Cake - FQ_codel the next generation
 help / color / mirror / Atom feed
From: "Toke Høiland-Jørgensen" <toke@toke.dk>
To: netdev@vger.kernel.org
Cc: cake@lists.bufferbloat.net,
	"Toke Høiland-Jørgensen" <toke@redhat.com>,
	"Pete Heist" <pete@heistp.net>
Subject: [Cake] [PATCH 2/4] sched: Fix detection of empty queues in child qdiscs
Date: Mon,  7 Jan 2019 20:47:31 +0100	[thread overview]
Message-ID: <20190107194733.31138-3-toke@toke.dk> (raw)
In-Reply-To: <20190107194733.31138-1-toke@toke.dk>

From: Toke Høiland-Jørgensen <toke@redhat.com>

Several qdiscs check on enqueue whether the packet was enqueued to a class
with an empty queue, in which case the class is activated. This is done by
checking if the qlen is exactly 1 after enqueue. However, if GSO splitting
is enabled in the child qdisc, a single packet can result in a qlen longer
than 1. This means the activation check fails, leading to a stalled queue.

Fix this by checking if the queue is empty *before* enqueue, and running
the activation logic if this was the case.

Reported-by: Pete Heist <pete@heistp.net>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 net/sched/sch_drr.c  | 4 +++-
 net/sched/sch_hfsc.c | 4 +++-
 net/sched/sch_qfq.c  | 4 +++-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index feaf47178653..09b800991065 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -354,6 +354,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl;
 	int err = 0;
+	bool first;
 
 	cl = drr_classify(skb, sch, &err);
 	if (cl == NULL) {
@@ -363,6 +364,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return err;
 	}
 
+	first = !cl->qdisc->q.qlen;
 	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
@@ -372,7 +374,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return err;
 	}
 
-	if (cl->qdisc->q.qlen == 1) {
+	if (first) {
 		list_add_tail(&cl->alist, &q->active);
 		cl->deficit = cl->quantum;
 	}
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 6bb8f73a8473..24cc220a3218 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1542,6 +1542,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 	unsigned int len = qdisc_pkt_len(skb);
 	struct hfsc_class *cl;
 	int uninitialized_var(err);
+	bool first;
 
 	cl = hfsc_classify(skb, sch, &err);
 	if (cl == NULL) {
@@ -1551,6 +1552,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 		return err;
 	}
 
+	first = !cl->qdisc->q.qlen;
 	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
@@ -1560,7 +1562,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 		return err;
 	}
 
-	if (cl->qdisc->q.qlen == 1) {
+	if (first) {
 		if (cl->cl_flags & HFSC_RSC)
 			init_ed(cl, len);
 		if (cl->cl_flags & HFSC_FSC)
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 8d5e55d5bed2..29f5c4a24688 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1215,6 +1215,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct qfq_class *cl;
 	struct qfq_aggregate *agg;
 	int err = 0;
+	bool first;
 
 	cl = qfq_classify(skb, sch, &err);
 	if (cl == NULL) {
@@ -1236,6 +1237,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
+	first = !cl->qdisc->q.qlen;
 	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
@@ -1253,7 +1255,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	agg = cl->agg;
 	/* if the queue was not empty, then done here */
-	if (cl->qdisc->q.qlen != 1) {
+	if (!first) {
 		if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) &&
 		    list_first_entry(&agg->active, struct qfq_class, alist)
 		    == cl && cl->deficit < len)
-- 
2.20.1


  parent reply	other threads:[~2019-01-07 19:48 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-07 19:47 [Cake] [PATCH 0/4] sched: Fix qdisc interactions exposed by using sch_cake as a leaf qdisc Toke Høiland-Jørgensen
2019-01-07 19:47 ` [Cake] [PATCH 1/4] sched: Avoid dereferencing skb pointer after child enqueue Toke Høiland-Jørgensen
2019-01-09  1:38   ` Cong Wang
2019-01-09  8:14     ` Toke Høiland-Jørgensen
2019-01-10 18:16       ` Cong Wang
2019-01-07 19:47 ` Toke Høiland-Jørgensen [this message]
2019-01-07 19:57   ` [Cake] [PATCH 2/4] sched: Fix detection of empty queues in child qdiscs Dave Taht
2019-01-07 19:47 ` [Cake] [PATCH 3/4] sch_api: Allow reducing queue backlog by a negative value Toke Høiland-Jørgensen
2019-01-07 20:54   ` Eric Dumazet
2019-01-08  9:55     ` Toke Høiland-Jørgensen
2019-01-07 19:47 ` [Cake] [PATCH 4/4] sch_cake: Correctly update parent qlen when splitting GSO packets Toke Høiland-Jørgensen
2019-01-08 21:30 ` [Cake] [PATCH 0/4] sched: Fix qdisc interactions exposed by using sch_cake as a leaf qdisc David Miller
2019-01-09  8:37   ` Toke Høiland-Jørgensen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://lists.bufferbloat.net/postorius/lists/cake.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190107194733.31138-3-toke@toke.dk \
    --to=toke@toke.dk \
    --cc=cake@lists.bufferbloat.net \
    --cc=netdev@vger.kernel.org \
    --cc=pete@heistp.net \
    --cc=toke@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox