fs: add real_fs to track task's actual fs_struct

Add a real_fs field to task_struct that always mirrors the fs field.
This lays the groundwork for distinguishing between a task's permanent
fs_struct and one that is temporarily overridden via scoped_with_init_fs().

When a kthread temporarily overrides current->fs for path lookup, we
need to know the original fs_struct for operations like exit_fs() and
unshare_fs_struct() that must operate on the real, permanent fs.

For now real_fs is always equal to fs. It is maintained alongside fs in
all the relevant paths: exit_fs(), unshare_fs_struct(),
switch_fs_struct(), and copy_fs().

Link: https://patch.msgid.link/20260601-work-kthread-nullfs-v4-4-77ee053060e0@kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

fs/fs_struct.c

@@ -61,7 +61,7 @@ void chroot_fs_refs(const struct path *old_root, const struct path *new_root)
 	read_lock(&tasklist_lock);
 	for_each_process_thread(g, p) {
 		task_lock(p);
-		fs = p->fs;
+		fs = p->real_fs;
 		if (fs) {
 			int hits = 0;
 			write_seqlock(&fs->seq);
@@ -89,12 +89,13 @@ 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 +127,7 @@ 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 +136,10 @@ 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);
 
@@ -177,8 +180,10 @@ struct fs_struct *switch_fs_struct(struct fs_struct *new_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

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);

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);

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);
 

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: */

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

kernel/fork.c

@@ -1616,6 +1616,8 @@ static int copy_exec_state(u64 clone_flags, struct task_struct *tsk)
 static int copy_fs(u64 clone_flags, struct task_struct *tsk)
 {
 	struct fs_struct *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);
@@ -1628,7 +1630,7 @@ 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;
@@ -3246,6 +3248,10 @@ 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;

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);