1 files changed, 89 insertions, 94 deletions

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d3b91e75cecd..cbc6acb0db3f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -8,6 +8,7 @@
  *
  */
 
+#include <linux/timekeeper_internal.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
@@ -20,71 +21,11 @@
 #include <linux/time.h>
 #include <linux/tick.h>
 #include <linux/stop_machine.h>
+#include <linux/pvclock_gtod.h>
 
-/* Structure holding internal timekeeping values. */
-struct timekeeper {
-        /* Current clocksource used for timekeeping. */
-        struct clocksource      *clock;
-        /* NTP adjusted clock multiplier */
-        u32                     mult;
-        /* The shift value of the current clocksource. */
-        u32                     shift;
-        /* Number of clock cycles in one NTP interval. */
-        cycle_t                 cycle_interval;
-        /* Number of clock shifted nano seconds in one NTP interval. */
-        u64                     xtime_interval;
-        /* shifted nano seconds left over when rounding cycle_interval */
-        s64                     xtime_remainder;
-        /* Raw nano seconds accumulated per NTP interval. */
-        u32                     raw_interval;
-
-        /* Current CLOCK_REALTIME time in seconds */
-        u64                     xtime_sec;
-        /* Clock shifted nano seconds */
-        u64                     xtime_nsec;
-
-        /* Difference between accumulated time and NTP time in ntp
-         * shifted nano seconds. */
-        s64                     ntp_error;
-        /* Shift conversion between clock shifted nano seconds and
-         * ntp shifted nano seconds. */
-        u32                     ntp_error_shift;
-
-        /*
-         * wall_to_monotonic is what we need to add to xtime (or xtime corrected
-         * for sub jiffie times) to get to monotonic time.  Monotonic is pegged
-         * at zero at system boot time, so wall_to_monotonic will be negative,
-         * however, we will ALWAYS keep the tv_nsec part positive so we can use
-         * the usual normalization.
-         *
-         * wall_to_monotonic is moved after resume from suspend for the
-         * monotonic time not to jump. We need to add total_sleep_time to
-         * wall_to_monotonic to get the real boot based time offset.
-         *
-         * - wall_to_monotonic is no longer the boot time, getboottime must be
-         * used instead.
-         */
-        struct timespec         wall_to_monotonic;
-        /* Offset clock monotonic -> clock realtime */
-        ktime_t                 offs_real;
-        /* time spent in suspend */
-        struct timespec         total_sleep_time;
-        /* Offset clock monotonic -> clock boottime */
-        ktime_t                 offs_boot;
-        /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
-        struct timespec         raw_time;
-        /* Seqlock for all timekeeper values */
-        seqlock_t               lock;
-};
 
 static struct timekeeper timekeeper;
 
-/*
- * This read-write spinlock protects us from races in SMP while
- * playing with xtime.
- */
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
-
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
@@ -96,15 +37,6 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
         }
 }
 
-static struct timespec tk_xtime(struct timekeeper *tk)
-{
-        struct timespec ts;
-
-        ts.tv_sec = tk->xtime_sec;
-        ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
-        return ts;
-}
-
 static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts)
 {
         tk->xtime_sec = ts->tv_sec;
@@ -243,17 +175,63 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
         return nsec + arch_gettimeoffset();
 }
 
+static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
+
+static void update_pvclock_gtod(struct timekeeper *tk)
+{
+        raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk);
+}
+
+/**
+ * pvclock_gtod_register_notifier - register a pvclock timedata update listener
+ *
+ * Must hold write on timekeeper.lock
+ */
+int pvclock_gtod_register_notifier(struct notifier_block *nb)
+{
+        struct timekeeper *tk = &timekeeper;
+        unsigned long flags;
+        int ret;
+
+        write_seqlock_irqsave(&tk->lock, flags);
+        ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
+        /* update timekeeping data */
+        update_pvclock_gtod(tk);
+        write_sequnlock_irqrestore(&tk->lock, flags);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
+
+/**
+ * pvclock_gtod_unregister_notifier - unregister a pvclock
+ * timedata update listener
+ *
+ * Must hold write on timekeeper.lock
+ */
+int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
+{
+        struct timekeeper *tk = &timekeeper;
+        unsigned long flags;
+        int ret;
+
+        write_seqlock_irqsave(&tk->lock, flags);
+        ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
+        write_sequnlock_irqrestore(&tk->lock, flags);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
+
 /* must hold write on timekeeper.lock */
 static void timekeeping_update(struct timekeeper *tk, bool clearntp)
 {
-        struct timespec xt;
-
         if (clearntp) {
                 tk->ntp_error = 0;
                 ntp_clear();
         }
-        xt = tk_xtime(tk);
-        update_vsyscall(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult);
+        update_vsyscall(tk);
+        update_pvclock_gtod(tk);
 }
 
 /**
@@ -776,6 +754,7 @@ static void timekeeping_resume(void)
 
         read_persistent_clock(&ts);
 
+        clockevents_resume();
         clocksource_resume();
 
         write_seqlock_irqsave(&tk->lock, flags);
@@ -835,6 +814,7 @@ static int timekeeping_suspend(void)
 
         clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
         clocksource_suspend();
+        clockevents_suspend();
 
         return 0;
 }
@@ -1111,7 +1091,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
         accumulate_nsecs_to_secs(tk);
 
         /* Accumulate raw time */
-        raw_nsecs = tk->raw_interval << shift;
+        raw_nsecs = (u64)tk->raw_interval << shift;
         raw_nsecs += tk->raw_time.tv_nsec;
         if (raw_nsecs >= NSEC_PER_SEC) {
                 u64 raw_secs = raw_nsecs;
@@ -1128,6 +1108,33 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
         return offset;
 }
 
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
+static inline void old_vsyscall_fixup(struct timekeeper *tk)
+{
+        s64 remainder;
+
+        /*
+        * Store only full nanoseconds into xtime_nsec after rounding
+        * it up and add the remainder to the error difference.
+        * XXX - This is necessary to avoid small 1ns inconsistnecies caused
+        * by truncating the remainder in vsyscalls. However, it causes
+        * additional work to be done in timekeeping_adjust(). Once
+        * the vsyscall implementations are converted to use xtime_nsec
+        * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
+        * users are removed, this can be killed.
+        */
+        remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1);
+        tk->xtime_nsec -= remainder;
+        tk->xtime_nsec += 1ULL << tk->shift;
+        tk->ntp_error += remainder << tk->ntp_error_shift;
+
+}
+#else
+#define old_vsyscall_fixup(tk)
+#endif
+
+
+
 /**
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
@@ -1139,7 +1146,6 @@ static void update_wall_time(void)
         cycle_t offset;
         int shift = 0, maxshift;
         unsigned long flags;
-        s64 remainder;
 
         write_seqlock_irqsave(&tk->lock, flags);
 
@@ -1181,20 +1187,11 @@ static void update_wall_time(void)
         /* correct the clock when NTP error is too big */
         timekeeping_adjust(tk, offset);
 
-
         /*
-        * Store only full nanoseconds into xtime_nsec after rounding
-        * it up and add the remainder to the error difference.
-        * XXX - This is necessary to avoid small 1ns inconsistnecies caused
-        * by truncating the remainder in vsyscalls. However, it causes
-        * additional work to be done in timekeeping_adjust(). Once
-        * the vsyscall implementations are converted to use xtime_nsec
-        * (shifted nanoseconds), this can be killed.
-        */
-        remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1);
-        tk->xtime_nsec -= remainder;
-        tk->xtime_nsec += 1ULL << tk->shift;
-        tk->ntp_error += remainder << tk->ntp_error_shift;
+         * XXX This can be killed once everyone converts
+         * to the new update_vsyscall.
+         */
+        old_vsyscall_fixup(tk);
 
         /*
          * Finally, make sure that after the rounding
@@ -1346,9 +1343,7 @@ struct timespec get_monotonic_coarse(void)
 }
 
 /*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
+ * Must hold jiffies_lock
  */
 void do_timer(unsigned long ticks)
 {
@@ -1436,7 +1431,7 @@ EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset);
  */
 void xtime_update(unsigned long ticks)
 {
-        write_seqlock(&xtime_lock);
+        write_seqlock(&jiffies_lock);
         do_timer(ticks);
-        write_sequnlock(&xtime_lock);
+        write_sequnlock(&jiffies_lock);
 }