From: Paolo Bonzini <pbonzini@redhat.com>
To: Nadav Amit <nadav.amit@gmail.com>
Cc: LKML <linux-kernel@vger.kernel.org>, KVM <kvm@vger.kernel.org>,
"Radim Krčmář" <rkrcmar@redhat.com>,
"Yang Zhang" <yang.zhang.wz@gmail.com>,
"feng wu" <feng.wu@intel.com>,
mst@redhat.com
Subject: Re: [PATCH 1/5] KVM: x86: avoid atomic operations on APICv vmentry
Date: Sat, 15 Oct 2016 03:47:45 -0400 (EDT) [thread overview]
Message-ID: <119879133.3749907.1476517665517.JavaMail.zimbra@redhat.com> (raw)
In-Reply-To: <9B7F4808-2294-426D-B463-CEB188CED2E0@gmail.com>
> > On Oct 14, 2016, at 11:56 AM, Paolo Bonzini <pbonzini@redhat.com> wrote:
> >>>
> >>> for (i = 0; i <= 7; i++) {
> >>> - pir_val = xchg(&pir[i], 0);
> >>> - if (pir_val)
> >>> + pir_val = READ_ONCE(pir[i]);
> >>
> >> Out of curiosity, do you really need this READ_ONCE?
> >
> > The answer can only be "depends on the compiler's whims". :)
> > If you think of READ_ONCE as a C11 relaxed atomic load, then yes.
>
> Hm.. So the idea is to make the code "race-free” in the sense
> that every concurrent memory access is done using READ_ONCE/WRITE_ONCE?
>
> If that is the case, I think there are many other cases that need to be
> changed, for example apic->irr_pending and vcpu->arch.pv.pv_unhalted.
There is no documentation for this in the kernel tree unfortunately.
But yes, I think we should do that. Using READ_ONCE/WRITE_ONCE around
memory barriers is a start.
Paolo
next prev parent reply other threads:[~2016-10-15 7:47 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-10-14 18:21 [PATCH 0/5] KVM: x86: cleanup and minimal speedup for APICv Paolo Bonzini
2016-10-14 18:21 ` [PATCH 1/5] KVM: x86: avoid atomic operations on APICv vmentry Paolo Bonzini
2016-10-14 18:50 ` Nadav Amit
2016-10-14 18:56 ` Paolo Bonzini
2016-10-14 19:44 ` Nadav Amit
2016-10-15 7:47 ` Paolo Bonzini [this message]
2016-10-16 2:29 ` Michael S. Tsirkin
2016-10-19 11:45 ` Paul E. McKenney
2016-10-26 21:50 ` Michael S. Tsirkin
2016-10-16 3:21 ` Michael S. Tsirkin
2016-10-17 11:07 ` Paolo Bonzini
2016-10-26 19:53 ` Radim Krčmář
2016-10-26 21:42 ` Michael S. Tsirkin
2016-10-27 16:44 ` Radim Krčmář
2016-10-27 16:51 ` Michael S. Tsirkin
2016-10-27 17:06 ` Radim Krčmář
2016-10-28 9:39 ` Paolo Bonzini
2016-10-28 22:04 ` Michael S. Tsirkin
2016-10-14 18:21 ` [PATCH 2/5] KVM: x86: do not scan IRR twice " Paolo Bonzini
2016-10-18 6:04 ` Wanpeng Li
2016-10-26 19:59 ` Radim Krčmář
2016-11-03 13:30 ` Paolo Bonzini
2016-11-03 13:53 ` Michael S. Tsirkin
2016-11-03 16:01 ` Paolo Bonzini
2016-11-03 15:03 ` Radim Krčmář
2016-11-03 16:00 ` Paolo Bonzini
2016-11-03 18:07 ` Radim Krčmář
2016-11-03 18:18 ` Paolo Bonzini
2016-11-03 18:29 ` Radim Krčmář
2016-11-03 20:16 ` Radim Krčmář
2016-11-04 9:38 ` Paolo Bonzini
2016-10-14 18:21 ` [PATCH 3/5] KVM: x86: do not use KVM_REQ_EVENT for APICv interrupt injection Paolo Bonzini
2016-10-26 20:05 ` Radim Krčmář
2016-10-14 18:21 ` [PATCH 4/5] KVM: x86: remove unnecessary sync_pir_to_irr Paolo Bonzini
2016-10-26 20:28 ` Radim Krčmář
2016-10-14 18:21 ` [PATCH 5/5] KVM: vmx: clear pending interrupts on KVM_SET_LAPIC Paolo Bonzini
2016-10-26 20:08 ` Radim Krčmář
2016-10-26 21:52 ` [PATCH 0/5] KVM: x86: cleanup and minimal speedup for APICv Michael S. Tsirkin
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=119879133.3749907.1476517665517.JavaMail.zimbra@redhat.com \
--to=pbonzini@redhat.com \
--cc=feng.wu@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=nadav.amit@gmail.com \
--cc=rkrcmar@redhat.com \
--cc=yang.zhang.wz@gmail.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).