[RFC PATCH 03/10] smp,cpu hotplug: Fix on_each_cpu_*() to prevent CPU offline properly

[Srivatsa S. Bhat]

With stop_machine() gone from the CPU offline path, we can't depend on
preempt_disable() to prevent CPUs from going offline from under us.

Use the get/put_online_cpus_stable_atomic() APIs to prevent CPUs from going
offline, while invoking from atomic context.

Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@xxxxxxxxxxxxxxxxxx>
---

 kernel/smp.c |   30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/kernel/smp.c b/kernel/smp.c
index 581727c..ea81293 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -688,12 +688,12 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait)
 	unsigned long flags;
 	int ret = 0;
 
-	preempt_disable();
+	get_online_cpus_stable_atomic();
 	ret = smp_call_function(func, info, wait);
 	local_irq_save(flags);
 	func(info);
 	local_irq_restore(flags);
-	preempt_enable();
+	put_online_cpus_stable_atomic();
 	return ret;
 }
 EXPORT_SYMBOL(on_each_cpu);
@@ -715,7 +715,11 @@ EXPORT_SYMBOL(on_each_cpu);
 void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
 			void *info, bool wait)
 {
-	int cpu = get_cpu();
+	int cpu;
+
+	get_online_cpus_stable_atomic();
+
+	cpu = smp_processor_id();
 
 	smp_call_function_many(mask, func, info, wait);
 	if (cpumask_test_cpu(cpu, mask)) {
@@ -723,7 +727,7 @@ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
 		func(info);
 		local_irq_enable();
 	}
-	put_cpu();
+	put_online_cpus_stable_atomic();
 }
 EXPORT_SYMBOL(on_each_cpu_mask);
 
@@ -748,8 +752,10 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * The function might sleep if the GFP flags indicates a non
  * atomic allocation is allowed.
  *
- * Preemption is disabled to protect against CPUs going offline but not online.
- * CPUs going online during the call will not be seen or sent an IPI.
+ * We use get/put_online_cpus_stable_atomic() to have a stable online mask
+ * to work with, whose CPUs won't go offline in-between our operation.
+ * And we will skip those CPUs which have already begun their offline journey.
+ * CPUs coming online during the call will not be seen or sent an IPI.
  *
  * You must not call this function with disabled interrupts or
  * from a hardware interrupt handler or from a bottom half handler.
@@ -764,26 +770,26 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 	might_sleep_if(gfp_flags & __GFP_WAIT);
 
 	if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
-		preempt_disable();
-		for_each_online_cpu(cpu)
+		get_online_cpus_stable_atomic();
+		for_each_online_cpu_stable(cpu)
 			if (cond_func(cpu, info))
 				cpumask_set_cpu(cpu, cpus);
 		on_each_cpu_mask(cpus, func, info, wait);
-		preempt_enable();
+		put_online_cpus_stable_atomic();
 		free_cpumask_var(cpus);
 	} else {
 		/*
 		 * No free cpumask, bother. No matter, we'll
 		 * just have to IPI them one by one.
 		 */
-		preempt_disable();
-		for_each_online_cpu(cpu)
+		get_online_cpus_stable_atomic();
+		for_each_online_cpu_stable(cpu)
 			if (cond_func(cpu, info)) {
 				ret = smp_call_function_single(cpu, func,
 								info, wait);
 				WARN_ON_ONCE(!ret);
 			}
-		preempt_enable();
+		put_online_cpus_stable_atomic();
 	}
 }
 EXPORT_SYMBOL(on_each_cpu_cond);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/