[PATCH] ip_tunnel: disable preemption when updating per-cpu tstats

[PATCH] ip_tunnel: disable preemption when updating per-cpu tstats

[Jason A. Donenfeld]

The below patch has made it into Linus' tree, but should be backported
quite far. From testing, I know this applies to 4.1, 4.2, and 4.3. I
haven't looked further back, but I imagine it's relevant there too.

Upstream commit:
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fe85f9c9146f60457e9512fb6055e69e6a7a65

=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
>From b4fe85f9c9146f60457e9512fb6055e69e6a7a65 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 12 Nov 2015 17:35:58 +0100
Subject: ip_tunnel: disable preemption when updating per-cpu tstats

Drivers like vxlan use the recently introduced
udp_tunnel_xmit_skb/udp_tunnel6_xmit_skb APIs. udp_tunnel6_xmit_skb
makes use of ip6tunnel_xmit, and ip6tunnel_xmit, after sending the
packet, updates the struct stats using the usual
u64_stats_update_begin/end calls on this_cpu_ptr(dev->tstats).
udp_tunnel_xmit_skb makes use of iptunnel_xmit, which doesn't touch
tstats, so drivers like vxlan, immediately after, call
iptunnel_xmit_stats, which does the same thing - calls
u64_stats_update_begin/end on this_cpu_ptr(dev->tstats).

While vxlan is probably fine (I don't know?), calling a similar function
from, say, an unbound workqueue, on a fully preemptable kernel causes
real issues:

[  188.434537] BUG: using smp_processor_id() in preemptible [00000000]
code: kworker/u8:0/6
[  188.435579] caller is debug_smp_processor_id+0x17/0x20
[  188.435583] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 4.2.6 #2
[  188.435607] Call Trace:
[  188.435611]  [<ffffffff8234e936>] dump_stack+0x4f/0x7b
[  188.435615]  [<ffffffff81915f3d>] check_preemption_disabled+0x19d/0x1c0
[  188.435619]  [<ffffffff81915f77>] debug_smp_processor_id+0x17/0x20

The solution would be to protect the whole
this_cpu_ptr(dev->tstats)/u64_stats_update_begin/end blocks with
disabling preemption and then reenabling it.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_tunnel.h | 3 ++-
 include/net/ip_tunnels.h | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index aaee6fa..ff788b6 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -90,11 +90,12 @@ static inline void ip6tunnel_xmit(struct sock *sk,
struct sk_buff *skb,
  err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);

  if (net_xmit_eval(err) == 0) {
- struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+ struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
  u64_stats_update_begin(&tstats->syncp);
  tstats->tx_bytes += pkt_len;
  tstats->tx_packets++;
  u64_stats_update_end(&tstats->syncp);
+ put_cpu_ptr(tstats);
  } else {
  stats->tx_errors++;
  stats->tx_aborted_errors++;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index f6dafec..62a750a 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -287,12 +287,13 @@ static inline void iptunnel_xmit_stats(int err,
        struct pcpu_sw_netstats __percpu *stats)
 {
  if (err > 0) {
- struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
+ struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats);

  u64_stats_update_begin(&tstats->syncp);
  tstats->tx_bytes += err;
  tstats->tx_packets++;
  u64_stats_update_end(&tstats->syncp);
+ put_cpu_ptr(tstats);
  } else if (err < 0) {
  err_stats->tx_errors++;
  err_stats->tx_aborted_errors++;
--

Re: [PATCH] ip_tunnel: disable preemption when updating per-cpu tstats

[Greg KH]

On Wed, Nov 18, 2015 at 09:22:19PM +0100, Jason A. Donenfeld wrote:
> The below patch has made it into Linus' tree, but should be backported
> quite far. From testing, I know this applies to 4.1, 4.2, and 4.3. I
> haven't looked further back, but I imagine it's relevant there too.
> 
> Upstream commit:
> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=b4fe85f9c9146f60457e9512fb6055e69e6a7a65
> 
> =~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
> >From b4fe85f9c9146f60457e9512fb6055e69e6a7a65 Mon Sep 17 00:00:00 2001
> From: "Jason A. Donenfeld" <Jason@zx2c4.com>
> Date: Thu, 12 Nov 2015 17:35:58 +0100
> Subject: ip_tunnel: disable preemption when updating per-cpu tstats

For networking patches, please email the netdev mailing list and ask for
a patch to be applied to the stable tree, the maintainer there will
handle it for you, he doesn't want people to send patches directly to
stable@ like this so that he can properly test them.

thanks,

greg k-h