summaryrefslogtreecommitdiff
path: root/drivers/cdrom
diff options
context:
space:
mode:
authorIan Campbell <ian.campbell@citrix.com>2009-05-19 08:27:42 +0200
committerJens Axboe <jens.axboe@oracle.com>2009-05-19 08:27:42 +0200
commit31a14400e8f365e5d4d1a0b2a1ef4d5405d6091e (patch)
tree9299d0d1edb3a44265201e286bd8d38084199bce /drivers/cdrom
parent28afea5b2ffaa48f4f43d22ae8edcc384c05df80 (diff)
downloadlinux-3.10-31a14400e8f365e5d4d1a0b2a1ef4d5405d6091e.tar.gz
linux-3.10-31a14400e8f365e5d4d1a0b2a1ef4d5405d6091e.tar.bz2
linux-3.10-31a14400e8f365e5d4d1a0b2a1ef4d5405d6091e.zip
xen/blkfront: fix warning when deleting gendisk on unplug/shutdown
Currently blkfront gives a warning when hot unplugging due to calling del_gendisk() with interrupts disabled (due to blkif_io_lock). WARNING: at kernel/softirq.c:124 local_bh_enable+0x36/0x84() Modules linked in: xenfs xen_netfront ext3 jbd mbcache xen_blkfront Pid: 13, comm: xenwatch Not tainted 2.6.29-xs5.5.0.13 #3 Call Trace: [<c012611c>] warn_slowpath+0x80/0xb6 [<c0104cf1>] xen_sched_clock+0x16/0x63 [<c0104710>] xen_force_evtchn_callback+0xc/0x10 [<c0104e32>] check_events+0x8/0xe [<c0104d9b>] xen_restore_fl_direct_end+0x0/0x1 [<c0103749>] xen_mc_flush+0x10a/0x13f [<c0105bd2>] __switch_to+0x114/0x14e [<c011d92b>] dequeue_task+0x62/0x70 [<c0123b6f>] finish_task_switch+0x2b/0x84 [<c0299877>] schedule+0x66d/0x6e7 [<c0104710>] xen_force_evtchn_callback+0xc/0x10 [<c0104710>] xen_force_evtchn_callback+0xc/0x10 [<c012a642>] local_bh_enable+0x36/0x84 [<c022f9a7>] sk_filter+0x57/0x5c [<c0233dae>] netlink_broadcast+0x1d5/0x315 [<c01c6371>] kobject_uevent_env+0x28d/0x331 [<c01e7ead>] device_del+0x10f/0x120 [<c01e7ec6>] device_unregister+0x8/0x10 [<c015f86d>] bdi_unregister+0x2d/0x39 [<c01bf6f4>] unlink_gendisk+0x23/0x3e [<c01ac946>] del_gendisk+0x7b/0xe7 [<d0828c19>] blkfront_closing+0x28/0x6e [xen_blkfront] [<d082900c>] backend_changed+0x3ad/0x41d [xen_blkfront] We can fix this by calling del_gendisk() later in blkfront_closing, after releasing blkif_io_lock. Since the queue is stopped during the interrupts disabled phase I don't think there is any danger of an event occuring between releasing the blkif_io_lock and deleting the disk. Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Diffstat (limited to 'drivers/cdrom')
0 files changed, 0 insertions, 0 deletions