Merge tag 'v6.6-rc3.vfs.ctime.revert' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull finegrained timestamp reverts from Christian Brauner:
"Earlier this week we sent a few minor fixes for the multi-grained
timestamp work in [1]. While we were polishing those up after Linus
realized that there might be a nicer way to fix them we received a
regression report in [2] that fine grained timestamps break gnulib
tests and thus possibly other tools.

The kernel will elide fine-grain timestamp updates when no one is
actively querying for them to avoid performance impacts. So a sequence
like write(f1) stat(f2) write(f2) stat(f2) write(f1) stat(f1) may
result in timestamp f1 to be older than the final f2 timestamp even
though f1 was last written too but the second write didn't update the
timestamp.

Such plotholes can lead to subtle bugs when programs compare
timestamps. For example, the nap() function in [2] will estimate that
it needs to wait one ns on a fine-grain timestamp enabled filesytem
between subsequent calls to observe a timestamp change. But in general
we don't update timestamps with more than one jiffie if we think that
no one is actively querying for fine-grain timestamps to avoid
performance impacts.

While discussing various fixes the decision was to go back to the
drawing board and ultimately to explore a solution that involves only
exposing such fine-grained timestamps to nfs internally and never to
userspace.

As there are multiple solutions discussed the honest thing to do here
is not to fix this up or disable it but to cleanly revert. The general
infrastructure will probably come back but there is no reason to keep
this code in mainline.

The general changes to timestamp handling are valid and a good cleanup
that will stay. The revert is fully bisectable"

Link: https://lore.kernel.org/all/20230918-hirte-neuzugang-4c2324e7bae3@brauner [1]
Link: https://lore.kernel.org/all/[e-mail] [2]

* tag 'v6.6-rc3.vfs.ctime.revert' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
Revert "fs: add infrastructure for multigrain timestamps"
Revert "btrfs: convert to multigrain timestamps"
Revert "ext4: switch to multigrain timestamps"
Revert "xfs: switch to multigrain timestamps"
Revert "tmpfs: add support for multigrain timestamps"

fs/btrfs/file.c

···
 	btrfs_drew_write_unlock(&inode->root->snapshot_lock);
 }
 
+static void update_time_for_write(struct inode *inode)
+{
+	struct timespec64 now, ctime;
+
+	if (IS_NOCMTIME(inode))
+		return;
+
+	now = current_time(inode);
+	if (!timespec64_equal(&inode->i_mtime, &now))
+		inode->i_mtime = now;
+
+	ctime = inode_get_ctime(inode);
+	if (!timespec64_equal(&ctime, &now))
+		inode_set_ctime_to_ts(inode, now);
+
+	if (IS_I_VERSION(inode))
+		inode_inc_iversion(inode);
+}
+
 static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from,
 			     size_t count)
 {
···
 	 * need to start yet another transaction to update the inode as we will
 	 * update the inode when we finish writing whatever data we write.
 	 */
-	if (!IS_NOCMTIME(inode)) {
-		inode->i_mtime = inode_set_ctime_current(inode);
-		inode_inc_iversion(inode);
-	}
+	update_time_for_write(inode);
 
 	start_pos = round_down(pos, fs_info->sectorsize);
 	oldsize = i_size_read(inode);

fs/btrfs/super.c

···
 	.name		= "btrfs",
 	.mount		= btrfs_mount,
 	.kill_sb	= btrfs_kill_super,
-	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_MGTIME,
+	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
 };
 
 static struct file_system_type btrfs_root_fs_type = {
···
 	.name		= "btrfs",
 	.mount		= btrfs_mount_root,
 	.kill_sb	= btrfs_kill_super,
-	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA |
-			  FS_ALLOW_IDMAP | FS_MGTIME,
+	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP,
 };
 
 MODULE_ALIAS_FS("btrfs");

fs/ext4/super.c

···
 	.init_fs_context	= ext4_init_fs_context,
 	.parameters		= ext4_param_specs,
 	.kill_sb		= ext4_kill_sb,
-	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
+	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
 };
 MODULE_ALIAS_FS("ext4");
 

fs/inode.c

···
 }
 EXPORT_SYMBOL(file_remove_privs);
 
-/**
- * current_mgtime - Return FS time (possibly fine-grained)
- * @inode: inode.
- *
- * Return the current time truncated to the time granularity supported by
- * the fs, as suitable for a ctime/mtime change. If the ctime is flagged
- * as having been QUERIED, get a fine-grained timestamp.
- */
-struct timespec64 current_mgtime(struct inode *inode)
-{
-	struct timespec64 now, ctime;
-	atomic_long_t *pnsec = (atomic_long_t *)&inode->__i_ctime.tv_nsec;
-	long nsec = atomic_long_read(pnsec);
-
-	if (nsec & I_CTIME_QUERIED) {
-		ktime_get_real_ts64(&now);
-		return timestamp_truncate(now, inode);
-	}
-
-	ktime_get_coarse_real_ts64(&now);
-	now = timestamp_truncate(now, inode);
-
-	/*
-	 * If we've recently fetched a fine-grained timestamp
-	 * then the coarse-grained one may still be earlier than the
-	 * existing ctime. Just keep the existing value if so.
-	 */
-	ctime = inode_get_ctime(inode);
-	if (timespec64_compare(&ctime, &now) > 0)
-		now = ctime;
-
-	return now;
-}
-EXPORT_SYMBOL(current_mgtime);
-
-static struct timespec64 current_ctime(struct inode *inode)
-{
-	if (is_mgtime(inode))
-		return current_mgtime(inode);
-	return current_time(inode);
-}
-
 static int inode_needs_update_time(struct inode *inode)
 {
 	int sync_it = 0;
-	struct timespec64 now = current_ctime(inode);
+	struct timespec64 now = current_time(inode);
 	struct timespec64 ctime;
 
 	/* First try to exhaust all avenues to not sync */
···
  */
 struct timespec64 inode_set_ctime_current(struct inode *inode)
 {
-	struct timespec64 now;
-	struct timespec64 ctime;
+	struct timespec64 now = current_time(inode);
 
-	ctime.tv_nsec = READ_ONCE(inode->__i_ctime.tv_nsec);
-	if (!(ctime.tv_nsec & I_CTIME_QUERIED)) {
-		now = current_time(inode);
-
-		/* Just copy it into place if it's not multigrain */
-		if (!is_mgtime(inode)) {
-			inode_set_ctime_to_ts(inode, now);
-			return now;
-		}
-
-		/*
-		 * If we've recently updated with a fine-grained timestamp,
-		 * then the coarse-grained one may still be earlier than the
-		 * existing ctime. Just keep the existing value if so.
-		 */
-		ctime.tv_sec = inode->__i_ctime.tv_sec;
-		if (timespec64_compare(&ctime, &now) > 0)
-			return ctime;
-
-		/*
-		 * Ctime updates are usually protected by the inode_lock, but
-		 * we can still race with someone setting the QUERIED flag.
-		 * Try to swap the new nsec value into place. If it's changed
-		 * in the interim, then just go with a fine-grained timestamp.
-		 */
-		if (cmpxchg(&inode->__i_ctime.tv_nsec, ctime.tv_nsec,
-			    now.tv_nsec) != ctime.tv_nsec)
-			goto fine_grained;
-		inode->__i_ctime.tv_sec = now.tv_sec;
-		return now;
-	}
-fine_grained:
-	ktime_get_real_ts64(&now);
-	inode_set_ctime_to_ts(inode, timestamp_truncate(now, inode));
+	inode_set_ctime(inode, now.tv_sec, now.tv_nsec);
 	return now;
 }
 EXPORT_SYMBOL(inode_set_ctime_current);

fs/stat.c

···
 #include "mount.h"
 
 /**
- * fill_mg_cmtime - Fill in the mtime and ctime and flag ctime as QUERIED
- * @stat: where to store the resulting values
- * @request_mask: STATX_* values requested
- * @inode: inode from which to grab the c/mtime
- *
- * Given @inode, grab the ctime and mtime out if it and store the result
- * in @stat. When fetching the value, flag it as queried so the next write
- * will use a fine-grained timestamp.
- */
-void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode)
-{
-	atomic_long_t *pnsec = (atomic_long_t *)&inode->__i_ctime.tv_nsec;
-
-	/* If neither time was requested, then don't report them */
-	if (!(request_mask & (STATX_CTIME|STATX_MTIME))) {
-		stat->result_mask &= ~(STATX_CTIME|STATX_MTIME);
-		return;
-	}
-
-	stat->mtime = inode->i_mtime;
-	stat->ctime.tv_sec = inode->__i_ctime.tv_sec;
-	/*
-	 * Atomically set the QUERIED flag and fetch the new value with
-	 * the flag masked off.
-	 */
-	stat->ctime.tv_nsec = atomic_long_fetch_or(I_CTIME_QUERIED, pnsec) &
-					~I_CTIME_QUERIED;
-}
-EXPORT_SYMBOL(fill_mg_cmtime);
-
-/**
  * generic_fillattr - Fill in the basic attributes from the inode struct
  * @idmap:		idmap of the mount the inode was found from
  * @request_mask:	statx request_mask
···
 	stat->rdev = inode->i_rdev;
 	stat->size = i_size_read(inode);
 	stat->atime = inode->i_atime;
-
-	if (is_mgtime(inode)) {
-		fill_mg_cmtime(stat, request_mask, inode);
-	} else {
-		stat->mtime = inode->i_mtime;
-		stat->ctime = inode_get_ctime(inode);
-	}
-
+	stat->mtime = inode->i_mtime;
+	stat->ctime = inode_get_ctime(inode);
 	stat->blksize = i_blocksize(inode);
 	stat->blocks = inode->i_blocks;
 

fs/xfs/libxfs/xfs_trans_inode.c

···
 	ASSERT(tp);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	/* If the mtime changes, then ctime must also change */
-	ASSERT(flags & XFS_ICHGTIME_CHG);
+	tv = current_time(inode);
 
-	tv = inode_set_ctime_current(inode);
 	if (flags & XFS_ICHGTIME_MOD)
 		inode->i_mtime = tv;
+	if (flags & XFS_ICHGTIME_CHG)
+		inode_set_ctime_to_ts(inode, tv);
 	if (flags & XFS_ICHGTIME_CREATE)
 		ip->i_crtime = tv;
 }

fs/xfs/xfs_iops.c

···
 	stat->gid = vfsgid_into_kgid(vfsgid);
 	stat->ino = ip->i_ino;
 	stat->atime = inode->i_atime;
+	stat->mtime = inode->i_mtime;
+	stat->ctime = inode_get_ctime(inode);
 	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) {
···
 	if (newsize != oldsize &&
 	    !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
 		iattr->ia_ctime = iattr->ia_mtime =
-			current_mgtime(inode);
+			current_time(inode);
 		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
 	}
 

fs/xfs/xfs_super.c

···
 	.init_fs_context	= xfs_init_fs_context,
 	.parameters		= xfs_fs_parameters,
 	.kill_sb		= xfs_kill_sb,
-	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
+	.fs_flags		= FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
 };
 MODULE_ALIAS_FS("xfs");
 

include/linux/fs.h

···
 	       kgid_has_mapping(fs_userns, kgid);
 }
 
-struct timespec64 current_mgtime(struct inode *inode);
 struct timespec64 current_time(struct inode *inode);
 struct timespec64 inode_set_ctime_current(struct inode *inode);
-
-/*
- * Multigrain timestamps
- *
- * Conditionally use fine-grained ctime and mtime timestamps when there
- * are users actively observing them via getattr. The primary use-case
- * for this is NFS clients that use the ctime to distinguish between
- * different states of the file, and that are often fooled by multiple
- * operations that occur in the same coarse-grained timer tick.
- *
- * The kernel always keeps normalized struct timespec64 values in the ctime,
- * which means that only the first 30 bits of the value are used. Use the
- * 31st bit of the ctime's tv_nsec field as a flag to indicate that the value
- * has been queried since it was last updated.
- */
-#define I_CTIME_QUERIED		(1L<<30)
 
 /**
  * inode_get_ctime - fetch the current ctime from the inode
  * @inode: inode from which to fetch ctime
  *
- * Grab the current ctime tv_nsec field from the inode, mask off the
- * I_CTIME_QUERIED flag and return it. This is mostly intended for use by
- * internal consumers of the ctime that aren't concerned with ensuring a
- * fine-grained update on the next change (e.g. when preparing to store
- * the value in the backing store for later retrieval).
- *
- * This is safe to call regardless of whether the underlying filesystem
- * is using multigrain timestamps.
+ * Grab the current ctime from the inode and return it.
  */
 static inline struct timespec64 inode_get_ctime(const struct inode *inode)
 {
-	struct timespec64 ctime;
-
-	ctime.tv_sec = inode->__i_ctime.tv_sec;
-	ctime.tv_nsec = inode->__i_ctime.tv_nsec & ~I_CTIME_QUERIED;
-
-	return ctime;
+	return inode->__i_ctime;
 }
 
 /**
···
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_DISALLOW_NOTIFY_PERM	16	/* Disable fanotify permission events */
 #define FS_ALLOW_IDMAP         32      /* FS has been updated to handle vfs idmappings. */
-#define FS_MGTIME		64	/* FS uses multigrain timestamps */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
···
 };
 
 #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
-
-/**
- * is_mgtime: is this inode using multigrain timestamps
- * @inode: inode to test for multigrain timestamps
- *
- * Return true if the inode uses multigrain timestamps, false otherwise.
- */
-static inline bool is_mgtime(const struct inode *inode)
-{
-	return inode->i_sb->s_type->fs_flags & FS_MGTIME;
-}
 
 extern struct dentry *mount_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
···
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
-void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode);
 void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
 void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
 extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);

mm/shmem.c

···
 #endif
 	.kill_sb	= kill_litter_super,
 #ifdef CONFIG_SHMEM
-	.fs_flags	= FS_USERNS_MOUNT | FS_ALLOW_IDMAP | FS_MGTIME,
+	.fs_flags	= FS_USERNS_MOUNT | FS_ALLOW_IDMAP,
 #else
 	.fs_flags	= FS_USERNS_MOUNT,
 #endif