[PATCH] clockevents: i386 drivers

Add clockevent drivers for i386: lapic (local) and PIT/HPET (global).  Update
the timer IRQ to call into the PIT/HPET driver's event handler and the
lapic-timer IRQ to call into the lapic clockevent driver.  The assignement of
timer functionality is delegated to the core framework code and replaces the
compile and runtime evalution in do_timer_interrupt_hook()

Use the clockevents broadcast support and implement the lapic_broadcast
function for ACPI.

No changes to existing functionality.

[ kdump fix from Vivek Goyal <vgoyal@in.ibm.com> ]
[ fixes based on review feedback from Arjan van de Ven <arjan@infradead.org> ]
Cleanups-from: Adrian Bunk <bunk@stusta.de>
Build-fixes-from: Andrew Morton <akpm@osdl.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

8 files changed, 717 insertions, 745 deletions

diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index c2b3b79dc436..4ae3dcf1d2f0 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -32,7 +32,6 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-y				+= sysenter.o vsyscall.o
 obj-$(CONFIG_ACPI_SRAT) 	+= srat.o
-obj-$(CONFIG_HPET_TIMER) 	+= time_hpet.o
 obj-$(CONFIG_EFI) 		+= efi.o efi_stub.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault.o
 obj-$(CONFIG_VM86)		+= vm86.o
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index b56448f214a7..e98b5c750bdf 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -25,6 +25,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
 #include <linux/cpu.h>
+#include <linux/clockchips.h>
 #include <linux/module.h>
 
 #include <asm/atomic.h>
@@ -52,28 +53,44 @@
 #endif
 
 /*
- * cpu_mask that denotes the CPUs that needs timer interrupt coming in as
- * IPIs in place of local APIC timers
- */
-static cpumask_t timer_bcast_ipi;
-
-/*
  * Knob to control our willingness to enable the local APIC.
  *
  * -1=force-disable, +1=force-enable
  */
 static int enable_local_apic __initdata = 0;
 
+/* Enable local APIC timer for highres/dyntick on UP */
+static int enable_local_apic_timer __initdata = 0;
+
 /*
  * Debug level, exported for io_apic.c
  */
 int apic_verbosity;
 
-static void apic_pm_activate(void);
+static unsigned int calibration_result;
 
+static int lapic_next_event(unsigned long delta,
+			    struct clock_event_device *evt);
+static void lapic_timer_setup(enum clock_event_mode mode,
+			      struct clock_event_device *evt);
+static void lapic_timer_broadcast(cpumask_t mask);
+static void apic_pm_activate(void);
 
-/* Using APIC to generate smp_local_timer_interrupt? */
-int using_apic_timer __read_mostly = 0;
+/*
+ * The local apic timer can be used for any function which is CPU local.
+ */
+static struct clock_event_device lapic_clockevent = {
+	.name		= "lapic",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
+			| CLOCK_EVT_FEAT_C3STOP,
+	.shift		= 32,
+	.set_mode	= lapic_timer_setup,
+	.set_next_event	= lapic_next_event,
+	.broadcast	= lapic_timer_broadcast,
+	.rating		= 100,
+	.irq		= -1,
+};
+static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase;
@@ -152,6 +169,11 @@ int lapic_get_maxlvt(void)
  */
 
 /*
+ * FIXME: Move this to i8253.h. There is no need to keep the access to
+ * the PIT scattered all around the place -tglx
+ */
+
+/*
  * The timer chip is already set up at HZ interrupts per second here,
  * but we do not accept timer interrupts yet. We only allow the BP
  * to calibrate.
@@ -209,16 +231,17 @@ void (*wait_timer_tick)(void) __devinitdata = wait_8254_wraparound;
 
 #define APIC_DIVISOR 16
 
-static void __setup_APIC_LVTT(unsigned int clocks)
+static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 {
 	unsigned int lvtt_value, tmp_value;
-	int cpu = smp_processor_id();
 
-	lvtt_value = APIC_LVT_TIMER_PERIODIC | LOCAL_TIMER_VECTOR;
+	lvtt_value = LOCAL_TIMER_VECTOR;
+	if (!oneshot)
+		lvtt_value |= APIC_LVT_TIMER_PERIODIC;
 	if (!lapic_is_integrated())
 		lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);
 
-	if (cpu_isset(cpu, timer_bcast_ipi))
+	if (!irqen)
 		lvtt_value |= APIC_LVT_MASKED;
 
 	apic_write_around(APIC_LVTT, lvtt_value);
@@ -231,31 +254,80 @@ static void __setup_APIC_LVTT(unsigned int clocks)
 				& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
 				| APIC_TDR_DIV_16);
 
-	apic_write_around(APIC_TMICT, clocks/APIC_DIVISOR);
+	if (!oneshot)
+		apic_write_around(APIC_TMICT, clocks/APIC_DIVISOR);
+}
+
+/*
+ * Program the next event, relative to now
+ */
+static int lapic_next_event(unsigned long delta,
+			    struct clock_event_device *evt)
+{
+	apic_write_around(APIC_TMICT, delta);
+	return 0;
 }
 
-static void __devinit setup_APIC_timer(unsigned int clocks)
+/*
+ * Setup the lapic timer in periodic or oneshot mode
+ */
+static void lapic_timer_setup(enum clock_event_mode mode,
+			      struct clock_event_device *evt)
 {
 	unsigned long flags;
+	unsigned int v;
 
 	local_irq_save(flags);
 
-	/*
-	 * Wait for IRQ0's slice:
-	 */
-	wait_timer_tick();
-
-	__setup_APIC_LVTT(clocks);
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+	case CLOCK_EVT_MODE_ONESHOT:
+		__setup_APIC_LVTT(calibration_result,
+				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		v = apic_read(APIC_LVTT);
+		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+		apic_write_around(APIC_LVTT, v);
+		break;
+	}
 
 	local_irq_restore(flags);
 }
 
 /*
+ * Local APIC timer broadcast function
+ */
+static void lapic_timer_broadcast(cpumask_t mask)
+{
+#ifdef CONFIG_SMP
+	send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+#endif
+}
+
+/*
+ * Setup the local APIC timer for this CPU. Copy the initilized values
+ * of the boot CPU and register the clock event in the framework.
+ */
+static void __devinit setup_APIC_timer(void)
+{
+	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+
+	memcpy(levt, &lapic_clockevent, sizeof(*levt));
+	levt->cpumask = cpumask_of_cpu(smp_processor_id());
+
+	clockevents_register_device(levt);
+}
+
+/*
  * In this function we calibrate APIC bus clocks to the external
  * timer. Unfortunately we cannot use jiffies and the timer irq
  * to calibrate, since some later bootup code depends on getting
  * the first irq? Ugh.
  *
+ * TODO: Fix this rather than saying "Ugh" -tglx
+ *
  * We want to do the calibration only once since we
  * want to have local timer irqs syncron. CPUs connected
  * by the same APIC bus have the very same bus frequency.
@@ -278,7 +350,7 @@ static int __init calibrate_APIC_clock(void)
 	 * value into the APIC clock, we just want to get the
 	 * counter running for calibration.
 	 */
-	__setup_APIC_LVTT(1000000000);
+	__setup_APIC_LVTT(1000000000, 0, 0);
 
 	/*
 	 * The timer chip counts down to zero. Let's wait
@@ -315,6 +387,17 @@ static int __init calibrate_APIC_clock(void)
 
 	result = (tt1-tt2)*APIC_DIVISOR/LOOPS;
 
+	/* Calculate the scaled math multiplication factor */
+	lapic_clockevent.mult = div_sc(tt1-tt2, TICK_NSEC * LOOPS, 32);
+	lapic_clockevent.max_delta_ns =
+		clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+	lapic_clockevent.min_delta_ns =
+		clockevent_delta2ns(0xF, &lapic_clockevent);
+
+	apic_printk(APIC_VERBOSE, "..... tt1-tt2 %ld\n", tt1 - tt2);
+	apic_printk(APIC_VERBOSE, "..... mult: %ld\n", lapic_clockevent.mult);
+	apic_printk(APIC_VERBOSE, "..... calibration result: %ld\n", result);
+
 	if (cpu_has_tsc)
 		apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
 			"%ld.%04ld MHz.\n",
@@ -329,13 +412,10 @@ static int __init calibrate_APIC_clock(void)
 	return result;
 }
 
-static unsigned int calibration_result;
-
 void __init setup_boot_APIC_clock(void)
 {
 	unsigned long flags;
 	apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n");
-	using_apic_timer = 1;
 
 	local_irq_save(flags);
 
@@ -343,97 +423,47 @@ void __init setup_boot_APIC_clock(void)
 	/*
 	 * Now set up the timer for real.
 	 */
-	setup_APIC_timer(calibration_result);
+	setup_APIC_timer();
 
 	local_irq_restore(flags);
 }
 
 void __devinit setup_secondary_APIC_clock(void)
 {
-	setup_APIC_timer(calibration_result);
-}
-
-void disable_APIC_timer(void)
-{
-	if (using_apic_timer) {
-		unsigned long v;
-
-		v = apic_read(APIC_LVTT);
-		/*
-		 * When an illegal vector value (0-15) is written to an LVT
-		 * entry and delivery mode is Fixed, the APIC may signal an
-		 * illegal vector error, with out regard to whether the mask
-		 * bit is set or whether an interrupt is actually seen on
-		 * input.
-		 *
-		 * Boot sequence might call this function when the LVTT has
-		 * '0' vector value. So make sure vector field is set to
-		 * valid value.
-		 */
-		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
-		apic_write_around(APIC_LVTT, v);
-	}
-}
-
-void enable_APIC_timer(void)
-{
-	int cpu = smp_processor_id();
-
-	if (using_apic_timer && !cpu_isset(cpu, timer_bcast_ipi)) {
-		unsigned long v;
-
-		v = apic_read(APIC_LVTT);
-		apic_write_around(APIC_LVTT, v & ~APIC_LVT_MASKED);
-	}
-}
-
-void switch_APIC_timer_to_ipi(void *cpumask)
-{
-	cpumask_t mask = *(cpumask_t *)cpumask;
-	int cpu = smp_processor_id();
-
-	if (cpu_isset(cpu, mask) &&
-	    !cpu_isset(cpu, timer_bcast_ipi)) {
-		disable_APIC_timer();
-		cpu_set(cpu, timer_bcast_ipi);
-	}
-}
-EXPORT_SYMBOL(switch_APIC_timer_to_ipi);
-
-void switch_ipi_to_APIC_timer(void *cpumask)
-{
-	cpumask_t mask = *(cpumask_t *)cpumask;
-	int cpu = smp_processor_id();
-
-	if (cpu_isset(cpu, mask) &&
-	    cpu_isset(cpu, timer_bcast_ipi)) {
-		cpu_clear(cpu, timer_bcast_ipi);
-		enable_APIC_timer();
-	}
+	setup_APIC_timer();
 }
-EXPORT_SYMBOL(switch_ipi_to_APIC_timer);
 
 /*
- * Local timer interrupt handler. It does both profiling and
- * process statistics/rescheduling.
+ * The guts of the apic timer interrupt
  */
-inline void smp_local_timer_interrupt(void)
+static void local_apic_timer_interrupt(void)
 {
-	profile_tick(CPU_PROFILING);
-#ifdef CONFIG_SMP
-	update_process_times(user_mode_vm(get_irq_regs()));
-#endif
+	int cpu = smp_processor_id();
+	struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
 
 	/*
-	 * We take the 'long' return path, and there every subsystem
-	 * grabs the apropriate locks (kernel lock/ irq lock).
+	 * Normally we should not be here till LAPIC has been
+	 * initialized but in some cases like kdump, its possible that
+	 * there is a pending LAPIC timer interrupt from previous
+	 * kernel's context and is delivered in new kernel the moment
+	 * interrupts are enabled.
 	 *
-	 * we might want to decouple profiling from the 'long path',
-	 * and do the profiling totally in assembly.
-	 *
-	 * Currently this isn't too much of an issue (performance wise),
-	 * we can take more than 100K local irqs per second on a 100 MHz P5.
+	 * Interrupts are enabled early and LAPIC is setup much later,
+	 * hence its possible that when we get here evt->event_handler
+	 * is NULL. Check for event_handler being NULL and discard
+	 * the interrupt as spurious.
 	 */
+	if (!evt->event_handler) {
+		printk(KERN_WARNING
+		       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+		/* Switch it off */
+		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+		return;
+	}
+
+	per_cpu(irq_stat, cpu).apic_timer_irqs++;
+
+	evt->event_handler(evt);
 }
 
 /*
@@ -445,15 +475,9 @@ inline void smp_local_timer_interrupt(void)
  *   interrupt as well. Thus we cannot inline the local irq ... ]
  */
 
-fastcall void smp_apic_timer_interrupt(struct pt_regs *regs)
+void fastcall smp_apic_timer_interrupt(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	int cpu = smp_processor_id();
-
-	/*
-	 * the NMI deadlock-detector uses this.
-	 */
-	per_cpu(irq_stat, cpu).apic_timer_irqs++;
 
 	/*
 	 * NOTE! We'd better ACK the irq immediately,
@@ -467,41 +491,10 @@ fastcall void smp_apic_timer_interrupt(struct pt_regs *regs)
 	 */
 	exit_idle();
 	irq_enter();
-	smp_local_timer_interrupt();
+	local_apic_timer_interrupt();
 	irq_exit();
-	set_irq_regs(old_regs);
-}
 
-#ifndef CONFIG_SMP
-static void up_apic_timer_interrupt_call(void)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * the NMI deadlock-detector uses this.
-	 */
-	per_cpu(irq_stat, cpu).apic_timer_irqs++;
-
-	smp_local_timer_interrupt();
-}
-#endif
-
-void smp_send_timer_broadcast_ipi(void)
-{
-	cpumask_t mask;
-
-	cpus_and(mask, cpu_online_map, timer_bcast_ipi);
-	if (!cpus_empty(mask)) {
-#ifdef CONFIG_SMP
-		send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
-#else
-		/*
-		 * We can directly call the apic timer interrupt handler
-		 * in UP case. Minus all irq related functions
-		 */
-		up_apic_timer_interrupt_call();
-#endif
-	}
+	set_irq_regs(old_regs);
 }
 
 int setup_profiling_timer(unsigned int multiplier)
@@ -914,6 +907,11 @@ void __devinit setup_local_APIC(void)
 			printk(KERN_INFO "No ESR for 82489DX.\n");
 	}
 
+	/* Disable the local apic timer */
+	value = apic_read(APIC_LVTT);
+	value |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+	apic_write_around(APIC_LVTT, value);
+
 	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
 }
@@ -1128,6 +1126,13 @@ static int __init parse_nolapic(char *arg)
 }
 early_param("nolapic", parse_nolapic);
 
+static int __init apic_enable_lapic_timer(char *str)
+{
+	enable_local_apic_timer = 1;
+	return 0;
+}
+early_param("lapictimer", apic_enable_lapic_timer);
+
 static int __init apic_set_verbosity(char *str)
 {
 	if (strcmp("debug", str) == 0)
@@ -1147,7 +1152,7 @@ __setup("apic=", apic_set_verbosity);
 /*
  * This interrupt should _never_ happen with our APIC/SMP architecture
  */
-fastcall void smp_spurious_interrupt(struct pt_regs *regs)
+void smp_spurious_interrupt(struct pt_regs *regs)
 {
 	unsigned long v;
 
@@ -1171,7 +1176,7 @@ fastcall void smp_spurious_interrupt(struct pt_regs *regs)
 /*
  * This interrupt should never happen with our APIC/SMP architecture
  */
-fastcall void smp_error_interrupt(struct pt_regs *regs)
+void smp_error_interrupt(struct pt_regs *regs)
 {
 	unsigned long v, v1;
 
diff --git a/arch/i386/kernel/hpet.c b/arch/i386/kernel/hpet.c
index 7d2739fff3a3..e1006b7acc9e 100644
--- a/arch/i386/kernel/hpet.c
+++ b/arch/i386/kernel/hpet.c
@@ -1,4 +1,5 @@
 #include <linux/clocksource.h>
+#include <linux/clockchips.h>
 #include <linux/errno.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
@@ -6,17 +7,278 @@
 #include <asm/hpet.h>
 #include <asm/io.h>
 
+extern struct clock_event_device *global_clock_event;
+
 #define HPET_MASK	CLOCKSOURCE_MASK(32)
 #define HPET_SHIFT	22
 
 /* FSEC = 10^-15 NSEC = 10^-9 */
 #define FSEC_PER_NSEC	1000000
 
-static void __iomem *hpet_ptr;
+/*
+ * HPET address is set in acpi/boot.c, when an ACPI entry exists
+ */
+unsigned long hpet_address;
+static void __iomem * hpet_virt_address;
+
+static inline unsigned long hpet_readl(unsigned long a)
+{
+	return readl(hpet_virt_address + a);
+}
+
+static inline void hpet_writel(unsigned long d, unsigned long a)
+{
+	writel(d, hpet_virt_address + a);
+}
+
+/*
+ * HPET command line enable / disable
+ */
+static int boot_hpet_disable;
+
+static int __init hpet_setup(char* str)
+{
+	if (str) {
+		if (!strncmp("disable", str, 7))
+			boot_hpet_disable = 1;
+	}
+	return 1;
+}
+__setup("hpet=", hpet_setup);
+
+static inline int is_hpet_capable(void)
+{
+	return (!boot_hpet_disable && hpet_address);
+}
+
+/*
+ * HPET timer interrupt enable / disable
+ */
+static int hpet_legacy_int_enabled;
+
+/**
+ * is_hpet_enabled - check whether the hpet timer interrupt is enabled
+ */
+int is_hpet_enabled(void)
+{
+	return is_hpet_capable() && hpet_legacy_int_enabled;
+}
+
+/*
+ * When the hpet driver (/dev/hpet) is enabled, we need to reserve
+ * timer 0 and timer 1 in case of RTC emulation.
+ */
+#ifdef CONFIG_HPET
+static void hpet_reserve_platform_timers(unsigned long id)
+{
+	struct hpet __iomem *hpet = hpet_virt_address;
+	struct hpet_timer __iomem *timer = &hpet->hpet_timers[2];
+	unsigned int nrtimers, i;
+	struct hpet_data hd;
+
+	nrtimers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
+
+	memset(&hd, 0, sizeof (hd));
+	hd.hd_phys_address = hpet_address;
+	hd.hd_address = hpet_virt_address;
+	hd.hd_nirqs = nrtimers;
+	hd.hd_flags = HPET_DATA_PLATFORM;
+	hpet_reserve_timer(&hd, 0);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+	hpet_reserve_timer(&hd, 1);
+#endif
+
+	hd.hd_irq[0] = HPET_LEGACY_8254;
+	hd.hd_irq[1] = HPET_LEGACY_RTC;
+
+	for (i = 2; i < nrtimers; timer++, i++)
+		hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >>
+			Tn_INT_ROUTE_CNF_SHIFT;
+
+	hpet_alloc(&hd);
+
+}
+#else
+static void hpet_reserve_platform_timers(unsigned long id) { }
+#endif
+
+/*
+ * Common hpet info
+ */
+static unsigned long hpet_period;
+
+static void hpet_set_mode(enum clock_event_mode mode,
+			  struct clock_event_device *evt);
+static int hpet_next_event(unsigned long delta,
+			   struct clock_event_device *evt);
+
+/*
+ * The hpet clock event device
+ */
+static struct clock_event_device hpet_clockevent = {
+	.name		= "hpet",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode	= hpet_set_mode,
+	.set_next_event = hpet_next_event,
+	.shift		= 32,
+	.irq		= 0,
+};
+
+static void hpet_start_counter(void)
+{
+	unsigned long cfg = hpet_readl(HPET_CFG);
+
+	cfg &= ~HPET_CFG_ENABLE;
+	hpet_writel(cfg, HPET_CFG);
+	hpet_writel(0, HPET_COUNTER);
+	hpet_writel(0, HPET_COUNTER + 4);
+	cfg |= HPET_CFG_ENABLE;
+	hpet_writel(cfg, HPET_CFG);
+}
+
+static void hpet_enable_int(void)
+{
+	unsigned long cfg = hpet_readl(HPET_CFG);
+
+	cfg |= HPET_CFG_LEGACY;
+	hpet_writel(cfg, HPET_CFG);
+	hpet_legacy_int_enabled = 1;
+}
+
+static void hpet_set_mode(enum clock_event_mode mode,
+			  struct clock_event_device *evt)
+{
+	unsigned long cfg, cmp, now;
+	uint64_t delta;
+
+	switch(mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * hpet_clockevent.mult;
+		delta >>= hpet_clockevent.shift;
+		now = hpet_readl(HPET_COUNTER);
+		cmp = now + (unsigned long) delta;
+		cfg = hpet_readl(HPET_T0_CFG);
+		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
+		       HPET_TN_SETVAL | HPET_TN_32BIT;
+		hpet_writel(cfg, HPET_T0_CFG);
+		/*
+		 * The first write after writing TN_SETVAL to the
+		 * config register sets the counter value, the second
+		 * write sets the period.
+		 */
+		hpet_writel(cmp, HPET_T0_CMP);
+		udelay(1);
+		hpet_writel((unsigned long) delta, HPET_T0_CMP);
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+		cfg = hpet_readl(HPET_T0_CFG);
+		cfg &= ~HPET_TN_PERIODIC;
+		cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+		hpet_writel(cfg, HPET_T0_CFG);
+		break;
+
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		cfg = hpet_readl(HPET_T0_CFG);
+		cfg &= ~HPET_TN_ENABLE;
+		hpet_writel(cfg, HPET_T0_CFG);
+		break;
+	}
+}
+
+static int hpet_next_event(unsigned long delta,
+			   struct clock_event_device *evt)
+{
+	unsigned long cnt;
+
+	cnt = hpet_readl(HPET_COUNTER);
+	cnt += delta;
+	hpet_writel(cnt, HPET_T0_CMP);
+
+	return ((long)(hpet_readl(HPET_COUNTER) - cnt ) > 0);
+}
+
+/*
+ * Try to setup the HPET timer
+ */
+int __init hpet_enable(void)
+{
+	unsigned long id;
+	uint64_t hpet_freq;
+
+	if (!is_hpet_capable())
+		return 0;
+
+	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+
+	/*
+	 * Read the period and check for a sane value:
+	 */
+	hpet_period = hpet_readl(HPET_PERIOD);
+	if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
+		goto out_nohpet;
+
+	/*
+	 * The period is a femto seconds value. We need to calculate the
+	 * scaled math multiplication factor for nanosecond to hpet tick
+	 * conversion.
+	 */
+	hpet_freq = 1000000000000000ULL;
+	do_div(hpet_freq, hpet_period);
+	hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
+				      NSEC_PER_SEC, 32);
+	/* Calculate the min / max delta */
+	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
+							   &hpet_clockevent);
+	hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30,
+							   &hpet_clockevent);
+
+	/*
+	 * Read the HPET ID register to retrieve the IRQ routing
+	 * information and the number of channels
+	 */
+	id = hpet_readl(HPET_ID);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+	/*
+	 * The legacy routing mode needs at least two channels, tick timer
+	 * and the rtc emulation channel.
+	 */
+	if (!(id & HPET_ID_NUMBER))
+		goto out_nohpet;
+#endif
+
+	/* Start the counter */
+	hpet_start_counter();
+
+	if (id & HPET_ID_LEGSUP) {
+		hpet_enable_int();
+		hpet_reserve_platform_timers(id);
+		/*
+		 * Start hpet with the boot cpu mask and make it
+		 * global after the IO_APIC has been initialized.
+		 */
+		hpet_clockevent.cpumask =cpumask_of_cpu(0);
+		clockevents_register_device(&hpet_clockevent);
+		global_clock_event = &hpet_clockevent;
+		return 1;
+	}
+	return 0;
 
+out_nohpet:
+	iounmap(hpet_virt_address);
+	hpet_virt_address = NULL;
+	return 0;
+}
+
+/*
+ * Clock source related code
+ */
 static cycle_t read_hpet(void)
 {
-	return (cycle_t)readl(hpet_ptr);
+	return (cycle_t)hpet_readl(HPET_COUNTER);
 }
 
 static struct clocksource clocksource_hpet = {
@@ -24,28 +286,17 @@ static struct clocksource clocksource_hpet = {
 	.rating		= 250,
 	.read		= read_hpet,
 	.mask		= 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;
-	int err;
 
-	if (!is_hpet_enabled())
+	if (!hpet_virt_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
@@ -61,11 +312,218 @@ static int __init init_hpet_clocksource(void)
 	do_div(tmp, FSEC_PER_NSEC);
 	clocksource_hpet.mult = (u32)tmp;
 
-	err = clocksource_register(&clocksource_hpet);
-	if (err)
-		iounmap(hpet_base);
-
-	return err;
+	return clocksource_register(&clocksource_hpet);
 }
 
 module_init(init_hpet_clocksource);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+
+/* HPET in LegacyReplacement Mode eats up RTC interrupt line. When, HPET
+ * is enabled, we support RTC interrupt functionality in software.
+ * RTC has 3 kinds of interrupts:
+ * 1) Update Interrupt - generate an interrupt, every sec, when RTC clock
+ *    is updated
+ * 2) Alarm Interrupt - generate an interrupt at a specific time of day
+ * 3) Periodic Interrupt - generate periodic interrupt, with frequencies
+ *    2Hz-8192Hz (2Hz-64Hz for non-root user) (all freqs in powers of 2)
+ * (1) and (2) above are implemented using polling at a frequency of
+ * 64 Hz. The exact frequency is a tradeoff between accuracy and interrupt
+ * overhead. (DEFAULT_RTC_INT_FREQ)
+ * For (3), we use interrupts at 64Hz or user specified periodic
+ * frequency, whichever is higher.
+ */
+#include <linux/mc146818rtc.h>
+#include <linux/rtc.h>
+
+#define DEFAULT_RTC_INT_FREQ	64
+#define DEFAULT_RTC_SHIFT	6
+#define RTC_NUM_INTS		1
+
+static unsigned long hpet_rtc_flags;
+static unsigned long hpet_prev_update_sec;
+static struct rtc_time hpet_alarm_time;
+static unsigned long hpet_pie_count;
+static unsigned long hpet_t1_cmp;
+static unsigned long hpet_default_delta;
+static unsigned long hpet_pie_delta;
+static unsigned long hpet_pie_limit;
+
+/*
+ * Timer 1 for RTC emulation. We use one shot mode, as periodic mode
+ * is not supported by all HPET implementations for timer 1.
+ *
+ * hpet_rtc_timer_init() is called when the rtc is initialized.
+ */
+int hpet_rtc_timer_init(void)
+{
+	unsigned long cfg, cnt, delta, flags;
+
+	if (!is_hpet_enabled())
+		return 0;
+
+	if (!hpet_default_delta) {
+		uint64_t clc;
+
+		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
+		clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT;
+		hpet_default_delta = (unsigned long) clc;
+	}
+
+	if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit)
+		delta = hpet_default_delta;
+	else
+		delta = hpet_pie_delta;
+
+	local_irq_save(flags);
+
+	cnt = delta + hpet_readl(HPET_COUNTER);
+	hpet_writel(cnt, HPET_T1_CMP);
+	hpet_t1_cmp = cnt;
+
+	cfg = hpet_readl(HPET_T1_CFG);
+	cfg &= ~HPET_TN_PERIODIC;
+	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+	hpet_writel(cfg, HPET_T1_CFG);
+
+	local_irq_restore(flags);
+
+	return 1;
+}
+
+/*
+ * The functions below are called from rtc driver.
+ * Return 0 if HPET is not being used.
+ * Otherwise do the necessary changes and return 1.
+ */
+int hpet_mask_rtc_irq_bit(unsigned long bit_mask)
+{
+	if (!is_hpet_enabled())
+		return 0;
+
+	hpet_rtc_flags &= ~bit_mask;
+	return 1;
+}
+
+int hpet_set_rtc_irq_bit(unsigned long bit_mask)
+{
+	unsigned long oldbits = hpet_rtc_flags;
+
+	if (!is_hpet_enabled())
+		return 0;
+
+	hpet_rtc_flags |= bit_mask;
+
+	if (!oldbits)
+		hpet_rtc_timer_init();
+
+	return 1;
+}
+
+int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
+			unsigned char sec)
+{
+	if (!is_hpet_enabled())
+		return 0;
+
+	hpet_alarm_time.tm_hour = hrs;
+	hpet_alarm_time.tm_min = min;
+	hpet_alarm_time.tm_sec = sec;
+
+	return 1;
+}
+
+int hpet_set_periodic_freq(unsigned long freq)
+{
+	uint64_t clc;
+
+	if (!is_hpet_enabled())
+		return 0;
+
+	if (freq <= DEFAULT_RTC_INT_FREQ)
+		hpet_pie_limit = DEFAULT_RTC_INT_FREQ / freq;
+	else {
+		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
+		do_div(clc, freq);
+		clc >>= hpet_clockevent.shift;
+		hpet_pie_delta = (unsigned long) clc;
+	}
+	return 1;
+}
+
+int hpet_rtc_dropped_irq(void)
+{
+	return is_hpet_enabled();
+}
+
+static void hpet_rtc_timer_reinit(void)
+{
+	unsigned long cfg, delta;
+	int lost_ints = -1;
+
+	if (unlikely(!hpet_rtc_flags)) {
+		cfg = hpet_readl(HPET_T1_CFG);
+		cfg &= ~HPET_TN_ENABLE;
+		hpet_writel(cfg, HPET_T1_CFG);
+		return;
+	}
+
+	if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit)
+		delta = hpet_default_delta;
+	else
+		delta = hpet_pie_delta;
+
+	/*
+	 * Increment the comparator value until we are ahead of the
+	 * current count.
+	 */
+	do {
+		hpet_t1_cmp += delta;
+		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
+		lost_ints++;
+	} while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
+
+	if (lost_ints) {
+		if (hpet_rtc_flags & RTC_PIE)
+			hpet_pie_count += lost_ints;
+		if (printk_ratelimit())
+			printk(KERN_WARNING "rtc: lost %d interrupts\n",
+				lost_ints);
+	}
+}
+
+irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
+{
+	struct rtc_time curr_time;
+	unsigned long rtc_int_flag = 0;
+
+	hpet_rtc_timer_reinit();
+
+	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
+		rtc_get_rtc_time(&curr_time);
+
+	if (hpet_rtc_flags & RTC_UIE &&
+	    curr_time.tm_sec != hpet_prev_update_sec) {
+		rtc_int_flag = RTC_UF;
+		hpet_prev_update_sec = curr_time.tm_sec;
+	}
+
+	if (hpet_rtc_flags & RTC_PIE &&
+	    ++hpet_pie_count >= hpet_pie_limit) {
+		rtc_int_flag |= RTC_PF;
+		hpet_pie_count = 0;
+	}
+
+	if (hpet_rtc_flags & RTC_PIE &&
+	    (curr_time.tm_sec == hpet_alarm_time.tm_sec) &&
+	    (curr_time.tm_min == hpet_alarm_time.tm_min) &&
+	    (curr_time.tm_hour == hpet_alarm_time.tm_hour))
+			rtc_int_flag |= RTC_AF;
+
+	if (rtc_int_flag) {
+		rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8));
+		rtc_interrupt(rtc_int_flag, dev_id);
+	}
+	return IRQ_HANDLED;
+}
+#endif
diff --git a/arch/i386/kernel/i8253.c b/arch/i386/kernel/i8253.c
index 9a0060b92e32..a6bc7bb38834 100644
--- a/arch/i386/kernel/i8253.c
+++ b/arch/i386/kernel/i8253.c
@@ -2,7 +2,7 @@
  * i8253.c  8253/PIT functions
  *
  */
-#include <linux/clocksource.h>
+#include <linux/clockchips.h>
 #include <linux/spinlock.h>
 #include <linux/jiffies.h>
 #include <linux/sysdev.h>
@@ -19,17 +19,97 @@
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
-void setup_pit_timer(void)
+/*
+ * HPET replaces the PIT, when enabled. So we need to know, which of
+ * the two timers is used
+ */
+struct clock_event_device *global_clock_event;
+
+/*
+ * Initialize the PIT timer.
+ *
+ * This is also called after resume to bring the PIT into operation again.
+ */
+static void init_pit_timer(enum clock_event_mode mode,
+			   struct clock_event_device *evt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&i8253_lock, flags);
+
+	switch(mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		/* binary, mode 2, LSB/MSB, ch 0 */
+		outb_p(0x34, PIT_MODE);
+		udelay(10);
+		outb_p(LATCH & 0xff , PIT_CH0);	/* LSB */
+		udelay(10);
+		outb(LATCH >> 8 , PIT_CH0);	/* MSB */
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		/* One shot setup */
+		outb_p(0x38, PIT_MODE);
+		udelay(10);
+		break;
+	}
+	spin_unlock_irqrestore(&i8253_lock, flags);
+}
+
+/*
+ * Program the next event in oneshot mode
+ *
+ * Delta is given in PIT ticks
+ */
+static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&i8253_lock, flags);
-	outb_p(0x34,PIT_MODE);		/* binary, mode 2, LSB/MSB, ch 0 */
-	udelay(10);
-	outb_p(LATCH & 0xff , PIT_CH0);	/* LSB */
-	udelay(10);
-	outb(LATCH >> 8 , PIT_CH0);	/* MSB */
+	outb_p(delta & 0xff , PIT_CH0);	/* LSB */
+	outb(delta >> 8 , PIT_CH0);	/* MSB */
 	spin_unlock_irqrestore(&i8253_lock, flags);
+
+	return 0;
+}
+
+/*
+ * On UP the PIT can serve all of the possible timer functions. On SMP systems
+ * it can be solely used for the global tick.
+ *
+ * The profiling and update capabilites are switched off once the local apic is
+ * registered. This mechanism replaces the previous #ifdef LOCAL_APIC -
+ * !using_apic_timer decisions in do_timer_interrupt_hook()
+ */
+struct clock_event_device pit_clockevent = {
+	.name		= "pit",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_O