CLOCK_MONOTONIC stops while the system is in suspend. This is because
to applications system suspend is invisible. However, there is a
growing set of applications that are wanting to be suspend-aware,
but do not want to deal with the complications of CLOCK_REALTIME
(which might jump around if settimeofday is called).

For these applications, I propose a new clockid: CLOCK_BOOTTIME.
CLOCK_BOOTTIME is idential to CLOCK_MONOTONIC, except it also
includes any time spent in suspend.

This patch add hrtimer base for CLOCK_BOOTTIME, using
get_monotonic_boottime/ktime_get_boottime, to allow
in kernel users to set timers against.

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>

Extend get_xtime_and_monotonic_offset to
get_xtime_and_monotonic_and_sleep_offset().

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>

This adds new functions that return the monotonic time since boot
(in other words, CLOCK_MONOTONIC + suspend time).

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>

The hrtimer code is written mainly with CLOCK_REALTIME and CLOCK_MONOTONIC
in mind. These are clockids 0 and 1 resepctively. However, if we are
to introduce any new hrtimer bases, using new clockids, we have to skip
the cputimers (clockids 2,3) as well as other clockids that may not impelement
timers.

This patch adds a little bit of indirection between the clockid and
the base, so that we can extend the base by one when we add
a new clockid at number 7 or so.

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>

The ADJ_SETOFFSET code redundantly checks the range of the nanoseconds
field of the time value. This field is checked again in the subsequent
call to timekeeping_inject_offset(). Also, as is, the check will not
detect whether the number of microseconds is out of range.

Let timekeeping_inject_offset() do the error checking.
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Cc: johnstul@us.ibm.com
LKML-Reference: <20110218090724.GA2924@riccoc20.at.omicron.at>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Only one CPU gets the timer interrupt so mn10300_last_tsc does not
need to be protected by xtime lock. Remove xtime lovking and use
xtime_update() which does the locking itself.
Signed-off-by: NTorben Hohn <torbenh@gmx.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com>
LKML-Reference: <20110127150011.23248.62040.stgit@localhost>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

This patch adds support for adding and removing posix clocks. The
clock lifetime cycle is patterned after usb devices. Each clock is
represented by a standard character device. In addition, the driver
may optionally implement custom character device operations.

The posix clock and timer system calls listed below now work with
dynamic posix clocks, as well as the traditional static clocks.
The following system calls are affected:

   - clock_adjtime (brand new syscall)
   - clock_gettime
   - clock_getres
   - clock_settime
   - timer_create
   - timer_delete
   - timer_gettime
   - timer_settime

[ tglx: Adapted to the posix-timer cleanup. Moved clock_posix_dynamic
  	to posix-clock.c and made all referenced functions static ]
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134420.164172635@linutronix.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Rename register_posix_clock() to posix_timers_register_clock(). That's
what the function really does. As a side effect this cleans up the
posix_clock namespace for the upcoming dynamic posix_clock
infrastructure.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
Cc: John Stultz <johnstul@us.ibm.com>
LKML-Reference: <alpine.LFD.2.00.1102021222240.31804@localhost6.localdomain6>

Extend the negative clockids which are currently used by posix cpu
timers to encode the PID with a file descriptor based type which
encodes the fd in the upper bits.

Originally-from: Richard Cochran <richard.cochran@omicron.at>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134420.062860200@linutronix.de>

This patch adds the clock_adjtime system call to the x86 architecture.
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134419.968905083@linutronix.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

A new syscall is introduced that allows tuning of a POSIX clock. The
new call, clock_adjtime, takes two parameters, the clock ID and a
pointer to a struct timex. Any ADJTIMEX(2) operation may be requested
via this system call, but various POSIX clocks may or may not support
tuning.

[ tglx: Adapted to the posix-timer cleanup series. Avoid copy_to_user
  	in the error case ]
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134419.869804645@linutronix.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Split out the compat timex accessors into separate
functions. Preparatory patch for a new syscall.

[ tglx: Split that patch from Richards "posix-timers: Introduce a
  	syscall for clock tuning.". Keeps the changes strictly
  	separate ]

Originally-from: Richard Cochran <richardcochran@gmail.com>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
LKML-Reference: <20110201134419.772343089@linutronix.de>

This patch adds a new mode bit into the timex structure. When set, the bit
instructs the kernel to add the given time value to the current time.
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134320.688829863@linutronix.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

This adds a kernel-internal timekeeping interface to add or subtract
a fixed amount from CLOCK_REALTIME. This makes it so kernel users or
interfaces trying to do so do not have to read the time, then add an
offset and then call settimeofday(), which adds some extra error in
comparision to just simply adding the offset in the kernel timekeeping
core.
Signed-off-by: NJohn Stultz <john.stultz@linaro.org>
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.584311693@linutronix.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Pick the cleanup to the comment in posix-timers.c from Richards all in
one conversion patch.

Originally-from: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134419.487708516@linutronix.de>

All functions are accessed via clock_posix_cpu now. So make them static.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.389755466@linutronix.de>

All users gone. Remove the cruft.

Huge thanks to Richard Cochran who tackled that maze first.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.294620613@linutronix.de>

Set the common function for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks
and use the new decoding function.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.198999420@linutronix.de>

Set the common function for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks
and use the new decoding function.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.101243181@linutronix.de>

Set the common function for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks
and use the new decoding function.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134419.001863714@linutronix.de>

Setup timer_create for CLOCK_MONOTONIC and CLOCK_REALTIME kclocks and
remove the no_timer_create() implementation.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.903604289@linutronix.de>

The res member of kclock is only used by mmtimer.c, but even there it
contains redundant information. Remove the field and fixup mmtimer.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.808714587@linutronix.de>

Use the new kclock decoding. Fixup the fallout in mmtimer.c
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.709802797@linutronix.de>

Richard said: "I would think that we can require k_clocks to provide
the read function. This could be checked and enforced in
register_posix_clock()."

Add checks for clock_getres and clock_get in the register function.
Suggested-by: NRichard Cochran <richardcochran@gmail.com>
Cc: John Stultz <johnstul@us.ibm.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Use the new kclock decoding mechanism and rename the misnomed
common_clock_get() to posix_clock_realtime_get().
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.611097203@linutronix.de>

Use the new kclock decoding function in clock_settime and cleanup all
kclocks which use the default functions. Rename the misnomed
common_clock_set() to posix_clock_realtime_set().
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.518851246@linutronix.de>

CLOCK_THREAD_CPUTIME_ID implements stub functions for nanosleep and
nanosleep_restart, which return -EINVAL. That return value is
wrong. The correct return value is -ENOTSUP.

Remove the stubs and let the new dispatch code return the correct
error code.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.422446502@linutronix.de>

posix timers were the last users of the legacy arg0-3 members of
restart_block. Remove the cruft.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.326209775@linutronix.de>

posix timers still use the legacy arg0-arg3 members of
restart_block. Use restart_block.nanosleep instead
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.232288779@linutronix.de>

Use the new kclock decoding function in clock_nanosleep_restart.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.131263211@linutronix.de>

Use the new kclock decoding function in clock_nanosleep and cleanup all
kclocks which use the default functions.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134418.034175556@linutronix.de>

New function to find the kclock for a given clockid.

Returns a pointer to clock_posix_cpu if clockid < 0. If clockid >=
MAXCLOCK or if the clock_getres pointer is not set it returns
NULL. For valid clocks it returns a pointer to the matching
posix_clock.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <johnstul@us.ibm.com>
Acked-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.938447839@linutronix.de>

The CLOCK_DISPATCH() macro is a horrible magic. We call common
functions if a function pointer is not set. That's just backwards.

To support dynamic file decriptor based clocks we need to cleanup that
dispatch logic.

Create a k_clock struct clock_posix_cpu which has all the
posix-cpu-timer functions filled in. After the cleanup the functions
can be made static.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.841974553@linutronix.de>

Cosmetic. No functional change
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.745627057@linutronix.de>

Define the conditional nanosleep not supported error value outside of
do_posix_clock_nonanosleep(). Preparatory patch for further cleanups. 
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
Tested-by: NRichard Cochran <richard.cochran@omicron.at>
LKML-Reference: <20110201134417.643486574@linutronix.de>

Both settimeofday() and clock_settime() promise with a 'const'
attribute not to alter the arguments passed in. This patch adds the
missing 'const' attribute into the various kernel functions
implementing these calls.
Signed-off-by: NRichard Cochran <richard.cochran@omicron.at>
Acked-by: NJohn Stultz <johnstul@us.ibm.com>
LKML-Reference: <20110201134417.545698637@linutronix.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

The xtime/dotimer cleanup broke architectures which do not implement
clockevents. Time to send out another __do_IRQ threat.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reported-by: NIngo Molnar <mingo@elte.hu>
Cc: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
LKML-Reference: <20110127145905.23248.30458.stgit@localhost>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

All callers of do_timer() are converted to xtime_update(). The only
users of xtime_lock are in kernel/time/. Make both local to
kernel/time/ and remove them from the global header files.

[ tglx: Reuse tick-internal.h instead of creating another local header
  	file. Massaged changelog ]
Signed-off-by: NTorben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

xtime_update() takes the xtime_lock itself.

set_linux_timer() does not need to be protected by xtime_lock.

[ tglx: This code is broken on SMP anyway. ]
Signed-off-by: NTorben Hohn <torbenh@gmx.de>
Cc: Chris Zankel <chris@zankel.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: hch@infradead.org
Cc: yong.zhang0@gmail.com
LKML-Reference: <20110127150027.23248.61798.stgit@localhost>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

xtime_update() takes the xtime_lock itself.

pcic_clear_clock_irq() and clear_clock_irq do not need
to be protected by xtime_lock.
Signed-off-by: NTorben Hohn <torbenh@gmx.de>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: hch@infradead.org
Cc: yong.zhang0@gmail.com
LKML-Reference: <20110127150022.23248.80369.stgit@localhost>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>