10 files changed, 277 insertions, 244 deletions

diff --git a/kernel/compat.c b/kernel/compat.c
index 4a856a3643bb..32c254a8ab9a 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -955,7 +955,8 @@ asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
                         __put_user(txc.jitcnt, &utp->jitcnt) ||
                         __put_user(txc.calcnt, &utp->calcnt) ||
                         __put_user(txc.errcnt, &utp->errcnt) ||
-                        __put_user(txc.stbcnt, &utp->stbcnt))
+                        __put_user(txc.stbcnt, &utp->stbcnt) ||
+                        __put_user(txc.tai, &utp->tai))
                 ret = -EFAULT;
 
         return ret;
diff --git a/kernel/kexec.c b/kernel/kexec.c
index cb85c79989b4..1c5fcacbcf33 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1217,7 +1217,7 @@ static int __init parse_crashkernel_mem(char 			*cmdline,
                 }
 
                 /* match ? */
-                if (system_ram >= start && system_ram <= end) {
+                if (system_ram >= start && system_ram < end) {
                         *crash_size = size;
                         break;
                 }
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index ae5c6c147c4b..f1525ad06cb3 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -4,8 +4,9 @@
 
 #include <linux/sched.h>
 #include <linux/posix-timers.h>
-#include <asm/uaccess.h>
 #include <linux/errno.h>
+#include <linux/math64.h>
+#include <asm/uaccess.h>
 
 static int check_clock(const clockid_t which_clock)
 {
@@ -47,12 +48,10 @@ static void sample_to_timespec(const clockid_t which_clock,
                                union cpu_time_count cpu,
                                struct timespec *tp)
 {
-        if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-                tp->tv_sec = div_long_long_rem(cpu.sched,
-                                               NSEC_PER_SEC, &tp->tv_nsec);
-        } else {
+        if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
+                *tp = ns_to_timespec(cpu.sched);
+        else
                 cputime_to_timespec(cpu.cpu, tp);
-        }
 }
 
 static inline int cpu_time_before(const clockid_t which_clock,
diff --git a/kernel/sched.c b/kernel/sched.c
index e2f7f5acc807..34bcc5bc120e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8025,7 +8025,7 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 
         se->my_q = cfs_rq;
         se->load.weight = tg->shares;
-        se->load.inv_weight = div64_64(1ULL<<32, se->load.weight);
+        se->load.inv_weight = div64_u64(1ULL<<32, se->load.weight);
         se->parent = parent;
 }
 #endif
@@ -8692,7 +8692,7 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares)
                 dequeue_entity(cfs_rq, se, 0);
 
         se->load.weight = shares;
-        se->load.inv_weight = div64_64((1ULL<<32), shares);
+        se->load.inv_weight = div64_u64((1ULL<<32), shares);
 
         if (on_rq)
                 enqueue_entity(cfs_rq, se, 0);
@@ -8787,7 +8787,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
         if (runtime == RUNTIME_INF)
                 return 1ULL << 16;
 
-        return div64_64(runtime << 16, period);
+        return div64_u64(runtime << 16, period);
 }
 
 #ifdef CONFIG_CGROUP_SCHED
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 8a9498e7c831..6b4a12558e88 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -357,8 +357,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
                 avg_per_cpu = p->se.sum_exec_runtime;
                 if (p->se.nr_migrations) {
-                        avg_per_cpu = div64_64(avg_per_cpu,
-                                               p->se.nr_migrations);
+                        avg_per_cpu = div64_u64(avg_per_cpu,
+                                                p->se.nr_migrations);
                 } else {
                         avg_per_cpu = -1LL;
                 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3c44956ee7e2..36e061740047 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -589,16 +589,20 @@ static void takeover_tasklets(unsigned int cpu)
         local_irq_disable();
 
         /* Find end, append list for that CPU. */
-        *__get_cpu_var(tasklet_vec).tail = per_cpu(tasklet_vec, cpu).head;
-        __get_cpu_var(tasklet_vec).tail = per_cpu(tasklet_vec, cpu).tail;
-        per_cpu(tasklet_vec, cpu).head = NULL;
-        per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head;
+        if (&per_cpu(tasklet_vec, cpu).head != per_cpu(tasklet_vec, cpu).tail) {
+                *(__get_cpu_var(tasklet_vec).tail) = per_cpu(tasklet_vec, cpu).head;
+                __get_cpu_var(tasklet_vec).tail = per_cpu(tasklet_vec, cpu).tail;
+                per_cpu(tasklet_vec, cpu).head = NULL;
+                per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head;
+        }
         raise_softirq_irqoff(TASKLET_SOFTIRQ);
 
-        *__get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).head;
-        __get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).tail;
-        per_cpu(tasklet_hi_vec, cpu).head = NULL;
-        per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head;
+        if (&per_cpu(tasklet_hi_vec, cpu).head != per_cpu(tasklet_hi_vec, cpu).tail) {
+                *__get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).head;
+                __get_cpu_var(tasklet_hi_vec).tail = per_cpu(tasklet_hi_vec, cpu).tail;
+                per_cpu(tasklet_hi_vec, cpu).head = NULL;
+                per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head;
+        }
         raise_softirq_irqoff(HI_SOFTIRQ);
 
         local_irq_enable();
diff --git a/kernel/time.c b/kernel/time.c
index 86729042e4cd..cbe0d5a222ff 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -36,6 +36,7 @@
 #include <linux/security.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/math64.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -391,13 +392,17 @@ EXPORT_SYMBOL(set_normalized_timespec);
 struct timespec ns_to_timespec(const s64 nsec)
 {
         struct timespec ts;
+        s32 rem;
 
         if (!nsec)
                 return (struct timespec) {0, 0};
 
-        ts.tv_sec = div_long_long_rem_signed(nsec, NSEC_PER_SEC, &ts.tv_nsec);
-        if (unlikely(nsec < 0))
-                set_normalized_timespec(&ts, ts.tv_sec, ts.tv_nsec);
+        ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
+        if (unlikely(rem < 0)) {
+                ts.tv_sec--;
+                rem += NSEC_PER_SEC;
+        }
+        ts.tv_nsec = rem;
 
         return ts;
 }
@@ -527,8 +532,10 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
          * Convert jiffies to nanoseconds and separate with
          * one divide.
          */
-        u64 nsec = (u64)jiffies * TICK_NSEC;
-        value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &value->tv_nsec);
+        u32 rem;
+        value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC,
+                                    NSEC_PER_SEC, &rem);
+        value->tv_nsec = rem;
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
@@ -566,12 +573,11 @@ void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value)
          * Convert jiffies to nanoseconds and separate with
          * one divide.
          */
-        u64 nsec = (u64)jiffies * TICK_NSEC;
-        long tv_usec;
+        u32 rem;
 
-        value->tv_sec = div_long_long_rem(nsec, NSEC_PER_SEC, &tv_usec);
-        tv_usec /= NSEC_PER_USEC;
-        value->tv_usec = tv_usec;
+        value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC,
+                                    NSEC_PER_SEC, &rem);
+        value->tv_usec = rem / NSEC_PER_USEC;
 }
 EXPORT_SYMBOL(jiffies_to_timeval);
 
@@ -587,9 +593,7 @@ clock_t jiffies_to_clock_t(long x)
         return x / (HZ / USER_HZ);
 # endif
 #else
-        u64 tmp = (u64)x * TICK_NSEC;
-        do_div(tmp, (NSEC_PER_SEC / USER_HZ));
-        return (long)tmp;
+        return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ);
 #endif
 }
 EXPORT_SYMBOL(jiffies_to_clock_t);
@@ -601,16 +605,12 @@ unsigned long clock_t_to_jiffies(unsigned long x)
                 return ~0UL;
         return x * (HZ / USER_HZ);
 #else
-        u64 jif;
-
         /* Don't worry about loss of precision here .. */
         if (x >= ~0UL / HZ * USER_HZ)
                 return ~0UL;
 
         /* .. but do try to contain it here */
-        jif = x * (u64) HZ;
-        do_div(jif, USER_HZ);
-        return jif;
+        return div_u64((u64)x * HZ, USER_HZ);
 #endif
 }
 EXPORT_SYMBOL(clock_t_to_jiffies);
@@ -619,10 +619,9 @@ u64 jiffies_64_to_clock_t(u64 x)
 {
 #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
 # if HZ < USER_HZ
-        x *= USER_HZ;
-        do_div(x, HZ);
+        x = div_u64(x * USER_HZ, HZ);
 # elif HZ > USER_HZ
-        do_div(x, HZ / USER_HZ);
+        x = div_u64(x, HZ / USER_HZ);
 # else
         /* Nothing to do */
 # endif
@@ -632,8 +631,7 @@ u64 jiffies_64_to_clock_t(u64 x)
          * but even this doesn't overflow in hundreds of years
          * in 64 bits, so..
          */
-        x *= TICK_NSEC;
-        do_div(x, (NSEC_PER_SEC / USER_HZ));
+        x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ));
 #endif
         return x;
 }
@@ -642,21 +640,17 @@ EXPORT_SYMBOL(jiffies_64_to_clock_t);
 u64 nsec_to_clock_t(u64 x)
 {
 #if (NSEC_PER_SEC % USER_HZ) == 0
-        do_div(x, (NSEC_PER_SEC / USER_HZ));
+        return div_u64(x, NSEC_PER_SEC / USER_HZ);
 #elif (USER_HZ % 512) == 0
-        x *= USER_HZ/512;
-        do_div(x, (NSEC_PER_SEC / 512));
+        return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512);
 #else
         /*
          * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
          * overflow after 64.99 years.
          * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
          */
-        x *= 9;
-        do_div(x, (unsigned long)((9ull * NSEC_PER_SEC + (USER_HZ/2)) /
-                                  USER_HZ));
+        return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ);
 #endif
-        return x;
 }
 
 #if (BITS_PER_LONG < 64)
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5fd9b9469770..5125ddd8196b 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -15,7 +15,8 @@
 #include <linux/jiffies.h>
 #include <linux/hrtimer.h>
 #include <linux/capability.h>
-#include <asm/div64.h>
+#include <linux/math64.h>
+#include <linux/clocksource.h>
 #include <asm/timex.h>
 
 /*
@@ -23,11 +24,14 @@
  */
 unsigned long tick_usec = TICK_USEC;            /* USER_HZ period (usec) */
 unsigned long tick_nsec;                        /* ACTHZ period (nsec) */
-static u64 tick_length, tick_length_base;
+u64 tick_length;
+static u64 tick_length_base;
+
+static struct hrtimer leap_timer;
 
 #define MAX_TICKADJ             500             /* microsecs */
 #define MAX_TICKADJ_SCALED      (((u64)(MAX_TICKADJ * NSEC_PER_USEC) << \
-                                  TICK_LENGTH_SHIFT) / NTP_INTERVAL_FREQ)
+                                  NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
 
 /*
  * phase-lock loop variables
@@ -35,11 +39,12 @@ static u64 tick_length, tick_length_base;
 /* TIME_ERROR prevents overwriting the CMOS clock */
 static int time_state = TIME_OK;        /* clock synchronization status */
 int time_status = STA_UNSYNC;           /* clock status bits            */
-static s64 time_offset;         /* time adjustment (ns)         */
+static long time_tai;                   /* TAI offset (s)               */
+static s64 time_offset;                 /* time adjustment (ns)         */
 static long time_constant = 2;          /* pll time constant            */
 long time_maxerror = NTP_PHASE_LIMIT;   /* maximum error (us)           */
 long time_esterror = NTP_PHASE_LIMIT;   /* estimated error (us)         */
-long time_freq;                         /* frequency offset (scaled ppm)*/
+static s64 time_freq;                   /* frequency offset (scaled ns/s)*/
 static long time_reftime;               /* time at last adjustment (s)  */
 long time_adjust;
 static long ntp_tick_adj;
@@ -47,16 +52,56 @@ static long ntp_tick_adj;
 static void ntp_update_frequency(void)
 {
         u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
-                                << TICK_LENGTH_SHIFT;
-        second_length += (s64)ntp_tick_adj << TICK_LENGTH_SHIFT;
-        second_length += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
+                                << NTP_SCALE_SHIFT;
+        second_length += (s64)ntp_tick_adj << NTP_SCALE_SHIFT;
+        second_length += time_freq;
 
         tick_length_base = second_length;
 
-        do_div(second_length, HZ);
-        tick_nsec = second_length >> TICK_LENGTH_SHIFT;
+        tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
+        tick_length_base = div_u64(tick_length_base, NTP_INTERVAL_FREQ);
+}
+
+static void ntp_update_offset(long offset)
+{
+        long mtemp;
+        s64 freq_adj;
+
+        if (!(time_status & STA_PLL))
+                return;
 
-        do_div(tick_length_base, NTP_INTERVAL_FREQ);
+        if (!(time_status & STA_NANO))
+                offset *= NSEC_PER_USEC;
+
+        /*
+         * Scale the phase adjustment and
+         * clamp to the operating range.
+         */
+        offset = min(offset, MAXPHASE);
+        offset = max(offset, -MAXPHASE);
+
+        /*
+         * Select how the frequency is to be controlled
+         * and in which mode (PLL or FLL).
+         */
+        if (time_status & STA_FREQHOLD || time_reftime == 0)
+                time_reftime = xtime.tv_sec;
+        mtemp = xtime.tv_sec - time_reftime;
+        time_reftime = xtime.tv_sec;
+
+        freq_adj = (s64)offset * mtemp;
+        freq_adj <<= NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant);
+        time_status &= ~STA_MODE;
+        if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) {
+                freq_adj += div_s64((s64)offset << (NTP_SCALE_SHIFT - SHIFT_FLL),
+                                    mtemp);
+                time_status |= STA_MODE;
+        }
+        freq_adj += time_freq;
+        freq_adj = min(freq_adj, MAXFREQ_SCALED);
+        time_freq = max(freq_adj, -MAXFREQ_SCALED);
+
+        time_offset = div_s64((s64)offset << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ);
 }
 
 /**
@@ -78,62 +123,70 @@ void ntp_clear(void)
 }
 
 /*
- * this routine handles the overflow of the microsecond field
- *
- * The tricky bits of code to handle the accurate clock support
- * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
- * They were originally developed for SUN and DEC kernels.
- * All the kudos should go to Dave for this stuff.
+ * Leap second processing. If in leap-insert state at the end of the
+ * day, the system clock is set back one second; if in leap-delete
+ * state, the system clock is set ahead one second.
  */
-void second_overflow(void)
+static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 {
-        long time_adj;
+        enum hrtimer_restart res = HRTIMER_NORESTART;
 
-        /* Bump the maxerror field */
-        time_maxerror += MAXFREQ >> SHIFT_USEC;
-        if (time_maxerror > NTP_PHASE_LIMIT) {
-                time_maxerror = NTP_PHASE_LIMIT;
-                time_status |= STA_UNSYNC;
-        }
+        write_seqlock_irq(&xtime_lock);
 
-        /*
-         * Leap second processing. If in leap-insert state at the end of the
-         * day, the system clock is set back one second; if in leap-delete
-         * state, the system clock is set ahead one second. The microtime()
-         * routine or external clock driver will insure that reported time is
-         * always monotonic. The ugly divides should be replaced.
-         */
         switch (time_state) {
         case TIME_OK:
-                if (time_status & STA_INS)
-                        time_state = TIME_INS;
-                else if (time_status & STA_DEL)
-                        time_state = TIME_DEL;
                 break;
         case TIME_INS:
-                if (xtime.tv_sec % 86400 == 0) {
-                        xtime.tv_sec--;
-                        wall_to_monotonic.tv_sec++;
-                        time_state = TIME_OOP;
-                        printk(KERN_NOTICE "Clock: inserting leap second "
-                                        "23:59:60 UTC\n");
-                }
+                xtime.tv_sec--;
+                wall_to_monotonic.tv_sec++;
+                time_state = TIME_OOP;
+                printk(KERN_NOTICE "Clock: "
+                       "inserting leap second 23:59:60 UTC\n");
+                leap_timer.expires = ktime_add_ns(leap_timer.expires,
+                                                  NSEC_PER_SEC);
+                res = HRTIMER_RESTART;
                 break;
         case TIME_DEL:
-                if ((xtime.tv_sec + 1) % 86400 == 0) {
-                        xtime.tv_sec++;
-                        wall_to_monotonic.tv_sec--;
-                        time_state = TIME_WAIT;
-                        printk(KERN_NOTICE "Clock: deleting leap second "
-                                        "23:59:59 UTC\n");
-                }
+                xtime.tv_sec++;
+                time_tai--;
+                wall_to_monotonic.tv_sec--;
+                time_state = TIME_WAIT;
+                printk(KERN_NOTICE "Clock: "
+                       "deleting leap second 23:59:59 UTC\n");
                 break;
         case TIME_OOP:
+                time_tai++;
                 time_state = TIME_WAIT;
-                break;
+                /* fall through */
         case TIME_WAIT:
                 if (!(time_status & (STA_INS | STA_DEL)))
-                time_state = TIME_OK;
+                        time_state = TIME_OK;
+                break;
+        }
+        update_vsyscall(&xtime, clock);
+
+        write_sequnlock_irq(&xtime_lock);
+
+        return res;
+}
+
+/*
+ * this routine handles the overflow of the microsecond field
+ *
+ * The tricky bits of code to handle the accurate clock support
+ * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
+ * They were originally developed for SUN and DEC kernels.
+ * All the kudos should go to Dave for this stuff.
+ */
+void second_overflow(void)
+{
+        s64 time_adj;
+
+        /* Bump the maxerror field */
+        time_maxerror += MAXFREQ / NSEC_PER_USEC;
+        if (time_maxerror > NTP_PHASE_LIMIT) {
+                time_maxerror = NTP_PHASE_LIMIT;
+                time_status |= STA_UNSYNC;
         }
 
         /*
@@ -143,7 +196,7 @@ void second_overflow(void)
         tick_length = tick_length_base;
         time_adj = shift_right(time_offset, SHIFT_PLL + time_constant);
         time_offset -= time_adj;
-        tick_length += (s64)time_adj << (TICK_LENGTH_SHIFT - SHIFT_UPDATE);
+        tick_length += time_adj;
 
         if (unlikely(time_adjust)) {
                 if (time_adjust > MAX_TICKADJ) {
@@ -154,25 +207,12 @@ void second_overflow(void)
                         tick_length -= MAX_TICKADJ_SCALED;
                 } else {
                         tick_length += (s64)(time_adjust * NSEC_PER_USEC /
-                                        NTP_INTERVAL_FREQ) << TICK_LENGTH_SHIFT;
+                                        NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT;
                         time_adjust = 0;
                 }
         }
 }
 
-/*
- * Return how long ticks are at the moment, that is, how much time
- * update_wall_time_one_tick will add to xtime next time we call it
- * (assuming no calls to do_adjtimex in the meantime).
- * The return value is in fixed-point nanoseconds shifted by the
- * specified number of bits to the right of the binary point.
- * This function has no side-effects.
- */
-u64 current_tick_length(void)
-{
-        return tick_length;
-}
-
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
 
 /* Disable the cmos update - used by virtualization and embedded */
@@ -236,8 +276,8 @@ static inline void notify_cmos_timer(void) { }
  */
 int do_adjtimex(struct timex *txc)
 {
-        long mtemp, save_adjust, rem;
-        s64 freq_adj, temp64;
+        struct timespec ts;
+        long save_adjust, sec;
         int result;
 
         /* In order to modify anything, you gotta be super-user! */
@@ -247,147 +287,132 @@ int do_adjtimex(struct timex *txc)
         /* Now we validate the data before disabling interrupts */
 
         if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) {
-          /* singleshot must not be used with any other mode bits */
-                if (txc->modes != ADJ_OFFSET_SINGLESHOT &&
-                                        txc->modes != ADJ_OFFSET_SS_READ)
+                /* singleshot must not be used with any other mode bits */
+                if (txc->modes & ~ADJ_OFFSET_SS_READ)
                         return -EINVAL;
         }
 
-        if (txc->modes != ADJ_OFFSET_SINGLESHOT && (txc->modes & ADJ_OFFSET))
-          /* adjustment Offset limited to +- .512 seconds */
-                if (txc->offset <= - MAXPHASE || txc->offset >= MAXPHASE )
-                        return -EINVAL;
-
         /* if the quartz is off by more than 10% something is VERY wrong ! */
         if (txc->modes & ADJ_TICK)
                 if (txc->tick <  900000/USER_HZ ||
                     txc->tick > 1100000/USER_HZ)
                         return -EINVAL;
 
+        if (time_state != TIME_OK && txc->modes & ADJ_STATUS)
+                hrtimer_cancel(&leap_timer);
+        getnstimeofday(&ts);
+
         write_seqlock_irq(&xtime_lock);
-        result = time_state;    /* mostly `TIME_OK' */
 
         /* Save for later - semantics of adjtime is to return old value */
         save_adjust = time_adjust;
 
-#if 0   /* STA_CLOCKERR is never set yet */
-        time_status &= ~STA_CLOCKERR;           /* reset STA_CLOCKERR */
-#endif
         /* If there are input parameters, then process them */
-        if (txc->modes)
-        {
-            if (txc->modes & ADJ_STATUS)        /* only set allowed bits */
-                time_status =  (txc->status & ~STA_RONLY) |
-                              (time_status & STA_RONLY);
-
-            if (txc->modes & ADJ_FREQUENCY) {   /* p. 22 */
-                if (txc->freq > MAXFREQ || txc->freq < -MAXFREQ) {
-                    result = -EINVAL;
-                    goto leave;
-                }
-                time_freq = ((s64)txc->freq * NSEC_PER_USEC)
-                                >> (SHIFT_USEC - SHIFT_NSEC);
-            }
-
-            if (txc->modes & ADJ_MAXERROR) {
-                if (txc->maxerror < 0 || txc->maxerror >= NTP_PHASE_LIMIT) {
-                    result = -EINVAL;
-                    goto leave;
+        if (txc->modes) {
+                if (txc->modes & ADJ_STATUS) {
+                        if ((time_status & STA_PLL) &&
+                            !(txc->status & STA_PLL)) {
+                                time_state = TIME_OK;
+                                time_status = STA_UNSYNC;
+                        }
+                        /* only set allowed bits */
+                        time_status &= STA_RONLY;
+                        time_status |= txc->status & ~STA_RONLY;
+
+                        switch (time_state) {
+                        case TIME_OK:
+                        start_timer:
+                                sec = ts.tv_sec;
+                                if (time_status & STA_INS) {
+                                        time_state = TIME_INS;
+                                        sec += 86400 - sec % 86400;
+                                        hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS);
+                                } else if (time_status & STA_DEL) {
+                                        time_state = TIME_DEL;
+                                        sec += 86400 - (sec + 1) % 86400;
+                                        hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS);
+                                }
+                                break;
+                        case TIME_INS:
+                        case TIME_DEL:
+                                time_state = TIME_OK;
+                                goto start_timer;
+                                break;
+                        case TIME_WAIT:
+                                if (!(time_status & (STA_INS | STA_DEL)))
+                                        time_state = TIME_OK;
+                                break;
+                        case TIME_OOP:
+                                hrtimer_restart(&leap_timer);
+                                break;
+                        }
                 }
-                time_maxerror = txc->maxerror;
-            }
 
-            if (txc->modes & ADJ_ESTERROR) {
-                if (txc->esterror < 0 || txc->esterror >= NTP_PHASE_LIMIT) {
-                    result = -EINVAL;
-                    goto leave;
+                if (txc->modes & ADJ_NANO)
+                        time_status |= STA_NANO;
+                if (txc->modes & ADJ_MICRO)
+                        time_status &= ~STA_NANO;
+
+                if (txc->modes & ADJ_FREQUENCY) {
+                        time_freq = (s64)txc->freq * PPM_SCALE;
+                        time_freq = min(time_freq, MAXFREQ_SCALED);
+                        time_freq = max(time_freq, -MAXFREQ_SCALED);
                 }
-                time_esterror = txc->esterror;
-            }
 
-            if (txc->modes & ADJ_TIMECONST) {   /* p. 24 */
-                if (txc->constant < 0) {        /* NTP v4 uses values > 6 */
-                    result = -EINVAL;
-                    goto leave;
+                if (txc->modes & ADJ_MAXERROR)
+                        time_maxerror = txc->maxerror;
+                if (txc->modes & ADJ_ESTERROR)
+                        time_esterror = txc->esterror;
+
+                if (txc->modes & ADJ_TIMECONST) {
+                        time_constant = txc->constant;
+                        if (!(time_status & STA_NANO))
+                                time_constant += 4;
+                        time_constant = min(time_constant, (long)MAXTC);
+                        time_constant = max(time_constant, 0l);
                 }
-                time_constant = min(txc->constant + 4, (long)MAXTC);
-            }
 
-            if (txc->modes & ADJ_OFFSET) {      /* values checked earlier */
-                if (txc->modes == ADJ_OFFSET_SINGLESHOT) {
-                    /* adjtime() is independent from ntp_adjtime() */
-                    time_adjust = txc->offset;
+                if (txc->modes & ADJ_TAI && txc->constant > 0)
+                        time_tai = txc->constant;
+
+                if (txc->modes & ADJ_OFFSET) {
+                        if (txc->modes == ADJ_OFFSET_SINGLESHOT)
+                                /* adjtime() is independent from ntp_adjtime() */
+                                time_adjust = txc->offset;
+                        else
+                                ntp_update_offset(txc->offset);
                 }
-                else if (time_status & STA_PLL) {
-                    time_offset = txc->offset * NSEC_PER_USEC;
-
-                    /*
-                     * Scale the phase adjustment and
-                     * clamp to the operating range.
-                     */
-                    time_offset = min(time_offset, (s64)MAXPHASE * NSEC_PER_USEC);
-                    time_offset = max(time_offset, (s64)-MAXPHASE * NSEC_PER_USEC);
-
-                    /*
-                     * Select whether the frequency is to be controlled
-                     * and in which mode (PLL or FLL). Clamp to the operating
-                     * range. Ugly multiply/divide should be replaced someday.
-                     */
-
-                    if (time_status & STA_FREQHOLD || time_reftime == 0)
-                        time_reftime = xtime.tv_sec;
-                    mtemp = xtime.tv_sec - time_reftime;
-                    time_reftime = xtime.tv_sec;
-
-                    freq_adj = time_offset * mtemp;
-                    freq_adj = shift_right(freq_adj, time_constant * 2 +
-                                           (SHIFT_PLL + 2) * 2 - SHIFT_NSEC);
-                    if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) {
-                        u64 utemp64;
-                        temp64 = time_offset << (SHIFT_NSEC - SHIFT_FLL);
-                        if (time_offset < 0) {
-                            utemp64 = -temp64;
-                            do_div(utemp64, mtemp);
-                            freq_adj -= utemp64;
-                        } else {
-                            utemp64 = temp64;
-                            do_div(utemp64, mtemp);
-                            freq_adj += utemp64;
-                        }
-                    }
-                    freq_adj += time_freq;
-                    freq_adj = min(freq_adj, (s64)MAXFREQ_NSEC);
-                    time_freq = max(freq_adj, (s64)-MAXFREQ_NSEC);
-                    time_offset = div_long_long_rem_signed(time_offset,
-                                                           NTP_INTERVAL_FREQ,
-                                                           &rem);
-                    time_offset <<= SHIFT_UPDATE;
-                } /* STA_PLL */
-            } /* txc->modes & ADJ_OFFSET */
-            if (txc->modes & ADJ_TICK)
-                tick_usec = txc->tick;
-
-            if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET))
-                    ntp_update_frequency();
-        } /* txc->modes */
-leave:  if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
+                if (txc->modes & ADJ_TICK)
+                        tick_usec = txc->tick;
+
+                if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET))
+                        ntp_update_frequency();
+        }
+
+        result = time_state;    /* mostly `TIME_OK' */
+        if (time_status & (STA_UNSYNC|STA_CLOCKERR))
                 result = TIME_ERROR;
 
         if ((txc->modes == ADJ_OFFSET_SINGLESHOT) ||
-                        (txc->modes == ADJ_OFFSET_SS_READ))
+            (txc->modes == ADJ_OFFSET_SS_READ))
                 txc->offset = save_adjust;
-        else
-                txc->offset = ((long)shift_right(time_offset, SHIFT_UPDATE)) *
-                                NTP_INTERVAL_FREQ / 1000;
-        txc->freq          = (time_freq / NSEC_PER_USEC) <<
-                                (SHIFT_USEC - SHIFT_NSEC);
+        else {
+                txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
+                                          NTP_SCALE_SHIFT);
+                if (!(time_status & STA_NANO))
+                        txc->offset /= NSEC_PER_USEC;
+        }
+        txc->freq          = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) *
+                                         (s64)PPM_SCALE_INV,
+                                         NTP_SCALE_SHIFT);
         txc->maxerror      = time_maxerror;
         txc->esterror      = time_esterror;
         txc->status        = time_status;
         txc->constant      = time_constant;
         txc->precision     = 1;
-        txc->tolerance     = MAXFREQ;
+        txc->tolerance     = MAXFREQ_SCALED / PPM_SCALE;
         txc->tick          = tick_usec;
+        txc->tai           = time_tai;
 
         /* PPS is not implemented, so these are zero */
         txc->ppsfreq       = 0;
@@ -399,9 +424,15 @@ leave:	if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
         txc->errcnt        = 0;
         txc->stbcnt        = 0;
         write_sequnlock_irq(&xtime_lock);
-        do_gettimeofday(&txc->time);
+
+        txc->time.tv_sec = ts.tv_sec;
+        txc->time.tv_usec = ts.tv_nsec;
+        if (!(time_status & STA_NANO))
+                txc->time.tv_usec /= NSEC_PER_USEC;
+
         notify_cmos_timer();
-        return(result);
+
+        return result;
 }
 
 static int __init ntp_tick_adj_setup(char *str)
@@ -411,3 +442,10 @@ static int __init ntp_tick_adj_setup(char *str)
 }
 
 __setup("ntp_tick_adj=", ntp_tick_adj_setup);
+
+void __init ntp_init(void)
+{
+        ntp_clear();
+        hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+        leap_timer.function = ntp_leap_second;
+}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2d6087c7cf98..e91c29f961c9 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -53,7 +53,7 @@ void update_xtime_cache(u64 nsec)
         timespec_add_ns(&xtime_cache, nsec);
 }
 
-static struct clocksource *clock; /* pointer to current clocksource */
+struct clocksource *clock;
 
 
 #ifdef CONFIG_GENERIC_TIME
@@ -246,7 +246,7 @@ void __init timekeeping_init(void)
 
         write_seqlock_irqsave(&xtime_lock, flags);
 
-        ntp_clear();
+        ntp_init();
 
         clock = clocksource_get_next();
         clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
@@ -371,7 +371,7 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval,
          * here.  This is tuned so that an error of about 1 msec is adjusted
          * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks).
          */
-        error2 = clock->error >> (TICK_LENGTH_SHIFT + 22 - 2 * SHIFT_HZ);
+        error2 = clock->error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
         error2 = abs(error2);
         for (look_ahead = 0; error2 > 0; look_ahead++)
                 error2 >>= 2;
@@ -380,8 +380,7 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval,
          * Now calculate the error in (1 << look_ahead) ticks, but first
          * remove the single look ahead already included in the error.
          */
-        tick_error = current_tick_length() >>
-                (TICK_LENGTH_SHIFT - clock->shift + 1);
+        tick_error = tick_length >> (NTP_SCALE_SHIFT - clock->shift + 1);
         tick_error -= clock->xtime_interval >> 1;
         error = ((error - tick_error) >> look_ahead) + tick_error;
 
@@ -412,7 +411,7 @@ static void clocksource_adjust(s64 offset)
         s64 error, interval = clock->cycle_interval;
         int adj;
 
-        error = clock->error >> (TICK_LENGTH_SHIFT - clock->shift - 1);
+        error = clock->error >> (NTP_SCALE_SHIFT - clock->shift - 1);
         if (error > interval) {
                 error >>= 2;
                 if (likely(error <= interval))
@@ -434,7 +433,7 @@ static void clocksource_adjust(s64 offset)
         clock->xtime_interval += interval;
         clock->xtime_nsec -= offset;
         clock->error -= (interval - offset) <<
-                        (TICK_LENGTH_SHIFT - clock->shift);
+                        (NTP_SCALE_SHIFT - clock->shift);
 }
 
 /**
@@ -473,8 +472,8 @@ void update_wall_time(void)
                 }
 
                 /* accumulate error between NTP and clock interval */
-                clock->error += current_tick_length();
-                clock->error -= clock->xtime_interval << (TICK_LENGTH_SHIFT - clock->shift);
+                clock->error += tick_length;
+                clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift);
         }
 
         /* correct the clock when NTP error is too big */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 721093a22561..29fc39f1029c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -195,7 +195,6 @@ static void delayed_work_timer_fn(unsigned long __data)
 int queue_delayed_work(struct workqueue_struct *wq,
                         struct delayed_work *dwork, unsigned long delay)
 {
-        timer_stats_timer_set_start_info(&dwork->timer);
         if (delay == 0)
                 return queue_work(wq, &dwork->work);
 
@@ -219,11 +218,12 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
         struct timer_list *timer = &dwork->timer;
         struct work_struct *work = &dwork->work;
 
-        timer_stats_timer_set_start_info(&dwork->timer);
         if (!test_and_set_bit(WORK_STRUCT_PENDING, work_data_bits(work))) {
                 BUG_ON(timer_pending(timer));
                 BUG_ON(!list_empty(&work->entry));
 
+                timer_stats_timer_set_start_info(&dwork->timer);
+
                 /* This stores cwq for the moment, for the timer_fn */
                 set_wq_data(work, wq_per_cpu(wq, raw_smp_processor_id()));
                 timer->expires = jiffies + delay;
@@ -564,7 +564,6 @@ EXPORT_SYMBOL(schedule_work);
 int schedule_delayed_work(struct delayed_work *dwork,
                                         unsigned long delay)
 {
-        timer_stats_timer_set_start_info(&dwork->timer);
         return queue_delayed_work(keventd_wq, dwork, delay);
 }
 EXPORT_SYMBOL(schedule_delayed_work);
@@ -581,7 +580,6 @@ EXPORT_SYMBOL(schedule_delayed_work);
 int schedule_delayed_work_on(int cpu,
                         struct delayed_work *dwork, unsigned long delay)
 {
-        timer_stats_timer_set_start_info(&dwork->timer);
         return queue_delayed_work_on(cpu, keventd_wq, dwork, delay);
 }
 EXPORT_SYMBOL(schedule_delayed_work_on);