linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: catalin.marinas@arm.com (Catalin Marinas)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC PATCHv1 0/7] ARM core support for hardware I/O coherency in non-SMP platforms
Date: Wed, 14 May 2014 18:04:56 +0100	[thread overview]
Message-ID: <20140514170456.GC15946@arm.com> (raw)
In-Reply-To: <1400082641-23871-1-git-send-email-thomas.petazzoni@free-electrons.com>

On Wed, May 14, 2014 at 04:50:34PM +0100, Thomas Petazzoni wrote:
> This hardware I/O coherency mechanism needs a set of ARM core
> requirements to operate properly:
> 
>  * On Armada 370 (a single core processor)
> 
>    - The cache policy of pages must be set to "write allocate".

Arguably, I would make this the default for ARMv6+ CPUs even if UP. It's
a hint that the CPU may or may not ignore but it shouldn't break
anything (well, maybe some artificial benchmarks designed to show
that write-allocate caches are bad).

[...]

>  * On Armada 375/38x (which have single core and dual core variants)
> 
>    - The cache policy of pages must be set to "write allocate".
>    - The SMP and TLB broadcast bits must be set in the Auxiliary
>      Control Register (the core is a Cortex-A9)

What about setting this bit in the firmware/bootloader? It's a sane
initialisation firmware should do.

>    - The pages must be set as shareable.

Here you may have some conflict between the initial page tables set in
__create_page_tables as non-shareable (that's unless MPIDR shows it as
SMP but I guess not since smp-on-up kicks in). I have to think a bit
more about the implications (the ARM ARM has a chapter on mismatched
memory attributes and I think it talks about shareable vs
non-shareable).

>    - The SCU must be enabled

Again, could the firmware do this?

-- 
Catalin

  parent reply	other threads:[~2014-05-14 17:04 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-05-14 15:50 [RFC PATCHv1 0/7] ARM core support for hardware I/O coherency in non-SMP platforms Thomas Petazzoni
2014-05-14 15:50 ` [RFC PATCHv1 1/7] ARM: extend machine_desc with additional flags Thomas Petazzoni
2014-05-14 15:50 ` [RFC PATCHv1 2/7] ARM: mm: implement the usage of the machine_desc flags Thomas Petazzoni
2014-05-14 15:50 ` [RFC PATCHv1 3/7] ARM: mm: enable SMP bit and TLB broadcast bit on !SMP when needed Thomas Petazzoni
2014-05-14 15:50 ` [RFC PATCHv1 4/7] ARM: kernel: allow the SCU to be enabled even on !SMP Thomas Petazzoni
2014-05-14 15:50 ` [RFC PATCHv1 5/7] ARM: mvebu: split Armada 370 and Armada XP machine_desc Thomas Petazzoni
2014-05-14 15:50 ` [RFC PATCHv1 6/7] ARM: mvebu: define the Armada 370/375/38x/XP machine_desc flags Thomas Petazzoni
2014-05-14 15:50 ` [RFC PATCHv1 7/7] ARM: mvebu: I/O coherency no longer needs SMP on 375 and 38x Thomas Petazzoni
2014-05-14 17:04 ` Catalin Marinas [this message]
2014-05-15  9:50   ` [RFC PATCHv1 0/7] ARM core support for hardware I/O coherency in non-SMP platforms Thomas Petazzoni
2014-05-15 14:22     ` Catalin Marinas
2014-05-15 14:59       ` Rob Herring
2014-05-15 15:25         ` Catalin Marinas
2014-05-15 19:11           ` Rob Herring
2014-05-16 15:11             ` Catalin Marinas
2014-05-19  9:19               ` Thomas Petazzoni
2014-05-19  9:17       ` Thomas Petazzoni
2014-05-19 10:42         ` Catalin Marinas
2014-05-19 11:17           ` Thomas Petazzoni
2014-05-19 15:19             ` Catalin Marinas
2014-05-19 13:38   ` Thomas Petazzoni
2014-05-14 17:07 ` Rob Herring
2014-05-15 10:01   ` Thomas Petazzoni
2014-05-15 13:27     ` Will Deacon
2014-05-15 13:44       ` Thomas Petazzoni
2014-05-15 14:44     ` Rob Herring
2014-05-19  9:31       ` Thomas Petazzoni
2014-05-19 16:53         ` Rob Herring

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=20140514170456.GC15946@arm.com \
    --to=catalin.marinas@arm.com \
    --cc=linux-arm-kernel@lists.infradead.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).