hrtimer: prevent migration for raising softirq
authorSteven Rostedt <rostedt@goodmis.org>
Thu, 3 Jul 2008 18:31:26 +0000 (14:31 -0400)
committerLinus Torvalds <torvalds@linux-foundation.org>
Thu, 3 Jul 2008 18:36:48 +0000 (11:36 -0700)
commitee3ece830f6db9837f7ac67008f532a8c1e755f4
tree86512e4fe0a03970003260671a3c28045f57f5e8
parent6beef7eb0c16b5216814148b04838cfa963d2cb4
hrtimer: prevent migration for raising softirq

Due to a possible deadlock, the waking of the softirq was pushed outside
of the hrtimer base locks. See commit 0c96c5979a522c3323c30a078a70120e29b5bdbc

Unfortunately this allows the task to migrate after setting up the softirq
and raising it. Since softirqs run a queue that is per-cpu we may raise the
softirq on the wrong CPU and this will keep the queued softirq task from
running.

To solve this issue, this patch disables preemption around the releasing
of the hrtimer lock and raising of the softirq.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
kernel/hrtimer.c