Merge tag 'iversion-v4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux

Pull inode->i_version rework from Jeff Layton:
 "This pile of patches is a rework of the inode->i_version field. We
  have traditionally incremented that field on every inode data or
  metadata change. Typically this increment needs to be logged on disk
  even when nothing else has changed, which is rather expensive.

  It turns out though that none of the consumers of that field actually
  require this behavior. The only real requirement for all of them is
  that it be different iff the inode has changed since the last time the
  field was checked.

  Given that, we can optimize away most of the i_version increments and
  avoid dirtying inode metadata when the only change is to the i_version
  and no one is querying it. Queries of the i_version field are rather
  rare, so we can help write performance under many common workloads.

  This patch series converts existing accesses of the i_version field to
  a new API, and then converts all of the in-kernel filesystems to use
  it. The last patch in the series then converts the backend
  implementation to a scheme that optimizes away a large portion of the
  metadata updates when no one is looking at it.

  In my own testing this series significantly helps performance with
  small I/O sizes. I also got this email for Christmas this year from
  the kernel test robot (a 244% r/w bandwidth improvement with XFS over
  DAX, with 4k writes):

    https://lkml.org/lkml/2017/12/25/8

  A few of the earlier patches in this pile are also flowing to you via
  other trees (mm, integrity, and nfsd trees in particular)".

* tag 'iversion-v4.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux: (22 commits)
  fs: handle inode->i_version more efficiently
  btrfs: only dirty the inode in btrfs_update_time if something was changed
  xfs: avoid setting XFS_ILOG_CORE if i_version doesn't need incrementing
  fs: only set S_VERSION when updating times if necessary
  IMA: switch IMA over to new i_version API
  xfs: convert to new i_version API
  ufs: use new i_version API
  ocfs2: convert to new i_version API
  nfsd: convert to new i_version API
  nfs: convert to new i_version API
  ext4: convert to new i_version API
  ext2: convert to new i_version API
  exofs: switch to new i_version API
  btrfs: convert to new i_version API
  afs: convert to new i_version API
  affs: convert to new i_version API
  fat: convert to new i_version API
  fs: don't take the i_lock in inode_inc_iversion
  fs: new API for handling inode->i_version
  ntfs: remove i_version handling
  ...

drivers/staging/lustre/lustre/llite/dir.c

@@ -369,8 +369,6 @@ static int ll_readdir(struct file *filp, struct dir_context *ctx)
 	}
 	ctx->pos = pos;
 	ll_finish_md_op_data(op_data);
-	filp->f_version = inode->i_version;
-
 out:
 	if (!rc)
 		ll_stats_ops_tally(sbi, LPROC_LL_READDIR, 1);
@@ -1678,7 +1676,6 @@ static loff_t ll_dir_seek(struct file *file, loff_t offset, int origin)
 			else
 				fd->lfd_pos = offset;
 			file->f_pos = offset;
-			file->f_version = 0;
 		}
 		ret = offset;
 	}

fs/affs/amigaffs.c

@@ -10,6 +10,7 @@
  */
 
 #include <linux/math64.h>
+#include <linux/iversion.h>
 #include "affs.h"
 
 /*
@@ -60,7 +61,7 @@ affs_insert_hash(struct inode *dir, struct buffer_head *bh)
 	affs_brelse(dir_bh);
 
 	dir->i_mtime = dir->i_ctime = current_time(dir);
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	mark_inode_dirty(dir);
 
 	return 0;
@@ -114,7 +115,7 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh)
 	affs_brelse(bh);
 
 	dir->i_mtime = dir->i_ctime = current_time(dir);
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	mark_inode_dirty(dir);
 
 	return retval;

fs/affs/dir.c

@@ -14,6 +14,7 @@
  *
  */
 
+#include <linux/iversion.h>
 #include "affs.h"
 
 static int affs_readdir(struct file *, struct dir_context *);
@@ -80,7 +81,7 @@ affs_readdir(struct file *file, struct dir_context *ctx)
 	 * we can jump directly to where we left off.
 	 */
 	ino = (u32)(long)file->private_data;
-	if (ino && file->f_version == inode->i_version) {
+	if (ino && inode_cmp_iversion(inode, file->f_version) == 0) {
 		pr_debug("readdir() left off=%d\n", ino);
 		goto inside;
 	}
@@ -130,7 +131,7 @@ inside:
 		} while (ino);
 	}
 done:
-	file->f_version = inode->i_version;
+	file->f_version = inode_query_iversion(inode);
 	file->private_data = (void *)(long)ino;
 	affs_brelse(fh_bh);
 

fs/affs/super.c

@@ -21,6 +21,7 @@
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/seq_file.h>
+#include <linux/iversion.h>
 #include "affs.h"
 
 static int affs_statfs(struct dentry *dentry, struct kstatfs *buf);
@@ -102,7 +103,7 @@ static struct inode *affs_alloc_inode(struct super_block *sb)
 	if (!i)
 		return NULL;
 
-	i->vfs_inode.i_version = 1;
+	inode_set_iversion(&i->vfs_inode, 1);
 	i->i_lc = NULL;
 	i->i_ext_bh = NULL;
 	i->i_pa_cnt = 0;

fs/afs/fsclient.c

@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/circ_buf.h>
+#include <linux/iversion.h>
 #include "internal.h"
 #include "afs_fs.h"
 
@@ -124,7 +125,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 		vnode->vfs_inode.i_ctime.tv_sec	= status->mtime_client;
 		vnode->vfs_inode.i_mtime	= vnode->vfs_inode.i_ctime;
 		vnode->vfs_inode.i_atime	= vnode->vfs_inode.i_ctime;
-		vnode->vfs_inode.i_version	= data_version;
+		inode_set_iversion_raw(&vnode->vfs_inode, data_version);
 	}
 
 	expected_version = status->data_version;

fs/afs/inode.c

@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/iversion.h>
 #include "internal.h"
 
 static const struct inode_operations afs_symlink_inode_operations = {
@@ -89,7 +90,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 	inode->i_atime		= inode->i_mtime = inode->i_ctime;
 	inode->i_blocks		= 0;
 	inode->i_generation	= vnode->fid.unique;
-	inode->i_version	= vnode->status.data_version;
+	inode_set_iversion_raw(inode, vnode->status.data_version);
 	inode->i_mapping->a_ops	= &afs_fs_aops;
 
 	read_sequnlock_excl(&vnode->cb_lock);
@@ -218,7 +219,7 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
 	inode->i_ctime.tv_nsec	= 0;
 	inode->i_atime		= inode->i_mtime = inode->i_ctime;
 	inode->i_blocks		= 0;
-	inode->i_version	= 0;
+	inode_set_iversion_raw(inode, 0);
 	inode->i_generation	= 0;
 
 	set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags);

fs/btrfs/delayed-inode.c

@@ -18,6 +18,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/iversion.h>
 #include "delayed-inode.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -1713,7 +1714,8 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_inode_nbytes(inode_item, inode_get_bytes(inode));
 	btrfs_set_stack_inode_generation(inode_item,
 					 BTRFS_I(inode)->generation);
-	btrfs_set_stack_inode_sequence(inode_item, inode->i_version);
+	btrfs_set_stack_inode_sequence(inode_item,
+				       inode_peek_iversion(inode));
 	btrfs_set_stack_inode_transid(inode_item, trans->transid);
 	btrfs_set_stack_inode_rdev(inode_item, inode->i_rdev);
 	btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags);
@@ -1767,7 +1769,8 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 	BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item);
         BTRFS_I(inode)->last_trans = btrfs_stack_inode_transid(inode_item);
 
-	inode->i_version = btrfs_stack_inode_sequence(inode_item);
+	inode_set_iversion_queried(inode,
+				   btrfs_stack_inode_sequence(inode_item));
 	inode->i_rdev = 0;
 	*rdev = btrfs_stack_inode_rdev(inode_item);
 	BTRFS_I(inode)->flags = btrfs_stack_inode_flags(inode_item);

fs/btrfs/file.c

@@ -31,6 +31,7 @@
 #include <linux/slab.h>
 #include <linux/btrfs.h>
 #include <linux/uio.h>
+#include <linux/iversion.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"

fs/btrfs/inode.c

@@ -43,6 +43,7 @@
 #include <linux/posix_acl_xattr.h>
 #include <linux/uio.h>
 #include <linux/magic.h>
+#include <linux/iversion.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -3777,7 +3778,8 @@ static int btrfs_read_locked_inode(struct inode *inode)
 	BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
 	BTRFS_I(inode)->last_trans = btrfs_inode_transid(leaf, inode_item);
 
-	inode->i_version = btrfs_inode_sequence(leaf, inode_item);
+	inode_set_iversion_queried(inode,
+				   btrfs_inode_sequence(leaf, inode_item));
 	inode->i_generation = BTRFS_I(inode)->generation;
 	inode->i_rdev = 0;
 	rdev = btrfs_inode_rdev(leaf, inode_item);
@@ -3945,7 +3947,8 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 				     &token);
 	btrfs_set_token_inode_generation(leaf, item, BTRFS_I(inode)->generation,
 					 &token);
-	btrfs_set_token_inode_sequence(leaf, item, inode->i_version, &token);
+	btrfs_set_token_inode_sequence(leaf, item, inode_peek_iversion(inode),
+				       &token);
 	btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
 	btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
 	btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
@@ -6104,19 +6107,20 @@ static int btrfs_update_time(struct inode *inode, struct timespec *now,
 			     int flags)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	bool dirty = flags & ~S_VERSION;
 
 	if (btrfs_root_readonly(root))
 		return -EROFS;
 
 	if (flags & S_VERSION)
-		inode_inc_iversion(inode);
+		dirty |= inode_maybe_inc_iversion(inode, dirty);
 	if (flags & S_CTIME)
 		inode->i_ctime = *now;
 	if (flags & S_MTIME)
 		inode->i_mtime = *now;
 	if (flags & S_ATIME)
 		inode->i_atime = *now;
-	return btrfs_dirty_inode(inode);
+	return dirty ? btrfs_dirty_inode(inode) : 0;
 }
 
 /*

fs/btrfs/ioctl.c

@@ -43,6 +43,7 @@
 #include <linux/uuid.h>
 #include <linux/btrfs.h>
 #include <linux/uaccess.h>
+#include <linux/iversion.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"

fs/btrfs/tree-log.c

@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/list_sort.h>
+#include <linux/iversion.h>
 #include "tree-log.h"
 #include "disk-io.h"
 #include "locking.h"
@@ -3609,7 +3610,8 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
 				     &token);
 
-	btrfs_set_token_inode_sequence(leaf, item, inode->i_version, &token);
+	btrfs_set_token_inode_sequence(leaf, item,
+				       inode_peek_iversion(inode), &token);
 	btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
 	btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
 	btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);

fs/btrfs/xattr.c

@@ -23,6 +23,7 @@
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/iversion.h>
 #include "ctree.h"
 #include "btrfs_inode.h"
 #include "transaction.h"

fs/exofs/dir.c

@@ -31,6 +31,7 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+#include <linux/iversion.h>
 #include "exofs.h"
 
 static inline unsigned exofs_chunk_size(struct inode *inode)
@@ -60,7 +61,7 @@ static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 	int err = 0;
 
-	dir->i_version++;
+	inode_inc_iversion(dir);
 
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
@@ -241,7 +242,7 @@ exofs_readdir(struct file *file, struct dir_context *ctx)
 	unsigned long n = pos >> PAGE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(exofs_chunk_size(inode)-1);
-	int need_revalidate = (file->f_version != inode->i_version);
+	bool need_revalidate = inode_cmp_iversion(inode, file->f_version);
 
 	if (pos > inode->i_size - EXOFS_DIR_REC_LEN(1))
 		return 0;
@@ -264,8 +265,8 @@ exofs_readdir(struct file *file, struct dir_context *ctx)
 								chunk_mask);
 				ctx->pos = (n<<PAGE_SHIFT) + offset;
 			}
-			file->f_version = inode->i_version;
-			need_revalidate = 0;
+			file->f_version = inode_query_iversion(inode);
+			need_revalidate = false;
 		}
 		de = (struct exofs_dir_entry *)(kaddr + offset);
 		limit = kaddr + exofs_last_byte(inode, n) -

fs/exofs/super.c

@@ -38,6 +38,7 @@
 #include <linux/module.h>
 #include <linux/exportfs.h>
 #include <linux/slab.h>
+#include <linux/iversion.h>
 
 #include "exofs.h"
 
@@ -159,7 +160,7 @@ static struct inode *exofs_alloc_inode(struct super_block *sb)
 	if (!oi)
 		return NULL;
 
-	oi->vfs_inode.i_version = 1;
+	inode_set_iversion(&oi->vfs_inode, 1);
 	return &oi->vfs_inode;
 }
 

fs/ext2/dir.c

@@ -26,6 +26,7 @@
 #include <linux/buffer_head.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
+#include <linux/iversion.h>
 
 typedef struct ext2_dir_entry_2 ext2_dirent;
 
@@ -92,7 +93,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 	int err = 0;
 
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	block_write_end(NULL, mapping, pos, len, len, page, NULL);
 
 	if (pos+len > dir->i_size) {
@@ -293,7 +294,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
 	unsigned char *types = NULL;
-	int need_revalidate = file->f_version != inode->i_version;
+	bool need_revalidate = inode_cmp_iversion(inode, file->f_version);
 
 	if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
 		return 0;
@@ -319,8 +320,8 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 				offset = ext2_validate_entry(kaddr, offset, chunk_mask);
 				ctx->pos = (n<<PAGE_SHIFT) + offset;
 			}
-			file->f_version = inode->i_version;
-			need_revalidate = 0;
+			file->f_version = inode_query_iversion(inode);
+			need_revalidate = false;
 		}
 		de = (ext2_dirent *)(kaddr+offset);
 		limit = kaddr + ext2_last_byte(inode, n) - EXT2_DIR_REC_LEN(1);

fs/ext2/super.c

@@ -33,6 +33,7 @@
 #include <linux/quotaops.h>
 #include <linux/uaccess.h>
 #include <linux/dax.h>
+#include <linux/iversion.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
@@ -184,7 +185,7 @@ static struct inode *ext2_alloc_inode(struct super_block *sb)
 	if (!ei)
 		return NULL;
 	ei->i_block_alloc_info = NULL;
-	ei->vfs_inode.i_version = 1;
+	inode_set_iversion(&ei->vfs_inode, 1);
 #ifdef CONFIG_QUOTA
 	memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
 #endif
@@ -1569,7 +1570,7 @@ out:
 		return err;
 	if (inode->i_size < off+len-towrite)
 		i_size_write(inode, off+len-towrite);
-	inode->i_version++;
+	inode_inc_iversion(inode);
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	mark_inode_dirty(inode);
 	return len - towrite;

fs/ext4/dir.c

@@ -25,6 +25,7 @@
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
+#include <linux/iversion.h>
 #include "ext4.h"
 #include "xattr.h"
 
@@ -208,7 +209,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 		 * readdir(2), then we might be pointing to an invalid
 		 * dirent right now.  Scan from the start of the block
 		 * to make sure. */
-		if (file->f_version != inode->i_version) {
+		if (inode_cmp_iversion(inode, file->f_version)) {
 			for (i = 0; i < sb->s_blocksize && i < offset; ) {
 				de = (struct ext4_dir_entry_2 *)
 					(bh->b_data + i);
@@ -227,7 +228,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 			offset = i;
 			ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1))
 				| offset;
-			file->f_version = inode->i_version;
+			file->f_version = inode_query_iversion(inode);
 		}
 
 		while (ctx->pos < inode->i_size
@@ -568,10 +569,10 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
 		 * cached entries.
 		 */
 		if ((!info->curr_node) ||
-		    (file->f_version != inode->i_version)) {
+		    inode_cmp_iversion(inode, file->f_version)) {
 			info->curr_node = NULL;
 			free_rb_tree_fname(&info->root);
-			file->f_version = inode->i_version;
+			file->f_version = inode_query_iversion(inode);
 			ret = ext4_htree_fill_tree(file, info->curr_hash,
 						   info->curr_minor_hash,
 						   &info->next_hash);

fs/ext4/inline.c

@@ -14,6 +14,7 @@
 
 #include <linux/iomap.h>
 #include <linux/fiemap.h>
+#include <linux/iversion.h>
 
 #include "ext4_jbd2.h"
 #include "ext4.h"
@@ -1042,7 +1043,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	 */
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ext4_update_dx_flag(dir);
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	return 1;
 }
 
@@ -1494,7 +1495,7 @@ int ext4_read_inline_dir(struct file *file,
 	 * dirent right now.  Scan from the start of the inline
 	 * dir to make sure.
 	 */
-	if (file->f_version != inode->i_version) {
+	if (inode_cmp_iversion(inode, file->f_version)) {
 		for (i = 0; i < extra_size && i < offset;) {
 			/*
 			 * "." is with offset 0 and
@@ -1526,7 +1527,7 @@ int ext4_read_inline_dir(struct file *file,
 		}
 		offset = i;
 		ctx->pos = offset;
-		file->f_version = inode->i_version;
+		file->f_version = inode_query_iversion(inode);
 	}
 
 	while (ctx->pos < extra_size) {

fs/ext4/inode.c

@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/bitops.h>
 #include <linux/iomap.h>
+#include <linux/iversion.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -4882,12 +4883,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
 
 	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
-		inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+		u64 ivers = le32_to_cpu(raw_inode->i_disk_version);
+
 		if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
 			if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
-				inode->i_version |=
+				ivers |=
 		    (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
 		}
+		inode_set_iversion_queried(inode, ivers);
 	}
 
 	ret = 0;
@@ -5173,11 +5176,13 @@ static int ext4_do_update_inode(handle_t *handle,
 	}
 
 	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
-		raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+		u64 ivers = inode_peek_iversion(inode);
+
+		raw_inode->i_disk_version = cpu_to_le32(ivers);
 		if (ei->i_extra_isize) {
 			if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
 				raw_inode->i_version_hi =
-					cpu_to_le32(inode->i_version >> 32);
+					cpu_to_le32(ivers >> 32);
 			raw_inode->i_extra_isize =
 				cpu_to_le16(ei->i_extra_isize);
 		}

fs/ext4/ioctl.c

@@ -19,6 +19,7 @@
 #include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <linux/delay.h>
+#include <linux/iversion.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include <linux/fsmap.h>
@@ -144,7 +145,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 		i_gid_write(inode_bl, 0);
 		inode_bl->i_flags = 0;
 		ei_bl->i_flags = 0;
-		inode_bl->i_version = 1;
+		inode_set_iversion(inode_bl, 1);
 		i_size_write(inode_bl, 0);
 		inode_bl->i_mode = S_IFREG;
 		if (ext4_has_feature_extents(sb)) {

fs/ext4/namei.c

@@ -34,6 +34,7 @@
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
 #include <linux/bio.h>
+#include <linux/iversion.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
@@ -2959,7 +2960,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 			     "empty directory '%.*s' has too many links (%u)",
 			     dentry->d_name.len, dentry->d_name.name,
 			     inode->i_nlink);
-	inode->i_version++;
+	inode_inc_iversion(inode);
 	clear_nlink(inode);
 	/* There's no need to set i_disksize: the fact that i_nlink is
 	 * zero will ensure that the right thing happens during any
@@ -3365,7 +3366,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
 	ent->de->inode = cpu_to_le32(ino);
 	if (ext4_has_feature_filetype(ent->dir->i_sb))
 		ent->de->file_type = file_type;
-	ent->dir->i_version++;
+	inode_inc_iversion(ent->dir);
 	ent->dir->i_ctime = ent->dir->i_mtime =
 		current_time(ent->dir);
 	ext4_mark_inode_dirty(handle, ent->dir);

fs/ext4/super.c

@@ -40,6 +40,7 @@
 #include <linux/dax.h>
 #include <linux/cleancache.h>
 #include <linux/uaccess.h>
+#include <linux/iversion.h>
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
@@ -967,7 +968,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	if (!ei)
 		return NULL;
 
-	ei->vfs_inode.i_version = 1;
+	inode_set_iversion(&ei->vfs_inode, 1);
 	spin_lock_init(&ei->i_raw_lock);
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
 	spin_lock_init(&ei->i_prealloc_lock);

fs/ext4/xattr.c

@@ -56,6 +56,7 @@
 #include <linux/slab.h>
 #include <linux/mbcache.h>
 #include <linux/quotaops.h>
+#include <linux/iversion.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"
@@ -294,13 +295,13 @@ ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size)
 static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode)
 {
 	return ((u64)ea_inode->i_ctime.tv_sec << 32) |
-	       ((u32)ea_inode->i_version);
+		(u32) inode_peek_iversion_raw(ea_inode);
 }
 
 static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count)
 {
 	ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32);
-	ea_inode->i_version = (u32)ref_count;
+	inode_set_iversion_raw(ea_inode, ref_count & 0xffffffff);
 }
 
 static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode)

fs/fat/dir.c

@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/uaccess.h>
+#include <linux/iversion.h>
 #include "fat.h"
 
 /*
@@ -1055,7 +1056,7 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo)
 	brelse(bh);
 	if (err)
 		return err;
-	dir->i_version++;
+	inode_inc_iversion(dir);
 
 	if (nr_slots) {
 		/*

fs/fat/inode.c

@@ -20,6 +20,7 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <asm/unaligned.h>
+#include <linux/iversion.h>
 #include "fat.h"
 
 #ifndef CONFIG_FAT_DEFAULT_IOCHARSET
@@ -507,7 +508,7 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 	MSDOS_I(inode)->i_pos = 0;
 	inode->i_uid = sbi->options.fs_uid;
 	inode->i_gid = sbi->options.fs_gid;
-	inode->i_version++;
+	inode_inc_iversion(inode);
 	inode->i_generation = get_seconds();
 
 	if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) {
@@ -590,7 +591,7 @@ struct inode *fat_build_inode(struct super_block *sb,
 		goto out;
 	}
 	inode->i_ino = iunique(sb, MSDOS_ROOT_INO);
-	inode->i_version = 1;
+	inode_set_iversion(inode, 1);
 	err = fat_fill_inode(inode, de);
 	if (err) {
 		iput(inode);
@@ -1377,7 +1378,7 @@ static int fat_read_root(struct inode *inode)
 	MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO;
 	inode->i_uid = sbi->options.fs_uid;
 	inode->i_gid = sbi->options.fs_gid;
-	inode->i_version++;
+	inode_inc_iversion(inode);
 	inode->i_generation = 0;
 	inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO);
 	inode->i_op = sbi->dir_ops;
@@ -1828,7 +1829,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	if (!root_inode)
 		goto out_fail;
 	root_inode->i_ino = MSDOS_ROOT_INO;
-	root_inode->i_version = 1;
+	inode_set_iversion(root_inode, 1);
 	error = fat_read_root(root_inode);
 	if (error < 0) {
 		iput(root_inode);

fs/fat/namei_msdos.c

@@ -7,6 +7,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/iversion.h>
 #include "fat.h"
 
 /* Characters that are undesirable in an MS-DOS file name */
@@ -480,7 +481,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 			} else
 				mark_inode_dirty(old_inode);
 
-			old_dir->i_version++;
+			inode_inc_iversion(old_dir);
 			old_dir->i_ctime = old_dir->i_mtime = current_time(old_dir);
 			if (IS_DIRSYNC(old_dir))
 				(void)fat_sync_inode(old_dir);
@@ -508,7 +509,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 			goto out;
 		new_i_pos = sinfo.i_pos;
 	}
-	new_dir->i_version++;
+	inode_inc_iversion(new_dir);
 
 	fat_detach(old_inode);
 	fat_attach(old_inode, new_i_pos);
@@ -540,7 +541,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 	old_sinfo.bh = NULL;
 	if (err)
 		goto error_dotdot;
-	old_dir->i_version++;
+	inode_inc_iversion(old_dir);
 	old_dir->i_ctime = old_dir->i_mtime = ts;
 	if (IS_DIRSYNC(old_dir))
 		(void)fat_sync_inode(old_dir);

fs/fat/namei_vfat.c

@@ -20,7 +20,7 @@
 #include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/kernel.h>
-
+#include <linux/iversion.h>
 #include "fat.h"
 
 static inline unsigned long vfat_d_version(struct dentry *dentry)
@@ -46,7 +46,7 @@ static int vfat_revalidate_shortname(struct dentry *dentry)
 {
 	int ret = 1;
 	spin_lock(&dentry->d_lock);
-	if (vfat_d_version(dentry) != d_inode(dentry->d_parent)->i_version)
+	if (inode_cmp_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry)))
 		ret = 0;
 	spin_unlock(&dentry->d_lock);
 	return ret;
@@ -759,7 +759,7 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 out:
 	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	if (!inode)
-		vfat_d_version_set(dentry, dir->i_version);
+		vfat_d_version_set(dentry, inode_query_iversion(dir));
 	return d_splice_alias(inode, dentry);
 error:
 	mutex_unlock(&MSDOS_SB(sb)->s_lock);
@@ -781,7 +781,7 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo);
 	if (err)
 		goto out;
-	dir->i_version++;
+	inode_inc_iversion(dir);
 
 	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
 	brelse(sinfo.bh);
@@ -789,7 +789,7 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		err = PTR_ERR(inode);
 		goto out;
 	}
-	inode->i_version++;
+	inode_inc_iversion(inode);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
 	/* timestamp is already written, so mark_inode_dirty() is unneeded. */
 
@@ -823,7 +823,7 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
 	clear_nlink(inode);
 	inode->i_mtime = inode->i_atime = current_time(inode);
 	fat_detach(inode);
-	vfat_d_version_set(dentry, dir->i_version);
+	vfat_d_version_set(dentry, inode_query_iversion(dir));
 out:
 	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 
@@ -849,7 +849,7 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry)
 	clear_nlink(inode);
 	inode->i_mtime = inode->i_atime = current_time(inode);
 	fat_detach(inode);
-	vfat_d_version_set(dentry, dir->i_version);
+	vfat_d_version_set(dentry, inode_query_iversion(dir));
 out:
 	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 
@@ -875,7 +875,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &ts, &sinfo);
 	if (err)
 		goto out_free;
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	inc_nlink(dir);
 
 	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
@@ -885,7 +885,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		/* the directory was completed, just return a error */
 		goto out;
 	}
-	inode->i_version++;
+	inode_inc_iversion(inode);
 	set_nlink(inode, 2);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
 	/* timestamp is already written, so mark_inode_dirty() is unneeded. */
@@ -951,7 +951,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto out;
 		new_i_pos = sinfo.i_pos;
 	}
-	new_dir->i_version++;
+	inode_inc_iversion(new_dir);
 
 	fat_detach(old_inode);
 	fat_attach(old_inode, new_i_pos);
@@ -979,7 +979,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 	old_sinfo.bh = NULL;
 	if (err)
 		goto error_dotdot;
-	old_dir->i_version++;
+	inode_inc_iversion(old_dir);
 	old_dir->i_ctime = old_dir->i_mtime = ts;
 	if (IS_DIRSYNC(old_dir))
 		(void)fat_sync_inode(old_dir);

fs/inode.c

@@ -18,6 +18,7 @@
 #include <linux/buffer_head.h> /* for inode_has_buffers */
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
+#include <linux/iversion.h>
 #include <trace/events/writeback.h>
 #include "internal.h"
 
@@ -1634,17 +1635,21 @@ static int relatime_need_update(const struct path *path, struct inode *inode,
 int generic_update_time(struct inode *inode, struct timespec *time, int flags)
 {
 	int iflags = I_DIRTY_TIME;
+	bool dirty = false;
 
 	if (flags & S_ATIME)
 		inode->i_atime = *time;
 	if (flags & S_VERSION)
-		inode_inc_iversion(inode);
+		dirty = inode_maybe_inc_iversion(inode, false);
 	if (flags & S_CTIME)
 		inode->i_ctime = *time;
 	if (flags & S_MTIME)
 		inode->i_mtime = *time;
+	if ((flags & (S_ATIME | S_CTIME | S_MTIME)) &&
+	    !(inode->i_sb->s_flags & SB_LAZYTIME))
+		dirty = true;
 
-	if (!(inode->i_sb->s_flags & SB_LAZYTIME) || (flags & S_VERSION))
+	if (dirty)
 		iflags |= I_DIRTY_SYNC;
 	__mark_inode_dirty(inode, iflags);
 	return 0;
@@ -1863,7 +1868,7 @@ int file_update_time(struct file *file)
 	if (!timespec_equal(&inode->i_ctime, &now))
 		sync_it |= S_CTIME;
 
-	if (IS_I_VERSION(inode))
+	if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
 		sync_it |= S_VERSION;
 
 	if (!sync_it)

fs/nfs/delegation.c

@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/iversion.h>
 
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
@@ -347,7 +348,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	nfs4_stateid_copy(&delegation->stateid, &res->delegation);
 	delegation->type = res->delegation_type;
 	delegation->pagemod_limit = res->pagemod_limit;
-	delegation->change_attr = inode->i_version;
+	delegation->change_attr = inode_peek_iversion_raw(inode);
 	delegation->cred = get_rpccred(cred);
 	delegation->inode = inode;
 	delegation->flags = 1<<NFS_DELEGATION_REFERENCED;

fs/nfs/fscache-index.c

@@ -16,6 +16,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
 #include <linux/in6.h>
+#include <linux/iversion.h>
 
 #include "internal.h"
 #include "fscache.h"
@@ -211,7 +212,7 @@ static uint16_t nfs_fscache_inode_get_aux(const void *cookie_netfs_data,
 	auxdata.ctime = nfsi->vfs_inode.i_ctime;
 
 	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata.change_attr = nfsi->vfs_inode.i_version;
+		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
 
 	if (bufmax > sizeof(auxdata))
 		bufmax = sizeof(auxdata);
@@ -243,7 +244,7 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
 	auxdata.ctime = nfsi->vfs_inode.i_ctime;
 
 	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
-		auxdata.change_attr = nfsi->vfs_inode.i_version;
+		auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
 
 	if (memcmp(data, &auxdata, datalen) != 0)
 		return FSCACHE_CHECKAUX_OBSOLETE;

fs/nfs/inode.c

@@ -38,8 +38,8 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/freezer.h>
-
 #include <linux/uaccess.h>
+#include <linux/iversion.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
@@ -483,7 +483,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		memset(&inode->i_atime, 0, sizeof(inode->i_atime));
 		memset(&inode->i_mtime, 0, sizeof(inode->i_mtime));
 		memset(&inode->i_ctime, 0, sizeof(inode->i_ctime));
-		inode->i_version = 0;
+		inode_set_iversion_raw(inode, 0);
 		inode->i_size = 0;
 		clear_nlink(inode);
 		inode->i_uid = make_kuid(&init_user_ns, -2);
@@ -508,7 +508,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		else if (nfs_server_capable(inode, NFS_CAP_CTIME))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
-			inode->i_version = fattr->change_attr;
+			inode_set_iversion_raw(inode, fattr->change_attr);
 		else
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_PAGECACHE);
@@ -1289,8 +1289,8 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 
 	if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
 			&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
-			&& inode->i_version == fattr->pre_change_attr) {
-		inode->i_version = fattr->change_attr;
+			&& !inode_cmp_iversion_raw(inode, fattr->pre_change_attr)) {
+		inode_set_iversion_raw(inode, fattr->change_attr);
 		if (S_ISDIR(inode->i_mode))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
 		ret |= NFS_INO_INVALID_ATTR;
@@ -1348,7 +1348,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 
 	if (!nfs_file_has_buffered_writers(nfsi)) {
 		/* Verify a few of the more important attributes */
-		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && inode->i_version != fattr->change_attr)
+		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && inode_cmp_iversion_raw(inode, fattr->change_attr))
 			invalid |= NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE;
 
 		if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
@@ -1642,7 +1642,7 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
 			(fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) {
-		fattr->pre_change_attr = inode->i_version;
+		fattr->pre_change_attr = inode_peek_iversion_raw(inode);
 		fattr->valid |= NFS_ATTR_FATTR_PRECHANGE;
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 &&
@@ -1778,7 +1778,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 
 	/* More cache consistency checks */
 	if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
-		if (inode->i_version != fattr->change_attr) {
+		if (inode_cmp_iversion_raw(inode, fattr->change_attr)) {
 			dprintk("NFS: change_attr change on server for file %s/%ld\n",
 					inode->i_sb->s_id, inode->i_ino);
 			/* Could it be a race with writeback? */
@@ -1790,7 +1790,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				if (S_ISDIR(inode->i_mode))
 					nfs_force_lookup_revalidate(inode);
 			}
-			inode->i_version = fattr->change_attr;
+			inode_set_iversion_raw(inode, fattr->change_attr);
 		}
 	} else {
 		nfsi->cache_validity |= save_cache_validity;

fs/nfs/nfs4proc.c

@@ -54,6 +54,7 @@
 #include <linux/xattr.h>
 #include <linux/utsname.h>
 #include <linux/freezer.h>
+#include <linux/iversion.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -1045,16 +1046,16 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo,
 
 	spin_lock(&dir->i_lock);
 	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-	if (cinfo->atomic && cinfo->before == dir->i_version) {
+	if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(dir)) {
 		nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE;
 		nfsi->attrtimeo_timestamp = jiffies;
 	} else {
 		nfs_force_lookup_revalidate(dir);
-		if (cinfo->before != dir->i_version)
+		if (cinfo->before != inode_peek_iversion_raw(dir))
 			nfsi->cache_validity |= NFS_INO_INVALID_ACCESS |
 				NFS_INO_INVALID_ACL;
 	}
-	dir->i_version = cinfo->after;
+	inode_set_iversion_raw(dir, cinfo->after);
 	nfsi->read_cache_jiffies = timestamp;
 	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_fscache_invalidate(dir);
@@ -2454,7 +2455,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 			data->file_created = true;
 		else if (o_res->cinfo.before != o_res->cinfo.after)
 			data->file_created = true;
-		if (data->file_created || dir->i_version != o_res->cinfo.after)
+		if (data->file_created ||
+		    inode_peek_iversion_raw(dir) != o_res->cinfo.after)
 			update_changeattr(dir, &o_res->cinfo,
 					o_res->f_attr->time_start);
 	}

fs/nfs/nfstrace.h

@@ -9,6 +9,7 @@
 #define _TRACE_NFS_H
 
 #include <linux/tracepoint.h>
+#include <linux/iversion.h>
 
 #define nfs_show_file_type(ftype) \
 	__print_symbolic(ftype, \
@@ -61,7 +62,7 @@ DECLARE_EVENT_CLASS(nfs_inode_event,
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
-			__entry->version = inode->i_version;
+			__entry->version = inode_peek_iversion_raw(inode);
 		),
 
 		TP_printk(
@@ -100,7 +101,7 @@ DECLARE_EVENT_CLASS(nfs_inode_event_done,
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
 			__entry->type = nfs_umode_to_dtype(inode->i_mode);
-			__entry->version = inode->i_version;
+			__entry->version = inode_peek_iversion_raw(inode);
 			__entry->size = i_size_read(inode);
 			__entry->nfsi_flags = nfsi->flags;
 			__entry->cache_validity = nfsi->cache_validity;

fs/nfs/write.c

@@ -23,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/freezer.h>
 #include <linux/wait.h>
+#include <linux/iversion.h>
 
 #include <linux/uaccess.h>
 
@@ -753,11 +754,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	 */
 	spin_lock(&mapping->private_lock);
 	if (!nfs_have_writebacks(inode) &&
-	    NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) {
-		spin_lock(&inode->i_lock);
-		inode->i_version++;
-		spin_unlock(&inode->i_lock);
-	}
+	    NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
+		inode_inc_iversion_raw(inode);
 	if (likely(!PageSwapCache(req->wb_page))) {
 		set_bit(PG_MAPPED, &req->wb_flags);
 		SetPagePrivate(req->wb_page);

fs/nfsd/nfsfh.h

@@ -11,6 +11,7 @@
 #include <linux/crc32.h>
 #include <linux/sunrpc/svc.h>
 #include <uapi/linux/nfsd/nfsfh.h>
+#include <linux/iversion.h>
 
 static inline __u32 ino_t_to_u32(ino_t ino)
 {
@@ -259,7 +260,7 @@ static inline u64 nfsd4_change_attribute(struct inode *inode)
 	chattr =  inode->i_ctime.tv_sec;
 	chattr <<= 30;
 	chattr += inode->i_ctime.tv_nsec;
-	chattr += inode->i_version;
+	chattr += inode_query_iversion(inode);
 	return chattr;
 }
 

fs/ntfs/inode.c

@@ -560,13 +560,6 @@ static int ntfs_read_locked_inode(struct inode *vi)
 	ntfs_debug("Entering for i_ino 0x%lx.", vi->i_ino);
 
 	/* Setup the generic vfs inode parts now. */
-
-	/*
-	 * This is for checking whether an inode has changed w.r.t. a file so
-	 * that the file can be updated if necessary (compare with f_version).
-	 */
-	vi->i_version = 1;
-
 	vi->i_uid = vol->uid;
 	vi->i_gid = vol->gid;
 	vi->i_mode = 0;
@@ -1240,7 +1233,6 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 	base_ni = NTFS_I(base_vi);
 
 	/* Just mirror the values from the base inode. */
-	vi->i_version	= base_vi->i_version;
 	vi->i_uid	= base_vi->i_uid;
 	vi->i_gid	= base_vi->i_gid;
 	set_nlink(vi, base_vi->i_nlink);
@@ -1507,7 +1499,6 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi)
 	ni	= NTFS_I(vi);
 	base_ni = NTFS_I(base_vi);
 	/* Just mirror the values from the base inode. */
-	vi->i_version	= base_vi->i_version;
 	vi->i_uid	= base_vi->i_uid;
 	vi->i_gid	= base_vi->i_gid;
 	set_nlink(vi, base_vi->i_nlink);

fs/ntfs/mft.c

@@ -2641,12 +2641,6 @@ mft_rec_already_initialized:
 			goto undo_mftbmp_alloc;
 		}
 		vi->i_ino = bit;
-		/*
-		 * This is for checking whether an inode has changed w.r.t. a
-		 * file so that the file can be updated if necessary (compare
-		 * with f_version).
-		 */
-		vi->i_version = 1;
 
 		/* The owner and group come from the ntfs volume. */
 		vi->i_uid = vol->uid;

fs/ocfs2/dir.c

@@ -42,6 +42,7 @@
 #include <linux/highmem.h>
 #include <linux/quotaops.h>
 #include <linux/sort.h>
+#include <linux/iversion.h>
 
 #include <cluster/masklog.h>
 
@@ -1174,7 +1175,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
 				le16_add_cpu(&pde->rec_len,
 						le16_to_cpu(de->rec_len));
 			de->inode = 0;
-			dir->i_version++;
+			inode_inc_iversion(dir);
 			ocfs2_journal_dirty(handle, bh);
 			goto bail;
 		}
@@ -1729,7 +1730,7 @@ int __ocfs2_add_entry(handle_t *handle,
 			if (ocfs2_dir_indexed(dir))
 				ocfs2_recalc_free_list(dir, handle, lookup);
 
-			dir->i_version++;
+			inode_inc_iversion(dir);
 			ocfs2_journal_dirty(handle, insert_bh);
 			retval = 0;
 			goto bail;
@@ -1775,7 +1776,7 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
 		 * readdir(2), then we might be pointing to an invalid
 		 * dirent right now.  Scan from the start of the block
 		 * to make sure. */
-		if (*f_version != inode->i_version) {
+		if (inode_cmp_iversion(inode, *f_version)) {
 			for (i = 0; i < i_size_read(inode) && i < offset; ) {
 				de = (struct ocfs2_dir_entry *)
 					(data->id_data + i);
@@ -1791,7 +1792,7 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
 				i += le16_to_cpu(de->rec_len);
 			}
 			ctx->pos = offset = i;
-			*f_version = inode->i_version;
+			*f_version = inode_query_iversion(inode);
 		}
 
 		de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos);
@@ -1869,7 +1870,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 		 * readdir(2), then we might be pointing to an invalid
 		 * dirent right now.  Scan from the start of the block
 		 * to make sure. */
-		if (*f_version != inode->i_version) {
+		if (inode_cmp_iversion(inode, *f_version)) {
 			for (i = 0; i < sb->s_blocksize && i < offset; ) {
 				de = (struct ocfs2_dir_entry *) (bh->b_data + i);
 				/* It's too expensive to do a full
@@ -1886,7 +1887,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 			offset = i;
 			ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1))
 				| offset;
-			*f_version = inode->i_version;
+			*f_version = inode_query_iversion(inode);
 		}
 
 		while (ctx->pos < i_size_read(inode)
@@ -1940,7 +1941,7 @@ static int ocfs2_dir_foreach_blk(struct inode *inode, u64 *f_version,
  */
 int ocfs2_dir_foreach(struct inode *inode, struct dir_context *ctx)
 {
-	u64 version = inode->i_version;
+	u64 version = inode_query_iversion(inode);
 	ocfs2_dir_foreach_blk(inode, &version, ctx, true);
 	return 0;
 }

fs/ocfs2/inode.c

@@ -28,6 +28,7 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
+#include <linux/iversion.h>
 
 #include <asm/byteorder.h>
 
@@ -302,7 +303,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 	OCFS2_I(inode)->ip_attr = le32_to_cpu(fe->i_attr);
 	OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features);
 
-	inode->i_version = 1;
+	inode_set_iversion(inode, 1);
 	inode->i_generation = le32_to_cpu(fe->i_generation);
 	inode->i_rdev = huge_decode_dev(le64_to_cpu(fe->id1.dev1.i_rdev));
 	inode->i_mode = le16_to_cpu(fe->i_mode);

fs/ocfs2/namei.c

@@ -41,6 +41,7 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/quotaops.h>
+#include <linux/iversion.h>
 
 #include <cluster/masklog.h>
 
@@ -1520,7 +1521,7 @@ static int ocfs2_rename(struct inode *old_dir,
 			mlog_errno(status);
 			goto bail;
 		}
-		new_dir->i_version++;
+		inode_inc_iversion(new_dir);
 
 		if (S_ISDIR(new_inode->i_mode))
 			ocfs2_set_links_count(newfe, 0);

fs/ocfs2/quota_global.c

@@ -12,6 +12,7 @@
 #include <linux/writeback.h>
 #include <linux/workqueue.h>
 #include <linux/llist.h>
+#include <linux/iversion.h>
 
 #include <cluster/masklog.h>
 
@@ -289,7 +290,7 @@ out:
 		mlog_errno(err);
 		return err;
 	}
-	gqinode->i_version++;
+	inode_inc_iversion(gqinode);
 	ocfs2_mark_inode_dirty(handle, gqinode, oinfo->dqi_gqi_bh);
 	return len;
 }

fs/ufs/dir.c

@@ -20,6 +20,7 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/swap.h>
+#include <linux/iversion.h>
 
 #include "ufs_fs.h"
 #include "ufs.h"
@@ -47,7 +48,7 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 	int err = 0;
 
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	block_write_end(NULL, mapping, pos, len, len, page, NULL);
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
@@ -428,7 +429,7 @@ ufs_readdir(struct file *file, struct dir_context *ctx)
 	unsigned long n = pos >> PAGE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1);
-	int need_revalidate = file->f_version != inode->i_version;
+	bool need_revalidate = inode_cmp_iversion(inode, file->f_version);
 	unsigned flags = UFS_SB(sb)->s_flags;
 
 	UFSD("BEGIN\n");
@@ -455,8 +456,8 @@ ufs_readdir(struct file *file, struct dir_context *ctx)
 				offset = ufs_validate_entry(sb, kaddr, offset, chunk_mask);
 				ctx->pos = (n<<PAGE_SHIFT) + offset;
 			}
-			file->f_version = inode->i_version;
-			need_revalidate = 0;
+			file->f_version = inode_query_iversion(inode);
+			need_revalidate = false;
 		}
 		de = (struct ufs_dir_entry *)(kaddr+offset);
 		limit = kaddr + ufs_last_byte(inode, n) - UFS_DIR_REC_LEN(1);

fs/ufs/inode.c

@@ -36,6 +36,7 @@
 #include <linux/mm.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/iversion.h>
 
 #include "ufs_fs.h"
 #include "ufs.h"
@@ -693,7 +694,7 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino)
 	if (err)
 		goto bad_inode;
 
-	inode->i_version++;
+	inode_inc_iversion(inode);
 	ufsi->i_lastfrag =
 		(inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift;
 	ufsi->i_dir_start_lookup = 0;

fs/ufs/super.c

@@ -88,6 +88,7 @@
 #include <linux/log2.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/iversion.h>
 
 #include "ufs_fs.h"
 #include "ufs.h"
@@ -1440,7 +1441,7 @@ static struct inode *ufs_alloc_inode(struct super_block *sb)
 	if (!ei)
 		return NULL;
 
-	ei->vfs_inode.i_version = 1;
+	inode_set_iversion(&ei->vfs_inode, 1);
 	seqlock_init(&ei->meta_lock);
 	mutex_init(&ei->truncate_mutex);
 	return &ei->vfs_inode;

fs/xfs/libxfs/xfs_inode_buf.c

@@ -32,6 +32,8 @@
 #include "xfs_ialloc.h"
 #include "xfs_dir2.h"
 
+#include <linux/iversion.h>
+
 /*
  * Check that none of the inode's in the buffer have a next
  * unlinked field of 0.
@@ -264,7 +266,8 @@ xfs_inode_from_disk(
 	to->di_flags	= be16_to_cpu(from->di_flags);
 
 	if (to->di_version == 3) {
-		inode->i_version = be64_to_cpu(from->di_changecount);
+		inode_set_iversion_queried(inode,
+					   be64_to_cpu(from->di_changecount));
 		to->di_crtime.t_sec = be32_to_cpu(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = be32_to_cpu(from->di_crtime.t_nsec);
 		to->di_flags2 = be64_to_cpu(from->di_flags2);
@@ -314,7 +317,7 @@ xfs_inode_to_disk(
 	to->di_flags = cpu_to_be16(from->di_flags);
 
 	if (from->di_version == 3) {
-		to->di_changecount = cpu_to_be64(inode->i_version);
+		to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
 		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
 		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
 		to->di_flags2 = cpu_to_be64(from->di_flags2);

fs/xfs/xfs_icache.c

@@ -37,6 +37,7 @@
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/iversion.h>
 
 /*
  * Allocate and initialise an xfs_inode.
@@ -293,14 +294,14 @@ xfs_reinit_inode(
 	int		error;
 	uint32_t	nlink = inode->i_nlink;
 	uint32_t	generation = inode->i_generation;
-	uint64_t	version = inode->i_version;
+	uint64_t	version = inode_peek_iversion(inode);
 	umode_t		mode = inode->i_mode;
 
 	error = inode_init_always(mp->m_super, inode);
 
 	set_nlink(inode, nlink);
 	inode->i_generation = generation;
-	inode->i_version = version;
+	inode_set_iversion_queried(inode, version);
 	inode->i_mode = mode;
 	return error;
 }

fs/xfs/xfs_inode.c

@@ -16,6 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include <linux/log2.h>
+#include <linux/iversion.h>
 
 #include "xfs.h"
 #include "xfs_fs.h"
@@ -832,7 +833,7 @@ xfs_ialloc(
 	ip->i_d.di_flags = 0;
 
 	if (ip->i_d.di_version == 3) {
-		inode->i_version = 1;
+		inode_set_iversion(inode, 1);
 		ip->i_d.di_flags2 = 0;
 		ip->i_d.di_cowextsize = 0;
 		ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec;

fs/xfs/xfs_inode_item.c

@@ -30,6 +30,7 @@
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
 
+#include <linux/iversion.h>
 
 kmem_zone_t	*xfs_ili_zone;		/* inode log item zone */
 
@@ -354,7 +355,7 @@ xfs_inode_to_log_dinode(
 	to->di_next_unlinked = NULLAGINO;
 
 	if (from->di_version == 3) {
-		to->di_changecount = inode->i_version;
+		to->di_changecount = inode_peek_iversion(inode);
 		to->di_crtime.t_sec = from->di_crtime.t_sec;
 		to->di_crtime.t_nsec = from->di_crtime.t_nsec;
 		to->di_flags2 = from->di_flags2;

fs/xfs/xfs_trans_inode.c

@@ -28,6 +28,8 @@
 #include "xfs_inode_item.h"
 #include "xfs_trace.h"
 
+#include <linux/iversion.h>
+
 /*
  * Add a locked inode to the transaction.
  *
@@ -110,15 +112,17 @@ xfs_trans_log_inode(
 
 	/*
 	 * First time we log the inode in a transaction, bump the inode change
-	 * counter if it is configured for this to occur. We don't use
-	 * inode_inc_version() because there is no need for extra locking around
-	 * i_version as we already hold the inode locked exclusively for
-	 * metadata modification.
+	 * counter if it is configured for this to occur. While we have the
+	 * inode locked exclusively for metadata modification, we can usually
+	 * avoid setting XFS_ILOG_CORE if no one has queried the value since
+	 * the last time it was incremented. If we have XFS_ILOG_CORE already
+	 * set however, then go ahead and bump the i_version counter
+	 * unconditionally.
 	 */
 	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
 	    IS_I_VERSION(VFS_I(ip))) {
-		VFS_I(ip)->i_version++;
-		flags |= XFS_ILOG_CORE;
+		if (inode_maybe_inc_iversion(VFS_I(ip), flags & XFS_ILOG_CORE))
+			flags |= XFS_ILOG_CORE;
 	}
 
 	tp->t_flags |= XFS_TRANS_DIRTY;

include/linux/fs.h

@@ -639,7 +639,7 @@ struct inode {
 		struct hlist_head	i_dentry;
 		struct rcu_head		i_rcu;
 	};
-	u64			i_version;
+	atomic64_t		i_version;
 	atomic_t		i_count;
 	atomic_t		i_dio_count;
 	atomic_t		i_writecount;
@@ -2036,21 +2036,6 @@ static inline void inode_dec_link_count(struct inode *inode)
 	mark_inode_dirty(inode);
 }
 
-/**
- * inode_inc_iversion - increments i_version
- * @inode: inode that need to be updated
- *
- * Every time the inode is modified, the i_version field will be incremented.
- * The filesystem has to be mounted with i_version flag
- */
-
-static inline void inode_inc_iversion(struct inode *inode)
-{
-       spin_lock(&inode->i_lock);
-       inode->i_version++;
-       spin_unlock(&inode->i_lock);
-}
-
 enum file_time_flags {
 	S_ATIME = 1,
 	S_MTIME = 2,

include/linux/iversion.h

@@ -0,0 +1,341 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IVERSION_H
+#define _LINUX_IVERSION_H
+
+#include <linux/fs.h>
+
+/*
+ * The inode->i_version field:
+ * ---------------------------
+ * The change attribute (i_version) is mandated by NFSv4 and is mostly for
+ * knfsd, but is also used for other purposes (e.g. IMA). The i_version must
+ * appear different to observers if there was a change to the inode's data or
+ * metadata since it was last queried.
+ *
+ * Observers see the i_version as a 64-bit number that never decreases. If it
+ * remains the same since it was last checked, then nothing has changed in the
+ * inode. If it's different then something has changed. Observers cannot infer
+ * anything about the nature or magnitude of the changes from the value, only
+ * that the inode has changed in some fashion.
+ *
+ * Not all filesystems properly implement the i_version counter. Subsystems that
+ * want to use i_version field on an inode should first check whether the
+ * filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro).
+ *
+ * Those that set SB_I_VERSION will automatically have their i_version counter
+ * incremented on writes to normal files. If the SB_I_VERSION is not set, then
+ * the VFS will not touch it on writes, and the filesystem can use it how it
+ * wishes. Note that the filesystem is always responsible for updating the
+ * i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.).
+ * We consider these sorts of filesystems to have a kernel-managed i_version.
+ *
+ * It may be impractical for filesystems to keep i_version updates atomic with
+ * respect to the changes that cause them.  They should, however, guarantee
+ * that i_version updates are never visible before the changes that caused
+ * them.  Also, i_version updates should never be delayed longer than it takes
+ * the original change to reach disk.
+ *
+ * This implementation uses the low bit in the i_version field as a flag to
+ * track when the value has been queried. If it has not been queried since it
+ * was last incremented, we can skip the increment in most cases.
+ *
+ * In the event that we're updating the ctime, we will usually go ahead and
+ * bump the i_version anyway. Since that has to go to stable storage in some
+ * fashion, we might as well increment it as well.
+ *
+ * With this implementation, the value should always appear to observers to
+ * increase over time if the file has changed. It's recommended to use
+ * inode_cmp_iversion() helper to compare values.
+ *
+ * Note that some filesystems (e.g. NFS and AFS) just use the field to store
+ * a server-provided value (for the most part). For that reason, those
+ * filesystems do not set SB_I_VERSION. These filesystems are considered to
+ * have a self-managed i_version.
+ *
+ * Persistently storing the i_version
+ * ----------------------------------
+ * Queries of the i_version field are not gated on them hitting the backing
+ * store. It's always possible that the host could crash after allowing
+ * a query of the value but before it has made it to disk.
+ *
+ * To mitigate this problem, filesystems should always use
+ * inode_set_iversion_queried when loading an existing inode from disk. This
+ * ensures that the next attempted inode increment will result in the value
+ * changing.
+ *
+ * Storing the value to disk therefore does not count as a query, so those
+ * filesystems should use inode_peek_iversion to grab the value to be stored.
+ * There is no need to flag the value as having been queried in that case.
+ */
+
+/*
+ * We borrow the lowest bit in the i_version to use as a flag to tell whether
+ * it has been queried since we last incremented it. If it has, then we must
+ * increment it on the next change. After that, we can clear the flag and
+ * avoid incrementing it again until it has again been queried.
+ */
+#define I_VERSION_QUERIED_SHIFT	(1)
+#define I_VERSION_QUERIED	(1ULL << (I_VERSION_QUERIED_SHIFT - 1))
+#define I_VERSION_INCREMENT	(1ULL << I_VERSION_QUERIED_SHIFT)
+
+/**
+ * inode_set_iversion_raw - set i_version to the specified raw value
+ * @inode: inode to set
+ * @val: new i_version value to set
+ *
+ * Set @inode's i_version field to @val. This function is for use by
+ * filesystems that self-manage the i_version.
+ *
+ * For example, the NFS client stores its NFSv4 change attribute in this way,
+ * and the AFS client stores the data_version from the server here.
+ */
+static inline void
+inode_set_iversion_raw(struct inode *inode, u64 val)
+{
+	atomic64_set(&inode->i_version, val);
+}
+
+/**
+ * inode_peek_iversion_raw - grab a "raw" iversion value
+ * @inode: inode from which i_version should be read
+ *
+ * Grab a "raw" inode->i_version value and return it. The i_version is not
+ * flagged or converted in any way. This is mostly used to access a self-managed
+ * i_version.
+ *
+ * With those filesystems, we want to treat the i_version as an entirely
+ * opaque value.
+ */
+static inline u64
+inode_peek_iversion_raw(const struct inode *inode)
+{
+	return atomic64_read(&inode->i_version);
+}
+
+/**
+ * inode_set_iversion - set i_version to a particular value
+ * @inode: inode to set
+ * @val: new i_version value to set
+ *
+ * Set @inode's i_version field to @val. This function is for filesystems with
+ * a kernel-managed i_version, for initializing a newly-created inode from
+ * scratch.
+ *
+ * In this case, we do not set the QUERIED flag since we know that this value
+ * has never been queried.
+ */
+static inline void
+inode_set_iversion(struct inode *inode, u64 val)
+{
+	inode_set_iversion_raw(inode, val << I_VERSION_QUERIED_SHIFT);
+}
+
+/**
+ * inode_set_iversion_queried - set i_version to a particular value as quereied
+ * @inode: inode to set
+ * @val: new i_version value to set
+ *
+ * Set @inode's i_version field to @val, and flag it for increment on the next
+ * change.
+ *
+ * Filesystems that persistently store the i_version on disk should use this
+ * when loading an existing inode from disk.
+ *
+ * When loading in an i_version value from a backing store, we can't be certain
+ * that it wasn't previously viewed before being stored. Thus, we must assume
+ * that it was, to ensure that we don't end up handing out the same value for
+ * different versions of the same inode.
+ */
+static inline void
+inode_set_iversion_queried(struct inode *inode, u64 val)
+{
+	inode_set_iversion_raw(inode, (val << I_VERSION_QUERIED_SHIFT) |
+				I_VERSION_QUERIED);
+}
+
+/**
+ * inode_maybe_inc_iversion - increments i_version
+ * @inode: inode with the i_version that should be updated
+ * @force: increment the counter even if it's not necessary?
+ *
+ * Every time the inode is modified, the i_version field must be seen to have
+ * changed by any observer.
+ *
+ * If "force" is set or the QUERIED flag is set, then ensure that we increment
+ * the value, and clear the queried flag.
+ *
+ * In the common case where neither is set, then we can return "false" without
+ * updating i_version.
+ *
+ * If this function returns false, and no other metadata has changed, then we
+ * can avoid logging the metadata.
+ */
+static inline bool
+inode_maybe_inc_iversion(struct inode *inode, bool force)
+{
+	u64 cur, old, new;
+
+	/*
+	 * The i_version field is not strictly ordered with any other inode
+	 * information, but the legacy inode_inc_iversion code used a spinlock
+	 * to serialize increments.
+	 *
+	 * Here, we add full memory barriers to ensure that any de-facto
+	 * ordering with other info is preserved.
+	 *
+	 * This barrier pairs with the barrier in inode_query_iversion()
+	 */
+	smp_mb();
+	cur = inode_peek_iversion_raw(inode);
+	for (;;) {
+		/* If flag is clear then we needn't do anything */
+		if (!force && !(cur & I_VERSION_QUERIED))
+			return false;
+
+		/* Since lowest bit is flag, add 2 to avoid it */
+		new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT;
+
+		old = atomic64_cmpxchg(&inode->i_version, cur, new);
+		if (likely(old == cur))
+			break;
+		cur = old;
+	}
+	return true;
+}
+
+
+/**
+ * inode_inc_iversion - forcibly increment i_version
+ * @inode: inode that needs to be updated
+ *
+ * Forcbily increment the i_version field. This always results in a change to
+ * the observable value.
+ */
+static inline void
+inode_inc_iversion(struct inode *inode)
+{
+	inode_maybe_inc_iversion(inode, true);
+}
+
+/**
+ * inode_iversion_need_inc - is the i_version in need of being incremented?
+ * @inode: inode to check
+ *
+ * Returns whether the inode->i_version counter needs incrementing on the next
+ * change. Just fetch the value and check the QUERIED flag.
+ */
+static inline bool
+inode_iversion_need_inc(struct inode *inode)
+{
+	return inode_peek_iversion_raw(inode) & I_VERSION_QUERIED;
+}
+
+/**
+ * inode_inc_iversion_raw - forcibly increment raw i_version
+ * @inode: inode that needs to be updated
+ *
+ * Forcbily increment the raw i_version field. This always results in a change
+ * to the raw value.
+ *
+ * NFS will use the i_version field to store the value from the server. It
+ * mostly treats it as opaque, but in the case where it holds a write
+ * delegation, it must increment the value itself. This function does that.
+ */
+static inline void
+inode_inc_iversion_raw(struct inode *inode)
+{
+	atomic64_inc(&inode->i_version);
+}
+
+/**
+ * inode_peek_iversion - read i_version without flagging it to be incremented
+ * @inode: inode from which i_version should be read
+ *
+ * Read the inode i_version counter for an inode without registering it as a
+ * query.
+ *
+ * This is typically used by local filesystems that need to store an i_version
+ * on disk. In that situation, it's not necessary to flag it as having been
+ * viewed, as the result won't be used to gauge changes from that point.
+ */
+static inline u64
+inode_peek_iversion(const struct inode *inode)
+{
+	return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT;
+}
+
+/**
+ * inode_query_iversion - read i_version for later use
+ * @inode: inode from which i_version should be read
+ *
+ * Read the inode i_version counter. This should be used by callers that wish
+ * to store the returned i_version for later comparison. This will guarantee
+ * that a later query of the i_version will result in a different value if
+ * anything has changed.
+ *
+ * In this implementation, we fetch the current value, set the QUERIED flag and
+ * then try to swap it into place with a cmpxchg, if it wasn't already set. If
+ * that fails, we try again with the newly fetched value from the cmpxchg.
+ */
+static inline u64
+inode_query_iversion(struct inode *inode)
+{
+	u64 cur, old, new;
+
+	cur = inode_peek_iversion_raw(inode);
+	for (;;) {
+		/* If flag is already set, then no need to swap */
+		if (cur & I_VERSION_QUERIED) {
+			/*
+			 * This barrier (and the implicit barrier in the
+			 * cmpxchg below) pairs with the barrier in
+			 * inode_maybe_inc_iversion().
+			 */
+			smp_mb();
+			break;
+		}
+
+		new = cur | I_VERSION_QUERIED;
+		old = atomic64_cmpxchg(&inode->i_version, cur, new);
+		if (likely(old == cur))
+			break;
+		cur = old;
+	}
+	return cur >> I_VERSION_QUERIED_SHIFT;
+}
+
+/**
+ * inode_cmp_iversion_raw - check whether the raw i_version counter has changed
+ * @inode: inode to check
+ * @old: old value to check against its i_version
+ *
+ * Compare the current raw i_version counter with a previous one. Returns 0 if
+ * they are the same or non-zero if they are different.
+ */
+static inline s64
+inode_cmp_iversion_raw(const struct inode *inode, u64 old)
+{
+	return (s64)inode_peek_iversion_raw(inode) - (s64)old;
+}
+
+/**
+ * inode_cmp_iversion - check whether the i_version counter has changed
+ * @inode: inode to check
+ * @old: old value to check against its i_version
+ *
+ * Compare an i_version counter with a previous one. Returns 0 if they are
+ * the same, a positive value if the one in the inode appears newer than @old,
+ * and a negative value if @old appears to be newer than the one in the
+ * inode.
+ *
+ * Note that we don't need to set the QUERIED flag in this case, as the value
+ * in the inode is not being recorded for later use.
+ */
+
+static inline s64
+inode_cmp_iversion(const struct inode *inode, u64 old)
+{
+	return (s64)(inode_peek_iversion_raw(inode) & ~I_VERSION_QUERIED) -
+	       (s64)(old << I_VERSION_QUERIED_SHIFT);
+}
+#endif

security/integrity/ima/ima_api.c

@@ -18,6 +18,7 @@
 #include <linux/fs.h>
 #include <linux/xattr.h>
 #include <linux/evm.h>
+#include <linux/iversion.h>
 
 #include "ima.h"
 
@@ -215,7 +216,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	 * which do not support i_version, support is limited to an initial
 	 * measurement/appraisal/audit.
 	 */
-	i_version = file_inode(file)->i_version;
+	i_version = inode_query_iversion(inode);
 	hash.hdr.algo = algo;
 
 	/* Initialize hash digest to 0's in case of failure */

security/integrity/ima/ima_main.c

@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/xattr.h>
 #include <linux/ima.h>
+#include <linux/iversion.h>
 
 #include "ima.h"
 
@@ -127,7 +128,8 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint,
 
 	inode_lock(inode);
 	if (atomic_read(&inode->i_writecount) == 1) {
-		if ((iint->version != inode->i_version) ||
+		if (!IS_I_VERSION(inode) ||
+		    inode_cmp_iversion(inode, iint->version) ||
 		    (iint->flags & IMA_NEW_FILE)) {
 			iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
 			iint->measured_pcrs = 0;