[PATCH 0/3] clocksource: CLOCK_MONOTONIC_RAW

[PATCH 0/3] clocksource: CLOCK_MONOTONIC_RAW

[zippel]

Hi,

This is a resend of the raw monotonic clock patches. Compared to the
original patches I inserted a cleanup patch inbetween to keep the last
patch simple and to avoid the rounding issues, I dropped the fraction
completely, so that it becomes even simpler.

bye, Roman

-- 

[PATCH 1/3] clocksource: keep track of original clocksource frequency

[zippel]

[-- Attachment #1: clocksource_mult_orig --]
[-- Type: text/plain, Size: 3466 bytes --]

From: John Stultz <johnstul@us.ibm.com>

The clocksource frequency is represented by
clocksource->mult/2^(clocksource->shift).  Currently, when NTP makes
adjustments to the clock frequency, they are made directly to the mult value.

This has the drawback that once changed, we cannot know what the orignal mult
value was, or how much adjustment has been applied.

This property causes problems in calculating proper ntp intervals when
switching back and forth between clocksources.

This patch separates the current mult value into a mult and mult_orig pair. 
The mult_orig value stays constant, while the ntp clocksource adjustments are
done only to the mult value.

This allows for correct ntp interval calculation and additionally lays the
groundwork for a new notion of time, what I'm calling the monotonic-raw time,
which is introduced in a following patch.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Roman Zippel <zippel@linux-m68k.org>
---
 include/linux/clocksource.h |   11 +++++++----
 kernel/time/clocksource.c   |    3 +++
 kernel/time/jiffies.c       |    1 +
 3 files changed, 11 insertions(+), 4 deletions(-)

Index: linux-2.6/include/linux/clocksource.h
===================================================================
--- linux-2.6.orig/include/linux/clocksource.h
+++ linux-2.6/include/linux/clocksource.h
@@ -45,7 +45,8 @@ struct clocksource;
  * @read:		returns a cycle value
  * @mask:		bitmask for two's complement
  *			subtraction of non 64 bit counters
- * @mult:		cycle to nanosecond multiplier
+ * @mult:		cycle to nanosecond multiplier (adjusted by NTP)
+ * @mult_orig:		cycle to nanosecond multiplier (unadjusted by NTP)
  * @shift:		cycle to nanosecond divisor (power of two)
  * @flags:		flags describing special properties
  * @vread:		vsyscall based read
@@ -63,6 +64,7 @@ struct clocksource {
 	cycle_t (*read)(void);
 	cycle_t mask;
 	u32 mult;
+	u32 mult_orig;
 	u32 shift;
 	unsigned long flags;
 	cycle_t (*vread)(void);
@@ -201,16 +203,17 @@ static inline void clocksource_calculate
 {
 	u64 tmp;
 
-	/* XXX - All of this could use a whole lot of optimization */
+	/* Do the ns -> cycle conversion first, using original mult */
 	tmp = length_nsec;
 	tmp <<= c->shift;
-	tmp += c->mult/2;
-	do_div(tmp, c->mult);
+	tmp += c->mult_orig/2;
+	do_div(tmp, c->mult_orig);
 
 	c->cycle_interval = (cycle_t)tmp;
 	if (c->cycle_interval == 0)
 		c->cycle_interval = 1;
 
+	/* Go back from cycles -> shifted ns, this time use ntp adjused mult */
 	c->xtime_interval = (u64)c->cycle_interval * c->mult;
 }
 
Index: linux-2.6/kernel/time/clocksource.c
===================================================================
--- linux-2.6.orig/kernel/time/clocksource.c
+++ linux-2.6/kernel/time/clocksource.c
@@ -325,6 +325,9 @@ int clocksource_register(struct clocksou
 	unsigned long flags;
 	int ret;
 
+	/* save mult_orig on registration */
+	c->mult_orig = c->mult;
+
 	spin_lock_irqsave(&clocksource_lock, flags);
 	ret = clocksource_enqueue(c);
 	if (!ret)
Index: linux-2.6/kernel/time/jiffies.c
===================================================================
--- linux-2.6.orig/kernel/time/jiffies.c
+++ linux-2.6/kernel/time/jiffies.c
@@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies =
 	.read		= jiffies_read,
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+	.mult_orig	= NSEC_PER_JIFFY << JIFFIES_SHIFT,
 	.shift		= JIFFIES_SHIFT,
 };
 

-- 

[PATCH 2/3] clocksource: introduce clocksource_forward_now()

[zippel]

[-- Attachment #1: clocksource_forward_now --]
[-- Type: text/plain, Size: 6027 bytes --]

To keep the raw monotonic patch simple first introduce
clocksource_forward_now(), which takes care of the offset since the last
update_wall_time() call and adds it to the clock, so there is no need
anymore to deal with it explicitly at various places, which need to make
significant changes to the clock.
This is also gets rid of the timekeeping_suspend_nsecs, instead of
waiting until resume, the value is accumulated during suspend. In the end
there is only a single user of __get_nsec_offset() left, so I integrated
it back to getnstimeofday().

Signed-off-by: Roman Zippel <zippel@linux-m68k.org>

---
 kernel/time/timekeeping.c |   71 +++++++++++++++++++++-------------------------
 1 file changed, 33 insertions(+), 38 deletions(-)

Index: linux-2.6/kernel/time/timekeeping.c
===================================================================
--- linux-2.6.orig/kernel/time/timekeeping.c
+++ linux-2.6/kernel/time/timekeeping.c
@@ -58,27 +58,23 @@ struct clocksource *clock;
 
 #ifdef CONFIG_GENERIC_TIME
 /**
- * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook
+ * clocksource_forward_now - update clock to the current time
  *
- * private function, must hold xtime_lock lock when being
- * called. Returns the number of nanoseconds since the
- * last call to update_wall_time() (adjusted by NTP scaling)
+ * Forward the current clock to update its state since the last call to
+ * update_wall_time(). This is useful before significant clock changes,
+ * as it avoids having to deal with this time offset explicitly.
  */
-static inline s64 __get_nsec_offset(void)
+static void clocksource_forward_now(void)
 {
 	cycle_t cycle_now, cycle_delta;
-	s64 ns_offset;
+	s64 nsec;
 
-	/* read clocksource: */
 	cycle_now = clocksource_read(clock);
-
-	/* calculate the delta since the last update_wall_time: */
 	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+	clock->cycle_last = cycle_now;
 
-	/* convert to nanoseconds: */
-	ns_offset = cyc2ns(clock, cycle_delta);
-
-	return ns_offset;
+	nsec = cyc2ns(clock, cycle_delta);
+	timespec_add_ns(&xtime, nsec);
 }
 
 /**
@@ -89,6 +85,7 @@ static inline s64 __get_nsec_offset(void
  */
 void getnstimeofday(struct timespec *ts)
 {
+	cycle_t cycle_now, cycle_delta;
 	unsigned long seq;
 	s64 nsecs;
 
@@ -96,7 +93,15 @@ void getnstimeofday(struct timespec *ts)
 		seq = read_seqbegin(&xtime_lock);
 
 		*ts = xtime;
-		nsecs = __get_nsec_offset();
+
+		/* read clocksource: */
+		cycle_now = clocksource_read(clock);
+
+		/* calculate the delta since the last update_wall_time: */
+		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+		/* convert to nanoseconds: */
+		nsecs = cyc2ns(clock, cycle_delta);
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -129,22 +134,22 @@ EXPORT_SYMBOL(do_gettimeofday);
  */
 int do_settimeofday(struct timespec *tv)
 {
+	struct timespec ts_delta;
 	unsigned long flags;
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
 
 	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
-	nsec -= __get_nsec_offset();
+	clocksource_forward_now();
+
+	ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
+	ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
+	wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta);
 
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
+	xtime = *tv;
 
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
 	update_xtime_cache(0);
 
 	clock->error = 0;
@@ -170,22 +175,17 @@ EXPORT_SYMBOL(do_settimeofday);
 static void change_clocksource(void)
 {
 	struct clocksource *new;
-	cycle_t now;
-	u64 nsec;
 
 	new = clocksource_get_next();
 
 	if (clock == new)
 		return;
 
-	new->cycle_last = 0;
-	now = clocksource_read(new);
-	nsec =  __get_nsec_offset();
-	timespec_add_ns(&xtime, nsec);
+	clocksource_forward_now();
 
 	clock = new;
-	clock->cycle_last = now;
-
+	clock->cycle_last = 0;
+	clock->cycle_last = clocksource_read(new);
 	clock->error = 0;
 	clock->xtime_nsec = 0;
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
@@ -200,8 +200,8 @@ static void change_clocksource(void)
 	 */
 }
 #else
+static inline void clocksource_forward_now(void) { }
 static inline void change_clocksource(void) { }
-static inline s64 __get_nsec_offset(void) { return 0; }
 #endif
 
 /**
@@ -265,8 +265,6 @@ void __init timekeeping_init(void)
 static int timekeeping_suspended;
 /* time in seconds when suspend began */
 static unsigned long timekeeping_suspend_time;
-/* xtime offset when we went into suspend */
-static s64 timekeeping_suspend_nsecs;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
@@ -292,8 +290,6 @@ static int timekeeping_resume(struct sys
 		wall_to_monotonic.tv_sec -= sleep_length;
 		total_sleep_time += sleep_length;
 	}
-	/* Make sure that we have the correct xtime reference */
-	timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
 	update_xtime_cache(0);
 	/* re-base the last cycle value */
 	clock->cycle_last = 0;
@@ -319,8 +315,7 @@ static int timekeeping_suspend(struct sy
 	timekeeping_suspend_time = read_persistent_clock();
 
 	write_seqlock_irqsave(&xtime_lock, flags);
-	/* Get the current xtime offset */
-	timekeeping_suspend_nsecs = __get_nsec_offset();
+	clocksource_forward_now();
 	timekeeping_suspended = 1;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -461,10 +456,10 @@ void update_wall_time(void)
 	 */
 	while (offset >= clock->cycle_interval) {
 		/* accumulate one interval */
-		clock->xtime_nsec += clock->xtime_interval;
-		clock->cycle_last += clock->cycle_interval;
 		offset -= clock->cycle_interval;
+		clock->cycle_last += clock->cycle_interval;
 
+		clock->xtime_nsec += clock->xtime_interval;
 		if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) {
 			clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift;
 			xtime.tv_sec++;

-- 

[PATCH 3/3] clocksource: introduce CLOCK_MONOTONIC_RAW

[zippel]

[-- Attachment #1: clocksource_monotonic_raw --]
[-- Type: text/plain, Size: 6552 bytes --]

From: John Stultz <johnstul@us.ibm.com>

In talking with Josip Loncaric, and his work on clock synchronization (see
btime.sf.net), he mentioned that for really close synchronization, it is
useful to have access to "hardware time", that is a notion of time that is not
in any way adjusted by the clock slewing done to keep close time sync.

Part of the issue is if we are using the kernel's ntp adjusted representation
of time in order to measure how we should correct time, we can run into what
Paul McKenney aptly described as "Painting a road using the lines we're
painting as the guide".

I had been thinking of a similar problem, and was trying to come up with a way
to give users access to a purely hardware based time representation that
avoided users having to know the underlying frequency and mask values needed
to deal with the wide variety of possible underlying hardware counters.

My solution is to introduce CLOCK_MONOTONIC_RAW.  This exposes a nanosecond
based time value, that increments starting at bootup and has no frequency
adjustments made to it what so ever.

The time is accessed from userspace via the posix_clock_gettime() syscall,
passing CLOCK_MONOTONIC_RAW as the clock_id.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Roman Zippel <zippel@linux-m68k.org>
---
 include/linux/clocksource.h |    3 +++
 include/linux/time.h        |    2 ++
 kernel/posix-timers.c       |   15 +++++++++++++++
 kernel/time/timekeeping.c   |   44 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 64 insertions(+)

Index: linux-2.6/include/linux/clocksource.h
===================================================================
--- linux-2.6.orig/include/linux/clocksource.h
+++ linux-2.6/include/linux/clocksource.h
@@ -79,6 +79,7 @@ struct clocksource {
 	/* timekeeping specific data, ignore */
 	cycle_t cycle_interval;
 	u64	xtime_interval;
+	u32	raw_interval;
 	/*
 	 * Second part is written at each timer interrupt
 	 * Keep it in a different cache line to dirty no
@@ -87,6 +88,7 @@ struct clocksource {
 	cycle_t cycle_last ____cacheline_aligned_in_smp;
 	u64 xtime_nsec;
 	s64 error;
+	struct timespec raw_time;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
@@ -215,6 +217,7 @@ static inline void clocksource_calculate
 
 	/* Go back from cycles -> shifted ns, this time use ntp adjused mult */
 	c->xtime_interval = (u64)c->cycle_interval * c->mult;
+	c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift;
 }
 
 
Index: linux-2.6/include/linux/time.h
===================================================================
--- linux-2.6.orig/include/linux/time.h
+++ linux-2.6/include/linux/time.h
@@ -117,6 +117,7 @@ extern int do_setitimer(int which, struc
 extern unsigned int alarm_setitimer(unsigned int seconds);
 extern int do_getitimer(int which, struct itimerval *value);
 extern void getnstimeofday(struct timespec *tv);
+extern void getrawmonotonic(struct timespec *ts);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
 
@@ -214,6 +215,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC			1
 #define CLOCK_PROCESS_CPUTIME_ID	2
 #define CLOCK_THREAD_CPUTIME_ID		3
+#define CLOCK_MONOTONIC_RAW		4
 
 /*
  * The IDs of various hardware clocks:
Index: linux-2.6/kernel/posix-timers.c
===================================================================
--- linux-2.6.orig/kernel/posix-timers.c
+++ linux-2.6/kernel/posix-timers.c
@@ -223,6 +223,15 @@ static int posix_ktime_get_ts(clockid_t 
 }
 
 /*
+ * Get monotonic time for posix timers
+ */
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+{
+	getrawmonotonic(tp);
+	return 0;
+}
+
+/*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
@@ -235,9 +244,15 @@ static __init int init_posix_timers(void
 		.clock_get = posix_ktime_get_ts,
 		.clock_set = do_posix_clock_nosettime,
 	};
+	struct k_clock clock_monotonic_raw = {
+		.clock_getres = hrtimer_get_res,
+		.clock_get = posix_get_monotonic_raw,
+		.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);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
Index: linux-2.6/kernel/time/timekeeping.c
===================================================================
--- linux-2.6.orig/kernel/time/timekeeping.c
+++ linux-2.6/kernel/time/timekeeping.c
@@ -75,6 +75,9 @@ static void clocksource_forward_now(void
 
 	nsec = cyc2ns(clock, cycle_delta);
 	timespec_add_ns(&xtime, nsec);
+
+	nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+	clock->raw_time.tv_nsec += nsec;
 }
 
 /**
@@ -181,6 +184,8 @@ static void change_clocksource(void)
 
 	clocksource_forward_now();
 
+	new->raw_time = clock->raw_time;
+
 	clock = new;
 	clock->cycle_last = 0;
 	clock->cycle_last = clocksource_read(new);
@@ -203,6 +208,39 @@ static inline void change_clocksource(vo
 #endif
 
 /**
+ * getrawmonotonic - Returns the raw monotonic time in a timespec
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the raw monotonic time (completely un-modified by ntp)
+ */
+void getrawmonotonic(struct timespec *ts)
+{
+	unsigned long seq;
+	s64 nsecs;
+	cycle_t cycle_now, cycle_delta;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+
+		/* read clocksource: */
+		cycle_now = clocksource_read(clock);
+
+		/* calculate the delta since the last update_wall_time: */
+		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+		/* convert to nanoseconds: */
+		nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+
+		*ts = clock->raw_time;
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	timespec_add_ns(ts, nsecs);
+}
+EXPORT_SYMBOL(getrawmonotonic);
+
+
+/**
  * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
  */
 int timekeeping_valid_for_hres(void)
@@ -464,6 +502,12 @@ void update_wall_time(void)
 			second_overflow();
 		}
 
+		clock->raw_time.tv_nsec += clock->raw_interval;
+		if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) {
+			clock->raw_time.tv_nsec -= NSEC_PER_SEC;
+			clock->raw_time.tv_sec++;
+		}
+
 		/* accumulate error between NTP and clock interval */
 		clock->error += tick_length;
 		clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift);

--