[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20100524101709.GA28349@redhat.com>
Date: Mon, 24 May 2010 13:17:10 +0300
From: "Michael S. Tsirkin" <mst@...hat.com>
To: David L Stevens <dlstevens@...ibm.com>
Cc: netdev@...r.kernel.org, kvm@...r.kernel.org
Subject: Re: [PATCH][VHOST] fix race with guest on multi-buffer used buffer
updates
On Thu, May 20, 2010 at 09:58:06AM -0700, David L Stevens wrote:
> [for Michael Tsirkin's vhost development git tree]
>
> This patch fixes a race between guest and host when
> adding used buffers wraps the ring. Without it, guests
> can see partial packets before num_buffers is set in
> the vnet header.
>
> Signed-off-by: David L Stevens <dlstevens@...ibm.com>
Could you please explain what the race is?
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 7f2568d..74790ab 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -1065,14 +1065,6 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
> vq_err(vq, "Failed to write used");
> return -EFAULT;
> }
> - /* Make sure buffer is written before we update index. */
> - smp_wmb();
> - if (put_user(vq->last_used_idx + count, &vq->used->idx)) {
> - vq_err(vq, "Failed to increment used idx");
> - return -EFAULT;
> - }
> - if (unlikely(vq->log_used))
> - vhost_log_used(vq, used);
> vq->last_used_idx += count;
> return 0;
> }
> @@ -1093,7 +1085,17 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
> heads += n;
> count -= n;
> }
> - return __vhost_add_used_n(vq, heads, count);
> + r = __vhost_add_used_n(vq, heads, count);
> +
> + /* Make sure buffer is written before we update index. */
> + smp_wmb();
> + if (put_user(vq->last_used_idx, &vq->used->idx)) {
> + vq_err(vq, "Failed to increment used idx");
> + return -EFAULT;
> + }
> + if (unlikely(vq->log_used))
> + vhost_log_used(vq, vq->used->ring + start);
> + return r;
> }
>
> /* This actually signals the guest, using eventfd. */
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists