[PATCH -v11 resend 01/11] CPU hotplug: Provide a generic helper to disable/enable CPU hotplug

[PATCH -v11 resend 01/11] CPU hotplug: Provide a generic helper to disable/enable CPU hotplug

[Robin Holt]

From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>

There are instances in the kernel where we would like to disable
CPU hotplug (from sysfs) during some important operation. Today
the freezer code depends on this and the code to do it was kinda
tailor-made for that.

Restructure the code and make it generic enough to be useful for
other usecases too.

Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Robin Holt <holt@sgi.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Russ Anderson <rja@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Cc: the arch/x86 maintainers <x86@kernel.org>
Cc: Arm Mailing List <linux-arm-kernel@lists.infradead.org>
Cc: <stable@vger.kernel.org>
---
 include/linux/cpu.h |  4 ++++
 kernel/cpu.c        | 55 ++++++++++++++++++++++-------------------------------
 2 files changed, 27 insertions(+), 32 deletions(-)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index c6f6e08..9f3c7e8 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -175,6 +175,8 @@ extern struct bus_type cpu_subsys;
 
 extern void get_online_cpus(void);
 extern void put_online_cpus(void);
+extern void cpu_hotplug_disable(void);
+extern void cpu_hotplug_enable(void);
 #define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
 #define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
 #define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
@@ -198,6 +200,8 @@ static inline void cpu_hotplug_driver_unlock(void)
 
 #define get_online_cpus()	do { } while (0)
 #define put_online_cpus()	do { } while (0)
+#define cpu_hotplug_disable()	do { } while (0)
+#define cpu_hotplug_enable()	do { } while (0)
 #define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 /* These aren't inline functions due to a GCC bug. */
 #define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
diff --git a/kernel/cpu.c b/kernel/cpu.c
index b5e4ab2..198a388 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -133,6 +133,27 @@ static void cpu_hotplug_done(void)
 	mutex_unlock(&cpu_hotplug.lock);
 }
 
+/*
+ * Wait for currently running CPU hotplug operations to complete (if any) and
+ * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
+ * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
+ * hotplug path before performing hotplug operations. So acquiring that lock
+ * guarantees mutual exclusion from any currently running hotplug operations.
+ */
+void cpu_hotplug_disable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 1;
+	cpu_maps_update_done();
+}
+
+void cpu_hotplug_enable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 0;
+	cpu_maps_update_done();
+}
+
 #else /* #if CONFIG_HOTPLUG_CPU */
 static void cpu_hotplug_begin(void) {}
 static void cpu_hotplug_done(void) {}
@@ -541,36 +562,6 @@ static int __init alloc_frozen_cpus(void)
 core_initcall(alloc_frozen_cpus);
 
 /*
- * Prevent regular CPU hotplug from racing with the freezer, by disabling CPU
- * hotplug when tasks are about to be frozen. Also, don't allow the freezer
- * to continue until any currently running CPU hotplug operation gets
- * completed.
- * To modify the 'cpu_hotplug_disabled' flag, we need to acquire the
- * 'cpu_add_remove_lock'. And this same lock is also taken by the regular
- * CPU hotplug path and released only after it is complete. Thus, we
- * (and hence the freezer) will block here until any currently running CPU
- * hotplug operation gets completed.
- */
-void cpu_hotplug_disable_before_freeze(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 1;
-	cpu_maps_update_done();
-}
-
-
-/*
- * When tasks have been thawed, re-enable regular CPU hotplug (which had been
- * disabled while beginning to freeze tasks).
- */
-void cpu_hotplug_enable_after_thaw(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 0;
-	cpu_maps_update_done();
-}
-
-/*
  * When callbacks for CPU hotplug notifications are being executed, we must
  * ensure that the state of the system with respect to the tasks being frozen
  * or not, as reported by the notification, remains unchanged *throughout the
@@ -589,12 +580,12 @@ cpu_hotplug_pm_callback(struct notifier_block *nb,
 
 	case PM_SUSPEND_PREPARE:
 	case PM_HIBERNATION_PREPARE:
-		cpu_hotplug_disable_before_freeze();
+		cpu_hotplug_disable();
 		break;
 
 	case PM_POST_SUSPEND:
 	case PM_POST_HIBERNATION:
-		cpu_hotplug_enable_after_thaw();
+		cpu_hotplug_enable();
 		break;
 
 	default:
-- 
1.8.2.1

[PATCH -v11 resend 02/11] Migrate shutdown/reboot to boot cpu.

[Robin Holt]

We recently noticed that reboot of a 1024 cpu machine takes approx 16
minutes of just stopping the cpus.  The slowdown was tracked to commit
f96972f.

The current implementation does all the work of hot removing the cpus
before halting the system.  We are switching to just migrating to the
boot cpu and then continuing with shutdown/reboot.

This also has the effect of not breaking x86's command line parameter for
specifying the reboot cpu.  Note, this code was shamelessly copied from
arch/x86/kernel/reboot.c with bits removed pertaining to the reboot_cpu
command line parameter.

Signed-off-by: Robin Holt <holt@sgi.com>
Tested-by: Shawn Guo <shawn.guo@linaro.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Russ Anderson <rja@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Cc: the arch/x86 maintainers <x86@kernel.org>
Cc: Arm Mailing List <linux-arm-kernel@lists.infradead.org>
Cc: <stable@vger.kernel.org>

---

Changes since -v8
 - Change stack parameter to make future patches cleaner.

Changes since -v6:
 - Add #define for PF_THREAD_BOUND as compatibility to make stable easier.
 - Fixup s/reboot_cpu_id/reboot_cpu/
---
 kernel/sys.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index b95d3c7..2bbd9a7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -362,6 +362,29 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
+/* Add backwards compatibility for stable trees. */
+#ifndef PF_NO_SETAFFINITY
+#define PF_NO_SETAFFINITY		PF_THREAD_BOUND
+#endif
+
+static void migrate_to_reboot_cpu(void)
+{
+	/* The boot cpu is always logical cpu 0 */
+	int cpu = 0;
+
+	cpu_hotplug_disable();
+
+	/* Make certain the cpu I'm about to reboot on is online */
+	if (!cpu_online(cpu))
+		cpu = cpumask_first(cpu_online_mask);
+
+	/* Prevent races with other tasks migrating this task */
+	current->flags |= PF_NO_SETAFFINITY;
+
+	/* Make certain I only run on the appropriate processor */
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
 /**
  *	kernel_restart - reboot the system
  *	@cmd: pointer to buffer containing command to execute for restart
@@ -373,7 +396,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
@@ -400,7 +423,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -419,7 +442,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
-- 
1.8.2.1

[PATCH -v11 resend 02/11] Migrate shutdown/reboot to boot cpu.

[Robin Holt]

We recently noticed that reboot of a 1024 cpu machine takes approx 16
minutes of just stopping the cpus.  The slowdown was tracked to commit
f96972f.

The current implementation does all the work of hot removing the cpus
before halting the system.  We are switching to just migrating to the
boot cpu and then continuing with shutdown/reboot.

This also has the effect of not breaking x86's command line parameter for
specifying the reboot cpu.  Note, this code was shamelessly copied from
arch/x86/kernel/reboot.c with bits removed pertaining to the reboot_cpu
command line parameter.

Signed-off-by: Robin Holt <holt@sgi.com>
Tested-by: Shawn Guo <shawn.guo@linaro.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Russ Anderson <rja@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Cc: the arch/x86 maintainers <x86@kernel.org>
Cc: Arm Mailing List <linux-arm-kernel@lists.infradead.org>
Cc: <stable@vger.kernel.org>

---

Changes since -v8
 - Change stack parameter to make future patches cleaner.

Changes since -v6:
 - Add #define for PF_THREAD_BOUND as compatibility to make stable easier.
 - Fixup s/reboot_cpu_id/reboot_cpu/
---
 kernel/sys.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index b95d3c7..2bbd9a7 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -362,6 +362,29 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
+/* Add backwards compatibility for stable trees. */
+#ifndef PF_NO_SETAFFINITY
+#define PF_NO_SETAFFINITY		PF_THREAD_BOUND
+#endif
+
+static void migrate_to_reboot_cpu(void)
+{
+	/* The boot cpu is always logical cpu 0 */
+	int cpu = 0;
+
+	cpu_hotplug_disable();
+
+	/* Make certain the cpu I'm about to reboot on is online */
+	if (!cpu_online(cpu))
+		cpu = cpumask_first(cpu_online_mask);
+
+	/* Prevent races with other tasks migrating this task */
+	current->flags |= PF_NO_SETAFFINITY;
+
+	/* Make certain I only run on the appropriate processor */
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
 /**
  *	kernel_restart - reboot the system
  *	@cmd: pointer to buffer containing command to execute for restart
@@ -373,7 +396,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
@@ -400,7 +423,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -419,7 +442,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
-- 
1.8.2.1