From: Tim Deegan <tim@xen.org>
To: Ian Campbell <Ian.Campbell@citrix.com>
Cc: julien.grall@citrix.com, xen-devel@lists.xen.org,
Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Subject: Re: [PATCH 06/10] xen: arm: Use SMP barriers when that is all which is required.
Date: Thu, 4 Jul 2013 12:30:23 +0100 [thread overview]
Message-ID: <20130704113023.GH40611@ocelot.phlegethon.org> (raw)
In-Reply-To: <1372692281.14691.84.camel@zakaz.uk.xensource.com>
At 16:24 +0100 on 01 Jul (1372695881), Ian Campbell wrote:
> On Mon, 2013-07-01 at 16:19 +0100, Stefano Stabellini wrote:
> > On Fri, 28 Jun 2013, Ian Campbell wrote:
> > > As explained in the previous commit SMP barriers can be used when all we care
> > > about is synchronising against other processors.
> > >
> > > Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
> > > ---
> > > xen/arch/arm/mm.c | 2 +-
> > > xen/arch/arm/smpboot.c | 4 ++--
> > > 2 files changed, 3 insertions(+), 3 deletions(-)
> > >
> > > diff --git a/xen/arch/arm/mm.c b/xen/arch/arm/mm.c
> > > index c5213f2..3f049cb 100644
> > > --- a/xen/arch/arm/mm.c
> > > +++ b/xen/arch/arm/mm.c
> > > @@ -776,7 +776,7 @@ void share_xen_page_with_guest(struct page_info *page,
> > > page->u.inuse.type_info |= PGT_validated | 1;
> > >
> > > page_set_owner(page, d);
> > > - wmb(); /* install valid domain ptr before updating refcnt. */
> > > + smp_wmb(); /* install valid domain ptr before updating refcnt. */
> > > ASSERT((page->count_info & ~PGC_xen_heap) == 0);
> > >
> > > /* Only add to the allocation list if the domain isn't dying. */
> > > diff --git a/xen/arch/arm/smpboot.c b/xen/arch/arm/smpboot.c
> > > index 8011987..727e09f 100644
> > > --- a/xen/arch/arm/smpboot.c
> > > +++ b/xen/arch/arm/smpboot.c
> > > @@ -170,11 +170,11 @@ void __cpuinit start_secondary(unsigned long boot_phys_offset,
> > >
> > > /* Run local notifiers */
> > > notify_cpu_starting(cpuid);
> > > - wmb();
> > > + smp_wmb();
> > >
> > > /* Now report this CPU is up */
> > > cpumask_set_cpu(cpuid, &cpu_online_map);
> > > - wmb();
> > > + smp_wmb();
> > >
> > > local_irq_enable();
> >
> > Did you missed few mb() in smpboot.c?
>
> The ones in __cpu_disable and __cpu_die?
>
> I think I just wasn't 100% sure they might not be touching hardware
> (i.e. some platform register to shutdown a CPU) and since they weren't
> performance critical I punted on them.
>
> Looking it again the first half of that logic seems to be bogus (that
> code goes nowhere near any peripheral).
Yes, I think they can both be smp_mb(). With or without that change,
Acked-by: Tim Deegan <tim@xen.org>
next prev parent reply other threads:[~2013-07-04 11:30 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-28 16:10 [PATCH 00/10] xen: arm: map normal memory as inner shareable, reduce scope of various barriers Ian Campbell
2013-06-28 16:10 ` [PATCH 01/10] xen: arm: map memory as inner shareable Ian Campbell
2013-07-01 15:39 ` Stefano Stabellini
2013-07-01 15:42 ` Ian Campbell
2013-07-02 14:09 ` Leif Lindholm
2013-07-02 14:26 ` Ian Campbell
2013-07-04 10:58 ` Tim Deegan
2013-07-04 11:03 ` Ian Campbell
2013-06-28 16:10 ` [PATCH 02/10] xen: arm: Only upgrade guest barriers to " Ian Campbell
2013-07-01 15:24 ` Stefano Stabellini
2013-07-04 10:58 ` Tim Deegan
2013-06-28 16:10 ` [PATCH 03/10] xen: arm: reduce instruction cache and tlb flushes to inner-shareable Ian Campbell
2013-07-01 15:25 ` Stefano Stabellini
2013-07-04 11:07 ` Tim Deegan
2013-07-04 11:19 ` Tim Deegan
2013-07-04 11:21 ` Tim Deegan
2013-06-28 16:10 ` [PATCH 04/10] xen: arm: consolidate barrier definitions Ian Campbell
2013-07-01 15:25 ` Stefano Stabellini
2013-07-04 11:07 ` Tim Deegan
2013-06-28 16:10 ` [PATCH 05/10] xen: use SMP barrier in common code dealing with shared memory protocols Ian Campbell
2013-06-28 16:15 ` Ian Campbell
2013-06-28 16:20 ` Keir Fraser
2013-07-04 11:26 ` Tim Deegan
2013-06-28 16:10 ` [PATCH 06/10] xen: arm: Use SMP barriers when that is all which is required Ian Campbell
2013-07-01 15:19 ` Stefano Stabellini
2013-07-01 15:24 ` Ian Campbell
2013-07-04 11:30 ` Tim Deegan [this message]
2013-06-28 16:10 ` [PATCH 07/10] xen: arm: Use dmb for smp barriers Ian Campbell
2013-07-01 15:20 ` Stefano Stabellini
2013-07-04 11:31 ` Tim Deegan
2013-06-28 16:10 ` [PATCH 08/10] xen: arm: add scope to dsb and dmb macros Ian Campbell
2013-07-01 15:21 ` Stefano Stabellini
2013-07-01 15:22 ` Stefano Stabellini
2013-07-04 11:44 ` (no subject) Tim Deegan
2013-06-28 16:10 ` [PATCH 09/10] xen: arm: weaken SMP barriers to inner shareable Ian Campbell
2013-07-01 15:21 ` Stefano Stabellini
2013-07-01 15:22 ` Stefano Stabellini
2013-07-04 11:35 ` Tim Deegan
2013-06-28 16:10 ` [PATCH 10/10] xen: arm: use more specific barriers for read and write barriers Ian Campbell
2013-07-01 15:22 ` Stefano Stabellini
2013-07-04 11:42 ` Tim Deegan
2013-07-04 11:46 ` Ian Campbell
2013-06-28 16:11 ` [PATCH 00/10] xen: arm: map normal memory as inner shareable, reduce scope of various barriers Ian Campbell
2013-07-04 11:32 (no subject) Tim Deegan
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=20130704113023.GH40611@ocelot.phlegethon.org \
--to=tim@xen.org \
--cc=Ian.Campbell@citrix.com \
--cc=julien.grall@citrix.com \
--cc=stefano.stabellini@eu.citrix.com \
--cc=xen-devel@lists.xen.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).