From: "Xia, Chenbo" <chenbo.xia@intel.com>
To: Eelco Chaudron <echaudro@redhat.com>,
Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: "david.marchand@redhat.com" <david.marchand@redhat.com>,
"dev@dpdk.org" <dev@dpdk.org>
Subject: RE: [PATCH v3 1/4] vhost: change vhost_virtqueue access lock to a read/write one
Date: Thu, 1 Jun 2023 01:45:16 +0000 [thread overview]
Message-ID: <SN6PR11MB350464DBEEAC878BE79D4B299C499@SN6PR11MB3504.namprd11.prod.outlook.com> (raw)
In-Reply-To: <04BFE798-9FA7-4D8F-9360-266946DAD5BC@redhat.com>
> -----Original Message-----
> From: Eelco Chaudron <echaudro@redhat.com>
> Sent: Wednesday, May 31, 2023 7:14 PM
> To: Maxime Coquelin <maxime.coquelin@redhat.com>
> Cc: Xia, Chenbo <chenbo.xia@intel.com>; david.marchand@redhat.com;
> dev@dpdk.org
> Subject: Re: [PATCH v3 1/4] vhost: change vhost_virtqueue access lock to a
> read/write one
>
>
>
> On 31 May 2023, at 11:27, Maxime Coquelin wrote:
>
> > On 5/31/23 08:37, Xia, Chenbo wrote:
> >> Hi Eelco,
> >>
> >>> -----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 1/4] vhost: change vhost_virtqueue access lock to a
> >>> read/write one
> >>>
> >>> This change will allow the vhost interrupt datapath handling to be
> split
> >>> between two processed without one of them holding an explicit lock.
> >>>
> >>> Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
> >>> ---
> >>> lib/eal/include/generic/rte_rwlock.h | 17 ++++++
> >>> lib/vhost/vhost.c | 46 +++++++++--------
> >>> lib/vhost/vhost.h | 4 +-
> >>> lib/vhost/vhost_user.c | 14 +++--
> >>> lib/vhost/virtio_net.c | 90 +++++++++++++++++-------
> -----
> >>> -----
> >>> 5 files changed, 94 insertions(+), 77 deletions(-)
> >>>
> >>> diff --git a/lib/eal/include/generic/rte_rwlock.h
> >>> b/lib/eal/include/generic/rte_rwlock.h
> >>> index 71e2d8d5f4..9e083bbc61 100644
> >>> --- a/lib/eal/include/generic/rte_rwlock.h
> >>> +++ b/lib/eal/include/generic/rte_rwlock.h
> >>> @@ -236,6 +236,23 @@ rte_rwlock_write_unlock(rte_rwlock_t *rwl)
> >>> __atomic_fetch_sub(&rwl->cnt, RTE_RWLOCK_WRITE,
> __ATOMIC_RELEASE);
> >>> }
> >>>
> >>> +/**
> >>> + * Test if the write lock is taken.
> >>> + *
> >>> + * @param rwl
> >>> + * A pointer to a rwlock structure.
> >>> + * @return
> >>> + * 1 if the write lock is currently taken; 0 otherwise.
> >>> + */
> >>> +static inline int
> >>> +rte_rwlock_write_is_locked(rte_rwlock_t *rwl)
> >>> +{
> >>> + if (__atomic_load_n(&rwl->cnt, __ATOMIC_RELAXED) & RTE_RWLOCK_WRITE)
> >>> + return 1;
> >>> +
> >>> + return 0;
> >>> +}
> >>> +
> >>
> >> Again we need to update release note as it's a new EAL API.
> >>
> >>> /**
> >>> * Try to execute critical section in a hardware memory transaction,
> if
> >>> it
> >>> * fails or not available take a read lock
> >>> diff --git a/lib/vhost/vhost.c b/lib/vhost/vhost.c
> >>> index ef37943817..74bdbfd810 100644
> >>> --- a/lib/vhost/vhost.c
> >>> +++ b/lib/vhost/vhost.c
> >>> @@ -393,9 +393,9 @@ free_vq(struct virtio_net *dev, struct
> vhost_virtqueue
> >>> *vq)
> >>> else
> >>> rte_free(vq->shadow_used_split);
> >>>
> >>> - rte_spinlock_lock(&vq->access_lock);
> >>> + rte_rwlock_write_lock(&vq->access_lock);
> >>> vhost_free_async_mem(vq);
> >>> - rte_spinlock_unlock(&vq->access_lock);
> >>> + rte_rwlock_write_unlock(&vq->access_lock);
> >>> rte_free(vq->batch_copy_elems);
> >>> vhost_user_iotlb_destroy(vq);
> >>> rte_free(vq->log_cache);
> >>> @@ -630,7 +630,7 @@ alloc_vring_queue(struct virtio_net *dev, uint32_t
> >>> vring_idx)
> >>>
> >>> dev->virtqueue[i] = vq;
> >>> init_vring_queue(dev, vq, i);
> >>> - rte_spinlock_init(&vq->access_lock);
> >>> + rte_rwlock_init(&vq->access_lock);
> >>> vq->avail_wrap_counter = 1;
> >>> vq->used_wrap_counter = 1;
> >>> vq->signalled_used_valid = false;
> >>> @@ -1305,14 +1305,14 @@ rte_vhost_vring_call(int vid, uint16_t
> vring_idx)
> >>> if (!vq)
> >>> return -1;
> >>>
> >>> - rte_spinlock_lock(&vq->access_lock);
> >>> + rte_rwlock_read_lock(&vq->access_lock);
> >>>
> >>> if (vq_is_packed(dev))
> >>> vhost_vring_call_packed(dev, vq);
> >>> else
> >>> vhost_vring_call_split(dev, vq);
> >>>
> >>> - rte_spinlock_unlock(&vq->access_lock);
> >>> + rte_rwlock_read_unlock(&vq->access_lock);
> >>
> >> Not sure about this. vhost_ring_call_packed/split is changing some
> field in
> >> Vq. Should we use write lock here?
> >
> > I don't think so, the purpose of the access_lock is not to make the
> > datapath threads-safe, but to protect the datapath from metadata changes
> > by the control path.
>
> Thanks Chinbo for the review, and see Maxime’s comment above. Does this
> clarify your concern/question?
Make sense to me. Thanks Eelco and Maxime!
With the release note added:
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
>
> >>
> >> Thanks,
> >> Chenbo
> >>
next prev parent reply other threads:[~2023-06-01 1:45 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 [this message]
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
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=SN6PR11MB350464DBEEAC878BE79D4B299C499@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).