ipv6: make ip6_rt_gc_expire an atomic_t

Reads and Writes to ip6_rt_gc_expire always have been racy,
as syzbot reported lately [1]

There is a possible risk of under-flow, leading
to unexpected high value passed to fib6_run_gc(),
although I have not observed this in the field.

Hosts hitting ip6_dst_gc() very hard are under pretty bad
state anyway.

[1]
BUG: KCSAN: data-race in ip6_dst_gc / ip6_dst_gc

read-write to 0xffff888102110744 of 4 bytes by task 13165 on cpu 1:
 ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311
 dst_alloc+0x9b/0x160 net/core/dst.c:86
 ip6_dst_alloc net/ipv6/route.c:344 [inline]
 icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261
 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807
 mld_send_cr net/ipv6/mcast.c:2119 [inline]
 mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651
 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289
 worker_thread+0x618/0xa70 kernel/workqueue.c:2436
 kthread+0x1a9/0x1e0 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30

read-write to 0xffff888102110744 of 4 bytes by task 11607 on cpu 0:
 ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311
 dst_alloc+0x9b/0x160 net/core/dst.c:86
 ip6_dst_alloc net/ipv6/route.c:344 [inline]
 icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261
 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807
 mld_send_cr net/ipv6/mcast.c:2119 [inline]
 mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651
 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289
 worker_thread+0x618/0xa70 kernel/workqueue.c:2436
 kthread+0x1a9/0x1e0 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30

value changed: 0x00000bb3 -> 0x00000ba9

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 11607 Comm: kworker/0:21 Not tainted 5.18.0-rc1-syzkaller-00037-g42e7a03d3bad-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: mld mld_ifc_work

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20220413181333.649424-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 3d83b64471d32391fb632e8c25e12a8ec7d1b42e..b4af4837d80b4ed47d05474432d5b8ebb42322e7 100644 (file)
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -75,8 +75,8 @@ struct netns_ipv6 {
        struct list_head        fib6_walkers;
        rwlock_t                fib6_walker_lock;
        spinlock_t              fib6_gc_lock;
-       unsigned int             ip6_rt_gc_expire;
-       unsigned long            ip6_rt_last_gc;
+       atomic_t                ip6_rt_gc_expire;
+       unsigned long           ip6_rt_last_gc;
        unsigned char           flowlabel_has_excl;
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
        bool                    fib6_has_custom_rules;

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 169e9df6d172ead607cc20a108c3371a20dbc632..c4b6ce017d5e3bf63c66a53df3d46c08370aed23 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3292,6 +3292,7 @@ static int ip6_dst_gc(struct dst_ops *ops)
        int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
        int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
        unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
+       unsigned int val;
        int entries;
 
        entries = dst_entries_get_fast(ops);
@@ -3302,13 +3303,13 @@ static int ip6_dst_gc(struct dst_ops *ops)
            entries <= rt_max_size)
                goto out;
 
-       net->ipv6.ip6_rt_gc_expire++;
-       fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true);
+       fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true);
        entries = dst_entries_get_slow(ops);
        if (entries < ops->gc_thresh)
-               net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
+               atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1);
 out:
-       net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
+       val = atomic_read(&net->ipv6.ip6_rt_gc_expire);
+       atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity));
        return entries > rt_max_size;
 }
 
@@ -6509,7 +6510,7 @@ static int __net_init ip6_route_net_init(struct net *net)
        net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
        net->ipv6.sysctl.skip_notify_on_dev_down = 0;
 
-       net->ipv6.ip6_rt_gc_expire = 30*HZ;
+       atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ);
 
        ret = 0;
 out: