From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: Changpeng Liu <changpeng.liu@intel.com>, dev@dpdk.org
Cc: Chenbo Xia <chenbo.xia@intel.com>,
David Marchand <david.marchand@redhat.com>
Subject: Re: [PATCH v2] vhost: add new `rte_vhost_vring_call_nonblock` API
Date: Thu, 13 Oct 2022 09:56:46 +0200 [thread overview]
Message-ID: <db846225-e807-360e-733a-14b98df5dfad@redhat.com> (raw)
In-Reply-To: <20221012064007.56040-1-changpeng.liu@intel.com>
Hi Changpeng,
On 10/12/22 08:40, Changpeng Liu wrote:
> Vhost-user library locks all VQ's access lock when processing
> vring based messages, such as SET_VRING_KICK and SET_VRING_CALL,
> and the data processing thread may already be started, e.g: SPDK
> vhost-blk and vhost-scsi will start the data processing thread
> when one vring is ready, then deadlock may happen when SPDK is
> posting interrupts to VM. Here, we add a new API which allows
> caller to try again later for this case.
>
> Bugzilla ID: 1015
> Fixes: c5736998305d ("vhost: fix missing virtqueue lock protection")
>
> Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
> ---
> lib/vhost/rte_vhost.h | 15 +++++++++++++++
> lib/vhost/version.map | 3 +++
> lib/vhost/vhost.c | 30 ++++++++++++++++++++++++++++++
> 3 files changed, 48 insertions(+)
>
> diff --git a/lib/vhost/rte_vhost.h b/lib/vhost/rte_vhost.h
> index bb7d86a432..d22b25cd4e 100644
> --- a/lib/vhost/rte_vhost.h
> +++ b/lib/vhost/rte_vhost.h
> @@ -909,6 +909,21 @@ rte_vhost_clr_inflight_desc_packed(int vid, uint16_t vring_idx,
> */
> int rte_vhost_vring_call(int vid, uint16_t vring_idx);
>
> +/**
> + * Notify the guest that used descriptors have been added to the vring. This
> + * function acts as a memory barrier. This function will return -EAGAIN when
> + * vq's access lock is held by other thread, user should try again later.
> + *
> + * @param vid
> + * vhost device ID
> + * @param vring_idx
> + * vring index
> + * @return
> + * 0 on success, -1 on failure, -EAGAIN for another retry
> + */
> +__rte_experimental
> +int rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx);
> +
> /**
> * Get vhost RX queue avail count.
> *
> diff --git a/lib/vhost/version.map b/lib/vhost/version.map
> index 7a00b65740..c8c44b8326 100644
> --- a/lib/vhost/version.map
> +++ b/lib/vhost/version.map
> @@ -94,6 +94,9 @@ EXPERIMENTAL {
> rte_vhost_async_try_dequeue_burst;
> rte_vhost_driver_get_vdpa_dev_type;
> rte_vhost_clear_queue;
> +
> + # added in 22.11
> + rte_vhost_vring_call_nonblock;
> };
>
> INTERNAL {
> diff --git a/lib/vhost/vhost.c b/lib/vhost/vhost.c
> index 8740aa2788..ed6efb003f 100644
> --- a/lib/vhost/vhost.c
> +++ b/lib/vhost/vhost.c
> @@ -1317,6 +1317,36 @@ rte_vhost_vring_call(int vid, uint16_t vring_idx)
> return 0;
> }
>
> +int
> +rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx)
> +{
> + struct virtio_net *dev;
> + struct vhost_virtqueue *vq;
> +
> + dev = get_device(vid);
> + if (!dev)
> + return -1;
> +
> + if (vring_idx >= VHOST_MAX_VRING)
> + return -1;
> +
> + vq = dev->virtqueue[vring_idx];
> + if (!vq)
> + return -1;
> +
> + if (!rte_spinlock_trylock(&vq->access_lock))
> + return -EAGAIN;
> +
> + if (vq_is_packed(dev))
> + vhost_vring_call_packed(dev, vq);
> + else
> + vhost_vring_call_split(dev, vq);
> +
> + rte_spinlock_unlock(&vq->access_lock);
> +
> + return 0;
> +}
> +
> uint16_t
> rte_vhost_avail_entries(int vid, uint16_t queue_id)
> {
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Thanks,
Maxime
next prev parent reply other threads:[~2022-10-13 7:57 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-06 2:22 [PATCH] vhost: use try_lock in rte_vhost_vring_call Changpeng Liu
2022-09-06 21:15 ` Stephen Hemminger
2022-09-07 0:40 ` Liu, Changpeng
2022-09-20 7:12 ` Maxime Coquelin
2022-09-20 2:24 ` Xia, Chenbo
2022-09-20 2:34 ` Liu, Changpeng
2022-09-20 2:53 ` Xia, Chenbo
2022-09-20 3:00 ` Liu, Changpeng
2022-09-20 7:23 ` Maxime Coquelin
2022-09-20 7:30 ` Maxime Coquelin
2022-09-20 7:19 ` Maxime Coquelin
2022-09-20 7:29 ` Liu, Changpeng
2022-09-20 7:34 ` Maxime Coquelin
2022-09-20 7:45 ` Liu, Changpeng
2022-09-20 8:12 ` Maxime Coquelin
2022-09-20 8:43 ` Liu, Changpeng
2022-09-21 9:41 ` Maxime Coquelin
2022-09-21 9:52 ` Liu, Changpeng
2022-10-11 11:56 ` Maxime Coquelin
2022-10-12 6:40 ` [PATCH v2] vhost: add new `rte_vhost_vring_call_nonblock` API Changpeng Liu
2022-10-13 7:56 ` Maxime Coquelin [this message]
2022-10-17 6:46 ` Xia, Chenbo
2022-10-17 7:17 ` Liu, Changpeng
2022-10-17 7:14 ` [PATCH v3] " Changpeng Liu
2022-10-17 7:39 ` Xia, Chenbo
2022-10-17 7:50 ` Liu, Changpeng
2022-10-17 7:48 ` [PATCH v4] " Changpeng Liu
2022-10-19 5:27 ` Xia, Chenbo
2022-10-26 9:24 ` Xia, Chenbo
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=db846225-e807-360e-733a-14b98df5dfad@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=changpeng.liu@intel.com \
--cc=chenbo.xia@intel.com \
--cc=david.marchand@redhat.com \
--cc=dev@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).