net: add a noref bit on skb dst

Use low order bit of skb->_skb_dst to tell dst is not refcounted.

Change _skb_dst to _skb_refdst to make sure all uses are catched.

skb_dst() returns the dst, regardless of noref bit set or not, but
with a lockdep check to make sure a noref dst is not given if current
user is not rcu protected.

New skb_dst_set_noref() helper to set an notrefcounted dst on a skb.
(with lockdep check)

skb_dst_drop() drops a reference only if skb dst was refcounted.

skb_dst_force() helper is used to force a refcount on dst, when skb
is queued and not anymore RCU protected.

Use skb_dst_force() in __sk_add_backlog(), __dev_xmit_skb() if
!IFF_XMIT_DST_RELEASE or skb enqueued on qdisc queue, in
sock_queue_rcv_skb(), in __nf_queue().

Use skb_dst_force() in dev_requeue_skb().

Note: dst_use_noref() still dirties dst, we might transform it
later to do one dirtying per jiffies.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 27 insertions, 13 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index cdcb9cbedf41..6c820650b80f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2052,6 +2052,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 		 * waiting to be sent out; and the qdisc is not running -
 		 * xmit the skb directly.
 		 */
+		if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
+			skb_dst_force(skb);
 		__qdisc_update_bstats(q, skb->len);
 		if (sch_direct_xmit(skb, q, dev, txq, root_lock))
 			__qdisc_run(q);
@@ -2060,6 +2062,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 		rc = NET_XMIT_SUCCESS;
 	} else {
+		skb_dst_force(skb);
 		rc = qdisc_enqueue_root(skb, q);
 		qdisc_run(q);
 	}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a9b0e1f77806..c543dd252433 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -520,7 +520,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->transport_header	= old->transport_header;
 	new->network_header	= old->network_header;
 	new->mac_header		= old->mac_header;
-	skb_dst_set(new, dst_clone(skb_dst(old)));
+	skb_dst_copy(new, old);
 	new->rxhash		= old->rxhash;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
diff --git a/net/core/sock.c b/net/core/sock.c
index 63530a03b8c2..bf88a167c8f2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -307,6 +307,11 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	skb_len = skb->len;
 
+	/* we escape from rcu protected region, make sure we dont leak
+	 * a norefcounted dst
+	 */
+	skb_dst_force(skb);
+
 	spin_lock_irqsave(&list->lock, flags);
 	skb->dropcount = atomic_read(&sk->sk_drops);
 	__skb_queue_tail(list, skb);
@@ -1536,6 +1541,7 @@ static void __release_sock(struct sock *sk)
 		do {
 			struct sk_buff *next = skb->next;
 
+			WARN_ON_ONCE(skb_dst_is_noref(skb));
 			skb->next = NULL;
 			sk_backlog_rcv(sk, skb);
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index f3d339f728b0..d65e9215bcd7 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -587,20 +587,20 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 			err = __ip_route_output_key(net, &rt2, &fl);
 		else {
 			struct flowi fl2 = {};
-			struct dst_entry *odst;
+			unsigned long orefdst;
 
 			fl2.fl4_dst = fl.fl4_src;
 			if (ip_route_output_key(net, &rt2, &fl2))
 				goto relookup_failed;
 
 			/* Ugh! */
-			odst = skb_dst(skb_in);
+			orefdst = skb_in->_skb_refdst; /* save old refdst */
 			err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src,
 					     RT_TOS(tos), rt2->u.dst.dev);
 
 			dst_release(&rt2->u.dst);
 			rt2 = skb_rtable(skb_in);
-			skb_dst_set(skb_in, odst);
+			skb_in->_skb_refdst = orefdst; /* restore old refdst */
 		}
 
 		if (err)
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 4c09a31fd140..3244133c24f6 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -601,6 +601,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 	unsigned char *optptr = skb_network_header(skb) + opt->srr;
 	struct rtable *rt = skb_rtable(skb);
 	struct rtable *rt2;
+	unsigned long orefdst;
 	int err;
 
 	if (!opt->srr)
@@ -624,16 +625,16 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 		}
 		memcpy(&nexthop, &optptr[srrptr-1], 4);
 
-		rt = skb_rtable(skb);
+		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
 		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
-			ip_rt_put(rt2);
-			skb_dst_set(skb, &rt->u.dst);
+			skb_dst_drop(skb);
+			skb->_skb_refdst = orefdst;
 			return -EINVAL;
 		}
-		ip_rt_put(rt);
+		refdst_drop(orefdst);
 		if (rt2->rt_type != RTN_LOCAL)
 			break;
 		/* Superfast 8) loopback forward */
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 82fb43c5c59e..07de855e2175 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -17,7 +17,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct flowi fl = {};
-	struct dst_entry *odst;
+	unsigned long orefdst;
 	unsigned int hh_len;
 	unsigned int type;
 
@@ -51,14 +51,14 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 		if (ip_route_output_key(net, &rt, &fl) != 0)
 			return -1;
 
-		odst = skb_dst(skb);
+		orefdst = skb->_skb_refdst;
 		if (ip_route_input(skb, iph->daddr, iph->saddr,
 				   RT_TOS(iph->tos), rt->u.dst.dev) != 0) {
 			dst_release(&rt->u.dst);
 			return -1;
 		}
 		dst_release(&rt->u.dst);
-		dst_release(odst);
+		refdst_drop(orefdst);
 	}
 
 	if (skb_dst(skb)->error)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index dea3f9264250..705eccfb4769 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3033,7 +3033,7 @@ int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
 				continue;
 			if (rt_is_expired(rt))
 				continue;
-			skb_dst_set(skb, dst_clone(&rt->u.dst));
+			skb_dst_set_noref(skb, &rt->u.dst);
 			if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
 					 cb->nlh->nlmsg_seq, RTM_NEWROUTE,
 					 1, NLM_F_MULTI) <= 0) {
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 0b1103c0b1f3..78b3cf9c519c 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -9,6 +9,7 @@
 #include <linux/rcupdate.h>
 #include <net/protocol.h>
 #include <net/netfilter/nf_queue.h>
+#include <net/dst.h>
 
 #include "nf_internals.h"
 
@@ -170,6 +171,7 @@ static int __nf_queue(struct sk_buff *skb,
 			dev_hold(physoutdev);
 	}
 #endif
+	skb_dst_force(skb);
 	afinfo->saveroute(skb, entry);
 	status = qh->outfn(entry, queuenum);
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a969b111bd76..a63029ef3edd 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -26,6 +26,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <net/pkt_sched.h>
+#include <net/dst.h>
 
 /* Main transmission queue. */
 
@@ -40,6 +41,7 @@
 
 static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
+	skb_dst_force(skb);
 	q->gso_skb = skb;
 	q->qstats.requeues++;
 	q->q.qlen++;	/* it's still part of the queue */
@@ -179,7 +181,7 @@ static inline int qdisc_restart(struct Qdisc *q)
 	skb = dequeue_skb(q);
 	if (unlikely(!skb))
 		return 0;
-
+	WARN_ON_ONCE(skb_dst_is_noref(skb));
 	root_lock = qdisc_lock(q);
 	dev = qdisc_dev(q);
 	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));