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: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Gautham R Shenoy <ego@in.ibm.com>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 17 insertions, 3 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6fd0b7455b0..d53cbf8acb8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -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);
diff --git a/mm/slab.c b/mm/slab.c
index 1a7a10de2a4..6f3d6e240c6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -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;
diff --git a/mm/slub.c b/mm/slub.c
index f7c120b93c4..a581fa8ae11 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2514,7 +2514,9 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
 
         switch (action) {
         case CPU_UP_CANCELED:
+        case CPU_UP_CANCELED_FROZEN:
         case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
                 for_all_slabs(__flush_cpu_slab, cpu);
                 break;
         default:
diff --git a/mm/swap.c b/mm/swap.c
index 218c52a24a2..d3cb966fe99 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -488,7 +488,7 @@ static int cpu_swap_callback(struct notifier_block *nfb,
         long *committed;
 
         committed = &per_cpu(committed_space, (long)hcpu);
-        if (action == CPU_DEAD) {
+        if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
                 atomic_add(*committed, &vm_committed_space);
                 *committed = 0;
                 __lru_add_drain((long)hcpu);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1c8e75a1cfc..1be5a6376ef 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1528,7 +1528,7 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
         pg_data_t *pgdat;
         cpumask_t mask;
 
-        if (action == CPU_ONLINE) {
+        if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
                 for_each_online_pgdat(pgdat) {
                         mask = node_to_cpumask(pgdat->node_id);
                         if (any_online_cpu(mask) != NR_CPUS)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6c488d6ac42..9a66dc4aed4 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -650,8 +650,11 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 {
         switch (action) {
         case CPU_UP_PREPARE:
+        case CPU_UP_PREPARE_FROZEN:
         case CPU_UP_CANCELED:
+        case CPU_UP_CANCELED_FROZEN:
         case CPU_DEAD:
+        case CPU_DEAD_FROZEN:
                 refresh_zone_stat_thresholds();
                 break;
         default: