Most (all) Intel SMP boards have the so-called 'IO-APIC', which is
an enhanced interrupt controller, able to route hardware interrupts
to multiple CPUs, or to CPU groups.

Linux supports the IO-APIC, but unfortunately there are broken boards
out there which make it unsafe to enable the IO-APIC unconditionally.
The Linux policy thus is to enable the IO-APIC only if it's 100% safe, ie.:

           - the board is on the 'whitelist'

        or - the board does not have PCI pins connected to the IO-APIC

        or - the user has overridden blacklisted settings with the
             pirq= boot option line.

Kernel messages tell you whether the board is 'safe'. If your box
boots with enabled IO-APIC IRQs, then you have nothing else to do. Your
/proc/interrupts will look like this one:

   ---------------------------->
   hell:~> cat /proc/interrupts
              CPU0       CPU1
     0:      90782          0   XT PIC   timer
     1:       4135       2375  IO-APIC   keyboard
     2:          0          0   XT PIC   cascade
     3:        851        807  IO-APIC   serial
     9:          6         22  IO-APIC   ncr53c8xx
    11:        307        154  IO-APIC   NE2000
    13:          4          0   XT PIC   fpu
    14:      56000      30610  IO-APIC   ide0
   NMI:          0
   IPI:          0
   <----------------------------

some interrupts will still be 'XT PIC', but this is not a problem, none
of those IRQ sources is 'heavy'.

If one of your boot messages says 'unlisted/blacklisted board, DISABLING
IO-APIC IRQs', then you should do this to get multi-CPU IO-APIC IRQs
running:

        A) if your board is unlisted, then mail to linux-smp to get
           it into either the white or the blacklist
        B) if your board is blacklisted, then figure out the appropriate
           pirq= option to get your system to boot


pirq= lines look like the following in /etc/lilo.conf:

        append="pirq=15,11,10"

the actual numbers depend on your system, on your PCI cards and on their
PCI slot position. Usually PCI slots are 'daisy chained' before they are
connected to the PCI chipset IRQ routing facility (the incoming PIRQ1-4
lines):

               ,-.        ,-.        ,-.        ,-.        ,-.
     PIRQ4 ----| |-.    ,-| |-.    ,-| |-.    ,-| |--------| |
               |S|  \  /  |S|  \  /  |S|  \  /  |S|        |S|
     PIRQ3 ----|l|-. `/---|l|-. `/---|l|-. `/---|l|--------|l|
               |o|  \/    |o|  \/    |o|  \/    |o|        |o|
     PIRQ2 ----|t|-./`----|t|-./`----|t|-./`----|t|--------|t|
               |1| /\     |2| /\     |3| /\     |4|        |5|
     PIRQ1 ----| |-  `----| |-  `----| |-  `----| |--------| |
               `-'        `-'        `-'        `-'        `-'

every PCI card emits a PCI IRQ, which can be INTA,INTB,INTC,INTD:

                               ,-.
                         INTD--| |
                               |S|
                         INTC--|l|
                               |o|
                         INTB--|t|
                               |x|
                         INTA--| |
                               `-'

These INTA-D PCI IRQs are always 'local to the card', their real meaning
depends on which slot they are in. If you look at the daisy chaining diagram,
a card in slot4, issuing INTA IRQ, it will end up as a signal on PIRQ2 of
the PCI chipset. Most cards issue INTA, this creates optimal distribution
between the PIRQ lines. (distributing IRQ sources properly is not a
necessity, PCI IRQs can be shared at will, but it's a good for performance
to have non shared interrupts). Slot5 should be used for videocards, they
do not use interrupts normally, thus they are not daisy chained either.

so if you have your SCSI card (IRQ11) in Slot1, Tulip card (IRQ9) in
Slot2, then you'll have to specify this pirq= line:

        append="pirq=11,9"

the following script tries to figure out such a default pirq= line from
your PCI configuration:

        echo -n pirq=; echo `scanpci | grep T_L | cut -c56-` | sed 's/ /,/g'

note that this script wont work if you have skipped a few slots or if your
board does not do default daisy-chaining. (or the IO-APIC has the PIRQ pins
connected in some strange way). E.g. if in the above case you have your SCSI
card (IRQ11) in Slot3, and have Slot1 empty:

        append="pirq=0,9,11"

[value '0' is a generic 'placeholder', reserved for empty (or non-IRQ emitting)
slots.]

generally, it's always possible to find out the correct pirq= settings, just
permute all IRQ numbers properly ... it will take some time though. An
'incorrect' pirq line will cause the booting process to hang, or a device
won't function properly (if it's inserted as eg. a module).

If you have 2 PCI buses, then you can use up to 8 pirq values. Although such
boards tend to have a good configuration and will be included in the
whitelist.

Be prepared that it might happen that you need some strange pirq line:

        append="pirq=0,0,0,0,0,0,9,11"

use smart try-and-err techniques to find out the correct pirq line ...


the following pirq line can be used to force a board into the whitelist:

        append="pirq=0"

[if your system works with no problems after this, then it should be added
to the official whitelist, contact us]

good luck and mail to linux-smp@vger.rutgers.edu or
linux-kernel@vger.rutgers.edu if you have any problems that are not covered
by this document.

-- mingo