[net-next PATCH 7/9] bpf: sockmap indicate sock events to listeners
flat view
STALE3344d
From: John Fastabend <john.fastabend@gmail.com>
Date: 2017-08-28 14:12:15
Subsystem:
bpf [general] (safe dynamic programs and tools), the rest · Maintainers:
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko, Eduard Zingerman, Kumar Kartikeya Dwivedi, Linus Torvalds
After userspace pushes sockets into a sockmap it may not be receiving
data (assuming stream_{parser|verdict} programs are attached). But, it
may still want to manage the socks. A common pattern is to poll/select
for a POLLRDHUP event so we can close the sock.
This patch adds the logic to wake up these listeners.
Also add TCP_SYN_SENT to the list of events to handle. We don't want
to break the connection just because we happen to be in this state.
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
---
kernel/bpf/sockmap.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 38bf4e4..bcc326a 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c@@ -162,6 +162,7 @@ static void smap_state_change(struct sock *sk) { struct smap_psock_map_entry *e, *tmp; struct smap_psock *psock; + struct socket_wq *wq; struct sock *osk; rcu_read_lock();
@@ -171,6 +172,7 @@ static void smap_state_change(struct sock *sk) * is established. */ switch (sk->sk_state) { + case TCP_SYN_SENT: case TCP_SYN_RECV: case TCP_ESTABLISHED: break;
@@ -208,6 +210,10 @@ static void smap_state_change(struct sock *sk) smap_report_sk_error(psock, EPIPE); break; } + + wq = rcu_dereference(sk->sk_wq); + if (skwq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); rcu_read_unlock(); }