1 files changed, 314 insertions, 0 deletions
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
new file mode 100644
index 000000000..303c90879
--- /dev/null
+++ b/mm/page_isolation.c
@@ -0,0 +1,314 @@
+/*
+ * linux/mm/page_isolation.c
+ */
+
+#include <linux/mm.h>
+#include <linux/page-isolation.h>
+#include <linux/pageblock-flags.h>
+#include <linux/memory.h>
+#include <linux/hugetlb.h>
+#include "internal.h"
+
+int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
+{
+	struct zone *zone;
+	unsigned long flags, pfn;
+	struct memory_isolate_notify arg;
+	int notifier_ret;
+	int ret = -EBUSY;
+
+	zone = page_zone(page);
+
+	spin_lock_irqsave(&zone->lock, flags);
+
+	pfn = page_to_pfn(page);
+	arg.start_pfn = pfn;
+	arg.nr_pages = pageblock_nr_pages;
+	arg.pages_found = 0;
+
+	/*
+	 * It may be possible to isolate a pageblock even if the
+	 * migratetype is not MIGRATE_MOVABLE. The memory isolation
+	 * notifier chain is used by balloon drivers to return the
+	 * number of pages in a range that are held by the balloon
+	 * driver to shrink memory. If all the pages are accounted for
+	 * by balloons, are free, or on the LRU, isolation can continue.
+	 * Later, for example, when memory hotplug notifier runs, these
+	 * pages reported as "can be isolated" should be isolated(freed)
+	 * by the balloon driver through the memory notifier chain.
+	 */
+	notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
+	notifier_ret = notifier_to_errno(notifier_ret);
+	if (notifier_ret)
+		goto out;
+	/*
+	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
+	 * We just check MOVABLE pages.
+	 */
+	if (!has_unmovable_pages(zone, page, arg.pages_found,
+				 skip_hwpoisoned_pages))
+		ret = 0;
+
+	/*
+	 * immobile means "not-on-lru" paes. If immobile is larger than
+	 * removable-by-driver pages reported by notifier, we'll fail.
+	 */
+
+out:
+	if (!ret) {
+		unsigned long nr_pages;
+		int migratetype = get_pageblock_migratetype(page);
+
+		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+		zone->nr_isolate_pageblock++;
+		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
+
+		__mod_zone_freepage_state(zone, -nr_pages, migratetype);
+	}
+
+	spin_unlock_irqrestore(&zone->lock, flags);
+	if (!ret)
+		drain_all_pages(zone);
+	return ret;
+}
+
+void unset_migratetype_isolate(struct page *page, unsigned migratetype)
+{
+	struct zone *zone;
+	unsigned long flags, nr_pages;
+	struct page *isolated_page = NULL;
+	unsigned int order;
+	unsigned long page_idx, buddy_idx;
+	struct page *buddy;
+
+	zone = page_zone(page);
+	spin_lock_irqsave(&zone->lock, flags);
+	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+		goto out;
+
+	/*
+	 * Because freepage with more than pageblock_order on isolated
+	 * pageblock is restricted to merge due to freepage counting problem,
+	 * it is possible that there is free buddy page.
+	 * move_freepages_block() doesn't care of merge so we need other
+	 * approach in order to merge them. Isolation and free will make
+	 * these pages to be merged.
+	 */
+	if (PageBuddy(page)) {
+		order = page_order(page);
+		if (order >= pageblock_order) {
+			page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
+			buddy_idx = __find_buddy_index(page_idx, order);
+			buddy = page + (buddy_idx - page_idx);
+
+			if (pfn_valid_within(page_to_pfn(buddy)) &&
+			    !is_migrate_isolate_page(buddy)) {
+				__isolate_free_page(page, order);
+				kernel_map_pages(page, (1 << order), 1);
+				set_page_refcounted(page);
+				isolated_page = page;
+			}
+		}
+	}
+
+	/*
+	 * If we isolate freepage with more than pageblock_order, there
+	 * should be no freepage in the range, so we could avoid costly
+	 * pageblock scanning for freepage moving.
+	 */
+	if (!isolated_page) {
+		nr_pages = move_freepages_block(zone, page, migratetype);
+		__mod_zone_freepage_state(zone, nr_pages, migratetype);
+	}
+	set_pageblock_migratetype(page, migratetype);
+	zone->nr_isolate_pageblock--;
+out:
+	spin_unlock_irqrestore(&zone->lock, flags);
+	if (isolated_page)
+		__free_pages(isolated_page, order);
+}
+
+static inline struct page *
+__first_valid_page(unsigned long pfn, unsigned long nr_pages)
+{
+	int i;
+	for (i = 0; i < nr_pages; i++)
+		if (pfn_valid_within(pfn + i))
+			break;
+	if (unlikely(i == nr_pages))
+		return NULL;
+	return pfn_to_page(pfn + i);
+}
+
+/*
+ * start_isolate_page_range() -- make page-allocation-type of range of pages
+ * to be MIGRATE_ISOLATE.
+ * @start_pfn: The lower PFN of the range to be isolated.
+ * @end_pfn: The upper PFN of the range to be isolated.
+ * @migratetype: migrate type to set in error recovery.
+ *
+ * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
+ * the range will never be allocated. Any free pages and pages freed in the
+ * future will not be allocated again.
+ *
+ * start_pfn/end_pfn must be aligned to pageblock_order.
+ * Returns 0 on success and -EBUSY if any part of range cannot be isolated.
+ */
+int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			     unsigned migratetype, bool skip_hwpoisoned_pages)
+{
+	unsigned long pfn;
+	unsigned long undo_pfn;
+	struct page *page;
+
+	BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
+	BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
+
+	for (pfn = start_pfn;
+	     pfn < end_pfn;
+	     pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (page &&
+		    set_migratetype_isolate(page, skip_hwpoisoned_pages)) {
+			undo_pfn = pfn;
+			goto undo;
+		}
+	}
+	return 0;
+undo:
+	for (pfn = start_pfn;
+	     pfn < undo_pfn;
+	     pfn += pageblock_nr_pages)
+		unset_migratetype_isolate(pfn_to_page(pfn), migratetype);
+
+	return -EBUSY;
+}
+
+/*
+ * Make isolated pages available again.
+ */
+int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
+			    unsigned migratetype)
+{
+	unsigned long pfn;
+	struct page *page;
+	BUG_ON((start_pfn) & (pageblock_nr_pages - 1));
+	BUG_ON((end_pfn) & (pageblock_nr_pages - 1));
+	for (pfn = start_pfn;
+	     pfn < end_pfn;
+	     pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+			continue;
+		unset_migratetype_isolate(page, migratetype);
+	}
+	return 0;
+}
+/*
+ * Test all pages in the range is free(means isolated) or not.
+ * all pages in [start_pfn...end_pfn) must be in the same zone.
+ * zone->lock must be held before call this.
+ *
+ * Returns 1 if all pages in the range are isolated.
+ */
+static int
+__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
+				  bool skip_hwpoisoned_pages)
+{
+	struct page *page;
+
+	while (pfn < end_pfn) {
+		if (!pfn_valid_within(pfn)) {
+			pfn++;
+			continue;
+		}
+		page = pfn_to_page(pfn);
+		if (PageBuddy(page)) {
+			/*
+			 * If race between isolatation and allocation happens,
+			 * some free pages could be in MIGRATE_MOVABLE list
+			 * although pageblock's migratation type of the page
+			 * is MIGRATE_ISOLATE. Catch it and move the page into
+			 * MIGRATE_ISOLATE list.
+			 */
+			if (get_freepage_migratetype(page) != MIGRATE_ISOLATE) {
+				struct page *end_page;
+
+				end_page = page + (1 << page_order(page)) - 1;
+				move_freepages(page_zone(page), page, end_page,
+						MIGRATE_ISOLATE);
+			}
+			pfn += 1 << page_order(page);
+		}
+		else if (page_count(page) == 0 &&
+			get_freepage_migratetype(page) == MIGRATE_ISOLATE)
+			pfn += 1;
+		else if (skip_hwpoisoned_pages && PageHWPoison(page)) {
+			/*
+			 * The HWPoisoned page may be not in buddy
+			 * system, and page_count() is not 0.
+			 */
+			pfn++;
+			continue;
+		}
+		else
+			break;
+	}
+	if (pfn < end_pfn)
+		return 0;
+	return 1;
+}
+
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
+			bool skip_hwpoisoned_pages)
+{
+	unsigned long pfn, flags;
+	struct page *page;
+	struct zone *zone;
+	int ret;
+
+	/*
+	 * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
+	 * are not aligned to pageblock_nr_pages.
+	 * Then we just check migratetype first.
+	 */
+	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (page && get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+			break;
+	}
+	page = __first_valid_page(start_pfn, end_pfn - start_pfn);
+	if ((pfn < end_pfn) || !page)
+		return -EBUSY;
+	/* Check all pages are free or marked as ISOLATED */
+	zone = page_zone(page);
+	spin_lock_irqsave(&zone->lock, flags);
+	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn,
+						skip_hwpoisoned_pages);
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret ? 0 : -EBUSY;
+}
+
+struct page *alloc_migrate_target(struct page *page, unsigned long private,
+				  int **resultp)
+{
+	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+
+	/*
+	 * TODO: allocate a destination hugepage from a nearest neighbor node,
+	 * accordance with memory policy of the user process if possible. For
+	 * now as a simple work-around, we use the next node for destination.
+	 */
+	if (PageHuge(page)) {
+		nodemask_t src = nodemask_of_node(page_to_nid(page));
+		nodemask_t dst;
+		nodes_complement(dst, src);
+		return alloc_huge_page_node(page_hstate(compound_head(page)),
+					    next_node(page_to_nid(page), dst));
+	}
+
+	if (PageHighMem(page))
+		gfp_mask |= __GFP_HIGHMEM;
+
+	return alloc_page(gfp_mask);
+}