From: John Fastabend <john.fastabend@gmail.com>
To: xiyou.wangcong@gmail.com, jhs@mojatatu.com
Cc: netdev@vger.kernel.org, davem@davemloft.net
Subject: [RCU PATCH 04/14] net: sched: cls_cgroup use RCU
Date: Mon, 10 Mar 2014 10:04:54 -0700 [thread overview]
Message-ID: <20140310170452.3011.33596.stgit@nitbit.x32> (raw)
In-Reply-To: <20140310170008.3011.73599.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 8e2158a..4919978 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -22,17 +22,17 @@ 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
@@ -80,13 +80,27 @@ 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;
@@ -94,25 +108,24 @@ 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)
@@ -127,20 +140,24 @@ 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);
}
}
@@ -151,7 +168,7 @@ 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;
@@ -167,7 +184,7 @@ skip:
static int cls_cgroup_dump(struct net *net, 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:[~2014-03-10 17:05 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-10 17:03 [RCU PATCH 00/14] Remove qdisc lock around ingress Qdisc John Fastabend
2014-03-10 17:03 ` [RCU PATCH 01/14] net: qdisc: use rcu prefix and silence sparse warnings John Fastabend
2014-03-10 17:20 ` Eric Dumazet
2014-03-10 17:04 ` [RCU PATCH 02/14] net: rcu-ify tcf_proto John Fastabend
2014-03-10 17:30 ` Eric Dumazet
2014-03-10 17:04 ` [RCU PATCH 03/14] net: sched: cls_basic use RCU John Fastabend
2014-03-10 17:33 ` Eric Dumazet
2014-03-10 17:04 ` John Fastabend [this message]
2014-03-10 17:36 ` [RCU PATCH 04/14] net: sched: cls_cgroup " Eric Dumazet
2014-03-10 17:05 ` [RCU PATCH 05/14] net: sched: cls_flow " John Fastabend
2014-03-10 17:38 ` Eric Dumazet
2014-03-10 17:05 ` [RCU PATCH 06/14] net: sched: fw " John Fastabend
2014-03-10 17:41 ` Eric Dumazet
2014-03-12 16:41 ` John Fastabend
2014-03-12 17:01 ` Eric Dumazet
2014-03-13 20:22 ` Paul E. McKenney
2014-03-13 20:56 ` Eric Dumazet
2014-03-13 21:15 ` Paul E. McKenney
2014-03-14 5:43 ` John Fastabend
2014-03-14 13:28 ` Paul E. McKenney
2014-03-14 13:46 ` Eric Dumazet
2014-03-14 15:38 ` Paul E. McKenney
2014-03-14 18:50 ` Paul E. McKenney
2014-03-14 18:59 ` Paul E. McKenney
2014-03-14 19:55 ` Eric Dumazet
2014-03-14 20:35 ` Paul E. McKenney
2014-03-16 16:06 ` [PATCH net-next] net: sched: use no more than one page in struct fw_head Eric Dumazet
2014-03-17 13:51 ` Thomas Graf
2014-03-17 14:13 ` Eric Dumazet
2014-03-17 14:29 ` David Laight
2014-03-17 15:16 ` Eric Dumazet
2014-03-17 15:30 ` Thomas Graf
2014-03-17 15:33 ` Eric Dumazet
2014-03-17 15:43 ` David Laight
2014-03-17 15:52 ` Eric Dumazet
2014-03-17 15:28 ` Thomas Graf
2014-03-17 15:50 ` Thomas Graf
2014-03-17 16:00 ` David Laight
2014-03-17 16:16 ` Eric Dumazet
2014-03-18 2:31 ` David Miller
2014-03-18 3:02 ` Eric Dumazet
2014-03-18 3:20 ` [PATCH v2 " Eric Dumazet
2014-03-18 9:19 ` Thomas Graf
2014-03-18 18:18 ` David Miller
2014-03-10 17:06 ` [RCU PATCH 07/14] net: sched: RCU cls_route John Fastabend
2014-03-10 17:45 ` Eric Dumazet
2014-03-10 19:36 ` John Fastabend
2014-03-10 17:06 ` [RCU PATCH 08/14] net: sched: RCU cls_tcindex John Fastabend
2014-03-10 17:07 ` [RCU PATCH 09/14] net: sched: make cls_u32 lockless John Fastabend
2014-03-10 17:58 ` Eric Dumazet
2014-03-10 17:07 ` [RCU PATCH 10/14] net: sched: rcu'ify cls_rsvp John Fastabend
2014-03-10 17:07 ` [RCU PATCH 11/14] net: make cls_bpf rcu safe John Fastabend
2014-03-10 17:08 ` [RCU PATCH 12/14] net: sched: make tc_action safe to walk under RCU John Fastabend
2014-03-10 17:08 ` [RCU PATCH 13/14] net: sched: make bstats per cpu and estimator RCU safe John Fastabend
2014-03-10 18:06 ` Eric Dumazet
2014-03-10 19:36 ` John Fastabend
2014-03-10 17:09 ` [RCU PATCH 14/14] net: sched: drop ingress qdisc lock John Fastabend
2014-03-11 20:36 ` [RCU PATCH 00/14] Remove qdisc lock around ingress Qdisc David Miller
2014-03-11 20:53 ` Eric Dumazet
2014-03-12 6:58 ` Jamal Hadi Salim
2014-03-12 16:45 ` John Fastabend
2014-03-13 8:44 ` Jamal Hadi Salim
2014-03-14 7:28 ` John Fastabend
2014-03-14 7:45 ` Jamal Hadi Salim
2014-03-12 18:25 ` Cong Wang
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=20140310170452.3011.33596.stgit@nitbit.x32 \
--to=john.fastabend@gmail.com \
--cc=davem@davemloft.net \
--cc=jhs@mojatatu.com \
--cc=netdev@vger.kernel.org \
--cc=xiyou.wangcong@gmail.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;
as well as URLs for NNTP newsgroup(s).