public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Jarek Poplawski <jarkao2@o2.pl>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	LKML <linux-kernel@vger.kernel.org>, Ingo Molnar <mingo@elte.hu>,
	Stable Team <stable@kernel.org>,
	Jean-Baptiste Vignaud <vignaud@xandmail.fr>,
	"marcin.slusarz" <marcin.slusarz@gmail.com>
Subject: Re: [patch 3/3] genirq: mark io_apic level interrupts to avoid resend
Date: Mon, 13 Aug 2007 13:42:12 -0500	[thread overview]
Message-ID: <1187030532.5330.11.camel@localhost.localdomain> (raw)
In-Reply-To: <1187006835.12828.112.camel@chaos>


> handle_fasteoi_irq is special. It is used by ioapic and weird Powerpc
> hardware. We marked the ioapic level interrupts IRQ_LEVEL, so we wont
> get a resend on them (see kernel/irq/resend.c)

s/weird/sane :-)

More specifically, it's used by "intelligent" PICs that automatically do
the masking of the source (or internally handle priority levels) and
only need an "eoi" when the OS is finished processing the latest
interrupt. (On those PICs, the ack is generally an implicit part of
fetching the next pending interrupt, and the eoi consist of bringing the
current processor priority back to what it was before the interrupt
occured).

I also suspect that any hypervisor using a different method than this
one for paravirt irqs is broken :-)

Ben.



  parent reply	other threads:[~2007-08-13 19:10 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-08-12 15:46 [patch 0/3] [patch 0/3] genirq: Suppress resend of level interrupts Thomas Gleixner
2007-08-12 15:46 ` [patch 1/3] genirq: cleanup mismerge artifact Thomas Gleixner
2007-08-12 15:46 ` [patch 2/3] genirq: suppress resend of level interrupts Thomas Gleixner
2007-08-12 15:46 ` [patch 3/3] genirq: mark io_apic level interrupts to avoid resend Thomas Gleixner
2007-08-13 11:28   ` Jarek Poplawski
2007-08-13 12:07     ` Thomas Gleixner
2007-08-13 13:53       ` Jarek Poplawski
2007-08-13 14:16         ` Jarek Poplawski
2007-08-13 16:30         ` Thomas Gleixner
2007-08-14  7:12           ` Jarek Poplawski
2007-08-14  8:10             ` Thomas Gleixner
2007-08-14  9:23               ` Jarek Poplawski
2007-08-13 19:07         ` Benjamin Herrenschmidt
2007-08-14  8:01           ` Jarek Poplawski
2007-08-13 18:42       ` Benjamin Herrenschmidt [this message]
2007-08-14  7:08 ` [patch 0/3] [patch 0/3] genirq: Suppress resend of level interrupts Marcin Ślusarz

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=1187030532.5330.11.camel@localhost.localdomain \
    --to=benh@kernel.crashing.org \
    --cc=akpm@linux-foundation.org \
    --cc=jarkao2@o2.pl \
    --cc=linux-kernel@vger.kernel.org \
    --cc=marcin.slusarz@gmail.com \
    --cc=mingo@elte.hu \
    --cc=stable@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=vignaud@xandmail.fr \
    /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