sched/numa: Fix task_numa_free() lockdep splat
authorMike Galbraith <bitbucket@online.de>
Mon, 7 Apr 2014 08:55:15 +0000 (10:55 +0200)
committerIngo Molnar <mingo@kernel.org>
Fri, 11 Apr 2014 08:39:15 +0000 (10:39 +0200)
commit60e69eed85bb7b5198ef70643b5895c26ad76ef7
tree4fa65bf81edbd0a28d5bc160f878341657f5ad82
parent467cbd207abdbfe29514b5804a22661ab6e80dc6
sched/numa: Fix task_numa_free() lockdep splat

Sasha reported that lockdep claims that the following commit:
made numa_group.lock interrupt unsafe:

  156654f491dd ("sched/numa: Move task_numa_free() to __put_task_struct()")

While I don't see how that could be, given the commit in question moved
task_numa_free() from one irq enabled region to another, the below does
make both gripes and lockups upon gripe with numa=fake=4 go away.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Fixes: 156654f491dd ("sched/numa: Move task_numa_free() to __put_task_struct()")
Signed-off-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Cc: mgorman@suse.com
Cc: akpm@linux-foundation.org
Cc: Dave Jones <davej@redhat.com>
Link: http://lkml.kernel.org/r/1396860915.5170.5.camel@marge.simpson.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
kernel/sched/fair.c
kernel/sched/sched.h