[lkml]   [2008]   [Dec]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Patch in this message
Subject[patch 71/83] sched: CPU remove deadlock fix
2.6.27-stable review patch.  If anyone has any objections, please let us know.


From: Brian King <>

commit 9a2bd244e18ffbb96c8b783210fda4eded7c7e6f upstream.

Impact: fix possible deadlock in CPU hot-remove path

This patch fixes a possible deadlock scenario in the CPU remove path.
migration_call grabs rq->lock, then wakes up everything on rq->migration_queue
with the lock held. Then one of the tasks on the migration queue ends up
calling tg_shares_up which then also tries to acquire the same rq->lock.

[c000000058eab2e0] c000000000502078 ._spin_lock_irqsave+0x98/0xf0
[c000000058eab370] c00000000008011c .tg_shares_up+0x10c/0x20c
[c000000058eab430] c00000000007867c .walk_tg_tree+0xc4/0xfc
[c000000058eab4d0] c0000000000840c8 .try_to_wake_up+0xb0/0x3c4
[c000000058eab590] c0000000000799a0 .__wake_up_common+0x6c/0xe0
[c000000058eab640] c00000000007ada4 .complete+0x54/0x80
[c000000058eab6e0] c000000000509fa8 .migration_call+0x5fc/0x6f8
[c000000058eab7c0] c000000000504074 .notifier_call_chain+0x68/0xe0
[c000000058eab860] c000000000506568 ._cpu_down+0x2b0/0x3f4
[c000000058eaba60] c000000000506750 .cpu_down+0xa4/0x108
[c000000058eabb10] c000000000507e54 .store_online+0x44/0xa8
[c000000058eabba0] c000000000396260 .sysdev_store+0x3c/0x50
[c000000058eabc10] c0000000001a39b8 .sysfs_write_file+0x124/0x18c
[c000000058eabcd0] c00000000013061c .vfs_write+0xd0/0x1bc
[c000000058eabd70] c0000000001308a4 .sys_write+0x68/0x114
[c000000058eabe30] c0000000000086b4 syscall_exit+0x0/0x40

Signed-off-by: Brian King <>
Acked-by: Peter Zijlstra <>
Signed-off-by: Ingo Molnar <>
Signed-off-by: Greg Kroah-Hartman <>

kernel/sched.c | 2 ++
1 file changed, 2 insertions(+)

--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6500,7 +6500,9 @@ migration_call(struct notifier_block *nf
req = list_entry(rq->,
struct migration_req, list);
+ spin_unlock_irq(&rq->lock);
+ spin_lock_irq(&rq->lock);

 \ /
  Last update: 2008-12-11 20:47    [W:0.280 / U:1.492 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site