From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: stable@dpdk.org, bluca@debian.org, jianfeng.tan@intel.com
Subject: Re: [dpdk-stable] [PATCH v16.11 LTS] vhost-user: fix deadlock in case of NUMA realloc
Date: Wed, 28 Mar 2018 21:46:46 +0200 [thread overview]
Message-ID: <bb8a77e6-1856-fc9b-cf24-f3074b720382@redhat.com> (raw)
In-Reply-To: <20180328194515.7696-1-maxime.coquelin@redhat.com>
Sorry, resent with Kevins's valid address
On 03/28/2018 09:45 PM, Maxime Coquelin wrote:
> Virtqueue's access lock was recently introduced to protect
> the device against async changes.
>
> One problem with the v16.11 backport is that in case of NUMA
> reallocation, the device gets stuck because the old access_lock
> gets unlocked instead of its reallocated copy. On the next
> vhost-user message received, the thread keeps spinning on the
> lock, as it will never be unlocked.
>
> Fixes: ce3b23dc9296 ("vhost: protect active rings from async ring changes")
>
> Cc: stable@dpdk.org
>
> Tested-by: Kevin Traynor <ktraynor@redhat.com>
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
> lib/librte_vhost/vhost_user.c | 12 ++++++++----
> 1 file changed, 8 insertions(+), 4 deletions(-)
>
> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
> index 80348dbf6..eb75e01cb 100644
> --- a/lib/librte_vhost/vhost_user.c
> +++ b/lib/librte_vhost/vhost_user.c
> @@ -249,7 +249,7 @@ numa_realloc(struct virtio_net *dev, int index)
> "Unable to get vq numa information.\n");
> return dev;
> }
> - if (oldnode != newnode) {
> + if (oldnode == newnode) {
> RTE_LOG(INFO, VHOST_CONFIG,
> "reallocate vq from %d to %d node\n", oldnode, newnode);
> vq = rte_malloc_socket(NULL, sizeof(*vq) * VIRTIO_QNUM, 0,
> @@ -269,7 +269,7 @@ numa_realloc(struct virtio_net *dev, int index)
> "Unable to get dev numa information.\n");
> goto out;
> }
> - if (oldnode != newnode) {
> + if (oldnode == newnode) {
> RTE_LOG(INFO, VHOST_CONFIG,
> "reallocate dev from %d to %d node\n",
> oldnode, newnode);
> @@ -327,9 +327,11 @@ qva_to_vva(struct virtio_net *dev, uint64_t qva)
> * This function then converts these to our address space.
> */
> static int
> -vhost_user_set_vring_addr(struct virtio_net *dev, struct vhost_vring_addr *addr)
> +vhost_user_set_vring_addr(struct virtio_net **pdev,
> + struct vhost_vring_addr *addr)
> {
> struct vhost_virtqueue *vq;
> + struct virtio_net *dev = *pdev;
>
> if (dev->mem == NULL)
> return -1;
> @@ -348,6 +350,8 @@ vhost_user_set_vring_addr(struct virtio_net *dev, struct vhost_vring_addr *addr)
> }
>
> dev = numa_realloc(dev, addr->index);
> + *pdev = dev;
> +
> vq = dev->virtqueue[addr->index];
>
> vq->avail = (struct vring_avail *)(uintptr_t)qva_to_vva(dev,
> @@ -1092,7 +1096,7 @@ vhost_user_msg_handler(int vid, int fd)
> vhost_user_set_vring_num(dev, &msg.payload.state);
> break;
> case VHOST_USER_SET_VRING_ADDR:
> - vhost_user_set_vring_addr(dev, &msg.payload.addr);
> + vhost_user_set_vring_addr(&dev, &msg.payload.addr);
> break;
> case VHOST_USER_SET_VRING_BASE:
> vhost_user_set_vring_base(dev, &msg.payload.state);
>
next prev parent reply other threads:[~2018-03-28 19:46 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-28 19:45 Maxime Coquelin
2018-03-28 19:46 ` Maxime Coquelin [this message]
2018-03-28 19:46 Maxime Coquelin
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=bb8a77e6-1856-fc9b-cf24-f3074b720382@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=bluca@debian.org \
--cc=jianfeng.tan@intel.com \
--cc=stable@dpdk.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).