From: "Xia, Chenbo" <chenbo.xia@intel.com>
To: Eelco Chaudron <echaudro@redhat.com>,
"maxime.coquelin@redhat.com" <maxime.coquelin@redhat.com>,
"david.marchand@redhat.com" <david.marchand@redhat.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: RE: [PATCH v3 2/4] vhost: make the guest_notifications statistic counter atomic
Date: Wed, 31 May 2023 07:03:54 +0000 [thread overview]
Message-ID: <SN6PR11MB3504AB4DDAD4D6332390D6DE9C489@SN6PR11MB3504.namprd11.prod.outlook.com> (raw)
In-Reply-To: <168431453456.558450.8798179744539843068.stgit@ebuild.local>
> -----Original Message-----
> From: Eelco Chaudron <echaudro@redhat.com>
> Sent: Wednesday, May 17, 2023 5:09 PM
> To: maxime.coquelin@redhat.com; Xia, Chenbo <chenbo.xia@intel.com>;
> david.marchand@redhat.com
> Cc: dev@dpdk.org
> Subject: [PATCH v3 2/4] vhost: make the guest_notifications statistic
> counter atomic
>
> Making the guest_notifications statistic counter atomic, allows
> it to be safely incremented while holding the read access_lock.
>
> Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
> ---
> lib/vhost/vhost.c | 8 ++++++++
> lib/vhost/vhost.h | 9 ++++++---
> 2 files changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/lib/vhost/vhost.c b/lib/vhost/vhost.c
> index 74bdbfd810..8ff6434c93 100644
> --- a/lib/vhost/vhost.c
> +++ b/lib/vhost/vhost.c
> @@ -2086,6 +2086,10 @@ rte_vhost_vring_stats_get(int vid, uint16_t
> queue_id,
>
> rte_rwlock_write_lock(&vq->access_lock);
> for (i = 0; i < VHOST_NB_VQ_STATS; i++) {
> + /*
> + * No need to the read atomic counters as such, due to the
> + * above write access_lock preventing them to be updated.
> + */
> stats[i].value =
> *(uint64_t *)(((char *)vq) +
> vhost_vq_stat_strings[i].offset);
> stats[i].id = i;
> @@ -2112,6 +2116,10 @@ int rte_vhost_vring_stats_reset(int vid, uint16_t
> queue_id)
> vq = dev->virtqueue[queue_id];
>
> rte_rwlock_write_lock(&vq->access_lock);
> + /*
> + * No need to the reset atomic counters as such, due to the
> + * above write access_lock preventing them to be updated.
> + */
> memset(&vq->stats, 0, sizeof(vq->stats));
> rte_rwlock_write_unlock(&vq->access_lock);
>
> diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h
> index 5c939ef06f..37609c7c8d 100644
> --- a/lib/vhost/vhost.h
> +++ b/lib/vhost/vhost.h
> @@ -135,11 +135,12 @@ struct virtqueue_stats {
> uint64_t broadcast;
> /* Size bins in array as RFC 2819, undersized [0], 64 [1], etc */
> uint64_t size_bins[8];
> - uint64_t guest_notifications;
> uint64_t iotlb_hits;
> uint64_t iotlb_misses;
> uint64_t inflight_submitted;
> uint64_t inflight_completed;
> + /* Counters below are atomic, and should be incremented as such. */
> + uint64_t guest_notifications;
> };
>
> /**
> @@ -907,7 +908,8 @@ vhost_vring_call_split(struct virtio_net *dev, struct
> vhost_virtqueue *vq)
> unlikely(!signalled_used_valid)) {
> eventfd_write(vq->callfd, (eventfd_t) 1);
> if (dev->flags & VIRTIO_DEV_STATS_ENABLED)
> - vq->stats.guest_notifications++;
> + __atomic_fetch_add(&vq->stats.guest_notifications,
> + 1, __ATOMIC_RELAXED);
> if (dev->notify_ops->guest_notified)
> dev->notify_ops->guest_notified(dev->vid);
> }
> @@ -917,7 +919,8 @@ vhost_vring_call_split(struct virtio_net *dev, struct
> vhost_virtqueue *vq)
> && (vq->callfd >= 0)) {
> eventfd_write(vq->callfd, (eventfd_t)1);
> if (dev->flags & VIRTIO_DEV_STATS_ENABLED)
> - vq->stats.guest_notifications++;
> + __atomic_fetch_add(&vq->stats.guest_notifications,
> + 1, __ATOMIC_RELAXED);
> if (dev->notify_ops->guest_notified)
> dev->notify_ops->guest_notified(dev->vid);
> }
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
next prev parent reply other threads:[~2023-05-31 7:04 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-17 9:08 [PATCH v3 0/4] vhost: add device op to offload the interrupt kick Eelco Chaudron
2023-05-17 9:08 ` [PATCH v3 1/4] vhost: change vhost_virtqueue access lock to a read/write one Eelco Chaudron
2023-05-17 17:33 ` Maxime Coquelin
2023-05-18 14:46 ` Eelco Chaudron
2023-05-31 6:37 ` Xia, Chenbo
2023-05-31 9:27 ` Maxime Coquelin
2023-05-31 11:13 ` Eelco Chaudron
2023-06-01 1:45 ` Xia, Chenbo
2023-05-17 9:08 ` [PATCH v3 2/4] vhost: make the guest_notifications statistic counter atomic Eelco Chaudron
2023-05-30 12:52 ` Maxime Coquelin
2023-05-31 7:03 ` Xia, Chenbo [this message]
2023-05-17 9:09 ` [PATCH v3 3/4] vhost: fix invalid call FD handling Eelco Chaudron
2023-05-30 12:54 ` Maxime Coquelin
2023-05-31 6:12 ` Xia, Chenbo
2023-05-31 9:30 ` Maxime Coquelin
2023-05-17 9:09 ` [PATCH v3 4/4] vhost: add device op to offload the interrupt kick Eelco Chaudron
2023-05-30 13:02 ` Maxime Coquelin
2023-05-30 13:16 ` Thomas Monjalon
2023-05-30 15:16 ` Maxime Coquelin
2023-05-31 6:19 ` Xia, Chenbo
2023-05-31 9:29 ` Maxime Coquelin
2023-05-31 11:21 ` Eelco Chaudron
2023-06-01 2:18 ` Xia, Chenbo
2023-06-01 8:15 ` Eelco Chaudron
2023-06-01 8:29 ` Maxime Coquelin
2023-06-01 8:49 ` Eelco Chaudron
2023-06-01 8:53 ` Maxime Coquelin
2023-05-31 11:49 ` David Marchand
2023-05-31 12:01 ` David Marchand
2023-05-31 12:48 ` Maxime Coquelin
2023-05-31 13:13 ` Eelco Chaudron
2023-05-31 14:12 ` David Marchand
2023-05-31 14:18 ` Maxime Coquelin
2023-06-01 20:00 ` [PATCH v3 0/4] " Maxime Coquelin
2023-06-02 6:20 ` Eelco Chaudron
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=SN6PR11MB3504AB4DDAD4D6332390D6DE9C489@SN6PR11MB3504.namprd11.prod.outlook.com \
--to=chenbo.xia@intel.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=echaudro@redhat.com \
--cc=maxime.coquelin@redhat.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).