[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <86802c440708051341q66aa1et3ea612beeab0f299@mail.gmail.com>
Date: Sun, 5 Aug 2007 13:41:24 -0700
From: "Yinghai Lu" <yhlu.kernel@...il.com>
To: "Jeff Garzik" <jeff@...zik.org>
Cc: "Muli Ben-Yehuda" <muli@...ibm.com>, "Andi Kleen" <ak@...e.de>,
"Andrew Morton" <akpm@...ux-foundation.org>, riku.seppala@...p.net,
"Andy Whitcroft" <apw@...dowen.org>,
"Chuck Ebbert" <cebbert@...hat.com>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH/RFT] finish i386 and x86-64 sysdata conversion
On 8/5/07, Jeff Garzik <jeff@...zik.org> wrote:
> Yinghai Lu wrote:
> > pci_scan_bus_on_node(int bus, struct pci_ops *ops, int node)
> > x86_pci_scan_root_bus(int bus)
> > {
> > pci_scan_bus_on_node(bus, &pci_root_ops, -1);
> > }
> >
> > i need node as one param for my patch later in irq.c and legacy.c
>
>
> It is a mistake to start coding NUMA details into pci scan functions.
>
> Anywhere the current code does not set the NUMA node, set it to -1 or
> some other default value.
Can you check
http://lkml.org/lkml/2007/7/26/377
http://lkml.org/lkml/2007/7/26/378
http://lkml.org/lkml/2007/7/26/379
it will make sure numa_node on device get correct value after pci scan.
esp for k8 system with second peer root bus on second node.
Thanks
Yinghai Lu
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists