kernel_optimize_test/net/sched/cls_basic.c
Daniel Borkmann d936377414 net, sched: respect rcu grace period on cls destruction
Roi reported a crash in flower where tp->root was NULL in ->classify()
callbacks. Reason is that in ->destroy() tp->root is set to NULL via
RCU_INIT_POINTER(). It's problematic for some of the classifiers, because
this doesn't respect RCU grace period for them, and as a result, still
outstanding readers from tc_classify() will try to blindly dereference
a NULL tp->root.

The tp->root object is strictly private to the classifier implementation
and holds internal data the core such as tc_ctl_tfilter() doesn't know
about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root
is only checked for NULL in ->get() callback, but nowhere else. This is
misleading and seemed to be copied from old classifier code that was not
cleaned up properly. For example, d3fa76ee6b ("[NET_SCHED]: cls_basic:
fix NULL pointer dereference") moved tp->root initialization into ->init()
routine, where before it was part of ->change(), so ->get() had to deal
with tp->root being NULL back then, so that was indeed a valid case, after
d3fa76ee6b, not really anymore. We used to set tp->root to NULL long
ago in ->destroy(), see 47a1a1d4be ("pkt_sched: remove unnecessary xchg()
in packet classifiers"); but the NULLifying was reintroduced with the
RCUification, but it's not correct for every classifier implementation.

In the cases that are fixed here with one exception of cls_cgroup, tp->root
object is allocated and initialized inside ->init() callback, which is always
performed at a point in time after we allocate a new tp, which means tp and
thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()).
Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy()
handler, same for the tp which is kfree_rcu()'ed right when we return
from ->destroy() in tcf_destroy(). This means, the head object's lifetime
for such classifiers is always tied to the tp lifetime. The RCU callback
invocation for the two kfree_rcu() could be out of order, but that's fine
since both are independent.

Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here
means that 1) we don't need a useless NULL check in fast-path and, 2) that
outstanding readers of that tp in tc_classify() can still execute under
respect with RCU grace period as it is actually expected.

Things that haven't been touched here: cls_fw and cls_route. They each
handle tp->root being NULL in ->classify() path for historic reasons, so
their ->destroy() implementation can stay as is. If someone actually
cares, they could get cleaned up at some point to avoid the test in fast
path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a
!head should anyone actually be using/testing it, so it at least aligns with
cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable
destruction (to a sleepable context) after RCU grace period as concurrent
readers might still access it. (Note that in this case we need to hold module
reference to keep work callback address intact, since we only wait on module
unload for all call_rcu()s to finish.)

This fixes one race to bring RCU grace period guarantees back. Next step
as worked on by Cong however is to fix 1e052be69d ("net_sched: destroy
proto tp when all filters are gone") to get the order of unlinking the tp
in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving
RCU_INIT_POINTER() before tcf_destroy() and let the notification for
removal be done through the prior ->delete() callback. Both are independant
issues. Once we have that right, we can then clean tp->root up for a number
of classifiers by not making them RCU pointers, which requires a new callback
(->uninit) that is triggered from tp's RCU callback, where we just kfree()
tp->root from there.

Fixes: 1f947bf151 ("net: sched: rcu'ify cls_bpf")
Fixes: 9888faefe1 ("net: sched: cls_basic use RCU")
Fixes: 70da9f0bf9 ("net: sched: cls_flow use RCU")
Fixes: 77b9900ef5 ("tc: introduce Flower classifier")
Fixes: bf3994d2ed ("net/sched: introduce Match-all classifier")
Fixes: 952313bd62 ("net: sched: cls_cgroup use RCU")
Reported-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Roi Dayan <roid@mellanox.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-28 10:47:35 -05:00

315 lines
6.8 KiB
C

/*
* net/sched/cls_basic.c Basic Packet Classifier.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Authors: Thomas Graf <tgraf@suug.ch>
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
#include <net/act_api.h>
#include <net/pkt_cls.h>
struct basic_head {
u32 hgenerator;
struct list_head flist;
struct rcu_head rcu;
};
struct basic_filter {
u32 handle;
struct tcf_exts exts;
struct tcf_ematch_tree ematches;
struct tcf_result res;
struct tcf_proto *tp;
struct list_head link;
struct rcu_head rcu;
};
static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res)
{
int r;
struct basic_head *head = rcu_dereference_bh(tp->root);
struct basic_filter *f;
list_for_each_entry_rcu(f, &head->flist, link) {
if (!tcf_em_tree_match(skb, &f->ematches, NULL))
continue;
*res = f->res;
r = tcf_exts_exec(skb, &f->exts, res);
if (r < 0)
continue;
return r;
}
return -1;
}
static unsigned long basic_get(struct tcf_proto *tp, u32 handle)
{
unsigned long l = 0UL;
struct basic_head *head = rtnl_dereference(tp->root);
struct basic_filter *f;
list_for_each_entry(f, &head->flist, link) {
if (f->handle == handle) {
l = (unsigned long) f;
break;
}
}
return l;
}
static int basic_init(struct tcf_proto *tp)
{
struct basic_head *head;
head = kzalloc(sizeof(*head), GFP_KERNEL);
if (head == NULL)
return -ENOBUFS;
INIT_LIST_HEAD(&head->flist);
rcu_assign_pointer(tp->root, head);
return 0;
}
static void basic_delete_filter(struct rcu_head *head)
{
struct basic_filter *f = container_of(head, struct basic_filter, rcu);
tcf_exts_destroy(&f->exts);
tcf_em_tree_destroy(&f->ematches);
kfree(f);
}
static bool basic_destroy(struct tcf_proto *tp, bool force)
{
struct basic_head *head = rtnl_dereference(tp->root);
struct basic_filter *f, *n;
if (!force && !list_empty(&head->flist))
return false;
list_for_each_entry_safe(f, n, &head->flist, link) {
list_del_rcu(&f->link);
tcf_unbind_filter(tp, &f->res);
call_rcu(&f->rcu, basic_delete_filter);
}
kfree_rcu(head, rcu);
return true;
}
static int basic_delete(struct tcf_proto *tp, unsigned long arg)
{
struct basic_filter *f = (struct basic_filter *) arg;
list_del_rcu(&f->link);
tcf_unbind_filter(tp, &f->res);
call_rcu(&f->rcu, basic_delete_filter);
return 0;
}
static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = {
[TCA_BASIC_CLASSID] = { .type = NLA_U32 },
[TCA_BASIC_EMATCHES] = { .type = NLA_NESTED },
};
static int basic_set_parms(struct net *net, struct tcf_proto *tp,
struct basic_filter *f, unsigned long base,
struct nlattr **tb,
struct nlattr *est, bool ovr)
{
int err;
struct tcf_exts e;
struct tcf_ematch_tree t;
err = tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE);
if (err < 0)
return err;
err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
if (err < 0)
goto errout;
err = tcf_em_tree_validate(tp, tb[TCA_BASIC_EMATCHES], &t);
if (err < 0)
goto errout;
if (tb[TCA_BASIC_CLASSID]) {
f->res.classid = nla_get_u32(tb[TCA_BASIC_CLASSID]);
tcf_bind_filter(tp, &f->res, base);
}
tcf_exts_change(tp, &f->exts, &e);
tcf_em_tree_change(tp, &f->ematches, &t);
f->tp = tp;
return 0;
errout:
tcf_exts_destroy(&e);
return err;
}
static int basic_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, unsigned long *arg, bool ovr)
{
int err;
struct basic_head *head = rtnl_dereference(tp->root);
struct nlattr *tb[TCA_BASIC_MAX + 1];
struct basic_filter *fold = (struct basic_filter *) *arg;
struct basic_filter *fnew;
if (tca[TCA_OPTIONS] == NULL)
return -EINVAL;
err = nla_parse_nested(tb, TCA_BASIC_MAX, tca[TCA_OPTIONS],
basic_policy);
if (err < 0)
return err;
if (fold != NULL) {
if (handle && fold->handle != handle)
return -EINVAL;
}
fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
if (!fnew)
return -ENOBUFS;
err = tcf_exts_init(&fnew->exts, TCA_BASIC_ACT, TCA_BASIC_POLICE);
if (err < 0)
goto errout;
err = -EINVAL;
if (handle) {
fnew->handle = handle;
} else if (fold) {
fnew->handle = fold->handle;
} else {
unsigned int i = 0x80000000;
do {
if (++head->hgenerator == 0x7FFFFFFF)
head->hgenerator = 1;
} while (--i > 0 && basic_get(tp, head->hgenerator));
if (i <= 0) {
pr_err("Insufficient number of handles\n");
goto errout;
}
fnew->handle = head->hgenerator;
}
err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr);
if (err < 0)
goto errout;
*arg = (unsigned long)fnew;
if (fold) {
list_replace_rcu(&fold->link, &fnew->link);
tcf_unbind_filter(tp, &fold->res);
call_rcu(&fold->rcu, basic_delete_filter);
} else {
list_add_rcu(&fnew->link, &head->flist);
}
return 0;
errout:
tcf_exts_destroy(&fnew->exts);
kfree(fnew);
return err;
}
static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
struct basic_head *head = rtnl_dereference(tp->root);
struct basic_filter *f;
list_for_each_entry(f, &head->flist, link) {
if (arg->count < arg->skip)
goto skip;
if (arg->fn(tp, (unsigned long) f, arg) < 0) {
arg->stop = 1;
break;
}
skip:
arg->count++;
}
}
static int basic_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
struct sk_buff *skb, struct tcmsg *t)
{
struct basic_filter *f = (struct basic_filter *) fh;
struct nlattr *nest;
if (f == NULL)
return skb->len;
t->tcm_handle = f->handle;
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (f->res.classid &&
nla_put_u32(skb, TCA_BASIC_CLASSID, f->res.classid))
goto nla_put_failure;
if (tcf_exts_dump(skb, &f->exts) < 0 ||
tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
if (tcf_exts_dump_stats(skb, &f->exts) < 0)
goto nla_put_failure;
return skb->len;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static struct tcf_proto_ops cls_basic_ops __read_mostly = {
.kind = "basic",
.classify = basic_classify,
.init = basic_init,
.destroy = basic_destroy,
.get = basic_get,
.change = basic_change,
.delete = basic_delete,
.walk = basic_walk,
.dump = basic_dump,
.owner = THIS_MODULE,
};
static int __init init_basic(void)
{
return register_tcf_proto_ops(&cls_basic_ops);
}
static void __exit exit_basic(void)
{
unregister_tcf_proto_ops(&cls_basic_ops);
}
module_init(init_basic)
module_exit(exit_basic)
MODULE_LICENSE("GPL");