Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "Incoming:

   - a small number of updates to scripts/, ocfs2 and fs/buffer.c

   - most of MM

  I still have quite a lot of material (mostly not MM) staged after
  linux-next due to -next dependencies. I'll send those across next week
  as the preprequisites get merged up"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (135 commits)
  mm/page_io.c: annotate refault stalls from swap_readpage
  mm/Kconfig: fix trivial help text punctuation
  mm/Kconfig: fix indentation
  mm/memory_hotplug.c: remove __online_page_set_limits()
  mm: fix typos in comments when calling __SetPageUptodate()
  mm: fix struct member name in function comments
  mm/shmem.c: cast the type of unmap_start to u64
  mm: shmem: use proper gfp flags for shmem_writepage()
  mm/shmem.c: make array 'values' static const, makes object smaller
  userfaultfd: require CAP_SYS_PTRACE for UFFD_FEATURE_EVENT_FORK
  fs/userfaultfd.c: wp: clear VM_UFFD_MISSING or VM_UFFD_WP during userfaultfd_register()
  userfaultfd: wrap the common dst_vma check into an inlined function
  userfaultfd: remove unnecessary WARN_ON() in __mcopy_atomic_hugetlb()
  userfaultfd: use vma_pagesize for all huge page size calculation
  mm/madvise.c: use PAGE_ALIGN[ED] for range checking
  mm/madvise.c: replace with page_size() in madvise_inject_error()
  mm/mmap.c: make vma_merge() comment more easy to understand
  mm/hwpoison-inject: use DEFINE_DEBUGFS_ATTRIBUTE to define debugfs fops
  autonuma: reduce cache footprint when scanning page tables
  autonuma: fix watermark checking in migrate_balanced_pgdat()
  ...

23 files changed, 334 insertions, 128 deletions

diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index e3667c9a33a5..c86cf7cb4bba 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -30,7 +30,6 @@
 #undef pud_free_tlb
 #define pud_free_tlb(tlb, x, addr)	do { } while (0)
 #define pud_free(mm, x)			do { } while (0)
-#define __pud_free_tlb(tlb, x, addr)	do { } while (0)
 
 #undef  pud_addr_end
 #define pud_addr_end(addr, end)		(end)
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
index f6947da70d71..4c74b1c1d13b 100644
--- a/include/asm-generic/5level-fixup.h
+++ b/include/asm-generic/5level-fixup.h
@@ -51,7 +51,6 @@ static inline int p4d_present(p4d_t p4d)
 #undef p4d_free_tlb
 #define p4d_free_tlb(tlb, x, addr)	do { } while (0)
 #define p4d_free(mm, x)			do { } while (0)
-#define __p4d_free_tlb(tlb, x, addr)	do { } while (0)
 
 #undef  p4d_addr_end
 #define p4d_addr_end(addr, end)		(end)
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index aebab905e6cd..ce2cbb3c380f 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -50,7 +50,7 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
  */
 #define p4d_alloc_one(mm, address)		NULL
 #define p4d_free(mm, x)				do { } while (0)
-#define __p4d_free_tlb(tlb, x, a)		do { } while (0)
+#define p4d_free_tlb(tlb, x, a)			do { } while (0)
 
 #undef  p4d_addr_end
 #define p4d_addr_end(addr, end)			(end)
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index b85b8271a73d..0d9b28cba16d 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -60,7 +60,7 @@ static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address)
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
 }
-#define __pmd_free_tlb(tlb, x, a)		do { } while (0)
+#define pmd_free_tlb(tlb, x, a)		do { } while (0)
 
 #undef  pmd_addr_end
 #define pmd_addr_end(addr, end)			(end)
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index c77a1d301155..d3776cb494c0 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -59,7 +59,7 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
  */
 #define pud_alloc_one(mm, address)		NULL
 #define pud_free(mm, x)				do { } while (0)
-#define __pud_free_tlb(tlb, x, a)		do { } while (0)
+#define pud_free_tlb(tlb, x, a)		        do { } while (0)
 
 #undef  pud_addr_end
 #define pud_addr_end(addr, end)			(end)
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 818691846c90..798ea36a0549 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -558,8 +558,19 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
  * Do the tests inline, but report and clear the bad entry in mm/memory.c.
  */
 void pgd_clear_bad(pgd_t *);
+
+#ifndef __PAGETABLE_P4D_FOLDED
 void p4d_clear_bad(p4d_t *);
+#else
+#define p4d_clear_bad(p4d)        do { } while (0)
+#endif
+
+#ifndef __PAGETABLE_PUD_FOLDED
 void pud_clear_bad(pud_t *);
+#else
+#define pud_clear_bad(p4d)        do { } while (0)
+#endif
+
 void pmd_clear_bad(pmd_t *);
 
 static inline int pgd_none_or_clear_bad(pgd_t *pgd)
@@ -903,6 +914,21 @@ static inline int pud_write(pud_t pud)
 }
 #endif /* pud_write */
 
+#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
+static inline int pmd_devmap(pmd_t pmd)
+{
+	return 0;
+}
+static inline int pud_devmap(pud_t pud)
+{
+	return 0;
+}
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
+#endif
+
 #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
 	(defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
 	 !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
@@ -912,6 +938,31 @@ static inline int pud_trans_huge(pud_t pud)
 }
 #endif
 
+/* See pmd_none_or_trans_huge_or_clear_bad for discussion. */
+static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud)
+{
+	pud_t pudval = READ_ONCE(*pud);
+
+	if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval))
+		return 1;
+	if (unlikely(pud_bad(pudval))) {
+		pud_clear_bad(pud);
+		return 1;
+	}
+	return 0;
+}
+
+/* See pmd_trans_unstable for discussion. */
+static inline int pud_trans_unstable(pud_t *pud)
+{
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&			\
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+	return pud_none_or_trans_huge_or_dev_or_clear_bad(pud);
+#else
+	return 0;
+#endif
+}
+
 #ifndef pmd_read_atomic
 static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
 {
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index e64991142a8b..2b10036fefd0 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -584,7 +584,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 	} while (0)
 #endif
 
-#ifndef __ARCH_HAS_4LEVEL_HACK
 #ifndef pud_free_tlb
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
@@ -594,9 +593,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
-#endif
 
-#ifndef __ARCH_HAS_5LEVEL_HACK
 #ifndef p4d_free_tlb
 #define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
@@ -605,7 +602,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
-#endif
 
 #endif /* CONFIG_MMU */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 670f96a6529c..c159a8bdee8b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3156,7 +3156,6 @@ enum {
 };
 
 void dio_end_io(struct bio *bio);
-void dio_warn_stale_pagecache(struct file *filp);
 
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
@@ -3201,6 +3200,11 @@ static inline void inode_dio_end(struct inode *inode)
 		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
 }
 
+/*
+ * Warn about a page cache invalidation failure diring a direct I/O write.
+ */
+void dio_warn_stale_pagecache(struct file *filp);
+
 extern void inode_set_flags(struct inode *inode, unsigned int flags,
 			    unsigned int mask);
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 61f2f6ff9467..e5b817cb86e7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -612,6 +612,8 @@ static inline bool pm_suspended_storage(void)
 /* The below functions must be run on a range from a single zone. */
 extern int alloc_contig_range(unsigned long start, unsigned long end,
 			      unsigned migratetype, gfp_t gfp_mask);
+extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
+				       int nid, nodemask_t *nodemask);
 #endif
 void free_contig_range(unsigned long pfn, unsigned int nr_pages);
 
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 53fc34f930d0..31d4920994b9 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -105,8 +105,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-				pgoff_t idx, unsigned long address);
+u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);
 
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
 
@@ -164,38 +163,130 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
-#define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n)	({ BUG(); 0; })
-#define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
-#define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
+static inline long follow_hugetlb_page(struct mm_struct *mm,
+			struct vm_area_struct *vma, struct page **pages,
+			struct vm_area_struct **vmas, unsigned long *position,
+			unsigned long *nr_pages, long i, unsigned int flags,
+			int *nonblocking)
+{
+	BUG();
+	return 0;
+}
+
+static inline struct page *follow_huge_addr(struct mm_struct *mm,
+					unsigned long address, int write)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int copy_hugetlb_page_range(struct mm_struct *dst,
+			struct mm_struct *src, struct vm_area_struct *vma)
+{
+	BUG();
+	return 0;
+}
+
 static inline void hugetlb_report_meminfo(struct seq_file *m)
 {
 }
-#define hugetlb_report_node_meminfo(n, buf)	0
+
+static inline int hugetlb_report_node_meminfo(int nid, char *buf)
+{
+	return 0;
+}
+
 static inline void hugetlb_show_meminfo(void)
 {
 }
-#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL
-#define follow_huge_pmd(mm, addr, pmd, flags)	NULL
-#define follow_huge_pud(mm, addr, pud, flags)	NULL
-#define follow_huge_pgd(mm, addr, pgd, flags)	NULL
-#define prepare_hugepage_range(file, addr, len)	(-EINVAL)
-#define pmd_huge(x)	0
-#define pud_huge(x)	0
-#define is_hugepage_only_range(mm, addr, len)	0
-#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
-#define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
-				src_addr, pagep)	({ BUG(); 0; })
-#define huge_pte_offset(mm, address, sz)	0
+
+static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
+				unsigned long address, hugepd_t hpd, int flags,
+				int pdshift)
+{
+	return NULL;
+}
+
+static inline struct page *follow_huge_pmd(struct mm_struct *mm,
+				unsigned long address, pmd_t *pmd, int flags)
+{
+	return NULL;
+}
+
+static inline struct page *follow_huge_pud(struct mm_struct *mm,
+				unsigned long address, pud_t *pud, int flags)
+{
+	return NULL;
+}
+
+static inline struct page *follow_huge_pgd(struct mm_struct *mm,
+				unsigned long address, pgd_t *pgd, int flags)
+{
+	return NULL;
+}
+
+static inline int prepare_hugepage_range(struct file *file,
+				unsigned long addr, unsigned long len)
+{
+	return -EINVAL;
+}
+
+static inline int pmd_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					unsigned long addr, unsigned long len)
+{
+	return 0;
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+				unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
+{
+	BUG();
+}
+
+static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
+						pte_t *dst_pte,
+						struct vm_area_struct *dst_vma,
+						unsigned long dst_addr,
+						unsigned long src_addr,
+						struct page **pagep)
+{
+	BUG();
+	return 0;
+}
+
+static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
+					unsigned long sz)
+{
+	return NULL;
+}
 
 static inline bool isolate_huge_page(struct page *page, struct list_head *list)
 {
 	return false;
 }
-#define putback_active_hugepage(p)	do {} while (0)
-#define move_hugetlb_state(old, new, reason)	do {} while (0)
 
-static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
-		unsigned long address, unsigned long end, pgprot_t newprot)
+static inline void putback_active_hugepage(struct page *page)
+{
+}
+
+static inline void move_hugetlb_state(struct page *oldpage,
+					struct page *newpage, int reason)
+{
+}
+
+static inline unsigned long hugetlb_change_protection(
+			struct vm_area_struct *vma, unsigned long address,
+			unsigned long end, pgprot_t newprot)
 {
 	return 0;
 }
@@ -213,9 +304,10 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 {
 	BUG();
 }
+
 static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
-				struct vm_area_struct *vma, unsigned long address,
-				unsigned int flags)
+			struct vm_area_struct *vma, unsigned long address,
+			unsigned int flags)
 {
 	BUG();
 	return 0;
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index cc8a03cc9674..4f404c565db1 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -70,8 +70,18 @@ struct kasan_cache {
 	int free_meta_offset;
 };
 
+/*
+ * These functions provide a special case to support backing module
+ * allocations with real shadow memory. With KASAN vmalloc, the special
+ * case is unnecessary, as the work is handled in the generic case.
+ */
+#ifndef CONFIG_KASAN_VMALLOC
 int kasan_module_alloc(void *addr, size_t size);
 void kasan_free_shadow(const struct vm_struct *vm);
+#else
+static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
+static inline void kasan_free_shadow(const struct vm_struct *vm) {}
+#endif
 
 int kasan_add_zero_shadow(void *start, unsigned long size);
 void kasan_remove_zero_shadow(void *start, unsigned long size);
@@ -194,4 +204,25 @@ static inline void *kasan_reset_tag(const void *addr)
 
 #endif /* CONFIG_KASAN_SW_TAGS */
 
+#ifdef CONFIG_KASAN_VMALLOC
+int kasan_populate_vmalloc(unsigned long requested_size,
+			   struct vm_struct *area);
+void kasan_poison_vmalloc(void *start, unsigned long size);
+void kasan_release_vmalloc(unsigned long start, unsigned long end,
+			   unsigned long free_region_start,
+			   unsigned long free_region_end);
+#else
+static inline int kasan_populate_vmalloc(unsigned long requested_size,
+					 struct vm_struct *area)
+{
+	return 0;
+}
+
+static inline void kasan_poison_vmalloc(void *start, unsigned long size) {}
+static inline void kasan_release_vmalloc(unsigned long start,
+					 unsigned long end,
+					 unsigned long free_region_start,
+					 unsigned long free_region_end) {}
+#endif
+
 #endif /* LINUX_KASAN_H */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index f491690d54c6..b38bbefabfab 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -358,6 +358,9 @@ static inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
 					 MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
+void *memblock_alloc_exact_nid_raw(phys_addr_t size, phys_addr_t align,
+				 phys_addr_t min_addr, phys_addr_t max_addr,
+				 int nid);
 void *memblock_alloc_try_nid_raw(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/memcontrol.h b/include/linux/memcontrol.h
index ae703ea3ef48..a7a0a1a5c8d5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -58,7 +58,6 @@ enum mem_cgroup_protection {
 
 struct mem_cgroup_reclaim_cookie {
 	pg_data_t *pgdat;
-	int priority;
 	unsigned int generation;
 };
 
@@ -81,7 +80,6 @@ struct mem_cgroup_id {
 enum mem_cgroup_events_target {
 	MEM_CGROUP_TARGET_THRESH,
 	MEM_CGROUP_TARGET_SOFTLIMIT,
-	MEM_CGROUP_TARGET_NUMAINFO,
 	MEM_CGROUP_NTARGETS,
 };
 
@@ -112,7 +110,7 @@ struct memcg_shrinker_map {
 };
 
 /*
- * per-zone information in memory controller.
+ * per-node information in memory controller.
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
@@ -126,7 +124,7 @@ struct mem_cgroup_per_node {
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
-	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
+	struct mem_cgroup_reclaim_iter	iter;
 
 	struct memcg_shrinker_map __rcu	*shrinker_map;
 
@@ -134,9 +132,6 @@ struct mem_cgroup_per_node {
 	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
-	bool			congested;	/* memcg has many dirty pages */
-						/* backed by a congested BDI */
-
 	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
 						/* use container_of	   */
 };
@@ -313,13 +308,6 @@ struct mem_cgroup {
 	struct list_head kmem_caches;
 #endif
 
-	int last_scanned_node;
-#if MAX_NUMNODES > 1
-	nodemask_t	scan_nodes;
-	atomic_t	numainfo_events;
-	atomic_t	numainfo_updating;
-#endif
-
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct list_head cgwb_list;
 	struct wb_domain cgwb_domain;
@@ -394,25 +382,27 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
 }
 
 /**
- * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
- * @node: node of the wanted lruvec
+ * mem_cgroup_lruvec - get the lru list vector for a memcg & node
  * @memcg: memcg of the wanted lruvec
  *
- * Returns the lru list vector holding pages for a given @node or a given
- * @memcg and @zone. This can be the node lruvec, if the memory controller
- * is disabled.
+ * Returns the lru list vector holding pages for a given @memcg &
+ * @node combination. This can be the node lruvec, if the memory
+ * controller is disabled.
  */
-static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
-				struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
+					       struct pglist_data *pgdat)
 {
 	struct mem_cgroup_per_node *mz;
 	struct lruvec *lruvec;
 
 	if (mem_cgroup_disabled()) {
-		lruvec = node_lruvec(pgdat);
+		lruvec = &pgdat->__lruvec;
 		goto out;
 	}
 
+	if (!memcg)
+		memcg = root_mem_cgroup;
+
 	mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
 	lruvec = &mz->lruvec;
 out:
@@ -728,7 +718,7 @@ static inline void __mod_lruvec_page_state(struct page *page,
 		return;
 	}
 
-	lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
+	lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat);
 	__mod_lruvec_state(lruvec, idx, val);
 }
 
@@ -899,16 +889,21 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
 {
 }
 
-static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
-				struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
+					       struct pglist_data *pgdat)
 {
-	return node_lruvec(pgdat);
+	return &pgdat->__lruvec;
 }
 
 static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 						    struct pglist_data *pgdat)
 {
-	return &pgdat->lruvec;
+	return &pgdat->__lruvec;
+}
+
+static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+{
+	return NULL;
 }
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index f46ea71b4ffd..3a08ecdfca11 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -102,13 +102,10 @@ extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
 
 typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
 
+extern void generic_online_page(struct page *page, unsigned int order);
 extern int set_online_page_callback(online_page_callback_t callback);
 extern int restore_online_page_callback(online_page_callback_t callback);
 
-extern void __online_page_set_limits(struct page *page);
-extern void __online_page_increment_counters(struct page *page);
-extern void __online_page_free(struct page *page);
-
 extern int try_online_node(int nid);
 
 extern int arch_add_memory(int nid, u64 start, u64 size,
@@ -229,9 +226,6 @@ void put_online_mems(void);
 void mem_hotplug_begin(void);
 void mem_hotplug_done(void);
 
-extern void set_zone_contiguous(struct zone *zone);
-extern void clear_zone_contiguous(struct zone *zone);
-
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 #define pfn_to_online_page(pfn)			\
 ({						\
@@ -339,6 +333,9 @@ static inline int remove_memory(int nid, u64 start, u64 size)
 static inline void __remove_memory(int nid, u64 start, u64 size) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
+extern void set_zone_contiguous(struct zone *zone);
+extern void clear_zone_contiguous(struct zone *zone);
+
 extern void __ref free_area_init_core_hotplug(int nid);
 extern int __add_memory(int nid, u64 start, u64 size);
 extern int add_memory(int nid, u64 start, u64 size);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f6fb714fa851..8b0ef04b6d15 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -564,21 +564,6 @@ int vma_is_stack_for_current(struct vm_area_struct *vma);
 struct mmu_gather;
 struct inode;
 
-#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline int pmd_devmap(pmd_t pmd)
-{
-	return 0;
-}
-static inline int pud_devmap(pud_t pud)
-{
-	return 0;
-}
-static inline int pgd_devmap(pgd_t pgd)
-{
-	return 0;
-}
-#endif
-
 /*
  * FIXME: take this include out, include page-flags.h in
  * files which need it (119 of them)
@@ -1643,19 +1628,27 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 	return (unsigned long)val;
 }
 
+void mm_trace_rss_stat(struct mm_struct *mm, int member, long count);
+
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
 {
-	atomic_long_add(value, &mm->rss_stat.count[member]);
+	long count = atomic_long_add_return(value, &mm->rss_stat.count[member]);
+
+	mm_trace_rss_stat(mm, member, count);
 }
 
 static inline void inc_mm_counter(struct mm_struct *mm, int member)
 {
-	atomic_long_inc(&mm->rss_stat.count[member]);
+	long count = atomic_long_inc_return(&mm->rss_stat.count[member]);
+
+	mm_trace_rss_stat(mm, member, count);
 }
 
 static inline void dec_mm_counter(struct mm_struct *mm, int member)
 {
-	atomic_long_dec(&mm->rss_stat.count[member]);
+	long count = atomic_long_dec_return(&mm->rss_stat.count[member]);
+
+	mm_trace_rss_stat(mm, member, count);
 }
 
 /* Optimized variant when page is already known not to be PageAnon */
@@ -2214,9 +2207,6 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...);
 
 extern void setup_per_cpu_pageset(void);
 
-extern void zone_pcp_update(struct zone *zone);
-extern void zone_pcp_reset(struct zone *zone);
-
 /* page_alloc.c */
 extern int min_free_kbytes;
 extern int watermark_boost_factor;
@@ -2780,7 +2770,7 @@ extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
 extern atomic_long_t num_poisoned_pages __read_mostly;
-extern int soft_offline_page(struct page *page, int flags);
+extern int soft_offline_page(unsigned long pfn, int flags);
 
 
 /*
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b0a36d1580b6..89d8ff06c9ce 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -273,12 +273,12 @@ enum lru_list {
 
 #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++)
 
-static inline int is_file_lru(enum lru_list lru)
+static inline bool is_file_lru(enum lru_list lru)
 {
 	return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE);
 }
 
-static inline int is_active_lru(enum lru_list lru)
+static inline bool is_active_lru(enum lru_list lru)
 {
 	return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
 }
@@ -296,6 +296,12 @@ struct zone_reclaim_stat {
 	unsigned long		recent_scanned[2];
 };
 
+enum lruvec_flags {
+	LRUVEC_CONGESTED,		/* lruvec has many dirty pages
+					 * backed by a congested BDI
+					 */
+};
+
 struct lruvec {
 	struct list_head		lists[NR_LRU_LISTS];
 	struct zone_reclaim_stat	reclaim_stat;
@@ -303,12 +309,14 @@ struct lruvec {
 	atomic_long_t			inactive_age;
 	/* Refaults at the time of last reclaim cycle */
 	unsigned long			refaults;
+	/* Various lruvec state flags (enum lruvec_flags) */
+	unsigned long			flags;
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat;
 #endif
 };
 
-/* Isolate unmapped file */
+/* Isolate unmapped pages */
 #define ISOLATE_UNMAPPED	((__force isolate_mode_t)0x2)
 /* Isolate for asynchronous migration */
 #define ISOLATE_ASYNC_MIGRATE	((__force isolate_mode_t)0x4)
@@ -572,9 +580,6 @@ struct zone {
 } ____cacheline_internodealigned_in_smp;
 
 enum pgdat_flags {
-	PGDAT_CONGESTED,		/* pgdat has many dirty pages backed by
-					 * a congested BDI
-					 */
 	PGDAT_DIRTY,			/* reclaim scanning has recently found
 					 * many dirty file pages at the tail
 					 * of the LRU.
@@ -777,7 +782,13 @@ typedef struct pglist_data {
 #endif
 
 	/* Fields commonly accessed by the page reclaim scanner */
-	struct lruvec		lruvec;
+
+	/*
+	 * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED.
+	 *
+	 * Use mem_cgroup_lruvec() to look up lruvecs.
+	 */
+	struct lruvec		__lruvec;
 
 	unsigned long		flags;
 
@@ -800,11 +811,6 @@ typedef struct pglist_data {
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
 
-static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
-{
-	return &pgdat->lruvec;
-}
-
 static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
 {
 	return pgdat->node_start_pfn + pgdat->node_spanned_pages;
@@ -842,7 +848,7 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 #ifdef CONFIG_MEMCG
 	return lruvec->pgdat;
 #else
-	return container_of(lruvec, struct pglist_data, lruvec);
+	return container_of(lruvec, struct pglist_data, __lruvec);
 #endif
 }
 
@@ -1079,7 +1085,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 /**
  * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask
  * @zone - The current zone in the iterator
- * @z - The current pointer within zonelist->zones being iterated
+ * @z - The current pointer within zonelist->_zonerefs being iterated
  * @zlist - The zonelist being iterated
  * @highidx - The zone index of the highest zone to return
  * @nodemask - Nodemask allowed by the allocator
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 5229c18025e9..ca92aea8a6bd 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -91,7 +91,7 @@ void module_arch_cleanup(struct module *mod);
 /* Any cleanup before freeing mod->module_init */
 void module_arch_freeing_init(struct module *mod);
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && !defined(CONFIG_KASAN_VMALLOC)
 #include <linux/kasan.h>
 #define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
 #else
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 1099c2fee20f..6861df759fad 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -30,7 +30,7 @@ static inline bool is_migrate_isolate(int migratetype)
 }
 #endif
 
-#define SKIP_HWPOISON	0x1
+#define MEMORY_OFFLINE	0x1
 #define REPORT_FAILURE	0x2
 
 bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
@@ -58,7 +58,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Test all pages in [start_pfn, end_pfn) are isolated or not.
  */
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
-			bool skip_hwpoisoned_pages);
+			int isol_flags);
 
 struct page *alloc_migrate_target(struct page *page, unsigned long private);
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 4d2a2fa55ed5..877a95c6a2d2 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -561,26 +561,6 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 	return __kmalloc(size, flags);
 }
 
-/*
- * Determine size used for the nth kmalloc cache.
- * return size or 0 if a kmalloc cache for that
- * size does not exist
- */
-static __always_inline unsigned int kmalloc_size(unsigned int n)
-{
-#ifndef CONFIG_SLOB
-	if (n > 2)
-		return 1U << n;
-
-	if (n == 1 && KMALLOC_MIN_SIZE <= 32)
-		return 96;
-
-	if (n == 2 && KMALLOC_MIN_SIZE <= 64)
-		return 192;
-#endif
-	return 0;
-}
-
 static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
 #ifndef CONFIG_SLOB
diff --git a/include/linux/string.h b/include/linux/string.h
index b6ccdc2c7f02..02894e417565 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -216,6 +216,8 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4);
 extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
 				       const void *from, size_t available);
 
+int ptr_to_hashval(const void *ptr, unsigned long *hashval_out);
+
 /**
  * strstarts - does @str start with @prefix?
  * @str: string to examine
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 063c0c1e112b..1e99f7ac1d7e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -307,7 +307,7 @@ struct vma_swap_readahead {
 };
 
 /* linux/mm/workingset.c */
-void *workingset_eviction(struct page *page);
+void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg);
 void workingset_refault(struct page *page, void *shadow);
 void workingset_activation(struct page *page);
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index b4c58a191eb1..a4b241102771 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -22,6 +22,18 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
+
+/*
+ * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
+ *
+ * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after
+ * shadow memory has been mapped. It's used to handle allocation errors so that
+ * we don't try to poision shadow on free if it was never allocated.
+ *
+ * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to
+ * determine which allocations need the module shadow freed.
+ */
+
 /*
  * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with
  * vfree_atomic().
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 69e8bb8963db..ad7e642bd497 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -316,6 +316,53 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->change_ownership)
 );
 
+/*
+ * Required for uniquely and securely identifying mm in rss_stat tracepoint.
+ */
+#ifndef __PTR_TO_HASHVAL
+static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr)
+{
+	int ret;
+	unsigned long hashval;
+
+	ret = ptr_to_hashval(ptr, &hashval);
+	if (ret)
+		return 0;
+
+	/* The hashed value is only 32-bit */
+	return (unsigned int)hashval;
+}
+#define __PTR_TO_HASHVAL
+#endif
+
+TRACE_EVENT(rss_stat,
+
+	TP_PROTO(struct mm_struct *mm,
+		int member,
+		long count),
+
+	TP_ARGS(mm, member, count),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, mm_id)
+		__field(unsigned int, curr)
+		__field(int, member)
+		__field(long, size)
+	),
+
+	TP_fast_assign(
+		__entry->mm_id = mm_ptr_to_hash(mm);
+		__entry->curr = !!(current->mm == mm);
+		__entry->member = member;
+		__entry->size = (count << PAGE_SHIFT);
+	),
+
+	TP_printk("mm_id=%u curr=%d member=%d size=%ldB",
+		__entry->mm_id,
+		__entry->curr,
+		__entry->member,
+		__entry->size)
+	);
 #endif /* _TRACE_KMEM_H */
 
 /* This part must be outside protection */