Re: PCI bus numbering in a system with multiple PCI controllers

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Saturday 20 February 2010 08:22:08 pm Matthew Wilcox wrote:
> On Sun, Feb 21, 2010 at 08:37:57AM +0530, Rajat Jain wrote:
> > 
> > I used to think that head host bridge / PCI controller is a domain in
> > itself. No?
> 
> Not necessarily.  You can have multiple PCI root bridges in a single domain.

As Matthew said, it's up to the hardware and firmware.  In the case
of the HP Itanium systems Matthew mentioned, firmware has historically
reported several host bridges as being in domain zero, but it would
be just as valid to report them as each bridge having its own domain.

Early on, we tripped over a few drivers that made assumptions like
"the bus/device/function is enough to uniquely identify a PCI device."
Obviously that breaks with multiple domains, so at the time, there was
less risk to keep all the host bridges in one domain.  But I'm not aware
of any current issues like that.

Bjorn
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[Index of Archives]     [DMA Engine]     [Linux Coverity]     [Linux USB]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [Greybus]

  Powered by Linux