Merge tag 'vfs-6.14-rc1.mount.v2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs mount updates from Christian Brauner:

 - Add a mountinfo program to demonstrate statmount()/listmount()

   Add a new "mountinfo" sample userland program that demonstrates how
   to use statmount() and listmount() to get at the same info that
   /proc/pid/mountinfo provides

 - Remove pointless nospec.h include

 - Prepend statmount.mnt_opts string with security_sb_mnt_opts()

   Currently these mount options aren't accessible via statmount()

 - Add new mount namespaces to mount namespace rbtree outside of the
   namespace semaphore

 - Lockless mount namespace lookup

   Currently we take the read lock when looking for a mount namespace to
   list mounts in. We can make this lockless. The simple search case can
   just use a sequence counter to detect concurrent changes to the
   rbtree

   For walking the list of mount namespaces sequentially via nsfs we
   keep a separate rcu list as rb_prev() and rb_next() aren't usable
   safely with rcu. Currently there is no primitive for retrieving the
   previous list member. To do this we need a new deletion primitive
   that doesn't poison the prev pointer and a corresponding retrieval
   helper

   Since creating mount namespaces is a relatively rare event compared
   with querying mounts in a foreign mount namespace this is worth it.
   Once libmount and systemd pick up this mechanism to list mounts in
   foreign mount namespaces this will be used very frequently

     - Add extended selftests for lockless mount namespace iteration

     - Add a sample program to list all mounts on the system, i.e., in
       all mount namespaces

 - Improve mount namespace iteration performance

   Make finding the last or first mount to start iterating the mount
   namespace from an O(1) operation and add selftests for iterating the
   mount table starting from the first and last mount

 - Use an xarray for the old mount id

   While the ida does use the xarray internally we can use it explicitly
   which allows us to increment the unique mount id under the xa lock.
   This allows us to remove the atomic as we're now allocating both ids
   in one go

 - Use a shared header for vfs sample programs

 - Fix build warnings for new sample program to list all mounts

* tag 'vfs-6.14-rc1.mount.v2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  samples/vfs: fix build warnings
  samples/vfs: use shared header
  samples/vfs/mountinfo: Use __u64 instead of uint64_t
  fs: remove useless lockdep assertion
  fs: use xarray for old mount id
  selftests: add listmount() iteration tests
  fs: cache first and last mount
  samples: add test-list-all-mounts
  selftests: remove unneeded include
  selftests: add tests for mntns iteration
  seltests: move nsfs into filesystems subfolder
  fs: simplify rwlock to spinlock
  fs: lockless mntns lookup for nsfs
  rculist: add list_bidir_{del,prev}_rcu()
  fs: lockless mntns rbtree lookup
  fs: add mount namespace to rbtree late
  fs: prepend statmount.mnt_opts string with security_sb_mnt_opts()
  mount: remove inlude/nospec.h include
  samples: add a mountinfo program to demonstrate statmount()/listmount()

5 files changed, 668 insertions, 1 deletions

diff --git a/samples/vfs/.gitignore b/samples/vfs/.gitignore
index 79212d91285b..8708341bc082 100644
--- a/samples/vfs/.gitignore
+++ b/samples/vfs/.gitignore
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 /test-fsmount
+/test-list-all-mounts
 /test-statx
+/mountinfo
diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile
index 6377a678134a..6554b73a75c8 100644
--- a/samples/vfs/Makefile
+++ b/samples/vfs/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-userprogs-always-y += test-fsmount test-statx
+userprogs-always-y += test-fsmount test-statx mountinfo test-list-all-mounts
 
 userccflags += -I usr/include
diff --git a/samples/vfs/mountinfo.c b/samples/vfs/mountinfo.c
new file mode 100644
index 000000000000..bc78275cac69
--- /dev/null
+++ b/samples/vfs/mountinfo.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/*
+ * Use pidfds, nsfds, listmount() and statmount() mimic the
+ * contents of /proc/self/mountinfo.
+ */
+#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__
+#include <stdio.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <alloca.h>
+#include <getopt.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <errno.h>
+
+#include "samples-vfs.h"
+
+/* max mounts per listmount call */
+#define MAXMOUNTS		1024
+
+/* size of struct statmount (including trailing string buffer) */
+#define STATMOUNT_BUFSIZE	4096
+
+static bool ext_format;
+
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open -1
+#endif
+
+/*
+ * There are no bindings in glibc for listmount() and statmount() (yet),
+ * make our own here.
+ */
+static int statmount(__u64 mnt_id, __u64 mnt_ns_id, __u64 mask,
+		     struct statmount *buf, size_t bufsize,
+		     unsigned int flags)
+{
+	struct mnt_id_req req = {
+		.size = MNT_ID_REQ_SIZE_VER0,
+		.mnt_id = mnt_id,
+		.param = mask,
+	};
+
+	if (mnt_ns_id) {
+		req.size = MNT_ID_REQ_SIZE_VER1;
+		req.mnt_ns_id = mnt_ns_id;
+	}
+
+	return syscall(__NR_statmount, &req, buf, bufsize, flags);
+}
+
+static ssize_t listmount(__u64 mnt_id, __u64 mnt_ns_id, __u64 last_mnt_id,
+			 __u64 list[], size_t num, unsigned int flags)
+{
+	struct mnt_id_req req = {
+		.size = MNT_ID_REQ_SIZE_VER0,
+		.mnt_id = mnt_id,
+		.param = last_mnt_id,
+	};
+
+	if (mnt_ns_id) {
+		req.size = MNT_ID_REQ_SIZE_VER1;
+		req.mnt_ns_id = mnt_ns_id;
+	}
+
+	return syscall(__NR_listmount, &req, list, num, flags);
+}
+
+static void show_mnt_attrs(__u64 flags)
+{
+	printf("%s", flags & MOUNT_ATTR_RDONLY ? "ro" : "rw");
+
+	if (flags & MOUNT_ATTR_NOSUID)
+		printf(",nosuid");
+	if (flags & MOUNT_ATTR_NODEV)
+		printf(",nodev");
+	if (flags & MOUNT_ATTR_NOEXEC)
+		printf(",noexec");
+
+	switch (flags & MOUNT_ATTR__ATIME) {
+	case MOUNT_ATTR_RELATIME:
+		printf(",relatime");
+		break;
+	case MOUNT_ATTR_NOATIME:
+		printf(",noatime");
+		break;
+	case MOUNT_ATTR_STRICTATIME:
+		/* print nothing */
+		break;
+	}
+
+	if (flags & MOUNT_ATTR_NODIRATIME)
+		printf(",nodiratime");
+	if (flags & MOUNT_ATTR_NOSYMFOLLOW)
+		printf(",nosymfollow");
+	if (flags & MOUNT_ATTR_IDMAP)
+		printf(",idmapped");
+}
+
+static void show_propagation(struct statmount *sm)
+{
+	if (sm->mnt_propagation & MS_SHARED)
+		printf(" shared:%llu", sm->mnt_peer_group);
+	if (sm->mnt_propagation & MS_SLAVE) {
+		printf(" master:%llu", sm->mnt_master);
+		if (sm->propagate_from && sm->propagate_from != sm->mnt_master)
+			printf(" propagate_from:%llu", sm->propagate_from);
+	}
+	if (sm->mnt_propagation & MS_UNBINDABLE)
+		printf(" unbindable");
+}
+
+static void show_sb_flags(__u64 flags)
+{
+	printf("%s", flags & MS_RDONLY ? "ro" : "rw");
+	if (flags & MS_SYNCHRONOUS)
+		printf(",sync");
+	if (flags & MS_DIRSYNC)
+		printf(",dirsync");
+	if (flags & MS_MANDLOCK)
+		printf(",mand");
+	if (flags & MS_LAZYTIME)
+		printf(",lazytime");
+}
+
+static int dump_mountinfo(__u64 mnt_id, __u64 mnt_ns_id)
+{
+	int ret;
+	struct statmount *buf = alloca(STATMOUNT_BUFSIZE);
+	const __u64 mask = STATMOUNT_SB_BASIC | STATMOUNT_MNT_BASIC |
+			   STATMOUNT_PROPAGATE_FROM | STATMOUNT_FS_TYPE |
+			   STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT |
+			   STATMOUNT_MNT_OPTS | STATMOUNT_FS_SUBTYPE |
+			   STATMOUNT_SB_SOURCE;
+
+	ret = statmount(mnt_id, mnt_ns_id, mask, buf, STATMOUNT_BUFSIZE, 0);
+	if (ret < 0) {
+		perror("statmount");
+		return 1;
+	}
+
+	if (ext_format)
+		printf("0x%llx 0x%llx 0x%llx ", mnt_ns_id, mnt_id, buf->mnt_parent_id);
+
+	printf("%u %u %u:%u %s %s ", buf->mnt_id_old, buf->mnt_parent_id_old,
+				   buf->sb_dev_major, buf->sb_dev_minor,
+				   &buf->str[buf->mnt_root],
+				   &buf->str[buf->mnt_point]);
+	show_mnt_attrs(buf->mnt_attr);
+	show_propagation(buf);
+
+	printf(" - %s", &buf->str[buf->fs_type]);
+	if (buf->mask & STATMOUNT_FS_SUBTYPE)
+		printf(".%s", &buf->str[buf->fs_subtype]);
+	if (buf->mask & STATMOUNT_SB_SOURCE)
+		printf(" %s ", &buf->str[buf->sb_source]);
+	else
+		printf(" :none ");
+
+	show_sb_flags(buf->sb_flags);
+	if (buf->mask & STATMOUNT_MNT_OPTS)
+		printf(",%s", &buf->str[buf->mnt_opts]);
+	printf("\n");
+	return 0;
+}
+
+static int dump_mounts(__u64 mnt_ns_id)
+{
+	__u64 mntid[MAXMOUNTS];
+	__u64 last_mnt_id = 0;
+	ssize_t count;
+	int i;
+
+	/*
+	 * Get a list of all mntids in mnt_ns_id. If it returns MAXMOUNTS
+	 * mounts, then go again until we get everything.
+	 */
+	do {
+		count = listmount(LSMT_ROOT, mnt_ns_id, last_mnt_id, mntid, MAXMOUNTS, 0);
+		if (count < 0 || count > MAXMOUNTS) {
+			errno = count < 0 ? errno : count;
+			perror("listmount");
+			return 1;
+		}
+
+		/* Walk the returned mntids and print info about each */
+		for (i = 0; i < count; ++i) {
+			int ret = dump_mountinfo(mntid[i], mnt_ns_id);
+
+			if (ret != 0)
+				return ret;
+		}
+		/* Set up last_mnt_id to pick up where we left off */
+		last_mnt_id = mntid[count - 1];
+	} while (count == MAXMOUNTS);
+	return 0;
+}
+
+static void usage(const char * const prog)
+{
+	printf("Usage:\n");
+	printf("%s [-e] [-p pid] [-r] [-h]\n", prog);
+	printf("    -e: extended format\n");
+	printf("    -h: print usage message\n");
+	printf("    -p: get mount namespace from given pid\n");
+	printf("    -r: recursively print all mounts in all child namespaces\n");
+}
+
+int main(int argc, char * const *argv)
+{
+	struct mnt_ns_info mni = { .size = MNT_NS_INFO_SIZE_VER0 };
+	int pidfd, mntns, ret, opt;
+	pid_t pid = getpid();
+	bool recursive = false;
+
+	while ((opt = getopt(argc, argv, "ehp:r")) != -1) {
+		switch (opt) {
+		case 'e':
+			ext_format = true;
+			break;
+		case 'h':
+			usage(argv[0]);
+			return 0;
+		case 'p':
+			pid = atoi(optarg);
+			break;
+		case 'r':
+			recursive = true;
+			break;
+		}
+	}
+
+	/* Get a pidfd for pid */
+	pidfd = syscall(__NR_pidfd_open, pid, 0);
+	if (pidfd < 0) {
+		perror("pidfd_open");
+		return 1;
+	}
+
+	/* Get the mnt namespace for pidfd */
+	mntns = ioctl(pidfd, PIDFD_GET_MNT_NAMESPACE, NULL);
+	if (mntns < 0) {
+		perror("PIDFD_GET_MNT_NAMESPACE");
+		return 1;
+	}
+	close(pidfd);
+
+	/* get info about mntns. In particular, the mnt_ns_id */
+	ret = ioctl(mntns, NS_MNT_GET_INFO, &mni);
+	if (ret < 0) {
+		perror("NS_MNT_GET_INFO");
+		return 1;
+	}
+
+	do {
+		int ret;
+
+		ret = dump_mounts(mni.mnt_ns_id);
+		if (ret)
+			return ret;
+
+		if (!recursive)
+			break;
+
+		/* get the next mntns (and overwrite the old mount ns info) */
+		ret = ioctl(mntns, NS_MNT_GET_NEXT, &mni);
+		close(mntns);
+		mntns = ret;
+	} while (mntns >= 0);
+
+	return 0;
+}
diff --git a/samples/vfs/samples-vfs.h b/samples/vfs/samples-vfs.h
new file mode 100644
index 000000000000..103e1e7c4cec
--- /dev/null
+++ b/samples/vfs/samples-vfs.h
@@ -0,0 +1,241 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SAMPLES_VFS_H
+#define __SAMPLES_VFS_H
+
+#include <errno.h>
+#include <linux/types.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+
+#define die_errno(format, ...)                                             \
+	do {                                                               \
+		fprintf(stderr, "%m | %s: %d: %s: " format "\n", __FILE__, \
+			__LINE__, __func__, ##__VA_ARGS__);                \
+		exit(EXIT_FAILURE);                                        \
+	} while (0)
+
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 mnt_opts;		/* [str] Options (comma separated, escaped) */
+	__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 mnt_ns_id;	/* ID of the mount namespace */
+	__u32 fs_subtype;	/* [str] Subtype of fs_type (if any) */
+	__u32 sb_source;	/* [str] Source string of the mount */
+	__u32 opt_num;		/* Number of fs options */
+	__u32 opt_array;	/* [str] Array of nul terminated fs options */
+	__u32 opt_sec_num;	/* Number of security options */
+	__u32 opt_sec_array;	/* [str] Array of nul terminated security options */
+	__u64 __spare2[46];
+	char str[];		/* Variable size part containing strings */
+};
+
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+	__u64 mnt_ns_id;
+};
+
+#ifndef MNT_ID_REQ_SIZE_VER0
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+#endif
+
+#ifndef MNT_ID_REQ_SIZE_VER1
+#define MNT_ID_REQ_SIZE_VER1	32 /* sizeof second published struct */
+#endif
+
+/* Get the id for a mount namespace */
+#ifndef NS_GET_MNTNS_ID
+#define NS_GET_MNTNS_ID _IO(0xb7, 0x5)
+#endif
+
+struct mnt_ns_info {
+	__u32 size;
+	__u32 nr_mounts;
+	__u64 mnt_ns_id;
+};
+
+#ifndef MNT_NS_INFO_SIZE_VER0
+#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */
+#endif
+
+#ifndef NS_MNT_GET_INFO
+#define NS_MNT_GET_INFO _IOR(0xb7, 10, struct mnt_ns_info)
+#endif
+
+#ifndef NS_MNT_GET_NEXT
+#define NS_MNT_GET_NEXT _IOR(0xb7, 11, struct mnt_ns_info)
+#endif
+
+#ifndef NS_MNT_GET_PREV
+#define NS_MNT_GET_PREV _IOR(0xb7, 12, struct mnt_ns_info)
+#endif
+
+#ifndef PIDFD_GET_MNT_NAMESPACE
+#define PIDFD_GET_MNT_NAMESPACE _IO(0xFF, 3)
+#endif
+
+#ifndef __NR_listmount
+#define __NR_listmount 458
+#endif
+
+#ifndef __NR_statmount
+#define __NR_statmount 457
+#endif
+
+#ifndef LSMT_ROOT
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+#endif
+
+/* @mask bits for statmount(2) */
+#ifndef STATMOUNT_SB_BASIC
+#define STATMOUNT_SB_BASIC		0x00000001U /* Want/got sb_... */
+#endif
+
+#ifndef STATMOUNT_MNT_BASIC
+#define STATMOUNT_MNT_BASIC		0x00000002U /* Want/got mnt_... */
+#endif
+
+#ifndef STATMOUNT_PROPAGATE_FROM
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U /* Want/got propagate_from */
+#endif
+
+#ifndef STATMOUNT_MNT_ROOT
+#define STATMOUNT_MNT_ROOT		0x00000008U /* Want/got mnt_root  */
+#endif
+
+#ifndef STATMOUNT_MNT_POINT
+#define STATMOUNT_MNT_POINT		0x00000010U /* Want/got mnt_point */
+#endif
+
+#ifndef STATMOUNT_FS_TYPE
+#define STATMOUNT_FS_TYPE		0x00000020U /* Want/got fs_type */
+#endif
+
+#ifndef STATMOUNT_MNT_NS_ID
+#define STATMOUNT_MNT_NS_ID		0x00000040U /* Want/got mnt_ns_id */
+#endif
+
+#ifndef STATMOUNT_MNT_OPTS
+#define STATMOUNT_MNT_OPTS		0x00000080U /* Want/got mnt_opts */
+#endif
+
+#ifndef STATMOUNT_FS_SUBTYPE
+#define STATMOUNT_FS_SUBTYPE		0x00000100U /* Want/got fs_subtype */
+#endif
+
+#ifndef STATMOUNT_SB_SOURCE
+#define STATMOUNT_SB_SOURCE		0x00000200U /* Want/got sb_source */
+#endif
+
+#ifndef STATMOUNT_OPT_ARRAY
+#define STATMOUNT_OPT_ARRAY		0x00000400U /* Want/got opt_... */
+#endif
+
+#ifndef STATMOUNT_OPT_SEC_ARRAY
+#define STATMOUNT_OPT_SEC_ARRAY		0x00000800U /* Want/got opt_sec... */
+#endif
+
+#ifndef STATX_MNT_ID_UNIQUE
+#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
+#endif
+
+#ifndef MOUNT_ATTR_RDONLY
+#define MOUNT_ATTR_RDONLY	0x00000001 /* Mount read-only */
+#endif
+
+#ifndef MOUNT_ATTR_NOSUID
+#define MOUNT_ATTR_NOSUID	0x00000002 /* Ignore suid and sgid bits */
+#endif
+
+#ifndef MOUNT_ATTR_NODEV
+#define MOUNT_ATTR_NODEV	0x00000004 /* Disallow access to device special files */
+#endif
+
+#ifndef MOUNT_ATTR_NOEXEC
+#define MOUNT_ATTR_NOEXEC	0x00000008 /* Disallow program execution */
+#endif
+
+#ifndef MOUNT_ATTR__ATIME
+#define MOUNT_ATTR__ATIME	0x00000070 /* Setting on how atime should be updated */
+#endif
+
+#ifndef MOUNT_ATTR_RELATIME
+#define MOUNT_ATTR_RELATIME	0x00000000 /* - Update atime relative to mtime/ctime. */
+#endif
+
+#ifndef MOUNT_ATTR_NOATIME
+#define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
+#endif
+
+#ifndef MOUNT_ATTR_STRICTATIME
+#define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
+#endif
+
+#ifndef MOUNT_ATTR_NODIRATIME
+#define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+#endif
+
+#ifndef MOUNT_ATTR_IDMAP
+#define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+#endif
+
+#ifndef MOUNT_ATTR_NOSYMFOLLOW
+#define MOUNT_ATTR_NOSYMFOLLOW	0x00200000 /* Do not follow symlinks */
+#endif
+
+#ifndef MS_RDONLY
+#define MS_RDONLY	 1	/* Mount read-only */
+#endif
+
+#ifndef MS_SYNCHRONOUS
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#endif
+
+#ifndef MS_MANDLOCK
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#endif
+
+#ifndef MS_DIRSYNC
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#endif
+
+#ifndef MS_UNBINDABLE
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#endif
+
+#ifndef MS_PRIVATE
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#endif
+
+#ifndef MS_SLAVE
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#endif
+
+#ifndef MS_SHARED
+#define MS_SHARED	(1<<20)	/* change to shared */
+#endif
+
+#ifndef MS_LAZYTIME
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+#endif
+
+#endif /* __SAMPLES_VFS_H */
diff --git a/samples/vfs/test-list-all-mounts.c b/samples/vfs/test-list-all-mounts.c
new file mode 100644
index 000000000000..1a02ea4593e3
--- /dev/null
+++ b/samples/vfs/test-list-all-mounts.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (c) 2024 Christian Brauner <brauner@kernel.org>
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <limits.h>
+#include <linux/types.h>
+#include <inttypes.h>
+#include <stdio.h>
+
+#include "../../tools/testing/selftests/pidfd/pidfd.h"
+#include "samples-vfs.h"
+
+static int __statmount(__u64 mnt_id, __u64 mnt_ns_id, __u64 mask,
+		       struct statmount *stmnt, size_t bufsize,
+		       unsigned int flags)
+{
+	struct mnt_id_req req = {
+		.size		= MNT_ID_REQ_SIZE_VER1,
+		.mnt_id		= mnt_id,
+		.param		= mask,
+		.mnt_ns_id	= mnt_ns_id,
+	};
+
+	return syscall(__NR_statmount, &req, stmnt, bufsize, flags);
+}
+
+static struct statmount *sys_statmount(__u64 mnt_id, __u64 mnt_ns_id,
+				       __u64 mask, unsigned int flags)
+{
+	size_t bufsize = 1 << 15;
+	struct statmount *stmnt = NULL, *tmp = NULL;
+	int ret;
+
+	for (;;) {
+		tmp = realloc(stmnt, bufsize);
+		if (!tmp)
+			goto out;
+
+		stmnt = tmp;
+		ret = __statmount(mnt_id, mnt_ns_id, mask, stmnt, bufsize, flags);
+		if (!ret)
+			return stmnt;
+
+		if (errno != EOVERFLOW)
+			goto out;
+
+		bufsize <<= 1;
+		if (bufsize >= UINT_MAX / 2)
+			goto out;
+	}
+
+out:
+	free(stmnt);
+	return NULL;
+}
+
+static ssize_t sys_listmount(__u64 mnt_id, __u64 last_mnt_id, __u64 mnt_ns_id,
+			     __u64 list[], size_t num, unsigned int flags)
+{
+	struct mnt_id_req req = {
+		.size		= MNT_ID_REQ_SIZE_VER1,
+		.mnt_id		= mnt_id,
+		.param		= last_mnt_id,
+		.mnt_ns_id	= mnt_ns_id,
+	};
+
+	return syscall(__NR_listmount, &req, list, num, flags);
+}
+
+int main(int argc, char *argv[])
+{
+#define LISTMNT_BUFFER 10
+	__u64 list[LISTMNT_BUFFER], last_mnt_id = 0;
+	int ret, pidfd, fd_mntns;
+	struct mnt_ns_info info = {};
+
+	pidfd = sys_pidfd_open(getpid(), 0);
+	if (pidfd < 0)
+		die_errno("pidfd_open failed");
+
+	fd_mntns = ioctl(pidfd, PIDFD_GET_MNT_NAMESPACE, 0);
+	if (fd_mntns < 0)
+		die_errno("ioctl(PIDFD_GET_MNT_NAMESPACE) failed");
+
+	ret = ioctl(fd_mntns, NS_MNT_GET_INFO, &info);
+	if (ret < 0)
+		die_errno("ioctl(NS_GET_MNTNS_ID) failed");
+
+	printf("Listing %u mounts for mount namespace %" PRIu64 "\n",
+	       info.nr_mounts, (uint64_t)info.mnt_ns_id);
+	for (;;) {
+		ssize_t nr_mounts;
+next:
+		nr_mounts = sys_listmount(LSMT_ROOT, last_mnt_id,
+					  info.mnt_ns_id, list, LISTMNT_BUFFER,
+					  0);
+		if (nr_mounts <= 0) {
+			int fd_mntns_next;
+
+			printf("Finished listing %u mounts for mount namespace %" PRIu64 "\n\n",
+			       info.nr_mounts, (uint64_t)info.mnt_ns_id);
+			fd_mntns_next = ioctl(fd_mntns, NS_MNT_GET_NEXT, &info);
+			if (fd_mntns_next < 0) {
+				if (errno == ENOENT) {
+					printf("Finished listing all mount namespaces\n");
+					exit(0);
+				}
+				die_errno("ioctl(NS_MNT_GET_NEXT) failed");
+			}
+			close(fd_mntns);
+			fd_mntns = fd_mntns_next;
+			last_mnt_id = 0;
+			printf("Listing %u mounts for mount namespace %" PRIu64 "\n",
+			       info.nr_mounts, (uint64_t)info.mnt_ns_id);
+			goto next;
+		}
+
+		for (size_t cur = 0; cur < nr_mounts; cur++) {
+			struct statmount *stmnt;
+
+			last_mnt_id = list[cur];
+
+			stmnt = sys_statmount(last_mnt_id, info.mnt_ns_id,
+					      STATMOUNT_SB_BASIC |
+					      STATMOUNT_MNT_BASIC |
+					      STATMOUNT_MNT_ROOT |
+					      STATMOUNT_MNT_POINT |
+					      STATMOUNT_MNT_NS_ID |
+					      STATMOUNT_MNT_OPTS |
+					      STATMOUNT_FS_TYPE, 0);
+			if (!stmnt) {
+				printf("Failed to statmount(%" PRIu64 ") in mount namespace(%" PRIu64 ")\n",
+				       (uint64_t)last_mnt_id, (uint64_t)info.mnt_ns_id);
+				continue;
+			}
+
+			printf("mnt_id:\t\t%" PRIu64 "\nmnt_parent_id:\t%" PRIu64 "\nfs_type:\t%s\nmnt_root:\t%s\nmnt_point:\t%s\nmnt_opts:\t%s\n\n",
+			       (uint64_t)stmnt->mnt_id,
+			       (uint64_t)stmnt->mnt_parent_id,
+			       stmnt->str + stmnt->fs_type,
+			       stmnt->str + stmnt->mnt_root,
+			       stmnt->str + stmnt->mnt_point,
+			       stmnt->str + stmnt->mnt_opts);
+			free(stmnt);
+		}
+	}
+
+	exit(0);
+}