hrtimer: Move schedule_work call to helper thread

When run ltp leapsec_timer test, the following call trace is caught:

BUG: sleeping function called from invalid context at kernel/rtmutex.c:659
in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1
Preemption disabled at:[<ffffffff810857f3>] cpu_startup_entry+0x133/0x310

CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.10.10-rt3 #2
Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010
ffffffff81c2f800 ffff880076843e40 ffffffff8169918d ffff880076843e58
ffffffff8106db31 ffff88007684b4a0 ffff880076843e70 ffffffff8169d9c0
ffff88007684b4a0 ffff880076843eb0 ffffffff81059da1 0000001876851200
Call Trace:
<IRQ>  [<ffffffff8169918d>] dump_stack+0x19/0x1b
[<ffffffff8106db31>] __might_sleep+0xf1/0x170
[<ffffffff8169d9c0>] rt_spin_lock+0x20/0x50
[<ffffffff81059da1>] queue_work_on+0x61/0x100
[<ffffffff81065aa1>] clock_was_set_delayed+0x21/0x30
[<ffffffff810883be>] do_timer+0x40e/0x660
[<ffffffff8108f487>] tick_do_update_jiffies64+0xf7/0x140
[<ffffffff8108fe42>] tick_check_idle+0x92/0xc0
[<ffffffff81044327>] irq_enter+0x57/0x70
[<ffffffff816a040e>] smp_apic_timer_interrupt+0x3e/0x9b
[<ffffffff8169f80a>] apic_timer_interrupt+0x6a/0x70
<EOI>  [<ffffffff8155ea1c>] ? cpuidle_enter_state+0x4c/0xc0
[<ffffffff8155eb68>] cpuidle_idle_call+0xd8/0x2d0
[<ffffffff8100b59e>] arch_cpu_idle+0xe/0x30
[<ffffffff8108585e>] cpu_startup_entry+0x19e/0x310
[<ffffffff8168efa2>] start_secondary+0x1ad/0x1b0

The clock_was_set_delayed is called in hard IRQ handler (timer interrupt), which
calls schedule_work.

Under PREEMPT_RT_FULL, schedule_work calls spinlocks which could sleep, so it's
not safe to call schedule_work in interrupt context.

Reference upstream commit b68d61c705ef02384c0538b8d9374545097899ca
(rt,ntp: Move call to schedule_delayed_work() to helper thread)
from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git, which
makes a similar change.

add a helper thread which does the call to schedule_work and wake up that
thread instead of calling schedule_work directly.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Yang Shi <yang.shi@windriver.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

1 files changed, 40 insertions, 0 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2ddbd6f..c383841 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -47,6 +47,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/timer.h>
+#include <linux/kthread.h>
 #include <linux/freezer.h>
 
 #include <asm/uaccess.h>
@@ -741,6 +742,44 @@ static void clock_was_set_work(struct work_struct *work)
 
 static DECLARE_WORK(hrtimer_work, clock_was_set_work);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * RT can not call schedule_work from real interrupt context.
+ * Need to make a thread to do the real work.
+ */
+static struct task_struct *clock_set_delay_thread;
+static bool do_clock_set_delay;
+
+static int run_clock_set_delay(void *ignore)
+{
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (do_clock_set_delay) {
+			do_clock_set_delay = false;
+			schedule_work(&hrtimer_work);
+		}
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+void clock_was_set_delayed(void)
+{
+	do_clock_set_delay = true;
+	/* Make visible before waking up process */
+	smp_wmb();
+	wake_up_process(clock_set_delay_thread);
+}
+
+static __init int create_clock_set_delay_thread(void)
+{
+	clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd");
+	BUG_ON(!clock_set_delay_thread);
+	return 0;
+}
+early_initcall(create_clock_set_delay_thread);
+#else /* PREEMPT_RT_FULL */
 /*
  * Called from timekeeping and resume code to reprogramm the hrtimer
  * interrupt device on all cpus.
@@ -749,6 +788,7 @@ void clock_was_set_delayed(void)
 {
 	schedule_work(&hrtimer_work);
 }
+#endif
 
 #else