mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Jens Axboe <jens.axboe@oracle.com>
To: Avi Kivity <avi@qumranet.com>
Cc: linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org,
	npiggin@suse.de, torvalds@linux-foundation.org
Subject: Re: [PATCH 1/11] Add generic helpers for arch IPI function calls
Date: Tue, 22 Apr 2008 11:22:30 +0200	[thread overview]
Message-ID: <20080422092230.GW12774@kernel.dk> (raw)
In-Reply-To: <480DACDD.7040108@qumranet.com>

On Tue, Apr 22 2008, Avi Kivity wrote:
> Jens Axboe wrote:
> >This adds kernel/smp.c which contains helpers for IPI function calls. In
> >addition to supporting the existing smp_call_function() in a more efficient
> >manner, it also adds a more scalable variant called 
> >smp_call_function_single()
> >for calling a given function on a single CPU only.
> >
> >The core of this is based on the x86-64 patch from Nick Piggin, lots of
> >changes since then. "Alan D. Brunelle" <Alan.Brunelle@hp.com> has
> >contributed lots of fixes and suggestions as well.
> >
> >+int smp_call_function_single(int cpu, void (*func) (void *info), void 
> >*info,
> >+			     int retry, int wait)
> >+{
> >+	unsigned long flags;
> >+	/* prevent preemption and reschedule on another processor */
> >+	int me = get_cpu();
> >+	int ret = 0;
> >+
> >+	/* Can deadlock when called with interrupts disabled */
> >+	WARN_ON(wait && irqs_disabled());
> >+
> >+	if (cpu == me) {
> >+		local_irq_save(flags);
> >+		func(info);
> >+		local_irq_restore(flags);
> >+	} else {
> >+		struct call_single_data d;
> >+		struct call_single_data *data;
> >+
> >+		if (!wait) {
> >+			data = kmalloc(sizeof(*data), GFP_ATOMIC);
> >+			if (unlikely(!data)) {
> >+				ret = -ENOMEM;
> >+				goto out;
> >+			}
> >+			data->flags = CSD_FLAG_ALLOC;
> >+		} else {
> >+			data = &d;
> >+			data->flags = CSD_FLAG_WAIT;
> >+		}
> >+
> >  
> 
> Instead of introducing a rare error case, how about falling back to the 
> wait case if the allocation fails?
> 
> Of course, if the called function relies on the calling cpu doing 
> something else, then this fails, but I don't think anybody would do 
> that?  On the other hand, there is at least one use of 
> smp_call_function_single() with !wait, which doesn't check the error return.

Sure, either failling back to waiting, or add a static call_single_data
like it exists for smp_call_function(). In reality it'll never happen,
so the fallback static structure appeals the most to me.

-- 
Jens Axboe


  reply	other threads:[~2008-04-22  9:22 UTC|newest]

Thread overview: 84+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-04-22  7:57 [PATCH 0/11] Generic smp_call_function() and friends Jens Axboe
2008-04-22  7:57 ` [PATCH 1/11] Add generic helpers for arch IPI function calls Jens Axboe
2008-04-22  9:16   ` Avi Kivity
2008-04-22  9:22     ` Jens Axboe [this message]
2008-04-22 11:14       ` Jens Axboe
2008-04-22 13:00         ` Peter Zijlstra
2008-04-22 14:25           ` Jens Axboe
2008-04-22 14:38             ` Avi Kivity
2008-04-22 14:43               ` Peter Zijlstra
2008-04-22 14:47                 ` Avi Kivity
2008-04-22 14:53               ` Jens Axboe
2008-04-22 14:43   ` Linus Torvalds
2008-04-22 14:51     ` Jens Axboe
2008-04-22 15:01       ` Linus Torvalds
2008-04-22 16:49         ` Jens Axboe
2008-04-22 17:04           ` Jens Axboe
2008-04-22 17:13             ` Jens Axboe
2008-04-22 17:29               ` Linus Torvalds
2008-04-22 18:23                 ` Jens Axboe
2008-04-22 18:39                   ` Linus Torvalds
2008-04-22 14:58     ` Linus Torvalds
2008-04-22 15:07       ` Jens Axboe
2008-04-22 23:12   ` Mark Lord
2008-04-23  7:24     ` Jens Axboe
2008-04-23 13:42       ` Mark Lord
2008-04-23 13:51         ` Jens Axboe
2008-04-23 14:46           ` Mark Lord
2008-04-24 10:59             ` Jens Axboe
2008-04-24 12:44               ` Mark Lord
2008-04-24 21:30                 ` Rafael J. Wysocki
2008-04-25 11:08                 ` Pavel Machek
2008-04-26  8:04               ` Pavel Machek
2008-04-28 15:13                 ` Mark Lord
2008-05-01 16:23                   ` Pavel Machek
2008-04-22  7:57 ` [PATCH 2/11] x86: convert to generic helpers for " Jens Axboe
2008-04-22  8:38   ` Sam Ravnborg
2008-04-22  8:43     ` Jens Axboe
2008-04-22 11:15       ` Jens Axboe
2008-04-22  8:47   ` Ingo Molnar
2008-04-22  8:48     ` Jacek Luczak
2008-04-22  8:56       ` Jens Axboe
2008-04-22  9:04         ` Jacek Luczak
2008-04-22  8:52     ` Jens Axboe
2008-04-26  8:59     ` Jeremy Fitzhardinge
2008-04-22  7:57 ` [PATCH 3/11] powerpc: " Jens Axboe
2008-04-22 12:03   ` Paul Mackerras
2008-04-22 12:13     ` Jens Axboe
2008-04-22 12:42       ` Paul Mackerras
2008-04-22 18:51         ` Jens Axboe
2008-04-22  7:57 ` [PATCH 4/11] ia64: " Jens Axboe
2008-04-22  7:57 ` [PATCH 5/11] alpha: " Jens Axboe
2008-04-22  7:57 ` [PATCH 6/11] arm: " Jens Axboe
2008-04-22 15:00   ` Catalin Marinas
2008-04-22 18:43     ` Jens Axboe
2008-04-22  7:57 ` [PATCH 7/11] m32r: " Jens Axboe
2008-04-22  7:57 ` [PATCH 8/11] mips: " Jens Axboe
2008-04-22  7:57 ` [PATCH 9/11] parisc: " Jens Axboe
2008-04-22 14:09   ` Kyle McMartin
2008-04-22 14:27     ` Jens Axboe
2008-04-22 14:30       ` Kyle McMartin
2008-04-22 14:49         ` Jens Axboe
2008-04-22  7:57 ` [PATCH 10/11] sh: " Jens Axboe
2008-04-22  7:57 ` [PATCH 11/11] s390: " Jens Axboe
2008-04-22  8:04   ` Martin Schwidefsky
2008-04-22  8:07     ` Jens Axboe
2008-04-22  7:57 ` Jens Axboe
2008-04-22  8:48 ` [PATCH 0/11] Generic smp_call_function() and friends Peter Zijlstra
2008-04-22 18:50 [PATCH 0/11] Generic smp_call_function() #2 Jens Axboe
2008-04-22 18:50 ` [PATCH 1/11] Add generic helpers for arch IPI function calls Jens Axboe
2008-04-22 20:17   ` Peter Zijlstra
2008-04-23  6:07     ` Jens Axboe
2008-04-23  6:32       ` Peter Zijlstra
2008-04-23  7:49         ` Jens Axboe
2008-04-23  7:50           ` Peter Zijlstra
2008-04-24 22:01   ` Russell King
2008-04-25  7:18     ` Jens Axboe
2008-04-26  6:28       ` Jeremy Fitzhardinge
2008-04-28  7:38         ` Jes Sorensen
2008-04-26  6:11   ` Andrew Morton
2008-04-26 14:13     ` James Bottomley
2008-04-27  0:58     ` Paul E. McKenney
2008-04-27 10:36       ` Jens Axboe
2008-04-27 10:30     ` Jens Axboe
2008-04-28 14:25     ` David Howells
2008-04-28 14:43       ` James Bottomley

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=20080422092230.GW12774@kernel.dk \
    --to=jens.axboe@oracle.com \
    --cc=avi@qumranet.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=npiggin@suse.de \
    --cc=torvalds@linux-foundation.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