Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

All conflicts seemed rather trivial, with some guidance from
Saeed Mameed on the tc_ct.c one.

Signed-off-by: David S. Miller <davem@davemloft.net>

19 files changed, 128 insertions, 120 deletions

diff --git a/mm/cma.c b/mm/cma.c
index 0463ad2ce06b..26ecff818881 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -339,13 +339,13 @@ int __init cma_declare_contiguous_nid(phys_addr_t base,
 		 */
 		if (base < highmem_start && limit > highmem_start) {
 			addr = memblock_alloc_range_nid(size, alignment,
-					highmem_start, limit, nid, false);
+					highmem_start, limit, nid, true);
 			limit = highmem_start;
 		}
 
 		if (!addr) {
 			addr = memblock_alloc_range_nid(size, alignment, base,
-					limit, nid, false);
+					limit, nid, true);
 			if (!addr) {
 				ret = -ENOMEM;
 				goto err;
diff --git a/mm/compaction.c b/mm/compaction.c
index fd988b7e5f2b..86375605faa9 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2316,15 +2316,26 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 		.page = NULL,
 	};
 
-	current->capture_control = &capc;
+	/*
+	 * Make sure the structs are really initialized before we expose the
+	 * capture control, in case we are interrupted and the interrupt handler
+	 * frees a page.
+	 */
+	barrier();
+	WRITE_ONCE(current->capture_control, &capc);
 
 	ret = compact_zone(&cc, &capc);
 
 	VM_BUG_ON(!list_empty(&cc.freepages));
 	VM_BUG_ON(!list_empty(&cc.migratepages));
 
-	*capture = capc.page;
-	current->capture_control = NULL;
+	/*
+	 * Make sure we hide capture control first before we read the captured
+	 * page pointer, otherwise an interrupt could free and capture a page
+	 * and we would leak it.
+	 */
+	WRITE_ONCE(current->capture_control, NULL);
+	*capture = READ_ONCE(capc.page);
 
 	return ret;
 }
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index e45623016aea..61ab16fb2e36 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -246,13 +246,13 @@ static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
 static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep,
 				   unsigned long vaddr)
 {
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 
 	pte = __pte(pte_val(pte) | RANDOM_ORVALUE);
 	set_pte_at(mm, vaddr, ptep, pte);
 	barrier();
 	pte_clear(mm, vaddr, ptep);
-	pte = READ_ONCE(*ptep);
+	pte = ptep_get(ptep);
 	WARN_ON(!pte_none(pte));
 }
 
diff --git a/mm/filemap.c b/mm/filemap.c
index f0ae9a6308cb..385759c4ce4b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2028,7 +2028,7 @@ find_page:
 
 		page = find_get_page(mapping, index);
 		if (!page) {
-			if (iocb->ki_flags & IOCB_NOWAIT)
+			if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
 				goto would_block;
 			page_cache_sync_readahead(mapping,
 					ra, filp,
@@ -2038,6 +2038,10 @@ find_page:
 				goto no_cached_page;
 		}
 		if (PageReadahead(page)) {
+			if (iocb->ki_flags & IOCB_NOIO) {
+				put_page(page);
+				goto out;
+			}
 			page_cache_async_readahead(mapping,
 					ra, filp, page,
 					index, last_index - index);
@@ -2160,6 +2164,11 @@ page_not_up_to_date_locked:
 		}
 
 readpage:
+		if (iocb->ki_flags & IOCB_NOIO) {
+			unlock_page(page);
+			put_page(page);
+			goto would_block;
+		}
 		/*
 		 * A previous I/O error may have been due to temporary
 		 * failures, eg. multipath errors.
@@ -2249,9 +2258,19 @@ EXPORT_SYMBOL_GPL(generic_file_buffered_read);
  *
  * This is the "read_iter()" routine for all filesystems
  * that can use the page cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall
+ * be returned when no data can be read without waiting for I/O requests
+ * to complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O
+ * requests shall be made for the read or for readahead.  When no data
+ * can be read, -EAGAIN shall be returned.  When readahead would be
+ * triggered, a partial, possibly empty read shall be returned.
+ *
  * Return:
  * * number of bytes copied, even for partial reads
- * * negative error code if nothing was read
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
  */
 ssize_t
 generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 57ece74e3aae..fab4485b9e52 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1593,7 +1593,7 @@ static struct address_space *_get_hugetlb_page_mapping(struct page *hpage)
 
 	/* Use first found vma */
 	pgoff_start = page_to_pgoff(hpage);
-	pgoff_end = pgoff_start + hpage_nr_pages(hpage) - 1;
+	pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1;
 	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
 					pgoff_start, pgoff_end) {
 		struct vm_area_struct *vma = avc->vma;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0b38b6ad547d..19622328e4b5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2772,8 +2772,10 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 		return;
 
 	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
-	if (!cw)
+	if (!cw) {
+		css_put(&memcg->css);
 		return;
+	}
 
 	cw->memcg = memcg;
 	cw->cachep = cachep;
@@ -6360,11 +6362,16 @@ static unsigned long effective_protection(unsigned long usage,
 	 * We're using unprotected memory for the weight so that if
 	 * some cgroups DO claim explicit protection, we don't protect
 	 * the same bytes twice.
+	 *
+	 * Check both usage and parent_usage against the respective
+	 * protected values. One should imply the other, but they
+	 * aren't read atomically - make sure the division is sane.
 	 */
 	if (!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT))
 		return ep;
-
-	if (parent_effective > siblings_protected && usage > protected) {
+	if (parent_effective > siblings_protected &&
+	    parent_usage > siblings_protected &&
+	    usage > protected) {
 		unsigned long unclaimed;
 
 		unclaimed = parent_effective - siblings_protected;
@@ -6416,7 +6423,7 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 
 	if (parent == root) {
 		memcg->memory.emin = READ_ONCE(memcg->memory.min);
-		memcg->memory.elow = memcg->memory.low;
+		memcg->memory.elow = READ_ONCE(memcg->memory.low);
 		goto out;
 	}
 
@@ -6428,7 +6435,8 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 			atomic_long_read(&parent->memory.children_min_usage)));
 
 	WRITE_ONCE(memcg->memory.elow, effective_protection(usage, parent_usage,
-			memcg->memory.low, READ_ONCE(parent->memory.elow),
+			READ_ONCE(memcg->memory.low),
+			READ_ONCE(parent->memory.elow),
 			atomic_long_read(&parent->memory.children_low_usage)));
 
 out:
diff --git a/mm/memory.c b/mm/memory.c
index dc7f3543b1fd..87ec87cdc1ff 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1498,7 +1498,7 @@ out:
 }
 
 #ifdef pte_index
-static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd,
+static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte,
 			unsigned long addr, struct page *page, pgprot_t prot)
 {
 	int err;
@@ -1506,8 +1506,9 @@ static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd,
 	if (!page_count(page))
 		return -EINVAL;
 	err = validate_page_before_insert(page);
-	return err ? err : insert_page_into_pte_locked(
-		mm, pte_offset_map(pmd, addr), addr, page, prot);
+	if (err)
+		return err;
+	return insert_page_into_pte_locked(mm, pte, addr, page, prot);
 }
 
 /* insert_pages() amortizes the cost of spinlock operations
@@ -1517,7 +1518,8 @@ static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
 			struct page **pages, unsigned long *num, pgprot_t prot)
 {
 	pmd_t *pmd = NULL;
-	spinlock_t *pte_lock = NULL;
+	pte_t *start_pte, *pte;
+	spinlock_t *pte_lock;
 	struct mm_struct *const mm = vma->vm_mm;
 	unsigned long curr_page_idx = 0;
 	unsigned long remaining_pages_total = *num;
@@ -1536,18 +1538,17 @@ more:
 	ret = -ENOMEM;
 	if (pte_alloc(mm, pmd))
 		goto out;
-	pte_lock = pte_lockptr(mm, pmd);
 
 	while (pages_to_write_in_pmd) {
 		int pte_idx = 0;
 		const int batch_size = min_t(int, pages_to_write_in_pmd, 8);
 
-		spin_lock(pte_lock);
-		for (; pte_idx < batch_size; ++pte_idx) {
-			int err = insert_page_in_batch_locked(mm, pmd,
+		start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock);
+		for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) {
+			int err = insert_page_in_batch_locked(mm, pte,
 				addr, pages[curr_page_idx], prot);
 			if (unlikely(err)) {
-				spin_unlock(pte_lock);
+				pte_unmap_unlock(start_pte, pte_lock);
 				ret = err;
 				remaining_pages_total -= pte_idx;
 				goto out;
@@ -1555,7 +1556,7 @@ more:
 			addr += PAGE_SIZE;
 			++curr_page_idx;
 		}
-		spin_unlock(pte_lock);
+		pte_unmap_unlock(start_pte, pte_lock);
 		pages_to_write_in_pmd -= batch_size;
 		remaining_pages_total -= batch_size;
 	}
@@ -3140,8 +3141,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 				err = mem_cgroup_charge(page, vma->vm_mm,
 							GFP_KERNEL);
 				ClearPageSwapCache(page);
-				if (err)
+				if (err) {
+					ret = VM_FAULT_OOM;
 					goto out_page;
+				}
+
+				/*
+				 * XXX: Move to lru_cache_add() when it
+				 * supports new vs putback
+				 */
+				spin_lock_irq(&page_pgdat(page)->lru_lock);
+				lru_note_cost_page(page);
+				spin_unlock_irq(&page_pgdat(page)->lru_lock);
 
 				lru_cache_add(page);
 				swap_readpage(page, true);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9b34e03e730a..da374cd3d45b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -471,11 +471,20 @@ void __ref remove_pfn_range_from_zone(struct zone *zone,
 				      unsigned long start_pfn,
 				      unsigned long nr_pages)
 {
+	const unsigned long end_pfn = start_pfn + nr_pages;
 	struct pglist_data *pgdat = zone->zone_pgdat;
-	unsigned long flags;
+	unsigned long pfn, cur_nr_pages, flags;
 
 	/* Poison struct pages because they are now uninitialized again. */
-	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+	for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) {
+		cond_resched();
+
+		/* Select all remaining pages up to the next section boundary */
+		cur_nr_pages =
+			min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn);
+		page_init_poison(pfn_to_page(pfn),
+				 sizeof(struct page) * cur_nr_pages);
+	}
 
 #ifdef CONFIG_ZONE_DEVICE
 	/*
diff --git a/mm/migrate.c b/mm/migrate.c
index f37729673558..40cd7016ae6f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1161,21 +1161,10 @@ out:
 }
 
 /*
- * gcc 4.7 and 4.8 on arm get an ICEs when inlining unmap_and_move().  Work
- * around it.
- */
-#if defined(CONFIG_ARM) && \
-	defined(GCC_VERSION) && GCC_VERSION < 40900 && GCC_VERSION >= 40700
-#define ICE_noinline noinline
-#else
-#define ICE_noinline
-#endif
-
-/*
  * Obtain the lock on page, remove all ptes and migrate the page
  * to the newly allocated page in newpage.
  */
-static ICE_noinline int unmap_and_move(new_page_t get_new_page,
+static int unmap_and_move(new_page_t get_new_page,
 				   free_page_t put_new_page,
 				   unsigned long private, struct page *page,
 				   int force, enum migrate_mode mode,
diff --git a/mm/nommu.c b/mm/nommu.c
index cdcad5d61dd1..f32a69095d50 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -291,23 +291,6 @@ void *vzalloc_node(unsigned long size, int node)
 EXPORT_SYMBOL(vzalloc_node);
 
 /**
- *	vmalloc_exec  -  allocate virtually contiguous, executable memory
- *	@size:		allocation size
- *
- *	Kernel-internal function to allocate enough pages to cover @size
- *	the page level allocator and map them into contiguous and
- *	executable kernel virtual space.
- *
- *	For tight control over page level allocator and protection flags
- *	use __vmalloc() instead.
- */
-
-void *vmalloc_exec(unsigned long size)
-{
-	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM);
-}
-
-/**
  * vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
  *	@size:		allocation size
  *
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 48eb0f1410d4..e028b87ce294 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7832,7 +7832,7 @@ void setup_per_zone_wmarks(void)
  * Initialise min_free_kbytes.
  *
  * For small machines we want it small (128k min).  For large machines
- * we want it large (64MB max).  But it is not linear, because network
+ * we want it large (256MB max).  But it is not linear, because network
  * bandwidth does not increase linearly with machine size.  We use
  *
  *	min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
diff --git a/mm/slab.h b/mm/slab.h
index 207c83ef6e06..74f7e09a7cfd 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -348,7 +348,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
 					     gfp_t gfp, int order,
 					     struct kmem_cache *s)
 {
-	unsigned int nr_pages = 1 << order;
+	int nr_pages = 1 << order;
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 	int ret;
@@ -388,7 +388,7 @@ out:
 static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 						struct kmem_cache *s)
 {
-	unsigned int nr_pages = 1 << order;
+	int nr_pages = 1 << order;
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 9e72ba224175..37d48a56431d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1726,7 +1726,7 @@ void kzfree(const void *p)
 	if (unlikely(ZERO_OR_NULL_PTR(mem)))
 		return;
 	ks = ksize(mem);
-	memset(mem, 0, ks);
+	memzero_explicit(mem, ks);
 	kfree(mem);
 }
 EXPORT_SYMBOL(kzfree);
diff --git a/mm/slub.c b/mm/slub.c
index fe81773fd97e..ef303070d175 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3766,15 +3766,13 @@ error:
 }
 
 static void list_slab_objects(struct kmem_cache *s, struct page *page,
-			      const char *text, unsigned long *map)
+			      const char *text)
 {
 #ifdef CONFIG_SLUB_DEBUG
 	void *addr = page_address(page);
+	unsigned long *map;
 	void *p;
 
-	if (!map)
-		return;
-
 	slab_err(s, page, text, s->name);
 	slab_lock(page);
 
@@ -3786,6 +3784,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 			print_tracking(s, p);
 		}
 	}
+	put_map(map);
 	slab_unlock(page);
 #endif
 }
@@ -3799,11 +3798,6 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
 	LIST_HEAD(discard);
 	struct page *page, *h;
-	unsigned long *map = NULL;
-
-#ifdef CONFIG_SLUB_DEBUG
-	map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL);
-#endif
 
 	BUG_ON(irqs_disabled());
 	spin_lock_irq(&n->list_lock);
@@ -3813,16 +3807,11 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 			list_add(&page->slab_list, &discard);
 		} else {
 			list_slab_objects(s, page,
-			  "Objects remaining in %s on __kmem_cache_shutdown()",
-			  map);
+			  "Objects remaining in %s on __kmem_cache_shutdown()");
 		}
 	}
 	spin_unlock_irq(&n->list_lock);
 
-#ifdef CONFIG_SLUB_DEBUG
-	bitmap_free(map);
-#endif
-
 	list_for_each_entry_safe(page, h, &discard, slab_list)
 		discard_slab(s, page);
 }
diff --git a/mm/swap.c b/mm/swap.c
index dbcab84c6fce..a82efc33411f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -443,8 +443,7 @@ void mark_page_accessed(struct page *page)
 		else
 			__lru_cache_activate_page(page);
 		ClearPageReferenced(page);
-		if (page_is_file_lru(page))
-			workingset_activation(page);
+		workingset_activation(page);
 	}
 	if (page_is_idle(page))
 		clear_page_idle(page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e98ff460e9e9..05889e8e3c97 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -21,7 +21,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
-
+#include "internal.h"
 
 /*
  * swapper_space is a fiction, retained to simplify the path through
@@ -429,7 +429,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	__SetPageSwapBacked(page);
 
 	/* May fail (-ENOMEM) if XArray node allocation failed. */
-	if (add_to_swap_cache(page, entry, gfp_mask & GFP_KERNEL)) {
+	if (add_to_swap_cache(page, entry, gfp_mask & GFP_RECLAIM_MASK)) {
 		put_swap_page(page, entry);
 		goto fail_unlock;
 	}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3091c2ca60df..5a2b55c8dd9a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1862,7 +1862,6 @@ EXPORT_SYMBOL(vm_unmap_ram);
  * @pages: an array of pointers to the pages to be mapped
  * @count: number of pages
  * @node: prefer to allocate data structures on this node
- * @prot: memory protection to use. PAGE_KERNEL for regular RAM
  *
  * If you use this function for less than VMAP_MAX_ALLOC pages, it could be
  * faster than vmap so it's good.  But if you mix long-life and short-life
@@ -2696,26 +2695,6 @@ void *vzalloc_node(unsigned long size, int node)
 }
 EXPORT_SYMBOL(vzalloc_node);
 
-/**
- * vmalloc_exec - allocate virtually contiguous, executable memory
- * @size:	  allocation size
- *
- * Kernel-internal function to allocate enough pages to cover @size
- * the page level allocator and map them into contiguous and
- * executable kernel virtual space.
- *
- * For tight control over page level allocator and protection flags
- * use __vmalloc() instead.
- *
- * Return: pointer to the allocated memory or %NULL on error
- */
-void *vmalloc_exec(unsigned long size)
-{
-	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
-			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
-			NUMA_NO_NODE, __builtin_return_address(0));
-}
-
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
 #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL)
 #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b6d84326bdf2..749d239c62b2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -904,6 +904,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		__delete_from_swap_cache(page, swap);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		put_swap_page(page, swap);
+		workingset_eviction(page, target_memcg);
 	} else {
 		void (*freepage)(struct page *);
 		void *shadow = NULL;
@@ -1884,6 +1885,8 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 				list_add(&page->lru, &pages_to_free);
 		} else {
 			nr_moved += nr_pages;
+			if (PageActive(page))
+				workingset_age_nonresident(lruvec, nr_pages);
 		}
 	}
 
diff --git a/mm/workingset.c b/mm/workingset.c
index d481ea452eeb..50b7937bab32 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -156,8 +156,8 @@
  *
  *		Implementation
  *
- * For each node's file LRU lists, a counter for inactive evictions
- * and activations is maintained (node->inactive_age).
+ * For each node's LRU lists, a counter for inactive evictions and
+ * activations is maintained (node->nonresident_age).
  *
  * On eviction, a snapshot of this counter (along with some bits to
  * identify the node) is stored in the now empty page cache
@@ -213,7 +213,17 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
 	*workingsetp = workingset;
 }
 
-static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat)
+/**
+ * workingset_age_nonresident - age non-resident entries as LRU ages
+ * @memcg: the lruvec that was aged
+ * @nr_pages: the number of pages to count
+ *
+ * As in-memory pages are aged, non-resident pages need to be aged as
+ * well, in order for the refault distances later on to be comparable
+ * to the in-memory dimensions. This function allows reclaim and LRU
+ * operations to drive the non-resident aging along in parallel.
+ */
+void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
 {
 	/*
 	 * Reclaiming a cgroup means reclaiming all its children in a
@@ -227,11 +237,8 @@ static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat)
 	 * the root cgroup's, age as well.
 	 */
 	do {
-		struct lruvec *lruvec;
-
-		lruvec = mem_cgroup_lruvec(memcg, pgdat);
-		atomic_long_inc(&lruvec->inactive_age);
-	} while (memcg && (memcg = parent_mem_cgroup(memcg)));
+		atomic_long_add(nr_pages, &lruvec->nonresident_age);
+	} while ((lruvec = parent_lruvec(lruvec)));
 }
 
 /**
@@ -254,12 +261,11 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
 	VM_BUG_ON_PAGE(page_count(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	advance_inactive_age(page_memcg(page), pgdat);
-
 	lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
 	/* XXX: target_memcg can be NULL, go through lruvec */
 	memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
-	eviction = atomic_long_read(&lruvec->inactive_age);
+	eviction = atomic_long_read(&lruvec->nonresident_age);
 	return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
 }
 
@@ -309,20 +315,20 @@ void workingset_refault(struct page *page, void *shadow)
 	if (!mem_cgroup_disabled() && !eviction_memcg)
 		goto out;
 	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
-	refault = atomic_long_read(&eviction_lruvec->inactive_age);
+	refault = atomic_long_read(&eviction_lruvec->nonresident_age);
 
 	/*
 	 * Calculate the refault distance
 	 *
 	 * The unsigned subtraction here gives an accurate distance
-	 * across inactive_age overflows in most cases. There is a
+	 * across nonresident_age overflows in most cases. There is a
 	 * special case: usually, shadow entries have a short lifetime
 	 * and are either refaulted or reclaimed along with the inode
 	 * before they get too old.  But it is not impossible for the
-	 * inactive_age to lap a shadow entry in the field, which can
-	 * then result in a false small refault distance, leading to a
-	 * false activation should this old entry actually refault
-	 * again.  However, earlier kernels used to deactivate
+	 * nonresident_age to lap a shadow entry in the field, which
+	 * can then result in a false small refault distance, leading
+	 * to a false activation should this old entry actually
+	 * refault again.  However, earlier kernels used to deactivate
 	 * unconditionally with *every* reclaim invocation for the
 	 * longest time, so the occasional inappropriate activation
 	 * leading to pressure on the active list is not a problem.
@@ -359,7 +365,7 @@ void workingset_refault(struct page *page, void *shadow)
 		goto out;
 
 	SetPageActive(page);
-	advance_inactive_age(memcg, pgdat);
+	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
 	inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
 
 	/* Page was active prior to eviction */
@@ -382,6 +388,7 @@ out:
 void workingset_activation(struct page *page)
 {
 	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
 
 	rcu_read_lock();
 	/*
@@ -394,7 +401,8 @@ void workingset_activation(struct page *page)
 	memcg = page_memcg_rcu(page);
 	if (!mem_cgroup_disabled() && !memcg)
 		goto out;
-	advance_inactive_age(memcg, page_pgdat(page));
+	lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+	workingset_age_nonresident(lruvec, hpage_nr_pages(page));
 out:
 	rcu_read_unlock();
 }