ARM: arch_timer: use full 64-bit counter for sched_clock

Only 32-bits of the arch timer were being used and wrapping was needlessly
being done in s/w. By using the full counter (56-64 bits), we don't need
to deal with wrapping and can simplify the implementation when using
arch timer.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>

arch/arm/kernel/arch_timer.c

@@ -22,9 +22,11 @@ static unsigned long arch_timer_read_counter_long(void)
 	return arch_timer_read_counter();
 }
 
-static u32 arch_timer_read_counter_u32(void)
+static u32 sched_clock_mult __read_mostly;
+
+static unsigned long long notrace arch_timer_sched_clock(void)
 {
-	return arch_timer_read_counter();
+	return arch_timer_read_counter() * sched_clock_mult;
 }
 
 static struct delay_timer arch_delay_timer;
@@ -52,10 +54,16 @@ int __init arch_timer_of_register(void)
 
 int __init arch_timer_sched_clock_init(void)
 {
-	if (arch_timer_get_rate() == 0)
+        u32 arch_timer_rate = arch_timer_get_rate();
+
+	if (arch_timer_rate == 0)
 		return -ENXIO;
 
-	setup_sched_clock(arch_timer_read_counter_u32,
-			  32, arch_timer_get_rate());
+	/* Cache the sched_clock multiplier to save a divide in the hot path. */
+	sched_clock_mult = NSEC_PER_SEC / arch_timer_rate;
+	sched_clock_func = arch_timer_sched_clock;
+	pr_info("sched_clock: ARM arch timer >56 bits at %ukHz, resolution %uns\n",
+		arch_timer_rate / 1000, sched_clock_mult);
+
 	return 0;
 }