Re: [GIT PULL] (xen) stable/for-jens-3.10 xenwatch: page allocation failure: order:7, mode:0x10c0d0

[David Vrabel <david.vrabel@citrix.com>]

On 24/04/13 19:16, Sander Eikelenboom wrote:
> 
> Hi Konrad / Roger,
> 

> I tried this pull on top of latest Linus latest linux-3.9 tree, but
> although it seems to boot and work fine at first, i seem to get trouble
> after running for about a day.
> Without this pull it runs fine for several days.
> 
> Trying to start a new guest I ended up with the splat below. In the
> output of xl-dmesg i seem to see more of these than before:
> (XEN) [2013-04-24 14:37:40] grant_table.c:1250:d1 Expanding dom (1)
> grant table from (9) to (10) frames

> [18496.013743] xenwatch: page allocation failure: order:7, mode:0x10c0d0

I think this is the allocation of blkif->pending_reqs in
xen_blkif_alloc() which is now enormous requiring a 512 KiB contiguous
allocation.

All the arrays in struct pending_req need to be turned into individual
allocations so no individual allocation is larger than a page.

David

> [18496.031948] Pid: 54, comm: xenwatch Not tainted 3.9.0-rc8-20130424-jens+ #1
> [18496.049897] Call Trace:
> [18496.067674]  [<ffffffff81100c51>] warn_alloc_failed+0xf1/0x140
> [18496.085453]  [<ffffffff810b25ed>] ? trace_hardirqs_on+0xd/0x10
> [18496.102951]  [<ffffffff810bdb24>] ? on_each_cpu_mask+0x94/0xd0
> [18496.120270]  [<ffffffff811028af>] __alloc_pages_nodemask+0x69f/0x960
> [18496.137306]  [<ffffffff8113a161>] alloc_pages_current+0xb1/0x160
> [18496.154051]  [<ffffffff81100679>] __get_free_pages+0x9/0x40
> [18496.170579]  [<ffffffff81142af4>] __kmalloc+0x134/0x160
> [18496.186921]  [<ffffffff815832d0>] xen_blkbk_probe+0x170/0x2f0
> [18496.202963]  [<ffffffff81474ce7>] xenbus_dev_probe+0x77/0x130
> [18496.218714]  [<ffffffff8156a390>] ? __driver_attach+0xa0/0xa0
> [18496.234237]  [<ffffffff8156a151>] driver_probe_device+0x81/0x220
> [18496.249605]  [<ffffffff8198198c>] ? klist_next+0x8c/0x110
> [18496.264681]  [<ffffffff8156a390>] ? __driver_attach+0xa0/0xa0
> [18496.279500]  [<ffffffff8156a3db>] __device_attach+0x4b/0x50
> [18496.294138]  [<ffffffff815684e8>] bus_for_each_drv+0x68/0x90
> [18496.308553]  [<ffffffff8156a0c9>] device_attach+0x89/0x90
> [18496.322694]  [<ffffffff81569258>] bus_probe_device+0xa8/0xd0
> [18496.336640]  [<ffffffff81567c80>] device_add+0x650/0x720
> [18496.350209]  [<ffffffff81573103>] ? device_pm_sleep_init+0x43/0x70
> [18496.363602]  [<ffffffff81567d69>] device_register+0x19/0x20
> [18496.376721]  [<ffffffff8147495b>] xenbus_probe_node+0x14b/0x160
> [18496.389611]  [<ffffffff815685b4>] ? bus_for_each_dev+0xa4/0xb0
> [18496.402298]  [<ffffffff81474b2c>] xenbus_dev_changed+0x1bc/0x1c0
> [18496.414732]  [<ffffffff810b67f7>] ? lock_release+0x117/0x260
> [18496.426904]  [<ffffffff81474f66>] backend_changed+0x16/0x20
> [18496.438835]  [<ffffffff81472f5e>] xenwatch_thread+0x4e/0x150
> [18496.450579]  [<ffffffff8108abb0>] ? wake_up_bit+0x40/0x40
> [18496.462048]  [<ffffffff81472f10>] ? xs_watch+0x60/0x60
> [18496.473286]  [<ffffffff8108a546>] kthread+0xd6/0xe0
> [18496.484235]  [<ffffffff8108a470>] ? __init_kthread_worker+0x70/0x70
> [18496.494987]  [<ffffffff819979bc>] ret_from_fork+0x7c/0xb0
> [18496.505560]  [<ffffffff8108a470>] ? __init_kthread_worker+0x70/0x70