Merge tag 'cpu-hotplug-3.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull CPU hotplug notifiers registration fixes from Rafael Wysocki:
 "The purpose of this single series of commits from Srivatsa S Bhat
  (with a small piece from Gautham R Shenoy) touching multiple
  subsystems that use CPU hotplug notifiers is to provide a way to
  register them that will not lead to deadlocks with CPU online/offline
  operations as described in the changelog of commit 93ae4f978ca7f ("CPU
  hotplug: Provide lockless versions of callback registration
  functions").

  The first three commits in the series introduce the API and document
  it and the rest simply goes through the users of CPU hotplug notifiers
  and converts them to using the new method"

* tag 'cpu-hotplug-3.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (52 commits)
  net/iucv/iucv.c: Fix CPU hotplug callback registration
  net/core/flow.c: Fix CPU hotplug callback registration
  mm, zswap: Fix CPU hotplug callback registration
  mm, vmstat: Fix CPU hotplug callback registration
  profile: Fix CPU hotplug callback registration
  trace, ring-buffer: Fix CPU hotplug callback registration
  xen, balloon: Fix CPU hotplug callback registration
  hwmon, via-cputemp: Fix CPU hotplug callback registration
  hwmon, coretemp: Fix CPU hotplug callback registration
  thermal, x86-pkg-temp: Fix CPU hotplug callback registration
  octeon, watchdog: Fix CPU hotplug callback registration
  oprofile, nmi-timer: Fix CPU hotplug callback registration
  intel-idle: Fix CPU hotplug callback registration
  clocksource, dummy-timer: Fix CPU hotplug callback registration
  drivers/base/topology.c: Fix CPU hotplug callback registration
  acpi-cpufreq: Fix CPU hotplug callback registration
  zsmalloc: Fix CPU hotplug callback registration
  scsi, fcoe: Fix CPU hotplug callback registration
  scsi, bnx2fc: Fix CPU hotplug callback registration
  scsi, bnx2i: Fix CPU hotplug callback registration
  ...

3 files changed, 62 insertions, 15 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index deff2e6..a9e710e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/gfp.h>
 #include <linux/suspend.h>
+#include <linux/lockdep.h>
 
 #include "smpboot.h"
 
@@ -27,18 +28,23 @@
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
 /*
- * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_mask, cpu_present_mask.
+ * The following two APIs (cpu_maps_update_begin/done) must be used when
+ * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
+ * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
+ * hotplug callback (un)registration performed using __register_cpu_notifier()
+ * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
+EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
+EXPORT_SYMBOL(cpu_notifier_register_done);
 
 static RAW_NOTIFIER_HEAD(cpu_chain);
 
@@ -57,17 +63,30 @@ static struct {
 	 * an ongoing cpu hotplug operation.
 	 */
 	int refcount;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
 } cpu_hotplug = {
 	.active_writer = NULL,
 	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
 	.refcount = 0,
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	.dep_map = {.name = "cpu_hotplug.lock" },
+#endif
 };
 
+/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
+#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
+#define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
+#define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
+
 void get_online_cpus(void)
 {
 	might_sleep();
 	if (cpu_hotplug.active_writer == current)
 		return;
+	cpuhp_lock_acquire_read();
 	mutex_lock(&cpu_hotplug.lock);
 	cpu_hotplug.refcount++;
 	mutex_unlock(&cpu_hotplug.lock);
@@ -87,6 +106,7 @@ void put_online_cpus(void)
 	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
 		wake_up_process(cpu_hotplug.active_writer);
 	mutex_unlock(&cpu_hotplug.lock);
+	cpuhp_lock_release();
 
 }
 EXPORT_SYMBOL_GPL(put_online_cpus);
@@ -117,6 +137,7 @@ void cpu_hotplug_begin(void)
 {
 	cpu_hotplug.active_writer = current;
 
+	cpuhp_lock_acquire();
 	for (;;) {
 		mutex_lock(&cpu_hotplug.lock);
 		if (likely(!cpu_hotplug.refcount))
@@ -131,6 +152,7 @@ void cpu_hotplug_done(void)
 {
 	cpu_hotplug.active_writer = NULL;
 	mutex_unlock(&cpu_hotplug.lock);
+	cpuhp_lock_release();
 }
 
 /*
@@ -166,6 +188,11 @@ int __ref register_cpu_notifier(struct notifier_block *nb)
 	return ret;
 }
 
+int __ref __register_cpu_notifier(struct notifier_block *nb)
+{
+	return raw_notifier_chain_register(&cpu_chain, nb);
+}
+
 static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
 			int *nr_calls)
 {
@@ -189,6 +216,7 @@ static void cpu_notify_nofail(unsigned long val, void *v)
 	BUG_ON(cpu_notify(val, v));
 }
 EXPORT_SYMBOL(register_cpu_notifier);
+EXPORT_SYMBOL(__register_cpu_notifier);
 
 void __ref unregister_cpu_notifier(struct notifier_block *nb)
 {
@@ -198,6 +226,12 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_cpu_notifier);
 
+void __ref __unregister_cpu_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_unregister(&cpu_chain, nb);
+}
+EXPORT_SYMBOL(__unregister_cpu_notifier);
+
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
  * @cpu: a CPU id
diff --git a/kernel/profile.c b/kernel/profile.c
index 1b266db..cb980f0 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -591,18 +591,28 @@ out_cleanup:
 int __ref create_proc_profile(void) /* false positive from hotcpu_notifier */
 {
 	struct proc_dir_entry *entry;
+	int err = 0;
 
 	if (!prof_on)
 		return 0;
-	if (create_hash_tables())
-		return -ENOMEM;
+
+	cpu_notifier_register_begin();
+
+	if (create_hash_tables()) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	entry = proc_create("profile", S_IWUSR | S_IRUGO,
 			    NULL, &proc_profile_operations);
 	if (!entry)
-		return 0;
+		goto out;
 	proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
-	hotcpu_notifier(profile_cpu_callback, 0);
-	return 0;
+	__hotcpu_notifier(profile_cpu_callback, 0);
+
+out:
+	cpu_notifier_register_done();
+	return err;
 }
 subsys_initcall(create_proc_profile);
 #endif /* CONFIG_PROC_FS */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index fc4da2d..c634868 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1301,7 +1301,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	 * In that off case, we need to allocate for all possible cpus.
 	 */
 #ifdef CONFIG_HOTPLUG_CPU
-	get_online_cpus();
+	cpu_notifier_register_begin();
 	cpumask_copy(buffer->cpumask, cpu_online_mask);
 #else
 	cpumask_copy(buffer->cpumask, cpu_possible_mask);
@@ -1324,10 +1324,10 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 #ifdef CONFIG_HOTPLUG_CPU
 	buffer->cpu_notify.notifier_call = rb_cpu_notify;
 	buffer->cpu_notify.priority = 0;
-	register_cpu_notifier(&buffer->cpu_notify);
+	__register_cpu_notifier(&buffer->cpu_notify);
+	cpu_notifier_register_done();
 #endif
 
-	put_online_cpus();
 	mutex_init(&buffer->mutex);
 
 	return buffer;
@@ -1341,7 +1341,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 
  fail_free_cpumask:
 	free_cpumask_var(buffer->cpumask);
-	put_online_cpus();
+#ifdef CONFIG_HOTPLUG_CPU
+	cpu_notifier_register_done();
+#endif
 
  fail_free_buffer:
 	kfree(buffer);
@@ -1358,16 +1360,17 @@ ring_buffer_free(struct ring_buffer *buffer)
 {
 	int cpu;
 
-	get_online_cpus();
-
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_cpu_notifier(&buffer->cpu_notify);
+	cpu_notifier_register_begin();
+	__unregister_cpu_notifier(&buffer->cpu_notify);
 #endif
 
 	for_each_buffer_cpu(buffer, cpu)
 		rb_free_cpu_buffer(buffer->buffers[cpu]);
 
-	put_online_cpus();
+#ifdef CONFIG_HOTPLUG_CPU
+	cpu_notifier_register_done();
+#endif
 
 	kfree(buffer->buffers);
 	free_cpumask_var(buffer->cpumask);