Merge tag 'kthread-cleanups-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull kthread updates from Eric Biederman:
 "This updates init and user mode helper tasks to be ordinary user mode
  tasks.

  Commit 40966e316f86 ("kthread: Ensure struct kthread is present for
  all kthreads") caused init and the user mode helper threads that call
  kernel_execve to have struct kthread allocated for them. This struct
  kthread going away during execve in turned made a use after free of
  struct kthread possible.

  Here, commit 343f4c49f243 ("kthread: Don't allocate kthread_struct for
  init and umh") is enough to fix the use after free and is simple
  enough to be backportable.

  The rest of the changes pass struct kernel_clone_args to clean things
  up and cause the code to make sense.

  In making init and the user mode helpers tasks purely user mode tasks
  I ran into two complications. The function task_tick_numa was
  detecting tasks without an mm by testing for the presence of
  PF_KTHREAD. The initramfs code in populate_initrd_image was using
  flush_delayed_fput to ensuere the closing of all it's file descriptors
  was complete, and flush_delayed_fput does not work in a userspace
  thread.

  I have looked and looked and more complications and in my code review
  I have not found any, and neither has anyone else with the code
  sitting in linux-next"

* tag 'kthread-cleanups-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  sched: Update task_tick_numa to ignore tasks without an mm
  fork: Stop allowing kthreads to call execve
  fork: Explicitly set PF_KTHREAD
  init: Deal with the init process being a user mode process
  fork: Generalize PF_IO_WORKER handling
  fork: Explicity test for idle tasks in copy_thread
  fork: Pass struct kernel_clone_args into copy_thread
  kthread: Don't allocate kthread_struct for init and umh

3 files changed, 42 insertions, 12 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 124829ed0163..9d44f2d46c69 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1982,7 +1982,7 @@ static __latent_entropy struct task_struct *copy_process(
 	struct task_struct *p;
 	struct multiprocess_signals delayed;
 	struct file *pidfile = NULL;
-	u64 clone_flags = args->flags;
+	const u64 clone_flags = args->flags;
 	struct nsproxy *nsp = current->nsproxy;
 
 	/*
@@ -2071,6 +2071,9 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
+	p->flags &= ~PF_KTHREAD;
+	if (args->kthread)
+		p->flags |= PF_KTHREAD;
 	if (args->io_thread) {
 		/*
 		 * Mark us an IO worker, and block any signal that isn't
@@ -2160,7 +2163,7 @@ 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;
 	}
@@ -2243,7 +2246,7 @@ static __latent_entropy struct task_struct *copy_process(
 	retval = copy_io(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls);
+	retval = copy_thread(p, args);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
@@ -2547,11 +2550,21 @@ static inline void init_idle_pids(struct task_struct *idle)
 	}
 }
 
+static int idle_dummy(void *dummy)
+{
+	/* This function is never called */
+	return 0;
+}
+
 struct task_struct * __init fork_idle(int cpu)
 {
 	struct task_struct *task;
 	struct kernel_clone_args args = {
-		.flags = CLONE_VM,
+		.flags		= CLONE_VM,
+		.fn		= &idle_dummy,
+		.fn_arg		= NULL,
+		.kthread	= 1,
+		.idle		= 1,
 	};
 
 	task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args);
@@ -2582,8 +2595,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
 		.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,
+		.fn		= fn,
+		.fn_arg		= arg,
 		.io_thread	= 1,
 	};
 
@@ -2687,8 +2700,25 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.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,
+		.fn		= fn,
+		.fn_arg		= 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),
+		.fn		= fn,
+		.fn_arg		= arg,
 	};
 
 	return kernel_clone(&args);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8c5b74f66bd3..77b2048a9326 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2927,7 +2927,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 	/*
 	 * We don't care about NUMA placement if we don't have memory.
 	 */
-	if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
+	if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
 		return;
 
 	/*
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);