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>

2 files changed, 59 insertions, 0 deletions

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);