ipv4: irq safe sk_dst_[re]set() and ipv4_sk_update_pmtu() fix

We have two different ways to handle changes to sk->sk_dst

First way (used by TCP) assumes socket lock is owned by caller, and use
no extra lock : __sk_dst_set() & __sk_dst_reset()

Another way (used by UDP) uses sk_dst_lock because socket lock is not
always taken. Note that sk_dst_lock is not softirq safe.

These ways are not inter changeable for a given socket type.

ipv4_sk_update_pmtu(), added in linux-3.8, added a race, as it used
the socket lock as synchronization, but users might be UDP sockets.

Instead of converting sk_dst_lock to a softirq safe version, use xchg()
as we did for sk_rx_dst in commit e47eb5dfb296b ("udp: ipv4: do not use
sk_dst_lock from softirq context")

In a follow up patch, we probably can remove sk_dst_lock, as it is
only used in IPv6.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Fixes: 9cb3a50c5f63e ("ipv4: Invalidate the socket cached route on pmtu events if possible")
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 7 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 082239ffe34a..3162ea923ded 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1010,7 +1010,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
         const struct iphdr *iph = (const struct iphdr *) skb->data;
         struct flowi4 fl4;
         struct rtable *rt;
-        struct dst_entry *dst;
+        struct dst_entry *odst = NULL;
         bool new = false;
 
         bh_lock_sock(sk);
@@ -1018,16 +1018,17 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
         if (!ip_sk_accept_pmtu(sk))
                 goto out;
 
-        rt = (struct rtable *) __sk_dst_get(sk);
+        odst = sk_dst_get(sk);
 
-        if (sock_owned_by_user(sk) || !rt) {
+        if (sock_owned_by_user(sk) || !odst) {
                 __ipv4_sk_update_pmtu(skb, sk, mtu);
                 goto out;
         }
 
         __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
 
-        if (!__sk_dst_check(sk, 0)) {
+        rt = (struct rtable *)odst;
+        if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
                 rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
                 if (IS_ERR(rt))
                         goto out;
@@ -1037,8 +1038,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 
         __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
 
-        dst = dst_check(&rt->dst, 0);
-        if (!dst) {
+        if (!dst_check(&rt->dst, 0)) {
                 if (new)
                         dst_release(&rt->dst);
 
@@ -1050,10 +1050,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
         }
 
         if (new)
-                __sk_dst_set(sk, &rt->dst);
+                sk_dst_set(sk, &rt->dst);
 
 out:
         bh_unlock_sock(sk);
+        dst_release(odst);
 }
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);