1 files changed, 49 insertions, 87 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a91a072f2b2c..19389cdc16a5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -355,7 +355,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 		if (unlikely(pfn_to_nid(start_pfn) != nid))
 			continue;
 
-		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
+		if (zone != page_zone(pfn_to_page(start_pfn)))
 			continue;
 
 		return start_pfn;
@@ -380,7 +380,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 		if (unlikely(pfn_to_nid(pfn) != nid))
 			continue;
 
-		if (zone && zone != page_zone(pfn_to_page(pfn)))
+		if (zone != page_zone(pfn_to_page(pfn)))
 			continue;
 
 		return pfn;
@@ -392,14 +392,11 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 			     unsigned long end_pfn)
 {
-	unsigned long zone_start_pfn = zone->zone_start_pfn;
-	unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
-	unsigned long zone_end_pfn = z;
 	unsigned long pfn;
 	int nid = zone_to_nid(zone);
 
 	zone_span_writelock(zone);
-	if (zone_start_pfn == start_pfn) {
+	if (zone->zone_start_pfn == start_pfn) {
 		/*
 		 * If the section is smallest section in the zone, it need
 		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
@@ -407,50 +404,30 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 		 * for shrinking zone.
 		 */
 		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
-						zone_end_pfn);
+						zone_end_pfn(zone));
 		if (pfn) {
+			zone->spanned_pages = zone_end_pfn(zone) - pfn;
 			zone->zone_start_pfn = pfn;
-			zone->spanned_pages = zone_end_pfn - pfn;
+		} else {
+			zone->zone_start_pfn = 0;
+			zone->spanned_pages = 0;
 		}
-	} else if (zone_end_pfn == end_pfn) {
+	} else if (zone_end_pfn(zone) == end_pfn) {
 		/*
 		 * If the section is biggest section in the zone, it need
 		 * shrink zone->spanned_pages.
 		 * In this case, we find second biggest valid mem_section for
 		 * shrinking zone.
 		 */
-		pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
+		pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn,
 					       start_pfn);
 		if (pfn)
-			zone->spanned_pages = pfn - zone_start_pfn + 1;
-	}
-
-	/*
-	 * The section is not biggest or smallest mem_section in the zone, it
-	 * only creates a hole in the zone. So in this case, we need not
-	 * change the zone. But perhaps, the zone has only hole data. Thus
-	 * it check the zone has only hole or not.
-	 */
-	pfn = zone_start_pfn;
-	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_to_online_page(pfn)))
-			continue;
-
-		if (page_zone(pfn_to_page(pfn)) != zone)
-			continue;
-
-		/* Skip range to be removed */
-		if (pfn >= start_pfn && pfn < end_pfn)
-			continue;
-
-		/* If we find valid section, we have nothing to do */
-		zone_span_writeunlock(zone);
-		return;
+			zone->spanned_pages = pfn - zone->zone_start_pfn + 1;
+		else {
+			zone->zone_start_pfn = 0;
+			zone->spanned_pages = 0;
+		}
 	}
-
-	/* The zone has no valid section */
-	zone->zone_start_pfn = 0;
-	zone->spanned_pages = 0;
 	zone_span_writeunlock(zone);
 }
 
@@ -490,6 +467,9 @@ void __ref remove_pfn_range_from_zone(struct zone *zone,
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long flags;
 
+	/* Poison struct pages because they are now uninitialized again. */
+	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+
 #ifdef CONFIG_ZONE_DEVICE
 	/*
 	 * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
@@ -536,25 +516,20 @@ static void __remove_section(unsigned long pfn, unsigned long nr_pages,
 void __remove_pages(unsigned long pfn, unsigned long nr_pages,
 		    struct vmem_altmap *altmap)
 {
+	const unsigned long end_pfn = pfn + nr_pages;
+	unsigned long cur_nr_pages;
 	unsigned long map_offset = 0;
-	unsigned long nr, start_sec, end_sec;
 
 	map_offset = vmem_altmap_offset(altmap);
 
 	if (check_pfn_span(pfn, nr_pages, "remove"))
 		return;
 
-	start_sec = pfn_to_section_nr(pfn);
-	end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
-	for (nr = start_sec; nr <= end_sec; nr++) {
-		unsigned long pfns;
-
+	for (; pfn < end_pfn; pfn += cur_nr_pages) {
 		cond_resched();
-		pfns = min(nr_pages, PAGES_PER_SECTION
-				- (pfn & ~PAGE_SECTION_MASK));
-		__remove_section(pfn, pfns, map_offset, altmap);
-		pfn += pfns;
-		nr_pages -= pfns;
+		/* Select all remaining pages up to the next section boundary */
+		cur_nr_pages = min(end_pfn - pfn, -(pfn | PAGE_SECTION_MASK));
+		__remove_section(pfn, cur_nr_pages, map_offset, altmap);
 		map_offset = 0;
 	}
 }
@@ -599,7 +574,13 @@ EXPORT_SYMBOL_GPL(restore_online_page_callback);
 
 void generic_online_page(struct page *page, unsigned int order)
 {
-	kernel_map_pages(page, 1 << order, 1);
+	/*
+	 * Freeing the page with debug_pagealloc enabled will try to unmap it,
+	 * so we should map it first. This is better than introducing a special
+	 * case in page freeing fast path.
+	 */
+	if (debug_pagealloc_enabled_static())
+		kernel_map_pages(page, 1 << order, 1);
 	__free_pages_core(page, order);
 	totalram_pages_add(1UL << order);
 #ifdef CONFIG_HIGHMEM
@@ -783,27 +764,18 @@ struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
 	return default_zone_for_pfn(nid, start_pfn, nr_pages);
 }
 
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
+		       int online_type, int nid)
 {
 	unsigned long flags;
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
 	int need_zonelists_rebuild = 0;
-	int nid;
 	int ret;
 	struct memory_notify arg;
-	struct memory_block *mem;
 
 	mem_hotplug_begin();
 
-	/*
-	 * We can't use pfn_to_nid() because nid might be stored in struct page
-	 * which is not yet initialized. Instead, we find nid from memory block.
-	 */
-	mem = find_memory_block(__pfn_to_section(pfn));
-	nid = mem->nid;
-	put_device(&mem->dev);
-
 	/* associate pfn range with the zone */
 	zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
 	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);
@@ -1182,7 +1154,7 @@ static bool is_pageblock_removable_nolock(unsigned long pfn)
 	if (!zone_spans_pfn(zone, pfn))
 		return false;
 
-	return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE,
+	return !has_unmovable_pages(zone, page, MIGRATE_MOVABLE,
 				    MEMORY_OFFLINE);
 }
 
@@ -1206,14 +1178,13 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 }
 
 /*
- * Confirm all pages in a range [start, end) belong to the same zone.
- * When true, return its valid [start, end).
+ * Confirm all pages in a range [start, end) belong to the same zone (skipping
+ * memory holes). When true, return the zone.
  */
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
-			 unsigned long *valid_start, unsigned long *valid_end)
+struct zone *test_pages_in_a_zone(unsigned long start_pfn,
+				  unsigned long end_pfn)
 {
 	unsigned long pfn, sec_end_pfn;
-	unsigned long start, end;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
@@ -1234,24 +1205,15 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 				continue;
 			/* Check if we got outside of the zone */
 			if (zone && !zone_spans_pfn(zone, pfn + i))
-				return 0;
+				return NULL;
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
-				return 0;
-			if (!zone)
-				start = pfn + i;
+				return NULL;
 			zone = page_zone(page);
-			end = pfn + MAX_ORDER_NR_PAGES;
 		}
 	}
 
-	if (zone) {
-		*valid_start = start;
-		*valid_end = min(end, end_pfn);
-		return 1;
-	} else {
-		return 0;
-	}
+	return zone;
 }
 
 /*
@@ -1496,7 +1458,6 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	unsigned long offlined_pages = 0;
 	int ret, node, nr_isolate_pageblock;
 	unsigned long flags;
-	unsigned long valid_start, valid_end;
 	struct zone *zone;
 	struct memory_notify arg;
 	char *reason;
@@ -1521,14 +1482,12 @@ static int __ref __offline_pages(unsigned long start_pfn,
 
 	/* This makes hotplug much easier...and readable.
 	   we assume this for now. .*/
-	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start,
-				  &valid_end)) {
+	zone = test_pages_in_a_zone(start_pfn, end_pfn);
+	if (!zone) {
 		ret = -EINVAL;
 		reason = "multizone range";
 		goto failed_removal;
 	}
-
-	zone = page_zone(pfn_to_page(valid_start));
 	node = zone_to_nid(zone);
 
 	/* set above range as isolated */
@@ -1764,8 +1723,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 
 	BUG_ON(check_hotplug_memory_range(start, size));
 
-	mem_hotplug_begin();
-
 	/*
 	 * All memory blocks must be offlined before removing memory.  Check
 	 * whether all memory blocks in question are offline and return error
@@ -1778,9 +1735,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 	/* remove memmap entry */
 	firmware_map_remove(start, start + size, "System RAM");
 
-	/* remove memory block devices before removing memory */
+	/*
+	 * Memory block device removal under the device_hotplug_lock is
+	 * a barrier against racing online attempts.
+	 */
 	remove_memory_block_devices(start, size);
 
+	mem_hotplug_begin();
+
 	arch_remove_memory(nid, start, size, NULL);
 	memblock_free(start, size);
 	memblock_remove(start, size);