Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-29 Thread Yunsheng Lin
On 2019/10/29 16:53, Michal Hocko wrote: > On Mon 28-10-19 17:20:33, Yunsheng Lin wrote: >> On 2019/10/12 15:40, Greg KH wrote: >>> On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: add pci and acpi maintainer cc linux-...@vger.kernel.org and linux-a...@vger.kernel.org >>

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-29 Thread Michal Hocko
On Mon 28-10-19 17:20:33, Yunsheng Lin wrote: > On 2019/10/12 15:40, Greg KH wrote: > > On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: > >> add pci and acpi maintainer > >> cc linux-...@vger.kernel.org and linux-a...@vger.kernel.org > >> > >> On 2019/10/11 19:15, Peter Zijlstra wrote

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-28 Thread Yunsheng Lin
On 2019/10/12 15:40, Greg KH wrote: > On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: >> add pci and acpi maintainer >> cc linux-...@vger.kernel.org and linux-a...@vger.kernel.org >> >> On 2019/10/11 19:15, Peter Zijlstra wrote: >>> On Fri, Oct 11, 2019 at 11:27:54AM +0800, Yunsheng L

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-16 Thread Yunsheng Lin
On 2019/10/16 0:58, Greg KH wrote: > On Tue, Oct 15, 2019 at 06:40:29PM +0800, Yunsheng Lin wrote: >> On 2019/10/14 17:25, Greg KH wrote: >>> On Mon, Oct 14, 2019 at 04:00:46PM +0800, Yunsheng Lin wrote: On 2019/10/12 18:47, Greg KH wrote: > On Sat, Oct 12, 2019 at 12:40:01PM +0200, Greg K

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-15 Thread Greg KH
On Tue, Oct 15, 2019 at 06:40:29PM +0800, Yunsheng Lin wrote: > On 2019/10/14 17:25, Greg KH wrote: > > On Mon, Oct 14, 2019 at 04:00:46PM +0800, Yunsheng Lin wrote: > >> On 2019/10/12 18:47, Greg KH wrote: > >>> On Sat, Oct 12, 2019 at 12:40:01PM +0200, Greg KH wrote: > On Sat, Oct 12, 2019 a

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-15 Thread Yunsheng Lin
On 2019/10/14 17:25, Greg KH wrote: > On Mon, Oct 14, 2019 at 04:00:46PM +0800, Yunsheng Lin wrote: >> On 2019/10/12 18:47, Greg KH wrote: >>> On Sat, Oct 12, 2019 at 12:40:01PM +0200, Greg KH wrote: On Sat, Oct 12, 2019 at 05:47:56PM +0800, Yunsheng Lin wrote: > On 2019/10/12 15:40, Greg

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-14 Thread Greg KH
On Mon, Oct 14, 2019 at 11:49:12AM +0200, Peter Zijlstra wrote: > On Mon, Oct 14, 2019 at 11:25:09AM +0200, Greg KH wrote: > > Good luck, I don't really think that most, if any, of this is needed, > > but hey, it's nice to clean it up where it can be :) > > Some of the virtual devices we have (tha

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-14 Thread Peter Zijlstra
On Mon, Oct 14, 2019 at 11:25:09AM +0200, Greg KH wrote: > Good luck, I don't really think that most, if any, of this is needed, > but hey, it's nice to clean it up where it can be :) Some of the virtual devices we have (that use devm) really ought to set the node too, like drivers/base/cpu.c and

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-14 Thread Greg KH
On Mon, Oct 14, 2019 at 04:00:46PM +0800, Yunsheng Lin wrote: > On 2019/10/12 18:47, Greg KH wrote: > > On Sat, Oct 12, 2019 at 12:40:01PM +0200, Greg KH wrote: > >> On Sat, Oct 12, 2019 at 05:47:56PM +0800, Yunsheng Lin wrote: > >>> On 2019/10/12 15:40, Greg KH wrote: > On Sat, Oct 12, 2019 a

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-14 Thread Yunsheng Lin
On 2019/10/12 18:47, Greg KH wrote: > On Sat, Oct 12, 2019 at 12:40:01PM +0200, Greg KH wrote: >> On Sat, Oct 12, 2019 at 05:47:56PM +0800, Yunsheng Lin wrote: >>> On 2019/10/12 15:40, Greg KH wrote: On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: > add pci and acpi maintaine

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-12 Thread Greg KH
On Sat, Oct 12, 2019 at 12:40:01PM +0200, Greg KH wrote: > On Sat, Oct 12, 2019 at 05:47:56PM +0800, Yunsheng Lin wrote: > > On 2019/10/12 15:40, Greg KH wrote: > > > On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: > > >> add pci and acpi maintainer > > >> cc linux-...@vger.kernel.org

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-12 Thread Greg KH
On Sat, Oct 12, 2019 at 05:47:56PM +0800, Yunsheng Lin wrote: > On 2019/10/12 15:40, Greg KH wrote: > > On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: > >> add pci and acpi maintainer > >> cc linux-...@vger.kernel.org and linux-a...@vger.kernel.org > >> > >> On 2019/10/11 19:15, Pete

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-12 Thread Yunsheng Lin
On 2019/10/12 15:40, Greg KH wrote: > On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: >> add pci and acpi maintainer >> cc linux-...@vger.kernel.org and linux-a...@vger.kernel.org >> >> On 2019/10/11 19:15, Peter Zijlstra wrote: >>> On Fri, Oct 11, 2019 at 11:27:54AM +0800, Yunsheng L

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-12 Thread Greg KH
On Sat, Oct 12, 2019 at 02:17:26PM +0800, Yunsheng Lin wrote: > add pci and acpi maintainer > cc linux-...@vger.kernel.org and linux-a...@vger.kernel.org > > On 2019/10/11 19:15, Peter Zijlstra wrote: > > On Fri, Oct 11, 2019 at 11:27:54AM +0800, Yunsheng Lin wrote: > >> But I failed to see why th

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-11 Thread Yunsheng Lin
add pci and acpi maintainer cc linux-...@vger.kernel.org and linux-a...@vger.kernel.org On 2019/10/11 19:15, Peter Zijlstra wrote: > On Fri, Oct 11, 2019 at 11:27:54AM +0800, Yunsheng Lin wrote: >> But I failed to see why the above is related to making node_to_cpumask_map() >> NUMA_NO_NODE aware?

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-11 Thread Peter Zijlstra
On Fri, Oct 11, 2019 at 11:27:54AM +0800, Yunsheng Lin wrote: > But I failed to see why the above is related to making node_to_cpumask_map() > NUMA_NO_NODE aware? Your initial bug is for hns3, which is a PCI device, which really _MUST_ have a node assigned. It not having one, is a straight up bug

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-10 Thread Yunsheng Lin
On 2019/10/10 15:32, Michal Hocko wrote: > On Thu 10-10-19 14:07:21, Yunsheng Lin wrote: >> On 2019/10/9 20:25, Robin Murphy wrote: >>> On 2019-10-08 9:38 am, Yunsheng Lin wrote: On 2019/9/25 18:41, Peter Zijlstra wrote: > On Wed, Sep 25, 2019 at 05:14:20PM +0800, Yunsheng Lin wrote: >

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-10 Thread Peter Zijlstra
On Wed, Oct 09, 2019 at 01:25:14PM +0100, Robin Murphy wrote: > On 2019-10-08 9:38 am, Yunsheng Lin wrote: > > On 2019/9/25 18:41, Peter Zijlstra wrote: > > > On Wed, Sep 25, 2019 at 05:14:20PM +0800, Yunsheng Lin wrote: > > > > From the discussion above, It seems making the node_to_cpumask_map()

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-10 Thread Michal Hocko
On Thu 10-10-19 14:07:21, Yunsheng Lin wrote: > On 2019/10/9 20:25, Robin Murphy wrote: > > On 2019-10-08 9:38 am, Yunsheng Lin wrote: > >> On 2019/9/25 18:41, Peter Zijlstra wrote: > >>> On Wed, Sep 25, 2019 at 05:14:20PM +0800, Yunsheng Lin wrote: > From the discussion above, It seems makin

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-09 Thread Yunsheng Lin
On 2019/10/9 20:25, Robin Murphy wrote: > On 2019-10-08 9:38 am, Yunsheng Lin wrote: >> On 2019/9/25 18:41, Peter Zijlstra wrote: >>> On Wed, Sep 25, 2019 at 05:14:20PM +0800, Yunsheng Lin wrote: From the discussion above, It seems making the node_to_cpumask_map() NUMA_NO_NODE aware is t

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-09 Thread Robin Murphy
On 2019-10-08 9:38 am, Yunsheng Lin wrote: On 2019/9/25 18:41, Peter Zijlstra wrote: On Wed, Sep 25, 2019 at 05:14:20PM +0800, Yunsheng Lin wrote: From the discussion above, It seems making the node_to_cpumask_map() NUMA_NO_NODE aware is the most feasible way to move forwad. That's still wro

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-10-08 Thread Yunsheng Lin
On 2019/9/25 18:41, Peter Zijlstra wrote: > On Wed, Sep 25, 2019 at 05:14:20PM +0800, Yunsheng Lin wrote: >> From the discussion above, It seems making the node_to_cpumask_map() >> NUMA_NO_NODE aware is the most feasible way to move forwad. > > That's still wrong. Hi, Peter It seems this has tra

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-26 Thread Peter Zijlstra
On Thu, Sep 26, 2019 at 01:45:53PM +0200, Geert Uytterhoeven wrote: > Hi Peter, > > On Thu, Sep 26, 2019 at 11:42 AM Peter Zijlstra wrote: > > On Wed, Sep 25, 2019 at 03:25:44PM +0200, Michal Hocko wrote: > > > I am sorry but I still do not understand why you consider this whack a > > > mole bett

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-26 Thread Peter Zijlstra
On Thu, Sep 26, 2019 at 11:05:59AM +0200, Peter Zijlstra wrote: > On Wed, Sep 25, 2019 at 11:45:26PM +0200, Peter Zijlstra wrote: > > [7.149889] [Firmware Bug]: device: 'pci:7f': no node assigned on > > NUMA capable HW > > [7.882888] [Firmware Bug]: device: 'pci:ff': no node assign

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-26 Thread Geert Uytterhoeven
Hi Peter, On Thu, Sep 26, 2019 at 11:42 AM Peter Zijlstra wrote: > On Wed, Sep 25, 2019 at 03:25:44PM +0200, Michal Hocko wrote: > > I am sorry but I still do not understand why you consider this whack a > > mole better then simply live with the fact that NUMA_NO_NODE is a > > reality and that us

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-26 Thread Peter Zijlstra
On Wed, Sep 25, 2019 at 11:45:26PM +0200, Peter Zijlstra wrote: > [7.149889] [Firmware Bug]: device: 'pci:7f': no node assigned on NUMA > capable HW > [7.882888] [Firmware Bug]: device: 'pci:ff': no node assigned on NUMA > capable HW Going by the limited number of intel numa boxe

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-25 Thread Peter Zijlstra
On Wed, Sep 25, 2019 at 06:31:54PM +0200, Peter Zijlstra wrote: > On Wed, Sep 25, 2019 at 03:25:44PM +0200, Michal Hocko wrote: > > I am sorry but I still do not understand why you consider this whack a > > mole better then simply live with the fact that NUMA_NO_NODE is a > > reality and that using

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-25 Thread Peter Zijlstra
On Wed, Sep 25, 2019 at 03:25:44PM +0200, Michal Hocko wrote: > I am sorry but I still do not understand why you consider this whack a > mole better then simply live with the fact that NUMA_NO_NODE is a > reality and that using the full cpu mask is a reasonable answer to that. Because it doesn't m

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-25 Thread Michal Hocko
On Wed 25-09-19 12:40:40, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 03:19:39PM +0200, Michal Hocko wrote: > > > > The below would get rid of the PMU and workqueue warnings with no > > > side-effects (the device isn't used for anything except sysfs). > > > > Hardcoding to 0 is simply wrong,

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-25 Thread Peter Zijlstra
On Wed, Sep 25, 2019 at 05:14:20PM +0800, Yunsheng Lin wrote: > From the discussion above, It seems making the node_to_cpumask_map() > NUMA_NO_NODE aware is the most feasible way to move forwad. That's still wrong.

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-25 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 03:19:39PM +0200, Michal Hocko wrote: > > The below would get rid of the PMU and workqueue warnings with no > > side-effects (the device isn't used for anything except sysfs). > > Hardcoding to 0 is simply wrong, if the node0 is cpuless for example... It doesn't matter...

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-25 Thread Yunsheng Lin
On 2019/9/24 21:19, Michal Hocko wrote: > On Tue 24-09-19 14:59:36, Peter Zijlstra wrote: >> On Tue, Sep 24, 2019 at 02:43:25PM +0200, Peter Zijlstra wrote: >>> On Tue, Sep 24, 2019 at 02:25:00PM +0200, Michal Hocko wrote: On Tue 24-09-19 14:09:43, Peter Zijlstra wrote: >>> > We can push b

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Michal Hocko
On Tue 24-09-19 14:59:36, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 02:43:25PM +0200, Peter Zijlstra wrote: > > On Tue, Sep 24, 2019 at 02:25:00PM +0200, Michal Hocko wrote: > > > On Tue 24-09-19 14:09:43, Peter Zijlstra wrote: > > > > > > We can push back and say we don't respect the specif

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 02:43:25PM +0200, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 02:25:00PM +0200, Michal Hocko wrote: > > On Tue 24-09-19 14:09:43, Peter Zijlstra wrote: > > > > We can push back and say we don't respect the specification because it > > > is batshit insane ;-) > > > > He

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 02:25:00PM +0200, Michal Hocko wrote: > On Tue 24-09-19 14:09:43, Peter Zijlstra wrote: > > We can push back and say we don't respect the specification because it > > is batshit insane ;-) > > Here is my fingers crossed. > > [...] > > > Now granted; there's a number of v

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Michal Hocko
On Tue 24-09-19 14:09:43, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 01:54:01PM +0200, Michal Hocko wrote: > > On Tue 24-09-19 13:23:49, Peter Zijlstra wrote: > > > On Tue, Sep 24, 2019 at 12:56:22PM +0200, Michal Hocko wrote: > > [...] > > > > To be honest I really fail to see why to object t

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 01:54:01PM +0200, Michal Hocko wrote: > On Tue 24-09-19 13:23:49, Peter Zijlstra wrote: > > On Tue, Sep 24, 2019 at 12:56:22PM +0200, Michal Hocko wrote: > [...] > > > To be honest I really fail to see why to object to a simple semantic > > > that NUMA_NO_NODE imply all usab

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Yunsheng Lin
On 2019/9/24 19:58, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 07:44:28PM +0800, Yunsheng Lin wrote: >> From [1], there is a lot of devices with node id of NUMA_NO_NODE with the >> FW_BUG. >> >> [1] >> https://lore.kernel.org/lkml/5a188e2b-6c07-a9db-fbaa-561e9362d...@huawei.com/ > > So aside

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 07:44:28PM +0800, Yunsheng Lin wrote: > From [1], there is a lot of devices with node id of NUMA_NO_NODE with the > FW_BUG. > > [1] > https://lore.kernel.org/lkml/5a188e2b-6c07-a9db-fbaa-561e9362d...@huawei.com/ So aside of all the software devices which we can (and reall

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Michal Hocko
On Tue 24-09-19 13:23:49, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 12:56:22PM +0200, Michal Hocko wrote: [...] > > To be honest I really fail to see why to object to a simple semantic > > that NUMA_NO_NODE imply all usable cpus. Could you explain that please? > > Because it feels wrong. The

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Yunsheng Lin
On 2019/9/24 19:28, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 07:07:36PM +0800, Yunsheng Lin wrote: >> On 2019/9/24 17:25, Peter Zijlstra wrote: >>> On Tue, Sep 24, 2019 at 09:29:50AM +0800, Yunsheng Lin wrote: On 2019/9/24 4:34, Peter Zijlstra wrote: >>> > I'm saying the ACPI standa

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 07:07:36PM +0800, Yunsheng Lin wrote: > On 2019/9/24 17:25, Peter Zijlstra wrote: > > On Tue, Sep 24, 2019 at 09:29:50AM +0800, Yunsheng Lin wrote: > >> On 2019/9/24 4:34, Peter Zijlstra wrote: > > > >>> I'm saying the ACPI standard is wrong. Explain to me how it is > >>> p

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 12:56:22PM +0200, Michal Hocko wrote: > On Tue 24-09-19 11:17:14, Peter Zijlstra wrote: > > On Tue, Sep 24, 2019 at 09:47:51AM +0200, Michal Hocko wrote: > > > On Mon 23-09-19 22:34:10, Peter Zijlstra wrote: > > > > On Mon, Sep 23, 2019 at 06:52:35PM +0200, Michal Hocko wrot

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Yunsheng Lin
On 2019/9/24 17:25, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 09:29:50AM +0800, Yunsheng Lin wrote: >> On 2019/9/24 4:34, Peter Zijlstra wrote: > >>> I'm saying the ACPI standard is wrong. Explain to me how it is >>> physically possible to have a device without NUMA affinity in a NUMA >>> sy

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Michal Hocko
On Tue 24-09-19 11:17:14, Peter Zijlstra wrote: > On Tue, Sep 24, 2019 at 09:47:51AM +0200, Michal Hocko wrote: > > On Mon 23-09-19 22:34:10, Peter Zijlstra wrote: > > > On Mon, Sep 23, 2019 at 06:52:35PM +0200, Michal Hocko wrote: > > [...] > > > > I even the > > > > ACPI standard is considering t

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 09:29:50AM +0800, Yunsheng Lin wrote: > On 2019/9/24 4:34, Peter Zijlstra wrote: > > I'm saying the ACPI standard is wrong. Explain to me how it is > > physically possible to have a device without NUMA affinity in a NUMA > > system? > > > > 1) The fundamental interconnect

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Peter Zijlstra
On Tue, Sep 24, 2019 at 09:47:51AM +0200, Michal Hocko wrote: > On Mon 23-09-19 22:34:10, Peter Zijlstra wrote: > > On Mon, Sep 23, 2019 at 06:52:35PM +0200, Michal Hocko wrote: > [...] > > > I even the > > > ACPI standard is considering this optional. Yunsheng Lin has referred to > > > the specifi

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-24 Thread Michal Hocko
On Mon 23-09-19 22:34:10, Peter Zijlstra wrote: > On Mon, Sep 23, 2019 at 06:52:35PM +0200, Michal Hocko wrote: [...] > > I even the > > ACPI standard is considering this optional. Yunsheng Lin has referred to > > the specific part of the standard in one of the earlier discussions. > > Trying to gu

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-23 Thread Yunsheng Lin
On 2019/9/24 4:34, Peter Zijlstra wrote: > On Mon, Sep 23, 2019 at 06:52:35PM +0200, Michal Hocko wrote: >> On Mon 23-09-19 17:48:52, Peter Zijlstra wrote: > >> To the NUMA_NO_NODE itself. Your earlier email noted: >> : > + >> : > if ((unsigned)node >= nr_node_ids) { >> : >

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-23 Thread Peter Zijlstra
On Mon, Sep 23, 2019 at 06:52:35PM +0200, Michal Hocko wrote: > On Mon 23-09-19 17:48:52, Peter Zijlstra wrote: > To the NUMA_NO_NODE itself. Your earlier email noted: > : > + > : > if ((unsigned)node >= nr_node_ids) { > : > printk(KERN_WARNING > : > "cpumask_of_node(

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-23 Thread Michal Hocko
On Mon 23-09-19 17:48:52, Peter Zijlstra wrote: > On Mon, Sep 23, 2019 at 05:28:56PM +0200, Michal Hocko wrote: > > On Mon 23-09-19 17:15:19, Peter Zijlstra wrote: > > > > > diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c > > > > index 4123100e..9859acb 100644 > > > > --- a/arch/x86/mm/numa.c

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-23 Thread Peter Zijlstra
On Mon, Sep 23, 2019 at 05:28:56PM +0200, Michal Hocko wrote: > On Mon 23-09-19 17:15:19, Peter Zijlstra wrote: > > > diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c > > > index 4123100e..9859acb 100644 > > > --- a/arch/x86/mm/numa.c > > > +++ b/arch/x86/mm/numa.c > > > @@ -861,6 +861,9 @@ vo

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-23 Thread Michal Hocko
On Mon 23-09-19 17:15:19, Peter Zijlstra wrote: > On Tue, Sep 17, 2019 at 08:48:54PM +0800, Yunsheng Lin wrote: > > When passing the return value of dev_to_node() to cpumask_of_node() > > without checking if the device's node id is NUMA_NO_NODE, there is > > global-out-of-bounds detected by KASAN.

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-23 Thread Peter Zijlstra
On Tue, Sep 17, 2019 at 08:48:54PM +0800, Yunsheng Lin wrote: > When passing the return value of dev_to_node() to cpumask_of_node() > without checking if the device's node id is NUMA_NO_NODE, there is > global-out-of-bounds detected by KASAN. > > From the discussion [1], NUMA_NO_NODE really means

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-22 Thread Yunsheng Lin
On 2019/9/22 6:38, Paul Burton wrote: > Hi Yunsheng, > > On Tue, Sep 17, 2019 at 08:48:54PM +0800, Yunsheng Lin wrote: >> When passing the return value of dev_to_node() to cpumask_of_node() >> without checking if the device's node id is NUMA_NO_NODE, there is >> global-out-of-bounds detected by KA

Re: [PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-21 Thread Paul Burton
Hi Yunsheng, On Tue, Sep 17, 2019 at 08:48:54PM +0800, Yunsheng Lin wrote: > When passing the return value of dev_to_node() to cpumask_of_node() > without checking if the device's node id is NUMA_NO_NODE, there is > global-out-of-bounds detected by KASAN. > > From the discussion [1], NUMA_NO_NODE

[PATCH v6] numa: make node_to_cpumask_map() NUMA_NO_NODE aware

2019-09-17 Thread Yunsheng Lin
When passing the return value of dev_to_node() to cpumask_of_node() without checking if the device's node id is NUMA_NO_NODE, there is global-out-of-bounds detected by KASAN. >From the discussion [1], NUMA_NO_NODE really means no node affinity, which also means all cpus should be usable. So the cp