kthread: Don't allocate kthread_struct for init and umh

If kthread_is_per_cpu runs concurrently with free_kthread_struct the
kthread_struct that was just freed may be read from.

This bug was introduced by commit 40966e316f86 ("kthread: Ensure
struct kthread is present for all kthreads").  When kthread_struct
started to be allocated for all tasks that have PF_KTHREAD set.  This
in turn required the kthread_struct to be freed in kernel_execve and
violated the assumption that kthread_struct will have the same
lifetime as the task.

Looking a bit deeper this only applies to callers of kernel_execve
which is just the init process and the user mode helper processes.
These processes really don't want to be kernel threads but are for
historical reasons.  Mostly that copy_thread does not know how to take
a kernel mode function to the process with for processes without
PF_KTHREAD or PF_IO_WORKER set.

Solve this by not allocating kthread_struct for the init process and
the user mode helper processes.

This is done by adding a kthread member to struct kernel_clone_args.
Setting kthread in fork_idle and kernel_thread.  Adding
user_mode_thread that works like kernel_thread except it does not set
kthread.  In fork only allocating the kthread_struct if .kthread is set.

I have looked at kernel/kthread.c and since commit 40966e316f86
("kthread: Ensure struct kthread is present for all kthreads") there
have been no assumptions added that to_kthread or __to_kthread will
not return NULL.

There are a few callers of to_kthread or __to_kthread that assume a
non-NULL struct kthread pointer will be returned.  These functions are
kthread_data(), kthread_parmme(), kthread_exit(), kthread(),
kthread_park(), kthread_unpark(), kthread_stop().  All of those functions
can reasonably expected to be called when it is know that a task is a
kthread so that assumption seems reasonable.

Cc: stable@vger.kernel.org
Fixes: 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads")
Reported-by: Максим Кутявин <maximkabox13@gmail.com>
Link: https://lkml.kernel.org/r/20220506141512.516114-1-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

2 files changed, 23 insertions, 5 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 9796897560ab..27c5203750b4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2157,7 +2157,7 @@ static __latent_entropy struct task_struct *copy_process(
 	p->io_context = NULL;
 	audit_set_context(p, NULL);
 	cgroup_fork(p);
-	if (p->flags & PF_KTHREAD) {
+	if (args->kthread) {
 		if (!set_kthread_struct(p))
 			goto bad_fork_cleanup_delayacct;
 	}
@@ -2548,7 +2548,8 @@ struct task_struct * __init fork_idle(int cpu)
 {
 	struct task_struct *task;
 	struct kernel_clone_args args = {
-		.flags = CLONE_VM,
+		.flags		= CLONE_VM,
+		.kthread	= 1,
 	};
 
 	task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args);
@@ -2686,6 +2687,23 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
 		.stack		= (unsigned long)fn,
 		.stack_size	= (unsigned long)arg,
+		.kthread	= 1,
+	};
+
+	return kernel_clone(&args);
+}
+
+/*
+ * Create a user mode thread.
+ */
+pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags)
+{
+	struct kernel_clone_args args = {
+		.flags		= ((lower_32_bits(flags) | CLONE_VM |
+				    CLONE_UNTRACED) & ~CSIGNAL),
+		.exit_signal	= (lower_32_bits(flags) & CSIGNAL),
+		.stack		= (unsigned long)fn,
+		.stack_size	= (unsigned long)arg,
 	};
 
 	return kernel_clone(&args);
diff --git a/kernel/umh.c b/kernel/umh.c
index 36c123360ab8..b989736e8707 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -132,7 +132,7 @@ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info)
 
 	/* If SIGCLD is ignored do_wait won't populate the status. */
 	kernel_sigaction(SIGCHLD, SIG_DFL);
-	pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
+	pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
 	if (pid < 0)
 		sub_info->retval = pid;
 	else
@@ -171,8 +171,8 @@ static void call_usermodehelper_exec_work(struct work_struct *work)
 		 * want to pollute current->children, and we need a parent
 		 * that always ignores SIGCHLD to ensure auto-reaping.
 		 */
-		pid = kernel_thread(call_usermodehelper_exec_async, sub_info,
-				    CLONE_PARENT | SIGCHLD);
+		pid = user_mode_thread(call_usermodehelper_exec_async, sub_info,
+				       CLONE_PARENT | SIGCHLD);
 		if (pid < 0) {
 			sub_info->retval = pid;
 			umh_complete(sub_info);