From: Yinghai Lu <yinghai@kernel.org>
To: Rusty Russell <rusty@rustcorp.com.au>,
Ingo Molnar <mingo@elte.hu>,
"Eric W. Biederman" <ebiederm@xmission.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC] Correct behaviour of irq affinity?
Date: Tue, 24 Mar 2009 00:21:43 -0700 [thread overview]
Message-ID: <86802c440903240021y20abab87j3a780f8a17574716@mail.gmail.com> (raw)
In-Reply-To: <200903241619.03517.rusty@rustcorp.com.au>
On Mon, Mar 23, 2009 at 10:49 PM, Rusty Russell <rusty@rustcorp.com.au> wrote:
> The effect of setting desc->affinity (ie. from userspace via sysfs) has varied
> over time. In 2.6.27, the 32-bit code anded the value with cpu_online_map,
> and both 32 and 64-bit did that anding whenever a cpu was unplugged.
>
> 2.6.29 consolidated this into one routine (and fixed hotplug) but introduced
> another variation: anding the affinity with cfg->domain. Is this right, or
> should we just set it to what the user said? Or as now, indicate that we're
> restricting it.
>
> If we should change it, here's what the patch looks like against x86 tip
> (cpu_mask_to_apicid_and already takes cpu_online_mask into account):
>
> diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
> index 86827d8..30906cd 100644
> --- a/arch/x86/kernel/apic/io_apic.c
> +++ b/arch/x86/kernel/apic/io_apic.c
> @@ -592,10 +592,10 @@ set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
> if (assign_irq_vector(irq, cfg, mask))
> return BAD_APICID;
>
> - cpumask_and(desc->affinity, cfg->domain, mask);
> + cpumask_copy(desc->affinity, mask);
> set_extra_move_desc(desc, mask);
>
> - return apic->cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask);
> + return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
> }
>
> static void
>
cfg->domain for logical flat: will be ALL_CPUS
for phys flat (aka bigsmp on 32bit) will be one cpu set mask.
so desc->affinity: for logical will be not changed, but
set_desc_affinity() return will be changed. ( not add with
cpu_online_mask anymore)
when mask is 0x0f
for phys flat, desc->affinity will be changed to 0x0f from
0x01/0x02/0x04/08, return set_desc_affinity is not changed.
so /proc/irq/xx/smp_affinity will be changed. and it does reflect that
actually affinity.
so this patch looks not right.
YH
next prev parent reply other threads:[~2009-03-24 7:21 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-24 5:49 Rusty Russell
2009-03-24 7:21 ` Yinghai Lu [this message]
2009-03-24 12:52 ` Rusty Russell
2009-03-24 20:36 ` Yinghai Lu
2009-03-24 12:39 ` Eric W. Biederman
2009-03-24 19:49 ` Yinghai Lu
2009-03-24 20:23 ` [PATCH] x86: fix set_extra_move_desc calling Yinghai Lu
2009-03-24 21:15 ` [tip:x86/apic] " Yinghai Lu
2009-03-24 21:15 ` [PATCH 1/3] " Yinghai Lu
2009-03-24 21:16 ` [PATCH 2/3] x86: use default_cpu_mask_to_apicid for 64bit Yinghai Lu
2009-03-24 21:30 ` [tip:x86/apic] " Yinghai Lu
2009-03-24 21:34 ` Ingo Molnar
2009-03-24 21:42 ` [PATCH 3/3] x86: Correct behaviour of irq affinity -v2 Yinghai Lu
2009-03-24 21:17 ` [PATCH 3/3] x86: Correct behaviour of irq affinity Yinghai Lu
2009-03-24 21:30 ` [tip:x86/apic] " Rusty Russell
2009-03-25 17:51 ` Rusty Russell
2009-03-25 0:33 ` [RFC] Correct behaviour of irq affinity? Rusty Russell
2009-03-25 0:59 ` Rusty Russell
2009-03-25 1:03 ` Yinghai Lu
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=86802c440903240021y20abab87j3a780f8a17574716@mail.gmail.com \
--to=yinghai@kernel.org \
--cc=ebiederm@xmission.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rusty@rustcorp.com.au \
--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
all inboxes | Powered by JetHome®