Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To:     linux-kernel@vger.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        stable@vger.kernel.org, Eric Dumazet <edumazet@google.com>,
        "David S. Miller" <davem@davemloft.net>
Subject: [PATCH 4.4 08/92] net_sched: fq: take care of throttled flows before reuse
Date:   Thu, 24 May 2018 11:37:45 +0200
Message-Id: <20180524093200.019659107@linuxfoundation.org>
In-Reply-To: <20180524093159.286472249@linuxfoundation.org>
References: <20180524093159.286472249@linuxfoundation.org>
User-Agent: quilt/0.65
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 7df40c2673a1307c3260aab6f9d4b9bf97ca8fd7 ]

Normally, a socket can not be freed/reused unless all its TX packets
left qdisc and were TX-completed. However connect(AF_UNSPEC) allows
this to happen.

With commit fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for
reused flows") we cleared f->time_next_packet but took no special
action if the flow was still in the throttled rb-tree.

Since f->time_next_packet is the key used in the rb-tree searches,
blindly clearing it might break rb-tree integrity. We need to make
sure the flow is no longer in the rb-tree to avoid this problem.

Fixes: fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for reused flows")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 net/sched/sch_fq.c |   37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -126,6 +126,28 @@ static bool fq_flow_is_detached(const st
 	return f->next == &detached;
 }
 
+static bool fq_flow_is_throttled(const struct fq_flow *f)
+{
+	return f->next == &throttled;
+}
+
+static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
+{
+	if (head->first)
+		head->last->next = flow;
+	else
+		head->first = flow;
+	head->last = flow;
+	flow->next = NULL;
+}
+
+static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f)
+{
+	rb_erase(&f->rate_node, &q->delayed);
+	q->throttled_flows--;
+	fq_flow_add_tail(&q->old_flows, f);
+}
+
 static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f)
 {
 	struct rb_node **p = &q->delayed.rb_node, *parent = NULL;
@@ -153,15 +175,6 @@ static void fq_flow_set_throttled(struct
 
 static struct kmem_cache *fq_flow_cachep __read_mostly;
 
-static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow)
-{
-	if (head->first)
-		head->last->next = flow;
-	else
-		head->first = flow;
-	head->last = flow;
-	flow->next = NULL;
-}
 
 /* limit number of collected flows per round */
 #define FQ_GC_MAX 8
@@ -265,6 +278,8 @@ static struct fq_flow *fq_classify(struc
 				     f->socket_hash != sk->sk_hash)) {
 				f->credit = q->initial_quantum;
 				f->socket_hash = sk->sk_hash;
+				if (fq_flow_is_throttled(f))
+					fq_flow_unset_throttled(q, f);
 				f->time_next_packet = 0ULL;
 			}
 			return f;
@@ -419,9 +434,7 @@ static void fq_check_throttled(struct fq
 			q->time_next_delayed_flow = f->time_next_packet;
 			break;
 		}
-		rb_erase(p, &q->delayed);
-		q->throttled_flows--;
-		fq_flow_add_tail(&q->old_flows, f);
+		fq_flow_unset_throttled(q, f);
 	}
 }