All of lore.kernel.org
 help / color / mirror / Atom feed
From: Marc Zyngier <maz@kernel.org>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, catalin.marinas@arm.com,
	andrew.jones@linux.dev, will@kernel.org, shan.gavin@gmail.com,
	bgardon@google.com, dmatlack@google.com, zhenyzha@redhat.com,
	shuah@kernel.org, kvmarm@lists.cs.columbia.edu
Subject: Re: [PATCH 5/6] KVM: selftests: dirty-log: Upgrade dirty_gfn_set_collected() to store-release
Date: Fri, 23 Sep 2022 15:49:07 +0100	[thread overview]
Message-ID: <87a66qjgd8.wl-maz@kernel.org> (raw)
In-Reply-To: <CABgObfbtVAM3t2WC6-8-fLdQZTs6B5Xf2-CZ4oWdJMzXNFWy_g@mail.gmail.com>

On Thu, 22 Sep 2022 22:38:58 +0100,
Paolo Bonzini <pbonzini@redhat.com> wrote:
> 
> On Thu, Sep 22, 2022 at 7:02 PM Marc Zyngier <maz@kernel.org> wrote:
> > To make sure that all the writes to the log marking the entries
> > as being in need of reset are observed in order, use a
> > smp_store_release() when updating the log entry flags.
> >
> > Signed-off-by: Marc Zyngier <maz@kernel.org>
> 
> You also need a load-acquire on the load of gfn->flags in
> dirty_gfn_is_dirtied. Otherwise reading cur->slot or cur->offset might
> see a stale value.

Ah, indeed. smp_wmb() is implemented as DMB ISHST, which only orders
writes, and not loads against writes. Global barriers are just
confusing.

/me goes and repaint the stuff...

	M.

-- 
Without deviation from the norm, progress is not possible.
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

WARNING: multiple messages have this Message-ID (diff)
From: Marc Zyngier <maz@kernel.org>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: kvmarm@lists.cs.columbia.edu, kvm@vger.kernel.org,
	catalin.marinas@arm.com, bgardon@google.com, shuah@kernel.org,
	andrew.jones@linux.dev, will@kernel.org, dmatlack@google.com,
	peterx@redhat.com, zhenyzha@redhat.com, shan.gavin@gmail.com,
	gshan@redhat.com, James Morse <james.morse@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Oliver Upton <oliver.upton@linux.dev>
Subject: Re: [PATCH 5/6] KVM: selftests: dirty-log: Upgrade dirty_gfn_set_collected() to store-release
Date: Fri, 23 Sep 2022 15:49:07 +0100	[thread overview]
Message-ID: <87a66qjgd8.wl-maz@kernel.org> (raw)
In-Reply-To: <CABgObfbtVAM3t2WC6-8-fLdQZTs6B5Xf2-CZ4oWdJMzXNFWy_g@mail.gmail.com>

On Thu, 22 Sep 2022 22:38:58 +0100,
Paolo Bonzini <pbonzini@redhat.com> wrote:
> 
> On Thu, Sep 22, 2022 at 7:02 PM Marc Zyngier <maz@kernel.org> wrote:
> > To make sure that all the writes to the log marking the entries
> > as being in need of reset are observed in order, use a
> > smp_store_release() when updating the log entry flags.
> >
> > Signed-off-by: Marc Zyngier <maz@kernel.org>
> 
> You also need a load-acquire on the load of gfn->flags in
> dirty_gfn_is_dirtied. Otherwise reading cur->slot or cur->offset might
> see a stale value.

Ah, indeed. smp_wmb() is implemented as DMB ISHST, which only orders
writes, and not loads against writes. Global barriers are just
confusing.

/me goes and repaint the stuff...

	M.

-- 
Without deviation from the norm, progress is not possible.

  reply	other threads:[~2022-09-23 14:49 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-22 17:01 [PATCH 0/6] KVM: Fix dirty-ring ordering on weakly ordered architectures Marc Zyngier
2022-09-22 17:01 ` Marc Zyngier
2022-09-22 17:01 ` [PATCH 1/6] KVM: Use acquire/release semantics when accessing dirty ring GFN state Marc Zyngier
2022-09-22 17:01   ` Marc Zyngier
2022-09-22 21:38   ` Peter Xu
2022-09-22 21:38     ` Peter Xu
2022-09-22 23:46     ` Gavin Shan
2022-09-22 23:46       ` Gavin Shan
2022-09-23 14:40       ` Marc Zyngier
2022-09-23 14:40         ` Marc Zyngier
2022-09-23 14:19     ` Marc Zyngier
2022-09-23 14:19       ` Marc Zyngier
2022-09-23 14:22       ` Paolo Bonzini
2022-09-23 14:22         ` Paolo Bonzini
2022-09-22 17:01 ` [PATCH 2/6] KVM: Add KVM_CAP_DIRTY_LOG_RING_ORDERED capability and config option Marc Zyngier
2022-09-22 17:01   ` Marc Zyngier
2022-09-22 21:48   ` Peter Xu
2022-09-22 21:48     ` Peter Xu
2022-09-23  0:04     ` Gavin Shan
2022-09-23  0:04       ` Gavin Shan
2022-09-23 14:28     ` Marc Zyngier
2022-09-23 14:28       ` Marc Zyngier
2022-09-23 18:26       ` Peter Xu
2022-09-23 18:26         ` Peter Xu
2022-09-23 21:23         ` Paolo Bonzini
2022-09-23 21:23           ` Paolo Bonzini
2022-09-23 22:34           ` Peter Xu
2022-09-23 22:34             ` Peter Xu
2022-09-24  8:51         ` Marc Zyngier
2022-09-24  8:51           ` Marc Zyngier
2022-09-24 11:26           ` Marc Zyngier
2022-09-24 11:26             ` Marc Zyngier
2022-09-24 13:22             ` Peter Xu
2022-09-24 13:22               ` Peter Xu
2022-09-24 18:57               ` Marc Zyngier
2022-09-24 18:57                 ` Marc Zyngier
2022-09-25 23:17                 ` Gavin Shan
2022-09-25 23:17                   ` Gavin Shan
2022-09-22 17:01 ` [PATCH 3/6] KVM: x86: Select CONFIG_HAVE_KVM_DIRTY_RING_ORDERED Marc Zyngier
2022-09-22 17:01   ` Marc Zyngier
2022-09-23 22:46   ` Peter Xu
2022-09-23 22:46     ` Peter Xu
2022-09-24  8:47     ` Marc Zyngier
2022-09-24  8:47       ` Marc Zyngier
2022-09-24 13:29       ` Peter Xu
2022-09-24 13:29         ` Peter Xu
2022-09-22 17:01 ` [PATCH 4/6] KVM: Document weakly ordered architecture requirements for dirty ring Marc Zyngier
2022-09-22 17:01   ` Marc Zyngier
2022-09-22 17:01 ` [PATCH 5/6] KVM: selftests: dirty-log: Upgrade dirty_gfn_set_collected() to store-release Marc Zyngier
2022-09-22 17:01   ` Marc Zyngier
2022-09-22 21:38   ` Paolo Bonzini
2022-09-22 21:38     ` Paolo Bonzini
2022-09-23 14:49     ` Marc Zyngier [this message]
2022-09-23 14:49       ` Marc Zyngier
2022-09-22 17:01 ` [PATCH 6/6] KVM: selftests: dirty-log: Use KVM_CAP_DIRTY_LOG_RING_ORDERED of available Marc Zyngier
2022-09-22 17:01   ` Marc Zyngier

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=87a66qjgd8.wl-maz@kernel.org \
    --to=maz@kernel.org \
    --cc=andrew.jones@linux.dev \
    --cc=bgardon@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=dmatlack@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=pbonzini@redhat.com \
    --cc=shan.gavin@gmail.com \
    --cc=shuah@kernel.org \
    --cc=will@kernel.org \
    --cc=zhenyzha@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.