mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Ingo Molnar <mingo@elte.hu>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>,
	LKML <linux-kernel@vger.kernel.org>,
	x86@kernel.org, Andi Kleen <andi@firstfloor.org>,
	Jens Axboe <jens.axboe@oracle.com>
Subject: Re: [PATCH 0 of 9] x86/smp function calls: convert x86 tlb flushes to use function calls [POST 2]
Date: Tue, 19 Aug 2008 20:49:51 +1000	[thread overview]
Message-ID: <200808192049.51270.nickpiggin@yahoo.com.au> (raw)
In-Reply-To: <20080819102430.GD6722@elte.hu>

On Tuesday 19 August 2008 20:24, Ingo Molnar wrote:
> * Nick Piggin <nickpiggin@yahoo.com.au> wrote:
> > > At least we could/should perhaps standardize/generalize all the
> > > 'specific' IPI handlers into the smp_function_call() framework: if
> > > function address equals to a pre-cooked IPI entry point we could
> > > call that function without a kmalloc. As these are all hardwired,
> > > __builtin_is_constant_p() could come to the help as well. Hm?
> >
> > No, it's not just the function call but also payload, list entry for
> > queue, scoreboard of CPUs have processed it, a lock, etc etc etc.
> >
> > smp_call_function is *always* going to be heavier than a hard wired
> > special case, no matter how it is implemented. For such low level
> > performance critical functionality, I miss the days when people were
> > rabid about saving every cycle rather than every line of code ;)
>
> no, i was thinking about really high level hardwiring, i.e. hardwiring
> the _function pointer_ knowledge into smp_function_call().
>
> for example for the reschedule IPI, it would be hardwired on x86 to just
> call into the special IPI handler, via:
>
>   smp_call_function_mask(target_mask, smp_send_reschedule, NULL, 0);
>
> Exactly same cost and call sequence as a direct hardwired-to-IPI
> function call (and the same underlying mechanism) - just consolidated
> around a single cross-call API.

So it would magically use a different IPI vector, magically be callable
from interrupt context, have a different function type etc.? Why would
we do such a thing? If it doesn't walk like a duck and doesn't quack
like a duck, why should we call it a duck? ;)


> Same for all the other special cross-CPU handlers. That way some
> architectures would hardwire it, some wouldnt, etc.

I think the right way is just to keep the "special" classes of IPI-ish
functions (I guess reschedule and TLB flush importantly). The arch code
is still free to implement these using their call function or a special
vector or whatever.

  reply	other threads:[~2008-08-19 10:50 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-08-18 18:23 Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 1 of 9] x86: put tlb_flush_others() stats in debugfs Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 2 of 9] x86-32: use smp_call_function_mask for SMP TLB invalidations Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 3 of 9] x86-64: " Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 4 of 9] x86: make tlb_32|64 closer Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 5 of 9] x86: unify tlb.c Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 6 of 9] smp_function_call: add multiple queues for scalability Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 7 of 9] x86: add multiple smp_call_function queues Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 8 of 9] x86: make number of smp_call_function queues truely configurable Jeremy Fitzhardinge
2008-08-18 18:23 ` [PATCH 9 of 9] smp function calls: add kernel parameter to disable multiple queues Jeremy Fitzhardinge
2008-08-19  0:45 ` [PATCH 0 of 9] x86/smp function calls: convert x86 tlb flushes to use function calls [POST 2] Ingo Molnar
2008-08-19  1:28   ` Ingo Molnar
2008-08-19  6:18     ` Jeremy Fitzhardinge
2008-08-19  9:27       ` Ingo Molnar
2008-08-19 14:58         ` Jeremy Fitzhardinge
2008-08-19  9:45       ` Peter Zijlstra
2008-08-19 14:58         ` Jeremy Fitzhardinge
2008-08-19  5:37   ` Jeremy Fitzhardinge
2008-08-19  9:31     ` Ingo Molnar
2008-08-19  9:56       ` Nick Piggin
2008-08-19 10:20         ` Ingo Molnar
2008-08-19 11:08           ` Nick Piggin
2008-08-19 11:44             ` Ingo Molnar
2008-08-19 10:24         ` Ingo Molnar
2008-08-19 10:49           ` Nick Piggin [this message]
2008-08-19 10:31         ` Andi Kleen
2008-08-19 11:04           ` Nick Piggin
2008-08-19 11:20             ` Andi Kleen
2008-08-19  7:32   ` Andi Kleen
2008-08-19  7:44     ` Jeremy Fitzhardinge
2008-08-19  7:48       ` Andi Kleen
2008-08-19  8:04         ` Jeremy Fitzhardinge

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=200808192049.51270.nickpiggin@yahoo.com.au \
    --to=nickpiggin@yahoo.com.au \
    --cc=andi@firstfloor.org \
    --cc=jens.axboe@oracle.com \
    --cc=jeremy@goop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=x86@kernel.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

Powered by JetHome