From: John Fastabend <john.fastabend@gmail•com>
To: xiyou.wangcong@gmail•com, jhs@mojatatu•com, eric.dumazet@gmail•com
Cc: netdev@vger•kernel.org, davem@davemloft•net
Subject: [RFC PATCH 04/12] net: sched: cls_cgroup use RCU
Date: Fri, 10 Jan 2014 01:38:35 -0800 [thread overview]
Message-ID: <20140110093833.7193.88085.stgit@nitbit.x32> (raw)
In-Reply-To: <20140110092041.7193.5952.stgit@nitbit.x32>
Make cgroup classifier safe for RCU.
Also drops the calls in the classify routine that were doing a
rcu_read_lock()/rcu_read_unlock(). If the rcu_read_lock() isn't held
entering this routine we have issues with deleting the classifier
chain so remove the unnecessary rcu_read_lock()/rcu_read_unlock()
pair noting all paths AFAIK hold rcu_read_lock.
If there is a case where classify is called without the rcu read lock
then an rcu splat will occur and we can correct it.
Signed-off-by: John Fastabend <john.r.fastabend@intel•com>
---
net/sched/cls_cgroup.c | 65 ++++++++++++++++++++++++++++++------------------
1 file changed, 41 insertions(+), 24 deletions(-)
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index f9d21258..7644912 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -118,17 +118,17 @@ struct cls_cgroup_head {
u32 handle;
struct tcf_exts exts;
struct tcf_ematch_tree ematches;
+ struct rcu_head rcu;
+ struct tcf_proto *tp;
};
static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
- struct cls_cgroup_head *head = tp->root;
+ struct cls_cgroup_head *head = rcu_dereference_bh(tp->root);
u32 classid;
- rcu_read_lock();
classid = task_cls_state(current)->classid;
- rcu_read_unlock();
/*
* Due to the nature of the classifier it is required to ignore all
@@ -176,13 +176,27 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
[TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED },
};
+static void cls_cgroup_destroy_rcu(struct rcu_head *root)
+{
+ struct cls_cgroup_head *head = container_of(root,
+ struct cls_cgroup_head,
+ rcu);
+
+ if (head) {
+ tcf_exts_destroy(head->tp, &head->exts);
+ tcf_em_tree_destroy(head->tp, &head->ematches);
+ kfree(head);
+ }
+}
+
static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
unsigned long *arg)
{
struct nlattr *tb[TCA_CGROUP_MAX + 1];
- struct cls_cgroup_head *head = tp->root;
+ struct cls_cgroup_head *head = rtnl_dereference(tp->root);
+ struct cls_cgroup_head *new;
struct tcf_ematch_tree t;
struct tcf_exts e;
int err;
@@ -190,25 +204,24 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
if (!tca[TCA_OPTIONS])
return -EINVAL;
- if (head == NULL) {
- if (!handle)
- return -EINVAL;
+ if (!head && !handle)
+ return -EINVAL;
- head = kzalloc(sizeof(*head), GFP_KERNEL);
- if (head == NULL)
- return -ENOBUFS;
+ if (head && handle != head->handle)
+ return -ENOENT;
- tcf_exts_init(&head->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
- head->handle = handle;
+ new = kzalloc(sizeof(*head), GFP_KERNEL);
+ if (!new)
+ return -ENOBUFS;
- tcf_tree_lock(tp);
- tp->root = head;
- tcf_tree_unlock(tp);
+ if (head) {
+ new->handle = head->handle;
+ } else {
+ tcf_exts_init(&new->exts, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
+ new->handle = handle;
}
- if (handle != head->handle)
- return -ENOENT;
-
+ new->tp = tp;
err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
cgroup_policy);
if (err < 0)
@@ -223,20 +236,24 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
if (err < 0)
return err;
- tcf_exts_change(tp, &head->exts, &e);
- tcf_em_tree_change(tp, &head->ematches, &t);
+ tcf_exts_change(tp, &new->exts, &e);
+ tcf_em_tree_change(tp, &new->ematches, &t);
+ rcu_assign_pointer(tp->root, new);
+ if (head)
+ call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
return 0;
}
static void cls_cgroup_destroy(struct tcf_proto *tp)
{
- struct cls_cgroup_head *head = tp->root;
+ struct cls_cgroup_head *head = rtnl_dereference(tp->root);
if (head) {
tcf_exts_destroy(tp, &head->exts);
tcf_em_tree_destroy(tp, &head->ematches);
- kfree(head);
+ rcu_assign_pointer(tp->root, NULL);
+ kfree_rcu(head, rcu);
}
}
@@ -247,7 +264,7 @@ static int cls_cgroup_delete(struct tcf_proto *tp, unsigned long arg)
static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
- struct cls_cgroup_head *head = tp->root;
+ struct cls_cgroup_head *head = rtnl_dereference(tp->root);
if (arg->count < arg->skip)
goto skip;
@@ -263,7 +280,7 @@ skip:
static int cls_cgroup_dump(struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
- struct cls_cgroup_head *head = tp->root;
+ struct cls_cgroup_head *head = rtnl_dereference(tp->root);
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
next prev parent reply other threads:[~2014-01-10 9:38 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-10 9:36 [RFC PATCH 00/12] RCU'ify the net:sched classifier chains John Fastabend
2014-01-10 9:37 ` [RFC PATCH 01/12] net: qdisc: use rcu prefix and silence sparse warnings John Fastabend
2014-01-10 9:37 ` [RFC PATCH 02/12] net: rcu-ify tcf_proto John Fastabend
2014-01-10 9:38 ` [RFC PATCH 03/12] net: sched: cls_basic use RCU John Fastabend
2014-01-10 9:38 ` John Fastabend [this message]
2014-01-10 9:39 ` [RFC PATCH 05/12] net: sched: cls_flow " John Fastabend
2014-01-10 9:39 ` [RFC PATCH 06/12] net: sched: fw " John Fastabend
2014-01-10 9:41 ` [RFC PATCH 07/12] net: sched: RCU cls_route John Fastabend
2014-01-10 9:42 ` [RFC PATCH 08/12] net: sched: RCU cls_tcindex John Fastabend
2014-01-10 9:42 ` [RFC PATCH 09/12] net: sched: make cls_u32 lockless John Fastabend
2014-01-10 9:43 ` [RFC PATCH 10/12] net: sched: rcu'ify cls_rsvp John Fastabend
2014-01-10 9:43 ` [RFC PATCH 11/12] net: make cls_bpf rcu safe John Fastabend
2014-01-10 9:44 ` [RFC PATCH 12/12] net: sched: make tc_action safe to walk under RCU John Fastabend
2014-01-11 19:43 ` [RFC PATCH 00/12] RCU'ify the net:sched classifier chains Cong Wang
2014-01-11 23:33 ` John Fastabend
2014-04-24 23:51 ` Cong Wang
2014-04-30 16:36 ` John Fastabend
2014-01-12 13:28 ` Jamal Hadi Salim
2014-01-12 13:57 ` Jamal Hadi Salim
2014-01-12 14:18 ` Jamal Hadi Salim
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
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140110093833.7193.88085.stgit@nitbit.x32 \
--to=john.fastabend@gmail$(echo .)com \
--cc=davem@davemloft$(echo .)net \
--cc=eric.dumazet@gmail$(echo .)com \
--cc=jhs@mojatatu$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=xiyou.wangcong@gmail$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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