ipv4: fix race in concurrent ip_route_input_slow()
Subsystems (3)
PATCH 1/1 ipv4: fix race in concurrent ip_route_input_slow()
CPUs can ask for local route via ip_route_input_noref() concurrently. if nh_rth_input is not cached yet, CPUs will proceed to allocate equivalent DSTs on 'lo' and then will try to cache them in nh_rth_input via rt_cache_route()
Most of the time they succeed, but on occasion the following two lines:
orig = *p; prev = cmpxchg(p, orig, rt);
in rt_cache_route() do race and one of the cpus fails to complete cmpxchg. But ip_route_input_slow() doesn't check the return code of rt_cache_route(), so dst is leaking. dst_destroy() is never called and 'lo' device refcnt doesn't go to zero, which can be seen in the logs as:
unregister_netdevice: waiting for lo to become free. Usage count = 1
Adding mdelay() between above two lines makes it easily reproducible. Fix it similar to nh_pcpu_rth_output case.
---
David,
looks like caacf05e5ad1 ("ipv4: Properly purge netdev references on uncached routes.") fixed the race for nexthop/rth_output, but missed it for rth_input.
I'm not sure what was the assumption why it's not needed there.
We're definitely seeing it every 12-24hr during nightly tests.
There are several bugs on ubuntu and debian forums with similar description. Some were closed, since folks struggled to reproduce it.
It took us more than a month to debug it.
Please queue for stable.
Alternative fix:
rt_free(rth); goto local_input;
imo is uglier.
Just like rt_free(rth) followed by re-read of nh_rth_input and re-check_valid
net/ipv4/route.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
net/ipv4/route.c +6 -2
@@ -1776,8 +1776,12 @@ local_input: rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL ; } -if (do_cache) -rt_cache_route (&FIB_RES_NH (res), rth); +if (do_cache) { +if (unlikely (!rt_cache_route (&FIB_RES_NH (res), rth))) { + rth->dst.flags |=DST_NOCACHE ; +rt_add_uncached_list (rth); + } + }skb_dst_set (skb, &rth->dst); err =0 ; goto out;
Signature · 1 line
1.7.9.5
David Miller
maintainerFrom: Alexei Starovoitov <[email protected]>
Date: Tue, 19 Nov 2013 19:12:34 -0800
Quoted 21 lines
CPUs can ask for local route via
ip_route_input_noref()concurrently. ifnh_rth_inputis not cached yet, CPUs will proceed to allocate equivalent DSTs on 'lo' and then will try to cache them innh_rth_inputviart_cache_route()
Most of the time they succeed, but on occasion the following two lines:orig = *p; prev = cmpxchg(p, orig, rt);in
rt_cache_route()do race and one of the cpus fails to complete cmpxchg. Butip_route_input_slow()doesn't check the return code ofrt_cache_route(), so dst is leaking.dst_destroy()is never called and 'lo' device refcnt doesn't go to zero, which can be seen in the logs as:
unregister_netdevice: waiting for lo to become free. Usage count = 1
Addingmdelay()between above two lines makes it easily reproducible. Fix it similar tonh_pcpu_rth_outputcase.Fixes d2d68ba9fe8b ("ipv4: Cache input routes in fib_info nexthops.")Signed-off-by Alexei Starovoitov <[email protected]>---
David,
Quoted 8 lines
looks like
caacf05e5ad1("ipv4: Properly purge netdev references on uncached routes.") fixed the race for nexthop/rth_output, but missed it forrth_input.
I'm not sure what was the assumption why it's not needed there.
We're definitely seeing it every 12-24hr during nightly tests.
There are several bugs on ubuntu and debian forums with similar description. Some were closed, since folks struggled to reproduce it.
It took us more than a month to debug it.
Please queue for stable.
Your analysis is accurate and your fix is absolutely correct, applied and queued up for -stable, thanks!