[PATCH v4 01/39] task_work: Fix TWA_NMI_CURRENT error handling

It's possible for irq_work_queue() to fail if the work has already been
claimed.  That can happen if a TWA_NMI_CURRENT task work is requested
before a previous TWA_NMI_CURRENT IRQ work on the same CPU has gotten a
chance to run.

The error has to be checked before the write to task->task_works.  Also
the try_cmpxchg() loop isn't needed in NMI context.  The TWA_NMI_CURRENT
case really is special, keep things simple by keeping its code all
together in one place.

Fixes: 466e4d801cd4 ("task_work: Add TWA_NMI_CURRENT as an additional notify mode.")
Signed-off-by: Josh Poimboeuf <[email protected]>
---
 kernel/task_work.c | 39 ++++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/kernel/task_work.c b/kernel/task_work.c
index c969f1f26be5..92024a8bfe12 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -58,25 +58,38 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 	int flags = notify & TWA_FLAGS;
 
 	notify &= ~TWA_FLAGS;
+
 	if (notify == TWA_NMI_CURRENT) {
-		if (WARN_ON_ONCE(task != current))
+		if (WARN_ON_ONCE(!in_nmi() || task != current))
 			return -EINVAL;
 		if (!IS_ENABLED(CONFIG_IRQ_WORK))
 			return -EINVAL;
-	} else {
-		/*
-		 * Record the work call stack in order to print it in KASAN
-		 * reports.
-		 *
-		 * Note that stack allocation can fail if TWAF_NO_ALLOC flag
-		 * is set and new page is needed to expand the stack buffer.
-		 */
-		if (flags & TWAF_NO_ALLOC)
-			kasan_record_aux_stack_noalloc(work);
-		else
-			kasan_record_aux_stack(work);
+#ifdef CONFIG_IRQ_WORK
+		head = task->task_works;
+		if (unlikely(head == &work_exited))
+			return -ESRCH;
+
+		if (!irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)))
+			return -EBUSY;
+
+		work->next = head;
+		task->task_works = work;
+#endif
+		return 0;
 	}
 
+	/*
+	 * Record the work call stack in order to print it in KASAN
+	 * reports.
+	 *
+	 * Note that stack allocation can fail if TWAF_NO_ALLOC flag
+	 * is set and new page is needed to expand the stack buffer.
+	 */
+	if (flags & TWAF_NO_ALLOC)
+		kasan_record_aux_stack_noalloc(work);
+	else
+		kasan_record_aux_stack(work);
+
 	head = READ_ONCE(task->task_works);
 	do {
 		if (unlikely(head == &work_exited))
-- 
2.48.1