kvm_async_pf_queue_task() can incorrectly try to kfree() a node
allocated on the stack of kvm_async_pf_task_wait_schedule().

This occurs when a task requests a PF while another task's PF request
with the same token is still pending. Since the token is derived from
the (u32)address in exc_page_fault(), two different tasks can generate
the same token.

Currently, kvm_async_pf_queue_task() assumes that any entry found in the
list is a dummy entry and tries to kfree() it. To fix this, add a flag
to the node structure to distinguish stack-allocated nodes, and only
kfree() the node if it is a dummy entry.

Signed-off-by: Ryosuke Yasuoka <ryasuoka@redhat.com>
---

v2:
Based on Vitaly's comment,
* Update comment in kvm_async_pf_queue_task
* Set n->dummy false in kvm_async_pf_queue_task
* Add explanation about what token is in commit message.

v1:
https://lore.kernel.org/all/87cy4vlmv8.fsf@redhat.com/


 arch/x86/kernel/kvm.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index df78ddee0abb..37dc8465e0f5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -89,6 +89,7 @@ struct kvm_task_sleep_node {
 	struct swait_queue_head wq;
 	u32 token;
 	int cpu;
+	bool dummy;
 };
 
 static struct kvm_task_sleep_head {
@@ -120,15 +121,26 @@ 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) {
-		/* dummy entry exist -> wake up was delivered ahead of PF */
-		hlist_del(&e->link);
+		struct kvm_task_sleep_node *dummy = NULL;
+
+		/*
+		 * The entry can either be a 'dummy' entry (which is put on the
+		 * list when wake-up happens ahead of APF handling completion)
+		 * or a token from another task which should not be touched.
+		 */
+		if (e->dummy) {
+			hlist_del(&e->link);
+			dummy = e;
+		}
+
 		raw_spin_unlock(&b->lock);
-		kfree(e);
+		kfree(dummy);
 		return false;
 	}
 
 	n->token = token;
 	n->cpu = smp_processor_id();
+	n->dummy = false;
 	init_swait_queue_head(&n->wq);
 	hlist_add_head(&n->link, &b->list);
 	raw_spin_unlock(&b->lock);
@@ -231,6 +243,7 @@ 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: 416f99c3b16f582a3fc6d64a1f77f39d94b76de5
-- 
2.52.0

Ryosuke Yasuoka <ryasuoka@redhat.com> writes:

> kvm_async_pf_queue_task() can incorrectly try to kfree() a node
> allocated on the stack of kvm_async_pf_task_wait_schedule().
>
> This occurs when a task requests a PF while another task's PF request
> with the same token is still pending. Since the token is derived from
> the (u32)address in exc_page_fault(), two different tasks can generate
> the same token.
>
> Currently, kvm_async_pf_queue_task() assumes that any entry found in the
> list is a dummy entry and tries to kfree() it. To fix this, add a flag
> to the node structure to distinguish stack-allocated nodes, and only
> kfree() the node if it is a dummy entry.
>
> Signed-off-by: Ryosuke Yasuoka <ryasuoka@redhat.com>
> ---
>
> v2:
> Based on Vitaly's comment,
> * Update comment in kvm_async_pf_queue_task
> * Set n->dummy false in kvm_async_pf_queue_task
> * Add explanation about what token is in commit message.
>
> v1:
> https://lore.kernel.org/all/87cy4vlmv8.fsf@redhat.com/
>
>
>  arch/x86/kernel/kvm.c | 19 ++++++++++++++++---
>  1 file changed, 16 insertions(+), 3 deletions(-)
>
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index df78ddee0abb..37dc8465e0f5 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -89,6 +89,7 @@ struct kvm_task_sleep_node {
>  	struct swait_queue_head wq;
>  	u32 token;
>  	int cpu;
> +	bool dummy;
>  };
>  
>  static struct kvm_task_sleep_head {
> @@ -120,15 +121,26 @@ 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) {
> -		/* dummy entry exist -> wake up was delivered ahead of PF */
> -		hlist_del(&e->link);
> +		struct kvm_task_sleep_node *dummy = NULL;
> +
> +		/*
> +		 * The entry can either be a 'dummy' entry (which is put on the
> +		 * list when wake-up happens ahead of APF handling completion)
> +		 * or a token from another task which should not be touched.
> +		 */
> +		if (e->dummy) {
> +			hlist_del(&e->link);
> +			dummy = e;
> +		}
> +
>  		raw_spin_unlock(&b->lock);
> -		kfree(e);
> +		kfree(dummy);
>  		return false;
>  	}
>  
>  	n->token = token;
>  	n->cpu = smp_processor_id();
> +	n->dummy = false;
>  	init_swait_queue_head(&n->wq);
>  	hlist_add_head(&n->link, &b->list);
>  	raw_spin_unlock(&b->lock);
> @@ -231,6 +243,7 @@ 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: 416f99c3b16f582a3fc6d64a1f77f39d94b76de5

Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>

-- 
Vitaly