From f8d9605243280f1870dd2c6c37a735b925c15f3c Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 7 Jul 2011 00:28:35 +0000 Subject: sctp: Enforce retransmission limit during shutdown When initiating a graceful shutdown while having data chunks on the retransmission queue with a peer which is in zero window mode the shutdown is never completed because the retransmission error count is reset periodically by the following two rules: - Do not timeout association while doing zero window probe. - Reset overall error count when a heartbeat request has been acknowledged. The graceful shutdown will wait for all outstanding TSN to be acknowledged before sending the SHUTDOWN request. This never happens due to the peer's zero window not acknowledging the continuously retransmitted data chunks. Although the error counter is incremented for each failed retransmission, the receiving of the SACK announcing the zero window clears the error count again immediately. Also heartbeat requests continue to be sent periodically. The peer acknowledges these requests causing the error counter to be reset as well. This patch changes behaviour to only reset the overall error counter for the above rules while not in shutdown. After reaching the maximum number of retransmission attempts, the T5 shutdown guard timer is scheduled to give the receiver some additional time to recover. The timer is stopped as soon as the receiver acknowledges any data. The issue can be easily reproduced by establishing a sctp association over the loopback device, constantly queueing data at the sender while not reading any at the receiver. Wait for the window to reach zero, then initiate a shutdown by killing both processes simultaneously. The association will never be freed and the chunks on the retransmission queue will be retransmitted indefinitely. Signed-off-by: Thomas Graf Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/outqueue.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'net/sctp/outqueue.c') diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 1c88c8911dc5..d03682109b7a 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1582,6 +1582,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, #endif /* SCTP_DEBUG */ if (transport) { if (bytes_acked) { + struct sctp_association *asoc = transport->asoc; + /* We may have counted DATA that was migrated * to this transport due to DEL-IP operation. * Subtract those bytes, since the were never @@ -1600,6 +1602,17 @@ static void sctp_check_transmitted(struct sctp_outq *q, transport->error_count = 0; transport->asoc->overall_error_count = 0; + /* + * While in SHUTDOWN PENDING, we may have started + * the T5 shutdown guard timer after reaching the + * retransmission limit. Stop that timer as soon + * as the receiver acknowledged any data. + */ + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && + del_timer(&asoc->timers + [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) + sctp_association_put(asoc); + /* Mark the destination transport address as * active if it is not so marked. */ @@ -1629,10 +1642,15 @@ static void sctp_check_transmitted(struct sctp_outq *q, * A sender is doing zero window probing when the * receiver's advertised window is zero, and there is * only one data chunk in flight to the receiver. + * + * Allow the association to timeout while in SHUTDOWN + * PENDING or SHUTDOWN RECEIVED in case the receiver + * stays in zero window mode forever. */ if (!q->asoc->peer.rwnd && !list_empty(&tlist) && - (sack_ctsn+2 == q->asoc->next_tsn)) { + (sack_ctsn+2 == q->asoc->next_tsn) && + q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) { SCTP_DEBUG_PRINTK("%s: SACK received for zero " "window probe: %u\n", __func__, sack_ctsn); -- cgit v1.2.3-58-ga151