diff mbox series

[bpf-next,v3,1/5] bpf: expose is_mptcp flag to bpf_tcp_sock

Message ID 20200918121046.190240-1-nicolas.rybowski@tessares.net
State Superseded
Headers show
Series [bpf-next,v3,1/5] bpf: expose is_mptcp flag to bpf_tcp_sock | expand

Commit Message

Nicolas Rybowski Sept. 18, 2020, 12:10 p.m. UTC
is_mptcp is a field from struct tcp_sock used to indicate that the
current tcp_sock is part of the MPTCP protocol.

In this protocol, a first socket (mptcp_sock) is created with
sk_protocol set to IPPROTO_MPTCP (=262) for control purpose but it
isn't directly on the wire. This is the role of the subflow (kernel)
sockets which are classical tcp_sock with sk_protocol set to
IPPROTO_TCP. The only way to differentiate such sockets from plain TCP
sockets is the is_mptcp field from tcp_sock.

Such an exposure in BPF is thus required to be able to differentiate
plain TCP sockets from MPTCP subflow sockets in BPF_PROG_TYPE_SOCK_OPS
programs.

The choice has been made to silently pass the case when CONFIG_MPTCP is
unset by defaulting is_mptcp to 0 in order to make BPF independent of
the MPTCP configuration. Another solution is to make the verifier fail
in 'bpf_tcp_sock_is_valid_ctx_access' but this will add an additional
'#ifdef CONFIG_MPTCP' in the BPF code and a same injected BPF program
will not run if MPTCP is not set.

An example use-case is provided in
https://github.com/multipath-tcp/mptcp_net-next/tree/scripts/bpf/examples

Suggested-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>
---
 include/uapi/linux/bpf.h       | 1 +
 net/core/filter.c              | 9 ++++++++-
 tools/include/uapi/linux/bpf.h | 1 +
 3 files changed, 10 insertions(+), 1 deletion(-)

Comments

Song Liu Sept. 18, 2020, 10:26 p.m. UTC | #1
On Fri, Sep 18, 2020 at 5:13 AM Nicolas Rybowski
<nicolas.rybowski@tessares.net> wrote:
>

> is_mptcp is a field from struct tcp_sock used to indicate that the

> current tcp_sock is part of the MPTCP protocol.

>

> In this protocol, a first socket (mptcp_sock) is created with

> sk_protocol set to IPPROTO_MPTCP (=262) for control purpose but it

> isn't directly on the wire. This is the role of the subflow (kernel)

> sockets which are classical tcp_sock with sk_protocol set to

> IPPROTO_TCP. The only way to differentiate such sockets from plain TCP

> sockets is the is_mptcp field from tcp_sock.

>

> Such an exposure in BPF is thus required to be able to differentiate

> plain TCP sockets from MPTCP subflow sockets in BPF_PROG_TYPE_SOCK_OPS

> programs.

>

> The choice has been made to silently pass the case when CONFIG_MPTCP is

> unset by defaulting is_mptcp to 0 in order to make BPF independent of

> the MPTCP configuration. Another solution is to make the verifier fail

> in 'bpf_tcp_sock_is_valid_ctx_access' but this will add an additional

> '#ifdef CONFIG_MPTCP' in the BPF code and a same injected BPF program

> will not run if MPTCP is not set.

>

> An example use-case is provided in

> https://github.com/multipath-tcp/mptcp_net-next/tree/scripts/bpf/examples

>

> Suggested-by: Matthieu Baerts <matthieu.baerts@tessares.net>

> Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>

> Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>

> Signed-off-by: Nicolas Rybowski <nicolas.rybowski@tessares.net>


Acked-by: Song Liu <songliubraving@fb.com>

[...]
diff mbox series

Patch

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a22812561064..351b3d0a6ca8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4067,6 +4067,7 @@  struct bpf_tcp_sock {
 	__u32 delivered;	/* Total data packets delivered incl. rexmits */
 	__u32 delivered_ce;	/* Like the above but only ECE marked packets */
 	__u32 icsk_retransmits;	/* Number of unrecovered [RTO] timeouts */
+	__u32 is_mptcp;		/* Is MPTCP subflow? */
 };
 
 struct bpf_sock_tuple {
diff --git a/net/core/filter.c b/net/core/filter.c
index d266c6941967..dab48528dceb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5837,7 +5837,7 @@  bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 				  struct bpf_insn_access_aux *info)
 {
 	if (off < 0 || off >= offsetofend(struct bpf_tcp_sock,
-					  icsk_retransmits))
+					  is_mptcp))
 		return false;
 
 	if (off % size != 0)
@@ -5971,6 +5971,13 @@  u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_tcp_sock, icsk_retransmits):
 		BPF_INET_SOCK_GET_COMMON(icsk_retransmits);
 		break;
+	case offsetof(struct bpf_tcp_sock, is_mptcp):
+#ifdef CONFIG_MPTCP
+		BPF_TCP_SOCK_GET_COMMON(is_mptcp);
+#else
+		*insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
+#endif
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a22812561064..351b3d0a6ca8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4067,6 +4067,7 @@  struct bpf_tcp_sock {
 	__u32 delivered;	/* Total data packets delivered incl. rexmits */
 	__u32 delivered_ce;	/* Like the above but only ECE marked packets */
 	__u32 icsk_retransmits;	/* Number of unrecovered [RTO] timeouts */
+	__u32 is_mptcp;		/* Is MPTCP subflow? */
 };
 
 struct bpf_sock_tuple {