From: Jason Wang <jasowang@redhat.com>
To: Stefano Garzarella <sgarzare@redhat.com>, netdev@vger.kernel.org
Cc: kvm@vger.kernel.org, virtualization@lists.linux-foundation.org,
Stefan Hajnoczi <stefanha@redhat.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 1/3] vsock/virtio: use RCU to avoid use-after-free on the_virtio_vsock
Date: Wed, 3 Jul 2019 17:53:58 +0800 [thread overview]
Message-ID: <05311244-ed23-d061-a620-7b83d83c11f5@redhat.com> (raw)
In-Reply-To: <20190628123659.139576-2-sgarzare@redhat.com>
On 2019/6/28 下午8:36, Stefano Garzarella wrote:
> Some callbacks used by the upper layers can run while we are in the
> .remove(). A potential use-after-free can happen, because we free
> the_virtio_vsock without knowing if the callbacks are over or not.
>
> To solve this issue we move the assignment of the_virtio_vsock at the
> end of .probe(), when we finished all the initialization, and at the
> beginning of .remove(), before to release resources.
> For the same reason, we do the same also for the vdev->priv.
>
> We use RCU to be sure that all callbacks that use the_virtio_vsock
> ended before freeing it. This is not required for callbacks that
> use vdev->priv, because after the vdev->config->del_vqs() we are sure
> that they are ended and will no longer be invoked.
>
> We also take the mutex during the .remove() to avoid that .probe() can
> run while we are resetting the device.
>
> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
> ---
> net/vmw_vsock/virtio_transport.c | 67 +++++++++++++++++++++-----------
> 1 file changed, 44 insertions(+), 23 deletions(-)
>
> diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
> index 9c287e3e393c..7ad510ec12e0 100644
> --- a/net/vmw_vsock/virtio_transport.c
> +++ b/net/vmw_vsock/virtio_transport.c
> @@ -65,19 +65,22 @@ struct virtio_vsock {
> u32 guest_cid;
> };
>
> -static struct virtio_vsock *virtio_vsock_get(void)
> -{
> - return the_virtio_vsock;
> -}
> -
> static u32 virtio_transport_get_local_cid(void)
> {
> - struct virtio_vsock *vsock = virtio_vsock_get();
> + struct virtio_vsock *vsock;
> + u32 ret;
>
> - if (!vsock)
> - return VMADDR_CID_ANY;
> + rcu_read_lock();
> + vsock = rcu_dereference(the_virtio_vsock);
> + if (!vsock) {
> + ret = VMADDR_CID_ANY;
> + goto out_rcu;
> + }
>
> - return vsock->guest_cid;
> + ret = vsock->guest_cid;
> +out_rcu:
> + rcu_read_unlock();
> + return ret;
> }
>
> static void virtio_transport_loopback_work(struct work_struct *work)
> @@ -197,14 +200,18 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
> struct virtio_vsock *vsock;
> int len = pkt->len;
>
> - vsock = virtio_vsock_get();
> + rcu_read_lock();
> + vsock = rcu_dereference(the_virtio_vsock);
> if (!vsock) {
> virtio_transport_free_pkt(pkt);
> - return -ENODEV;
> + len = -ENODEV;
> + goto out_rcu;
> }
>
> - if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid)
> - return virtio_transport_send_pkt_loopback(vsock, pkt);
> + if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) {
> + len = virtio_transport_send_pkt_loopback(vsock, pkt);
> + goto out_rcu;
> + }
>
> if (pkt->reply)
> atomic_inc(&vsock->queued_replies);
> @@ -214,6 +221,9 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt)
> spin_unlock_bh(&vsock->send_pkt_list_lock);
>
> queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
> +
> +out_rcu:
> + rcu_read_unlock();
> return len;
> }
>
> @@ -222,12 +232,14 @@ virtio_transport_cancel_pkt(struct vsock_sock *vsk)
> {
> struct virtio_vsock *vsock;
> struct virtio_vsock_pkt *pkt, *n;
> - int cnt = 0;
> + int cnt = 0, ret;
> LIST_HEAD(freeme);
>
> - vsock = virtio_vsock_get();
> + rcu_read_lock();
> + vsock = rcu_dereference(the_virtio_vsock);
> if (!vsock) {
> - return -ENODEV;
> + ret = -ENODEV;
> + goto out_rcu;
> }
>
> spin_lock_bh(&vsock->send_pkt_list_lock);
> @@ -255,7 +267,11 @@ virtio_transport_cancel_pkt(struct vsock_sock *vsk)
> queue_work(virtio_vsock_workqueue, &vsock->rx_work);
> }
>
> - return 0;
> + ret = 0;
> +
> +out_rcu:
> + rcu_read_unlock();
> + return ret;
> }
>
> static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
> @@ -590,8 +606,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
> vsock->rx_buf_max_nr = 0;
> atomic_set(&vsock->queued_replies, 0);
>
> - vdev->priv = vsock;
> - the_virtio_vsock = vsock;
> mutex_init(&vsock->tx_lock);
> mutex_init(&vsock->rx_lock);
> mutex_init(&vsock->event_lock);
> @@ -613,6 +627,9 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
> virtio_vsock_event_fill(vsock);
> mutex_unlock(&vsock->event_lock);
>
> + vdev->priv = vsock;
> + rcu_assign_pointer(the_virtio_vsock, vsock);
You probably need to use rcu_dereference_protected() to access
the_virtio_vsock in the function in order to survive from sparse.
> +
> mutex_unlock(&the_virtio_vsock_mutex);
> return 0;
>
> @@ -627,6 +644,12 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
> struct virtio_vsock *vsock = vdev->priv;
> struct virtio_vsock_pkt *pkt;
>
> + mutex_lock(&the_virtio_vsock_mutex);
> +
> + vdev->priv = NULL;
> + rcu_assign_pointer(the_virtio_vsock, NULL);
This is still suspicious, can we access the_virtio_vsock through
vdev->priv? If yes, we may still get use-after-free since it was not
protected by RCU.
Another more interesting question, I believe we will do singleton for
virtio_vsock structure. Then what's the point of using vdev->priv to
access the_virtio_vsock? It looks to me we can it brings extra troubles
for doing synchronization.
Thanks
> + synchronize_rcu();
> +
> flush_work(&vsock->loopback_work);
> flush_work(&vsock->rx_work);
> flush_work(&vsock->tx_work);
> @@ -666,12 +689,10 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
> }
> spin_unlock_bh(&vsock->loopback_list_lock);
>
> - mutex_lock(&the_virtio_vsock_mutex);
> - the_virtio_vsock = NULL;
> - mutex_unlock(&the_virtio_vsock_mutex);
> -
> vdev->config->del_vqs(vdev);
>
> + mutex_unlock(&the_virtio_vsock_mutex);
> +
> kfree(vsock);
> }
>
next prev parent reply other threads:[~2019-07-03 9:54 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-28 12:36 [PATCH v2 0/3] vsock/virtio: several fixes in the .probe() and .remove() Stefano Garzarella
2019-06-28 12:36 ` [PATCH v2 1/3] vsock/virtio: use RCU to avoid use-after-free on the_virtio_vsock Stefano Garzarella
2019-07-01 14:54 ` Stefan Hajnoczi
2019-07-01 15:10 ` Stefan Hajnoczi
2019-07-03 9:53 ` Jason Wang [this message]
2019-07-03 10:41 ` Stefano Garzarella
2019-07-04 3:58 ` Jason Wang
2019-07-04 9:20 ` Stefano Garzarella
2019-07-05 0:18 ` Jason Wang
2019-07-04 10:17 ` Stefan Hajnoczi
2019-06-28 12:36 ` [PATCH v2 2/3] vsock/virtio: stop workers during the .remove() Stefano Garzarella
2019-07-04 4:00 ` Jason Wang
2019-06-28 12:36 ` [PATCH v2 3/3] vsock/virtio: fix flush of works " Stefano Garzarella
2019-07-01 15:08 ` Stefan Hajnoczi
2019-07-01 15:09 ` Stefan Hajnoczi
2019-07-01 15:11 ` [PATCH v2 0/3] vsock/virtio: several fixes in the .probe() and .remove() Stefan Hajnoczi
2019-07-01 17:03 ` Stefano Garzarella
2019-07-03 9:14 ` Stefan Hajnoczi
2019-07-03 10:07 ` Stefano Garzarella
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=05311244-ed23-d061-a620-7b83d83c11f5@redhat.com \
--to=jasowang@redhat.com \
--cc=davem@davemloft.net \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=sgarzare@redhat.com \
--cc=stefanha@redhat.com \
--cc=virtualization@lists.linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).