Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Zoltan HERPAI]

On 09/10/2017 07:10 PM, Zoltan HERPAI wrote:
The A8-based devices don't boot (A10/A13), waiting on me to come up 
with a fix.


-w-

On Sun, 10 Sep 2017, Lucian CRISTIAN wrote:


Is something that blocks these patch sets to go in trunk ?

Regards
Lucian

Hauke,

With the splitted configs for the Cortex-A7/A8 devices in your updated 
staging tree (with LPAE turned off on A8), an A10 booted fine, so:




[Tested on Linksprite pcDuino (A10) and BananaPro (A20).]
Acked-by: Zoltan HERPAI 


___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Zoltan HERPAI]

On Sun, 10 Sep 2017, Zoltan HERPAI wrote:

The A8-based devices don't boot (A10/A13), waiting on me to come up with a 
fix.


-w-

On Sun, 10 Sep 2017, Lucian CRISTIAN wrote:


Is something that blocks these patch sets to go in trunk ?


It looks like that CONFIG_ARM_LPAE is the culprit for these boards - 
without it the kernel boots fine on a pcduino-a10, with it it doesn't. It 
would be a good idea to split the kernel config for A7 and A8 now that 
they're separated anyways.


Regards,
-w-

___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Zoltan HERPAI]

The A8-based devices don't boot (A10/A13), waiting on me to come up with a 
fix.


-w-

On Sun, 10 Sep 2017, Lucian CRISTIAN wrote:


Is something that blocks these patch sets to go in trunk ?

Regards
Lucian

___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev



___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Lucian CRISTIAN]

Is something that blocks these patch sets to go in trunk ?

Regards
Lucian

___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Luis Araneda]

On Wed, Aug 9, 2017 at 6:41 PM, Lucian Cristian  wrote:
> On 09.08.2017 22:08, Hauke Mehrtens wrote:
>>
>> On 08/08/2017 01:13 AM, Lucian Cristian wrote:
>>>
>>> On 07.08.2017 19:47, Lucian Cristian wrote:

 On 07.08.2017 19:43, Hauke Mehrtens wrote:
>
> ...
> Hi Lucian,
>
> The eMMC version needs an extra device tree file, could you please use
> this one:
> arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts
>
> We should probably add two device one for the normal lime2 and one
> lime2-emmc.
>
> Hauke

 Yes, I know, on 4.4 it worked with or without emmc dts, but since it
 wasn't merged I didn't made a patch for eMMC version, I'll return with
 output asap

 Regards


 ___
 Lede-dev mailing list
 Lede-dev@lists.infradead.org
 http://lists.infradead.org/mailman/listinfo/lede-dev
>>>
>>> So I made a test without the split and it worked, but on the same three
>>> with the split I didn't had an option for root partition size on
>>> menuconfig so I made a new git clone and I can confirm that is booting.
>>>
>>> Something must have been broken in my branch!
>>>
>>>
>>> Regards
>>>
>> Hi Lucian,
>>
>> So your device is now booting with my full patch series applied + your
>> change to add the lime2 emmc?
>>
>> Hauke
>>
>> ___
>> Lede-dev mailing list
>> Lede-dev@lists.infradead.org
>> http://lists.infradead.org/mailman/listinfo/lede-dev
>
>
> Yes !
>
>
> Regards
>
>
> ___
> Lede-dev mailing list
> Lede-dev@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/lede-dev

Hi,

I've applied your patches, and I've made others to add support for the
Nanopi M1 Plus board, which uses an H3 SoC.
Everything seems working fine, even the WiFi card on the board
(.dts+nvram files).

Are you waiting for more testing to merge this to master? I'm
sure that almost all H3 based boards can be supported, at least at
some basic level.

Regards,

Luis Araneda.

___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Lucian Cristian]

On 09.08.2017 22:08, Hauke Mehrtens wrote:

On 08/08/2017 01:13 AM, Lucian Cristian wrote:

On 07.08.2017 19:47, Lucian Cristian wrote:

On 07.08.2017 19:43, Hauke Mehrtens wrote:

...
Hi Lucian,

The eMMC version needs an extra device tree file, could you please use
this one:
arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts

We should probably add two device one for the normal lime2 and one
lime2-emmc.

Hauke

Yes, I know, on 4.4 it worked with or without emmc dts, but since it
wasn't merged I didn't made a patch for eMMC version, I'll return with
output asap

Regards


___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

So I made a test without the split and it worked, but on the same three
with the split I didn't had an option for root partition size on
menuconfig so I made a new git clone and I can confirm that is booting.

Something must have been broken in my branch!


Regards


Hi Lucian,

So your device is now booting with my full patch series applied + your
change to add the lime2 emmc?

Hauke

___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev


Yes !

Regards


___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Hauke Mehrtens]

On 08/08/2017 01:13 AM, Lucian Cristian wrote:
> On 07.08.2017 19:47, Lucian Cristian wrote:
>> On 07.08.2017 19:43, Hauke Mehrtens wrote:
>>> ...

>>> Hi Lucian,
>>>
>>> The eMMC version needs an extra device tree file, could you please use
>>> this one:
>>> arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts
>>>
>>> We should probably add two device one for the normal lime2 and one
>>> lime2-emmc.
>>>
>>> Hauke
>>
>> Yes, I know, on 4.4 it worked with or without emmc dts, but since it
>> wasn't merged I didn't made a patch for eMMC version, I'll return with
>> output asap
>>
>> Regards
>>
>>
>> ___
>> Lede-dev mailing list
>> Lede-dev@lists.infradead.org
>> http://lists.infradead.org/mailman/listinfo/lede-dev
> 
> So I made a test without the split and it worked, but on the same three
> with the split I didn't had an option for root partition size on
> menuconfig so I made a new git clone and I can confirm that is booting.
> 
> Something must have been broken in my branch!
> 
> 
> Regards
> 
Hi Lucian,

So your device is now booting with my full patch series applied + your
change to add the lime2 emmc?

Hauke

___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Lucian Cristian]

On 07.08.2017 19:47, Lucian Cristian wrote:

On 07.08.2017 19:43, Hauke Mehrtens wrote:

...



Hi Lucian,

The eMMC version needs an extra device tree file, could you please use
this one:
arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts

We should probably add two device one for the normal lime2 and one
lime2-emmc.

Hauke


Yes, I know, on 4.4 it worked with or without emmc dts, but since it 
wasn't merged I didn't made a patch for eMMC version, I'll return with 
output asap


Regards


___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev


So I made a test without the split and it worked, but on the same three 
with the split I didn't had an option for root partition size on 
menuconfig so I made a new git clone and I can confirm that is booting.


Something must have been broken in my branch!


Regards


___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Lucian Cristian]

On 07.08.2017 19:43, Hauke Mehrtens wrote:


On 08/07/2017 06:13 PM, Lucian Cristian wrote:

On 07.08.2017 18:55, Hauke Mehrtens wrote:

On 08/06/2017 08:16 PM, Lucian Cristian wrote:

On 04.08.2017 00:37, Hauke Mehrtens wrote:

This upgrades the target to kernel 4.9 and also adds support for the
Allwinner A64 SoC. This was only tested on the pine64+ and I do not own
any older Allwinner SoC.

Could someone please test this on an older 32 bit Allwinner SoC and
report back some results.

Hauke Mehrtens (13):
 kernel: add some config options
 sunix: add support for kernel 4.9
 include: u-boot.mk: remove LEDE HOSTCPPFLAGS from u-boot
HOSTCPPFLAGS
 uboot-sunxi: update to version 2017.07
 uboot-sunxi: do not depend on dtc being install on host
 uboot-sunxi: revert the usage of binman
 sunxi: fix build of rtc package when module not available
 sunxi: split into cortex A8 and A7 subtarget
 arm-trusted-firmware-sunxi: add new package
 uboot-sunxi: build A64 SoC and pine64 U-Boot
 sunxi: Backport patches needed for A64
 sunxi: Backport patches from kernel 4.11 for A64
 sunxi: Add A64 support with cortex53 subtarget

...

On LIME2 I get the attached boot log


Regards

Hi Lucian,

Thanks you for testing. Could you send me your patch you applied to add
LIME2 please.

It looks like executing the init binary failed, could you try to only
apply my patches till "sunxi: fix build of rtc package when module not
available" please, I assume the subtarget split is somehow not working.

Hauke

I just added to the image/cortex-a7.mk, and no more dts patching like on
4.4

define Device/sun7i-a20-olinuxino-lime2
   DEVICE_TITLE:=Olimex A20-OLinuXino-LIME2
   DEVICE_PACKAGES:=kmod-ata-core kmod-ata-sunxi kmod-rtc-sunxi kmod-usb-hid
   SUPPORTED_DEVICES:=olimex,a20-olinuxino-lime2
   SUNXI_DTS:=sun7i-a20-olinuxino-lime2
endef

TARGET_DEVICES += sun7i-a20-olinuxino-lime2


and for uboot patch from here

https://github.com/lucize/source/commit/325304c62dd8f6ef1b82b94873397c31226a6f88#diff-1ab1035312dfd60272886d810ef44e7f


I actually own an eMMC version, tried that too, but is the same, for
eMMC uboot needs this

https://github.com/armbian/build/blob/master/patch/u-boot/u-boot-sunxi/add-lime2-emmc.patch


I'll try without the split

Regards


Hi Lucian,

The eMMC version needs an extra device tree file, could you please use
this one:
arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts

We should probably add two device one for the normal lime2 and one
lime2-emmc.

Hauke


Yes, I know, on 4.4 it worked with or without emmc dts, but since it 
wasn't merged I didn't made a patch for eMMC version, I'll return with 
output asap


Regards


___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Hauke Mehrtens]

On 08/07/2017 06:13 PM, Lucian Cristian wrote:
> On 07.08.2017 18:55, Hauke Mehrtens wrote:
>>
>> On 08/06/2017 08:16 PM, Lucian Cristian wrote:
>>> On 04.08.2017 00:37, Hauke Mehrtens wrote:
 This upgrades the target to kernel 4.9 and also adds support for the
 Allwinner A64 SoC. This was only tested on the pine64+ and I do not own
 any older Allwinner SoC.

 Could someone please test this on an older 32 bit Allwinner SoC and
 report back some results.

 Hauke Mehrtens (13):
 kernel: add some config options
 sunix: add support for kernel 4.9
 include: u-boot.mk: remove LEDE HOSTCPPFLAGS from u-boot
 HOSTCPPFLAGS
 uboot-sunxi: update to version 2017.07
 uboot-sunxi: do not depend on dtc being install on host
 uboot-sunxi: revert the usage of binman
 sunxi: fix build of rtc package when module not available
 sunxi: split into cortex A8 and A7 subtarget
 arm-trusted-firmware-sunxi: add new package
 uboot-sunxi: build A64 SoC and pine64 U-Boot
 sunxi: Backport patches needed for A64
 sunxi: Backport patches from kernel 4.11 for A64
 sunxi: Add A64 support with cortex53 subtarget

 ...
>>> On LIME2 I get the attached boot log
>>>
>>>
>>> Regards
>> Hi Lucian,
>>
>> Thanks you for testing. Could you send me your patch you applied to add
>> LIME2 please.
>>
>> It looks like executing the init binary failed, could you try to only
>> apply my patches till "sunxi: fix build of rtc package when module not
>> available" please, I assume the subtarget split is somehow not working.
>>
>> Hauke
> 
> I just added to the image/cortex-a7.mk, and no more dts patching like on
> 4.4
> 
> define Device/sun7i-a20-olinuxino-lime2
>   DEVICE_TITLE:=Olimex A20-OLinuXino-LIME2
>   DEVICE_PACKAGES:=kmod-ata-core kmod-ata-sunxi kmod-rtc-sunxi kmod-usb-hid
>   SUPPORTED_DEVICES:=olimex,a20-olinuxino-lime2
>   SUNXI_DTS:=sun7i-a20-olinuxino-lime2
> endef
> 
> TARGET_DEVICES += sun7i-a20-olinuxino-lime2
> 
> 
> and for uboot patch from here
> 
> https://github.com/lucize/source/commit/325304c62dd8f6ef1b82b94873397c31226a6f88#diff-1ab1035312dfd60272886d810ef44e7f
> 
> 
> I actually own an eMMC version, tried that too, but is the same, for
> eMMC uboot needs this
> 
> https://github.com/armbian/build/blob/master/patch/u-boot/u-boot-sunxi/add-lime2-emmc.patch
> 
> 
> I'll try without the split
> 
> Regards
> 

Hi Lucian,

The eMMC version needs an extra device tree file, could you please use
this one:
arch/arm/boot/dts/sun7i-a20-olinuxino-lime2-emmc.dts

We should probably add two device one for the normal lime2 and one
lime2-emmc.

Hauke

___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Lucian Cristian]

On 07.08.2017 18:55, Hauke Mehrtens wrote:


On 08/06/2017 08:16 PM, Lucian Cristian wrote:

On 04.08.2017 00:37, Hauke Mehrtens wrote:

This upgrades the target to kernel 4.9 and also adds support for the
Allwinner A64 SoC. This was only tested on the pine64+ and I do not own
any older Allwinner SoC.

Could someone please test this on an older 32 bit Allwinner SoC and
report back some results.

Hauke Mehrtens (13):
kernel: add some config options
sunix: add support for kernel 4.9
include: u-boot.mk: remove LEDE HOSTCPPFLAGS from u-boot HOSTCPPFLAGS
uboot-sunxi: update to version 2017.07
uboot-sunxi: do not depend on dtc being install on host
uboot-sunxi: revert the usage of binman
sunxi: fix build of rtc package when module not available
sunxi: split into cortex A8 and A7 subtarget
arm-trusted-firmware-sunxi: add new package
uboot-sunxi: build A64 SoC and pine64 U-Boot
sunxi: Backport patches needed for A64
sunxi: Backport patches from kernel 4.11 for A64
sunxi: Add A64 support with cortex53 subtarget

...

On LIME2 I get the attached boot log


Regards

Hi Lucian,

Thanks you for testing. Could you send me your patch you applied to add
LIME2 please.

It looks like executing the init binary failed, could you try to only
apply my patches till "sunxi: fix build of rtc package when module not
available" please, I assume the subtarget split is somehow not working.

Hauke


I just added to the image/cortex-a7.mk, and no more dts patching like on 4.4

define Device/sun7i-a20-olinuxino-lime2
  DEVICE_TITLE:=Olimex A20-OLinuXino-LIME2
  DEVICE_PACKAGES:=kmod-ata-core kmod-ata-sunxi kmod-rtc-sunxi kmod-usb-hid
  SUPPORTED_DEVICES:=olimex,a20-olinuxino-lime2
  SUNXI_DTS:=sun7i-a20-olinuxino-lime2
endef

TARGET_DEVICES += sun7i-a20-olinuxino-lime2


and for uboot patch from here

https://github.com/lucize/source/commit/325304c62dd8f6ef1b82b94873397c31226a6f88#diff-1ab1035312dfd60272886d810ef44e7f

I actually own an eMMC version, tried that too, but is the same, for 
eMMC uboot needs this


https://github.com/armbian/build/blob/master/patch/u-boot/u-boot-sunxi/add-lime2-emmc.patch

I'll try without the split

Regards


___
Lede-dev mailing list
Lede-dev@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/lede-dev

Re: [LEDE-DEV] [PATCH 00/13] sunxi: upgrade to kernel 4.9 and add A64 support

[Lucian Cristian]

On 04.08.2017 00:37, Hauke Mehrtens wrote:

This upgrades the target to kernel 4.9 and also adds support for the
Allwinner A64 SoC. This was only tested on the pine64+ and I do not own
any older Allwinner SoC.

Could someone please test this on an older 32 bit Allwinner SoC and
report back some results.

Hauke Mehrtens (13):
   kernel: add some config options
   sunix: add support for kernel 4.9
   include: u-boot.mk: remove LEDE HOSTCPPFLAGS from u-boot HOSTCPPFLAGS
   uboot-sunxi: update to version 2017.07
   uboot-sunxi: do not depend on dtc being install on host
   uboot-sunxi: revert the usage of binman
   sunxi: fix build of rtc package when module not available
   sunxi: split into cortex A8 and A7 subtarget
   arm-trusted-firmware-sunxi: add new package
   uboot-sunxi: build A64 SoC and pine64 U-Boot
   sunxi: Backport patches needed for A64
   sunxi: Backport patches from kernel 4.11 for A64
   sunxi: Add A64 support with cortex53 subtarget

...

On LIME2 I get the attached boot log


Regards


U-Boot SPL 2017.07 (Aug 05 2017 - 07:47:41)
DRAM: 1024 MiB
CPU: 91200Hz, AXI/AHB/APB: 3/2/2
Trying to boot from MMC1


U-Boot 2017.07 (Aug 05 2017 - 07:47:41 +) Allwinner Technology

CPU:   Allwinner A20 (SUN7I)
Model: Olimex A20-OLinuXino-LIME2
I2C:   ready
DRAM:  1 GiB
MMC:   SUNXI SD/MMC: 0
*** Warning - bad CRC, using default environment

In:serial
Out:   serial
Err:   serial
SCSI:  SATA link 0 timeout.
AHCI 0001.0100 32 slots 1 ports 3 Gbps 0x1 impl SATA mode
flags: ncq stag pm led clo only pmp pio slum part ccc apst
Net:   eth0: ethernet@01c5
starting USB...
USB0:   USB EHCI 1.00
USB1:   USB OHCI 1.0
USB2:   USB EHCI 1.00
USB3:   USB OHCI 1.0
scanning bus 0 for devices... 1 USB Device(s) found
scanning bus 2 for devices... 1 USB Device(s) found
   scanning usb for storage devices... 0 Storage Device(s) found
Hit any key to stop autoboot:  0
switch to partitions #0, OK
mmc0 is current device
Scanning mmc 0:1...
Found U-Boot script /boot.scr
reading /boot.scr
377 bytes read in 15 ms (24.4 KiB/s)
## Executing script at 4310
reading uImage
2193256 bytes read in 143 ms (14.6 MiB/s)
reading dtb
34531 bytes read in 26 ms (1.3 MiB/s)
## Booting kernel from Legacy Image at 4200 ...
   Image Name:   ARM LEDE Linux-4.9.40
   Image Type:   ARM Linux Kernel Image (uncompressed)
   Data Size:2193192 Bytes = 2.1 MiB
   Load Address: 40008000
   Entry Point:  40008000
   Verifying Checksum ... OK
## Flattened Device Tree blob at 4300
   Booting using the fdt blob at 0x4300
   Loading Kernel Image ... OK
   Using Device Tree in place at 4300, end 4300b6e2

Starting kernel ...

[0.00] Booting Linux on physical CPU 0x0
[0.00] Linux version 4.9.40 (luci@droid) (gcc version 5.4.0 (LEDE GCC 
5.4.0 r4675-e5e6045) ) #0 SMP PREEMPT Sat Aug 5 07:47:41 2017
[0.00] CPU: ARMv7 Processor [410fc074] revision 4 (ARMv7), cr=32c5387d
[0.00] CPU: div instructions available: patching division code
[0.00] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing 
instruction cache
[0.00] OF: fdt:Machine model: Olimex A20-OLinuXino-LIME2
[0.00] Memory policy: Data cache writealloc
[0.00] psci: probing for conduit method from DT.
[0.00] psci: Using PSCI v0.1 Function IDs from DT
[0.00] percpu: Embedded 14 pages/cpu @ef7c2000 s25036 r8192 d24116 
u57344
[0.00] Built 1 zonelists in Zone order, mobility grouping on.  Total 
pages: 260608
[0.00] Kernel command line: console=ttyS0,115200 earlyprintk 
root=/dev/mmcblk0p2 rootwait
[0.00] PID hash table entries: 4096 (order: 2, 16384 bytes)
[0.00] Dentry cache hash table entries: 131072 (order: 7, 524288 bytes)
[0.00] Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
[0.00] Memory: 1032660K/1048576K available (4406K kernel code, 224K 
rwdata, 1292K rodata, 284K init, 277K bss, 15916K reserved, 0K cma-reserved, 
262144K highmem)
[0.00] Virtual kernel memory layout:
[0.00] vector  : 0x - 0x1000   (   4 kB)
[0.00] fixmap  : 0xffc0 - 0xfff0   (3072 kB)
[0.00] vmalloc : 0xf080 - 0xff80   ( 240 MB)
[0.00] lowmem  : 0xc000 - 0xf000   ( 768 MB)
[0.00] pkmap   : 0xbfe0 - 0xc000   (   2 MB)
[0.00] modules : 0xbf00 - 0xbfe0   (  14 MB)
[0.00]   .text : 0xc0008000 - 0xc0455df0   (4408 kB)
[0.00]   .init : 0xc05bd000 - 0xc0604000   ( 284 kB)
[0.00]   .data : 0xc0604000 - 0xc063c300   ( 225 kB)
[0.00].bss : 0xc063e000 - 0xc06835d4   ( 278 kB)
[0.00] SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=2, Nodes=1
[0.00] Preemptible hierarchical RCU implementation.
[0.00]  RCU restricting CPUs from NR_CPUS=8 to nr_cpu_ids=2.
[0.00] RCU: Adjusting geometry for rcu_fanout_leaf=16, nr_cpu_ids=2
[0.00] NR_IRQS:16