kvm_async_pf_queue_task() can incorrectly remove a node allocated on the
stack of kvm_async_pf_task_wait_schedule(). This occurs when a task
request a PF while another task's PF request with the same token is
still pending. Currently, kvm_async_pf_queue_task() assumes that any
entry in the list is a dummy entry and tries to kfree(). To fix this,
add a dummy flag to the node structure and the function should check
this flag and kfree() only if it is a dummy entry.

Signed-off-by: Ryosuke Yasuoka <ryasuoka@redhat.com>
---
 arch/x86/kernel/kvm.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b67d7c59dca0..2c92ec528379 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -88,6 +88,7 @@ struct kvm_task_sleep_node {
 	struct swait_queue_head wq;
 	u32 token;
 	int cpu;
+	bool dummy;
 };
 
 static struct kvm_task_sleep_head {
@@ -119,10 +120,17 @@ static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
 	raw_spin_lock(&b->lock);
 	e = _find_apf_task(b, token);
 	if (e) {
+		struct kvm_task_sleep_node *dummy = NULL;
+
 		/* dummy entry exist -> wake up was delivered ahead of PF */
-		hlist_del(&e->link);
+		/* Otherwise it should not be freed here. */
+		if (e->dummy) {
+			hlist_del(&e->link);
+			dummy = e;
+		}
+
 		raw_spin_unlock(&b->lock);
-		kfree(e);
+		kfree(dummy);
 		return false;
 	}
 
@@ -230,6 +238,7 @@ static void kvm_async_pf_task_wake(u32 token)
 		}
 		dummy->token = token;
 		dummy->cpu = smp_processor_id();
+		dummy->dummy = true;
 		init_swait_queue_head(&dummy->wq);
 		hlist_add_head(&dummy->link, &b->list);
 		dummy = NULL;

base-commit: 2eba5e05d9bcf4cdea995ed51b0f07ba0275794a
-- 
2.51.0