fanotify: allow to set errno in FAN_DENY permission response

With FAN_DENY response, user trying to perform the filesystem operation
gets an error with errno set to EPERM.

It is useful for hierarchical storage management (HSM) service to be able
to deny access for reasons more diverse than EPERM, for example EAGAIN,
if HSM could retry the operation later.

Allow fanotify groups with priority FAN_CLASSS_PRE_CONTENT to responsd
to permission events with the response value FAN_DENY_ERRNO(errno),
instead of FAN_DENY to return a custom error.

Limit custom error values to errors expected on read(2)/write(2) and
open(2) of regular files. This list could be extended in the future.
Userspace can test for legitimate values of FAN_DENY_ERRNO(errno) by
writing a response to an fanotify group fd with a value of FAN_NOFD in
the fd field of the response.

The change in fanotify_response is backward compatible, because errno is
written in the high 8 bits of the 32bit response field and old kernels
reject respose value with high bits set.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/1e5fb6af84b69ca96b5c849fa5f10bdf4d1dc414.1731684329.git.josef@toxicpanda.com

fs/notify/fanotify/fanotify.c

@@ -223,7 +223,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
 				 struct fanotify_perm_event *event,
 				 struct fsnotify_iter_info *iter_info)
 {
-	int ret;
+	int ret, errno;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
@@ -262,14 +262,23 @@ static int fanotify_get_response(struct fsnotify_group *group,
 		ret = 0;
 		break;
 	case FAN_DENY:
+		/* Check custom errno from pre-content events */
+		errno = fanotify_get_response_errno(event->response);
+		if (errno) {
+			ret = -errno;
+			break;
+		}
+		fallthrough;
 	default:
 		ret = -EPERM;
 	}
 
 	/* Check if the response should be audited */
-	if (event->response & FAN_AUDIT)
-		audit_fanotify(event->response & ~FAN_AUDIT,
-			       &event->audit_rule);
+	if (event->response & FAN_AUDIT) {
+		u32 response = event->response &
+			(FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS);
+		audit_fanotify(response & ~FAN_AUDIT, &event->audit_rule);
+	}
 
 	pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
 		 group, event, ret);

fs/notify/fanotify/fanotify.h

@@ -528,3 +528,8 @@ static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
 
 	return mflags;
 }
+
+static inline u32 fanotify_get_response_errno(int res)
+{
+	return (res >> FAN_ERRNO_SHIFT) & FAN_ERRNO_MASK;
+}

fs/notify/fanotify/fanotify_user.c

@@ -327,11 +327,12 @@ static int process_access_response(struct fsnotify_group *group,
 	struct fanotify_perm_event *event;
 	int fd = response_struct->fd;
 	u32 response = response_struct->response;
+	int errno = fanotify_get_response_errno(response);
 	int ret = info_len;
 	struct fanotify_response_info_audit_rule friar;
 
-	pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__,
-		 group, fd, response, info, info_len);
+	pr_debug("%s: group=%p fd=%d response=%x errno=%d buf=%p size=%zu\n",
+		 __func__, group, fd, response, errno, info, info_len);
 	/*
 	 * make sure the response is valid, if invalid we do nothing and either
 	 * userspace can send a valid response or we will clean it up after the
@@ -342,7 +343,31 @@ static int process_access_response(struct fsnotify_group *group,
 
 	switch (response & FANOTIFY_RESPONSE_ACCESS) {
 	case FAN_ALLOW:
+		if (errno)
+			return -EINVAL;
+		break;
 	case FAN_DENY:
+		/* Custom errno is supported only for pre-content groups */
+		if (errno && group->priority != FSNOTIFY_PRIO_PRE_CONTENT)
+			return -EINVAL;
+
+		/*
+		 * Limit errno to values expected on open(2)/read(2)/write(2)
+		 * of regular files.
+		 */
+		switch (errno) {
+		case 0:
+		case EIO:
+		case EPERM:
+		case EBUSY:
+		case ETXTBSY:
+		case EAGAIN:
+		case ENOSPC:
+		case EDQUOT:
+			break;
+		default:
+			return -EINVAL;
+		}
 		break;
 	default:
 		return -EINVAL;

include/linux/fanotify.h

@@ -132,7 +132,9 @@
 /* These masks check for invalid bits in permission responses. */
 #define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY)
 #define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO)
-#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS)
+#define FANOTIFY_RESPONSE_VALID_MASK \
+	(FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS | \
+	 (FAN_ERRNO_MASK << FAN_ERRNO_SHIFT))
 
 /* Do not use these old uapi constants internally */
 #undef FAN_ALL_CLASS_BITS

include/uapi/linux/fanotify.h

@@ -235,6 +235,13 @@ struct fanotify_response_info_audit_rule {
 /* Legit userspace responses to a _PERM event */
 #define FAN_ALLOW	0x01
 #define FAN_DENY	0x02
+/* errno other than EPERM can specified in upper byte of deny response */
+#define FAN_ERRNO_BITS	8
+#define FAN_ERRNO_SHIFT (32 - FAN_ERRNO_BITS)
+#define FAN_ERRNO_MASK	((1 << FAN_ERRNO_BITS) - 1)
+#define FAN_DENY_ERRNO(err) \
+	(FAN_DENY | ((((__u32)(err)) & FAN_ERRNO_MASK) << FAN_ERRNO_SHIFT))
+
 #define FAN_AUDIT	0x10	/* Bitmask to create audit record for result */
 #define FAN_INFO	0x20	/* Bitmask to indicate additional information */