Merge tag 'vfs-6.8.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs mount updates from Christian Brauner:
 "This contains the work to retrieve detailed information about mounts
  via two new system calls. This is hopefully the beginning of the end
  of the saga that started with fsinfo() years ago.

  The LWN articles in [1] and [2] can serve as a summary so we can avoid
  rehashing everything here.

  At LSFMM in May 2022 we got into a room and agreed on what we want to
  do about fsinfo(). Basically, split it into pieces. This is the first
  part of that agreement. Specifically, it is concerned with retrieving
  information about mounts. So this only concerns the mount information
  retrieval, not the mount table change notification, or the extended
  filesystem specific mount option work. That is separate work.

  Currently mounts have a 32bit id. Mount ids are already in heavy use
  by libmount and other low-level userspace but they can't be relied
  upon because they're recycled very quickly. We agreed that mounts
  should carry a unique 64bit id by which they can be referenced
  directly. This is now implemented as part of this work.

  The new 64bit mount id is exposed in statx() through the new
  STATX_MNT_ID_UNIQUE flag. If the flag isn't raised the old mount id is
  returned. If it is raised and the kernel supports the new 64bit mount
  id the flag is raised in the result mask and the new 64bit mount id is
  returned. New and old mount ids do not overlap so they cannot be
  conflated.

  Two new system calls are introduced that operate on the 64bit mount
  id: statmount() and listmount(). A summary of the api and usage can be
  found on LWN as well (cf. [3]) but of course, I'll provide a summary
  here as well.

  Both system calls rely on struct mnt_id_req. Which is the request
  struct used to pass the 64bit mount id identifying the mount to
  operate on. It is extensible to allow for the addition of new
  parameters and for future use in other apis that make use of mount
  ids.

  statmount() mimicks the semantics of statx() and exposes a set flags
  that userspace may raise in mnt_id_req to request specific information
  to be retrieved. A statmount() call returns a struct statmount filled
  in with information about the requested mount. Supported requests are
  indicated by raising the request flag passed in struct mnt_id_req in
  the @mask argument in struct statmount.

  Currently we do support:

   - STATMOUNT_SB_BASIC:
     Basic filesystem info

   - STATMOUNT_MNT_BASIC
     Mount information (mount id, parent mount id, mount attributes etc)

   - STATMOUNT_PROPAGATE_FROM
     Propagation from what mount in current namespace

   - STATMOUNT_MNT_ROOT
     Path of the root of the mount (e.g., mount --bind /bla /mnt returns /bla)

   - STATMOUNT_MNT_POINT
     Path of the mount point (e.g., mount --bind /bla /mnt returns /mnt)

   - STATMOUNT_FS_TYPE
     Name of the filesystem type as the magic number isn't enough due to submounts

  The string options STATMOUNT_MNT_{ROOT,POINT} and STATMOUNT_FS_TYPE
  are appended to the end of the struct. Userspace can use the offsets
  in @fs_type, @mnt_root, and @mnt_point to reference those strings
  easily.

  The struct statmount reserves quite a bit of space currently for
  future extensibility. This isn't really a problem and if this bothers
  us we can just send a follow-up pull request during this cycle.

  listmount() is given a 64bit mount id via mnt_id_req just as
  statmount(). It takes a buffer and a size to return an array of the
  64bit ids of the child mounts of the requested mount. Userspace can
  thus choose to either retrieve child mounts for a mount in batches or
  iterate through the child mounts. For most use-cases it will be
  sufficient to just leave space for a few child mounts. But for big
  mount tables having an iterator is really helpful. Iterating through a
  mount table works by setting @param in mnt_id_req to the mount id of
  the last child mount retrieved in the previous listmount() call"

Link: https://lwn.net/Articles/934469 [1]
Link: https://lwn.net/Articles/829212 [2]
Link: https://lwn.net/Articles/950569 [3]

* tag 'vfs-6.8.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  add selftest for statmount/listmount
  fs: keep struct mnt_id_req extensible
  wire up syscalls for statmount/listmount
  add listmount(2) syscall
  statmount: simplify string option retrieval
  statmount: simplify numeric option retrieval
  add statmount(2) syscall
  namespace: extract show_path() helper
  mounts: keep list of mounts in an rbtree
  add unique mount ID

arch/alpha/kernel/syscalls/syscall.tbl

@@ -496,3 +496,5 @@
 564	common	futex_wake			sys_futex_wake
 565	common	futex_wait			sys_futex_wait
 566	common	futex_requeue			sys_futex_requeue
+567	common	statmount			sys_statmount
+568	common	listmount			sys_listmount

arch/arm/tools/syscall.tbl

@@ -470,3 +470,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

arch/arm64/include/asm/unistd32.h

@@ -919,6 +919,10 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
 __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_statmount 457
+__SYSCALL(__NR_statmount, sys_statmount)
+#define __NR_listmount 458
+__SYSCALL(__NR_listmount, sys_listmount)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/m68k/kernel/syscalls/syscall.tbl

@@ -456,3 +456,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -462,3 +462,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

arch/mips/kernel/syscalls/syscall_n32.tbl

@@ -395,3 +395,5 @@
 454	n32	futex_wake			sys_futex_wake
 455	n32	futex_wait			sys_futex_wait
 456	n32	futex_requeue			sys_futex_requeue
+457	n32	statmount			sys_statmount
+458	n32	listmount			sys_listmount

arch/mips/kernel/syscalls/syscall_n64.tbl

@@ -371,3 +371,5 @@
 454	n64	futex_wake			sys_futex_wake
 455	n64	futex_wait			sys_futex_wait
 456	n64	futex_requeue			sys_futex_requeue
+457	n64	statmount			sys_statmount
+458	n64	listmount			sys_listmount

arch/mips/kernel/syscalls/syscall_o32.tbl

@@ -444,3 +444,5 @@
 454	o32	futex_wake			sys_futex_wake
 455	o32	futex_wait			sys_futex_wait
 456	o32	futex_requeue			sys_futex_requeue
+457	o32	statmount			sys_statmount
+458	o32	listmount			sys_listmount

arch/parisc/kernel/syscalls/syscall.tbl

@@ -455,3 +455,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -543,3 +543,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

arch/s390/kernel/syscalls/syscall.tbl

@@ -459,3 +459,5 @@
 454  common	futex_wake		sys_futex_wake			sys_futex_wake
 455  common	futex_wait		sys_futex_wait			sys_futex_wait
 456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
+457  common	statmount		sys_statmount			sys_statmount
+458  common	listmount		sys_listmount			sys_listmount

arch/sh/kernel/syscalls/syscall.tbl

@@ -459,3 +459,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

arch/sparc/kernel/syscalls/syscall.tbl

@@ -502,3 +502,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

arch/x86/entry/syscalls/syscall_32.tbl

@@ -461,3 +461,5 @@
 454	i386	futex_wake		sys_futex_wake
 455	i386	futex_wait		sys_futex_wait
 456	i386	futex_requeue		sys_futex_requeue
+457	i386	statmount		sys_statmount
+458	i386	listmount		sys_listmount

arch/x86/entry/syscalls/syscall_64.tbl

@@ -378,6 +378,8 @@
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
 456	common	futex_requeue		sys_futex_requeue
+457	common	statmount		sys_statmount
+458	common	listmount		sys_listmount
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -427,3 +427,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount

fs/internal.h

@@ -83,6 +83,8 @@ int path_mount(const char *dev_name, struct path *path,
 		const char *type_page, unsigned long flags, void *data_page);
 int path_umount(struct path *path, int flags);
 
+int show_path(struct seq_file *m, struct dentry *root);
+
 /*
  * fs_struct.c
  */

fs/mount.h

@@ -8,19 +8,13 @@
 struct mnt_namespace {
 	struct ns_common	ns;
 	struct mount *	root;
-	/*
-	 * Traversal and modification of .list is protected by either
-	 * - taking namespace_sem for write, OR
-	 * - taking namespace_sem for read AND taking .ns_lock.
-	 */
-	struct list_head	list;
-	spinlock_t		ns_lock;
+	struct rb_root		mounts; /* Protected by namespace_sem */
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
 	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	u64 event;
-	unsigned int		mounts; /* # of mounts in the namespace */
+	unsigned int		nr_mounts; /* # of mounts in the namespace */
 	unsigned int		pending_mounts;
 } __randomize_layout;
 
@@ -55,7 +49,10 @@ struct mount {
 	struct list_head mnt_child;	/* and going through their mnt_child */
 	struct list_head mnt_instance;	/* mount instance on sb->s_mounts */
 	const char *mnt_devname;	/* Name of device e.g. /dev/dsk/hda1 */
-	struct list_head mnt_list;
+	union {
+		struct rb_node mnt_node;	/* Under ns->mounts */
+		struct list_head mnt_list;
+	};
 	struct list_head mnt_expire;	/* link in fs-specific expiry list */
 	struct list_head mnt_share;	/* circular list of shared mounts */
 	struct list_head mnt_slave_list;/* list of slave mounts */
@@ -72,7 +69,8 @@ struct mount {
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 #endif
-	int mnt_id;			/* mount identifier */
+	int mnt_id;			/* mount identifier, reused */
+	u64 mnt_id_unique;		/* mount ID unique until reboot */
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
@@ -127,7 +125,6 @@ struct proc_mounts {
 	struct mnt_namespace *ns;
 	struct path root;
 	int (*show)(struct seq_file *, struct vfsmount *);
-	struct mount cursor;
 };
 
 extern const struct seq_operations mounts_op;
@@ -146,4 +143,12 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
 	return ns->seq == 0;
 }
 
+static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
+{
+	WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB));
+	mnt->mnt.mnt_flags &= ~MNT_ONRB;
+	rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts);
+	list_add_tail(&mnt->mnt_list, dt_list);
+}
+
 extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);

fs/pnode.c

@@ -468,7 +468,7 @@ static void umount_one(struct mount *mnt, struct list_head *to_umount)
 	mnt->mnt.mnt_flags |= MNT_UMOUNT;
 	list_del_init(&mnt->mnt_child);
 	list_del_init(&mnt->mnt_umounting);
-	list_move_tail(&mnt->mnt_list, to_umount);
+	move_from_ns(mnt, to_umount);
 }
 
 /*

fs/proc_namespace.c

@@ -142,13 +142,9 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
 
 	seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
 		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
-	if (sb->s_op->show_path) {
-		err = sb->s_op->show_path(m, mnt->mnt_root);
-		if (err)
-			goto out;
-	} else {
-		seq_dentry(m, mnt->mnt_root, " \t\n\\");
-	}
+	err = show_path(m, mnt->mnt_root);
+	if (err)
+		goto out;
 	seq_putc(m, ' ');
 
 	/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
@@ -283,8 +279,6 @@ static int mounts_open_common(struct inode *inode, struct file *file,
 	p->ns = ns;
 	p->root = root;
 	p->show = show;
-	INIT_LIST_HEAD(&p->cursor.mnt_list);
-	p->cursor.mnt.mnt_flags = MNT_CURSOR;
 
 	return 0;
 
@@ -301,7 +295,6 @@ static int mounts_release(struct inode *inode, struct file *file)
 	struct seq_file *m = file->private_data;
 	struct proc_mounts *p = m->private;
 	path_put(&p->root);
-	mnt_cursor_del(p->ns, &p->cursor);
 	put_mnt_ns(p->ns);
 	return seq_release_private(inode, file);
 }

fs/stat.c

@@ -247,8 +247,13 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
 
-	stat->mnt_id = real_mount(path.mnt)->mnt_id;
-	stat->result_mask |= STATX_MNT_ID;
+	if (request_mask & STATX_MNT_ID_UNIQUE) {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id_unique;
+		stat->result_mask |= STATX_MNT_ID_UNIQUE;
+	} else {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id;
+		stat->result_mask |= STATX_MNT_ID;
+	}
 
 	if (path.mnt->mnt_root == path.dentry)
 		stat->attributes |= STATX_ATTR_MOUNT_ROOT;

include/linux/mount.h

@@ -50,8 +50,7 @@ struct path;
 #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
 
 #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
-			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \
-			    MNT_CURSOR)
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB)
 
 #define MNT_INTERNAL	0x4000
 
@@ -65,7 +64,7 @@ struct path;
 #define MNT_SYNC_UMOUNT		0x2000000
 #define MNT_MARKED		0x4000000
 #define MNT_UMOUNT		0x8000000
-#define MNT_CURSOR		0x10000000
+#define MNT_ONRB		0x10000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */

include/linux/syscalls.h

@@ -74,6 +74,8 @@ struct landlock_ruleset_attr;
 enum landlock_rule_type;
 struct cachestat_range;
 struct cachestat;
+struct statmount;
+struct mnt_id_req;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -407,6 +409,12 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz,
 asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf);
 asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz,
 				struct statfs64 __user *buf);
+asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
+			      struct statmount __user *buf, size_t bufsize,
+			      unsigned int flags);
+asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
+			      u64 __user *buf, size_t bufsize,
+			      unsigned int flags);
 asmlinkage long sys_truncate(const char __user *path, long length);
 asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
 #if BITS_PER_LONG == 32

include/uapi/asm-generic/unistd.h

@@ -829,8 +829,14 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_statmount   457
+__SYSCALL(__NR_statmount, sys_statmount)
+
+#define __NR_listmount   458
+__SYSCALL(__NR_listmount, sys_listmount)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 459
 
 /*
  * 32 bit systems traditionally used different

include/uapi/linux/mount.h

@@ -138,4 +138,74 @@ struct mount_attr {
 /* List of all mount_attr versions. */
 #define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 __spare2[50];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
 #endif /* _UAPI_LINUX_MOUNT_H */

include/uapi/linux/stat.h

@@ -154,6 +154,7 @@ struct statx {
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 

tools/testing/selftests/Makefile

@@ -27,6 +27,7 @@ TARGETS += filesystems/binderfs
 TARGETS += filesystems/epoll
 TARGETS += filesystems/fat
 TARGETS += filesystems/overlayfs
+TARGETS += filesystems/statmount
 TARGETS += firmware
 TARGETS += fpu
 TARGETS += ftrace

tools/testing/selftests/filesystems/statmount/.gitignore

+# SPDX-License-Identifier: GPL-2.0-only
+/*_test

tools/testing/selftests/filesystems/statmount/Makefile

+# SPDX-License-Identifier: GPL-2.0-or-later
+
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+TEST_GEN_PROGS := statmount_test
+
+include ../../lib.mk