Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc bits

 - ocfs2 updates

 - almost all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (131 commits)
  memory hotplug: fix comments when adding section
  mm: make alloc_node_mem_map a void call if we don't have CONFIG_FLAT_NODE_MEM_MAP
  mm: simplify nodemask printing
  mm,oom_reaper: remove pointless kthread_run() error check
  mm/page_ext.c: check if page_ext is not prepared
  writeback: remove unused function parameter
  mm: do not rely on preempt_count in print_vma_addr
  mm, sparse: do not swamp log with huge vmemmap allocation failures
  mm/hmm: remove redundant variable align_end
  mm/list_lru.c: mark expected switch fall-through
  mm/shmem.c: mark expected switch fall-through
  mm/page_alloc.c: broken deferred calculation
  mm: don't warn about allocations which stall for too long
  fs: fuse: account fuse_inode slab memory as reclaimable
  mm, page_alloc: fix potential false positive in __zone_watermark_ok
  mm: mlock: remove lru_add_drain_all()
  mm, sysctl: make NUMA stats configurable
  shmem: convert shmem_init_inodecache() to void
  Unify migrate_pages and move_pages access checks
  mm, pagevec: rename pagevec drained field
  ...

37 files changed, 300 insertions, 359 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f41ca8486e02..e54e7e0033eb 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -93,7 +93,7 @@ extern void wb_writeout_inc(struct bdi_writeback *wb);
 /*
  * maximal error of a stat counter.
  */
-static inline unsigned long wb_stat_error(struct bdi_writeback *wb)
+static inline unsigned long wb_stat_error(void)
 {
 #ifdef CONFIG_SMP
 	return nr_cpu_ids * WB_STAT_BATCH;
@@ -122,6 +122,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  *
  * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback.
+ * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be
+ *			   inefficient.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
@@ -129,6 +131,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_STABLE_WRITES	0x00000008
 #define BDI_CAP_STRICTLIMIT	0x00000010
 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
+#define BDI_CAP_SYNCHRONOUS_IO	0x00000040
 
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
 	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
@@ -174,6 +177,11 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
 
+static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi)
+{
+	return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO;
+}
+
 static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
 {
 	return bdi->capabilities & BDI_CAP_STABLE_WRITES;
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index fdf40ca04b3c..a53063e9d7d8 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -161,6 +161,9 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 #define BOOTMEM_ALLOC_ANYWHERE		(~(phys_addr_t)0)
 
 /* FIXME: Move to memblock.h at a point where we remove nobootmem.c */
+void *memblock_virt_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align,
+				      phys_addr_t min_addr,
+				      phys_addr_t max_addr, int nid);
 void *memblock_virt_alloc_try_nid_nopanic(phys_addr_t size,
 		phys_addr_t align, phys_addr_t min_addr,
 		phys_addr_t max_addr, int nid);
@@ -177,6 +180,14 @@ static inline void * __init memblock_virt_alloc(
 					    NUMA_NO_NODE);
 }
 
+static inline void * __init memblock_virt_alloc_raw(
+					phys_addr_t size,  phys_addr_t align)
+{
+	return memblock_virt_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT,
+					    BOOTMEM_ALLOC_ACCESSIBLE,
+					    NUMA_NO_NODE);
+}
+
 static inline void * __init memblock_virt_alloc_nopanic(
 					phys_addr_t size, phys_addr_t align)
 {
@@ -258,6 +269,14 @@ static inline void * __init memblock_virt_alloc(
 	return __alloc_bootmem(size, align, BOOTMEM_LOW_LIMIT);
 }
 
+static inline void * __init memblock_virt_alloc_raw(
+					phys_addr_t size,  phys_addr_t align)
+{
+	if (!align)
+		align = SMP_CACHE_BYTES;
+	return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT);
+}
+
 static inline void * __init memblock_virt_alloc_nopanic(
 					phys_addr_t size, phys_addr_t align)
 {
@@ -310,6 +329,14 @@ static inline void * __init memblock_virt_alloc_try_nid(phys_addr_t size,
 					  min_addr);
 }
 
+static inline void * __init memblock_virt_alloc_try_nid_raw(
+			phys_addr_t size, phys_addr_t align,
+			phys_addr_t min_addr, phys_addr_t max_addr, int nid)
+{
+	return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align,
+				min_addr, max_addr);
+}
+
 static inline void * __init memblock_virt_alloc_try_nid_nopanic(
 			phys_addr_t size, phys_addr_t align,
 			phys_addr_t min_addr, phys_addr_t max_addr, int nid)
diff --git a/include/linux/c2port.h b/include/linux/c2port.h
index 4efabcb51347..f2736348ca26 100644
--- a/include/linux/c2port.h
+++ b/include/linux/c2port.h
@@ -9,8 +9,6 @@
  * the Free Software Foundation
  */
 
-#include <linux/kmemcheck.h>
-
 #define C2PORT_NAME_LEN			32
 
 struct device;
@@ -22,10 +20,8 @@ struct device;
 /* Main struct */
 struct c2port_ops;
 struct c2port_device {
-	kmemcheck_bitfield_begin(flags);
 	unsigned int access:1;
 	unsigned int flash_access:1;
-	kmemcheck_bitfield_end(flags);
 
 	int id;
 	char name[C2PORT_NAME_LEN];
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index eee1499db396..e8f8e8fb244d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -9,7 +9,6 @@
 #include <linux/dma-debug.h>
 #include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
-#include <linux/kmemcheck.h>
 #include <linux/bug.h>
 #include <linux/mem_encrypt.h>
 
@@ -232,7 +231,6 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	dma_addr_t addr;
 
-	kmemcheck_mark_initialized(ptr, size);
 	BUG_ON(!valid_dma_direction(dir));
 	addr = ops->map_page(dev, virt_to_page(ptr),
 			     offset_in_page(ptr), size,
@@ -265,11 +263,8 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 				   unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-	int i, ents;
-	struct scatterlist *s;
+	int ents;
 
-	for_each_sg(sg, s, nents, i)
-		kmemcheck_mark_initialized(sg_virt(s), s->length);
 	BUG_ON(!valid_dma_direction(dir));
 	ents = ops->map_sg(dev, sg, nents, dir, attrs);
 	BUG_ON(ents < 0);
@@ -299,7 +294,6 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	dma_addr_t addr;
 
-	kmemcheck_mark_initialized(page_address(page) + offset, size);
 	BUG_ON(!valid_dma_direction(dir));
 	addr = ops->map_page(dev, page, offset, size, dir, attrs);
 	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0cd02ff4ae30..80b5b482cb46 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -454,13 +454,11 @@ struct bpf_binary_header {
 
 struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
-	kmemcheck_bitfield_begin(meta);
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				locked:1,	/* Program image locked? */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1;	/* Do we need dst entry? */
-	kmemcheck_bitfield_end(meta);
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	u32			len;		/* Number of filter blocks */
 	u32			jited_len;	/* Size of jited insns in bytes */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 710143741eb5..1a4582b44d32 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -24,7 +24,6 @@ struct vm_area_struct;
 #define ___GFP_HIGH		0x20u
 #define ___GFP_IO		0x40u
 #define ___GFP_FS		0x80u
-#define ___GFP_COLD		0x100u
 #define ___GFP_NOWARN		0x200u
 #define ___GFP_RETRY_MAYFAIL	0x400u
 #define ___GFP_NOFAIL		0x800u
@@ -37,7 +36,6 @@ struct vm_area_struct;
 #define ___GFP_THISNODE		0x40000u
 #define ___GFP_ATOMIC		0x80000u
 #define ___GFP_ACCOUNT		0x100000u
-#define ___GFP_NOTRACK		0x200000u
 #define ___GFP_DIRECT_RECLAIM	0x400000u
 #define ___GFP_WRITE		0x800000u
 #define ___GFP_KSWAPD_RECLAIM	0x1000000u
@@ -193,27 +191,15 @@ struct vm_area_struct;
 /*
  * Action modifiers
  *
- * __GFP_COLD indicates that the caller does not expect to be used in the near
- *   future. Where possible, a cache-cold page will be returned.
- *
  * __GFP_NOWARN suppresses allocation failure reports.
  *
  * __GFP_COMP address compound page metadata.
  *
  * __GFP_ZERO returns a zeroed page on success.
- *
- * __GFP_NOTRACK avoids tracking with kmemcheck.
- *
- * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of
- *   distinguishing in the source between false positives and allocations that
- *   cannot be supported (e.g. page tables).
  */
-#define __GFP_COLD	((__force gfp_t)___GFP_COLD)
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
-#define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)
-#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
 /* Disable lockdep for GFP context tracking */
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
@@ -539,8 +525,8 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
-extern void free_hot_cold_page(struct page *page, bool cold);
-extern void free_hot_cold_page_list(struct list_head *list, bool cold);
+extern void free_unref_page(struct page *page);
+extern void free_unref_page_list(struct list_head *list);
 
 struct page_frag_cache;
 extern void __page_frag_cache_drain(struct page *page, unsigned int count);
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 96e69979f84d..325017ad9311 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -471,9 +471,9 @@ static inline void hmm_devmem_page_set_drvdata(struct page *page,
  * @page: pointer to struct page
  * Return: driver data value
  */
-static inline unsigned long hmm_devmem_page_get_drvdata(struct page *page)
+static inline unsigned long hmm_devmem_page_get_drvdata(const struct page *page)
 {
-	unsigned long *drvdata = (unsigned long *)&page->pgmap;
+	const unsigned long *drvdata = (const unsigned long *)&page->pgmap;
 
 	return drvdata[1];
 }
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index baeb872283d9..69c238210325 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -594,21 +594,6 @@ static inline void tasklet_hi_schedule(struct tasklet_struct *t)
 		__tasklet_hi_schedule(t);
 }
 
-extern void __tasklet_hi_schedule_first(struct tasklet_struct *t);
-
-/*
- * This version avoids touching any other tasklets. Needed for kmemcheck
- * in order not to take any page faults while enqueueing this tasklet;
- * consider VERY carefully whether you really need this or
- * tasklet_hi_schedule()...
- */
-static inline void tasklet_hi_schedule_first(struct tasklet_struct *t)
-{
-	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
-		__tasklet_hi_schedule_first(t);
-}
-
-
 static inline void tasklet_disable_nosync(struct tasklet_struct *t)
 {
 	atomic_inc(&t->count);
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 5017269e3f04..e3eb834c9a35 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -46,7 +46,7 @@ void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
 
 void kasan_cache_create(struct kmem_cache *cache, size_t *size,
-			unsigned long *flags);
+			slab_flags_t *flags);
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
 
@@ -95,7 +95,7 @@ static inline void kasan_free_pages(struct page *page, unsigned int order) {}
 
 static inline void kasan_cache_create(struct kmem_cache *cache,
 				      size_t *size,
-				      unsigned long *flags) {}
+				      slab_flags_t *flags) {}
 static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
 static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
 
diff --git a/include/linux/kmemcheck.h b/include/linux/kmemcheck.h
index 7b1d7bead7d9..ea32a7d3cf1b 100644
--- a/include/linux/kmemcheck.h
+++ b/include/linux/kmemcheck.h
@@ -1,172 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef LINUX_KMEMCHECK_H
-#define LINUX_KMEMCHECK_H
-
-#include <linux/mm_types.h>
-#include <linux/types.h>
-
-#ifdef CONFIG_KMEMCHECK
-extern int kmemcheck_enabled;
-
-/* The slab-related functions. */
-void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node);
-void kmemcheck_free_shadow(struct page *page, int order);
-void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
-			  size_t size);
-void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size);
-
-void kmemcheck_pagealloc_alloc(struct page *p, unsigned int order,
-			       gfp_t gfpflags);
-
-void kmemcheck_show_pages(struct page *p, unsigned int n);
-void kmemcheck_hide_pages(struct page *p, unsigned int n);
-
-bool kmemcheck_page_is_tracked(struct page *p);
-
-void kmemcheck_mark_unallocated(void *address, unsigned int n);
-void kmemcheck_mark_uninitialized(void *address, unsigned int n);
-void kmemcheck_mark_initialized(void *address, unsigned int n);
-void kmemcheck_mark_freed(void *address, unsigned int n);
-
-void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n);
-void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n);
-void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n);
-
-int kmemcheck_show_addr(unsigned long address);
-int kmemcheck_hide_addr(unsigned long address);
-
-bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size);
-
-/*
- * Bitfield annotations
- *
- * How to use: If you have a struct using bitfields, for example
- *
- *     struct a {
- *             int x:8, y:8;
- *     };
- *
- * then this should be rewritten as
- *
- *     struct a {
- *             kmemcheck_bitfield_begin(flags);
- *             int x:8, y:8;
- *             kmemcheck_bitfield_end(flags);
- *     };
- *
- * Now the "flags_begin" and "flags_end" members may be used to refer to the
- * beginning and end, respectively, of the bitfield (and things like
- * &x.flags_begin is allowed). As soon as the struct is allocated, the bit-
- * fields should be annotated:
- *
- *     struct a *a = kmalloc(sizeof(struct a), GFP_KERNEL);
- *     kmemcheck_annotate_bitfield(a, flags);
- */
-#define kmemcheck_bitfield_begin(name)	\
-	int name##_begin[0];
-
-#define kmemcheck_bitfield_end(name)	\
-	int name##_end[0];
-
-#define kmemcheck_annotate_bitfield(ptr, name)				\
-	do {								\
-		int _n;							\
-									\
-		if (!ptr)						\
-			break;						\
-									\
-		_n = (long) &((ptr)->name##_end)			\
-			- (long) &((ptr)->name##_begin);		\
-		BUILD_BUG_ON(_n < 0);					\
-									\
-		kmemcheck_mark_initialized(&((ptr)->name##_begin), _n);	\
-	} while (0)
-
-#define kmemcheck_annotate_variable(var)				\
-	do {								\
-		kmemcheck_mark_initialized(&(var), sizeof(var));	\
-	} while (0)							\
-
-#else
-#define kmemcheck_enabled 0
-
-static inline void
-kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
-{
-}
-
-static inline void
-kmemcheck_free_shadow(struct page *page, int order)
-{
-}
-
-static inline void
-kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
-		     size_t size)
-{
-}
-
-static inline void kmemcheck_slab_free(struct kmem_cache *s, void *object,
-				       size_t size)
-{
-}
-
-static inline void kmemcheck_pagealloc_alloc(struct page *p,
-	unsigned int order, gfp_t gfpflags)
-{
-}
-
-static inline bool kmemcheck_page_is_tracked(struct page *p)
-{
-	return false;
-}
-
-static inline void kmemcheck_mark_unallocated(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_uninitialized(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_freed(void *address, unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_unallocated_pages(struct page *p,
-						    unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_uninitialized_pages(struct page *p,
-						      unsigned int n)
-{
-}
-
-static inline void kmemcheck_mark_initialized_pages(struct page *p,
-						    unsigned int n)
-{
-}
-
-static inline bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size)
-{
-	return true;
-}
-
-#define kmemcheck_bitfield_begin(name)
-#define kmemcheck_bitfield_end(name)
-#define kmemcheck_annotate_bitfield(ptr, name)	\
-	do {					\
-	} while (0)
-
-#define kmemcheck_annotate_variable(var)	\
-	do {					\
-	} while (0)
-
-#endif /* CONFIG_KMEMCHECK */
-
-#endif /* LINUX_KMEMCHECK_H */
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 590343f6c1b1..5ac416e2d339 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -48,14 +48,14 @@ extern void kmemleak_not_leak_phys(phys_addr_t phys) __ref;
 extern void kmemleak_ignore_phys(phys_addr_t phys) __ref;
 
 static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
-					    int min_count, unsigned long flags,
+					    int min_count, slab_flags_t flags,
 					    gfp_t gfp)
 {
 	if (!(flags & SLAB_NOLEAKTRACE))
 		kmemleak_alloc(ptr, size, min_count, gfp);
 }
 
-static inline void kmemleak_free_recursive(const void *ptr, unsigned long flags)
+static inline void kmemleak_free_recursive(const void *ptr, slab_flags_t flags)
 {
 	if (!(flags & SLAB_NOLEAKTRACE))
 		kmemleak_free(ptr);
@@ -76,7 +76,7 @@ static inline void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 {
 }
 static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
-					    int min_count, unsigned long flags,
+					    int min_count, slab_flags_t flags,
 					    gfp_t gfp)
 {
 }
@@ -94,7 +94,7 @@ static inline void kmemleak_free(const void *ptr)
 static inline void kmemleak_free_part(const void *ptr, size_t size)
 {
 }
-static inline void kmemleak_free_recursive(const void *ptr, unsigned long flags)
+static inline void kmemleak_free_recursive(const void *ptr, slab_flags_t flags)
 {
 }
 static inline void kmemleak_free_percpu(const void __percpu *ptr)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index bae11c7e7bf3..7ed0f7782d16 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -237,6 +237,22 @@ unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn);
 	for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved,	\
 			       nid, flags, p_start, p_end, p_nid)
 
+/**
+ * for_each_resv_unavail_range - iterate through reserved and unavailable memory
+ * @i: u64 used as loop variable
+ * @flags: pick from blocks based on memory attributes
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ *
+ * Walks over unavailable but reserved (reserved && !memory) areas of memblock.
+ * Available as soon as memblock is initialized.
+ * Note: because this memory does not belong to any physical node, flags and
+ * nid arguments do not make sense and thus not exported as arguments.
+ */
+#define for_each_resv_unavail_range(i, p_start, p_end)			\
+	for_each_mem_range(i, &memblock.reserved, &memblock.memory,	\
+			   NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL)
+
 static inline void memblock_set_region_flags(struct memblock_region *r,
 					     unsigned long flags)
 {
@@ -389,10 +405,10 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
 	     region++)
 
-#define for_each_memblock_type(memblock_type, rgn)			\
-	for (idx = 0, rgn = &memblock_type->regions[0];			\
-	     idx < memblock_type->cnt;					\
-	     idx++, rgn = &memblock_type->regions[idx])
+#define for_each_memblock_type(i, memblock_type, rgn)			\
+	for (i = 0, rgn = &memblock_type->regions[0];			\
+	     i < memblock_type->cnt;					\
+	     i++, rgn = &memblock_type->regions[i])
 
 #ifdef CONFIG_MEMTEST
 extern void early_memtest(phys_addr_t start, phys_addr_t end);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 91b46f99b4d2..c7b1d617dff6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -96,6 +96,15 @@ extern int mmap_rnd_compat_bits __read_mostly;
 #endif
 
 /*
+ * On some architectures it is expensive to call memset() for small sizes.
+ * Those architectures should provide their own implementation of "struct page"
+ * zeroing by defining this macro in <asm/pgtable.h>.
+ */
+#ifndef mm_zero_struct_page
+#define mm_zero_struct_page(pp)  ((void)memset((pp), 0, sizeof(struct page)))
+#endif
+
+/*
  * Default maximum number of active map areas, this limits the number of vmas
  * per mm struct. Users can overwrite this number by sysctl but there is a
  * problem.
@@ -1431,7 +1440,13 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
 			  struct bdi_writeback *wb);
 int set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
-void cancel_dirty_page(struct page *page);
+void __cancel_dirty_page(struct page *page);
+static inline void cancel_dirty_page(struct page *page)
+{
+	/* Avoid atomic ops, locking, etc. when not actually needed. */
+	if (PageDirty(page))
+		__cancel_dirty_page(page);
+}
 int clear_page_dirty_for_io(struct page *page);
 
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);
@@ -1599,26 +1614,32 @@ static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
 int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
 #endif
 
-#ifdef __PAGETABLE_PUD_FOLDED
+#if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU)
 static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
 						unsigned long address)
 {
 	return 0;
 }
+static inline void mm_inc_nr_puds(struct mm_struct *mm) {}
+static inline void mm_dec_nr_puds(struct mm_struct *mm) {}
+
 #else
 int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
-#endif
 
-#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
-static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
-						unsigned long address)
+static inline void mm_inc_nr_puds(struct mm_struct *mm)
 {
-	return 0;
+	atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
 }
 
-static inline void mm_nr_pmds_init(struct mm_struct *mm) {}
+static inline void mm_dec_nr_puds(struct mm_struct *mm)
+{
+	atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
+}
+#endif
 
-static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
+static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
+						unsigned long address)
 {
 	return 0;
 }
@@ -1629,25 +1650,47 @@ static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}
 #else
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 
-static inline void mm_nr_pmds_init(struct mm_struct *mm)
+static inline void mm_inc_nr_pmds(struct mm_struct *mm)
 {
-	atomic_long_set(&mm->nr_pmds, 0);
+	atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
 
-static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+static inline void mm_dec_nr_pmds(struct mm_struct *mm)
 {
-	return atomic_long_read(&mm->nr_pmds);
+	atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
+#endif
 
-static inline void mm_inc_nr_pmds(struct mm_struct *mm)
+#ifdef CONFIG_MMU
+static inline void mm_pgtables_bytes_init(struct mm_struct *mm)
 {
-	atomic_long_inc(&mm->nr_pmds);
+	atomic_long_set(&mm->pgtables_bytes, 0);
 }
 
-static inline void mm_dec_nr_pmds(struct mm_struct *mm)
+static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
+{
+	return atomic_long_read(&mm->pgtables_bytes);
+}
+
+static inline void mm_inc_nr_ptes(struct mm_struct *mm)
+{
+	atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
+}
+
+static inline void mm_dec_nr_ptes(struct mm_struct *mm)
 {
-	atomic_long_dec(&mm->nr_pmds);
+	atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);
 }
+#else
+
+static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {}
+static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void mm_inc_nr_ptes(struct mm_struct *mm) {}
+static inline void mm_dec_nr_ptes(struct mm_struct *mm) {}
 #endif
 
 int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
@@ -2002,6 +2045,12 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 					struct mminit_pfnnid_cache *state);
 #endif
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+void zero_resv_unavail(void);
+#else
+static inline void zero_resv_unavail(void) {}
+#endif
+
 extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long,
 				unsigned long, enum memmap_context);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index c85f11dafd56..cfd0ac4e5e0e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -48,8 +48,10 @@ struct page {
 						 * inode address_space, or NULL.
 						 * If page mapped as anonymous
 						 * memory, low bit is set, and
-						 * it points to anon_vma object:
-						 * see PAGE_MAPPING_ANON below.
+						 * it points to anon_vma object
+						 * or KSM private structure. See
+						 * PAGE_MAPPING_ANON and
+						 * PAGE_MAPPING_KSM.
 						 */
 		void *s_mem;			/* slab first object */
 		atomic_t compound_mapcount;	/* first tail page */
@@ -207,14 +209,6 @@ struct page {
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
 
-#ifdef CONFIG_KMEMCHECK
-	/*
-	 * kmemcheck wants to track the status of each byte in a page; this
-	 * is a pointer to such a status block. NULL if not tracked.
-	 */
-	void *shadow;
-#endif
-
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 	int _last_cpupid;
 #endif
@@ -399,9 +393,8 @@ struct mm_struct {
 	 */
 	atomic_t mm_count;
 
-	atomic_long_t nr_ptes;			/* PTE page table pages */
-#if CONFIG_PGTABLE_LEVELS > 2
-	atomic_long_t nr_pmds;			/* PMD page table pages */
+#ifdef CONFIG_MMU
+	atomic_long_t pgtables_bytes;		/* PTE page table pages */
 #endif
 	int map_count;				/* number of VMAs */
 
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 2cf1c3c807f6..b25dc9db19fc 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -156,7 +156,8 @@ struct mmu_notifier_ops {
 	 * shared page-tables, it not necessary to implement the
 	 * invalidate_range_start()/end() notifiers, as
 	 * invalidate_range() alread catches the points in time when an
-	 * external TLB range needs to be flushed.
+	 * external TLB range needs to be flushed. For more in depth
+	 * discussion on this see Documentation/vm/mmu_notifier.txt
 	 *
 	 * The invalidate_range() function is called under the ptl
 	 * spin-lock and not allowed to sleep.
@@ -213,7 +214,8 @@ extern void __mmu_notifier_change_pte(struct mm_struct *mm,
 extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 				  unsigned long start, unsigned long end);
 extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
-				  unsigned long start, unsigned long end);
+				  unsigned long start, unsigned long end,
+				  bool only_end);
 extern void __mmu_notifier_invalidate_range(struct mm_struct *mm,
 				  unsigned long start, unsigned long end);
 
@@ -267,7 +269,14 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
 	if (mm_has_notifiers(mm))
-		__mmu_notifier_invalidate_range_end(mm, start, end);
+		__mmu_notifier_invalidate_range_end(mm, start, end, false);
+}
+
+static inline void mmu_notifier_invalidate_range_only_end(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_invalidate_range_end(mm, start, end, true);
 }
 
 static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
@@ -438,6 +447,11 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 {
 }
 
+static inline void mmu_notifier_invalidate_range_only_end(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+}
+
 static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a507f43ad221..67f2e3c38939 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -700,7 +700,8 @@ typedef struct pglist_data {
 	 * is the first PFN that needs to be initialised.
 	 */
 	unsigned long first_deferred_pfn;
-	unsigned long static_init_size;
+	/* Number of non-deferred pages */
+	unsigned long static_init_pgcnt;
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -712,12 +713,6 @@ typedef struct pglist_data {
 	/* Fields commonly accessed by the page reclaim scanner */
 	struct lruvec		lruvec;
 
-	/*
-	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
-	 * this node's LRU.  Maintained by the pageout code.
-	 */
-	unsigned int inactive_ratio;
-
 	unsigned long		flags;
 
 	ZONE_PADDING(_pad2_)
diff --git a/include/linux/net.h b/include/linux/net.h
index d97d80d7fdf8..caeb159abda5 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -22,7 +22,6 @@
 #include <linux/random.h>
 #include <linux/wait.h>
 #include <linux/fcntl.h>	/* For O_CLOEXEC and O_NONBLOCK */
-#include <linux/kmemcheck.h>
 #include <linux/rcupdate.h>
 #include <linux/once.h>
 #include <linux/fs.h>
@@ -111,9 +110,7 @@ struct socket_wq {
 struct socket {
 	socket_state		state;
 
-	kmemcheck_bitfield_begin(type);
 	short			type;
-	kmemcheck_bitfield_end(type);
 
 	unsigned long		flags;
 
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index de1c50b93c61..15cab3967d6d 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -104,7 +104,9 @@ extern nodemask_t _unused_nodemask_arg_;
  *
  * Can be used to provide arguments for '%*pb[l]' when printing a nodemask.
  */
-#define nodemask_pr_args(maskp)		MAX_NUMNODES, (maskp)->bits
+#define nodemask_pr_args(maskp)				\
+	((maskp) != NULL) ? MAX_NUMNODES : 0,		\
+	((maskp) != NULL) ? (maskp)->bits : NULL
 
 /*
  * The inline keyword gives the compiler room to decide to inline, or
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 584b14c774c1..3ec44e27aa9d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -18,7 +18,7 @@
  * Various page->flags bits:
  *
  * PG_reserved is set for special pages, which can never be swapped out. Some
- * of them might not even exist (eg empty_bad_page)...
+ * of them might not even exist...
  *
  * The PG_private bitflag is set on pagecache pages if they contain filesystem
  * specific data (which is normally at page->private). It can be used by
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 05a04e603686..cdad58bbfd8b 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -31,7 +31,7 @@ static inline bool is_migrate_isolate(int migratetype)
 #endif
 
 bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
-			 bool skip_hwpoisoned_pages);
+			 int migratetype, bool skip_hwpoisoned_pages);
 void set_pageblock_migratetype(struct page *page, int migratetype);
 int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype, int *num_movable);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e08b5339023c..34ce3ebf97d5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -16,6 +16,8 @@
 #include <linux/hardirq.h> /* for in_interrupt() */
 #include <linux/hugetlb_inline.h>
 
+struct pagevec;
+
 /*
  * Bits in mapping->flags.
  */
@@ -116,7 +118,7 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 	m->gfp_mask = mask;
 }
 
-void release_pages(struct page **pages, int nr, bool cold);
+void release_pages(struct page **pages, int nr);
 
 /*
  * speculatively take a reference to a page.
@@ -232,15 +234,9 @@ static inline struct page *page_cache_alloc(struct address_space *x)
 	return __page_cache_alloc(mapping_gfp_mask(x));
 }
 
-static inline struct page *page_cache_alloc_cold(struct address_space *x)
-{
-	return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD);
-}
-
 static inline gfp_t readahead_gfp_mask(struct address_space *x)
 {
-	return mapping_gfp_mask(x) |
-				  __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN;
+	return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN;
 }
 
 typedef int filler_t(void *, struct page *);
@@ -366,8 +362,16 @@ static inline unsigned find_get_pages(struct address_space *mapping,
 }
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
 			       unsigned int nr_pages, struct page **pages);
-unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
-			int tag, unsigned int nr_pages, struct page **pages);
+unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
+			pgoff_t end, int tag, unsigned int nr_pages,
+			struct page **pages);
+static inline unsigned find_get_pages_tag(struct address_space *mapping,
+			pgoff_t *index, int tag, unsigned int nr_pages,
+			struct page **pages)
+{
+	return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag,
+					nr_pages, pages);
+}
 unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
 			int tag, unsigned int nr_entries,
 			struct page **entries, pgoff_t *indices);
@@ -616,6 +620,8 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 extern void delete_from_page_cache(struct page *page);
 extern void __delete_from_page_cache(struct page *page, void *shadow);
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
+void delete_from_page_cache_batch(struct address_space *mapping,
+				  struct pagevec *pvec);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 2636c0c0f279..5fb6580f7f23 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -17,7 +17,7 @@ struct address_space;
 
 struct pagevec {
 	unsigned long nr;
-	unsigned long cold;
+	bool percpu_pvec_drained;
 	struct page *pages[PAGEVEC_SIZE];
 };
 
@@ -38,14 +38,22 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec,
 	return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1);
 }
 
-unsigned pagevec_lookup_tag(struct pagevec *pvec,
-		struct address_space *mapping, pgoff_t *index, int tag,
-		unsigned nr_pages);
+unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
+		struct address_space *mapping, pgoff_t *index, pgoff_t end,
+		int tag);
+unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
+		struct address_space *mapping, pgoff_t *index, pgoff_t end,
+		int tag, unsigned max_pages);
+static inline unsigned pagevec_lookup_tag(struct pagevec *pvec,
+		struct address_space *mapping, pgoff_t *index, int tag)
+{
+	return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag);
+}
 
-static inline void pagevec_init(struct pagevec *pvec, int cold)
+static inline void pagevec_init(struct pagevec *pvec)
 {
 	pvec->nr = 0;
-	pvec->cold = cold;
+	pvec->percpu_pvec_drained = false;
 }
 
 static inline void pagevec_reinit(struct pagevec *pvec)
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 567ebb5eaab0..0ca448c1cb42 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -301,18 +301,17 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index,
 void *radix_tree_lookup(const struct radix_tree_root *, unsigned long);
 void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *,
 					unsigned long index);
-typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *);
+typedef void (*radix_tree_update_node_t)(struct radix_tree_node *);
 void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *,
 			  void __rcu **slot, void *entry,
-			  radix_tree_update_node_t update_node, void *private);
+			  radix_tree_update_node_t update_node);
 void radix_tree_iter_replace(struct radix_tree_root *,
 		const struct radix_tree_iter *, void __rcu **slot, void *entry);
 void radix_tree_replace_slot(struct radix_tree_root *,
 			     void __rcu **slot, void *entry);
 void __radix_tree_delete_node(struct radix_tree_root *,
 			      struct radix_tree_node *,
-			      radix_tree_update_node_t update_node,
-			      void *private);
+			      radix_tree_update_node_t update_node);
 void radix_tree_iter_delete(struct radix_tree_root *,
 			struct radix_tree_iter *iter, void __rcu **slot);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index fa6ace66fea5..289e4d54e3e0 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -2,7 +2,6 @@
 #ifndef _LINUX_RING_BUFFER_H
 #define _LINUX_RING_BUFFER_H
 
-#include <linux/kmemcheck.h>
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/poll.h>
@@ -14,9 +13,7 @@ struct ring_buffer_iter;
  * Don't refer to this struct directly, use functions below.
  */
 struct ring_buffer_event {
-	kmemcheck_bitfield_begin(bitfield);
 	u32		type_len:5, time_delta:27;
-	kmemcheck_bitfield_end(bitfield);
 
 	u32		array[];
 };
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 54fe91183a8e..ed06e1c28fc7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -15,7 +15,6 @@
 #define _LINUX_SKBUFF_H
 
 #include <linux/kernel.h>
-#include <linux/kmemcheck.h>
 #include <linux/compiler.h>
 #include <linux/time.h>
 #include <linux/bug.h>
@@ -711,7 +710,6 @@ struct sk_buff {
 	/* Following fields are _not_ copied in __copy_skb_header()
 	 * Note that queue_mapping is here mostly to fill a hole.
 	 */
-	kmemcheck_bitfield_begin(flags1);
 	__u16			queue_mapping;
 
 /* if you move cloned around you also must adapt those constants */
@@ -730,7 +728,6 @@ struct sk_buff {
 				head_frag:1,
 				xmit_more:1,
 				__unused:1; /* one bit hole */
-	kmemcheck_bitfield_end(flags1);
 
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
@@ -2664,7 +2661,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
 	 * 4.  __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to
 	 *     code in gfp_to_alloc_flags that should be enforcing this.
 	 */
-	gfp_mask |= __GFP_COLD | __GFP_COMP | __GFP_MEMALLOC;
+	gfp_mask |= __GFP_COMP | __GFP_MEMALLOC;
 
 	return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
 }
diff --git a/include/linux/slab.h b/include/linux/slab.h
index af5aa65c7c18..50697a1d6621 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -21,13 +21,20 @@
  * Flags to pass to kmem_cache_create().
  * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set.
  */
-#define SLAB_CONSISTENCY_CHECKS	0x00000100UL	/* DEBUG: Perform (expensive) checks on alloc/free */
-#define SLAB_RED_ZONE		0x00000400UL	/* DEBUG: Red zone objs in a cache */
-#define SLAB_POISON		0x00000800UL	/* DEBUG: Poison objects */
-#define SLAB_HWCACHE_ALIGN	0x00002000UL	/* Align objs on cache lines */
-#define SLAB_CACHE_DMA		0x00004000UL	/* Use GFP_DMA memory */
-#define SLAB_STORE_USER		0x00010000UL	/* DEBUG: Store the last owner for bug hunting */
-#define SLAB_PANIC		0x00040000UL	/* Panic if kmem_cache_create() fails */
+/* DEBUG: Perform (expensive) checks on alloc/free */
+#define SLAB_CONSISTENCY_CHECKS	((slab_flags_t __force)0x00000100U)
+/* DEBUG: Red zone objs in a cache */
+#define SLAB_RED_ZONE		((slab_flags_t __force)0x00000400U)
+/* DEBUG: Poison objects */
+#define SLAB_POISON		((slab_flags_t __force)0x00000800U)
+/* Align objs on cache lines */
+#define SLAB_HWCACHE_ALIGN	((slab_flags_t __force)0x00002000U)
+/* Use GFP_DMA memory */
+#define SLAB_CACHE_DMA		((slab_flags_t __force)0x00004000U)
+/* DEBUG: Store the last owner for bug hunting */
+#define SLAB_STORE_USER		((slab_flags_t __force)0x00010000U)
+/* Panic if kmem_cache_create() fails */
+#define SLAB_PANIC		((slab_flags_t __force)0x00040000U)
 /*
  * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
  *
@@ -65,44 +72,45 @@
  *
  * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
  */
-#define SLAB_TYPESAFE_BY_RCU	0x00080000UL	/* Defer freeing slabs to RCU */
-#define SLAB_MEM_SPREAD		0x00100000UL	/* Spread some memory over cpuset */
-#define SLAB_TRACE		0x00200000UL	/* Trace allocations and frees */
+/* Defer freeing slabs to RCU */
+#define SLAB_TYPESAFE_BY_RCU	((slab_flags_t __force)0x00080000U)
+/* Spread some memory over cpuset */
+#define SLAB_MEM_SPREAD		((slab_flags_t __force)0x00100000U)
+/* Trace allocations and frees */
+#define SLAB_TRACE		((slab_flags_t __force)0x00200000U)
 
 /* Flag to prevent checks on free */
 #ifdef CONFIG_DEBUG_OBJECTS
-# define SLAB_DEBUG_OBJECTS	0x00400000UL
+# define SLAB_DEBUG_OBJECTS	((slab_flags_t __force)0x00400000U)
 #else
-# define SLAB_DEBUG_OBJECTS	0x00000000UL
+# define SLAB_DEBUG_OBJECTS	0
 #endif
 
-#define SLAB_NOLEAKTRACE	0x00800000UL	/* Avoid kmemleak tracing */
+/* Avoid kmemleak tracing */
+#define SLAB_NOLEAKTRACE	((slab_flags_t __force)0x00800000U)
 
-/* Don't track use of uninitialized memory */
-#ifdef CONFIG_KMEMCHECK
-# define SLAB_NOTRACK		0x01000000UL
-#else
-# define SLAB_NOTRACK		0x00000000UL
-#endif
+/* Fault injection mark */
 #ifdef CONFIG_FAILSLAB
-# define SLAB_FAILSLAB		0x02000000UL	/* Fault injection mark */
+# define SLAB_FAILSLAB		((slab_flags_t __force)0x02000000U)
 #else
-# define SLAB_FAILSLAB		0x00000000UL
+# define SLAB_FAILSLAB		0
 #endif
+/* Account to memcg */
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
-# define SLAB_ACCOUNT		0x04000000UL	/* Account to memcg */
+# define SLAB_ACCOUNT		((slab_flags_t __force)0x04000000U)
 #else
-# define SLAB_ACCOUNT		0x00000000UL
+# define SLAB_ACCOUNT		0
 #endif
 
 #ifdef CONFIG_KASAN
-#define SLAB_KASAN		0x08000000UL
+#define SLAB_KASAN		((slab_flags_t __force)0x08000000U)
 #else
-#define SLAB_KASAN		0x00000000UL
+#define SLAB_KASAN		0
 #endif
 
 /* The following flags affect the page allocator grouping pages by mobility */
-#define SLAB_RECLAIM_ACCOUNT	0x00020000UL		/* Objects are reclaimable */
+/* Objects are reclaimable */
+#define SLAB_RECLAIM_ACCOUNT	((slab_flags_t __force)0x00020000U)
 #define SLAB_TEMPORARY		SLAB_RECLAIM_ACCOUNT	/* Objects are short-lived */
 /*
  * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests.
@@ -128,7 +136,7 @@ void __init kmem_cache_init(void);
 bool slab_is_available(void);
 
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
-			unsigned long,
+			slab_flags_t,
 			void (*)(void *));
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
@@ -459,9 +467,6 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  * Also it is possible to set different flags by OR'ing
  * in one or more of the following additional @flags:
  *
- * %__GFP_COLD - Request cache-cold pages instead of
- *   trying to return cache-warm pages.
- *
  * %__GFP_HIGH - This allocation has high priority and may use emergency pools.
  *
  * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail
@@ -636,6 +641,22 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
 #define kmalloc_track_caller(size, flags) \
 	__kmalloc_track_caller(size, flags, _RET_IP_)
 
+static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags,
+				       int node)
+{
+	if (size != 0 && n > SIZE_MAX / size)
+		return NULL;
+	if (__builtin_constant_p(n) && __builtin_constant_p(size))
+		return kmalloc_node(n * size, flags, node);
+	return __kmalloc_node(n * size, flags, node);
+}
+
+static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node)
+{
+	return kmalloc_array_node(n, size, flags | __GFP_ZERO, node);
+}
+
+
 #ifdef CONFIG_NUMA
 extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long);
 #define kmalloc_node_track_caller(size, flags, node) \
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 8f7d2b1656d2..072e46e9e1d5 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -20,7 +20,7 @@ struct kmem_cache {
 	struct reciprocal_value reciprocal_buffer_size;
 /* 2) touched by every alloc & free from the backend */
 
-	unsigned int flags;		/* constant flags */
+	slab_flags_t flags;		/* constant flags */
 	unsigned int num;		/* # of objs per slab */
 
 /* 3) cache_grow/shrink */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 39fa09bcde23..0adae162dc8f 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -82,7 +82,7 @@ struct kmem_cache_order_objects {
 struct kmem_cache {
 	struct kmem_cache_cpu __percpu *cpu_slab;
 	/* Used for retriving partial slabs etc */
-	unsigned long flags;
+	slab_flags_t flags;
 	unsigned long min_partial;
 	int size;		/* The size of an object including meta data */
 	int object_size;	/* The size of an object without meta data */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f02fb5db8914..c2b8128799c1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -171,8 +171,9 @@ enum {
 	SWP_AREA_DISCARD = (1 << 8),	/* single-time swap area discards */
 	SWP_PAGE_DISCARD = (1 << 9),	/* freed swap page-cluster discards */
 	SWP_STABLE_WRITES = (1 << 10),	/* no overwrite PG_writeback pages */
+	SWP_SYNCHRONOUS_IO = (1 << 11),	/* synchronous IO is efficient */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 11),	/* refcount in scan_swap_map */
+	SWP_SCANNING	= (1 << 12),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
@@ -297,7 +298,18 @@ struct vma_swap_readahead {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
-void workingset_update_node(struct radix_tree_node *node, void *private);
+
+/* Do not use directly, use workingset_lookup_update */
+void workingset_update_node(struct radix_tree_node *node);
+
+/* Returns workingset_update_node() if the mapping has shadow entries. */
+#define workingset_lookup_update(mapping)				\
+({									\
+	radix_tree_update_node_t __helper = workingset_update_node;	\
+	if (dax_mapping(mapping) || shmem_mapping(mapping))		\
+		__helper = NULL;					\
+	__helper;							\
+})
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
@@ -462,9 +474,11 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
+extern int __swap_count(struct swap_info_struct *si, swp_entry_t entry);
 extern int __swp_swapcount(swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
+extern struct swap_info_struct *swp_swap_info(swp_entry_t entry);
 extern bool reuse_swap_page(struct page *, int *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
@@ -473,6 +487,16 @@ extern void exit_swap_address_space(unsigned int type);
 
 #else /* CONFIG_SWAP */
 
+static inline int swap_readpage(struct page *page, bool do_poll)
+{
+	return 0;
+}
+
+static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
+{
+	return NULL;
+}
+
 #define swap_address_space(entry)		(NULL)
 #define get_nr_swap_pages()			0L
 #define total_swap_pages			0L
@@ -486,7 +510,7 @@ extern void exit_swap_address_space(unsigned int type);
 #define free_page_and_swap_cache(page) \
 	put_page(page)
 #define free_pages_and_swap_cache(pages, nr) \
-	release_pages((pages), (nr), false);
+	release_pages((pages), (nr));
 
 static inline void show_swap_cache_info(void)
 {
@@ -577,6 +601,11 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
+static inline int __swap_count(struct swap_info_struct *si, swp_entry_t entry)
+{
+	return 0;
+}
+
 static inline int __swp_swapcount(swp_entry_t entry)
 {
 	return 0;
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 4bcdf00c110f..34f053a150a9 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -44,10 +44,9 @@ enum {
 #endif
 
 #if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \
-				 __GFP_ZERO)
+# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_ZERO)
 #else
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_NOTRACK)
+# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT)
 #endif
 
 /*
diff --git a/include/linux/types.h b/include/linux/types.h
index 34fce54e4f1b..c94d59ef96cc 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -156,6 +156,7 @@ typedef u32 dma_addr_t;
 #endif
 
 typedef unsigned __bitwise gfp_t;
+typedef unsigned __bitwise slab_flags_t;
 typedef unsigned __bitwise fmode_t;
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 1e0cb72e0598..1779c9817b39 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -7,9 +7,19 @@
 #include <linux/mmzone.h>
 #include <linux/vm_event_item.h>
 #include <linux/atomic.h>
+#include <linux/static_key.h>
 
 extern int sysctl_stat_interval;
 
+#ifdef CONFIG_NUMA
+#define ENABLE_NUMA_STAT   1
+#define DISABLE_NUMA_STAT   0
+extern int sysctl_vm_numa_stat;
+DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key);
+extern int sysctl_vm_numa_stat_handler(struct ctl_table *table,
+		int write, void __user *buffer, size_t *length, loff_t *ppos);
+#endif
+
 #ifdef CONFIG_VM_EVENT_COUNTERS
 /*
  * Light weight per cpu counter implementation.
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 2135c9ba6ac3..39efb968b7a4 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -17,7 +17,6 @@
 #define _INET_SOCK_H
 
 #include <linux/bitops.h>
-#include <linux/kmemcheck.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/jhash.h>
@@ -84,7 +83,6 @@ struct inet_request_sock {
 #define ireq_state		req.__req_common.skc_state
 #define ireq_family		req.__req_common.skc_family
 
-	kmemcheck_bitfield_begin(flags);
 	u16			snd_wscale : 4,
 				rcv_wscale : 4,
 				tstamp_ok  : 1,
@@ -94,7 +92,6 @@ struct inet_request_sock {
 				acked	   : 1,
 				no_srccheck: 1,
 				smc_ok	   : 1;
-	kmemcheck_bitfield_end(flags);
 	u32                     ir_mark;
 	union {
 		struct ip_options_rcu __rcu	*ireq_opt;
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 6a75d67a30fd..1356fa6a7566 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -15,8 +15,6 @@
 #ifndef _INET_TIMEWAIT_SOCK_
 #define _INET_TIMEWAIT_SOCK_
 
-
-#include <linux/kmemcheck.h>
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/types.h>
@@ -69,14 +67,12 @@ struct inet_timewait_sock {
 	/* Socket demultiplex comparisons on incoming packets. */
 	/* these three are in inet_sock */
 	__be16			tw_sport;
-	kmemcheck_bitfield_begin(flags);
 	/* And these are ours. */
 	unsigned int		tw_kill		: 1,
 				tw_transparent  : 1,
 				tw_flowlabel	: 20,
 				tw_pad		: 2,	/* 2 bits hole */
 				tw_tos		: 8;
-	kmemcheck_bitfield_end(flags);
 	struct timer_list	tw_timer;
 	struct inet_bind_bucket	*tw_tb;
 };
diff --git a/include/net/sock.h b/include/net/sock.h
index f8715c5af37d..79e1a2c7912c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -440,7 +440,6 @@ struct sock {
 #define SK_FL_TYPE_MASK    0xffff0000
 #endif
 
-	kmemcheck_bitfield_begin(flags);
 	unsigned int		sk_padding : 1,
 				sk_kern_sock : 1,
 				sk_no_check_tx : 1,
@@ -449,8 +448,6 @@ struct sock {
 				sk_protocol  : 8,
 				sk_type      : 16;
 #define SK_PROTOCOL_MAX U8_MAX
-	kmemcheck_bitfield_end(flags);
-
 	u16			sk_gso_max_segs;
 	u8			sk_pacing_shift;
 	unsigned long	        sk_lingertime;
@@ -1114,7 +1111,7 @@ struct proto {
 
 	struct kmem_cache	*slab;
 	unsigned int		obj_size;
-	int			slab_flags;
+	slab_flags_t		slab_flags;
 
 	struct percpu_counter	*orphan_count;
 
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 285feeadac39..eb57e3037deb 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -172,24 +172,21 @@ TRACE_EVENT(mm_page_free,
 
 TRACE_EVENT(mm_page_free_batched,
 
-	TP_PROTO(struct page *page, int cold),
+	TP_PROTO(struct page *page),
 
-	TP_ARGS(page, cold),
+	TP_ARGS(page),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)
-		__field(	int,		cold		)
 	),
 
 	TP_fast_assign(
 		__entry->pfn		= page_to_pfn(page);
-		__entry->cold		= cold;
 	),
 
-	TP_printk("page=%p pfn=%lu order=0 cold=%d",
+	TP_printk("page=%p pfn=%lu order=0",
 			pfn_to_page(__entry->pfn),
-			__entry->pfn,
-			__entry->cold)
+			__entry->pfn)
 );
 
 TRACE_EVENT(mm_page_alloc,
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 648cbf603736..dbe1bb058c09 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -32,7 +32,6 @@
 	{(unsigned long)__GFP_ATOMIC,		"__GFP_ATOMIC"},	\
 	{(unsigned long)__GFP_IO,		"__GFP_IO"},		\
 	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
-	{(unsigned long)__GFP_COLD,		"__GFP_COLD"},		\
 	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
 	{(unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
 	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
@@ -46,7 +45,6 @@
 	{(unsigned long)__GFP_RECLAIMABLE,	"__GFP_RECLAIMABLE"},	\
 	{(unsigned long)__GFP_MOVABLE,		"__GFP_MOVABLE"},	\
 	{(unsigned long)__GFP_ACCOUNT,		"__GFP_ACCOUNT"},	\
-	{(unsigned long)__GFP_NOTRACK,		"__GFP_NOTRACK"},	\
 	{(unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
 	{(unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
 	{(unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\