linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: "Grant Likely" <grant.likely@secretlab.ca>
To: "Matt Sealey" <matt@genesi-usa.com>
Cc: linuxppc-dev@ozlabs.org, "S. Fricke" <silvio.fricke@gmail.com>
Subject: Re: [NEWBIE] Interrupt-problem mpc5200
Date: Fri, 14 Sep 2007 08:53:40 -0600	[thread overview]
Message-ID: <fa686aa40709140753sb3e0e9cv28fa5215f4db3a@mail.gmail.com> (raw)
In-Reply-To: <46EA8CD7.2050304@genesi-usa.com>

On 9/14/07, Matt Sealey <matt@genesi-usa.com> wrote:
> Grant!
>
> I have a newbie question which I never had properly answered. On the
> MPC52xx and specifically regarding the device tree, how are interrupt
> numbers assigned?
>
> On Efika (and in the DT docs) it's basically the X Y Z where X is the
> type (critical, main, peripheral, sdma), Y is the number of the
> interrupt, and Z is it's sense level.
>
> However while X and Z are easy to derive, how do you work out what Y
> is meant to be given a device? Is it a bit number in the interrupt
> register, or the value of the encoded interrupt register or something
> else algorithmically determined?
>
> I am just finding the code in Linux that derives this number fairly
> elusive (the irq setup function for the mpc52xx platform is truly
> sparse, irq_of_find_and_map isn't much help). Maybe I am just not
> looking in the right place but not being an MPC52xx PIC Expert I
> wouldn't even know where to start...

The l2 irq numbers map directly to the interrupt numbers listed in the
5200b user guide.  For example, on p7-11, the masks are listed for
main interrupts 0 through 16.  and on p7-17,18, the peripherial
interrupts are listed as numbered from 0 to 23 (but notice that it
does *not* line up with bit positions).

However, it is interesting to note that other than in the register
definitions, I don't think there is anywhere in the 5200b user manual
that simple lists the interrupt numbers for each interrupt type.

Cheers,
g.
>
> --
> Matt Sealey <matt@genesi-usa.com>
> Genesi, Manager, Developer Relations
>
> Grant Likely wrote:
> > On 9/11/07, S. Fricke <silvio.fricke@googlemail.com> wrote:
> >> Hello,
> >>
> >>>> [...]
> >>>>     intr = mpc52xx_find_and_map("mpc52xx-pic");
> >>>>     if(!intr) {
> >>>>         panic(__FILE__ ": mpc52xx-pic - MAP failed");
> >>>>     }
> >>>>
> >>>>     set_irq_chip(MPC52xx_IRQ2, &my_irq_chip);
> >>> You probably don't want to do this (unless you are cascading IRQs to
> >>> custom external hardware).  All you should need is the call to
> >>> request_irq() to register your irq handler, and code in your ISR
> >>> handler to clear the interrupt condition.
> >>>
> >>> You do *NOT* want to program the interrupt controller directly.  The
> >>> mpc5200 interrupt controller already has a driver.  Don't go twiddling
> >>> the registers manually.
> >> OK!
> >>
> >> I have tried it before and i get a "-ENOSYS" returned.
> >>
> >> My code was/is now:
> >> --==>
> >> request_irq(MPC52xx_IRQ2, intmod_isr, IRQF_DISABLED , "intmod",
> >>             INTMOD_IRQ_BOARD);
> >> <==--
> >>
> >> I have looked up "kernel/irq/manage.c". "-ENOSYS" is returned on function
> >> "setup_irq" because the used irq(MPC52xx_IRQ2) is the same as no_irq_chip.
> >>
> >> THE MPC52xx_IRQ2 is a excerpt from "include/ppc/mpc52xx.h" (per copy
> >> paste), but mpc52xx is (now) a powerpc-arch. What is the desired value for
> >> IRQ-2 on a mpc5200b?
> >
> > The irq number you pass into request_irq is a system-wide irq number;
> > it doesn't necessarily map directly onto the MPC52xx irq number.
> > Typically, you'd have a node for your device in the device tree which
> > has a phandle back to the interrupt node and you would use
> > irq_of_parse_and_map() to map it back to a system-wide irq number.
> >
> > Otherwise, you need to call of_irq_map_raw with the pointer to the
> > 52xx interrupt controller node and the interrupt number in the form
> > expected by the device tree.  (But adding a device tree node for your
> > device is far easier).
> >
> > Cheers,
> > g.
> >
>


-- 
Grant Likely, B.Sc., P.Eng.
Secret Lab Technologies Ltd.
grant.likely@secretlab.ca
(403) 399-0195

  reply	other threads:[~2007-09-14 14:53 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-09-06 13:30 [NEWBIE] Interrupt-problem mpc5200 S. Fricke
2007-09-11 12:41 ` S. Fricke
2007-09-11 14:19   ` Grant Likely
2007-09-11 18:28     ` S. Fricke
2007-09-11 19:05       ` Grant Likely
2007-09-12 18:30         ` S. Fricke
2007-09-12 19:29           ` Grant Likely
2007-09-19  7:16             ` S. Fricke
2007-09-19 14:31               ` Grant Likely
2007-09-14 13:29         ` Matt Sealey
2007-09-14 14:53           ` Grant Likely [this message]
2007-09-14 15:18             ` Matt Sealey
2007-09-14 15:49               ` Grant Likely
2007-09-14 16:04                 ` Matt Sealey

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=fa686aa40709140753sb3e0e9cv28fa5215f4db3a@mail.gmail.com \
    --to=grant.likely@secretlab.ca \
    --cc=linuxppc-dev@ozlabs.org \
    --cc=matt@genesi-usa.com \
    --cc=silvio.fricke@gmail.com \
    /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;
as well as URLs for NNTP newsgroup(s).