From 107fb2b43f5c80686ee6454713f4963728ca2737 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 Dec 2013 09:16:52 -0500 Subject: [PATCH] cpu hotplug: Document why PREEMPT_RT uses a spinlock Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/3.14/patches-3.14.0-rt1.tar.xz The patch: cpu: Make hotplug.lock a "sleeping" spinlock on RT Tasks can block on hotplug.lock in pin_current_cpu(), but their state might be != RUNNING. So the mutex wakeup will set the state unconditionally to RUNNING. That might cause spurious unexpected wakeups. We could provide a state preserving mutex_lock() function, but this is semantically backwards. So instead we convert the hotplug.lock() to a spinlock for RT, which has the state preserving semantics already. Fixed a bug where the hotplug lock on PREEMPT_RT can be called after a task set its state to TASK_UNINTERRUPTIBLE and before it called schedule. If the hotplug_lock used a mutex, and there was contention, the current task's state would be turned to TASK_RUNNABLE and the schedule call will not sleep. This caused unexpected results. Although the patch had a description of the change, the code had no comments about it. This causes confusion to those that review the code, and as PREEMPT_RT is held in a quilt queue and not git, it's not as easy to see why a change was made. Even if it was in git, the code should still have a comment for something as subtle as this. Document the rational for using a spinlock on PREEMPT_RT in the hotplug lock code. Reported-by: Nicholas Mc Guire Signed-off-by: Steven Rostedt Signed-off-by: Sebastian Andrzej Siewior --- kernel/cpu.c | 8 ++++++++ 1 file changed, 8 insertions(+) --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -84,6 +84,14 @@ struct hotplug_pcp { int grab_lock; struct completion synced; #ifdef CONFIG_PREEMPT_RT_FULL + /* + * Note, on PREEMPT_RT, the hotplug lock must save the state of + * the task, otherwise the mutex will cause the task to fail + * to sleep when required. (Because it's called from migrate_disable()) + * + * The spinlock_t on PREEMPT_RT is a mutex that saves the task's + * state. + */ spinlock_t lock; #else struct mutex mutex;