[Patch net-next 1/2] net_sched: fix a race condition in tcindex_destroy()

[Patch net-next 1/2] net_sched: fix a race condition in tcindex_destroy()

[Cong Wang]

(cherry picked from commit 8015d93ebd27484418d4952284fd02172fa4b0b2)

tcindex_destroy() invokes tcindex_destroy_element() via
a walker to delete each filter result in its perfect hash
table, and tcindex_destroy_element() calls tcindex_delete()
which schedules tcf RCU works to do the final deletion work.
Unfortunately this races with the RCU callback
__tcindex_destroy(), which could lead to use-after-free as
reported by Adrian.

Fix this by migrating this RCU callback to tcf RCU work too,
as that workqueue is ordered, we will not have use-after-free.

Note, we don't need to hold netns refcnt because we don't call
tcf_exts_destroy() here.

Fixes: 27ce4f05e2ab ("net_sched: use tcf_queue_work() in tcindex filter")
Reported-by: Adrian <bugs@abtelecom.ro>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
---
 net/sched/cls_tcindex.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index e1981628047b..81a433ae31b3 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -48,7 +48,7 @@ struct tcindex_data {
 	u32 hash;		/* hash table size; 0 if undefined */
 	u32 alloc_hash;		/* allocated size */
 	u32 fall_through;	/* 0: only classify if explicit match */
-	struct rcu_head rcu;
+	struct rcu_work rwork;
 };
 
 static inline int tcindex_filter_is_set(struct tcindex_filter_result *r)
@@ -229,9 +229,11 @@ static int tcindex_destroy_element(struct tcf_proto *tp,
 	return tcindex_delete(tp, arg, &last, false, NULL);
 }
 
-static void __tcindex_destroy(struct rcu_head *head)
+static void tcindex_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p->h);
@@ -258,9 +260,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r)
 	return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 }
 
-static void __tcindex_partial_destroy(struct rcu_head *head)
+static void tcindex_partial_destroy_work(struct work_struct *work)
 {
-	struct tcindex_data *p = container_of(head, struct tcindex_data, rcu);
+	struct tcindex_data *p = container_of(to_rcu_work(work),
+					      struct tcindex_data,
+					      rwork);
 
 	kfree(p->perfect);
 	kfree(p);
@@ -480,7 +484,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	}
 
 	if (oldp)
-		call_rcu(&oldp->rcu, __tcindex_partial_destroy);
+		tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work);
 	return 0;
 
 errout_alloc:
@@ -572,7 +576,7 @@ static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
 	walker.fn = tcindex_destroy_element;
 	tcindex_walk(tp, &walker, true);
 
-	call_rcu(&p->rcu, __tcindex_destroy);
+	tcf_queue_work(&p->rwork, tcindex_destroy_work);
 }
 
 
-- 
2.20.1

[Patch net-next 2/2] net_sched: fix a memory leak in cls_tcindex

[Cong Wang]

(cherry picked from commit 033b228e7f26b29ae37f8bfa1bc6b209a5365e9f)

When tcindex_destroy() destroys all the filter results in
the perfect hash table, it invokes the walker to delete
each of them. However, results with class==0 are skipped
in either tcindex_walk() or tcindex_delete(), which causes
a memory leak reported by kmemleak.

This patch fixes it by skipping the walker and directly
deleting these filter results so we don't miss any filter
result.

As a result of this change, we have to initialize exts->net
properly in tcindex_alloc_perfect_hash(). For net-next, we
need to consider whether we should initialize ->net in
tcf_exts_init() instead, before that just directly test
CONFIG_NET_CLS_ACT=y.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
---
 net/sched/cls_tcindex.c | 37 ++++++++++++++++++++++++-------------
 1 file changed, 24 insertions(+), 13 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 81a433ae31b3..fbf3519a12d8 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -221,14 +221,6 @@ static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last,
 	return 0;
 }
 
-static int tcindex_destroy_element(struct tcf_proto *tp,
-				   void *arg, struct tcf_walker *walker)
-{
-	bool last;
-
-	return tcindex_delete(tp, arg, &last, false, NULL);
-}
-
 static void tcindex_destroy_work(struct work_struct *work)
 {
 	struct tcindex_data *p = container_of(to_rcu_work(work),
@@ -568,13 +560,32 @@ static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held,
 			    struct netlink_ext_ack *extack)
 {
 	struct tcindex_data *p = rtnl_dereference(tp->root);
-	struct tcf_walker walker;
+	int i;
 
 	pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p);
-	walker.count = 0;
-	walker.skip = 0;
-	walker.fn = tcindex_destroy_element;
-	tcindex_walk(tp, &walker, true);
+
+	if (p->perfect) {
+		for (i = 0; i < p->hash; i++) {
+			struct tcindex_filter_result *r = p->perfect + i;
+
+			tcf_unbind_filter(tp, &r->res);
+			if (tcf_exts_get_net(&r->exts))
+				tcf_queue_work(&r->rwork,
+					       tcindex_destroy_rexts_work);
+			else
+				__tcindex_destroy_rexts(r);
+		}
+	}
+
+	for (i = 0; p->h && i < p->hash; i++) {
+		struct tcindex_filter *f, *next;
+		bool last;
+
+		for (f = rtnl_dereference(p->h[i]); f; f = next) {
+			next = rtnl_dereference(f->next);
+			tcindex_delete(tp, &f->result, &last, rtnl_held, NULL);
+		}
+	}
 
 	tcf_queue_work(&p->rwork, tcindex_destroy_work);
 }
-- 
2.20.1

Re: [Patch net-next 1/2] net_sched: fix a race condition in tcindex_destroy()

[David Miller]

From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 16 Feb 2019 10:58:26 -0800

> (cherry picked from commit 8015d93ebd27484418d4952284fd02172fa4b0b2)
> 
> tcindex_destroy() invokes tcindex_destroy_element() via
> a walker to delete each filter result in its perfect hash
> table, and tcindex_destroy_element() calls tcindex_delete()
> which schedules tcf RCU works to do the final deletion work.
> Unfortunately this races with the RCU callback
> __tcindex_destroy(), which could lead to use-after-free as
> reported by Adrian.
> 
> Fix this by migrating this RCU callback to tcf RCU work too,
> as that workqueue is ordered, we will not have use-after-free.
> 
> Note, we don't need to hold netns refcnt because we don't call
> tcf_exts_destroy() here.
> 
> Fixes: 27ce4f05e2ab ("net_sched: use tcf_queue_work() in tcindex filter")
> Reported-by: Adrian <bugs@abtelecom.ro>
> Cc: Ben Hutchings <ben@decadent.org.uk>
> Cc: Jamal Hadi Salim <jhs@mojatatu.com>
> Cc: Jiri Pirko <jiri@resnulli.us>
> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>

Applied.

Re: [Patch net-next 2/2] net_sched: fix a memory leak in cls_tcindex

[David Miller]

From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 16 Feb 2019 10:58:27 -0800

> (cherry picked from commit 033b228e7f26b29ae37f8bfa1bc6b209a5365e9f)
> 
> When tcindex_destroy() destroys all the filter results in
> the perfect hash table, it invokes the walker to delete
> each of them. However, results with class==0 are skipped
> in either tcindex_walk() or tcindex_delete(), which causes
> a memory leak reported by kmemleak.
> 
> This patch fixes it by skipping the walker and directly
> deleting these filter results so we don't miss any filter
> result.
> 
> As a result of this change, we have to initialize exts->net
> properly in tcindex_alloc_perfect_hash(). For net-next, we
> need to consider whether we should initialize ->net in
> tcf_exts_init() instead, before that just directly test
> CONFIG_NET_CLS_ACT=y.
> 
> Cc: Jamal Hadi Salim <jhs@mojatatu.com>
> Cc: Jiri Pirko <jiri@resnulli.us>
> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>

Applied.