task_work: Add TWA_NMI_CURRENT as an additional notify mode.

Adding task_work from NMI context requires the following:
- The kasan_record_aux_stack() is not NMU safe and must be avoided.
- Using TWA_RESUME is NMI safe. If the NMI occurs while the CPU is in
  userland then it will continue in userland and not invoke the `work'
  callback.

Add TWA_NMI_CURRENT as an additional notify mode. In this mode skip
kasan and use irq_work in hardirq-mode to for needed interrupt. Set
TIF_NOTIFY_RESUME within the irq_work callback due to k[ac]san
instrumentation in test_and_set_bit() which does not look NMI safe in
case of a report.

Suggested-by: Peter Zijlstra <[email protected]>
Signed-off-by: Sebastian Andrzej Siewior <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: Sebastian Andrzej Siewior

include/linux/task_work.h

@@ -18,6 +18,7 @@ enum task_work_notify_mode {
 	TWA_RESUME,
 	TWA_SIGNAL,
 	TWA_SIGNAL_NO_IPI,
+	TWA_NMI_CURRENT,
 };
 
 static inline bool task_work_pending(struct task_struct *task)

kernel/task_work.c

@@ -1,18 +1,26 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/irq_work.h>
 #include <linux/spinlock.h>
 #include <linux/task_work.h>
 #include <linux/resume_user_mode.h>
 
 static struct callback_head work_exited; /* all we need is ->next == NULL */
 
+static void task_work_set_notify_irq(struct irq_work *entry)
+{
+	test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+}
+static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) =
+	IRQ_WORK_INIT_HARD(task_work_set_notify_irq);
+
 /**
  * task_work_add - ask the @task to execute @work->func()
  * @task: the task which should run the callback
  * @work: the callback to run
  * @notify: how to notify the targeted task
  *
  * Queue @work for task_work_run() below and notify the @task if @notify
- * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI.
+ * is @TWA_RESUME, @TWA_SIGNAL, @TWA_SIGNAL_NO_IPI or @TWA_NMI_CURRENT.
  *
  * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted
  * task and run the task_work, regardless of whether the task is currently
@@ -24,6 +32,8 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * kernel anyway.
  * @TWA_RESUME work is run only when the task exits the kernel and returns to
  * user mode, or before entering guest mode.
+ * @TWA_NMI_CURRENT works like @TWA_RESUME, except it can only be used for the
+ * current @task and if the current context is NMI.
  *
  * Fails if the @task is exiting/exited and thus it can't process this @work.
  * Otherwise @work->func() will be called when the @task goes through one of
@@ -44,8 +54,13 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 {
 	struct callback_head *head;
 
-	/* record the work call stack in order to print it in KASAN reports */
-	kasan_record_aux_stack(work);
+	if (notify == TWA_NMI_CURRENT) {
+		if (WARN_ON_ONCE(task != current))
+			return -EINVAL;
+	} else {
+		/* record the work call stack in order to print it in KASAN reports */
+		kasan_record_aux_stack(work);
+	}
 
 	head = READ_ONCE(task->task_works);
 	do {
@@ -66,6 +81,9 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 	case TWA_SIGNAL_NO_IPI:
 		__set_notify_signal(task);
 		break;
+	case TWA_NMI_CURRENT:
+		irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume));
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;