We want to be able to set up the monitoring application so that it can
be aysnchronously notified when "interesting" events happen, e.g., when
application-determined thresholds on parameters like RTT estimate, number
of retransmissions, RTO are reached.
The bpf_sock_ops infrastructure provided as part of Commit 40304b2a1567
("bpf: BPF support for sock_ops") provides an elegant way to trigger
this asynchronous notification. The BPF program can examine the
current TCP state reported in the bpf_sock_ops and conditionally
return a (new) status BPF_TCP_INFO_NOTIFY. The return status is used
by the caller to queue up a tcp_info notification for the application.
Signed-off-by: Sowmini Varadhan <sowmini.varad...@oracle.com>
---
include/net/tcp.h | 15 +++++++++++++--
include/uapi/linux/bpf.h | 4 ++++
2 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0d29292..df06a9f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -47,6 +47,7 @@
#include <linux/seq_file.h>
#include <linux/memcontrol.h>
#include <linux/bpf-cgroup.h>
+#include <linux/sock_diag.h>
extern struct inet_hashinfo tcp_hashinfo;
@@ -2065,6 +2066,12 @@ struct tcp_ulp_ops {
__MODULE_INFO(alias, alias_userspace, name); \
__MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name)
+#define TCPDIAG_CB(sk)
\
+do { \
+ if (unlikely(sk->sk_net_refcnt && sock_diag_has_listeners(sk))) \
+ sock_diag_broadcast(sk); \
+} while (0)
+
/* Call BPF_SOCK_OPS program that returns an int. If the return value
* is < 0, then the BPF op failed (for example if the loaded BPF
* program does not support the chosen operation or there is no BPF
@@ -2088,9 +2095,13 @@ static inline int tcp_call_bpf(struct sock *sk, int op,
u32 nargs, u32 *args)
memcpy(sock_ops.args, args, nargs * sizeof(*args));
ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
- if (ret == 0)
+ if (ret == 0) {
ret = sock_ops.reply;
- else
+
+ /* XXX would be nice if we could use replylong[1] here */
+ if (ret == BPF_TCP_INFO_NOTIFY)
+ TCPDIAG_CB(sk);
+ } else
ret = -1;
return ret;
}
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index aa5ccd2..bc45e5e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2678,6 +2678,10 @@ enum {
BPF_TCP_MAX_STATES /* Leave at the end! */
};
+enum {
+ BPF_TCP_INFO_NOTIFY = 2
+};
+
#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */
#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
--
1.7.1
