[PATCH] memory hotplug locking: zone span seqlock

See the "fixup bad_range()" patch for more information, but this actually
creates a the lock to protect things making assumptions about a zone's size
staying constant at runtime.

Signed-off-by: Dave Hansen <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/memory_hotplug.h

···
 static inline
 void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
 {
-	spin_lock_irqrestore(&pgdat->node_size_lock, *flags);
+	spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
 }
 static inline
 void pgdat_resize_init(struct pglist_data *pgdat)
 {
 	spin_lock_init(&pgdat->node_size_lock);
+}
+/*
+ * Zone resizing functions
+ */
+static inline unsigned zone_span_seqbegin(struct zone *zone)
+{
+	return read_seqbegin(&zone->span_seqlock);
+}
+static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
+{
+	return read_seqretry(&zone->span_seqlock, iv);
+}
+static inline void zone_span_writelock(struct zone *zone)
+{
+	write_seqlock(&zone->span_seqlock);
+}
+static inline void zone_span_writeunlock(struct zone *zone)
+{
+	write_sequnlock(&zone->span_seqlock);
+}
+static inline void zone_seqlock_init(struct zone *zone)
+{
+	seqlock_init(&zone->span_seqlock);
 }
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 /*
···
 static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
 static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
 static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
-#endif
+
+static inline unsigned zone_span_seqbegin(struct zone *zone)
+{
+	return 0;
+}
+static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
+{
+	return 0;
+}
+static inline void zone_span_writelock(struct zone *zone) {}
+static inline void zone_span_writeunlock(struct zone *zone) {}
+static inline void zone_seqlock_init(struct zone *zone) {}
+#endif /* ! CONFIG_MEMORY_HOTPLUG */
 #endif /* __LINUX_MEMORY_HOTPLUG_H */

include/linux/mmzone.h

···
 #include <linux/threads.h>
 #include <linux/numa.h>
 #include <linux/init.h>
+#include <linux/seqlock.h>
 #include <asm/atomic.h>
 
 /* Free memory management - zoned buddy allocator.  */
···
 	 * free areas of different sizes
 	 */
 	spinlock_t		lock;
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/* see spanned/present_pages for more description */
+	seqlock_t		span_seqlock;
+#endif
 	struct free_area	free_area[MAX_ORDER];
 
 
···
 	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
 	unsigned long		zone_start_pfn;
 
+	/*
+	 * zone_start_pfn, spanned_pages and present_pages are all
+	 * protected by span_seqlock.  It is a seqlock because it has
+	 * to be read outside of zone->lock, and it is done in the main
+	 * allocator path.  But, it is written quite infrequently.
+	 *
+	 * The lock is declared along with zone->lock because it is
+	 * frequently read in proximity to zone->lock.  It's good to
+	 * give them a chance of being in the same cacheline.
+	 */
 	unsigned long		spanned_pages;	/* total size, including holes */
 	unsigned long		present_pages;	/* amount of memory (excluding holes) */
 

mm/page_alloc.c

···
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
+#include <linux/memory_hotplug.h>
 #include <linux/nodemask.h>
 #include <linux/vmalloc.h>
 
···
 
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 {
-	if (page_to_pfn(page) >= zone->zone_start_pfn + zone->spanned_pages)
-		return 1;
-	if (page_to_pfn(page) < zone->zone_start_pfn)
-		return 1;
+	int ret = 0;
+	unsigned seq;
+	unsigned long pfn = page_to_pfn(page);
 
-	return 0;
+	do {
+		seq = zone_span_seqbegin(zone);
+		if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
+			ret = 1;
+		else if (pfn < zone->zone_start_pfn)
+			ret = 1;
+	} while (zone_span_seqretry(zone, seq));
+
+	return ret;
 }
 
 static int page_is_consistent(struct zone *zone, struct page *page)
···
 		zone->name = zone_names[j];
 		spin_lock_init(&zone->lock);
 		spin_lock_init(&zone->lru_lock);
+		zone_seqlock_init(zone);
 		zone->zone_pgdat = pgdat;
 		zone->free_pages = 0;