Revert "time: Remove xtime_cache"

This reverts commit 7bc7d637452383d56ba4368d4336b0dde1bb476d, as
requested by John Stultz. Quoting John:

 "Petr Titěra reported an issue where he saw odd atime regressions with
  2.6.33 where there were a full second worth of nanoseconds in the
  nanoseconds field.

  He also reviewed the time code and narrowed down the problem: unhandled
  overflow of the nanosecond field caused by rounding up the
  sub-nanosecond accumulated time.

  Details:

   * At the end of update_wall_time(), we currently round up the
  sub-nanosecond portion of accumulated time when storing it into xtime.
  This was added to avoid time inconsistencies caused when the
  sub-nanosecond portion was truncated when storing into xtime.
  Unfortunately we don't handle the possible second overflow caused by
  that rounding.

   * Previously the xtime_cache code hid this overflow by normalizing the
  xtime value when storing into the xtime_cache.

   * We could try to handle the second overflow after the rounding up, but
  since this affects the timekeeping's internal state, this would further
  complicate the next accumulation cycle, causing small errors in ntp
  steering. As much as I'd like to get rid of it, the xtime_cache code is
  known to work.

   * The correct fix is really to include the sub-nanosecond portion in the
  timekeeping accessor function, so we don't need to round up at during
  accumulation. This would greatly simplify the accumulation code.
  Unfortunately, we can't do this safely until the last three
  non-GENERIC_TIME arches (sparc32, arm, cris) are converted  (those
  patches are in -mm) and we kill off the spots where arches set xtime
  directly. This is all 2.6.34 material, so I think reverting the
  xtime_cache change is the best approach for now.

  Many thanks to Petr for both reporting and finding the issue!"

Reported-by: Petr Titěra <P.Titera@century.cz>
Requested-by: john stultz <johnstul@us.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/time.c b/kernel/time.c
index c6324d9..8047980 100644 (file)
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -136,6 +136,7 @@ static inline void warp_clock(void)
        write_seqlock_irq(&xtime_lock);
        wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
        xtime.tv_sec += sys_tz.tz_minuteswest * 60;
+       update_xtime_cache(0);
        write_sequnlock_irq(&xtime_lock);
        clock_was_set();
 }

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index af4135f..7faaa32 100644 (file)
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -165,6 +165,13 @@ 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)
 {
@@ -325,6 +332,8 @@ int do_settimeofday(struct timespec *tv)
 
        xtime = *tv;
 
+       update_xtime_cache(0);
+
        timekeeper.ntp_error = 0;
        ntp_clear();
 
@@ -550,6 +559,7 @@ 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);
@@ -583,6 +593,7 @@ 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 +733,7 @@ static void timekeeping_adjust(s64 offset)
                                timekeeper.ntp_error_shift;
 }
 
+
 /**
  * logarithmic_accumulation - shifted accumulation of cycles
  *
@@ -765,6 +777,7 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
        return offset;
 }
 
+
 /**
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
@@ -774,6 +787,7 @@ void update_wall_time(void)
 {
        struct clocksource *clock;
        cycle_t offset;
+       u64 nsecs;
        int shift = 0, maxshift;
 
        /* Make sure we're fully resumed: */
@@ -839,6 +853,9 @@ 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, timekeeper.mult);
 }
@@ -875,13 +892,13 @@ void monotonic_to_bootbased(struct timespec *ts)
 
 unsigned long get_seconds(void)
 {
-       return xtime.tv_sec;
+       return xtime_cache.tv_sec;
 }
 EXPORT_SYMBOL(get_seconds);
 
 struct timespec __current_kernel_time(void)
 {
-       return xtime;
+       return xtime_cache;
 }
 
 struct timespec current_kernel_time(void)
@@ -891,7 +908,8 @@ struct timespec current_kernel_time(void)
 
        do {
                seq = read_seqbegin(&xtime_lock);
-               now = xtime;
+
+               now = xtime_cache;
        } while (read_seqretry(&xtime_lock, seq));
 
        return now;
@@ -905,7 +923,8 @@ struct timespec get_monotonic_coarse(void)
 
        do {
                seq = read_seqbegin(&xtime_lock);
-               now = xtime;
+
+               now = xtime_cache;
                mono = wall_to_monotonic;
        } while (read_seqretry(&xtime_lock, seq));