| Message ID | 9c96424d052af79cfcefeec8bc53b6b541c1900f.1511615658.git.lucien.xin@gmail.com |
|---|---|
| State | Accepted, archived |
| Delegated to: | David Miller |
| Headers | show |
| Series | a couple of fixes for chunks abandoned in prsctp | expand |
On Sat, Nov 25, 2017 at 09:18:34PM +0800, Xin Long wrote: > Now outstanding_bytes is only increased when appending chunks into one > packet and sending it at 1st time, while decreased when it is about to > move into retransmit queue. It means outstanding_bytes value is already > decreased for all chunks in retransmit queue. > > However sctp_prsctp_prune_sent is a common function to check the chunks > in both transmitted and retransmit queue, it decrease outstanding_bytes > when moving a chunk into abandoned queue from either of them. > > It could cause outstanding_bytes underflow, as it also decreases it's > value for the chunks in retransmit queue. > > This patch fixes it by only updating outstanding_bytes for transmitted > queue when pruning queues for prsctp prio policy, the same fix is also > needed in sctp_check_transmitted. > > Fixes: 8dbdf1f5b09c ("sctp: implement prsctp PRIO policy") > Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> > --- > net/sctp/outqueue.c | 6 ++++-- > 1 file changed, 4 insertions(+), 2 deletions(-) > > diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c > index 4db012a..7029f8b 100644 > --- a/net/sctp/outqueue.c > +++ b/net/sctp/outqueue.c > @@ -377,7 +377,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, > asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; > streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; > > - if (!chk->tsn_gap_acked) { > + if (queue != &asoc->outqueue.retransmit && > + !chk->tsn_gap_acked) { > if (chk->transport) > chk->transport->flight_size -= > sctp_data_size(chk); > @@ -1434,7 +1435,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, > /* If this chunk has not been acked, stop > * considering it as 'outstanding'. > */ > - if (!tchunk->tsn_gap_acked) { > + if (transmitted_queue != &q->retransmit && > + !tchunk->tsn_gap_acked) { > if (tchunk->transport) > tchunk->transport->flight_size -= > sctp_data_size(tchunk); > -- > 2.1.0 > > -- > To unsubscribe from this list: send the line "unsubscribe linux-sctp" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html >
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 4db012a..7029f8b 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -377,7 +377,8 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; - if (!chk->tsn_gap_acked) { + if (queue != &asoc->outqueue.retransmit && + !chk->tsn_gap_acked) { if (chk->transport) chk->transport->flight_size -= sctp_data_size(chk); @@ -1434,7 +1435,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, /* If this chunk has not been acked, stop * considering it as 'outstanding'. */ - if (!tchunk->tsn_gap_acked) { + if (transmitted_queue != &q->retransmit && + !tchunk->tsn_gap_acked) { if (tchunk->transport) tchunk->transport->flight_size -= sctp_data_size(tchunk);
Now outstanding_bytes is only increased when appending chunks into one packet and sending it at 1st time, while decreased when it is about to move into retransmit queue. It means outstanding_bytes value is already decreased for all chunks in retransmit queue. However sctp_prsctp_prune_sent is a common function to check the chunks in both transmitted and retransmit queue, it decrease outstanding_bytes when moving a chunk into abandoned queue from either of them. It could cause outstanding_bytes underflow, as it also decreases it's value for the chunks in retransmit queue. This patch fixes it by only updating outstanding_bytes for transmitted queue when pruning queues for prsctp prio policy, the same fix is also needed in sctp_check_transmitted. Fixes: 8dbdf1f5b09c ("sctp: implement prsctp PRIO policy") Signed-off-by: Xin Long <lucien.xin@gmail.com> --- net/sctp/outqueue.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)