ipv6: fixes rt6_probe() and fib6_nh->last_probe init

[ Upstream commit 1bef4c223b8588cf50433bdc2c6953d82949b3b3 ]

While looking at a syzbot KCSAN report [1], I found multiple
issues in this code :

1) fib6_nh->last_probe has an initial value of 0.

   While probably okay on 64bit kernels, this causes an issue
   on 32bit kernels since the time_after(jiffies, 0 + interval)
   might be false ~24 days after boot (for HZ=1000)

2) The data-race found by KCSAN
   I could use READ_ONCE() and WRITE_ONCE(), but we also can
   take the opportunity of not piling-up too many rt6_probe_deferred()
   works by using instead cmpxchg() so that only one cpu wins the race.

[1]
BUG: KCSAN: data-race in find_match / find_match

write to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 1:
 rt6_probe net/ipv6/route.c:663 [inline]
 find_match net/ipv6/route.c:757 [inline]
 find_match+0x5bd/0x790 net/ipv6/route.c:733
 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831
 find_rr_leaf net/ipv6/route.c:852 [inline]
 rt6_select net/ipv6/route.c:896 [inline]
 fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164
 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200
 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452
 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117
 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484
 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497
 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049
 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150
 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106
 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169
 tcp_transmit_skb net/ipv4/tcp_output.c:1185 [inline]
 tcp_xmit_probe_skb+0x19b/0x1d0 net/ipv4/tcp_output.c:3735

read to 0xffff8880bb7aabe8 of 8 bytes by interrupt on cpu 0:
 rt6_probe net/ipv6/route.c:657 [inline]
 find_match net/ipv6/route.c:757 [inline]
 find_match+0x521/0x790 net/ipv6/route.c:733
 __find_rr_leaf+0xe3/0x780 net/ipv6/route.c:831
 find_rr_leaf net/ipv6/route.c:852 [inline]
 rt6_select net/ipv6/route.c:896 [inline]
 fib6_table_lookup+0x383/0x650 net/ipv6/route.c:2164
 ip6_pol_route+0xee/0x5c0 net/ipv6/route.c:2200
 ip6_pol_route_output+0x48/0x60 net/ipv6/route.c:2452
 fib6_rule_lookup+0x3d6/0x470 net/ipv6/fib6_rules.c:117
 ip6_route_output_flags_noref+0x16b/0x230 net/ipv6/route.c:2484
 ip6_route_output_flags+0x50/0x1a0 net/ipv6/route.c:2497
 ip6_dst_lookup_tail+0x25d/0xc30 net/ipv6/ip6_output.c:1049
 ip6_dst_lookup_flow+0x68/0x120 net/ipv6/ip6_output.c:1150
 inet6_csk_route_socket+0x2f7/0x420 net/ipv6/inet6_connection_sock.c:106
 inet6_csk_xmit+0x91/0x1f0 net/ipv6/inet6_connection_sock.c:121
 __tcp_transmit_skb+0xe81/0x1d60 net/ipv4/tcp_output.c:1169

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 18894 Comm: udevd Not tainted 5.4.0-rc3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: cc3a86c802f0 ("ipv6: Change rt6_probe to take a fib6_nh")
Fixes: f547fac624be ("ipv6: rate-limit probes for neighbourless routes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c885863..076c21f 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -521,6 +521,7 @@ static void rt6_probe(struct fib6_info *rt)
 {
        struct __rt6_probe_work *work = NULL;
        const struct in6_addr *nh_gw;
+       unsigned long last_probe;
        struct neighbour *neigh;
        struct net_device *dev;
        struct inet6_dev *idev;
@@ -539,6 +540,7 @@ static void rt6_probe(struct fib6_info *rt)
        nh_gw = &rt->fib6_nh.nh_gw;
        dev = rt->fib6_nh.nh_dev;
        rcu_read_lock_bh();
+       last_probe = READ_ONCE(rt->last_probe);
        idev = __in6_dev_get(dev);
        neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
        if (neigh) {
@@ -554,13 +556,15 @@ static void rt6_probe(struct fib6_info *rt)
                                __neigh_set_probe_once(neigh);
                }
                write_unlock(&neigh->lock);
-       } else if (time_after(jiffies, rt->last_probe +
+       } else if (time_after(jiffies, last_probe +
                                       idev->cnf.rtr_probe_interval)) {
                work = kmalloc(sizeof(*work), GFP_ATOMIC);
        }
 
-       if (work) {
-               rt->last_probe = jiffies;
+       if (!work || cmpxchg(&rt->last_probe,
+                            last_probe, jiffies) != last_probe) {
+               kfree(work);
+       } else {
                INIT_WORK(&work->work, rt6_probe_deferred);
                work->target = *nh_gw;
                dev_hold(dev);
@@ -3066,6 +3070,9 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
        if (!rt)
                goto out;
 
+#ifdef CONFIG_IPV6_ROUTER_PREF
+       rt->last_probe = jiffies;
+#endif
        if (cfg->fc_flags & RTF_ADDRCONF)
                rt->dst_nocount = true;