fs: add FS_IOC_GETFSSYSFSPATH

Add a new ioctl for getting the sysfs name of a filesystem - the path
under /sys/fs.

This is going to let us standardize exporting data from sysfs across
filesystems, e.g. time stats.

The returned path will always be of the form "$FSTYP/$SYSFS_IDENTIFIER",
where the sysfs identifier may be a UUID (for bcachefs) or a device name
(xfs).

Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Darrick J. Wong <djwong@kernel.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Link: https://lore.kernel.org/r/20240207025624.1019754-6-kent.overstreet@linux.dev
Signed-off-by: Christian Brauner <brauner@kernel.org>

3 files changed, 70 insertions, 0 deletions

diff --git a/fs/ioctl.c b/fs/ioctl.c
index 74eab9549383..1d5abfdf0f22 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -776,6 +776,20 @@ static int ioctl_getfsuuid(struct file *file, void __user *argp)
 	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
 }
 
+static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+
+	if (!strlen(sb->s_sysfs_name))
+		return -ENOIOCTLCMD;
+
+	struct fs_sysfs_path u = {};
+
+	u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name);
+
+	return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0;
+}
+
 /*
  * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
  * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
@@ -861,6 +875,9 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd,
 	case FS_IOC_GETFSUUID:
 		return ioctl_getfsuuid(filp, argp);
 
+	case FS_IOC_GETFSSYSFSPATH:
+		return ioctl_get_fs_sysfs_path(filp, argp);
+
 	default:
 		if (S_ISREG(inode->i_mode))
 			return file_ioctl(filp, cmd, argp);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index acdc56987cb1..c6d9e1b7032c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1255,10 +1255,23 @@ struct super_block {
 	struct fsnotify_mark_connector __rcu	*s_fsnotify_marks;
 #endif
 
+	/*
+	 * q: why are s_id and s_sysfs_name not the same? both are human
+	 * readable strings that identify the filesystem
+	 * a: s_id is allowed to change at runtime; it's used in log messages,
+	 * and we want to when a device starts out as single device (s_id is dev
+	 * name) but then a device is hot added and we have to switch to
+	 * identifying it by UUID
+	 * but s_sysfs_name is a handle for programmatic access, and can't
+	 * change at runtime
+	 */
 	char			s_id[32];	/* Informational name */
 	uuid_t			s_uuid;		/* UUID */
 	u8			s_uuid_len;	/* Default 16, possibly smaller for weird filesystems */
 
+	/* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
+	char			s_sysfs_name[UUID_STRING_LEN + 1];
+
 	unsigned int		s_max_links;
 
 	/*
@@ -2541,6 +2554,36 @@ static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsign
 	memcpy(&sb->s_uuid, uuid, len);
 }
 
+/* set sb sysfs name based on sb->s_bdev */
+static inline void super_set_sysfs_name_bdev(struct super_block *sb)
+{
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev);
+}
+
+/* set sb sysfs name based on sb->s_uuid */
+static inline void super_set_sysfs_name_uuid(struct super_block *sb)
+{
+	WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid));
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b);
+}
+
+/* set sb sysfs name based on sb->s_id */
+static inline void super_set_sysfs_name_id(struct super_block *sb)
+{
+	strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name));
+}
+
+/* try to use something standard before you use this */
+__printf(2, 3)
+static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args);
+	va_end(args);
+}
+
 extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 40880ce99d02..dcd6c8c7d2c7 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -77,6 +77,11 @@ struct fsuuid2 {
 	__u8	uuid[16];
 };
 
+struct fs_sysfs_path {
+	__u8			len;
+	__u8			name[128];
+};
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
@@ -230,6 +235,11 @@ struct fsxattr {
 #define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
 /* Returns the external filesystem UUID, the same one blkid returns */
 #define FS_IOC_GETFSUUID		_IOR(0x15, 0, struct fsuuid2)
+/*
+ * Returns the path component under /sys/fs/ that refers to this filesystem;
+ * also /sys/kernel/debug/ for filesystems with debugfs exports
+ */
+#define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
 
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)