bpf: Hooks for sys_sendmsg

In addition to already existing BPF hooks for sys_bind and sys_connect,
the patch provides new hooks for sys_sendmsg.

It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR`
that provides access to socket itlself (properties like family, type,
protocol) and user-passed `struct sockaddr *` so that BPF program can
override destination IP and port for system calls such as sendto(2) or
sendmsg(2) and/or assign source IP to the socket.

The hooks are implemented as two new attach types:
`BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and
UDPv6 correspondingly.

UDPv4 and UDPv6 separate attach types for same reason as sys_bind and
sys_connect 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.

The difference with already existing hooks is sys_sendmsg are
implemented only for unconnected UDP.

For TCP it doesn't make sense to change user-provided `struct sockaddr *`
at sendto(2)/sendmsg(2) time since socket either was already connected
and has source/destination set or wasn't connected and call to
sendto(2)/sendmsg(2) would lead to ENOTCONN anyway.

Connected UDP is already handled by sys_connect hooks that can override
source/destination at connect time and use fast-path later, i.e. these
hooks don't affect UDP fast-path.

Rewriting source IP is implemented differently than that in sys_connect
hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to
just bind socket to desired local IP address since source IP can be set
on per-packet basis by using ancillary data (cmsg(3)). So no matter if
socket is bound or not, source IP has to be rewritten on every call to
sys_sendmsg.

To do so two new fields are added to UAPI `struct bpf_sock_addr`;
* `msg_src_ip4` to set source IPv4 for UDPv4;
* `msg_src_ip6` to set source IPv6 for UDPv6.

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

1 files changed, 39 insertions, 0 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index acf1f4f..24e6ce8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5299,6 +5299,7 @@ static bool sock_addr_is_valid_access(int off, int size,
 		switch (prog->expected_attach_type) {
 		case BPF_CGROUP_INET4_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_UDP4_SENDMSG:
 			break;
 		default:
 			return false;
@@ -5308,6 +5309,24 @@ static bool sock_addr_is_valid_access(int off, int size,
 		switch (prog->expected_attach_type) {
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_UDP6_SENDMSG:
+			break;
+		default:
+			return false;
+		}
+		break;
+	case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_UDP4_SENDMSG:
+			break;
+		default:
+			return false;
+		}
+		break;
+	case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
+				msg_src_ip6[3]):
+		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_UDP6_SENDMSG:
 			break;
 		default:
 			return false;
@@ -5318,6 +5337,9 @@ static bool sock_addr_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct bpf_sock_addr, user_ip4):
 	case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]):
+	case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
+	case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
+				msg_src_ip6[3]):
 		/* Only narrow read access allowed for now. */
 		if (type == BPF_READ) {
 			bpf_ctx_record_field_size(info, size_default);
@@ -6072,6 +6094,23 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
 					SK_FL_PROTO_SHIFT);
 		break;
+
+	case offsetof(struct bpf_sock_addr, msg_src_ip4):
+		/* Treat t_ctx as struct in_addr for msg_src_ip4. */
+		SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
+			struct bpf_sock_addr_kern, struct in_addr, t_ctx,
+			s_addr, BPF_SIZE(si->code), 0, tmp_reg);
+		break;
+
+	case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
+				msg_src_ip6[3]):
+		off = si->off;
+		off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]);
+		/* Treat t_ctx as struct in6_addr for msg_src_ip6. */
+		SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
+			struct bpf_sock_addr_kern, struct in6_addr, t_ctx,
+			s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg);
+		break;
 	}
 
 	return insn - insn_buf;