Change userspace_init_fs from a declared-but-unused extern struct to
a dynamically initialized pointer. Add init_userspace_fs() which is
called early in kernel_init() (PID 1) to record PID 1's fs_struct
as the canonical userspace filesystem state.

Wire up __override_init_fs() and __revert_init_fs() to actually swap
current->fs to/from userspace_init_fs. Previously these were no-ops
that stored current->fs back to itself.

Fix nullfs_userspace_init() to compare against userspace_init_fs
instead of &init_fs. When PID 1 unshares its filesystem state, revert
userspace_init_fs to init_fs's root (nullfs) so that stale filesystem
state is not silently inherited by kworkers and usermodehelpers.

At this stage PID 1's fs still points to rootfs (set by
init_mount_tree), so userspace_init_fs points to rootfs and
scoped_with_init_fs() is functionally equivalent to its previous no-op
behavior.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fs_struct.c            | 48 ++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/fs_struct.h | 15 ++++++++-------
 include/linux/init_task.h |  1 +
 init/main.c               |  3 +++
 4 files changed, 59 insertions(+), 8 deletions(-)

diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index c03a574ed65a..f44e43ce6d93 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.
@@ -163,15 +164,34 @@ EXPORT_SYMBOL_GPL(unshare_fs_struct);
  * 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 != &init_fs)
+	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)
@@ -201,3 +221,29 @@ struct fs_struct init_fs = {
 	.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/include/linux/fs_struct.h b/include/linux/fs_struct.h
index e11d0e57168f..97eef8d3863d 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -17,6 +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 *);
@@ -57,17 +58,17 @@ static inline int current_umask(void)
  */
 static inline struct fs_struct *__override_init_fs(void)
 {
-	struct fs_struct *fs;
+	struct fs_struct *old_fs;
 
-	fs = current->fs;
-	WRITE_ONCE(current->fs, fs);
-	return fs;
+	old_fs = current->fs;
+	WRITE_ONCE(current->fs, userspace_init_fs);
+	return old_fs;
 }
 
-static inline void __revert_init_fs(struct fs_struct *revert_fs)
+static inline void __revert_init_fs(struct fs_struct *old_fs)
 {
-	VFS_WARN_ON_ONCE(current->fs != revert_fs);
-	WRITE_ONCE(current->fs, revert_fs);
+	VFS_WARN_ON_ONCE(current->fs != userspace_init_fs);
+	WRITE_ONCE(current->fs, old_fs);
 }
 
 DEFINE_CLASS(__override_init_fs,
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/init/main.c b/init/main.c
index 1cb395dd94e4..5ccc642a5aa7 100644
--- a/init/main.c
+++ b/init/main.c
@@ -102,6 +102,7 @@
 #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>
@@ -1574,6 +1575,8 @@ static int __ref kernel_init(void *unused)
 {
 	int ret;
 
+	init_userspace_fs();
+
 	/*
 	 * Wait until kthreadd is all set-up.
 	 */

-- 
2.47.3