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 |   61 +++++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 41 insertions(+), 20 deletions(-)

--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -60,6 +60,7 @@
 #include <linux/page-debug-flags.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
+#include <linux/locallock.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -221,6 +222,18 @@ 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;
 
 void set_pageblock_migratetype(struct page *page, int migratetype)
@@ -731,12 +744,12 @@ static void __free_pages_ok(struct page
 	if (!free_pages_prepare(page, order))
 		return;
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	__count_vm_events(PGFREE, 1 << order);
 	migratetype = get_pageblock_migratetype(page);
 	set_freepage_migratetype(page, migratetype);
 	free_one_page(page_zone(page), page, order, migratetype);
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 
 /*
@@ -1180,7 +1193,7 @@ void drain_zone_pages(struct zone *zone,
 	unsigned long flags;
 	int to_drain;
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	if (pcp->count >= pcp->batch)
 		to_drain = pcp->batch;
 	else
@@ -1189,7 +1202,7 @@ void drain_zone_pages(struct zone *zone,
 		free_pcppages_bulk(zone, to_drain, pcp);
 		pcp->count -= to_drain;
 	}
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 #endif
 
@@ -1209,7 +1222,7 @@ static void drain_pages(unsigned int cpu
 		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;
@@ -1217,7 +1230,7 @@ static void drain_pages(unsigned int cpu
 			free_pcppages_bulk(zone, pcp->count, pcp);
 			pcp->count = 0;
 		}
-		local_irq_restore(flags);
+		cpu_unlock_irqrestore(cpu, flags);
 	}
 }
 
@@ -1270,7 +1283,12 @@ void drain_all_pages(void)
 		else
 			cpumask_clear_cpu(cpu, &cpus_with_pcps);
 	}
+#ifndef CONFIG_PREEMPT_RT_BASE
 	on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
+#else
+	for_each_cpu(cpu, &cpus_with_pcps)
+		drain_pages(cpu);
+#endif
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -1325,7 +1343,7 @@ void free_hot_cold_page(struct page *pag
 
 	migratetype = get_pageblock_migratetype(page);
 	set_freepage_migratetype(page, migratetype);
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	__count_vm_event(PGFREE);
 
 	/*
@@ -1355,7 +1373,7 @@ void free_hot_cold_page(struct page *pag
 	}
 
 out:
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 
 /*
@@ -1485,7 +1503,7 @@ again:
 		struct per_cpu_pages *pcp;
 		struct list_head *list;
 
-		local_irq_save(flags);
+		local_lock_irqsave(pa_lock, flags);
 		pcp = &this_cpu_ptr(zone->pageset)->pcp;
 		list = &pcp->lists[migratetype];
 		if (list_empty(list)) {
@@ -1517,18 +1535,20 @@ again:
 			 */
 			WARN_ON_ONCE(order > 1);
 		}
-		spin_lock_irqsave(&zone->lock, flags);
+		local_spin_lock_irqsave(pa_lock, &zone->lock, flags);
 		page = __rmqueue(zone, order, migratetype);
-		spin_unlock(&zone->lock);
-		if (!page)
+		if (!page) {
+			spin_unlock(&zone->lock);
 			goto failed;
+		}
 		__mod_zone_freepage_state(zone, -(1 << order),
 					  get_pageblock_migratetype(page));
+		spin_unlock(&zone->lock);
 	}
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 
 	VM_BUG_ON(bad_range(zone, page));
 	if (prep_new_page(page, order, gfp_flags))
@@ -1536,7 +1556,7 @@ again:
 	return page;
 
 failed:
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 	return NULL;
 }
 
@@ -5233,6 +5253,7 @@ 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);
 }
 
 /*
@@ -5471,11 +5492,11 @@ int __meminit init_per_zone_wmark_min(vo
 module_init(init_per_zone_wmark_min)
 
 /*
- * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so 
+ * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
  *	that we can call two helper functions whenever min_free_kbytes
  *	changes.
  */
-int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 
+int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	proc_dointvec(table, write, buffer, length, ppos);
@@ -6060,12 +6081,12 @@ static int __meminit __zone_pcp_update(v
 		pset = per_cpu_ptr(zone->pageset, cpu);
 		pcp = &pset->pcp;
 
-		local_irq_save(flags);
+		cpu_lock_irqsave(cpu, flags);
 		if (pcp->count > 0)
 			free_pcppages_bulk(zone, pcp->count, pcp);
 		drain_zonestat(zone, pset);
 		setup_pageset(pset, batch);
-		local_irq_restore(flags);
+		cpu_unlock_irqrestore(cpu, flags);
 	}
 	return 0;
 }
@@ -6083,7 +6104,7 @@ 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);
@@ -6092,7 +6113,7 @@ 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