Merge branch 'akpm' (updates from Andrew Morton)

Merge first patch-bomb from Andrew Morton:
 - various misc bits
 - I'm been patchmonkeying ocfs2 for a while, as Joel and Mark have been
   distracted.  There has been quite a bit of activity.
 - About half the MM queue
 - Some backlight bits
 - Various lib/ updates
 - checkpatch updates
 - zillions more little rtc patches
 - ptrace
 - signals
 - exec
 - procfs
 - rapidio
 - nbd
 - aoe
 - pps
 - memstick
 - tools/testing/selftests updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (445 commits)
  tools/testing/selftests: don't assume the x bit is set on scripts
  selftests: add .gitignore for kcmp
  selftests: fix clean target in kcmp Makefile
  selftests: add .gitignore for vm
  selftests: add hugetlbfstest
  self-test: fix make clean
  selftests: exit 1 on failure
  kernel/resource.c: remove the unneeded assignment in function __find_resource
  aio: fix wrong comment in aio_complete()
  drivers/w1/slaves/w1_ds2408.c: add magic sequence to disable P0 test mode
  drivers/memstick/host/r592.c: convert to module_pci_driver
  drivers/memstick/host/jmb38x_ms: convert to module_pci_driver
  pps-gpio: add device-tree binding and support
  drivers/pps/clients/pps-gpio.c: convert to module_platform_driver
  drivers/pps/clients/pps-gpio.c: convert to devm_* helpers
  drivers/parport/share.c: use kzalloc
  Documentation/accounting/getdelays.c: avoid strncpy in accounting tool
  aoe: update internal version number to v83
  aoe: update copyright date
  aoe: perform I/O completions in parallel
  ...

22 files changed, 1021 insertions, 516 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index f5e698e30d4a..7e28ecfa8aa4 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -477,3 +477,15 @@ config FRONTSWAP
 	  and swap data is stored as normal on the matching swap device.
 
 	  If unsure, say Y to enable frontswap.
+
+config MEM_SOFT_DIRTY
+	bool "Track memory changes"
+	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
+	select PROC_PAGE_MONITOR
+	help
+	  This option enables memory changes tracking by introducing a
+	  soft-dirty bit on pte-s. This bit it set when someone writes
+	  into a page just as regular dirty bit, but unlike the latter
+	  it can be cleared by hands.
+
+	  See Documentation/vm/soft-dirty.txt for more details.
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 502517492258..d014ee5fcbbd 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -515,7 +515,6 @@ EXPORT_SYMBOL(bdi_destroy);
 int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
 			   unsigned int cap)
 {
-	char tmp[32];
 	int err;
 
 	bdi->name = name;
@@ -524,8 +523,8 @@ int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
 	if (err)
 		return err;
 
-	sprintf(tmp, "%.28s%s", name, "-%d");
-	err = bdi_register(bdi, NULL, tmp, atomic_long_inc_return(&bdi_seq));
+	err = bdi_register(bdi, NULL, "%.28s-%ld", name,
+			   atomic_long_inc_return(&bdi_seq));
 	if (err) {
 		bdi_destroy(bdi);
 		return err;
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 2b0bcb019ec2..6ab7744e692e 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -241,33 +241,26 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 	return count;
 }
 
-static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
+static int reset_managed_pages_done __initdata;
+
+static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	/*
-	 * In free_area_init_core(), highmem zone's managed_pages is set to
-	 * present_pages, and bootmem allocator doesn't allocate from highmem
-	 * zones. So there's no need to recalculate managed_pages because all
-	 * highmem pages will be managed by the buddy system. Here highmem
-	 * zone also includes highmem movable zone.
-	 */
+	if (reset_managed_pages_done)
+		return;
+
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
-		if (!is_highmem(z))
-			z->managed_pages = 0;
+		z->managed_pages = 0;
 }
 
-/**
- * free_all_bootmem_node - release a node's free pages to the buddy allocator
- * @pgdat: node to be released
- *
- * Returns the number of pages actually released.
- */
-unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
+void __init reset_all_zones_managed_pages(void)
 {
-	register_page_bootmem_info_node(pgdat);
-	reset_node_lowmem_managed_pages(pgdat);
-	return free_all_bootmem_core(pgdat->bdata);
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_managed_pages(pgdat);
+	reset_managed_pages_done = 1;
 }
 
 /**
@@ -279,14 +272,14 @@ unsigned long __init free_all_bootmem(void)
 {
 	unsigned long total_pages = 0;
 	bootmem_data_t *bdata;
-	struct pglist_data *pgdat;
 
-	for_each_online_pgdat(pgdat)
-		reset_node_lowmem_managed_pages(pgdat);
+	reset_all_zones_managed_pages();
 
 	list_for_each_entry(bdata, &bdata_list, list)
 		total_pages += free_all_bootmem_core(bdata);
 
+	totalram_pages += total_pages;
+
 	return total_pages;
 }
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 362c329b83fe..d8b3b850150c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1429,7 +1429,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 	if (ret == 1) {
 		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
-		set_pmd_at(mm, new_addr, new_pmd, pmd);
+		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
 		spin_unlock(&mm->page_table_lock);
 	}
 out:
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index aed085ad11a8..83aff0a4d093 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -319,7 +319,7 @@ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
 
 	hstate = hstate_vma(vma);
 
-	return 1UL << (hstate->order + PAGE_SHIFT);
+	return 1UL << huge_page_shift(hstate);
 }
 EXPORT_SYMBOL_GPL(vma_kernel_pagesize);
 
@@ -1263,7 +1263,7 @@ static void __init gather_bootmem_prealloc(void)
 		 * side-effects, like CommitLimit going negative.
 		 */
 		if (h->order > (MAX_ORDER - 1))
-			totalram_pages += 1 << h->order;
+			adjust_managed_page_count(page, 1 << h->order);
 	}
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 194721839cf5..2e851f453814 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1148,6 +1148,58 @@ skip_node:
 	return NULL;
 }
 
+static void mem_cgroup_iter_invalidate(struct mem_cgroup *root)
+{
+	/*
+	 * When a group in the hierarchy below root is destroyed, the
+	 * hierarchy iterator can no longer be trusted since it might
+	 * have pointed to the destroyed group.  Invalidate it.
+	 */
+	atomic_inc(&root->dead_count);
+}
+
+static struct mem_cgroup *
+mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
+		     struct mem_cgroup *root,
+		     int *sequence)
+{
+	struct mem_cgroup *position = NULL;
+	/*
+	 * A cgroup destruction happens in two stages: offlining and
+	 * release.  They are separated by a RCU grace period.
+	 *
+	 * If the iterator is valid, we may still race with an
+	 * offlining.  The RCU lock ensures the object won't be
+	 * released, tryget will fail if we lost the race.
+	 */
+	*sequence = atomic_read(&root->dead_count);
+	if (iter->last_dead_count == *sequence) {
+		smp_rmb();
+		position = iter->last_visited;
+		if (position && !css_tryget(&position->css))
+			position = NULL;
+	}
+	return position;
+}
+
+static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
+				   struct mem_cgroup *last_visited,
+				   struct mem_cgroup *new_position,
+				   int sequence)
+{
+	if (last_visited)
+		css_put(&last_visited->css);
+	/*
+	 * We store the sequence count from the time @last_visited was
+	 * loaded successfully instead of rereading it here so that we
+	 * don't lose destruction events in between.  We could have
+	 * raced with the destruction of @new_position after all.
+	 */
+	iter->last_visited = new_position;
+	smp_wmb();
+	iter->last_dead_count = sequence;
+}
+
 /**
  * mem_cgroup_iter - iterate over memory cgroup hierarchy
  * @root: hierarchy root
@@ -1171,7 +1223,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 {
 	struct mem_cgroup *memcg = NULL;
 	struct mem_cgroup *last_visited = NULL;
-	unsigned long uninitialized_var(dead_count);
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -1191,6 +1242,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	rcu_read_lock();
 	while (!memcg) {
 		struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
+		int uninitialized_var(seq);
 
 		if (reclaim) {
 			int nid = zone_to_nid(reclaim->zone);
@@ -1204,37 +1256,13 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				goto out_unlock;
 			}
 
-			/*
-			 * If the dead_count mismatches, a destruction
-			 * has happened or is happening concurrently.
-			 * If the dead_count matches, a destruction
-			 * might still happen concurrently, but since
-			 * we checked under RCU, that destruction
-			 * won't free the object until we release the
-			 * RCU reader lock.  Thus, the dead_count
-			 * check verifies the pointer is still valid,
-			 * css_tryget() verifies the cgroup pointed to
-			 * is alive.
-			 */
-			dead_count = atomic_read(&root->dead_count);
-			if (dead_count == iter->last_dead_count) {
-				smp_rmb();
-				last_visited = iter->last_visited;
-				if (last_visited &&
-				    !css_tryget(&last_visited->css))
-					last_visited = NULL;
-			}
+			last_visited = mem_cgroup_iter_load(iter, root, &seq);
 		}
 
 		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
-			if (last_visited)
-				css_put(&last_visited->css);
-
-			iter->last_visited = memcg;
-			smp_wmb();
-			iter->last_dead_count = dead_count;
+			mem_cgroup_iter_update(iter, last_visited, memcg, seq);
 
 			if (!memcg)
 				iter->generation++;
@@ -1448,11 +1476,12 @@ static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 	return ret;
 }
 
-int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg)
+bool task_in_mem_cgroup(struct task_struct *task,
+			const struct mem_cgroup *memcg)
 {
-	int ret;
 	struct mem_cgroup *curr = NULL;
 	struct task_struct *p;
+	bool ret;
 
 	p = find_lock_task_mm(task);
 	if (p) {
@@ -1464,14 +1493,14 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg)
 		 * killer still needs to detect if they have already been oom
 		 * killed to prevent needlessly killing additional tasks.
 		 */
-		task_lock(task);
+		rcu_read_lock();
 		curr = mem_cgroup_from_task(task);
 		if (curr)
 			css_get(&curr->css);
-		task_unlock(task);
+		rcu_read_unlock();
 	}
 	if (!curr)
-		return 0;
+		return false;
 	/*
 	 * We should check use_hierarchy of "memcg" not "curr". Because checking
 	 * use_hierarchy of "curr" here make this function true if hierarchy is
@@ -6317,14 +6346,14 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
 	struct mem_cgroup *parent = memcg;
 
 	while ((parent = parent_mem_cgroup(parent)))
-		atomic_inc(&parent->dead_count);
+		mem_cgroup_iter_invalidate(parent);
 
 	/*
 	 * if the root memcg is not hierarchical we have to check it
 	 * explicitely.
 	 */
 	if (!root_mem_cgroup->use_hierarchy)
-		atomic_inc(&root_mem_cgroup->dead_count);
+		mem_cgroup_iter_invalidate(root_mem_cgroup);
 }
 
 static void mem_cgroup_css_offline(struct cgroup *cont)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ceb0c7f1932f..2c13aa7a0164 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1410,7 +1410,8 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 
 	/*
 	 * Isolate the page, so that it doesn't get reallocated if it
-	 * was free.
+	 * was free. This flag should be kept set until the source page
+	 * is freed and PG_hwpoison on it is set.
 	 */
 	set_migratetype_isolate(p, true);
 	/*
@@ -1433,7 +1434,6 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags)
 		/* Not a free page */
 		ret = 1;
 	}
-	unset_migratetype_isolate(p, MIGRATE_MOVABLE);
 	unlock_memory_hotplug();
 	return ret;
 }
@@ -1494,7 +1494,6 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		atomic_long_add(1 << compound_trans_order(hpage),
 				&num_poisoned_pages);
 	}
-	/* keep elevated page count for bad page */
 	return ret;
 }
 
@@ -1559,7 +1558,7 @@ int soft_offline_page(struct page *page, int flags)
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	}
-	/* keep elevated page count for bad page */
+	unset_migratetype_isolate(page, MIGRATE_MOVABLE);
 	return ret;
 }
 
@@ -1625,7 +1624,22 @@ static int __soft_offline_page(struct page *page, int flags)
 			if (ret > 0)
 				ret = -EIO;
 		} else {
+			/*
+			 * After page migration succeeds, the source page can
+			 * be trapped in pagevec and actual freeing is delayed.
+			 * Freeing code works differently based on PG_hwpoison,
+			 * so there's a race. We need to make sure that the
+			 * source page should be freed back to buddy before
+			 * setting PG_hwpoison.
+			 */
+			if (!is_free_buddy_page(page))
+				lru_add_drain_all();
+			if (!is_free_buddy_page(page))
+				drain_all_pages();
 			SetPageHWPoison(page);
+			if (!is_free_buddy_page(page))
+				pr_info("soft offline: %#lx: page leaked\n",
+					pfn);
 			atomic_long_inc(&num_poisoned_pages);
 		}
 	} else {
diff --git a/mm/memory.c b/mm/memory.c
index 95d0cce63583..b68812d682b6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -82,7 +82,6 @@ EXPORT_SYMBOL(max_mapnr);
 EXPORT_SYMBOL(mem_map);
 #endif
 
-unsigned long num_physpages;
 /*
  * A number of key systems in x86 including ioremap() rely on the assumption
  * that high_memory defines the upper bound on direct map memory, then end
@@ -92,7 +91,6 @@ unsigned long num_physpages;
  */
 void * high_memory;
 
-EXPORT_SYMBOL(num_physpages);
 EXPORT_SYMBOL(high_memory);
 
 /*
@@ -1101,6 +1099,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
+	unsigned long range_start = addr;
 
 again:
 	init_rss_vec(rss);
@@ -1206,12 +1205,14 @@ again:
 		force_flush = 0;
 
 #ifdef HAVE_GENERIC_MMU_GATHER
-		tlb->start = addr;
-		tlb->end = end;
+		tlb->start = range_start;
+		tlb->end = addr;
 #endif
 		tlb_flush_mmu(tlb);
-		if (addr != end)
+		if (addr != end) {
+			range_start = addr;
 			goto again;
+		}
 	}
 
 	return addr;
@@ -2904,7 +2905,7 @@ static inline void unmap_mapping_range_tree(struct rb_root *root,
 			details->first_index, details->last_index) {
 
 		vba = vma->vm_pgoff;
-		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
+		vea = vba + vma_pages(vma) - 1;
 		/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
 		zba = details->first_index;
 		if (zba < vba)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 081b4d654ed6..f5ba127b2051 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -75,7 +75,7 @@ static struct resource *register_memory_resource(u64 start, u64 size)
 	res->end = start + size - 1;
 	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	if (request_resource(&iomem_resource, res) < 0) {
-		printk("System RAM resource %pR cannot be added\n", res);
+		pr_debug("System RAM resource %pR cannot be added\n", res);
 		kfree(res);
 		res = NULL;
 	}
@@ -101,12 +101,9 @@ void get_page_bootmem(unsigned long info,  struct page *page,
 	atomic_inc(&page->_count);
 }
 
-/* reference to __meminit __free_pages_bootmem is valid
- * so use __ref to tell modpost not to generate a warning */
-void __ref put_page_bootmem(struct page *page)
+void put_page_bootmem(struct page *page)
 {
 	unsigned long type;
-	static DEFINE_MUTEX(ppb_lock);
 
 	type = (unsigned long) page->lru.next;
 	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
@@ -116,17 +113,8 @@ void __ref put_page_bootmem(struct page *page)
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
-
-		/*
-		 * Please refer to comment for __free_pages_bootmem()
-		 * for why we serialize here.
-		 */
-		mutex_lock(&ppb_lock);
-		__free_pages_bootmem(page, 0);
-		mutex_unlock(&ppb_lock);
-		totalram_pages++;
+		free_reserved_page(page);
 	}
-
 }
 
 #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
@@ -309,7 +297,7 @@ static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
 	/* can't move pfns which are higher than @z2 */
 	if (end_pfn > zone_end_pfn(z2))
 		goto out_fail;
-	/* the move out part mast at the left most of @z2 */
+	/* the move out part must be at the left most of @z2 */
 	if (start_pfn > z2->zone_start_pfn)
 		goto out_fail;
 	/* must included/overlap */
@@ -775,29 +763,18 @@ EXPORT_SYMBOL_GPL(restore_online_page_callback);
 
 void __online_page_set_limits(struct page *page)
 {
-	unsigned long pfn = page_to_pfn(page);
-
-	if (pfn >= num_physpages)
-		num_physpages = pfn + 1;
 }
 EXPORT_SYMBOL_GPL(__online_page_set_limits);
 
 void __online_page_increment_counters(struct page *page)
 {
-	totalram_pages++;
-
-#ifdef CONFIG_HIGHMEM
-	if (PageHighMem(page))
-		totalhigh_pages++;
-#endif
+	adjust_managed_page_count(page, 1);
 }
 EXPORT_SYMBOL_GPL(__online_page_increment_counters);
 
 void __online_page_free(struct page *page)
 {
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
+	__free_reserved_page(page);
 }
 EXPORT_SYMBOL_GPL(__online_page_free);
 
@@ -918,6 +895,7 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 
 int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
 {
+	unsigned long flags;
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
 	int need_zonelists_rebuild = 0;
@@ -994,9 +972,12 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 		return ret;
 	}
 
-	zone->managed_pages += onlined_pages;
 	zone->present_pages += onlined_pages;
+
+	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	zone->zone_pgdat->node_present_pages += onlined_pages;
+	pgdat_resize_unlock(zone->zone_pgdat, &flags);
+
 	if (onlined_pages) {
 		node_states_set_node(zone_to_nid(zone), &arg);
 		if (need_zonelists_rebuild)
@@ -1487,6 +1468,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	unsigned long pfn, nr_pages, expire;
 	long offlined_pages;
 	int ret, drain, retry_max, node;
+	unsigned long flags;
 	struct zone *zone;
 	struct memory_notify arg;
 
@@ -1578,10 +1560,12 @@ repeat:
 	/* reset pagetype flags and makes migrate type to be MOVABLE */
 	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
 	/* removal success */
-	zone->managed_pages -= offlined_pages;
+	adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
 	zone->present_pages -= offlined_pages;
+
+	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	zone->zone_pgdat->node_present_pages -= offlined_pages;
-	totalram_pages -= offlined_pages;
+	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
 	init_per_zone_wmark_min();
 
diff --git a/mm/mm_init.c b/mm/mm_init.c
index c280a02ea11e..633c08863fd8 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -9,6 +9,8 @@
 #include <linux/init.h>
 #include <linux/kobject.h>
 #include <linux/export.h>
+#include <linux/memory.h>
+#include <linux/notifier.h>
 #include "internal.h"
 
 #ifdef CONFIG_DEBUG_MEMORY_INIT
@@ -147,6 +149,51 @@ early_param("mminit_loglevel", set_mminit_loglevel);
 struct kobject *mm_kobj;
 EXPORT_SYMBOL_GPL(mm_kobj);
 
+#ifdef CONFIG_SMP
+s32 vm_committed_as_batch = 32;
+
+static void __meminit mm_compute_batch(void)
+{
+	u64 memsized_batch;
+	s32 nr = num_present_cpus();
+	s32 batch = max_t(s32, nr*2, 32);
+
+	/* batch size set to 0.4% of (total memory/#cpus), or max int32 */
+	memsized_batch = min_t(u64, (totalram_pages/nr)/256, 0x7fffffff);
+
+	vm_committed_as_batch = max_t(s32, memsized_batch, batch);
+}
+
+static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
+					unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		mm_compute_batch();
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block compute_batch_nb __meminitdata = {
+	.notifier_call = mm_compute_batch_notifier,
+	.priority = IPC_CALLBACK_PRI, /* use lowest priority */
+};
+
+static int __init mm_compute_batch_init(void)
+{
+	mm_compute_batch();
+	register_hotmemory_notifier(&compute_batch_nb);
+
+	return 0;
+}
+
+__initcall(mm_compute_batch_init);
+
+#endif
+
 static int __init mm_sysfs_init(void)
 {
 	mm_kobj = kobject_create_and_add("mm", kernel_kobj);
diff --git a/mm/mmap.c b/mm/mmap.c
index f681e1842fad..8468ffd05bae 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -955,7 +955,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
 	if (is_mergeable_vma(vma, file, vm_flags) &&
 	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
 		pgoff_t vm_pglen;
-		vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+		vm_pglen = vma_pages(vma);
 		if (vma->vm_pgoff + vm_pglen == vm_pgoff)
 			return 1;
 	}
diff --git a/mm/mremap.c b/mm/mremap.c
index 463a25705ac6..3708655378e9 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -126,7 +126,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 			continue;
 		pte = ptep_get_and_clear(mm, old_addr, old_pte);
 		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
-		set_pte_at(mm, new_addr, new_pte, pte);
+		set_pte_at(mm, new_addr, new_pte, pte_mksoft_dirty(pte));
 	}
 
 	arch_leave_lazy_mmu_mode();
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index bdd3fa2fc73b..61107cf55bb3 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -137,20 +137,25 @@ static unsigned long __init free_low_memory_core_early(void)
 	return count;
 }
 
-static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
+static int reset_managed_pages_done __initdata;
+
+static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	/*
-	 * In free_area_init_core(), highmem zone's managed_pages is set to
-	 * present_pages, and bootmem allocator doesn't allocate from highmem
-	 * zones. So there's no need to recalculate managed_pages because all
-	 * highmem pages will be managed by the buddy system. Here highmem
-	 * zone also includes highmem movable zone.
-	 */
+	if (reset_managed_pages_done)
+		return;
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
-		if (!is_highmem(z))
-			z->managed_pages = 0;
+		z->managed_pages = 0;
+}
+
+void __init reset_all_zones_managed_pages(void)
+{
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_managed_pages(pgdat);
+	reset_managed_pages_done = 1;
 }
 
 /**
@@ -160,17 +165,19 @@ static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
  */
 unsigned long __init free_all_bootmem(void)
 {
-	struct pglist_data *pgdat;
+	unsigned long pages;
 
-	for_each_online_pgdat(pgdat)
-		reset_node_lowmem_managed_pages(pgdat);
+	reset_all_zones_managed_pages();
 
 	/*
 	 * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
 	 *  because in some case like Node0 doesn't have RAM installed
 	 *  low ram will be on Node1
 	 */
-	return free_low_memory_core_early();
+	pages = free_low_memory_core_early();
+	totalram_pages += pages;
+
+	return pages;
 }
 
 /**
diff --git a/mm/nommu.c b/mm/nommu.c
index 298884dcd6e7..e44e6e0a125c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -56,7 +56,6 @@
 void *high_memory;
 struct page *mem_map;
 unsigned long max_mapnr;
-unsigned long num_physpages;
 unsigned long highest_memmap_pfn;
 struct percpu_counter vm_committed_as;
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
@@ -85,7 +84,6 @@ unsigned long vm_memory_committed(void)
 EXPORT_SYMBOL_GPL(vm_memory_committed);
 
 EXPORT_SYMBOL(mem_map);
-EXPORT_SYMBOL(num_physpages);
 
 /* list of mapped, potentially shareable regions */
 static struct kmem_cache *vm_region_jar;
@@ -282,6 +280,10 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
 
 long vread(char *buf, char *addr, unsigned long count)
 {
+	/* Don't allow overflow */
+	if ((unsigned long) buf + count < count)
+		count = -(unsigned long) buf;
+
 	memcpy(buf, addr, count);
 	return count;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c3edb624fccf..327516b7aee9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -61,10 +61,14 @@
 #include <linux/hugetlb.h>
 #include <linux/sched/rt.h>
 
+#include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
 #include "internal.h"
 
+/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
+static DEFINE_MUTEX(pcp_batch_high_lock);
+
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -100,6 +104,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
 };
 EXPORT_SYMBOL(node_states);
 
+/* Protect totalram_pages and zone->managed_pages */
+static DEFINE_SPINLOCK(managed_page_count_lock);
+
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
 /*
@@ -739,14 +746,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	local_irq_restore(flags);
 }
 
-/*
- * Read access to zone->managed_pages is safe because it's unsigned long,
- * but we still need to serialize writers. Currently all callers of
- * __free_pages_bootmem() except put_page_bootmem() should only be used
- * at boot time. So for shorter boot time, we shift the burden to
- * put_page_bootmem() to serialize writers.
- */
-void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
+void __init __free_pages_bootmem(struct page *page, unsigned int order)
 {
 	unsigned int nr_pages = 1 << order;
 	unsigned int loop;
@@ -781,11 +781,7 @@ void __init init_cma_reserved_pageblock(struct page *page)
 	set_page_refcounted(page);
 	set_pageblock_migratetype(page, MIGRATE_CMA);
 	__free_pages(page, pageblock_order);
-	totalram_pages += pageblock_nr_pages;
-#ifdef CONFIG_HIGHMEM
-	if (PageHighMem(page))
-		totalhigh_pages += pageblock_nr_pages;
-#endif
+	adjust_managed_page_count(page, pageblock_nr_pages);
 }
 #endif
 
@@ -1179,10 +1175,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
 	unsigned long flags;
 	int to_drain;
+	unsigned long batch;
 
 	local_irq_save(flags);
-	if (pcp->count >= pcp->batch)
-		to_drain = pcp->batch;
+	batch = ACCESS_ONCE(pcp->batch);
+	if (pcp->count >= batch)
+		to_drain = batch;
 	else
 		to_drain = pcp->count;
 	if (to_drain > 0) {
@@ -1350,8 +1348,9 @@ void free_hot_cold_page(struct page *page, int cold)
 		list_add(&page->lru, &pcp->lists[migratetype]);
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
-		free_pcppages_bulk(zone, pcp->batch, pcp);
-		pcp->count -= pcp->batch;
+		unsigned long batch = ACCESS_ONCE(pcp->batch);
+		free_pcppages_bulk(zone, batch, pcp);
+		pcp->count -= batch;
 	}
 
 out:
@@ -2839,7 +2838,7 @@ EXPORT_SYMBOL(free_pages_exact);
  * nr_free_zone_pages() counts the number of counts pages which are beyond the
  * high watermark within all zones at or below a given zone index.  For each
  * zone, the number of pages is calculated as:
- *     present_pages - high_pages
+ *     managed_pages - high_pages
  */
 static unsigned long nr_free_zone_pages(int offset)
 {
@@ -2906,9 +2905,13 @@ EXPORT_SYMBOL(si_meminfo);
 #ifdef CONFIG_NUMA
 void si_meminfo_node(struct sysinfo *val, int nid)
 {
+	int zone_type;		/* needs to be signed */
+	unsigned long managed_pages = 0;
 	pg_data_t *pgdat = NODE_DATA(nid);
 
-	val->totalram = pgdat->node_present_pages;
+	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
+		managed_pages += pgdat->node_zones[zone_type].managed_pages;
+	val->totalram = managed_pages;
 	val->freeram = node_page_state(nid, NR_FREE_PAGES);
 #ifdef CONFIG_HIGHMEM
 	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages;
@@ -3250,18 +3253,25 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 	static DEFINE_MUTEX(zl_order_mutex);
 
 	mutex_lock(&zl_order_mutex);
-	if (write)
-		strcpy(saved_string, (char*)table->data);
+	if (write) {
+		if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) {
+			ret = -EINVAL;
+			goto out;
+		}
+		strcpy(saved_string, (char *)table->data);
+	}
 	ret = proc_dostring(table, write, buffer, length, ppos);
 	if (ret)
 		goto out;
 	if (write) {
 		int oldval = user_zonelist_order;
-		if (__parse_numa_zonelist_order((char*)table->data)) {
+
+		ret = __parse_numa_zonelist_order((char *)table->data);
+		if (ret) {
 			/*
 			 * bogus value.  restore saved string
 			 */
-			strncpy((char*)table->data, saved_string,
+			strncpy((char *)table->data, saved_string,
 				NUMA_ZONELIST_ORDER_LEN);
 			user_zonelist_order = oldval;
 		} else if (oldval != user_zonelist_order) {
@@ -3425,8 +3435,8 @@ static int default_zonelist_order(void)
 			z = &NODE_DATA(nid)->node_zones[zone_type];
 			if (populated_zone(z)) {
 				if (zone_type < ZONE_NORMAL)
-					low_kmem_size += z->present_pages;
-				total_size += z->present_pages;
+					low_kmem_size += z->managed_pages;
+				total_size += z->managed_pages;
 			} else if (zone_type == ZONE_NORMAL) {
 				/*
 				 * If any node has only lowmem, then node order
@@ -3705,12 +3715,12 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 		mminit_verify_zonelist();
 		cpuset_init_current_mems_allowed();
 	} else {
-		/* we have to stop all cpus to guarantee there is no user
-		   of zonelist */
 #ifdef CONFIG_MEMORY_HOTPLUG
 		if (zone)
 			setup_zone_pageset(zone);
 #endif
+		/* we have to stop all cpus to guarantee there is no user
+		   of zonelist */
 		stop_machine(__build_all_zonelists, pgdat, NULL);
 		/* cpuset refresh routine should be here */
 	}
@@ -4032,7 +4042,40 @@ static int __meminit zone_batchsize(struct zone *zone)
 #endif
 }
 
-static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+/*
+ * pcp->high and pcp->batch values are related and dependent on one another:
+ * ->batch must never be higher then ->high.
+ * The following function updates them in a safe manner without read side
+ * locking.
+ *
+ * Any new users of pcp->batch and pcp->high should ensure they can cope with
+ * those fields changing asynchronously (acording the the above rule).
+ *
+ * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
+ * outside of boot time (or some other assurance that no concurrent updaters
+ * exist).
+ */
+static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
+		unsigned long batch)
+{
+       /* start with a fail safe value for batch */
+	pcp->batch = 1;
+	smp_wmb();
+
+       /* Update high, then batch, in order */
+	pcp->high = high;
+	smp_wmb();
+
+	pcp->batch = batch;
+}
+
+/* a companion to pageset_set_high() */
+static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
+{
+	pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
+}
+
+static void pageset_init(struct per_cpu_pageset *p)
 {
 	struct per_cpu_pages *pcp;
 	int migratetype;
@@ -4041,45 +4084,55 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
 
 	pcp = &p->pcp;
 	pcp->count = 0;
-	pcp->high = 6 * batch;
-	pcp->batch = max(1UL, 1 * batch);
 	for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
 		INIT_LIST_HEAD(&pcp->lists[migratetype]);
 }
 
+static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+{
+	pageset_init(p);
+	pageset_set_batch(p, batch);
+}
+
 /*
- * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
+ * pageset_set_high() sets the high water mark for hot per_cpu_pagelist
  * to the value high for the pageset p.
  */
-
-static void setup_pagelist_highmark(struct per_cpu_pageset *p,
+static void pageset_set_high(struct per_cpu_pageset *p,
 				unsigned long high)
 {
-	struct per_cpu_pages *pcp;
+	unsigned long batch = max(1UL, high / 4);
+	if ((high / 4) > (PAGE_SHIFT * 8))
+		batch = PAGE_SHIFT * 8;
 
-	pcp = &p->pcp;
-	pcp->high = high;
-	pcp->batch = max(1UL, high/4);
-	if ((high/4) > (PAGE_SHIFT * 8))
-		pcp->batch = PAGE_SHIFT * 8;
+	pageset_update(&p->pcp, high, batch);
 }
 
-static void __meminit setup_zone_pageset(struct zone *zone)
+static void __meminit pageset_set_high_and_batch(struct zone *zone,
+		struct per_cpu_pageset *pcp)
 {
-	int cpu;
-
-	zone->pageset = alloc_percpu(struct per_cpu_pageset);
+	if (percpu_pagelist_fraction)
+		pageset_set_high(pcp,
+			(zone->managed_pages /
+				percpu_pagelist_fraction));
+	else
+		pageset_set_batch(pcp, zone_batchsize(zone));
+}
 
-	for_each_possible_cpu(cpu) {
-		struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
+static void __meminit zone_pageset_init(struct zone *zone, int cpu)
+{
+	struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
 
-		setup_pageset(pcp, zone_batchsize(zone));
+	pageset_init(pcp);
+	pageset_set_high_and_batch(zone, pcp);
+}
 
-		if (percpu_pagelist_fraction)
-			setup_pagelist_highmark(pcp,
-				(zone->managed_pages /
-					percpu_pagelist_fraction));
-	}
+static void __meminit setup_zone_pageset(struct zone *zone)
+{
+	int cpu;
+	zone->pageset = alloc_percpu(struct per_cpu_pageset);
+	for_each_possible_cpu(cpu)
+		zone_pageset_init(zone, cpu);
 }
 
 /*
@@ -5150,35 +5203,101 @@ early_param("movablecore", cmdline_parse_movablecore);
 
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
-unsigned long free_reserved_area(unsigned long start, unsigned long end,
-				 int poison, char *s)
+void adjust_managed_page_count(struct page *page, long count)
+{
+	spin_lock(&managed_page_count_lock);
+	page_zone(page)->managed_pages += count;
+	totalram_pages += count;
+#ifdef CONFIG_HIGHMEM
+	if (PageHighMem(page))
+		totalhigh_pages += count;
+#endif
+	spin_unlock(&managed_page_count_lock);
+}
+EXPORT_SYMBOL(adjust_managed_page_count);
+
+unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 {
-	unsigned long pages, pos;
+	void *pos;
+	unsigned long pages = 0;
 
-	pos = start = PAGE_ALIGN(start);
-	end &= PAGE_MASK;
-	for (pages = 0; pos < end; pos += PAGE_SIZE, pages++) {
-		if (poison)
-			memset((void *)pos, poison, PAGE_SIZE);
-		free_reserved_page(virt_to_page((void *)pos));
+	start = (void *)PAGE_ALIGN((unsigned long)start);
+	end = (void *)((unsigned long)end & PAGE_MASK);
+	for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
+		if ((unsigned int)poison <= 0xFF)
+			memset(pos, poison, PAGE_SIZE);
+		free_reserved_page(virt_to_page(pos));
 	}
 
 	if (pages && s)
-		pr_info("Freeing %s memory: %ldK (%lx - %lx)\n",
+		pr_info("Freeing %s memory: %ldK (%p - %p)\n",
 			s, pages << (PAGE_SHIFT - 10), start, end);
 
 	return pages;
 }
+EXPORT_SYMBOL(free_reserved_area);
 
 #ifdef	CONFIG_HIGHMEM
 void free_highmem_page(struct page *page)
 {
 	__free_reserved_page(page);
 	totalram_pages++;
+	page_zone(page)->managed_pages++;
 	totalhigh_pages++;
 }
 #endif
 
+
+void __init mem_init_print_info(const char *str)
+{
+	unsigned long physpages, codesize, datasize, rosize, bss_size;
+	unsigned long init_code_size, init_data_size;
+
+	physpages = get_num_physpages();
+	codesize = _etext - _stext;
+	datasize = _edata - _sdata;
+	rosize = __end_rodata - __start_rodata;
+	bss_size = __bss_stop - __bss_start;
+	init_data_size = __init_end - __init_begin;
+	init_code_size = _einittext - _sinittext;
+
+	/*
+	 * Detect special cases and adjust section sizes accordingly:
+	 * 1) .init.* may be embedded into .data sections
+	 * 2) .init.text.* may be out of [__init_begin, __init_end],
+	 *    please refer to arch/tile/kernel/vmlinux.lds.S.
+	 * 3) .rodata.* may be embedded into .text or .data sections.
+	 */
+#define adj_init_size(start, end, size, pos, adj) \
+	if (start <= pos && pos < end && size > adj) \
+		size -= adj;
+
+	adj_init_size(__init_begin, __init_end, init_data_size,
+		     _sinittext, init_code_size);
+	adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size);
+	adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size);
+	adj_init_size(_stext, _etext, codesize, __start_rodata, rosize);
+	adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize);
+
+#undef	adj_init_size
+
+	printk("Memory: %luK/%luK available "
+	       "(%luK kernel code, %luK rwdata, %luK rodata, "
+	       "%luK init, %luK bss, %luK reserved"
+#ifdef	CONFIG_HIGHMEM
+	       ", %luK highmem"
+#endif
+	       "%s%s)\n",
+	       nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10),
+	       codesize >> 10, datasize >> 10, rosize >> 10,
+	       (init_data_size + init_code_size) >> 10, bss_size >> 10,
+	       (physpages - totalram_pages) << (PAGE_SHIFT-10),
+#ifdef	CONFIG_HIGHMEM
+	       totalhigh_pages << (PAGE_SHIFT-10),
+#endif
+	       str ? ", " : "", str ? str : "");
+}
+
 /**
  * set_dma_reserve - set the specified number of pages reserved in the first zone
  * @new_dma_reserve: The number of pages to mark reserved
@@ -5540,7 +5659,6 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
  * cpu.  It is the fraction of total pages in each zone that a hot per cpu pagelist
  * can have before it gets flushed back to buddy allocator.
  */
-
 int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
@@ -5551,14 +5669,16 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
 	if (!write || (ret < 0))
 		return ret;
+
+	mutex_lock(&pcp_batch_high_lock);
 	for_each_populated_zone(zone) {
-		for_each_possible_cpu(cpu) {
-			unsigned long  high;
-			high = zone->managed_pages / percpu_pagelist_fraction;
-			setup_pagelist_highmark(
-				per_cpu_ptr(zone->pageset, cpu), high);
-		}
+		unsigned long  high;
+		high = zone->managed_pages / percpu_pagelist_fraction;
+		for_each_possible_cpu(cpu)
+			pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
+					 high);
 	}
+	mutex_unlock(&pcp_batch_high_lock);
 	return 0;
 }
 
@@ -6047,32 +6167,18 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-static int __meminit __zone_pcp_update(void *data)
-{
-	struct zone *zone = data;
-	int cpu;
-	unsigned long batch = zone_batchsize(zone), flags;
-
-	for_each_possible_cpu(cpu) {
-		struct per_cpu_pageset *pset;
-		struct per_cpu_pages *pcp;
-
-		pset = per_cpu_ptr(zone->pageset, cpu);
-		pcp = &pset->pcp;
-
-		local_irq_save(flags);
-		if (pcp->count > 0)
-			free_pcppages_bulk(zone, pcp->count, pcp);
-		drain_zonestat(zone, pset);
-		setup_pageset(pset, batch);
-		local_irq_restore(flags);
-	}
-	return 0;
-}
-
+/*
+ * The zone indicated has a new number of managed_pages; batch sizes and percpu
+ * page high values need to be recalulated.
+ */
 void __meminit zone_pcp_update(struct zone *zone)
 {
-	stop_machine(__zone_pcp_update, zone, NULL);
+	unsigned cpu;
+	mutex_lock(&pcp_batch_high_lock);
+	for_each_possible_cpu(cpu)
+		pageset_set_high_and_batch(zone,
+				per_cpu_ptr(zone->pageset, cpu));
+	mutex_unlock(&pcp_batch_high_lock);
 }
 #endif
 
@@ -6142,6 +6248,10 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		list_del(&page->lru);
 		rmv_page_order(page);
 		zone->free_area[order].nr_free--;
+#ifdef CONFIG_HIGHMEM
+		if (PageHighMem(page))
+			totalhigh_pages -= 1 << order;
+#endif
 		for (i = 0; i < (1 << order); i++)
 			SetPageReserved((page+i));
 		pfn += (1 << order);
diff --git a/mm/page_io.c b/mm/page_io.c
index a8a3ef45fed7..ba05b64e5d8d 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -21,6 +21,7 @@
 #include <linux/writeback.h>
 #include <linux/frontswap.h>
 #include <linux/aio.h>
+#include <linux/blkdev.h>
 #include <asm/pgtable.h>
 
 static struct bio *get_swap_bio(gfp_t gfp_flags,
@@ -80,9 +81,54 @@ void end_swap_bio_read(struct bio *bio, int err)
 				imajor(bio->bi_bdev->bd_inode),
 				iminor(bio->bi_bdev->bd_inode),
 				(unsigned long long)bio->bi_sector);
-	} else {
-		SetPageUptodate(page);
+		goto out;
 	}
+
+	SetPageUptodate(page);
+
+	/*
+	 * There is no guarantee that the page is in swap cache - the software
+	 * suspend code (at least) uses end_swap_bio_read() against a non-
+	 * swapcache page.  So we must check PG_swapcache before proceeding with
+	 * this optimization.
+	 */
+	if (likely(PageSwapCache(page))) {
+		struct swap_info_struct *sis;
+
+		sis = page_swap_info(page);
+		if (sis->flags & SWP_BLKDEV) {
+			/*
+			 * The swap subsystem performs lazy swap slot freeing,
+			 * expecting that the page will be swapped out again.
+			 * So we can avoid an unnecessary write if the page
+			 * isn't redirtied.
+			 * This is good for real swap storage because we can
+			 * reduce unnecessary I/O and enhance wear-leveling
+			 * if an SSD is used as the as swap device.
+			 * But if in-memory swap device (eg zram) is used,
+			 * this causes a duplicated copy between uncompressed
+			 * data in VM-owned memory and compressed data in
+			 * zram-owned memory.  So let's free zram-owned memory
+			 * and make the VM-owned decompressed page *dirty*,
+			 * so the page should be swapped out somewhere again if
+			 * we again wish to reclaim it.
+			 */
+			struct gendisk *disk = sis->bdev->bd_disk;
+			if (disk->fops->swap_slot_free_notify) {
+				swp_entry_t entry;
+				unsigned long offset;
+
+				entry.val = page_private(page);
+				offset = swp_offset(entry);
+
+				SetPageDirty(page);
+				disk->fops->swap_slot_free_notify(sis->bdev,
+						offset);
+			}
+		}
+	}
+
+out:
 	unlock_page(page);
 	bio_put(bio);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 6280da86b5d6..e22ceeb6e5ec 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1093,9 +1093,10 @@ void page_add_new_anon_rmap(struct page *page,
 	else
 		__inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
 	__page_set_anon_rmap(page, vma, address, 1);
-	if (!mlocked_vma_newpage(vma, page))
-		lru_cache_add_lru(page, LRU_ACTIVE_ANON);
-	else
+	if (!mlocked_vma_newpage(vma, page)) {
+		SetPageActive(page);
+		lru_cache_add(page);
+	} else
 		add_page_to_unevictable_list(page);
 }
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 1c91f0d3f6ab..3194ec414728 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -481,6 +481,9 @@ void __init sparse_init(void)
 	struct page **map_map;
 #endif
 
+	/* see include/linux/mmzone.h 'struct mem_section' definition */
+	BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section)));
+
 	/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
 	set_pageblock_order();
 
diff --git a/mm/swap.c b/mm/swap.c
index dfd7d71d6841..4a1d0d2c52fa 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -34,10 +34,13 @@
 
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/pagemap.h>
+
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
 
-static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
 static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
 static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
 
@@ -384,6 +387,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec,
 		SetPageActive(page);
 		lru += LRU_ACTIVE;
 		add_page_to_lru_list(page, lruvec, lru);
+		trace_mm_lru_activate(page, page_to_pfn(page));
 
 		__count_vm_event(PGACTIVATE);
 		update_page_reclaim_stat(lruvec, file, 1);
@@ -428,6 +432,33 @@ void activate_page(struct page *page)
 }
 #endif
 
+static void __lru_cache_activate_page(struct page *page)
+{
+	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+	int i;
+
+	/*
+	 * Search backwards on the optimistic assumption that the page being
+	 * activated has just been added to this pagevec. Note that only
+	 * the local pagevec is examined as a !PageLRU page could be in the
+	 * process of being released, reclaimed, migrated or on a remote
+	 * pagevec that is currently being drained. Furthermore, marking
+	 * a remote pagevec's page PageActive potentially hits a race where
+	 * a page is marked PageActive just after it is added to the inactive
+	 * list causing accounting errors and BUG_ON checks to trigger.
+	 */
+	for (i = pagevec_count(pvec) - 1; i >= 0; i--) {
+		struct page *pagevec_page = pvec->pages[i];
+
+		if (pagevec_page == page) {
+			SetPageActive(page);
+			break;
+		}
+	}
+
+	put_cpu_var(lru_add_pvec);
+}
+
 /*
  * Mark a page as having seen activity.
  *
@@ -438,8 +469,18 @@ void activate_page(struct page *page)
 void mark_page_accessed(struct page *page)
 {
 	if (!PageActive(page) && !PageUnevictable(page) &&
-			PageReferenced(page) && PageLRU(page)) {
-		activate_page(page);
+			PageReferenced(page)) {
+
+		/*
+		 * If the page is on the LRU, queue it for activation via
+		 * activate_page_pvecs. Otherwise, assume the page is on a
+		 * pagevec, mark it active and it'll be moved to the active
+		 * LRU on the next drain.
+		 */
+		if (PageLRU(page))
+			activate_page(page);
+		else
+			__lru_cache_activate_page(page);
 		ClearPageReferenced(page);
 	} else if (!PageReferenced(page)) {
 		SetPageReferenced(page);
@@ -448,42 +489,37 @@ void mark_page_accessed(struct page *page)
 EXPORT_SYMBOL(mark_page_accessed);
 
 /*
- * Order of operations is important: flush the pagevec when it's already
- * full, not when adding the last page, to make sure that last page is
- * not added to the LRU directly when passed to this function. Because
- * mark_page_accessed() (called after this when writing) only activates
- * pages that are on the LRU, linear writes in subpage chunks would see
- * every PAGEVEC_SIZE page activated, which is unexpected.
+ * Queue the page for addition to the LRU via pagevec. The decision on whether
+ * to add the page to the [in]active [file|anon] list is deferred until the
+ * pagevec is drained. This gives a chance for the caller of __lru_cache_add()
+ * have the page added to the active list using mark_page_accessed().
  */
-void __lru_cache_add(struct page *page, enum lru_list lru)
+void __lru_cache_add(struct page *page)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru];
+	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
 
 	page_cache_get(page);
 	if (!pagevec_space(pvec))
-		__pagevec_lru_add(pvec, lru);
+		__pagevec_lru_add(pvec);
 	pagevec_add(pvec, page);
-	put_cpu_var(lru_add_pvecs);
+	put_cpu_var(lru_add_pvec);
 }
 EXPORT_SYMBOL(__lru_cache_add);
 
 /**
- * lru_cache_add_lru - add a page to a page list
+ * lru_cache_add - add a page to a page list
  * @page: the page to be added to the LRU.
- * @lru: the LRU list to which the page is added.
  */
-void lru_cache_add_lru(struct page *page, enum lru_list lru)
+void lru_cache_add(struct page *page)
 {
 	if (PageActive(page)) {
 		VM_BUG_ON(PageUnevictable(page));
-		ClearPageActive(page);
 	} else if (PageUnevictable(page)) {
 		VM_BUG_ON(PageActive(page));
-		ClearPageUnevictable(page);
 	}
 
-	VM_BUG_ON(PageLRU(page) || PageActive(page) || PageUnevictable(page));
-	__lru_cache_add(page, lru);
+	VM_BUG_ON(PageLRU(page));
+	__lru_cache_add(page);
 }
 
 /**
@@ -583,15 +619,10 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
  */
 void lru_add_drain_cpu(int cpu)
 {
-	struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu);
-	struct pagevec *pvec;
-	int lru;
+	struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);
 
-	for_each_lru(lru) {
-		pvec = &pvecs[lru - LRU_BASE];
-		if (pagevec_count(pvec))
-			__pagevec_lru_add(pvec, lru);
-	}
+	if (pagevec_count(pvec))
+		__pagevec_lru_add(pvec);
 
 	pvec = &per_cpu(lru_rotate_pvecs, cpu);
 	if (pagevec_count(pvec)) {
@@ -708,6 +739,9 @@ void release_pages(struct page **pages, int nr, int cold)
 			del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		}
 
+		/* Clear Active bit in case of parallel mark_page_accessed */
+		ClearPageActive(page);
+
 		list_add(&page->lru, &pages_to_free);
 	}
 	if (zone)
@@ -795,30 +829,26 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
 static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
 				 void *arg)
 {
-	enum lru_list lru = (enum lru_list)arg;
-	int file = is_file_lru(lru);
-	int active = is_active_lru(lru);
+	int file = page_is_file_cache(page);
+	int active = PageActive(page);
+	enum lru_list lru = page_lru(page);
 
-	VM_BUG_ON(PageActive(page));
 	VM_BUG_ON(PageUnevictable(page));
 	VM_BUG_ON(PageLRU(page));
 
 	SetPageLRU(page);
-	if (active)
-		SetPageActive(page);
 	add_page_to_lru_list(page, lruvec, lru);
 	update_page_reclaim_stat(lruvec, file, active);
+	trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page));
 }
 
 /*
  * Add the passed pages to the LRU, then drop the caller's refcount
  * on them.  Reinitialises the caller's pagevec.
  */
-void __pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
+void __pagevec_lru_add(struct pagevec *pvec)
 {
-	VM_BUG_ON(is_unevictable_lru(lru));
-
-	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, (void *)lru);
+	pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL);
 }
 EXPORT_SYMBOL(__pagevec_lru_add);
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 746af55b8455..36af6eeaa67e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -212,7 +212,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 			si->cluster_nr = SWAPFILE_CLUSTER - 1;
 			goto checks;
 		}
-		if (si->flags & SWP_DISCARDABLE) {
+		if (si->flags & SWP_PAGE_DISCARD) {
 			/*
 			 * Start range check on racing allocations, in case
 			 * they overlap the cluster we eventually decide on
@@ -322,7 +322,7 @@ checks:
 
 	if (si->lowest_alloc) {
 		/*
-		 * Only set when SWP_DISCARDABLE, and there's a scan
+		 * Only set when SWP_PAGE_DISCARD, and there's a scan
 		 * for a free cluster in progress or just completed.
 		 */
 		if (found_free_cluster) {
@@ -2016,6 +2016,20 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	return nr_extents;
 }
 
+/*
+ * Helper to sys_swapon determining if a given swap
+ * backing device queue supports DISCARD operations.
+ */
+static bool swap_discardable(struct swap_info_struct *si)
+{
+	struct request_queue *q = bdev_get_queue(si->bdev);
+
+	if (!q || !blk_queue_discard(q))
+		return false;
+
+	return true;
+}
+
 SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 {
 	struct swap_info_struct *p;
@@ -2123,8 +2137,37 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			p->flags |= SWP_SOLIDSTATE;
 			p->cluster_next = 1 + (prandom_u32() % p->highest_bit);
 		}
-		if ((swap_flags & SWAP_FLAG_DISCARD) && discard_swap(p) == 0)
-			p->flags |= SWP_DISCARDABLE;
+
+		if ((swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
+			/*
+			 * When discard is enabled for swap with no particular
+			 * policy flagged, we set all swap discard flags here in
+			 * order to sustain backward compatibility with older
+			 * swapon(8) releases.
+			 */
+			p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD |
+				     SWP_PAGE_DISCARD);
+
+			/*
+			 * By flagging sys_swapon, a sysadmin can tell us to
+			 * either do single-time area discards only, or to just
+			 * perform discards for released swap page-clusters.
+			 * Now it's time to adjust the p->flags accordingly.
+			 */
+			if (swap_flags & SWAP_FLAG_DISCARD_ONCE)
+				p->flags &= ~SWP_PAGE_DISCARD;
+			else if (swap_flags & SWAP_FLAG_DISCARD_PAGES)
+				p->flags &= ~SWP_AREA_DISCARD;
+
+			/* issue a swapon-time discard if it's still required */
+			if (p->flags & SWP_AREA_DISCARD) {
+				int err = discard_swap(p);
+				if (unlikely(err))
+					printk(KERN_ERR
+					       "swapon: discard_swap(%p): %d\n",
+						p, err);
+			}
+		}
 	}
 
 	mutex_lock(&swapon_mutex);
@@ -2135,11 +2178,13 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	enable_swap_info(p, prio, swap_map, frontswap_map);
 
 	printk(KERN_INFO "Adding %uk swap on %s.  "
-			"Priority:%d extents:%d across:%lluk %s%s%s\n",
+			"Priority:%d extents:%d across:%lluk %s%s%s%s%s\n",
 		p->pages<<(PAGE_SHIFT-10), name->name, p->prio,
 		nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
 		(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
 		(p->flags & SWP_DISCARDABLE) ? "D" : "",
+		(p->flags & SWP_AREA_DISCARD) ? "s" : "",
+		(p->flags & SWP_PAGE_DISCARD) ? "c" : "",
 		(frontswap_map) ? "FS" : "");
 
 	mutex_unlock(&swapon_mutex);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d365724feb05..91a10472a39a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -292,7 +292,7 @@ static struct vmap_area *__find_vmap_area(unsigned long addr)
 		va = rb_entry(n, struct vmap_area, rb_node);
 		if (addr < va->va_start)
 			n = n->rb_left;
-		else if (addr > va->va_start)
+		else if (addr >= va->va_end)
 			n = n->rb_right;
 		else
 			return va;
@@ -1322,13 +1322,6 @@ static void clear_vm_unlist(struct vm_struct *vm)
 	vm->flags &= ~VM_UNLIST;
 }
 
-static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
-			      unsigned long flags, const void *caller)
-{
-	setup_vmalloc_vm(vm, va, flags, caller);
-	clear_vm_unlist(vm);
-}
-
 static struct vm_struct *__get_vm_area_node(unsigned long size,
 		unsigned long align, unsigned long flags, unsigned long start,
 		unsigned long end, int node, gfp_t gfp_mask, const void *caller)
@@ -1337,16 +1330,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 	struct vm_struct *area;
 
 	BUG_ON(in_interrupt());
-	if (flags & VM_IOREMAP) {
-		int bit = fls(size);
-
-		if (bit > IOREMAP_MAX_ORDER)
-			bit = IOREMAP_MAX_ORDER;
-		else if (bit < PAGE_SHIFT)
-			bit = PAGE_SHIFT;
-
-		align = 1ul << bit;
-	}
+	if (flags & VM_IOREMAP)
+		align = 1ul << clamp(fls(size), PAGE_SHIFT, IOREMAP_MAX_ORDER);
 
 	size = PAGE_ALIGN(size);
 	if (unlikely(!size))
@@ -1367,16 +1352,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 		return NULL;
 	}
 
-	/*
-	 * When this function is called from __vmalloc_node_range,
-	 * we add VM_UNLIST flag to avoid accessing uninitialized
-	 * members of vm_struct such as pages and nr_pages fields.
-	 * They will be set later.
-	 */
-	if (flags & VM_UNLIST)
-		setup_vmalloc_vm(area, va, flags, caller);
-	else
-		insert_vmalloc_vm(area, va, flags, caller);
+	setup_vmalloc_vm(area, va, flags, caller);
 
 	return area;
 }
@@ -1476,10 +1452,9 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	if (!addr)
 		return;
 
-	if ((PAGE_SIZE-1) & (unsigned long)addr) {
-		WARN(1, KERN_ERR "Trying to vfree() bad address (%p)\n", addr);
+	if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
+			addr));
 		return;
-	}
 
 	area = remove_vm_area(addr);
 	if (unlikely(!area)) {
@@ -2148,42 +2123,43 @@ finished:
 }
 
 /**
- *	remap_vmalloc_range  -  map vmalloc pages to userspace
- *	@vma:		vma to cover (map full range of vma)
- *	@addr:		vmalloc memory
- *	@pgoff:		number of pages into addr before first page to map
+ *	remap_vmalloc_range_partial  -  map vmalloc pages to userspace
+ *	@vma:		vma to cover
+ *	@uaddr:		target user address to start at
+ *	@kaddr:		virtual address of vmalloc kernel memory
+ *	@size:		size of map area
  *
  *	Returns:	0 for success, -Exxx on failure
  *
- *	This function checks that addr is a valid vmalloc'ed area, and
- *	that it is big enough to cover the vma. Will return failure if
- *	that criteria isn't met.
+ *	This function checks that @kaddr is a valid vmalloc'ed area,
+ *	and that it is big enough to cover the range starting at
+ *	@uaddr in @vma. Will return failure if that criteria isn't
+ *	met.
  *
  *	Similar to remap_pfn_range() (see mm/memory.c)
  */
-int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
-						unsigned long pgoff)
+int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
+				void *kaddr, unsigned long size)
 {
 	struct vm_struct *area;
-	unsigned long uaddr = vma->vm_start;
-	unsigned long usize = vma->vm_end - vma->vm_start;
 
-	if ((PAGE_SIZE-1) & (unsigned long)addr)
+	size = PAGE_ALIGN(size);
+
+	if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr))
 		return -EINVAL;
 
-	area = find_vm_area(addr);
+	area = find_vm_area(kaddr);
 	if (!area)
 		return -EINVAL;
 
 	if (!(area->flags & VM_USERMAP))
 		return -EINVAL;
 
-	if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE)
+	if (kaddr + size > area->addr + area->size)
 		return -EINVAL;
 
-	addr += pgoff << PAGE_SHIFT;
 	do {
-		struct page *page = vmalloc_to_page(addr);
+		struct page *page = vmalloc_to_page(kaddr);
 		int ret;
 
 		ret = vm_insert_page(vma, uaddr, page);
@@ -2191,14 +2167,37 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 			return ret;
 
 		uaddr += PAGE_SIZE;
-		addr += PAGE_SIZE;
-		usize -= PAGE_SIZE;
-	} while (usize > 0);
+		kaddr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	} while (size > 0);
 
 	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
 
 	return 0;
 }
+EXPORT_SYMBOL(remap_vmalloc_range_partial);
+
+/**
+ *	remap_vmalloc_range  -  map vmalloc pages to userspace
+ *	@vma:		vma to cover (map full range of vma)
+ *	@addr:		vmalloc memory
+ *	@pgoff:		number of pages into addr before first page to map
+ *
+ *	Returns:	0 for success, -Exxx on failure
+ *
+ *	This function checks that addr is a valid vmalloc'ed area, and
+ *	that it is big enough to cover the vma. Will return failure if
+ *	that criteria isn't met.
+ *
+ *	Similar to remap_pfn_range() (see mm/memory.c)
+ */
+int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
+						unsigned long pgoff)
+{
+	return remap_vmalloc_range_partial(vma, vma->vm_start,
+					   addr + (pgoff << PAGE_SHIFT),
+					   vma->vm_end - vma->vm_start);
+}
 EXPORT_SYMBOL(remap_vmalloc_range);
 
 /*
@@ -2512,8 +2511,8 @@ found:
 
 	/* insert all vm's */
 	for (area = 0; area < nr_vms; area++)
-		insert_vmalloc_vm(vms[area], vas[area], VM_ALLOC,
-				  pcpu_get_vm_areas);
+		setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC,
+				 pcpu_get_vm_areas);
 
 	kfree(vas);
 	return vms;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fa6a85378ee4..99b3ac7771ad 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -546,7 +546,6 @@ int remove_mapping(struct address_space *mapping, struct page *page)
 void putback_lru_page(struct page *page)
 {
 	int lru;
-	int active = !!TestClearPageActive(page);
 	int was_unevictable = PageUnevictable(page);
 
 	VM_BUG_ON(PageLRU(page));
@@ -561,8 +560,8 @@ redo:
 		 * unevictable page on [in]active list.
 		 * We know how to handle that.
 		 */
-		lru = active + page_lru_base_type(page);
-		lru_cache_add_lru(page, lru);
+		lru = page_lru_base_type(page);
+		lru_cache_add(page);
 	} else {
 		/*
 		 * Put unevictable pages directly on zone's unevictable
@@ -669,6 +668,35 @@ static enum page_references page_check_references(struct page *page,
 	return PAGEREF_RECLAIM;
 }
 
+/* Check if a page is dirty or under writeback */
+static void page_check_dirty_writeback(struct page *page,
+				       bool *dirty, bool *writeback)
+{
+	struct address_space *mapping;
+
+	/*
+	 * Anonymous pages are not handled by flushers and must be written
+	 * from reclaim context. Do not stall reclaim based on them
+	 */
+	if (!page_is_file_cache(page)) {
+		*dirty = false;
+		*writeback = false;
+		return;
+	}
+
+	/* By default assume that the page flags are accurate */
+	*dirty = PageDirty(page);
+	*writeback = PageWriteback(page);
+
+	/* Verify dirty/writeback state if the filesystem supports it */
+	if (!page_has_private(page))
+		return;
+
+	mapping = page_mapping(page);
+	if (mapping && mapping->a_ops->is_dirty_writeback)
+		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
+}
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -677,16 +705,21 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				      struct scan_control *sc,
 				      enum ttu_flags ttu_flags,
 				      unsigned long *ret_nr_dirty,
+				      unsigned long *ret_nr_unqueued_dirty,
+				      unsigned long *ret_nr_congested,
 				      unsigned long *ret_nr_writeback,
+				      unsigned long *ret_nr_immediate,
 				      bool force_reclaim)
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
 	int pgactivate = 0;
+	unsigned long nr_unqueued_dirty = 0;
 	unsigned long nr_dirty = 0;
 	unsigned long nr_congested = 0;
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_writeback = 0;
+	unsigned long nr_immediate = 0;
 
 	cond_resched();
 
@@ -696,6 +729,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		struct page *page;
 		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM_CLEAN;
+		bool dirty, writeback;
 
 		cond_resched();
 
@@ -723,25 +757,77 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
 			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
 
+		/*
+		 * The number of dirty pages determines if a zone is marked
+		 * reclaim_congested which affects wait_iff_congested. kswapd
+		 * will stall and start writing pages if the tail of the LRU
+		 * is all dirty unqueued pages.
+		 */
+		page_check_dirty_writeback(page, &dirty, &writeback);
+		if (dirty || writeback)
+			nr_dirty++;
+
+		if (dirty && !writeback)
+			nr_unqueued_dirty++;
+
+		/*
+		 * Treat this page as congested if the underlying BDI is or if
+		 * pages are cycling through the LRU so quickly that the
+		 * pages marked for immediate reclaim are making it to the
+		 * end of the LRU a second time.
+		 */
+		mapping = page_mapping(page);
+		if ((mapping && bdi_write_congested(mapping->backing_dev_info)) ||
+		    (writeback && PageReclaim(page)))
+			nr_congested++;
+
+		/*
+		 * If a page at the tail of the LRU is under writeback, there
+		 * are three cases to consider.
+		 *
+		 * 1) If reclaim is encountering an excessive number of pages
+		 *    under writeback and this page is both under writeback and
+		 *    PageReclaim then it indicates that pages are being queued
+		 *    for IO but are being recycled through the LRU before the
+		 *    IO can complete. Waiting on the page itself risks an
+		 *    indefinite stall if it is impossible to writeback the
+		 *    page due to IO error or disconnected storage so instead
+		 *    note that the LRU is being scanned too quickly and the
+		 *    caller can stall after page list has been processed.
+		 *
+		 * 2) Global reclaim encounters a page, memcg encounters a
+		 *    page that is not marked for immediate reclaim or
+		 *    the caller does not have __GFP_IO. In this case mark
+		 *    the page for immediate reclaim and continue scanning.
+		 *
+		 *    __GFP_IO is checked  because a loop driver thread might
+		 *    enter reclaim, and deadlock if it waits on a page for
+		 *    which it is needed to do the write (loop masks off
+		 *    __GFP_IO|__GFP_FS for this reason); but more thought
+		 *    would probably show more reasons.
+		 *
+		 *    Don't require __GFP_FS, since we're not going into the
+		 *    FS, just waiting on its writeback completion. Worryingly,
+		 *    ext4 gfs2 and xfs allocate pages with
+		 *    grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing
+		 *    may_enter_fs here is liable to OOM on them.
+		 *
+		 * 3) memcg encounters a page that is not already marked
+		 *    PageReclaim. memcg does not have any dirty pages
+		 *    throttling so we could easily OOM just because too many
+		 *    pages are in writeback and there is nothing else to
+		 *    reclaim. Wait for the writeback to complete.
+		 */
 		if (PageWriteback(page)) {
-			/*
-			 * memcg doesn't have any dirty pages throttling so we
-			 * could easily OOM just because too many pages are in
-			 * writeback and there is nothing else to reclaim.
-			 *
-			 * Check __GFP_IO, certainly because a loop driver
-			 * thread might enter reclaim, and deadlock if it waits
-			 * on a page for which it is needed to do the write
-			 * (loop masks off __GFP_IO|__GFP_FS for this reason);
-			 * but more thought would probably show more reasons.
-			 *
-			 * Don't require __GFP_FS, since we're not going into
-			 * the FS, just waiting on its writeback completion.
-			 * Worryingly, ext4 gfs2 and xfs allocate pages with
-			 * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so
-			 * testing may_enter_fs here is liable to OOM on them.
-			 */
-			if (global_reclaim(sc) ||
+			/* Case 1 above */
+			if (current_is_kswapd() &&
+			    PageReclaim(page) &&
+			    zone_is_reclaim_writeback(zone)) {
+				nr_immediate++;
+				goto keep_locked;
+
+			/* Case 2 above */
+			} else if (global_reclaim(sc) ||
 			    !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
 				/*
 				 * This is slightly racy - end_page_writeback()
@@ -756,9 +842,13 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				 */
 				SetPageReclaim(page);
 				nr_writeback++;
+
 				goto keep_locked;
+
+			/* Case 3 above */
+			} else {
+				wait_on_page_writeback(page);
 			}
-			wait_on_page_writeback(page);
 		}
 
 		if (!force_reclaim)
@@ -784,9 +874,10 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			if (!add_to_swap(page, page_list))
 				goto activate_locked;
 			may_enter_fs = 1;
-		}
 
-		mapping = page_mapping(page);
+			/* Adding to swap updated mapping */
+			mapping = page_mapping(page);
+		}
 
 		/*
 		 * The page is mapped into the page tables of one or more
@@ -806,16 +897,14 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (PageDirty(page)) {
-			nr_dirty++;
-
 			/*
 			 * Only kswapd can writeback filesystem pages to
-			 * avoid risk of stack overflow but do not writeback
-			 * unless under significant pressure.
+			 * avoid risk of stack overflow but only writeback
+			 * if many dirty pages have been encountered.
 			 */
 			if (page_is_file_cache(page) &&
 					(!current_is_kswapd() ||
-					 sc->priority >= DEF_PRIORITY - 2)) {
+					 !zone_is_reclaim_dirty(zone))) {
 				/*
 				 * Immediately reclaim when written back.
 				 * Similar in principal to deactivate_page()
@@ -838,7 +927,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			/* Page is dirty, try to write it out here */
 			switch (pageout(page, mapping, sc)) {
 			case PAGE_KEEP:
-				nr_congested++;
 				goto keep_locked;
 			case PAGE_ACTIVATE:
 				goto activate_locked;
@@ -946,22 +1034,16 @@ keep:
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
 
-	/*
-	 * Tag a zone as congested if all the dirty pages encountered were
-	 * backed by a congested BDI. In this case, reclaimers should just
-	 * back off and wait for congestion to clear because further reclaim
-	 * will encounter the same problem
-	 */
-	if (nr_dirty && nr_dirty == nr_congested && global_reclaim(sc))
-		zone_set_flag(zone, ZONE_CONGESTED);
-
 	free_hot_cold_page_list(&free_pages, 1);
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 	mem_cgroup_uncharge_end();
 	*ret_nr_dirty += nr_dirty;
+	*ret_nr_congested += nr_congested;
+	*ret_nr_unqueued_dirty += nr_unqueued_dirty;
 	*ret_nr_writeback += nr_writeback;
+	*ret_nr_immediate += nr_immediate;
 	return nr_reclaimed;
 }
 
@@ -973,7 +1055,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 		.priority = DEF_PRIORITY,
 		.may_unmap = 1,
 	};
-	unsigned long ret, dummy1, dummy2;
+	unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5;
 	struct page *page, *next;
 	LIST_HEAD(clean_pages);
 
@@ -985,8 +1067,8 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 	}
 
 	ret = shrink_page_list(&clean_pages, zone, &sc,
-				TTU_UNMAP|TTU_IGNORE_ACCESS,
-				&dummy1, &dummy2, true);
+			TTU_UNMAP|TTU_IGNORE_ACCESS,
+			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
 	list_splice(&clean_pages, page_list);
 	__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
 	return ret;
@@ -1281,7 +1363,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_taken;
 	unsigned long nr_dirty = 0;
+	unsigned long nr_congested = 0;
+	unsigned long nr_unqueued_dirty = 0;
 	unsigned long nr_writeback = 0;
+	unsigned long nr_immediate = 0;
 	isolate_mode_t isolate_mode = 0;
 	int file = is_file_lru(lru);
 	struct zone *zone = lruvec_zone(lruvec);
@@ -1323,7 +1408,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		return 0;
 
 	nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP,
-					&nr_dirty, &nr_writeback, false);
+				&nr_dirty, &nr_unqueued_dirty, &nr_congested,
+				&nr_writeback, &nr_immediate,
+				false);
 
 	spin_lock_irq(&zone->lru_lock);
 
@@ -1357,7 +1444,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * same way balance_dirty_pages() manages.
 	 *
 	 * This scales the number of dirty pages that must be under writeback
-	 * before throttling depending on priority. It is a simple backoff
+	 * before a zone gets flagged ZONE_WRITEBACK. It is a simple backoff
 	 * function that has the most effect in the range DEF_PRIORITY to
 	 * DEF_PRIORITY-2 which is the priority reclaim is considered to be
 	 * in trouble and reclaim is considered to be in trouble.
@@ -1368,9 +1455,53 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * ...
 	 * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any
 	 *                     isolated page is PageWriteback
+	 *
+	 * Once a zone is flagged ZONE_WRITEBACK, kswapd will count the number
+	 * of pages under pages flagged for immediate reclaim and stall if any
+	 * are encountered in the nr_immediate check below.
 	 */
 	if (nr_writeback && nr_writeback >=
 			(nr_taken >> (DEF_PRIORITY - sc->priority)))
+		zone_set_flag(zone, ZONE_WRITEBACK);
+
+	/*
+	 * memcg will stall in page writeback so only consider forcibly
+	 * stalling for global reclaim
+	 */
+	if (global_reclaim(sc)) {
+		/*
+		 * Tag a zone as congested if all the dirty pages scanned were
+		 * backed by a congested BDI and wait_iff_congested will stall.
+		 */
+		if (nr_dirty && nr_dirty == nr_congested)
+			zone_set_flag(zone, ZONE_CONGESTED);
+
+		/*
+		 * If dirty pages are scanned that are not queued for IO, it
+		 * implies that flushers are not keeping up. In this case, flag
+		 * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
+		 * pages from reclaim context. It will forcibly stall in the
+		 * next check.
+		 */
+		if (nr_unqueued_dirty == nr_taken)
+			zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
+
+		/*
+		 * In addition, if kswapd scans pages marked marked for
+		 * immediate reclaim and under writeback (nr_immediate), it
+		 * implies that pages are cycling through the LRU faster than
+		 * they are written so also forcibly stall.
+		 */
+		if (nr_unqueued_dirty == nr_taken || nr_immediate)
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
+	}
+
+	/*
+	 * Stall direct reclaim for IO completions if underlying BDIs or zone
+	 * is congested. Allow kswapd to continue until it starts encountering
+	 * unqueued dirty pages or cycling through the LRU too quickly.
+	 */
+	if (!sc->hibernation_mode && !current_is_kswapd())
 		wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
 
 	trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
@@ -1822,17 +1953,25 @@ out:
 static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	unsigned long nr[NR_LRU_LISTS];
+	unsigned long targets[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
 	enum lru_list lru;
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct blk_plug plug;
+	bool scan_adjusted = false;
 
 	get_scan_count(lruvec, sc, nr);
 
+	/* Record the original scan target for proportional adjustments later */
+	memcpy(targets, nr, sizeof(nr));
+
 	blk_start_plug(&plug);
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
+		unsigned long nr_anon, nr_file, percentage;
+		unsigned long nr_scanned;
+
 		for_each_evictable_lru(lru) {
 			if (nr[lru]) {
 				nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
@@ -1842,17 +1981,60 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 							    lruvec, sc);
 			}
 		}
+
+		if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
+			continue;
+
 		/*
-		 * On large memory systems, scan >> priority can become
-		 * really large. This is fine for the starting priority;
-		 * we want to put equal scanning pressure on each zone.
-		 * However, if the VM has a harder time of freeing pages,
-		 * with multiple processes reclaiming pages, the total
-		 * freeing target can get unreasonably large.
+		 * For global direct reclaim, reclaim only the number of pages
+		 * requested. Less care is taken to scan proportionally as it
+		 * is more important to minimise direct reclaim stall latency
+		 * than it is to properly age the LRU lists.
 		 */
-		if (nr_reclaimed >= nr_to_reclaim &&
-		    sc->priority < DEF_PRIORITY)
+		if (global_reclaim(sc) && !current_is_kswapd())
 			break;
+
+		/*
+		 * For kswapd and memcg, reclaim at least the number of pages
+		 * requested. Ensure that the anon and file LRUs shrink
+		 * proportionally what was requested by get_scan_count(). We
+		 * stop reclaiming one LRU and reduce the amount scanning
+		 * proportional to the original scan target.
+		 */
+		nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
+		nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
+
+		if (nr_file > nr_anon) {
+			unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
+						targets[LRU_ACTIVE_ANON] + 1;
+			lru = LRU_BASE;
+			percentage = nr_anon * 100 / scan_target;
+		} else {
+			unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
+						targets[LRU_ACTIVE_FILE] + 1;
+			lru = LRU_FILE;
+			percentage = nr_file * 100 / scan_target;
+		}
+
+		/* Stop scanning the smaller of the LRU */
+		nr[lru] = 0;
+		nr[lru + LRU_ACTIVE] = 0;
+
+		/*
+		 * Recalculate the other LRU scan count based on its original
+		 * scan target and the percentage scanning already complete
+		 */
+		lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE;
+		nr_scanned = targets[lru] - nr[lru];
+		nr[lru] = targets[lru] * (100 - percentage) / 100;
+		nr[lru] -= min(nr[lru], nr_scanned);
+
+		lru += LRU_ACTIVE;
+		nr_scanned = targets[lru] - nr[lru];
+		nr[lru] = targets[lru] * (100 - percentage) / 100;
+		nr[lru] -= min(nr[lru], nr_scanned);
+
+		scan_adjusted = true;
 	}
 	blk_finish_plug(&plug);
 	sc->nr_reclaimed += nr_reclaimed;
@@ -2222,17 +2404,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 						WB_REASON_TRY_TO_FREE_PAGES);
 			sc->may_writepage = 1;
 		}
-
-		/* Take a nap, wait for some writeback to complete */
-		if (!sc->hibernation_mode && sc->nr_scanned &&
-		    sc->priority < DEF_PRIORITY - 2) {
-			struct zone *preferred_zone;
-
-			first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask),
-						&cpuset_current_mems_allowed,
-						&preferred_zone);
-			wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10);
-		}
 	} while (--sc->priority >= 0);
 
 out:
@@ -2601,6 +2772,91 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 }
 
 /*
+ * kswapd shrinks the zone by the number of pages required to reach
+ * the high watermark.
+ *
+ * Returns true if kswapd scanned at least the requested number of pages to
+ * reclaim or if the lack of progress was due to pages under writeback.
+ * This is used to determine if the scanning priority needs to be raised.
+ */
+static bool kswapd_shrink_zone(struct zone *zone,
+			       int classzone_idx,
+			       struct scan_control *sc,
+			       unsigned long lru_pages,
+			       unsigned long *nr_attempted)
+{
+	unsigned long nr_slab;
+	int testorder = sc->order;
+	unsigned long balance_gap;
+	struct reclaim_state *reclaim_state = current->reclaim_state;
+	struct shrink_control shrink = {
+		.gfp_mask = sc->gfp_mask,
+	};
+	bool lowmem_pressure;
+
+	/* Reclaim above the high watermark. */
+	sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone));
+
+	/*
+	 * Kswapd reclaims only single pages with compaction enabled. Trying
+	 * too hard to reclaim until contiguous free pages have become
+	 * available can hurt performance by evicting too much useful data
+	 * from memory. Do not reclaim more than needed for compaction.
+	 */
+	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
+			compaction_suitable(zone, sc->order) !=
+				COMPACT_SKIPPED)
+		testorder = 0;
+
+	/*
+	 * We put equal pressure on every zone, unless one zone has way too
+	 * many pages free already. The "too many pages" is defined as the
+	 * high wmark plus a "gap" where the gap is either the low
+	 * watermark or 1% of the zone, whichever is smaller.
+	 */
+	balance_gap = min(low_wmark_pages(zone),
+		(zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
+		KSWAPD_ZONE_BALANCE_GAP_RATIO);
+
+	/*
+	 * If there is no low memory pressure or the zone is balanced then no
+	 * reclaim is necessary
+	 */
+	lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone));
+	if (!lowmem_pressure && zone_balanced(zone, testorder,
+						balance_gap, classzone_idx))
+		return true;
+
+	shrink_zone(zone, sc);
+
+	reclaim_state->reclaimed_slab = 0;
+	nr_slab = shrink_slab(&shrink, sc->nr_scanned, lru_pages);
+	sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+
+	/* Account for the number of pages attempted to reclaim */
+	*nr_attempted += sc->nr_to_reclaim;
+
+	if (nr_slab == 0 && !zone_reclaimable(zone))
+		zone->all_unreclaimable = 1;
+
+	zone_clear_flag(zone, ZONE_WRITEBACK);
+
+	/*
+	 * If a zone reaches its high watermark, consider it to be no longer
+	 * congested. It's possible there are dirty pages backed by congested
+	 * BDIs but as pressure is relieved, speculatively avoid congestion
+	 * waits.
+	 */
+	if (!zone->all_unreclaimable &&
+	    zone_balanced(zone, testorder, 0, classzone_idx)) {
+		zone_clear_flag(zone, ZONE_CONGESTED);
+		zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
+	}
+
+	return sc->nr_scanned >= sc->nr_to_reclaim;
+}
+
+/*
  * For kswapd, balance_pgdat() will work across all this node's zones until
  * they are all at high_wmark_pages(zone).
  *
@@ -2624,35 +2880,28 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 							int *classzone_idx)
 {
-	bool pgdat_is_balanced = false;
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
-	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
+		.priority = DEF_PRIORITY,
 		.may_unmap = 1,
 		.may_swap = 1,
-		/*
-		 * kswapd doesn't want to be bailed out while reclaim. because
-		 * we want to put equal scanning pressure on each zone.
-		 */
-		.nr_to_reclaim = ULONG_MAX,
+		.may_writepage = !laptop_mode,
 		.order = order,
 		.target_mem_cgroup = NULL,
 	};
-	struct shrink_control shrink = {
-		.gfp_mask = sc.gfp_mask,
-	};
-loop_again:
-	sc.priority = DEF_PRIORITY;
-	sc.nr_reclaimed = 0;
-	sc.may_writepage = !laptop_mode;
 	count_vm_event(PAGEOUTRUN);
 
 	do {
 		unsigned long lru_pages = 0;
+		unsigned long nr_attempted = 0;
+		bool raise_priority = true;
+		bool pgdat_needs_compaction = (order > 0);
+
+		sc.nr_reclaimed = 0;
 
 		/*
 		 * Scan in the highmem->dma direction for the highest
@@ -2689,23 +2938,46 @@ loop_again:
 				end_zone = i;
 				break;
 			} else {
-				/* If balanced, clear the congested flag */
+				/*
+				 * If balanced, clear the dirty and congested
+				 * flags
+				 */
 				zone_clear_flag(zone, ZONE_CONGESTED);
+				zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
 			}
 		}
 
-		if (i < 0) {
-			pgdat_is_balanced = true;
+		if (i < 0)
 			goto out;
-		}
 
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
+			if (!populated_zone(zone))
+				continue;
+
 			lru_pages += zone_reclaimable_pages(zone);
+
+			/*
+			 * If any zone is currently balanced then kswapd will
+			 * not call compaction as it is expected that the
+			 * necessary pages are already available.
+			 */
+			if (pgdat_needs_compaction &&
+					zone_watermark_ok(zone, order,
+						low_wmark_pages(zone),
+						*classzone_idx, 0))
+				pgdat_needs_compaction = false;
 		}
 
 		/*
+		 * If we're getting trouble reclaiming, start doing writepage
+		 * even in laptop mode.
+		 */
+		if (sc.priority < DEF_PRIORITY - 2)
+			sc.may_writepage = 1;
+
+		/*
 		 * Now scan the zone in the dma->highmem direction, stopping
 		 * at the last zone which needs scanning.
 		 *
@@ -2716,8 +2988,6 @@ loop_again:
 		 */
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
-			int nr_slab, testorder;
-			unsigned long balance_gap;
 
 			if (!populated_zone(zone))
 				continue;
@@ -2738,65 +3008,14 @@ loop_again:
 			sc.nr_reclaimed += nr_soft_reclaimed;
 
 			/*
-			 * We put equal pressure on every zone, unless
-			 * one zone has way too many pages free
-			 * already. The "too many pages" is defined
-			 * as the high wmark plus a "gap" where the
-			 * gap is either the low watermark or 1%
-			 * of the zone, whichever is smaller.
+			 * There should be no need to raise the scanning
+			 * priority if enough pages are already being scanned
+			 * that that high watermark would be met at 100%
+			 * efficiency.
 			 */
-			balance_gap = min(low_wmark_pages(zone),
-				(zone->managed_pages +
-					KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
-				KSWAPD_ZONE_BALANCE_GAP_RATIO);
-			/*
-			 * Kswapd reclaims only single pages with compaction
-			 * enabled. Trying too hard to reclaim until contiguous
-			 * free pages have become available can hurt performance
-			 * by evicting too much useful data from memory.
-			 * Do not reclaim more than needed for compaction.
-			 */
-			testorder = order;
-			if (IS_ENABLED(CONFIG_COMPACTION) && order &&
-					compaction_suitable(zone, order) !=
-						COMPACT_SKIPPED)
-				testorder = 0;
-
-			if ((buffer_heads_over_limit && is_highmem_idx(i)) ||
-			    !zone_balanced(zone, testorder,
-					   balance_gap, end_zone)) {
-				shrink_zone(zone, &sc);
-
-				reclaim_state->reclaimed_slab = 0;
-				nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
-				sc.nr_reclaimed += reclaim_state->reclaimed_slab;
-
-				if (nr_slab == 0 && !zone_reclaimable(zone))
-					zone->all_unreclaimable = 1;
-			}
-
-			/*
-			 * If we're getting trouble reclaiming, start doing
-			 * writepage even in laptop mode.
-			 */
-			if (sc.priority < DEF_PRIORITY - 2)
-				sc.may_writepage = 1;
-
-			if (zone->all_unreclaimable) {
-				if (end_zone && end_zone == i)
-					end_zone--;
-				continue;
-			}
-
-			if (zone_balanced(zone, testorder, 0, end_zone))
-				/*
-				 * If a zone reaches its high watermark,
-				 * consider it to be no longer congested. It's
-				 * possible there are dirty pages backed by
-				 * congested BDIs but as pressure is relieved,
-				 * speculatively avoid congestion waits
-				 */
-				zone_clear_flag(zone, ZONE_CONGESTED);
+			if (kswapd_shrink_zone(zone, end_zone, &sc,
+					lru_pages, &nr_attempted))
+				raise_priority = false;
 		}
 
 		/*
@@ -2808,74 +3027,38 @@ loop_again:
 				pfmemalloc_watermark_ok(pgdat))
 			wake_up(&pgdat->pfmemalloc_wait);
 
-		if (pgdat_balanced(pgdat, order, *classzone_idx)) {
-			pgdat_is_balanced = true;
-			break;		/* kswapd: all done */
-		}
-
 		/*
-		 * We do this so kswapd doesn't build up large priorities for
-		 * example when it is freeing in parallel with allocators. It
-		 * matches the direct reclaim path behaviour in terms of impact
-		 * on zone->*_priority.
+		 * Fragmentation may mean that the system cannot be rebalanced
+		 * for high-order allocations in all zones. If twice the
+		 * allocation size has been reclaimed and the zones are still
+		 * not balanced then recheck the watermarks at order-0 to
+		 * prevent kswapd reclaiming excessively. Assume that a
+		 * process requested a high-order can direct reclaim/compact.
 		 */
-		if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
-			break;
-	} while (--sc.priority >= 0);
-
-out:
-	if (!pgdat_is_balanced) {
-		cond_resched();
+		if (order && sc.nr_reclaimed >= 2UL << order)
+			order = sc.order = 0;
 
-		try_to_freeze();
+		/* Check if kswapd should be suspending */
+		if (try_to_freeze() || kthread_should_stop())
+			break;
 
 		/*
-		 * Fragmentation may mean that the system cannot be
-		 * rebalanced for high-order allocations in all zones.
-		 * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
-		 * it means the zones have been fully scanned and are still
-		 * not balanced. For high-order allocations, there is
-		 * little point trying all over again as kswapd may
-		 * infinite loop.
-		 *
-		 * Instead, recheck all watermarks at order-0 as they
-		 * are the most important. If watermarks are ok, kswapd will go
-		 * back to sleep. High-order users can still perform direct
-		 * reclaim if they wish.
+		 * Compact if necessary and kswapd is reclaiming at least the
+		 * high watermark number of pages as requsted
 		 */
-		if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
-			order = sc.order = 0;
-
-		goto loop_again;
-	}
-
-	/*
-	 * If kswapd was reclaiming at a higher order, it has the option of
-	 * sleeping without all zones being balanced. Before it does, it must
-	 * ensure that the watermarks for order-0 on *all* zones are met and
-	 * that the congestion flags are cleared. The congestion flag must
-	 * be cleared as kswapd is the only mechanism that clears the flag
-	 * and it is potentially going to sleep here.
-	 */
-	if (order) {
-		int zones_need_compaction = 1;
-
-		for (i = 0; i <= end_zone; i++) {
-			struct zone *zone = pgdat->node_zones + i;
-
-			if (!populated_zone(zone))
-				continue;
-
-			/* Check if the memory needs to be defragmented. */
-			if (zone_watermark_ok(zone, order,
-				    low_wmark_pages(zone), *classzone_idx, 0))
-				zones_need_compaction = 0;
-		}
-
-		if (zones_need_compaction)
+		if (pgdat_needs_compaction && sc.nr_reclaimed > nr_attempted)
 			compact_pgdat(pgdat, order);
-	}
 
+		/*
+		 * Raise priority if scanning rate is too low or there was no
+		 * progress in reclaiming pages
+		 */
+		if (raise_priority || !sc.nr_reclaimed)
+			sc.priority--;
+	} while (sc.priority >= 1 &&
+		 !pgdat_balanced(pgdat, order, *classzone_idx));
+
+out:
 	/*
 	 * Return the order we were reclaiming at so prepare_kswapd_sleep()
 	 * makes a decision on the order we were last reclaiming at. However,