08 Oct, 2007
1 commit
-
When using /proc/timer_stats on ppc64 I noticed the events/sec field wasnt
accurate. Sometimes the integer part was incorrect due to rounding (we
werent taking the fractional seconds into consideration).The fraction part is also wrong, we need to pad the printf statement and
take the bottom three digits of 1000 times the value.Signed-off-by: Anton Blanchard
Acked-by: Ingo Molnar
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
23 Sep, 2007
1 commit
-
In a desparate attempt to fix the suspend/resume problem on Andrews
VAIO I added a workaround which enforced the broadcast of the oneshot
timer on resume. This was actually resolving the problem on the VAIO
but was just a stupid workaround, which was not tackling the root
cause: the assignement of lower idle C-States in the ACPI processor_idle
code. The cpuidle patches, which utilize the dynamic tick feature and
go faster into deeper C-states exposed the problem again. The correct
solution is the previous patch, which prevents lower C-states across
the suspend/resume.Remove the enforcement code, including the conditional broadcast timer
arming, which helped to pamper over the real problem for quite a time.
The oneshot broadcast flag for the cpu, which runs the resume code can
never be set at the time when this code is executed. It only gets set,
when the CPU is entering a lower idle C-State.Signed-off-by: Thomas Gleixner
Tested-by: Andrew Morton
Cc: Len Brown
Cc: Venkatesh Pallipadi
Cc: Rafael J. Wysocki
Signed-off-by: Linus Torvalds
16 Sep, 2007
5 commits
-
Taking a cpu offline removes the cpu from the online mask before the
CPU_DEAD notification is done. The clock events layer does the cleanup
of the dead CPU from the CPU_DEAD notifier chain. tick_do_timer_cpu is
used to avoid xtime lock contention by assigning the task of jiffies
xtime updates to one CPU. If a CPU is taken offline, then this
assignment becomes stale. This went unnoticed because most of the time
the offline CPU went dead before the online CPU reached __cpu_die(),
where the CPU_DEAD state is checked. In the case that the offline CPU did
not reach the DEAD state before we reach __cpu_die(), the code in there
goes to sleep for 100ms. Due to the stale time update assignment, the
system is stuck forever.Take the assignment away when a cpu is not longer in the cpu_online_mask.
We do this in the last call to tick_nohz_stop_sched_tick() when the offline
CPU is on the way to the final play_dead() idle entry.Signed-off-by: Thomas Gleixner
-
When a cpu goes offline it is removed from the broadcast masks. If the
mask becomes empty the code shuts down the broadcast device. This is
wrong, because the broadcast device needs to be ready for the online
cpu going idle (into a c-state, which stops the local apic timer).Signed-off-by: Thomas Gleixner
-
The jinxed VAIO refuses to resume without hitting keys on the keyboard
when this is not enforced. It is unclear why the cpu ends up in a lower
C State without notifying the clock events layer, but enforcing the
oneshot broadcast here is safe.Signed-off-by: Thomas Gleixner
-
Timekeeping resume adjusts xtime by adding the slept time in seconds and
resets the reference value of the clock source (clock->cycle_last).
clock->cycle last is used to calculate the delta between the last xtime
update and the readout of the clock source in __get_nsec_offset(). xtime
plus the offset is the current time. The resume code ignores the delta
which had already elapsed between the last xtime update and the actual
time of suspend. If the suspend time is short, then we can see time
going backwards on resume.Suspend:
offs_s = clock->read() - clock->cycle_last;
now = xtime + offs_s;
timekeeping_suspend_time = read_rtc();Resume:
sleep_time = read_rtc() - timekeeping_suspend_time;
xtime.tv_sec += sleep_time;
clock->cycle_last = clock->read();
offs_r = clock->read() - clock->cycle_last;
now = xtime + offs_r;if sleep_time_seconds == 0 and offs_r < offs_s, then time goes
backwards.Fix this by storing the offset from the last xtime update and add it to
xtime during resume, when we reset clock->cycle_last:sleep_time = read_rtc() - timekeeping_suspend_time;
xtime.tv_sec += sleep_time;
xtime += offs_s; /* Fixup xtime offset at suspend time */
clock->cycle_last = clock->read();
offs_r = clock->read() - clock->cycle_last;
now = xtime + offs_r;Thanks to Marcelo for tracking this down on the OLPC and providing the
necessary details to analyze the root cause.Signed-off-by: Thomas Gleixner
Cc: John Stultz
Cc: Tosatti -
Lockdep complains about the access of rtc in timekeeping_suspend
inside the interrupt disabled region of the write locked xtime lock.
Move the access outside.Signed-off-by: Thomas Gleixner
Cc: John Stultz
12 Sep, 2007
1 commit
-
Seems to me that this timer will only get started on platforms that say
they don't want it?Signed-off-by: Tony Breeds
Cc: Paul Mackerras
Cc: Gabriel Paubert
Cc: Zachary Amsden
Acked-by: Thomas Gleixner
Cc: John Stultz
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
12 Aug, 2007
1 commit
-
I find a function(clockevents_unregister_notifier) which is not called by
anything in tree.Signed-off-by: Miao Xie
Acked-by: Thomas Gleixner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
01 Aug, 2007
1 commit
-
On every open/close one struct seq_operations leaks.
Kudos to /proc/slab_allocators.Signed-off-by: Alexey Dobriyan
Acked-by: Ingo Molnar
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
26 Jul, 2007
2 commits
-
This avoids xtime lag seen with dynticks, because while 'xtime' itself
is still not updated often, we keep a 'xtime_cache' variable around that
contains the approximate real-time that _is_ updated each time we do a
'update_wall_time()', and is thus never off by more than one tick.IOW, this restores the original semantics for 'xtime' users, as long as
you use the proper abstraction functions (ie 'current_kernel_time()' or
'get_seconds()' depending on whether you want a timespec or just the
seconds field).[ Updated Patch. As penance for my sins I've also yanked another #ifdef
that was added to avoid the xtime lag w/ hrtimers. ]Signed-off-by: John Stultz
Cc: Ingo Molnar
Cc: Thomas Gleixner
Signed-off-by: Linus Torvalds -
This avoids use of the kernel-internal "xtime" variable directly outside
of the actual time-related functions. Instead, use the helper functions
that we already have available to us.This doesn't actually change any behaviour, but this will allow us to
fix the fact that "xtime" isn't updated very often with CONFIG_NO_HZ
(because much of the realtime information is maintained as separate
offsets to 'xtime'), which has caused interfaces that use xtime directly
to get a time that is out of sync with the real-time clock by up to a
third of a second or so.Signed-off-by: John Stultz
Cc: Ingo Molnar
Cc: Thomas Gleixner
Signed-off-by: Linus Torvalds
22 Jul, 2007
5 commits
-
i386 and sparc64 have the identical code to update the cmos clock. Move it
into kernel/time/ntp.c as there are other architectures coming along with the
same requirements.[akpm@linux-foundation.org: build fixes]
Signed-off-by: Thomas Gleixner
Cc: Chris Wright
Cc: Ingo Molnar
Cc: john stultz
Cc: David Miller
Cc: Roman Zippel
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add some more debug information to the hrtimer and clock events code.
Signed-off-by: Ingo Molnar
Signed-off-by: Thomas Gleixner
Cc: john stultz
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
After discussing w/ Thomas over IRC, it seems the issue is the sched tick
fires on every cpu at the same time, causing extra lock contention.This smaller change, adds an extra offset per cpu so the ticks don't line up.
This patch also drops the idle latency from 40us down to under 20us.Signed-off-by: john stultz
Signed-off-by: Thomas Gleixner
Cc: Ingo Molnar
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
When a device is replaced by a better rated device, then the broadcast
mode needs to be evaluated again. When the new device has no requirement
for broadcasting, then the broadcast bits for the CPU must be cleared.Signed-off-by: Thomas Gleixner
Cc: john stultz
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
We need to make sure, that the clockevent devices are resumed, before
the tick is resumed. The current resume logic does not guarantee this.Add CLOCK_EVT_MODE_RESUME and call the set mode functions of the clock
event devices before resuming the tick / oneshot functionality.Fixup the existing users.
Thanks to Nigel Cunningham for tracking down a long standing thinko,
which affected the jinxed VAIO.[akpm@linux-foundation.org: xen build fix]
Signed-off-by: Thomas Gleixner
Cc: john stultz
Cc: Rusty Russell
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
21 Jul, 2007
2 commits
-
Remove time_interpolator code (This is generic code, but
only user was ia64. It has been superseded by the
CONFIG_GENERIC_TIME code).Signed-off-by: Bob Picco
Signed-off-by: John Stultz
Signed-off-by: Peter Keilty
Signed-off-by: Tony Luck
20 Jul, 2007
1 commit
-
clocksource_adjust() has a clock argument, which shadows the file global clock
variable. Fix this up.Signed-off-by: Thomas Gleixner
Cc: john stultz
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
18 Jul, 2007
1 commit
-
KSYM_NAME_LEN is peculiar in that it does not include the space for the
trailing '\0', forcing all users to use KSYM_NAME_LEN + 1 when allocating
buffer. This is nonsense and error-prone. Moreover, when the caller
forgets that it's very likely to subtly bite back by corrupting the stack
because the last position of the buffer is always cleared to zero.This patch increments KSYM_NAME_LEN by one and updates code accordingly.
* off-by-one bug in asm-powerpc/kprobes.h::kprobe_lookup_name() macro
is fixed.* Where MODULE_NAME_LEN and KSYM_NAME_LEN were used together,
MODULE_NAME_LEN was treated as if it didn't include space for the
trailing '\0'. Fix it.Signed-off-by: Tejun Heo
Acked-by: Paulo Marques
Cc: Benjamin Herrenschmidt
Cc: Paul Mackerras
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
17 Jul, 2007
4 commits
-
I forgot to remove capability.h from mm.h while removing sched.h! This
patch remedies that, because the only inline function which was using
CAP_something was made out of line.Cross-compile tested without regressions on:
all powerpc defconfigs
all mips defconfigs
all m68k defconfigs
all arm defconfigs
all ia64 defconfigsalpha alpha-allnoconfig alpha-defconfig alpha-up
arm
i386 i386-allnoconfig i386-defconfig i386-up
ia64 ia64-allnoconfig ia64-defconfig ia64-up
m68k
mips
parisc parisc-allnoconfig parisc-defconfig parisc-up
powerpc powerpc-up
s390 s390-allnoconfig s390-defconfig s390-up
sparc sparc-allnoconfig sparc-defconfig sparc-up
sparc64 sparc64-allnoconfig sparc64-defconfig sparc64-up
um-x86_64
x86_64 x86_64-allnoconfig x86_64-defconfig x86_64-upas well as my two usual configs.
Signed-off-by: Alexey Dobriyan
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add a flag in /proc/timer_stats to indicate deferrable timers. This will
let developers/users to differentiate between types of tiemrs in
/proc/timer_stats.Deferrable timer and normal timer will appear in /proc/timer_stats as below.
10D, 1 swapper queue_delayed_work_on (delayed_work_timer_fn)
10, 1 swapper queue_delayed_work_on (delayed_work_timer_fn)Also version of timer_stats changes from v0.1 to v0.2
Signed-off-by: Venkatesh Pallipadi
Acked-by: Ingo Molnar
Cc: Thomas Gleixner
Cc: john stultz
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Not called by anything in tree.
Signed-off-by: Andi Kleen
Acked-by: Ingo Molnar
Cc: Thomas Gleixner
Cc: john stultz
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The commits
411187fb05cd11676b0979d9fbf3291db69dbce2 (GTOD: persistent clock support)
c1d370e167d66b10bca3b602d3740405469383de (i386: use GTOD persistent clock
support)changed the monotonic time so that it no longer jumps after resume, but it's
not possible to use it for boot time and process start time calculations then.
Also, the uptime no longer increases during suspend.I add a variable to track the wall_to_monotonic changes, a function to get the
real boot time and a function to get the boot based time from the monotonic
one.[akpm@linux-foundation.org: remove exports, add comment]
Signed-off-by: Tomas Janousek
Cc: Tomas Smetana
Cc: John Stultz
Cc: Thomas Gleixner
Cc: Ingo Molnar
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
04 Jul, 2007
1 commit
-
The clock_was_set() call in seconds_overflow() which happens only when
leap seconds are inserted / deleted is wrong in two aspects:1. it results in a call to on_each_cpu() with interrupts disabled
2. it is potential deadlock source vs. call_lock in smp_call_function()The only possible side effect of the removal might be, that an absolute
CLOCK_REALTIME timer fires 1 second too late, in the rare case of leap
second deletion and an absolute CLOCK_REALTIME timer which expires in
the affected time frame. It will never fire too early.This was probably observed by the reporter of a June 30th -> July 1st
hang: http://lkml.org/lkml/2007/7/3/103A similar problem was observed by Dave Jones, who provided a screen shot
with a lockdep back trace, which allowed to analyse the problem.Signed-off-by: Thomas Gleixner
Acked-by: Ingo Molnar
Signed-off-by: Linus Torvalds
01 Jun, 2007
2 commits
-
Make timer-stats have almost zero overhead when enabled in the config but
not used. (this way distros can enable it more easily)Also update the documentation about overhead of timer_stats - it was
written for the first version which had a global lock and a linear list
walk based lookup ;-)Signed-off-by: Ingo Molnar
Cc: Thomas Gleixner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix two races in the timer stats lookup code. One by ensuring that the
initialization of a new entry is finished upon insertion of that entry.
The other by cleaning up the hash table when the entries array is cleared,
so that we don't have any "pre-inserted" entries.Thanks to Eric Dumazet for reminding me of the memory barriers.
Signed-off-by: Bjorn Steinbrink
Signed-off-by: Ian Kumlien
Acked-by: Ingo Molnar
Cc: Eric Dumazet
Cc: Thomas Gleixner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
30 May, 2007
1 commit
-
get_next_timer_interrupt() returns a delta of (LONG_MAX > 1) in case
there is no timer pending. On 64 bit machines this results in a
multiplication overflow in tick_nohz_stop_sched_tick().Reported by: Dave Miller
Make the return value a constant and limit the return value to a 32 bit
value.When the max timeout value is returned, we can safely stop the tick
timer device. The max jiffies delta results in a 12 days timeout for
HZ=1000.In the long term the get_next_timer_interrupt() code needs to be
reworked to return ktime instead of jiffies, but we have to wait until
the last users of the original NO_IDLE_HZ code are converted.Signed-off-by: Thomas Gleixner
Acked-off-by: David S. Miller
Signed-off-by: Linus Torvalds
24 May, 2007
2 commits
-
The warning in the NOHZ code, which triggers when a CPU goes idle with
softirqs pending can fill up the logs quite quickly. Rate limit the output
until we found the root cause of that problem.Signed-off-by: Thomas Gleixner
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Booting a SMP kernel with maxcpus=1 on a SMP system leads to a hard hang,
because ACPI ignores the maxcpus setting and sends timer broadcast info for
the offline CPUs. This results in a stuck for ever call to
smp_call_function_single() on an offline CPU.Ignore the bogus information and print a kernel error to remind ACPI
folks to fix it.Signed-off-by: Thomas Gleixner
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
22 May, 2007
1 commit
-
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectlyNet result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfigas well as my two usual configs.
Signed-off-by: Alexey Dobriyan
Signed-off-by: Linus Torvalds
15 May, 2007
2 commits
-
lockdep complains about the lock nesting of clocksource and watchdog lock
in the resume path.Change the resume marker to a bit operation and remove the lock from this
path.Signed-off-by: Thomas Gleixner
Cc: john stultz
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The time keeping code move to kernel/time/timekeeping.c broke the
clocksource resume logic patch, which got applied to the old file by a
fuzzy application. Fix it up and move the clocksource_resume() call to
the appropriate place.Signed-off-by: Thomas Gleixner
[ tssk, tssk, everybody should use --fuzz=0 ]
Signed-off-by: Linus Torvalds
10 May, 2007
3 commits
-
We need to make sure that the clocksources are resumed, when timekeeping is
resumed. The current resume logic does not guarantee this.Add a resume function pointer to the clocksource struct, so clocksource
drivers which need to reinitialize the clocksource can provide a resume
function.Add a resume function, which calls the maybe available clocksource resume
functions and resets the watchdog function, so a stable TSC can be used
accross suspend/resume.Signed-off-by: Thomas Gleixner
Cc: john stultz
Cc: Andi Kleen
Cc: Ingo Molnar
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
u64 and s64 are not necessarily 'long long' on some 64-bit
platforms, so explicit the type to kill the compiler warnings.Also consistently use '%Lu' which is unsigned.
Signed-off-by: David S. Miller
Cc: Thomas Gleixner
Cc: Ingo Molnar
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
There's more that need fixing, and fix my own subject spelling error too.
Signed-off-by: Daniel Walker
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
09 May, 2007
3 commits
-
Fix the process idle load balancing in the presence of dynticks. cpus for
which ticks are stopped will sleep till the next event wakes it up.
Potentially these sleeps can be for large durations and during which today,
there is no periodic idle load balancing being done.This patch nominates an owner among the idle cpus, which does the idle load
balancing on behalf of the other idle cpus. And once all the cpus are
completely idle, then we can stop this idle load balancing too. Checks added
in fast path are minimized. Whenever there are busy cpus in the system, there
will be an owner(idle cpu) doing the system wide idle load balancing.Open items:
1. Intelligent owner selection (like an idle core in a busy package).
2. Merge with rcu's nohz_cpu_mask?Signed-off-by: Suresh Siddha
Acked-by: Ingo Molnar
Cc: Thomas Gleixner
Cc: Nick Piggin
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
While the !highres/!dyntick code assigns the duty of the do_timer() call to
one specific CPU, this was dropped in the highres/dyntick part during
development.Steven Rostedt discovered the xtime lock contention on highres/dyntick due
to several CPUs trying to update jiffies.Add the single CPU assignement back. In the dyntick case this needs to be
handled carefully, as the CPU which has the do_timer() duty must drop the
assignement and let it be grabbed by another CPU, which is active.
Otherwise the do_timer() calls would not happen during the long sleep.Signed-off-by: Thomas Gleixner
Acked-by: Ingo Molnar
Cc: Steven Rostedt
Acked-by: Mark Lord
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
kallsyms_lookup() can go iterating over modules list unprotected which is OK
for emergency situations (oops), but not OK for regular stuff like
/proc/*/wchan.Introduce lookup_symbol_name()/lookup_module_symbol_name() which copy symbol
name into caller-supplied buffer or return -ERANGE. All copying is done with
module_mutex held, so...Signed-off-by: Alexey Dobriyan
Cc: Rusty Russell
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
