From: Scott Wood <scottwood@freescale.com>
To: Alexander Graf <agraf@suse.de>
Cc: Bharat Bhushan <r65777@freescale.com>,
kvm-ppc@vger.kernel.org, kvm@vger.kernel.org,
Bharat Bhushan <Bharat.Bhushan@freescale.com>
Subject: Re: [PATCH 2/2 v2] kvm: powerpc: set cache coherency only for kernel managed pages
Date: Thu, 18 Jul 2013 17:39:16 +0000 [thread overview]
Message-ID: <1374169156.5357.8@snotra> (raw)
In-Reply-To: <7B6715E8-E136-4B05-862D-3D3F58D45760@suse.de> (from agraf@suse.de on Thu Jul 18 12:32:18 2013)
On 07/18/2013 12:32:18 PM, Alexander Graf wrote:
>
> On 18.07.2013, at 19:17, Scott Wood wrote:
>
> > On 07/18/2013 08:19:03 AM, Bharat Bhushan wrote:
> > Likewise, we want to make sure this matches the host entry.
> Unfortunately, this is a bit of a mess already. 64-bit booke appears
> to always set MAS2_M for TLB0 mappings. The initial KERNELBASE
> mapping on boot uses M_IF_SMP, and the settlbcam() that (IIRC)
> replaces it uses _PAGE_COHERENT. 32-bit always uses _PAGE_COHERENT,
> except that initial KERNELBASE mapping. _PAGE_COHERENT appears to be
> set based on CONFIG_SMP || CONFIG_PPC_STD_MMU (the latter config
> clears _PAGE_COHERENT in the non-CPU_FTR_NEED_COHERENT case).
> >
> > As for what we actually want to happen, there are cases when we
> want M to be set for non-SMP. One such case is AMP, where CPUs may
> be sharing memory even if the Linux instance only runs on one CPU
> (this is not hypothetical, BTW). It's also possible that we
> encounter a hardware bug that requires MAS2_M, similar to what some
> of our non-booke chips require.
>
> How about we always set M then for RAM?
M is like I in that bad things happen if you mix them. So we really
want to match exactly what the rest of the kernel is doing.
Plus, the performance penalty on some single-core chips can be pretty
bad.
-Scott
WARNING: multiple messages have this Message-ID (diff)
From: Scott Wood <scottwood@freescale.com>
To: Alexander Graf <agraf@suse.de>
Cc: Bharat Bhushan <r65777@freescale.com>, <kvm-ppc@vger.kernel.org>,
<kvm@vger.kernel.org>,
Bharat Bhushan <Bharat.Bhushan@freescale.com>
Subject: Re: [PATCH 2/2 v2] kvm: powerpc: set cache coherency only for kernel managed pages
Date: Thu, 18 Jul 2013 12:39:16 -0500 [thread overview]
Message-ID: <1374169156.5357.8@snotra> (raw)
In-Reply-To: <7B6715E8-E136-4B05-862D-3D3F58D45760@suse.de> (from agraf@suse.de on Thu Jul 18 12:32:18 2013)
On 07/18/2013 12:32:18 PM, Alexander Graf wrote:
>
> On 18.07.2013, at 19:17, Scott Wood wrote:
>
> > On 07/18/2013 08:19:03 AM, Bharat Bhushan wrote:
> > Likewise, we want to make sure this matches the host entry.
> Unfortunately, this is a bit of a mess already. 64-bit booke appears
> to always set MAS2_M for TLB0 mappings. The initial KERNELBASE
> mapping on boot uses M_IF_SMP, and the settlbcam() that (IIRC)
> replaces it uses _PAGE_COHERENT. 32-bit always uses _PAGE_COHERENT,
> except that initial KERNELBASE mapping. _PAGE_COHERENT appears to be
> set based on CONFIG_SMP || CONFIG_PPC_STD_MMU (the latter config
> clears _PAGE_COHERENT in the non-CPU_FTR_NEED_COHERENT case).
> >
> > As for what we actually want to happen, there are cases when we
> want M to be set for non-SMP. One such case is AMP, where CPUs may
> be sharing memory even if the Linux instance only runs on one CPU
> (this is not hypothetical, BTW). It's also possible that we
> encounter a hardware bug that requires MAS2_M, similar to what some
> of our non-booke chips require.
>
> How about we always set M then for RAM?
M is like I in that bad things happen if you mix them. So we really
want to match exactly what the rest of the kernel is doing.
Plus, the performance penalty on some single-core chips can be pretty
bad.
-Scott
next prev parent reply other threads:[~2013-07-18 17:39 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-18 13:19 [PATCH 1/2 v2] kvm: powerpc: Do not ignore "E" attribute in mas2 Bharat Bhushan
2013-07-18 13:31 ` Bharat Bhushan
2013-07-18 13:19 ` [PATCH 2/2 v2] kvm: powerpc: set cache coherency only for kernel managed pages Bharat Bhushan
2013-07-18 13:31 ` Bharat Bhushan
2013-07-18 14:53 ` Alexander Graf
2013-07-18 14:53 ` Alexander Graf
2013-07-18 15:15 ` Bhushan Bharat-R65777
2013-07-18 15:19 ` Alexander Graf
2013-07-18 15:19 ` Alexander Graf
2013-07-18 17:17 ` Scott Wood
2013-07-18 17:17 ` Scott Wood
2013-07-18 17:32 ` Alexander Graf
2013-07-18 17:32 ` Alexander Graf
2013-07-18 17:39 ` Scott Wood [this message]
2013-07-18 17:39 ` Scott Wood
2013-07-22 4:39 ` Bhushan Bharat-R65777
2013-07-22 18:47 ` Scott Wood
2013-07-22 18:47 ` Scott Wood
2013-07-23 3:39 ` Bhushan Bharat-R65777
2013-07-23 16:44 ` Scott Wood
2013-07-23 16:44 ` Scott Wood
2013-07-23 16:50 ` Bhushan Bharat-R65777
2013-07-23 18:20 ` Scott Wood
2013-07-23 18:20 ` Scott Wood
2013-07-24 1:06 ` Bhushan Bharat-R65777
2013-07-23 11:13 ` Bhushan Bharat-R65777
2013-07-23 18:26 ` Scott Wood
2013-07-23 18:26 ` Scott Wood
2013-07-18 14:48 ` [PATCH 1/2 v2] kvm: powerpc: Do not ignore "E" attribute in mas2 Alexander Graf
2013-07-18 14:48 ` Alexander Graf
2013-07-18 15:12 ` Bhushan Bharat-R65777
2013-07-18 15:19 ` Alexander Graf
2013-07-18 15:19 ` Alexander Graf
2013-07-18 15:20 ` Bhushan Bharat-R65777
2013-07-18 16:15 ` Scott Wood
2013-07-18 16:15 ` Scott Wood
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=1374169156.5357.8@snotra \
--to=scottwood@freescale.com \
--cc=Bharat.Bhushan@freescale.com \
--cc=agraf@suse.de \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=r65777@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.