Blob Blame History Raw
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 7 Jun 2013 22:37:06 +0200
Subject: kernel/cpu: fix cpu down problem if kthread's cpu is going down
Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git
Git-commit: 8f8aad478c8448ade9492a7f4083506dea555484
Patch-mainline: Queued in subsystem maintainer repository
References: SLE Realtime Extension

If kthread is pinned to CPUx and CPUx is going down then we get into
trouble:
- first the unplug thread is created
- it will set itself to hp->unplug. As a result, every task that is
  going to take a lock, has to leave the CPU.
- the CPU_DOWN_PREPARE notifier are started. The worker thread will
  start a new process for the "high priority worker".
  Now kthread would like to take a lock but since it can't leave the CPU
  it will never complete its task.

We could fire the unplug thread after the notifier but then the cpu is
no longer marked "online" and the unplug thread will run on CPU0 which
was fixed before :)

So instead the unplug thread is started and kept waiting until the
notfier complete their work.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
---
 kernel/cpu.c |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -255,6 +255,7 @@ struct hotplug_pcp {
 	int refcount;
 	int grab_lock;
 	struct completion synced;
+	struct completion unplug_wait;
 #ifdef CONFIG_PREEMPT_RT_FULL
 	/*
 	 * Note, on PREEMPT_RT, the hotplug lock must save the state of
@@ -358,6 +359,7 @@ static int sync_unplug_thread(void *data
 {
 	struct hotplug_pcp *hp = data;
 
+	wait_for_completion(&hp->unplug_wait);
 	preempt_disable();
 	hp->unplug = current;
 	wait_for_pinned_cpus(hp);
@@ -423,6 +425,14 @@ static void __cpu_unplug_sync(struct hot
 	wait_for_completion(&hp->synced);
 }
 
+static void __cpu_unplug_wait(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+	complete(&hp->unplug_wait);
+	wait_for_completion(&hp->synced);
+}
+
 /*
  * Start the sync_unplug_thread on the target cpu and wait for it to
  * complete.
@@ -446,6 +456,7 @@ static int cpu_unplug_begin(unsigned int
 	tell_sched_cpu_down_begin(cpu);
 
 	init_completion(&hp->synced);
+	init_completion(&hp->unplug_wait);
 
 	hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
 	if (IS_ERR(hp->sync_tsk)) {
@@ -461,8 +472,7 @@ static int cpu_unplug_begin(unsigned int
 	 * wait for tasks that are going to enter these sections and
 	 * we must not have them block.
 	 */
-	__cpu_unplug_sync(hp);
-
+	wake_up_process(hp->sync_tsk);
 	return 0;
 }
 
@@ -1016,6 +1026,7 @@ static int takedown_cpu(unsigned int cpu
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	int err;
 
+	__cpu_unplug_wait(cpu);
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);