patches/mm-page_alloc-rt-friendly-per-cpu-pages.patch

From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 3 Jul 2009 08:29:37 -0500
Subject: mm: page_alloc: rt-friendly per-cpu pages

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>
---
 mm/page_alloc.c |   57 ++++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 16 deletions(-)

--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -61,6 +61,7 @@
 #include <linux/page_ext.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
+#include <linux/locallock.h>
 #include <linux/page_owner.h>
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
@@ -276,6 +277,18 @@ EXPORT_SYMBOL(nr_node_ids);
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
+static DEFINE_LOCAL_IRQ_LOCK(pa_lock);
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define cpu_lock_irqsave(cpu, flags)		\
+	spin_lock_irqsave(&per_cpu(pa_lock, cpu).lock, flags)
+# define cpu_unlock_irqrestore(cpu, flags)	\
+	spin_unlock_irqrestore(&per_cpu(pa_lock, cpu).lock, flags)
+#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
@@ -1228,10 +1241,10 @@ 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);
 }
 
 static void __init __free_pages_boot_core(struct page *page, unsigned int order)
@@ -2221,14 +2234,14 @@ void drain_zone_pages(struct zone *zone,
 	unsigned long flags;
 	int to_drain, batch;
 
-	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) {
 		free_pcppages_bulk(zone, to_drain, pcp);
 		pcp->count -= to_drain;
 	}
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 #endif
 
@@ -2245,7 +2258,7 @@ static void drain_pages_zone(unsigned in
 	struct per_cpu_pageset *pset;
 	struct per_cpu_pages *pcp;
 
-	local_irq_save(flags);
+	cpu_lock_irqsave(cpu, flags);
 	pset = per_cpu_ptr(zone->pageset, cpu);
 
 	pcp = &pset->pcp;
@@ -2253,7 +2266,7 @@ static void drain_pages_zone(unsigned in
 		free_pcppages_bulk(zone, pcp->count, pcp);
 		pcp->count = 0;
 	}
-	local_irq_restore(flags);
+	cpu_unlock_irqrestore(cpu, flags);
 }
 
 /*
@@ -2339,8 +2352,17 @@ void drain_all_pages(struct zone *zone)
 		else
 			cpumask_clear_cpu(cpu, &cpus_with_pcps);
 	}
+#ifndef CONFIG_PREEMPT_RT_BASE
 	on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
 								zone, 1);
+#else
+	for_each_cpu(cpu, &cpus_with_pcps) {
+		if (zone)
+			drain_pages_zone(cpu, zone);
+		else
+			drain_pages(cpu);
+	}
+#endif
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -2400,7 +2422,7 @@ void free_hot_cold_page(struct page *pag
 
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	set_pcppage_migratetype(page, migratetype);
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	__count_vm_event(PGFREE);
 
 	/*
@@ -2431,7 +2453,7 @@ void free_hot_cold_page(struct page *pag
 	}
 
 out:
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 
 /*
@@ -2568,7 +2590,7 @@ struct page *buffered_rmqueue(struct zon
 		struct per_cpu_pages *pcp;
 		struct list_head *list;
 
-		local_irq_save(flags);
+		local_lock_irqsave(pa_lock, flags);
 		do {
 			pcp = &this_cpu_ptr(zone->pageset)->pcp;
 			list = &pcp->lists[migratetype];
@@ -2595,7 +2617,7 @@ struct page *buffered_rmqueue(struct zon
 		 * 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;
@@ -2607,22 +2629,24 @@ struct page *buffered_rmqueue(struct zon
 			if (!page)
 				page = __rmqueue(zone, order, migratetype);
 		} while (page && check_new_pages(page, order));
-		spin_unlock(&zone->lock);
-		if (!page)
+		if (!page) {
+			spin_unlock(&zone->lock);
 			goto failed;
+		}
 		__mod_zone_freepage_state(zone, -(1 << order),
 					  get_pcppage_migratetype(page));
+		spin_unlock(&zone->lock);
 	}
 
 	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 	return page;
 
 failed:
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 	return NULL;
 }
 
@@ -6564,6 +6588,7 @@ static int page_alloc_cpu_notify(struct
 void __init page_alloc_init(void)
 {
 	hotcpu_notifier(page_alloc_cpu_notify, 0);
+	local_irq_lock_init(pa_lock);
 }
 
 /*
@@ -7380,7 +7405,7 @@ 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);
@@ -7389,7 +7414,7 @@ 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