Commit 8bb78442 authored by Rafael J. Wysocki's avatar Rafael J. Wysocki Committed by Linus Torvalds
Browse files

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).

[oleg@tv-sign.ru: cleanups]
Signed-off-by: default avatarRafael J. Wysocki <rjw@sisk.pl>
Cc: Gautham R Shenoy <ego@in.ibm.com>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: default avatarOleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent f37bc271
......@@ -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;
}
......
......@@ -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;
}
......
......@@ -745,6 +745,7 @@ 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);
......@@ -752,24 +753,29 @@ static int comp_pool_callback(struct notifier_block *nfb,
}
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);
......
......@@ -2889,7 +2889,9 @@ 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);
......@@ -2897,6 +2899,7 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
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,
......
......@@ -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;
}
......
......@@ -1734,11 +1734,13 @@ 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);
......@@ -1746,6 +1748,7 @@ xfs_icsb_cpu_notify(
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. */
......
......@@ -197,5 +197,17 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
#define CPU_LOCK_ACQUIRE 0x0008 /* Acquire all hotcpu locks */
#define CPU_LOCK_RELEASE 0x0009 /* Release all hotcpu locks */
/* Used for CPU hotplug events occuring while tasks are frozen due to a suspend
* operation in progress
*/
#define CPU_TASKS_FROZEN 0x0010
#define CPU_ONLINE_FROZEN (CPU_ONLINE | CPU_TASKS_FROZEN)
#define CPU_UP_PREPARE_FROZEN (CPU_UP_PREPARE | CPU_TASKS_FROZEN)
#define CPU_UP_CANCELED_FROZEN (CPU_UP_CANCELED | CPU_TASKS_FROZEN)
#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
#define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
#define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN)
#endif /* __KERNEL__ */
#endif /* _LINUX_NOTIFIER_H */
......@@ -120,12 +120,13 @@ static int take_cpu_down(void *unused)
}
/* Requires cpu_add_remove_lock to be held */
static int _cpu_down(unsigned int cpu)
static int _cpu_down(unsigned int cpu, int tasks_frozen)
{
int err, nr_calls = 0;
struct task_struct *p;
cpumask_t old_allowed, tmp;
void *hcpu = (void *)(long)cpu;
unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
if (num_online_cpus() == 1)
return -EBUSY;
......@@ -134,11 +135,11 @@ static int _cpu_down(unsigned int cpu)
return -EINVAL;
raw_notifier_call_chain(&cpu_chain, CPU_LOCK_ACQUIRE, hcpu);
err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
hcpu, -1, &nr_calls);
if (err == NOTIFY_BAD) {
__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED, hcpu,
nr_calls, NULL);
__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
hcpu, nr_calls, NULL);
printk("%s: attempt to take down CPU %u failed\n",
__FUNCTION__, cpu);
err = -EINVAL;
......@@ -157,7 +158,7 @@ static int _cpu_down(unsigned int cpu)
if (IS_ERR(p) || cpu_online(cpu)) {
/* CPU didn't die: tell everyone. Can't complain. */
if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
hcpu) == NOTIFY_BAD)
BUG();
......@@ -176,7 +177,8 @@ static int _cpu_down(unsigned int cpu)
__cpu_die(cpu);
/* CPU is completely dead: tell everyone. Too late to complain. */
if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD, hcpu) == NOTIFY_BAD)
if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD | mod,
hcpu) == NOTIFY_BAD)
BUG();
check_for_tasks(cpu);
......@@ -186,8 +188,7 @@ out_thread:
out_allowed:
set_cpus_allowed(current, old_allowed);
out_release:
raw_notifier_call_chain(&cpu_chain, CPU_LOCK_RELEASE,
(void *)(long)cpu);
raw_notifier_call_chain(&cpu_chain, CPU_LOCK_RELEASE, hcpu);
return err;
}
......@@ -199,7 +200,7 @@ int cpu_down(unsigned int cpu)
if (cpu_hotplug_disabled)
err = -EBUSY;
else
err = _cpu_down(cpu);
err = _cpu_down(cpu, 0);
mutex_unlock(&cpu_add_remove_lock);
return err;
......@@ -207,16 +208,17 @@ int cpu_down(unsigned int cpu)
#endif /*CONFIG_HOTPLUG_CPU*/
/* Requires cpu_add_remove_lock to be held */
static int __cpuinit _cpu_up(unsigned int cpu)
static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
{
int ret, nr_calls = 0;
void *hcpu = (void *)(long)cpu;
unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
if (cpu_online(cpu) || !cpu_present(cpu))
return -EINVAL;
raw_notifier_call_chain(&cpu_chain, CPU_LOCK_ACQUIRE, hcpu);
ret = __raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu,
ret = __raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE | mod, hcpu,
-1, &nr_calls);
if (ret == NOTIFY_BAD) {
printk("%s: attempt to bring up CPU %u failed\n",
......@@ -234,12 +236,12 @@ static int __cpuinit _cpu_up(unsigned int cpu)
BUG_ON(!cpu_online(cpu));
/* Now call notifier in preparation. */
raw_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
out_notify:
if (ret != 0)
__raw_notifier_call_chain(&cpu_chain,
CPU_UP_CANCELED, hcpu, nr_calls, NULL);
CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
raw_notifier_call_chain(&cpu_chain, CPU_LOCK_RELEASE, hcpu);
return ret;
......@@ -253,7 +255,7 @@ int __cpuinit cpu_up(unsigned int cpu)
if (cpu_hotplug_disabled)
err = -EBUSY;
else
err = _cpu_up(cpu);
err = _cpu_up(cpu, 0);
mutex_unlock(&cpu_add_remove_lock);
return err;
......@@ -283,7 +285,7 @@ int disable_nonboot_cpus(void)
for_each_online_cpu(cpu) {
if (cpu == first_cpu)
continue;
error = _cpu_down(cpu);
error = _cpu_down(cpu, 1);
if (!error) {
cpu_set(cpu, frozen_cpus);
printk("CPU%d is down\n", cpu);
......@@ -318,7 +320,7 @@ void enable_nonboot_cpus(void)
suspend_cpu_hotplug = 1;
printk("Enabling non-boot CPUs ...\n");
for_each_cpu_mask(cpu, frozen_cpus) {
error = _cpu_up(cpu);
error = _cpu_up(cpu, 1);
if (!error) {
printk("CPU%d is up\n", cpu);
continue;
......
......@@ -1411,11 +1411,13 @@ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
init_hrtimers_cpu(cpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DEAD:
case CPU_DEAD_FROZEN:
clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
migrate_hrtimers(cpu);
break;
......
......@@ -340,6 +340,7 @@ static int __devinit profile_cpu_callback(struct notifier_block *info,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
node = cpu_to_node(cpu);
per_cpu(cpu_profile_flip, cpu) = 0;
if (!per_cpu(cpu_profile_hits, cpu)[1]) {
......@@ -365,10 +366,13 @@ static int __devinit profile_cpu_callback(struct notifier_block *info,
__free_page(page);
return NOTIFY_BAD;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
cpu_set(cpu, prof_cpu_mask);
break;
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
cpu_clear(cpu, prof_cpu_mask);
if (per_cpu(cpu_profile_hits, cpu)[0]) {
page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]);
......
......@@ -558,9 +558,11 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
long cpu = (long)hcpu;
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
rcu_online_cpu(cpu);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
rcu_offline_cpu(cpu);
break;
default:
......
......@@ -484,6 +484,7 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb,
switch(action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
mutex_lock(&relay_channels_mutex);
list_for_each_entry(chan, &relay_channels, list) {
if (chan->buf[hotcpu])
......@@ -500,6 +501,7 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb,
mutex_unlock(&relay_channels_mutex);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
/* No need to flush the cpu : will be flushed upon
* final relay_flush() call. */
break;
......
......@@ -5394,6 +5394,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
break;
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
if (IS_ERR(p))
return NOTIFY_BAD;
......@@ -5407,12 +5408,14 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
/* Strictly unneccessary, as first user will wake it. */
wake_up_process(cpu_rq(cpu)->migration_thread);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
if (!cpu_rq(cpu)->migration_thread)
break;
/* Unbind it from offline cpu so it can run. Fall thru. */
......@@ -5423,6 +5426,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
migrate_live_tasks(cpu);
rq = cpu_rq(cpu);
kthread_stop(rq->migration_thread);
......@@ -6912,14 +6916,20 @@ static int update_sched_domains(struct notifier_block *nfb,
{
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
detach_destroy_domains(&cpu_online_map);
return NOTIFY_OK;
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
/*
* Fall through and re-initialise the domains.
*/
......
......@@ -593,6 +593,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
if (IS_ERR(p)) {
printk("ksoftirqd for %i failed\n", hotcpu);
......@@ -602,16 +603,19 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
per_cpu(ksoftirqd, hotcpu) = p;
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
wake_up_process(per_cpu(ksoftirqd, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
if (!per_cpu(ksoftirqd, hotcpu))
break;
/* Unbind so it can run. Fall thru. */
kthread_bind(per_cpu(ksoftirqd, hotcpu),
any_online_cpu(cpu_online_map));
case CPU_DEAD:
case CPU_DEAD_FROZEN:
p = per_cpu(ksoftirqd, hotcpu);
per_cpu(ksoftirqd, hotcpu) = NULL;
kthread_stop(p);
......
......@@ -146,6 +146,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
BUG_ON(per_cpu(watchdog_task, hotcpu));
p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu);
if (IS_ERR(p)) {
......@@ -157,16 +158,19 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
kthread_bind(p, hotcpu);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
wake_up_process(per_cpu(watchdog_task, hotcpu));
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
if (!per_cpu(watchdog_task, hotcpu))
break;
/* Unbind so it can run. Fall thru. */
kthread_bind(per_cpu(watchdog_task, hotcpu),
any_online_cpu(cpu_online_map));
case CPU_DEAD:
case CPU_DEAD_FROZEN:
p = per_cpu(watchdog_task, hotcpu);
per_cpu(watchdog_task, hotcpu) = NULL;
kthread_stop(p);
......
......@@ -1293,11 +1293,13 @@ static int __cpuinit timer_cpu_notify(struct notifier_block *self,
long cpu = (long)hcpu;
switch(action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
if (init_timers_cpu(cpu) < 0)
return NOTIFY_BAD;
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DEAD:
case CPU_DEAD_FROZEN:
migrate_timers(cpu);
break;
#endif
......
......@@ -799,6 +799,8 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
struct cpu_workqueue_struct *cwq;
struct workqueue_struct *wq;
action &= ~CPU_TASKS_FROZEN;
switch (action) {
case CPU_LOCK_ACQUIRE:
mutex_lock(&workqueue_mutex);
......
......@@ -1004,7 +1004,7 @@ static int radix_tree_callback(struct notifier_block *nfb,
struct radix_tree_preload *rtp;
/* Free per-cpu pool of perloaded nodes */
if (action == CPU_DEAD) {
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
rtp = &per_cpu(radix_tree_preloads, cpu);
while (rtp->nr) {
kmem_cache_free(radix_tree_node_cachep,
......
......@@ -2148,11 +2148,14 @@ static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
if (process_zones(cpu))
ret = NOTIFY_BAD;
break;
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
free_zone_pagesets(cpu);
break;
default:
......@@ -3012,7 +3015,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
{
int cpu = (unsigned long)hcpu;
if (action == CPU_DEAD) {
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
local_irq_disable();
__drain_pages(cpu);
vm_events_fold_cpu(cpu);
......
......@@ -1190,6 +1190,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
mutex_lock(&cache_chain_mutex);
break;
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
/*
* We need to do this right in the beginning since
* alloc_arraycache's are going to use this list.
......@@ -1276,10 +1277,12 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
}
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
start_cpu_timer(cpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
/*
* Shutdown cache reaper. Note that the cache_chain_mutex is
* held so that if cache_reap() is invoked it cannot do
......@@ -1291,9 +1294,11 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
per_cpu(reap_work, cpu).work.func = NULL;
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
start_cpu_timer(cpu);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
/*
* Even if all the cpus of a node are down, we don't free the
* kmem_list3 of any cache. This to avoid a race between
......@@ -1305,6 +1310,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
/* fall thru */
#endif
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
list_for_each_entry(cachep, &cache_chain, next) {
struct array_cache *nc;
struct array_cache *shared;
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment