1 files changed, 155 insertions, 134 deletions

diff --git a/kernel/mm/migrate.c b/kernel/mm/migrate.c
index f53838fe3..6d17e0ab4 100644
--- a/kernel/mm/migrate.c
+++ b/kernel/mm/migrate.c
@@ -1,5 +1,5 @@
 /*
- * Memory Migration functionality - linux/mm/migration.c
+ * Memory Migration functionality - linux/mm/migrate.c
  *
  * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
  *
@@ -30,13 +30,14 @@
 #include <linux/mempolicy.h>
 #include <linux/vmalloc.h>
 #include <linux/security.h>
-#include <linux/memcontrol.h>
+#include <linux/backing-dev.h>
 #include <linux/syscalls.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
 #include <linux/balloon_compaction.h>
 #include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
 
 #include <asm/tlbflush.h>
 
@@ -170,6 +171,9 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	else
 		page_add_file_rmap(new);
 
+	if (vma->vm_flags & VM_LOCKED)
+		mlock_vma_page(new);
+
 	/* No need to invalidate - it was non-present before */
 	update_mmu_cache(vma, addr, ptep);
 unlock:
@@ -310,6 +314,8 @@ int migrate_page_move_mapping(struct address_space *mapping,
 		struct buffer_head *head, enum migrate_mode mode,
 		int extra_count)
 {
+	struct zone *oldzone, *newzone;
+	int dirty;
 	int expected_count = 1 + extra_count;
 	void **pslot;
 
@@ -317,9 +323,20 @@ int migrate_page_move_mapping(struct address_space *mapping,
 		/* Anonymous page without mapping */
 		if (page_count(page) != expected_count)
 			return -EAGAIN;
+
+		/* No turning back from here */
+		set_page_memcg(newpage, page_memcg(page));
+		newpage->index = page->index;
+		newpage->mapping = page->mapping;
+		if (PageSwapBacked(page))
+			SetPageSwapBacked(newpage);
+
 		return MIGRATEPAGE_SUCCESS;
 	}
 
+	oldzone = page_zone(page);
+	newzone = page_zone(newpage);
+
 	spin_lock_irq(&mapping->tree_lock);
 
 	pslot = radix_tree_lookup_slot(&mapping->page_tree,
@@ -352,14 +369,28 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	}
 
 	/*
-	 * Now we know that no one else is looking at the page.
+	 * Now we know that no one else is looking at the page:
+	 * no turning back from here.
 	 */
+	set_page_memcg(newpage, page_memcg(page));
+	newpage->index = page->index;
+	newpage->mapping = page->mapping;
+	if (PageSwapBacked(page))
+		SetPageSwapBacked(newpage);
+
 	get_page(newpage);	/* add cache reference */
 	if (PageSwapCache(page)) {
 		SetPageSwapCache(newpage);
 		set_page_private(newpage, page_private(page));
 	}
 
+	/* Move dirty while page refs frozen and newpage not yet exposed */
+	dirty = PageDirty(page);
+	if (dirty) {
+		ClearPageDirty(page);
+		SetPageDirty(newpage);
+	}
+
 	radix_tree_replace_slot(pslot, newpage);
 
 	/*
@@ -369,6 +400,9 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	page_unfreeze_refs(page, expected_count - 1);
 
+	spin_unlock(&mapping->tree_lock);
+	/* Leave irq disabled to prevent preemption while updating stats */
+
 	/*
 	 * If moved to a different zone then also account
 	 * the page for that zone. Other VM counters will be
@@ -379,13 +413,19 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 * via NR_FILE_PAGES and NR_ANON_PAGES if they
 	 * are mapped to swap space.
 	 */
-	__dec_zone_page_state(page, NR_FILE_PAGES);
-	__inc_zone_page_state(newpage, NR_FILE_PAGES);
-	if (!PageSwapCache(page) && PageSwapBacked(page)) {
-		__dec_zone_page_state(page, NR_SHMEM);
-		__inc_zone_page_state(newpage, NR_SHMEM);
+	if (newzone != oldzone) {
+		__dec_zone_state(oldzone, NR_FILE_PAGES);
+		__inc_zone_state(newzone, NR_FILE_PAGES);
+		if (PageSwapBacked(page) && !PageSwapCache(page)) {
+			__dec_zone_state(oldzone, NR_SHMEM);
+			__inc_zone_state(newzone, NR_SHMEM);
+		}
+		if (dirty && mapping_cap_account_dirty(mapping)) {
+			__dec_zone_state(oldzone, NR_FILE_DIRTY);
+			__inc_zone_state(newzone, NR_FILE_DIRTY);
+		}
 	}
-	spin_unlock_irq(&mapping->tree_lock);
+	local_irq_enable();
 
 	return MIGRATEPAGE_SUCCESS;
 }
@@ -400,12 +440,6 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 	int expected_count;
 	void **pslot;
 
-	if (!mapping) {
-		if (page_count(page) != 1)
-			return -EAGAIN;
-		return MIGRATEPAGE_SUCCESS;
-	}
-
 	spin_lock_irq(&mapping->tree_lock);
 
 	pslot = radix_tree_lookup_slot(&mapping->page_tree,
@@ -423,6 +457,9 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 		return -EAGAIN;
 	}
 
+	set_page_memcg(newpage, page_memcg(page));
+	newpage->index = page->index;
+	newpage->mapping = page->mapping;
 	get_page(newpage);
 
 	radix_tree_replace_slot(pslot, newpage);
@@ -509,20 +546,14 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 	if (PageMappedToDisk(page))
 		SetPageMappedToDisk(newpage);
 
-	if (PageDirty(page)) {
-		clear_page_dirty_for_io(page);
-		/*
-		 * Want to mark the page and the radix tree as dirty, and
-		 * redo the accounting that clear_page_dirty_for_io undid,
-		 * but we can't use set_page_dirty because that function
-		 * is actually a signal that all of the page has become dirty.
-		 * Whereas only part of our page may be dirty.
-		 */
-		if (PageSwapBacked(page))
-			SetPageDirty(newpage);
-		else
-			__set_page_dirty_nobuffers(newpage);
- 	}
+	/* Move dirty on pages not done by migrate_page_move_mapping() */
+	if (PageDirty(page))
+		SetPageDirty(newpage);
+
+	if (page_is_young(page))
+		set_page_young(newpage);
+	if (page_is_idle(page))
+		set_page_idle(newpage);
 
 	/*
 	 * Copy NUMA information to the new page, to prevent over-eager
@@ -531,7 +562,6 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 	cpupid = page_cpupid_xchg_last(page, -1);
 	page_cpupid_xchg_last(newpage, cpupid);
 
-	mlock_migrate_page(newpage, page);
 	ksm_migrate_page(newpage, page);
 	/*
 	 * Please do not reorder this without considering how mm/ksm.c's
@@ -715,24 +745,13 @@ static int fallback_migrate_page(struct address_space *mapping,
  *  MIGRATEPAGE_SUCCESS - success
  */
 static int move_to_new_page(struct page *newpage, struct page *page,
-				int page_was_mapped, enum migrate_mode mode)
+				enum migrate_mode mode)
 {
 	struct address_space *mapping;
 	int rc;
 
-	/*
-	 * Block others from accessing the page when we get around to
-	 * establishing additional references. We are the only one
-	 * holding a reference to the new page at this point.
-	 */
-	if (!trylock_page(newpage))
-		BUG();
-
-	/* Prepare mapping for the new page.*/
-	newpage->index = page->index;
-	newpage->mapping = page->mapping;
-	if (PageSwapBacked(page))
-		SetPageSwapBacked(newpage);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
 
 	mapping = page_mapping(page);
 	if (!mapping)
@@ -744,22 +763,19 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		 * space which also has its own migratepage callback. This
 		 * is the most common path for page migration.
 		 */
-		rc = mapping->a_ops->migratepage(mapping,
-						newpage, page, mode);
+		rc = mapping->a_ops->migratepage(mapping, newpage, page, mode);
 	else
 		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
-	if (rc != MIGRATEPAGE_SUCCESS) {
-		newpage->mapping = NULL;
-	} else {
-		mem_cgroup_migrate(page, newpage, false);
-		if (page_was_mapped)
-			remove_migration_ptes(page, newpage);
-		page->mapping = NULL;
+	/*
+	 * When successful, old pagecache page->mapping must be cleared before
+	 * page is freed; but stats require that PageAnon be left as PageAnon.
+	 */
+	if (rc == MIGRATEPAGE_SUCCESS) {
+		set_page_memcg(page, NULL);
+		if (!PageAnon(page))
+			page->mapping = NULL;
 	}
-
-	unlock_page(newpage);
-
 	return rc;
 }
 
@@ -808,6 +824,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 			goto out_unlock;
 		wait_on_page_writeback(page);
 	}
+
 	/*
 	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
 	 * we cannot notice that anon_vma is freed while we migrates a page.
@@ -815,34 +832,26 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	 * of migration. File cache pages are no problem because of page_lock()
 	 * File Caches may use write_page() or lock_page() in migration, then,
 	 * just care Anon page here.
+	 *
+	 * Only page_get_anon_vma() understands the subtleties of
+	 * getting a hold on an anon_vma from outside one of its mms.
+	 * But if we cannot get anon_vma, then we won't need it anyway,
+	 * because that implies that the anon page is no longer mapped
+	 * (and cannot be remapped so long as we hold the page lock).
 	 */
-	if (PageAnon(page) && !PageKsm(page)) {
-		/*
-		 * Only page_lock_anon_vma_read() understands the subtleties of
-		 * getting a hold on an anon_vma from outside one of its mms.
-		 */
+	if (PageAnon(page) && !PageKsm(page))
 		anon_vma = page_get_anon_vma(page);
-		if (anon_vma) {
-			/*
-			 * Anon page
-			 */
-		} else if (PageSwapCache(page)) {
-			/*
-			 * We cannot be sure that the anon_vma of an unmapped
-			 * swapcache page is safe to use because we don't
-			 * know in advance if the VMA that this page belonged
-			 * to still exists. If the VMA and others sharing the
-			 * data have been freed, then the anon_vma could
-			 * already be invalid.
-			 *
-			 * To avoid this possibility, swapcache pages get
-			 * migrated but are not remapped when migration
-			 * completes
-			 */
-		} else {
-			goto out_unlock;
-		}
-	}
+
+	/*
+	 * Block others from accessing the new page when we get around to
+	 * establishing additional references. We are usually the only one
+	 * holding a reference to newpage at this point. We used to have a BUG
+	 * here if trylock_page(newpage) fails, but would like to allow for
+	 * cases where there might be a race with the previous use of newpage.
+	 * This is much like races on refcount of oldpage: just don't BUG().
+	 */
+	if (unlikely(!trylock_page(newpage)))
+		goto out_unlock;
 
 	if (unlikely(isolated_balloon_page(page))) {
 		/*
@@ -853,7 +862,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		 * the page migration right away (proteced by page lock).
 		 */
 		rc = balloon_page_migrate(newpage, page, mode);
-		goto out_unlock;
+		goto out_unlock_both;
 	}
 
 	/*
@@ -872,30 +881,30 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		VM_BUG_ON_PAGE(PageAnon(page), page);
 		if (page_has_private(page)) {
 			try_to_free_buffers(page);
-			goto out_unlock;
+			goto out_unlock_both;
 		}
-		goto skip_unmap;
-	}
-
-	/* Establish migration ptes or remove ptes */
-	if (page_mapped(page)) {
+	} else if (page_mapped(page)) {
+		/* Establish migration ptes */
+		VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
+				page);
 		try_to_unmap(page,
 			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
 		page_was_mapped = 1;
 	}
 
-skip_unmap:
 	if (!page_mapped(page))
-		rc = move_to_new_page(newpage, page, page_was_mapped, mode);
+		rc = move_to_new_page(newpage, page, mode);
 
-	if (rc && page_was_mapped)
-		remove_migration_ptes(page, page);
+	if (page_was_mapped)
+		remove_migration_ptes(page,
+			rc == MIGRATEPAGE_SUCCESS ? newpage : page);
 
+out_unlock_both:
+	unlock_page(newpage);
+out_unlock:
 	/* Drop an anon_vma reference if we took one */
 	if (anon_vma)
 		put_anon_vma(anon_vma);
-
-out_unlock:
 	unlock_page(page);
 out:
 	return rc;
@@ -918,12 +927,14 @@ out:
 static ICE_noinline int unmap_and_move(new_page_t get_new_page,
 				   free_page_t put_new_page,
 				   unsigned long private, struct page *page,
-				   int force, enum migrate_mode mode)
+				   int force, enum migrate_mode mode,
+				   enum migrate_reason reason)
 {
-	int rc = 0;
+	int rc = MIGRATEPAGE_SUCCESS;
 	int *result = NULL;
-	struct page *newpage = get_new_page(page, private, &result);
+	struct page *newpage;
 
+	newpage = get_new_page(page, private, &result);
 	if (!newpage)
 		return -ENOMEM;
 
@@ -937,6 +948,8 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page,
 			goto out;
 
 	rc = __unmap_and_move(page, newpage, force, mode);
+	if (rc == MIGRATEPAGE_SUCCESS)
+		put_new_page = NULL;
 
 out:
 	if (rc != -EAGAIN) {
@@ -949,7 +962,13 @@ out:
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		putback_lru_page(page);
+		/* Soft-offlined page shouldn't go through lru cache list */
+		if (reason == MR_MEMORY_FAILURE) {
+			put_page(page);
+			if (!test_set_page_hwpoison(page))
+				num_poisoned_pages_inc();
+		} else
+			putback_lru_page(page);
 	}
 
 	/*
@@ -957,10 +976,9 @@ out:
 	 * it.  Otherwise, putback_lru_page() will drop the reference grabbed
 	 * during isolation.
 	 */
-	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
-		ClearPageSwapBacked(newpage);
+	if (put_new_page)
 		put_new_page(newpage, private);
-	} else if (unlikely(__is_movable_balloon_page(newpage))) {
+	else if (unlikely(__is_movable_balloon_page(newpage))) {
 		/* drop our reference, page already in the balloon */
 		put_page(newpage);
 	} else
@@ -998,7 +1016,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 				struct page *hpage, int force,
 				enum migrate_mode mode)
 {
-	int rc = 0;
+	int rc = -EAGAIN;
 	int *result = NULL;
 	int page_was_mapped = 0;
 	struct page *new_hpage;
@@ -1020,8 +1038,6 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	if (!new_hpage)
 		return -ENOMEM;
 
-	rc = -EAGAIN;
-
 	if (!trylock_page(hpage)) {
 		if (!force || mode != MIGRATE_SYNC)
 			goto out;
@@ -1031,6 +1047,9 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	if (PageAnon(hpage))
 		anon_vma = page_get_anon_vma(hpage);
 
+	if (unlikely(!trylock_page(new_hpage)))
+		goto put_anon;
+
 	if (page_mapped(hpage)) {
 		try_to_unmap(hpage,
 			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
@@ -1038,16 +1057,22 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	}
 
 	if (!page_mapped(hpage))
-		rc = move_to_new_page(new_hpage, hpage, page_was_mapped, mode);
+		rc = move_to_new_page(new_hpage, hpage, mode);
 
-	if (rc != MIGRATEPAGE_SUCCESS && page_was_mapped)
-		remove_migration_ptes(hpage, hpage);
+	if (page_was_mapped)
+		remove_migration_ptes(hpage,
+			rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage);
 
+	unlock_page(new_hpage);
+
+put_anon:
 	if (anon_vma)
 		put_anon_vma(anon_vma);
 
-	if (rc == MIGRATEPAGE_SUCCESS)
+	if (rc == MIGRATEPAGE_SUCCESS) {
 		hugetlb_cgroup_migrate(hpage, new_hpage);
+		put_new_page = NULL;
+	}
 
 	unlock_page(hpage);
 out:
@@ -1059,10 +1084,10 @@ out:
 	 * it.  Otherwise, put_page() will drop the reference grabbed during
 	 * isolation.
 	 */
-	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
+	if (put_new_page)
 		put_new_page(new_hpage, private);
 	else
-		put_page(new_hpage);
+		putback_active_hugepage(new_hpage);
 
 	if (result) {
 		if (rc)
@@ -1089,7 +1114,7 @@ out:
  *
  * The function returns after 10 attempts or if no pages are movable any more
  * because the list has become empty or no retryable pages exist any more.
- * The caller should call putback_lru_pages() to return pages to the LRU
+ * The caller should call putback_movable_pages() to return pages to the LRU
  * or free list only if ret != 0.
  *
  * Returns the number of pages that were not migrated, or an error code.
@@ -1122,7 +1147,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 						pass > 2, mode);
 			else
 				rc = unmap_and_move(get_new_page, put_new_page,
-						private, page, pass > 2, mode);
+						private, page, pass > 2, mode,
+						reason);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -1145,7 +1171,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 			}
 		}
 	}
-	rc = nr_failed + retry;
+	nr_failed += retry;
+	rc = nr_failed;
 out:
 	if (nr_succeeded)
 		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
@@ -1187,7 +1214,7 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 		return alloc_huge_page_node(page_hstate(compound_head(p)),
 					pm->node);
 	else
-		return alloc_pages_exact_node(pm->node,
+		return __alloc_pages_node(pm->node,
 				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
 }
 
@@ -1219,7 +1246,9 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 		if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma))
 			goto set_status;
 
-		page = follow_page(vma, pp->addr, FOLL_GET|FOLL_SPLIT);
+		/* FOLL_DUMP to ignore special (like zero) pages */
+		page = follow_page(vma, pp->addr,
+				FOLL_GET | FOLL_SPLIT | FOLL_DUMP);
 
 		err = PTR_ERR(page);
 		if (IS_ERR(page))
@@ -1229,10 +1258,6 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 		if (!page)
 			goto set_status;
 
-		/* Use PageReserved to check for zero page */
-		if (PageReserved(page))
-			goto put_and_set;
-
 		pp->page = page;
 		err = page_to_nid(page);
 
@@ -1389,18 +1414,14 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 		if (!vma || addr < vma->vm_start)
 			goto set_status;
 
-		page = follow_page(vma, addr, 0);
+		/* FOLL_DUMP to ignore special (like zero) pages */
+		page = follow_page(vma, addr, FOLL_DUMP);
 
 		err = PTR_ERR(page);
 		if (IS_ERR(page))
 			goto set_status;
 
-		err = -ENOENT;
-		/* Use PageReserved to check for zero page */
-		if (!page || PageReserved(page))
-			goto set_status;
-
-		err = page_to_nid(page);
+		err = page ? page_to_nid(page) : -ENOENT;
 set_status:
 		*status = err;
 
@@ -1553,11 +1574,11 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 	int nid = (int) data;
 	struct page *newpage;
 
-	newpage = alloc_pages_exact_node(nid,
+	newpage = __alloc_pages_node(nid,
 					 (GFP_HIGHUSER_MOVABLE |
 					  __GFP_THISNODE | __GFP_NOMEMALLOC |
 					  __GFP_NORETRY | __GFP_NOWARN) &
-					 ~GFP_IOFS, 0);
+					 ~__GFP_RECLAIM, 0);
 
 	return newpage;
 }
@@ -1731,7 +1752,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		goto out_dropref;
 
 	new_page = alloc_pages_node(node,
-		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT,
+		(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_RECLAIM,
 		HPAGE_PMD_ORDER);
 	if (!new_page)
 		goto out_fail;
@@ -1768,7 +1789,6 @@ fail_putback:
 			SetPageActive(page);
 		if (TestClearPageUnevictable(new_page))
 			SetPageUnevictable(page);
-		mlock_migrate_page(page, new_page);
 
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */
@@ -1796,7 +1816,7 @@ fail_putback:
 	 */
 	flush_cache_range(vma, mmun_start, mmun_end);
 	page_add_anon_rmap(new_page, vma, mmun_start);
-	pmdp_clear_flush_notify(vma, mmun_start, pmd);
+	pmdp_huge_clear_flush_notify(vma, mmun_start, pmd);
 	set_pmd_at(mm, mmun_start, pmd, entry);
 	flush_tlb_range(vma, mmun_start, mmun_end);
 	update_mmu_cache_pmd(vma, address, &entry);
@@ -1810,8 +1830,9 @@ fail_putback:
 		goto fail_putback;
 	}
 
-	mem_cgroup_migrate(page, new_page, false);
-
+	mlock_migrate_page(new_page, page);
+	set_page_memcg(new_page, page_memcg(page));
+	set_page_memcg(page, NULL);
 	page_remove_rmap(page);
 
 	spin_unlock(ptl);