From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Alexander Graf <agraf@suse.de>
Cc: "Scott Wood" <scottwood@freescale.com>,
kvm-ppc@vger.kernel.org, "Jörg Sommer" <joerg@alea.gnuu.de>,
"KVM list" <kvm@vger.kernel.org>
Subject: Re: [PATCH 4/4] KVM: PPC: align vcpu_kick with x86
Date: Fri, 23 Dec 2011 21:50:11 +0000 [thread overview]
Message-ID: <1324677011.6632.15.camel@pasglop> (raw)
In-Reply-To: <E9B7009D-24F8-497A-AE56-EB0472C167DA@suse.de>
On Fri, 2011-12-23 at 13:56 +0100, Alexander Graf wrote:
> > Hmm, unless smp_send_reschedule must be called with preemption disabled
> > (doesn't seem like an obvious requirement, even if callers commonly have
> > a reason to do so, and the only documentation of it I see is on the ia64
> > implementation), that seems like a bug in the MPIC IPI implementation.
> >
> > It wouldn't be an issue (and would make the MPIC driver slightly faster,
> > too) if the MPIC driver were to use the magic CPU region instead of
> > manually indexing the non-magic array of per-CPU regions. Maybe it
> > doesn't work on all hardware the driver supports?
Right, the magic per-cpu region doesn't work on all HW.
> I'd say that's a question I'll redirect to Ben :).
>
> > Not that it matters much here -- we want this patch anyway, because we
> > want to check that it's not the current CPU.
>
> Yeah. Well - eventually we want the exact same vcpu_kick function across architectures.
> But this is a good step in the right direction.
Cheers,
Ben.
WARNING: multiple messages have this Message-ID (diff)
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Alexander Graf <agraf@suse.de>
Cc: "Scott Wood" <scottwood@freescale.com>,
kvm-ppc@vger.kernel.org, "Jörg Sommer" <joerg@alea.gnuu.de>,
"KVM list" <kvm@vger.kernel.org>
Subject: Re: [PATCH 4/4] KVM: PPC: align vcpu_kick with x86
Date: Sat, 24 Dec 2011 08:50:11 +1100 [thread overview]
Message-ID: <1324677011.6632.15.camel@pasglop> (raw)
In-Reply-To: <E9B7009D-24F8-497A-AE56-EB0472C167DA@suse.de>
On Fri, 2011-12-23 at 13:56 +0100, Alexander Graf wrote:
> > Hmm, unless smp_send_reschedule must be called with preemption disabled
> > (doesn't seem like an obvious requirement, even if callers commonly have
> > a reason to do so, and the only documentation of it I see is on the ia64
> > implementation), that seems like a bug in the MPIC IPI implementation.
> >
> > It wouldn't be an issue (and would make the MPIC driver slightly faster,
> > too) if the MPIC driver were to use the magic CPU region instead of
> > manually indexing the non-magic array of per-CPU regions. Maybe it
> > doesn't work on all hardware the driver supports?
Right, the magic per-cpu region doesn't work on all HW.
> I'd say that's a question I'll redirect to Ben :).
>
> > Not that it matters much here -- we want this patch anyway, because we
> > want to check that it's not the current CPU.
>
> Yeah. Well - eventually we want the exact same vcpu_kick function across architectures.
> But this is a good step in the right direction.
Cheers,
Ben.
next prev parent reply other threads:[~2011-12-23 21:50 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-12-09 15:26 [PATCH 0/4] Fix book3s-pr KVM with preemption Alexander Graf
2011-12-09 15:26 ` Alexander Graf
2011-12-09 15:26 ` [PATCH 1/4] KVM: PPC: Book3s: PR: Disable preemption in vcpu_run Alexander Graf
2011-12-09 15:26 ` Alexander Graf
2011-12-09 18:19 ` Scott Wood
2011-12-09 18:19 ` Scott Wood
2011-12-09 23:18 ` Alexander Graf
2011-12-09 23:18 ` Alexander Graf
2011-12-13 21:15 ` Scott Wood
2011-12-13 21:15 ` Scott Wood
2011-12-09 15:26 ` [PATCH 2/4] KVM: PPC: Book3s: PR: No irq_disable " Alexander Graf
2011-12-09 15:26 ` Alexander Graf
2011-12-09 15:26 ` [PATCH 3/4] KVM: PPC: Use get/set for to_svcpu to help preemption Alexander Graf
2011-12-09 15:26 ` Alexander Graf
2011-12-09 15:26 ` [PATCH 4/4] KVM: PPC: align vcpu_kick with x86 Alexander Graf
2011-12-09 15:26 ` Alexander Graf
2011-12-09 18:19 ` Scott Wood
2011-12-09 18:19 ` Scott Wood
2011-12-09 19:10 ` Alexander Graf
2011-12-09 19:10 ` Alexander Graf
2011-12-09 19:15 ` Scott Wood
2011-12-09 19:15 ` Scott Wood
2011-12-09 23:15 ` Alexander Graf
2011-12-09 23:15 ` Alexander Graf
2011-12-12 17:32 ` Scott Wood
2011-12-12 17:32 ` Scott Wood
2011-12-23 12:56 ` Alexander Graf
2011-12-23 12:56 ` Alexander Graf
2011-12-23 21:50 ` Benjamin Herrenschmidt [this message]
2011-12-23 21:50 ` Benjamin Herrenschmidt
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=1324677011.6632.15.camel@pasglop \
--to=benh@kernel.crashing.org \
--cc=agraf@suse.de \
--cc=joerg@alea.gnuu.de \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=scottwood@freescale.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.