clockevents: Fix cpu_down() race for hrtimer based broadcasting
It was found when doing a hotplug stress test on POWER, that the
machine either hit softlockups or rcu_sched stall warnings. The
issue was traced to commit:
7cba160ad789 ("powernv/cpuidle: Redesign idle states management")
which exposed the cpu_down() race with hrtimer based broadcast mode:
5d1638acb9f6 ("tick: Introduce hrtimer based broadcast")
The race is the following:
Assume CPU1 is the CPU which holds the hrtimer broadcasting duty
before it is taken down.
CPU0 CPU1
cpu_down() take_cpu_down()
disable_interrupts()
cpu_die()
while (CPU1 != CPU_DEAD) {
msleep(100);
switch_to_idle();
stop_cpu_timer();
schedule_broadcast();
}
tick_cleanup_cpu_dead()
take_over_broadcast()
So after CPU1 disabled interrupts it cannot handle the broadcast
hrtimer anymore, so CPU0 will be stuck forever.
Fix this by explicitly taking over broadcast duty before cpu_die().
This is a temporary workaround. What we really want is a callback
in the clockevent device which allows us to do that from the dying
CPU by pushing the hrtimer onto a different cpu. That might involve
an IPI and is definitely more complex than this immediate fix.
Changelog was picked up from:
https://lkml.org/lkml/2015/2/16/213
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Preeti U. Murthy <preeti@linux.vnet.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: mpe@ellerman.id.au
Cc: nicolas.pitre@linaro.org
Cc: peterz@infradead.org
Cc: rjw@rjwysocki.net
Fixes: http://linuxppc.10917.n7.nabble.com/offlining-cpus-breakage-td88619.html
Link: http://lkml.kernel.org/r/20150330092410.24979.59887.stgit@preeti.in.ibm.com
[ Merged it to the latest timer tree, renamed the callback, tidied up the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 589868b..f9ff225 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -36,6 +36,12 @@
static inline void tick_irq_enter(void) { }
#endif
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu);
+#else
+static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { }
+#endif
+
#ifdef CONFIG_NO_HZ_COMMON
extern int tick_nohz_tick_stopped(void);
extern void tick_nohz_idle_enter(void);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 1972b16..af5db20 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -20,6 +20,7 @@
#include <linux/gfp.h>
#include <linux/suspend.h>
#include <linux/lockdep.h>
+#include <linux/tick.h>
#include <trace/events/power.h>
#include "smpboot.h"
@@ -411,6 +412,7 @@
while (!idle_cpu(cpu))
cpu_relax();
+ hotplug_cpu__broadcast_tick_pull(cpu);
/* This actually kills the CPU. */
__cpu_die(cpu);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 19cfb38..f5e0fd5 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -680,14 +680,19 @@
clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
}
-static void broadcast_move_bc(int deadcpu)
+void hotplug_cpu__broadcast_tick_pull(int deadcpu)
{
- struct clock_event_device *bc = tick_broadcast_device.evtdev;
+ struct clock_event_device *bc;
+ unsigned long flags;
- if (!bc || !broadcast_needs_cpu(bc, deadcpu))
- return;
- /* This moves the broadcast assignment to this cpu */
- clockevents_program_event(bc, bc->next_event, 1);
+ raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
+ bc = tick_broadcast_device.evtdev;
+
+ if (bc && broadcast_needs_cpu(bc, deadcpu)) {
+ /* This moves the broadcast assignment to this CPU: */
+ clockevents_program_event(bc, bc->next_event, 1);
+ }
+ raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
/*
@@ -924,8 +929,6 @@
cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
- broadcast_move_bc(cpu);
-
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}