. cputime_t can
always fit into it.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Stanislaw Gruszka sgrus...@redhat.com
Cc: Thomas Gleixner t...@linutronix.de
Cc: Peter Zijlstra a.p.zijls...@chello.nl
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@elte.hu
Cc: Oleg
Consolidate the common code amongst per thread and per process
timers list on tick time.
List traversal, expiry check and subsequent updates can be
shared in a common helper.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Stanislaw Gruszka sgrus...@redhat.com
Cc: Thomas Gleixner t
Cleaning up the posix cpu timers on task exit shares
some common code among timer list types, most notably the
list traversal and expiry time update.
Unify this in a common helper.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Stanislaw Gruszka sgrus...@redhat.com
Cc: Thomas Gleixner
2013/2/19 Marcelo Tosatti mtosa...@redhat.com:
On Mon, Feb 18, 2013 at 05:43:47PM +0100, Frederic Weisbecker wrote:
2013/2/5 Michael Wolf m...@linux.vnet.ibm.com:
In the case of where you have a system that is running in a
capped or overcommitted environment the user may see steal time
2013/3/5 Michael Wolf m...@linux.vnet.ibm.com:
Sorry for the delay in the response. I did not see the email
right away.
On Mon, 2013-02-18 at 22:11 -0300, Marcelo Tosatti wrote:
On Mon, Feb 18, 2013 at 05:43:47PM +0100, Frederic Weisbecker wrote:
2013/2/5 Michael Wolf m
cjash...@linux.vnet.ibm.com
Cc: Frederic Weisbecker fweis...@gmail.com
Cc: Ingo Molnar mi...@elte.hu
Cc: Namhyung Kim namhy...@kernel.org
Cc: Paul Mackerras pau...@samba.org
Cc: Peter Zijlstra a.p.zijls...@chello.nl
Cc: Arnaldo Carvalho de Melo a...@redhat.com
---
kernel/events/ring_buffer.c
2013/3/6 Jiri Olsa jo...@redhat.com:
nope, because CONFIG_PERF_USE_VMALLOC rb uses only 1st slot
of rg-data_pages[], so rb-nr_page is either 0 or 1
the actuall number of pages is counted via rb-page_order
(which is -1 for case with no data pages)
Ah right.
--
To unsubscribe from this list:
Hi,
This new set handles the div64_u64_rem() implementation in 32 bits.
If no comment arise I'll test further the 32 bits case then send a pull
request to Ingo.
Thanks.
Frederic Weisbecker (2):
math64: New div64_u64_rem helper
sched: Lower chances of cputime scaling overflow
include/linux
Provide an extended version of div64_u64() that
also returns the remainder of the division.
We are going to need this to refine the cputime
scaling code.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Stanislaw Gruszka sgrus...@redhat.com
Cc: Steven Rostedt rost...@goodmis.org
Cc
to the signal struct. And then we'll need to
scale one-by-one the live threads cputime in thread_group_cputime(). The
drawback may be a slightly slower code on exit time.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Stanislaw Gruszka sgrus...@redhat.com
Cc: Steven Rostedt rost...@goodmis.org
Cc
there).
Thanks.
---
Changes include:
* Generalize exception handling
* Fix race in context tracking state restore on return from exception
and irq exit kernel preemption
* Fix cputime scaling in full dynticks accounting dynamic off-case
* Fix default Kconfig value
---
Frederic Weisbecker (5
2013/2/11 Borislav Petkov b...@alien8.de:
On Tue, Jan 08, 2013 at 03:08:07AM +0100, Frederic Weisbecker wrote:
[ … ]
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 8601f0d..dc6381d 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -70,6 +70,15 @@ config NO_HZ
2013/2/20 Borislav Petkov b...@alien8.de:
On Mon, Feb 11, 2013 at 03:35:29PM +0100, Borislav Petkov wrote:
+/* Parse the boot-time nohz CPU list from the kernel parameters. */
+static int __init tick_nohz_full_setup(char *str)
+{
+ alloc_bootmem_cpumask_var(full_nohz_mask);
+
2013/1/8 Li Zhong zh...@linux.vnet.ibm.com:
On Tue, 2013-01-08 at 03:08 +0100, Frederic Weisbecker wrote:
move_tasks() and active_load_balance_cpu_stop() both need
to have the busiest rq clock uptodate because they may end
up calling can_migrate_task() that uses rq-clock_task
to determine
2013/1/23 Hakan Akkan hakanak...@gmail.com:
Hi,
This WARN_ON is triggered for every full nohz CPU in the system during
AP boot in a 16 core machine:
Yeah it happens because we are enqueuing a timer to an offline CPU.
I'm trying to fix it, tell me if you still see the warning on the next
2012/11/29 Li Zhong zh...@linux.vnet.ibm.com:
On Tue, 2012-11-27 at 19:33 +0100, Frederic Weisbecker wrote:
[]
-
- WARN_ON_ONCE(!current-mm);
-
- local_irq_save(flags);
- rdtp = __get_cpu_var(rcu_dynticks);
- if (!rdtp-ignore_user_qs !rdtp-in_user
2012/11/29 Li Zhong zh...@linux.vnet.ibm.com:
On Wed, 2012-11-28 at 13:55 +0100, Frederic Weisbecker wrote:
With rcu_user_exit() at the beginning, now rcu_irq_enter() only protects
the cpu idle eqs, but it's not good to call rcu_irq_exit() after the cpu
halt and the page ready.
Hmm, why
2012/11/29 Gleb Natapov g...@redhat.com:
On Wed, Nov 28, 2012 at 03:25:07PM +0100, Frederic Weisbecker wrote:
2012/11/28 Gleb Natapov g...@redhat.com:
On Wed, Nov 28, 2012 at 01:55:42PM +0100, Frederic Weisbecker wrote:
Yes but if rcu_irq_*() calls are fine to be called there, and I
the adjustement code
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Frederic Weisbecker (4):
cputime: Move thread_group_cputime() to sched code
cputime: Rename thread_group_times to thread_group_cputime_adjusted
2012/11/28 Hakan Akkan hakanak...@gmail.com:
+static int check_drop_timer_duty(int cpu)
+{
+ int curr_handler, prev_handler, new_handler;
+ int nrepeat = -1;
+ bool drop_recheck;
+
+repeat:
+ WARN_ON_ONCE(++nrepeat 1);
+ drop_recheck = false;
+
2012/12/2 Stephen Rothwell s...@canb.auug.org.au:
Well, these are a bit late (I expected Linus to release v3.7 today), but
since Ingo has not piped in over the weekend, I have added them from today
after the tip tree merge.
Yeah sorry to submit that so late. Those branches are in pending pull
2013/2/8 Stephen Rothwell s...@canb.auug.org.au:
Hi Frederic,
On Fri, 8 Feb 2013 14:07:49 +1100 Stephen Rothwell s...@canb.auug.org.au
wrote:
This patch has the side effect of changing the default configurations:
(This is PowerPC pseries_defconfig before/after this patch)
@@ -119,8
2013/2/4 Vincent Guittot vincent.guit...@linaro.org:
On 1 February 2013 19:03, Frederic Weisbecker fweis...@gmail.com wrote:
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 257002c..fd41924 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5884,6 +5884,7 @@ static
2013/2/7 Ingo Molnar mi...@kernel.org:
* Frederic Weisbecker fweis...@gmail.com wrote:
2013/2/7 Ingo Molnar mi...@kernel.org:
* Steven Rostedt rost...@goodmis.org wrote:
I'll reply to this as I come up with comments.
First thing is, don't call it NO_HZ_FULL. A better name would
2013/2/7 Christoph Lameter c...@linux.com:
On Thu, 7 Feb 2013, Frederic Weisbecker wrote:
Not with hrtick.
hrtick? Did we not already try that a couple of years back and it turned
out that the overhead of constantly reprogramming a timer via the PCI bus
was causing too much of a performance
-by: Frederic Weisbecker fweis...@gmail.com
---
arch/powerpc/include/asm/thread_info.h |7 +--
arch/powerpc/kernel/ptrace.c |5 +
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/thread_info.h
b/arch/powerpc/include/asm
2013/2/1 Li Zhong zh...@linux.vnet.ibm.com:
This is the exception hooks for context tracking subsystem, including
data access, program check, single step, instruction breakpoint, machine
check,
alignment, fp unavailable, altivec assist, unknown exception, whose handlers
might use RCU.
This
that context location
and cputime snaphots are synchronized between write and read
side such that the latter can safely retrieve the pending tickless
cputime of a task and add it to its latest cputime snapshot to
return the correct result to the user.
Signed-off-by: Frederic Weisbecker fweis
just made a new branch
that contains tip:irq/core with nohz/printk-v8 merged inside which deals
with the conflict.
Thanks.
---
Frederic Weisbecker (5):
nohz: Add API to check tick state
irq_work: Don't stop the tick with pending works
irq_work: Make self-IPIs optable
2013/2/5 Andrew Morton a...@linux-foundation.org:
On Tue, 5 Feb 2013 01:51:18 +0100
Frederic Weisbecker fweis...@gmail.com wrote:
printk: Wake up klogd using irq_work
That seems reasonable.
I'm wondering if we can now remove the printk_sched() special-case.
iirc, that was needed
2013/2/5 Steven Rostedt rost...@goodmis.org:
On Mon, 2013-02-04 at 18:09 -0800, Andrew Morton wrote:
Maybe there were other deadlock scenarios, dunno. That knowledge
appears to be disappearing into the mists of time :(
Discussing this on IRC with Frederic, he brought up that the
2013/2/5 Andrew Morton a...@linux-foundation.org:
On Mon, 4 Feb 2013 23:17:10 +0100
Jan Kara j...@suse.cz wrote:
A CPU can be caught in console_unlock() for a long time (tens of seconds are
reported by our customers) when other CPUs are using printk heavily and
serial
console makes
2013/2/6 Ingo Molnar mi...@kernel.org:
btw., I got a non-trivial conflicts in
kernel/context_tracking.c, with the following commits
interacting between the RCU tree (tip:core/rcu) and the
scheduler tree (tip:sched/core):
6a61671bb2f3 cputime: Safely read cputime of full dynticks CPUs
---
Frederic Weisbecker (26):
nohz: Basic full dynticks interface
nohz: Assign timekeeping duty to a non-full-nohz CPU
nohz: Trace timekeeping update
nohz: Wake up full dynticks CPUs when a timer gets enqueued
rcu: Restart the tick on non-responding full dynticks CPUs
sched: Comment on rq-clock
2013/2/6 Daniel Baluta dbal...@ixiacom.com:
Obviously this is a typo and could result in memory leaks
if kzalloc fails on a given cpu.
Signed-off-by: Daniel Baluta dbal...@ixiacom.com
Good catch!
Acked-by: Frederic Weisbecker fweis...@gmail.com
---
kernel/events/hw_breakpoint.c |2
2013/2/1 Li Zhong zh...@linux.vnet.ibm.com:
This is the syscall slow path hooks for context tracking subsystem,
corresponding to
[PATCH] x86: Syscall hooks for userspace RCU extended QS
commit bf5a3c13b939813d28ce26c01425054c740d6731
TIF_MEMDIE is moved to the second 16-bits (with value
2013/2/7 Li Zhong zh...@linux.vnet.ibm.com:
On Thu, 2013-02-07 at 01:29 +0100, Frederic Weisbecker wrote:
In x86-64, schedule_user() and do_notify_resume() can be called before
syscall_trace_leave(). As a result we may be entering
syscall_trace_leave() in user mode (from a context tracking POV
2013/2/7 Ingo Molnar mi...@kernel.org:
* Steven Rostedt rost...@goodmis.org wrote:
I'll reply to this as I come up with comments.
First thing is, don't call it NO_HZ_FULL. A better name would
be NO_HZ_CPU. I would like to reserve NO_HZ_FULL when we
totally remove jiffies :-)
I don't
2013/2/7 Steven Rostedt rost...@goodmis.org:
I'll reply to this as I come up with comments.
First thing is, don't call it NO_HZ_FULL. A better name would be
NO_HZ_CPU. I would like to reserve NO_HZ_FULL when we totally remove
jiffies :-)
I'm not sure we'll ever be able to completely remove
2013/2/7 Steven Rostedt rost...@goodmis.org:
On Thu, 2013-02-07 at 17:25 +0100, Frederic Weisbecker wrote:
At least for now we seem to agree on CONFIG_NO_HZ_IDLE and keep
CONFIG_NO_HZ for compatibility. Are you ok with that? If so I'll send
a patch.
I believe that Ingo was suggesting
2013/2/7 Steven Rostedt rost...@goodmis.org:
On Thu, 2013-02-07 at 17:41 +0100, Frederic Weisbecker wrote:
I'm not convinced that single task must be a fundamental component
of this. It's an implementation detail. We should be able to keep the
tick off in the future when more than one task
2013/2/7 Steven Rostedt rost...@goodmis.org:
On Thu, 2013-02-07 at 17:45 +0100, Frederic Weisbecker wrote:
config NO_HZ_TASK
bool Stop tick on specified CPUs when single task is running
default n
depends on NO_HZ
Ok I launched another debate about that single
2013/1/29 Steven Rostedt rost...@goodmis.org:
On Tue, 2013-01-29 at 16:12 +0100, Frederic Weisbecker wrote:
I have set some cputime tracepoint and looked at the stacktrace. They
are sorted by weight, which is the amount of cputime accounted. I
can't find anything wrong on these. See
2013/1/29 Steven Rostedt rost...@goodmis.org:
On Mon, 2013-01-28 at 21:36 -0500, Steven Rostedt wrote:
[root@bxtest ~]# time /work/c/kernelspin 10
real 0m10.001s
user 0m1.114s
sys 0m8.886s
But after enabling the force context_tracking I get this:
[root@bxtest ~]# time
2013/1/28 Sedat Dilek sedat.di...@gmail.com:
On Mon, Jan 28, 2013 at 8:04 PM, Frederic Weisbecker fweis...@gmail.com
wrote:
While remotely reading the cputime of a task running in a
full dynticks CPU, the values stored in utime/stime fields
of struct task_struct may be stale. Its values may
2013/1/31 Sedat Dilek sedat.di...@gmail.com:
On Thu, Jan 31, 2013 at 1:38 AM, Frederic Weisbecker fweis...@gmail.com
wrote:
2013/1/28 Sedat Dilek sedat.di...@gmail.com:
On Mon, Jan 28, 2013 at 8:04 PM, Frederic Weisbecker fweis...@gmail.com
wrote:
While remotely reading the cputime
2013/1/31 Sedat Dilek sedat.di...@gmail.com:
I still dunno all parts of dynticks and their correlation.
AFAICS they seem to be independent, can't say if it is complete with
dynticks-cputime-only.
Dynticks cputime and dynticks printk are both standalone and
independant. In mainline, both printk
2013/1/29 Vincent Guittot vincent.guit...@linaro.org:
On my smp platform which is made of 5 cores in 2 clusters,I have the
nr_busy_cpu field of sched_group_power struct that is not null when the
platform is fully idle. The root cause seems to be:
During the boot sequence, some CPUs reach the
2013/2/2 anish kumar anish198519851...@gmail.com:
On Sat, 2013-01-26 at 17:24 +0100, Frederic Weisbecker wrote:
2012/11/3 anish kumar anish198519851...@gmail.com:
From: anish kumar anish198519851...@gmail.com
As no one is using the return value of irq_work_queue function
it is better
__irq_work_queue
intermediate function]
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
---
include/linux/irq_work.h |2 +-
kernel/irq_work.c| 31 ++-
2 files changed, 11 insertions(+), 22 deletions(-)
diff --git a/include/linux/irq_work.h b/include/linux
2013/2/22 Vincent Guittot vincent.guit...@linaro.org:
I wanted to avoid having to use the sd pointer for testing NOHZ_IDLE
flag because it occurs each time we go into idle but it seems to be
not easily feasible.
Another solution could be to add a synchronization step between
2013/2/26 Thomas Gleixner t...@linutronix.de:
On Fri, 22 Feb 2013, Linus Torvalds wrote:
On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner t...@linutronix.de wrote:
I prefer to let you guys have the final word on this patch. Whether you
apply it or not, I fear I'll never be entirely happy
2013/2/21 Kevin Hilman khil...@linaro.org:
From a8a0a8b8b12512a7f862ade459cd88d2b48e2bf3 Mon Sep 17 00:00:00 2001
From: Kevin Hilman khil...@linaro.org
Date: Thu, 14 Feb 2013 11:27:36 -0800
Subject: [PATCH 4/5] cputime: use do_div() for nsec resolution conversion
helpers
For the nsec
2013/2/26 Thomas Gleixner t...@linutronix.de:
On Tue, 26 Feb 2013, Frederic Weisbecker wrote:
2013/2/26 Thomas Gleixner t...@linutronix.de:
On Fri, 22 Feb 2013, Linus Torvalds wrote:
On Fri, Feb 22, 2013 at 7:06 AM, Thomas Gleixner t...@linutronix.de
wrote:
I prefer to let you
2013/2/26 Vincent Guittot vincent.guit...@linaro.org:
On 26 February 2013 14:16, Frederic Weisbecker fweis...@gmail.com wrote:
2013/2/22 Vincent Guittot vincent.guit...@linaro.org:
I wanted to avoid having to use the sd pointer for testing NOHZ_IDLE
flag because it occurs each time we go
(because
nr_pages is 0). This needs to be recognized in the rb_free_work
function and set 'nr' to 0 in this case, so only the user page
gets freed.
Reported-by: Jan Stancek jstan...@redhat.com
Signed-off-by: Jiri Olsa jo...@redhat.com
Cc: Corey Ashford cjash...@linux.vnet.ibm.com
Cc: Frederic
2013/2/27 Kevin Hilman khil...@linaro.org:
From 61e35f069a64c03a2bce348487d41072aeb9f36b Mon Sep 17 00:00:00 2001
From: Kevin Hilman khil...@linaro.org
Date: Thu, 14 Feb 2013 10:17:37 -0800
Subject: [PATCH] context tracking: conditionalize guest support based on
CONFIG_KVM
So that it can
On Wed, Feb 27, 2013 at 09:28:26AM +0100, Vincent Guittot wrote:
Ok I don't like having a per cpu state in struct sched domain but for
now I can't find anything better. So my suggestion is that we do this
and describe well the race, define the issue in the changelog and code
comments and
Hi,
Until everyone agrees on https://patchwork.kernel.org/patch/2174211/ ,
here are two commits that seem quite uncontroversial to me.
Please pull from:
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
irq/urgent-for-tip
Thanks.
Frederic Weisbecker (2):
irq
in the end of this function that is not covered by the
HARDIRQ_OFFSET but want to stay non-preemptible.
Now that irq are always disabled in irq_exit(), the whole code
is guaranteed not to be preempted. We can thus remove this hack.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Linus Torvalds
not be a problem for these archs. Prior to
this commit this was already happening anytime we processed
pending softirqs anyway.
Suggested-by: Linus Torvalds torva...@linux-foundation.org
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Linus Torvalds torva...@linux-foundation.org
Cc: Thomas
Hi,
Here is a bunch of patches preview for 3.10
Thanks.
Frederic Weisbecker (5):
context_tracking: Move exception handling to generic code
context_tracking: Restore correct previous context state on exception
exit
context_tracking: Restore preempted context state after
Exceptions handling on context tracking should share common
treatment: on entry we exit user mode if the exception triggered
in that context. Then on exception exit we return to that previous
context.
Generalize this to avoid duplication across archs.
Signed-off-by: Frederic Weisbecker fweis
exactly. If so,
sorry for the missing credit).
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Kevin Hilman khil...@linaro.org
Cc: Mats Liljegren mats.liljeg...@enea.com
Cc: Peter Zijlstra pet...@infradead.org
Cc: Ingo Molnar mi...@kernel.org
Cc
accounting to
improve its result. We are doing this for CONFIG_TICK_CPU_ACCOUNTING,
now we also need to expand it to full dynticks accounting dynamic
off-case as well.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Kevin Hilman khil...@linaro.org
Cc
dynticks cputime accounting.
Let's enable these probes selftests by default for now.
Suggested: Steven Rostedt rost...@goodmis.org
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Kevin Hilman khil...@linaro.org
Cc: Mats Liljegren mats.liljeg...@enea.com
, if preempt_schedule_irq() is called in the tiny frame between
user_enter() and the actual return to userspace, we resume userspace with
the wrong context tracking state.
Fix this by using exception_enter/exit() which are a perfect fit for this
kind of issue.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Li
2012/12/3 Vincent Guittot vincent.guit...@linaro.org:
With the coupled cpuidle driver (but probably also with other drivers),
a CPU loops in a temporary safe state while waiting for other CPUs of its
cluster to be ready to enter the coupled C-state. If an IRQ or a softirq
occurs, the CPU will
2013/1/24 Xiaotian Feng xtf...@gmail.com:
On Thu, Jan 10, 2013 at 2:33 AM, Frederic Weisbecker fweis...@gmail.com
wrote:
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -509,11 +509,11 @@ EXPORT_SYMBOL_GPL(vtime_account);
# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies
2013/1/25 Vincent Guittot vincent.guit...@linaro.org:
This sequence is not the right one
I'm going to look for the saved trace to check the sequence above
I haven't been able to reproduce the bug that this patch was supposed to
solved. The patch 2 and 3 seem enough to fix the nr_busy_cpus
2013/1/25 Vincent Guittot vincent.guit...@linaro.org:
Le 25 janv. 2013 13:00, Frederic Weisbecker fweis...@gmail.com a écrit :
2013/1/25 Vincent Guittot vincent.guit...@linaro.org:
This sequence is not the right one
I'm going to look for the saved trace to check the sequence above
2013/1/26 Paul E. McKenney paul...@linux.vnet.ibm.com:
Right... Replied to the wrong email. :-/
I queued context_tracking: Add comments on interface and internals.
Sounds perfect, thanks :)
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to
2012/11/16 liguang lig.f...@cn.fujitsu.com:
Signed-off-by: liguang lig.f...@cn.fujitsu.com
---
kernel/sched/cputime.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 81b763b..d2c24c1 100644
---
2013/1/26 Joe Perches j...@perches.com:
On Sat, 2013-01-26 at 01:45 +0100, Frederic Weisbecker wrote:
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
[]
@@ -282,7 +282,7 @@ static __always_inline bool
steal_account_process_tick(void)
[]
- return st
sgrus...@redhat.com
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@kernel.org
Cc: Oleg Nesterov o...@redhat.com
Cc: Peter Zijlstra pet...@infradead.org
---
kernel/sched/cputime.c | 18 +-
1 files changed, 9
2012/11/3 anish kumar anish198519851...@gmail.com:
From: anish kumar anish198519851...@gmail.com
As no one is using the return value of irq_work_queue function
it is better to just make it void.
Acked-by: Steven Rostedt rost...@goodmis.org
Signed-off-by: anish kumar
result to the user.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
---
Changes since v6:
* Fix build error with kvm modules (Thanks Sedat Dilek and
Wu Fenguang)
* Fix mistyped header inclusion in ia64
* Fix more missing symbols for kvm
---
Frederic Weisbecker (8):
context_tracking
Export the context state: whether we run in user / kernel
from the context tracking subsystem point of view.
This is going to be used by the generic virtual cputime
accounting subsystem that is needed to implement the full
dynticks.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc
tick and vtime based accounting anytime in order to minimize the
overhead associated to user hooks.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@kernel.org
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Namhyung Kim namhyung
.
To fix this, flush the cputime of the dynticks CPUs on
kernel - user transition and record the time / context
where we did this. Then on top of this snapshot and the current
time, perform the fixup on the reader side from task_times()
accessors.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc
Do some ground preparatory work before adding guest_enter()
and guest_exit() context tracking callbacks. Those will
be later used to read the guest cputime safely when we
run in full dynticks mode.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
so all we need is to librarize its implementation in the asm
generic headers.
Also librarize the default per jiffy granularity cputime_t
as well so that we can easily pick either implementation
depending on the cputime accounting config we choose.
Signed-off-by: Frederic Weisbecker fweis
This is in preparation for the full dynticks feature. While
remotely reading the cputime of a task running in a full
dynticks CPU, we'll need to do some extra-computation. This
way we can account the time it spent tickless in userspace
since its last cputime snapshot.
Signed-off-by: Frederic
-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@kernel.org
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Namhyung Kim namhyung@lge.com
Cc: Paul E. McKenney paul...@linux.vnet.ibm.com
Cc: Paul Gortmaker paul.gortma...@windriver.com
Cc: Peter
this definition to the jiffies based
cputime headers as it is the only place where it belongs to.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@kernel.org
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Namhyung Kim namhyung
2013/1/28 Christoph Lameter c...@linux.com:
On Mon, 28 Jan 2013, Frederic Weisbecker wrote:
My last concern is the dependency on CONFIG_64BIT. We rely on cputime_t
being u64 for reasonable nanosec granularity implementation. And therefore
we need a single instruction fetch to read kernel
2013/1/29 Steven Rostedt rost...@goodmis.org:
On Mon, 2013-01-28 at 20:03 +0100, Frederic Weisbecker wrote:
Ingo,
Please pull the new full dynticks cputime accounting code that
can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
tags/full
2013/1/28 Christoph Lameter c...@linux.com:
On Mon, 28 Jan 2013, Frederic Weisbecker wrote:
2013/1/28 Christoph Lameter c...@linux.com:
On Mon, 28 Jan 2013, Frederic Weisbecker wrote:
My last concern is the dependency on CONFIG_64BIT. We rely on cputime_t
being u64 for reasonable
2013/1/29 Steven Rostedt rost...@goodmis.org:
On Mon, 2013-01-28 at 19:02 -0500, Steven Rostedt wrote:
I've ran these through some basic tests and I don't see any issues. But
why did you drop the 'comment' patch that you had in v6?
Acked-by: Steven Rostedt rost...@goodmis.org
I'm sorry
2013/1/29 Steven Rostedt rost...@goodmis.org:
On Tue, 2013-01-29 at 03:39 +0100, Frederic Weisbecker wrote:
Please send me your kernelspin so I can test as well.
http://rostedt.homelinux.com/private/kernelspin.c
I can't reproduce your issue. I'm getting almost the same results with
vtime
archs to make kern_cpustat reading to be atomic
Thanks.
---
Frederic Weisbecker (8):
context_tracking: Export context state for generic vtime
cputime: Librarize per nsecs resolution cputime definitions
cputime: Move default nsecs_to_cputime() to jiffies based cputime
file
cputime
Export the context state: whether we run in user / kernel
from the context tracking subsystem point of view.
This is going to be used by the generic virtual cputime
accounting subsystem that is needed to implement the full
dynticks.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc
this definition to the jiffies based
cputime headers as it is the only place where it belongs to.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@kernel.org
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Namhyung Kim namhyung
tick and vtime based accounting anytime in order to minimize the
overhead associated to user hooks.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@kernel.org
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Namhyung Kim namhyung
This is in preparation for the full dynticks feature. While
remotely reading the cputime of a task running in a full
dynticks CPU, we'll need to do some extra-computation. This
way we can account the time it spent tickless in userspace
since its last cputime snapshot.
Signed-off-by: Frederic
so all we need is to librarize its implementation in the asm
generic headers.
Also librarize the default per jiffy granularity cputime_t
as well so that we can easily pick either implementation
depending on the cputime accounting config we choose.
Signed-off-by: Frederic Weisbecker fweis
.
To fix this, flush the cputime of the dynticks CPUs on
kernel - user transition and record the time / context
where we did this. Then on top of this snapshot and the current
time, perform the fixup on the reader side from task_times()
accessors.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc
Do some ground preparatory work before adding guest_enter()
and guest_exit() context tracking callbacks. Those will
be later used to read the guest cputime safely when we
run in full dynticks mode.
Signed-off-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
-by: Frederic Weisbecker fweis...@gmail.com
Cc: Andrew Morton a...@linux-foundation.org
Cc: Ingo Molnar mi...@kernel.org
Cc: Li Zhong zh...@linux.vnet.ibm.com
Cc: Namhyung Kim namhyung@lge.com
Cc: Paul E. McKenney paul...@linux.vnet.ibm.com
Cc: Paul Gortmaker paul.gortma...@windriver.com
Cc: Peter
error with CONFIG_IRQ_TIME_ACCOUNTING (thanks Wu Fenguang)
- Depend on 64 bits archs to make kernel_cpustat reading to be atomic
Thanks.
---
Frederic Weisbecker (44):
irq_work: Fix racy IRQ_WORK_BUSY flag setting
irq_work: Fix racy check on work pending flag
irq_work: Remove
301 - 400 of 8299 matches
Mail list logo