[PATCH v3 bpf-next 10/11] bpf: Add BPF_SOCK_OPS_STATE_CB

[Lawrence Brakmo <brakmo@fb.com>]

Adds support for calling sock_ops BPF program when there is a TCP state
change. Two arguments are used; one for the old state and another for
the new state.

There is a new enum in include/uapi/linux/bpf.h that exports the TCP
states that prepends BPF_ to the current TCP state names. If it is ever
necessary to change the internal TCP state values (other than adding
more to the end), then it will become necessary to convert from the
internal TCP state value to the BPF value before calling the BPF
sock_ops function.

New op: BPF_SOCK_OPS_STATE_CB.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
 include/uapi/linux/bpf.h | 26 ++++++++++++++++++++++++++
 include/uapi/linux/tcp.h |  1 +
 net/ipv4/tcp.c           |  4 ++++
 3 files changed, 31 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 415b951..b653273 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1024,6 +1024,32 @@ enum {
 					 * Arg1: sequence number of 1st byte
 					 * Arg2: # segments
 					 */
+	BPF_SOCK_OPS_STATE_CB,		/* Called when TCP changes state.
+					 * Arg1: old_state
+					 * Arg2: new_state
+					 */
+};
+
+/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
+ * changes between the TCP and BPF versions. Ideally this should never happen.
+ * If it does, we need to add code to convert them before calling
+ * the BPF sock_ops function.
+ */
+enum {
+	BPF_TCP_ESTABLISHED = 1,
+	BPF_TCP_SYN_SENT,
+	BPF_TCP_SYN_RECV,
+	BPF_TCP_FIN_WAIT1,
+	BPF_TCP_FIN_WAIT2,
+	BPF_TCP_TIME_WAIT,
+	BPF_TCP_CLOSE,
+	BPF_TCP_CLOSE_WAIT,
+	BPF_TCP_LAST_ACK,
+	BPF_TCP_LISTEN,
+	BPF_TCP_CLOSING,	/* Now a valid state */
+	BPF_TCP_NEW_SYN_RECV,
+
+	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
 
 #define TCP_BPF_IW		1001	/* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index dc36d3c..211322c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -262,6 +262,7 @@ struct tcp_md5sig {
 /* Definitions for bpf_sock_ops_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG	(1<<0)
 #define BPF_SOCK_OPS_RETRANS_CB_FLAG	(1<<1)
+#define BPF_SOCK_OPS_STATE_CB_FLAG	(1<<2)
 
 /* INET_DIAG_MD5SIG */
 struct tcp_diag_md5sig {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a1fe7a7..b321dfd 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2044,6 +2044,10 @@ void tcp_set_state(struct sock *sk, int state)
 {
 	int oldstate = sk->sk_state;
 
+	BUILD_BUG_ON(BPF_TCP_MAX_STATES != TCP_MAX_STATES);
+	if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG))
+		tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state);
+
 	switch (state) {
 	case TCP_ESTABLISHED:
 		if (oldstate != TCP_ESTABLISHED)
-- 
2.9.5