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>
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index f3d339f..d65e9215 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -587,20 +587,20 @@
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 4c09a31..3244133 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -601,6 +601,7 @@
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 @@
}
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 82fb43c..07de855 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -17,7 +17,7 @@
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 @@
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 dea3f92..705eccf 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3033,7 +3033,7 @@
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) {