From: "Michael S. Tsirkin" <mst@redhat.com>
To: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: dev@dpdk.org, huawei.xie@intel.com
Subject: Re: [dpdk-dev] [PATCH 4/6] vhost: workaround stale vring base
Date: Mon, 9 May 2016 15:19:13 +0300 [thread overview]
Message-ID: <20160509151754-mutt-send-email-mst@redhat.com> (raw)
In-Reply-To: <1462603224-29510-5-git-send-email-yuanhan.liu@linux.intel.com>
On Fri, May 06, 2016 at 11:40:22PM -0700, Yuanhan Liu wrote:
> When DPDK app crashes (or quits, or gets killed), and when QEMU supports
> reconnecting (patches have been sent, not merged yet), a restart of DPDK
> app would get stale vring base from QEMU. That would break the kernel
> virtio net completely, making it non-work any more, unless a driver reset
> is done.
>
> So, instead of getting the stale vring base from QEMU, Huawei suggested
> we could get a proper one from used->idx.
>
> Cc: "Michael S. Tsirkin" <mst@redhat.com>
> Suggested-by: "Xie, Huawei" <huawei.xie@intel.com>
> Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
> ---
>
> Note that a right way to handle reconnect from abnormal quit would be
> let the guest driver to initiate a reset when reconnect is detected
> from QEMU. As a reset from the virtio net driver would resets all virtio
> related meta datas, and trigger the vhost-user re-initiation again,
> therefore, it would make the reconnect work as expected.
>
> What's unforunate is that driver reset on reconnect, as the term "driver"
> implies, need driver hackings, which could be a linux kernel virtio net
> driver, DPDK pmd driver, or even, the windows driver. Apparently, it will
> not work so far, or even for a long while, until we are adapted to the
> new kernel.
>
> The fix (or more precisely, the workaround) from this patch would make
> reconnect work in most case, including the following two hypothesis that
> might corrupt virtio memory:
>
> - vring_used_elem might be in stale state when we are in the middle of
> updating used vring. Say, we might have updated the "id" field, but
> leaving "len" untouched.
>
> - vring desc buff might also be in stale state, when we are copying
> data into it.
>
> The reason it still works is that we haven't updated used->idx yet,
> which means guest driver will not start processing those buggy used
> entries. Therefore, no issues.
>
> However, Michael claims some concerns: he made a good point: a crash
> is happening means some memory is corrupted, and it could be the virtio
> memory being corrupted. In such case, nothing will work without the
> reset.
>
> But I would say, that an app in product use would rare crash, and even
> if it crashes, the chance that virtio memory being corrupted would be
> relatively smaller then. Besides that, it would work, say when the app
> is killed by ctrl-c or kill command. So, it works in the most cases.
> But still, I would say it's just a workaround so far.
>
> On the other hand, without this patch, it would be 100% not working
> from abnormal quit. But with this patch, it works in most cases, just
> don't work in a rare case that when virtio memory is corrupted. Therefore,
> I'd say, it is still good to have, until we have a perfect solution.
> ---
> lib/librte_vhost/virtio-net.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
> index c88aaa3..df103aa 100644
> --- a/lib/librte_vhost/virtio-net.c
> +++ b/lib/librte_vhost/virtio-net.c
> @@ -560,6 +560,14 @@ vhost_set_vring_addr(int vid, struct vhost_vring_addr *addr)
> return -1;
> }
>
> + if (vq->last_used_idx != vq->used->idx) {
> + RTE_LOG(WARNING, VHOST_CONFIG,
> + "last_used_idx (%u) and vq->used->idx (%u) mismatch\n",
> + vq->last_used_idx, vq->used->idx);
> + vq->last_used_idx = vq->used->idx;
> + vq->last_used_idx_res = vq->used->idx;
> + }
> +
> vq->log_guest_addr = addr->log_guest_addr;
>
> LOG_DEBUG(VHOST_CONFIG, "(%d) mapped address desc: %p\n",
Acked-by: Michael S. Tsirkin <mst@redhat.com>
And I would go further and just ignore the index coming from QEMU.
dpdk processes packets in order so it does not need it.
> --
> 1.9.0
next prev parent reply other threads:[~2016-05-09 12:19 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-07 6:40 [dpdk-dev] [PATCH 0/6] vhost: add vhost-user client mode and reconnect ability Yuanhan Liu
2016-05-07 6:40 ` [dpdk-dev] [PATCH 1/6] vhost: rename structs for enabling client mode Yuanhan Liu
2016-05-07 6:40 ` [dpdk-dev] [PATCH 2/6] vhost: add vhost-user " Yuanhan Liu
2016-05-09 10:33 ` Victor Kaplansky
2016-05-09 20:33 ` Yuanhan Liu
2016-05-09 20:30 ` Michael S. Tsirkin
2016-05-07 6:40 ` [dpdk-dev] [PATCH 3/6] vhost: add reconnect ability Yuanhan Liu
2016-05-09 16:47 ` Xie, Huawei
2016-05-09 18:12 ` Yuanhan Liu
2016-05-10 7:24 ` Xie, Huawei
2016-05-10 7:54 ` Michael S. Tsirkin
2016-05-10 8:07 ` Xie, Huawei
2016-05-10 8:42 ` Michael S. Tsirkin
2016-05-10 9:00 ` Xie, Huawei
2016-05-10 9:17 ` Michael S. Tsirkin
2016-05-10 17:17 ` Loftus, Ciara
2016-05-11 21:46 ` Michael S. Tsirkin
2016-05-07 6:40 ` [dpdk-dev] [PATCH 4/6] vhost: workaround stale vring base Yuanhan Liu
2016-05-09 10:45 ` Victor Kaplansky
2016-05-09 13:39 ` Xie, Huawei
2016-05-09 18:23 ` Yuanhan Liu
2016-05-09 12:19 ` Michael S. Tsirkin [this message]
2016-05-09 16:25 ` Xie, Huawei
2016-05-09 18:22 ` Yuanhan Liu
2016-06-13 20:47 ` Michael S. Tsirkin
2016-05-10 8:21 ` Xie, Huawei
2016-05-07 6:40 ` [dpdk-dev] [PATCH 5/6] examples/vhost: add client and reconnect option Yuanhan Liu
2016-05-09 10:47 ` Victor Kaplansky
2016-05-07 6:40 ` [dpdk-dev] [PATCH 6/6] vhost: add pmd " Yuanhan Liu
2016-05-09 10:54 ` Victor Kaplansky
2016-05-09 18:26 ` Yuanhan Liu
2016-05-10 3:23 ` [dpdk-dev] [PATCH 0/6] vhost: add vhost-user client mode and reconnect ability Xu, Qian Q
2016-05-10 17:41 ` Yuanhan Liu
2016-05-13 6:16 ` [dpdk-dev] [PATCH v2 " Yuanhan Liu
2016-05-13 6:16 ` [dpdk-dev] [PATCH v2 1/6] vhost: rename structs for enabling client mode Yuanhan Liu
2016-05-13 6:16 ` [dpdk-dev] [PATCH v2 2/6] vhost: add vhost-user " Yuanhan Liu
2016-05-13 6:16 ` [dpdk-dev] [PATCH v2 3/6] vhost: add reconnect ability Yuanhan Liu
2016-05-13 6:16 ` [dpdk-dev] [PATCH v2 4/6] vhost: workaround stale vring base Yuanhan Liu
2016-05-13 6:16 ` [dpdk-dev] [PATCH v2 5/6] examples/vhost: add client and reconnect option Yuanhan Liu
2016-05-13 6:16 ` [dpdk-dev] [PATCH v2 6/6] vhost: add pmd " Yuanhan Liu
2016-05-25 17:45 ` Rich Lane
2016-05-26 8:01 ` Yuanhan Liu
2016-06-07 4:05 ` [dpdk-dev] [PATCH v3 0/6] vhost: add vhost-user client mode and reconnect ability Yuanhan Liu
2016-06-07 4:05 ` [dpdk-dev] [PATCH v3 1/6] vhost: rename structs for enabling client mode Yuanhan Liu
2016-06-07 4:05 ` [dpdk-dev] [PATCH v3 2/6] vhost: add vhost-user " Yuanhan Liu
2016-06-07 4:05 ` [dpdk-dev] [PATCH v3 3/6] vhost: add reconnect ability Yuanhan Liu
2016-06-07 4:05 ` [dpdk-dev] [PATCH v3 4/6] vhost: workaround stale vring base Yuanhan Liu
2016-06-07 4:05 ` [dpdk-dev] [PATCH v3 5/6] examples/vhost: add client option Yuanhan Liu
2016-06-07 4:05 ` [dpdk-dev] [PATCH v3 6/6] vhost: add pmd " Yuanhan Liu
2016-06-14 12:00 ` [dpdk-dev] [PATCH v3 0/6] vhost: add vhost-user client mode and reconnect ability Yuanhan Liu
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=20160509151754-mutt-send-email-mst@redhat.com \
--to=mst@redhat.com \
--cc=dev@dpdk.org \
--cc=huawei.xie@intel.com \
--cc=yuanhan.liu@linux.intel.com \
/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).