[PATCH] time: x86_64: convert x86_64 to use GENERIC_TIME

This patch converts x86_64 to use the GENERIC_TIME infrastructure and adds
clocksource structures for both TSC and HPET (ACPI PM is shared w/ i386).

[akpm@osdl.org: fix printk timestamps]
[akpm@osdl.org: fix printk ckeanups]
[akpm@osdl.org: hpet build fix]
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <ak@muc.de>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86_64/Kconfig

@@ -24,6 +24,10 @@ config X86
 	bool
 	default y
 
+config GENERIC_TIME
+	bool
+	default y
+
 config ZONE_DMA32
 	bool
 	default y

arch/x86_64/kernel/apic.c

@@ -786,7 +786,7 @@ static void setup_APIC_timer(unsigned int clocks)
 	/* Turn off PIT interrupt if we use APIC timer as main timer.
 	   Only works with the PM timer right now
 	   TBD fix it for HPET too. */
-	if (vxtime.mode == VXTIME_PMTMR &&
+	if ((pmtmr_ioport != 0) &&
 		smp_processor_id() == boot_cpu_id &&
 		apic_runs_main_timer == 1 &&
 		!cpu_isset(boot_cpu_id, timer_interrupt_broadcast_ipi_mask)) {

arch/x86_64/kernel/hpet.c

@@ -21,12 +21,6 @@ unsigned long hpet_tick;	/* HPET clocks / interrupt */
 int hpet_use_timer;		/* Use counter of hpet for time keeping,
 				 * otherwise PIT
 				 */
-unsigned int do_gettimeoffset_hpet(void)
-{
-	/* cap counter read to one tick to avoid inconsistencies */
-	unsigned long counter = hpet_readl(HPET_COUNTER) - vxtime.last;
-	return (min(counter,hpet_tick) * vxtime.quot) >> US_SCALE;
-}
 
 #ifdef	CONFIG_HPET
 static __init int late_hpet_init(void)
@@ -451,3 +445,61 @@ static int __init nohpet_setup(char *s)
 
 __setup("nohpet", nohpet_setup);
 
+#define HPET_MASK	0xFFFFFFFF
+#define HPET_SHIFT	22
+
+/* FSEC = 10^-15 NSEC = 10^-9 */
+#define FSEC_PER_NSEC	1000000
+
+static void *hpet_ptr;
+
+static cycle_t read_hpet(void)
+{
+	return (cycle_t)readl(hpet_ptr);
+}
+
+struct clocksource clocksource_hpet = {
+	.name		= "hpet",
+	.rating		= 250,
+	.read		= read_hpet,
+	.mask		= (cycle_t)HPET_MASK,
+	.mult		= 0, /* set below */
+	.shift		= HPET_SHIFT,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int __init init_hpet_clocksource(void)
+{
+	unsigned long hpet_period;
+	void __iomem *hpet_base;
+	u64 tmp;
+
+	if (!hpet_address)
+		return -ENODEV;
+
+	/* calculate the hpet address: */
+	hpet_base = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+	hpet_ptr = hpet_base + HPET_COUNTER;
+
+	/* calculate the frequency: */
+	hpet_period = readl(hpet_base + HPET_PERIOD);
+
+	/*
+	 * hpet period is in femto seconds per cycle
+	 * so we need to convert this to ns/cyc units
+	 * aproximated by mult/2^shift
+	 *
+	 *  fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift
+	 *  fsec/cyc * 1ns/1000000fsec * 2^shift = mult
+	 *  fsec/cyc * 2^shift * 1nsec/1000000fsec = mult
+	 *  (fsec/cyc << shift)/1000000 = mult
+	 *  (hpet_period << shift)/FSEC_PER_NSEC = mult
+	 */
+	tmp = (u64)hpet_period << HPET_SHIFT;
+	do_div(tmp, FSEC_PER_NSEC);
+	clocksource_hpet.mult = (u32)tmp;
+
+	return clocksource_register(&clocksource_hpet);
+}
+
+module_init(init_hpet_clocksource);

arch/x86_64/kernel/pmtimer.c

@@ -24,15 +24,6 @@
 #include <asm/msr.h>
 #include <asm/vsyscall.h>
 
-/* The I/O port the PMTMR resides at.
- * The location is detected during setup_arch(),
- * in arch/i386/kernel/acpi/boot.c */
-u32 pmtmr_ioport __read_mostly;
-
-/* value of the Power timer at last timer interrupt */
-static u32 offset_delay;
-static u32 last_pmtmr_tick;
-
 #define ACPI_PM_MASK 0xFFFFFF /* limit it to 24 bits */
 
 static inline u32 cyc2us(u32 cycles)
@@ -48,38 +39,6 @@ static inline u32 cyc2us(u32 cycles)
 	return (cycles >> 10);
 }
 
-int pmtimer_mark_offset(void)
-{
-	static int first_run = 1;
-	unsigned long tsc;
-	u32 lost;
-
-	u32 tick = inl(pmtmr_ioport);
-	u32 delta;
-
-	delta = cyc2us((tick - last_pmtmr_tick) & ACPI_PM_MASK);
-
-	last_pmtmr_tick = tick;
-	monotonic_base += delta * NSEC_PER_USEC;
-
-	delta += offset_delay;
-
-	lost = delta / (USEC_PER_SEC / HZ);
-	offset_delay = delta % (USEC_PER_SEC / HZ);
-
-	rdtscll(tsc);
-	vxtime.last_tsc = tsc - offset_delay * (u64)cpu_khz / 1000;
-
-	/* don't calculate delay for first run,
-	   or if we've got less then a tick */
-	if (first_run || (lost < 1)) {
-		first_run = 0;
-		offset_delay = 0;
-	}
-
-	return lost - 1;
-}
-
 static unsigned pmtimer_wait_tick(void)
 {
 	u32 a, b;
@@ -101,23 +60,6 @@ void pmtimer_wait(unsigned us)
 	} while (cyc2us(b - a) < us);
 }
 
-void pmtimer_resume(void)
-{
-	last_pmtmr_tick = inl(pmtmr_ioport);
-}
-
-unsigned int do_gettimeoffset_pm(void)
-{
-	u32 now, offset, delta = 0;
-
-	offset = last_pmtmr_tick;
-	now = inl(pmtmr_ioport);
-	delta = (now - offset) & ACPI_PM_MASK;
-
-	return offset_delay + cyc2us(delta);
-}
-
-
 static int __init nopmtimer_setup(char *s)
 {
 	pmtmr_ioport = 0;

arch/x86_64/kernel/smpboot.c

@@ -982,7 +982,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	smp_cleanup_boot();
 	setup_ioapic_dest();
 	check_nmi_watchdog();
-	time_init_gtod();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

arch/x86_64/kernel/tsc.c

@@ -9,32 +9,11 @@
 
 #include <asm/timex.h>
 
-int notsc __initdata = 0;
+static int notsc __initdata = 0;
 
 unsigned int cpu_khz;		/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
 
-/*
- * do_gettimeoffset() returns microseconds since last timer interrupt was
- * triggered by hardware. A memory read of HPET is slower than a register read
- * of TSC, but much more reliable. It's also synchronized to the timer
- * interrupt. Note that do_gettimeoffset() may return more than hpet_tick, if a
- * timer interrupt has happened already, but vxtime.trigger wasn't updated yet.
- * This is not a problem, because jiffies hasn't updated either. They are bound
- * together by xtime_lock.
- */
-
-unsigned int do_gettimeoffset_tsc(void)
-{
-	unsigned long t;
-	unsigned long x;
-	t = get_cycles_sync();
-	if (t < vxtime.last_tsc)
-		t = vxtime.last_tsc; /* hack */
-	x = ((t - vxtime.last_tsc) * vxtime.tsc_quot) >> US_SCALE;
-	return x;
-}
-
 static unsigned int cyc2ns_scale __read_mostly;
 
 void set_cyc2ns_scale(unsigned long khz)
@@ -42,7 +21,7 @@ void set_cyc2ns_scale(unsigned long khz)
 	cyc2ns_scale = (NSEC_PER_MSEC << NS_SCALE) / khz;
 }
 
-unsigned long long cycles_2_ns(unsigned long long cyc)
+static unsigned long long cycles_2_ns(unsigned long long cyc)
 {
 	return (cyc * cyc2ns_scale) >> NS_SCALE;
 }
@@ -61,6 +40,12 @@ unsigned long long sched_clock(void)
 	return cycles_2_ns(a);
 }
 
+static int tsc_unstable;
+
+static inline int check_tsc_unstable(void)
+{
+	return tsc_unstable;
+}
 #ifdef CONFIG_CPU_FREQ
 
 /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
@@ -89,24 +74,6 @@ static void handle_cpufreq_delayed_get(struct work_struct *v)
 	cpufreq_delayed_issched = 0;
 }
 
-/* if we notice lost ticks, schedule a call to cpufreq_get() as it tries
- * to verify the CPU frequency the timing core thinks the CPU is running
- * at is still correct.
- */
-void cpufreq_delayed_get(void)
-{
-	static int warned;
-	if (cpufreq_init && !cpufreq_delayed_issched) {
-		cpufreq_delayed_issched = 1;
-		if (!warned) {
-			warned = 1;
-			printk(KERN_DEBUG "Losing some ticks... "
-				"checking if CPU frequency changed.\n");
-		}
-		schedule_work(&cpufreq_delayed_get_work);
-	}
-}
-
 static unsigned int  ref_freq = 0;
 static unsigned long loops_per_jiffy_ref = 0;
 
@@ -142,7 +109,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 
 		cpu_khz = cpufreq_scale(cpu_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
-			vxtime.tsc_quot = (USEC_PER_MSEC << US_SCALE) / cpu_khz;
+			mark_tsc_unstable();
 	}
 
 	set_cyc2ns_scale(cpu_khz_ref);
@@ -169,12 +136,6 @@ core_initcall(cpufreq_tsc);
 
 static int tsc_unstable = 0;
 
-void mark_tsc_unstable(void)
-{
-	tsc_unstable = 1;
-}
-EXPORT_SYMBOL_GPL(mark_tsc_unstable);
-
 /*
  * Make an educated guess if the TSC is trustworthy and synchronized
  * over all CPUs.
@@ -210,3 +171,49 @@ int __init notsc_setup(char *s)
 }
 
 __setup("notsc", notsc_setup);
+
+
+/* clock source code: */
+static cycle_t read_tsc(void)
+{
+	cycle_t ret = (cycle_t)get_cycles_sync();
+	return ret;
+}
+
+static struct clocksource clocksource_tsc = {
+	.name			= "tsc",
+	.rating			= 300,
+	.read			= read_tsc,
+	.mask			= CLOCKSOURCE_MASK(64),
+	.shift			= 22,
+	.flags			= CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_MUST_VERIFY,
+};
+
+void mark_tsc_unstable(void)
+{
+	if (!tsc_unstable) {
+		tsc_unstable = 1;
+		/* Change only the rating, when not registered */
+		if (clocksource_tsc.mult)
+			clocksource_change_rating(&clocksource_tsc, 0);
+		else
+			clocksource_tsc.rating = 0;
+	}
+}
+EXPORT_SYMBOL_GPL(mark_tsc_unstable);
+
+static int __init init_tsc_clocksource(void)
+{
+	if (!notsc) {
+		clocksource_tsc.mult = clocksource_khz2mult(cpu_khz,
+							clocksource_tsc.shift);
+		if (check_tsc_unstable())
+			clocksource_tsc.rating = 0;
+
+		return clocksource_register(&clocksource_tsc);
+	}
+	return 0;
+}
+
+module_init(init_tsc_clocksource);

drivers/char/hangcheck-timer.c

@@ -117,7 +117,7 @@ __setup("hcheck_reboot", hangcheck_parse_reboot);
 __setup("hcheck_dump_tasks", hangcheck_parse_dump_tasks);
 #endif /* not MODULE */
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_S390)
+#if defined(CONFIG_S390)
 # define HAVE_MONOTONIC
 # define TIMER_FREQ 1000000000ULL
 #elif defined(CONFIG_IA64)

include/asm-x86_64/proto.h

@@ -45,11 +45,9 @@ extern u32 pmtmr_ioport;
 #else
 #define pmtmr_ioport 0
 #endif
-extern unsigned long long monotonic_base;
 extern int sysctl_vsyscall;
 extern int nohpet;
 extern unsigned long vxtime_hz;
-extern void time_init_gtod(void);
 
 extern void early_printk(const char *fmt, ...) __attribute__((format(printf,1,2)));
 

include/asm-x86_64/timex.h

@@ -28,9 +28,6 @@ extern int read_current_timer(unsigned long *timer_value);
 #define US_SCALE        32 /* 2^32, arbitralrily chosen */
 
 extern struct vxtime_data vxtime;
-
-extern unsigned int do_gettimeoffset_hpet(void);
-extern unsigned int do_gettimeoffset_tsc(void);
+extern void mark_tsc_unstable(void);
 extern void set_cyc2ns_scale(unsigned long khz);
-extern int notsc;
 #endif