1 files changed, 77 insertions, 49 deletions

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fb0f46fa1ecd..af4135f05825 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -13,6 +13,7 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <linux/sysdev.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
@@ -164,19 +165,12 @@ struct timespec raw_time;
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
-static struct timespec xtime_cache __attribute__ ((aligned (16)));
-void update_xtime_cache(u64 nsec)
-{
-        xtime_cache = xtime;
-        timespec_add_ns(&xtime_cache, nsec);
-}
-
 /* must hold xtime_lock */
 void timekeeping_leap_insert(int leapsecond)
 {
         xtime.tv_sec += leapsecond;
         wall_to_monotonic.tv_sec -= leapsecond;
-        update_vsyscall(&xtime, timekeeper.clock);
+        update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
 }
 
 #ifdef CONFIG_GENERIC_TIME
@@ -331,12 +325,10 @@ int do_settimeofday(struct timespec *tv)
 
         xtime = *tv;
 
-        update_xtime_cache(0);
-
         timekeeper.ntp_error = 0;
         ntp_clear();
 
-        update_vsyscall(&xtime, timekeeper.clock);
+        update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
 
         write_sequnlock_irqrestore(&xtime_lock, flags);
 
@@ -487,6 +479,17 @@ int timekeeping_valid_for_hres(void)
 }
 
 /**
+ * timekeeping_max_deferment - Returns max time the clocksource can be deferred
+ *
+ * Caller must observe xtime_lock via read_seqbegin/read_seqretry to
+ * ensure that the clocksource does not change!
+ */
+u64 timekeeping_max_deferment(void)
+{
+        return timekeeper.clock->max_idle_ns;
+}
+
+/**
  * read_persistent_clock -  Return time from the persistent clock.
  *
  * Weak dummy function for arches that do not yet support it.
@@ -547,7 +550,6 @@ void __init timekeeping_init(void)
         }
         set_normalized_timespec(&wall_to_monotonic,
                                 -boot.tv_sec, -boot.tv_nsec);
-        update_xtime_cache(0);
         total_sleep_time.tv_sec = 0;
         total_sleep_time.tv_nsec = 0;
         write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -581,7 +583,6 @@ static int timekeeping_resume(struct sys_device *dev)
                 wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
                 total_sleep_time = timespec_add_safe(total_sleep_time, ts);
         }
-        update_xtime_cache(0);
         /* re-base the last cycle value */
         timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
         timekeeper.ntp_error = 0;
@@ -722,6 +723,49 @@ static void timekeeping_adjust(s64 offset)
 }
 
 /**
+ * logarithmic_accumulation - shifted accumulation of cycles
+ *
+ * This functions accumulates a shifted interval of cycles into
+ * into a shifted interval nanoseconds. Allows for O(log) accumulation
+ * loop.
+ *
+ * Returns the unconsumed cycles.
+ */
+static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+{
+        u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+
+        /* If the offset is smaller then a shifted interval, do nothing */
+        if (offset < timekeeper.cycle_interval<<shift)
+                return offset;
+
+        /* Accumulate one shifted interval */
+        offset -= timekeeper.cycle_interval << shift;
+        timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
+
+        timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
+        while (timekeeper.xtime_nsec >= nsecps) {
+                timekeeper.xtime_nsec -= nsecps;
+                xtime.tv_sec++;
+                second_overflow();
+        }
+
+        /* Accumulate into raw time */
+        raw_time.tv_nsec += timekeeper.raw_interval << shift;;
+        while (raw_time.tv_nsec >= NSEC_PER_SEC) {
+                raw_time.tv_nsec -= NSEC_PER_SEC;
+                raw_time.tv_sec++;
+        }
+
+        /* Accumulate error between NTP and clock interval */
+        timekeeper.ntp_error += tick_length << shift;
+        timekeeper.ntp_error -= timekeeper.xtime_interval <<
+                                (timekeeper.ntp_error_shift + shift);
+
+        return offset;
+}
+
+/**
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
  * Called from the timer interrupt, must hold a write on xtime_lock.
@@ -730,7 +774,7 @@ void update_wall_time(void)
 {
         struct clocksource *clock;
         cycle_t offset;
-        u64 nsecs;
+        int shift = 0, maxshift;
 
         /* Make sure we're fully resumed: */
         if (unlikely(timekeeping_suspended))
@@ -744,33 +788,22 @@ void update_wall_time(void)
 #endif
         timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
 
-        /* normally this loop will run just once, however in the
-         * case of lost or late ticks, it will accumulate correctly.
+        /*
+         * With NO_HZ we may have to accumulate many cycle_intervals
+         * (think "ticks") worth of time at once. To do this efficiently,
+         * we calculate the largest doubling multiple of cycle_intervals
+         * that is smaller then the offset. We then accumulate that
+         * chunk in one go, and then try to consume the next smaller
+         * doubled multiple.
          */
+        shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
+        shift = max(0, shift);
+        /* Bound shift to one less then what overflows tick_length */
+        maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+        shift = min(shift, maxshift);
         while (offset >= timekeeper.cycle_interval) {
-                u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
-
-                /* accumulate one interval */
-                offset -= timekeeper.cycle_interval;
-                clock->cycle_last += timekeeper.cycle_interval;
-
-                timekeeper.xtime_nsec += timekeeper.xtime_interval;
-                if (timekeeper.xtime_nsec >= nsecps) {
-                        timekeeper.xtime_nsec -= nsecps;
-                        xtime.tv_sec++;
-                        second_overflow();
-                }
-
-                raw_time.tv_nsec += timekeeper.raw_interval;
-                if (raw_time.tv_nsec >= NSEC_PER_SEC) {
-                        raw_time.tv_nsec -= NSEC_PER_SEC;
-                        raw_time.tv_sec++;
-                }
-
-                /* accumulate error between NTP and clock interval */
-                timekeeper.ntp_error += tick_length;
-                timekeeper.ntp_error -= timekeeper.xtime_interval <<
-                                        timekeeper.ntp_error_shift;
+                offset = logarithmic_accumulation(offset, shift);
+                shift--;
         }
 
         /* correct the clock when NTP error is too big */
@@ -806,11 +839,8 @@ void update_wall_time(void)
         timekeeper.ntp_error += timekeeper.xtime_nsec <<
                                 timekeeper.ntp_error_shift;
 
-        nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
-        update_xtime_cache(nsecs);
-
         /* check to see if there is a new clocksource to use */
-        update_vsyscall(&xtime, timekeeper.clock);
+        update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
 }
 
 /**
@@ -845,13 +875,13 @@ void monotonic_to_bootbased(struct timespec *ts)
 
 unsigned long get_seconds(void)
 {
-        return xtime_cache.tv_sec;
+        return xtime.tv_sec;
 }
 EXPORT_SYMBOL(get_seconds);
 
 struct timespec __current_kernel_time(void)
 {
-        return xtime_cache;
+        return xtime;
 }
 
 struct timespec current_kernel_time(void)
@@ -861,8 +891,7 @@ struct timespec current_kernel_time(void)
 
         do {
                 seq = read_seqbegin(&xtime_lock);
-
-                now = xtime_cache;
+                now = xtime;
         } while (read_seqretry(&xtime_lock, seq));
 
         return now;
@@ -876,8 +905,7 @@ struct timespec get_monotonic_coarse(void)
 
         do {
                 seq = read_seqbegin(&xtime_lock);
-
-                now = xtime_cache;
+                now = xtime;
                 mono = wall_to_monotonic;
         } while (read_seqretry(&xtime_lock, seq));