21 files changed, 194 insertions, 418 deletions

diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b117efd24f7..8a439d364b9 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -30,7 +30,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/io.h>
 #include <linux/gfp.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/mtrr.h>
 #include <asm/pgtable.h>
 #include <asm/proto.h>
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 2b6630d75e1..afdc3f756de 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -27,15 +27,12 @@
  * timer, but by default APB timer has higher rating than local APIC timers.
  */
 
-#include <linux/clocksource.h>
-#include <linux/clockchips.h>
 #include <linux/delay.h>
+#include <linux/dw_apb_timer.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/sysdev.h>
 #include <linux/slab.h>
 #include <linux/pm.h>
-#include <linux/pci.h>
 #include <linux/sfi.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
@@ -46,75 +43,46 @@
 #include <asm/mrst.h>
 #include <asm/time.h>
 
-#define APBT_MASK			CLOCKSOURCE_MASK(32)
-#define APBT_SHIFT			22
 #define APBT_CLOCKEVENT_RATING		110
 #define APBT_CLOCKSOURCE_RATING		250
-#define APBT_MIN_DELTA_USEC		200
 
-#define EVT_TO_APBT_DEV(evt) container_of(evt, struct apbt_dev, evt)
 #define APBT_CLOCKEVENT0_NUM   (0)
-#define APBT_CLOCKEVENT1_NUM   (1)
 #define APBT_CLOCKSOURCE_NUM   (2)
 
-static unsigned long apbt_address;
+static phys_addr_t apbt_address;
 static int apb_timer_block_enabled;
 static void __iomem *apbt_virt_address;
-static int phy_cs_timer_id;
 
 /*
  * Common DW APB timer info
  */
-static uint64_t apbt_freq;
-
-static void apbt_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt);
-static int apbt_next_event(unsigned long delta,
-			   struct clock_event_device *evt);
-static cycle_t apbt_read_clocksource(struct clocksource *cs);
-static void apbt_restart_clocksource(struct clocksource *cs);
+static unsigned long apbt_freq;
 
 struct apbt_dev {
-	struct clock_event_device evt;
-	unsigned int num;
-	int cpu;
-	unsigned int irq;
-	unsigned int tick;
-	unsigned int count;
-	unsigned int flags;
-	char name[10];
+	struct dw_apb_clock_event_device	*timer;
+	unsigned int				num;
+	int					cpu;
+	unsigned int				irq;
+	char					name[10];
 };
 
-static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev);
+static struct dw_apb_clocksource *clocksource_apbt;
 
-#ifdef CONFIG_SMP
-static unsigned int apbt_num_timers_used;
-static struct apbt_dev *apbt_devs;
-#endif
-
-static	inline unsigned long apbt_readl_reg(unsigned long a)
+static inline void __iomem *adev_virt_addr(struct apbt_dev *adev)
 {
-	return readl(apbt_virt_address + a);
+	return apbt_virt_address + adev->num * APBTMRS_REG_SIZE;
 }
 
-static inline void apbt_writel_reg(unsigned long d, unsigned long a)
-{
-	writel(d, apbt_virt_address + a);
-}
-
-static inline unsigned long apbt_readl(int n, unsigned long a)
-{
-	return readl(apbt_virt_address + a + n * APBTMRS_REG_SIZE);
-}
+static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev);
 
-static inline void apbt_writel(int n, unsigned long d, unsigned long a)
-{
-	writel(d, apbt_virt_address + a + n * APBTMRS_REG_SIZE);
-}
+#ifdef CONFIG_SMP
+static unsigned int apbt_num_timers_used;
+#endif
 
 static inline void apbt_set_mapping(void)
 {
 	struct sfi_timer_table_entry *mtmr;
+	int phy_cs_timer_id = 0;
 
 	if (apbt_virt_address) {
 		pr_debug("APBT base already mapped\n");
@@ -126,21 +94,18 @@ static inline void apbt_set_mapping(void)
 		       APBT_CLOCKEVENT0_NUM);
 		return;
 	}
-	apbt_address = (unsigned long)mtmr->phys_addr;
+	apbt_address = (phys_addr_t)mtmr->phys_addr;
 	if (!apbt_address) {
 		printk(KERN_WARNING "No timer base from SFI, use default\n");
 		apbt_address = APBT_DEFAULT_BASE;
 	}
 	apbt_virt_address = ioremap_nocache(apbt_address, APBT_MMAP_SIZE);
-	if (apbt_virt_address) {
-		pr_debug("Mapped APBT physical addr %p at virtual addr %p\n",\
-			 (void *)apbt_address, (void *)apbt_virt_address);
-	} else {
-		pr_debug("Failed mapping APBT phy address at %p\n",\
-			 (void *)apbt_address);
+	if (!apbt_virt_address) {
+		pr_debug("Failed mapping APBT phy address at %lu\n",\
+			 (unsigned long)apbt_address);
 		goto panic_noapbt;
 	}
-	apbt_freq = mtmr->freq_hz / USEC_PER_SEC;
+	apbt_freq = mtmr->freq_hz;
 	sfi_free_mtmr(mtmr);
 
 	/* Now figure out the physical timer id for clocksource device */
@@ -149,9 +114,14 @@ static inline void apbt_set_mapping(void)
 		goto panic_noapbt;
 
 	/* Now figure out the physical timer id */
-	phy_cs_timer_id = (unsigned int)(mtmr->phys_addr & 0xff)
-		/ APBTMRS_REG_SIZE;
-	pr_debug("Use timer %d for clocksource\n", phy_cs_timer_id);
+	pr_debug("Use timer %d for clocksource\n",
+		 (int)(mtmr->phys_addr & 0xff) / APBTMRS_REG_SIZE);
+	phy_cs_timer_id = (unsigned int)(mtmr->phys_addr & 0xff) /
+		APBTMRS_REG_SIZE;
+
+	clocksource_apbt = dw_apb_clocksource_init(APBT_CLOCKSOURCE_RATING,
+		"apbt0", apbt_virt_address + phy_cs_timer_id *
+		APBTMRS_REG_SIZE, apbt_freq);
 	return;
 
 panic_noapbt:
@@ -173,82 +143,6 @@ static inline int is_apbt_capable(void)
 	return apbt_virt_address ? 1 : 0;
 }
 
-static struct clocksource clocksource_apbt = {
-	.name		= "apbt",
-	.rating		= APBT_CLOCKSOURCE_RATING,
-	.read		= apbt_read_clocksource,
-	.mask		= APBT_MASK,
-	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-	.resume		= apbt_restart_clocksource,
-};
-
-/* boot APB clock event device */
-static struct clock_event_device apbt_clockevent = {
-	.name		= "apbt0",
-	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-	.set_mode	= apbt_set_mode,
-	.set_next_event = apbt_next_event,
-	.shift		= APBT_SHIFT,
-	.irq		= 0,
-	.rating		= APBT_CLOCKEVENT_RATING,
-};
-
-/*
- * start count down from 0xffff_ffff. this is done by toggling the enable bit
- * then load initial load count to ~0.
- */
-static void apbt_start_counter(int n)
-{
-	unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
-
-	ctrl &= ~APBTMR_CONTROL_ENABLE;
-	apbt_writel(n, ctrl, APBTMR_N_CONTROL);
-	apbt_writel(n, ~0, APBTMR_N_LOAD_COUNT);
-	/* enable, mask interrupt */
-	ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC;
-	ctrl |= (APBTMR_CONTROL_ENABLE | APBTMR_CONTROL_INT);
-	apbt_writel(n, ctrl, APBTMR_N_CONTROL);
-	/* read it once to get cached counter value initialized */
-	apbt_read_clocksource(&clocksource_apbt);
-}
-
-static irqreturn_t apbt_interrupt_handler(int irq, void *data)
-{
-	struct apbt_dev *dev = (struct apbt_dev *)data;
-	struct clock_event_device *aevt = &dev->evt;
-
-	if (!aevt->event_handler) {
-		printk(KERN_INFO "Spurious APBT timer interrupt on %d\n",
-		       dev->num);
-		return IRQ_NONE;
-	}
-	aevt->event_handler(aevt);
-	return IRQ_HANDLED;
-}
-
-static void apbt_restart_clocksource(struct clocksource *cs)
-{
-	apbt_start_counter(phy_cs_timer_id);
-}
-
-static void apbt_enable_int(int n)
-{
-	unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
-	/* clear pending intr */
-	apbt_readl(n, APBTMR_N_EOI);
-	ctrl &= ~APBTMR_CONTROL_INT;
-	apbt_writel(n, ctrl, APBTMR_N_CONTROL);
-}
-
-static void apbt_disable_int(int n)
-{
-	unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
-
-	ctrl |= APBTMR_CONTROL_INT;
-	apbt_writel(n, ctrl, APBTMR_N_CONTROL);
-}
-
-
 static int __init apbt_clockevent_register(void)
 {
 	struct sfi_timer_table_entry *mtmr;
@@ -261,45 +155,21 @@ static int __init apbt_clockevent_register(void)
 		return -ENODEV;
 	}
 
-	/*
-	 * We need to calculate the scaled math multiplication factor for
-	 * nanosecond to apbt tick conversion.
-	 * mult = (nsec/cycle)*2^APBT_SHIFT
-	 */
-	apbt_clockevent.mult = div_sc((unsigned long) mtmr->freq_hz
-				      , NSEC_PER_SEC, APBT_SHIFT);
-
-	/* Calculate the min / max delta */
-	apbt_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
-							   &apbt_clockevent);
-	apbt_clockevent.min_delta_ns = clockevent_delta2ns(
-		APBT_MIN_DELTA_USEC*apbt_freq,
-		&apbt_clockevent);
-	/*
-	 * Start apbt with the boot cpu mask and make it
-	 * global if not used for per cpu timer.
-	 */
-	apbt_clockevent.cpumask = cpumask_of(smp_processor_id());
 	adev->num = smp_processor_id();
-	memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device));
+	adev->timer = dw_apb_clockevent_init(smp_processor_id(), "apbt0",
+		mrst_timer_options == MRST_TIMER_LAPIC_APBT ?
+		APBT_CLOCKEVENT_RATING - 100 : APBT_CLOCKEVENT_RATING,
+		adev_virt_addr(adev), 0, apbt_freq);
+	/* Firmware does EOI handling for us. */
+	adev->timer->eoi = NULL;
 
 	if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) {
-		adev->evt.rating = APBT_CLOCKEVENT_RATING - 100;
-		global_clock_event = &adev->evt;
+		global_clock_event = &adev->timer->ced;
 		printk(KERN_DEBUG "%s clockevent registered as global\n",
 		       global_clock_event->name);
 	}
 
-	if (request_irq(apbt_clockevent.irq, apbt_interrupt_handler,
-			IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
-			apbt_clockevent.name, adev)) {
-		printk(KERN_ERR "Failed request IRQ for APBT%d\n",
-		       apbt_clockevent.irq);
-	}
-
-	clockevents_register_device(&adev->evt);
-	/* Start APBT 0 interrupts */
-	apbt_enable_int(APBT_CLOCKEVENT0_NUM);
+	dw_apb_clockevent_register(adev->timer);
 
 	sfi_free_mtmr(mtmr);
 	return 0;
@@ -317,52 +187,34 @@ static void apbt_setup_irq(struct apbt_dev *adev)
 	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
 	/* APB timer irqs are set up as mp_irqs, timer is edge type */
 	__irq_set_handler(adev->irq, handle_edge_irq, 0, "edge");
-
-	if (system_state == SYSTEM_BOOTING) {
-		if (request_irq(adev->irq, apbt_interrupt_handler,
-					IRQF_TIMER | IRQF_DISABLED |
-					IRQF_NOBALANCING,
-					adev->name, adev)) {
-			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
-			       adev->num);
-		}
-	} else
-		enable_irq(adev->irq);
 }
 
 /* Should be called with per cpu */
 void apbt_setup_secondary_clock(void)
 {
 	struct apbt_dev *adev;
-	struct clock_event_device *aevt;
 	int cpu;
 
 	/* Don't register boot CPU clockevent */
 	cpu = smp_processor_id();
 	if (!cpu)
 		return;
-	/*
-	 * We need to calculate the scaled math multiplication factor for
-	 * nanosecond to apbt tick conversion.
-	 * mult = (nsec/cycle)*2^APBT_SHIFT
-	 */
-	printk(KERN_INFO "Init per CPU clockevent %d\n", cpu);
-	adev = &per_cpu(cpu_apbt_dev, cpu);
-	aevt = &adev->evt;
 
-	memcpy(aevt, &apbt_clockevent, sizeof(*aevt));
-	aevt->cpumask = cpumask_of(cpu);
-	aevt->name = adev->name;
-	aevt->mode = CLOCK_EVT_MODE_UNUSED;
+	adev = &__get_cpu_var(cpu_apbt_dev);
+	if (!adev->timer) {
+		adev->timer = dw_apb_clockevent_init(cpu, adev->name,
+			APBT_CLOCKEVENT_RATING, adev_virt_addr(adev),
+			adev->irq, apbt_freq);
+		adev->timer->eoi = NULL;
+	} else {
+		dw_apb_clockevent_resume(adev->timer);
+	}
 
-	printk(KERN_INFO "Registering CPU %d clockevent device %s, mask %08x\n",
-	       cpu, aevt->name, *(u32 *)aevt->cpumask);
+	printk(KERN_INFO "Registering CPU %d clockevent device %s, cpu %08x\n",
+	       cpu, adev->name, adev->cpu);
 
 	apbt_setup_irq(adev);
-
-	clockevents_register_device(aevt);
-
-	apbt_enable_int(cpu);
+	dw_apb_clockevent_register(adev->timer);
 
 	return;
 }
@@ -385,13 +237,12 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 
 	switch (action & 0xf) {
 	case CPU_DEAD:
-		disable_irq(adev->irq);
-		apbt_disable_int(cpu);
+		dw_apb_clockevent_pause(adev->timer);
 		if (system_state == SYSTEM_RUNNING) {
 			pr_debug("skipping APBT CPU %lu offline\n", cpu);
 		} else if (adev) {
 			pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
-			free_irq(adev->irq, adev);
+			dw_apb_clockevent_stop(adev->timer);
 		}
 		break;
 	default:
@@ -416,116 +267,16 @@ void apbt_setup_secondary_clock(void) {}
 
 #endif /* CONFIG_SMP */
 
-static void apbt_set_mode(enum clock_event_mode mode,
-			  struct clock_event_device *evt)
-{
-	unsigned long ctrl;
-	uint64_t delta;
-	int timer_num;
-	struct apbt_dev *adev = EVT_TO_APBT_DEV(evt);
-
-	BUG_ON(!apbt_virt_address);
-
-	timer_num = adev->num;
-	pr_debug("%s CPU %d timer %d mode=%d\n",
-		 __func__, first_cpu(*evt->cpumask), timer_num, mode);
-
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * apbt_clockevent.mult;
-		delta >>= apbt_clockevent.shift;
-		ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
-		ctrl |= APBTMR_CONTROL_MODE_PERIODIC;
-		apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-		/*
-		 * DW APB p. 46, have to disable timer before load counter,
-		 * may cause sync problem.
-		 */
-		ctrl &= ~APBTMR_CONTROL_ENABLE;
-		apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-		udelay(1);
-		pr_debug("Setting clock period %d for HZ %d\n", (int)delta, HZ);
-		apbt_writel(timer_num, delta, APBTMR_N_LOAD_COUNT);
-		ctrl |= APBTMR_CONTROL_ENABLE;
-		apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-		break;
-		/* APB timer does not have one-shot mode, use free running mode */
-	case CLOCK_EVT_MODE_ONESHOT:
-		ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
-		/*
-		 * set free running mode, this mode will let timer reload max
-		 * timeout which will give time (3min on 25MHz clock) to rearm
-		 * the next event, therefore emulate the one-shot mode.
-		 */
-		ctrl &= ~APBTMR_CONTROL_ENABLE;
-		ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC;
-
-		apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-		/* write again to set free running mode */
-		apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-
-		/*
-		 * DW APB p. 46, load counter with all 1s before starting free
-		 * running mode.
-		 */
-		apbt_writel(timer_num, ~0, APBTMR_N_LOAD_COUNT);
-		ctrl &= ~APBTMR_CONTROL_INT;
-		ctrl |= APBTMR_CONTROL_ENABLE;
-		apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-		break;
-
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		apbt_disable_int(timer_num);
-		ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
-		ctrl &= ~APBTMR_CONTROL_ENABLE;
-		apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-		break;
-
-	case CLOCK_EVT_MODE_RESUME:
-		apbt_enable_int(timer_num);
-		break;
-	}
-}
-
-static int apbt_next_event(unsigned long delta,
-			   struct clock_event_device *evt)
-{
-	unsigned long ctrl;
-	int timer_num;
-
-	struct apbt_dev *adev = EVT_TO_APBT_DEV(evt);
-
-	timer_num = adev->num;
-	/* Disable timer */
-	ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
-	ctrl &= ~APBTMR_CONTROL_ENABLE;
-	apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-	/* write new count */
-	apbt_writel(timer_num, delta, APBTMR_N_LOAD_COUNT);
-	ctrl |= APBTMR_CONTROL_ENABLE;
-	apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
-	return 0;
-}
-
-static cycle_t apbt_read_clocksource(struct clocksource *cs)
-{
-	unsigned long current_count;
-
-	current_count = apbt_readl(phy_cs_timer_id, APBTMR_N_CURRENT_VALUE);
-	return (cycle_t)~current_count;
-}
-
 static int apbt_clocksource_register(void)
 {
 	u64 start, now;
 	cycle_t t1;
 
 	/* Start the counter, use timer 2 as source, timer 0/1 for event */
-	apbt_start_counter(phy_cs_timer_id);
+	dw_apb_clocksource_start(clocksource_apbt);
 
 	/* Verify whether apbt counter works */
-	t1 = apbt_read_clocksource(&clocksource_apbt);
+	t1 = dw_apb_clocksource_read(clocksource_apbt);
 	rdtscll(start);
 
 	/*
@@ -540,10 +291,10 @@ static int apbt_clocksource_register(void)
 	} while ((now - start) < 200000UL);
 
 	/* APBT is the only always on clocksource, it has to work! */
-	if (t1 == apbt_read_clocksource(&clocksource_apbt))
+	if (t1 == dw_apb_clocksource_read(clocksource_apbt))
 		panic("APBT counter not counting. APBT disabled\n");
 
-	clocksource_register_khz(&clocksource_apbt, (u32)apbt_freq*1000);
+	dw_apb_clocksource_register(clocksource_apbt);
 
 	return 0;
 }
@@ -567,10 +318,7 @@ void __init apbt_time_init(void)
 	if (apb_timer_block_enabled)
 		return;
 	apbt_set_mapping();
-	if (apbt_virt_address) {
-		pr_debug("Found APBT version 0x%lx\n",\
-			 apbt_readl_reg(APBTMRS_COMP_VERSION));
-	} else
+	if (!apbt_virt_address)
 		goto out_noapbt;
 	/*
 	 * Read the frequency and check for a sane value, for ESL model
@@ -578,7 +326,7 @@ void __init apbt_time_init(void)
 	 */
 
 	if (apbt_freq < APBT_MIN_FREQ || apbt_freq > APBT_MAX_FREQ) {
-		pr_debug("APBT has invalid freq 0x%llx\n", apbt_freq);
+		pr_debug("APBT has invalid freq 0x%lx\n", apbt_freq);
 		goto out_noapbt;
 	}
 	if (apbt_clocksource_register()) {
@@ -604,30 +352,20 @@ void __init apbt_time_init(void)
 	} else {
 		percpu_timer = 0;
 		apbt_num_timers_used = 1;
-		adev = &per_cpu(cpu_apbt_dev, 0);
-		adev->flags &= ~APBT_DEV_USED;
 	}
 	pr_debug("%s: %d APB timers used\n", __func__, apbt_num_timers_used);
 
 	/* here we set up per CPU timer data structure */
-	apbt_devs = kzalloc(sizeof(struct apbt_dev) * apbt_num_timers_used,
-			    GFP_KERNEL);
-	if (!apbt_devs) {
-		printk(KERN_ERR "Failed to allocate APB timer devices\n");
-		return;
-	}
 	for (i = 0; i < apbt_num_timers_used; i++) {
 		adev = &per_cpu(cpu_apbt_dev, i);
 		adev->num = i;
 		adev->cpu = i;
 		p_mtmr = sfi_get_mtmr(i);
-		if (p_mtmr) {
-			adev->tick = p_mtmr->freq_hz;
+		if (p_mtmr)
 			adev->irq = p_mtmr->irq;
-		} else
+		else
 			printk(KERN_ERR "Failed to get timer for cpu %d\n", i);
-		adev->count = 0;
-		sprintf(adev->name, "apbt%d", i);
+		snprintf(adev->name, sizeof(adev->name) - 1, "apbt%d", i);
 	}
 #endif
 
@@ -639,17 +377,8 @@ out_noapbt:
 	panic("failed to enable APB timer\n");
 }
 
-static inline void apbt_disable(int n)
-{
-	if (is_apbt_capable()) {
-		unsigned long ctrl =  apbt_readl(n, APBTMR_N_CONTROL);
-		ctrl &= ~APBTMR_CONTROL_ENABLE;
-		apbt_writel(n, ctrl, APBTMR_N_CONTROL);
-	}
-}
-
 /* called before apb_timer_enable, use early map */
-unsigned long apbt_quick_calibrate()
+unsigned long apbt_quick_calibrate(void)
 {
 	int i, scale;
 	u64 old, new;
@@ -658,31 +387,31 @@ unsigned long apbt_quick_calibrate()
 	u32 loop, shift;
 
 	apbt_set_mapping();
-	apbt_start_counter(phy_cs_timer_id);
+	dw_apb_clocksource_start(clocksource_apbt);
 
 	/* check if the timer can count down, otherwise return */
-	old = apbt_read_clocksource(&clocksource_apbt);
+	old = dw_apb_clocksource_read(clocksource_apbt);
 	i = 10000;
 	while (--i) {
-		if (old != apbt_read_clocksource(&clocksource_apbt))
+		if (old != dw_apb_clocksource_read(clocksource_apbt))
 			break;
 	}
 	if (!i)
 		goto failed;
 
 	/* count 16 ms */
-	loop = (apbt_freq * 1000) << 4;
+	loop = (apbt_freq / 1000) << 4;
 
 	/* restart the timer to ensure it won't get to 0 in the calibration */
-	apbt_start_counter(phy_cs_timer_id);
+	dw_apb_clocksource_start(clocksource_apbt);
 
-	old = apbt_read_clocksource(&clocksource_apbt);
+	old = dw_apb_clocksource_read(clocksource_apbt);
 	old += loop;
 
 	t1 = __native_read_tsc();
 
 	do {
-		new = apbt_read_clocksource(&clocksource_apbt);
+		new = dw_apb_clocksource_read(clocksource_apbt);
 	} while (new < old);
 
 	t2 = __native_read_tsc();
@@ -694,7 +423,7 @@ unsigned long apbt_quick_calibrate()
 		return 0;
 	}
 	scale = (int)div_u64((t2 - t1), loop >> shift);
-	khz = (scale * apbt_freq * 1000) >> shift;
+	khz = (scale * (apbt_freq / 1000)) >> shift;
 	printk(KERN_INFO "TSC freq calculated by APB timer is %lu khz\n", khz);
 	return khz;
 failed:
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 9498b844518..52fa56399a5 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -38,7 +38,7 @@
 #include <asm/perf_event.h>
 #include <asm/x86_init.h>
 #include <asm/pgalloc.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/mpspec.h>
 #include <asm/i8259.h>
 #include <asm/proto.h>
@@ -1944,10 +1944,28 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 
 void __cpuinit generic_processor_info(int apicid, int version)
 {
-	int cpu;
+	int cpu, max = nr_cpu_ids;
+	bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
+				phys_cpu_present_map);
+
+	/*
+	 * If boot cpu has not been detected yet, then only allow upto
+	 * nr_cpu_ids - 1 processors and keep one slot free for boot cpu
+	 */
+	if (!boot_cpu_detected && num_processors >= nr_cpu_ids - 1 &&
+	    apicid != boot_cpu_physical_apicid) {
+		int thiscpu = max + disabled_cpus - 1;
+
+		pr_warning(
+			"ACPI: NR_CPUS/possible_cpus limit of %i almost"
+			" reached. Keeping one slot for boot cpu."
+			"  Processor %d/0x%x ignored.\n", max, thiscpu, apicid);
+
+		disabled_cpus++;
+		return;
+	}
 
 	if (num_processors >= nr_cpu_ids) {
-		int max = nr_cpu_ids;
 		int thiscpu = max + disabled_cpus;
 
 		pr_warning(
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 9536b3fe43f..5d513bc47b6 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -48,7 +48,7 @@
 #include <linux/io.h>
 
 #include <asm/apicdef.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 525514cf33c..46674fbb62b 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -62,6 +62,8 @@ static void __init check_fpu(void)
 		return;
 	}
 
+	kernel_fpu_begin();
+
 	/*
 	 * trap_init() enabled FXSR and company _before_ testing for FP
 	 * problems here.
@@ -80,6 +82,8 @@ static void __init check_fpu(void)
 		: "=m" (*&fdiv_bug)
 		: "m" (*&x), "m" (*&y));
 
+	kernel_fpu_end();
+
 	boot_cpu_data.fdiv_bug = fdiv_bug;
 	if (boot_cpu_data.fdiv_bug)
 		printk(KERN_WARNING "Hmm, FPU with FDIV bug.\n");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 22a073d7fbf..62184390a60 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -21,7 +21,7 @@
 #include <linux/topology.h>
 #include <linux/cpumask.h>
 #include <asm/pgtable.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
 #include <asm/apic.h>
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 8095f8611f8..755f64fb074 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -32,11 +32,11 @@
  */
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
-	&x86_hyper_vmware,
-	&x86_hyper_ms_hyperv,
 #ifdef CONFIG_XEN_PVHVM
 	&x86_hyper_xen_hvm,
 #endif
+	&x86_hyper_vmware,
+	&x86_hyper_ms_hyperv,
 };
 
 const struct hypervisor_x86 *x86_hyper;
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 12aff253768..739d8598f78 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -321,7 +321,7 @@ static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
 	return tmp;
 }
 
-#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16);
+#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16)
 #define FP_EXP_TAG_VALID	0
 #define FP_EXP_TAG_ZERO		1
 #define FP_EXP_TAG_SPECIAL	2
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 65b8f5c2eeb..610485223bd 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -14,7 +14,7 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/system.h>
 #include <asm/timer.h>
 #include <asm/hw_irq.h>
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index f09d4bbe2d2..b3300e6bace 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -15,7 +15,7 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/system.h>
 #include <asm/timer.h>
 #include <asm/hw_irq.h>
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 33c07b0b122..a9c2116001d 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -51,6 +51,15 @@ static int parse_no_kvmapf(char *arg)
 
 early_param("no-kvmapf", parse_no_kvmapf);
 
+static int steal_acc = 1;
+static int parse_no_stealacc(char *arg)
+{
+        steal_acc = 0;
+        return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
 struct kvm_para_state {
 	u8 mmu_queue[MMU_QUEUE_SIZE];
 	int mmu_queue_len;
@@ -58,6 +67,8 @@ struct kvm_para_state {
 
 static DEFINE_PER_CPU(struct kvm_para_state, para_state);
 static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
+static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
+static int has_steal_clock = 0;
 
 static struct kvm_para_state *kvm_para_state(void)
 {
@@ -441,6 +452,21 @@ static void __init paravirt_ops_setup(void)
 #endif
 }
 
+static void kvm_register_steal_time(void)
+{
+	int cpu = smp_processor_id();
+	struct kvm_steal_time *st = &per_cpu(steal_time, cpu);
+
+	if (!has_steal_clock)
+		return;
+
+	memset(st, 0, sizeof(*st));
+
+	wrmsrl(MSR_KVM_STEAL_TIME, (__pa(st) | KVM_MSR_ENABLED));
+	printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n",
+		cpu, __pa(st));
+}
+
 void __cpuinit kvm_guest_cpu_init(void)
 {
 	if (!kvm_para_available())
@@ -457,6 +483,9 @@ void __cpuinit kvm_guest_cpu_init(void)
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
 	}
+
+	if (has_steal_clock)
+		kvm_register_steal_time();
 }
 
 static void kvm_pv_disable_apf(void *unused)
@@ -483,6 +512,31 @@ static struct notifier_block kvm_pv_reboot_nb = {
 	.notifier_call = kvm_pv_reboot_notify,
 };
 
+static u64 kvm_steal_clock(int cpu)
+{
+	u64 steal;
+	struct kvm_steal_time *src;
+	int version;
+
+	src = &per_cpu(steal_time, cpu);
+	do {
+		version = src->version;
+		rmb();
+		steal = src->steal;
+		rmb();
+	} while ((version & 1) || (version != src->version));
+
+	return steal;
+}
+
+void kvm_disable_steal_time(void)
+{
+	if (!has_steal_clock)
+		return;
+
+	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
+}
+
 #ifdef CONFIG_SMP
 static void __init kvm_smp_prepare_boot_cpu(void)
 {
@@ -500,6 +554,7 @@ static void __cpuinit kvm_guest_cpu_online(void *dummy)
 
 static void kvm_guest_cpu_offline(void *dummy)
 {
+	kvm_disable_steal_time();
 	kvm_pv_disable_apf(NULL);
 	apf_task_wake_all();
 }
@@ -548,6 +603,11 @@ void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
 		x86_init.irqs.trap_init = kvm_apf_trap_init;
 
+	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+		has_steal_clock = 1;
+		pv_time_ops.steal_clock = kvm_steal_clock;
+	}
+
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 	register_cpu_notifier(&kvm_cpu_notifier);
@@ -555,3 +615,15 @@ void __init kvm_guest_init(void)
 	kvm_guest_cpu_init();
 #endif
 }
+
+static __init int activate_jump_labels(void)
+{
+	if (has_steal_clock) {
+		jump_label_inc(&paravirt_steal_enabled);
+		if (steal_acc)
+			jump_label_inc(&paravirt_steal_rq_enabled);
+	}
+
+	return 0;
+}
+arch_initcall(activate_jump_labels);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 6389a6bca11..c1a0188e29a 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -160,6 +160,7 @@ static void __cpuinit kvm_setup_secondary_clock(void)
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_crash_shutdown(regs);
 }
 #endif
@@ -167,6 +168,7 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 static void kvm_shutdown(void)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_shutdown();
 }
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 52f256f2cc8..925179f871d 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -45,21 +45,6 @@ void *module_alloc(unsigned long size)
 				-1, __builtin_return_address(0));
 }
 
-/* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
-{
-	vfree(module_region);
-}
-
-/* We don't need anything special. */
-int module_frob_arch_sections(Elf_Ehdr *hdr,
-			      Elf_Shdr *sechdrs,
-			      char *secstrings,
-			      struct module *mod)
-{
-	return 0;
-}
-
 #ifdef CONFIG_X86_32
 int apply_relocate(Elf32_Shdr *sechdrs,
 		   const char *strtab,
@@ -100,17 +85,6 @@ int apply_relocate(Elf32_Shdr *sechdrs,
 	}
 	return 0;
 }
-
-int apply_relocate_add(Elf32_Shdr *sechdrs,
-		       const char *strtab,
-		       unsigned int symindex,
-		       unsigned int relsec,
-		       struct module *me)
-{
-	printk(KERN_ERR "module %s: ADD RELOCATION unsupported\n",
-	       me->name);
-	return -ENOEXEC;
-}
 #else /*X86_64*/
 int apply_relocate_add(Elf64_Shdr *sechdrs,
 		   const char *strtab,
@@ -181,17 +155,6 @@ overflow:
 	       me->name);
 	return -ENOEXEC;
 }
-
-int apply_relocate(Elf_Shdr *sechdrs,
-		   const char *strtab,
-		   unsigned int symindex,
-		   unsigned int relsec,
-		   struct module *me)
-{
-	printk(KERN_ERR "non add relocation not supported\n");
-	return -ENOSYS;
-}
-
 #endif
 
 int module_finalize(const Elf_Ehdr *hdr,
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 869e1aeeb71..613a7931ecc 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -202,6 +202,14 @@ static void native_flush_tlb_single(unsigned long addr)
 	__native_flush_tlb_single(addr);
 }
 
+struct jump_label_key paravirt_steal_enabled;
+struct jump_label_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
 /* These are in entry.S */
 extern void native_iret(void);
 extern void native_irq_enable_sysexit(void);
@@ -307,6 +315,7 @@ struct pv_init_ops pv_init_ops = {
 
 struct pv_time_ops pv_time_ops = {
 	.sched_clock = native_sched_clock,
+	.steal_clock = native_steal_clock,
 };
 
 struct pv_irq_ops pv_irq_ops = {
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index e8c33a30200..726494b5834 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1553,7 +1553,7 @@ static void __init calgary_fixup_one_tce_space(struct pci_dev *dev)
 			continue;
 
 		/* cover the whole region */
-		npages = (r->end - r->start) >> PAGE_SHIFT;
+		npages = resource_size(r) >> PAGE_SHIFT;
 		npages++;
 
 		iommu_range_reserve(tbl, r->start, npages);
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index ba0a4cce53b..63228035f9d 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -234,7 +234,7 @@ void __init probe_roms(void)
 	/* check for extension rom (ignore length byte!) */
 	rom = isa_bus_to_virt(extension_rom_resource.start);
 	if (romsignature(rom)) {
-		length = extension_rom_resource.end - extension_rom_resource.start + 1;
+		length = resource_size(&extension_rom_resource);
 		if (romchecksum(rom, length)) {
 			request_resource(&iomem_resource, &extension_rom_resource);
 			upper = extension_rom_resource.start;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 8bbe8c56916..b78643d0f9a 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -10,7 +10,7 @@
 
 static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 {
-	u8 config, rev;
+	u8 config;
 	u16 word;
 
 	/* BIOS may enable hardware IRQ balancing for
@@ -18,8 +18,7 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 	 * based platforms.
 	 * Disable SW irqbalance/affinity on those platforms.
 	 */
-	pci_read_config_byte(dev, PCI_CLASS_REVISION, &rev);
-	if (rev > 0x9)
+	if (dev->revision > 0x9)
 		return;
 
 	/* enable access to config space*/
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index 41235531b11..36818f8ec2b 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -97,6 +97,8 @@ relocate_kernel:
 	ret
 
 identity_mapped:
+	/* set return address to 0 if not preserving context */
+	pushl	$0
 	/* store the start address on the stack */
 	pushl   %edx
 
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 4de8f5b3d47..7a6f3b3be3c 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -100,6 +100,8 @@ relocate_kernel:
 	ret
 
 identity_mapped:
+	/* set return address to 0 if not preserving context */
+	pushq	$0
 	/* store the start address on the stack */
 	pushq   %rdx
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index fbc097a085c..9682ec50180 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -49,7 +49,7 @@
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
 #include <asm/debugreg.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/system.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 56c633a5db7..db483369f10 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -5,7 +5,6 @@
 #include <linux/timer.h>
 #include <linux/acpi_pmtmr.h>
 #include <linux/cpufreq.h>
-#include <linux/dmi.h>
 #include <linux/delay.h>
 #include <linux/clocksource.h>
 #include <linux/percpu.h>
@@ -800,27 +799,6 @@ void mark_tsc_unstable(char *reason)
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
-static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE "%s detected: marking TSC unstable.\n",
-			d->ident);
-	tsc_unstable = 1;
-	return 0;
-}
-
-/* List of systems that have known TSC problems */
-static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
-	{
-		.callback = dmi_mark_tsc_unstable,
-		.ident = "IBM Thinkpad 380XD",
-		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
-			DMI_MATCH(DMI_BOARD_NAME, "2635FA0"),
-		},
-	},
-	{}
-};
-
 static void __init check_system_tsc_reliable(void)
 {
 #ifdef CONFIG_MGEODE_LX
@@ -1010,8 +988,6 @@ void __init tsc_init(void)
 	lpj_fine = lpj;
 
 	use_tsc_delay();
-	/* Check and install the TSC clocksource */
-	dmi_check_system(bad_tsc_dmi_table);
 
 	if (unsynchronized_tsc())
 		mark_tsc_unstable("TSCs unsynchronized");