Merge branch 'x86-mrst-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-mrst-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
  x86, mrst: Fix whitespace breakage in apb_timer.c
  x86, mrst: Fix APB timer per cpu clockevent
  x86, mrst: Remove X86_MRST dependency on PCI_IOAPIC
  x86, olpc: Use pci subarch init for OLPC
  x86, pci: Add arch_init to x86_init abstraction
  x86, mrst: Add Kconfig dependencies for Moorestown
  x86, pci: Exclude Moorestown PCI code if CONFIG_X86_MRST=n
  x86, numaq: Make CONFIG_X86_NUMAQ depend on CONFIG_PCI
  x86, pci: Add sanity check for PCI fixed bar probing
  x86, legacy_irq: Remove duplicate vector assigment
  x86, legacy_irq: Remove left over nr_legacy_irqs
  x86, mrst: Platform clock setup code
  x86, apbt: Moorestown APB system timer driver
  x86, mrst: Add vrtc platform data setup code
  x86, mrst: Add platform timer info parsing code
  x86, mrst: Fill in PCI functions in x86_init layer
  x86, mrst: Add dummy legacy pic to platform setup
  x86/PCI: Moorestown PCI support
  x86, ioapic: Add dummy ioapic functions
  x86, ioapic: Early enable ioapic for timer irq
  ...

Fixed up semantic conflict of new clocksources due to commit
17622339af25 ("clocksource: add argument to resume callback").

14 files changed, 1157 insertions, 66 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d87f09bc5a5..4c58352209e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)      += early_printk.o
 
 obj-$(CONFIG_HPET_TIMER)        += hpet.o
+obj-$(CONFIG_APB_TIMER)         += apb_timer.o
 
 obj-$(CONFIG_K8_NB)             += k8.o
 obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 738fcb60e70..a54d714545f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -35,6 +35,7 @@
 #include <linux/ioport.h>
 #include <linux/pci.h>
 
+#include <asm/pci_x86.h>
 #include <asm/pgtable.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
@@ -1624,6 +1625,9 @@ int __init acpi_boot_init(void)
 
         acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet);
 
+        if (!acpi_noirq)
+                x86_init.pci.init = pci_acpi_init;
+
         return 0;
 }
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
new file mode 100644
index 00000000000..4b7099526d2
--- /dev/null
+++ b/arch/x86/kernel/apb_timer.c
@@ -0,0 +1,784 @@
+/*
+ * apb_timer.c: Driver for Langwell APB timers
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Note:
+ * Langwell is the south complex of Intel Moorestown MID platform. There are
+ * eight external timers in total that can be used by the operating system.
+ * The timer information, such as frequency and addresses, is provided to the
+ * OS via SFI tables.
+ * Timer interrupts are routed via FW/HW emulated IOAPIC independently via
+ * individual redirection table entries (RTE).
+ * Unlike HPET, there is no master counter, therefore one of the timers are
+ * used as clocksource. The overall allocation looks like:
+ *  - timer 0 - NR_CPUs for per cpu timer
+ *  - one timer for clocksource
+ *  - one timer for watchdog driver.
+ * It is also worth notice that APB timer does not support true one-shot mode,
+ * free-running mode will be used here to emulate one-shot mode.
+ * APB timer can also be used as broadcast timer along with per cpu local APIC
+ * 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/errno.h>
+#include <linux/init.h>
+#include <linux/sysdev.h>
+#include <linux/pm.h>
+#include <linux/pci.h>
+#include <linux/sfi.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+
+#include <asm/fixmap.h>
+#include <asm/apb_timer.h>
+
+#define APBT_MASK                       CLOCKSOURCE_MASK(32)
+#define APBT_SHIFT                      22
+#define APBT_CLOCKEVENT_RATING          150
+#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 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);
+
+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];
+};
+
+int disable_apbt_percpu __cpuinitdata;
+
+static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev);
+
+#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)
+{
+        return readl(apbt_virt_address + a);
+}
+
+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 inline void apbt_writel(int n, unsigned long d, unsigned long a)
+{
+        writel(d, apbt_virt_address + a + n * APBTMRS_REG_SIZE);
+}
+
+static inline void apbt_set_mapping(void)
+{
+        struct sfi_timer_table_entry *mtmr;
+
+        if (apbt_virt_address) {
+                pr_debug("APBT base already mapped\n");
+                return;
+        }
+        mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
+        if (mtmr == NULL) {
+                printk(KERN_ERR "Failed to get MTMR %d from SFI\n",
+                       APBT_CLOCKEVENT0_NUM);
+                return;
+        }
+        apbt_address = (unsigned long)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);
+                goto panic_noapbt;
+        }
+        apbt_freq = mtmr->freq_hz / USEC_PER_SEC;
+        sfi_free_mtmr(mtmr);
+
+        /* Now figure out the physical timer id for clocksource device */
+        mtmr = sfi_get_mtmr(APBT_CLOCKSOURCE_NUM);
+        if (mtmr == NULL)
+                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);
+        return;
+
+panic_noapbt:
+        panic("Failed to setup APB system timer\n");
+
+}
+
+static inline void apbt_clear_mapping(void)
+{
+        iounmap(apbt_virt_address);
+        apbt_virt_address = NULL;
+}
+
+/*
+ * APBT timer interrupt enable / disable
+ */
+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,
+        .shift          = APBT_SHIFT,
+        .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,
+};
+
+/*
+ * if user does not want to use per CPU apb timer, just give it a lower rating
+ * than local apic timer and skip the late per cpu timer init.
+ */
+static inline int __init setup_x86_mrst_timer(char *arg)
+{
+        if (!arg)
+                return -EINVAL;
+
+        if (strcmp("apbt_only", arg) == 0)
+                disable_apbt_percpu = 0;
+        else if (strcmp("lapic_and_apbt", arg) == 0)
+                disable_apbt_percpu = 1;
+        else {
+                pr_warning("X86 MRST timer option %s not recognised"
+                           " use x86_mrst_timer=apbt_only or lapic_and_apbt\n",
+                           arg);
+                return -EINVAL;
+        }
+        return 0;
+}
+__setup("x86_mrst_timer=", setup_x86_mrst_timer);
+
+/*
+ * 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);
+}
+
+/* Setup IRQ routing via IOAPIC */
+#ifdef CONFIG_SMP
+static void apbt_setup_irq(struct apbt_dev *adev)
+{
+        struct irq_chip *chip;
+        struct irq_desc *desc;
+
+        /* timer0 irq has been setup early */
+        if (adev->irq == 0)
+                return;
+        desc = irq_to_desc(adev->irq);
+        chip = get_irq_chip(adev->irq);
+        disable_irq(adev->irq);
+        desc->status |= IRQ_MOVE_PCNTXT;
+        irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
+        /* APB timer irqs are set up as mp_irqs, timer is edge triggerred */
+        set_irq_chip_and_handler_name(adev->irq, chip, handle_edge_irq, "edge");
+        enable_irq(adev->irq);
+        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);
+                }
+}
+#endif
+
+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;
+        struct apbt_dev *adev = &__get_cpu_var(cpu_apbt_dev);
+
+        mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
+        if (mtmr == NULL) {
+                printk(KERN_ERR "Failed to get MTMR %d from SFI\n",
+                       APBT_CLOCKEVENT0_NUM);
+                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));
+
+        if (disable_apbt_percpu) {
+                apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100;
+                global_clock_event = &adev->evt;
+                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);
+
+        sfi_free_mtmr(mtmr);
+        return 0;
+}
+
+#ifdef CONFIG_SMP
+/* 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 == boot_cpu_id)
+                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;
+
+        printk(KERN_INFO "Registering CPU %d clockevent device %s, mask %08x\n",
+               cpu, aevt->name, *(u32 *)aevt->cpumask);
+
+        apbt_setup_irq(adev);
+
+        clockevents_register_device(aevt);
+
+        apbt_enable_int(cpu);
+
+        return;
+}
+
+/*
+ * this notify handler process CPU hotplug events. in case of S0i3, nonboot
+ * cpus are disabled/enabled frequently, for performance reasons, we keep the
+ * per cpu timer irq registered so that we do need to do free_irq/request_irq.
+ *
+ * TODO: it might be more reliable to directly disable percpu clockevent device
+ * without the notifier chain. currently, cpu 0 may get interrupts from other
+ * cpu timers during the offline process due to the ordering of notification.
+ * the extra interrupt is harmless.
+ */
+static int apbt_cpuhp_notify(struct notifier_block *n,
+                             unsigned long action, void *hcpu)
+{
+        unsigned long cpu = (unsigned long)hcpu;
+        struct apbt_dev *adev = &per_cpu(cpu_apbt_dev, cpu);
+
+        switch (action & 0xf) {
+        case CPU_DEAD:
+                apbt_disable_int(cpu);
+                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);
+                }
+                break;
+        default:
+                pr_debug(KERN_INFO "APBT notified %lu, no action\n", action);
+        }
+        return NOTIFY_OK;
+}
+
+static __init int apbt_late_init(void)
+{
+        if (disable_apbt_percpu)
+                return 0;
+        /* This notifier should be called after workqueue is ready */
+        hotcpu_notifier(apbt_cpuhp_notify, -20);
+        return 0;
+}
+fs_initcall(apbt_late_init);
+#else
+
+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);
+
+        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;
+}
+
+/*
+ * APB timer clock is not in sync with pclk on Langwell, which translates to
+ * unreliable read value caused by sampling error. the error does not add up
+ * overtime and only happens when sampling a 0 as a 1 by mistake. so the time
+ * would go backwards. the following code is trying to prevent time traveling
+ * backwards. little bit paranoid.
+ */
+static cycle_t apbt_read_clocksource(struct clocksource *cs)
+{
+        unsigned long t0, t1, t2;
+        static unsigned long last_read;
+
+bad_count:
+        t1 = apbt_readl(phy_cs_timer_id,
+                        APBTMR_N_CURRENT_VALUE);
+        t2 = apbt_readl(phy_cs_timer_id,
+                        APBTMR_N_CURRENT_VALUE);
+        if (unlikely(t1 < t2)) {
+                pr_debug("APBT: read current count error %lx:%lx:%lx\n",
+                         t1, t2, t2 - t1);
+                goto bad_count;
+        }
+        /*
+         * check against cached last read, makes sure time does not go back.
+         * it could be a normal rollover but we will do tripple check anyway
+         */
+        if (unlikely(t2 > last_read)) {
+                /* check if we have a normal rollover */
+                unsigned long raw_intr_status =
+                        apbt_readl_reg(APBTMRS_RAW_INT_STATUS);
+                /*
+                 * cs timer interrupt is masked but raw intr bit is set if
+                 * rollover occurs. then we read EOI reg to clear it.
+                 */
+                if (raw_intr_status & (1 << phy_cs_timer_id)) {
+                        apbt_readl(phy_cs_timer_id, APBTMR_N_EOI);
+                        goto out;
+                }
+                pr_debug("APB CS going back %lx:%lx:%lx ",
+                         t2, last_read, t2 - last_read);
+bad_count_x3:
+                pr_debug(KERN_INFO "tripple check enforced\n");
+                t0 = apbt_readl(phy_cs_timer_id,
+                                APBTMR_N_CURRENT_VALUE);
+                udelay(1);
+                t1 = apbt_readl(phy_cs_timer_id,
+                                APBTMR_N_CURRENT_VALUE);
+                udelay(1);
+                t2 = apbt_readl(phy_cs_timer_id,
+                                APBTMR_N_CURRENT_VALUE);
+                if ((t2 > t1) || (t1 > t0)) {
+                        printk(KERN_ERR "Error: APB CS tripple check failed\n");
+                        goto bad_count_x3;
+                }
+        }
+out:
+        last_read = t2;
+        return (cycle_t)~t2;
+}
+
+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);
+
+        /* Verify whether apbt counter works */
+        t1 = apbt_read_clocksource(&clocksource_apbt);
+        rdtscll(start);
+
+        /*
+         * We don't know the TSC frequency yet, but waiting for
+         * 200000 TSC cycles is safe:
+         * 4 GHz == 50us
+         * 1 GHz == 200us
+         */
+        do {
+                rep_nop();
+                rdtscll(now);
+        } while ((now - start) < 200000UL);
+
+        /* APBT is the only always on clocksource, it has to work! */
+        if (t1 == apbt_read_clocksource(&clocksource_apbt))
+                panic("APBT counter not counting. APBT disabled\n");
+
+        /*
+         * initialize and register APBT clocksource
+         * convert that to ns/clock cycle
+         * mult = (ns/c) * 2^APBT_SHIFT
+         */
+        clocksource_apbt.mult = div_sc(MSEC_PER_SEC,
+                                       (unsigned long) apbt_freq, APBT_SHIFT);
+        clocksource_register(&clocksource_apbt);
+
+        return 0;
+}
+
+/*
+ * Early setup the APBT timer, only use timer 0 for booting then switch to
+ * per CPU timer if possible.
+ * returns 1 if per cpu apbt is setup
+ * returns 0 if no per cpu apbt is chosen
+ * panic if set up failed, this is the only platform timer on Moorestown.
+ */
+void __init apbt_time_init(void)
+{
+#ifdef CONFIG_SMP
+        int i;
+        struct sfi_timer_table_entry *p_mtmr;
+        unsigned int percpu_timer;
+        struct apbt_dev *adev;
+#endif
+
+        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
+                goto out_noapbt;
+        /*
+         * Read the frequency and check for a sane value, for ESL model
+         * we extend the possible clock range to allow time scaling.
+         */
+
+        if (apbt_freq < APBT_MIN_FREQ || apbt_freq > APBT_MAX_FREQ) {
+                pr_debug("APBT has invalid freq 0x%llx\n", apbt_freq);
+                goto out_noapbt;
+        }
+        if (apbt_clocksource_register()) {
+                pr_debug("APBT has failed to register clocksource\n");
+                goto out_noapbt;
+        }
+        if (!apbt_clockevent_register())
+                apb_timer_block_enabled = 1;
+        else {
+                pr_debug("APBT has failed to register clockevent\n");
+                goto out_noapbt;
+        }
+#ifdef CONFIG_SMP
+        /* kernel cmdline disable apb timer, so we will use lapic timers */
+        if (disable_apbt_percpu) {
+                printk(KERN_INFO "apbt: disabled per cpu timer\n");
+                return;
+        }
+        pr_debug("%s: %d CPUs online\n", __func__, num_online_cpus());
+        if (num_possible_cpus() <= sfi_mtimer_num) {
+                percpu_timer = 1;
+                apbt_num_timers_used = num_possible_cpus();
+        } 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;
+                        adev->irq = p_mtmr->irq;
+                } else
+                        printk(KERN_ERR "Failed to get timer for cpu %d\n", i);
+                adev->count = 0;
+                sprintf(adev->name, "apbt%d", i);
+        }
+#endif
+
+        return;
+
+out_noapbt:
+        apbt_clear_mapping();
+        apb_timer_block_enabled = 0;
+        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()
+{
+        int i, scale;
+        u64 old, new;
+        cycle_t t1, t2;
+        unsigned long khz = 0;
+        u32 loop, shift;
+
+        apbt_set_mapping();
+        apbt_start_counter(phy_cs_timer_id);
+
+        /* check if the timer can count down, otherwise return */
+        old = apbt_read_clocksource(&clocksource_apbt);
+        i = 10000;
+        while (--i) {
+                if (old != apbt_read_clocksource(&clocksource_apbt))
+                        break;
+        }
+        if (!i)
+                goto failed;
+
+        /* count 16 ms */
+        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);
+
+        old = apbt_read_clocksource(&clocksource_apbt);
+        old += loop;
+
+        t1 = __native_read_tsc();
+
+        do {
+                new = apbt_read_clocksource(&clocksource_apbt);
+        } while (new < old);
+
+        t2 = __native_read_tsc();
+
+        shift = 5;
+        if (unlikely(loop >> shift == 0)) {
+                printk(KERN_INFO
+                       "APBT TSC calibration failed, not enough resolution\n");
+                return 0;
+        }
+        scale = (int)div_u64((t2 - t1), loop >> shift);
+        khz = (scale * apbt_freq * 1000) >> shift;
+        printk(KERN_INFO "TSC freq calculated by APB timer is %lu khz\n", khz);
+        return khz;
+failed:
+        return 0;
+}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6e29b2a77aa..00187f1fcfb 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1390,7 +1390,7 @@ void __init enable_IR_x2apic(void)
         }
 
         local_irq_save(flags);
-        mask_8259A();
+        legacy_pic->mask_all();
         mask_IO_APIC_setup(ioapic_entries);
 
         if (dmar_table_init_ret)
@@ -1422,7 +1422,7 @@ void __init enable_IR_x2apic(void)
 nox2apic:
         if (!ret) /* IR enabling failed */
                 restore_IO_APIC_setup(ioapic_entries);
-        unmask_8259A();
+        legacy_pic->restore_mask();
         local_irq_restore(flags);
 
 out:
@@ -2018,7 +2018,7 @@ static int lapic_resume(struct sys_device *dev)
                 }
 
                 mask_IO_APIC_setup(ioapic_entries);
-                mask_8259A();
+                legacy_pic->mask_all();
         }
 
         if (x2apic_mode)
@@ -2062,7 +2062,7 @@ static int lapic_resume(struct sys_device *dev)
 
         if (intr_remapping_enabled) {
                 reenable_intr_remapping(x2apic_mode);
-                unmask_8259A();
+                legacy_pic->restore_mask();
                 restore_IO_APIC_setup(ioapic_entries);
                 free_ioapic_entries(ioapic_entries);
         }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 14862f11cc4..e4e0ddcb154 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -143,12 +143,6 @@ static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY];
 static struct irq_cfg irq_cfgx[NR_IRQS];
 #endif
 
-void __init io_apic_disable_legacy(void)
-{
-        nr_legacy_irqs = 0;
-        nr_irqs_gsi = 0;
-}
-
 int __init arch_early_irq_init(void)
 {
         struct irq_cfg *cfg;
@@ -157,6 +151,11 @@ int __init arch_early_irq_init(void)
         int node;
         int i;
 
+        if (!legacy_pic->nr_legacy_irqs) {
+                nr_irqs_gsi = 0;
+                io_apic_irqs = ~0UL;
+        }
+
         cfg = irq_cfgx;
         count = ARRAY_SIZE(irq_cfgx);
         node= cpu_to_node(boot_cpu_id);
@@ -170,7 +169,7 @@ int __init arch_early_irq_init(void)
                  * For legacy IRQ's, start with assigning irq0 to irq15 to
                  * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
                  */
-                if (i < nr_legacy_irqs) {
+                if (i < legacy_pic->nr_legacy_irqs) {
                         cfg[i].vector = IRQ0_VECTOR + i;
                         cpumask_set_cpu(0, cfg[i].domain);
                 }
@@ -852,7 +851,7 @@ static int __init find_isa_irq_apic(int irq, int type)
  */
 static int EISA_ELCR(unsigned int irq)
 {
-        if (irq < nr_legacy_irqs) {
+        if (irq < legacy_pic->nr_legacy_irqs) {
                 unsigned int port = 0x4d0 + (irq >> 3);
                 return (inb(port) >> (irq & 7)) & 1;
         }
@@ -1439,7 +1438,7 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
          * controllers like 8259. Now that IO-APIC can handle this irq, update
          * the cfg->domain.
          */
-        if (irq < nr_legacy_irqs && cpumask_test_cpu(0, cfg->domain))
+        if (irq < legacy_pic->nr_legacy_irqs && cpumask_test_cpu(0, cfg->domain))
                 apic->vector_allocation_domain(0, cfg->domain);
 
         if (assign_irq_vector(irq, cfg, apic->target_cpus()))
@@ -1463,8 +1462,8 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
         }
 
         ioapic_register_intr(irq, desc, trigger);
-        if (irq < nr_legacy_irqs)
-                disable_8259A_irq(irq);
+        if (irq < legacy_pic->nr_legacy_irqs)
+                legacy_pic->chip->mask(irq);
 
         ioapic_write_entry(apic_id, pin, entry);
 }
@@ -1873,7 +1872,7 @@ __apicdebuginit(void) print_PIC(void)
         unsigned int v;
         unsigned long flags;
 
-        if (!nr_legacy_irqs)
+        if (!legacy_pic->nr_legacy_irqs)
                 return;
 
         printk(KERN_DEBUG "\nprinting PIC contents\n");
@@ -1957,7 +1956,7 @@ void __init enable_IO_APIC(void)
                 nr_ioapic_registers[apic] = reg_01.bits.entries+1;
         }
 
-        if (!nr_legacy_irqs)
+        if (!legacy_pic->nr_legacy_irqs)
                 return;
 
         for(apic = 0; apic < nr_ioapics; apic++) {
@@ -2014,7 +2013,7 @@ void disable_IO_APIC(void)
          */
         clear_IO_APIC();
 
-        if (!nr_legacy_irqs)
+        if (!legacy_pic->nr_legacy_irqs)
                 return;
 
         /*
@@ -2247,9 +2246,9 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
         struct irq_cfg *cfg;
 
         raw_spin_lock_irqsave(&ioapic_lock, flags);
-        if (irq < nr_legacy_irqs) {
-                disable_8259A_irq(irq);
-                if (i8259A_irq_pending(irq))
+        if (irq < legacy_pic->nr_legacy_irqs) {
+                legacy_pic->chip->mask(irq);
+                if (legacy_pic->irq_pending(irq))
                         was_pending = 1;
         }
         cfg = irq_cfg(irq);
@@ -2782,8 +2781,8 @@ static inline void init_IO_APIC_traps(void)
                          * so default to an old-fashioned 8259
                          * interrupt if we can..
                          */
-                        if (irq < nr_legacy_irqs)
-                                make_8259A_irq(irq);
+                        if (irq < legacy_pic->nr_legacy_irqs)
+                                legacy_pic->make_irq(irq);
                         else
                                 /* Strange. Oh, well.. */
                                 desc->chip = &no_irq_chip;
@@ -2940,7 +2939,7 @@ static inline void __init check_timer(void)
         /*
          * get/set the timer IRQ vector:
          */
-        disable_8259A_irq(0);
+        legacy_pic->chip->mask(0);
         assign_irq_vector(0, cfg, apic->target_cpus());
 
         /*
@@ -2953,7 +2952,7 @@ static inline void __init check_timer(void)
          * automatically.
          */
         apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-        init_8259A(1);
+        legacy_pic->init(1);
 #ifdef CONFIG_X86_32
         {
                 unsigned int ver;
@@ -3012,7 +3011,7 @@ static inline void __init check_timer(void)
                 if (timer_irq_works()) {
                         if (nmi_watchdog == NMI_IO_APIC) {
                                 setup_nmi();
-                                enable_8259A_irq(0);
+                                legacy_pic->chip->unmask(0);
                         }
                         if (disable_timer_pin_1 > 0)
                                 clear_IO_APIC_pin(0, pin1);
@@ -3035,14 +3034,14 @@ static inline void __init check_timer(void)
                  */
                 replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
                 setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
-                enable_8259A_irq(0);
+                legacy_pic->chip->unmask(0);
                 if (timer_irq_works()) {
                         apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
                         timer_through_8259 = 1;
                         if (nmi_watchdog == NMI_IO_APIC) {
-                                disable_8259A_irq(0);
+                                legacy_pic->chip->mask(0);
                                 setup_nmi();
-                                enable_8259A_irq(0);
+                                legacy_pic->chip->unmask(0);
                         }
                         goto out;
                 }
@@ -3050,7 +3049,7 @@ static inline void __init check_timer(void)
                  * Cleanup, just in case ...
                  */
                 local_irq_disable();
-                disable_8259A_irq(0);
+                legacy_pic->chip->mask(0);
                 clear_IO_APIC_pin(apic2, pin2);
                 apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
         }
@@ -3069,22 +3068,22 @@ static inline void __init check_timer(void)
 
         lapic_register_intr(0, desc);
         apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);     /* Fixed mode */
-        enable_8259A_irq(0);
+        legacy_pic->chip->unmask(0);
 
         if (timer_irq_works()) {
                 apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
                 goto out;
         }
         local_irq_disable();
-        disable_8259A_irq(0);
+        legacy_pic->chip->mask(0);
         apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
         apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
 
         apic_printk(APIC_QUIET, KERN_INFO
                     "...trying to set up timer as ExtINT IRQ...\n");
 
-        init_8259A(0);
-        make_8259A_irq(0);
+        legacy_pic->init(0);
+        legacy_pic->make_irq(0);
         apic_write(APIC_LVT0, APIC_DM_EXTINT);
 
         unlock_ExtINT_logic();
@@ -3126,7 +3125,7 @@ void __init setup_IO_APIC(void)
         /*
          * calling enable_IO_APIC() is moved to setup_local_APIC for BP
          */
-        io_apic_irqs = nr_legacy_irqs ? ~PIC_IRQS : ~0UL;
+        io_apic_irqs = legacy_pic->nr_legacy_irqs ? ~PIC_IRQS : ~0UL;
 
         apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
         /*
@@ -3137,7 +3136,7 @@ void __init setup_IO_APIC(void)
         sync_Arb_IDs();
         setup_IO_APIC_irqs();
         init_IO_APIC_traps();
-        if (nr_legacy_irqs)
+        if (legacy_pic->nr_legacy_irqs)
                 check_timer();
 }
 
@@ -3928,7 +3927,7 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
         /*
          * IRQs < 16 are already in the irq_2_pin[] map
          */
-        if (irq >= nr_legacy_irqs) {
+        if (irq >= legacy_pic->nr_legacy_irqs) {
                 cfg = desc->chip_data;
                 if (add_pin_to_irq_node_nopanic(cfg, node, ioapic, pin)) {
                         printk(KERN_INFO "can not add pin %d for irq %d\n",
@@ -4302,3 +4301,24 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 
         nr_ioapics++;
 }
+
+/* Enable IOAPIC early just for system timer */
+void __init pre_init_apic_IRQ0(void)
+{
+        struct irq_cfg *cfg;
+        struct irq_desc *desc;
+
+        printk(KERN_INFO "Early APIC setup for system timer0\n");
+#ifndef CONFIG_SMP
+        phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+#endif
+        desc = irq_to_desc_alloc_node(0, 0);
+
+        setup_local_APIC();
+
+        cfg = irq_cfg(0);
+        add_pin_to_irq_node(cfg, 0, 0, 0);
+        set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
+
+        setup_IO_APIC_irq(0, 0, 0, desc, 0, 0);
+}
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index bd7c96b5e8d..8aa65adbd25 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -177,7 +177,7 @@ int __init check_nmi_watchdog(void)
 error:
         if (nmi_watchdog == NMI_IO_APIC) {
                 if (!timer_through_8259)
-                        disable_8259A_irq(0);
+                        legacy_pic->chip->mask(0);
                 on_each_cpu(__acpi_nmi_disable, NULL, 1);
         }
 
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 47dd856708e..3e28401f161 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -277,6 +277,7 @@ static __init void early_check_numaq(void)
                 x86_init.mpparse.mpc_oem_pci_bus = mpc_oem_pci_bus;
                 x86_init.mpparse.mpc_oem_bus_info = mpc_oem_bus_info;
                 x86_init.timers.tsc_pre_init = numaq_tsc_init;
+                x86_init.pci.init = pci_numaq_init;
         }
 }
 
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 8c93a84bb62..fb725ee15f5 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -34,6 +34,12 @@
 static int i8259A_auto_eoi;
 DEFINE_RAW_SPINLOCK(i8259A_lock);
 static void mask_and_ack_8259A(unsigned int);
+static void mask_8259A(void);
+static void unmask_8259A(void);
+static void disable_8259A_irq(unsigned int irq);
+static void enable_8259A_irq(unsigned int irq);
+static void init_8259A(int auto_eoi);
+static int i8259A_irq_pending(unsigned int irq);
 
 struct irq_chip i8259A_chip = {
         .name           = "XT-PIC",
@@ -63,7 +69,7 @@ unsigned int cached_irq_mask = 0xffff;
  */
 unsigned long io_apic_irqs;
 
-void disable_8259A_irq(unsigned int irq)
+static void disable_8259A_irq(unsigned int irq)
 {
         unsigned int mask = 1 << irq;
         unsigned long flags;
@@ -77,7 +83,7 @@ void disable_8259A_irq(unsigned int irq)
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-void enable_8259A_irq(unsigned int irq)
+static void enable_8259A_irq(unsigned int irq)
 {
         unsigned int mask = ~(1 << irq);
         unsigned long flags;
@@ -91,7 +97,7 @@ void enable_8259A_irq(unsigned int irq)
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-int i8259A_irq_pending(unsigned int irq)
+static int i8259A_irq_pending(unsigned int irq)
 {
         unsigned int mask = 1<<irq;
         unsigned long flags;
@@ -107,7 +113,7 @@ int i8259A_irq_pending(unsigned int irq)
         return ret;
 }
 
-void make_8259A_irq(unsigned int irq)
+static void make_8259A_irq(unsigned int irq)
 {
         disable_irq_nosync(irq);
         io_apic_irqs &= ~(1<<irq);
@@ -281,7 +287,7 @@ static int __init i8259A_init_sysfs(void)
 
 device_initcall(i8259A_init_sysfs);
 
-void mask_8259A(void)
+static void mask_8259A(void)
 {
         unsigned long flags;
 
@@ -293,7 +299,7 @@ void mask_8259A(void)
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-void unmask_8259A(void)
+static void unmask_8259A(void)
 {
         unsigned long flags;
 
@@ -305,7 +311,7 @@ void unmask_8259A(void)
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-void init_8259A(int auto_eoi)
+static void init_8259A(int auto_eoi)
 {
         unsigned long flags;
 
@@ -358,3 +364,47 @@ void init_8259A(int auto_eoi)
 
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
+
+/*
+ * make i8259 a driver so that we can select pic functions at run time. the goal
+ * is to make x86 binary compatible among pc compatible and non-pc compatible
+ * platforms, such as x86 MID.
+ */
+
+static void legacy_pic_noop(void) { };
+static void legacy_pic_uint_noop(unsigned int unused) { };
+static void legacy_pic_int_noop(int unused) { };
+
+static struct irq_chip dummy_pic_chip  = {
+        .name = "dummy pic",
+        .mask = legacy_pic_uint_noop,
+        .unmask = legacy_pic_uint_noop,
+        .disable = legacy_pic_uint_noop,
+        .mask_ack = legacy_pic_uint_noop,
+};
+static int legacy_pic_irq_pending_noop(unsigned int irq)
+{
+        return 0;
+}
+
+struct legacy_pic null_legacy_pic = {
+        .nr_legacy_irqs = 0,
+        .chip = &dummy_pic_chip,
+        .mask_all = legacy_pic_noop,
+        .restore_mask = legacy_pic_noop,
+        .init = legacy_pic_int_noop,
+        .irq_pending = legacy_pic_irq_pending_noop,
+        .make_irq = legacy_pic_uint_noop,
+};
+
+struct legacy_pic default_legacy_pic = {
+        .nr_legacy_irqs = NR_IRQS_LEGACY,
+        .chip  = &i8259A_chip,
+        .mask_all  = mask_8259A,
+        .restore_mask = unmask_8259A,
+        .init = init_8259A,
+        .irq_pending = i8259A_irq_pending,
+        .make_irq = make_8259A_irq,
+};
+
+struct legacy_pic *legacy_pic = &default_legacy_pic;
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index fce55d53263..ef257fc2921 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -99,9 +99,6 @@ int vector_used_by_percpu_irq(unsigned int vector)
         return 0;
 }
 
-/* Number of legacy interrupts */
-int nr_legacy_irqs __read_mostly = NR_IRQS_LEGACY;
-
 void __init init_ISA_irqs(void)
 {
         int i;
@@ -109,12 +106,12 @@ void __init init_ISA_irqs(void)
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
         init_bsp_APIC();
 #endif
-        init_8259A(0);
+        legacy_pic->init(0);
 
         /*
          * 16 old-style INTA-cycle interrupts:
          */
-        for (i = 0; i < NR_IRQS_LEGACY; i++) {
+        for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) {
                 struct irq_desc *desc = irq_to_desc(i);
 
                 desc->status = IRQ_DISABLED;
@@ -138,7 +135,7 @@ void __init init_IRQ(void)
          * then this vector space can be freed and re-used dynamically as the
          * irq's migrate etc.
          */
-        for (i = 0; i < nr_legacy_irqs; i++)
+        for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
                 per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i;
 
         x86_init.irqs.intr_init();
diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c
index 3b7078abc87..0aad8670858 100644
--- a/arch/x86/kernel/mrst.c
+++ b/arch/x86/kernel/mrst.c
@@ -10,8 +10,211 @@
  * of the License.
  */
 #include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sfi.h>
+#include <linux/irq.h>
+#include <linux/module.h>
 
 #include <asm/setup.h>
+#include <asm/mpspec_def.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/mrst.h>
+#include <asm/io.h>
+#include <asm/i8259.h>
+#include <asm/apb_timer.h>
+
+static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM];
+static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM];
+int sfi_mtimer_num;
+
+struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX];
+EXPORT_SYMBOL_GPL(sfi_mrtc_array);
+int sfi_mrtc_num;
+
+static inline void assign_to_mp_irq(struct mpc_intsrc *m,
+                                    struct mpc_intsrc *mp_irq)
+{
+        memcpy(mp_irq, m, sizeof(struct mpc_intsrc));
+}
+
+static inline int mp_irq_cmp(struct mpc_intsrc *mp_irq,
+                                struct mpc_intsrc *m)
+{
+        return memcmp(mp_irq, m, sizeof(struct mpc_intsrc));
+}
+
+static void save_mp_irq(struct mpc_intsrc *m)
+{
+        int i;
+
+        for (i = 0; i < mp_irq_entries; i++) {
+                if (!mp_irq_cmp(&mp_irqs[i], m))
+                        return;
+        }
+
+        assign_to_mp_irq(m, &mp_irqs[mp_irq_entries]);
+        if (++mp_irq_entries == MAX_IRQ_SOURCES)
+                panic("Max # of irq sources exceeded!!\n");
+}
+
+/* parse all the mtimer info to a static mtimer array */
+static int __init sfi_parse_mtmr(struct sfi_table_header *table)
+{
+        struct sfi_table_simple *sb;
+        struct sfi_timer_table_entry *pentry;
+        struct mpc_intsrc mp_irq;
+        int totallen;
+
+        sb = (struct sfi_table_simple *)table;
+        if (!sfi_mtimer_num) {
+                sfi_mtimer_num = SFI_GET_NUM_ENTRIES(sb,
+                                        struct sfi_timer_table_entry);
+                pentry = (struct sfi_timer_table_entry *) sb->pentry;
+                totallen = sfi_mtimer_num * sizeof(*pentry);
+                memcpy(sfi_mtimer_array, pentry, totallen);
+        }
+
+        printk(KERN_INFO "SFI: MTIMER info (num = %d):\n", sfi_mtimer_num);
+        pentry = sfi_mtimer_array;
+        for (totallen = 0; totallen < sfi_mtimer_num; totallen++, pentry++) {
+                printk(KERN_INFO "timer[%d]: paddr = 0x%08x, freq = %dHz,"
+                        " irq = %d\n", totallen, (u32)pentry->phys_addr,
+                        pentry->freq_hz, pentry->irq);
+                        if (!pentry->irq)
+                                continue;
+                        mp_irq.type = MP_IOAPIC;
+                        mp_irq.irqtype = mp_INT;
+/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
+                        mp_irq.irqflag = 5;
+                        mp_irq.srcbus = 0;
+                        mp_irq.srcbusirq = pentry->irq; /* IRQ */
+                        mp_irq.dstapic = MP_APIC_ALL;
+                        mp_irq.dstirq = pentry->irq;
+                        save_mp_irq(&mp_irq);
+        }
+
+        return 0;
+}
+
+struct sfi_timer_table_entry *sfi_get_mtmr(int hint)
+{
+        int i;
+        if (hint < sfi_mtimer_num) {
+                if (!sfi_mtimer_usage[hint]) {
+                        pr_debug("hint taken for timer %d irq %d\n",\
+                                hint, sfi_mtimer_array[hint].irq);
+                        sfi_mtimer_usage[hint] = 1;
+                        return &sfi_mtimer_array[hint];
+                }
+        }
+        /* take the first timer available */
+        for (i = 0; i < sfi_mtimer_num;) {
+                if (!sfi_mtimer_usage[i]) {
+                        sfi_mtimer_usage[i] = 1;
+                        return &sfi_mtimer_array[i];
+                }
+                i++;
+        }
+        return NULL;
+}
+
+void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr)
+{
+        int i;
+        for (i = 0; i < sfi_mtimer_num;) {
+                if (mtmr->irq == sfi_mtimer_array[i].irq) {
+                        sfi_mtimer_usage[i] = 0;
+                        return;
+                }
+                i++;
+        }
+}
+
+/* parse all the mrtc info to a global mrtc array */
+int __init sfi_parse_mrtc(struct sfi_table_header *table)
+{
+        struct sfi_table_simple *sb;
+        struct sfi_rtc_table_entry *pentry;
+        struct mpc_intsrc mp_irq;
+
+        int totallen;
+
+        sb = (struct sfi_table_simple *)table;
+        if (!sfi_mrtc_num) {
+                sfi_mrtc_num = SFI_GET_NUM_ENTRIES(sb,
+                                                struct sfi_rtc_table_entry);
+                pentry = (struct sfi_rtc_table_entry *)sb->pentry;
+                totallen = sfi_mrtc_num * sizeof(*pentry);
+                memcpy(sfi_mrtc_array, pentry, totallen);
+        }
+
+        printk(KERN_INFO "SFI: RTC info (num = %d):\n", sfi_mrtc_num);
+        pentry = sfi_mrtc_array;
+        for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) {
+                printk(KERN_INFO "RTC[%d]: paddr = 0x%08x, irq = %d\n",
+                        totallen, (u32)pentry->phys_addr, pentry->irq);
+                mp_irq.type = MP_IOAPIC;
+                mp_irq.irqtype = mp_INT;
+                mp_irq.irqflag = 0;
+                mp_irq.srcbus = 0;
+                mp_irq.srcbusirq = pentry->irq; /* IRQ */
+                mp_irq.dstapic = MP_APIC_ALL;
+                mp_irq.dstirq = pentry->irq;
+                save_mp_irq(&mp_irq);
+        }
+        return 0;
+}
+
+/*
+ * the secondary clock in Moorestown can be APBT or LAPIC clock, default to
+ * APBT but cmdline option can also override it.
+ */
+static void __cpuinit mrst_setup_secondary_clock(void)
+{
+        /* restore default lapic clock if disabled by cmdline */
+        if (disable_apbt_percpu)
+                return setup_secondary_APIC_clock();
+        apbt_setup_secondary_clock();
+}
+
+static unsigned long __init mrst_calibrate_tsc(void)
+{
+        unsigned long flags, fast_calibrate;
+
+        local_irq_save(flags);
+        fast_calibrate = apbt_quick_calibrate();
+        local_irq_restore(flags);
+
+        if (fast_calibrate)
+                return fast_calibrate;
+
+        return 0;
+}
+
+void __init mrst_time_init(void)
+{
+        sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
+        pre_init_apic_IRQ0();
+        apbt_time_init();
+}
+
+void __init mrst_rtc_init(void)
+{
+        sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
+}
+
+/*
+ * if we use per cpu apb timer, the bootclock already setup. if we use lapic
+ * timer and one apbt timer for broadcast, we need to set up lapic boot clock.
+ */
+static void __init mrst_setup_boot_clock(void)
+{
+        pr_info("%s: per cpu apbt flag %d \n", __func__, disable_apbt_percpu);
+        if (disable_apbt_percpu)
+                setup_boot_APIC_clock();
+};
 
 /*
  * Moorestown specific x86_init function overrides and early setup
@@ -21,4 +224,17 @@ void __init x86_mrst_early_setup(void)
 {
         x86_init.resources.probe_roms = x86_init_noop;
         x86_init.resources.reserve_resources = x86_init_noop;
+
+        x86_init.timers.timer_init = mrst_time_init;
+        x86_init.timers.setup_percpu_clockev = mrst_setup_boot_clock;
+
+        x86_init.irqs.pre_vector_init = x86_init_noop;
+
+        x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock;
+
+        x86_platform.calibrate_tsc = mrst_calibrate_tsc;
+        x86_init.pci.init = pci_mrst_init;
+        x86_init.pci.fixup_irqs = x86_init_noop;
+
+        legacy_pic = &null_legacy_pic;
 }
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 9d1d263f786..8297160c41b 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -17,7 +17,9 @@
 #include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/string.h>
+
 #include <asm/geode.h>
+#include <asm/setup.h>
 #include <asm/olpc.h>
 
 #ifdef CONFIG_OPEN_FIRMWARE
@@ -243,9 +245,11 @@ static int __init olpc_init(void)
         olpc_ec_cmd(EC_FIRMWARE_REV, NULL, 0,
                         (unsigned char *) &olpc_platform_info.ecver, 1);
 
-        /* check to see if the VSA exists */
-        if (cs5535_has_vsa2())
-                olpc_platform_info.flags |= OLPC_F_VSA;
+#ifdef CONFIG_PCI_OLPC
+        /* If the VSA exists let it emulate PCI, if not emulate in kernel */
+        if (!cs5535_has_vsa2())
+                x86_init.pci.arch_init = pci_olpc_init;
+#endif
 
         printk(KERN_INFO "OLPC board revision %s%X (EC=%x)\n",
                         ((olpc_platform_info.boardrev & 0xf) < 8) ? "pre" : "",
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a435c76d714..a02e80c3c54 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -48,6 +48,7 @@
 #include <linux/err.h>
 #include <linux/nmi.h>
 #include <linux/tboot.h>
+#include <linux/stackprotector.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -67,6 +68,7 @@
 #include <linux/mc146818rtc.h>
 
 #include <asm/smpboot_hooks.h>
+#include <asm/i8259.h>
 
 #ifdef CONFIG_X86_32
 u8 apicid_2_node[MAX_APICID];
@@ -291,9 +293,9 @@ notrace static void __cpuinit start_secondary(void *unused)
         check_tsc_sync_target();
 
         if (nmi_watchdog == NMI_IO_APIC) {
-                disable_8259A_irq(0);
+                legacy_pic->chip->mask(0);
                 enable_NMI_through_LVT0();
-                enable_8259A_irq(0);
+                legacy_pic->chip->unmask(0);
         }
 
 #ifdef CONFIG_X86_32
@@ -329,6 +331,9 @@ notrace static void __cpuinit start_secondary(void *unused)
         /* enable local interrupts */
         local_irq_enable();
 
+        /* to prevent fake stack check failure in clock setup */
+        boot_init_stack_canary();
+
         x86_cpuinit.setup_percpu_clockev();
 
         wmb();
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index ab38ce0984f..e680ea52db9 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -49,11 +49,6 @@ extern int no_broadcast;
 char visws_board_type   = -1;
 char visws_board_rev    = -1;
 
-int is_visws_box(void)
-{
-        return visws_board_type >= 0;
-}
-
 static void __init visws_time_init(void)
 {
         printk(KERN_INFO "Starting Cobalt Timer system clock\n");
@@ -242,6 +237,8 @@ void __init visws_early_detect(void)
         x86_init.irqs.pre_vector_init = visws_pre_intr_init;
         x86_init.irqs.trap_init = visws_trap_init;
         x86_init.timers.timer_init = visws_time_init;
+        x86_init.pci.init = pci_visws_init;
+        x86_init.pci.init_irq = x86_init_noop;
 
         /*
          * Install reboot quirks:
@@ -508,7 +505,7 @@ static struct irq_chip cobalt_irq_type = {
  */
 static unsigned int startup_piix4_master_irq(unsigned int irq)
 {
-        init_8259A(0);
+        legacy_pic->init(0);
 
         return startup_cobalt_irq(irq);
 }
@@ -532,9 +529,6 @@ static struct irq_chip piix4_master_irq_type = {
 
 static struct irq_chip piix4_virtual_irq_type = {
         .name =         "PIIX4-virtual",
-        .shutdown =     disable_8259A_irq,
-        .enable =       enable_8259A_irq,
-        .disable =      disable_8259A_irq,
 };
 
 
@@ -609,7 +603,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
                 handle_IRQ_event(realirq, desc->action);
 
         if (!(desc->status & IRQ_DISABLED))
-                enable_8259A_irq(realirq);
+                legacy_pic->chip->unmask(realirq);
 
         return IRQ_HANDLED;
 
@@ -628,6 +622,12 @@ static struct irqaction cascade_action = {
         .name =         "cascade",
 };
 
+static inline void set_piix4_virtual_irq_type(void)
+{
+        piix4_virtual_irq_type.shutdown = i8259A_chip.mask;
+        piix4_virtual_irq_type.enable = i8259A_chip.unmask;
+        piix4_virtual_irq_type.disable = i8259A_chip.mask;
+}
 
 void init_VISWS_APIC_irqs(void)
 {
@@ -653,6 +653,7 @@ void init_VISWS_APIC_irqs(void)
                         desc->chip = &piix4_master_irq_type;
                 }
                 else if (i < CO_IRQ_APIC0) {
+                        set_piix4_virtual_irq_type();
                         desc->chip = &piix4_virtual_irq_type;
                 }
                 else if (IS_CO_APIC(i)) {
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index ee5746c9462..61a1e8c7e19 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -4,9 +4,11 @@
  *  For licencing details see kernel-base/COPYING
  */
 #include <linux/init.h>
+#include <linux/ioport.h>
 
 #include <asm/bios_ebda.h>
 #include <asm/paravirt.h>
+#include <asm/pci_x86.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/apic.h>
@@ -70,6 +72,12 @@ struct x86_init_ops x86_init __initdata = {
         .iommu = {
                 .iommu_init             = iommu_init_noop,
         },
+
+        .pci = {
+                .init                   = x86_default_pci_init,
+                .init_irq               = x86_default_pci_init_irq,
+                .fixup_irqs             = x86_default_pci_fixup_irqs,
+        },
 };
 
 struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {