fanotify: introduce FAN_PRE_ACCESS permission event

Similar to FAN_ACCESS_PERM permission event, but it is only allowed with
class FAN_CLASS_PRE_CONTENT and only allowed on regular files and dirs.

Unlike FAN_ACCESS_PERM, it is safe to write to the file being accessed
in the context of the event handler.

This pre-content event is meant to be used by hierarchical storage
managers that want to fill the content of files on first read access.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/b80986f8d5b860acea2c9a73c0acd93587be5fe4.1731684329.git.josef@toxicpanda.com

2 files changed, 32 insertions, 6 deletions

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 2e6ba94ec405..da6c3c1c7edf 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -916,8 +916,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
 	BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
 	BUILD_BUG_ON(FAN_RENAME != FS_RENAME);
+	BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22);
 
 	mask = fanotify_group_event_mask(group, iter_info, &match_mask,
 					 mask, data, data_type, dir);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 456cc3e92c88..08e4d8659ef5 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1287,7 +1287,7 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group)
 }
 
 static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
-					      unsigned int fan_flags)
+					     __u32 mask, unsigned int fan_flags)
 {
 	/*
 	 * Non evictable mark cannot be downgraded to evictable mark.
@@ -1314,6 +1314,11 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
 	    fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
 		return -EEXIST;
 
+	/* For now pre-content events are not generated for directories */
+	mask |= fsn_mark->mask;
+	if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR)
+		return -EEXIST;
+
 	return 0;
 }
 
@@ -1340,7 +1345,7 @@ static int fanotify_add_mark(struct fsnotify_group *group,
 	/*
 	 * Check if requested mark flags conflict with an existing mark flags.
 	 */
-	ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags);
+	ret = fanotify_may_update_existing_mark(fsn_mark, mask, fan_flags);
 	if (ret)
 		goto out;
 
@@ -1640,12 +1645,24 @@ static int fanotify_events_supported(struct fsnotify_group *group,
 				     unsigned int flags)
 {
 	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+	bool is_dir = d_is_dir(path->dentry);
 	/* Strict validation of events in non-dir inode mask with v5.17+ APIs */
 	bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) ||
 				 (mask & FAN_RENAME) ||
 				 (flags & FAN_MARK_IGNORE);
 
 	/*
+	 * Filesystems need to opt-into pre-content evnets (a.k.a HSM)
+	 * and they are only supported on regular files and directories.
+	 */
+	if (mask & FANOTIFY_PRE_CONTENT_EVENTS) {
+		if (!(path->mnt->mnt_sb->s_iflags & SB_I_ALLOW_HSM))
+			return -EOPNOTSUPP;
+		if (!is_dir && !d_is_reg(path->dentry))
+			return -EINVAL;
+	}
+
+	/*
 	 * Some filesystems such as 'proc' acquire unusual locks when opening
 	 * files. For them fanotify permission events have high chances of
 	 * deadlocking the system - open done when reporting fanotify event
@@ -1677,7 +1694,7 @@ static int fanotify_events_supported(struct fsnotify_group *group,
 	 * but because we always allowed it, error only when using new APIs.
 	 */
 	if (strict_dir_events && mark_type == FAN_MARK_INODE &&
-	    !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
+	    !is_dir && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
 		return -ENOTDIR;
 
 	return 0;
@@ -1778,10 +1795,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 		return -EPERM;
 
 	/*
-	 * Permission events require minimum priority FAN_CLASS_CONTENT.
+	 * Permission events are not allowed for FAN_CLASS_NOTIF.
+	 * Pre-content permission events are not allowed for FAN_CLASS_CONTENT.
 	 */
 	if (mask & FANOTIFY_PERM_EVENTS &&
-	    group->priority < FSNOTIFY_PRIO_CONTENT)
+	    group->priority == FSNOTIFY_PRIO_NORMAL)
+		return -EINVAL;
+	else if (mask & FANOTIFY_PRE_CONTENT_EVENTS &&
+		 group->priority == FSNOTIFY_PRIO_CONTENT)
 		return -EINVAL;
 
 	if (mask & FAN_FS_ERROR &&
@@ -1816,6 +1837,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
 		return -EINVAL;
 
+	/* Pre-content events are not currently generated for directories. */
+	if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR)
+		return -EINVAL;
+
 	if (mark_cmd == FAN_MARK_FLUSH) {
 		if (mark_type == FAN_MARK_MOUNT)
 			fsnotify_clear_vfsmount_marks_by_group(group);