[PATCH 3/4] sctp: fix association hangs due to errors when reneging events from the ordering queue

[PATCH 3/4] sctp: fix association hangs due to errors when reneging events from the ordering queue

[Roberts, Lee A.]

From: Lee A. Roberts <lee.roberts@hp.com>

Resolve SCTP association hangs observed during SCTP stress
testing.  Observable symptoms include communications hangs
with data being held in the association reassembly and/or lobby
(ordering) queues.  Close examination of reassembly queue shows
missing packets.

In sctp_ulpq_renege_list(), events being reneged from the
ordering queue may correspond to multiple TSNs.  Identify
all affected packets; sum freed space and renege from the
tsnmap.

Patch applies to linux-3.8 kernel.

Signed-off-by: Lee A. Roberts <lee.roberts@hp.com>
---
 net/sctp/ulpqueue.c |   26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff -uprN -X linux-3.8-vanilla/Documentation/dontdiff linux-3.8-SCTP+2/net/sctp/ulpqueue.c linux-3.8-SCTP+3/net/sctp/ulpqueue.c
--- linux-3.8-SCTP+2/net/sctp/ulpqueue.c	2013-02-21 07:39:40.888281496 -0700
+++ linux-3.8-SCTP+3/net/sctp/ulpqueue.c	2013-02-21 07:55:32.817713326 -0700
@@ -962,8 +962,8 @@ static __u16 sctp_ulpq_renege_list(struc
 		struct sk_buff_head *list, __u16 needed)
 {
 	__u16 freed = 0;
-	__u32 tsn;
-	struct sk_buff *skb;
+	__u32 tsn, last_tsn;
+	struct sk_buff *skb, *flist, *last;
 	struct sctp_ulpevent *event;
 	struct sctp_tsnmap *tsnmap;
 
@@ -977,10 +977,28 @@ static __u16 sctp_ulpq_renege_list(struc
 		if (TSN_lte(tsn, sctp_tsnmap_get_ctsn(tsnmap)))
 			break;
 
-		__skb_unlink(skb, list);
+		/* Events in ordering queue may have multiple fragments
+		 * corresponding to additional TSNs.  Sum the total
+		 * freed space; find the last TSN.
+		 */
 		freed += skb_headlen(skb);
+		flist = skb_shinfo(skb)->frag_list;
+		for (last = flist; flist; flist = flist->next) {
+			last = flist;
+			freed += skb_headlen(last);
+		}
+		if (last)
+			last_tsn = sctp_skb2event(last)->tsn;
+		else
+			last_tsn = tsn;
+
+		/* Unlink the event, then renege all applicable TSNs. */
+		__skb_unlink(skb, list);
 		sctp_ulpevent_free(event);
-		sctp_tsnmap_renege(tsnmap, tsn);
+		while (TSN_lte(tsn, last_tsn)) {
+			sctp_tsnmap_renege(tsnmap, tsn);
+			tsn++;
+		}
 		if (freed >= needed)
 			return freed;
 	}

Re: [PATCH 3/4] sctp: fix association hangs due to errors when reneging events from the ordering queue

[Vlad Yasevich]

On 02/21/2013 11:44 AM, Roberts, Lee A. wrote:
> From: Lee A. Roberts <lee.roberts@hp.com>
>
> Resolve SCTP association hangs observed during SCTP stress
> testing.  Observable symptoms include communications hangs
> with data being held in the association reassembly and/or lobby
> (ordering) queues.  Close examination of reassembly queue shows
> missing packets.
>
> In sctp_ulpq_renege_list(), events being reneged from the
> ordering queue may correspond to multiple TSNs.  Identify
> all affected packets; sum freed space and renege from the
> tsnmap.
>
> Patch applies to linux-3.8 kernel.
>
> Signed-off-by: Lee A. Roberts <lee.roberts@hp.com>

Acked-by: Vlad Yasevich <vyasevich@gmail.com>

-vlad

> ---
>   net/sctp/ulpqueue.c |   26 ++++++++++++++++++++++----
>   1 file changed, 22 insertions(+), 4 deletions(-)
>
> diff -uprN -X linux-3.8-vanilla/Documentation/dontdiff linux-3.8-SCTP+2/net/sctp/ulpqueue.c linux-3.8-SCTP+3/net/sctp/ulpqueue.c
> --- linux-3.8-SCTP+2/net/sctp/ulpqueue.c	2013-02-21 07:39:40.888281496 -0700
> +++ linux-3.8-SCTP+3/net/sctp/ulpqueue.c	2013-02-21 07:55:32.817713326 -0700
> @@ -962,8 +962,8 @@ static __u16 sctp_ulpq_renege_list(struc
>   		struct sk_buff_head *list, __u16 needed)
>   {
>   	__u16 freed = 0;
> -	__u32 tsn;
> -	struct sk_buff *skb;
> +	__u32 tsn, last_tsn;
> +	struct sk_buff *skb, *flist, *last;
>   	struct sctp_ulpevent *event;
>   	struct sctp_tsnmap *tsnmap;
>
> @@ -977,10 +977,28 @@ static __u16 sctp_ulpq_renege_list(struc
>   		if (TSN_lte(tsn, sctp_tsnmap_get_ctsn(tsnmap)))
>   			break;
>
> -		__skb_unlink(skb, list);
> +		/* Events in ordering queue may have multiple fragments
> +		 * corresponding to additional TSNs.  Sum the total
> +		 * freed space; find the last TSN.
> +		 */
>   		freed += skb_headlen(skb);
> +		flist = skb_shinfo(skb)->frag_list;
> +		for (last = flist; flist; flist = flist->next) {
> +			last = flist;
> +			freed += skb_headlen(last);
> +		}
> +		if (last)
> +			last_tsn = sctp_skb2event(last)->tsn;
> +		else
> +			last_tsn = tsn;
> +
> +		/* Unlink the event, then renege all applicable TSNs. */
> +		__skb_unlink(skb, list);
>   		sctp_ulpevent_free(event);
> -		sctp_tsnmap_renege(tsnmap, tsn);
> +		while (TSN_lte(tsn, last_tsn)) {
> +			sctp_tsnmap_renege(tsnmap, tsn);
> +			tsn++;
> +		}
>   		if (freed >= needed)
>   			return freed;
>   	}
> --
> 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
>

[PATCH 0/4] sctp: fix association hangs due to reassembly/ordering logic

[Lee A. Roberts]

From: "Lee A. Roberts" <lee.roberts@hp.com>

This series of patches resolves several SCTP association hangs observed during
SCTP stress testing.  Observable symptoms include communications hangs with
data being held in the association reassembly and/or lobby (ordering) queues.
Close examination of reassembly/ordering queues may show either duplicated
or missing packets.

Lee A. Roberts (4):
  sctp: fix association hangs due to off-by-one errors in
    sctp_tsnmap_grow()
  sctp: fix association hangs due to reneging packets below the
    cumulative TSN ACK point
  sctp: fix association hangs due to errors when reneging events from
    the ordering queue
  sctp: fix association hangs due to partial delivery errors

 net/sctp/tsnmap.c   |   13 ++++----
 net/sctp/ulpqueue.c |   87 +++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 78 insertions(+), 22 deletions(-)

-- 
1.7.9.5

[PATCH 3/4] sctp: fix association hangs due to errors when reneging events from the ordering queue

[Lee A. Roberts]

From: "Lee A. Roberts" <lee.roberts@hp.com>

Resolve SCTP association hangs observed during SCTP stress
testing.  Observable symptoms include communications hangs
with data being held in the association reassembly and/or lobby
(ordering) queues.  Close examination of reassembly queue shows
missing packets.

In sctp_ulpq_renege_list(), events being reneged from the
ordering queue may correspond to multiple TSNs.  Identify
all affected packets; sum freed space and renege from the
tsnmap.

Signed-off-by: Lee A. Roberts <lee.roberts@hp.com>
---
 net/sctp/ulpqueue.c |   26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 63afddc..f221fbb 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -962,8 +962,8 @@ static __u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq,
 		struct sk_buff_head *list, __u16 needed)
 {
 	__u16 freed = 0;
-	__u32 tsn;
-	struct sk_buff *skb;
+	__u32 tsn, last_tsn;
+	struct sk_buff *skb, *flist, *last;
 	struct sctp_ulpevent *event;
 	struct sctp_tsnmap *tsnmap;
 
@@ -977,10 +977,28 @@ static __u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq,
 		if (TSN_lte(tsn, sctp_tsnmap_get_ctsn(tsnmap)))
 			break;
 
-		__skb_unlink(skb, list);
+		/* Events in ordering queue may have multiple fragments
+		 * corresponding to additional TSNs.  Sum the total
+		 * freed space; find the last TSN.
+		 */
 		freed += skb_headlen(skb);
+		flist = skb_shinfo(skb)->frag_list;
+		for (last = flist; flist; flist = flist->next) {
+			last = flist;
+			freed += skb_headlen(last);
+		}
+		if (last)
+			last_tsn = sctp_skb2event(last)->tsn;
+		else
+			last_tsn = tsn;
+
+		/* Unlink the event, then renege all applicable TSNs. */
+		__skb_unlink(skb, list);
 		sctp_ulpevent_free(event);
-		sctp_tsnmap_renege(tsnmap, tsn);
+		while (TSN_lte(tsn, last_tsn)) {
+			sctp_tsnmap_renege(tsnmap, tsn);
+			tsn++;
+		}
 		if (freed >= needed)
 			return freed;
 	}
-- 
1.7.9.5

Re: [PATCH 3/4] sctp: fix association hangs due to errors when reneging events from the ordering queue

[Vlad Yasevich]

On 02/26/2013 09:36 AM, Lee A. Roberts wrote:
> From: "Lee A. Roberts" <lee.roberts@hp.com>
>
> Resolve SCTP association hangs observed during SCTP stress
> testing.  Observable symptoms include communications hangs
> with data being held in the association reassembly and/or lobby
> (ordering) queues.  Close examination of reassembly queue shows
> missing packets.
>
> In sctp_ulpq_renege_list(), events being reneged from the
> ordering queue may correspond to multiple TSNs.  Identify
> all affected packets; sum freed space and renege from the
> tsnmap.
>
> Signed-off-by: Lee A. Roberts <lee.roberts@hp.com>

Acked-by: Vlad Yasevich <vyasevich@gmail.com>

-vlad

> ---
>   net/sctp/ulpqueue.c |   26 ++++++++++++++++++++++----
>   1 file changed, 22 insertions(+), 4 deletions(-)
>
> diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
> index 63afddc..f221fbb 100644
> --- a/net/sctp/ulpqueue.c
> +++ b/net/sctp/ulpqueue.c
> @@ -962,8 +962,8 @@ static __u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq,
>   		struct sk_buff_head *list, __u16 needed)
>   {
>   	__u16 freed = 0;
> -	__u32 tsn;
> -	struct sk_buff *skb;
> +	__u32 tsn, last_tsn;
> +	struct sk_buff *skb, *flist, *last;
>   	struct sctp_ulpevent *event;
>   	struct sctp_tsnmap *tsnmap;
>
> @@ -977,10 +977,28 @@ static __u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq,
>   		if (TSN_lte(tsn, sctp_tsnmap_get_ctsn(tsnmap)))
>   			break;
>
> -		__skb_unlink(skb, list);
> +		/* Events in ordering queue may have multiple fragments
> +		 * corresponding to additional TSNs.  Sum the total
> +		 * freed space; find the last TSN.
> +		 */
>   		freed += skb_headlen(skb);
> +		flist = skb_shinfo(skb)->frag_list;
> +		for (last = flist; flist; flist = flist->next) {
> +			last = flist;
> +			freed += skb_headlen(last);
> +		}
> +		if (last)
> +			last_tsn = sctp_skb2event(last)->tsn;
> +		else
> +			last_tsn = tsn;
> +
> +		/* Unlink the event, then renege all applicable TSNs. */
> +		__skb_unlink(skb, list);
>   		sctp_ulpevent_free(event);
> -		sctp_tsnmap_renege(tsnmap, tsn);
> +		while (TSN_lte(tsn, last_tsn)) {
> +			sctp_tsnmap_renege(tsnmap, tsn);
> +			tsn++;
> +		}
>   		if (freed >= needed)
>   			return freed;
>   	}
>