net: rcu-ify tcf_proto

rcu'ify tcf_proto this allows calling tc_classify() without holding
any locks. Updaters are protected by RTNL.

This patch prepares the core net_sched infrastracture for running
the classifier/action chains without holding the qdisc lock however
it does nothing to ensure cls_xxx and act_xxx types also work without
locking. Additional patches are required to address the fall out.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 15 insertions, 15 deletions

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c28b0d327b12..e547efdaba9d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -117,7 +117,6 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
-	spinlock_t *root_lock;
 	struct tcmsg *t;
 	u32 protocol;
 	u32 prio;
@@ -125,7 +124,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 parent;
 	struct net_device *dev;
 	struct Qdisc  *q;
-	struct tcf_proto **back, **chain;
+	struct tcf_proto __rcu **back;
+	struct tcf_proto __rcu **chain;
 	struct tcf_proto *tp;
 	const struct tcf_proto_ops *tp_ops;
 	const struct Qdisc_class_ops *cops;
@@ -197,7 +197,9 @@ replay:
 		goto errout;
 
 	/* Check the chain for existence of proto-tcf with this priority */
-	for (back = chain; (tp = *back) != NULL; back = &tp->next) {
+	for (back = chain;
+	     (tp = rtnl_dereference(*back)) != NULL;
+	     back = &tp->next) {
 		if (tp->prio >= prio) {
 			if (tp->prio == prio) {
 				if (!nprio ||
@@ -209,8 +211,6 @@ replay:
 		}
 	}
 
-	root_lock = qdisc_root_sleeping_lock(q);
-
 	if (tp == NULL) {
 		/* Proto-tcf does not exist, create new one */
 
@@ -259,7 +259,8 @@ replay:
 		}
 		tp->ops = tp_ops;
 		tp->protocol = protocol;
-		tp->prio = nprio ? : TC_H_MAJ(tcf_auto_prio(*back));
+		tp->prio = nprio ? :
+			       TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back)));
 		tp->q = q;
 		tp->classify = tp_ops->classify;
 		tp->classid = parent;
@@ -280,9 +281,9 @@ replay:
 
 	if (fh == 0) {
 		if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
-			spin_lock_bh(root_lock);
-			*back = tp->next;
-			spin_unlock_bh(root_lock);
+			struct tcf_proto *next = rtnl_dereference(tp->next);
+
+			RCU_INIT_POINTER(*back, next);
 
 			tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER);
 			tcf_destroy(tp);
@@ -322,10 +323,8 @@ replay:
 			      n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE);
 	if (err == 0) {
 		if (tp_created) {
-			spin_lock_bh(root_lock);
-			tp->next = *back;
-			*back = tp;
-			spin_unlock_bh(root_lock);
+			RCU_INIT_POINTER(tp->next, rtnl_dereference(*back));
+			rcu_assign_pointer(*back, tp);
 		}
 		tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER);
 	} else {
@@ -420,7 +419,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	int s_t;
 	struct net_device *dev;
 	struct Qdisc *q;
-	struct tcf_proto *tp, **chain;
+	struct tcf_proto *tp, __rcu **chain;
 	struct tcmsg *tcm = nlmsg_data(cb->nlh);
 	unsigned long cl = 0;
 	const struct Qdisc_class_ops *cops;
@@ -454,7 +453,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 
 	s_t = cb->args[0];
 
-	for (tp = *chain, t = 0; tp; tp = tp->next, t++) {
+	for (tp = rtnl_dereference(*chain), t = 0;
+	     tp; tp = rtnl_dereference(tp->next), t++) {
 		if (t < s_t)
 			continue;
 		if (TC_H_MAJ(tcm->tcm_info) &&