On 02.02.16 15:39:15, Ganapatrao Kulkarni wrote:
> Ganapatrao Kulkarni (8):
> arm64, numa: adding numa support for arm64 platforms.
> Documentation, dt, numa: dt bindings for numa.
> dt, numa: adding numa dt binding implementation.
> arm64, numa : Enable numa dt for arm64 platforms.
>
On Saturday 30 January 2016 08:37 AM, Sukadev Bhattiprolu wrote:
> From a1aa992fb25fb8e98a5c5724376ae8cc91463de3 Mon Sep 17 00:00:00 2001
> From: Sukadev Bhattiprolu
> Date: Mon, 25 Jan 2016 23:05:36 -0500
> Subject: [PATCH 2/2] powerpc/perf/hv-24x7: Display change
Create sysfs attributes to export throttle information in
/sys/devices/system/cpu/cpufreq/chipX. The newly added sysfs files are as
follows:
1)/sys/devices/system/cpu/cpufreq/chipX/throttle_table
This table gives the detailed information on number of times Pmax is
limited to different frequencies
Currently we use printk message to notify the throttle event. But this
can flood the console if the cpu is throttled frequently. So replace the
printk with the tracepoint to notify the throttle event. And also events
like throttle below nominal frequency and OCC_RESET are reduced to
In the kworker_thread powernv_cpufreq_work_fn(), we can end up
sending an IPI to a cpu going offline. This is a rare corner case
which is fixed using {get/put}_online_cpus(). Along with this fix,
this patch adds changes to do oneshot cpumask_{clear/and} operation.
Suggested-by: Shreyas B Prabhu
Madhavan Srinivasan [ma...@linux.vnet.ibm.com] wrote:
>
>
> On Saturday 30 January 2016 08:37 AM, Sukadev Bhattiprolu wrote:
> > From a1aa992fb25fb8e98a5c5724376ae8cc91463de3 Mon Sep 17 00:00:00 2001
> > From: Sukadev Bhattiprolu
> > Date: Mon, 25 Jan 2016 23:05:36
This will free the dynamically allocated memory of 'chips' on
module exit.
Signed-off-by: Shilpasri G Bhat
Reviewed-by: Gautham R. Shenoy
Acked-by: Viresh Kumar
---
Changes from v7:
- Minor typo fix in the commit
Agreed, raised an eyebrow initially when select ppc64 and 32 :D
I'll give a word on the trackpad issue later, cant remember seeing any
changes that ought effect it really. guess the compile is done in a good
hour or so, took the tiime to slim it down to someting reasonable
Thanks man
On 2 Feb
cpu_to_chip_id() does a DT walk through to find out the chip id by
taking a contended device tree lock. This adds an unnecessary overhead
in a hot path. So instead of calling cpu_to_chip_id() everytime cache
the chip ids for all cores in the array 'core_to_chip_map' and use it
in the hotpath.
In POWER8, OCC(On-Chip-Controller) can throttle the frequency of the
CPU when the chip crosses its thermal and power limits. Currently,
powernv-cpufreq driver detects and reports this event as a console
message. Some machines may not sustain the max turbo frequency in all
conditions and can be
--- Begin Message ---
On Thu, 28 Jan 2016, David Rientjes wrote:
> On Thu, 28 Jan 2016, Christian Borntraeger wrote:
>
> > Indeed, I only touched the identity mapping and dump stack.
> > The question is do we really want to change free_init_pages as well?
> > The unmapping during runtime causes
On 02/02/2016 10:51 PM, David Rientjes wrote:
> On Thu, 28 Jan 2016, David Rientjes wrote:
>
>> On Thu, 28 Jan 2016, Christian Borntraeger wrote:
>>
>>> Indeed, I only touched the identity mapping and dump stack.
>>> The question is do we really want to change free_init_pages as well?
>>> The
On Tue, 2 Feb 2016, Petr Mladek wrote:
> Note that TOC is not set only when the problematic functions are
> compiled with --mprofile-kernel. I still see the TOC stuff when
> compiling only with -pg.
I don't see how this wouldn't be a gcc bug.
No matter whether it's plain profiling call (-pg)
On Tue, 2 Feb 2016 22:53:36 +0100 Christian Borntraeger
wrote:
> >> I don't think we should have a CONFIG_DEBUG_PAGEALLOC that does some stuff
> >> and then a commandline parameter or CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
> >> to enable more stuff. It should either be
On Tue, Jan 19, 2016 at 06:18:19PM -0200, Guilherme G. Piccoli wrote:
>The function eeh_add_device_early() is used to perform EEH initialization in
>devices added later on the system, like in hotplug/DLPAR scenarios. Since the
>commit 89a51df5ab1d ("powerpc/eeh: Fix crash in eeh_add_device_early()
On 02/02/2016 11:21 PM, Andrew Morton wrote:
> On Tue, 2 Feb 2016 22:53:36 +0100 Christian Borntraeger
> wrote:
>
I don't think we should have a CONFIG_DEBUG_PAGEALLOC that does some stuff
and then a commandline parameter or
On Tue, Feb 02, 2016 at 03:39:18PM +0530, Ganapatrao Kulkarni wrote:
> dt node parsing for numa topology is done using device property
> numa-node-id and device node distance-map.
>
> Reviewed-by: Robert Richter
> Signed-off-by: Ganapatrao Kulkarni
On Tue, 2 Feb 2016 23:37:50 +0100 Christian Borntraeger
wrote:
> On 02/02/2016 11:21 PM, Andrew Morton wrote:
> > On Tue, 2 Feb 2016 22:53:36 +0100 Christian Borntraeger
> > wrote:
> >
> I don't think we should have a
On Tue, Jan 19, 2016 at 06:18:20PM -0200, Guilherme G. Piccoli wrote:
>The Dynamic DMA Window (DDW) mechanism relies on EEH to obtain the
>configuration address of devices. For example, the functions query_ddw()
>and create_ddw() make use of eeh_dev struct. So, the dependency is
>intrinsic - DDW
Normally as far as i can tell it should register it as input and that's not
happening, verified the config entry CONFIG_MOUSE_APPLETOUCH is selected
and compiled in both tests i've done for rc-1 and rc-2.
syslog.1:Feb 1 21:58:40 PowerBook-G4 kernel: [ 14.744538] usbcore:
registered new
Hi Andrew,
On Tue, 2 Feb 2016 15:04:35 -0800 Andrew Morton
wrote:
>
> On Tue, 2 Feb 2016 23:37:50 +0100 Christian Borntraeger
> wrote:
>
> >
> > I pushed it on my tree for kbuild testing purposes some days ago.
> > Will drop so that it can
This patch adds the powernv_throttle tracepoint to trace the CPU
frequency throttling event, which is used by the powernv-cpufreq
driver in POWER8.
Signed-off-by: Shilpasri G Bhat
Reviewed-by: Gautham R. Shenoy
---
No changes from v7.
On Tue, Feb 02, 2016 at 09:04:23AM -0600, Nathan Fontenot wrote:
> On 01/28/2016 11:23 PM, David Gibson wrote:
> > This makes a number of cleanups to handling of mapping failures during
> > memory hotplug on Power:
> >
> > For errors creating the linear mapping for the hot-added region:
> > *
On 02/02/2016 07:28 PM, Denis Kirjanov wrote:
> On 2/1/16, Mahesh J Salgaonkar wrote:
>> From: Mahesh Salgaonkar
>>
>> The kernel boot parameter 'nr_cpus=' allows one to specify number of
>> possible cpus in the system. In the normal scenario
perf probe through debuginfo__find_probes() in util/probe-finder.c
checks for the functions' frame descriptions in either .eh_frame section
of an ELF or the .debug_frame. The check is based on whether either one
of these sections is present. Depending on distro, toolchain defaults,
architetcutre,
On 01/28/2016 11:23 PM, David Gibson wrote:
> This makes a number of cleanups to handling of mapping failures during
> memory hotplug on Power:
>
> For errors creating the linear mapping for the hot-added region:
> * This is now reported with EFAULT which is more appropriate than the
>
At present cpumask_of_pcibus is defined for !CONFIG_NUMA and moving out
to common will allow to use for numa too. This also avoids
redefinition of this macro in respective architecture header files.
Reviewed-by: Robert Richter
Signed-off-by: Ganapatrao Kulkarni
Adding numa support for arm64 based platforms.
This patch adds by default the dummy numa node and
maps all memory and cpus to node 0.
using this patch, numa can be simulated on single node arm64 platforms.
Tested-by: Shannon Zhao
Reviewed-by: Robert Richter
dt node parsing for numa topology is done using device property
numa-node-id and device node distance-map.
Reviewed-by: Robert Richter
Signed-off-by: Ganapatrao Kulkarni
---
drivers/of/Kconfig | 11 +++
drivers/of/Makefile | 1 +
Adding numa dt binding support for arm64 based platforms.
Reviewed-by: Robert Richter
Signed-off-by: Ganapatrao Kulkarni
---
arch/arm64/include/asm/numa.h | 2 ++
arch/arm64/kernel/smp.c | 2 ++
arch/arm64/mm/numa.c | 17
Adding dt file for Cavium's Thunderx dual socket platform.
Signed-off-by: Ganapatrao Kulkarni
---
arch/arm64/boot/dts/cavium/Makefile | 2 +-
arch/arm64/boot/dts/cavium/thunder-88xx-2n.dts | 83 +++
arch/arm64/boot/dts/cavium/thunder-88xx-2n.dtsi |
DT bindings for numa mapping of memory, cores and IOs.
Reviewed-by: Robert Richter
Signed-off-by: Ganapatrao Kulkarni
---
Documentation/devicetree/bindings/numa.txt | 272 +
1 file changed, 272 insertions(+)
create
v10:
- Incorporated review comments from Rob Herring.
- Moved numa binding and implementation to devicetree core.
- Added cleanup patch to remove redundant NODE_DATA macro from asm
header files
- Include numa balancing support for arm64 patch in this series.
enabled numa balancing for arm64 platforms.
added pte, pmd protnone helpers for use by automatic NUMA balancing.
Reviewed-by: Robert Richter
Signed-off-by: Ganapatrao Kulkarni
---
arch/arm64/Kconfig | 1 +
NODE_DATA is defined across multiple asm header files.
Moving generic definition to asm-generic/mmzone.h to
remove redundant definitions.
Reviewed-by: Robert Richter
Signed-off-by: Ganapatrao Kulkarni
---
arch/arm64/include/asm/mmzone.h | 4
On Tue 2016-02-02 16:45:23, Torsten Duwe wrote:
> On Tue, Feb 02, 2016 at 01:12:24PM +0100, Petr Mladek wrote:
> >
> > Hmm, the size of the offset is not a constant. In particular, leaf
> > functions do not set TOC before the mcount location.
>
> To be slightly more precise, a leaf function that
On Tue 2016-01-26 13:48:53, Petr Mladek wrote:
> On Tue 2016-01-26 11:50:25, Miroslav Benes wrote:
> >
> > [ added Petr to CC list ]
> >
> > On Mon, 25 Jan 2016, Torsten Duwe wrote:
> >
> > > * create the appropriate files+functions
> > > arch/powerpc/include/asm/livepatch.h
> > >
On 1/25/16, Torsten Duwe wrote:
> * create the appropriate files+functions
> arch/powerpc/include/asm/livepatch.h
> klp_check_compiler_support,
> klp_arch_set_pc
> arch/powerpc/kernel/livepatch.c with a stub for
> klp_write_module_reloc
> This is
On Tue, Feb 2, 2016 at 1:48 AM, Aneesh Kumar K.V
wrote:
>
> This patch didn't work for you ?
>
> http://mid.gmane.org/1454086969-21074-1-git-send-email-aneesh.ku...@linux.vnet.ibm.com
>
This actually is a better patch. I didn't realize that we have the _64
On Tue, Feb 02, 2016 at 01:12:24PM +0100, Petr Mladek wrote:
>
> Hmm, the size of the offset is not a constant. In particular, leaf
> functions do not set TOC before the mcount location.
To be slightly more precise, a leaf function that additionally uses
no global data. No global function calls,
The new IFC controller version 2.0 has a different memory map page.
Upto IFC 1.4 PAGE size is 4 KB and from IFC2.0 PAGE size is 64KB.
This patch segregates the IFC global and runtime registers to appropriate
PAGE sizes.
Signed-off-by: Jaiprakash Singh
Signed-off-by: Raghav
Hi,
On 01/26/2016 12:26 AM, Torsten Duwe wrote:
The gcc switch -mprofile-kernel, available for ppc64 on gcc > 4.8.5,
allows to call _mcount very early in the function, which low-level
ASM code and code patching functions need to consider.
Especially the link register and the parameter registers
Not made any less confusing with the presence of the evdev event4 and
correct /dev/input/mouse ... cat on the device indicates no input is
passed. Xorg correctly finds and assigns the pad and functions, evdev sets
it up... But no inputs registered, i cannot spot any changes comparing to
4.3.3 that
On 1/29/16, David Gibson wrote:
> At the moment the hpte_removebolted callback in ppc_md returns void and
> will BUG_ON() if the hpte it's asked to remove doesn't exist in the first
> place. This is awkward for the case of cleaning up a mapping which was
> partially
On 2/1/16, Mahesh J Salgaonkar wrote:
> From: Mahesh Salgaonkar
>
> The kernel boot parameter 'nr_cpus=' allows one to specify number of
> possible cpus in the system. In the normal scenario the first cpu (cpu0)
> that shows up is the boot
From: Mahesh Salgaonkar
The kernel boot parameter 'nr_cpus=' allows one to specify number of
possible cpus in the system. In the normal scenario the first cpu (cpu0)
that shows up is the boot cpu and hence it gets covered under nr_cpus
limit.
But this assumption will
46 matches
Mail list logo