fs: add infrastructure for multigrain timestamps

The VFS has always used coarse-grained timestamps when updating the
ctime and mtime after a change. This has the benefit of allowing
filesystems to optimize away a lot 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 when 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 fine-grained timestamps were always used, that would improve the
situation, but that becomes rather expensive, as the underlying
filesystem would have to log a lot more metadata updates.

What is needed is a way to only use fine-grained timestamps when they
are being actively queried. Use the (unused) top bit in
inode->i_ctime_nsec as a flag that indicates whether the current
timestamps have been queried via stat() or the like. When it's set,
allow the update to use a fine-grained timestamp iff it's necessary to
make the ctime show a different value.

If it has been queried, then first see whether the current coarse time
is later than the existing ctime. If it is, accept that value.  If it
isn't, then get a fine-grained timestamp and attempt to stamp the inode
ctime with that value. If that races with another concurrent stamp, then
abandon the update and take the new value without retrying.

Filesystems can opt into this by setting the FS_MGTIME fstype flag.
Others should be unaffected (other than being subject to the same floor
value as multigrain filesystems).

Tested-by: Randy Dunlap <rdunlap@infradead.org> # documentation bits
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20241002-mgtime-v10-3-d1c4717f5284@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 114 insertions, 25 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 10c4619faeef..53f56f6e1ff2 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2172,19 +2172,58 @@ int file_remove_privs(struct file *file)
 }
 EXPORT_SYMBOL(file_remove_privs);
 
+/**
+ * current_time - 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, but don't update
+ * the floor.
+ *
+ * For a multigrain inode, this is effectively an estimate of the timestamp
+ * that a file would receive. An actual update must go through
+ * inode_set_ctime_current().
+ */
+struct timespec64 current_time(struct inode *inode)
+{
+	struct timespec64 now;
+	u32 cns;
+
+	ktime_get_coarse_real_ts64_mg(&now);
+
+	if (!is_mgtime(inode))
+		goto out;
+
+	/* If nothing has queried it, then coarse time is fine */
+	cns = smp_load_acquire(&inode->i_ctime_nsec);
+	if (cns & I_CTIME_QUERIED) {
+		/*
+		 * If there is no apparent change, then get a fine-grained
+		 * timestamp.
+		 */
+		if (now.tv_nsec == (cns & ~I_CTIME_QUERIED))
+			ktime_get_real_ts64(&now);
+	}
+out:
+	return timestamp_truncate(now, inode);
+}
+EXPORT_SYMBOL(current_time);
+
 static int inode_needs_update_time(struct inode *inode)
 {
+	struct timespec64 now, ts;
 	int sync_it = 0;
-	struct timespec64 now = current_time(inode);
-	struct timespec64 ts;
 
 	/* First try to exhaust all avenues to not sync */
 	if (IS_NOCMTIME(inode))
 		return 0;
 
+	now = current_time(inode);
+
 	ts = inode_get_mtime(inode);
 	if (!timespec64_equal(&ts, &now))
-		sync_it = S_MTIME;
+		sync_it |= S_MTIME;
 
 	ts = inode_get_ctime(inode);
 	if (!timespec64_equal(&ts, &now))
@@ -2562,6 +2601,15 @@ void inode_nohighmem(struct inode *inode)
 }
 EXPORT_SYMBOL(inode_nohighmem);
 
+struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts)
+{
+	set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec);
+	inode->i_ctime_sec = ts.tv_sec;
+	inode->i_ctime_nsec = ts.tv_nsec;
+	return ts;
+}
+EXPORT_SYMBOL(inode_set_ctime_to_ts);
+
 /**
  * timestamp_truncate - Truncate timespec to a granularity
  * @t: Timespec
@@ -2594,36 +2642,77 @@ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode)
 EXPORT_SYMBOL(timestamp_truncate);
 
 /**
- * current_time - Return FS time
- * @inode: inode.
+ * inode_set_ctime_current - set the ctime to current_time
+ * @inode: inode
  *
- * Return the current time truncated to the time granularity supported by
- * the fs.
+ * Set the inode's ctime to the current value for the inode. Returns the
+ * current value that was assigned. If this is not a multigrain inode, then we
+ * set it to the later of the coarse time and floor value.
  *
- * Note that inode and inode->sb cannot be NULL.
- * Otherwise, the function warns and returns time without truncation.
+ * If it is multigrain, then we first see if the coarse-grained timestamp is
+ * distinct from what is already there. If so, then use that. Otherwise, get a
+ * fine-grained timestamp.
+ *
+ * After that, try to swap the new value into i_ctime_nsec. Accept the
+ * resulting ctime, regardless of the outcome of the swap. If it has
+ * already been replaced, then that timestamp is later than the earlier
+ * unacceptable one, and is thus acceptable.
  */
-struct timespec64 current_time(struct inode *inode)
+struct timespec64 inode_set_ctime_current(struct inode *inode)
 {
 	struct timespec64 now;
+	u32 cns, cur;
 
-	ktime_get_coarse_real_ts64(&now);
-	return timestamp_truncate(now, inode);
-}
-EXPORT_SYMBOL(current_time);
+	ktime_get_coarse_real_ts64_mg(&now);
+	now = timestamp_truncate(now, inode);
 
-/**
- * inode_set_ctime_current - set the ctime to current_time
- * @inode: inode
- *
- * Set the inode->i_ctime to the current value for the inode. Returns
- * the current value that was assigned to i_ctime.
- */
-struct timespec64 inode_set_ctime_current(struct inode *inode)
-{
-	struct timespec64 now = current_time(inode);
+	/* Just return that if this is not a multigrain fs */
+	if (!is_mgtime(inode)) {
+		inode_set_ctime_to_ts(inode, now);
+		goto out;
+	}
 
-	inode_set_ctime_to_ts(inode, now);
+	/*
+	 * A fine-grained time is only needed if someone has queried
+	 * for timestamps, and the current coarse grained time isn't
+	 * later than what's already there.
+	 */
+	cns = smp_load_acquire(&inode->i_ctime_nsec);
+	if (cns & I_CTIME_QUERIED) {
+		struct timespec64 ctime = { .tv_sec = inode->i_ctime_sec,
+					    .tv_nsec = cns & ~I_CTIME_QUERIED };
+
+		if (timespec64_compare(&now, &ctime) <= 0) {
+			ktime_get_real_ts64_mg(&now);
+			now = timestamp_truncate(now, inode);
+		}
+	}
+
+	/* No need to cmpxchg if it's exactly the same */
+	if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec)
+		goto out;
+	cur = cns;
+retry:
+	/* Try to swap the nsec value into place. */
+	if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) {
+		/* If swap occurred, then we're (mostly) done */
+		inode->i_ctime_sec = now.tv_sec;
+	} else {
+		/*
+		 * Was the change due to someone marking the old ctime QUERIED?
+		 * If so then retry the swap. This can only happen once since
+		 * the only way to clear I_CTIME_QUERIED is to stamp the inode
+		 * with a new ctime.
+		 */
+		if (!(cns & I_CTIME_QUERIED) && (cns | I_CTIME_QUERIED) == cur) {
+			cns = cur;
+			goto retry;
+		}
+		/* Otherwise, keep the existing ctime */
+		now.tv_sec = inode->i_ctime_sec;
+		now.tv_nsec = cur & ~I_CTIME_QUERIED;
+	}
+out:
 	return now;
 }
 EXPORT_SYMBOL(inode_set_ctime_current);