[PATCH RFC tip/core/rcu 14/14] rcu/nohz: Make multi_cpu_stop() enable tick on all online CPUs

From: Paul E. McKenney
Date: Fri Aug 02 2019 - 11:15:21 EST


The multi_cpu_stop() function relies on the scheduler to gain control from
whatever is running on the various online CPUs, including any nohz_full
CPUs running long loops in kernel-mode code. Lack of the scheduler-clock
interrupt on such CPUs can delay multi_cpu_stop() for several minutes
and can also result in RCU CPU stall warnings. This commit therefore
causes multi_cpu_stop() to enable the scheduler-clock interrupt on all
online CPUs.

Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxx>
---
kernel/stop_machine.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index b4f83f7bdf86..a2659f61ed92 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -20,6 +20,7 @@
#include <linux/smpboot.h>
#include <linux/atomic.h>
#include <linux/nmi.h>
+#include <linux/tick.h>
#include <linux/sched/wake_q.h>

/*
@@ -187,15 +188,19 @@ static int multi_cpu_stop(void *data)
{
struct multi_stop_data *msdata = data;
enum multi_stop_state curstate = MULTI_STOP_NONE;
- int cpu = smp_processor_id(), err = 0;
+ int cpu, err = 0;
const struct cpumask *cpumask;
unsigned long flags;
bool is_active;

+ for_each_online_cpu(cpu)
+ tick_nohz_dep_set_cpu(cpu, TICK_DEP_MASK_RCU);
+
/*
* When called from stop_machine_from_inactive_cpu(), irq might
* already be disabled. Save the state and restore it on exit.
*/
+ cpu = smp_processor_id();
local_save_flags(flags);

if (!msdata->active_cpus) {
@@ -236,6 +241,8 @@ static int multi_cpu_stop(void *data)
} while (curstate != MULTI_STOP_EXIT);

local_irq_restore(flags);
+ for_each_online_cpu(cpu)
+ tick_nohz_dep_clear_cpu(cpu, TICK_DEP_MASK_RCU);
return err;
}

--
2.17.1