Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things and hotfixes

 - ocfs2

 - almost all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (139 commits)
  kernel/memremap.c: remove the unused device_private_entry_fault() export
  mm: delete find_get_entries_tag
  mm/huge_memory.c: make __thp_get_unmapped_area static
  mm/mprotect.c: fix compilation warning because of unused 'mm' variable
  mm/page-writeback: introduce tracepoint for wait_on_page_writeback()
  mm/vmscan: simplify trace_reclaim_flags and trace_shrink_flags
  mm/Kconfig: update "Memory Model" help text
  mm/vmscan.c: don't disable irq again when count pgrefill for memcg
  mm: memblock: make keeping memblock memory opt-in rather than opt-out
  hugetlbfs: always use address space in inode for resv_map pointer
  mm/z3fold.c: support page migration
  mm/z3fold.c: add structure for buddy handles
  mm/z3fold.c: improve compression by extending search
  mm/z3fold.c: introduce helper functions
  mm/page_alloc.c: remove unnecessary parameter in rmqueue_pcplist
  mm/hmm: add ARCH_HAS_HMM_MIRROR ARCH_HAS_HMM_DEVICE Kconfig
  mm/vmscan.c: simplify shrink_inactive_list()
  fs/sync.c: sync_file_range(2) may use WB_SYNC_ALL writeback
  xen/privcmd-buf.c: convert to use vm_map_pages_zero()
  xen/gntdev.c: convert to use vm_map_pages()
  ...

10 files changed, 74 insertions, 66 deletions

diff --git a/fs/dax.c b/fs/dax.c
index e5e54da1715f..f74386293632 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -814,7 +814,7 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
 				goto unlock_pmd;
 
 			flush_cache_page(vma, address, pfn);
-			pmd = pmdp_huge_clear_flush(vma, address, pmdp);
+			pmd = pmdp_invalidate(vma, address, pmdp);
 			pmd = pmd_wrprotect(pmd);
 			pmd = pmd_mkclean(pmd);
 			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
@@ -1575,8 +1575,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		}
 
 		trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry);
-		result = vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
-					    write);
+		result = vmf_insert_pfn_pmd(vmf, pfn, write);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
@@ -1686,8 +1685,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
 		ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
 #ifdef CONFIG_FS_DAX_PMD
 	else if (order == PMD_ORDER)
-		ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
-			pfn, true);
+		ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
 #endif
 	else
 		ret = VM_FAULT_FALLBACK;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index c74ef4426282..1dcc57189382 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -440,9 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			u32 hash;
 
 			index = page->index;
-			hash = hugetlb_fault_mutex_hash(h, current->mm,
-							&pseudo_vma,
-							mapping, index, 0);
+			hash = hugetlb_fault_mutex_hash(h, mapping, index, 0);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 			/*
@@ -499,8 +497,15 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	struct resv_map *resv_map;
 
 	remove_inode_hugepages(inode, 0, LLONG_MAX);
-	resv_map = (struct resv_map *)inode->i_mapping->private_data;
-	/* root inode doesn't have the resv_map, so we should check it */
+
+	/*
+	 * Get the resv_map from the address space embedded in the inode.
+	 * This is the address space which points to any resv_map allocated
+	 * at inode creation time.  If this is a device special inode,
+	 * i_mapping may not point to the original address space.
+	 */
+	resv_map = (struct resv_map *)(&inode->i_data)->private_data;
+	/* Only regular and link inodes have associated reserve maps */
 	if (resv_map)
 		resv_map_release(&resv_map->refs);
 	clear_inode(inode);
@@ -639,8 +644,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		addr = index * hpage_size;
 
 		/* mutex taken here, fault path and hole punch */
-		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
-						index, addr);
+		hash = hugetlb_fault_mutex_hash(h, mapping, index, addr);
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		/* See if already present in mapping to avoid alloc/free */
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 48ea3977012a..fdc18321d70c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2697,8 +2697,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ret = 0;
 		down_read(&current->mm->mmap_sem);
-		pret = get_user_pages_longterm(ubuf, nr_pages, FOLL_WRITE,
-						pages, vmas);
+		pret = get_user_pages(ubuf, nr_pages,
+				      FOLL_WRITE | FOLL_LONGTERM,
+				      pages, vmas);
 		if (pret == nr_pages) {
 			/* don't support file backed memory */
 			for (j = 0; j < nr_pages; j++) {
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index c121abbdfc7d..85f21caaa6ec 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -69,10 +69,6 @@
 #define NAMEI_RA_BLOCKS  4
 #define NAMEI_RA_SIZE        (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
 
-static unsigned char ocfs2_filetype_table[] = {
-	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
-};
-
 static int ocfs2_do_extend_dir(struct super_block *sb,
 			       handle_t *handle,
 			       struct inode *dir,
@@ -1718,7 +1714,7 @@ int __ocfs2_add_entry(handle_t *handle,
 				de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len));
 				de = de1;
 			}
-			de->file_type = OCFS2_FT_UNKNOWN;
+			de->file_type = FT_UNKNOWN;
 			if (blkno) {
 				de->inode = cpu_to_le64(blkno);
 				ocfs2_set_de_type(de, inode->i_mode);
@@ -1803,13 +1799,9 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
 		}
 		offset += le16_to_cpu(de->rec_len);
 		if (le64_to_cpu(de->inode)) {
-			unsigned char d_type = DT_UNKNOWN;
-
-			if (de->file_type < OCFS2_FT_MAX)
-				d_type = ocfs2_filetype_table[de->file_type];
-
 			if (!dir_emit(ctx, de->name, de->name_len,
-				      le64_to_cpu(de->inode), d_type))
+				      le64_to_cpu(de->inode),
+				      fs_ftype_to_dtype(de->file_type)))
 				goto out;
 		}
 		ctx->pos += le16_to_cpu(de->rec_len);
@@ -1900,14 +1892,10 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 				break;
 			}
 			if (le64_to_cpu(de->inode)) {
-				unsigned char d_type = DT_UNKNOWN;
-
-				if (de->file_type < OCFS2_FT_MAX)
-					d_type = ocfs2_filetype_table[de->file_type];
 				if (!dir_emit(ctx, de->name,
 						de->name_len,
 						le64_to_cpu(de->inode),
-						d_type)) {
+					fs_ftype_to_dtype(de->file_type))) {
 					brelse(bh);
 					return 0;
 				}
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 4bf8d5854b27..af2888d23de3 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -148,16 +148,24 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 	u64 blkno;
 	struct dentry *parent;
 	struct inode *dir = d_inode(child);
+	int set;
 
 	trace_ocfs2_get_parent(child, child->d_name.len, child->d_name.name,
 			       (unsigned long long)OCFS2_I(dir)->ip_blkno);
 
+	status = ocfs2_nfs_sync_lock(OCFS2_SB(dir->i_sb), 1);
+	if (status < 0) {
+		mlog(ML_ERROR, "getting nfs sync lock(EX) failed %d\n", status);
+		parent = ERR_PTR(status);
+		goto bail;
+	}
+
 	status = ocfs2_inode_lock(dir, NULL, 0);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
 		parent = ERR_PTR(status);
-		goto bail;
+		goto unlock_nfs_sync;
 	}
 
 	status = ocfs2_lookup_ino_from_name(dir, "..", 2, &blkno);
@@ -166,11 +174,31 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 		goto bail_unlock;
 	}
 
+	status = ocfs2_test_inode_bit(OCFS2_SB(dir->i_sb), blkno, &set);
+	if (status < 0) {
+		if (status == -EINVAL) {
+			status = -ESTALE;
+		} else
+			mlog(ML_ERROR, "test inode bit failed %d\n", status);
+		parent = ERR_PTR(status);
+		goto bail_unlock;
+	}
+
+	trace_ocfs2_get_dentry_test_bit(status, set);
+	if (!set) {
+		status = -ESTALE;
+		parent = ERR_PTR(status);
+		goto bail_unlock;
+	}
+
 	parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0));
 
 bail_unlock:
 	ocfs2_inode_unlock(dir, 0);
 
+unlock_nfs_sync:
+	ocfs2_nfs_sync_unlock(OCFS2_SB(dir->i_sb), 1);
+
 bail:
 	trace_ocfs2_get_parent_end(parent);
 
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 7071ad0dec90..b86bf5e74348 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -392,21 +392,6 @@ static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = {
 #define OCFS2_HB_GLOBAL			"heartbeat=global"
 
 /*
- * OCFS2 directory file types.  Only the low 3 bits are used.  The
- * other bits are reserved for now.
- */
-#define OCFS2_FT_UNKNOWN	0
-#define OCFS2_FT_REG_FILE	1
-#define OCFS2_FT_DIR		2
-#define OCFS2_FT_CHRDEV		3
-#define OCFS2_FT_BLKDEV		4
-#define OCFS2_FT_FIFO		5
-#define OCFS2_FT_SOCK		6
-#define OCFS2_FT_SYMLINK	7
-
-#define OCFS2_FT_MAX		8
-
-/*
  * OCFS2_DIR_PAD defines the directory entries boundaries
  *
  * NOTE: It must be a multiple of 4
@@ -424,17 +409,6 @@ static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = {
 #define	OCFS2_LINKS_HI_SHIFT	16
 #define	OCFS2_DX_ENTRIES_MAX	(0xffffffffU)
 
-#define S_SHIFT			12
-static unsigned char ocfs2_type_by_mode[S_IFMT >> S_SHIFT] = {
-	[S_IFREG >> S_SHIFT]  = OCFS2_FT_REG_FILE,
-	[S_IFDIR >> S_SHIFT]  = OCFS2_FT_DIR,
-	[S_IFCHR >> S_SHIFT]  = OCFS2_FT_CHRDEV,
-	[S_IFBLK >> S_SHIFT]  = OCFS2_FT_BLKDEV,
-	[S_IFIFO >> S_SHIFT]  = OCFS2_FT_FIFO,
-	[S_IFSOCK >> S_SHIFT] = OCFS2_FT_SOCK,
-	[S_IFLNK >> S_SHIFT]  = OCFS2_FT_SYMLINK,
-};
-
 
 /*
  * Convenience casts
@@ -1629,7 +1603,7 @@ static inline int ocfs2_sprintf_system_inode_name(char *buf, int len,
 static inline void ocfs2_set_de_type(struct ocfs2_dir_entry *de,
 				    umode_t mode)
 {
-	de->file_type = ocfs2_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
+	de->file_type = fs_umode_to_ftype(mode);
 }
 
 static inline int ocfs2_gd_is_discontig(struct ocfs2_group_desc *gd)
diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
index d4811f981608..2bb916d68576 100644
--- a/fs/orangefs/orangefs-bufmap.c
+++ b/fs/orangefs/orangefs-bufmap.c
@@ -269,7 +269,7 @@ orangefs_bufmap_map(struct orangefs_bufmap *bufmap,
 
 	/* map the pages */
 	ret = get_user_pages_fast((unsigned long)user_desc->ptr,
-			     bufmap->page_count, 1, bufmap->page_array);
+			     bufmap->page_count, FOLL_WRITE, bufmap->page_array);
 
 	if (ret < 0)
 		return ret;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 95ca1fe7283c..01d4eb0e6bd1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1169,7 +1169,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				break;
 			}
 
-			mmu_notifier_range_init(&range, mm, 0, -1UL);
+			mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
+						0, NULL, mm, 0, -1UL);
 			mmu_notifier_invalidate_range_start(&range);
 		}
 		walk_page_range(0, mm->highest_vm_end, &clear_refs_walk);
diff --git a/fs/sync.c b/fs/sync.c
index 01e82170545a..4d1ff010bc5a 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -292,8 +292,14 @@ int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
 	}
 
 	if (flags & SYNC_FILE_RANGE_WRITE) {
+		int sync_mode = WB_SYNC_NONE;
+
+		if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) ==
+			     SYNC_FILE_RANGE_WRITE_AND_WAIT)
+			sync_mode = WB_SYNC_ALL;
+
 		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
-						 WB_SYNC_NONE);
+						 sync_mode);
 		if (ret < 0)
 			goto out;
 	}
@@ -306,9 +312,9 @@ out:
 }
 
 /*
- * sys_sync_file_range() permits finely controlled syncing over a segment of
+ * ksys_sync_file_range() permits finely controlled syncing over a segment of
  * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
- * zero then sys_sync_file_range() will operate from offset out to EOF.
+ * zero then ksys_sync_file_range() will operate from offset out to EOF.
  *
  * The flag bits are:
  *
@@ -325,7 +331,7 @@ out:
  * Useful combinations of the flag bits are:
  *
  * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
- * in the range which were dirty on entry to sys_sync_file_range() are placed
+ * in the range which were dirty on entry to ksys_sync_file_range() are placed
  * under writeout.  This is a start-write-for-data-integrity operation.
  *
  * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
@@ -337,10 +343,13 @@ out:
  * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
  * for that operation to complete and to return the result.
  *
- * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER
+ * (a.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT):
  * a traditional sync() operation.  This is a write-for-data-integrity operation
  * which will ensure that all pages in the range which were dirty on entry to
- * sys_sync_file_range() are committed to disk.
+ * ksys_sync_file_range() are written to disk.  It should be noted that disk
+ * caches are not flushed by this call, so there are no guarantees here that the
+ * data will be available on disk after a crash.
  *
  *
  * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f5de1e726356..3b30301c90ec 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -30,6 +30,8 @@
 #include <linux/security.h>
 #include <linux/hugetlb.h>
 
+int sysctl_unprivileged_userfaultfd __read_mostly = 1;
+
 static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
 
 enum userfaultfd_state {
@@ -1930,6 +1932,9 @@ SYSCALL_DEFINE1(userfaultfd, int, flags)
 	struct userfaultfd_ctx *ctx;
 	int fd;
 
+	if (!sysctl_unprivileged_userfaultfd && !capable(CAP_SYS_PTRACE))
+		return -EPERM;
+
 	BUG_ON(!current->mm);
 
 	/* Check the UFFD_* constants for consistency.  */