Messages in this thread | | | Date | Sun, 5 Jul 2009 12:09:53 +0800 | From | Herbert Xu <> | Subject | Re: [GIT]: Networking |
| |
Ingo Molnar <mingo@elte.hu> wrote: > > I triggered other networking problems today though, a trylock > failure message in netconsole, plus a dma-debug assert from e1000e: > > [ 1275.442025] Hangcheck: hangcheck value past margin! > [ 1451.860024] ------------[ cut here ]------------ > [ 1451.860024] BUG: spinlock trylock failure on UP on CPU#0, distcc/32540 > [ 1451.860024] lock: f5318760, .magic: dead4ead, .owner: distcc/32540, .owner_cpu: 0 > [ 1451.860024] Pid: 32540, comm: distcc Tainted: G W 2.6.31-rc1-tip-01236-gb62d24b-dirty #6631 > [ 1451.860024] Call Trace: > [ 1451.860024] [<c17764e8>] spin_bug+0x98/0x140 > [ 1451.860024] [<c1776d01>] _raw_spin_trylock+0x71/0xc0 > [ 1451.860024] [<c283ffbb>] _spin_trylock+0x1b/0x80 > [ 1451.860024] [<c23c7868>] netpoll_send_skb+0x198/0x470 > [ 1451.860024] [<c23c7eb0>] netpoll_send_udp+0x240/0x290 > [ 1451.860024] [<c2840884>] ? _spin_lock_irqsave+0x64/0x90 > [ 1451.860024] [<c1d69beb>] write_msg+0xeb/0x160 > [ 1451.860024] [<c10933c8>] __call_console_drivers+0x78/0xa0 > [ 1451.860024] [<c10934d9>] _call_console_drivers+0xe9/0x120 > [ 1451.860024] [<c10938e7>] call_console_drivers+0x137/0x260 > [ 1451.860024] [<c1093aaa>] release_console_sem+0x9a/0x1a0 > [ 1451.860024] [<c10949b6>] vprintk+0x416/0x500 > [ 1451.860024] [<c178b8f7>] ? check_for_illegal_area+0x197/0x340 > [ 1451.860024] [<c1094abb>] printk+0x1b/0x20 > [ 1451.860024] [<c1092bdb>] warn_slowpath_common+0x1b/0xe0 > [ 1451.860024] [<c1092ce9>] warn_slowpath_fmt+0x29/0x30 > [ 1451.860024] [<c178b8f7>] check_for_illegal_area+0x197/0x340 > [ 1451.860024] [<c178be4c>] debug_dma_map_page+0x1cc/0x310 > [ 1451.860024] [<c239fe19>] skb_dma_map+0x219/0x580 > [ 1451.860024] [<c23919b6>] ? skb_copy_bits+0x126/0x590 > [ 1451.860024] [<c1ab920f>] e1000_tx_map+0x4f/0x2a0 > [ 1451.860024] [<c1abbb6b>] e1000_xmit_frame+0x28b/0x5a0
I don't know about the DMA error but this is perfectly normal. You're invoking netpoll from within the NIC's xmit routine, that's why the trylock fails. So I guess you should fix spinlock debugging instead :)
Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au> Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
| |