Jaggi, Manish | 10 Feb 10:33 2016

[4.4rt3] Preemption disabled at:[<ffff8000000aba44>] kvm_vcpu_ioctl+0x30c/0x750

I am trying to run a kvm guest on a host with 4.4 rt3 patchset applied. (Cavium thunderX arm64 system)
Getting the following error: 

BUG: scheduling while atomic: qemu-system-aar/41889/0x00000002
[  341.647463] Modules linked in: ipv6 thunderx_edac_lmc thunderx_edac_ccpi i2c_octeon edac_core
shpchp aes_ce_blk ablk_helper cryptd aes_ce_cipher ghash_ce sha2_ce sha1_ce uio_pdrv_genirq
rtc_efi uio
[  341.647477] Preemption disabled at:[<ffff8000000aba44>] kvm_vcpu_ioctl+0x30c/0x750
[  341.647478] 
[  341.647484] CPU: 2 PID: 41889 Comm: qemu-system-aar Not tainted 4.4.0-rt3-00120-gbb974fa #64
[  341.647486] Hardware name: www.cavium.com ThunderX CRB1S/ThunderX CRB1S, BIOS 0.3 Dec  3 2015
[  341.647488] Call trace:
[  341.647494] [<ffff800000097878>] dump_backtrace+0x0/0x160
[  341.647499] [<ffff8000000979fc>] show_stack+0x24/0x30
[  341.647503] [<ffff800000512608>] dump_stack+0x88/0xa8
[  341.647509] [<ffff8000000f25c0>] __schedule_bug+0x70/0xc0
[  341.647514] [<ffff8000008f8f38>] __schedule+0x510/0x580
[  341.647517] [<ffff8000008f90e8>] schedule+0x50/0xf0
[  341.647521] [<ffff8000008fa9a4>] rt_spin_lock_slowlock+0x124/0x2e0
[  341.647525] [<ffff8000008fc5e0>] rt_spin_lock+0x60/0x70
[  341.647530] [<ffff8000000bffe0>] kvm_vgic_flush_hwstate+0x60/0x278
[  341.647535] [<ffff8000000b3140>] kvm_arch_vcpu_ioctl_run+0x108/0x618
[  341.647547] [<ffff8000000aba44>] kvm_vcpu_ioctl+0x30c/0x750
[  341.647553] [<ffff80000024b4dc>] do_vfs_ioctl+0x364/0x628
[  341.647556] [<ffff80000024b834>] SyS_ioctl+0x94/0xa8
[  341.647560] [<ffff800000093b04>] el0_svc_naked+0x38/0x3c

The below patch enables preemption:
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/arch/arm/kvm/arm.c?h=v4.4&id=1b3d546daf85ed2bc9966e12cee3e6435fb65eca

(Continue reading)

David Aldrich | 8 Feb 13:16 2016
Picon

Linux RT newbie question

Hi

For a new project we need to demonstrate a Linux RT-Kernel running on a 'standard' x86 desktop PC.

The question is which distro to use?  I am aware of commercially supported embedded distros from Wind River
and Monta Vista.  However, as ours is not strictly an embedded target, I wonder if a standard Linux distro +
RT kernel patch would be a better choice?

I have done some research and found the Planet CCRMA patches for Fedora and the Pengutronix patches for Debian.

Are there any other distros and patches that I should consider?  

Any advice on a way forward would be much appreciated.

Best regards

David

--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Alexander Gerasiov | 8 Feb 10:40 2016
Picon
Gravatar

Boot IRQ issue on Intel C602J (Advantech ASMB-822)

Hello there.

We are using 3.10.74-rt79 in our system and found some problem with
Advantech ASMB-822 motherboard.

It's Intel C602J based m/b with 2 IO-APIC.

We have 2 special PCIe adapters installed. They use legacy interrupts
through APIC.

On 3.10.74 one of adapter generate only several (~10) interrupts and
then halts. As I discovered, it works ok, but no interrupts was
delivered. The same time (but after device stops receiving irqs) boot
irqs occur and irq 16 got disabled by the kernel.

I tried 3.18.25 with the same result.

Right now I'm running 4.4.1-rt4 and finally it works, but there are
still boot irqs and kernel disables IRQ 16 because of them.

So I need some ideas, how to deal with boot interrupts on this chipset.
May be to add workaround like masking boot irq together with IO-APIC
irq.

PS If someone could give a clue, what was changed in 4.4.1 from 3.18
that would be great. (As I'm not sure we could switch production system
to 4.4.1 soon, and I'd like to backport this change set to old kernel if
possible.)

--

-- 
(Continue reading)

Simone Pietro Lossani, 3L | 7 Feb 21:22 2016

Config file settings


Hello,

I installed OpenSuse 13.2 on Siemens IPC
with the native kernel 13.16.6.

After that I downloaded kernel 3.18.25
and the relative RT PREEMPT PATCH.

I done the patch.

I copied from boot directory the file
config-3.16.6-2-desktop to usr/src/linux-3.18.25. I renamed it to .config.

And then I started make menuconfig and
at this point I got some problems.

I didn’t find setting written In the howto:

The most default configurations here are ok as-they-are. However you should make sure that you have

enable
CONFIG_PREEMPT_RT

activated
the High-Resolution-Timer Option (Attention, the amount of supported platforms by the HR timer is still
very limited. Right now the option is only supported on x86 systems, PowerPC and ARM Support are however in queue.)

disabled
all Power Management Options like ACPI or APM (not all ACPI functions are "bad", but you will have to check
(Continue reading)

Simone Pietro Lossani, 3L | 7 Feb 20:26 2016

Config file settings

Hello,

I installed OpenSuse 13.2 on IPC277E
with the native kernel 13.16.6.

After that I downloaded kernel 3.18.25
and the relative RT PREEMPT PATCH.

I done the patch.

I copied from boot directory the file
config-3.16.6-2-desktop to usr/src/linux-3.18.25. I renamed it to .config.

And then I started make menuconfig and
at this point I got some problems.

I didn’t find setting written In the howto:

The most default configurations here are ok as-they-are. However you
should make sure that you have

enable
CONFIG_PREEMPT_RT
 
activated
the High-Resolution-Timer Option (Attention, the amount of supported platforms
by the HR timer is still very limited. Right now the option is only supported
on x86 systems, PowerPC and ARM Support are however in queue.)

disabled
(Continue reading)

Lampersperger Andreas | 4 Feb 08:31 2016
Picon

lock/reserve 2nd level cache for rt tasks

Hello,

on my quad core cpu (intel i7) the x11vnc (server) slows down 
the rt-task (it took up to 5 times longer), even if I bound 
the x11vnc to another core than the rt-task via taskset. 

I guessed that the x11vnc invalidates 2nd and/or 3rd level.

Is there any way to reserve cpu cache to a specified task 
or to a specified core?

Thanks for any idea.

Andreas

------------------------------------------------------------------------------------------------------
Registergericht: Traunstein / Registry Court: HRB 275 - Sitz / Head Office: Traunreut
Aufsichtsratsvorsitzender / Chairman of Supervisory Board: Rainer Burkhard
Geschäftsführung / Management Board: Thomas Sesselmann (Vorsitzender / Chairman),
Michael Grimm, Hubert Ermer, Lutz Rissing

E-Mail Haftungsausschluss / E-Mail Disclaimer: http://www.heidenhain.de/disclaimer
DIXLOR | 3 Feb 20:06 2016
Picon
Gravatar

SMP even/odd cores latency

# ./cyclictest -sm -n -p99 --policy=fifo -S -D60
# /dev/cpu_dma_latency set to 0us
policy: fifo: loadavg: 2.89 1.37 0.64 1/506 15232

T: 0 (15179) P:99 I:1000 C:  59999 Min:     14 Act:   56 Avg:   51 Max:      99
T: 1 (15180) P:99 I:1500 C:  39999 Min:      3 Act:   13 Avg:   29 Max:     100
T: 2 (15181) P:99 I:2000 C:  29999 Min:     12 Act:   50 Avg:   48 Max:     101
T: 3 (15182) P:99 I:2500 C:  23999 Min:      4 Act:   13 Avg:   29 Max:     101
T: 4 (15183) P:99 I:3000 C:  19999 Min:     16 Act:   60 Avg:   51 Max:     104
T: 5 (15184) P:99 I:3500 C:  17142 Min:      4 Act:   60 Avg:   30 Max:     102
T: 6 (15185) P:99 I:4000 C:  14999 Min:     14 Act:   29 Avg:   51 Max:     106
T: 7 (15186) P:99 I:4500 C:  13333 Min:      4 Act:   11 Avg:   32 Max:     106
T: 8 (15187) P:99 I:5000 C:  11999 Min:     17 Act:   42 Avg:   47 Max:      90
T: 9 (15188) P:99 I:5500 C:  10908 Min:      5 Act:   40 Avg:   29 Max:      89
T:10 (15189) P:99 I:6000 C:   9999 Min:     18 Act:   43 Avg:   49 Max:      99
T:11 (15190) P:99 I:6500 C:   9230 Min:      5 Act:   28 Avg:   29 Max:      99
T:12 (15191) P:99 I:7000 C:   8571 Min:     14 Act:   56 Avg:   47 Max:      98
T:13 (15192) P:99 I:7500 C:   7999 Min:      5 Act:   11 Avg:   31 Max:      97
T:14 (15193) P:99 I:8000 C:   7499 Min:     16 Act:   64 Avg:   49 Max:     100
T:15 (15194) P:99 I:8500 C:   7058 Min:      5 Act:   42 Avg:   30 Max:      96

Minimum latency on even cores is approximately equal to 15, on the odd - 5 
Аverage latency on the even - 50, on the odd cores - 30 :)

- Linux 4.4.1-rt4+ x86_64
- gcc version 4.9.2 (Debian 4.9.2-10)
- 2 x AMD Opteron(tm) Processor 4386
- Mb: TYAN S8225

(Continue reading)

$rik@nth | 25 Jan 13:01 2016
Picon

[RT-Tests] pmqtest on ARM

Hi All,

I am having dragonboard 410c with Android kernel. Tried successfully
cross compile rt-tests for ARM using cross tool-chain.

pmqtest is showing error "could not open POSIX message queue #1"

Do i need to compile rt-tests with any additional/specific flags
inorder to work on ARM platform as well? Request someone to share
pointers to unblock my debugging.

--

-- 
Thanks & Regards,
M.Srikanth Kumar.
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Sebastian Andrzej Siewior | 23 Jan 00:08 2016
Picon

[ANNOUNCE] 4.4-rt3

Dear RT folks!

I'm pleased to announce the v4.4-rt3 patch set.
Changes since v4.4-rt2:

- various compile fixes found by kbuild test robot and Grygorii
  Strashko.

- kbuild test robot reported that we open interrupts too early in
  ptrace_freeze_traced().
  
- dropping a GPIO patch from the OMAP queue which is no longer
  required (requested by Grygorii Strashko)

- dropping a retry loop in the mm/anon_vma_free() which was probably
  just duct tape and does no longer seems required.

- Various people pointed out that the AT91 clocksource driver did not
  not compile. It does now. However AT91 does not yet boot. There are
  two issues:
  - the free_irq() from irq-off region is not good and triggers a
    warning because it is invoked twice. This will be addressed later,
    the current patch is not bulletproof and not yet part of the series.
  - The PMC driver invokes request_irq() very early which leads to a
    NULL pointer exception (non-RT with threaded interrupts has the same
    problem). A longer explanation by Alexandre Belloni and his current
    patch series he refers to can be found at:
    http://lkml.kernel.org/r/1452997394-8554-1-git-send-email-alexandre.belloni <at> free-electrons.com

- Using a virtual network device (like a bridge) could lead to a "Dead
(Continue reading)

Joël Krähemann | 22 Jan 10:37 2016
Picon

deterministic usage of JIFFIES and how to relocate the clock

Hi all

Since I'm hardware newbie I just ask in my very own words, how to
relocate the clock. I want to play around with the clock modulator in
GNU/Linux. Is there any interface to relocate it?

What must do a user-space application do to change underlaying cipher?
I don't care about gdb or valgrind issues or trap-points. Might be in
further sense interrupts.

Is possible to have a VM in userspace? Once I have seen different VMs
available in the kernel. Does even have the VM control of
clock-modulator? Do I need some knowledge about ACPI to do so?

Are there some good books about that thematics I could start with?
Since I like math it would be fun to do so.

bests,
Joël Krähemann
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

mr. sindar | 22 Jan 08:40 2016
Picon

(unknown)


unsubscribe linux-rt-users

--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo <at> vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html


Gmane