All of lore.kernel.org
 help / color / mirror / Atom feed
* IRQ range in domain 0
@ 2005-08-25 11:12 John Que
  0 siblings, 0 replies; 3+ messages in thread
From: John Que @ 2005-08-25 11:12 UTC (permalink / raw)
  To: Xen-devel

Hello, 
  I am running Xen-Unstable on intel x386 , with one CPU ; When running 
cat /proc/interrupts on Domain 0  I see the following:

          CPU0
  1:       1424        Phys-irq  i8042
  9:          0        Phys-irq  acpi
 14:     421055        Phys-irq  ide0
 15:         16        Phys-irq  ide1
 17:       4419        Phys-irq  eth0
 20:      10884        Phys-irq  ohci_hcd:usb1
 21:          0        Phys-irq  ohci_hcd:usb2
256:          0     Dynamic-irq  ctrl-if
257:      77411     Dynamic-irq  timer0
258:          0     Dynamic-irq  console
259:          0     Dynamic-irq  net-be-dbg
NMI:          0
LOC:          0
ERR:          0
MIS:          0

can I deduce from this that the number of available physical IRQ is
higher than 15?
What is strange to me is that on an ordinary linux kernel (not a
xen-patched kernel ) , there can be up to 15 interrupts,and in all
cases I know, they are in the range 0-14.
I don't remeber I saw a phiyscal interrupt whose number is higher than 14
on a standard x386 platform.

Also according to "Unerstanding the Linux Kernel" book,chapter 4: 
"Tradional PICs are implemented by connecting "in cascade" two
8259A-style external chips.Each chip can handle up to eight different
IRQ input lines. Since the INT output line of the slave PIC is
connected to the IRQ2 pin of the master PIC, the number of available
IRQ lines is limited to 15."


Any ideas?
Regards
John Que.

^ permalink raw reply	[flat|nested] 3+ messages in thread

* RE: IRQ range in domain 0
@ 2005-08-25 11:13 Petersson, Mats
  0 siblings, 0 replies; 3+ messages in thread
From: Petersson, Mats @ 2005-08-25 11:13 UTC (permalink / raw)
  To: John Que, Xen-devel

1. The APIC that is included in almost every CPU produced today
(certainly all PC processors produced today) is capable of more than 15
inputs (as I understand it, there's 256 "inputs".

2. Interupts with numbers higher than 256 are "virtual interrupts",
which is a "XEN thing", and they are not REAL interrupts from hardware,
but signalling within XEN to (for example) wake up another Domain. 

This is to the best of my understanding, and I have spent no time trying
to trace, understand or research any of this, so if you're going to use
any of the above for anything serious, I suggest you do some reasearch
to confirm or revise the above statements.

--
Mats
> -----Original Message-----
> From: xen-devel-bounces@lists.xensource.com 
> [mailto:xen-devel-bounces@lists.xensource.com] On Behalf Of John Que
> Sent: 25 August 2005 12:13
> To: Xen-devel@lists.xensource.com
> Subject: [Xen-devel] IRQ range in domain 0
> 
> Hello,
>   I am running Xen-Unstable on intel x386 , with one CPU ; 
> When running cat /proc/interrupts on Domain 0  I see the following:
> 
>           CPU0
>   1:       1424        Phys-irq  i8042
>   9:          0        Phys-irq  acpi
>  14:     421055        Phys-irq  ide0
>  15:         16        Phys-irq  ide1
>  17:       4419        Phys-irq  eth0
>  20:      10884        Phys-irq  ohci_hcd:usb1
>  21:          0        Phys-irq  ohci_hcd:usb2
> 256:          0     Dynamic-irq  ctrl-if
> 257:      77411     Dynamic-irq  timer0
> 258:          0     Dynamic-irq  console
> 259:          0     Dynamic-irq  net-be-dbg
> NMI:          0
> LOC:          0
> ERR:          0
> MIS:          0
> 
> can I deduce from this that the number of available physical 
> IRQ is higher than 15?
> What is strange to me is that on an ordinary linux kernel 
> (not a xen-patched kernel ) , there can be up to 15 
> interrupts,and in all cases I know, they are in the range 0-14.
> I don't remeber I saw a phiyscal interrupt whose number is 
> higher than 14 on a standard x386 platform.
> 
> Also according to "Unerstanding the Linux Kernel" book,chapter 4: 
> "Tradional PICs are implemented by connecting "in cascade" 
> two 8259A-style external chips.Each chip can handle up to 
> eight different IRQ input lines. Since the INT output line of 
> the slave PIC is connected to the IRQ2 pin of the master PIC, 
> the number of available IRQ lines is limited to 15."
> 
> 
> Any ideas?
> Regards
> John Que.
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel
> 

^ permalink raw reply	[flat|nested] 3+ messages in thread

* RE: IRQ range in domain 0
@ 2005-08-25 12:14 James Harper
  0 siblings, 0 replies; 3+ messages in thread
From: James Harper @ 2005-08-25 12:14 UTC (permalink / raw)
  To: John Que, Xen-devel

Something to do with APIC (Advanced Programmable Interrupt Controller) I
think. Here's the output of one system...

           CPU0
  0: 2548267677  local-APIC-edge  timer
  1:      16419    IO-APIC-edge  i8042
  9:          0   IO-APIC-level  acpi
 11:  211183161   IO-APIC-level  ohci_hcd
 14:          2    IO-APIC-edge  ide2
169:  230697393   IO-APIC-level  ide0, ide1
177:  247537790   IO-APIC-level  eth0
201:         63   IO-APIC-level  aic7xxx
209:  185403163   IO-APIC-level  eth1
217:  126336295   IO-APIC-level  eth2
NMI:          0
LOC: 2549847962
ERR:      58866
MIS:          0


> -----Original Message-----
> From: xen-devel-bounces@lists.xensource.com [mailto:xen-devel-
> bounces@lists.xensource.com] On Behalf Of John Que
> Sent: Thursday, 25 August 2005 21:13
> To: Xen-devel@lists.xensource.com
> Subject: [Xen-devel] IRQ range in domain 0
> 
> Hello,
>   I am running Xen-Unstable on intel x386 , with one CPU ; When
running
> cat /proc/interrupts on Domain 0  I see the following:
> 
>           CPU0
>   1:       1424        Phys-irq  i8042
>   9:          0        Phys-irq  acpi
>  14:     421055        Phys-irq  ide0
>  15:         16        Phys-irq  ide1
>  17:       4419        Phys-irq  eth0
>  20:      10884        Phys-irq  ohci_hcd:usb1
>  21:          0        Phys-irq  ohci_hcd:usb2
> 256:          0     Dynamic-irq  ctrl-if
> 257:      77411     Dynamic-irq  timer0
> 258:          0     Dynamic-irq  console
> 259:          0     Dynamic-irq  net-be-dbg
> NMI:          0
> LOC:          0
> ERR:          0
> MIS:          0
> 
> can I deduce from this that the number of available physical IRQ is
> higher than 15?
> What is strange to me is that on an ordinary linux kernel (not a
> xen-patched kernel ) , there can be up to 15 interrupts,and in all
> cases I know, they are in the range 0-14.
> I don't remeber I saw a phiyscal interrupt whose number is higher than
14
> on a standard x386 platform.
> 
> Also according to "Unerstanding the Linux Kernel" book,chapter 4:
> "Tradional PICs are implemented by connecting "in cascade" two
> 8259A-style external chips.Each chip can handle up to eight different
> IRQ input lines. Since the INT output line of the slave PIC is
> connected to the IRQ2 pin of the master PIC, the number of available
> IRQ lines is limited to 15."
> 
> 
> Any ideas?
> Regards
> John Que.
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xensource.com
> http://lists.xensource.com/xen-devel

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2005-08-25 12:14 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2005-08-25 11:12 IRQ range in domain 0 John Que
  -- strict thread matches above, loose matches on Subject: below --
2005-08-25 11:13 Petersson, Mats
2005-08-25 12:14 James Harper

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.