Merge tag 'vfs-7.3-rc1.failfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull failfs filesystem from Christian Brauner:
 "Add failfs and expose a FD_FAILFS_ROOT sentinel.

  This allows userspace to shed their filesystem state completely. A
  process with its root or working directory in failfs must anchor every
  path lookup at an explicit file descriptor. Absolute paths, absolute
  symlinks and AT_FDCWD-relative lookups simply fail.

  Failfs is the counterpart to nullfs. nullfs says adds a permanently
  empty, immutable directory whose lookups fail with ENOENT but which
  can be opened, read, stat'd and mounted upon. Failfs on the other hand
  fails every operation. The root cannot be opened at all. A single
  instance is mounted during early boot via kern_mount(), which makes it
  logically distinct from every mount namespace.

  This is accompanied by a new fchroot() system call which makes
  chrooting via a file descriptor a first class concept. It's possible
  to chroot into failfs as an unprivileged user provided the task has no
  new privileges set"

* tag 'vfs-7.3-rc1.failfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  Documentation: add failfs documentation
  selftests/filesystems: add failfs selftests
  arch: hookup fchroot() system call
  fs: support FD_FAILFS_ROOT in fchroot()
  fs: add fchroot()
  fs: support FD_FAILFS_ROOT in fchdir()
  fs: add failfs

44 files changed, 931 insertions, 5 deletions

diff --git a/Documentation/filesystems/failfs.rst b/Documentation/filesystems/failfs.rst
new file mode 100644
index 000000000000..21ff2db7941d
--- /dev/null
+++ b/Documentation/filesystems/failfs.rst
@@ -0,0 +1,73 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======
+failfs
+======
+
+failfs is a kernel-internal filesystem that fails every operation
+reaching it with ``EOPNOTSUPP``. It is the counterpart to nullfs. Where
+nullfs is permanently empty, failfs means "nothing is supported here".
+It cannot be mounted from userspace, nothing can be mounted on top of
+it. It cannot be cloned.
+
+The only way into it is the ``FD_FAILFS_ROOT`` file descriptor sentinel which
+is understood by ``fchdir(2)`` and ``fchroot(2)``.
+
+Semantics
+=========
+
+Every path walk of a component through failfs fails with
+``EOPNOTSUPP`` before that component is parsed, including ``.``.
+
+No path lookup can open the root, not even with ``O_PATH``.
+
+A process with its working directory in failfs fails every
+``AT_FDCWD``-relative lookup. As with any working directory that is
+unreachable from the process root, the ``getcwd(2)`` system call returns
+a path prefixed with ``(unreachable)``.
+
+A process with its root directory in failfs fails every absolute path
+lookup including absolute symlinks and the interpreter of dynamically
+linked binaries. In other words, this fails exec.
+
+Lookups anchored at explicit directory file descriptors keep working. It
+is the ``fs_struct`` equivalent of ``RESOLVE_BENEATH``. The process must
+anchor every lookup at a file descriptor it explicitly holds.
+
+Entering
+========
+
+``fchroot(FD_FAILFS_ROOT, 0)`` requires ``CAP_SYS_CHROOT`` in the
+caller's user namespace, mirroring ``chroot(2)``. Unprivileged callers
+may enter if all of the following hold:
+
+* ``no_new_privs`` is set: setuid binaries on regular mounts remain
+  reachable via inherited directory file descriptors and executing them
+  with an unusable root directory is the classic confused deputy.
+
+* The caller is not already chrooted: the root directory is what
+  confines ``..`` resolution and the failfs root can never be reached by
+  walking up a real mount tree, so moving the root of a chrooted task to
+  failfs would allow it to escape its chroot via ``openat(fd, "..")``.
+
+* The caller does not share its ``fs_struct``: ``no_new_privs`` is
+  checked on the calling thread, but the root lives in the ``fs_struct``.
+  A ``CLONE_FS`` sibling without ``no_new_privs`` could otherwise execute
+  a setuid binary with the failfs root, so entry requires ``fs->users ==
+  1``, the same restriction ``setns(2)`` applies for the mount and user
+  namespaces.
+
+Leaving
+=======
+
+Backing out is currently hard, but this is a property of the current
+implementation, not a guaranteed interface, and may be loosened later.
+For now a process that entered failfs counts as chrooted, so it cannot
+create user namespaces to regain ``CAP_SYS_CHROOT``, and ``chroot(2)``
+or ``fchroot(2)`` back out require ``CAP_SYS_CHROOT``. The remaining way
+out today is ``setns(2)`` with a mount namespace file descriptor, which
+requires ``CAP_SYS_ADMIN`` over the target mount namespace as well as
+``CAP_SYS_CHROOT`` and ``CAP_SYS_ADMIN`` in the caller's user namespace
+and resets both root and working directory. A process that holds no such
+file descriptor and restricts ``*chdir()``/``*chroot()``/``setns()`` via
+seccomp cannot currently get back out.
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 1f71cf159547..734a45e51667 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -91,6 +91,7 @@ Documentation for filesystem implementations.
    ext3
    ext4/index
    f2fs
+   failfs
    gfs2/index
    hfs
    hfsplus
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index f31b7afffc34..52e3538cc7df 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -511,3 +511,4 @@
 579	common	file_setattr			sys_file_setattr
 580	common	listns				sys_listns
 581	common	rseq_slice_yield		sys_rseq_slice_yield
+582	common	fchroot				sys_fchroot
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 94351e22bfcf..55717ed32c27 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -486,3 +486,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/arm64/tools/syscall_32.tbl b/arch/arm64/tools/syscall_32.tbl
index 62d93d88e0fe..df2d1d82fb3c 100644
--- a/arch/arm64/tools/syscall_32.tbl
+++ b/arch/arm64/tools/syscall_32.tbl
@@ -483,3 +483,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 248934257101..ba7a4d8903d0 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -471,3 +471,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 223d26303627..c55a5c96f49b 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -477,3 +477,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 7430714e2b8f..9ae88e4eac61 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -410,3 +410,4 @@
 469	n32	file_setattr			sys_file_setattr
 470	n32	listns				sys_listns
 471	n32	rseq_slice_yield		sys_rseq_slice_yield
+472	n32	fchroot				sys_fchroot
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 630aab9e5425..83dc93a0712f 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -386,3 +386,4 @@
 469	n64	file_setattr			sys_file_setattr
 470	n64	listns				sys_listns
 471	n64	rseq_slice_yield		sys_rseq_slice_yield
+472	n64	fchroot				sys_fchroot
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 128653112284..9c62429c9b7b 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -459,3 +459,4 @@
 469	o32	file_setattr			sys_file_setattr
 470	o32	listns				sys_listns
 471	o32	rseq_slice_yield		sys_rseq_slice_yield
+472	o32	fchroot				sys_fchroot
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index c6331dad9461..88adc4016cce 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -470,3 +470,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 4fcc7c58a105..cfbb70039ff0 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -562,3 +562,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	nospu	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 09a7ef04d979..1b45e68a217b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -398,3 +398,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 70b315cbe710..ace068dff0de 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -475,3 +475,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 7e71bf7fcd14..5b9fe0e8140f 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -517,3 +517,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index f832ebd2d79b..2c172ef48dfd 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -477,3 +477,4 @@
 469	i386	file_setattr		sys_file_setattr
 470	i386	listns			sys_listns
 471	i386	rseq_slice_yield	sys_rseq_slice_yield
+472	i386	fchroot			sys_fchroot
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 524155d655da..d5b6045b0090 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -396,6 +396,7 @@
 469	common	file_setattr		sys_file_setattr
 470	common	listns			sys_listns
 471	common	rseq_slice_yield	sys_rseq_slice_yield
+472	common	fchroot			sys_fchroot
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index a9bca4e484de..d354bb231796 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/fs/Makefile b/fs/Makefile
index d4704321c3d8..055dfc23d82b 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -16,7 +16,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
 		fs_dirent.o fs_context.o fs_parser.o fsopen.o init.o \
 		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o \
-		file_attr.o fserror.o nullfs.o
+		file_attr.o fserror.o nullfs.o failfs.o
 
 obj-$(CONFIG_BUFFER_HEAD)	+= buffer.o mpage.o
 obj-$(CONFIG_PROC_FS)		+= proc_namespace.o
diff --git a/fs/d_path.c b/fs/d_path.c
index a48957c0971e..c25309006d5d 100644
--- a/fs/d_path.c
+++ b/fs/d_path.c
@@ -279,7 +279,8 @@ char *d_path(const struct path *path, char *buf, int buflen)
 	 * and instead have d_path return the mounted path.
 	 */
 	if (path->dentry->d_op && path->dentry->d_op->d_dname &&
-	    (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root))
+	    (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root ||
+	     failfs_mnt(path->mnt)))
 		return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
 
 	rcu_read_lock();
diff --git a/fs/failfs.c b/fs/failfs.c
new file mode 100644
index 000000000000..66a36da3d236
--- /dev/null
+++ b/fs/failfs.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2026 Christian Brauner <brauner@kernel.org> */
+#include <linux/fs.h>
+#include <linux/fs/super_types.h>
+#include <linux/fs_context.h>
+#include <linux/fs_struct.h>
+#include <linux/magic.h>
+#include <linux/mount.h>
+
+#include "internal.h"
+
+static struct path failfs_root_path = {};
+
+void failfs_get_root(struct path *path)
+{
+	*path = failfs_root_path;
+	path_get(path);
+}
+
+bool failfs_mnt(const struct vfsmount *mnt)
+{
+	return mnt->mnt_sb == failfs_root_path.mnt->mnt_sb;
+}
+
+static int failfs_permission(struct mnt_idmap *idmap, struct inode *inode,
+			     int mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct dentry *failfs_lookup(struct inode *dir, struct dentry *dentry,
+				    unsigned int flags)
+{
+	/* Unreachable: ->permission() already failed the walk. */
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static int failfs_getattr(struct mnt_idmap *idmap, const struct path *path,
+			  struct kstat *stat, u32 request_mask,
+			  unsigned int query_flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct inode_operations failfs_dir_inode_operations = {
+	.permission	= failfs_permission,
+	.lookup		= failfs_lookup,
+	.getattr	= failfs_getattr,
+};
+
+static const struct file_operations failfs_dir_operations = {};
+
+static int failfs_d_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	/*
+	 * The root is only ever reached as a path-walk terminal by jumping
+	 * to it: as "/" when it is the caller's root, or through a
+	 * /proc/<pid>/{root,cwd} magic link. ->permission() already fails
+	 * every walk of a component, but a jump lands on the root without
+	 * one. Refuse here too so the root cannot be pinned by an O_PATH
+	 * open or encoded into a file handle.
+	 */
+	return -EOPNOTSUPP;
+}
+
+static char *failfs_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+	return dynamic_dname(buffer, buflen, "failfs:/");
+}
+
+static const struct dentry_operations failfs_dentry_operations = {
+	.d_dname		= failfs_dname,
+	.d_weak_revalidate	= failfs_d_weak_revalidate,
+};
+
+static int failfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct super_operations failfs_super_operations = {
+	.statfs	= failfs_statfs,
+};
+
+static int failfs_fill_super(struct super_block *s, struct fs_context *fc)
+{
+	struct inode *inode;
+
+	s->s_maxbytes		= MAX_LFS_FILESIZE;
+	s->s_blocksize		= PAGE_SIZE;
+	s->s_blocksize_bits	= PAGE_SHIFT;
+	s->s_magic		= FAIL_FS_MAGIC;
+	s->s_op			= &failfs_super_operations;
+	s->s_export_op		= NULL;
+	s->s_xattr		= NULL;
+	s->s_time_gran		= 1;
+	s->s_d_flags		= 0;
+
+	inode = new_inode(s);
+	if (!inode)
+		return -ENOMEM;
+
+	/* failfs supports no operations... */
+	inode->i_mode	= S_IFDIR;
+	set_nlink(inode, 2);
+	inode->i_op	= &failfs_dir_inode_operations;
+	inode->i_fop	= &failfs_dir_operations;
+	simple_inode_init_ts(inode);
+	inode->i_ino	= 1;
+	/* ... and is immutable. */
+	inode->i_flags |= S_IMMUTABLE;
+
+	set_default_d_op(s, &failfs_dentry_operations);
+	s->s_root = d_make_root(inode);
+	if (!s->s_root)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int failfs_get_tree(struct fs_context *fc)
+{
+	return get_tree_single(fc, failfs_fill_super);
+}
+
+static const struct fs_context_operations failfs_context_ops = {
+	.get_tree	= failfs_get_tree,
+};
+
+static int failfs_init_fs_context(struct fs_context *fc)
+{
+	fc->ops		= &failfs_context_ops;
+	fc->global	= true;
+	fc->sb_flags	|= SB_NOUSER;
+	fc->s_iflags	|= SB_I_NOEXEC | SB_I_NODEV;
+	return 0;
+}
+
+int failfs_current_chdir(void)
+{
+	struct path path;
+
+	failfs_get_root(&path);
+	set_fs_pwd(current->fs, &path);
+	path_put(&path);
+	return 0;
+}
+
+static struct file_system_type failfs_fs_type = {
+	.name			= "failfs",
+	.init_fs_context	= failfs_init_fs_context,
+	.kill_sb		= kill_anon_super,
+};
+
+void __init failfs_init(void)
+{
+	struct vfsmount *mnt;
+
+	/* A single instance that is member of no mount namespace. */
+	mnt = kern_mount(&failfs_fs_type);
+	if (IS_ERR(mnt))
+		panic("VFS: Failed to create failfs");
+
+	failfs_root_path.mnt	= mnt;
+	failfs_root_path.dentry	= mnt->mnt_root;
+}
diff --git a/fs/internal.h b/fs/internal.h
index 355d93f92208..67aa0444351b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -362,3 +362,7 @@ int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		       struct iattr *attr);
 void pidfs_get_root(struct path *path);
 void nsfs_get_root(struct path *path);
+void failfs_get_root(struct path *path);
+void __init failfs_init(void);
+bool failfs_mnt(const struct vfsmount *mnt);
+int failfs_current_chdir(void);
diff --git a/fs/namespace.c b/fs/namespace.c
index 3d5cd5bf3b05..87c365f2f82b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -6274,6 +6274,7 @@ void __init mnt_init(void)
 	shmem_init();
 	init_rootfs();
 	init_mount_tree();
+	failfs_init();
 }
 
 void put_mnt_ns(struct mnt_namespace *ns)
diff --git a/fs/open.c b/fs/open.c
index 408925d7bd0b..6b1c14e684a9 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -570,9 +570,12 @@ retry:
 
 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
-	CLASS(fd_raw, f)(fd);
 	int error;
 
+	if ((int)fd == FD_FAILFS_ROOT)
+		return failfs_current_chdir();
+
+	CLASS(fd_raw, f)(fd);
 	if (fd_empty(f))
 		return -EBADF;
 
@@ -615,6 +618,52 @@ dput_and_out:
 	return error;
 }
 
+SYSCALL_DEFINE2(fchroot, int, fd, unsigned int, flags)
+{
+	struct path path;
+	int error;
+
+	if (flags)
+		return -EINVAL;
+
+	if (fd == FD_FAILFS_ROOT) {
+		if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) {
+			if (!task_no_new_privs(current))
+				return -EPERM;
+			/* A shared fs_struct lets a sibling exec setuid past the check above. */
+			if (current->fs->users != 1)
+				return -EINVAL;
+			/* Moving the root to failfs lifts the old root's ".." barrier. */
+			if (current_chrooted())
+				return -EPERM;
+		}
+		failfs_get_root(&path);
+	} else {
+		CLASS(fd_raw, f)(fd);
+		if (fd_empty(f))
+			return -EBADF;
+
+		if (!d_can_lookup(fd_file(f)->f_path.dentry))
+			return -ENOTDIR;
+
+		error = file_permission(fd_file(f), MAY_EXEC | MAY_CHDIR);
+		if (error)
+			return error;
+
+		if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
+			return -EPERM;
+
+		path = fd_file(f)->f_path;
+		path_get(&path);
+	}
+
+	error = security_path_chroot(&path);
+	if (!error)
+		set_fs_root(current->fs, &path);
+	path_put(&path);
+	return error;
+}
+
 int chmod_common(const struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 874d9067a43b..8413b624ad47 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -457,6 +457,7 @@ asmlinkage long sys_faccessat2(int dfd, const char __user *filename, int mode,
 asmlinkage long sys_chdir(const char __user *filename);
 asmlinkage long sys_fchdir(unsigned int fd);
 asmlinkage long sys_chroot(const char __user *filename);
+asmlinkage long sys_fchroot(int fd, unsigned int flags);
 asmlinkage long sys_fchmod(unsigned int fd, umode_t mode);
 asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
 			     umode_t mode);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index a627acc8fb5f..5b7e77a7c736 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -863,8 +863,12 @@ __SYSCALL(__NR_listns, sys_listns)
 #define __NR_rseq_slice_yield 471
 __SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield)
 
+/* fs/open.c */
+#define __NR_fchroot 472
+__SYSCALL(__NR_fchroot, sys_fchroot)
+
 #undef __NR_syscalls
-#define __NR_syscalls 472
+#define __NR_syscalls 473
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index aadfbf6e0cb3..e43e3de3e9ee 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -124,6 +124,7 @@ struct delegation {
 
 #define FD_PIDFS_ROOT			-10002 /* Root of the pidfs filesystem */
 #define FD_NSFS_ROOT			-10003 /* Root of the nsfs filesystem */
+#define FD_FAILFS_ROOT			-10004 /* Root of the failfs filesystem */
 #define FD_INVALID			-10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */
 
 /* Generic flags for the *at(2) family of syscalls. */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 4f2da935a76c..fd5f0e95648e 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -105,5 +105,6 @@
 #define PID_FS_MAGIC		0x50494446	/* "PIDF" */
 #define GUEST_MEMFD_MAGIC	0x474d454d	/* "GMEM" */
 #define NULL_FS_MAGIC		0x4E554C4C	/* "NULL" */
+#define FAIL_FS_MAGIC		0x4641494C	/* "FAIL" */
 
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/scripts/syscall.tbl b/scripts/syscall.tbl
index 7a42b32b6577..0ab531605120 100644
--- a/scripts/syscall.tbl
+++ b/scripts/syscall.tbl
@@ -412,3 +412,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index a627acc8fb5f..5b7e77a7c736 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -863,8 +863,12 @@ __SYSCALL(__NR_listns, sys_listns)
 #define __NR_rseq_slice_yield 471
 __SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield)
 
+/* fs/open.c */
+#define __NR_fchroot 472
+__SYSCALL(__NR_fchroot, sys_fchroot)
+
 #undef __NR_syscalls
-#define __NR_syscalls 472
+#define __NR_syscalls 473
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
index 94351e22bfcf..55717ed32c27 100644
--- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
@@ -486,3 +486,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 630aab9e5425..83dc93a0712f 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -386,3 +386,4 @@
 469	n64	file_setattr			sys_file_setattr
 470	n64	listns				sys_listns
 471	n64	rseq_slice_yield		sys_rseq_slice_yield
+472	n64	fchroot				sys_fchroot
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 4fcc7c58a105..cfbb70039ff0 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -562,3 +562,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	nospu	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 09a7ef04d979..1b45e68a217b 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -398,3 +398,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
index 70b315cbe710..ace068dff0de 100644
--- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
@@ -475,3 +475,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
index 7e71bf7fcd14..5b9fe0e8140f 100644
--- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
@@ -517,3 +517,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index f832ebd2d79b..2c172ef48dfd 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -477,3 +477,4 @@
 469	i386	file_setattr		sys_file_setattr
 470	i386	listns			sys_listns
 471	i386	rseq_slice_yield	sys_rseq_slice_yield
+472	i386	fchroot			sys_fchroot
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 524155d655da..d5b6045b0090 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -396,6 +396,7 @@
 469	common	file_setattr		sys_file_setattr
 470	common	listns			sys_listns
 471	common	rseq_slice_yield	sys_rseq_slice_yield
+472	common	fchroot			sys_fchroot
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
index a9bca4e484de..d354bb231796 100644
--- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl
index 7a42b32b6577..0ab531605120 100644
--- a/tools/scripts/syscall.tbl
+++ b/tools/scripts/syscall.tbl
@@ -412,3 +412,4 @@
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
 471	common	rseq_slice_yield		sys_rseq_slice_yield
+472	common	fchroot				sys_fchroot
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index b622052ec3e9..4854a8eda449 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -33,6 +33,7 @@ TARGETS += fchmodat2
 TARGETS += filesystems
 TARGETS += filesystems/binderfs
 TARGETS += filesystems/epoll
+TARGETS += filesystems/failfs
 TARGETS += filesystems/fat
 TARGETS += filesystems/overlayfs
 TARGETS += filesystems/statmount
diff --git a/tools/testing/selftests/filesystems/failfs/.gitignore b/tools/testing/selftests/filesystems/failfs/.gitignore
new file mode 100644
index 000000000000..cd3b5d884d7e
--- /dev/null
+++ b/tools/testing/selftests/filesystems/failfs/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+failfs_test
diff --git a/tools/testing/selftests/filesystems/failfs/Makefile b/tools/testing/selftests/filesystems/failfs/Makefile
new file mode 100644
index 000000000000..3c5d98b4fe72
--- /dev/null
+++ b/tools/testing/selftests/filesystems/failfs/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
+TEST_GEN_PROGS := failfs_test
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/failfs/failfs_test.c b/tools/testing/selftests/filesystems/failfs/failfs_test.c
new file mode 100644
index 000000000000..29a3c294127e
--- /dev/null
+++ b/tools/testing/selftests/filesystems/failfs/failfs_test.c
@@ -0,0 +1,585 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <link.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../../kselftest_harness.h"
+
+#ifndef __NR_fchroot
+#define __NR_fchroot 472
+#endif
+
+#ifndef FD_PIDFS_ROOT
+#define FD_PIDFS_ROOT -10002
+#endif
+
+#ifndef FD_NSFS_ROOT
+#define FD_NSFS_ROOT -10003
+#endif
+
+#ifndef FD_FAILFS_ROOT
+#define FD_FAILFS_ROOT -10004
+#endif
+
+#define NOBODY_UID 65534
+
+/* Child sentinel exit code: the exec was blocked as expected. */
+#define FAILFS_EXEC_BLOCKED 99
+
+/* Stack for the CLONE_FS helper in fchroot_sentinel_shared_fs_struct. */
+#define FAILFS_CLONE_STACK (64 * 1024)
+
+static int sys_fchroot(int fd, unsigned int flags)
+{
+	return syscall(__NR_fchroot, fd, flags);
+}
+
+/*
+ * Raw syscall: glibc's getcwd() rejects the kernel's "(unreachable)"
+ * result and falls back to a generic implementation.
+ */
+static long sys_getcwd(char *buf, size_t size)
+{
+	return syscall(__NR_getcwd, buf, size);
+}
+
+static int drop_to_nobody(void)
+{
+	return setresuid(NOBODY_UID, NOBODY_UID, NOBODY_UID);
+}
+
+/* Parked CLONE_FS child; dies with its parent so it never leaks. */
+static int failfs_park(void *arg)
+{
+	pid_t parent = (pid_t)(long)arg;
+
+	prctl(PR_SET_PDEATHSIG, SIGKILL);
+	/* The parent may have died before the death signal was armed. */
+	if (getppid() != parent)
+		_exit(0);
+	pause();
+	return 0;
+}
+
+/* Is fd a dynamically linked ELF with an absolute PT_INTERP interpreter? */
+static int elf_has_absolute_interp(int fd)
+{
+	ElfW(Ehdr) ehdr;
+	ElfW(Phdr) phdr;
+	char interp;
+	int i;
+
+	if (pread(fd, &ehdr, sizeof(ehdr), 0) != sizeof(ehdr))
+		return 0;
+	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0)
+		return 0;
+
+	for (i = 0; i < ehdr.e_phnum; i++) {
+		if (pread(fd, &phdr, sizeof(phdr),
+			  ehdr.e_phoff + i * sizeof(phdr)) != sizeof(phdr))
+			return 0;
+		if (phdr.p_type != PT_INTERP)
+			continue;
+		if (pread(fd, &interp, 1, phdr.p_offset) != 1)
+			return 0;
+		return interp == '/';
+	}
+
+	return 0;
+}
+
+TEST(fchdir_sentinel)
+{
+	char buf[PATH_MAX];
+	int fd;
+
+	ASSERT_EQ(fchdir(FD_FAILFS_ROOT), 0);
+
+	/* The working directory is unreachable from the process root. */
+	ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0);
+	ASSERT_EQ(strncmp(buf, "(unreachable)", 13), 0);
+
+	/* Every AT_FDCWD-relative lookup fails. */
+	ASSERT_EQ(openat(AT_FDCWD, "foo", O_RDONLY), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+	ASSERT_EQ(openat(AT_FDCWD, ".", O_RDONLY), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+	ASSERT_EQ(openat(AT_FDCWD, "..", O_RDONLY), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+	ASSERT_EQ(openat(AT_FDCWD, "foo", O_WRONLY | O_CREAT, 0600), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* The cwd cannot be pinned by following /proc/self/cwd into it. */
+	ASSERT_EQ(open("/proc/self/cwd", O_PATH), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* The root is untouched so absolute lookups keep working... */
+	fd = open("/", O_RDONLY | O_DIRECTORY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(close(fd), 0);
+
+	/* ... and the working directory can be recovered. */
+	ASSERT_EQ(chdir("/"), 0);
+	ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0);
+	ASSERT_EQ(strcmp(buf, "/"), 0);
+}
+
+TEST(fchdir_rejects_other_sentinels)
+{
+	ASSERT_EQ(fchdir(FD_PIDFS_ROOT), -1);
+	ASSERT_EQ(errno, EBADF);
+	ASSERT_EQ(fchdir(FD_NSFS_ROOT), -1);
+	ASSERT_EQ(errno, EBADF);
+	ASSERT_EQ(fchdir(-10009), -1);
+	ASSERT_EQ(errno, EBADF);
+}
+
+TEST(fchroot_flags)
+{
+	int fd;
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 1), -1);
+	ASSERT_EQ(errno, EINVAL);
+
+	fd = open("/", O_PATH | O_DIRECTORY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(sys_fchroot(fd, 1), -1);
+	ASSERT_EQ(errno, EINVAL);
+	ASSERT_EQ(close(fd), 0);
+}
+
+TEST(fchroot_bad_fd)
+{
+	ASSERT_EQ(sys_fchroot(-1, 0), -1);
+	ASSERT_EQ(errno, EBADF);
+
+	/* Only FD_FAILFS_ROOT is a valid sentinel. */
+	ASSERT_EQ(sys_fchroot(FD_PIDFS_ROOT, 0), -1);
+	ASSERT_EQ(errno, EBADF);
+	ASSERT_EQ(sys_fchroot(FD_NSFS_ROOT, 0), -1);
+	ASSERT_EQ(errno, EBADF);
+}
+
+TEST(fchroot_notdir)
+{
+	int fd;
+
+	fd = open("/proc/self/status", O_RDONLY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(sys_fchroot(fd, 0), -1);
+	ASSERT_EQ(errno, ENOTDIR);
+	ASSERT_EQ(close(fd), 0);
+}
+
+TEST(fchroot_realfd_requires_cap)
+{
+	int fd;
+
+	if (geteuid() == 0)
+		ASSERT_EQ(drop_to_nobody(), 0);
+
+	fd = open("/", O_PATH | O_DIRECTORY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(sys_fchroot(fd, 0), -1);
+	ASSERT_EQ(errno, EPERM);
+	ASSERT_EQ(close(fd), 0);
+}
+
+TEST(fchroot_realfd)
+{
+	char template[] = "/tmp/failfs_test.XXXXXX";
+	char path[PATH_MAX];
+	struct stat st;
+	int tmpfd, dfd, fd;
+
+	if (geteuid() != 0)
+		SKIP(return, "fchroot() with a regular fd requires CAP_SYS_CHROOT");
+
+	tmpfd = open("/tmp", O_PATH | O_DIRECTORY);
+	ASSERT_GE(tmpfd, 0);
+
+	ASSERT_NE(mkdtemp(template), NULL);
+	snprintf(path, sizeof(path), "%s/canary", template);
+	fd = open(path, O_WRONLY | O_CREAT, 0600);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(close(fd), 0);
+
+	dfd = open(template, O_PATH | O_DIRECTORY);
+	ASSERT_GE(dfd, 0);
+	ASSERT_EQ(sys_fchroot(dfd, 0), 0);
+	ASSERT_EQ(close(dfd), 0);
+
+	ASSERT_EQ(stat("/canary", &st), 0);
+
+	/* Best-effort cleanup: dirfd-anchored I/O works with the new root. */
+	snprintf(path, sizeof(path), "%s/canary", template + strlen("/tmp/"));
+	unlinkat(tmpfd, path, 0);
+	unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR);
+}
+
+TEST(fchroot_sentinel)
+{
+	char template[] = "/tmp/failfs_test.XXXXXX";
+	struct stat realroot, st;
+	struct statfs sfs;
+	char buf[PATH_MAX];
+	int procfd, tmpfd, dfd, fd;
+	struct {
+		struct file_handle handle;
+		unsigned char f_handle[MAX_HANDLE_SZ];
+	} fh;
+	int mntid;
+	ssize_t ret;
+
+	if (geteuid() != 0)
+		SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT");
+
+	ASSERT_EQ(stat("/", &realroot), 0);
+	procfd = open("/proc", O_PATH | O_DIRECTORY);
+	ASSERT_GE(procfd, 0);
+	tmpfd = open("/tmp", O_PATH | O_DIRECTORY);
+	ASSERT_GE(tmpfd, 0);
+	ASSERT_NE(mkdtemp(template), NULL);
+	dfd = open(template, O_RDONLY | O_DIRECTORY);
+	ASSERT_GE(dfd, 0);
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+
+	/* Absolute lookups fail. */
+	ASSERT_EQ(open("/etc/passwd", O_RDONLY), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+	ASSERT_EQ(mkdir("/foo", 0700), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/*
+	 * The root cannot be referenced at all - not even an O_PATH open,
+	 * which skips ->permission(), because it lands on the root as a
+	 * jumped walk terminal that ->d_weak_revalidate() refuses.
+	 */
+	ASSERT_EQ(open("/", O_RDONLY | O_DIRECTORY), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+	ASSERT_EQ(open("/", O_PATH), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+	ASSERT_EQ(statfs("/", &sfs), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/*
+	 * It cannot be pinned by following /proc/self/root into it either
+	 * (only the root is in failfs here, so self/cwd is still real).
+	 */
+	ASSERT_EQ(openat(procfd, "self/root", O_PATH), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* Nor encoded into a file handle. */
+	fh.handle.handle_bytes = MAX_HANDLE_SZ;
+	ASSERT_EQ(name_to_handle_at(AT_FDCWD, "/", &fh.handle, &mntid, 0), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* The working directory is now unreachable from the root. */
+	ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0);
+	ASSERT_EQ(strncmp(buf, "(unreachable)", 13), 0);
+
+	/* Lookups anchored at real directories keep working. */
+	fd = openat(AT_FDCWD, ".", O_RDONLY | O_DIRECTORY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(close(fd), 0);
+	fd = openat(dfd, "canary", O_WRONLY | O_CREAT, 0600);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(write(fd, "x", 1), 1);
+	ASSERT_EQ(close(fd), 0);
+	fd = openat(dfd, "canary", O_RDONLY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(close(fd), 0);
+
+	/* ".." walks clamp at the top of the mount tree, not at failfs. */
+	fd = openat(AT_FDCWD, "../../../../../../../../../..", O_PATH);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(fstat(fd, &st), 0);
+	ASSERT_EQ(st.st_dev, realroot.st_dev);
+	ASSERT_EQ(st.st_ino, realroot.st_ino);
+	ASSERT_EQ(close(fd), 0);
+
+	/* readlink of the magic link still works: it does not follow. */
+	ret = readlinkat(procfd, "self/root", buf, sizeof(buf) - 1);
+	ASSERT_GT(ret, 0);
+	buf[ret] = '\0';
+	TH_LOG("/proc/self/root points to '%s'", buf);
+	/* d_path() names the failfs root synthetically, never as a real path. */
+	ASSERT_EQ(strcmp(buf, "failfs:/"), 0);
+
+	/* But following it into failfs is refused. */
+	ASSERT_EQ(fstatat(procfd, "self/root", &st, 0), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* Best-effort cleanup via the pre-opened dirfds. */
+	unlinkat(dfd, "canary", 0);
+	unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR);
+}
+
+TEST(fchroot_sentinel_absolute_symlink)
+{
+	char template[] = "/tmp/failfs_test.XXXXXX";
+	int tmpfd, dfd, fd;
+
+	if (geteuid() != 0)
+		SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT");
+
+	tmpfd = open("/tmp", O_PATH | O_DIRECTORY);
+	ASSERT_GE(tmpfd, 0);
+	ASSERT_NE(mkdtemp(template), NULL);
+	dfd = open(template, O_RDONLY | O_DIRECTORY);
+	ASSERT_GE(dfd, 0);
+
+	fd = openat(dfd, "target", O_WRONLY | O_CREAT, 0600);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(close(fd), 0);
+	ASSERT_EQ(symlinkat("target", dfd, "rel"), 0);
+	ASSERT_EQ(symlinkat("/etc", dfd, "abs"), 0);
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+
+	/* Relative symlinks keep resolving within the dirfd-anchored walk... */
+	fd = openat(dfd, "rel", O_RDONLY);
+	ASSERT_GE(fd, 0);
+	ASSERT_EQ(close(fd), 0);
+
+	/* ... absolute symlinks restart the walk at the failfs root. */
+	ASSERT_EQ(openat(dfd, "abs", O_RDONLY), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* Best-effort cleanup via the pre-opened dirfds. */
+	unlinkat(dfd, "abs", 0);
+	unlinkat(dfd, "rel", 0);
+	unlinkat(dfd, "target", 0);
+	unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR);
+}
+
+TEST(fchroot_sentinel_unprivileged)
+{
+	char buf[PATH_MAX];
+
+	if (geteuid() == 0)
+		ASSERT_EQ(drop_to_nobody(), 0);
+
+	/* Without no_new_privs entering failfs is not allowed... */
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), -1);
+	ASSERT_EQ(errno, EPERM);
+
+	/* ... with no_new_privs set it is allowed. */
+	ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0);
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+
+	ASSERT_EQ(open("/etc/passwd", O_RDONLY), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* The task counts as chrooted: no user namespaces anymore. */
+	ASSERT_EQ(unshare(CLONE_NEWUSER), -1);
+	ASSERT_EQ(errno, EPERM);
+
+	/* With both root and cwd in failfs getcwd() reports "/". */
+	ASSERT_EQ(fchdir(FD_FAILFS_ROOT), 0);
+	ASSERT_GT(sys_getcwd(buf, sizeof(buf)), 0);
+	ASSERT_EQ(strcmp(buf, "/"), 0);
+}
+
+TEST(fchroot_sentinel_rejected_when_chrooted)
+{
+	char template[] = "/tmp/failfs_test.XXXXXX";
+	int tmpfd;
+
+	if (geteuid() != 0)
+		SKIP(return, "chroot() requires CAP_SYS_CHROOT");
+
+	tmpfd = open("/tmp", O_PATH | O_DIRECTORY);
+	ASSERT_GE(tmpfd, 0);
+	ASSERT_NE(mkdtemp(template), NULL);
+	ASSERT_EQ(chroot(template), 0);
+	ASSERT_EQ(chdir("/"), 0);
+
+	/* Remove the jail while still privileged; sticky /tmp blocks nobody. */
+	unlinkat(tmpfd, template + strlen("/tmp/"), AT_REMOVEDIR);
+
+	ASSERT_EQ(drop_to_nobody(), 0);
+	ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0);
+
+	/* An unprivileged chrooted task must not lift its ".." barrier. */
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), -1);
+	ASSERT_EQ(errno, EPERM);
+}
+
+TEST(fchroot_sentinel_shared_fs_struct)
+{
+	char stack[FAILFS_CLONE_STACK];
+	pid_t pid;
+
+	if (geteuid() == 0)
+		ASSERT_EQ(drop_to_nobody(), 0);
+
+	/* A CLONE_FS sibling shares the fs_struct: bump fs->users to 2. */
+	pid = clone(failfs_park, stack + sizeof(stack), CLONE_FS | SIGCHLD,
+		    (void *)(long)getpid());
+	ASSERT_GE(pid, 0);
+
+	ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0);
+
+	/*
+	 * A sibling without no_new_privs could exec a setuid binary with
+	 * the failfs root, so a shared fs_struct is refused even with
+	 * no_new_privs set.
+	 */
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), -1);
+	ASSERT_EQ(errno, EINVAL);
+
+	ASSERT_EQ(kill(pid, SIGKILL), 0);
+	ASSERT_EQ(waitpid(pid, NULL, 0), pid);
+}
+
+TEST(fchroot_sentinel_no_overmount)
+{
+	if (geteuid() != 0)
+		SKIP(return, "mounting requires privileges");
+
+	/*
+	 * Contain the blast radius: if failfs ever regressed and "/"
+	 * resolved to the real root, the tmpfs mount below must not touch
+	 * the host. A private mount namespace keeps it local to this child.
+	 */
+	ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+	ASSERT_EQ(mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL), 0);
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+
+	/*
+	 * Nothing can be mounted on top of the failfs root. It cannot even
+	 * be named as a mount target: resolving "/" is refused before the
+	 * mount machinery (which, failfs being in no mount namespace, would
+	 * reject it anyway) is ever reached. open_tree(OPEN_TREE_CLONE) is
+	 * likewise moot since no fd to the root can be obtained.
+	 */
+	ASSERT_EQ(mount("none", "/", "tmpfs", 0, NULL), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+}
+
+TEST(fchroot_sentinel_setns_escape)
+{
+	struct stat realroot, st;
+	int nsfd;
+
+	if (geteuid() != 0)
+		SKIP(return, "setns() to a mount namespace requires privileges");
+
+	ASSERT_EQ(stat("/", &realroot), 0);
+	nsfd = open("/proc/self/ns/mnt", O_RDONLY);
+	ASSERT_GE(nsfd, 0);
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+	ASSERT_EQ(open("/etc", O_PATH), -1);
+	ASSERT_EQ(errno, EOPNOTSUPP);
+
+	/* A mount namespace fd is the key out: it resets root and cwd. */
+	ASSERT_EQ(setns(nsfd, CLONE_NEWNS), 0);
+	ASSERT_EQ(close(nsfd), 0);
+
+	ASSERT_EQ(stat("/", &st), 0);
+	ASSERT_EQ(st.st_dev, realroot.st_dev);
+	ASSERT_EQ(st.st_ino, realroot.st_ino);
+}
+
+TEST(fchroot_sentinel_exec)
+{
+	pid_t pid;
+	int status;
+
+	if (geteuid() != 0)
+		SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT");
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+
+	/*
+	 * Exec in a child: a wrongly successful exec would replace the test
+	 * image and its exit code would not match the sentinel below.
+	 */
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		execl("/bin/true", "true", NULL);
+		_exit(errno == EOPNOTSUPP ? FAILFS_EXEC_BLOCKED : 1);
+	}
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), FAILFS_EXEC_BLOCKED);
+}
+
+TEST(fchroot_sentinel_exec_interpreter)
+{
+	static const char * const argv[] = { "failfs_test", NULL };
+	static const char * const envp[] = { NULL };
+	pid_t pid;
+	int status, exefd;
+
+	if (geteuid() != 0)
+		SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT");
+
+	/* Exec ourselves: the one binary guaranteed to be around. */
+	exefd = open("/proc/self/exe", O_RDONLY);
+	ASSERT_GE(exefd, 0);
+	if (!elf_has_absolute_interp(exefd))
+		SKIP(return, "test binary has no absolute PT_INTERP interpreter");
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+
+	/*
+	 * The binary itself needs no path lookup - it is executed by fd -
+	 * but loading it fails on opening the absolute PT_INTERP
+	 * interpreter. Run it in a child so a wrongly successful exec does
+	 * not replace the test image and masquerade as a pass.
+	 */
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		syscall(__NR_execveat, exefd, "", argv, envp, AT_EMPTY_PATH);
+		_exit(errno == EOPNOTSUPP ? FAILFS_EXEC_BLOCKED : 1);
+	}
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), FAILFS_EXEC_BLOCKED);
+}
+
+TEST(fchroot_sentinel_inherited)
+{
+	pid_t pid;
+	int status;
+
+	if (geteuid() != 0)
+		SKIP(return, "privileged fchroot(FD_FAILFS_ROOT) requires CAP_SYS_CHROOT");
+
+	ASSERT_EQ(sys_fchroot(FD_FAILFS_ROOT, 0), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		if (open("/etc", O_PATH) != -1 || errno != EOPNOTSUPP)
+			_exit(1);
+		_exit(0);
+	}
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+}
+
+TEST_HARNESS_MAIN