[PATCH 0/2] Add CLOCK_BOOTTIME functionality

[PATCH 0/2] Add CLOCK_BOOTTIME functionality

[John Stultz]

This patchset extends the hrtimers code to handle additional
clockids and then introduces CLOCK_BOOTTIME which is identical
to CLOCK_MONOTONIC, except it also includes any time spent in
suspend (currently as measured by read_persistent_clock()).

CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>

John Stultz (2):
  [RFC] hrtimers: extend hrtimer base code to handle more then 2
    clockids
  [RFC] hrtimers: Add CLOCK_BOOTTIME clockid, hrtimerbase and posix
    interface

 include/linux/hrtimer.h   |    8 ++++-
 include/linux/time.h      |    4 ++
 kernel/hrtimer.c          |   71 ++++++++++++++++++++++++++++++++--------
 kernel/posix-timers.c     |   16 ++++++++-
 kernel/time/timekeeping.c |   79 ++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 160 insertions(+), 18 deletions(-)

-- 
1.7.3.2.146.gca209

[PATCH 1/2] hrtimers: extend hrtimer base code to handle more then 2 clockids

[John Stultz]

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: John Stultz <john.stultz@linaro.org>
---
 include/linux/hrtimer.h |    6 ++++-
 kernel/hrtimer.c        |   55 +++++++++++++++++++++++++++++++++++-----------
 2 files changed, 47 insertions(+), 14 deletions(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index f376ddc..20b8e66 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -148,7 +148,11 @@ struct hrtimer_clock_base {
 #endif
 };
 
-#define HRTIMER_MAX_CLOCK_BASES 2
+enum  hrtimer_base_type {
+	HRTIMER_BASE_REALTIME,
+	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_MAX_CLOCK_BASES,
+};
 
 /*
  * struct hrtimer_cpu_base - the per cpu clock bases
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 0c8d7c0..ce6dd95 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -53,11 +53,10 @@
 /*
  * The timer bases:
  *
- * Note: If we want to add new timer bases, we have to skip the two
- * clock ids captured by the cpu-timers. We do this by holding empty
- * entries rather than doing math adjustment of the clock ids.
- * This ensures that we capture erroneous accesses to these clock ids
- * rather than moving them into the range of valid clock id's.
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base()
+ * is used to convert from clockid to the proper hrtimer_base_type.
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
@@ -77,6 +76,24 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	}
 };
 
+static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+	int ret = hrtimer_clock_to_base_table[clock_id];
+
+	if(ret == -1) {
+		WARN_ON(1);
+		/* We just hit an invalid clock base,
+		 * but returning -1 isn't safe, so
+		 * return the _REALTIME base
+		 */
+		return HRTIMER_BASE_REALTIME; 
+	}
+	return ret;
+}
+
+
 /*
  * Get the coarse grained time at the softirq based on xtime and
  * wall_to_monotonic.
@@ -95,8 +112,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 
 	xtim = timespec_to_ktime(xts);
 	tomono = timespec_to_ktime(tom);
-	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
-	base->clock_base[CLOCK_MONOTONIC].softirq_time =
+	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time =
 		ktime_add(xtim, tomono);
 }
 
@@ -184,10 +201,11 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 	struct hrtimer_cpu_base *new_cpu_base;
 	int this_cpu = smp_processor_id();
 	int cpu = hrtimer_get_target(this_cpu, pinned);
+	int basenum = hrtimer_clockid_to_base(base->index);
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
-	new_base = &new_cpu_base->clock_base[base->index];
+	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
 		/*
@@ -627,7 +645,7 @@ static void retrigger_next_event(void *arg)
 
 	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[CLOCK_REALTIME].offset =
+	base->clock_base[HRTIMER_BASE_REALTIME].offset =
 		timespec_to_ktime(realtime_offset);
 
 	hrtimer_force_reprogram(base, 0);
@@ -725,8 +743,8 @@ static int hrtimer_switch_to_hres(void)
 		return 0;
 	}
 	base->hres_active = 1;
-	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
-	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
 
@@ -1121,6 +1139,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base;
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
@@ -1129,7 +1148,8 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
 
-	timer->base = &cpu_base->clock_base[clock_id];
+	base = hrtimer_clockid_to_base(clock_id);
+	timer->base = &cpu_base->clock_base[base];
 	hrtimer_init_timer_hres(timer);
 	timerqueue_init(&timer->node);
 
@@ -1165,9 +1185,10 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base = hrtimer_clockid_to_base(which_clock);
 
 	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
+	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
 }
@@ -1714,6 +1735,14 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
 
 void __init hrtimers_init(void)
 {
+	int i;
+
+	/* Init the clockid -> base mapping */
+	for (i = 0; i < MAX_CLOCKS; i++)
+		hrtimer_clock_to_base_table[i] = -1;
+	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
+	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
+
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
-- 
1.7.3.2.146.gca209

Re: [PATCH 1/2] hrtimers: extend hrtimer base code to handle more then 2 clockids

[Thomas Gleixner]

On Mon, 31 Jan 2011, John Stultz wrote:
> @@ -53,11 +53,10 @@
>  /*
>   * The timer bases:
>   *
> - * Note: If we want to add new timer bases, we have to skip the two
> - * clock ids captured by the cpu-timers. We do this by holding empty
> - * entries rather than doing math adjustment of the clock ids.
> - * This ensures that we capture erroneous accesses to these clock ids
> - * rather than moving them into the range of valid clock id's.
> + * There are more clockids then hrtimer bases. Thus, we index

s/then/than/

> + * into the timer bases by the hrtimer_base_type enum. When trying
> + * to reach a base using a clockid, hrtimer_clockid_to_base()
> + * is used to convert from clockid to the proper hrtimer_base_type.
>   */
>  DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
>  {
> @@ -77,6 +76,24 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
>  	}
>  };
>  
> +static int hrtimer_clock_to_base_table[MAX_CLOCKS];
> +
> +static inline int hrtimer_clockid_to_base(clockid_t clock_id)
> +{
> +	int ret = hrtimer_clock_to_base_table[clock_id];
> +
> +	if(ret == -1) {
> +		WARN_ON(1);
> +		/* We just hit an invalid clock base,
> +		 * but returning -1 isn't safe, so
> +		 * return the _REALTIME base
> +		 */

  How can this happen ?

> +		return HRTIMER_BASE_REALTIME; 
> +	}
> +	return ret;
> +}

Thanks,

	tglx

Re: [PATCH 1/2] hrtimers: extend hrtimer base code to handle more then 2 clockids

[John Stultz]

On Tue, 2011-02-01 at 15:10 +0100, Thomas Gleixner wrote:
> On Mon, 31 Jan 2011, John Stultz wrote:
> > @@ -53,11 +53,10 @@
> >  /*
> >   * The timer bases:
> >   *
> > - * Note: If we want to add new timer bases, we have to skip the two
> > - * clock ids captured by the cpu-timers. We do this by holding empty
> > - * entries rather than doing math adjustment of the clock ids.
> > - * This ensures that we capture erroneous accesses to these clock ids
> > - * rather than moving them into the range of valid clock id's.
> > + * There are more clockids then hrtimer bases. Thus, we index
> 
> s/then/than/

Thenks! ;)

> > + * into the timer bases by the hrtimer_base_type enum. When trying
> > + * to reach a base using a clockid, hrtimer_clockid_to_base()
> > + * is used to convert from clockid to the proper hrtimer_base_type.
> >   */
> >  DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
> >  {
> > @@ -77,6 +76,24 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
> >  	}
> >  };
> >  
> > +static int hrtimer_clock_to_base_table[MAX_CLOCKS];
> > +
> > +static inline int hrtimer_clockid_to_base(clockid_t clock_id)
> > +{
> > +	int ret = hrtimer_clock_to_base_table[clock_id];
> > +
> > +	if(ret == -1) {
> > +		WARN_ON(1);
> > +		/* We just hit an invalid clock base,
> > +		 * but returning -1 isn't safe, so
> > +		 * return the _REALTIME base
> > +		 */
> 
>   How can this happen ?

It can't right now. I'm just worried someone will try to put a clockid
that doesn't have an hrtimer base into that function sometime in the
future. We can wrap it in a debug config maybe?

thanks
-john

Re: [PATCH 1/2] hrtimers: extend hrtimer base code to handle more then 2 clockids

[Thomas Gleixner]

On Tue, 1 Feb 2011, John Stultz wrote:
> On Tue, 2011-02-01 at 15:10 +0100, Thomas Gleixner wrote:
> > On Mon, 31 Jan 2011, John Stultz wrote:
> > > +static inline int hrtimer_clockid_to_base(clockid_t clock_id)
> > > +{
> > > +	int ret = hrtimer_clock_to_base_table[clock_id];
> > > +
> > > +	if(ret == -1) {
> > > +		WARN_ON(1);
> > > +		/* We just hit an invalid clock base,
> > > +		 * but returning -1 isn't safe, so
> > > +		 * return the _REALTIME base
> > > +		 */
> > 
> >   How can this happen ?
> 
> It can't right now. I'm just worried someone will try to put a clockid
> that doesn't have an hrtimer base into that function sometime in the
> future. We can wrap it in a debug config maybe?

Hmm. That would have exploded the current code as well. So I won't
worry too much about.

Thanks,

	tglx

[PATCH 2/2] hrtimers: Add CLOCK_BOOTTIME clockid, hrtimerbase and posix interface

[John Stultz]

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 complicatoins 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 adds the new CLOCK_BOOTTIME clockid, as well as the
infrastructure needed to support hrtimers against it, and the
wiring to expose it out via the posix interface.

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: John Stultz <john.stultz@linaro.org>
---
 include/linux/hrtimer.h   |    2 +
 include/linux/time.h      |    4 ++
 kernel/hrtimer.c          |   16 ++++++++-
 kernel/posix-timers.c     |   16 ++++++++-
 kernel/time/timekeeping.c |   79 ++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 113 insertions(+), 4 deletions(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 20b8e66..6bc1804 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -151,6 +151,7 @@ struct hrtimer_clock_base {
 enum  hrtimer_base_type {
 	HRTIMER_BASE_REALTIME,
 	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_BASE_BOOTTIME,
 	HRTIMER_MAX_CLOCK_BASES,
 };
 
@@ -312,6 +313,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_real(void);
+extern ktime_t ktime_get_boottime(void);
 
 
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
diff --git a/include/linux/time.h b/include/linux/time.h
index 1e6d3b5..9c520f4 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -126,6 +126,8 @@ unsigned long get_seconds(void);
 struct timespec current_kernel_time(void);
 struct timespec __current_kernel_time(void); /* does not take xtime_lock */
 struct timespec __get_wall_to_monotonic(void); /* does not take xtime_lock */
+extern struct timespec __get_sleep_time(void); /* does not take xtime_lock */
+
 struct timespec get_monotonic_coarse(void);
 
 #define CURRENT_TIME		(current_kernel_time())
@@ -162,6 +164,7 @@ extern void getnstime_raw_and_real(struct timespec *ts_raw,
 		struct timespec *ts_real);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
+extern void get_monotonic_boottime(struct timespec *ts);
 
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 extern int timekeeping_valid_for_hres(void);
@@ -292,6 +295,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC_RAW		4
 #define CLOCK_REALTIME_COARSE		5
 #define CLOCK_MONOTONIC_COARSE		6
+#define CLOCK_BOOTTIME			7
 
 /*
  * The IDs of various hardware clocks:
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ce6dd95..628c734 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -73,6 +73,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.get_time = &ktime_get,
 			.resolution = KTIME_LOW_RES,
 		},
+		{
+			.index = CLOCK_BOOTTIME,
+			.get_time = &ktime_get_boottime,
+			.resolution = KTIME_LOW_RES,
+		},
 	}
 };
 
@@ -100,21 +105,26 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id)
  */
 static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 {
-	ktime_t xtim, tomono;
-	struct timespec xts, tom;
+	ktime_t xtim, tomono, sleep;
+	struct timespec xts, tom, slp;
 	unsigned long seq;
 
 	do {
 		seq = read_seqbegin(&xtime_lock);
 		xts = __current_kernel_time();
 		tom = __get_wall_to_monotonic();
+		slp = __get_sleep_time();
 	} while (read_seqretry(&xtime_lock, seq));
 
 	xtim = timespec_to_ktime(xts);
 	tomono = timespec_to_ktime(tom);
+	sleep = timespec_to_ktime(slp);
 	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time =
 		ktime_add(xtim, tomono);
+	base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time =
+		ktime_add(base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time,
+				sleep);
 }
 
 /*
@@ -745,6 +755,7 @@ static int hrtimer_switch_to_hres(void)
 	base->hres_active = 1;
 	base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_BOOTTIME].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
 
@@ -1742,6 +1753,7 @@ void __init hrtimers_init(void)
 		hrtimer_clock_to_base_table[i] = -1;
 	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
 	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
+	hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
 
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 93bd2eb..389d5d5 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -240,7 +240,7 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 }
 
 /*
- * Get monotonic time for posix timers
+ * Get monotonic-raw time for posix timers
  */
 static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
 {
@@ -267,6 +267,14 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp
 	*tp = ktime_to_timespec(KTIME_LOW_RES);
 	return 0;
 }
+
+static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+{
+	get_monotonic_boottime(tp);
+	return 0;
+}
+
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
@@ -301,12 +309,18 @@ static __init int init_posix_timers(void)
 		.timer_create = no_timer_create,
 		.nsleep = no_nsleep,
 	};
+	struct k_clock clock_boottime = {
+		.clock_getres = hrtimer_get_res,
+		.clock_get = posix_get_boottime,
+		.clock_set = do_posix_clock_nosettime,
+	};
 
 	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
 	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
 	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
 	register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
 	register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+	register_posix_clock(CLOCK_BOOTTIME, &clock_boottime);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d27c756..d063aed 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -871,7 +871,7 @@ void update_wall_time(void)
  * getboottime - Return the real time of system boot.
  * @ts:		pointer to the timespec to be set
  *
- * Returns the time of day in a timespec.
+ * Returns the wall-time of boot in a timespec.
  *
  * This is based on the wall_to_monotonic offset and the total suspend
  * time. Calls to settimeofday will affect the value returned (which
@@ -889,6 +889,83 @@ void getboottime(struct timespec *ts)
 }
 EXPORT_SYMBOL_GPL(getboottime);
 
+
+/**
+ * get_monotonic_boottime - Returns monotonic time since boot
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the monotonic time since boot in a timespec.
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
+ * includes the time spent in suspend.
+ */
+void get_monotonic_boottime(struct timespec *ts)
+{
+	struct timespec tomono, sleep;
+	unsigned int seq;
+	s64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		*ts = xtime;
+		tomono = wall_to_monotonic;
+		sleep = total_sleep_time;
+		nsecs = timekeeping_get_ns();
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
+			ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
+}
+EXPORT_SYMBOL_GPL(get_monotonic_boottime);
+
+/**
+ * ktime_get_boottime - Returns monotonic time since boot in a ktime
+ *
+ * Returns the monotonic time since boot in a ktime
+ *
+ * This is similar to CLOCK_MONTONIC/ktime_get, but also
+ * includes the time spent in suspend.
+ */
+ktime_t ktime_get_boottime(void)
+{
+	unsigned int seq;
+	s64 secs, nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		secs = xtime.tv_sec;
+		secs += wall_to_monotonic.tv_sec;
+		secs += total_sleep_time.tv_sec;
+		nsecs = xtime.tv_nsec;
+		nsecs += wall_to_monotonic.tv_nsec;
+		nsecs += total_sleep_time.tv_nsec;
+		nsecs += timekeeping_get_ns();
+
+	} while (read_seqretry(&xtime_lock, seq));
+	/*
+	 * Use ktime_set/ktime_add_ns to create a proper ktime on
+	 * 32-bit architectures without CONFIG_KTIME_SCALAR.
+	 */
+	return ktime_add_ns(ktime_set(secs, 0), nsecs);
+}
+EXPORT_SYMBOL_GPL(ktime_get_boottime);
+
+/**
+ * __get_sleep_time - returns total_sleep_time
+ *
+ * Returns total time spent in suspend.
+ * Requires the xtime lock be held
+ */
+struct timespec __get_sleep_time(void)
+{
+	return total_sleep_time;
+}
+
 /**
  * monotonic_to_bootbased - Convert the monotonic time to boot based.
  * @ts:		pointer to the timespec to be converted
-- 
1.7.3.2.146.gca209

Re: [PATCH 2/2] hrtimers: Add CLOCK_BOOTTIME clockid, hrtimerbase and posix interface

[Thomas Gleixner]

On Mon, 31 Jan 2011, John Stultz wrote:

> 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 complicatoins 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 adds the new CLOCK_BOOTTIME clockid, as well as the
> infrastructure needed to support hrtimers against it, and the
> wiring to expose it out via the posix interface.

Can you please split that into parts:

    - Add the new functions
    - Wire up hrtimers, posix-timers

>  static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
>  {
> -	ktime_t xtim, tomono;
> -	struct timespec xts, tom;
> +	ktime_t xtim, tomono, sleep;
> +	struct timespec xts, tom, slp;
>  	unsigned long seq;
>  
>  	do {
>  		seq = read_seqbegin(&xtime_lock);
>  		xts = __current_kernel_time();
>  		tom = __get_wall_to_monotonic();
> +		slp = __get_sleep_time();
>  	} while (read_seqretry(&xtime_lock, seq));

Hmm, that conflicts with the xtime_lock cleanup in tip/timers/core.

>  /*
>   * Initialize everything, well, just everything in Posix clocks/timers ;)
>   */
> @@ -301,12 +309,18 @@ static __init int init_posix_timers(void)
>  		.timer_create = no_timer_create,
>  		.nsleep = no_nsleep,
>  	};
> +	struct k_clock clock_boottime = {
> +		.clock_getres = hrtimer_get_res,
> +		.clock_get = posix_get_boottime,
> +		.clock_set = do_posix_clock_nosettime,

That's going to conflict with the posix timer cleanup, but it's easy enough to fix.

Thanks,

	tglx

Re: [PATCH 2/2] hrtimers: Add CLOCK_BOOTTIME clockid, hrtimerbase and posix interface

[John Stultz]

On Tue, 2011-02-01 at 15:16 +0100, Thomas Gleixner wrote:
> On Mon, 31 Jan 2011, John Stultz wrote:
> 
> > 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 complicatoins 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 adds the new CLOCK_BOOTTIME clockid, as well as the
> > infrastructure needed to support hrtimers against it, and the
> > wiring to expose it out via the posix interface.
> 
> Can you please split that into parts:
> 
>     - Add the new functions
>     - Wire up hrtimers, posix-timers

Will do. And will rebase to tip/timers/core.

thanks
-john

[PATCH 0/2] [RFC] Introduce CLOCK_BOOTTIME

[John Stultz]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=UTF-8, Size: 1874 bytes --]

After some discussions with Jamie Lokier about some of the 
drawbacks of CLOCK_MONOTONIC not incrementing during suspend
(see http://www.spinics.net/lists/linux-fsdevel/msg40272.html),
I wanted to see if we couldn't provide a new clockid that would 
allow applications that wanted to be aware of time passing during
suspend without having to deal with the inconsistencies of 
CLOCK_REALTIME caused by calls to settimeofday.

So this patchset introduces CLOCK_BOOTTIME, which is identical
to CLOCK_MONOTONIC, but includes any time spent in suspend.

This is just my initial stab at this, so I'd appreciate any comments
or thougths on these patches.

Jamie: On platforms that don't implement read_persistent_clock,
your issue would still be present, but fixing that is on my list.
Other then that issue, does this seem to address your concern?

Thomas: Let me know if the hrtimer_base indirection is too 
gross. It just seemed silly to create 5 empty bases so we could
have an exact match between the clockids and the bases.

Arve: I believe CLOCK_BOOTTIME would be sufficient for what
Android is using as elapsedRealtime() or 
ANDROID_ALARM_ELAPSED_REALTIME. If not please let me know why.

thanks
-john


CC: Jamie Lokier <jamie@shareable.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Alexander Shishkin <virtuoso@slind.org>
CC: Arve Hjønnevåg <arve@android.com>


John Stultz (2):
  hrtimers: extend hrtimer base code to handle more then 2 clockids
  hrtimers: Add CLOCK_BOOTTIME clockid, hrtimerbase and posix interface

 include/linux/hrtimer.h   |   22 ++++++++++++-
 include/linux/time.h      |    4 ++
 kernel/hrtimer.c          |   44 ++++++++++++++++---------
 kernel/posix-timers.c     |   16 ++++++++-
 kernel/time/timekeeping.c |   79 ++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 146 insertions(+), 19 deletions(-)

-- 
1.7.3.2.146.gca209

[PATCH 1/2] hrtimers: extend hrtimer base code to handle more then 2 clockids

[John Stultz]

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.

Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/hrtimer.h |   18 +++++++++++++++++-
 kernel/hrtimer.c        |   30 ++++++++++++++++--------------
 2 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 330586f..e41b64b 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -149,7 +149,23 @@ struct hrtimer_clock_base {
 #endif
 };
 
-#define HRTIMER_MAX_CLOCK_BASES 2
+enum  hrtimer_base_type {
+	HRTIMER_BASE_REALTIME,
+	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_MAX_CLOCK_BASES,
+};
+
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+	switch(clock_id) {
+		case CLOCK_REALTIME:
+			return HRTIMER_BASE_REALTIME;
+		case CLOCK_MONOTONIC:
+			return HRTIMER_BASE_MONOTONIC;
+	}
+	WARN_ON(1); /* Unknown clock_id */
+	return 0;
+}
 
 /*
  * struct hrtimer_cpu_base - the per cpu clock bases
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 7a7a206..a6642c7 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -53,11 +53,10 @@
 /*
  * The timer bases:
  *
- * Note: If we want to add new timer bases, we have to skip the two
- * clock ids captured by the cpu-timers. We do this by holding empty
- * entries rather than doing math adjustment of the clock ids.
- * This ensures that we capture erroneous accesses to these clock ids
- * rather than moving them into the range of valid clock id's.
+ * There are more clockids then hrtimer bases. Thus, we index
+ * into the timer bases by the hrtimer_base_type enum. When trying
+ * to reach a base using a clockid, hrtimer_clockid_to_base() 
+ * is used to convert from clockid to the proper hrtimer_base_type.
  */
 DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 {
@@ -95,8 +94,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 
 	xtim = timespec_to_ktime(xts);
 	tomono = timespec_to_ktime(tom);
-	base->clock_base[CLOCK_REALTIME].softirq_time = xtim;
-	base->clock_base[CLOCK_MONOTONIC].softirq_time =
+	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time =
 		ktime_add(xtim, tomono);
 }
 
@@ -184,10 +183,11 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base,
 	struct hrtimer_cpu_base *new_cpu_base;
 	int this_cpu = smp_processor_id();
 	int cpu = hrtimer_get_target(this_cpu, pinned);
+	int basenum = hrtimer_clockid_to_base(base->index);
 
 again:
 	new_cpu_base = &per_cpu(hrtimer_bases, cpu);
-	new_base = &new_cpu_base->clock_base[base->index];
+	new_base = &new_cpu_base->clock_base[basenum];
 
 	if (base != new_base) {
 		/*
@@ -627,7 +627,7 @@ static void retrigger_next_event(void *arg)
 
 	/* Adjust CLOCK_REALTIME offset */
 	raw_spin_lock(&base->lock);
-	base->clock_base[CLOCK_REALTIME].offset =
+	base->clock_base[HRTIMER_BASE_REALTIME].offset =
 		timespec_to_ktime(realtime_offset);
 
 	hrtimer_force_reprogram(base, 0);
@@ -725,8 +725,8 @@ static int hrtimer_switch_to_hres(void)
 		return 0;
 	}
 	base->hres_active = 1;
-	base->clock_base[CLOCK_REALTIME].resolution = KTIME_HIGH_RES;
-	base->clock_base[CLOCK_MONOTONIC].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES;
+	base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES;
 
 	tick_setup_sched_timer();
 
@@ -1116,7 +1116,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
 	struct hrtimer_cpu_base *cpu_base;
-
+	int base;
 	memset(timer, 0, sizeof(struct hrtimer));
 
 	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
@@ -1124,7 +1124,8 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
 
-	timer->base = &cpu_base->clock_base[clock_id];
+	base = hrtimer_clockid_to_base(clock_id);
+	timer->base = &cpu_base->clock_base[base];
 	hrtimer_init_timer_hres(timer);
 	timerqueue_init(&timer->node);
 
@@ -1160,9 +1161,10 @@ EXPORT_SYMBOL_GPL(hrtimer_init);
 int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 {
 	struct hrtimer_cpu_base *cpu_base;
+	int base = hrtimer_clockid_to_base(which_clock);
 
 	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
-	*tp = ktime_to_timespec(cpu_base->clock_base[which_clock].resolution);
+	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
 }
-- 
1.7.3.2.146.gca209