All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@fb.com>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Jan Kara <jack@suse.cz>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	James Bottomley <James.Bottomley@HansenPartnership.com>,
	Brian J King <bjking1@us.ibm.com>
Subject: Re: [BUG] kernel BUG at /.../block/cfq-iosched.c:3145!
Date: Wed, 9 Apr 2014 19:31:34 -0600	[thread overview]
Message-ID: <5345F476.2000602@fb.com> (raw)
In-Reply-To: <1397088144.3671.155.camel@pasglop>

On 2014-04-09 18:02, Benjamin Herrenschmidt wrote:
> On Thu, 2014-04-10 at 09:47 +1000, Benjamin Herrenschmidt wrote:
>
>>> Nope, that's not a known issue. This must be related to the FIFO
>>> changes... How reproducible is this?
>>
>> Dunno yet, haven't had a chance to dig. I'll try to grab that machine
>> later today and reproduce &| bisect.
>
> Second boot leads to a slightly different symptom (see below). I'll
> try bisecting a bit later today if I get a chance.
>
> =============================================================================
> BUG blkdev_requests (Not tainted): Poison overwritten
> -----------------------------------------------------------------------------
>
> Disabling lock debugging due to kernel taint
> INFO: 0xc000003ca627f790-0xc000003ca627f797. First byte 0xc0 instead of 0x6b
> INFO: Allocated in .mempool_alloc_slab+0x1c/0x30 age=17 cpu=36 pid=3579
> 	.kmem_cache_alloc+0xc0/0x1ac
> 	.mempool_alloc_slab+0x1c/0x30
> 	.mempool_alloc+0x98/0x18c
> 	.get_request+0x248/0x490
> 	.blk_queue_bio+0x174/0x25c
> 	.generic_make_request+0xa8/0xec
> 	.submit_bio+0x134/0x14c
> 	.mpage_readpages+0x108/0x118
> 	.ext4_readpages+0x48/0x5c
> 	.__do_page_cache_readahead+0x1b0/0x298
> 	.ra_submit+0x28/0x38
> 	.filemap_fault+0x158/0x3e4
> 	.__do_fault+0x48/0xbc
> 	.do_read_fault.isra.65+0x2c/0xe4
> 	.handle_mm_fault+0x460/0xbb8
> 	.do_page_fault+0x498/0x7e0
> INFO: Freed in .mempool_free_slab+0x1c/0x30 age=17 cpu=36 pid=0
> 	.kmem_cache_free+0x1d4/0x1fc
> 	.mempool_free_slab+0x1c/0x30
> 	.mempool_free+0xb0/0xbc
> 	.__blk_put_request+0xd0/0x104
> 	.blk_end_bidi_request+0x40/0x64
> 	.scsi_io_completion+0x198/0x5a4
> 	.scsi_finish_command+0xd0/0xdc
> 	.scsi_softirq_done+0x128/0x134
> 	.blk_done_softirq+0xa0/0xb8
> 	.__do_softirq+0x1b8/0x370
> 	.irq_exit+0x74/0xa4
> 	.__do_irq+0x90/0xa4
> 	.call_do_irq+0x14/0x24
> 	.do_IRQ+0x80/0xc0
> 	hardware_interrupt_common+0x138/0x180
> 	0xc000000001e46640
> INFO: Slab 0xf00000000d445888 objects=92 used=92 fp=0x          (null) flags=0x13fff8000000080
> INFO: Object 0xc000003ca627f788 @offset=63368 fp=0xc000003ca6270de8
>
> Bytes b4 c000003ca627f778: 00 00 00 00 ff fe ef be 5a 5a 5a 5a 5a 5a 5a 5a  ........ZZZZZZZZ
> Object c000003ca627f788: 6b 6b 6b 6b 6b 6b 6b 6b c0 00 00 3c a6 27 fa 50  kkkkkkkk...<.'.P
> Object c000003ca627f798: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f7a8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f7b8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f7c8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f7d8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f7e8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f7f8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f808: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f818: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f828: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f838: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f848: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f858: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f868: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f878: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f888: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f898: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f8a8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f8b8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f8c8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f8d8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f8e8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
> Object c000003ca627f8f8: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b a5  kkkkkkkkkkkkkkk.
> Redzone c000003ca627f908: bb bb bb bb bb bb bb bb                          ........
> Padding c000003ca627fa48: 5a 5a 5a 5a 5a 5a 5a 5a                          ZZZZZZZZ
> CPU: 60 PID: 3579 Comm: X Tainted: G    B        3.14.0-test #1
> Call Trace:
> [c000003ca331aaf0] [c00000000001405c] .show_stack+0x50/0x14c (unreliable)
> [c000003ca331abc0] [c0000000008a3a94] .dump_stack+0x90/0xc0
> [c000003ca331ac40] [c00000000014bbec] .print_trailer+0x17c/0x188
> [c000003ca331acd0] [c00000000014bd08] .check_bytes_and_report+0xc0/0x114
> [c000003ca331ad80] [c00000000014be44] .check_object+0xe8/0x240
> [c000003ca331ae20] [c0000000008a2488] .alloc_debug_processing+0x184/0x19c
> [c000003ca331aeb0] [c0000000008a2958] .__slab_alloc+0x4b8/0x540
> [c000003ca331b020] [c00000000014de68] .kmem_cache_alloc+0xc0/0x1ac
> [c000003ca331b0d0] [c000000000107f3c] .mempool_alloc_slab+0x1c/0x30
> [c000003ca331b140] [c0000000001080d4] .mempool_alloc+0x98/0x18c
> [c000003ca331b220] [c0000000003227c4] .get_request+0x248/0x490
> [c000003ca331b340] [c000000000324a68] .blk_queue_bio+0x174/0x25c
> [c000003ca331b3e0] [c000000000322280] .generic_make_request+0xa8/0xec
> [c000003ca331b470] [c0000000003223f8] .submit_bio+0x134/0x14c
> [c000003ca331b530] [c000000000186030] ._submit_bh+0x244/0x278
> [c000003ca331b5c0] [c000000000186b14] .ll_rw_block+0xd4/0x100
> [c000003ca331b670] [c000000000188d80] .__breadahead+0x2c/0x4c
> [c000003ca331b6f0] [c00000000021d18c] .__ext4_get_inode_loc+0x390/0x444
> [c000003ca331b7c0] [c00000000021f7cc] .ext4_iget+0x4c/0x97c
> [c000003ca331b8c0] [c000000000229558] .ext4_lookup+0xc4/0x15c
> [c000003ca331b960] [c00000000016007c] .lookup_real+0x4c/0x74
> [c000003ca331b9e0] [c000000000165bdc] .do_last+0x58c/0xc54
> [c000003ca331bb10] [c00000000016650c] .path_openat+0x268/0x6a0
> [c000003ca331bc30] [c000000000166cc0] .do_filp_open+0x34/0x80
> [c000003ca331bd70] [c000000000155a10] .do_sys_open+0x1a4/0x250
> [c000003ca331be30] [c00000000000a024] syscall_exit+0x0/0x98
> FIX blkdev_requests: Restoring 0xc000003ca627f790-0xc000003ca627f797=0x6b
>
> FIX blkdev_requests: Marking all objects used
> ------------[ cut here ]------------
> kernel BUG at /home/benh/linux-powerpc-test/block/elevator.c:262!
> cpu 0x34: Vector: 700 (Program Check) at [c000001febbd32c0]
>      pc: c00000000031ee40: .elv_rqhash_add+0x10/0x8c
>      lr: c0000000003202c8: .__elv_add_request+0x264/0x27c
>      sp: c000001febbd3540
>     msr: 9000000000029032
>    current = 0xc000003ca620c320
>    paca    = 0xc00000000ffed000	 softe: 0	 irq_happened: 0x01
>      pid   = 3565, comm = in:imjournal
> kernel BUG at /home/benh/linux-powerpc-test/block/elevator.c:262!
> enter ? for help
> [link register   ] c0000000003202c8 .__elv_add_request+0x264/0x27c
> [c000001febbd3540] c0000000003201a0 .__elv_add_request+0x13c/0x27c (unreliable)
> [c000001febbd35e0] c000000000324858 .blk_flush_plug_list+0x1f4/0x254
> [c000001febbd36a0] c0000000003248d0 .blk_finish_plug+0x18/0x3c
> [c000001febbd3720] c000000000111a84 .__do_page_cache_readahead+0x268/0x298
> [c000001febbd3870] c000000000111d24 .ra_submit+0x28/0x38
> [c000001febbd38e0] c000000000106f54 .filemap_fault+0x158/0x3e4
> [c000001febbd39b0] c000000000126cfc .__do_fault+0x48/0xbc
> [c000001febbd3a60] c0000000001272b0 .do_read_fault.isra.65+0x2c/0xe4
> [c000001febbd3b20] c00000000012a718 .handle_mm_fault+0x460/0xbb8
> [c000001febbd3c00] c00000000002ff54 .do_page_fault+0x498/0x7e0
> [c000001febbd3e30] c0000000000094e8 handle_page_fault+0x10/0x30
> --- Exception: 301 (Data Access) at 00003fff9a40d2d4
> SP (3fff9585df30) is in userspace
> 34:mon>

OK, I think we're seeing different symptoms of the same bug. Stay tuned, 
will have something for you to test shortly, I hope.

-- 
Jens Axboe


  reply	other threads:[~2014-04-10  1:31 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-04-09  4:44 [BUG] kernel BUG at /.../block/cfq-iosched.c:3145! Benjamin Herrenschmidt
2014-04-09 13:35 ` Jens Axboe
2014-04-09 23:47   ` Benjamin Herrenschmidt
2014-04-10  0:02     ` Benjamin Herrenschmidt
2014-04-10  1:31       ` Jens Axboe [this message]
2014-04-10  1:36         ` Benjamin Herrenschmidt
2014-04-10  1:38           ` Jens Axboe
2014-04-10  2:25           ` Jens Axboe
2014-04-10  3:35             ` Benjamin Herrenschmidt
2014-04-10  3:52               ` Jens Axboe
2014-04-10  6:45                 ` Benjamin Herrenschmidt
2014-04-10 13:47                   ` Jens Axboe
2014-04-10 18:10                   ` Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=5345F476.2000602@fb.com \
    --to=axboe@fb.com \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=benh@kernel.crashing.org \
    --cc=bjking1@us.ibm.com \
    --cc=fweisbec@gmail.com \
    --cc=jack@suse.cz \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.