From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:37 -0500
Subject: mm: page_alloc: rt-friendly per-cpu pages
Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git
Git-commit: da77ceac3d20f27310a07a7c346a4ee6b40d6c28
Patch-mainline: Queued in subsystem maintainer repository
References: SLE Realtime Extension

rt-friendly per-cpu pages: convert the irqs-off per-cpu locking
method into a preemptible, explicit-per-cpu-locks method.

Contains fixes from:
	 Peter Zijlstra <a.p.zijlstra@chello.nl>
	 Thomas Gleixner <tglx@linutronix.de>

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
---
 mm/page_alloc.c |   51 ++++++++++++++++++++++++++++++++-------------------
 1 file changed, 32 insertions(+), 19 deletions(-)

--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -61,6 +61,7 @@
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/mm.h>
+#include <linux/locallock.h>
 #include <linux/page_owner.h>
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
@@ -357,6 +358,18 @@ EXPORT_SYMBOL(nr_node_ids);
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
+static DEFINE_LOCAL_IRQ_LOCK(pa_lock);
+
+#ifdef CONFIG_PREEMPT_RT
+# define cpu_lock_irqsave(cpu, flags)		\
+	local_lock_irqsave_on(pa_lock, flags, cpu)
+# define cpu_unlock_irqrestore(cpu, flags)	\
+	local_unlock_irqrestore_on(pa_lock, flags, cpu)
+#else
+# define cpu_lock_irqsave(cpu, flags)		local_irq_save(flags)
+# define cpu_unlock_irqrestore(cpu, flags)	local_irq_restore(flags)
+#endif
+
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -1443,10 +1456,10 @@ static void __free_pages_ok(struct page
 		return;
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	__count_vm_events(PGFREE, 1 << order);
 	free_one_page(page_zone(page), page, pfn, order, migratetype);
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 
 void __free_pages_core(struct page *page, unsigned int order)
@@ -2812,13 +2825,13 @@ void drain_zone_pages(struct zone *zone,
 	int to_drain, batch;
 	LIST_HEAD(dst);
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	batch = READ_ONCE(pcp->batch);
 	to_drain = min(pcp->count, batch);
 	if (to_drain > 0)
 		isolate_pcp_pages(to_drain, pcp, &dst);
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 
 	if (to_drain > 0)
 		free_pcppages_bulk(zone, &dst, false);
@@ -2840,7 +2853,7 @@ static void drain_pages_zone(unsigned in
 	LIST_HEAD(dst);
 	int count;
 
-	local_irq_save(flags);
+	cpu_lock_irqsave(cpu, flags);
 	pset = per_cpu_ptr(zone->pageset, cpu);
 
 	pcp = &pset->pcp;
@@ -2848,7 +2861,7 @@ static void drain_pages_zone(unsigned in
 	if (count)
 		isolate_pcp_pages(count, pcp, &dst);
 
-	local_irq_restore(flags);
+	cpu_unlock_irqrestore(cpu, flags);
 
 	if (count)
 		free_pcppages_bulk(zone, &dst, false);
@@ -3098,9 +3111,9 @@ void free_unref_page(struct page *page)
 	if (!free_unref_page_prepare(page, pfn))
 		return;
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	free_unref_page_commit(page, pfn, &dst);
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 	if (!list_empty(&dst))
 		free_pcppages_bulk(zone, &dst, false);
 }
@@ -3127,7 +3140,7 @@ void free_unref_page_list(struct list_he
 		set_page_private(page, pfn);
 	}
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	list_for_each_entry_safe(page, next, list, lru) {
 		unsigned long pfn = page_private(page);
 		enum zone_type type;
@@ -3142,12 +3155,12 @@ void free_unref_page_list(struct list_he
 		 * a large list of pages to free.
 		 */
 		if (++batch_count == SWAP_CLUSTER_MAX) {
-			local_irq_restore(flags);
+			local_unlock_irqrestore(pa_lock, flags);
 			batch_count = 0;
-			local_irq_save(flags);
+			local_lock_irqsave(pa_lock, flags);
 		}
 	}
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 
 	for (i = 0; i < __MAX_NR_ZONES; ) {
 		struct page *page;
@@ -3297,7 +3310,7 @@ static struct page *rmqueue_pcplist(stru
 	struct page *page;
 	unsigned long flags;
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
 	list = &pcp->lists[migratetype];
 	page = __rmqueue_pcplist(zone,  migratetype, alloc_flags, pcp, list);
@@ -3305,7 +3318,7 @@ static struct page *rmqueue_pcplist(stru
 		__count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
 		zone_statistics(preferred_zone, zone);
 	}
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 	return page;
 }
 
@@ -3332,7 +3345,7 @@ struct page *rmqueue(struct zone *prefer
 	 * allocate greater than order-1 page units with __GFP_NOFAIL.
 	 */
 	WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
-	spin_lock_irqsave(&zone->lock, flags);
+	local_spin_lock_irqsave(pa_lock, &zone->lock, flags);
 
 	do {
 		page = NULL;
@@ -3352,7 +3365,7 @@ struct page *rmqueue(struct zone *prefer
 
 	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 	zone_statistics(preferred_zone, zone);
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 
 out:
 	/* Separate test+clear to avoid unnecessary atomics */
@@ -3365,7 +3378,7 @@ struct page *rmqueue(struct zone *prefer
 	return page;
 
 failed:
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 	return NULL;
 }
 
@@ -8599,7 +8612,7 @@ void zone_pcp_reset(struct zone *zone)
 	struct per_cpu_pageset *pset;
 
 	/* avoid races with drain_pages()  */
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	if (zone->pageset != &boot_pageset) {
 		for_each_online_cpu(cpu) {
 			pset = per_cpu_ptr(zone->pageset, cpu);
@@ -8608,7 +8621,7 @@ void zone_pcp_reset(struct zone *zone)
 		free_percpu(zone->pageset);
 		zone->pageset = &boot_pageset;
 	}
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE