All of lore.kernel.org
 help / color / mirror / Atom feed
From: Richard Henderson <rth@twiddle.net>
To: "Peter Maydell" <peter.maydell@linaro.org>,
	"KONRAD Frédéric" <fred.konrad@greensocs.com>
Cc: mttcg@greensocs.com, "J. Kiszka" <jan.kiszka@siemens.com>,
	Mark Burton <mark.burton@greensocs.com>,
	QEMU Developers <qemu-devel@nongnu.org>,
	Alexander Graf <agraf@suse.de>,
	Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: [Qemu-devel] [RFC 05/10] extract TBContext from TCGContext.
Date: Tue, 03 Feb 2015 08:30:06 -0800	[thread overview]
Message-ID: <54D0F78E.4060107@twiddle.net> (raw)
In-Reply-To: <CAFEAcA8cZD1REWcvJJVv6AjB95GXgA3FueQ8b6ZSaCj8JTnGAg@mail.gmail.com>

On 01/29/2015 07:44 AM, Peter Maydell wrote:
> On 16 January 2015 at 17:19,  <fred.konrad@greensocs.com> wrote:
>> From: KONRAD Frederic <fred.konrad@greensocs.com>
>>
>> In order to have one TCGContext per thread and a single TBContext we have to
>> extract TBContext from TCGContext.
> 
> This seems a bit odd. It's not clear to me what the advantages
> are of having one TCGContext per thread but only a single
> TBContext (as opposed to either (1) having a single TCGContext
> and TBContext with locks protecting against multiple threads
> generating code at once, or (2) having each thread have its
> own TCGContext and TBContext and completely independent codegen).
> 
> Maybe it would help if you sketched out your design in a little
> more detail in the cover letter, with emphasis on which data
> structures are going to be per-thread and which are going to
> be shared (and if so how shared).
> 
> (Long term we would want to be able to have multiple
> TBContexts to support heterogenous systems where CPUs
> might be different architectures or have different views
> of physical memory...)

Seconded.


r~

  reply	other threads:[~2015-02-03 16:30 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-01-16 17:19 [Qemu-devel] [RFC 00/10] MultiThread TCG fred.konrad
2015-01-16 17:19 ` [Qemu-devel] [RFC 01/10] target-arm: protect cpu_exclusive_* fred.konrad
2015-01-27 14:36   ` Alex Bennée
2015-01-29 15:17   ` Peter Maydell
2015-02-02  8:31     ` Frederic Konrad
2015-02-02  8:36       ` Peter Maydell
2015-02-26 18:09     ` Frederic Konrad
2015-02-26 20:36       ` Alexander Graf
2015-02-26 22:56       ` Peter Maydell
2015-02-27  7:54         ` Mark Burton
2015-03-02 12:27           ` Peter Maydell
2015-03-03 15:29             ` Mark Burton
2015-03-03 15:32               ` Paolo Bonzini
2015-03-03 15:33                 ` Mark Burton
2015-03-03 15:34                   ` Paolo Bonzini
2015-03-03 15:41                     ` Mark Burton
2015-03-03 15:47                   ` Dr. David Alan Gilbert
2015-03-13 19:38                     ` Richard Henderson
2015-03-13 20:04                       ` Dr. David Alan Gilbert
2015-01-16 17:19 ` [Qemu-devel] [RFC 02/10] use a different translation block list for each cpu fred.konrad
2015-01-27 14:45   ` Alex Bennée
2015-01-27 15:16     ` Frederic Konrad
2015-01-29 15:24   ` Peter Maydell
2015-01-29 15:33     ` Mark Burton
2015-02-02  8:39     ` Frederic Konrad
2015-02-02  8:49       ` Peter Maydell
2015-02-03 16:17   ` Richard Henderson
2015-02-03 16:33     ` Paolo Bonzini
2015-01-16 17:19 ` [Qemu-devel] [RFC 03/10] replace spinlock by QemuMutex fred.konrad
2015-01-29 15:25   ` Peter Maydell
2015-02-02  8:45     ` Frederic Konrad
2015-01-16 17:19 ` [Qemu-devel] [RFC 04/10] remove unused spinlock fred.konrad
2015-01-16 17:19 ` [Qemu-devel] [RFC 05/10] extract TBContext from TCGContext fred.konrad
2015-01-29 15:44   ` Peter Maydell
2015-02-03 16:30     ` Richard Henderson [this message]
2015-01-16 17:19 ` [Qemu-devel] [RFC 06/10] protect TBContext with tb_lock fred.konrad
2015-01-16 17:19 ` [Qemu-devel] [RFC 07/10] tcg: remove tcg_halt_cond global variable fred.konrad
2015-01-16 17:19 ` [Qemu-devel] [RFC 08/10] Drop global lock during TCG code execution fred.konrad
2015-01-16 17:19 ` [Qemu-devel] [RFC 09/10] cpu: remove exit_request global fred.konrad
2015-01-29 15:52   ` Peter Maydell
2015-02-02 10:03     ` Paolo Bonzini
2015-02-02 13:12       ` Peter Maydell
2015-02-02 13:14         ` Paolo Bonzini
2015-02-03  9:37     ` Frederic Konrad
2015-02-03 10:29       ` Peter Maydell
2015-01-16 17:19 ` [Qemu-devel] [RFC 10/10] tcg: switch on multithread fred.konrad
2015-03-27 10:08 ` [Qemu-devel] [RFC 00/10] MultiThread TCG Alex Bennée
2015-03-27 10:37   ` Frederic Konrad
2015-03-30  6:52     ` Mark Burton
2015-03-30 21:46       ` Peter Maydell
2015-03-31  6:41         ` Mark Burton
2015-04-10 16:03         ` Frederic Konrad
2015-04-22 12:26           ` Frederic Konrad
2015-04-22 13:18             ` Peter Maydell
2015-04-23  7:38               ` Frederic Konrad
2015-04-23 15:44             ` Alex Bennée
2015-04-23 15:46               ` Alex Bennée
2015-04-27  7:37                 ` Frederic Konrad
2015-04-27 17:06             ` Emilio G. Cota
2015-04-28  8:17               ` Frederic Konrad
2015-04-28  9:06               ` Paolo Bonzini
2015-04-28 17:49                 ` Emilio G. Cota

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=54D0F78E.4060107@twiddle.net \
    --to=rth@twiddle.net \
    --cc=agraf@suse.de \
    --cc=fred.konrad@greensocs.com \
    --cc=jan.kiszka@siemens.com \
    --cc=mark.burton@greensocs.com \
    --cc=mttcg@greensocs.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.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 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.