On 8/5/07, Jeff Garzik <[email protected]> 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 [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
- References:
- Oops in 2.6.23-rc1-git9, arch/x86_64/pci/k8-bus.c::fill_mp_bus_to_cpumask()
- From: Chuck Ebbert <[email protected]>
- Re: Oops in 2.6.23-rc1-git9, arch/x86_64/pci/k8-bus.c::fill_mp_bus_to_cpumask()
- From: Andrew Morton <[email protected]>
- Re: Oops in 2.6.23-rc1-git9, arch/x86_64/pci/k8-bus.c::fill_mp_bus_to_cpumask()
- From: Andi Kleen <[email protected]>
- Re: Oops in 2.6.23-rc1-git9, arch/x86_64/pci/k8-bus.c::fill_mp_bus_to_cpumask()
- From: Muli Ben-Yehuda <[email protected]>
- Re: Oops in 2.6.23-rc1-git9, arch/x86_64/pci/k8-bus.c::fill_mp_bus_to_cpumask()
- From: "Yinghai Lu" <[email protected]>
- [PATCH/RFT] finish i386 and x86-64 sysdata conversion
- From: Muli Ben-Yehuda <[email protected]>
- Re: [PATCH/RFT] finish i386 and x86-64 sysdata conversion
- From: "Yinghai Lu" <[email protected]>
- Re: [PATCH/RFT] finish i386 and x86-64 sysdata conversion
- From: Muli Ben-Yehuda <[email protected]>
- Re: [PATCH/RFT] finish i386 and x86-64 sysdata conversion
- From: "Yinghai Lu" <[email protected]>
- Re: [PATCH/RFT] finish i386 and x86-64 sysdata conversion
- From: Jeff Garzik <[email protected]>
- Oops in 2.6.23-rc1-git9, arch/x86_64/pci/k8-bus.c::fill_mp_bus_to_cpumask()
- Prev by Date: Re: [PATCH 00/23] per device dirty throttling -v8
- Next by Date: Re: [patch] implement smarter atime updates support, v2
- Previous by thread: Re: [PATCH/RFT] finish i386 and x86-64 sysdata conversion
- Next by thread: Re: [PATCH/RFT] finish i386 and x86-64 sysdata conversion
- Index(es):