Add suspend-related notifications for CPU hotplug

Since nonboot CPUs are now disabled after tasks and devices have been frozen and the CPU hotplug infrastructure is used for this purpose, we need special CPU hotplug notifications that will help the CPU-hotplug-aware subsystems distinguish normal CPU hotplug events from CPU hotplug events related to a system-wide suspend or resume operation in progress. This patch introduces such notifications and causes them to be used during suspend and resume transitions. It also changes all of the CPU-hotplug-aware subsystems to take these notifications into consideration (for now they are handled in the same way as the corresponding "normal" ones). [[email protected]: cleanups] Signed-off-by: Rafael J. Wysocki <[email protected]> Cc: Gautham R Shenoy <[email protected]> Cc: Pavel Machek <[email protected]> Signed-off-by: Oleg Nesterov <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
josf · May 9, 2007 · 8bb7844 · 8bb7844
1 parent f37bc27
commit 8bb7844
Show file tree

Hide file tree

Showing 47 changed files with 152 additions and 27 deletions.
diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
@@ -217,14 +217,17 @@ Q: What happens when a CPU is being logically offlined?
 A: The following happen, listed in no particular order :-)
 
 - A notification is sent to in-kernel registered modules by sending an event
-  CPU_DOWN_PREPARE
+  CPU_DOWN_PREPARE or CPU_DOWN_PREPARE_FROZEN, depending on whether or not the
+  CPU is being offlined while tasks are frozen due to a suspend operation in
+  progress
 - All process is migrated away from this outgoing CPU to a new CPU
 - All interrupts targeted to this CPU is migrated to a new CPU
 - timers/bottom half/task lets are also migrated to a new CPU
 - Once all services are migrated, kernel calls an arch specific routine
   __cpu_disable() to perform arch specific cleanup.
 - Once this is successful, an event for successful cleanup is sent by an event
-  CPU_DEAD.
+  CPU_DEAD (or CPU_DEAD_FROZEN if tasks are frozen due to a suspend while the
+  CPU is being offlined).
 
   "It is expected that each service cleans up when the CPU_DOWN_PREPARE
   notifier is called, when CPU_DEAD is called its expected there is nothing
@@ -242,9 +245,11 @@ A: This is what you would need in your kernel code to receive notifications.
 
 		switch (action) {
 		case CPU_ONLINE:
+		case CPU_ONLINE_FROZEN:
 			foobar_online_action(cpu);
 			break;
 		case CPU_DEAD:
+		case CPU_DEAD_FROZEN:
 			foobar_dead_action(cpu);
 			break;
 		}

diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c
@@ -733,9 +733,11 @@ static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb,
 	sys_dev = get_cpu_sysdev(cpu);
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		cache_add_dev(sys_dev);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		cache_remove_dev(sys_dev);
 		break;
 	}

diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c
@@ -137,10 +137,12 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	mutex_lock(&therm_cpu_lock);
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		err = thermal_throttle_add_dev(sys_dev);
 		WARN_ON(err);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		thermal_throttle_remove_dev(sys_dev);
 		break;
 	}

diff --git a/arch/i386/kernel/cpuid.c b/arch/i386/kernel/cpuid.c
@@ -169,9 +169,11 @@ static int cpuid_class_cpu_callback(struct notifier_block *nfb, unsigned long ac
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		cpuid_device_create(cpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu));
 		break;
 	}

diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c
@@ -775,10 +775,13 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 	sys_dev = get_cpu_sysdev(cpu);
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
 		mc_sysdev_add(sys_dev);
 		break;
 	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
 		mc_sysdev_remove(sys_dev);
 		break;
 	}

diff --git a/arch/i386/kernel/msr.c b/arch/i386/kernel/msr.c
@@ -153,9 +153,11 @@ static int msr_class_cpu_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		msr_device_create(cpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu));
 		break;
 	}

diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
@@ -236,9 +236,11 @@ static int __cpuinit err_inject_cpu_callback(struct notifier_block *nfb,
 	sys_dev = get_cpu_sysdev(cpu);
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		err_inject_add_dev(sys_dev);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		err_inject_remove_dev(sys_dev);
 		break;
 	}

diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c
@@ -975,9 +975,11 @@ static int palinfo_cpu_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		create_palinfo_proc_entries(hotcpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		remove_palinfo_proc_entries(hotcpu);
 		break;
 	}

diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
@@ -582,6 +582,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu
 	struct salinfo_data *data;
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		spin_lock_irqsave(&data_saved_lock, flags);
 		for (i = 0, data = salinfo_data;
 		     i < ARRAY_SIZE(salinfo_data);
@@ -592,6 +593,7 @@ salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu
 		spin_unlock_irqrestore(&data_saved_lock, flags);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		spin_lock_irqsave(&data_saved_lock, flags);
 		for (i = 0, data = salinfo_data;
 		     i < ARRAY_SIZE(salinfo_data);

diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
@@ -412,9 +412,11 @@ static int __cpuinit cache_cpu_callback(struct notifier_block *nfb,
 	sys_dev = get_cpu_sysdev(cpu);
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		cache_add_dev(sys_dev);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		cache_remove_dev(sys_dev);
 		break;
 	}

diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
@@ -342,10 +342,12 @@ static int __cpuinit sysfs_cpu_notify(struct notifier_block *self,
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		register_cpu_online(cpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		unregister_cpu_online(cpu);
 		break;
 #endif

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
@@ -252,12 +252,15 @@ static int __cpuinit cpu_numa_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		numa_setup_cpu(lcpu);
 		ret = NOTIFY_OK;
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 		unmap_cpu_from_node(lcpu);
 		break;
 		ret = NOTIFY_OK;

diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
@@ -567,9 +567,11 @@ appldata_cpu_notify(struct notifier_block *self,
 {
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		appldata_online_cpu((long) hcpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		appldata_offline_cpu((long) hcpu);
 		break;
 	default:

diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
@@ -789,10 +789,12 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self,
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		if (sysdev_create_file(s, &attr_capability))
 			return NOTIFY_BAD;
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		sysdev_remove_file(s, &attr_capability);
 		break;
 	}

diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
@@ -720,9 +720,11 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		mce_create_device(cpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		mce_remove_device(cpu);
 		break;
 	}

diff --git a/arch/x86_64/kernel/mce_amd.c b/arch/x86_64/kernel/mce_amd.c
@@ -654,9 +654,11 @@ static int threshold_cpu_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		threshold_create_device(cpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		threshold_remove_device(cpu);
 		break;
 	default:

diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
@@ -327,7 +327,7 @@ static int __cpuinit
 cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
 {
 	long cpu = (long)arg;
-	if (action == CPU_ONLINE)
+	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
 		smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 0, 1);
 	return NOTIFY_DONE;
 }

diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
@@ -3507,7 +3507,7 @@ static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
 	 * If a CPU goes away, splice its entries to the current CPU
 	 * and trigger a run of the softirq
 	 */
-	if (action == CPU_DEAD) {
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
 		int cpu = (unsigned long) hcpu;
 
 		local_irq_disable();

diff --git a/drivers/base/topology.c b/drivers/base/topology.c
@@ -126,10 +126,13 @@ static int __cpuinit topology_cpu_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		rc = topology_add_dev(cpu);
 		break;
 	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		topology_remove_dev(cpu);
 		break;
 	}

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
@@ -1685,9 +1685,11 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 	if (sys_dev) {
 		switch (action) {
 		case CPU_ONLINE:
+		case CPU_ONLINE_FROZEN:
 			cpufreq_add_dev(sys_dev);
 			break;
 		case CPU_DOWN_PREPARE:
+		case CPU_DOWN_PREPARE_FROZEN:
 			if (unlikely(lock_policy_rwsem_write(cpu)))
 				BUG();
 
@@ -1699,6 +1701,7 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 			__cpufreq_remove_dev(sys_dev);
 			break;
 		case CPU_DOWN_FAILED:
+		case CPU_DOWN_FAILED_FROZEN:
 			cpufreq_add_dev(sys_dev);
 			break;
 		}

diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
@@ -313,9 +313,11 @@ static int cpufreq_stat_cpu_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		cpufreq_update_policy(cpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		cpufreq_stats_free_table(cpu);
 		break;
 	}

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
@@ -309,9 +309,11 @@ static int coretemp_cpu_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		coretemp_device_add(cpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		coretemp_device_remove(cpu);
 		break;
 	}

diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -745,31 +745,37 @@ static int comp_pool_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
 		if(!create_comp_task(pool, cpu)) {
 			ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
 			return NOTIFY_BAD;
 		}
 		break;
 	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_CANCELED)", cpu);
 		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
 		kthread_bind(cct->task, any_online_cpu(cpu_online_map));
 		destroy_comp_task(pool, cpu);
 		break;
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_ONLINE)", cpu);
 		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
 		kthread_bind(cct->task, cpu);
 		wake_up_process(cct->task);
 		break;
 	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_DOWN_PREPARE)", cpu);
 		break;
 	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_DOWN_FAILED)", cpu);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_DEAD)", cpu);
 		destroy_comp_task(pool, cpu);
 		take_over_work(pool, cpu);

diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
@@ -2889,14 +2889,17 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 
 	switch (val) {
 	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
 	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
 		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
 		       cpu);
 		decache_vcpus_on_cpu(cpu);
 		smp_call_function_single(cpu, kvm_arch_ops->hardware_disable,
 					 NULL, 0, 1);
 		break;
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
 		smp_call_function_single(cpu, kvm_arch_ops->hardware_enable,

diff --git a/fs/buffer.c b/fs/buffer.c
@@ -2946,7 +2946,7 @@ static void buffer_exit_cpu(int cpu)
 static int buffer_cpu_notify(struct notifier_block *self,
 			      unsigned long action, void *hcpu)
 {
-	if (action == CPU_DEAD)
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
 		buffer_exit_cpu((unsigned long)hcpu);
 	return NOTIFY_OK;
 }

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
@@ -1734,18 +1734,21 @@ xfs_icsb_cpu_notify(
 			per_cpu_ptr(mp->m_sb_cnts, (unsigned long)hcpu);
 	switch (action) {
 	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
 		/* Easy Case - initialize the area and locks, and
 		 * then rebalance when online does everything else for us. */
 		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
 		break;
 	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		xfs_icsb_lock(mp);
 		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0, 0);
 		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0, 0);
 		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0, 0);
 		xfs_icsb_unlock(mp);
 		break;
 	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
 		/* Disable all the counters, then fold the dead cpu's
 		 * count into the total on the global superblock and
 		 * re-enable the counters. */