qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Artyom Tarasenko <atar4qemu@gmail.com>
To: edgar.iglesias@gmail.com
Cc: "Peter Maydell" <peter.maydell@linaro.org>,
	qemu-devel <qemu-devel@nongnu.org>,
	"Blue Swirl" <blauwirbel@gmail.com>,
	aliguori@amazon.com, pcrost@xilinx.com,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Andreas Färber" <afaerber@suse.de>,
	"Aurelien Jarno" <aurelien@aurel32.net>,
	"Richard Henderson" <rth@twiddle.net>
Subject: Re: [Qemu-devel] [PATCH v3 00/22] Steps towards per CPU address-spaces
Date: Mon, 13 Jan 2014 21:37:23 +0100	[thread overview]
Message-ID: <CACXAS8B4Kup0f5a5X=8hSuTehPd1kNpTSvazrmj4bVgfe5UxvA@mail.gmail.com> (raw)
In-Reply-To: <1389598802-14977-1-git-send-email-edgar.iglesias@gmail.com>

Hi Edgar,

On Mon, Jan 13, 2014 at 8:39 AM,  <edgar.iglesias@gmail.com> wrote:
> From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
>
> Hi,
>
> I'm looking at modeling systems where multiple CPUs co-exist with
> different views of their attached buses/devs.
>
> With this series I'm trying to take some steps towards having
> an address-space per CPU.

This is a very interesting approach. Would it be also possible to have
multiple address-spaces per CPU?
At least SPARC emulation would profit from that, the CPUs have
separate MMUs for data and code.

Artyom

> It's not complete but good enough for
> making it possible to model (to some extent) CPU local memories
> for MicroBlaze systems in emulation mode (TCG). I'm updating the
> petalogix-ml605 here and will follow-up later with the petalogix-s3adsp.
>
> The per-cpu address space is added into the CPUState. I tried to
> measure performance diff with having it in the CPUState->env.
> For "normal" and even for IO heavy workloads on linux kernels,
> the diff is not measurable. I also tested with a tight guest loop
> that continuously does I/O accesses and there I can see a 2.5% drop in perf.
> I dont think the runtime type check involved when casting from env to CS
> will be much of a problem.
>
> I've reordered the series and moved the AS props to the end, hoping
> we can get through the bulk of the series with less controversy and
> get it commited soon.
> I've kept the interface with properties to set AddressSpace pointers
> which I think is the more flexible approach but we can explore other
> ideas if there are.
>
> There is lots of future work needed, for example to transform more of
> the cpu_* bus accessing functions. To add more usage of AddressSpace
> properties to pass on address spaces to DMA models. Qtest mechanisms
> to target specific address spaces, etc...
>
> Cheers,
> Edgar
>
> v2 -> v3:
> Move CPU address-space prop into CPUState level.
>
> v1 -> v2:
> Add braces in cpu_memory_rw_debug.
> Avoid mixing var/code declarations in tcg_commit.
> Move per-cpu address space into CPUState.
> Reorder patch series to add the AS properties last.



-- 
Regards,
Artyom Tarasenko

linux/sparc and solaris/sparc under qemu blog:
http://tyom.blogspot.com/search/label/qemu

  parent reply	other threads:[~2014-01-13 20:37 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-01-13  7:39 [Qemu-devel] [PATCH v3 00/22] Steps towards per CPU address-spaces edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 01/22] exec: Make tb_invalidate_phys_addr input an AS edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 02/22] exec: Make iotlb_to_region " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 03/22] exec: Always initialize MemorySection address spaces edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 04/22] exec: Make memory_region_section_get_iotlb use section AS edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 05/22] memory: Add MemoryListener to typedefs.h edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 06/22] cpu: Add per-cpu address space edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 07/22] exec: On AS changes, only flush affected CPU TLBs edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 08/22] exec: Make ldl_*_phys input an AddressSpace edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 09/22] exec: Make ldq/ldub_*_phys " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 10/22] exec: Make lduw_*_phys " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 11/22] exec: Make stq_*_phys " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 12/22] exec: Make stl_*_phys " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 13/22] exec: Make stl_phys_notdirty " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 14/22] exec: Make stw_*_phys " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 15/22] exec: Make stb_phys " edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 16/22] exec: Make cpu_physical_memory_write_rom input an AS edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 17/22] exec: Make cpu_memory_rw_debug use the CPUs AS edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 18/22] memory: Add address_space_find_by_name() edgar.iglesias
2014-01-13  7:39 ` [Qemu-devel] [PATCH v3 19/22] qdev: Add qdev property type for AddressSpaces edgar.iglesias
2014-01-13  7:40 ` [Qemu-devel] [PATCH v3 20/22] cpu: Add address-space property edgar.iglesias
2014-01-13  7:40 ` [Qemu-devel] [PATCH v3 21/22] petalogix-ml605: Create the CPU with object_new() edgar.iglesias
2014-01-13  7:40 ` [Qemu-devel] [PATCH v3 22/22] petalogix-ml605: Make the LMB visible only to the CPU edgar.iglesias
2014-01-13 20:37 ` Artyom Tarasenko [this message]
2014-01-13 23:34   ` [Qemu-devel] [PATCH v3 00/22] Steps towards per CPU address-spaces Edgar E. Iglesias

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='CACXAS8B4Kup0f5a5X=8hSuTehPd1kNpTSvazrmj4bVgfe5UxvA@mail.gmail.com' \
    --to=atar4qemu@gmail.com \
    --cc=afaerber@suse.de \
    --cc=aliguori@amazon.com \
    --cc=aurelien@aurel32.net \
    --cc=blauwirbel@gmail.com \
    --cc=edgar.iglesias@gmail.com \
    --cc=pbonzini@redhat.com \
    --cc=pcrost@xilinx.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    /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).