Page allocator: clean up pcp draining functions

- Add comments explaing how drain_pages() works.

- Eliminate useless functions

- Rename drain_all_local_pages to drain_all_pages(). It does drain
  all pages not only those of the local processor.

- Eliminate useless interrupt off / on sequences. drain_pages()
  disables interrupts on its own. The execution thread is
  pinned to processor by the caller. So there is no need to
  disable interrupts.

- Put drain_all_pages() declaration in gfp.h and remove the
  declarations from suspend.h and from mm/memory_hotplug.c

- Make software suspend call drain_all_pages(). The draining
  of processor local pages is may not the right approach if
  software suspend wants to support SMP. If they call drain_all_pages
  then we can make drain_pages() static.

[akpm@linux-foundation.org: fix build]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Daniel Walker <dwalker@mvista.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/gfp.h

@@ -228,5 +228,7 @@ extern void FASTCALL(free_cold_page(struct page *page));
 
 void page_alloc_init(void);
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
+void drain_all_pages(void);
+void drain_local_pages(void *dummy);
 
 #endif /* __LINUX_GFP_H */

include/linux/suspend.h

@@ -130,7 +130,6 @@ struct pbe {
 };
 
 /* mm/page_alloc.c */
-extern void drain_local_pages(void);
 extern void mark_free_pages(struct zone *zone);
 
 /**

kernel/power/snapshot.c

@@ -1203,7 +1203,7 @@ asmlinkage int swsusp_save(void)
 
 	printk(KERN_INFO "PM: Creating hibernation image: \n");
 
-	drain_local_pages();
+	drain_local_pages(NULL);
 	nr_pages = count_data_pages();
 	nr_highmem = count_highmem_pages();
 	printk(KERN_INFO "PM: Need to copy %u pages\n", nr_pages + nr_highmem);
@@ -1221,7 +1221,7 @@ asmlinkage int swsusp_save(void)
 	/* During allocating of suspend pagedir, new cold pages may appear.
 	 * Kill them.
 	 */
-	drain_local_pages();
+	drain_local_pages(NULL);
 	copy_data_pages(&copy_bm, &orig_bm);
 
 	/*

mm/memory_hotplug.c

@@ -481,8 +481,6 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	return offlined;
 }
 
-extern void drain_all_local_pages(void);
-
 int offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn, unsigned long timeout)
 {
@@ -540,7 +538,7 @@ repeat:
 		lru_add_drain_all();
 		flush_scheduled_work();
 		cond_resched();
-		drain_all_local_pages();
+		drain_all_pages();
 	}
 
 	pfn = scan_lru_pages(start_pfn, end_pfn);
@@ -563,7 +561,7 @@ repeat:
 	flush_scheduled_work();
 	yield();
 	/* drain pcp pages , this is synchrouns. */
-	drain_all_local_pages();
+	drain_all_pages();
 	/* check again */
 	offlined_pages = check_pages_isolated(start_pfn, end_pfn);
 	if (offlined_pages < 0) {

mm/page_alloc.c

@@ -890,7 +890,14 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 }
 #endif
 
-static void __drain_pages(unsigned int cpu)
+/*
+ * Drain pages of the indicated processor.
+ *
+ * The processor must either be the current processor and the
+ * thread pinned to the current processor or a processor that
+ * is not online.
+ */
+static void drain_pages(unsigned int cpu)
 {
 	unsigned long flags;
 	struct zone *zone;
@@ -915,6 +922,22 @@ static void __drain_pages(unsigned int cpu)
 	}
 }
 
+/*
+ * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ */
+void drain_local_pages(void *arg)
+{
+	drain_pages(smp_processor_id());
+}
+
+/*
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ */
+void drain_all_pages(void)
+{
+	on_each_cpu(drain_local_pages, NULL, 0, 1);
+}
+
 #ifdef CONFIG_HIBERNATION
 
 void mark_free_pages(struct zone *zone)
@@ -951,37 +974,6 @@ void mark_free_pages(struct zone *zone)
 }
 #endif /* CONFIG_PM */
 
-/*
- * Spill all of this CPU's per-cpu pages back into the buddy allocator.
- */
-void drain_local_pages(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);	
-	__drain_pages(smp_processor_id());
-	local_irq_restore(flags);	
-}
-
-void smp_drain_local_pages(void *arg)
-{
-	drain_local_pages();
-}
-
-/*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
- */
-void drain_all_local_pages(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__drain_pages(smp_processor_id());
-	local_irq_restore(flags);
-
-	smp_call_function(smp_drain_local_pages, NULL, 0, 1);
-}
-
 /*
  * Free a 0-order page
  */
@@ -1569,7 +1561,7 @@ nofail_alloc:
 	cond_resched();
 
 	if (order != 0)
-		drain_all_local_pages();
+		drain_all_pages();
 
 	if (likely(did_some_progress)) {
 		page = get_page_from_freelist(gfp_mask, order,
@@ -3978,10 +3970,23 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
 	int cpu = (unsigned long)hcpu;
 
 	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		local_irq_disable();
+		drain_pages(cpu);
-		__drain_pages(cpu);
+
+		/*
+		 * Spill the event counters of the dead processor
+		 * into the current processors event counters.
+		 * This artificially elevates the count of the current
+		 * processor.
+		 */
 		vm_events_fold_cpu(cpu);
-		local_irq_enable();
+
+		/*
+		 * Zero the differential counters of the dead processor
+		 * so that the vm statistics are consistent.
+		 *
+		 * This is only okay since the processor is dead and cannot
+		 * race with what we are doing.
+		 */
 		refresh_cpu_vm_stats(cpu);
 	}
 	return NOTIFY_OK;
@@ -4480,7 +4485,7 @@ int set_migratetype_isolate(struct page *page)
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
 	if (!ret)
-		drain_all_local_pages();
+		drain_all_pages();
 	return ret;
 }