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

Pull kthread vfs updates from Christian Brauner:
 "This stops kernel threads from sharing filesystem state with
  userspace. This work is about 3 cycles old and has been in -next
  for about that time.

  When the kernel boots init_task creates PID 1 and then kthreadd. From
  that point every kthread and PID 1 share the same fs_struct. That is
  why pivot_root() has to rewrite the fs_struct of all kthreads. The
  rewriting exists so that kthreads can use init's filesystem state when
  they want to. It also means userspace can move the ground out from
  under the kernel.

  PID 1 now gets a completely separate fs_struct. All kthreads are
  anchored in a private SB_KERNMOUNT instance of nullfs that cannot be
  mounted on and cannot be used to follow other mounts. Userspace init
  can no longer affect kthread filesystem state and kthreads can no
  longer affect userspace fs state without explicit opting in to that.

  Path lookup from a kthread now fails by default. It makes it
  deliberately hard to offload security sensitive operations into init's
  filesystem state from a kthread.

  Places that legitimately need to look something up there opt in
  through the new scoped_with_init_fs() which temporarily overrides the
  caller's fs_struct with init's. usermodehelpers remain the only kernel
  tasks that genuinely share init's filesystem state, since they execute
  random binaries in the root filesystem (excellent...).

  The visible result is that /proc/2/root is a nullfs with an empty
  mountinfo while /proc/1/root is the real root"

* tag 'vfs-7.3-rc1.kthread' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (26 commits)
  initramfs_test: use test init/exit hooks to override init fs
  fs: stop rewriting paths for PF_EXITING | PF_DUMPCORE
  fs: stop rewriting kthread fs structs
  fs: start all kthreads in nullfs
  nullfs: make nullfs multi-instance
  devtmpfs: create private mount namespace
  fs: add umh argument to struct kernel_clone_args
  fs: stop sharing fs_struct between init_task and pid 1
  af_unix: use scoped_with_init_fs() for coredump socket lookup
  initramfs: use scoped_with_init_fs() for rootfs unpacking
  pnfs/blocklayout: use scoped_with_init_fs() for SCSI device lookup
  ksmbd: use scoped_with_init_fs() for VFS path operations
  ksmbd: use scoped_with_init_fs() for filesystem info path lookup
  ksmbd: use scoped_with_init_fs() for share path resolution
  fs: use scoped_with_init_fs() for kernel_read_file_from_path_initns()
  coredump: use scoped_with_init_fs() for coredump path resolution
  btrfs: use scoped_with_init_fs() for update_dev_time()
  scsi: target: use scoped_with_init_fs() for APTPL metadata
  scsi: target: use scoped_with_init_fs() for ALUA metadata
  crypto: ccp: use scoped_with_init_fs() for SEV file access
  ...

31 files changed, 311 insertions, 116 deletions

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index b1c4ceb65026..aef0fcc6aba1 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -413,7 +413,7 @@ static noinline int __init devtmpfs_setup(void *p)
 {
 	int err;
 
-	err = ksys_unshare(CLONE_NEWNS);
+	err = ksys_unshare(UNSHARE_EMPTY_MNTNS);
 	if (err)
 		goto out;
 	err = init_mount("devtmpfs", "/", "devtmpfs", DEVTMPFS_MFLAGS, NULL);
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index 10e8c438bb43..79c9a5fb418f 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -11,6 +11,7 @@
 
 #include <linux/module.h>
 #include <linux/blkdev.h>
+#include <linux/fs_struct.h>
 
 #include "rnbd-srv.h"
 #include "rnbd-srv-trace.h"
@@ -734,7 +735,8 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 		goto reject;
 	}
 
-	bdev_file = bdev_file_open_by_path(full_path, open_flags, NULL, NULL);
+	scoped_with_init_fs()
+		bdev_file = bdev_file_open_by_path(full_path, open_flags, NULL, NULL);
 	if (IS_ERR(bdev_file)) {
 		ret = PTR_ERR(bdev_file);
 		pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %pe\n",
diff --git a/drivers/char/misc_minor_kunit.c b/drivers/char/misc_minor_kunit.c
index e930c78e1ef9..e85210cbb640 100644
--- a/drivers/char/misc_minor_kunit.c
+++ b/drivers/char/misc_minor_kunit.c
@@ -5,6 +5,7 @@
 #include <linux/miscdevice.h>
 #include <linux/fs.h>
 #include <linux/file.h>
+#include <linux/fs_struct.h>
 #include <linux/init_syscalls.h>
 
 /* static minor (LCD_MINOR) */
@@ -160,18 +161,22 @@ static void __init miscdev_test_can_open(struct kunit *test, struct miscdevice *
 	char *devname;
 
 	devname = kasprintf(GFP_KERNEL, "/dev/%s", misc->name);
-	ret = init_mknod(devname, S_IFCHR | 0600,
-			 new_encode_dev(MKDEV(MISC_MAJOR, misc->minor)));
-	if (ret != 0)
-		KUNIT_FAIL(test, "failed to create node\n");
 
-	filp = filp_open(devname, O_RDONLY, 0);
-	if (IS_ERR(filp))
-		KUNIT_FAIL(test, "failed to open misc device: %ld\n", PTR_ERR(filp));
-	else
-		fput(filp);
+	/* Tests run in a nullfs kthread; borrow the init fs to resolve /dev. */
+	scoped_with_init_fs() {
+		ret = init_mknod(devname, S_IFCHR | 0600,
+				 new_encode_dev(MKDEV(MISC_MAJOR, misc->minor)));
+		if (ret != 0)
+			KUNIT_FAIL(test, "failed to create node\n");
+
+		filp = filp_open(devname, O_RDONLY, 0);
+		if (IS_ERR(filp))
+			KUNIT_FAIL(test, "failed to open misc device: %ld\n", PTR_ERR(filp));
+		else
+			fput(filp);
 
-	init_unlink(devname);
+		init_unlink(devname);
+	}
 	kfree(devname);
 }
 
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index ca473ca198b8..0f72352030ba 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -260,20 +260,16 @@ static int sev_cmd_buffer_len(int cmd)
 
 static struct file *open_file_as_root(const char *filename, int flags, umode_t mode)
 {
-	struct path root __free(path_put) = {};
-
-	task_lock(&init_task);
-	get_fs_root(init_task.fs, &root);
-	task_unlock(&init_task);
-
 	CLASS(prepare_creds, cred)();
 	if (!cred)
 		return ERR_PTR(-ENOMEM);
 
 	cred->fsuid = GLOBAL_ROOT_UID;
 
-	scoped_with_creds(cred)
-		return file_open_root(&root, filename, flags, mode);
+	scoped_with_init_fs() {
+		scoped_with_creds(cred)
+			return filp_open(filename, flags, mode);
+	}
 }
 
 static int sev_read_init_ex_file(void)
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 10250aca5a81..140154d93c43 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -18,6 +18,8 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
+#include <linux/kthread.h>
 #include <scsi/scsi_proto.h>
 #include <linux/unaligned.h>
 
@@ -856,10 +858,17 @@ static int core_alua_write_tpg_metadata(
 	unsigned char *md_buf,
 	u32 md_buf_len)
 {
-	struct file *file = filp_open(path, O_RDWR | O_CREAT | O_TRUNC, 0600);
+	struct file *file;
 	loff_t pos = 0;
 	int ret;
 
+	if (tsk_is_kthread(current)) {
+		scoped_with_init_fs()
+			file = filp_open(path, O_RDWR | O_CREAT | O_TRUNC, 0600);
+	} else {
+		file = filp_open(path, O_RDWR | O_CREAT | O_TRUNC, 0600);
+	}
+
 	if (IS_ERR(file)) {
 		pr_err("filp_open(%s) for ALUA metadata failed\n", path);
 		return -ENODEV;
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 1a77b4bb62b0..25b1bcacc0c8 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -18,6 +18,7 @@
 #include <linux/file.h>
 #include <linux/fcntl.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <scsi/scsi_proto.h>
 #include <linux/unaligned.h>
 
@@ -1969,7 +1970,8 @@ static int __core_scsi3_write_aptpl_to_file(
 	if (!path)
 		return -ENOMEM;
 
-	file = filp_open(path, flags, 0600);
+	scoped_with_init_fs()
+		file = filp_open(path, flags, 0600);
 	if (IS_ERR(file)) {
 		pr_err("filp_open(%s) for APTPL metadata"
 			" failed\n", path);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6eab4cc73ce4..dc5f4a122d55 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -12,6 +12,7 @@
 #include <linux/uuid.h>
 #include <linux/list_sort.h>
 #include <linux/namei.h>
+#include <linux/fs_struct.h>
 #include "misc.h"
 #include "disk-io.h"
 #include "extent-tree.h"
@@ -2125,8 +2126,16 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 static void update_dev_time(const char *device_path)
 {
 	struct path path;
+	int err;
 
-	if (!kern_path(device_path, LOOKUP_FOLLOW, &path)) {
+	if (tsk_is_kthread(current)) {
+		scoped_with_init_fs()
+			err = kern_path(device_path, LOOKUP_FOLLOW, &path);
+	} else {
+		err = kern_path(device_path, LOOKUP_FOLLOW, &path);
+	}
+
+	if (!err) {
 		vfs_utimes(&path, NULL);
 		path_put(&path);
 	}
diff --git a/fs/coredump.c b/fs/coredump.c
index e68a76ff92a3..ac3cd74808c6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -921,15 +921,10 @@ static bool coredump_file(struct core_name *cn, struct coredump_params *cprm,
 		 * with a fully qualified path" rule is to control where
 		 * coredumps may be placed using root privileges,
 		 * current->fs->root must not be used. Instead, use the
-		 * root directory of init_task.
+		 * root directory of PID 1.
 		 */
-		struct path root;
-
-		task_lock(&init_task);
-		get_fs_root(init_task.fs, &root);
-		task_unlock(&init_task);
-		file = file_open_root(&root, cn->corename, open_flags, 0600);
-		path_put(&root);
+		scoped_with_init_fs()
+			file = filp_open(cn->corename, open_flags, 0600);
 	} else {
 		file = filp_open(cn->corename, open_flags, 0600);
 	}
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 394875d06fd6..34699f3b6f88 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -8,6 +8,7 @@
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include "internal.h"
+#include "mount.h"
 
 /*
  * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
@@ -60,8 +61,11 @@ void chroot_fs_refs(const struct path *old_root, const struct path *new_root)
 
 	read_lock(&tasklist_lock);
 	for_each_process_thread(g, p) {
+		if (p->flags & (PF_KTHREAD | PF_EXITING | PF_DUMPCORE))
+			continue;
+
 		task_lock(p);
-		fs = p->fs;
+		fs = p->real_fs;
 		if (fs) {
 			int hits = 0;
 			write_seqlock(&fs->seq);
@@ -89,12 +93,13 @@ void free_fs_struct(struct fs_struct *fs)
 
 void exit_fs(struct task_struct *tsk)
 {
-	struct fs_struct *fs = tsk->fs;
+	struct fs_struct *fs = tsk->real_fs;
 
 	if (fs) {
 		int kill;
 		task_lock(tsk);
 		read_seqlock_excl(&fs->seq);
+		tsk->real_fs = NULL;
 		tsk->fs = NULL;
 		kill = !--fs->users;
 		read_sequnlock_excl(&fs->seq);
@@ -126,7 +131,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 
 int unshare_fs_struct(void)
 {
-	struct fs_struct *fs = current->fs;
+	struct fs_struct *fs = current->real_fs;
 	struct fs_struct *new_fs = copy_fs_struct(fs);
 	int kill;
 
@@ -135,8 +140,10 @@ int unshare_fs_struct(void)
 
 	task_lock(current);
 	read_seqlock_excl(&fs->seq);
+	VFS_WARN_ON_ONCE(fs != current->fs);
 	kill = !--fs->users;
 	current->fs = new_fs;
+	current->real_fs = new_fs;
 	read_sequnlock_excl(&fs->seq);
 	task_unlock(current);
 
@@ -147,9 +154,99 @@ int unshare_fs_struct(void)
 }
 EXPORT_SYMBOL_GPL(unshare_fs_struct);
 
+/*
+ * PID 1 may choose to stop sharing fs_struct state with us.
+ * Either via unshare(CLONE_FS) or unshare(CLONE_NEWNS). Of
+ * course, PID 1 could have chosen to create arbitrary process
+ * trees that all share fs_struct state via CLONE_FS. This is a
+ * strong statement: We only care about PID 1 aka the thread-group
+ * leader so subthread's fs_struct state doesn't matter.
+ *
+ * PID 1 unsharing fs_struct state is a bug. PID 1 relies on
+ * various kthreads to be able to perform work based on its
+ * fs_struct state. Breaking that contract sucks for both sides.
+ * So just don't bother with extra work for this. No sane init
+ * system should ever do this.
+ *
+ * On older kernels if PID 1 unshared its filesystem state with us the
+ * kernel simply used the stale fs_struct state implicitly pinning
+ * anything that PID 1 had last used. Even if PID 1 might've moved on to
+ * some completely different fs_struct state and might've even unmounted
+ * the old root.
+ *
+ * This has hilarious consequences: Think continuing to dump coredump
+ * state into an implicitly pinned directory somewhere. Calling random
+ * binaries in the old rootfs via usermodehelpers.
+ *
+ * Be aggressive about this: We simply reject operating on stale
+ * fs_struct state by reverting to nullfs. Every kworker that does
+ * lookups after this point will fail. Every usermodehelper call will
+ * fail. Tough luck but let's be kind and emit a warning to userspace.
+ */
+static inline void validate_fs_switch(struct fs_struct *old_fs)
+{
+	might_sleep();
+
+	if (likely(current->pid != 1))
+		return;
+	/* @old_fs may be dangling but for comparison it's fine */
+	if (old_fs != userspace_init_fs)
+		return;
+	pr_warn("VFS: Pid 1 stopped sharing filesystem state\n");
+	set_fs_root(userspace_init_fs, &init_fs.root);
+	set_fs_pwd(userspace_init_fs, &init_fs.root);
+}
+
+struct fs_struct *switch_fs_struct(struct fs_struct *new_fs)
+{
+	struct fs_struct *fs;
+
+	scoped_guard(task_lock, current) {
+		fs = current->fs;
+		VFS_WARN_ON_ONCE(fs != current->real_fs);
+		read_seqlock_excl(&fs->seq);
+		current->fs = new_fs;
+		current->real_fs = new_fs;
+		if (--fs->users)
+			new_fs = NULL;
+		else
+			new_fs = fs;
+		read_sequnlock_excl(&fs->seq);
+	}
+
+	validate_fs_switch(fs);
+	return new_fs;
+}
+
 /* to be mentioned only in INIT_TASK */
 struct fs_struct init_fs = {
 	.users		= 1,
 	.seq		= __SEQLOCK_UNLOCKED(init_fs.seq),
 	.umask		= 0022,
 };
+
+struct fs_struct *userspace_init_fs __ro_after_init;
+EXPORT_SYMBOL_GPL(userspace_init_fs);
+
+void __init init_userspace_fs(void)
+{
+	struct mount *m;
+	struct path root;
+
+	/* Move PID 1 from nullfs into the initramfs. */
+	m = topmost_overmount(current->nsproxy->mnt_ns->root);
+	root.mnt = &m->mnt;
+	root.dentry = root.mnt->mnt_root;
+
+	VFS_WARN_ON_ONCE(current->pid != 1);
+
+	set_fs_root(current->fs, &root);
+	set_fs_pwd(current->fs, &root);
+
+	/* Hold a reference for the global pointer. */
+	read_seqlock_excl(&current->fs->seq);
+	current->fs->users++;
+	read_sequnlock_excl(&current->fs->seq);
+
+	userspace_init_fs = current->fs;
+}
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index de32c95d823d..9c2ba9240083 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -150,18 +150,13 @@ ssize_t kernel_read_file_from_path_initns(const char *path, loff_t offset,
 					  enum kernel_read_file_id id)
 {
 	struct file *file;
-	struct path root;
 	ssize_t ret;
 
 	if (!path || !*path)
 		return -EINVAL;
 
-	task_lock(&init_task);
-	get_fs_root(init_task.fs, &root);
-	task_unlock(&init_task);
-
-	file = file_open_root(&root, path, O_RDONLY, 0);
-	path_put(&root);
+	scoped_with_init_fs()
+		file = filp_open(path, O_RDONLY, 0);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 87c365f2f82b..eca22cea4380 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -6184,12 +6184,14 @@ static void __init init_mount_tree(void)
 	struct path root;
 
 	/*
-	 * We create two mounts:
+	 * We create three mounts:
 	 *
 	 * (1) nullfs with mount id 1
 	 * (2) mutable rootfs with mount id 2
+	 * (3) private nullfs for kthreads (SB_KERNMOUNT)
 	 *
-	 * with (2) mounted on top of (1).
+	 * with (2) mounted on top of (1). The init_task's root and pwd
+	 * are pointed at (3) so all kthreads start isolated in nullfs.
 	 */
 	nullfs_mnt = vfs_kern_mount(&nullfs_fs_type, 0, "nullfs", NULL);
 	if (IS_ERR(nullfs_mnt))
@@ -6229,12 +6231,14 @@ static void __init init_mount_tree(void)
 		init_mnt_ns.nr_mounts++;
 	}
 
+	nullfs_mnt = kern_mount(&nullfs_fs_type);
+	if (IS_ERR(nullfs_mnt))
+		panic("VFS: Failed to create private nullfs instance");
+	root.mnt	= nullfs_mnt;
+	root.dentry	= nullfs_mnt->mnt_root;
+
 	init_task.nsproxy->mnt_ns = &init_mnt_ns;
 	get_mnt_ns(&init_mnt_ns);
-
-	/* The root and pwd always point to the mutable rootfs. */
-	root.mnt	= mnt;
-	root.dentry	= mnt->mnt_root;
 	set_fs_pwd(current->fs, &root);
 	set_fs_root(current->fs, &root);
 
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index bb35f88501ce..368d20daf67b 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -4,6 +4,7 @@
  */
 #include <linux/sunrpc/svc.h>
 #include <linux/blkdev.h>
+#include <linux/fs_struct.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_xdr.h>
@@ -363,15 +364,22 @@ static struct file *
 bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 {
 	struct file *bdev_file;
-	const char *devname;
+	const char *devname __free(kfree) = NULL;
 
 	devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN",
 			prefix, v->scsi.designator_len, v->scsi.designator);
 	if (!devname)
 		return ERR_PTR(-ENOMEM);
 
-	bdev_file = bdev_file_open_by_path(devname,
-			BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
+	if (tsk_is_kthread(current)) {
+		scoped_with_init_fs()
+			bdev_file = bdev_file_open_by_path(devname,
+					BLK_OPEN_READ | BLK_OPEN_WRITE,
+					NULL, NULL);
+	} else {
+		bdev_file = bdev_file_open_by_path(devname,
+				BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
+	}
 	if (IS_ERR(bdev_file)) {
 		dprintk("failed to open device %s (%ld)\n",
 			devname, PTR_ERR(bdev_file));
@@ -380,7 +388,6 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 			file_bdev(bdev_file)->bd_disk->disk_name);
 	}
 
-	kfree(devname);
 	return bdev_file;
 }
 
diff --git a/fs/nullfs.c b/fs/nullfs.c
index fdbd3e5d3d71..c6f5b9493e26 100644
--- a/fs/nullfs.c
+++ b/fs/nullfs.c
@@ -40,14 +40,9 @@ static int nullfs_fs_fill_super(struct super_block *s, struct fs_context *fc)
 	return 0;
 }
 
-/*
- * For now this is a single global instance. If needed we can make it
- * mountable by userspace at which point we will need to make it
- * multi-instance.
- */
 static int nullfs_fs_get_tree(struct fs_context *fc)
 {
-	return get_tree_single(fc, nullfs_fs_fill_super);
+	return get_tree_nodev(fc, nullfs_fs_fill_super);
 }
 
 static const struct fs_context_operations nullfs_fs_context_ops = {
@@ -57,9 +52,8 @@ static const struct fs_context_operations nullfs_fs_context_ops = {
 static int nullfs_init_fs_context(struct fs_context *fc)
 {
 	fc->ops		= &nullfs_fs_context_ops;
-	fc->global	= true;
-	fc->sb_flags	= SB_NOUSER;
-	fc->s_iflags	= SB_I_NOEXEC | SB_I_NODEV;
+	fc->sb_flags	|= SB_NOUSER;
+	fc->s_iflags	|= SB_I_NOEXEC | SB_I_NODEV;
 	return 0;
 }
 
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 479ea8cb4ef4..f6f75d206762 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -168,8 +168,8 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	cred = get_task_cred(p);
 
 	task_lock(p);
-	if (p->fs)
-		umask = p->fs->umask;
+	if (p->real_fs)
+		umask = p->real_fs->umask;
 	if (p->files)
 		max_fds = files_fdtable(p->files)->max_fds;
 	task_unlock(p);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 780f81259052..6a39de424f62 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -211,8 +211,8 @@ static int get_task_root(struct task_struct *task, struct path *root)
 	int result = -ENOENT;
 
 	task_lock(task);
-	if (task->fs) {
-		get_fs_root(task->fs, root);
+	if (task->real_fs) {
+		get_fs_root(task->real_fs, root);
 		result = 0;
 	}
 	task_unlock(task);
@@ -225,8 +225,8 @@ static int proc_cwd_link(struct dentry *dentry, struct path *path,
 	int result = -ENOENT;
 
 	task_lock(task);
-	if (task->fs) {
-		get_fs_pwd(task->fs, path);
+	if (task->real_fs) {
+		get_fs_pwd(task->real_fs, path);
 		result = 0;
 	}
 	task_unlock(task);
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 5c555db68aa2..036356c0a55b 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -254,13 +254,13 @@ static int mounts_open_common(struct inode *inode, struct file *file,
 	}
 	ns = nsp->mnt_ns;
 	get_mnt_ns(ns);
-	if (!task->fs) {
+	if (!task->real_fs) {
 		task_unlock(task);
 		put_task_struct(task);
 		ret = -ENOENT;
 		goto err_put_ns;
 	}
-	get_fs_root(task->fs, &root);
+	get_fs_root(task->real_fs, &root);
 	task_unlock(task);
 	put_task_struct(task);
 
diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c
index 6f97f8d39657..e00aee155935 100644
--- a/fs/smb/server/mgmt/share_config.c
+++ b/fs/smb/server/mgmt/share_config.c
@@ -9,6 +9,7 @@
 #include <linux/rwsem.h>
 #include <linux/parser.h>
 #include <linux/namei.h>
+#include <linux/fs_struct.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 
@@ -193,7 +194,8 @@ static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work,
 				goto out;
 			}
 
-			ret = kern_path(share->path, 0, &share->vfs_path);
+			scoped_with_init_fs()
+				ret = kern_path(share->path, 0, &share->vfs_path);
 			ksmbd_revert_fsids(work);
 			if (ret) {
 				ksmbd_debug(SMB, "failed to access '%s'\n",
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 76f63f9adc72..d092709734e2 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -9,6 +9,7 @@
 #include <net/addrconf.h>
 #include <linux/syscalls.h>
 #include <linux/namei.h>
+#include <linux/fs_struct.h>
 #include <linux/statfs.h>
 #include <linux/ethtool.h>
 #include <linux/falloc.h>
@@ -5949,7 +5950,8 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 	if (!share->path)
 		return -EIO;
 
-	rc = kern_path(share->path, LOOKUP_NO_SYMLINKS, &path);
+	scoped_with_init_fs()
+		rc = kern_path(share->path, LOOKUP_NO_SYMLINKS, &path);
 	if (rc) {
 		pr_err("cannot create vfs path\n");
 		return -EIO;
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index d324585c0566..e493725c3fe3 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -7,6 +7,7 @@
 #include <crypto/sha2.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/filelock.h>
 #include <linux/uaccess.h>
 #include <linux/backing-dev.h>
@@ -67,8 +68,9 @@ static int ksmbd_vfs_path_lookup(struct ksmbd_share_config *share_conf,
 	}
 
 	CLASS(filename_kernel, filename)(pathname);
-	err = vfs_path_parent_lookup(filename, flags, path, &last,
-				     root_share_path);
+	scoped_with_init_fs()
+		err = vfs_path_parent_lookup(filename, flags, path, &last,
+					     root_share_path);
 	if (err)
 		return err;
 
@@ -623,7 +625,8 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname,
 	if (ksmbd_override_fsids(work))
 		return -ENOMEM;
 
-	err = kern_path(oldname, LOOKUP_NO_SYMLINKS, &oldpath);
+	scoped_with_init_fs()
+		err = kern_path(oldname, LOOKUP_NO_SYMLINKS, &oldpath);
 	if (err) {
 		pr_err("cannot get linux path for %s, err = %d\n",
 		       oldname, err);
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 0070764b790a..97eef8d3863d 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -6,6 +6,7 @@
 #include <linux/path.h>
 #include <linux/spinlock.h>
 #include <linux/seqlock.h>
+#include <linux/vfsdebug.h>
 
 struct fs_struct {
 	int users;
@@ -16,6 +17,7 @@ struct fs_struct {
 } __randomize_layout;
 
 extern struct kmem_cache *fs_cachep;
+extern struct fs_struct *userspace_init_fs;
 
 extern void exit_fs(struct task_struct *);
 extern void set_fs_root(struct fs_struct *, const struct path *);
@@ -40,6 +42,8 @@ static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd)
 	read_sequnlock_excl(&fs->seq);
 }
 
+struct fs_struct *switch_fs_struct(struct fs_struct *new_fs);
+
 extern bool current_chrooted(void);
 
 static inline int current_umask(void)
@@ -47,4 +51,34 @@ static inline int current_umask(void)
 	return current->fs->umask;
 }
 
+/*
+ * Temporarily use userspace_init_fs for path resolution in kthreads.
+ * Callers should use scoped_with_init_fs() which automatically
+ * restores the original fs_struct at scope exit.
+ */
+static inline struct fs_struct *__override_init_fs(void)
+{
+	struct fs_struct *old_fs;
+
+	old_fs = current->fs;
+	WRITE_ONCE(current->fs, userspace_init_fs);
+	return old_fs;
+}
+
+static inline void __revert_init_fs(struct fs_struct *old_fs)
+{
+	VFS_WARN_ON_ONCE(current->fs != userspace_init_fs);
+	WRITE_ONCE(current->fs, old_fs);
+}
+
+DEFINE_CLASS(__override_init_fs,
+	     struct fs_struct *,
+	     __revert_init_fs(_T),
+	     __override_init_fs(), void)
+
+#define scoped_with_init_fs() \
+	scoped_class(__override_init_fs, __UNIQUE_ID(label))
+
+void __init init_userspace_fs(void);
+
 #endif /* _LINUX_FS_STRUCT_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index a6cb241ea00c..61536be773f5 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -24,6 +24,7 @@
 
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
+extern struct fs_struct *userspace_init_fs;
 extern struct nsproxy init_nsproxy;
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 373bcc0598d1..1e4136c2b2a3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1191,6 +1191,7 @@ struct task_struct {
 	unsigned long			last_switch_time;
 #endif
 	/* Filesystem information: */
+	struct fs_struct		*real_fs;
 	struct fs_struct		*fs;
 
 	/* Open file information: */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 41ed884cffc9..e0c1ca8c6a18 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -31,6 +31,7 @@ struct kernel_clone_args {
 	u32 io_thread:1;
 	u32 user_worker:1;
 	u32 no_files:1;
+	u32 umh:1;
 	unsigned long stack;
 	unsigned long stack_size;
 	unsigned long tls;
diff --git a/init/init_task.c b/init/init_task.c
index b67ef6040a65..ba5c2523f7e0 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -162,6 +162,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 	RCU_POINTER_INITIALIZER(cred, &init_cred),
 	.comm		= INIT_TASK_COMM,
 	.thread		= INIT_THREAD,
+	.real_fs	= &init_fs,
 	.fs		= &init_fs,
 	.files		= &init_files,
 #ifdef CONFIG_IO_URING
diff --git a/init/initramfs.c b/init/initramfs.c
index 20a18fcda48e..4e27b97a8844 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -6,6 +6,7 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/hex.h>
 #include <linux/init.h>
 #include <linux/init_syscalls.h>
@@ -716,7 +717,7 @@ static void __init populate_initrd_image(char *err)
 }
 #endif /* CONFIG_BLK_DEV_RAM */
 
-static void __init do_populate_rootfs(void *unused, async_cookie_t cookie)
+static void __init unpack_initramfs(async_cookie_t cookie)
 {
 	/* Load the built in initramfs */
 	char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
@@ -724,7 +725,7 @@ static void __init do_populate_rootfs(void *unused, async_cookie_t cookie)
 		panic_show_mem("%s", err); /* Failed to decompress INTERNAL initramfs */
 
 	if (!initrd_start || IS_ENABLED(CONFIG_INITRAMFS_FORCE))
-		goto done;
+		return;
 
 	if (IS_ENABLED(CONFIG_BLK_DEV_RAM))
 		printk(KERN_INFO "Trying to unpack rootfs image as initramfs...\n");
@@ -739,9 +740,14 @@ static void __init do_populate_rootfs(void *unused, async_cookie_t cookie)
 		printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err);
 #endif
 	}
+}
 
-done:
-	security_initramfs_populated();
+static void __init do_populate_rootfs(void *unused, async_cookie_t cookie)
+{
+	scoped_with_init_fs() {
+		unpack_initramfs(cookie);
+		security_initramfs_populated();
+	}
 
 	/*
 	 * If the initrd region is overlapped with crashkernel reserved region,
diff --git a/init/initramfs_test.c b/init/initramfs_test.c
index bc55306d226d..9cf316c13ffa 100644
--- a/init/initramfs_test.c
+++ b/init/initramfs_test.c
@@ -3,6 +3,7 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/init.h>
 #include <linux/init_syscalls.h>
 #include <linux/initrd.h>
@@ -562,7 +563,7 @@ static struct kunit_case __refdata initramfs_test_cases[] = {
 	{},
 };
 
-static int __init initramfs_test_init(struct kunit_suite *suite)
+static int __init initramfs_suite_init(struct kunit_suite *suite)
 {
 	/*
 	 * unpack_to_rootfs() uses module-static state (victim, byte_count,
@@ -574,9 +575,23 @@ static int __init initramfs_test_init(struct kunit_suite *suite)
 	return 0;
 }
 
+/* Tests run in a nullfs kthread; always use the init fs for path resolution. */
+static int __init initramfs_test_init(struct kunit *test)
+{
+	test->priv = __override_init_fs();
+	return 0;
+}
+
+static void __init initramfs_test_exit(struct kunit *test)
+{
+	__revert_init_fs(test->priv);
+}
+
 static struct kunit_suite __refdata initramfs_test_suite = {
 	.name = "initramfs",
-	.suite_init = initramfs_test_init,
+	.suite_init = initramfs_suite_init,
+	.init = initramfs_test_init,
+	.exit = initramfs_test_exit,
 	.test_cases = initramfs_test_cases,
 };
 kunit_test_init_section_suites(&initramfs_test_suite);
diff --git a/init/main.c b/init/main.c
index e363232b428b..92d34e496a33 100644
--- a/init/main.c
+++ b/init/main.c
@@ -103,6 +103,7 @@
 #include <linux/stackdepot.h>
 #include <linux/randomize_kstack.h>
 #include <linux/pidfs.h>
+#include <linux/fs_struct.h>
 #include <linux/ptdump.h>
 #include <linux/time_namespace.h>
 #include <linux/unaligned.h>
@@ -670,6 +671,11 @@ static __initdata DECLARE_COMPLETION(kthreadd_done);
 
 static noinline void __ref __noreturn rest_init(void)
 {
+	struct kernel_clone_args init_args = {
+		.flags		= (CLONE_VM | CLONE_UNTRACED),
+		.fn		= kernel_init,
+		.fn_arg		= NULL,
+	};
 	struct task_struct *tsk;
 	int pid;
 
@@ -679,7 +685,7 @@ static noinline void __ref __noreturn rest_init(void)
 	 * the init task will end up wanting to create kthreads, which, if
 	 * we schedule it before we create kthreadd, will OOPS.
 	 */
-	pid = user_mode_thread(kernel_init, NULL, CLONE_FS);
+	pid = kernel_clone(&init_args);
 	/*
 	 * Pin init on the boot CPU. Task migration is not properly working
 	 * until sched_init_smp() has been run. It will set the allowed
@@ -1540,6 +1546,8 @@ static int __ref kernel_init(void *unused)
 {
 	int ret;
 
+	init_userspace_fs();
+
 	/*
 	 * Wait until kthreadd is all set-up.
 	 */
diff --git a/kernel/fork.c b/kernel/fork.c
index f0e2e131a9a5..94e021eabf1d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1618,9 +1618,27 @@ static int copy_exec_state(u64 clone_flags, struct task_struct *tsk)
 	return task_exec_state_copy(tsk);
 }
 
-static int copy_fs(u64 clone_flags, struct task_struct *tsk)
+static int copy_fs(u64 clone_flags, struct task_struct *tsk, bool umh)
 {
-	struct fs_struct *fs = current->fs;
+	struct fs_struct *fs;
+
+	/*
+	 * Usermodehelper may copy userspace_init_fs filesystem state but
+	 * they don't get to create mount namespaces, share the
+	 * filesystem state, or be started from a non-initial mount
+	 * namespace.
+	 */
+	if (umh) {
+		if (clone_flags & (CLONE_NEWNS | CLONE_FS))
+			return -EINVAL;
+		if (current->nsproxy->mnt_ns != &init_mnt_ns)
+			return -EINVAL;
+		fs = userspace_init_fs;
+	} else {
+		fs = current->fs;
+		VFS_WARN_ON_ONCE(current->fs != current->real_fs);
+	}
+
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
 		read_seqlock_excl(&fs->seq);
@@ -1633,7 +1651,7 @@ static int copy_fs(u64 clone_flags, struct task_struct *tsk)
 		read_sequnlock_excl(&fs->seq);
 		return 0;
 	}
-	tsk->fs = copy_fs_struct(fs);
+	tsk->real_fs = tsk->fs = copy_fs_struct(fs);
 	if (!tsk->fs)
 		return -ENOMEM;
 	return 0;
@@ -2277,7 +2295,7 @@ __latent_entropy struct task_struct *copy_process(
 	retval = copy_files(clone_flags, p, args->no_files);
 	if (retval)
 		goto bad_fork_cleanup_semundo;
-	retval = copy_fs(clone_flags, p);
+	retval = copy_fs(clone_flags, p, args->umh);
 	if (retval)
 		goto bad_fork_cleanup_files;
 	retval = copy_sighand(clone_flags, p);
@@ -2819,6 +2837,7 @@ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.exit_signal	= (flags & CSIGNAL),
 		.fn		= fn,
 		.fn_arg		= arg,
+		.umh		= 1,
 	};
 
 	return kernel_clone(&args);
@@ -3216,7 +3235,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
  */
 int ksys_unshare(unsigned long unshare_flags)
 {
-	struct fs_struct *fs, *new_fs = NULL;
+	struct fs_struct *new_fs = NULL;
 	struct files_struct *new_fd = NULL;
 	struct cred *new_cred = NULL;
 	struct nsproxy *new_nsproxy = NULL;
@@ -3247,6 +3266,10 @@ int ksys_unshare(unsigned long unshare_flags)
 	if (unshare_flags & CLONE_NEWNS)
 		unshare_flags |= CLONE_FS;
 
+	/* No unsharing with overriden fs state */
+	VFS_WARN_ON_ONCE(unshare_flags & (CLONE_NEWNS | CLONE_FS) &&
+			 current->fs != current->real_fs);
+
 	err = check_unshare_flags(unshare_flags);
 	if (err)
 		goto bad_unshare_out;
@@ -3294,23 +3317,13 @@ int ksys_unshare(unsigned long unshare_flags)
 			new_nsproxy = NULL;
 		}
 
-		task_lock(current);
+		if (new_fs)
+			new_fs = switch_fs_struct(new_fs);
 
-		if (new_fs) {
-			fs = current->fs;
-			read_seqlock_excl(&fs->seq);
-			current->fs = new_fs;
-			if (--fs->users)
-				new_fs = NULL;
-			else
-				new_fs = fs;
-			read_sequnlock_excl(&fs->seq);
-		}
-
-		if (new_fd)
+		if (new_fd) {
+			guard(task_lock)(current);
 			swap(current->files, new_fd);
-
-		task_unlock(current);
+		}
 
 		if (new_cred) {
 			/* Install the new user namespace */
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 7c1a65bd5f8d..76476aeee067 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -186,7 +186,7 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 		ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES);
 		break;
 	case KCMP_FS:
-		ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS);
+		ret = kcmp_ptr(task1->real_fs, task2->real_fs, KCMP_FS);
 		break;
 	case KCMP_SIGHAND:
 		ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND);
diff --git a/kernel/umh.c b/kernel/umh.c
index 48117c569e1a..6e2c7bb315c6 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -71,10 +71,8 @@ static int call_usermodehelper_exec_async(void *data)
 	spin_unlock_irq(&current->sighand->siglock);
 
 	/*
-	 * Initial kernel threads share ther FS with init, in order to
-	 * get the init root directory. But we've now created a new
-	 * thread that is going to execve a user process and has its own
-	 * 'struct fs_struct'. Reset umask to the default.
+	 * Usermodehelper threads get a copy of userspace init's
+	 * fs_struct. Reset umask to the default.
 	 */
 	current->fs->umask = 0022;
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 10ed9421e43a..7794740fa80f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1197,17 +1197,12 @@ static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len,
 	unix_mkname_bsd(sunaddr, addr_len);
 
 	if (flags & SOCK_COREDUMP) {
-		struct path root;
-
-		task_lock(&init_task);
-		get_fs_root(init_task.fs, &root);
-		task_unlock(&init_task);
-
-		scoped_with_kernel_creds()
-			err = vfs_path_lookup(root.dentry, root.mnt, sunaddr->sun_path,
-					      LOOKUP_BENEATH | LOOKUP_NO_SYMLINKS |
-					      LOOKUP_NO_MAGICLINKS, &path);
-		path_put(&root);
+		scoped_with_init_fs() {
+			scoped_with_kernel_creds()
+				err = kern_path(sunaddr->sun_path,
+						LOOKUP_NO_SYMLINKS |
+						LOOKUP_NO_MAGICLINKS, &path);
+		}
 		if (err)
 			goto fail;
 	} else {