Hi Tomas
Some minor nits and one substantial issue. See below.
On a related note, were you going to re-submit the receiver patch as well?
On 07/04/2011 09:50 AM, Thomas Graf wrote:
>
> diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
> index 1c88c89..0ae911f 100644
> --- a/net/sctp/outqueue.c
> +++ b/net/sctp/outqueue.c
> @@ -1582,6 +1582,9 @@ static void sctp_check_transmitted(struct sctp_outq *q,
> #endif /* SCTP_DEBUG */
> if (transport) {
> if (bytes_acked) {
> + struct sctp_association *asoc = transport->asoc;
> + struct timer_list *t;
> +
> /* 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 +1603,17 @@ 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.
> + */
> + t = &asoc->timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD];
> + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING &&
> + timer_pending(t) && del_timer(t))
> + sctp_association_put(asoc);
> +
I believe 'state' and 'timers' are in different cache lines, so might be able to optimize it
a little by checking the state prior to referencing timers array.
> /* Mark the destination transport address as
> * active if it is not so marked.
> */
> @@ -1629,10 +1643,15 @@ 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 if SHUTDOWN is
> + * pending 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)) {
Would a test for (q->asoc->state != SCTP_STATE_SHUTDOWN_PENDING) be clearer? We only
care about the PENDING state here.
> SCTP_DEBUG_PRINTK("%s: SACK received for zero "
> "window probe: %u\n",
> __func__, sack_ctsn);
> diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
> index 534c2e5..fa92f4d6 100644
> --- a/net/sctp/sm_sideeffect.c
> +++ b/net/sctp/sm_sideeffect.c
> @@ -670,10 +670,21 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds,
> /* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the
> * HEARTBEAT should clear the error counter of the destination
> * transport address to which the HEARTBEAT was sent.
> - * The association's overall error count is also cleared.
> */
> t->error_count = 0;
> - t->asoc->overall_error_count = 0;
> +
> + /*
> + * Although RFC2960 and RFC4460 specify that the overall error
> + * count must be cleared when a HEARTBEAT ACK is received this
> + * behaviour may prevent the maximum retransmission count from
> + * being reached while in SHUTDOWN. If the peer keeps its window
> + * closed not acknowledging any outstanding TSN we may rely on
> + * reaching the max_retrans limit via the T3-rtx timer to close
> + * the association which will never happen if the error count is
> + * reset every heartbeat interval.
> + */
> + if (!(t->asoc->state >= SCTP_STATE_SHUTDOWN_PENDING))
> + t->asoc->overall_error_count = 0;
Same here. We only care about the PENDING state. Also, please fix the comment to reflect
the code.
>
> /* Clear the hb_sent flag to signal that we had a good
> * acknowledgement.
> diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
> index a297283..e6a0c35 100644
> --- a/net/sctp/sm_statefuns.c
> +++ b/net/sctp/sm_statefuns.c
> @@ -5154,7 +5154,7 @@ sctp_disposition_t sctp_sf_do_9_2_start_shutdown(
> * The sender of the SHUTDOWN MAY also start an overall guard timer
> * 'T5-shutdown-guard' to bound the overall time for shutdown sequence.
> */
> - sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START,
> + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART,
> SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD));
>
> if (asoc->autoclose)
> @@ -5299,14 +5299,28 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(const struct sctp_endpoint *ep,
> SCTP_INC_STATS(SCTP_MIB_T3_RTX_EXPIREDS);
>
> if (asoc->overall_error_count >= asoc->max_retrans) {
> - sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
> - SCTP_ERROR(ETIMEDOUT));
> - /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */
> - sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
> - SCTP_PERR(SCTP_ERROR_NO_ERROR));
> - SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
> - SCTP_DEC_STATS(SCTP_MIB_CURRESTAB);
> - return SCTP_DISPOSITION_DELETE_TCB;
> + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) {
> + /*
> + * We are here likely because the receiver had its rwnd
> + * closed for a while and we have not been able to
> + * transmit the locally queued data within the maximum
> + * retransmission attempts limit. Start the T5
> + * shutdown guard timer to give the receiver one last
> + * chance and some additional time to recover before
> + * aborting.
> + */
> + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART,
> + SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD));
This is bug. You don't want to restart the timer every time you hit a T3-timeout. Remember, since you fall
through here, you do another retransmission and schedule another timeout. So next time the timeout happens,
you'll restart the SHUTDOWN_GUARD, which is not what you want.
We want to start it once if it isn't pending, and leave it running without restart if it is already pending.
-vlad
> + } else {
> + sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
> + SCTP_ERROR(ETIMEDOUT));
> + /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */
> + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
> + SCTP_PERR(SCTP_ERROR_NO_ERROR));
> + SCTP_INC_STATS(SCTP_MIB_ABORTEDS);
> + SCTP_DEC_STATS(SCTP_MIB_CURRESTAB);
> + return SCTP_DISPOSITION_DELETE_TCB;
> + }
> }
>
> /* E1) For the destination address for which the timer
> diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
> index 0338dc6..7c211a7 100644
> --- a/net/sctp/sm_statetable.c
> +++ b/net/sctp/sm_statetable.c
> @@ -827,7 +827,7 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_
> /* SCTP_STATE_ESTABLISHED */ \
> TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
> /* SCTP_STATE_SHUTDOWN_PENDING */ \
> - TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
> + TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \
> /* SCTP_STATE_SHUTDOWN_SENT */ \
> TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \
> /* SCTP_STATE_SHUTDOWN_RECEIVED */ \
>
--
To unsubscribe from this list: send the line "unsubscribe linux-sctp" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
