Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753510AbaARHQJ (ORCPT ); Sat, 18 Jan 2014 02:16:09 -0500 Received: from rydia.net ([69.46.88.68]:41880 "EHLO mail.rydia.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752066AbaARHQI (ORCPT ); Sat, 18 Jan 2014 02:16:08 -0500 Date: Fri, 17 Jan 2014 23:16:04 -0800 (PST) From: dormando X-X-Sender: dormando@dinf To: Eric Dumazet cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Alexei Starovoitov Subject: Re: ipv4_dst_destroy panic regression after 3.10.15 In-Reply-To: <1390028976.31367.512.camel@edumazet-glaptop2.roam.corp.google.com> Message-ID: References: <1390027758.31367.505.camel@edumazet-glaptop2.roam.corp.google.com> <1390028976.31367.512.camel@edumazet-glaptop2.roam.corp.google.com> User-Agent: Alpine 2.10 (DEB 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > On Fri, 2014-01-17 at 22:49 -0800, Eric Dumazet wrote: > > On Fri, 2014-01-17 at 17:25 -0800, dormando wrote: > > > Hi, > > > > > > Upgraded a few kernels to the latest 3.10 stable tree while tracking down > > > a rare kernel panic, seems to have introduced a much more frequent kernel > > > panic. Takes anywhere from 4 hours to 2 days to trigger: > > > > > > <4>[196727.311203] general protection fault: 0000 [#1] SMP > > > <4>[196727.311224] Modules linked in: xt_TEE xt_dscp xt_DSCP macvlan bridge coretemp crc32_pclmul ghash_clmulni_intel gpio_ich microcode ipmi_watchdog ipmi_devintf sb_edac edac_core lpc_ich mfd_core tpm_tis tpm tpm_bios ipmi_si ipmi_msghandler isci igb libsas i2c_algo_bit ixgbe ptp pps_core mdio > > > <4>[196727.311333] CPU: 17 PID: 0 Comm: swapper/17 Not tainted 3.10.26 #1 > > > <4>[196727.311344] Hardware name: Supermicro X9DRi-LN4+/X9DR3-LN4+/X9DRi-LN4+/X9DR3-LN4+, BIOS 3.0 07/05/2013 > > > <4>[196727.311364] task: ffff885e6f069700 ti: ffff885e6f072000 task.ti: ffff885e6f072000 > > > <4>[196727.311377] RIP: 0010:[] [] ipv4_dst_destroy+0x4f/0x80 > > > <4>[196727.311399] RSP: 0018:ffff885effd23a70 EFLAGS: 00010282 > > > <4>[196727.311409] RAX: dead000000200200 RBX: ffff8854c398ecc0 RCX: 0000000000000040 > > > <4>[196727.311423] RDX: dead000000100100 RSI: dead000000100100 RDI: dead000000200200 > > > <4>[196727.311437] RBP: ffff885effd23a80 R08: ffffffff815fd9e0 R09: ffff885d5a590800 > > > <4>[196727.311451] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 > > > <4>[196727.311464] R13: ffffffff81c8c280 R14: 0000000000000000 R15: ffff880e85ee16ce > > > <4>[196727.311510] FS: 0000000000000000(0000) GS:ffff885effd20000(0000) knlGS:0000000000000000 > > > <4>[196727.311554] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > > > <4>[196727.311581] CR2: 00007a46751eb000 CR3: 0000005e65688000 CR4: 00000000000407e0 > > > <4>[196727.311625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > > > <4>[196727.311669] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > > > <4>[196727.311713] Stack: > > > <4>[196727.311733] ffff8854c398ecc0 ffff8854c398ecc0 ffff885effd23ab0 ffffffff815b7f42 > > > <4>[196727.311784] ffff88be6595bc00 ffff8854c398ecc0 0000000000000000 ffff8854c398ecc0 > > > <4>[196727.311834] ffff885effd23ad0 ffffffff815b86c6 ffff885d5a590800 ffff8816827821c0 > > > <4>[196727.311885] Call Trace: > > > <4>[196727.311907] > > > <4>[196727.311912] [] dst_destroy+0x32/0xe0 > > > <4>[196727.311959] [] dst_release+0x56/0x80 > > > <4>[196727.311986] [] tcp_v4_do_rcv+0x2a5/0x4a0 > > > <4>[196727.312013] [] tcp_v4_rcv+0x7da/0x820 > > > <4>[196727.312041] [] ? ip_rcv_finish+0x360/0x360 > > > <4>[196727.312070] [] ? nf_hook_slow+0x7d/0x150 > > > <4>[196727.312097] [] ? ip_rcv_finish+0x360/0x360 > > > <4>[196727.312125] [] ip_local_deliver_finish+0xb2/0x230 > > > <4>[196727.312154] [] ip_local_deliver+0x4a/0x90 > > > <4>[196727.312183] [] ip_rcv_finish+0x119/0x360 > > > <4>[196727.312212] [] ip_rcv+0x22b/0x340 > > > <4>[196727.312242] [] ? macvlan_broadcast+0x160/0x160 [macvlan] > > > <4>[196727.312275] [] __netif_receive_skb_core+0x512/0x640 > > > <4>[196727.312308] [] ? kmem_cache_alloc+0x13b/0x150 > > > <4>[196727.312338] [] __netif_receive_skb+0x21/0x70 > > > <4>[196727.312368] [] netif_receive_skb+0x31/0xa0 > > > <4>[196727.312397] [] napi_gro_receive+0xe8/0x140 > > > <4>[196727.312433] [] ixgbe_poll+0x551/0x11f0 [ixgbe] > > > <4>[196727.312463] [] ? ip_rcv+0x22b/0x340 > > > <4>[196727.312491] [] net_rx_action+0x111/0x210 > > > <4>[196727.312521] [] ? __netif_receive_skb+0x21/0x70 > > > <4>[196727.312552] [] __do_softirq+0xd0/0x270 > > > <4>[196727.312583] [] call_softirq+0x1c/0x30 > > > <4>[196727.312613] [] do_softirq+0x55/0x90 > > > <4>[196727.312640] [] irq_exit+0x55/0x60 > > > <4>[196727.312668] [] do_IRQ+0x63/0xe0 > > > <4>[196727.312696] [] common_interrupt+0x6a/0x6a > > > <4>[196727.312722] > > > <4>[196727.312727] [] ? default_idle+0x20/0xe0 > > > <4>[196727.312775] [] arch_cpu_idle+0xf/0x20 > > > <4>[196727.312803] [] cpu_startup_entry+0xc0/0x270 > > > <4>[196727.312833] [] start_secondary+0x1f9/0x200 > > > <4>[196727.312860] Code: 4a 9f e9 81 e8 13 cb 0c 00 48 8b 93 b0 00 00 00 48 bf 00 02 20 00 00 00 ad de 48 8b 83 b8 00 00 00 48 be 00 01 10 00 00 00 ad de <48> 89 42 08 48 89 10 48 89 bb b8 00 00 00 48 c7 c7 4a 9f e9 81 > > > <1>[196727.313071] RIP [] ipv4_dst_destroy+0x4f/0x80 > > > <4>[196727.313100] RSP > > > <4>[196727.313377] ---[ end trace 64b3f14fae0f2e29 ]--- > > > <0>[196727.380908] Kernel panic - not syncing: Fatal exception in interrupt > > > > > > > > > ... bisecting it's going to be a pain... I tried eyeballing the diffs and > > > am trying a revert or two. > > > > > > We've hit it in .25, .26 so far. I have .27 running but not sure if it > > > crashed, so the change exists between .15 and .25. > > > > Please try following fix, thanks for the report ! > > > > diff --git a/net/ipv4/route.c b/net/ipv4/route.c > > index 25071b48921c..78a50a22298a 100644 > > --- a/net/ipv4/route.c > > +++ b/net/ipv4/route.c > > @@ -1333,7 +1333,7 @@ static void ipv4_dst_destroy(struct dst_entry > > *dst) > > > > if (!list_empty(&rt->rt_uncached)) { > > spin_lock_bh(&rt_uncached_lock); > > - list_del(&rt->rt_uncached); > > + list_del_init(&rt->rt_uncached); > > spin_unlock_bh(&rt_uncached_lock); > > } > > } > > > > Problem could come from this commit, in linux 3.10.23, > you also could try to revert it > > commit 62713c4b6bc10c2d082ee1540e11b01a2b2162ab > Author: Alexei Starovoitov > Date: Tue Nov 19 19:12:34 2013 -0800 > > ipv4: fix race in concurrent ip_route_input_slow() > > [ Upstream commit dcdfdf56b4a6c9437fc37dbc9cee94a788f9b0c4 ] > > 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. > > Fixes: d2d68ba9fe8b ("ipv4: Cache input routes in fib_info nexthops.") > Signed-off-by: Alexei Starovoitov > Signed-off-by: David S. Miller > Signed-off-by: Greg Kroah-Hartman > Heh. I spent an hour squinting at the difflog from .15 to .25 and this was my best guess. I have a kernel running in production with only this reverted as of ~5 hours ago. Won't know if it helps for a day or two. I'm building a kernel now with your route patch, but 62713c4 *not* reverted, which I can throw on a different machine. Does this sound like a good idea? Thanks for your quick help as always! -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/