Merge branch 'akpm' (patchbomb from Andrew)

Merge first patchbomb from Andrew Morton:
 - a few minor cifs fixes
 - dma-debug upadtes
 - ocfs2
 - slab
 - about half of MM
 - procfs
 - kernel/exit.c
 - panic.c tweaks
 - printk upates
 - lib/ updates
 - checkpatch updates
 - fs/binfmt updates
 - the drivers/rtc tree
 - nilfs
 - kmod fixes
 - more kernel/exit.c
 - various other misc tweaks and fixes

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits)
  exit: pidns: fix/update the comments in zap_pid_ns_processes()
  exit: pidns: alloc_pid() leaks pid_namespace if child_reaper is exiting
  exit: exit_notify: re-use "dead" list to autoreap current
  exit: reparent: call forget_original_parent() under tasklist_lock
  exit: reparent: avoid find_new_reaper() if no children
  exit: reparent: introduce find_alive_thread()
  exit: reparent: introduce find_child_reaper()
  exit: reparent: document the ->has_child_subreaper checks
  exit: reparent: s/while_each_thread/for_each_thread/ in find_new_reaper()
  exit: reparent: fix the cross-namespace PR_SET_CHILD_SUBREAPER reparenting
  exit: reparent: fix the dead-parent PR_SET_CHILD_SUBREAPER reparenting
  exit: proc: don't try to flush /proc/tgid/task/tgid
  exit: release_task: fix the comment about group leader accounting
  exit: wait: drop tasklist_lock before psig->c* accounting
  exit: wait: don't use zombie->real_parent
  exit: wait: cleanup the ptrace_reparented() checks
  usermodehelper: kill the kmod_thread_locker logic
  usermodehelper: don't use CLONE_VFORK for ____call_usermodehelper()
  fs/hfs/catalog.c: fix comparison bug in hfs_cat_keycmp
  nilfs2: fix the nilfs_iget() vs. nilfs_new_inode() races
  ...

28 files changed, 1236 insertions, 1954 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 8405eb0023a9..b3c6ce932c64 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -55,7 +55,9 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
-obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o
+obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
+obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
+obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
diff --git a/mm/cma.c b/mm/cma.c
index fde706e1284f..8e9ec13d31db 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -215,9 +215,21 @@ int __init cma_declare_contiguous(phys_addr_t base,
 			bool fixed, struct cma **res_cma)
 {
 	phys_addr_t memblock_end = memblock_end_of_DRAM();
-	phys_addr_t highmem_start = __pa(high_memory);
+	phys_addr_t highmem_start;
 	int ret = 0;
 
+#ifdef CONFIG_X86
+	/*
+	 * high_memory isn't direct mapped memory so retrieving its physical
+	 * address isn't appropriate.  But it would be useful to check the
+	 * physical address of the highmem boundary so it's justfiable to get
+	 * the physical address from it.  On x86 there is a validation check for
+	 * this case, so the following workaround is needed to avoid it.
+	 */
+	highmem_start = __pa_nodebug(high_memory);
+#else
+	highmem_start = __pa(high_memory);
+#endif
 	pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
 		__func__, &size, &base, &limit, &alignment);
 
diff --git a/mm/compaction.c b/mm/compaction.c
index f9792ba3537c..546e571e9d60 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -41,15 +41,17 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 static unsigned long release_freepages(struct list_head *freelist)
 {
 	struct page *page, *next;
-	unsigned long count = 0;
+	unsigned long high_pfn = 0;
 
 	list_for_each_entry_safe(page, next, freelist, lru) {
+		unsigned long pfn = page_to_pfn(page);
 		list_del(&page->lru);
 		__free_page(page);
-		count++;
+		if (pfn > high_pfn)
+			high_pfn = pfn;
 	}
 
-	return count;
+	return high_pfn;
 }
 
 static void map_pages(struct list_head *list)
@@ -195,16 +197,12 @@ static void update_pageblock_skip(struct compact_control *cc,
 
 	/* Update where async and sync compaction should restart */
 	if (migrate_scanner) {
-		if (cc->finished_update_migrate)
-			return;
 		if (pfn > zone->compact_cached_migrate_pfn[0])
 			zone->compact_cached_migrate_pfn[0] = pfn;
 		if (cc->mode != MIGRATE_ASYNC &&
 		    pfn > zone->compact_cached_migrate_pfn[1])
 			zone->compact_cached_migrate_pfn[1] = pfn;
 	} else {
-		if (cc->finished_update_free)
-			return;
 		if (pfn < zone->compact_cached_free_pfn)
 			zone->compact_cached_free_pfn = pfn;
 	}
@@ -715,7 +713,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 
 isolate_success:
-		cc->finished_update_migrate = true;
 		list_add(&page->lru, migratelist);
 		cc->nr_migratepages++;
 		nr_isolated++;
@@ -889,15 +886,6 @@ static void isolate_freepages(struct compact_control *cc)
 				block_start_pfn - pageblock_nr_pages;
 
 		/*
-		 * Set a flag that we successfully isolated in this pageblock.
-		 * In the next loop iteration, zone->compact_cached_free_pfn
-		 * will not be updated and thus it will effectively contain the
-		 * highest pageblock we isolated pages from.
-		 */
-		if (isolated)
-			cc->finished_update_free = true;
-
-		/*
 		 * isolate_freepages_block() might have aborted due to async
 		 * compaction being contended
 		 */
@@ -1086,9 +1074,9 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 
 	/* Compaction run is not finished if the watermark is not met */
 	watermark = low_wmark_pages(zone);
-	watermark += (1 << cc->order);
 
-	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
+							cc->alloc_flags))
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
@@ -1114,7 +1102,8 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
-unsigned long compaction_suitable(struct zone *zone, int order)
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
 	unsigned long watermark;
@@ -1126,21 +1115,30 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (order == -1)
 		return COMPACT_CONTINUE;
 
+	watermark = low_wmark_pages(zone);
+	/*
+	 * If watermarks for high-order allocation are already met, there
+	 * should be no need for compaction at all.
+	 */
+	if (zone_watermark_ok(zone, order, watermark, classzone_idx,
+								alloc_flags))
+		return COMPACT_PARTIAL;
+
 	/*
 	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
 	 * This is because during migration, copies of pages need to be
 	 * allocated and for a short time, the footprint is higher
 	 */
-	watermark = low_wmark_pages(zone) + (2UL << order);
-	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+	watermark += (2UL << order);
+	if (!zone_watermark_ok(zone, 0, watermark, classzone_idx, alloc_flags))
 		return COMPACT_SKIPPED;
 
 	/*
 	 * fragmentation index determines if allocation failures are due to
 	 * low memory or external fragmentation
 	 *
-	 * index of -1000 implies allocations might succeed depending on
-	 * watermarks
+	 * index of -1000 would imply allocations might succeed depending on
+	 * watermarks, but we already failed the high-order watermark check
 	 * index towards 0 implies failure is due to lack of memory
 	 * index towards 1000 implies failure is due to fragmentation
 	 *
@@ -1150,10 +1148,6 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
 		return COMPACT_SKIPPED;
 
-	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
-	    0, 0))
-		return COMPACT_PARTIAL;
-
 	return COMPACT_CONTINUE;
 }
 
@@ -1164,8 +1158,10 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
+	unsigned long last_migrated_pfn = 0;
 
-	ret = compaction_suitable(zone, cc->order);
+	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
+							cc->classzone_idx);
 	switch (ret) {
 	case COMPACT_PARTIAL:
 	case COMPACT_SKIPPED:
@@ -1208,6 +1204,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	while ((ret = compact_finished(zone, cc, migratetype)) ==
 						COMPACT_CONTINUE) {
 		int err;
+		unsigned long isolate_start_pfn = cc->migrate_pfn;
 
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
@@ -1216,7 +1213,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			cc->nr_migratepages = 0;
 			goto out;
 		case ISOLATE_NONE:
-			continue;
+			/*
+			 * We haven't isolated and migrated anything, but
+			 * there might still be unflushed migrations from
+			 * previous cc->order aligned block.
+			 */
+			goto check_drain;
 		case ISOLATE_SUCCESS:
 			;
 		}
@@ -1241,12 +1243,61 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 				goto out;
 			}
 		}
+
+		/*
+		 * Record where we could have freed pages by migration and not
+		 * yet flushed them to buddy allocator. We use the pfn that
+		 * isolate_migratepages() started from in this loop iteration
+		 * - this is the lowest page that could have been isolated and
+		 * then freed by migration.
+		 */
+		if (!last_migrated_pfn)
+			last_migrated_pfn = isolate_start_pfn;
+
+check_drain:
+		/*
+		 * Has the migration scanner moved away from the previous
+		 * cc->order aligned block where we migrated from? If yes,
+		 * flush the pages that were freed, so that they can merge and
+		 * compact_finished() can detect immediately if allocation
+		 * would succeed.
+		 */
+		if (cc->order > 0 && last_migrated_pfn) {
+			int cpu;
+			unsigned long current_block_start =
+				cc->migrate_pfn & ~((1UL << cc->order) - 1);
+
+			if (last_migrated_pfn < current_block_start) {
+				cpu = get_cpu();
+				lru_add_drain_cpu(cpu);
+				drain_local_pages(zone);
+				put_cpu();
+				/* No more flushing until we migrate again */
+				last_migrated_pfn = 0;
+			}
+		}
+
 	}
 
 out:
-	/* Release free pages and check accounting */
-	cc->nr_freepages -= release_freepages(&cc->freepages);
-	VM_BUG_ON(cc->nr_freepages != 0);
+	/*
+	 * Release free pages and update where the free scanner should restart,
+	 * so we don't leave any returned pages behind in the next attempt.
+	 */
+	if (cc->nr_freepages > 0) {
+		unsigned long free_pfn = release_freepages(&cc->freepages);
+
+		cc->nr_freepages = 0;
+		VM_BUG_ON(free_pfn == 0);
+		/* The cached pfn is always the first in a pageblock */
+		free_pfn &= ~(pageblock_nr_pages-1);
+		/*
+		 * Only go back, not forward. The cached pfn might have been
+		 * already reset to zone end in compact_finished()
+		 */
+		if (free_pfn > zone->compact_cached_free_pfn)
+			zone->compact_cached_free_pfn = free_pfn;
+	}
 
 	trace_mm_compaction_end(ret);
 
@@ -1254,7 +1305,8 @@ out:
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
+		int alloc_flags, int classzone_idx)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1264,6 +1316,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = mode,
+		.alloc_flags = alloc_flags,
+		.classzone_idx = classzone_idx,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1288,14 +1342,13 @@ int sysctl_extfrag_threshold = 500;
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that determines if compaction was aborted due to
  *	       need_resched() or lock contention
- * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1303,7 +1356,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_DEFERRED;
-	int alloc_flags = 0;
 	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
 
 	*contended = COMPACT_CONTENDED_NONE;
@@ -1312,10 +1364,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
-#ifdef CONFIG_CMA
-	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
@@ -1326,7 +1374,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-							&zone_contended);
+				&zone_contended, alloc_flags, classzone_idx);
 		rc = max(status, rc);
 		/*
 		 * It takes at least one zone that wasn't lock contended
@@ -1335,9 +1383,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
-		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags)) {
-			*candidate_zone = zone;
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
+					classzone_idx, alloc_flags)) {
 			/*
 			 * We think the allocation will succeed in this zone,
 			 * but it is not certain, hence the false. The caller
@@ -1359,7 +1406,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			goto break_loop;
 		}
 
-		if (mode != MIGRATE_ASYNC) {
+		if (mode != MIGRATE_ASYNC && status == COMPACT_COMPLETE) {
 			/*
 			 * We think that allocation won't succeed in this zone
 			 * so we defer compaction there. If it ends up
diff --git a/mm/debug.c b/mm/debug.c
index 5ce45c9a29b5..0e58f3211f89 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -95,7 +95,10 @@ void dump_page_badflags(struct page *page, const char *reason,
 		dump_flags(page->flags & badflags,
 				pageflag_names, ARRAY_SIZE(pageflag_names));
 	}
-	mem_cgroup_print_bad_page(page);
+#ifdef CONFIG_MEMCG
+	if (page->mem_cgroup)
+		pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
+#endif
 }
 
 void dump_page(struct page *page, const char *reason)
diff --git a/mm/frontswap.c b/mm/frontswap.c
index f2a3571c6e22..8d82809eb085 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -182,7 +182,7 @@ void __frontswap_init(unsigned type, unsigned long *map)
 	if (frontswap_ops)
 		frontswap_ops->init(type);
 	else {
-		BUG_ON(type > MAX_SWAPFILES);
+		BUG_ON(type >= MAX_SWAPFILES);
 		set_bit(type, need_init);
 	}
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index de984159cf0b..5b2c6875fc38 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -784,7 +784,6 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	if (!pmd_none(*pmd))
 		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
-	entry = pmd_wrprotect(entry);
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9fd722769927..30cd96879152 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2638,8 +2638,9 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+	address = start;
 again:
-	for (address = start; address < end; address += sz) {
+	for (; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
@@ -2686,6 +2687,7 @@ again:
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
 		if (force_flush) {
+			address += sz;
 			spin_unlock(ptl);
 			break;
 		}
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index a67c26e0f360..037e1c00a5b7 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/page_counter.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
@@ -23,7 +24,7 @@ struct hugetlb_cgroup {
 	/*
 	 * the counter to account for hugepages from hugetlb.
 	 */
-	struct res_counter hugepage[HUGE_MAX_HSTATE];
+	struct page_counter hugepage[HUGE_MAX_HSTATE];
 };
 
 #define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
@@ -60,7 +61,7 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
 	int idx;
 
 	for (idx = 0; idx < hugetlb_max_hstate; idx++) {
-		if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
+		if (page_counter_read(&h_cg->hugepage[idx]))
 			return true;
 	}
 	return false;
@@ -79,12 +80,12 @@ hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	if (parent_h_cgroup) {
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx],
-					 &parent_h_cgroup->hugepage[idx]);
+			page_counter_init(&h_cgroup->hugepage[idx],
+					  &parent_h_cgroup->hugepage[idx]);
 	} else {
 		root_h_cgroup = h_cgroup;
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx], NULL);
+			page_counter_init(&h_cgroup->hugepage[idx], NULL);
 	}
 	return &h_cgroup->css;
 }
@@ -108,9 +109,8 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
 static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 				       struct page *page)
 {
-	int csize;
-	struct res_counter *counter;
-	struct res_counter *fail_res;
+	unsigned int nr_pages;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *page_hcg;
 	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
 
@@ -123,15 +123,15 @@ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 	if (!page_hcg || page_hcg != h_cg)
 		goto out;
 
-	csize = PAGE_SIZE << compound_order(page);
+	nr_pages = 1 << compound_order(page);
 	if (!parent) {
 		parent = root_h_cgroup;
 		/* root has no limit */
-		res_counter_charge_nofail(&parent->hugepage[idx],
-					  csize, &fail_res);
+		page_counter_charge(&parent->hugepage[idx], nr_pages);
 	}
 	counter = &h_cg->hugepage[idx];
-	res_counter_uncharge_until(counter, counter->parent, csize);
+	/* Take the pages off the local counter */
+	page_counter_cancel(counter, nr_pages);
 
 	set_hugetlb_cgroup(page, parent);
 out:
@@ -166,9 +166,8 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 				 struct hugetlb_cgroup **ptr)
 {
 	int ret = 0;
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = NULL;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		goto done;
@@ -187,7 +186,7 @@ again:
 	}
 	rcu_read_unlock();
 
-	ret = res_counter_charge(&h_cg->hugepage[idx], csize, &fail_res);
+	ret = page_counter_try_charge(&h_cg->hugepage[idx], nr_pages, &counter);
 	css_put(&h_cg->css);
 done:
 	*ptr = h_cg;
@@ -213,7 +212,6 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 				  struct page *page)
 {
 	struct hugetlb_cgroup *h_cg;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		return;
@@ -222,61 +220,76 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 	if (unlikely(!h_cg))
 		return;
 	set_hugetlb_cgroup(page, NULL);
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
 void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 				    struct hugetlb_cgroup *h_cg)
 {
-	unsigned long csize = nr_pages * PAGE_SIZE;
-
 	if (hugetlb_cgroup_disabled() || !h_cg)
 		return;
 
 	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
 		return;
 
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
 static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 				   struct cftype *cft)
 {
-	int idx, name;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
 
-	idx = MEMFILE_IDX(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)];
 
-	return res_counter_read_u64(&h_cg->hugepage[idx], name);
+	switch (MEMFILE_ATTR(cft->private)) {
+	case RES_USAGE:
+		return (u64)page_counter_read(counter) * PAGE_SIZE;
+	case RES_LIMIT:
+		return (u64)counter->limit * PAGE_SIZE;
+	case RES_MAX_USAGE:
+		return (u64)counter->watermark * PAGE_SIZE;
+	case RES_FAILCNT:
+		return counter->failcnt;
+	default:
+		BUG();
+	}
 }
 
+static DEFINE_MUTEX(hugetlb_limit_mutex);
+
 static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret;
-	unsigned long long val;
+	int ret, idx;
+	unsigned long nr_pages;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
+	if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */
+		return -EINVAL;
+
 	buf = strstrip(buf);
+	ret = page_counter_memparse(buf, &nr_pages);
+	if (ret)
+		return ret;
+
 	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
-		if (hugetlb_cgroup_is_root(h_cg)) {
-			/* Can't set limit on root */
-			ret = -EINVAL;
-			break;
-		}
-		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
-			break;
-		val = ALIGN(val, 1ULL << huge_page_shift(&hstates[idx]));
-		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+		mutex_lock(&hugetlb_limit_mutex);
+		ret = page_counter_limit(&h_cg->hugepage[idx], nr_pages);
+		mutex_unlock(&hugetlb_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -288,18 +301,18 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret = 0;
+	int ret = 0;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)];
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&h_cg->hugepage[idx]);
+		page_counter_reset_watermark(counter);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&h_cg->hugepage[idx]);
+		counter->failcnt = 0;
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/mm/internal.h b/mm/internal.h
index a4f90ba7068e..efad241f7014 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -161,13 +161,10 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
-	bool finished_update_free;	/* True when the zone cached pfns are
-					 * no longer being updated
-					 */
-	bool finished_update_migrate;
-
 	int order;			/* order a direct compactor needs */
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
+	const int alloc_flags;		/* alloc flags of a direct compactor */
+	const int classzone_idx;	/* zone index of a direct compactor */
 	struct zone *zone;
 	int contended;			/* Signal need_sched() or lock
 					 * contention detected during
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ee48428cf8e3..85df503ec023 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -25,7 +25,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/res_counter.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/mm.h>
@@ -51,7 +51,7 @@
 #include <linux/seq_file.h>
 #include <linux/vmpressure.h>
 #include <linux/mm_inline.h>
-#include <linux/page_cgroup.h>
+#include <linux/swap_cgroup.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include <linux/lockdep.h>
@@ -143,14 +143,8 @@ struct mem_cgroup_stat_cpu {
 	unsigned long targets[MEM_CGROUP_NTARGETS];
 };
 
-struct mem_cgroup_reclaim_iter {
-	/*
-	 * last scanned hierarchy member. Valid only if last_dead_count
-	 * matches memcg->dead_count of the hierarchy root group.
-	 */
-	struct mem_cgroup *last_visited;
-	int last_dead_count;
-
+struct reclaim_iter {
+	struct mem_cgroup *position;
 	/* scan generation, increased every round-trip */
 	unsigned int generation;
 };
@@ -162,10 +156,10 @@ struct mem_cgroup_per_zone {
 	struct lruvec		lruvec;
 	unsigned long		lru_size[NR_LRU_LISTS];
 
-	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
+	struct reclaim_iter	iter[DEF_PRIORITY + 1];
 
 	struct rb_node		tree_node;	/* RB tree node */
-	unsigned long long	usage_in_excess;/* Set to the value by which */
+	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
 	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
@@ -198,7 +192,7 @@ static struct mem_cgroup_tree soft_limit_tree __read_mostly;
 
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
-	u64 threshold;
+	unsigned long threshold;
 };
 
 /* For threshold */
@@ -284,10 +278,13 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
  */
 struct mem_cgroup {
 	struct cgroup_subsys_state css;
-	/*
-	 * the counter to account for memory usage
-	 */
-	struct res_counter res;
+
+	/* Accounted resources */
+	struct page_counter memory;
+	struct page_counter memsw;
+	struct page_counter kmem;
+
+	unsigned long soft_limit;
 
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
@@ -296,15 +293,6 @@ struct mem_cgroup {
 	int initialized;
 
 	/*
-	 * the counter to account for mem+swap usage.
-	 */
-	struct res_counter memsw;
-
-	/*
-	 * the counter to account for kernel memory usage.
-	 */
-	struct res_counter kmem;
-	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
@@ -352,7 +340,6 @@ struct mem_cgroup {
 	struct mem_cgroup_stat_cpu nocpu_base;
 	spinlock_t pcp_counter_lock;
 
-	atomic_t	dead_count;
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
 	struct cg_proto tcp_mem;
 #endif
@@ -382,7 +369,6 @@ struct mem_cgroup {
 /* internal only representation about the status of kmem accounting. */
 enum {
 	KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */
-	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
 };
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -396,22 +382,6 @@ static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
 }
 
-static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
-{
-	/*
-	 * Our caller must use css_get() first, because memcg_uncharge_kmem()
-	 * will call css_put() if it sees the memcg is dead.
-	 */
-	smp_wmb();
-	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
-		set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
-}
-
-static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
-{
-	return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
-				  &memcg->kmem_account_flags);
-}
 #endif
 
 /* Stuffs for move charges at task migration. */
@@ -650,7 +620,7 @@ static void disarm_kmem_keys(struct mem_cgroup *memcg)
 	 * This check can't live in kmem destruction function,
 	 * since the charges will outlive the cgroup
 	 */
-	WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0);
+	WARN_ON(page_counter_read(&memcg->kmem));
 }
 #else
 static void disarm_kmem_keys(struct mem_cgroup *memcg)
@@ -664,8 +634,6 @@ static void disarm_static_keys(struct mem_cgroup *memcg)
 	disarm_kmem_keys(memcg);
 }
 
-static void drain_all_stock_async(struct mem_cgroup *memcg);
-
 static struct mem_cgroup_per_zone *