fs: handle delegated timestamps in setattr_copy_mgtime

An update to the inode ctime typically requires the latest clock
value possible. The exception to this rule is when there is a nfsd write
delegation and the server is proxying timestamps from the client.

When nfsd gets a CB_GETATTR response, update the timestamp value in the
inode to the values that the client is tracking. The client doesn't send
a ctime value (since that's always determined by the exported
filesystem), but it can send a mtime value. In the case where it does,
update the ctime to a value commensurate with that instead of the
current time.

If ATTR_DELEG is set, then use ia_ctime value instead of setting the
timestamp to the current time.

With the addition of delegated timestamps, the server may receive a
request to update only the atime, which doesn't involve a ctime update.
Trust the ATTR_CTIME flag in the update and only update the ctime when
it's set.

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-v10-5-d1c4717f5284@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

fs/attr.c

@@ -286,16 +286,21 @@ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr)
 	unsigned int ia_valid = attr->ia_valid;
 	struct timespec64 now;
 
-	/*
+	if (ia_valid & ATTR_CTIME) {
-	 * If the ctime isn't being updated then nothing else should be
+		/*
-	 * either.
+		 * In the case of an update for a write delegation, we must respect
-	 */
+		 * the value in ia_ctime and not use the current time.
-	if (!(ia_valid & ATTR_CTIME)) {
+		 */
-		WARN_ON_ONCE(ia_valid & (ATTR_ATIME|ATTR_MTIME));
+		if (ia_valid & ATTR_DELEG)
-		return;
+			now = inode_set_ctime_deleg(inode, attr->ia_ctime);
+		else
+			now = inode_set_ctime_current(inode);
+	} else {
+		/* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */
+		WARN_ON_ONCE(ia_valid & ATTR_MTIME);
+		now = current_time(inode);
 	}
 
-	now = inode_set_ctime_current(inode);
 	if (ia_valid & ATTR_ATIME_SET)
 		inode_set_atime_to_ts(inode, attr->ia_atime);
 	else if (ia_valid & ATTR_ATIME)
@@ -354,8 +359,12 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
 		inode_set_atime_to_ts(inode, attr->ia_atime);
 	if (ia_valid & ATTR_MTIME)
 		inode_set_mtime_to_ts(inode, attr->ia_mtime);
-	if (ia_valid & ATTR_CTIME)
+	if (ia_valid & ATTR_CTIME) {
-		inode_set_ctime_to_ts(inode, attr->ia_ctime);
+		if (ia_valid & ATTR_DELEG)
+			inode_set_ctime_deleg(inode, attr->ia_ctime);
+		else
+			inode_set_ctime_to_ts(inode, attr->ia_ctime);
+	}
 }
 EXPORT_SYMBOL(setattr_copy);
 

fs/inode.c

@@ -2717,6 +2717,79 @@ out:
 }
 EXPORT_SYMBOL(inode_set_ctime_current);
 
+/**
+ * inode_set_ctime_deleg - try to update the ctime on a delegated inode
+ * @inode: inode to update
+ * @update: timespec64 to set the ctime
+ *
+ * Attempt to atomically update the ctime on behalf of a delegation holder.
+ *
+ * The nfs server can call back the holder of a delegation to get updated
+ * inode attributes, including the mtime. When updating the mtime, update
+ * the ctime to a value at least equal to that.
+ *
+ * This can race with concurrent updates to the inode, in which
+ * case the update is skipped.
+ *
+ * Note that this works even when multigrain timestamps are not enabled,
+ * so it is used in either case.
+ */
+struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update)
+{
+	struct timespec64 now, cur_ts;
+	u32 cur, old;
+
+	/* pairs with try_cmpxchg below */
+	cur = smp_load_acquire(&inode->i_ctime_nsec);
+	cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED;
+	cur_ts.tv_sec = inode->i_ctime_sec;
+
+	/* If the update is older than the existing value, skip it. */
+	if (timespec64_compare(&update, &cur_ts) <= 0)
+		return cur_ts;
+
+	ktime_get_coarse_real_ts64_mg(&now);
+
+	/* Clamp the update to "now" if it's in the future */
+	if (timespec64_compare(&update, &now) > 0)
+		update = now;
+
+	update = timestamp_truncate(update, inode);
+
+	/* No need to update if the values are already the same */
+	if (timespec64_equal(&update, &cur_ts))
+		return cur_ts;
+
+	/*
+	 * Try to swap the nsec value into place. If it fails, that means
+	 * it raced with an update due to a write or similar activity. That
+	 * stamp takes precedence, so just skip the update.
+	 */
+retry:
+	old = cur;
+	if (try_cmpxchg(&inode->i_ctime_nsec, &cur, update.tv_nsec)) {
+		inode->i_ctime_sec = update.tv_sec;
+		mgtime_counter_inc(mg_ctime_swaps);
+		return update;
+	}
+
+	/*
+	 * Was the change due to another task 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 (!(old & I_CTIME_QUERIED) && (cur == (old | I_CTIME_QUERIED)))
+		goto retry;
+
+	/* Otherwise, it was a new timestamp. */
+	cur_ts.tv_sec = inode->i_ctime_sec;
+	cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED;
+	return cur_ts;
+}
+EXPORT_SYMBOL(inode_set_ctime_deleg);
+
 /**
  * in_group_or_capable - check whether caller is CAP_FSETID privileged
  * @idmap:	idmap of the mount @inode was found from

include/linux/fs.h

@@ -1544,6 +1544,8 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb,
 
 struct timespec64 current_time(struct inode *inode);
 struct timespec64 inode_set_ctime_current(struct inode *inode);
+struct timespec64 inode_set_ctime_deleg(struct inode *inode,
+					struct timespec64 update);
 
 static inline time64_t inode_get_atime_sec(const struct inode *inode)
 {