Daniel Wagner | 27 Jun 09:44 2016
Gravatar

A summit on the Summit

Hi,

I tried to write up what happened in the Austrian Alps beginning of 
June. It took a bit longer because I had to do it via corporate 
processes. Finally, here it is:

http://www.bmw-carit.com/blog/a-summit-on-the-summit/

Please let me know if there is anything not correct in the text.

cheers,
daniel
--
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

Steven Rostedt | 24 Jun 22:51 2016
Gravatar

[ANNOUNCE] 3.2.81-rt116


Dear RT Folks,

I'm pleased to announce the 3.2.81-rt116 stable release.

This release is just an update to the new stable 3.2.81 version
and no RT specific changes have been made.

You can get this release via the git tree at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git

  branch: v3.2-rt
  Head SHA1: 3c32278dfdc27c86ddd1d9b4e10f1559882a091c

Or to build 3.2.81-rt116 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.2.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.2.81.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/patch-3.2.81-rt116.patch.xz

Enjoy,

-- Steve

--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo <at> vger.kernel.org
(Continue reading)

John Kacur | 24 Jun 13:46 2016
Picon

[PATCH] rt-tests-1.0.1: Remove _GNU_SOURCE from source files

Remove _GNU_SOURCE from source files since it is already defined in via
the Makefile

Signed-off-by: John Kacur <jkacur <at> redhat.com>
---
 src/rt-migrate-test/rt-migrate-test.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/src/rt-migrate-test/rt-migrate-test.c b/src/rt-migrate-test/rt-migrate-test.c
index d7b68ddac3e5..0a0bb77ab661 100644
--- a/src/rt-migrate-test/rt-migrate-test.c
+++ b/src/rt-migrate-test/rt-migrate-test.c
 <at>  <at>  -20,9 +20,6  <at>  <at> 
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
-#ifndef _GNU_SOURCE
-#define _GNU_SOURCE
-#endif
 #include <stdio.h>
 #ifndef __USE_XOPEN2K
 # define __USE_XOPEN2K
--

-- 
2.4.11

--
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

(Continue reading)

Henrik Austad | 15 Jun 13:39 2016
Picon
Gravatar

Linux RT workshop colocated with ELCE'16

Hi all!

So a brief discussion on #linux-rt today spurred me into action

Are people going to ELCE in Berlin this year, and if so, would it make 
sense to organize a linux-rt workshop/miniconf around the same time?

ELCE is Tuesday 11. Oct - Thursday 13. Oct, so either Monday or Friday with 
perhaps some overlap with ELCE.

--

-- 
Henrik Austad
Mike Galbraith | 14 Jun 10:56 2016
Picon

[rfc patch] locking: Cleanup local locks


1. Remove unneeded local_irq_lock.flags.
2. Make local_lock_irq() use spin_lock/unlock_irq() for PREEMPT_RTB
3. Make local_lock_irqsave/on() disable irqs for PREEMPT_RTB without
   mucking about with remote cpu ->flags for local_lock_irqsave_on().
4. Line up backslashes for no particular reason.

Signed-off-by: Mike Galbraith <umgwanakikbuti <at> gmail.com>
---
 include/linux/locallock.h |   44 ++++++++++++++++++++++++--------------------
 1 file changed, 24 insertions(+), 20 deletions(-)

--- a/include/linux/locallock.h
+++ b/include/linux/locallock.h
 <at>  <at>  -19,7 +19,6  <at>  <at>  struct local_irq_lock {
 	spinlock_t		lock;
 	struct task_struct	*owner;
 	int			nestcnt;
-	unsigned long		flags;
 };

 #define DEFINE_LOCAL_IRQ_LOCK(lvar)					\
 <at>  <at>  -46,10 +45,14  <at>  <at>  struct local_irq_lock {
 # define spin_lock_local(lock)			rt_spin_lock__no_mg(lock)
 # define spin_trylock_local(lock)		rt_spin_trylock__no_mg(lock)
 # define spin_unlock_local(lock)		rt_spin_unlock__no_mg(lock)
+# define spin_lock_irq_local(lock)		rt_spin_lock__no_mg(lock)
+# define spin_unlock_irq_local(lock)		rt_spin_unlock__no_mg(lock)
 #else
 # define spin_lock_local(lock)			spin_lock(lock)
(Continue reading)

Jens Koehler | 13 Jun 11:16 2016

Re: hrtimer: interrupt took 10252 ns - meaning?

I found now out that the problem with RT throttling could happen when
my application sends UDP broadcasts (and receive its own broadcast).

Is this an already known problem?

[137482.258011] hrtimer: interrupt took 9434 ns
[178458.961966] NOHZ: local_softirq_pending 102
[178458.967583] NOHZ: local_softirq_pending 102
[178458.973295] NOHZ: local_softirq_pending 102
[178458.980249] NOHZ: local_softirq_pending 102
[178458.984994] NOHZ: local_softirq_pending 102
[178458.990582] NOHZ: local_softirq_pending 102
[178458.996292] NOHZ: local_softirq_pending 102
[178459.000348] [sched_delayed] sched: RT throttling activated

Jens
--
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

Mike Galbraith | 5 Jun 08:57 2016
Picon

RT, what to do about up/down_read_non_owner()

Greetings,

In v4.7, Al added those buggers to NFS.  BCACHE is disabled in RT
because of same.. but that's a somewhat suboptimal solution for
something as widely used as NFS.

Suggestions?  I reverted the offending commit to get 4.7-rt up and
running, but that's not gonna fly long term.

	-Mike
--
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

Mike Galbraith | 4 Jun 16:53 2016
Picon

RT trees fail ltp futex_wait04 - culprit=65d8fc777f6d (futex: Remove requirement for lock_page() in get_futex_key())

Hi Mel,

Doing some RT tree consolidation this weekend to see what I should try
to upstream, I found that 4.[67]-rt trees fail ltp futex_wait04, and
tracked it down to commit in $subject.

Looking at that commit, I recalled it being in SLE, and SLERT working
just fine, so I went to see what a futex.c diff looked like.  Taking
what was left after tossing THP bits (irrelevant to RT) and applying
that to my RT trees fixes the testcase failure.

Snarfed-and-munged-by: Mike Galbraith <umgwanakikbuti <at> gmail.com>
---
 kernel/futex.c |   39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
 <at>  <at>  -469,7 +469,7  <at>  <at>  get_futex_key(u32 __user *uaddr, int fsh
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct page *page;
+	struct page *page, *page_head;
 	struct address_space *mapping;
 	int err, ro = 0;

 <at>  <at>  -520,6 +520,12  <at>  <at>  get_futex_key(u32 __user *uaddr, int fsh
 	else
 		err = 0;
(Continue reading)

Luis Claudio R. Goncalves | 3 Jun 18:37 2016

Lockdep chain_key key collision warning on 4.6.1-rt3

Hello,

Right after boot, on both 4.6.1-rt2 and 4.6.1-rt3, I saw the lockdep warning
listed below. What caught my attention are those two lines:

   DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))

   modprobe/1050: Hash chain already cached but the contents don't match!

Anybody else saw something similar?

[   30.736024] ------------[ cut here ]------------
[   30.736028] WARNING: CPU: 1 PID: 1050 at /home/lclaudio/kernel-rt/kernel/locking/lockdep.c:2090 __lock_acquire+0x17d8/0x1fb0
[   30.736030] DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))
[   30.736059] Modules linked in: nf_conntrack(+) bnep coretemp kvm_intel kvm arc4 rt2800pci rt2800mmio
rt2800lib eeprom_93cx6 rt2x00pci rt2x00mmio rt2x00lib btusb btrtl btbcm vfat fat mac80211 btintel
bluetooth iTCO_wdt iTCO_vendor_support joydev irqbypass snd_hda_codec_idt crc32c_intel pcspkr
ghash_clmulni_intel snd_hda_codec_generic snd_hda_intel snd_hda_codec cfg80211 acpi_cpufreq
snd_hda_core crc_ccitt rfkill snd_hwdep tpm_tis snd_seq tpm snd_seq_device snd_pcm shpchp snd_timer
snd soundcore lpc_ich mfd_core i2c_i801 nfsd auth_rpcgss nfs_acl lockd grace sunrpc binfmt_misc
sch_fq_codel i915 serio_raw i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt
fb_sys_fops drm r8169 mii i2c_core video usb_storage efivarfs
[   30.736060] CPU: 1 PID: 1050 Comm: modprobe Not tainted 4.6.1-rt3 #2
[   30.736061] Hardware name: Hewlett-Packard p7-1512/2ADA, BIOS 8.15 02/05/2013
[   30.736063]  0000000000000086 00000000c9a2388d ffff8800d31c34a8 ffffffff813f1c5c
[   30.736064]  ffff8800d31c34f8 0000000000000000 ffff8800d31c34e8 ffffffff81088954
[   30.736065]  0000082a00000008 ffff88003ca3c000 0000000000000000 ffffffff8239cb20
[   30.736065] Call Trace:
[   30.736069]  [<ffffffff813f1c5c>] dump_stack+0x67/0x9b
[   30.736070]  [<ffffffff81088954>] __warn+0xe4/0x100
(Continue reading)

Pratyush Patel | 2 Jun 18:05 2016
Picon
Gravatar

PREEMPT_RT git tree

Hello,

I want to use the CONFIG_PREEMPT_RT git tree for development and
testing instead of patching a Linux kernel. Could anyone please let me
know where I can find the current stable/development trees?

Note that I already tried cloning linux-stable-rt:

$ git clone http://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git/

However, I noticed that this is based on the 3.x kernel version and
the latest commit as per 'git log' was in 2011, whereas the current rt
patch is for Linux 4.4. I have been unable to find any newer git tree
version.

Thanks,
Pratyush
--
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

Pankaj Gupta | 2 Jun 12:10 2016
Picon

Query - state of memory hotplug with RT kernel

Hello,

Recently, I have been debugging some of the issues with memory 
hotplug with RT kernel. I want to know state of memory hotplug 
with RT kernel and if there are any known issues or work going
on upstream?

I came to know that there is rework of 'cpu hotplug' going on.
Not sure about 'memory hotplug'.

Any inputs or pointers on this?

Best regards,
Pankaj
--
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