From: "Michael S. Tsirkin" <mst@redhat.com>
To: Jason Wang <jasowang@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>,
kvm@vger.kernel.org, virtualization@lists.linux-foundation.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
davem@davemloft.net
Subject: Re: [RFC PATCH V3 1/5] vhost: generalize adding used elem
Date: Mon, 7 Jan 2019 09:50:19 -0500 [thread overview]
Message-ID: <20190107094739-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <9111a7a2-8396-d866-449e-11ee4008f988@redhat.com>
On Mon, Jan 07, 2019 at 03:00:17PM +0800, Jason Wang wrote:
>
> On 2019/1/5 上午8:33, Sean Christopherson wrote:
> > On Fri, Jan 04, 2019 at 04:29:34PM -0500, Michael S. Tsirkin wrote:
> > > On Sat, Dec 29, 2018 at 08:46:52PM +0800, Jason Wang wrote:
> > > > Use one generic vhost_copy_to_user() instead of two dedicated
> > > > accessor. This will simplify the conversion to fine grain
> > > > accessors. About 2% improvement of PPS were seen during vitio-user
> > > > txonly test.
> > > >
> > > > Signed-off-by: Jason Wang <jasowang@redhat.com>
> > > I don't hve a problem with this patch but do you have
> > > any idea how come removing what's supposed to be
> > > an optimization speeds things up?
> > With SMAP, the 2x vhost_put_user() will also mean an extra STAC/CLAC pair,
> > which is probably slower than the overhead of CALL+RET to whatever flavor
> > of copy_user_generic() gets used. CALL+RET is really the only overhead
> > since all variants of copy_user_generic() unroll accesses smaller than
> > 64 bytes, e.g. on a 64-bit system, __copy_to_user() will write all 8
> > bytes in a single MOV.
> >
> > Removing the special casing also eliminates a few hundred bytes of code
> > as well as the need for hardware to predict count==1 vs. count>1.
> >
>
> Yes, I don't measure, but STAC/CALC is pretty expensive when we are do very
> small copies based on the result of nosmap PPS.
>
> Thanks
Yes all this really looks like a poster child for uaccess_begin/end
plus unsafe accesses. And if these APIs don't do the job for us
then maybe better ones are needed ...
--
MST
next prev parent reply other threads:[~2019-01-07 14:50 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-29 12:46 [RFC PATCH V3 0/5] Hi: Jason Wang
2018-12-29 12:46 ` [RFC PATCH V3 1/5] vhost: generalize adding used elem Jason Wang
2019-01-04 21:29 ` Michael S. Tsirkin
2019-01-05 0:33 ` Sean Christopherson
2019-01-07 7:00 ` Jason Wang
2019-01-07 14:50 ` Michael S. Tsirkin [this message]
2018-12-29 12:46 ` [RFC PATCH V3 2/5] vhost: fine grain userspace memory accessors Jason Wang
2018-12-29 12:46 ` [RFC PATCH V3 3/5] vhost: rename vq_iotlb_prefetch() to vq_meta_prefetch() Jason Wang
2018-12-29 12:46 ` [RFC PATCH V3 4/5] vhost: introduce helpers to get the size of metadata area Jason Wang
2018-12-29 12:46 ` [RFC PATCH V3 5/5] vhost: access vq metadata through kernel virtual address Jason Wang
2019-01-04 21:34 ` Michael S. Tsirkin
2019-01-07 8:40 ` Jason Wang
2019-01-02 20:47 ` [RFC PATCH V3 0/5] Hi: Michael S. Tsirkin
2019-01-07 2:19 ` Jason Wang
2019-01-07 3:28 ` Michael S. Tsirkin
2019-01-07 3:53 ` Jason Wang
2019-01-07 4:17 ` Michael S. Tsirkin
2019-01-07 6:50 ` Jason Wang
2019-01-07 14:37 ` Michael S. Tsirkin
2019-01-08 10:01 ` Jason Wang
2019-01-07 7:15 ` Dan Williams
2019-01-07 14:11 ` Michael S. Tsirkin
2019-01-07 21:39 ` Dan Williams
2019-01-07 22:25 ` Michael S. Tsirkin
2019-01-07 22:44 ` Dan Williams
2019-01-09 4:31 ` __get_user slower than get_user (was Re: [RFC PATCH V3 0/5] Hi:) Michael S. Tsirkin
2019-01-09 5:19 ` Linus Torvalds
2019-01-08 11:42 ` [RFC PATCH V3 0/5] Hi: Jason Wang
2019-01-04 21:41 ` Michael S. Tsirkin
2019-01-07 6:58 ` Jason Wang
2019-01-07 14:47 ` Michael S. Tsirkin
2019-01-08 10:12 ` Jason Wang
2019-01-11 8:59 ` Jason Wang
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=20190107094739-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=davem@davemloft.net \
--cc=jasowang@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=sean.j.christopherson@intel.com \
--cc=virtualization@lists.linux-foundation.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).