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
  ...

15 files changed, 190 insertions, 110 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 97e7b77c9309..89a750d292ba 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -223,10 +223,13 @@ config TMPFS_INODE64
 
 	  If unsure, say N.
 
+config ARCH_SUPPORTS_HUGETLBFS
+	def_bool n
+
 config HUGETLBFS
 	bool "HugeTLB file system support"
 	depends on X86 || IA64 || SPARC64 || (S390 && 64BIT) || \
-		   SYS_SUPPORTS_HUGETLBFS || BROKEN
+		   ARCH_SUPPORTS_HUGETLBFS || BROKEN
 	help
 	  hugetlbfs is a filesystem backing for HugeTLB pages, based on
 	  ramfs. For architectures that support it, say Y here and read
diff --git a/fs/block_dev.c b/fs/block_dev.c
index a5244e08b6c8..9114e0a0e7b4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -79,7 +79,7 @@ static void kill_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
+	if (mapping_empty(mapping))
 		return;
 
 	invalidate_bh_lrus();
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 17f93fd28f7e..2bea01d23a5b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -591,16 +591,13 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		free_extent_map(em);
 
 		if (page->index == end_index) {
-			char *userpage;
 			size_t zero_offset = offset_in_page(isize);
 
 			if (zero_offset) {
 				int zeros;
 				zeros = PAGE_SIZE - zero_offset;
-				userpage = kmap_atomic(page);
-				memset(userpage + zero_offset, 0, zeros);
+				memzero_page(page, zero_offset, zeros);
 				flush_dcache_page(page);
-				kunmap_atomic(userpage);
 			}
 		}
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f2d1bb234377..074a78a202b8 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3421,15 +3421,12 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 	}
 
 	if (page->index == last_byte >> PAGE_SHIFT) {
-		char *userpage;
 		size_t zero_offset = offset_in_page(last_byte);
 
 		if (zero_offset) {
 			iosize = PAGE_SIZE - zero_offset;
-			userpage = kmap_atomic(page);
-			memset(userpage + zero_offset, 0, iosize);
+			memzero_page(page, zero_offset, iosize);
 			flush_dcache_page(page);
-			kunmap_atomic(userpage);
 		}
 	}
 	begin_page_read(fs_info, page);
@@ -3438,14 +3435,11 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		u64 disk_bytenr;
 
 		if (cur >= last_byte) {
-			char *userpage;
 			struct extent_state *cached = NULL;
 
 			iosize = PAGE_SIZE - pg_offset;
-			userpage = kmap_atomic(page);
-			memset(userpage + pg_offset, 0, iosize);
+			memzero_page(page, pg_offset, iosize);
 			flush_dcache_page(page);
-			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
 			unlock_extent_cached(tree, cur,
@@ -3528,13 +3522,10 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 
 		/* we've found a hole, just zero and go on */
 		if (block_start == EXTENT_MAP_HOLE) {
-			char *userpage;
 			struct extent_state *cached = NULL;
 
-			userpage = kmap_atomic(page);
-			memset(userpage + pg_offset, 0, iosize);
+			memzero_page(page, pg_offset, iosize);
 			flush_dcache_page(page);
-			kunmap_atomic(userpage);
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
@@ -3845,12 +3836,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	}
 
 	if (page->index == end_index) {
-		char *userpage;
-
-		userpage = kmap_atomic(page);
-		memset(userpage + pg_offset, 0,
-		       PAGE_SIZE - pg_offset);
-		kunmap_atomic(userpage);
+		memzero_page(page, pg_offset, PAGE_SIZE - pg_offset);
 		flush_dcache_page(page);
 	}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b21d491b3adc..4af336008b12 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -646,17 +646,12 @@ again:
 		if (!ret) {
 			unsigned long offset = offset_in_page(total_compressed);
 			struct page *page = pages[nr_pages - 1];
-			char *kaddr;
 
 			/* zero the tail end of the last page, we might be
 			 * sending it down to disk
 			 */
-			if (offset) {
-				kaddr = kmap_atomic(page);
-				memset(kaddr + offset, 0,
-				       PAGE_SIZE - offset);
-				kunmap_atomic(kaddr);
-			}
+			if (offset)
+				memzero_page(page, offset, PAGE_SIZE - offset);
 			will_compress = 1;
 		}
 	}
@@ -4833,7 +4828,6 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
 	struct extent_changeset *data_reserved = NULL;
-	char *kaddr;
 	bool only_release_metadata = false;
 	u32 blocksize = fs_info->sectorsize;
 	pgoff_t index = from >> PAGE_SHIFT;
@@ -4925,15 +4919,13 @@ again:
 	if (offset != blocksize) {
 		if (!len)
 			len = blocksize - offset;
-		kaddr = kmap(page);
 		if (front)
-			memset(kaddr + (block_start - page_offset(page)),
-				0, offset);
+			memzero_page(page, (block_start - page_offset(page)),
+				     offset);
 		else
-			memset(kaddr + (block_start - page_offset(page)) +  offset,
-				0, len);
+			memzero_page(page, (block_start - page_offset(page)) + offset,
+				     len);
 		flush_dcache_page(page);
-		kunmap(page);
 	}
 	ClearPageChecked(page);
 	set_page_dirty(page);
@@ -6832,11 +6824,9 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	 * cover that region here.
 	 */
 
-	if (max_size + pg_offset < PAGE_SIZE) {
-		char *map = kmap(page);
-		memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset);
-		kunmap(page);
-	}
+	if (max_size + pg_offset < PAGE_SIZE)
+		memzero_page(page,  pg_offset + max_size,
+			     PAGE_SIZE - max_size - pg_offset);
 	kfree(tmp);
 	return ret;
 }
@@ -8506,7 +8496,6 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
 	struct extent_changeset *data_reserved = NULL;
-	char *kaddr;
 	unsigned long zero_start;
 	loff_t size;
 	vm_fault_t ret;
@@ -8620,10 +8609,8 @@ again:
 		zero_start = PAGE_SIZE;
 
 	if (zero_start != PAGE_SIZE) {
-		kaddr = kmap(page);
-		memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start);
+		memzero_page(page, zero_start, PAGE_SIZE - zero_start);
 		flush_dcache_page(page);
-		kunmap(page);
 	}
 	ClearPageChecked(page);
 	set_page_dirty(page);
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index f4ec06b53aa0..3928ecc40d7b 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -129,12 +129,8 @@ static int copy_inline_to_page(struct btrfs_inode *inode,
 	 * So what's in the range [500, 4095] corresponds to zeroes.
 	 */
 	if (datal < block_size) {
-		char *map;
-
-		map = kmap(page);
-		memset(map + datal, 0, block_size - datal);
+		memzero_page(page, datal, block_size - datal);
 		flush_dcache_page(page);
-		kunmap(page);
 	}
 
 	SetPageUptodate(page);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index d524acf7b3e5..c3fa7d3fa770 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -375,7 +375,6 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 	unsigned long bytes_left;
 	unsigned long total_out = 0;
 	unsigned long pg_offset = 0;
-	char *kaddr;
 
 	destlen = min_t(unsigned long, destlen, PAGE_SIZE);
 	bytes_left = destlen;
@@ -455,9 +454,7 @@ next:
 	 * end of the inline extent (destlen) to the end of the page
 	 */
 	if (pg_offset < destlen) {
-		kaddr = kmap_atomic(dest_page);
-		memset(kaddr + pg_offset, 0, destlen - pg_offset);
-		kunmap_atomic(kaddr);
+		memzero_page(dest_page, pg_offset, destlen - pg_offset);
 	}
 	return ret;
 }
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 8e9626d63976..3e26b466476a 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -631,7 +631,6 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 	size_t ret2;
 	unsigned long total_out = 0;
 	unsigned long pg_offset = 0;
-	char *kaddr;
 
 	stream = ZSTD_initDStream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
@@ -696,9 +695,7 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 	ret = 0;
 finish:
 	if (pg_offset < destlen) {
-		kaddr = kmap_atomic(dest_page);
-		memset(kaddr + pg_offset, 0, destlen - pg_offset);
-		kunmap_atomic(kaddr);
+		memzero_page(dest_page, pg_offset, destlen - pg_offset);
 	}
 	return ret;
 }
diff --git a/fs/buffer.c b/fs/buffer.c
index c2e052c0fc5d..ea48c01fb76b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1260,6 +1260,15 @@ static void bh_lru_install(struct buffer_head *bh)
 	int i;
 
 	check_irqs_on();
+	/*
+	 * the refcount of buffer_head in bh_lru prevents dropping the
+	 * attached page(i.e., try_to_free_buffers) so it could cause
+	 * failing page migration.
+	 * Skip putting upcoming bh into bh_lru until migration is done.
+	 */
+	if (lru_cache_disabled())
+		return;
+
 	bh_lru_lock();
 
 	b = this_cpu_ptr(&bh_lrus);
@@ -1400,6 +1409,15 @@ __bread_gfp(struct block_device *bdev, sector_t block,
 }
 EXPORT_SYMBOL(__bread_gfp);
 
+static void __invalidate_bh_lrus(struct bh_lru *b)
+{
+	int i;
+
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		brelse(b->bhs[i]);
+		b->bhs[i] = NULL;
+	}
+}
 /*
  * invalidate_bh_lrus() is called rarely - but not only at unmount.
  * This doesn't race because it runs in each cpu either in irq
@@ -1408,16 +1426,12 @@ EXPORT_SYMBOL(__bread_gfp);
 static void invalidate_bh_lru(void *arg)
 {
 	struct bh_lru *b = &get_cpu_var(bh_lrus);
-	int i;
 
-	for (i = 0; i < BH_LRU_SIZE; i++) {
-		brelse(b->bhs[i]);
-		b->bhs[i] = NULL;
-	}
+	__invalidate_bh_lrus(b);
 	put_cpu_var(bh_lrus);
 }
 
-static bool has_bh_in_lru(int cpu, void *dummy)
+bool has_bh_in_lru(int cpu, void *dummy)
 {
 	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
 	int i;
@@ -1436,6 +1450,16 @@ void invalidate_bh_lrus(void)
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
+void invalidate_bh_lrus_cpu(int cpu)
+{
+	struct bh_lru *b;
+
+	bh_lru_lock();
+	b = per_cpu_ptr(&bh_lrus, cpu);
+	__invalidate_bh_lrus(b);
+	bh_lru_unlock();
+}
+
 void set_bh_page(struct buffer_head *bh,
 		struct page *page, unsigned long offset)
 {
diff --git a/fs/dax.c b/fs/dax.c
index b3d27fdc6775..69216241392f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -525,7 +525,7 @@ retry:
 		dax_disassociate_entry(entry, mapping, false);
 		xas_store(xas, NULL);	/* undo the PMD join */
 		dax_wake_entry(xas, entry, true);
-		mapping->nrexceptional--;
+		mapping->nrpages -= PG_PMD_NR;
 		entry = NULL;
 		xas_set(xas, index);
 	}
@@ -541,7 +541,7 @@ retry:
 		dax_lock_entry(xas, entry);
 		if (xas_error(xas))
 			goto out_unlock;
-		mapping->nrexceptional++;
+		mapping->nrpages += 1UL << order;
 	}
 
 out_unlock:
@@ -661,7 +661,7 @@ static int __dax_invalidate_entry(struct address_space *mapping,
 		goto out;
 	dax_disassociate_entry(entry, mapping, trunc);
 	xas_store(&xas, NULL);
-	mapping->nrexceptional--;
+	mapping->nrpages -= 1UL << dax_entry_order(entry);
 	ret = 1;
 out:
 	put_unlocked_entry(&xas, entry);
@@ -965,7 +965,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
 		return -EIO;
 
-	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+	if (mapping_empty(mapping) || wbc->sync_mode != WB_SYNC_ALL)
 		return 0;
 
 	trace_dax_writeback_range(inode, xas.xa_index, end_index);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 84c38103aa06..ea7fc5c641c7 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -273,8 +273,7 @@ static void __gfs2_glock_put(struct gfs2_glock *gl)
 	if (mapping) {
 		truncate_inode_pages_final(mapping);
 		if (!gfs2_withdrawn(sdp))
-			GLOCK_BUG_ON(gl, mapping->nrpages ||
-				     mapping->nrexceptional);
+			GLOCK_BUG_ON(gl, !mapping_empty(mapping));
 	}
 	trace_gfs2_glock_put(gl);
 	sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 701c82c36138..a2a42335e8fd 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -463,14 +463,11 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	struct address_space *mapping = &inode->i_data;
 	const pgoff_t start = lstart >> huge_page_shift(h);
 	const pgoff_t end = lend >> huge_page_shift(h);
-	struct vm_area_struct pseudo_vma;
 	struct pagevec pvec;
 	pgoff_t next, index;
 	int i, freed = 0;
 	bool truncate_op = (lend == LLONG_MAX);
 
-	vma_init(&pseudo_vma, current->mm);
-	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pagevec_init(&pvec);
 	next = start;
 	while (next < end) {
@@ -482,10 +479,9 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 
 		for (i = 0; i < pagevec_count(&pvec); ++i) {
 			struct page *page = pvec.pages[i];
-			u32 hash;
+			u32 hash = 0;
 
 			index = page->index;
-			hash = hugetlb_fault_mutex_hash(mapping, index);
 			if (!truncate_op) {
 				/*
 				 * Only need to hold the fault mutex in the
@@ -493,6 +489,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 				 * page faults.  Races are not possible in the
 				 * case of truncation.
 				 */
+				hash = hugetlb_fault_mutex_hash(mapping, index);
 				mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			}
 
@@ -1435,7 +1432,7 @@ static int get_hstate_idx(int page_size_log)
 
 	if (!h)
 		return -1;
-	return h - hstates;
+	return hstate_index(h);
 }
 
 /*
diff --git a/fs/inode.c b/fs/inode.c
index 9e192bea0630..c93500d84264 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -529,7 +529,14 @@ void clear_inode(struct inode *inode)
 	 */
 	xa_lock_irq(&inode->i_data.i_pages);
 	BUG_ON(inode->i_data.nrpages);
-	BUG_ON(inode->i_data.nrexceptional);
+	/*
+	 * Almost always, mapping_empty(&inode->i_data) here; but there are
+	 * two known and long-standing ways in which nodes may get left behind
+	 * (when deep radix-tree node allocation failed partway; or when THP
+	 * collapse_file() failed). Until those two known cases are cleaned up,
+	 * or a cleanup function is called here, do not BUG_ON(!mapping_empty),
+	 * nor even WARN_ON(!mapping_empty).
+	 */
 	xa_unlock_irq(&inode->i_data.i_pages);
 	BUG_ON(!list_empty(&inode->i_data.private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e862cab69583..fc9784544b24 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -661,6 +661,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_PKEY_BIT4)]	= "",
 #endif
 #endif /* CONFIG_ARCH_HAS_PKEYS */
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+		[ilog2(VM_UFFD_MINOR)]	= "ui",
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
 	};
 	size_t i;
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 0be8cdd4425a..14f92285d04f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -15,6 +15,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/mm.h>
+#include <linux/mmu_notifier.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
@@ -196,24 +197,21 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
 	msg_init(&msg);
 	msg.event = UFFD_EVENT_PAGEFAULT;
 	msg.arg.pagefault.address = address;
+	/*
+	 * These flags indicate why the userfault occurred:
+	 * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
+	 * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault.
+	 * - Neither of these flags being set indicates a MISSING fault.
+	 *
+	 * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write
+	 * fault. Otherwise, it was a read fault.
+	 */
 	if (flags & FAULT_FLAG_WRITE)
-		/*
-		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
-		 * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE
-		 * was not set in a UFFD_EVENT_PAGEFAULT, it means it
-		 * was a read fault, otherwise if set it means it's
-		 * a write fault.
-		 */
 		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
 	if (reason & VM_UFFD_WP)
-		/*
-		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
-		 * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was
-		 * not set in a UFFD_EVENT_PAGEFAULT, it means it was
-		 * a missing fault, otherwise if set it means it's a
-		 * write protect fault.
-		 */
 		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
+	if (reason & VM_UFFD_MINOR)
+		msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR;
 	if (features & UFFD_FEATURE_THREAD_ID)
 		msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
 	return msg;
@@ -400,8 +398,10 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 
 	BUG_ON(ctx->mm != mm);
 
-	VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP));
-	VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP));
+	/* Any unrecognized flag is a bug. */
+	VM_BUG_ON(reason & ~__VM_UFFD_FLAGS);
+	/* 0 or > 1 flags set is a bug; we expect exactly 1. */
+	VM_BUG_ON(!reason || (reason & (reason - 1)));
 
 	if (ctx->features & UFFD_FEATURE_SIGBUS)
 		goto out;
@@ -611,7 +611,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 		for (vma = mm->mmap; vma; vma = vma->vm_next)
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-				vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+				vma->vm_flags &= ~__VM_UFFD_FLAGS;
 			}
 		mmap_write_unlock(mm);
 
@@ -643,7 +643,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 	octx = vma->vm_userfaultfd_ctx.ctx;
 	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+		vma->vm_flags &= ~__VM_UFFD_FLAGS;
 		return 0;
 	}
 
@@ -725,7 +725,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 	} else {
 		/* Drop uffd context if remap feature not enabled */
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+		vma->vm_flags &= ~__VM_UFFD_FLAGS;
 	}
 }
 
@@ -866,12 +866,12 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		cond_resched();
 		BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
-		       !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+		       !!(vma->vm_flags & __VM_UFFD_FLAGS));
 		if (vma->vm_userfaultfd_ctx.ctx != ctx) {
 			prev = vma;
 			continue;
 		}
-		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
 		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
 				 new_flags, vma->anon_vma,
 				 vma->vm_file, vma->vm_pgoff,
@@ -1261,9 +1261,19 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 				     unsigned long vm_flags)
 {
 	/* FIXME: add WP support to hugetlbfs and shmem */
-	return vma_is_anonymous(vma) ||
-		((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
-		 !(vm_flags & VM_UFFD_WP));
+	if (vm_flags & VM_UFFD_WP) {
+		if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
+			return false;
+	}
+
+	if (vm_flags & VM_UFFD_MINOR) {
+		/* FIXME: Add minor fault interception for shmem. */
+		if (!is_vm_hugetlb_page(vma))
+			return false;
+	}
+
+	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
+	       vma_is_shmem(vma);
 }
 
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
@@ -1289,14 +1299,19 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	ret = -EINVAL;
 	if (!uffdio_register.mode)
 		goto out;
-	if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING|
-				     UFFDIO_REGISTER_MODE_WP))
+	if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES)
 		goto out;
 	vm_flags = 0;
 	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
 		vm_flags |= VM_UFFD_MISSING;
 	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
 		vm_flags |= VM_UFFD_WP;
+	if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+		goto out;
+#endif
+		vm_flags |= VM_UFFD_MINOR;
+	}
 
 	ret = validate_range(mm, &uffdio_register.range.start,
 			     uffdio_register.range.len);
@@ -1340,7 +1355,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		cond_resched();
 
 		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
-		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+		       !!(cur->vm_flags & __VM_UFFD_FLAGS));
 
 		/* check not compatible vmas */
 		ret = -EINVAL;
@@ -1420,8 +1435,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 			start = vma->vm_start;
 		vma_end = min(end, vma->vm_end);
 
-		new_flags = (vma->vm_flags &
-			     ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags;
+		new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
 		prev = vma_merge(mm, prev, start, vma_end, new_flags,
 				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
 				 vma_policy(vma),
@@ -1449,6 +1463,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx.ctx = ctx;
 
+		if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
+			hugetlb_unshare_all_pmds(vma);
+
 	skip:
 		prev = vma;
 		start = vma->vm_end;
@@ -1470,6 +1487,10 @@ out_unlock:
 		if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
 			ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
 
+		/* CONTINUE ioctl is only supported for MINOR ranges. */
+		if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR))
+			ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE);
+
 		/*
 		 * Now that we scanned all vmas we can already tell
 		 * userland which ioctls methods are guaranteed to
@@ -1540,7 +1561,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		cond_resched();
 
 		BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
-		       !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP)));
+		       !!(cur->vm_flags & __VM_UFFD_FLAGS));
 
 		/*
 		 * Check not compatible vmas, not strictly required
@@ -1591,7 +1612,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
 		}
 
-		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
+		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
 		prev = vma_merge(mm, prev, start, vma_end, new_flags,
 				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
 				 vma_policy(vma),
@@ -1823,6 +1844,66 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 	return ret;
 }
 
+static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_continue uffdio_continue;
+	struct uffdio_continue __user *user_uffdio_continue;
+	struct userfaultfd_wake_range range;
+
+	user_uffdio_continue = (struct uffdio_continue __user *)arg;
+
+	ret = -EAGAIN;
+	if (READ_ONCE(ctx->mmap_changing))
+		goto out;
+
+	ret = -EFAULT;
+	if (copy_from_user(&uffdio_continue, user_uffdio_continue,
+			   /* don't copy the output fields */
+			   sizeof(uffdio_continue) - (sizeof(__s64))))
+		goto out;
+
+	ret = validate_range(ctx->mm, &uffdio_continue.range.start,
+			     uffdio_continue.range.len);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	/* double check for wraparound just in case. */
+	if (uffdio_continue.range.start + uffdio_continue.range.len <=
+	    uffdio_continue.range.start) {
+		goto out;
+	}
+	if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE)
+		goto out;
+
+	if (mmget_not_zero(ctx->mm)) {
+		ret = mcopy_continue(ctx->mm, uffdio_continue.range.start,
+				     uffdio_continue.range.len,
+				     &ctx->mmap_changing);
+		mmput(ctx->mm);
+	} else {
+		return -ESRCH;
+	}
+
+	if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+
+	/* len == 0 would wake all */
+	BUG_ON(!ret);
+	range.len = ret;
+	if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) {
+		range.start = uffdio_continue.range.start;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN;
+
+out:
+	return ret;
+}
+
 static inline unsigned int uffd_ctx_features(__u64 user_features)
 {
 	/*
@@ -1859,6 +1940,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 		goto err_out;
 	/* report all available features and ioctls to userland */
 	uffdio_api.features = UFFD_API_FEATURES;
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+	uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS;
+#endif
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
 	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
@@ -1907,6 +1991,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_WRITEPROTECT:
 		ret = userfaultfd_writeprotect(ctx, arg);
 		break;
+	case UFFDIO_CONTINUE:
+		ret = userfaultfd_continue(ctx, arg);
+		break;
 	}
 	return ret;
 }