clocksource: introduce CLOCK_MONOTONIC_RAW

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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 64 insertions, 0 deletions

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index f0a7fb984413..f88d32f8ff7c 100644
--- a/include/linux/clocksource.h
+++ b/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_interval(struct clocksource *c,
 
 	/* 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;
 }
 
 
diff --git a/include/linux/time.h b/include/linux/time.h
index e15206a7e82e..205f974b9ebf 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -117,6 +117,7 @@ extern int do_setitimer(int which, struct itimerval *value,
 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:
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index e36d5798cbff..d3c66b53dff6 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -223,6 +223,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 }
 
 /*
+ * 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,
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 83d3555a6998..5099c95b8aa2 100644
--- a/kernel/time/timekeeping.c
+++ b/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;
 }
 
 /**
@@ -183,6 +186,8 @@ 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);
@@ -205,6 +210,39 @@ static inline void change_clocksource(void) { }
 #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)
@@ -466,6 +504,12 @@ 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);