1 files changed, 80 insertions, 93 deletions

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 4892352f0e49..15facb1b9c60 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -142,13 +142,6 @@ static void __clocksource_unstable(struct clocksource *cs)
                 schedule_work(&watchdog_work);
 }
 
-static void clocksource_unstable(struct clocksource *cs, int64_t delta)
-{
-        printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n",
-               cs->name, delta);
-        __clocksource_unstable(cs);
-}
-
 /**
  * clocksource_mark_unstable - mark clocksource unstable via watchdog
  * @cs:         clocksource to be marked unstable
@@ -174,7 +167,7 @@ void clocksource_mark_unstable(struct clocksource *cs)
 static void clocksource_watchdog(unsigned long data)
 {
         struct clocksource *cs;
-        cycle_t csnow, wdnow, delta;
+        cycle_t csnow, wdnow, cslast, wdlast, delta;
         int64_t wd_nsec, cs_nsec;
         int next_cpu, reset_pending;
 
@@ -213,6 +206,8 @@ static void clocksource_watchdog(unsigned long data)
 
                 delta = clocksource_delta(csnow, cs->cs_last, cs->mask);
                 cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
+                wdlast = cs->wd_last; /* save these in case we print them */
+                cslast = cs->cs_last;
                 cs->cs_last = csnow;
                 cs->wd_last = wdnow;
 
@@ -221,7 +216,12 @@ static void clocksource_watchdog(unsigned long data)
 
                 /* Check the deviation from the watchdog clocksource. */
                 if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
-                        clocksource_unstable(cs, cs_nsec - wd_nsec);
+                        pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name);
+                        pr_warn("       '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
+                                watchdog->name, wdnow, wdlast, watchdog->mask);
+                        pr_warn("       '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
+                                cs->name, csnow, cslast, cs->mask);
+                        __clocksource_unstable(cs);
                         continue;
                 }
 
@@ -469,26 +469,25 @@ static u32 clocksource_max_adjustment(struct clocksource *cs)
  * @shift:      cycle to nanosecond divisor (power of two)
  * @maxadj:     maximum adjustment value to mult (~11%)
  * @mask:       bitmask for two's complement subtraction of non 64 bit counters
+ * @max_cyc:    maximum cycle value before potential overflow (does not include
+ *              any safety margin)
+ *
+ * NOTE: This function includes a safety margin of 50%, in other words, we
+ * return half the number of nanoseconds the hardware counter can technically
+ * cover. This is done so that we can potentially detect problems caused by
+ * delayed timers or bad hardware, which might result in time intervals that
+ * are larger then what the math used can handle without overflows.
  */
-u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
+u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc)
 {
         u64 max_nsecs, max_cycles;
 
         /*
          * Calculate the maximum number of cycles that we can pass to the
-         * cyc2ns function without overflowing a 64-bit signed result. The
-         * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj)
-         * which is equivalent to the below.
-         * max_cycles < (2^63)/(mult + maxadj)
-         * max_cycles < 2^(log2((2^63)/(mult + maxadj)))
-         * max_cycles < 2^(log2(2^63) - log2(mult + maxadj))
-         * max_cycles < 2^(63 - log2(mult + maxadj))
-         * max_cycles < 1 << (63 - log2(mult + maxadj))
-         * Please note that we add 1 to the result of the log2 to account for
-         * any rounding errors, ensure the above inequality is satisfied and
-         * no overflow will occur.
+         * cyc2ns() function without overflowing a 64-bit result.
          */
-        max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1));
+        max_cycles = ULLONG_MAX;
+        do_div(max_cycles, mult+maxadj);
 
         /*
          * The actual maximum number of cycles we can defer the clocksource is
@@ -499,27 +498,26 @@ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
         max_cycles = min(max_cycles, mask);
         max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
 
+        /* return the max_cycles value as well if requested */
+        if (max_cyc)
+                *max_cyc = max_cycles;
+
+        /* Return 50% of the actual maximum, so we can detect bad values */
+        max_nsecs >>= 1;
+
         return max_nsecs;
 }
 
 /**
- * clocksource_max_deferment - Returns max time the clocksource can be deferred
- * @cs:         Pointer to clocksource
+ * clocksource_update_max_deferment - Updates the clocksource max_idle_ns & max_cycles
+ * @cs:         Pointer to clocksource to be updated
  *
  */
-static u64 clocksource_max_deferment(struct clocksource *cs)
+static inline void clocksource_update_max_deferment(struct clocksource *cs)
 {
-        u64 max_nsecs;
-
-        max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj,
-                                          cs->mask);
-        /*
-         * To ensure that the clocksource does not wrap whilst we are idle,
-         * limit the time the clocksource can be deferred by 12.5%. Please
-         * note a margin of 12.5% is used because this can be computed with
-         * a shift, versus say 10% which would require division.
-         */
-        return max_nsecs - (max_nsecs >> 3);
+        cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
+                                                cs->maxadj, cs->mask,
+                                                &cs->max_cycles);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -648,7 +646,7 @@ static void clocksource_enqueue(struct clocksource *cs)
 }
 
 /**
- * __clocksource_updatefreq_scale - Used update clocksource with new freq
+ * __clocksource_update_freq_scale - Used update clocksource with new freq
  * @cs:         clocksource to be registered
  * @scale:      Scale factor multiplied against freq to get clocksource hz
  * @freq:       clocksource frequency (cycles per second) divided by scale
@@ -656,48 +654,64 @@ static void clocksource_enqueue(struct clocksource *cs)
  * This should only be called from the clocksource->enable() method.
  *
  * This *SHOULD NOT* be called directly! Please use the
- * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions.
+ * __clocksource_update_freq_hz() or __clocksource_update_freq_khz() helper
+ * functions.
  */
-void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
+void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
         u64 sec;
+
         /*
-         * Calc the maximum number of seconds which we can run before
-         * wrapping around. For clocksources which have a mask > 32bit
-         * we need to limit the max sleep time to have a good
-         * conversion precision. 10 minutes is still a reasonable
-         * amount. That results in a shift value of 24 for a
-         * clocksource with mask >= 40bit and f >= 4GHz. That maps to
-         * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
-         * margin as we do in clocksource_max_deferment()
+         * Default clocksources are *special* and self-define their mult/shift.
+         * But, you're not special, so you should specify a freq value.
          */
-        sec = (cs->mask - (cs->mask >> 3));
-        do_div(sec, freq);
-        do_div(sec, scale);
-        if (!sec)
-                sec = 1;
-        else if (sec > 600 && cs->mask > UINT_MAX)
-                sec = 600;
-
-        clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
-                               NSEC_PER_SEC / scale, sec * scale);
-
+        if (freq) {
+                /*
+                 * Calc the maximum number of seconds which we can run before
+                 * wrapping around. For clocksources which have a mask > 32-bit
+                 * we need to limit the max sleep time to have a good
+                 * conversion precision. 10 minutes is still a reasonable
+                 * amount. That results in a shift value of 24 for a
+                 * clocksource with mask >= 40-bit and f >= 4GHz. That maps to
+                 * ~ 0.06ppm granularity for NTP.
+                 */
+                sec = cs->mask;
+                do_div(sec, freq);
+                do_div(sec, scale);
+                if (!sec)
+                        sec = 1;
+                else if (sec > 600 && cs->mask > UINT_MAX)
+                        sec = 600;
+
+                clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
+                                       NSEC_PER_SEC / scale, sec * scale);
+        }
         /*
-         * for clocksources that have large mults, to avoid overflow.
-         * Since mult may be adjusted by ntp, add an safety extra margin
-         *
+         * Ensure clocksources that have large 'mult' values don't overflow
+         * when adjusted.
          */
         cs->maxadj = clocksource_max_adjustment(cs);
-        while ((cs->mult + cs->maxadj < cs->mult)
-                || (cs->mult - cs->maxadj > cs->mult)) {
+        while (freq && ((cs->mult + cs->maxadj < cs->mult)
+                || (cs->mult - cs->maxadj > cs->mult))) {
                 cs->mult >>= 1;
                 cs->shift--;
                 cs->maxadj = clocksource_max_adjustment(cs);
         }
 
-        cs->max_idle_ns = clocksource_max_deferment(cs);
+        /*
+         * Only warn for *special* clocksources that self-define
+         * their mult/shift values and don't specify a freq.
+         */
+        WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+                "timekeeping: Clocksource %s might overflow on 11%% adjustment\n",
+                cs->name);
+
+        clocksource_update_max_deferment(cs);
+
+        pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n",
+                        cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns);
 }
-EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
+EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale);
 
 /**
  * __clocksource_register_scale - Used to install new clocksources
@@ -714,7 +728,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 
         /* Initialize mult/shift and max_idle_ns */
-        __clocksource_updatefreq_scale(cs, scale, freq);
+        __clocksource_update_freq_scale(cs, scale, freq);
 
         /* Add clocksource to the clocksource list */
         mutex_lock(&clocksource_mutex);
@@ -726,33 +740,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 }
 EXPORT_SYMBOL_GPL(__clocksource_register_scale);
 
-
-/**
- * clocksource_register - Used to install new clocksources
- * @cs:         clocksource to be registered
- *
- * Returns -EBUSY if registration fails, zero otherwise.
- */
-int clocksource_register(struct clocksource *cs)
-{
-        /* calculate max adjustment for given mult/shift */
-        cs->maxadj = clocksource_max_adjustment(cs);
-        WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
-                "Clocksource %s might overflow on 11%% adjustment\n",
-                cs->name);
-
-        /* calculate max idle time permitted for this clocksource */
-        cs->max_idle_ns = clocksource_max_deferment(cs);
-
-        mutex_lock(&clocksource_mutex);
-        clocksource_enqueue(cs);
-        clocksource_enqueue_watchdog(cs);
-        clocksource_select();
-        mutex_unlock(&clocksource_mutex);
-        return 0;
-}
-EXPORT_SYMBOL(clocksource_register);
-
 static void __clocksource_change_rating(struct clocksource *cs, int rating)
 {
         list_del(&cs->list);