arch_timer: Move to generic sched_clock framework

Register with the generic sched_clock framework now that it
supports 64 bits. This fixes two problems with the current
sched_clock support for machines using the architected timers.
First off, we don't subtract the start value from subsequent
sched_clock calls so we can potentially start off with
sched_clock returning gigantic numbers. Second, there is no
support for suspend/resume handling so problems such as discussed
in 6a4dae5 (ARM: 7565/1: sched: stop sched_clock() during
suspend, 2012-10-23) can happen without this patch. Finally, it
allows us to move the sched_clock setup into drivers clocksource
out of the arch ports.

Cc: Christopher Covington <[e-mail]>
Cc: Catalin Marinas <[e-mail]>
Acked-by: Will Deacon <[e-mail]>
Signed-off-by: Stephen Boyd <[e-mail]>
Signed-off-by: John Stultz <[e-mail]>

arch/arm/kernel/arch_timer.c

···
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/sched_clock.h>
 
 #include <asm/delay.h>
 
···
 static unsigned long arch_timer_read_counter_long(void)
 {
 	return arch_timer_read_counter();
-}
-
-static u32 sched_clock_mult __read_mostly;
-
-static unsigned long long notrace arch_timer_sched_clock(void)
-{
-	return arch_timer_read_counter() * sched_clock_mult;
 }
 
 static struct delay_timer arch_delay_timer;
···
 		return -ENXIO;
 
 	arch_timer_delay_timer_register();
-
-	/* 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;
 }

arch/arm64/Kconfig

···
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
+	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND

arch/arm64/kernel/time.c

···
 EXPORT_SYMBOL(profile_pc);
 #endif
 
-static u64 sched_clock_mult __read_mostly;
-
-unsigned long long notrace sched_clock(void)
-{
-	return arch_timer_read_counter() * sched_clock_mult;
-}
-
 void __init time_init(void)
 {
 	u32 arch_timer_rate;
···
 	arch_timer_rate = arch_timer_get_rate();
 	if (!arch_timer_rate)
 		panic("Unable to initialise architected timer.\n");
-
-	/* Cache the sched_clock multiplier to save a divide in the hot path. */
-	sched_clock_mult = NSEC_PER_SEC / arch_timer_rate;
 
 	/* Calibrate the delay loop directly */
 	lpj_fine = arch_timer_rate / HZ;

drivers/clocksource/arm_arch_timer.c

···
 #include <linux/of_address.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/sched_clock.h>
 
 #include <asm/arch_timer.h>
 #include <asm/virt.h>
···
 		err = -ENOMEM;
 		goto out;
 	}
+
+	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
+	cyclecounter.mult = clocksource_counter.mult;
+	cyclecounter.shift = clocksource_counter.shift;
+	timecounter_init(&timecounter, &cyclecounter,
+			 arch_counter_get_cntvct());
+
+	/* 56 bits minimum, so we assume worst case rollover */
+	sched_clock_register(arch_timer_read_counter, 56, arch_timer_rate);
 
 	if (arch_timer_use_virtual) {
 		ppi = arch_timer_ppi[VIRT_PPI];