Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "The remainder of the main mm/ queue.

  143 patches.

  Subsystems affected by this patch series (all mm): pagecache, hugetlb,
  userfaultfd, vmscan, compaction, migration, cma, ksm, vmstat, mmap,
  kconfig, util, memory-hotplug, zswap, zsmalloc, highmem, cleanups, and
  kfence"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (143 commits)
  kfence: use power-efficient work queue to run delayed work
  kfence: maximize allocation wait timeout duration
  kfence: await for allocation using wait_event
  kfence: zero guard page after out-of-bounds access
  mm/process_vm_access.c: remove duplicate include
  mm/mempool: minor coding style tweaks
  mm/highmem.c: fix coding style issue
  btrfs: use memzero_page() instead of open coded kmap pattern
  iov_iter: lift memzero_page() to highmem.h
  mm/zsmalloc: use BUG_ON instead of if condition followed by BUG.
  mm/zswap.c: switch from strlcpy to strscpy
  arm64/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
  x86/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
  mm,memory_hotplug: add kernel boot option to enable memmap_on_memory
  acpi,memhotplug: enable MHP_MEMMAP_ON_MEMORY when supported
  mm,memory_hotplug: allocate memmap from the added memory range
  mm,memory_hotplug: factor out adjusting present pages into adjust_present_page_count()
  mm,memory_hotplug: relax fully spanned sections check
  drivers/base/memory: introduce memory_block_{online,offline}
  mm/memory_hotplug: remove broken locking of zone PCP structures during hot remove
  ...

28 files changed, 358 insertions, 73 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 6b47f94378c5..e7e99da31349 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -194,6 +194,8 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size,
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
+void invalidate_bh_lrus_cpu(int cpu);
+bool has_bh_in_lru(int cpu, void *dummy);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
@@ -406,6 +408,8 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void invalidate_bh_lrus_cpu(int cpu) {}
+static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; }
 #define buffer_heads_over_limit 0
 
 #endif /* CONFIG_BLOCK */
diff --git a/include/linux/cma.h b/include/linux/cma.h
index 217999c8a762..53fd8c3cdbd0 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -44,9 +44,9 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 					unsigned int order_per_bit,
 					const char *name,
 					struct cma **res_cma);
-extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align,
+extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align,
 			      bool no_warn);
-extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count);
+extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count);
 
 extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data);
 #endif
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index ed4070ed41ef..4221888bdcd6 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -81,7 +81,6 @@ static inline unsigned long compact_gap(unsigned int order)
 }
 
 #ifdef CONFIG_COMPACTION
-extern int sysctl_compact_memory;
 extern unsigned int sysctl_compaction_proactiveness;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 12766edee81f..acef282b97c6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -442,7 +442,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
  * @i_mmap: Tree of private and shared mappings.
  * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
  * @nrpages: Number of page entries, protected by the i_pages lock.
- * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock.
  * @writeback_index: Writeback starts here.
  * @a_ops: Methods.
  * @flags: Error bits and flags (AS_*).
@@ -463,7 +462,6 @@ struct address_space {
 	struct rb_root_cached	i_mmap;
 	struct rw_semaphore	i_mmap_rwsem;
 	unsigned long		nrpages;
-	unsigned long		nrexceptional;
 	pgoff_t			writeback_index;
 	const struct address_space_operations *a_ops;
 	unsigned long		flags;
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 26f4d907254a..8a5f6c3d7dba 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -657,7 +657,7 @@ extern int alloc_contig_range(unsigned long start, unsigned long end,
 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);
+void free_contig_range(unsigned long pfn, unsigned long nr_pages);
 
 #ifdef CONFIG_CMA
 /* CMA stuff */
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 44170f312ae7..832b49b50c7b 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -332,4 +332,11 @@ static inline void memcpy_to_page(struct page *page, size_t offset,
 	kunmap_local(to);
 }
 
+static inline void memzero_page(struct page *page, size_t offset, size_t len)
+{
+	char *addr = kmap_atomic(page);
+	memset(addr + offset, 0, len);
+	kunmap_atomic(addr);
+}
+
 #endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ba973efcd369..9626fda5efce 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -87,9 +87,6 @@ enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
 	TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
-#ifdef CONFIG_DEBUG_VM
-	TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
-#endif
 };
 
 struct kobject;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index cccd1aab69dd..b92f25ccef58 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -11,6 +11,7 @@
 #include <linux/kref.h>
 #include <linux/pgtable.h>
 #include <linux/gfp.h>
+#include <linux/userfaultfd_k.h>
 
 struct ctl_table;
 struct user_struct;
@@ -134,11 +135,14 @@ void hugetlb_show_meminfo(void);
 unsigned long hugetlb_total_pages(void);
 vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags);
+#ifdef CONFIG_USERFAULTFD
 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,
+				enum mcopy_atomic_mode mode,
 				struct page **pagep);
+#endif /* CONFIG_USERFAULTFD */
 bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
@@ -152,7 +156,8 @@ void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
 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);
+pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pud_t *pud);
 
 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage);
 
@@ -161,7 +166,7 @@ extern struct list_head huge_boot_pages;
 
 /* arch callbacks */
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
@@ -187,6 +192,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
 bool is_hugetlb_entry_migration(pte_t pte);
+void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
@@ -308,16 +314,19 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	BUG();
 }
 
+#ifdef CONFIG_USERFAULTFD
 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,
+						enum mcopy_atomic_mode mode,
 						struct page **pagep)
 {
 	BUG();
 	return 0;
 }
+#endif /* CONFIG_USERFAULTFD */
 
 static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 					unsigned long sz)
@@ -368,6 +377,8 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
 	return 0;
 }
 
+static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { }
+
 #endif /* !CONFIG_HUGETLB_PAGE */
 /*
  * hugepages at page global directory. If arch support
@@ -555,6 +566,7 @@ HPAGEFLAG(Freed, freed)
 #define HSTATE_NAME_LEN 32
 /* Defines one hugetlb page size */
 struct hstate {
+	struct mutex resize_lock;
 	int next_nid_to_alloc;
 	int next_nid_to_free;
 	unsigned int order;
@@ -583,6 +595,7 @@ struct huge_bootmem_page {
 	struct hstate *hstate;
 };
 
+int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
@@ -865,6 +878,12 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
+static inline int isolate_or_dissolve_huge_page(struct page *page,
+						struct list_head *list)
+{
+	return -ENOMEM;
+}
+
 static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   int avoid_reserve)
@@ -1039,4 +1058,14 @@ static inline __init void hugetlb_cma_check(void)
 }
 #endif
 
+bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
+
+#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+/*
+ * ARCHes with special requirements for evicting HUGETLB backing TLB entries can
+ * implement this.
+ */
+#define flush_hugetlb_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
+#endif
+
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5904716f29ba..c193be760709 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -114,12 +114,13 @@ struct batched_lruvec_stat {
 };
 
 /*
- * Bitmap of shrinker::id corresponding to memcg-aware shrinkers,
- * which have elements charged to this memcg.
+ * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
+ * shrinkers, which have elements charged to this memcg.
  */
-struct memcg_shrinker_map {
+struct shrinker_info {
 	struct rcu_head rcu;
-	unsigned long map[];
+	atomic_long_t *nr_deferred;
+	unsigned long *map;
 };
 
 /*
@@ -145,7 +146,7 @@ struct mem_cgroup_per_node {
 
 	struct mem_cgroup_reclaim_iter	iter;
 
-	struct memcg_shrinker_map __rcu	*shrinker_map;
+	struct shrinker_info __rcu	*shrinker_info;
 
 	struct rb_node		tree_node;	/* RB tree node */
 	unsigned long		usage_in_excess;/* Set to the value by which */
@@ -1610,10 +1611,10 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 	return false;
 }
 
-extern int memcg_expand_shrinker_maps(int new_id);
-
-extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
-				   int nid, int shrinker_id);
+int alloc_shrinker_info(struct mem_cgroup *memcg);
+void free_shrinker_info(struct mem_cgroup *memcg);
+void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id);
+void reparent_shrinker_deferred(struct mem_cgroup *memcg);
 #else
 #define mem_cgroup_sockets_enabled 0
 static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
@@ -1623,8 +1624,8 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 	return false;
 }
 
-static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
-					  int nid, int shrinker_id)
+static inline void set_shrinker_bit(struct mem_cgroup *memcg,
+				    int nid, int shrinker_id)
 {
 }
 #endif
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 4da95e684e20..97e92e8b556a 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -29,6 +29,11 @@ struct memory_block {
 	int online_type;		/* for passing data to online routine */
 	int nid;			/* NID for this memory block */
 	struct device dev;
+	/*
+	 * Number of vmemmap pages. These pages
+	 * lay at the beginning of the memory block.
+	 */
+	unsigned long nr_vmemmap_pages;
 };
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
@@ -80,7 +85,8 @@ static inline int memory_notify(unsigned long val, void *v)
 #else
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
-int create_memory_block_devices(unsigned long start, unsigned long size);
+int create_memory_block_devices(unsigned long start, unsigned long size,
+				unsigned long vmemmap_pages);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 7288aa5ef73b..28f32fd00fe9 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -56,6 +56,14 @@ typedef int __bitwise mhp_t;
 #define MHP_MERGE_RESOURCE	((__force mhp_t)BIT(0))
 
 /*
+ * We want memmap (struct page array) to be self contained.
+ * To do so, we will use the beginning of the hot-added range to build
+ * the page tables for the memmap array that describes the entire range.
+ * Only selected architectures support it with SPARSE_VMEMMAP.
+ */
+#define MHP_MEMMAP_ON_MEMORY   ((__force mhp_t)BIT(1))
+
+/*
  * Extended parameters for memory hotplug:
  * altmap: alternative allocator for memmap array (optional)
  * pgprot: page protection flags to apply to newly created page tables
@@ -99,9 +107,13 @@ static inline void zone_seqlock_init(struct zone *zone)
 extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
+extern void adjust_present_page_count(struct zone *zone, long nr_pages);
 /* VM interface that may be used by firmware interface */
+extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
+				     struct zone *zone);
+extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages);
 extern int online_pages(unsigned long pfn, unsigned long nr_pages,
-			int online_type, int nid);
+			struct zone *zone);
 extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
 					 unsigned long end_pfn);
 extern void __offline_isolated_pages(unsigned long start_pfn,
@@ -359,6 +371,7 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_
 extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
 				      struct mhp_params *params);
 void arch_remove_linear_mapping(u64 start, u64 size);
+extern bool mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index f5b464daeeca..45a79da89c5f 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -17,7 +17,7 @@ struct device;
  * @alloc: track pages consumed, private to vmemmap_populate()
  */
 struct vmem_altmap {
-	const unsigned long base_pfn;
+	unsigned long base_pfn;
 	const unsigned long end_pfn;
 	const unsigned long reserve;
 	unsigned long free;
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 3a389633b68f..4bb4e519e3f5 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -27,6 +27,7 @@ enum migrate_reason {
 	MR_MEMPOLICY_MBIND,
 	MR_NUMA_MISPLACED,
 	MR_CONTIG_RANGE,
+	MR_LONGTERM_PIN,
 	MR_TYPES
 };
 
@@ -43,10 +44,7 @@ extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 		unsigned long private, enum migrate_mode mode, int reason);
 extern struct page *alloc_migration_target(struct page *page, unsigned long private);
 extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
-extern void putback_movable_page(struct page *page);
 
-extern void migrate_prep(void);
-extern void migrate_prep_local(void);
 extern void migrate_page_states(struct page *newpage, struct page *page);
 extern void migrate_page_copy(struct page *newpage, struct page *page);
 extern int migrate_huge_page_move_mapping(struct address_space *mapping,
@@ -66,9 +64,6 @@ static inline struct page *alloc_migration_target(struct page *page,
 static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
 	{ return -EBUSY; }
 
-static inline int migrate_prep(void) { return -ENOSYS; }
-static inline int migrate_prep_local(void) { return -ENOSYS; }
-
 static inline void migrate_page_states(struct page *newpage, struct page *page)
 {
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 011f43605807..76e27ebb28a3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -372,6 +372,13 @@ extern unsigned int kobjsize(const void *objp);
 # define VM_GROWSUP	VM_NONE
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+# define VM_UFFD_MINOR_BIT	37
+# define VM_UFFD_MINOR		BIT(VM_UFFD_MINOR_BIT)	/* UFFD minor faults */
+#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
+# define VM_UFFD_MINOR		VM_NONE
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
+
 /* Bits set in the VMA until the stack is in its final location */
 #define VM_STACK_INCOMPLETE_SETUP	(VM_RAND_READ | VM_SEQ_READ)
 
@@ -1134,6 +1141,11 @@ static inline bool is_zone_device_page(const struct page *page)
 }
 #endif
 
+static inline bool is_zone_movable_page(const struct page *page)
+{
+	return page_zonenum(page) == ZONE_MOVABLE;
+}
+
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 void free_devmap_managed_page(struct page *page);
 DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
@@ -1543,6 +1555,20 @@ static inline unsigned long page_to_section(const struct page *page)
 }
 #endif
 
+/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
+#ifdef CONFIG_MIGRATION
+static inline bool is_pinnable_page(struct page *page)
+{
+	return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) ||
+		is_zero_pfn(page_to_pfn(page));
+}
+#else
+static inline bool is_pinnable_page(struct page *page)
+{
+	return true;
+}
+#endif
+
 static inline void set_page_zone(struct page *page, enum zone_type zone)
 {
 	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3b2205741048..917bd6c604d5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -407,8 +407,13 @@ enum zone_type {
 	 * to increase the number of THP/huge pages. Notable special cases are:
 	 *
 	 * 1. Pinned pages: (long-term) pinning of movable pages might
-	 *    essentially turn such pages unmovable. Memory offlining might
-	 *    retry a long time.
+	 *    essentially turn such pages unmovable. Therefore, we do not allow
+	 *    pinning long-term pages in ZONE_MOVABLE. When pages are pinned and
+	 *    faulted, they come from the right zone right away. However, it is
+	 *    still possible that address space already has pages in
+	 *    ZONE_MOVABLE at the time when pages are pinned (i.e. user has
+	 *    touches that memory before pinning). In such case we migrate them
+	 *    to a different zone. When migration fails - pinning fails.
 	 * 2. memblock allocations: kernelcore/movablecore setups might create
 	 *    situations where ZONE_MOVABLE contains unmovable allocations
 	 *    after boot. Memory offlining and allocations fail early.
@@ -427,6 +432,15 @@ enum zone_type {
 	 *    techniques might use alloc_contig_range() to hide previously
 	 *    exposed pages from the buddy again (e.g., to implement some sort
 	 *    of memory unplug in virtio-mem).
+	 * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create
+	 *    situations where ZERO_PAGE(0) which is allocated differently
+	 *    on different platforms may end up in a movable zone. ZERO_PAGE(0)
+	 *    cannot be migrated.
+	 * 7. Memory-hotplug: when using memmap_on_memory and onlining the
+	 *    memory to the MOVABLE zone, the vmemmap pages are also placed in
+	 *    such zone. Such pages cannot be really moved around as they are
+	 *    self-stored in the range, but they are treated as movable when
+	 *    the range they describe is about to be offlined.
 	 *
 	 * In general, no unmovable allocations that degrade memory offlining
 	 * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range())
@@ -1383,10 +1397,8 @@ static inline int online_section_nr(unsigned long nr)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
 #endif
-#endif
 
 static inline struct mem_section *__pfn_to_section(unsigned long pfn)
 {
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 469fa7ffcf96..a4bd41128bf3 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -18,6 +18,11 @@
 
 struct pagevec;
 
+static inline bool mapping_empty(struct address_space *mapping)
+{
+	return xa_empty(&mapping->i_pages);
+}
+
 /*
  * Bits in mapping->flags.
  */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 5e772392a379..2194a9cd885c 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1111,6 +1111,7 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 extern void untrack_pfn_moved(struct vm_area_struct *vma);
 #endif
 
+#ifdef CONFIG_MMU
 #ifdef __HAVE_COLOR_ZERO_PAGE
 static inline int is_zero_pfn(unsigned long pfn)
 {
@@ -1134,6 +1135,17 @@ static inline unsigned long my_zero_pfn(unsigned long addr)
 	return zero_pfn;
 }
 #endif
+#else
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	return 0;
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	return 0;
+}
+#endif /* CONFIG_MMU */
 
 #ifdef CONFIG_MMU
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c25c8e67030..d2c881384517 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1583,7 +1583,7 @@ extern struct pid *cad_pid;
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #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_MEMALLOC_PIN		0x10000000	/* Allocation context constrained to zones which allow long term pinning. */
 #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 90b2a0bce11c..e24b1fe348e3 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -151,12 +151,13 @@ 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_PIN  implies !GFP_MOVABLE
  */
 static inline gfp_t current_gfp_context(gfp_t flags)
 {
 	unsigned int pflags = READ_ONCE(current->flags);
 
-	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS))) {
+	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) {
 		/*
 		 * NOIO implies both NOIO and NOFS and it is a weaker context
 		 * so always make sure it makes precedence
@@ -165,6 +166,9 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 			flags &= ~(__GFP_IO | __GFP_FS);
 		else if (pflags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
+
+		if (pflags & PF_MEMALLOC_PIN)
+			flags &= ~__GFP_MOVABLE;
 	}
 	return flags;
 }
@@ -271,29 +275,18 @@ 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)
+static inline unsigned int memalloc_pin_save(void)
 {
-	unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
+	unsigned int flags = current->flags & PF_MEMALLOC_PIN;
 
-	current->flags |= PF_MEMALLOC_NOCMA;
+	current->flags |= PF_MEMALLOC_PIN;
 	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)
+static inline void memalloc_pin_restore(unsigned int flags)
 {
+	current->flags = (current->flags & ~PF_MEMALLOC_PIN) | flags;
 }
-#endif
 
 #ifdef CONFIG_MEMCG
 DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 0f80123650e2..1eac79ce57d4 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -79,13 +79,14 @@ struct shrinker {
 #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
 
 /* Flags */
-#define SHRINKER_NUMA_AWARE	(1 << 0)
-#define SHRINKER_MEMCG_AWARE	(1 << 1)
+#define SHRINKER_REGISTERED	(1 << 0)
+#define SHRINKER_NUMA_AWARE	(1 << 1)
+#define SHRINKER_MEMCG_AWARE	(1 << 2)
 /*
  * It just makes sense when the shrinker is also MEMCG_AWARE for now,
  * non-MEMCG_AWARE shrinker should not have this flag set.
  */
-#define SHRINKER_NONSLAB	(1 << 2)
+#define SHRINKER_NONSLAB	(1 << 3)
 
 extern int prealloc_shrinker(struct shrinker *shrinker);
 extern void register_shrinker_prepared(struct shrinker *shrinker);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4cc6ec3bf0ab..f69e0f67651d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -12,6 +12,7 @@
 #include <linux/fs.h>
 #include <linux/atomic.h>
 #include <linux/page-flags.h>
+#include <uapi/linux/mempolicy.h>
 #include <asm/page.h>
 
 struct notifier_block;
@@ -339,6 +340,20 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file,
 extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
 extern void mark_page_accessed(struct page *);
+
+extern atomic_t lru_disable_count;
+
+static inline bool lru_cache_disabled(void)
+{
+	return atomic_read(&lru_disable_count);
+}
+
+static inline void lru_cache_enable(void)
+{
+	atomic_dec(&lru_disable_count);
+}
+
+extern void lru_cache_disable(void);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_cpu_zone(struct zone *zone);
@@ -378,6 +393,12 @@ extern int sysctl_min_slab_ratio;
 #define node_reclaim_mode 0
 #endif
 
+static inline bool node_reclaim_enabled(void)
+{
+	/* Is any node_reclaim_mode bit set? */
+	return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP);
+}
+
 extern void check_move_unevictable_pages(struct pagevec *pvec);
 
 extern int kswapd_run(int nid);
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index a8e5f3ea9bb2..794d1538b8ba 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -17,6 +17,9 @@
 #include <linux/mm.h>
 #include <asm-generic/pgtable_uffd.h>
 
+/* The set of all possible UFFD-related VM flags. */
+#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR)
+
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
  * new flags, since they might collide with O_* ones. We want
@@ -34,6 +37,22 @@ extern int sysctl_unprivileged_userfaultfd;
 
 extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
+/*
+ * The mode of operation for __mcopy_atomic and its helpers.
+ *
+ * This is almost an implementation detail (mcopy_atomic below doesn't take this
+ * as a parameter), but it's exposed here because memory-kind-specific
+ * implementations (e.g. hugetlbfs) need to know the mode of operation.
+ */
+enum mcopy_atomic_mode {
+	/* A normal copy_from_user into the destination range. */
+	MCOPY_ATOMIC_NORMAL,
+	/* Don't copy; map the destination range to the zero page. */
+	MCOPY_ATOMIC_ZEROPAGE,
+	/* Just install pte(s) with the existing page(s) in the page cache. */
+	MCOPY_ATOMIC_CONTINUE,
+};
+
 extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 			    unsigned long src_start, unsigned long len,
 			    bool *mmap_changing, __u64 mode);
@@ -41,6 +60,8 @@ extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
 			      unsigned long dst_start,
 			      unsigned long len,
 			      bool *mmap_changing);
+extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start,
+			      unsigned long len, bool *mmap_changing);
 extern int mwriteprotect_range(struct mm_struct *dst_mm,
 			       unsigned long start, unsigned long len,
 			       bool enable_wp, bool *mmap_changing);
@@ -52,6 +73,22 @@ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 	return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx;
 }
 
+/*
+ * Never enable huge pmd sharing on some uffd registered vmas:
+ *
+ * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry.
+ *
+ * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for
+ *   VMAs which share huge pmds. (If you have two mappings to the same
+ *   underlying pages, and fault in the non-UFFD-registered one with a write,
+ *   with huge pmd sharing this would *also* setup the second UFFD-registered
+ *   mapping, and we'd not get minor faults.)
+ */
+static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR);
+}
+
 static inline bool userfaultfd_missing(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & VM_UFFD_MISSING;
@@ -62,6 +99,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_UFFD_WP;
 }
 
+static inline bool userfaultfd_minor(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & VM_UFFD_MINOR;
+}
+
 static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
 				      pte_t pte)
 {
@@ -76,7 +118,7 @@ static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma,
 
 static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 {
-	return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP);
+	return vma->vm_flags & __VM_UFFD_FLAGS;
 }
 
 extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
@@ -123,6 +165,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline bool userfaultfd_minor(struct vm_area_struct *vma)
+{
+	return false;
+}
+
 static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
 				      pte_t pte)
 {
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 18e75974d4e3..ae0dd1948c2b 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -71,6 +71,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_HUGETLB_PAGE
 		HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
 #endif
+#ifdef CONFIG_CMA
+		CMA_ALLOC_SUCCESS,
+		CMA_ALLOC_FAIL,
+#endif
 		UNEVICTABLE_PGCULLED,	/* culled to noreclaim list */
 		UNEVICTABLE_PGSCANNED,	/* scanned for reclaimability */
 		UNEVICTABLE_PGRESCUED,	/* rescued from noreclaim list */
@@ -121,6 +125,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		SWAP_RA,
 		SWAP_RA_HIT,
 #endif
+#ifdef CONFIG_X86
+		DIRECT_MAP_LEVEL2_SPLIT,
+		DIRECT_MAP_LEVEL3_SPLIT,
+#endif
 		NR_VM_EVENT_ITEMS
 };
 
diff --git a/include/trace/events/cma.h b/include/trace/events/cma.h
index 5017a8829270..c3d354702cb0 100644
--- a/include/trace/events/cma.h
+++ b/include/trace/events/cma.h
@@ -8,28 +8,31 @@
 #include <linux/types.h>
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(cma_alloc,
+DECLARE_EVENT_CLASS(cma_alloc_class,
 
-	TP_PROTO(unsigned long pfn, const struct page *page,
-		 unsigned int count, unsigned int align),
+	TP_PROTO(const char *name, unsigned long pfn, const struct page *page,
+		 unsigned long count, unsigned int align),
 
-	TP_ARGS(pfn, page, count, align),
+	TP_ARGS(name, pfn, page, count, align),
 
 	TP_STRUCT__entry(
+		__string(name, name)
 		__field(unsigned long, pfn)
 		__field(const struct page *, page)
-		__field(unsigned int, count)
+		__field(unsigned long, count)
 		__field(unsigned int, align)
 	),
 
 	TP_fast_assign(
+		__assign_str(name, name);
 		__entry->pfn = pfn;
 		__entry->page = page;
 		__entry->count = count;
 		__entry->align = align;
 	),
 
-	TP_printk("pfn=%lx page=%p count=%u align=%u",
+	TP_printk("name=%s pfn=%lx page=%p count=%lu align=%u",
+		  __get_str(name),
 		  __entry->pfn,
 		  __entry->page,
 		  __entry->count,
@@ -38,29 +41,72 @@ TRACE_EVENT(cma_alloc,
 
 TRACE_EVENT(cma_release,
 
-	TP_PROTO(unsigned long pfn, const struct page *page,
-		 unsigned int count),
+	TP_PROTO(const char *name, unsigned long pfn, const struct page *page,
+		 unsigned long count),
 
-	TP_ARGS(pfn, page, count),
+	TP_ARGS(name, pfn, page, count),
 
 	TP_STRUCT__entry(
+		__string(name, name)
 		__field(unsigned long, pfn)
 		__field(const struct page *, page)
-		__field(unsigned int, count)
+		__field(unsigned long, count)
 	),
 
 	TP_fast_assign(
+		__assign_str(name, name);
 		__entry->pfn = pfn;
 		__entry->page = page;
 		__entry->count = count;
 	),
 
-	TP_printk("pfn=%lx page=%p count=%u",
+	TP_printk("name=%s pfn=%lx page=%p count=%lu",
+		  __get_str(name),
 		  __entry->pfn,
 		  __entry->page,
 		  __entry->count)
 );
 
+TRACE_EVENT(cma_alloc_start,
+
+	TP_PROTO(const char *name, unsigned long count, unsigned int align),
+
+	TP_ARGS(name, count, align),
+
+	TP_STRUCT__entry(
+		__string(name, name)
+		__field(unsigned long, count)
+		__field(unsigned int, align)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->count = count;
+		__entry->align = align;
+	),
+
+	TP_printk("name=%s count=%lu align=%u",
+		  __get_str(name),
+		  __entry->count,
+		  __entry->align)
+);
+
+DEFINE_EVENT(cma_alloc_class, cma_alloc_finish,
+
+	TP_PROTO(const char *name, unsigned long pfn, const struct page *page,
+		 unsigned long count, unsigned int align),
+
+	TP_ARGS(name, pfn, page, count, align)
+);
+
+DEFINE_EVENT(cma_alloc_class, cma_alloc_busy_retry,
+
+	TP_PROTO(const char *name, unsigned long pfn, const struct page *page,
+		 unsigned long count, unsigned int align),
+
+	TP_ARGS(name, pfn, page, count, align)
+);
+
 #endif /* _TRACE_CMA_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index 4d434398d64d..9fb2a3bbcdfb 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -20,7 +20,8 @@
 	EM( MR_SYSCALL,		"syscall_or_cpuset")		\
 	EM( MR_MEMPOLICY_MBIND,	"mempolicy_mbind")		\
 	EM( MR_NUMA_MISPLACED,	"numa_misplaced")		\
-	EMe(MR_CONTIG_RANGE,	"contig_range")
+	EM( MR_CONTIG_RANGE,	"contig_range")			\
+	EMe(MR_LONGTERM_PIN,	"longterm_pin")
 
 /*
  * First define the enums in the above macros to be exported to userspace
@@ -81,6 +82,28 @@ TRACE_EVENT(mm_migrate_pages,
 		__print_symbolic(__entry->mode, MIGRATE_MODE),
 		__print_symbolic(__entry->reason, MIGRATE_REASON))
 );
+
+TRACE_EVENT(mm_migrate_pages_start,
+
+	TP_PROTO(enum migrate_mode mode, int reason),
+
+	TP_ARGS(mode, reason),
+
+	TP_STRUCT__entry(
+		__field(enum migrate_mode, mode)
+		__field(int, reason)
+	),
+
+	TP_fast_assign(
+		__entry->mode	= mode;
+		__entry->reason	= reason;
+	),
+
+	TP_printk("mode=%s reason=%s",
+		  __print_symbolic(__entry->mode, MIGRATE_MODE),
+		  __print_symbolic(__entry->reason, MIGRATE_REASON))
+);
+
 #endif /* _TRACE_MIGRATE_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 67018d367b9f..629c7a0eaff2 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -137,6 +137,12 @@ IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)
 #define IF_HAVE_VM_SOFTDIRTY(flag,name)
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+# define IF_HAVE_UFFD_MINOR(flag, name) {flag, name},
+#else
+# define IF_HAVE_UFFD_MINOR(flag, name)
+#endif
+
 #define __def_vmaflag_names						\
 	{VM_READ,			"read"		},		\
 	{VM_WRITE,			"write"		},		\
@@ -148,6 +154,7 @@ IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)
 	{VM_MAYSHARE,			"mayshare"	},		\
 	{VM_GROWSDOWN,			"growsdown"	},		\
 	{VM_UFFD_MISSING,		"uffd_missing"	},		\
+IF_HAVE_UFFD_MINOR(VM_UFFD_MINOR,	"uffd_minor"	)		\
 	{VM_PFNMAP,			"pfnmap"	},		\
 	{VM_DENYWRITE,			"denywrite"	},		\
 	{VM_UFFD_WP,			"uffd_wp"	},		\
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 8948467b3992..4832fd0b5642 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -64,5 +64,12 @@ enum {
 #define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
 #define MPOL_F_MORON	(1 << 4) /* Migrate On protnone Reference On Node */
 
+/*
+ * These bit locations are exposed in the vm.zone_reclaim_mode sysctl
+ * ABI.  New bits are OK, but existing bits can never change.
+ */
+#define RECLAIM_ZONE	(1<<0)	/* Run shrink_inactive_list on the zone */
+#define RECLAIM_WRITE	(1<<1)	/* Writeout pages during reclaim */
+#define RECLAIM_UNMAP	(1<<2)	/* Unmap pages during reclaim */
 
 #endif /* _UAPI_LINUX_MEMPOLICY_H */
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 5f2d88212f7c..bafbeb1a2624 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -19,15 +19,19 @@
  * means the userland is reading).
  */
 #define UFFD_API ((__u64)0xAA)
+#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING |	\
+				 UFFDIO_REGISTER_MODE_WP |	\
+				 UFFDIO_REGISTER_MODE_MINOR)
 #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP |	\
 			   UFFD_FEATURE_EVENT_FORK |		\
 			   UFFD_FEATURE_EVENT_REMAP |		\
-			   UFFD_FEATURE_EVENT_REMOVE |	\
+			   UFFD_FEATURE_EVENT_REMOVE |		\
 			   UFFD_FEATURE_EVENT_UNMAP |		\
 			   UFFD_FEATURE_MISSING_HUGETLBFS |	\
 			   UFFD_FEATURE_MISSING_SHMEM |		\
 			   UFFD_FEATURE_SIGBUS |		\
-			   UFFD_FEATURE_THREAD_ID)
+			   UFFD_FEATURE_THREAD_ID |		\
+			   UFFD_FEATURE_MINOR_HUGETLBFS)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -36,10 +40,12 @@
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
 	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
-	 (__u64)1 << _UFFDIO_WRITEPROTECT)
+	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
+	 (__u64)1 << _UFFDIO_CONTINUE)
 #define UFFD_API_RANGE_IOCTLS_BASIC		\
 	((__u64)1 << _UFFDIO_WAKE |		\
-	 (__u64)1 << _UFFDIO_COPY)
+	 (__u64)1 << _UFFDIO_COPY |		\
+	 (__u64)1 << _UFFDIO_CONTINUE)
 
 /*
  * Valid ioctl command number range with this API is from 0x00 to
@@ -55,6 +61,7 @@
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
 #define _UFFDIO_WRITEPROTECT		(0x06)
+#define _UFFDIO_CONTINUE		(0x07)
 #define _UFFDIO_API			(0x3F)
 
 /* userfaultfd ioctl ids */
@@ -73,6 +80,8 @@
 				      struct uffdio_zeropage)
 #define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
 				      struct uffdio_writeprotect)
+#define UFFDIO_CONTINUE		_IOR(UFFDIO, _UFFDIO_CONTINUE,	\
+				     struct uffdio_continue)
 
 /* read() structure */
 struct uffd_msg {
@@ -127,6 +136,7 @@ struct uffd_msg {
 /* flags for UFFD_EVENT_PAGEFAULT */
 #define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
 #define UFFD_PAGEFAULT_FLAG_WP		(1<<1)	/* If reason is VM_UFFD_WP */
+#define UFFD_PAGEFAULT_FLAG_MINOR	(1<<2)	/* If reason is VM_UFFD_MINOR */
 
 struct uffdio_api {
 	/* userland asks for an API number and the features to enable */
@@ -171,6 +181,10 @@ struct uffdio_api {
 	 *
 	 * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will
 	 * be returned, if feature is not requested 0 will be returned.
+	 *
+	 * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults
+	 * can be intercepted (via REGISTER_MODE_MINOR) for
+	 * hugetlbfs-backed pages.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -181,6 +195,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_EVENT_UNMAP		(1<<6)
 #define UFFD_FEATURE_SIGBUS			(1<<7)
 #define UFFD_FEATURE_THREAD_ID			(1<<8)
+#define UFFD_FEATURE_MINOR_HUGETLBFS		(1<<9)
 	__u64 features;
 
 	__u64 ioctls;
@@ -195,6 +210,7 @@ struct uffdio_register {
 	struct uffdio_range range;
 #define UFFDIO_REGISTER_MODE_MISSING	((__u64)1<<0)
 #define UFFDIO_REGISTER_MODE_WP		((__u64)1<<1)
+#define UFFDIO_REGISTER_MODE_MINOR	((__u64)1<<2)
 	__u64 mode;
 
 	/*
@@ -257,6 +273,18 @@ struct uffdio_writeprotect {
 	__u64 mode;
 };
 
+struct uffdio_continue {
+	struct uffdio_range range;
+#define UFFDIO_CONTINUE_MODE_DONTWAKE		((__u64)1<<0)
+	__u64 mode;
+
+	/*
+	 * Fields below here are written by the ioctl and must be at the end:
+	 * the copy_from_user will not read past here.
+	 */
+	__s64 mapped;
+};
+
 /*
  * Flags for the userfaultfd(2) system call itself.
  */