1 files changed, 109 insertions, 14 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index d179657f8685..5053439be6ab 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1418,22 +1418,35 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 		enum migrate_mode mode, int reason)
 {
 	int retry = 1;
+	int thp_retry = 1;
 	int nr_failed = 0;
 	int nr_succeeded = 0;
+	int nr_thp_succeeded = 0;
+	int nr_thp_failed = 0;
+	int nr_thp_split = 0;
 	int pass = 0;
+	bool is_thp = false;
 	struct page *page;
 	struct page *page2;
 	int swapwrite = current->flags & PF_SWAPWRITE;
-	int rc;
+	int rc, nr_subpages;
 
 	if (!swapwrite)
 		current->flags |= PF_SWAPWRITE;
 
-	for(pass = 0; pass < 10 && retry; pass++) {
+	for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
 		retry = 0;
+		thp_retry = 0;
 
 		list_for_each_entry_safe(page, page2, from, lru) {
 retry:
+			/*
+			 * THP statistics is based on the source huge page.
+			 * Capture required information that might get lost
+			 * during migration.
+			 */
+			is_thp = PageTransHuge(page);
+			nr_subpages = hpage_nr_pages(page);
 			cond_resched();
 
 			if (PageHuge(page))
@@ -1464,15 +1477,30 @@ retry:
 					unlock_page(page);
 					if (!rc) {
 						list_safe_reset_next(page, page2, lru);
+						nr_thp_split++;
 						goto retry;
 					}
 				}
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					goto out;
+				}
 				nr_failed++;
 				goto out;
 			case -EAGAIN:
+				if (is_thp) {
+					thp_retry++;
+					break;
+				}
 				retry++;
 				break;
 			case MIGRATEPAGE_SUCCESS:
+				if (is_thp) {
+					nr_thp_succeeded++;
+					nr_succeeded += nr_subpages;
+					break;
+				}
 				nr_succeeded++;
 				break;
 			default:
@@ -1482,19 +1510,27 @@ retry:
 				 * removed from migration page list and not
 				 * retried in the next outer loop.
 				 */
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					break;
+				}
 				nr_failed++;
 				break;
 			}
 		}
 	}
-	nr_failed += retry;
+	nr_failed += retry + thp_retry;
+	nr_thp_failed += thp_retry;
 	rc = nr_failed;
 out:
-	if (nr_succeeded)
-		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
-	if (nr_failed)
-		count_vm_events(PGMIGRATE_FAIL, nr_failed);
-	trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
+	count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
+	count_vm_events(PGMIGRATE_FAIL, nr_failed);
+	count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
+	count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed);
+	count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split);
+	trace_mm_migrate_pages(nr_succeeded, nr_failed, nr_thp_succeeded,
+			       nr_thp_failed, nr_thp_split, mode, reason);
 
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
@@ -1502,6 +1538,49 @@ out:
 	return rc;
 }
 
+struct page *alloc_migration_target(struct page *page, unsigned long private)
+{
+	struct migration_target_control *mtc;
+	gfp_t gfp_mask;
+	unsigned int order = 0;
+	struct page *new_page = NULL;
+	int nid;
+	int zidx;
+
+	mtc = (struct migration_target_control *)private;
+	gfp_mask = mtc->gfp_mask;
+	nid = mtc->nid;
+	if (nid == NUMA_NO_NODE)
+		nid = page_to_nid(page);
+
+	if (PageHuge(page)) {
+		struct hstate *h = page_hstate(compound_head(page));
+
+		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
+		return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask);
+	}
+
+	if (PageTransHuge(page)) {
+		/*
+		 * clear __GFP_RECLAIM to make the migration callback
+		 * consistent with regular THP allocations.
+		 */
+		gfp_mask &= ~__GFP_RECLAIM;
+		gfp_mask |= GFP_TRANSHUGE;
+		order = HPAGE_PMD_ORDER;
+	}
+	zidx = zone_idx(page_zone(page));
+	if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE)
+		gfp_mask |= __GFP_HIGHMEM;
+
+	new_page = __alloc_pages_nodemask(gfp_mask, order, nid, mtc->nmask);
+
+	if (new_page && PageTransHuge(new_page))
+		prep_transhuge_page(new_page);
+
+	return new_page;
+}
+
 #ifdef CONFIG_NUMA
 
 static int store_status(int __user *status, int start, int value, int nr)
@@ -1519,9 +1598,13 @@ static int do_move_pages_to_node(struct mm_struct *mm,
 		struct list_head *pagelist, int node)
 {
 	int err;
+	struct migration_target_control mtc = {
+		.nid = node,
+		.gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE,
+	};
 
-	err = migrate_pages(pagelist, alloc_new_node_page, NULL, node,
-			MIGRATE_SYNC, MR_SYSCALL);
+	err = migrate_pages(pagelist, alloc_migration_target, NULL,
+			(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL);
 	if (err)
 		putback_movable_pages(pagelist);
 	return err;
@@ -2168,6 +2251,16 @@ static int migrate_vma_collect_hole(unsigned long start,
 	struct migrate_vma *migrate = walk->private;
 	unsigned long addr;
 
+	/* Only allow populating anonymous memory. */
+	if (!vma_is_anonymous(walk->vma)) {
+		for (addr = start; addr < end; addr += PAGE_SIZE) {
+			migrate->src[migrate->npages] = 0;
+			migrate->dst[migrate->npages] = 0;
+			migrate->npages++;
+		}
+		return 0;
+	}
+
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
 		migrate->dst[migrate->npages] = 0;
@@ -2260,8 +2353,10 @@ again:
 		pte = *ptep;
 
 		if (pte_none(pte)) {
-			mpfn = MIGRATE_PFN_MIGRATE;
-			migrate->cpages++;
+			if (vma_is_anonymous(vma)) {
+				mpfn = MIGRATE_PFN_MIGRATE;
+				migrate->cpages++;
+			}
 			goto next;
 		}
 
@@ -2619,7 +2714,7 @@ restore:
 
 /**
  * migrate_vma_setup() - prepare to migrate a range of memory
- * @args: contains the vma, start, and and pfns arrays for the migration
+ * @args: contains the vma, start, and pfns arrays for the migration
  *
  * Returns: negative errno on failures, 0 when 0 or more pages were migrated
  * without an error.
@@ -2830,7 +2925,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	inc_mm_counter(mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, addr, false);
 	if (!is_zone_device_page(page))
-		lru_cache_add_active_or_unevictable(page, vma);
+		lru_cache_add_inactive_or_unevictable(page, vma);
 	get_page(page);
 
 	if (flush) {