summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2015-04-23 10:42:39 -0700
committerJiri Slaby <jslaby@suse.cz>2015-04-30 13:28:09 +0200
commit90a176dc03dc495e17a34edb12bade9ce481d238 (patch)
treebbd4dfb897255cb92f30a59ba2ecf3f93e86e4a6 /net
parent3644030ff70814406747455e2997cb5d000a8bf7 (diff)
tcp: avoid looping in tcp_send_fin()
[ Upstream commit 845704a535e9b3c76448f52af1b70e4422ea03fd ] Presence of an unbound loop in tcp_send_fin() had always been hard to explain when analyzing crash dumps involving gigantic dying processes with millions of sockets. Lets try a different strategy : In case of memory pressure, try to add the FIN flag to last packet in write queue, even if packet was already sent. TCP stack will be able to deliver this FIN after a timeout event. Note that this FIN being delivered by a retransmit, it also carries a Push flag given our current implementation. By checking sk_under_memory_pressure(), we anticipate that cooking many FIN packets might deplete tcp memory. In the case we could not allocate a packet, even with __GFP_WAIT allocation, then not sending a FIN seems quite reasonable if it allows to get rid of this socket, free memory, and not block the process from eventually doing other useful work. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/tcp_output.c50
1 files changed, 29 insertions, 21 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 59d4f17b1992..47b27e9dd8cc 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2583,7 +2583,8 @@ begin_fwd:
/* We allow to exceed memory limits for FIN packets to expedite
* connection tear down and (memory) recovery.
- * Otherwise tcp_send_fin() could loop forever.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
*/
static void sk_forced_wmem_schedule(struct sock *sk, int size)
{
@@ -2596,33 +2597,40 @@ static void sk_forced_wmem_schedule(struct sock *sk, int size)
sk_memory_allocated_add(sk, amt, &status);
}
-/* Send a fin. The caller locks the socket for us. This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
*/
void tcp_send_fin(struct sock *sk)
{
+ struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb = tcp_write_queue_tail(sk);
- int mss_now;
- /* Optimization, tack on the FIN if we have a queue of
- * unsent frames. But be careful about outgoing SACKS
- * and IP options.
+ /* Optimization, tack on the FIN if we have one skb in write queue and
+ * this skb was not yet sent, or we are under memory pressure.
+ * Note: in the latter case, FIN packet will be sent after a timeout,
+ * as TCP stack thinks it has already been transmitted.
*/
- mss_now = tcp_current_mss(sk);
-
- if (tcp_send_head(sk) != NULL) {
- TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
- TCP_SKB_CB(skb)->end_seq++;
+ if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+ TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+ TCP_SKB_CB(tskb)->end_seq++;
tp->write_seq++;
+ if (!tcp_send_head(sk)) {
+ /* This means tskb was already sent.
+ * Pretend we included the FIN on previous transmit.
+ * We need to set tp->snd_nxt to the value it would have
+ * if FIN had been sent. This is because retransmit path
+ * does not change tp->snd_nxt.
+ */
+ tp->snd_nxt++;
+ return;
+ }
} else {
- /* Socket is locked, keep trying until memory is available. */
- for (;;) {
- skb = alloc_skb_fclone(MAX_TCP_HEADER,
- sk->sk_allocation);
- if (skb)
- break;
- yield();
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+ if (unlikely(!skb)) {
+ if (tskb)
+ goto coalesce;
+ return;
}
skb_reserve(skb, MAX_TCP_HEADER);
sk_forced_wmem_schedule(sk, skb->truesize);
@@ -2631,7 +2639,7 @@ void tcp_send_fin(struct sock *sk)
TCPHDR_ACK | TCPHDR_FIN);
tcp_queue_skb(sk, skb);
}
- __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+ __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
}
/* We get here when a process closes a file descriptor (either due to