0a44..41f50472679d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -412,13 +412,20 @@ int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 		sk->sk_ipv6only = 1;
 
 	/* Make sure we are allowed to bind here. */
-	if ((snum || !(inet->bind_address_no_port ||
-		       force_bind_address_no_port)) &&
-	    sk->sk_prot->get_port(sk, snum)) {
-		sk->sk_ipv6only = saved_ipv6only;
-		inet_reset_saddr(sk);
-		err = -EADDRINUSE;
-		goto out;
+	if (snum || !(inet->bind_address_no_port ||
+		      force_bind_address_no_port)) {
+		if (sk->sk_prot->get_port(sk, snum)) {
+			sk->sk_ipv6only = saved_ipv6only;
+			inet_reset_saddr(sk);
+			err = -EADDRINUSE;
+			goto out;
+		}
+		err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk);
+		if (err) {
+			sk->sk_ipv6only = saved_ipv6only;
+			inet_reset_saddr(sk);
+			goto out;
+		}
 	}
 
 	if (addr_type != IPV6_ADDR_ANY)