Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (159 commits)
  tools/testing/selftests/proc/proc-self-syscall.c: remove duplicate include
  proc: more robust bulk read test
  proc: test /proc/*/maps, smaps, smaps_rollup, statm
  proc: use seq_puts() everywhere
  proc: read kernel cpu stat pointer once
  proc: remove unused argument in proc_pid_lookup()
  fs/proc/thread_self.c: code cleanup for proc_setup_thread_self()
  fs/proc/self.c: code cleanup for proc_setup_self()
  proc: return exit code 4 for skipped tests
  mm,mremap: bail out earlier in mremap_to under map pressure
  mm/sparse: fix a bad comparison
  mm/memory.c: do_fault: avoid usage of stale vm_area_struct
  writeback: fix inode cgroup switching comment
  mm/huge_memory.c: fix "orig_pud" set but not used
  mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC
  mm/memcontrol.c: fix bad line in comment
  mm/cma.c: cma_declare_contiguous: correct err handling
  mm/page_ext.c: fix an imbalance with kmemleak
  mm/compaction: pass pgdat to too_many_isolated() instead of zone
  mm: remove zone_lru_lock() function, access ->lru_lock directly
  ...

30 files changed, 305 insertions, 119 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 05e61e6c843f..fa782fba51ee 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -606,7 +606,7 @@ static inline int pmd_none_or_clear_bad(pmd_t *pmd)
         return 0;
 }
 
-static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
+static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma,
                                              unsigned long addr,
                                              pte_t *ptep)
 {
@@ -615,10 +615,10 @@ static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
          * non-present, preventing the hardware from asynchronously
          * updating it.
          */
-        return ptep_get_and_clear(mm, addr, ptep);
+        return ptep_get_and_clear(vma->vm_mm, addr, ptep);
 }
 
-static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
+static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma,
                                              unsigned long addr,
                                              pte_t *ptep, pte_t pte)
 {
@@ -626,7 +626,7 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
          * The pte is non-present, so there's no hardware state to
          * preserve.
          */
-        set_pte_at(mm, addr, ptep, pte);
+        set_pte_at(vma->vm_mm, addr, ptep, pte);
 }
 
 #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@@ -644,22 +644,22 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
  * queue the update to be done at some later time.  The update must be
  * actually committed before the pte lock is released, however.
  */
-static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
+static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
                                            unsigned long addr,
                                            pte_t *ptep)
 {
-        return __ptep_modify_prot_start(mm, addr, ptep);
+        return __ptep_modify_prot_start(vma, addr, ptep);
 }
 
 /*
  * Commit an update to a pte, leaving any hardware-controlled bits in
  * the PTE unmodified.
  */
-static inline void ptep_modify_prot_commit(struct mm_struct *mm,
+static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
                                            unsigned long addr,
-                                           pte_t *ptep, pte_t pte)
+                                           pte_t *ptep, pte_t old_pte, pte_t pte)
 {
-        __ptep_modify_prot_commit(mm, addr, ptep, pte);
+        __ptep_modify_prot_commit(vma, addr, ptep, pte);
 }
 #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
 #endif /* CONFIG_MMU */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c28a47cbe355..f9b029180241 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -365,7 +365,7 @@ unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
         rcu_read_lock();
 
         /*
-         * Paired with store_release in inode_switch_wb_work_fn() and
+         * Paired with store_release in inode_switch_wbs_work_fn() and
          * ensures that we see the new wb if we see cleared I_WB_SWITCH.
          */
         cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 53051f3d8f25..f111c780ef1d 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -4,15 +4,18 @@
  *
  * Common interface definitions for making balloon pages movable by compaction.
  *
- * Despite being perfectly possible to perform ballooned pages migration, they
- * make a special corner case to compaction scans because balloon pages are not
- * enlisted at any LRU list like the other pages we do compact / migrate.
+ * Balloon page migration makes use of the general non-lru movable page
+ * feature.
+ *
+ * page->private is used to reference the responsible balloon device.
+ * page->mapping is used in context of non-lru page migration to reference
+ * the address space operations for page isolation/migration/compaction.
  *
  * As the page isolation scanning step a compaction thread does is a lockless
  * procedure (from a page standpoint), it might bring some racy situations while
  * performing balloon page compaction. In order to sort out these racy scenarios
  * and safely perform balloon's page compaction and migration we must, always,
- * ensure following these three simple rules:
+ * ensure following these simple rules:
  *
  *   i. when updating a balloon's page ->mapping element, strictly do it under
  *      the following lock order, independently of the far superior
@@ -21,19 +24,8 @@
  *            +--spin_lock_irq(&b_dev_info->pages_lock);
  *                  ... page->mapping updates here ...
  *
- *  ii. before isolating or dequeueing a balloon page from the balloon device
- *      pages list, the page reference counter must be raised by one and the
- *      extra refcount must be dropped when the page is enqueued back into
- *      the balloon device page list, thus a balloon page keeps its reference
- *      counter raised only while it is under our special handling;
- *
- * iii. after the lockless scan step have selected a potential balloon page for
- *      isolation, re-test the PageBalloon mark and the PagePrivate flag
- *      under the proper page lock, to ensure isolating a valid balloon page
- *      (not yet isolated, nor under release procedure)
- *
- *  iv. isolation or dequeueing procedure must clear PagePrivate flag under
- *      page lock together with removing page from balloon device page list.
+ *  ii. isolation or dequeueing procedure must remove the page from balloon
+ *      device page list under b_dev_info->pages_lock.
  *
  * The functions provided by this interface are placed to help on coping with
  * the aforementioned balloon page corner case, as well as to ensure the simple
@@ -103,7 +95,7 @@ extern int balloon_page_migrate(struct address_space *mapping,
 static inline void balloon_page_insert(struct balloon_dev_info *balloon,
                                        struct page *page)
 {
-        __SetPageBalloon(page);
+        __SetPageOffline(page);
         __SetPageMovable(page, balloon->inode->i_mapping);
         set_page_private(page, (unsigned long)balloon);
         list_add(&page->lru, &balloon->pages);
@@ -119,7 +111,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
  */
 static inline void balloon_page_delete(struct page *page)
 {
-        __ClearPageBalloon(page);
+        __ClearPageOffline(page);
         __ClearPageMovable(page);
         set_page_private(page, 0);
         /*
@@ -149,13 +141,13 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
 static inline void balloon_page_insert(struct balloon_dev_info *balloon,
                                        struct page *page)
 {
-        __SetPageBalloon(page);
+        __SetPageOffline(page);
         list_add(&page->lru, &balloon->pages);
 }
 
 static inline void balloon_page_delete(struct page *page)
 {
-        __ClearPageBalloon(page);
+        __ClearPageOffline(page);
         list_del(&page->lru);
 }
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8fcbae1b8db0..aad3babef007 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -32,6 +32,7 @@ struct kernfs_node;
 struct kernfs_ops;
 struct kernfs_open_file;
 struct seq_file;
+struct poll_table_struct;
 
 #define MAX_CGROUP_TYPE_NAMELEN 32
 #define MAX_CGROUP_ROOT_NAMELEN 64
@@ -574,6 +575,9 @@ struct cftype {
         ssize_t (*write)(struct kernfs_open_file *of,
                          char *buf, size_t nbytes, loff_t off);
 
+        __poll_t (*poll)(struct kernfs_open_file *of,
+                         struct poll_table_struct *pt);
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
         struct lock_class_key   lockdep_key;
 #endif
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 68250a57aace..9569e7c786d3 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -88,14 +88,13 @@ extern int sysctl_compact_memory;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
                         void __user *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_extfrag_threshold;
-extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
-                        void __user *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_compact_unevictable_allowed;
 
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
                 unsigned int order, unsigned int alloc_flags,
-                const struct alloc_context *ac, enum compact_priority prio);
+                const struct alloc_context *ac, enum compact_priority prio,
+                struct page **page);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern enum compact_result compaction_suitable(struct zone *zone, int order,
                 unsigned int alloc_flags, int classzone_idx);
@@ -227,8 +226,8 @@ static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_i
 
 #endif /* CONFIG_COMPACTION */
 
-#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
 struct node;
+#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
 extern int compaction_register_node(struct node *node);
 extern void compaction_unregister_node(struct node *node);
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 6cb4640b6160..4d2f13e8c540 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1095,7 +1095,7 @@ static inline void set_dev_node(struct device *dev, int node)
 #else
 static inline int dev_to_node(struct device *dev)
 {
-        return -1;
+        return NUMA_NO_NODE;
 }
 static inline void set_dev_node(struct device *dev, int node)
 {
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index 011965c08b93..6d775984905b 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -7,6 +7,13 @@
 #include <linux/bitops.h>
 #include <linux/jump_label.h>
 
+/*
+ * Return code to denote that requested number of
+ * frontswap pages are unused(moved to page cache).
+ * Used in in shmem_unuse and try_to_unuse.
+ */
+#define FRONTSWAP_PAGES_UNUSED  2
+
 struct frontswap_ops {
         void (*init)(unsigned); /* this swap type was just swapon'ed */
         int (*store)(unsigned, pgoff_t, struct page *); /* store a page */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fd423fec8d83..08f26046233e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2091,7 +2091,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
  * I_WB_SWITCH          Cgroup bdi_writeback switching in progress.  Used to
  *                      synchronize competing switching instances and to tell
  *                      wb stat updates to grab the i_pages lock.  See
- *                      inode_switch_wb_work_fn() for details.
+ *                      inode_switch_wbs_work_fn() for details.
  *
  * I_OVL_INUSE          Used by overlayfs to get exclusive ownership on upper
  *                      and work dirs among overlayfs mounts.
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 5f5e25fd6149..fdab7de7490d 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -24,21 +24,21 @@ struct vm_area_struct;
 #define ___GFP_HIGH             0x20u
 #define ___GFP_IO               0x40u
 #define ___GFP_FS               0x80u
-#define ___GFP_WRITE            0x100u
-#define ___GFP_NOWARN           0x200u
-#define ___GFP_RETRY_MAYFAIL    0x400u
-#define ___GFP_NOFAIL           0x800u
-#define ___GFP_NORETRY          0x1000u
-#define ___GFP_MEMALLOC         0x2000u
-#define ___GFP_COMP             0x4000u
-#define ___GFP_ZERO             0x8000u
-#define ___GFP_NOMEMALLOC       0x10000u
-#define ___GFP_HARDWALL         0x20000u
-#define ___GFP_THISNODE         0x40000u
-#define ___GFP_ATOMIC           0x80000u
-#define ___GFP_ACCOUNT          0x100000u
-#define ___GFP_DIRECT_RECLAIM   0x200000u
-#define ___GFP_KSWAPD_RECLAIM   0x400000u
+#define ___GFP_ZERO             0x100u
+#define ___GFP_ATOMIC           0x200u
+#define ___GFP_DIRECT_RECLAIM   0x400u
+#define ___GFP_KSWAPD_RECLAIM   0x800u
+#define ___GFP_WRITE            0x1000u
+#define ___GFP_NOWARN           0x2000u
+#define ___GFP_RETRY_MAYFAIL    0x4000u
+#define ___GFP_NOFAIL           0x8000u
+#define ___GFP_NORETRY          0x10000u
+#define ___GFP_MEMALLOC         0x20000u
+#define ___GFP_COMP             0x40000u
+#define ___GFP_NOMEMALLOC       0x80000u
+#define ___GFP_HARDWALL         0x100000u
+#define ___GFP_THISNODE         0x200000u
+#define ___GFP_ACCOUNT          0x400000u
 #ifdef CONFIG_LOCKDEP
 #define ___GFP_NOLOCKDEP        0x800000u
 #else
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 087fd5f48c91..ea35263eb76b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -371,6 +371,8 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
                                 nodemask_t *nmask);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
                                 unsigned long address);
+struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+                                     int nid, nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
                         pgoff_t idx);
 
@@ -493,17 +495,54 @@ static inline pgoff_t basepage_index(struct page *page)
 extern int dissolve_free_huge_page(struct page *page);
 extern int dissolve_free_huge_pages(unsigned long start_pfn,
                                     unsigned long end_pfn);
-static inline bool hugepage_migration_supported(struct hstate *h)
-{
+
 #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+#ifndef arch_hugetlb_migration_supported
+static inline bool arch_hugetlb_migration_supported(struct hstate *h)
+{
         if ((huge_page_shift(h) == PMD_SHIFT) ||
-                (huge_page_shift(h) == PGDIR_SHIFT))
+                (huge_page_shift(h) == PUD_SHIFT) ||
+                        (huge_page_shift(h) == PGDIR_SHIFT))
                 return true;
         else
                 return false;
+}
+#endif
 #else
+static inline bool arch_hugetlb_migration_supported(struct hstate *h)
+{
         return false;
+}
 #endif
+
+static inline bool hugepage_migration_supported(struct hstate *h)
+{
+        return arch_hugetlb_migration_supported(h);
+}
+
+/*
+ * Movability check is different as compared to migration check.
+ * It determines whether or not a huge page should be placed on
+ * movable zone or not. Movability of any huge page should be
+ * required only if huge page size is supported for migration.
+ * There wont be any reason for the huge page to be movable if
+ * it is not migratable to start with. Also the size of the huge
+ * page should be large enough to be placed under a movable zone
+ * and still feasible enough to be migratable. Just the presence
+ * in movable zone does not make the migration feasible.
+ *
+ * So even though large huge page sizes like the gigantic ones
+ * are migratable they should not be movable because its not
+ * feasible to migrate them from movable zone.
+ */
+static inline bool hugepage_movable_supported(struct hstate *h)
+{
+        if (!hugepage_migration_supported(h))
+                return false;
+
+        if (hstate_is_gigantic(h))
+                return false;
+        return true;
 }
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
@@ -543,6 +582,26 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
         set_huge_pte_at(mm, addr, ptep, pte);
 }
 #endif
+
+#ifndef huge_ptep_modify_prot_start
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+                                                unsigned long addr, pte_t *ptep)
+{
+        return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+#endif
+
+#ifndef huge_ptep_modify_prot_commit
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+                                                unsigned long addr, pte_t *ptep,
+                                                pte_t old_pte, pte_t pte)
+{
+        set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
+#endif
+
 #else   /* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
@@ -602,6 +661,11 @@ static inline bool hugepage_migration_supported(struct hstate *h)
         return false;
 }
 
+static inline bool hugepage_movable_supported(struct hstate *h)
+{
+        return false;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
                                            struct mm_struct *mm, pte_t *pte)
 {
diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h
index d314150658a4..a61dc075e2ce 100644
--- a/include/linux/kasan-checks.h
+++ b/include/linux/kasan-checks.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_KASAN_CHECKS_H
 #define _LINUX_KASAN_CHECKS_H
 
-#ifdef CONFIG_KASAN
+#if defined(__SANITIZE_ADDRESS__) || defined(__KASAN_INTERNAL)
 void kasan_check_read(const volatile void *p, unsigned int size);
 void kasan_check_write(const volatile void *p, unsigned int size);
 #else
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5b36b1287a5a..0cac1207bb00 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -25,6 +25,7 @@ struct seq_file;
 struct vm_area_struct;
 struct super_block;
 struct file_system_type;
+struct poll_table_struct;
 
 struct kernfs_open_node;
 struct kernfs_iattrs;
@@ -261,6 +262,9 @@ struct kernfs_ops {
         ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
                          loff_t off);
 
+        __poll_t (*poll)(struct kernfs_open_file *of,
+                         struct poll_table_struct *pt);
+
         int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -350,6 +354,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
                      const char *new_name, const void *new_ns);
 int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
+__poll_t kernfs_generic_poll(struct kernfs_open_file *of,
+                             struct poll_table_struct *pt);
 void kernfs_notify(struct kernfs_node *kn);
 
 const void *kernfs_super_ns(struct super_block *sb);
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 161e8164abcf..e48b1e453ff5 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -53,6 +53,8 @@ struct page *ksm_might_need_to_copy(struct page *page,
 
 void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
 void ksm_migrate_page(struct page *newpage, struct page *oldpage);
+bool reuse_ksm_page(struct page *page,
+                        struct vm_area_struct *vma, unsigned long address);
 
 #else  /* !CONFIG_KSM */
 
@@ -86,6 +88,11 @@ static inline void rmap_walk_ksm(struct page *page,
 static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
 }
+static inline bool reuse_ksm_page(struct page *page,
+                        struct vm_area_struct *vma, unsigned long address)
+{
+        return false;
+}
 #endif /* CONFIG_MMU */
 #endif /* !CONFIG_KSM */
 
diff --git a/include/linux/list.h b/include/linux/list.h
index edb7628e46ed..79626b5ab36c 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -207,6 +207,17 @@ static inline void list_bulk_move_tail(struct list_head *head,
 }
 
 /**
+ * list_is_first -- tests whether @ list is the first entry in list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_first(const struct list_head *list,
+                                        const struct list_head *head)
+{
+        return list->prev == head;
+}
+
+/**
  * list_is_last - tests whether @list is the last entry in list @head
  * @list: the entry to test
  * @head: the head of the list
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 83ae11cbd12c..1f3d880b7ca1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -429,6 +429,11 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 }
 struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
 
+static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
+{
+        return mem_cgroup_from_css(seq_css(m));
+}
+
 static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
 {
         struct mem_cgroup_per_node *mz;
@@ -937,6 +942,11 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
         return NULL;
 }
 
+static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m)
+{
+        return NULL;
+}
+
 static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
 {
         return NULL;
@@ -1273,12 +1283,12 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 
 struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
 void memcg_kmem_put_cache(struct kmem_cache *cachep);
-int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
-                            struct mem_cgroup *memcg);
 
 #ifdef CONFIG_MEMCG_KMEM
-int memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
-void memcg_kmem_uncharge(struct page *page, int order);
+int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
+void __memcg_kmem_uncharge(struct page *page, int order);
+int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+                              struct mem_cgroup *memcg);
 
 extern struct static_key_false memcg_kmem_enabled_key;
 extern struct workqueue_struct *memcg_kmem_cache_wq;
@@ -1300,6 +1310,26 @@ static inline bool memcg_kmem_enabled(void)
         return static_branch_unlikely(&memcg_kmem_enabled_key);
 }
 
+static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+{
+        if (memcg_kmem_enabled())
+                return __memcg_kmem_charge(page, gfp, order);
+        return 0;
+}
+
+static inline void memcg_kmem_uncharge(struct page *page, int order)
+{
+        if (memcg_kmem_enabled())
+                __memcg_kmem_uncharge(page, order);
+}
+
+static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp,
+                                          int order, struct mem_cgroup *memcg)
+{
+        if (memcg_kmem_enabled())
+                return __memcg_kmem_charge_memcg(page, gfp, order, memcg);
+        return 0;
+}
 /*
  * helper for accessing a memcg's index. It will be used as an index in the
  * child cache array in kmem_cache, and also to derive its name. This function
@@ -1325,6 +1355,15 @@ static inline void memcg_kmem_uncharge(struct page *page, int order)
 {
 }
 
+static inline int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+{
+        return 0;
+}
+
+static inline void __memcg_kmem_uncharge(struct page *page, int order)
+{
+}
+
 #define for_each_memcg_cache_index(_idx)        \
         for (; NULL; )
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 368267c1b71b..52869d6d38b3 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -89,7 +89,7 @@ extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
         unsigned long *valid_start, unsigned long *valid_end);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
-typedef void (*online_page_callback_t)(struct page *page);
+typedef void (*online_page_callback_t)(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);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80bb6408fe73..20ec56f8e2bb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1536,7 +1536,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
                     unsigned int gup_flags, struct page **pages, int *locked);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
                     struct page **pages, unsigned int gup_flags);
-#ifdef CONFIG_FS_DAX
+
+#if defined(CONFIG_FS_DAX) || defined(CONFIG_CMA)
 long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
                             unsigned int gup_flags, struct page **pages,
                             struct vm_area_struct **vmas);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0a36a22228e7..ab9b48420200 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -80,7 +80,7 @@ struct page {
                 struct {        /* Page cache and anonymous pages */
                         /**
                          * @lru: Pageout list, eg. active_list protected by
-                         * zone_lru_lock.  Sometimes used as a generic list
+                         * pgdat->lru_lock.  Sometimes used as a generic list
                          * by the page owner.
                          */
                         struct list_head lru;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 842f9189537b..fba7741533be 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -480,6 +480,8 @@ struct zone {
         unsigned long           compact_cached_free_pfn;
         /* pfn where async and sync compaction migration scanner should start */
         unsigned long           compact_cached_migrate_pfn[2];
+        unsigned long           compact_init_migrate_pfn;
+        unsigned long           compact_init_free_pfn;
 #endif
 
 #ifdef CONFIG_COMPACTION
@@ -728,10 +730,6 @@ 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 spinlock_t *zone_lru_lock(struct zone *zone)
-{
-        return &zone->zone_pgdat->lru_lock;
-}
 
 static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
 {
@@ -1299,7 +1297,7 @@ void memory_present(int nid, unsigned long start, unsigned long end);
 
 /*
  * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
- * need to check pfn validility within that MAX_ORDER_NR_PAGES block.
+ * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
  * pfn_valid_within() should be used in this case; we optimise this away
  * when we have no holes within a MAX_ORDER_NR_PAGES block.
  */
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 5a30ad594ccc..27e7fa36f707 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -444,8 +444,8 @@ static inline int next_memory_node(int nid)
         return next_node(nid, node_states[N_MEMORY]);
 }
 
-extern int nr_node_ids;
-extern int nr_online_nodes;
+extern unsigned int nr_node_ids;
+extern unsigned int nr_online_nodes;
 
 static inline void node_set_online(int nid)
 {
@@ -485,8 +485,8 @@ static inline int num_node_state(enum node_states state)
 #define first_online_node       0
 #define first_memory_node       0
 #define next_online_node(nid)   (MAX_NUMNODES)
-#define nr_node_ids             1
-#define nr_online_nodes         1
+#define nr_node_ids             1U
+#define nr_online_nodes         1U
 
 #define node_set_online(node)      node_set_state((node), N_ONLINE)
 #define node_set_offline(node)     node_clear_state((node), N_ONLINE)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 39b4494e29f1..9f8712a4b1a5 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -17,8 +17,37 @@
 /*
  * Various page->flags bits:
  *
- * PG_reserved is set for special pages, which can never be swapped out. Some
- * of them might not even exist...
+ * PG_reserved is set for special pages. The "struct page" of such a page
+ * should in general not be touched (e.g. set dirty) except by its owner.
+ * Pages marked as PG_reserved include:
+ * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS,
+ *   initrd, HW tables)
+ * - Pages reserved or allocated early during boot (before the page allocator
+ *   was initialized). This includes (depending on the architecture) the
+ *   initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much
+ *   much more. Once (if ever) freed, PG_reserved is cleared and they will
+ *   be given to the page allocator.
+ * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying
+ *   to read/write these pages might end badly. Don't touch!
+ * - The zero page(s)
+ * - Pages not added to the page allocator when onlining a section because
+ *   they were excluded via the online_page_callback() or because they are
+ *   PG_hwpoison.
+ * - Pages allocated in the context of kexec/kdump (loaded kernel image,
+ *   control pages, vmcoreinfo)
+ * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are
+ *   not marked PG_reserved (as they might be in use by somebody else who does
+ *   not respect the caching strategy).
+ * - Pages part of an offline section (struct pages of offline sections should
+ *   not be trusted as they will be initialized when first onlined).
+ * - MCA pages on ia64
+ * - Pages holding CPU notes for POWER Firmware Assisted Dump
+ * - Device memory (e.g. PMEM, DAX, HMM)
+ * Some PG_reserved pages will be excluded from the hibernation image.
+ * PG_reserved does in general not hinder anybody from dumping or swapping
+ * and is no longer required for remap_pfn_range(). ioremap might require it.
+ * Consequently, PG_reserved for a page mapped into user space can indicate
+ * the zero page, the vDSO, MMIO pages or device memory.
  *
  * 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
@@ -671,7 +700,7 @@ PAGEFLAG_FALSE(DoubleMap)
 /* Reserve              0x0000007f to catch underflows of page_mapcount */
 #define PAGE_MAPCOUNT_RESERVE   -128
 #define PG_buddy        0x00000080
-#define PG_balloon      0x00000100
+#define PG_offline      0x00000100
 #define PG_kmemcg       0x00000200
 #define PG_table        0x00000400
 
@@ -706,10 +735,13 @@ static __always_inline void __ClearPage##uname(struct page *page)	\
 PAGE_TYPE_OPS(Buddy, buddy)
 
 /*
- * PageBalloon() is true for pages that are on the balloon page list
- * (see mm/balloon_compaction.c).
+ * PageOffline() indicates that the page is logically offline although the
+ * containing section is online. (e.g. inflated in a balloon driver or
+ * not onlined when onlining the section).
+ * The content of these pages is effectively stale. Such pages should not
+ * be touched (read/write/dump/save) except by their owner.
  */
-PAGE_TYPE_OPS(Balloon, balloon)
+PAGE_TYPE_OPS(Offline, offline)
 
 /*
  * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e2d7039af6a3..b477a70cc2e4 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -164,7 +164,7 @@ void release_pages(struct page **pages, int nr);
  * will find the page or it will not. Likewise, the old find_get_page could run
  * either before the insertion or afterwards, depending on timing.
  */
-static inline int page_cache_get_speculative(struct page *page)
+static inline int __page_cache_add_speculative(struct page *page, int count)
 {
 #ifdef CONFIG_TINY_RCU
 # ifdef CONFIG_PREEMPT_COUNT
@@ -180,10 +180,10 @@ static inline int page_cache_get_speculative(struct page *page)
          * SMP requires.
          */
         VM_BUG_ON_PAGE(page_count(page) == 0, page);
-        page_ref_inc(page);
+        page_ref_add(page, count);
 
 #else
-        if (unlikely(!get_page_unless_zero(page))) {
+        if (unlikely(!page_ref_add_unless(page, count, 0))) {
                 /*
                  * Either the page has been freed, or will be freed.
                  * In either case, retry here and the caller should
@@ -197,27 +197,14 @@ static inline int page_cache_get_speculative(struct page *page)
         return 1;
 }
 
-/*
- * Same as above, but add instead of inc (could just be merged)
- */
-static inline int page_cache_add_speculative(struct page *page, int count)
+static inline int page_cache_get_speculative(struct page *page)
 {
-        VM_BUG_ON(in_interrupt());
-
-#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
-# ifdef CONFIG_PREEMPT_COUNT
-        VM_BUG_ON(!in_atomic() && !irqs_disabled());
-# endif
-        VM_BUG_ON_PAGE(page_count(page) == 0, page);
-        page_ref_add(page, count);
-
-#else
-        if (unlikely(!page_ref_add_unless(page, count, 0)))
-                return 0;
-#endif
-        VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page);
+        return __page_cache_add_speculative(page, 1);
+}
 
-        return 1;
+static inline int page_cache_add_speculative(struct page *page, int count)
+{
+        return __page_cache_add_speculative(page, count);
 }
 
 #ifdef CONFIG_NUMA
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 15927ebc22f2..5046bad0c1c5 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -30,7 +30,7 @@
  */
 #define TIMER_ENTRY_STATIC      ((void *) 0x300 + POISON_POINTER_DELTA)
 
-/********** mm/debug-pagealloc.c **********/
+/********** mm/page_poison.c **********/
 #ifdef CONFIG_PAGE_POISONING_ZERO
 #define PAGE_POISON 0x00
 #else
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 903ef29b62c3..f073bd59df32 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -48,6 +48,7 @@ struct pid_namespace;
 struct pipe_inode_info;
 struct rcu_node;
 struct reclaim_state;
+struct capture_control;
 struct robust_list_head;
 struct sched_attr;
 struct sched_param;
@@ -950,6 +951,9 @@ struct task_struct {
 
         struct io_context               *io_context;
 
+#ifdef CONFIG_COMPACTION
+        struct capture_control          *capture_control;
+#endif
         /* Ptrace state: */
         unsigned long                   ptrace_message;
         kernel_siginfo_t                *last_siginfo;
@@ -1395,6 +1399,7 @@ extern struct pid *cad_pid;
 #define PF_UMH                  0x02000000      /* I'm an Usermodehelper process */
 #define PF_NO_SETAFFINITY       0x04000000      /* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY            0x08000000      /* Early kill for mce process policy */
+#define PF_MEMALLOC_NOCMA       0x10000000      /* All allocation request will have _GFP_MOVABLE cleared */
 #define PF_FREEZER_SKIP         0x40000000      /* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK         0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3bfa6a0cbba4..0cd9f10423fb 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -148,17 +148,25 @@ static inline bool in_vfork(struct task_struct *tsk)
  * Applies per-task gfp context to the given allocation flags.
  * PF_MEMALLOC_NOIO implies GFP_NOIO
  * PF_MEMALLOC_NOFS implies GFP_NOFS
+ * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
  */
 static inline gfp_t current_gfp_context(gfp_t flags)
 {
-        /*
-         * NOIO implies both NOIO and NOFS and it is a weaker context
-         * so always make sure it makes precedence
-         */
-        if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-                flags &= ~(__GFP_IO | __GFP_FS);
-        else if (unlikely(current->flags & PF_MEMALLOC_NOFS))
-                flags &= ~__GFP_FS;
+        if (unlikely(current->flags &
+                     (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
+                /*
+                 * NOIO implies both NOIO and NOFS and it is a weaker context
+                 * so always make sure it makes precedence
+                 */
+                if (current->flags & PF_MEMALLOC_NOIO)
+                        flags &= ~(__GFP_IO | __GFP_FS);
+                else if (current->flags & PF_MEMALLOC_NOFS)
+                        flags &= ~__GFP_FS;
+#ifdef CONFIG_CMA
+                if (current->flags & PF_MEMALLOC_NOCMA)
+                        flags &= ~__GFP_MOVABLE;
+#endif
+        }
         return flags;
 }
 
@@ -248,6 +256,30 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
         current->flags = (current->flags & ~PF_MEMALLOC) | flags;
 }
 
+#ifdef CONFIG_CMA
+static inline unsigned int memalloc_nocma_save(void)
+{
+        unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
+
+        current->flags |= PF_MEMALLOC_NOCMA;
+        return flags;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+        current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
+}
+#else
+static inline unsigned int memalloc_nocma_save(void)
+{
+        return 0;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+}
+#endif
+
 #ifdef CONFIG_MEMCG
 /**
  * memalloc_use_memcg - Starts the remote memcg charging scope.
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index f155dc607112..f3fb1edb3526 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -72,7 +72,8 @@ extern void shmem_unlock_mapping(struct address_space *mapping);
 extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
                                         pgoff_t index, gfp_t gfp_mask);
 extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
-extern int shmem_unuse(swp_entry_t entry, struct page *page);
+extern int shmem_unuse(unsigned int type, bool frontswap,
+                       unsigned long *fs_pages_to_unuse);
 
 extern unsigned long shmem_swap_usage(struct vm_area_struct *vma);
 extern unsigned long shmem_partial_swap_usage(struct address_space *mapping,
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 3a1a1dbc6f49..d2153789bd9f 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -81,12 +81,12 @@ struct kmem_cache_order_objects {
  */
 struct kmem_cache {
         struct kmem_cache_cpu __percpu *cpu_slab;
-        /* Used for retriving partial slabs etc */
+        /* Used for retrieving partial slabs, etc. */
         slab_flags_t flags;
         unsigned long min_partial;
-        unsigned int size;      /* The size of an object including meta data */
-        unsigned int object_size;/* The size of an object without meta data */
-        unsigned int offset;    /* Free pointer offset. */
+        unsigned int size;      /* The size of an object including metadata */
+        unsigned int object_size;/* The size of an object without metadata */
+        unsigned int offset;    /* Free pointer offset */
 #ifdef CONFIG_SLUB_CPU_PARTIAL
         /* Number of per cpu partial objects to keep around */
         unsigned int cpu_partial;
@@ -110,7 +110,7 @@ struct kmem_cache {
 #endif
 #ifdef CONFIG_MEMCG
         struct memcg_cache_params memcg_params;
-        /* for propagation, maximum size of a stored attr */
+        /* For propagation, maximum size of a stored attr */
         unsigned int max_attr_size;
 #ifdef CONFIG_SYSFS
         struct kset *memcg_kset;
@@ -151,7 +151,7 @@ struct kmem_cache {
 #else
 #define slub_cpu_partial(s)             (0)
 #define slub_set_cpu_partial(s, n)
-#endif // CONFIG_SLUB_CPU_PARTIAL
+#endif /* CONFIG_SLUB_CPU_PARTIAL */
 
 #ifdef CONFIG_SYSFS
 #define SLAB_SUPPORTS_SYSFS
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 622025ac1461..fc50e21b3b88 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 address_space *mapping, struct page *page);
+void *workingset_eviction(struct page *page);
 void workingset_refault(struct page *page, void *shadow);
 void workingset_activation(struct page *page);
 
@@ -625,7 +625,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
                 return vm_swappiness;
 
         /* root ? */
-        if (mem_cgroup_disabled() || !memcg->css.parent)
+        if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg))
                 return vm_swappiness;
 
         return memcg->swappiness;
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 6448cdd9a350..a2f8658f1c55 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -41,6 +41,7 @@
 #define F_SEAL_SHRINK   0x0002  /* prevent file from shrinking */
 #define F_SEAL_GROW     0x0004  /* prevent file from growing */
 #define F_SEAL_WRITE    0x0008  /* prevent writes */
+#define F_SEAL_FUTURE_WRITE     0x0010  /* prevent future writes while mapped */
 /* (1U << 31) is reserved for signed error codes */
 
 /*
diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h
index 21b9113c69da..6f2f2720f3ac 100644
--- a/include/uapi/linux/kernel-page-flags.h
+++ b/include/uapi/linux/kernel-page-flags.h
@@ -32,7 +32,7 @@
 
 #define KPF_KSM                 21
 #define KPF_THP                 22
-#define KPF_BALLOON             23
+#define KPF_OFFLINE             23
 #define KPF_ZERO_PAGE           24
 #define KPF_IDLE                25
 #define KPF_PGTABLE             26