diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index c0f71f2e7160c5c0d46472df141fd8d3d7be498b..ef02be869cf286e4d710bad9c2c9ab30cd743750 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -31,6 +31,7 @@ struct kernel_clone_args {
 	/* Number of elements in *set_tid */
 	size_t set_tid_size;
 	int cgroup;
+	int io_thread;
 	struct cgroup *cgrp;
 	struct css_set *cset;
 };
@@ -82,6 +83,7 @@ extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
 extern pid_t kernel_clone(struct kernel_clone_args *kargs);
+struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/kernel/fork.c b/kernel/fork.c
index d66cd1014211b92de6e9f881089175395845265c..d3171e8e88e5d4af93ab1fa21a2dfe4c41b67292 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1940,6 +1940,8 @@ static __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
+	if (args->io_thread)
+		p->flags |= PF_IO_WORKER;
 
 	/*
 	 * This _must_ happen before we call free_task(), i.e. before we jump
@@ -2410,6 +2412,34 @@ struct mm_struct *copy_init_mm(void)
 	return dup_mm(NULL, &init_mm);
 }
 
+/*
+ * This is like kernel_clone(), but shaved down and tailored to just
+ * creating io_uring workers. It returns a created task, or an error pointer.
+ * The returned task is inactive, and the caller must fire it up through
+ * wake_up_new_task(p). All signals are blocked in the created task.
+ */
+struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
+{
+	unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD|
+				CLONE_IO;
+	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,
+		.io_thread	= 1,
+	};
+	struct task_struct *tsk;
+
+	tsk = copy_process(NULL, 0, node, &args);
+	if (!IS_ERR(tsk)) {
+		sigfillset(&tsk->blocked);
+		sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
+	}
+	return tsk;
+}
+
 /*
  *  Ok, this is the main fork-routine.
  *