Setup clocksource mult_orig in clocksource_enable().

Clocksource drivers can save power by using keeping the
device clock disabled while the clocksource is unused.

In practice this means that the enable() and disable()
callbacks perform clk_enable() and clk_disable().

The enable() callback may also use clk_get_rate() to get
the clock rate from the clock framework. This information
can then be used to calculate the shift and mult variables.

Currently the mult_orig variable is setup from mult at
registration time only. This is conflicting with the above
case since the clock is disabled and the mult variable is
not yet calculated at the time of registration.

Moving the mult_orig setup code to clocksource_enable()
allows us to both handle the common case with no enable()
callback and the mult-changed-after-enable() case.

[ Impact: allow dynamic clock source usage ]
Signed-off-by: NMagnus Damm <damm@igel.co.jp>
LKML-Reference: <20090501054546.8193.10688.sendpatchset@rx1.opensource.se>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Add enable() and disable() callbacks for clocksources.

This allows us to put unused clocksources in power save mode.  The
functions clocksource_enable() and clocksource_disable() wrap the
callbacks and are inserted in the timekeeping code to enable before use
and disable after switching to a new clocksource.
Signed-off-by: NMagnus Damm <damm@igel.co.jp>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Pass clocksource pointer to the read() callback for clocksources.  This
allows us to share the callback between multiple instances.

[hugh@veritas.com: fix powerpc build of clocksource pass clocksource mods]
[akpm@linux-foundation.org: cleanup]
Signed-off-by: NMagnus Damm <damm@igel.co.jp>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The time_status conditional was accidentally placed right after we clear
the checked time_status bits, which causes us to take the conditional
every time through. This fixes it by moving the conditional to before we
clear the time_status bits.
Signed-off-by: NJohn Stultz <johnstul@us.ibm.com>
Cc: Clark Williams <williams@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

The 'time_adj' local variable is named in a very confusing
way because it almost shadows the 'time_adjust' global
variable - which is used in this same function.

Rename it to 'delta' - to make them stand apart more clearly.

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2545	    114	    144	   2803	    af3	ntp.o.before
   2545	    114	    144	   2803	    af3	ntp.o.after

md5:
   1bf0b3be564512279ba7cee299d1d2be  ntp.o.before.asm
   1bf0b3be564512279ba7cee299d1d2be  ntp.o.after.asm
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: micro-optimization

Convert the (internal) ntp_tick_adj value we store from unscaled
units to scaled units. This is a constant that we never modify,
so scaling it up once during bootup is enough - we dont have to
do it for every adjustment step.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

 - make PPM_SCALE an explicit s64 constant, to
   remove (s64) casts from usage sites.

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2536	    114	    136	   2786	    ae2	ntp.o.before
   2536	    114	    136	   2786	    ae2	ntp.o.after

md5:
   40a7728d1188aa18e83e21a81fa7b150  ntp.o.before.asm
   40a7728d1188aa18e83e21a81fa7b150  ntp.o.after.asm
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

Further simplify do_adjtimex():

 - introduce the ntp_start_leap_timer() helper function
 - eliminate the goto adj_done complication
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

do_adjtimex() is currently a monster function with a maze of
branches. Refactor the txc->modes setting aspects of it into
two new helper functions:

	process_adj_status()
	process_adjtimex_modes()

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2512	    114	    136	   2762	    aca	ntp.o.before
   2512	    114	    136	   2762	    aca	ntp.o.after
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: change (fix) the way the NTP PLL seconds offset is initialized/tracked

Fix a bug and do a micro-optimization:

When PLL is enabled we do not reset time_reftime. If the PLL
was off for a long time (for example after bootup), this is
arguably the wrong thing to do.

We already had a hack for the common boot-time case in
ntp_update_offset(), in form of:

	if (unlikely(time_status & STA_FREQHOLD || time_reftime == 0))
 		secs = 0;

But the update delta should be reset later on too - not just when
the PLL is enabled for the first time after bootup.

So do it on !STA_PLL -> STA_PLL transitions.

This changes behavior, as previously if ntpd was disabled for
a long time and we restarted it, we'd run from that last update,
with a very large delta.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

The time_reftime update in ntp_update_offset() to xtime.tv_sec
is a convoluted way of saying that we want to freeze the frequency
and want the 'secs' delta to be 0. Also make this branch unlikely.

This shaves off 8 bytes from the code size:

   text	   data	    bss	    dec	    hex	filename
   2504	    114	    136	   2754	    ac2	ntp.o.before
   2496	    114	    136	   2746	    aba	ntp.o.after
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

Change ntp_update_offset_fll() to delta logic instead of
absolute value logic. This eliminates 'freq_adj' from the
function.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

- introduce the ntp_update_offset_fll() helper
- clean up the flow and variable naming

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2504	    114	    136	   2754	    ac2	ntp.o.before
   2504	    114	    136	   2754	    ac2	ntp.o.after

md5:
   01f7b8e1a5472a3056f9e4ae84d46315  ntp.o.before.asm
   01f7b8e1a5472a3056f9e4ae84d46315  ntp.o.after.asm
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

Change ntp_update_frequency() from a hard to follow code
flow that uses global variables as temporaries, to a clean
input+output flow.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

Prepare a refactoring of ntp_update_frequency().

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2504	    114	    136	   2754	    ac2	ntp.o.before
   2504	    114	    136	   2754	    ac2	ntp.o.after

md5:
   41f3009debc9b397d7394dd77d912f0a  ntp.o.before.asm
   41f3009debc9b397d7394dd77d912f0a  ntp.o.after.asm
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

There's an ugly u64 typecase in the MAX_TICKADJ_SCALED definition,
this can be eliminated by making the MAX_TICKADJ constant's type
64-bit (signed).

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2504	    114	    136	   2754	    ac2	ntp.o.before
   2504	    114	    136	   2754	    ac2	ntp.o.after

md5:
   41f3009debc9b397d7394dd77d912f0a  ntp.o.before.asm
   41f3009debc9b397d7394dd77d912f0a  ntp.o.after.asm
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

Instead of a hierarchy of conditions, transform them to clean
gradual conditions and return's.

This makes the flow easier to read and makes the purpose of
the function easier to understand.

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2552	    170	    168	   2890	    b4a	ntp.o.before
   2552	    170	    168	   2890	    b4a	ntp.o.after

md5:
   eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.before.asm
   eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.after.asm
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, no functionality changed

Make this file a bit more readable by applying a consistent coding style.

No code changed:

kernel/time/ntp.o:

   text	   data	    bss	    dec	    hex	filename
   2552	    170	    168	   2890	    b4a	ntp.o.before
   2552	    170	    168	   2890	    b4a	ntp.o.after

md5:
   eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.before.asm
   eae1275df0b7d6290c13f6f6f8f05c8c  ntp.o.after.asm
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Since the GENERIC_TIME changes landed, the adjtimex behavior changed
for struct timex.tick and .freq changed. When the tick or freq value
is set, we adjust the tick_length_base in ntp_update_frequency().
However, this new value doesn't get applied to tick_length until the
next second (via second_overflow).

This means some applications that do quick time tweaking do not see the
requested change made as quickly as expected.

I've run a few tests with this change, and ntpd still functions fine.
Signed-off-by: NJohn Stultz <johnstul@us.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Mapping from a struct timecounter to a time returned by functions like
ktime_get_real() is implemented. This is sufficient to use this code
in a network device driver which wants to support hardware time
stamping and transformation of hardware time stamps to system time.

The interface could have been made more versatile by not depending on
a time counter, but this wasn't done to avoid writing glue code
elsewhere.

The method implemented here is the one used and analyzed under the name
"assisted PTP" in the LCI PTP paper:
http://www.linuxclustersinstitute.org/conferences/archive/2008/PDF/Ohly_92221.pdfAcked-by: NJohn Stultz <johnstul@us.ibm.com>
Signed-off-by: NPatrick Ohly <patrick.ohly@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

So far struct clocksource acted as the interface between time/timekeeping.c
and hardware. This patch generalizes the concept so that a similar
interface can also be used in other contexts. For that it introduces
new structures and related functions *without* touching the existing
struct clocksource.

The reasons for adding these new structures to clocksource.[ch] are
* the APIs are clearly related
* struct clocksource could be cleaned up to use the new structs
* avoids proliferation of files with similar names (timesource.h?
  timecounter.h?)

As outlined in the discussion with John Stultz, this patch adds
* struct cyclecounter: stateless API to hardware which counts clock cycles
* struct timecounter: stateful utility code built on a cyclecounter which
  provides a nanosecond counter
* only the function to read the nanosecond counter; deltas are used internally
  and not exposed to users of timecounter

The code does no locking of the shared state. It must be called at least
as often as the cycle counter wraps around to detect these wrap arounds.
Both is the responsibility of the timecounter user.
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Signed-off-by: NPatrick Ohly <patrick.ohly@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Impact: fix CPU hotplug hang on Power6 testbox

On architectures that support offlining all cpus (at least powerpc/pseries),
hot-unpluging the tick_do_timer_cpu can result in a system hang.

This comes from the fact that if the cpu going down happens to be the
cpu doing the tick, then as the tick_do_timer_cpu handover happens after the
cpu is dead (via the CPU_DEAD notification), we're left without ticks,
jiffies are frozen and any task relying on timers (msleep, ...) is stuck.
That's particularly the case for the cpu looping in __cpu_die() waiting
for the dying cpu to be dead.

This patch addresses this by having the tick_do_timer_cpu handover happen
earlier during the CPU_DYING notification. For this, a new clockevent
notification type is introduced (CLOCK_EVT_NOTIFY_CPU_DYING) which is triggered
in hrtimer_cpu_notify().
Signed-off-by: NSebastien Dugue <sebastien.dugue@bull.net>
Cc: <stable@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Allow the set_mode() clockevent callback to decide and fill in delta
details such as shift, mult, max_delta_ns and min_delta_ns.

With this change the clockevent can be registered without delta details
which allows us to keep the parent clock disabled until the clockevent
gets setup using set_mode().

Letting set_mode() fill in or update delta details allows us to save
power by disabling the parent clock while the clockevent is unused.
This may however make the parent clock rate change, so next time the
clockevent gets enabled we need let set_mode() to update the detla
details accordingly. Doing it at registration time is not enough.

Furthermore, the delta details seem unused in the case of periodic-only
clockevent drivers, so this change also allows registration of such
drivers without the delta details filled in.
Signed-off-by: NMagnus Damm <damm@igel.co.jp>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Impact: cleanup, reduce kernel size a bit, avoid sparse warning

Fixes sparse warning:

 kernel/time/tick-sched.c:137:6: warning: symbol 'tick_nohz_update_jiffies' was not declared. Should it be static?
Signed-off-by: NJaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

- (better, more, bigger ...) then -> (...) than
Signed-off-by: NFrederik Schwarzer <schwarzerf@gmail.com>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

Impact: cleanup

Simple replacement, now the _nr is redundant.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NMike Travis <travis@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>

Impact: Use new APIs

Convert kernel/time functions to use struct cpumask *.

Note the ugly bitmap declarations in tick-broadcast.c.  These should
be cpumask_var_t, but there was no obvious initialization function to
put the alloc_cpumask_var() calls in.  This was safe.

(Eventually 'struct cpumask' will be undefined for CONFIG_CPUMASK_OFFSTACK,
so we use a bitmap here to show we really mean it).
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NMike Travis <travis@sgi.com>

The cpu time spent by the idle process actually doing something is
currently accounted as idle time. This is plain wrong, the architectures
that support VIRT_CPU_ACCOUNTING=y can do better: distinguish between the
time spent doing nothing and the time spent by idle doing work. The first
is accounted with account_idle_time and the second with account_system_time.
The architectures that use the account_xxx_time interface directly and not
the account_xxx_ticks interface now need to do the check for the idle
process in their arch code. In particular to improve the system vs true
idle time accounting the arch code needs to measure the true idle time
instead of just testing for the idle process.
To improve the tick based accounting as well we would need an architecture
primitive that can tell us if the pt_regs of the interrupted context
points to the magic instruction that halts the cpu.

In addition idle time is no more added to the stime of the idle process.
This field now contains the system time of the idle process as it should
be. On systems without VIRT_CPU_ACCOUNTING this will always be zero as
every tick that occurs while idle is running will be accounted as idle
time.

This patch contains the necessary common code changes to be able to
distinguish idle system time and true idle time. The architectures with
support for VIRT_CPU_ACCOUNTING need some changes to exploit this.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

The utimescaled / stimescaled fields in the task structure and the
global cpustat should be set on all architectures. On s390 the calls
to account_user_time_scaled and account_system_time_scaled never have
been added. In addition system time that is accounted as guest time
to the user time of a process is accounted to the scaled system time
instead of the scaled user time.
To fix the bugs and to prevent future forgetfulness this patch merges
account_system_time_scaled into account_system_time and
account_user_time_scaled into account_user_time.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Michael Neuling <mikey@neuling.org>
Acked-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

Redo:

  5b7dba4f: sched_clock: prevent scd->clock from moving backwards

which had to be reverted due to s2ram hangs:

  ca7e716c: Revert "sched_clock: prevent scd->clock from moving backwards"

... this time with resume restoring GTOD later in the sequence
taken into account as well.

The "timekeeping_suspended" flag is not very nice but we cannot call into
GTOD before it has been properly resumed and the scheduler will run very
early in the resume sequence.

Cc: <stable@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix CPU hotplug hang on Power6 testbox

On architectures that support offlining all cpus (at least powerpc/pseries),
hot-unpluging the tick_do_timer_cpu can result in a system hang.

This comes from the fact that if the cpu going down happens to be the
cpu doing the tick, then as the tick_do_timer_cpu handover happens after the
cpu is dead (via the CPU_DEAD notification), we're left without ticks,
jiffies are frozen and any task relying on timers (msleep, ...) is stuck.
That's particularly the case for the cpu looping in __cpu_die() waiting
for the dying cpu to be dead.

This patch addresses this by having the tick_do_timer_cpu handover happen
earlier during the CPU_DYING notification. For this, a new clockevent
notification type is introduced (CLOCK_EVT_NOTIFY_CPU_DYING) which is triggered
in hrtimer_cpu_notify().
Signed-off-by: NSebastien Dugue <sebastien.dugue@bull.net>
Cc: <stable@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: change calling convention of existing clock_event APIs

struct clock_event_timer's cpumask field gets changed to take pointer,
as does the ->broadcast function.

Another single-patch change.  For safety, we BUG_ON() in
clockevents_register_device() if it's not set.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Cc: Ingo Molnar <mingo@elte.hu>

Impact: change existing irq_chip API

Not much point with gentle transition here: the struct irq_chip's
setaffinity method signature needs to change.

Fortunately, not widely used code, but hits a few architectures.

Note: In irq_select_affinity() I save a temporary in by mangling
irq_desc[irq].affinity directly.  Ingo, does this break anything?

(Folded in fix from KOSAKI Motohiro)
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NMike Travis <travis@sgi.com>
Reviewed-by: NGrant Grundler <grundler@parisc-linux.org>
Acked-by: NIngo Molnar <mingo@redhat.com>
Cc: ralf@linux-mips.org
Cc: grundler@parisc-linux.org
Cc: jeremy@xensource.com
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>

In my device I get many interrupts from a high speed USB device in a very
short period of time.  The system spends a lot of time reprogramming the
hardware timer which is in a slower timing domain as compared to the CPU. 
This results in the CPU spending a huge amount of time waiting for the
timer posting to be done.  All of this reprogramming is useless as the
wake up time has not changed.

As measured using ETM trace this drops my reprogramming penalty from
almost 60% CPU load down to 15% during high interrupt rate.  I can send
traces to show this.

Suppress setting of duplicate timer event when timer already stopped. 
Timer programming can be very costly and can result in long cpu stall/wait
times.

[akpm@linux-foundation.org: coding-style fixes]
[tglx@linutronix.de: move the check to the right place and avoid raising
		     the softirq for nothing]
Signed-off-by: NRichard Woodruff <r-woodruff2@ti.com>
Cc: johnstul@us.ibm.com
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Impact: remove false positive warning

After a cpu was taken down during cpu hotplug (read: disabled for interrupts)
it still might have pending softirqs. However take_cpu_down makes sure
that the idle task will run next instead of ksoftirqd on the taken down cpu.
The idle task will call tick_nohz_stop_sched_tick which might warn about
pending softirqs just before the cpu kills itself completely.

However the pending softirqs on the dead cpu aren't a problem because they
will be moved to an online cpu during CPU_DEAD handling.

So make sure we warn only for online cpus.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix time warp bug

Alex Shi, along with Yanmin Zhang have been noticing occasional time
inconsistencies recently. Through their great diagnosis, they found that
the xtime_nsec value used in update_wall_time was occasionally going
negative. After looking through the code for awhile, I realized we have
the possibility for an underflow when three conditions are met in
update_wall_time():

  1) We have accumulated a second's worth of nanoseconds, so we
     incremented xtime.tv_sec and appropriately decrement xtime_nsec.
     (This doesn't cause xtime_nsec to go negative, but it can cause it
      to be small).

  2) The remaining offset value is large, but just slightly less then
     cycle_interval.

  3) clocksource_adjust() is speeding up the clock, causing a
     corrective amount (compensating for the increase in the multiplier
     being multiplied against the unaccumulated offset value) to be
     subtracted from xtime_nsec.

This can cause xtime_nsec to underflow.

Unfortunately, since we notify the NTP subsystem via second_overflow()
whenever we accumulate a full second, and this effects the error
accumulation that has already occured, we cannot simply revert the
accumulated second from xtime nor move the second accumulation to after
the clocksource_adjust call without a change in behavior.

This leaves us with (at least) two options:

1) Simply return from clocksource_adjust() without making a change if we
   notice the adjustment would cause xtime_nsec to go negative.

This would work, but I'm concerned that if a large adjustment was needed
(due to the error being large), it may be possible to get stuck with an
ever increasing error that becomes too large to correct (since it may
always force xtime_nsec negative). This may just be paranoia on my part.

2) Catch xtime_nsec if it is negative, then add back the amount its
   negative to both xtime_nsec and the error.

This second method is consistent with how we've handled earlier rounding
issues, and also has the benefit that the error being added is always in
the oposite direction also always equal or smaller then the correction
being applied. So the risk of a corner case where things get out of
control is lessened.

This patch fixes bug 11970, as tested by Yanmin Zhang
http://bugzilla.kernel.org/show_bug.cgi?id=11970

Reported-by: alex.shi@intel.com
Signed-off-by: NJohn Stultz <johnstul@us.ibm.com>
Acked-by: N"Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Tested-by: N"Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup, move all hrtimer processing into hardirq context

This is an attempt at removing some of the hrtimer complexity by
reducing the number of callback modes to 1.

This means that all hrtimer callback functions will be ran from HARD-irq
context.

I went through all the 30 odd hrtimer callback functions in the kernel
and saw only one that I'm not quite sure of, which is the one in
net/can/bcm.c - hence I'm CC-ing the folks responsible for that code.

Furthermore, the hrtimer core now calls callbacks directly with IRQs
disabled in case you try to enqueue an expired timer. If this timer is a
periodic timer (which should use hrtimer_forward() to advance its time)
then it might be possible to end up in an inf. recursive loop due to the
fact that hrtimer_forward() doesn't round up to the next timer
granularity, and therefore keeps on calling the callback - obviously
this needs a fix.

Aside from that, this seems to compile and actually boot on my dual core
test box - although I'm sure there are some bugs in, me not hitting any
makes me certain :-)
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: (future) size reduction for large NR_CPUS.

Dynamically allocating cpumasks (when CONFIG_CPUMASK_OFFSTACK) saves
space for small nr_cpu_ids but big CONFIG_NR_CPUS.  cpumask_var_t
is just a struct cpumask for !CONFIG_CPUMASK_OFFSTACK.
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: nohz powersavings and wakeup regression

commit fb02fbc1 (NOHZ: restart tick
device from irq_enter()) causes a serious wakeup regression.

While the patch is correct it does not take into account that spurious
wakeups happen on x86. A fix for this issue is available, but we just
revert to the .27 behaviour and let long running softirqs screw
themself.

Disable it for now.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

commit fb02fbc1 (NOHZ: restart tick
device from irq_enter())

solves the problem of stale jiffies when long running softirqs happen
in a long idle sleep period, but it has a major thinko in it:

When the interrupt which came in _is_ the timer interrupt which should
expire ts->sched_timer then we cancel and rearm the timer _before_ it
gets expired in hrtimer_interrupt() to the next period. That means the
call back function is not called. This game can go on for ever :(

Prevent this by making sure to only rearm the timer when the expiry
time is more than one tick_period away. Otherwise keep it running as
it is either already expired or will expiry at the right point to
update jiffies.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Tested-by: NVenkatesch Pallipadi <venkatesh.pallipadi@intel.com>