Merge tag 'v6.6-vfs.ctime' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs timestamp updates from Christian Brauner:
 "This adds VFS support for multi-grain timestamps and converts tmpfs,
  xfs, ext4, and btrfs to use them. This carries acks from all relevant
  filesystems.

  The VFS always uses coarse-grained timestamps when updating the ctime
  and mtime after a change. This has the benefit of allowing filesystems
  to optimize away a lot of metadata updates, down to around 1 per
  jiffy, even when a file is under heavy writes.

  Unfortunately, this has always been an issue when we're exporting via
  NFSv3, which relies on timestamps to validate caches. A lot of changes
  can happen in a jiffy, so timestamps aren't sufficient to help the
  client decide to invalidate the cache.

  Even with NFSv4, a lot of exported filesystems don't properly support
  a change attribute and are subject to the same problems with timestamp
  granularity. Other applications have similar issues with timestamps
  (e.g., backup applications).

  If we were to always use fine-grained timestamps, that would improve
  the situation, but that becomes rather expensive, as the underlying
  filesystem would have to log a lot more metadata updates.

  This introduces fine-grained timestamps that are used when they are
  actively queried.

  This uses the 31st bit of the ctime tv_nsec field to indicate that
  something has queried the inode for the mtime or ctime. When this flag
  is set, on the next mtime or ctime update, the kernel will fetch a
  fine-grained timestamp instead of the usual coarse-grained one.

  As POSIX generally mandates that when the mtime changes, the ctime
  must also change the kernel always stores normalized ctime values, so
  only the first 30 bits of the tv_nsec field are ever used.

  Filesytems can opt into this behavior by setting the FS_MGTIME flag in
  the fstype. Filesystems that don't set this flag will continue to use
  coarse-grained timestamps.

  Various preparatory changes, fixes and cleanups are included:

   - Fixup all relevant places where POSIX requires updating ctime
     together with mtime. This is a wide-range of places and all
     maintainers provided necessary Acks.

   - Add new accessors for inode->i_ctime directly and change all
     callers to rely on them. Plain accesses to inode->i_ctime are now
     gone and it is accordingly rename to inode->__i_ctime and commented
     as requiring accessors.

   - Extend generic_fillattr() to pass in a request mask mirroring in a
     sense the statx() uapi. This allows callers to pass in a request
     mask to only get a subset of attributes filled in.

   - Rework timestamp updates so it's possible to drop the @now
     parameter the update_time() inode operation and associated helpers.

   - Add inode_update_timestamps() and convert all filesystems to it
     removing a bunch of open-coding"

* tag 'v6.6-vfs.ctime' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (107 commits)
  btrfs: convert to multigrain timestamps
  ext4: switch to multigrain timestamps
  xfs: switch to multigrain timestamps
  tmpfs: add support for multigrain timestamps
  fs: add infrastructure for multigrain timestamps
  fs: drop the timespec64 argument from update_time
  xfs: have xfs_vn_update_time gets its own timestamp
  fat: make fat_update_time get its own timestamp
  fat: remove i_version handling from fat_update_time
  ubifs: have ubifs_update_time use inode_update_timestamps
  btrfs: have it use inode_update_timestamps
  fs: drop the timespec64 arg from generic_update_time
  fs: pass the request_mask to generic_fillattr
  fs: remove silly warning from current_time
  gfs2: fix timestamp handling on quota inodes
  fs: rename i_ctime field to __i_ctime
  selinux: convert to ctime accessor functions
  security: convert to ctime accessor functions
  apparmor: convert to ctime accessor functions
  sunrpc: convert to ctime accessor functions
  ...

9 files changed, 31 insertions, 24 deletions

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 758aacd8166b..a35781577cad 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -222,7 +222,8 @@ xfs_inode_from_disk(
 	 */
 	inode->i_atime = xfs_inode_from_disk_ts(from, from->di_atime);
 	inode->i_mtime = xfs_inode_from_disk_ts(from, from->di_mtime);
-	inode->i_ctime = xfs_inode_from_disk_ts(from, from->di_ctime);
+	inode_set_ctime_to_ts(inode,
+			      xfs_inode_from_disk_ts(from, from->di_ctime));
 
 	ip->i_disk_size = be64_to_cpu(from->di_size);
 	ip->i_nblocks = be64_to_cpu(from->di_nblocks);
@@ -316,7 +317,7 @@ xfs_inode_to_disk(
 
 	to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime);
 	to->di_mtime = xfs_inode_to_disk_ts(ip, inode->i_mtime);
-	to->di_ctime = xfs_inode_to_disk_ts(ip, inode->i_ctime);
+	to->di_ctime = xfs_inode_to_disk_ts(ip, inode_get_ctime(inode));
 	to->di_nlink = cpu_to_be32(inode->i_nlink);
 	to->di_gen = cpu_to_be32(inode->i_generation);
 	to->di_mode = cpu_to_be16(inode->i_mode);
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index cb4796b6e693..ad22656376d3 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -62,12 +62,12 @@ xfs_trans_ichgtime(
 	ASSERT(tp);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	tv = current_time(inode);
+	/* If the mtime changes, then ctime must also change */
+	ASSERT(flags & XFS_ICHGTIME_CHG);
 
+	tv = inode_set_ctime_current(inode);
 	if (flags & XFS_ICHGTIME_MOD)
 		inode->i_mtime = tv;
-	if (flags & XFS_ICHGTIME_CHG)
-		inode->i_ctime = tv;
 	if (flags & XFS_ICHGTIME_CREATE)
 		ip->i_crtime = tv;
 }
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 791db7d9c849..6b840301817a 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -233,7 +233,7 @@ xfs_acl_set_mode(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 	inode->i_mode = mode;
-	inode->i_ctime = current_time(inode);
+	inode_set_ctime_current(inode);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	if (xfs_has_wsync(mp))
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index fbb675563208..fcefab687285 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1644,6 +1644,7 @@ xfs_swap_extents(
 	uint64_t		f;
 	int			resblks = 0;
 	unsigned int		flags = 0;
+	struct timespec64	ctime;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
@@ -1756,8 +1757,9 @@ xfs_swap_extents(
 	 * process that the file was not changed out from
 	 * under it.
 	 */
-	if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
-	    (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
+	ctime = inode_get_ctime(VFS_I(ip));
+	if ((sbp->bs_ctime.tv_sec != ctime.tv_sec) ||
+	    (sbp->bs_ctime.tv_nsec != ctime.tv_nsec) ||
 	    (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
 	    (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
 		error = -EBUSY;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9e62cc500140..360fe83a334f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -843,10 +843,9 @@ xfs_init_new_inode(
 	ip->i_df.if_nextents = 0;
 	ASSERT(ip->i_nblocks == 0);
 
-	tv = current_time(inode);
+	tv = inode_set_ctime_current(inode);
 	inode->i_mtime = tv;
 	inode->i_atime = tv;
-	inode->i_ctime = tv;
 
 	ip->i_extsize = 0;
 	ip->i_diflags = 0;
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 91c847a84e10..127b2410eb20 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -528,7 +528,7 @@ xfs_inode_to_log_dinode(
 	memset(to->di_pad3, 0, sizeof(to->di_pad3));
 	to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode->i_atime);
 	to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode->i_mtime);
-	to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode->i_ctime);
+	to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode_get_ctime(inode));
 	to->di_nlink = inode->i_nlink;
 	to->di_gen = inode->i_generation;
 	to->di_mode = inode->i_mode;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 24718adb3c16..2ededd3f6b8c 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -573,10 +573,10 @@ xfs_vn_getattr(
 	stat->gid = vfsgid_into_kgid(vfsgid);
 	stat->ino = ip->i_ino;
 	stat->atime = inode->i_atime;
-	stat->mtime = inode->i_mtime;
-	stat->ctime = inode->i_ctime;
 	stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
 
+	fill_mg_cmtime(stat, request_mask, inode);
+
 	if (xfs_has_v3inodes(mp)) {
 		if (request_mask & STATX_BTIME) {
 			stat->result_mask |= STATX_BTIME;
@@ -917,7 +917,7 @@ xfs_setattr_size(
 	if (newsize != oldsize &&
 	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
 		iattr->ia_ctime = iattr->ia_mtime =
-			current_time(inode);
+			current_mgtime(inode);
 		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
 	}
 
@@ -1029,7 +1029,6 @@ xfs_vn_setattr(
 STATIC int
 xfs_vn_update_time(
 	struct inode		*inode,
-	struct timespec64	*now,
 	int			flags)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
@@ -1037,13 +1036,16 @@ xfs_vn_update_time(
 	int			log_flags = XFS_ILOG_TIMESTAMP;
 	struct xfs_trans	*tp;
 	int			error;
+	struct timespec64	now;
 
 	trace_xfs_update_time(ip);
 
 	if (inode->i_sb->s_flags & SB_LAZYTIME) {
 		if (!((flags & S_VERSION) &&
-		      inode_maybe_inc_iversion(inode, false)))
-			return generic_update_time(inode, now, flags);
+		      inode_maybe_inc_iversion(inode, false))) {
+			generic_update_time(inode, flags);
+			return 0;
+		}
 
 		/* Capture the iversion update that just occurred */
 		log_flags |= XFS_ILOG_CORE;
@@ -1054,12 +1056,15 @@ xfs_vn_update_time(
 		return error;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (flags & S_CTIME)
-		inode->i_ctime = *now;
+	if (flags & (S_CTIME|S_MTIME))
+		now = inode_set_ctime_current(inode);
+	else
+		now = current_time(inode);
+
 	if (flags & S_MTIME)
-		inode->i_mtime = *now;
+		inode->i_mtime = now;
 	if (flags & S_ATIME)
-		inode->i_atime = *now;
+		inode->i_atime = now;
 
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 	xfs_trans_log_inode(tp, ip, log_flags);
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index f225413a993c..c2093cb56092 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -100,8 +100,8 @@ xfs_bulkstat_one_int(
 	buf->bs_atime_nsec = inode->i_atime.tv_nsec;
 	buf->bs_mtime = inode->i_mtime.tv_sec;
 	buf->bs_mtime_nsec = inode->i_mtime.tv_nsec;
-	buf->bs_ctime = inode->i_ctime.tv_sec;
-	buf->bs_ctime_nsec = inode->i_ctime.tv_nsec;
+	buf->bs_ctime = inode_get_ctime(inode).tv_sec;
+	buf->bs_ctime_nsec = inode_get_ctime(inode).tv_nsec;
 	buf->bs_gen = inode->i_generation;
 	buf->bs_mode = inode->i_mode;
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 818510243130..4b10edb2c972 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2009,7 +2009,7 @@ static struct file_system_type xfs_fs_type = {
 	.init_fs_context	= xfs_init_fs_context,
 	.parameters		= xfs_fs_parameters,
 	.kill_sb		= kill_block_super,
-	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
+	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
 };
 MODULE_ALIAS_FS("xfs");