Merge git://git.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-x86

* git://git.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-x86: (40 commits)
  x86: HPET add another ICH7 PCI id
  x86: HPET force enable ICH5 suspend/resume fix
  x86: HPET force enable for ICH5
  x86: HPET try to activate force detected hpet
  x86: HPET force enable o ICH7 and later
  x86: HPET restructure hpet code for hpet force enable
  clock events: allow replacement of broadcast timer
  i386/x8664: cleanup the shared hpet code
  i386: Remove the useless #ifdef in i8253.h
  ACPI: remove the now unused ifdef code
  jiffies: remove unused macros
  x86_64: cleanup apic.c after clock events switch
  x86_64: remove now unused code
  x86: unify timex.h variants
  x86: kill 8253pit.h
  x86: disable apic timer for AMD C1E enabled CPUs
  x86: Fix irq0 / local apic timer accounting
  x86_64: convert to clock events
  x86_64: Add (not yet used) clock event functions
  x86_64: prepare idle loop for dynamic ticks
  ...

Documentation/kernel-parameters.txt

@@ -1009,6 +1009,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	meye.*=		[HW] Set MotionEye Camera parameters
 			See Documentation/video4linux/meye.txt.
 
+	mfgpt_irq=	[IA-32] Specify the IRQ to use for the
+			Multi-Function General Purpose Timers on AMD Geode
+			platforms.
+
 	mga=		[HW,DRM]
 
 	mousedev.tap_time=
@@ -1160,6 +1164,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nomce		[X86-32] Machine Check Exception
 
+	nomfgpt		[X86-32] Disable Multi-Function General Purpose
+			Timer usage (for AMD Geode machines).
+
 	noreplace-paravirt	[X86-32,PV_OPS] Don't patch paravirt_ops
 
 	noreplace-smp	[X86-32,SMP] Don't replace SMP instructions

arch/i386/Kconfig

@@ -1206,6 +1206,16 @@ config SCx200HR_TIMER
 	  processor goes idle (as is done by the scheduler).  The
 	  other workaround is idle=poll boot option.
 
+config GEODE_MFGPT_TIMER
+	bool "Geode Multi-Function General Purpose Timer (MFGPT) events"
+	depends on MGEODE_LX && GENERIC_TIME && GENERIC_CLOCKEVENTS
+	default y
+	help
+	  This driver provides a clock event source based on the MFGPT
+	  timer(s) in the CS5535 and CS5536 companion chip for the geode.
+	  MFGPTs have a better resolution and max interval than the
+	  generic PIT, and are suitable for use as high-res timers.
+
 config K8_NB
 	def_bool y
 	depends on AGP_AMD64

arch/x86/kernel/Makefile_32

@@ -7,7 +7,7 @@ extra-y := head_32.o init_task_32.o vmlinux.lds
 obj-y	:= process_32.o signal_32.o entry_32.o traps_32.o irq_32.o \
 		ptrace_32.o time_32.o ioport_32.o ldt_32.o setup_32.o i8259_32.o sys_i386_32.o \
 		pci-dma_32.o i386_ksyms_32.o i387_32.o bootflag.o e820_32.o\
-		quirks.o i8237.o topology.o alternative.o i8253_32.o tsc_32.o
+		quirks.o i8237.o topology.o alternative.o i8253.o tsc_32.o
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-y				+= cpu/
@@ -37,9 +37,9 @@ obj-$(CONFIG_EFI) 		+= efi_32.o efi_stub_32.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-obj-$(CONFIG_HPET_TIMER) 	+= hpet_32.o
+obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_K8_NB)		+= k8.o
-obj-$(CONFIG_MGEODE_LX)		+= geode_32.o
+obj-$(CONFIG_MGEODE_LX)		+= geode_32.o mfgpt_32.o
 
 obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt_32.o

arch/x86/kernel/Makefile_64

@@ -8,8 +8,8 @@ obj-y	:= process_64.o signal_64.o entry_64.o traps_64.o irq_64.o \
 		ptrace_64.o time_64.o ioport_64.o ldt_64.o setup_64.o i8259_64.o sys_x86_64.o \
 		x8664_ksyms_64.o i387_64.o syscall_64.o vsyscall_64.o \
 		setup64.o bootflag.o e820_64.o reboot_64.o quirks.o i8237.o \
-		pci-dma_64.o pci-nommu_64.o alternative.o hpet_64.o tsc_64.o bugs_64.o \
-		perfctr-watchdog.o
+		pci-dma_64.o pci-nommu_64.o alternative.o hpet.o tsc_64.o bugs_64.o \
+		perfctr-watchdog.o i8253.o
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_X86_MCE)		+= mce_64.o therm_throt.o

arch/x86/kernel/geode_32.c

@@ -145,10 +145,14 @@ EXPORT_SYMBOL_GPL(geode_gpio_setup_event);
 
 static int __init geode_southbridge_init(void)
 {
+	int timers;
+
 	if (!is_geode())
 		return -ENODEV;
 
 	init_lbars();
+	timers = geode_mfgpt_detect();
+	printk(KERN_INFO "geode:  %d MFGPT timers available.\n", timers);
 	return 0;
 }
 

arch/x86/kernel/hpet_32.c → arch/x86/kernel/hpet.c

 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
@@ -7,11 +8,11 @@
 #include <linux/pm.h>
 #include <linux/delay.h>
 
+#include <asm/fixmap.h>
 #include <asm/hpet.h>
+#include <asm/i8253.h>
 #include <asm/io.h>
 
-extern struct clock_event_device *global_clock_event;
-
 #define HPET_MASK	CLOCKSOURCE_MASK(32)
 #define HPET_SHIFT	22
 
@@ -22,9 +23,9 @@ extern struct clock_event_device *global_clock_event;
  * HPET address is set in acpi/boot.c, when an ACPI entry exists
  */
 unsigned long hpet_address;
-static void __iomem * hpet_virt_address;
+static void __iomem *hpet_virt_address;
 
-static inline unsigned long hpet_readl(unsigned long a)
+unsigned long hpet_readl(unsigned long a)
 {
 	return readl(hpet_virt_address + a);
 }
@@ -34,6 +35,36 @@ static inline void hpet_writel(unsigned long d, unsigned long a)
 	writel(d, hpet_virt_address + a);
 }
 
+#ifdef CONFIG_X86_64
+
+#include <asm/pgtable.h>
+
+static inline void hpet_set_mapping(void)
+{
+	set_fixmap_nocache(FIX_HPET_BASE, hpet_address);
+	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
+	hpet_virt_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE);
+}
+
+static inline void hpet_clear_mapping(void)
+{
+	hpet_virt_address = NULL;
+}
+
+#else
+
+static inline void hpet_set_mapping(void)
+{
+	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+}
+
+static inline void hpet_clear_mapping(void)
+{
+	iounmap(hpet_virt_address);
+	hpet_virt_address = NULL;
+}
+#endif
+
 /*
  * HPET command line enable / disable
  */
@@ -49,6 +80,13 @@ static int __init hpet_setup(char* str)
 }
 __setup("hpet=", hpet_setup);
 
+static int __init disable_hpet(char *str)
+{
+	boot_hpet_disable = 1;
+	return 1;
+}
+__setup("nohpet", disable_hpet);
+
 static inline int is_hpet_capable(void)
 {
 	return (!boot_hpet_disable && hpet_address);
@@ -83,7 +121,7 @@ static void hpet_reserve_platform_timers(unsigned long id)
 
 	memset(&hd, 0, sizeof (hd));
 	hd.hd_phys_address = hpet_address;
-	hd.hd_address = hpet_virt_address;
+	hd.hd_address = hpet;
 	hd.hd_nirqs = nrtimers;
 	hd.hd_flags = HPET_DATA_PLATFORM;
 	hpet_reserve_timer(&hd, 0);
@@ -111,9 +149,9 @@ static void hpet_reserve_platform_timers(unsigned long id) { }
  */
 static unsigned long hpet_period;
 
-static void hpet_set_mode(enum clock_event_mode mode,
+static void hpet_legacy_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt);
-static int hpet_next_event(unsigned long delta,
+static int hpet_legacy_next_event(unsigned long delta,
 			   struct clock_event_device *evt);
 
 /*
@@ -122,10 +160,11 @@ static int hpet_next_event(unsigned long delta,
 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,
+	.set_mode	= hpet_legacy_set_mode,
+	.set_next_event = hpet_legacy_next_event,
 	.shift		= 32,
 	.irq		= 0,
+	.rating		= 50,
 };
 
 static void hpet_start_counter(void)
@@ -140,7 +179,18 @@ static void hpet_start_counter(void)
 	hpet_writel(cfg, HPET_CFG);
 }
 
-static void hpet_enable_int(void)
+static void hpet_resume_device(void)
+{
+	force_hpet_resume();
+}
+
+static void hpet_restart_counter(void)
+{
+	hpet_resume_device();
+	hpet_start_counter();
+}
+
+static void hpet_enable_legacy_int(void)
 {
 	unsigned long cfg = hpet_readl(HPET_CFG);
 
@@ -149,7 +199,39 @@ static void hpet_enable_int(void)
 	hpet_legacy_int_enabled = 1;
 }
 
-static void hpet_set_mode(enum clock_event_mode mode,
+static void hpet_legacy_clockevent_register(void)
+{
+	uint64_t hpet_freq;
+
+	/* Start HPET legacy interrupts */
+	hpet_enable_legacy_int();
+
+	/*
+	 * 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);
+
+	/*
+	 * Start hpet with the boot cpu mask and make it
+	 * global after the IO_APIC has been initialized.
+	 */
+	hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
+	clockevents_register_device(&hpet_clockevent);
+	global_clock_event = &hpet_clockevent;
+	printk(KERN_DEBUG "hpet clockevent registered\n");
+}
+
+static void hpet_legacy_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt)
 {
 	unsigned long cfg, cmp, now;
@@ -190,12 +272,12 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		break;
 
 	case CLOCK_EVT_MODE_RESUME:
-		hpet_enable_int();
+		hpet_enable_legacy_int();
 		break;
 	}
 }
 
-static int hpet_next_event(unsigned long delta,
+static int hpet_legacy_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
 {
 	unsigned long cnt;
@@ -215,6 +297,13 @@ static cycle_t read_hpet(void)
 	return (cycle_t)hpet_readl(HPET_COUNTER);
 }
 
+#ifdef CONFIG_X86_64
+static cycle_t __vsyscall_fn vread_hpet(void)
+{
+	return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
+}
+#endif
+
 static struct clocksource clocksource_hpet = {
 	.name		= "hpet",
 	.rating		= 250,
@@ -222,61 +311,17 @@ static struct clocksource clocksource_hpet = {
 	.mask		= HPET_MASK,
 	.shift		= HPET_SHIFT,
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-	.resume		= hpet_start_counter,
+	.resume		= hpet_restart_counter,
+#ifdef CONFIG_X86_64
+	.vread		= vread_hpet,
+#endif
 };
 
-/*
- * Try to setup the HPET timer
- */
-int __init hpet_enable(void)
+static int hpet_clocksource_register(void)
 {
-	unsigned long id;
-	uint64_t hpet_freq;
 	u64 tmp, start, now;
 	cycle_t t1;
 
-	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();
 
@@ -298,7 +343,7 @@ int __init hpet_enable(void)
 	if (t1 == read_hpet()) {
 		printk(KERN_WARNING
 		       "HPET counter not counting. HPET disabled\n");
-		goto out_nohpet;
+		return -ENODEV;
 	}
 
 	/* Initialize and register HPET clocksource
@@ -319,27 +364,84 @@ int __init hpet_enable(void)
 
 	clocksource_register(&clocksource_hpet);
 
-	if (id & HPET_ID_LEGSUP) {
-		hpet_enable_int();
-		hpet_reserve_platform_timers(id);
+	return 0;
+}
+
+/*
+ * Try to setup the HPET timer
+ */
+int __init hpet_enable(void)
+{
+	unsigned long id;
+
+	if (!is_hpet_capable())
+		return 0;
+
+	hpet_set_mapping();
+
 	/*
-		 * Start hpet with the boot cpu mask and make it
-		 * global after the IO_APIC has been initialized.
+	 * Read the period and check for a sane value:
 	 */
-		hpet_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
-		clockevents_register_device(&hpet_clockevent);
-		global_clock_event = &hpet_clockevent;
+	hpet_period = hpet_readl(HPET_PERIOD);
+	if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
+		goto out_nohpet;
+
+	/*
+	 * 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
+
+	if (hpet_clocksource_register())
+		goto out_nohpet;
+
+	if (id & HPET_ID_LEGSUP) {
+		hpet_legacy_clockevent_register();
 		return 1;
 	}
 	return 0;
 
 out_nohpet:
-	iounmap(hpet_virt_address);
-	hpet_virt_address = NULL;
+	hpet_clear_mapping();
 	boot_hpet_disable = 1;
 	return 0;
 }
 
+/*
+ * Needs to be late, as the reserve_timer code calls kalloc !
+ *
+ * Not a problem on i386 as hpet_enable is called from late_time_init,
+ * but on x86_64 it is necessary !
+ */
+static __init int hpet_late_init(void)
+{
+	if (boot_hpet_disable)
+		return -ENODEV;
+
+	if (!hpet_address) {
+		if (!force_hpet_address)
+			return -ENODEV;
+
+		hpet_address = force_hpet_address;
+		hpet_enable();
+		if (!hpet_virt_address)
+			return -ENODEV;
+	}
+
+	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
+
+	return 0;
+}
+fs_initcall(hpet_late_init);
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 

arch/x86/kernel/i8253_32.c → arch/x86/kernel/i8253.c

@@ -13,7 +13,6 @@
 #include <asm/delay.h>
 #include <asm/i8253.h>
 #include <asm/io.h>
-#include <asm/timer.h>
 
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
@@ -120,6 +119,7 @@ void __init setup_pit_timer(void)
 	global_clock_event = &pit_clockevent;
 }
 
+#ifndef CONFIG_X86_64
 /*
  * Since the PIT overflows every tick, its not very useful
  * to just read by itself. So use jiffies to emulate a free
@@ -204,3 +204,5 @@ static int __init init_pit_clocksource(void)
 	return clocksource_register(&clocksource_pit);
 }
 arch_initcall(init_pit_clocksource);
+
+#endif

arch/x86/kernel/i8259_32.c

@@ -10,7 +10,6 @@
 #include <linux/sysdev.h>
 #include <linux/bitops.h>
 
-#include <asm/8253pit.h>
 #include <asm/atomic.h>
 #include <asm/system.h>
 #include <asm/io.h>

arch/x86/kernel/i8259_64.c

@@ -444,46 +444,6 @@ void __init init_ISA_irqs (void)
 	}
 }
 
-static void setup_timer_hardware(void)
-{
-	outb_p(0x34,0x43);		/* binary, mode 2, LSB/MSB, ch 0 */
-	udelay(10);
-	outb_p(LATCH & 0xff , 0x40);	/* LSB */
-	udelay(10);
-	outb(LATCH >> 8 , 0x40);	/* MSB */
-}
-
-static int timer_resume(struct sys_device *dev)
-{
-	setup_timer_hardware();
-	return 0;
-}
-
-void i8254_timer_resume(void)
-{
-	setup_timer_hardware();
-}
-
-static struct sysdev_class timer_sysclass = {
-	set_kset_name("timer_pit"),
-	.resume		= timer_resume,
-};
-
-static struct sys_device device_timer = {
-	.id		= 0,
-	.cls		= &timer_sysclass,
-};
-
-static int __init init_timer_sysfs(void)
-{
-	int error = sysdev_class_register(&timer_sysclass);
-	if (!error)
-		error = sysdev_register(&device_timer);
-	return error;
-}
-
-device_initcall(init_timer_sysfs);
-
 void __init init_IRQ(void)
 {
 	int i;
@@ -533,12 +493,6 @@ void __init init_IRQ(void)
 	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
-	/*
-	 * Set the clock to HZ Hz, we already have a valid
-	 * vector now:
-	 */
-	setup_timer_hardware();
-
 	if (!acpi_ioapic)
 		setup_irq(2, &irq2);
 }

arch/x86/kernel/mfgpt_32.c

+/*
+ * Driver/API for AMD Geode Multi-Function General Purpose Timers (MFGPT)
+ *
+ * Copyright (C) 2006, Advanced Micro Devices, Inc.
+ * Copyright (C) 2007, Andres Salomon <dilinger@debian.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * The MFGPTs are documented in AMD Geode CS5536 Companion Device Data Book.
+ */
+
+/*
+ * We are using the 32Khz input clock - its the only one that has the
+ * ranges we find desirable.  The following table lists the suitable
+ * divisors and the associated hz, minimum interval
+ * and the maximum interval:
+ *
+ *  Divisor   Hz      Min Delta (S) Max Delta (S)
+ *   1        32000     .0005          2.048
+ *   2        16000      .001          4.096
+ *   4         8000      .002          8.192
+ *   8         4000      .004         16.384
+ *   16        2000      .008         32.768
+ *   32        1000      .016         65.536
+ *   64         500      .032        131.072
+ *  128         250      .064        262.144
+ *  256         125      .128        524.288
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <asm/geode.h>
+
+#define F_AVAIL    0x01
+
+static struct mfgpt_timer_t {
+	int flags;
+	struct module *owner;
+} mfgpt_timers[MFGPT_MAX_TIMERS];
+
+/* Selected from the table above */
+
+#define MFGPT_DIVISOR 16
+#define MFGPT_SCALE  4     /* divisor = 2^(scale) */
+#define MFGPT_HZ  (32000 / MFGPT_DIVISOR)
+#define MFGPT_PERIODIC (MFGPT_HZ / HZ)
+
+#ifdef CONFIG_GEODE_MFGPT_TIMER
+static int __init mfgpt_timer_setup(void);
+#else
+#define mfgpt_timer_setup() (0)
+#endif
+
+/* Allow for disabling of MFGPTs */
+static int disable;
+static int __init mfgpt_disable(char *s)
+{
+	disable = 1;
+	return 1;
+}
+__setup("nomfgpt", mfgpt_disable);
+
+/*
+ * Check whether any MFGPTs are available for the kernel to use.  In most
+ * cases, firmware that uses AMD's VSA code will claim all timers during
+ * bootup; we certainly don't want to take them if they're already in use.
+ * In other cases (such as with VSAless OpenFirmware), the system firmware
+ * leaves timers available for us to use.
+ */
+int __init geode_mfgpt_detect(void)
+{
+	int count = 0, i;
+	u16 val;
+
+	if (disable) {
+		printk(KERN_INFO "geode-mfgpt:  Skipping MFGPT setup\n");
+		return 0;
+	}
+
+	for (i = 0; i < MFGPT_MAX_TIMERS; i++) {
+		val = geode_mfgpt_read(i, MFGPT_REG_SETUP);
+		if (!(val & MFGPT_SETUP_SETUP)) {
+			mfgpt_timers[i].flags = F_AVAIL;
+			count++;
+		}
+	}
+
+	/* set up clock event device, if desired */
+	i = mfgpt_timer_setup();
+
+	return count;
+}
+
+int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
+{
+	u32 msr, mask, value, dummy;
+	int shift = (cmp == MFGPT_CMP1) ? 0 : 8;
+
+	if (timer < 0 || timer >= MFGPT_MAX_TIMERS)
+		return -EIO;
+
+	/*
+	 * The register maps for these are described in sections 6.17.1.x of
+	 * the AMD Geode CS5536 Companion Device Data Book.
+	 */
+	switch (event) {
+	case MFGPT_EVENT_RESET:
+		/*
+		 * XXX: According to the docs, we cannot reset timers above
+		 * 6; that is, resets for 7 and 8 will be ignored.  Is this
+		 * a problem?   -dilinger
+		 */
+		msr = MFGPT_NR_MSR;
+		mask = 1 << (timer + 24);
+		break;
+
+	case MFGPT_EVENT_NMI:
+		msr = MFGPT_NR_MSR;
+		mask = 1 << (timer + shift);
+		break;
+
+	case MFGPT_EVENT_IRQ:
+		msr = MFGPT_IRQ_MSR;
+		mask = 1 << (timer + shift);
+		break;
+
+	default:
+		return -EIO;
+	}
+
+	rdmsr(msr, value, dummy);
+
+	if (enable)
+		value |= mask;
+	else
+		value &= ~mask;
+
+	wrmsr(msr, value, dummy);
+	return 0;
+}
+
+int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable)
+{
+	u32 val, dummy;
+	int offset;
+
+	if (timer < 0 || timer >= MFGPT_MAX_TIMERS)
+		return -EIO;
+
+	if (geode_mfgpt_toggle_event(timer, cmp, MFGPT_EVENT_IRQ, enable))
+		return -EIO;
+
+	rdmsr(MSR_PIC_ZSEL_LOW, val, dummy);
+
+	offset = (timer % 4) * 4;
+
+	val &= ~((0xF << offset) | (0xF << (offset + 16)));
+
+	if (enable) {
+		val |= (irq & 0x0F) << (offset);
+		val |= (irq & 0x0F) << (offset + 16);
+	}
+
+	wrmsr(MSR_PIC_ZSEL_LOW, val, dummy);
+	return 0;
+}
+
+static int mfgpt_get(int timer, struct module *owner)
+{
+	mfgpt_timers[timer].flags &= ~F_AVAIL;
+	mfgpt_timers[timer].owner = owner;
+	printk(KERN_INFO "geode-mfgpt:  Registered timer %d\n", timer);
+	return timer;
+}
+
+int geode_mfgpt_alloc_timer(int timer, int domain, struct module *owner)
+{
+	int i;
+
+	if (!geode_get_dev_base(GEODE_DEV_MFGPT))
+		return -ENODEV;
+	if (timer >= MFGPT_MAX_TIMERS)
+		return -EIO;
+
+	if (timer < 0) {
+		/* Try to find an available timer */
+		for (i = 0; i < MFGPT_MAX_TIMERS; i++) {
+			if (mfgpt_timers[i].flags & F_AVAIL)
+				return mfgpt_get(i, owner);
+
+			if (i == 5 && domain == MFGPT_DOMAIN_WORKING)
+				break;
+		}
+	} else {
+		/* If they requested a specific timer, try to honor that */
+		if (mfgpt_timers[timer].flags & F_AVAIL)
+			return mfgpt_get(timer, owner);
+	}
+
+	/* No timers available - too bad */
+	return -1;
+}
+
+
+#ifdef CONFIG_GEODE_MFGPT_TIMER
+
+/*
+ * The MFPGT timers on the CS5536 provide us with suitable timers to use
+ * as clock event sources - not as good as a HPET or APIC, but certainly
+ * better then the PIT.  This isn't a general purpose MFGPT driver, but
+ * a simplified one designed specifically to act as a clock event source.
+ * For full details about the MFGPT, please consult the CS5536 data sheet.
+ */
+
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+
+static unsigned int mfgpt_tick_mode = CLOCK_EVT_MODE_SHUTDOWN;
+static u16 mfgpt_event_clock;
+
+static int irq = 7;
+static int __init mfgpt_setup(char *str)
+{
+	get_option(&str, &irq);
+	return 1;
+}
+__setup("mfgpt_irq=", mfgpt_setup);
+
+static inline void mfgpt_disable_timer(u16 clock)
+{
+	u16 val = geode_mfgpt_read(clock, MFGPT_REG_SETUP);
+	geode_mfgpt_write(clock, MFGPT_REG_SETUP, val & ~MFGPT_SETUP_CNTEN);
+}
+
+static int mfgpt_next_event(unsigned long, struct clock_event_device *);
+static void mfgpt_set_mode(enum clock_event_mode, struct clock_event_device *);
+
+static struct clock_event_device mfgpt_clockevent = {
+	.name = "mfgpt-timer",
+	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode = mfgpt_set_mode,
+	.set_next_event = mfgpt_next_event,
+	.rating = 250,
+	.cpumask = CPU_MASK_ALL,
+	.shift = 32
+};
+
+static inline void mfgpt_start_timer(u16 clock, u16 delta)
+{
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_CMP2, (u16) delta);
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_COUNTER, 0);
+
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP,
+			  MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2);
+}
+
+static void mfgpt_set_mode(enum clock_event_mode mode,
+			   struct clock_event_device *evt)
+{
+	mfgpt_disable_timer(mfgpt_event_clock);
+
+	if (mode == CLOCK_EVT_MODE_PERIODIC)
+		mfgpt_start_timer(mfgpt_event_clock, MFGPT_PERIODIC);
+
+	mfgpt_tick_mode = mode;
+}
+
+static int mfgpt_next_event(unsigned long delta, struct clock_event_device *evt)
+{
+	mfgpt_start_timer(mfgpt_event_clock, delta);
+	return 0;
+}
+
+/* Assume (foolishly?), that this interrupt was due to our tick */
+
+static irqreturn_t mfgpt_tick(int irq, void *dev_id)
+{
+	if (mfgpt_tick_mode == CLOCK_EVT_MODE_SHUTDOWN)
+		return IRQ_HANDLED;
+
+	/* Turn off the clock */
+	mfgpt_disable_timer(mfgpt_event_clock);
+
+	/* Clear the counter */
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_COUNTER, 0);
+
+	/* Restart the clock in periodic mode */
+
+	if (mfgpt_tick_mode == CLOCK_EVT_MODE_PERIODIC) {
+		geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP,
+				  MFGPT_SETUP_CNTEN | MFGPT_SETUP_CMP2);
+	}
+
+	mfgpt_clockevent.event_handler(&mfgpt_clockevent);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction mfgptirq  = {
+	.handler = mfgpt_tick,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING,
+	.mask = CPU_MASK_NONE,
+	.name = "mfgpt-timer"
+};
+
+static int __init mfgpt_timer_setup(void)
+{
+	int timer, ret;
+	u16 val;
+
+	timer = geode_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING,
+			THIS_MODULE);
+	if (timer < 0) {
+		printk(KERN_ERR
+		       "mfgpt-timer:  Could not allocate a MFPGT timer\n");
+		return -ENODEV;
+	}
+
+	mfgpt_event_clock = timer;
+	/* Set the clock scale and enable the event mode for CMP2 */
+	val = MFGPT_SCALE | (3 << 8);
+
+	geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP, val);
+
+	/* Set up the IRQ on the MFGPT side */
+	if (geode_mfgpt_setup_irq(mfgpt_event_clock, MFGPT_CMP2, irq)) {
+		printk(KERN_ERR "mfgpt-timer:  Could not set up IRQ %d\n", irq);
+		return -EIO;
+	}
+
+	/* And register it with the kernel */
+	ret = setup_irq(irq, &mfgptirq);
+
+	if (ret) {
+		printk(KERN_ERR
+		       "mfgpt-timer:  Unable to set up the interrupt.\n");
+		goto err;
+	}
+
+	/* Set up the clock event */
+	mfgpt_clockevent.mult = div_sc(MFGPT_HZ, NSEC_PER_SEC, 32);
+	mfgpt_clockevent.min_delta_ns = clockevent_delta2ns(0xF,
+			&mfgpt_clockevent);
+	mfgpt_clockevent.max_delta_ns = clockevent_delta2ns(0xFFFE,
+			&mfgpt_clockevent);
+
+	printk(KERN_INFO
+	       "mfgpt-timer:  registering the MFGT timer as a clock event.\n");
+	clockevents_register_device(&mfgpt_clockevent);
+
+	return 0;
+
+err:
+	geode_mfgpt_release_irq(mfgpt_event_clock, MFGPT_CMP2, irq);
+	printk(KERN_ERR
+	       "mfgpt-timer:  Unable to set up the MFGPT clock source\n");
+	return -EIO;
+}
+
+#endif

arch/x86/kernel/nmi_32.c

@@ -353,7 +353,8 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 	 * Take the local apic timer and PIT/HPET into account. We don't
 	 * know which one is active, when we have highres/dyntick on
 	 */
-	sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_cpu(cpu).irqs[0];
+	sum = per_cpu(irq_stat, cpu).apic_timer_irqs +
+		per_cpu(irq_stat, cpu).irq0_irqs;
 
 	/* if the none of the timers isn't firing, this cpu isn't doing much */
 	if (!touched && last_irq_sums[cpu] == sum) {

arch/x86/kernel/nmi_64.c

@@ -329,7 +329,7 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 		touched = 1;
 	}
 
-	sum = read_pda(apic_timer_irqs);
+	sum = read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
 	if (__get_cpu_var(nmi_touch)) {
 		__get_cpu_var(nmi_touch) = 0;
 		touched = 1;

arch/x86/kernel/process_64.c

@@ -38,6 +38,7 @@
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
+#include <linux/tick.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -208,6 +209,8 @@ void cpu_idle (void)
 			if (__get_cpu_var(cpu_idle_state))
 				__get_cpu_var(cpu_idle_state) = 0;
 
+			tick_nohz_stop_sched_tick();
+
 			rmb();
 			idle = pm_idle;
 			if (!idle)
@@ -228,6 +231,7 @@ void cpu_idle (void)
 			__exit_idle();
 		}
 
+		tick_nohz_restart_sched_tick();
 		preempt_enable_no_resched();
 		schedule();
 		preempt_disable();

arch/x86/kernel/quirks.c

@@ -4,6 +4,8 @@
 #include <linux/pci.h>
 #include <linux/irq.h>
 
+#include <asm/hpet.h>
+
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 
 static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
@@ -47,3 +49,206 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7320_MCH,	quir
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7525_MCH,	quirk_intel_irqbalance);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7520_MCH,	quirk_intel_irqbalance);
 #endif
+
+#if defined(CONFIG_HPET_TIMER)
+unsigned long force_hpet_address;
+
+static enum {
+	NONE_FORCE_HPET_RESUME,
+	OLD_ICH_FORCE_HPET_RESUME,
+	ICH_FORCE_HPET_RESUME
+} force_hpet_resume_type;
+
+static void __iomem *rcba_base;
+
+static void ich_force_hpet_resume(void)
+{
+	u32 val;
+
+	if (!force_hpet_address)
+		return;
+
+	if (rcba_base == NULL)
+		BUG();
+
+	/* read the Function Disable register, dword mode only */
+	val = readl(rcba_base + 0x3404);
+	if (!(val & 0x80)) {
+		/* HPET disabled in HPTC. Trying to enable */
+		writel(val | 0x80, rcba_base + 0x3404);
+	}
+
+	val = readl(rcba_base + 0x3404);
+	if (!(val & 0x80))
+		BUG();
+	else
+		printk(KERN_DEBUG "Force enabled HPET at resume\n");
+
+	return;
+}
+
+static void ich_force_enable_hpet(struct pci_dev *dev)
+{
+	u32 val;
+	u32 uninitialized_var(rcba);
+	int err = 0;
+
+	if (hpet_address || force_hpet_address)
+		return;
+
+	pci_read_config_dword(dev, 0xF0, &rcba);
+	rcba &= 0xFFFFC000;
+	if (rcba == 0) {
+		printk(KERN_DEBUG "RCBA disabled. Cannot force enable HPET\n");
+		return;
+	}
+
+	/* use bits 31:14, 16 kB aligned */
+	rcba_base = ioremap_nocache(rcba, 0x4000);
+	if (rcba_base == NULL) {
+		printk(KERN_DEBUG "ioremap failed. Cannot force enable HPET\n");
+		return;
+	}
+
+	/* read the Function Disable register, dword mode only */
+	val = readl(rcba_base + 0x3404);
+
+	if (val & 0x80) {
+		/* HPET is enabled in HPTC. Just not reported by BIOS */
+		val = val & 0x3;
+		force_hpet_address = 0xFED00000 | (val << 12);
+		printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n",
+			       force_hpet_address);
+		iounmap(rcba_base);
+		return;
+	}
+
+	/* HPET disabled in HPTC. Trying to enable */
+	writel(val | 0x80, rcba_base + 0x3404);
+
+	val = readl(rcba_base + 0x3404);
+	if (!(val & 0x80)) {
+		err = 1;
+	} else {
+		val = val & 0x3;
+		force_hpet_address = 0xFED00000 | (val << 12);
+	}
+
+	if (err) {
+		force_hpet_address = 0;
+		iounmap(rcba_base);
+		printk(KERN_DEBUG "Failed to force enable HPET\n");
+	} else {
+		force_hpet_resume_type = ICH_FORCE_HPET_RESUME;
+		printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n",
+			       force_hpet_address);
+	}
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB2_0,
+                         ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_1,
+                         ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_0,
+                         ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_1,
+                         ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_31,
+                         ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_1,
+                         ich_force_enable_hpet);
+
+
+static struct pci_dev *cached_dev;
+
+static void old_ich_force_hpet_resume(void)
+{
+	u32 val;
+	u32 uninitialized_var(gen_cntl);
+
+	if (!force_hpet_address || !cached_dev)
+		return;
+
+	pci_read_config_dword(cached_dev, 0xD0, &gen_cntl);
+	gen_cntl &= (~(0x7 << 15));
+	gen_cntl |= (0x4 << 15);
+
+	pci_write_config_dword(cached_dev, 0xD0, gen_cntl);
+	pci_read_config_dword(cached_dev, 0xD0, &gen_cntl);
+	val = gen_cntl >> 15;
+	val &= 0x7;
+	if (val == 0x4)
+		printk(KERN_DEBUG "Force enabled HPET at resume\n");
+	else
+		BUG();
+}
+
+static void old_ich_force_enable_hpet(struct pci_dev *dev)
+{
+	u32 val;
+	u32 uninitialized_var(gen_cntl);
+
+	if (hpet_address || force_hpet_address)
+		return;
+
+	pci_read_config_dword(dev, 0xD0, &gen_cntl);
+	/*
+	 * Bit 17 is HPET enable bit.
+	 * Bit 16:15 control the HPET base address.
+	 */
+	val = gen_cntl >> 15;
+	val &= 0x7;
+	if (val & 0x4) {
+		val &= 0x3;
+		force_hpet_address = 0xFED00000 | (val << 12);
+		printk(KERN_DEBUG "HPET at base address 0x%lx\n",
+			       force_hpet_address);
+		return;
+	}
+
+	/*
+	 * HPET is disabled. Trying enabling at FED00000 and check
+	 * whether it sticks
+	 */
+	gen_cntl &= (~(0x7 << 15));
+	gen_cntl |= (0x4 << 15);
+	pci_write_config_dword(dev, 0xD0, gen_cntl);
+
+	pci_read_config_dword(dev, 0xD0, &gen_cntl);
+
+	val = gen_cntl >> 15;
+	val &= 0x7;
+	if (val & 0x4) {
+		/* HPET is enabled in HPTC. Just not reported by BIOS */
+		val &= 0x3;
+		force_hpet_address = 0xFED00000 | (val << 12);
+		printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n",
+			       force_hpet_address);
+		cached_dev = dev;
+		force_hpet_resume_type = OLD_ICH_FORCE_HPET_RESUME;
+		return;
+	}
+
+	printk(KERN_DEBUG "Failed to force enable HPET\n");
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801EB_0,
+                         old_ich_force_enable_hpet);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801EB_12,
+                         old_ich_force_enable_hpet);
+
+void force_hpet_resume(void)
+{
+	switch (force_hpet_resume_type) {
+	    case ICH_FORCE_HPET_RESUME:
+		return ich_force_hpet_resume();
+
+	    case OLD_ICH_FORCE_HPET_RESUME:
+		return old_ich_force_hpet_resume();
+
+	    default:
+		break;
+	}
+}
+
+#endif

arch/x86/kernel/setup_64.c

@@ -546,6 +546,37 @@ static void __init amd_detect_cmp(struct cpuinfo_x86 *c)
 #endif
 }
 
+#define ENABLE_C1E_MASK		0x18000000
+#define CPUID_PROCESSOR_SIGNATURE	1
+#define CPUID_XFAM		0x0ff00000
+#define CPUID_XFAM_K8		0x00000000
+#define CPUID_XFAM_10H		0x00100000
+#define CPUID_XFAM_11H		0x00200000
+#define CPUID_XMOD		0x000f0000
+#define CPUID_XMOD_REV_F	0x00040000
+
+/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
+static __cpuinit int amd_apic_timer_broken(void)
+{
+	u32 lo, hi;
+	u32 eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
+	switch (eax & CPUID_XFAM) {
+	case CPUID_XFAM_K8:
+		if ((eax & CPUID_XMOD) < CPUID_XMOD_REV_F)
+			break;
+	case CPUID_XFAM_10H:
+	case CPUID_XFAM_11H:
+		rdmsr(MSR_K8_ENABLE_C1E, lo, hi);
+		if (lo & ENABLE_C1E_MASK)
+			return 1;
+		break;
+	default:
+		/* err on the side of caution */
+		return 1;
+	}
+	return 0;
+}
+
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 {
 	unsigned level;
@@ -617,6 +648,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	/* Family 10 doesn't support C states in MWAIT so don't use it */
 	if (c->x86 == 0x10 && !force_mwait)
 		clear_bit(X86_FEATURE_MWAIT, &c->x86_capability);
+
+	if (amd_apic_timer_broken())
+		disable_apic_timer = 1;
 }
 
 static void __cpuinit detect_ht(struct cpuinfo_x86 *c)

arch/x86/kernel/smpboot_64.c

@@ -223,8 +223,6 @@ void __cpuinit smp_callin(void)
 	local_irq_disable();
 	Dprintk("Stack at about %p\n",&cpuid);
 
-	disable_APIC_timer();
-
 	/*
 	 * Save our processor parameters
 	 */
@@ -348,8 +346,6 @@ void __cpuinit start_secondary(void)
 		enable_8259A_irq(0);
 	}
 
-	enable_APIC_timer();
-
 	/*
 	 * The sibling maps must be set before turing the online map on for
 	 * this cpu

arch/x86/kernel/time_32.c

@@ -157,6 +157,9 @@ EXPORT_SYMBOL(profile_pc);
  */
 irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
+	/* Keep nmi watchdog up to date */
+	per_cpu(irq_stat, smp_processor_id()).irq0_irqs++;
+
 #ifdef CONFIG_X86_IO_APIC
 	if (timer_ack) {
 		/*

arch/x86/kernel/time_64.c

@@ -28,11 +28,12 @@
 #include <linux/cpu.h>
 #include <linux/kallsyms.h>
 #include <linux/acpi.h>
+#include <linux/clockchips.h>
+
 #ifdef CONFIG_ACPI
 #include <acpi/achware.h>	/* for PM timer frequency */
 #include <acpi/acpi_bus.h>
 #endif
-#include <asm/8253pit.h>
 #include <asm/i8253.h>
 #include <asm/pgtable.h>
 #include <asm/vsyscall.h>
@@ -47,12 +48,8 @@
 #include <asm/nmi.h>
 #include <asm/vgtod.h>
 
-static char *timename = NULL;
-
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL(rtc_lock);
-DEFINE_SPINLOCK(i8253_lock);
-EXPORT_SYMBOL(i8253_lock);
 
 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
 
@@ -153,45 +150,12 @@ int update_persistent_clock(struct timespec now)
 	return set_rtc_mmss(now.tv_sec);
 }
 
-void main_timer_handler(void)
+static irqreturn_t timer_event_interrupt(int irq, void *dev_id)
 {
-/*
- * Here we are in the timer irq handler. We have irqs locally disabled (so we
- * don't need spin_lock_irqsave()) but we don't know if the timer_bh is running
- * on the other CPU, so we need a lock. We also need to lock the vsyscall
- * variables, because both do_timer() and us change them -arca+vojtech
- */
-
-	write_seqlock(&xtime_lock);
-
-/*
- * Do the timer stuff.
- */
-
-	do_timer(1);
-#ifndef CONFIG_SMP
-	update_process_times(user_mode(get_irq_regs()));
-#endif
+	add_pda(irq0_irqs, 1);
 
-/*
- * In the SMP case we use the local APIC timer interrupt to do the profiling,
- * except when we simulate SMP mode on a uniprocessor system, in that case we
- * have to call the local interrupt handler.
- */
+	global_clock_event->event_handler(global_clock_event);
 
-	if (!using_apic_timer)
-		smp_local_timer_interrupt();
-
-	write_sequnlock(&xtime_lock);
-}
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	if (apic_runs_main_timer > 1)
-		return IRQ_HANDLED;
-	main_timer_handler();
-	if (using_apic_timer)
-		smp_send_timer_broadcast_ipi();
 	return IRQ_HANDLED;
 }
 
@@ -292,97 +256,21 @@ static unsigned int __init tsc_calibrate_cpu_khz(void)
 	return pmc_now * tsc_khz / (tsc_now - tsc_start);
 }
 
-/*
- * pit_calibrate_tsc() uses the speaker output (channel 2) of
- * the PIT. This is better than using the timer interrupt output,
- * because we can read the value of the speaker with just one inb(),
- * where we need three i/o operations for the interrupt channel.
- * We count how many ticks the TSC does in 50 ms.
- */
-
-static unsigned int __init pit_calibrate_tsc(void)
-{
-	unsigned long start, end;
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8253_lock, flags);
-
-	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
-
-	outb(0xb0, 0x43);
-	outb((PIT_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
-	outb((PIT_TICK_RATE / (1000 / 50)) >> 8, 0x42);
-	start = get_cycles_sync();
-	while ((inb(0x61) & 0x20) == 0);
-	end = get_cycles_sync();
-
-	spin_unlock_irqrestore(&i8253_lock, flags);
-
-	return (end - start) / 50;
-}
-
-#define PIT_MODE 0x43
-#define PIT_CH0  0x40
-
-static void __pit_init(int val, u8 mode)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&i8253_lock, flags);
-	outb_p(mode, PIT_MODE);
-	outb_p(val & 0xff, PIT_CH0);	/* LSB */
-	outb_p(val >> 8, PIT_CH0);	/* MSB */
-	spin_unlock_irqrestore(&i8253_lock, flags);
-}
-
-void __init pit_init(void)
-{
-	__pit_init(LATCH, 0x34); /* binary, mode 2, LSB/MSB, ch 0 */
-}
-
-void pit_stop_interrupt(void)
-{
-	__pit_init(0, 0x30); /* mode 0 */
-}
-
-void stop_timer_interrupt(void)
-{
-	char *name;
-	if (hpet_address) {
-		name = "HPET";
-		hpet_timer_stop_set_go(0);
-	} else {
-		name = "PIT";
-		pit_stop_interrupt();
-	}
-	printk(KERN_INFO "timer: %s interrupt stopped.\n", name);
-}
-
 static struct irqaction irq0 = {
-	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_IRQPOLL,
+	.handler	= timer_event_interrupt,
+	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING,
 	.mask		= CPU_MASK_NONE,
 	.name		= "timer"
 };
 
 void __init time_init(void)
 {
-	if (nohpet)
-		hpet_address = 0;
+	if (!hpet_enable())
+		setup_pit_timer();
 
-	if (hpet_arch_init())
-		hpet_address = 0;
+	setup_irq(0, &irq0);
 
-	if (hpet_use_timer) {
-		/* set tick_nsec to use the proper rate for HPET */
-		tick_nsec = TICK_NSEC_HPET;
-		tsc_khz = hpet_calibrate_tsc();
-		timename = "HPET";
-	} else {
-		pit_init();
-		tsc_khz = pit_calibrate_tsc();
-		timename = "PIT";
-	}
+	tsc_calibrate();
 
 	cpu_khz = tsc_khz;
 	if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
@@ -398,50 +286,7 @@ void __init time_init(void)
 	else
 		vgetcpu_mode = VGETCPU_LSL;
 
-	set_cyc2ns_scale(tsc_khz);
 	printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
 		cpu_khz / 1000, cpu_khz % 1000);
 	init_tsc_clocksource();
-
-	setup_irq(0, &irq0);
-}
-
-/*
- * sysfs support for the timer.
- */
-
-static int timer_suspend(struct sys_device *dev, pm_message_t state)
-{
-	return 0;
-}
-
-static int timer_resume(struct sys_device *dev)
-{
-	if (hpet_address)
-		hpet_reenable();
-	else
-		i8254_timer_resume();
-	return 0;
 }
-
-static struct sysdev_class timer_sysclass = {
-	.resume = timer_resume,
-	.suspend = timer_suspend,
-	set_kset_name("timer"),
-};
-
-/* XXX this sysfs stuff should probably go elsewhere later -john */
-static struct sys_device device_timer = {
-	.id	= 0,
-	.cls	= &timer_sysclass,
-};
-
-static int time_init_device(void)
-{
-	int error = sysdev_class_register(&timer_sysclass);
-	if (!error)
-		error = sysdev_register(&device_timer);
-	return error;
-}
-
-device_initcall(time_init_device);

arch/x86/kernel/tsc_64.c

@@ -6,7 +6,9 @@
 #include <linux/time.h>
 #include <linux/acpi.h>
 #include <linux/cpufreq.h>
+#include <linux/acpi_pmtmr.h>
 
+#include <asm/hpet.h>
 #include <asm/timex.h>
 
 static int notsc __initdata = 0;
@@ -18,7 +20,7 @@ EXPORT_SYMBOL(tsc_khz);
 
 static unsigned int cyc2ns_scale __read_mostly;
 
-void set_cyc2ns_scale(unsigned long khz)
+static inline void set_cyc2ns_scale(unsigned long khz)
 {
 	cyc2ns_scale = (NSEC_PER_MSEC << NS_SCALE) / khz;
 }
@@ -118,6 +120,95 @@ core_initcall(cpufreq_tsc);
 
 #endif
 
+#define MAX_RETRIES	5
+#define SMI_TRESHOLD	50000
+
+/*
+ * Read TSC and the reference counters. Take care of SMI disturbance
+ */
+static unsigned long __init tsc_read_refs(unsigned long *pm,
+					  unsigned long *hpet)
+{
+	unsigned long t1, t2;
+	int i;
+
+	for (i = 0; i < MAX_RETRIES; i++) {
+		t1 = get_cycles_sync();
+		if (hpet)
+			*hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
+		else
+			*pm = acpi_pm_read_early();
+		t2 = get_cycles_sync();
+		if ((t2 - t1) < SMI_TRESHOLD)
+			return t2;
+	}
+	return ULONG_MAX;
+}
+
+/**
+ * tsc_calibrate - calibrate the tsc on boot
+ */
+void __init tsc_calibrate(void)
+{
+	unsigned long flags, tsc1, tsc2, tr1, tr2, pm1, pm2, hpet1, hpet2;
+	int hpet = is_hpet_enabled();
+
+	local_irq_save(flags);
+
+	tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
+
+	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+	outb(0xb0, 0x43);
+	outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
+	outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
+	tr1 = get_cycles_sync();
+	while ((inb(0x61) & 0x20) == 0);
+	tr2 = get_cycles_sync();
+
+	tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+
+	local_irq_restore(flags);
+
+	/*
+	 * Preset the result with the raw and inaccurate PIT
+	 * calibration value
+	 */
+	tsc_khz = (tr2 - tr1) / 50;
+
+	/* hpet or pmtimer available ? */
+	if (!hpet && !pm1 && !pm2) {
+		printk(KERN_INFO "TSC calibrated against PIT\n");
+		return;
+	}
+
+	/* Check, whether the sampling was disturbed by an SMI */
+	if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) {
+		printk(KERN_WARNING "TSC calibration disturbed by SMI, "
+		       "using PIT calibration result\n");
+		return;
+	}
+
+	tsc2 = (tsc2 - tsc1) * 1000000L;
+
+	if (hpet) {
+		printk(KERN_INFO "TSC calibrated against HPET\n");
+		if (hpet2 < hpet1)
+			hpet2 += 0x100000000;
+		hpet2 -= hpet1;
+		tsc1 = (hpet2 * hpet_readl(HPET_PERIOD)) / 1000000;
+	} else {
+		printk(KERN_INFO "TSC calibrated against PM_TIMER\n");
+		if (pm2 < pm1)
+			pm2 += ACPI_PM_OVRRUN;
+		pm2 -= pm1;
+		tsc1 = (pm2 * 1000000000) / PMTMR_TICKS_PER_SEC;
+	}
+
+	tsc_khz = tsc2 / tsc1;
+	set_cyc2ns_scale(tsc_khz);
+}
+
 /*
  * Make an educated guess if the TSC is trustworthy and synchronized
  * over all CPUs.

arch/x86_64/Kconfig

@@ -36,6 +36,18 @@ config GENERIC_CMOS_UPDATE
 	bool
 	default y
 
+config CLOCKSOURCE_WATCHDOG
+	bool
+	default y
+
+config GENERIC_CLOCKEVENTS
+	bool
+	default y
+
+config GENERIC_CLOCKEVENTS_BROADCAST
+	bool
+	default y
+
 config ZONE_DMA32
 	bool
 	default y
@@ -130,6 +142,8 @@ source "init/Kconfig"
 
 menu "Processor type and features"
 
+source "kernel/time/Kconfig"
+
 choice
 	prompt "Subarchitecture Type"
 	default X86_PC

drivers/acpi/processor_idle.c

@@ -276,21 +276,12 @@ static void acpi_timer_check_state(int state, struct acpi_processor *pr,
 
 static void acpi_propagate_timer_broadcast(struct acpi_processor *pr)
 {
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
 	unsigned long reason;
 
 	reason = pr->power.timer_broadcast_on_state < INT_MAX ?
 		CLOCK_EVT_NOTIFY_BROADCAST_ON : CLOCK_EVT_NOTIFY_BROADCAST_OFF;
 
 	clockevents_notify(reason, &pr->id);
-#else
-	cpumask_t mask = cpumask_of_cpu(pr->id);
-
-	if (pr->power.timer_broadcast_on_state < INT_MAX)
-		on_each_cpu(switch_APIC_timer_to_ipi, &mask, 1, 1);
-	else
-		on_each_cpu(switch_ipi_to_APIC_timer, &mask, 1, 1);
-#endif
 }
 
 /* Power(C) State timer broadcast control */
@@ -298,8 +289,6 @@ static void acpi_state_timer_broadcast(struct acpi_processor *pr,
 				       struct acpi_processor_cx *cx,
 				       int broadcast)
 {
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
-
 	int state = cx - pr->power.states;
 
 	if (state >= pr->power.timer_broadcast_on_state) {
@@ -309,7 +298,6 @@ static void acpi_state_timer_broadcast(struct acpi_processor *pr,
 			CLOCK_EVT_NOTIFY_BROADCAST_EXIT;
 		clockevents_notify(reason, &pr->id);
 	}
-#endif
 }
 
 #else

drivers/input/misc/pcspkr.c

@@ -17,7 +17,6 @@
 #include <linux/init.h>
 #include <linux/input.h>
 #include <linux/platform_device.h>
-#include <asm/8253pit.h>
 #include <asm/io.h>
 
 MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
@@ -28,6 +27,7 @@ MODULE_LICENSE("GPL");
 /* Use the global PIT lock ! */
 #include <asm/i8253.h>
 #else
+#include <asm/8253pit.h>
 static DEFINE_SPINLOCK(i8253_lock);
 #endif
 

include/asm-x86/8253pit.h

-#ifdef CONFIG_X86_32
-# include "8253pit_32.h"
-#else
-# include "8253pit_64.h"
-#endif

include/asm-x86/8253pit_32.h

-/*
- * 8253/8254 Programmable Interval Timer
- */
-
-#ifndef _8253PIT_H
-#define _8253PIT_H
-
-#include <asm/timex.h>
-
-#define PIT_TICK_RATE 	CLOCK_TICK_RATE
-
-#endif

include/asm-x86/8253pit_64.h

-/*
- * 8253/8254 Programmable Interval Timer
- */
-
-#ifndef _8253PIT_H
-#define _8253PIT_H
-
-#define PIT_TICK_RATE 	1193182UL
-
-#endif

include/asm-x86/apic_64.h

@@ -19,7 +19,7 @@
 extern int apic_verbosity;
 extern int apic_runs_main_timer;
 extern int ioapic_force;
-extern int apic_mapped;
+extern int disable_apic_timer;
 
 /*
  * Define the default level of output to be very little
@@ -79,8 +79,6 @@ extern void smp_local_timer_interrupt (void);
 extern void setup_boot_APIC_clock (void);
 extern void setup_secondary_APIC_clock (void);
 extern int APIC_init_uniprocessor (void);
-extern void disable_APIC_timer(void);
-extern void enable_APIC_timer(void);
 extern void setup_apic_routing(void);
 
 extern void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
@@ -95,10 +93,6 @@ extern int apic_is_clustered_box(void);
 #define K8_APIC_EXT_INT_MSG_EXT 0x7
 #define K8_APIC_EXT_LVT_ENTRY_THRESHOLD    0
 
-void smp_send_timer_broadcast_ipi(void);
-void switch_APIC_timer_to_ipi(void *cpumask);
-void switch_ipi_to_APIC_timer(void *cpumask);
-
 #define ARCH_APICTIMER_STOPS_ON_C3	1
 
 extern unsigned boot_cpu_id;

include/asm-x86/geode.h

@@ -156,4 +156,54 @@ static inline int is_geode(void)
 	return (is_geode_gx() || is_geode_lx());
 }
 
+/* MFGPTs */
+
+#define MFGPT_MAX_TIMERS	8
+#define MFGPT_TIMER_ANY		-1
+
+#define MFGPT_DOMAIN_WORKING	1
+#define MFGPT_DOMAIN_STANDBY	2
+#define MFGPT_DOMAIN_ANY	(MFGPT_DOMAIN_WORKING | MFGPT_DOMAIN_STANDBY)
+
+#define MFGPT_CMP1		0
+#define MFGPT_CMP2		1
+
+#define MFGPT_EVENT_IRQ		0
+#define MFGPT_EVENT_NMI		1
+#define MFGPT_EVENT_RESET	3
+
+#define MFGPT_REG_CMP1		0
+#define MFGPT_REG_CMP2		2
+#define MFGPT_REG_COUNTER	4
+#define MFGPT_REG_SETUP		6
+
+#define MFGPT_SETUP_CNTEN	(1 << 15)
+#define MFGPT_SETUP_CMP2	(1 << 14)
+#define MFGPT_SETUP_CMP1	(1 << 13)
+#define MFGPT_SETUP_SETUP	(1 << 12)
+#define MFGPT_SETUP_STOPEN	(1 << 11)
+#define MFGPT_SETUP_EXTEN	(1 << 10)
+#define MFGPT_SETUP_REVEN	(1 << 5)
+#define MFGPT_SETUP_CLKSEL	(1 << 4)
+
+static inline void geode_mfgpt_write(int timer, u16 reg, u16 value)
+{
+	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
+	outw(value, base + reg + (timer * 8));
+}
+
+static inline u16 geode_mfgpt_read(int timer, u16 reg)
+{
+	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
+	return inw(base + reg + (timer * 8));
+}
+
+extern int __init geode_mfgpt_detect(void);
+extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable);
+extern int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable);
+extern int geode_mfgpt_alloc_timer(int timer, int domain, struct module *owner);
+
+#define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1)
+#define geode_mfgpt_release_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 0)
+
 #endif

include/asm-x86/hardirq_32.h

@@ -9,6 +9,7 @@ typedef struct {
 	unsigned long idle_timestamp;
 	unsigned int __nmi_count;	/* arch dependent */
 	unsigned int apic_timer_irqs;	/* arch dependent */
+	unsigned int irq0_irqs;
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU(irq_cpustat_t, irq_stat);

include/asm-x86/hpet.h

-#ifdef CONFIG_X86_32
-# include "hpet_32.h"
+#ifndef ASM_X86_HPET_H
+#define ASM_X86_HPET_H
+
+#ifdef CONFIG_HPET_TIMER
+
+/*
+ * Documentation on HPET can be found at:
+ *      http://www.intel.com/ial/home/sp/pcmmspec.htm
+ *      ftp://download.intel.com/ial/home/sp/mmts098.pdf
+ */
+
+#define HPET_MMAP_SIZE		1024
+
+#define HPET_ID			0x000
+#define HPET_PERIOD		0x004
+#define HPET_CFG		0x010
+#define HPET_STATUS		0x020
+#define HPET_COUNTER		0x0f0
+#define HPET_T0_CFG		0x100
+#define HPET_T0_CMP		0x108
+#define HPET_T0_ROUTE		0x110
+#define HPET_T1_CFG		0x120
+#define HPET_T1_CMP		0x128
+#define HPET_T1_ROUTE		0x130
+#define HPET_T2_CFG		0x140
+#define HPET_T2_CMP		0x148
+#define HPET_T2_ROUTE		0x150
+
+#define HPET_ID_REV		0x000000ff
+#define HPET_ID_NUMBER		0x00001f00
+#define HPET_ID_64BIT		0x00002000
+#define HPET_ID_LEGSUP		0x00008000
+#define HPET_ID_VENDOR		0xffff0000
+#define	HPET_ID_NUMBER_SHIFT	8
+#define HPET_ID_VENDOR_SHIFT	16
+
+#define HPET_ID_VENDOR_8086	0x8086
+
+#define HPET_CFG_ENABLE		0x001
+#define HPET_CFG_LEGACY		0x002
+#define	HPET_LEGACY_8254	2
+#define	HPET_LEGACY_RTC		8
+
+#define HPET_TN_LEVEL		0x0002
+#define HPET_TN_ENABLE		0x0004
+#define HPET_TN_PERIODIC	0x0008
+#define HPET_TN_PERIODIC_CAP	0x0010
+#define HPET_TN_64BIT_CAP	0x0020
+#define HPET_TN_SETVAL		0x0040
+#define HPET_TN_32BIT		0x0100
+#define HPET_TN_ROUTE		0x3e00
+#define HPET_TN_FSB		0x4000
+#define HPET_TN_FSB_CAP		0x8000
+#define HPET_TN_ROUTE_SHIFT	9
+
+/* Max HPET Period is 10^8 femto sec as in HPET spec */
+#define HPET_MAX_PERIOD		100000000UL
+/*
+ * Min HPET period is 10^5 femto sec just for safety. If it is less than this,
+ * then 32 bit HPET counter wrapsaround in less than 0.5 sec.
+ */
+#define HPET_MIN_PERIOD		100000UL
+
+/* hpet memory map physical address */
+extern unsigned long hpet_address;
+extern unsigned long force_hpet_address;
+extern int is_hpet_enabled(void);
+extern int hpet_enable(void);
+extern unsigned long hpet_readl(unsigned long a);
+extern void force_hpet_resume(void);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+
+#include <linux/interrupt.h>
+
+extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask);
+extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
+extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
+			       unsigned char sec);
+extern int hpet_set_periodic_freq(unsigned long freq);
+extern int hpet_rtc_dropped_irq(void);
+extern int hpet_rtc_timer_init(void);
+extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id);
+
+#endif /* CONFIG_HPET_EMULATE_RTC */
+
 #else
-# include "hpet_64.h"
-#endif
+
+static inline int hpet_enable(void) { return 0; }
+static inline unsigned long hpet_readl(unsigned long a) { return 0; }
+
+#endif /* CONFIG_HPET_TIMER */
+#endif /* ASM_X86_HPET_H */

include/asm-x86/hpet_32.h

-
-#ifndef _I386_HPET_H
-#define _I386_HPET_H
-
-#ifdef CONFIG_HPET_TIMER
-
-/*
- * Documentation on HPET can be found at:
- *      http://www.intel.com/ial/home/sp/pcmmspec.htm
- *      ftp://download.intel.com/ial/home/sp/mmts098.pdf
- */
-
-#define HPET_MMAP_SIZE		1024
-
-#define HPET_ID			0x000
-#define HPET_PERIOD		0x004
-#define HPET_CFG		0x010
-#define HPET_STATUS		0x020
-#define HPET_COUNTER		0x0f0
-#define HPET_T0_CFG		0x100
-#define HPET_T0_CMP		0x108
-#define HPET_T0_ROUTE		0x110
-#define HPET_T1_CFG		0x120
-#define HPET_T1_CMP		0x128
-#define HPET_T1_ROUTE		0x130
-#define HPET_T2_CFG		0x140
-#define HPET_T2_CMP		0x148
-#define HPET_T2_ROUTE		0x150
-
-#define HPET_ID_REV		0x000000ff
-#define HPET_ID_NUMBER		0x00001f00
-#define HPET_ID_64BIT		0x00002000
-#define HPET_ID_LEGSUP		0x00008000
-#define HPET_ID_VENDOR		0xffff0000
-#define	HPET_ID_NUMBER_SHIFT	8
-#define HPET_ID_VENDOR_SHIFT	16
-
-#define HPET_ID_VENDOR_8086	0x8086
-
-#define HPET_CFG_ENABLE		0x001
-#define HPET_CFG_LEGACY		0x002
-#define	HPET_LEGACY_8254	2
-#define	HPET_LEGACY_RTC		8
-
-#define HPET_TN_LEVEL		0x0002
-#define HPET_TN_ENABLE		0x0004
-#define HPET_TN_PERIODIC	0x0008
-#define HPET_TN_PERIODIC_CAP	0x0010
-#define HPET_TN_64BIT_CAP	0x0020
-#define HPET_TN_SETVAL		0x0040
-#define HPET_TN_32BIT		0x0100
-#define HPET_TN_ROUTE		0x3e00
-#define HPET_TN_FSB		0x4000
-#define HPET_TN_FSB_CAP		0x8000
-#define HPET_TN_ROUTE_SHIFT	9
-
-/* Max HPET Period is 10^8 femto sec as in HPET spec */
-#define HPET_MAX_PERIOD		100000000UL
-/*
- * Min HPET period is 10^5 femto sec just for safety. If it is less than this,
- * then 32 bit HPET counter wrapsaround in less than 0.5 sec.
- */
-#define HPET_MIN_PERIOD		100000UL
-
-/* hpet memory map physical address */
-extern unsigned long hpet_address;
-extern int is_hpet_enabled(void);
-extern int hpet_enable(void);
-
-#ifdef CONFIG_HPET_EMULATE_RTC
-
-#include <linux/interrupt.h>
-
-extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask);
-extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
-extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
-			       unsigned char sec);
-extern int hpet_set_periodic_freq(unsigned long freq);
-extern int hpet_rtc_dropped_irq(void);
-extern int hpet_rtc_timer_init(void);
-extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id);
-
-#endif /* CONFIG_HPET_EMULATE_RTC */
-
-#else
-
-static inline int hpet_enable(void) { return 0; }
-
-#endif /* CONFIG_HPET_TIMER */
-#endif /* _I386_HPET_H */

include/asm-x86/hpet_64.h

-#ifndef _ASM_X8664_HPET_H
-#define _ASM_X8664_HPET_H 1
-
-#include <asm/hpet_32.h>
-
-#define HPET_TICK_RATE (HZ * 100000UL)
-
-extern int hpet_rtc_timer_init(void);
-extern int hpet_arch_init(void);
-extern int hpet_timer_stop_set_go(unsigned long tick);
-extern int hpet_reenable(void);
-extern unsigned int hpet_calibrate_tsc(void);
-
-extern int hpet_use_timer;
-extern unsigned long hpet_period;
-extern unsigned long hpet_tick;
-
-#endif

include/asm-x86/i8253.h

-#ifdef CONFIG_X86_32
-# include "i8253_32.h"
-#else
-# include "i8253_64.h"
-#endif
+#ifndef __ASM_I8253_H__
+#define __ASM_I8253_H__
+
+/* i8253A PIT registers */
+#define PIT_MODE		0x43
+#define PIT_CH0			0x40
+#define PIT_CH2			0x42
+
+extern spinlock_t i8253_lock;
+
+extern struct clock_event_device *global_clock_event;
+
+extern void setup_pit_timer(void);
+
+#endif	/* __ASM_I8253_H__ */

include/asm-x86/i8253_32.h

-#ifndef __ASM_I8253_H__
-#define __ASM_I8253_H__
-
-#include <linux/clockchips.h>
-
-/* i8253A PIT registers */
-#define PIT_MODE		0x43
-#define PIT_CH0			0x40
-#define PIT_CH2			0x42
-
-extern spinlock_t i8253_lock;
-
-extern struct clock_event_device *global_clock_event;
-
-extern void setup_pit_timer(void);
-
-#endif	/* __ASM_I8253_H__ */

include/asm-x86/i8253_64.h

-#ifndef __ASM_I8253_H__
-#define __ASM_I8253_H__
-
-extern spinlock_t i8253_lock;
-
-#endif	/* __ASM_I8253_H__ */

include/asm-x86/pda.h

@@ -29,6 +29,7 @@ struct x8664_pda {
 	short isidle;
 	struct mm_struct *active_mm;
 	unsigned apic_timer_irqs;
+	unsigned irq0_irqs;
 } ____cacheline_aligned_in_smp;
 
 extern struct x8664_pda *_cpu_pda[];

include/asm-x86/proto.h

@@ -51,9 +51,6 @@ extern void reserve_bootmem_generic(unsigned long phys, unsigned len);
 
 extern void load_gs_index(unsigned gs);
 
-extern void stop_timer_interrupt(void);
-extern void main_timer_handler(void);
-
 extern unsigned long end_pfn_map; 
 
 extern void show_trace(struct task_struct *, struct pt_regs *, unsigned long * rsp);
@@ -90,14 +87,10 @@ extern int timer_over_8254;
 
 extern int gsi_irq_sharing(int gsi);
 
-extern void smp_local_timer_interrupt(void);
-
 extern int force_mwait;
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
-void i8254_timer_resume(void);
-
 #define round_up(x,y) (((x) + (y) - 1) & ~((y)-1))
 #define round_down(x,y) ((x) & ~((y)-1))
 

include/asm-x86/timex.h

-#ifdef CONFIG_X86_32
-# include "timex_32.h"
+/* x86 architecture timex specifications */
+#ifndef _ASM_X86_TIMEX_H
+#define _ASM_X86_TIMEX_H
+
+#include <asm/processor.h>
+#include <asm/tsc.h>
+
+#ifdef CONFIG_X86_ELAN
+#  define PIT_TICK_RATE 1189200 /* AMD Elan has different frequency! */
 #else
-# include "timex_64.h"
+#  define PIT_TICK_RATE 1193182 /* Underlying HZ */
+#endif
+#define CLOCK_TICK_RATE	PIT_TICK_RATE
+
+extern int read_current_timer(unsigned long *timer_value);
+#define ARCH_HAS_READ_CURRENT_TIMER	1
+
 #endif

include/asm-x86/timex_32.h

-/*
- * linux/include/asm-i386/timex.h
- *
- * i386 architecture timex specifications
- */
-#ifndef _ASMi386_TIMEX_H
-#define _ASMi386_TIMEX_H
-
-#include <asm/processor.h>
-#include <asm/tsc.h>
-
-#ifdef CONFIG_X86_ELAN
-#  define CLOCK_TICK_RATE 1189200 /* AMD Elan has different frequency! */
-#else
-#  define CLOCK_TICK_RATE 1193182 /* Underlying HZ */
-#endif
-
-
-extern int read_current_timer(unsigned long *timer_value);
-#define ARCH_HAS_READ_CURRENT_TIMER	1
-
-#endif

include/asm-x86/timex_64.h

-/*
- * linux/include/asm-x86_64/timex.h
- *
- * x86-64 architecture timex specifications
- */
-#ifndef _ASMx8664_TIMEX_H
-#define _ASMx8664_TIMEX_H
-
-#include <asm/8253pit.h>
-#include <asm/msr.h>
-#include <asm/vsyscall.h>
-#include <asm/system.h>
-#include <asm/processor.h>
-#include <asm/tsc.h>
-#include <linux/compiler.h>
-
-#define CLOCK_TICK_RATE	PIT_TICK_RATE	/* Underlying HZ */
-
-extern int read_current_timer(unsigned long *timer_value);
-#define ARCH_HAS_READ_CURRENT_TIMER	1
-
-#define USEC_PER_TICK (USEC_PER_SEC / HZ)
-#define NSEC_PER_TICK (NSEC_PER_SEC / HZ)
-#define FSEC_PER_TICK (FSEC_PER_SEC / HZ)
-
-#define NS_SCALE        10 /* 2^10, carefully chosen */
-#define US_SCALE        32 /* 2^32, arbitralrily chosen */
-
-extern void mark_tsc_unstable(char *msg);
-extern void set_cyc2ns_scale(unsigned long khz);
-#endif

include/asm-x86/tsc.h

 /*
- * linux/include/asm-i386/tsc.h
- *
- * i386 TSC related functions
+ * x86 TSC related functions
  */
-#ifndef _ASM_i386_TSC_H
-#define _ASM_i386_TSC_H
+#ifndef _ASM_X86_TSC_H
+#define _ASM_X86_TSC_H
 
 #include <asm/processor.h>
 
+#define NS_SCALE	10 /* 2^10, carefully chosen */
+#define US_SCALE	32 /* 2^32, arbitralrily chosen */
+
 /*
  * Standard way to access the cycle counter.
  */
@@ -72,4 +73,8 @@ int check_tsc_unstable(void);
 extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 
+#ifdef CONFIG_X86_64
+extern void tsc_calibrate(void);
+#endif
+
 #endif

include/asm-x86/vsyscall.h

@@ -29,9 +29,6 @@ enum vsyscall_num {
 #define VGETCPU_RDTSCP	1
 #define VGETCPU_LSL	2
 
-#define hpet_readl(a)           readl((const void __iomem *)fix_to_virt(FIX_HPET_BASE) + a)
-#define hpet_writel(d,a)        writel(d, (void __iomem *)fix_to_virt(FIX_HPET_BASE) + a)
-
 extern int __vgetcpu_mode;
 extern volatile unsigned long __jiffies;
 

include/linux/clockchips.h

@@ -8,7 +8,7 @@
 #ifndef _LINUX_CLOCKCHIPS_H
 #define _LINUX_CLOCKCHIPS_H
 
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
 
 #include <linux/clocksource.h>
 #include <linux/cpumask.h>
@@ -126,11 +126,14 @@ extern int clockevents_register_notifier(struct notifier_block *nb);
 extern int clockevents_program_event(struct clock_event_device *dev,
 				     ktime_t expires, ktime_t now);
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern void clockevents_notify(unsigned long reason, void *arg);
-
 #else
+# define clockevents_notify(reason, arg) do { } while (0)
+#endif
+
+#else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */
 
-static inline void clockevents_resume_events(void) { }
 #define clockevents_notify(reason, arg) do { } while (0)
 
 #endif

include/linux/jiffies.h

@@ -36,8 +36,6 @@
 /* LATCH is used in the interval timer and ftape setup. */
 #define LATCH  ((CLOCK_TICK_RATE + HZ/2) / HZ)	/* For divider */
 
-#define LATCH_HPET ((HPET_TICK_RATE + HZ/2) / HZ)
-
 /* Suppose we want to devide two numbers NOM and DEN: NOM/DEN, the we can
  * improve accuracy by shifting LSH bits, hence calculating:
  *     (NOM << LSH) / DEN
@@ -53,13 +51,9 @@
 /* HZ is the requested value. ACTHZ is actual HZ ("<< 8" is for accuracy) */
 #define ACTHZ (SH_DIV (CLOCK_TICK_RATE, LATCH, 8))
 
-#define ACTHZ_HPET (SH_DIV (HPET_TICK_RATE, LATCH_HPET, 8))
-
 /* TICK_NSEC is the time between ticks in nsec assuming real ACTHZ */
 #define TICK_NSEC (SH_DIV (1000000UL * 1000, ACTHZ, 8))
 
-#define TICK_NSEC_HPET (SH_DIV(1000000UL * 1000, ACTHZ_HPET, 8))
-
 /* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */
 #define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ)
 

include/linux/pci_ids.h

@@ -2242,6 +2242,7 @@
 #define PCI_DEVICE_ID_INTEL_82801EB_5	0x24d5
 #define PCI_DEVICE_ID_INTEL_82801EB_6	0x24d6
 #define PCI_DEVICE_ID_INTEL_82801EB_11	0x24db
+#define PCI_DEVICE_ID_INTEL_82801EB_12	0x24dc
 #define PCI_DEVICE_ID_INTEL_82801EB_13	0x24dd
 #define PCI_DEVICE_ID_INTEL_ESB_1	0x25a1
 #define PCI_DEVICE_ID_INTEL_ESB_2	0x25a2

kernel/time/Kconfig

@@ -23,3 +23,8 @@ config HIGH_RES_TIMERS
 	  hardware is not capable then this option only increases
 	  the size of the kernel image.
 
+config GENERIC_CLOCKEVENTS_BUILD
+	bool
+	default y
+	depends on GENERIC_CLOCKEVENTS || GENERIC_CLOCKEVENTS_MIGR
+

kernel/time/Makefile

 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
 
-obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= clockevents.o
+obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= tick-broadcast.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o

kernel/time/clockevents.c

@@ -194,6 +194,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
 /**
  * clockevents_notify - notification about relevant events
  */
@@ -222,4 +223,4 @@ void clockevents_notify(unsigned long reason, void *arg)
 	spin_unlock(&clockevents_lock);
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
-
+#endif

kernel/time/tick-broadcast.c

@@ -64,7 +64,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
  */
 int tick_check_broadcast_device(struct clock_event_device *dev)
 {
-	if (tick_broadcast_device.evtdev ||
+	if ((tick_broadcast_device.evtdev &&
+	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
@@ -176,8 +177,6 @@ static void tick_do_periodic_broadcast(void)
  */
 static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
-	dev->next_event.tv64 = KTIME_MAX;
-
 	tick_do_periodic_broadcast();
 
 	/*
@@ -515,11 +514,9 @@ static void tick_broadcast_clear_oneshot(int cpu)
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
-	if (bc->mode != CLOCK_EVT_MODE_ONESHOT) {
 	bc->event_handler = tick_handle_oneshot_broadcast;
 	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 	bc->next_event.tv64 = KTIME_MAX;
-	}
 }
 
 /*

kernel/time/tick-common.c

@@ -200,7 +200,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 
 	cpu = smp_processor_id();
 	if (!cpu_isset(cpu, newdev->cpumask))
-		goto out;
+		goto out_bc;
 
 	td = &per_cpu(tick_cpu_device, cpu);
 	curdev = td->evtdev;
@@ -265,7 +265,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	 */
 	if (tick_check_broadcast_device(newdev))
 		ret = NOTIFY_STOP;
-out:
+
 	spin_unlock_irqrestore(&tick_device_lock, flags);
 
 	return ret;