Merge branch 'linus' into x86/urgent

Merge reason: Bring in changes that the next patch will depend on.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

34 files changed, 532 insertions, 706 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 832cb838cb48..4ba419b668a5 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -31,8 +31,8 @@ GCOV_PROFILE_paravirt.o		:= n
 
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o i8259.o irqinit.o
+obj-y			+= time.o ioport.o ldt.o dumpstack.o
+obj-y			+= setup.o x86_init.o i8259.o irqinit.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -105,6 +105,7 @@ obj-$(CONFIG_SCx200)		+= scx200.o
 scx200-y			+= scx200_32.o
 
 obj-$(CONFIG_OLPC)		+= olpc.o
+obj-$(CONFIG_X86_MRST)		+= mrst.o
 
 microcode-y				:= microcode_core.o
 microcode-$(CONFIG_MICROCODE_INTEL)	+= microcode_intel.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2d59dfa29785..a58ef98be155 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -36,6 +36,7 @@
 #include <linux/mm.h>
 
 #include <asm/perf_counter.h>
+#include <asm/x86_init.h>
 #include <asm/pgalloc.h>
 #include <asm/atomic.h>
 #include <asm/mpspec.h>
@@ -1708,7 +1709,7 @@ int __init APIC_init_uniprocessor(void)
 	localise_nmi_watchdog();
 #endif
 
-	setup_boot_clock();
+	x86_init.timers.setup_percpu_clockev();
 #ifdef CONFIG_X86_64
 	check_nmi_watchdog();
 #endif
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 676cdac385c0..77a06413b6b2 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -112,7 +112,7 @@ static physid_mask_t bigsmp_ioapic_phys_id_map(physid_mask_t phys_map)
 	return physids_promote(0xFFL);
 }
 
-static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid)
+static int bigsmp_check_phys_apicid_present(int phys_apicid)
 {
 	return 1;
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 593c4f8a8bb8..64970b9885f2 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -96,6 +96,11 @@ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 /* # of MP IRQ source entries */
 int mp_irq_entries;
 
+/* Number of legacy interrupts */
+static int nr_legacy_irqs __read_mostly = NR_IRQS_LEGACY;
+/* GSI interrupts */
+static int nr_irqs_gsi = NR_IRQS_LEGACY;
+
 #if defined (CONFIG_MCA) || defined (CONFIG_EISA)
 int mp_bus_id_to_type[MAX_MP_BUSSES];
 #endif
@@ -173,6 +178,12 @@ static struct irq_cfg irq_cfgx[NR_IRQS] = {
 	[15] = { .vector = IRQ15_VECTOR, },
 };
 
+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;
@@ -190,7 +201,7 @@ int __init arch_early_irq_init(void)
 		desc->chip_data = &cfg[i];
 		zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
 		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
-		if (i < NR_IRQS_LEGACY)
+		if (i < nr_legacy_irqs)
 			cpumask_setall(cfg[i].domain);
 	}
 
@@ -867,7 +878,7 @@ static int __init find_isa_irq_apic(int irq, int type)
  */
 static int EISA_ELCR(unsigned int irq)
 {
-	if (irq < NR_IRQS_LEGACY) {
+	if (irq < nr_legacy_irqs) {
 		unsigned int port = 0x4d0 + (irq >> 3);
 		return (inb(port) >> (irq & 7)) & 1;
 	}
@@ -1464,7 +1475,7 @@ 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_IRQS_LEGACY)
+	if (irq < nr_legacy_irqs)
 		disable_8259A_irq(irq);
 
 	ioapic_write_entry(apic_id, pin, entry);
@@ -1831,7 +1842,7 @@ __apicdebuginit(void) print_PIC(void)
 	unsigned int v;
 	unsigned long flags;
 
-	if (apic_verbosity == APIC_QUIET)
+	if (apic_verbosity == APIC_QUIET || !nr_legacy_irqs)
 		return;
 
 	printk(KERN_DEBUG "\nprinting PIC contents\n");
@@ -1894,6 +1905,10 @@ void __init enable_IO_APIC(void)
 		spin_unlock_irqrestore(&ioapic_lock, flags);
 		nr_ioapic_registers[apic] = reg_01.bits.entries+1;
 	}
+
+	if (!nr_legacy_irqs)
+		return;
+
 	for(apic = 0; apic < nr_ioapics; apic++) {
 		int pin;
 		/* See if any of the pins is in ExtINT mode */
@@ -1948,6 +1963,9 @@ void disable_IO_APIC(void)
 	 */
 	clear_IO_APIC();
 
+	if (!nr_legacy_irqs)
+		return;
+
 	/*
 	 * If the i8259 is routed through an IOAPIC
 	 * Put that IOAPIC in virtual wire mode
@@ -1994,7 +2012,7 @@ void disable_IO_APIC(void)
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
 
-static void __init setup_ioapic_ids_from_mpc(void)
+void __init setup_ioapic_ids_from_mpc(void)
 {
 	union IO_APIC_reg_00 reg_00;
 	physid_mask_t phys_id_present_map;
@@ -2003,9 +2021,8 @@ static void __init setup_ioapic_ids_from_mpc(void)
 	unsigned char old_id;
 	unsigned long flags;
 
-	if (x86_quirks->setup_ioapic_ids && x86_quirks->setup_ioapic_ids())
+	if (acpi_ioapic)
 		return;
-
 	/*
 	 * Don't check I/O APIC IDs for xAPIC systems.  They have
 	 * no meaning without the serial APIC bus.
@@ -2179,7 +2196,7 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
 	struct irq_cfg *cfg;
 
 	spin_lock_irqsave(&ioapic_lock, flags);
-	if (irq < NR_IRQS_LEGACY) {
+	if (irq < nr_legacy_irqs) {
 		disable_8259A_irq(irq);
 		if (i8259A_irq_pending(irq))
 			was_pending = 1;
@@ -2657,7 +2674,7 @@ static inline void init_IO_APIC_traps(void)
 			 * so default to an old-fashioned 8259
 			 * interrupt if we can..
 			 */
-			if (irq < NR_IRQS_LEGACY)
+			if (irq < nr_legacy_irqs)
 				make_8259A_irq(irq);
 			else
 				/* Strange. Oh, well.. */
@@ -2993,7 +3010,7 @@ out:
  * the I/O APIC in all cases now.  No actual device should request
  * it anyway.  --macro
  */
-#define PIC_IRQS	(1 << PIC_CASCADE_IR)
+#define PIC_IRQS	(1UL << PIC_CASCADE_IR)
 
 void __init setup_IO_APIC(void)
 {
@@ -3001,21 +3018,19 @@ void __init setup_IO_APIC(void)
 	/*
 	 * calling enable_IO_APIC() is moved to setup_local_APIC for BP
 	 */
-
-	io_apic_irqs = ~PIC_IRQS;
+	io_apic_irqs = nr_legacy_irqs ? ~PIC_IRQS : ~0UL;
 
 	apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
 	/*
          * Set up IO-APIC IRQ routing.
          */
-#ifdef CONFIG_X86_32
-	if (!acpi_ioapic)
-		setup_ioapic_ids_from_mpc();
-#endif
+	x86_init.mpparse.setup_ioapic_ids();
+
 	sync_Arb_IDs();
 	setup_IO_APIC_irqs();
 	init_IO_APIC_traps();
-	check_timer();
+	if (nr_legacy_irqs)
+		check_timer();
 }
 
 /*
@@ -3116,7 +3131,6 @@ static int __init ioapic_init_sysfs(void)
 
 device_initcall(ioapic_init_sysfs);
 
-static int nr_irqs_gsi = NR_IRQS_LEGACY;
 /*
  * Dynamic irq allocate and deallocation
  */
@@ -3856,7 +3870,7 @@ 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_IRQS_LEGACY) {
+	if (irq >= 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",
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index ca96e68f0d23..efa00e2b8505 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -66,7 +66,6 @@ struct mpc_trans {
 	unsigned short			trans_reserved;
 };
 
-/* x86_quirks member */
 static int				mpc_record;
 
 static struct mpc_trans			*translation_table[MAX_MPC_ENTRY];
@@ -130,10 +129,9 @@ void __cpuinit numaq_tsc_disable(void)
 	}
 }
 
-static int __init numaq_pre_time_init(void)
+static void __init numaq_tsc_init(void)
 {
 	numaq_tsc_disable();
-	return 0;
 }
 
 static inline int generate_logical_apicid(int quad, int phys_apicid)
@@ -177,6 +175,19 @@ static void mpc_oem_pci_bus(struct mpc_bus *m)
 	quad_local_to_mp_bus_id[quad][local] = m->busid;
 }
 
+/*
+ * Called from mpparse code.
+ * mode = 0: prescan
+ * mode = 1: one mpc entry scanned
+ */
+static void numaq_mpc_record(unsigned int mode)
+{
+	if (!mode)
+		mpc_record = 0;
+	else
+		mpc_record++;
+}
+
 static void __init MP_translation_info(struct mpc_trans *m)
 {
 	printk(KERN_INFO
@@ -206,9 +217,9 @@ static int __init mpf_checksum(unsigned char *mp, int len)
 /*
  * Read/parse the MPC oem tables
  */
-static void __init
- smp_read_mpc_oem(struct mpc_oemtable *oemtable, unsigned short oemsize)
+static void __init smp_read_mpc_oem(struct mpc_table *mpc)
 {
+	struct mpc_oemtable *oemtable = (void *)(long)mpc->oemptr;
 	int count = sizeof(*oemtable);	/* the header size */
 	unsigned char *oemptr = ((unsigned char *)oemtable) + count;
 
@@ -250,29 +261,6 @@ static void __init
 	}
 }
 
-static int __init numaq_setup_ioapic_ids(void)
-{
-	/* so can skip it */
-	return 1;
-}
-
-static struct x86_quirks numaq_x86_quirks __initdata = {
-	.arch_pre_time_init		= numaq_pre_time_init,
-	.arch_time_init			= NULL,
-	.arch_pre_intr_init		= NULL,
-	.arch_memory_setup		= NULL,
-	.arch_intr_init			= NULL,
-	.arch_trap_init			= NULL,
-	.mach_get_smp_config		= NULL,
-	.mach_find_smp_config		= NULL,
-	.mpc_record			= &mpc_record,
-	.mpc_apic_id			= mpc_apic_id,
-	.mpc_oem_bus_info		= mpc_oem_bus_info,
-	.mpc_oem_pci_bus		= mpc_oem_pci_bus,
-	.smp_read_mpc_oem		= smp_read_mpc_oem,
-	.setup_ioapic_ids		= numaq_setup_ioapic_ids,
-};
-
 static __init void early_check_numaq(void)
 {
 	/*
@@ -286,8 +274,15 @@ static __init void early_check_numaq(void)
 	if (smp_found_config)
 		early_get_smp_config();
 
-	if (found_numaq)
-		x86_quirks = &numaq_x86_quirks;
+	if (found_numaq) {
+		x86_init.mpparse.mpc_record = numaq_mpc_record;
+		x86_init.mpparse.setup_ioapic_ids = x86_init_noop;
+		x86_init.mpparse.mpc_apic_id = mpc_apic_id;
+		x86_init.mpparse.smp_read_mpc_oem = smp_read_mpc_oem;
+		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;
+	}
 }
 
 int __init get_memcfg_numaq(void)
@@ -418,7 +413,7 @@ static inline physid_mask_t numaq_apicid_to_cpu_present(int logical_apicid)
 /* Where the IO area was mapped on multiquad, always 0 otherwise */
 void *xquad_portio;
 
-static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid)
+static inline int numaq_check_phys_apicid_present(int phys_apicid)
 {
 	return 1;
 }
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index eafdfbd1ea95..645ecc4ff0be 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -272,7 +272,7 @@ static physid_mask_t summit_apicid_to_cpu_present(int apicid)
 	return physid_mask_of_physid(0);
 }
 
-static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
+static int summit_check_phys_apicid_present(int physical_apicid)
 {
 	return 1;
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 4109679863c1..7bb676c533aa 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -526,6 +526,21 @@ static const struct dmi_system_id sw_any_bug_dmi_table[] = {
 	},
 	{ }
 };
+
+static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
+{
+	/* http://www.intel.com/Assets/PDF/specupdate/314554.pdf
+	 * AL30: A Machine Check Exception (MCE) Occurring during an
+	 * Enhanced Intel SpeedStep Technology Ratio Change May Cause
+	 * Both Processor Cores to Lock Up when HT is enabled*/
+	if (c->x86_vendor == X86_VENDOR_INTEL) {
+		if ((c->x86 == 15) &&
+		    (c->x86_model == 6) &&
+		    (c->x86_mask == 8) && smt_capable())
+			return -ENODEV;
+		}
+	return 0;
+}
 #endif
 
 static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
@@ -540,6 +555,12 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	dprintk("acpi_cpufreq_cpu_init\n");
 
+#ifdef CONFIG_SMP
+	result = acpi_cpufreq_blacklist(c);
+	if (result)
+		return result;
+#endif
+
 	data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 2a50ef891000..6394aa5c7985 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -605,9 +605,10 @@ static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst,
 	return 0;
 }
 
-static void invalidate_entry(struct powernow_k8_data *data, unsigned int entry)
+static void invalidate_entry(struct cpufreq_frequency_table *powernow_table,
+		unsigned int entry)
 {
-	data->powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID;
+	powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID;
 }
 
 static void print_basics(struct powernow_k8_data *data)
@@ -854,6 +855,10 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 		goto err_out;
 	}
 
+	/* fill in data */
+	data->numps = data->acpi_data.state_count;
+	powernow_k8_acpi_pst_values(data, 0);
+
 	if (cpu_family == CPU_HW_PSTATE)
 		ret_val = fill_powernow_table_pstate(data, powernow_table);
 	else
@@ -866,11 +871,8 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 	powernow_table[data->acpi_data.state_count].index = 0;
 	data->powernow_table = powernow_table;
 
-	/* fill in data */
-	data->numps = data->acpi_data.state_count;
 	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
-	powernow_k8_acpi_pst_values(data, 0);
 
 	/* notify BIOS that we exist */
 	acpi_processor_notify_smm(THIS_MODULE);
@@ -914,13 +916,13 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 					"bad value %d.\n", i, index);
 			printk(KERN_ERR PFX "Please report to BIOS "
 					"manufacturer\n");
-			invalidate_entry(data, i);
+			invalidate_entry(powernow_table, i);
 			continue;
 		}
 		rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi);
 		if (!(hi & HW_PSTATE_VALID_MASK)) {
 			dprintk("invalid pstate %d, ignoring\n", index);
-			invalidate_entry(data, i);
+			invalidate_entry(powernow_table, i);
 			continue;
 		}
 
@@ -941,7 +943,6 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 		struct cpufreq_frequency_table *powernow_table)
 {
 	int i;
-	int cntlofreq = 0;
 
 	for (i = 0; i < data->acpi_data.state_count; i++) {
 		u32 fid;
@@ -970,7 +971,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 		/* verify frequency is OK */
 		if ((freq > (MAX_FREQ * 1000)) || (freq < (MIN_FREQ * 1000))) {
 			dprintk("invalid freq %u kHz, ignoring\n", freq);
-			invalidate_entry(data, i);
+			invalidate_entry(powernow_table, i);
 			continue;
 		}
 
@@ -978,38 +979,17 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 		 * BIOSs are using "off" to indicate invalid */
 		if (vid == VID_OFF) {
 			dprintk("invalid vid %u, ignoring\n", vid);
-			invalidate_entry(data, i);
+			invalidate_entry(powernow_table, i);
 			continue;
 		}
 
-		/* verify only 1 entry from the lo frequency table */
-		if (fid < HI_FID_TABLE_BOTTOM) {
-			if (cntlofreq) {
-				/* if both entries are the same,
-				 * ignore this one ... */
-				if ((freq != powernow_table[cntlofreq].frequency) ||
-				    (index != powernow_table[cntlofreq].index)) {
-					printk(KERN_ERR PFX
-						"Too many lo freq table "
-						"entries\n");
-					return 1;
-				}
-
-				dprintk("double low frequency table entry, "
-						"ignoring it.\n");
-				invalidate_entry(data, i);
-				continue;
-			} else
-				cntlofreq = i;
-		}
-
 		if (freq != (data->acpi_data.states[i].core_frequency * 1000)) {
 			printk(KERN_INFO PFX "invalid freq entries "
 				"%u kHz vs. %u kHz\n", freq,
 				(unsigned int)
 				(data->acpi_data.states[i].core_frequency
 				 * 1000));
-			invalidate_entry(data, i);
+			invalidate_entry(powernow_table, i);
 			continue;
 		}
 	}
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 93ba8eeb100a..08be922de33a 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -34,13 +34,6 @@ detect_hypervisor_vendor(struct cpuinfo_x86 *c)
 		c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE;
 }
 
-unsigned long get_hypervisor_tsc_freq(void)
-{
-	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
-		return vmware_get_tsc_khz();
-	return 0;
-}
-
 static inline void __cpuinit
 hypervisor_set_feature_bits(struct cpuinfo_x86 *c)
 {
@@ -55,3 +48,10 @@ void __cpuinit init_hypervisor(struct cpuinfo_x86 *c)
 	detect_hypervisor_vendor(c);
 	hypervisor_set_feature_bits(c);
 }
+
+void __init init_hypervisor_platform(void)
+{
+	init_hypervisor(&boot_cpu_data);
+	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
+		vmware_platform_setup();
+}
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index bc24f514ec93..0a46b4df5d80 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -24,6 +24,7 @@
 #include <linux/dmi.h>
 #include <asm/div64.h>
 #include <asm/vmware.h>
+#include <asm/x86_init.h>
 
 #define CPUID_VMWARE_INFO_LEAF	0x40000000
 #define VMWARE_HYPERVISOR_MAGIC	0x564D5868
@@ -47,21 +48,29 @@ static inline int __vmware_platform(void)
 	return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
 }
 
-static unsigned long __vmware_get_tsc_khz(void)
+static unsigned long vmware_get_tsc_khz(void)
 {
 	uint64_t tsc_hz;
 	uint32_t eax, ebx, ecx, edx;
 
 	VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
 
-	if (ebx == UINT_MAX)
-		return 0;
 	tsc_hz = eax | (((uint64_t)ebx) << 32);
 	do_div(tsc_hz, 1000);
 	BUG_ON(tsc_hz >> 32);
 	return tsc_hz;
 }
 
+void __init vmware_platform_setup(void)
+{
+	uint32_t eax, ebx, ecx, edx;
+
+	VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
+
+	if (ebx != UINT_MAX)
+		x86_platform.calibrate_tsc = vmware_get_tsc_khz;
+}
+
 /*
  * While checking the dmi string infomation, just checking the product
  * serial key should be enough, as this will always have a VMware
@@ -87,12 +96,6 @@ int vmware_platform(void)
 	return 0;
 }
 
-unsigned long vmware_get_tsc_khz(void)
-{
-	BUG_ON(!vmware_platform());
-	return __vmware_get_tsc_khz();
-}
-
 /*
  * VMware hypervisor takes care of exporting a reliable TSC to the guest.
  * Still, due to timing difference when running on virtual cpus, the TSC can
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 147005a1cc3c..a3210ce1eccd 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1455,28 +1455,11 @@ char *__init default_machine_specific_memory_setup(void)
 	return who;
 }
 
-char *__init __attribute__((weak)) machine_specific_memory_setup(void)
-{
-	if (x86_quirks->arch_memory_setup) {
-		char *who = x86_quirks->arch_memory_setup();
-
-		if (who)
-			return who;
-	}
-	return default_machine_specific_memory_setup();
-}
-
-/* Overridden in paravirt.c if CONFIG_PARAVIRT */
-char * __init __attribute__((weak)) memory_setup(void)
-{
-	return machine_specific_memory_setup();
-}
-
 void __init setup_memory_map(void)
 {
 	char *who;
 
-	who = memory_setup();
+	who = x86_init.resources.memory_setup();
 	memcpy(&e820_saved, &e820, sizeof(struct e820map));
 	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
 	e820_print_map(who);
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index fe26ba3e3451..ad5bd988fb79 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -42,6 +42,7 @@
 #include <asm/time.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
+#include <asm/x86_init.h>
 
 #define EFI_DEBUG	1
 #define PFX 		"EFI: "
@@ -453,6 +454,9 @@ void __init efi_init(void)
 	if (add_efi_memmap)
 		do_add_efi_memmap();
 
+	x86_platform.get_wallclock = efi_get_time;
+	x86_platform.set_wallclock = efi_set_rtc_mmss;
+
 	/* Setup for EFI runtime service */
 	reboot_type = BOOT_EFI;
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 3f8579f8d42c..4f8e2507e8f3 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -11,8 +11,21 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/e820.h>
-#include <asm/bios_ebda.h>
+#include <asm/page.h>
 #include <asm/trampoline.h>
+#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/bios_ebda.h>
+
+static void __init i386_default_early_setup(void)
+{
+	/* Initilize 32bit specific setup functions */
+	x86_init.resources.probe_roms = probe_roms;
+	x86_init.resources.reserve_resources = i386_reserve_resources;
+	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
+
+	reserve_ebda_region();
+}
 
 void __init i386_start_kernel(void)
 {
@@ -29,7 +42,16 @@ void __init i386_start_kernel(void)
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
-	reserve_ebda_region();
+
+	/* Call the subarch specific early setup function */
+	switch (boot_params.hdr.hardware_subarch) {
+	case X86_SUBARCH_MRST:
+		x86_mrst_early_setup();
+		break;
+	default:
+		i386_default_early_setup();
+		break;
+	}
 
 	/*
 	 * At this point everything still needed from the boot loader
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 70eaa852c732..0b06cd778fd9 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -23,8 +23,8 @@
 #include <asm/sections.h>
 #include <asm/kdebug.h>
 #include <asm/e820.h>
-#include <asm/bios_ebda.h>
 #include <asm/trampoline.h>
+#include <asm/bios_ebda.h>
 
 static void __init zap_identity_mappings(void)
 {
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 7ffec6b3b331..b766e8c7252d 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -157,6 +157,7 @@ subarch_entries:
 	.long default_entry		/* normal x86/PC */
 	.long lguest_entry		/* lguest hypervisor */
 	.long xen_entry			/* Xen hypervisor */
+	.long default_entry		/* Moorestown MID */
 num_subarch_entries = (. - subarch_entries) / 4
 .previous
 #endif /* CONFIG_PARAVIRT */
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 5cf36c053ac4..23c167925a5c 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -19,12 +19,6 @@
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
-#ifdef CONFIG_X86_32
-static void pit_disable_clocksource(void);
-#else
-static inline void pit_disable_clocksource(void) { }
-#endif
-
 /*
  * HPET replaces the PIT, when enabled. So we need to know, which of
  * the two timers is used
@@ -57,12 +51,10 @@ static void init_pit_timer(enum clock_event_mode mode,
 			outb_pit(0, PIT_CH0);
 			outb_pit(0, PIT_CH0);
 		}
-		pit_disable_clocksource();
 		break;
 
 	case CLOCK_EVT_MODE_ONESHOT:
 		/* One shot setup */
-		pit_disable_clocksource();
 		outb_pit(0x38, PIT_MODE);
 		break;
 
@@ -200,17 +192,6 @@ static struct clocksource pit_cs = {
 	.shift		= 20,
 };
 
-static void pit_disable_clocksource(void)
-{
-	/*
-	 * Use mult to check whether it is registered or not
-	 */
-	if (pit_cs.mult) {
-		clocksource_unregister(&pit_cs);
-		pit_cs.mult = 0;
-	}
-}
-
 static int __init init_pit_clocksource(void)
 {
 	 /*
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index ccf8ab54f31a..300883112e3d 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -116,7 +116,7 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	return 0;
 }
 
-static void __init init_ISA_irqs(void)
+void __init init_ISA_irqs(void)
 {
 	int i;
 
@@ -140,8 +140,10 @@ static void __init init_ISA_irqs(void)
 	}
 }
 
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+void __init init_IRQ(void)
+{
+	x86_init.irqs.intr_init();
+}
 
 static void __init smp_intr_init(void)
 {
@@ -213,32 +215,12 @@ static void __init apic_intr_init(void)
 #endif
 }
 
-/**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- *	Perform any necessary interrupt initialisation prior to setting up
- *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
- *	interrupts should be initialised here if the machine emulates a PC
- *	in any way.
- **/
-static void __init x86_quirk_pre_intr_init(void)
-{
-#ifdef CONFIG_X86_32
-	if (x86_quirks->arch_pre_intr_init) {
-		if (x86_quirks->arch_pre_intr_init())
-			return;
-	}
-#endif
-	init_ISA_irqs();
-}
-
 void __init native_init_IRQ(void)
 {
 	int i;
 
 	/* Execute any quirks before the call gates are initialised: */
-	x86_quirk_pre_intr_init();
+	x86_init.irqs.pre_vector_init();
 
 	apic_intr_init();
 
@@ -258,12 +240,6 @@ void __init native_init_IRQ(void)
 
 #ifdef CONFIG_X86_32
 	/*
-	 * Call quirks after call gates are initialised (usually add in
-	 * the architecture specific gates):
-	 */
-	x86_quirk_intr_init();
-
-	/*
 	 * External FPU? Set up irq13 if so, for
 	 * original braindamaged IBM FERR coupling.
 	 */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index e5efcdcca31b..feaeb0d3aa4f 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -22,6 +22,8 @@
 #include <asm/msr.h>
 #include <asm/apic.h>
 #include <linux/percpu.h>
+
+#include <asm/x86_init.h>
 #include <asm/reboot.h>
 
 #define KVM_SCALE 22
@@ -182,12 +184,13 @@ void __init kvmclock_init(void)
 	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
 		if (kvm_register_clock("boot clock"))
 			return;
-		pv_time_ops.get_wallclock = kvm_get_wallclock;
-		pv_time_ops.set_wallclock = kvm_set_wallclock;
 		pv_time_ops.sched_clock = kvm_clock_read;
-		pv_time_ops.get_tsc_khz = kvm_get_tsc_khz;
+		x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+		x86_platform.get_wallclock = kvm_get_wallclock;
+		x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+		x86_cpuinit.setup_percpu_clockev =
+			kvm_setup_secondary_clock;
 #endif
 #ifdef CONFIG_SMP
 		smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index fcd513bf2846..5be95ef4ffec 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -45,6 +45,11 @@ static int __init mpf_checksum(unsigned char *mp, int len)
 	return sum & 0xFF;
 }
 
+int __init default_mpc_apic_id(struct mpc_cpu *m)
+{
+	return m->apicid;
+}
+
 static void __init MP_processor_info(struct mpc_cpu *m)
 {
 	int apicid;
@@ -55,10 +60,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 		return;
 	}
 
-	if (x86_quirks->mpc_apic_id)
-		apicid = x86_quirks->mpc_apic_id(m);
-	else
-		apicid = m->apicid;
+	apicid = x86_init.mpparse.mpc_apic_id(m);
 
 	if (m->cpuflag & CPU_BOOTPROCESSOR) {
 		bootup_cpu = " (Bootup-CPU)";
@@ -70,16 +72,18 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 }
 
 #ifdef CONFIG_X86_IO_APIC
-static void __init MP_bus_info(struct mpc_bus *m)
+void __init default_mpc_oem_bus_info(struct mpc_bus *m, char *str)
 {
-	char str[7];
 	memcpy(str, m->bustype, 6);
 	str[6] = 0;
+	apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->busid, str);
+}
 
-	if (x86_quirks->mpc_oem_bus_info)
-		x86_quirks->mpc_oem_bus_info(m, str);
-	else
-		apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->busid, str);
+static void __init MP_bus_info(struct mpc_bus *m)
+{
+	char str[7];
+
+	x86_init.mpparse.mpc_oem_bus_info(m, str);
 
 #if MAX_MP_BUSSES < 256
 	if (m->busid >= MAX_MP_BUSSES) {
@@ -96,8 +100,8 @@ static void __init MP_bus_info(struct mpc_bus *m)
 		mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
 #endif
 	} else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) {
-		if (x86_quirks->mpc_oem_pci_bus)
-			x86_quirks->mpc_oem_pci_bus(m);
+		if (x86_init.mpparse.mpc_oem_pci_bus)
+			x86_init.mpparse.mpc_oem_pci_bus(m);
 
 		clear_bit(m->busid, mp_bus_not_pci);
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
@@ -291,6 +295,8 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt)
 			1, mpc, mpc->length, 1);
 }
 
+void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { }
+
 static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 {
 	char str[16];
@@ -312,16 +318,13 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 	if (early)
 		return 1;
 
-	if (mpc->oemptr && x86_quirks->smp_read_mpc_oem) {
-		struct mpc_oemtable *oem_table = (void *)(long)mpc->oemptr;
-		x86_quirks->smp_read_mpc_oem(oem_table, mpc->oemsize);
-	}
+	if (mpc->oemptr)
+		x86_init.mpparse.smp_read_mpc_oem(mpc);
 
 	/*
 	 *      Now process the configuration blocks.
 	 */
-	if (x86_quirks->mpc_record)
-		*x86_quirks->mpc_record = 0;
+	x86_init.mpparse.mpc_record(0);
 
 	while (count < mpc->length) {
 		switch (*mpt) {
@@ -353,8 +356,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 			count = mpc->length;
 			break;
 		}
-		if (x86_quirks->mpc_record)
-			(*x86_quirks->mpc_record)++;
+		x86_init.mpparse.mpc_record(1);
 	}
 
 #ifdef CONFIG_X86_BIGSMP
@@ -608,7 +610,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
 /*
  * Scan the memory blocks for an SMP configuration block.
  */
-static void __init __get_smp_config(unsigned int early)
+void __init default_get_smp_config(unsigned int early)
 {
 	struct mpf_intel *mpf = mpf_found;
 
@@ -625,11 +627,6 @@ static void __init __get_smp_config(unsigned int early)
 	if (acpi_lapic && acpi_ioapic)
 		return;
 
-	if (x86_quirks->mach_get_smp_config) {
-		if (x86_quirks->mach_get_smp_config(early))
-			return;
-	}
-
 	printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
 	       mpf->specification);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
@@ -670,16 +667,6 @@ static void __init __get_smp_config(unsigned int early)
 	 */
 }
 
-void __init early_get_smp_config(void)
-{
-	__get_smp_config(1);
-}
-
-void __init get_smp_config(void)
-{
-	__get_smp_config(0);
-}
-
 static void __init smp_reserve_bootmem(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
@@ -745,14 +732,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 	return 0;
 }
 
-static void __init __find_smp_config(unsigned int reserve)
+void __init default_find_smp_config(unsigned int reserve)
 {
 	unsigned int address;
 
-	if (x86_quirks->mach_find_smp_config) {
-		if (x86_quirks->mach_find_smp_config(reserve))
-			return;
-	}
 	/*
 	 * FIXME: Linux assumes you have 640K of base ram..
 	 * this continues the error...
@@ -787,16 +770,6 @@ static void __init __find_smp_config(unsigned int reserve)
 		smp_scan_config(address, 0x400, reserve);
 }
 
-void __init early_find_smp_config(void)
-{
-	__find_smp_config(0);
-}
-
-void __init find_smp_config(void)
-{
-	__find_smp_config(1);
-}
-
 #ifdef CONFIG_X86_IO_APIC
 static u8 __initdata irq_used[MAX_IRQ_SOURCES];
 
diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c
new file mode 100644
index 000000000000..3b7078abc871
--- /dev/null
+++ b/arch/x86/kernel/mrst.c
@@ -0,0 +1,24 @@
+/*
+ * mrst.c: Intel Moorestown platform specific setup code
+ *
+ * (C) Copyright 2008 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.
+ */
+#include <linux/init.h>
+
+#include <asm/setup.h>
+
+/*
+ * Moorestown specific x86_init function overrides and early setup
+ * calls.
+ */
+void __init x86_mrst_early_setup(void)
+{
+	x86_init.resources.probe_roms = x86_init_noop;
+	x86_init.resources.reserve_resources = x86_init_noop;
+}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f5b0b4a01fb2..1b1739d16310 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -54,17 +54,12 @@ u64 _paravirt_ident_64(u64 x)
 	return x;
 }
 
-static void __init default_banner(void)
+void __init default_banner(void)
 {
 	printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
 	       pv_info.name);
 }
 
-char *memory_setup(void)
-{
-	return pv_init_ops.memory_setup();
-}
-
 /* Simple instruction patching code. */
 #define DEF_NATIVE(ops, name, code)					\
 	extern const char start_##ops##_##name[], end_##ops##_##name[];	\
@@ -188,11 +183,6 @@ unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
 	return insn_len;
 }
 
-void init_IRQ(void)
-{
-	pv_irq_ops.init_IRQ();
-}
-
 static void native_flush_tlb(void)
 {
 	__native_flush_tlb();
@@ -218,13 +208,6 @@ extern void native_irq_enable_sysexit(void);
 extern void native_usergs_sysret32(void);
 extern void native_usergs_sysret64(void);
 
-static int __init print_banner(void)
-{
-	pv_init_ops.banner();
-	return 0;
-}
-core_initcall(print_banner);
-
 static struct resource reserve_ioports = {
 	.start = 0,
 	.end = IO_SPACE_LIMIT,
@@ -320,21 +303,13 @@ struct pv_info pv_info = {
 
 struct pv_init_ops pv_init_ops = {
 	.patch = native_patch,
-	.banner = default_banner,
-	.arch_setup = paravirt_nop,
-	.memory_setup = machine_specific_memory_setup,
 };
 
 struct pv_time_ops pv_time_ops = {
-	.time_init = hpet_time_init,
-	.get_wallclock = native_get_wallclock,
-	.set_wallclock = native_set_wallclock,
 	.sched_clock = native_sched_clock,
-	.get_tsc_khz = native_calibrate_tsc,
 };
 
 struct pv_irq_ops pv_irq_ops = {
-	.init_IRQ = native_init_IRQ,
 	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
 	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
 	.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
@@ -409,8 +384,6 @@ struct pv_cpu_ops pv_cpu_ops = {
 
 struct pv_apic_ops pv_apic_ops = {
 #ifdef CONFIG_X86_LOCAL_APIC
-	.setup_boot_clock = setup_boot_APIC_clock,
-	.setup_secondary_clock = setup_secondary_APIC_clock,
 	.startup_ipi_hook = paravirt_nop,
 #endif
 };
@@ -424,13 +397,6 @@ struct pv_apic_ops pv_apic_ops = {
 #endif
 
 struct pv_mmu_ops pv_mmu_ops = {
-#ifndef CONFIG_X86_64
-	.pagetable_setup_start = native_pagetable_setup_start,
-	.pagetable_setup_done = native_pagetable_setup_done,
-#else
-	.pagetable_setup_start = paravirt_nop,
-	.pagetable_setup_done = paravirt_nop,
-#endif
 
 	.read_cr2 = native_read_cr2,
 	.write_cr2 = native_write_cr2,
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 5d465b207e72..1cfbbfc3ae26 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -8,6 +8,7 @@
 #include <linux/pnp.h>
 
 #include <asm/vsyscall.h>
+#include <asm/x86_init.h>
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_32
@@ -165,33 +166,29 @@ void rtc_cmos_write(unsigned char val, unsigned char addr)
 }
 EXPORT_SYMBOL(rtc_cmos_write);
 
-static int set_rtc_mmss(unsigned long nowtime)
+int update_persistent_clock(struct timespec now)
 {
 	unsigned long flags;
 	int retval;
 
 	spin_lock_irqsave(&rtc_lock, flags);
-	retval = set_wallclock(nowtime);
+	retval = x86_platform.set_wallclock(now.tv_sec);
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	return retval;
 }
 
 /* not static: needed by APM */
-unsigned long read_persistent_clock(void)
+void read_persistent_clock(struct timespec *ts)
 {
 	unsigned long retval, flags;
 
 	spin_lock_irqsave(&rtc_lock, flags);
-	retval = get_wallclock();
+	retval = x86_platform.get_wallclock();
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
-	return retval;
-}
-
-int update_persistent_clock(struct timespec now)
-{
-	return set_rtc_mmss(now.tv_sec);
+	ts->tv_sec = retval;
+	ts->tv_nsec = 0;
 }
 
 unsigned long long native_read_tsc(void)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f5baa2ae0c87..f327bccf5089 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -109,10 +109,6 @@
 #include <asm/numa_64.h>
 #endif
 
-#ifndef ARCH_SETUP
-#define ARCH_SETUP
-#endif
-
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
  * The direct mapping extends to max_pfn_mapped, so that we can directly access
@@ -134,9 +130,9 @@ int default_cpu_present_to_apicid(int mps_cpu)
 	return __default_cpu_present_to_apicid(mps_cpu);
 }
 
-int default_check_phys_apicid_present(int boot_cpu_physical_apicid)
+int default_check_phys_apicid_present(int phys_apicid)
 {
-	return __default_check_phys_apicid_present(boot_cpu_physical_apicid);
+	return __default_check_phys_apicid_present(phys_apicid);
 }
 #endif
 
@@ -172,13 +168,6 @@ static struct resource bss_resource = {
 
 
 #ifdef CONFIG_X86_32
-static struct resource video_ram_resource = {
-	.name	= "Video RAM area",
-	.start	= 0xa0000,
-	.end	= 0xbffff,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
-};
-
 /* cpu data as detected by the assembly code in head.S */
 struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1};
 /* common cpu data for all cpus */
@@ -606,7 +595,7 @@ static struct resource standard_io_resources[] = {
 		.flags = IORESOURCE_BUSY | IORESOURCE_IO }
 };
 
-static void __init reserve_standard_io_resources(void)
+void __init reserve_standard_io_resources(void)
 {
 	int i;
 
@@ -638,10 +627,6 @@ static int __init setup_elfcorehdr(char *arg)
 early_param("elfcorehdr", setup_elfcorehdr);
 #endif
 
-static struct x86_quirks default_x86_quirks __initdata;
-
-struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
-
 #ifdef CONFIG_X86_RESERVE_LOW_64K
 static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 {
@@ -758,7 +743,7 @@ void __init setup_arch(char **cmdline_p)
 	}
 #endif
 
-	ARCH_SETUP
+	x86_init.oem.arch_setup();
 
 	setup_memory_map();
 	parse_setup_data();
@@ -844,11 +829,9 @@ void __init setup_arch(char **cmdline_p)
 	 * VMware detection requires dmi to be available, so this
 	 * needs to be done after dmi_scan_machine, for the BP.
 	 */
-	init_hypervisor(&boot_cpu_data);
+	init_hypervisor_platform();
 
-#ifdef CONFIG_X86_32
-	probe_roms();
-#endif
+	x86_init.resources.probe_roms();
 
 	/* after parse_early_param, so could debug it */
 	insert_resource(&iomem_resource, &code_resource);
@@ -983,10 +966,9 @@ void __init setup_arch(char **cmdline_p)
 	kvmclock_init();
 #endif
 
-	paravirt_pagetable_setup_start(swapper_pg_dir);
+	x86_init.paging.pagetable_setup_start(swapper_pg_dir);
 	paging_init();
-	paravirt_pagetable_setup_done(swapper_pg_dir);
-	paravirt_post_allocator_init();
+	x86_init.paging.pagetable_setup_done(swapper_pg_dir);
 
 	tboot_probe();
 
@@ -1003,13 +985,11 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	acpi_boot_init();
 
-#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS)
 	/*
 	 * get boot-time SMP configuration:
 	 */
 	if (smp_found_config)
 		get_smp_config();
-#endif
 
 	prefill_possible_map();
 
@@ -1028,10 +1008,7 @@ void __init setup_arch(char **cmdline_p)
 	e820_reserve_resources();
 	e820_mark_nosave_regions(max_low_pfn);
 
-#ifdef CONFIG_X86_32
-	request_resource(&iomem_resource, &video_ram_resource);
-#endif
-	reserve_standard_io_resources();
+	x86_init.resources.reserve_resources();
 
 	e820_setup_gap();
 
@@ -1043,78 +1020,22 @@ void __init setup_arch(char **cmdline_p)
 	conswitchp = &dummy_con;
 #endif
 #endif
+	x86_init.oem.banner();
 }
 
 #ifdef CONFIG_X86_32
 
-/**
- * x86_quirk_intr_init - post gate setup interrupt initialisation
- *
- * Description:
- *	Fill in any interrupts that may have been left out by the general
- *	init_IRQ() routine.  interrupts having to do with the machine rather
- *	than the devices on the I/O bus (like APIC interrupts in intel MP
- *	systems) are started here.
- **/
-void __init x86_quirk_intr_init(void)
-{
-	if (x86_quirks->arch_intr_init) {
-		if (x86_quirks->arch_intr_init())
-			return;
-	}
-}
-
-/**
- * x86_quirk_trap_init - initialise system specific traps
- *
- * Description:
- *	Called as the final act of trap_init().  Used in VISWS to initialise
- *	the various board specific APIC traps.
- **/
-void __init x86_quirk_trap_init(void)
-{
-	if (x86_quirks->arch_trap_init) {
-		if (x86_quirks->arch_trap_init())
-			return;
-	}
-}
-
-static struct irqaction irq0  = {
-	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
-	.name = "timer"
+static struct resource video_ram_resource = {
+	.name	= "Video RAM area",
+	.start	= 0xa0000,
+	.end	= 0xbffff,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
 };
 
-/**
- * x86_quirk_pre_time_init - do any specific initialisations before.
- *
- **/
-void __init x86_quirk_pre_time_init(void)
+void __init i386_reserve_resources(void)
 {
-	if (x86_quirks->arch_pre_time_init)
-		x86_quirks->arch_pre_time_init();
+	request_resource(&iomem_resource, &video_ram_resource);
+	reserve_standard_io_resources();
 }
 
-/**
- * x86_quirk_time_init - do any specific initialisations for the system timer.
- *
- * Description:
- *	Must plug the system timer interrupt source at HZ into the IRQ listed
- *	in irq_vectors.h:TIMER_IRQ
- **/
-void __init x86_quirk_time_init(void)
-{
-	if (x86_quirks->arch_time_init) {
-		/*
-		 * A nonzero return code does not mean failure, it means
-		 * that the architecture quirk does not want any
-		 * generic (timer) setup to be performed after this:
-		 */
-		if (x86_quirks->arch_time_init())
-			return;
-	}
-
-	irq0.mask = cpumask_of_cpu(0);
-	setup_irq(0, &irq0);
-}
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a25eeec00080..09c5e077dff7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -324,7 +324,7 @@ notrace static void __cpuinit start_secondary(void *unused)
 	/* enable local interrupts */
 	local_irq_enable();
 
-	setup_secondary_clock();
+	x86_cpuinit.setup_percpu_clockev();
 
 	wmb();
 	cpu_idle();
@@ -1114,7 +1114,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	printk(KERN_INFO "CPU%d: ", 0);
 	print_cpu_info(&cpu_data(0));
-	setup_boot_clock();
+	x86_init.timers.setup_percpu_clockev();
 
 	if (is_uv_system())
 		uv_system_init();
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
new file mode 100644
index 000000000000..e293ac56c723
--- /dev/null
+++ b/arch/x86/kernel/time.c
@@ -0,0 +1,121 @@
+/*
+ *  Copyright (c) 1991,1992,1995  Linus Torvalds
+ *  Copyright (c) 1994  Alan Modra
+ *  Copyright (c) 1995  Markus Kuhn
+ *  Copyright (c) 1996  Ingo Molnar
+ *  Copyright (c) 1998  Andrea Arcangeli
+ *  Copyright (c) 2002,2006  Vojtech Pavlik
+ *  Copyright (c) 2003  Andi Kleen
+ *
+ */
+
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/mca.h>
+
+#include <asm/vsyscall.h>
+#include <asm/x86_init.h>
+#include <asm/i8259.h>
+#include <asm/i8253.h>
+#include <asm/timer.h>
+#include <asm/hpet.h>
+#include <asm/time.h>
+
+#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
+int timer_ack;
+#endif
+
+#ifdef CONFIG_X86_64
+volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
+#endif
+
+unsigned long profile_pc(struct pt_regs *regs)
+{
+	unsigned long pc = instruction_pointer(regs);
+
+	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
+#ifdef CONFIG_FRAME_POINTER
+		return *(unsigned long *)(regs->bp + sizeof(long));
+#else
+		unsigned long *sp = (unsigned long *)regs->sp;
+		/*
+		 * Return address is either directly at stack pointer
+		 * or above a saved flags. Eflags has bits 22-31 zero,
+		 * kernel addresses don't.
+		 */
+		if (sp[0] >> 22)
+			return sp[0];
+		if (sp[1] >> 22)
+			return sp[1];
+#endif
+	}
+	return pc;
+}
+EXPORT_SYMBOL(profile_pc);
+
+/*
+ * Default timer interrupt handler for PIT/HPET
+ */
+static irqreturn_t timer_interrupt(int irq, void *dev_id)
+{
+	/* Keep nmi watchdog up to date */
+	inc_irq_stat(irq0_irqs);
+
+	/* Optimized out for !IO_APIC and x86_64 */
+	if (timer_ack) {
+		/*
+		 * Subtle, when I/O APICs are used we have to ack timer IRQ
+		 * manually to deassert NMI lines for the watchdog if run
+		 * on an 82489DX-based system.
+		 */
+		spin_lock(&i8259A_lock);
+		outb(0x0c, PIC_MASTER_OCW3);
+		/* Ack the IRQ; AEOI will end it automatically. */
+		inb(PIC_MASTER_POLL);
+		spin_unlock(&i8259A_lock);
+	}
+
+	global_clock_event->event_handler(global_clock_event);
+
+	/* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */
+	if (MCA_bus)
+		outb_p(inb_p(0x61)| 0x80, 0x61);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction irq0  = {
+	.handler = timer_interrupt,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
+	.name = "timer"
+};
+
+void __init setup_default_timer_irq(void)
+{
+	irq0.mask = cpumask_of_cpu(0);
+	setup_irq(0, &irq0);
+}
+
+/* Default timer init function */
+void __init hpet_time_init(void)
+{
+	if (!hpet_enable())
+		setup_pit_timer();
+	setup_default_timer_irq();
+}
+
+static __init void x86_late_time_init(void)
+{
+	x86_init.timers.timer_init();
+	tsc_init();
+}
+
+/*
+ * Initialize TSC and delay the periodic timer init to
+ * late x86_late_time_init() so ioremap works.
+ */
+void __init time_init(void)
+{
+	late_time_init = x86_late_time_init;
+}
diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time_32.c
deleted file mode 100644
index 5c5d87f0b2e1..000000000000
--- a/arch/x86/kernel/time_32.c
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992, 1995  Linus Torvalds
- *
- * This file contains the PC-specific time handling details:
- * reading the RTC at bootup, etc..
- * 1994-07-02    Alan Modra
- *	fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
- * 1995-03-26    Markus Kuhn
- *      fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887
- *      precision CMOS clock update
- * 1996-05-03    Ingo Molnar
- *      fixed time warps in do_[slow|fast]_gettimeoffset()
- * 1997-09-10	Updated NTP code according to technical memorandum Jan '96
- *		"A Kernel Model for Precision Timekeeping" by Dave Mills
- * 1998-09-05    (Various)
- *	More robust do_fast_gettimeoffset() algorithm implemented
- *	(works with APM, Cyrix 6x86MX and Centaur C6),
- *	monotonic gettimeofday() with fast_get_timeoffset(),
- *	drift-proof precision TSC calibration on boot
- *	(C. Scott Ananian <cananian@alumni.princeton.edu>, Andrew D.
- *	Balsa <andrebalsa@altern.org>, Philip Gladstone <philip@raptor.com>;
- *	ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@tu-harburg.de>).
- * 1998-12-16    Andrea Arcangeli
- *	Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy
- *	because was not accounting lost_ticks.
- * 1998-12-24 Copyright (C) 1998  Andrea Arcangeli
- *	Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
- *	serialize accesses to xtime/lost_ticks).
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/time.h>
-#include <linux/mca.h>
-
-#include <asm/setup.h>
-#include <asm/hpet.h>
-#include <asm/time.h>
-#include <asm/timer.h>
-
-#include <asm/do_timer.h>
-
-int timer_ack;
-
-unsigned long profile_pc(struct pt_regs *regs)
-{
-	unsigned long pc = instruction_pointer(regs);
-
-#ifdef CONFIG_SMP
-	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
-#ifdef CONFIG_FRAME_POINTER
-		return *(unsigned long *)(regs->bp + sizeof(long));
-#else
-		unsigned long *sp = (unsigned long *)&regs->sp;
-
-		/* Return address is either directly at stack pointer
-		   or above a saved flags. Eflags has bits 22-31 zero,
-		   kernel addresses don't. */
-		if (sp[0] >> 22)
-			return sp[0];
-		if (sp[1] >> 22)
-			return sp[1];
-#endif
-	}
-#endif
-	return pc;
-}
-EXPORT_SYMBOL(profile_pc);
-
-/*
- * This is the same as the above, except we _also_ save the current
- * Time Stamp Counter value at the time of the timer interrupt, so that
- * we later on can estimate the time of day more exactly.
- */
-irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	/* Keep nmi watchdog up to date */
-	inc_irq_stat(irq0_irqs);
-
-#ifdef CONFIG_X86_IO_APIC
-	if (timer_ack) {
-		/*
-		 * Subtle, when I/O APICs are used we have to ack timer IRQ
-		 * manually to deassert NMI lines for the watchdog if run
-		 * on an 82489DX-based system.
-		 */
-		spin_lock(&i8259A_lock);
-		outb(0x0c, PIC_MASTER_OCW3);
-		/* Ack the IRQ; AEOI will end it automatically. */
-		inb(PIC_MASTER_POLL);
-		spin_unlock(&i8259A_lock);
-	}
-#endif
-
-	do_timer_interrupt_hook();
-
-#ifdef CONFIG_MCA
-	if (MCA_bus) {
-		/* The PS/2 uses level-triggered interrupts.  You can't
-		turn them off, nor would you want to (any attempt to
-		enable edge-triggered interrupts usually gets intercepted by a
-		special hardware circuit).  Hence we have to acknowledge
-		the timer interrupt.  Through some incredibly stupid
-		design idea, the reset for IRQ 0 is done by setting the
-		high bit of the PPI port B (0x61).  Note that some PS/2s,
-		notably the 55SX, work fine if this is removed.  */
-
-		u8 irq_v = inb_p(0x61);		/* read the current state */
-		outb_p(irq_v | 0x80, 0x61);	/* reset the IRQ */
-	}
-#endif
-
-	return IRQ_HANDLED;
-}
-
-/* Duplicate of time_init() below, with hpet_enable part added */
-void __init hpet_time_init(void)
-{
-	if (!hpet_enable())
-		setup_pit_timer();
-	x86_quirk_time_init();
-}
-
-/*
- * This is called directly from init code; we must delay timer setup in the
- * HPET case as we can't make the decision to turn on HPET this early in the
- * boot process.
- *
- * The chosen time_init function will usually be hpet_time_init, above, but
- * in the case of virtual hardware, an alternative function may be substituted.
- */
-void __init time_init(void)
-{
-	x86_quirk_pre_time_init();
-	tsc_init();
-	late_time_init = choose_time_init();
-}
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
deleted file mode 100644
index 5ba343e61844..000000000000
--- a/arch/x86/kernel/time_64.c
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- *  "High Precision Event Timer" based timekeeping.
- *
- *  Copyright (c) 1991,1992,1995  Linus Torvalds
- *  Copyright (c) 1994  Alan Modra
- *  Copyright (c) 1995  Markus Kuhn
- *  Copyright (c) 1996  Ingo Molnar
- *  Copyright (c) 1998  Andrea Arcangeli
- *  Copyright (c) 2002,2006  Vojtech Pavlik
- *  Copyright (c) 2003  Andi Kleen
- *  RTC support code taken from arch/i386/kernel/timers/time_hpet.c
- */
-
-#include <linux/clockchips.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/time.h>
-#include <linux/mca.h>
-#include <linux/nmi.h>
-
-#include <asm/i8253.h>
-#include <asm/hpet.h>
-#include <asm/vgtod.h>
-#include <asm/time.h>
-#include <asm/timer.h>
-
-volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
-
-unsigned long profile_pc(struct pt_regs *regs)
-{
-	unsigned long pc = instruction_pointer(regs);
-
-	/* Assume the lock function has either no stack frame or a copy
-	   of flags from PUSHF
-	   Eflags always has bits 22 and up cleared unlike kernel addresses. */
-	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
-#ifdef CONFIG_FRAME_POINTER
-		return *(unsigned long *)(regs->bp + sizeof(long));
-#else
-		unsigned long *sp = (unsigned long *)regs->sp;
-		if (sp[0] >> 22)
-			return sp[0];
-		if (sp[1] >> 22)
-			return sp[1];
-#endif
-	}
-	return pc;
-}
-EXPORT_SYMBOL(profile_pc);
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	inc_irq_stat(irq0_irqs);
-
-	global_clock_event->event_handler(global_clock_event);
-
-#ifdef CONFIG_MCA
-	if (MCA_bus) {
-		u8 irq_v = inb_p(0x61);       /* read the current state */
-		outb_p(irq_v|0x80, 0x61);     /* reset the IRQ */
-	}
-#endif
-
-	return IRQ_HANDLED;
-}
-
-/* calibrate_cpu is used on systems with fixed rate TSCs to determine
- * processor frequency */
-#define TICK_COUNT 100000000
-unsigned long __init calibrate_cpu(void)
-{
-	int tsc_start, tsc_now;
-	int i, no_ctr_free;
-	unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
-	unsigned long flags;
-
-	for (i = 0; i < 4; i++)
-		if (avail_to_resrv_perfctr_nmi_bit(i))
-			break;
-	no_ctr_free = (i == 4);
-	if (no_ctr_free) {
-		WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
-		     "cpu_khz value may be incorrect.\n");
-		i = 3;
-		rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		rdmsrl(MSR_K7_PERFCTR3, pmc3);
-	} else {
-		reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-	local_irq_save(flags);
-	/* start measuring cycles, incrementing from 0 */
-	wrmsrl(MSR_K7_PERFCTR0 + i, 0);
-	wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
-	rdtscl(tsc_start);
-	do {
-		rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
-		tsc_now = get_cycles();
-	} while ((tsc_now - tsc_start) < TICK_COUNT);
-
-	local_irq_restore(flags);
-	if (no_ctr_free) {
-		wrmsrl(MSR_K7_EVNTSEL3, 0);
-		wrmsrl(MSR_K7_PERFCTR3, pmc3);
-		wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
-	} else {
-		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-	}
-
-	return pmc_now * tsc_khz / (tsc_now - tsc_start);
-}
-
-static struct irqaction irq0 = {
-	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER,
-	.name		= "timer"
-};
-
-void __init hpet_time_init(void)
-{
-	if (!hpet_enable())
-		setup_pit_timer();
-
-	setup_irq(0, &irq0);
-}
-
-void __init time_init(void)
-{
-	tsc_init();
-
-	late_time_init = choose_time_init();
-}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 83264922a878..7dc0de9d1ed9 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -59,6 +59,7 @@
 #include <asm/mach_traps.h>
 
 #ifdef CONFIG_X86_64
+#include <asm/x86_init.h>
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #else
@@ -972,7 +973,5 @@ void __init trap_init(void)
 	 */
 	cpu_init();
 
-#ifdef CONFIG_X86_32
-	x86_quirk_trap_init();
-#endif
+	x86_init.irqs.trap_init();
 }
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 8a2fc1123690..cd982f48e23e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -17,6 +17,8 @@
 #include <asm/time.h>
 #include <asm/delay.h>
 #include <asm/hypervisor.h>
+#include <asm/nmi.h>
+#include <asm/x86_init.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -400,15 +402,9 @@ unsigned long native_calibrate_tsc(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate, hv_tsc_khz;
+	unsigned long flags, latch, ms, fast_calibrate;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	hv_tsc_khz = get_hypervisor_tsc_freq();
-	if (hv_tsc_khz) {
-		printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
-		return hv_tsc_khz;
-	}
-
 	local_irq_save(flags);
 	fast_calibrate = quick_pit_calibrate();
 	local_irq_restore(flags);
@@ -566,7 +562,7 @@ int recalibrate_cpu_khz(void)
 	unsigned long cpu_khz_old = cpu_khz;
 
 	if (cpu_has_tsc) {
-		tsc_khz = calibrate_tsc();
+		tsc_khz = x86_platform.calibrate_tsc();
 		cpu_khz = tsc_khz;
 		cpu_data(0).loops_per_jiffy =
 			cpufreq_scale(cpu_data(0).loops_per_jiffy,
@@ -744,10 +740,16 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 }
 #endif
 
+static void resume_tsc(void)
+{
+	clocksource_tsc.cycle_last = 0;
+}
+
 static struct clocksource clocksource_tsc = {
 	.name                   = "tsc",
 	.rating                 = 300,
 	.read                   = read_tsc,
+	.resume			= resume_tsc,
 	.mask                   = CLOCKSOURCE_MASK(64),
 	.shift                  = 22,
 	.flags                  = CLOCK_SOURCE_IS_CONTINUOUS |
@@ -761,12 +763,14 @@ void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
-		printk("Marking TSC unstable due to %s\n", reason);
+		printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
 		/* Change only the rating, when not registered */
 		if (clocksource_tsc.mult)
-			clocksource_change_rating(&clocksource_tsc, 0);
-		else
+			clocksource_mark_unstable(&clocksource_tsc);
+		else {
+			clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
 			clocksource_tsc.rating = 0;
+		}
 	}
 }
 
@@ -852,15 +856,71 @@ static void __init init_tsc_clocksource(void)
 	clocksource_register(&clocksource_tsc);
 }
 
+#ifdef CONFIG_X86_64
+/*
+ * calibrate_cpu is used on systems with fixed rate TSCs to determine
+ * processor frequency
+ */
+#define TICK_COUNT 100000000
+static unsigned long __init calibrate_cpu(void)
+{
+	int tsc_start, tsc_now;
+	int i, no_ctr_free;
+	unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
+	unsigned long flags;
+
+	for (i = 0; i < 4; i++)
+		if (avail_to_resrv_perfctr_nmi_bit(i))
+			break;
+	no_ctr_free = (i == 4);
+	if (no_ctr_free) {
+		WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
+		     "cpu_khz value may be incorrect.\n");
+		i = 3;
+		rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
+		wrmsrl(MSR_K7_EVNTSEL3, 0);
+		rdmsrl(MSR_K7_PERFCTR3, pmc3);
+	} else {
+		reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+		reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+	}
+	local_irq_save(flags);
+	/* start measuring cycles, incrementing from 0 */
+	wrmsrl(MSR_K7_PERFCTR0 + i, 0);
+	wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
+	rdtscl(tsc_start);
+	do {
+		rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
+		tsc_now = get_cycles();
+	} while ((tsc_now - tsc_start) < TICK_COUNT);
+
+	local_irq_restore(flags);
+	if (no_ctr_free) {
+		wrmsrl(MSR_K7_EVNTSEL3, 0);
+		wrmsrl(MSR_K7_PERFCTR3, pmc3);
+		wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
+	} else {
+		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+		release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+	}
+
+	return pmc_now * tsc_khz / (tsc_now - tsc_start);
+}
+#else
+static inline unsigned long calibrate_cpu(void) { return cpu_khz; }
+#endif
+
 void __init tsc_init(void)
 {
 	u64 lpj;
 	int cpu;
 
+	x86_init.timers.tsc_pre_init();
+
 	if (!cpu_has_tsc)
 		return;
 
-	tsc_khz = calibrate_tsc();
+	tsc_khz = x86_platform.calibrate_tsc();
 	cpu_khz = tsc_khz;
 
 	if (!tsc_khz) {
@@ -868,11 +928,9 @@ void __init tsc_init(void)
 		return;
 	}
 
-#ifdef CONFIG_X86_64
 	if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
 			(boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
 		cpu_khz = calibrate_cpu();
-#endif
 
 	printk("Detected %lu.%03lu MHz processor.\n",
 			(unsigned long)cpu_khz / 1000,
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 31ffc24eec4d..f068553a1b17 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -30,6 +30,7 @@
 #include <asm/setup.h>
 #include <asm/apic.h>
 #include <asm/e820.h>
+#include <asm/time.h>
 #include <asm/io.h>
 
 #include <linux/kernel_stat.h>
@@ -53,7 +54,7 @@ int is_visws_box(void)
 	return visws_board_type >= 0;
 }
 
-static int __init visws_time_init(void)
+static void __init visws_time_init(void)
 {
 	printk(KERN_INFO "Starting Cobalt Timer system clock\n");
 
@@ -66,21 +67,13 @@ static int __init visws_time_init(void)
 	/* Enable (unmask) the timer interrupt */
 	co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) & ~CO_CTRL_TIMEMASK);
 
-	/*
-	 * Zero return means the generic timer setup code will set up
-	 * the standard vector:
-	 */
-	return 0;
+	setup_default_timer_irq();
 }
 
-static int __init visws_pre_intr_init(void)
+/* Replaces the default init_ISA_irqs in the generic setup */
+static void __init visws_pre_intr_init(void)
 {
 	init_VISWS_APIC_irqs();
-
-	/*
-	 * We dont want ISA irqs to be set up by the generic code:
-	 */
-	return 1;
 }
 
 /* Quirk for machine specific memory setup. */
@@ -156,12 +149,8 @@ static void visws_machine_power_off(void)
 	outl(PIIX_SPECIAL_STOP, 0xCFC);
 }
 
-static int __init visws_get_smp_config(unsigned int early)
+static void __init visws_get_smp_config(unsigned int early)
 {
-	/*
-	 * Prevent MP-table parsing by the generic code:
-	 */
-	return 1;
 }
 
 /*
@@ -208,7 +197,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 	apic_version[m->apicid] = ver;
 }
 
-static int __init visws_find_smp_config(unsigned int reserve)
+static void __init visws_find_smp_config(unsigned int reserve)
 {
 	struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS);
 	unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS));
@@ -230,21 +219,9 @@ static int __init visws_find_smp_config(unsigned int reserve)
 		MP_processor_info(mp++);
 
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
-
-	return 1;
 }
 
-static int visws_trap_init(void);
-
-static struct x86_quirks visws_x86_quirks __initdata = {
-	.arch_time_init		= visws_time_init,
-	.arch_pre_intr_init	= visws_pre_intr_init,
-	.arch_memory_setup	= visws_memory_setup,
-	.arch_intr_init		= NULL,
-	.arch_trap_init		= visws_trap_init,
-	.mach_get_smp_config	= visws_get_smp_config,
-	.mach_find_smp_config	= visws_find_smp_config,
-};
+static void visws_trap_init(void);
 
 void __init visws_early_detect(void)
 {
@@ -257,11 +234,14 @@ void __init visws_early_detect(void)
 		return;
 
 	/*
-	 * Install special quirks for timer, interrupt and memory setup:
-	 * Fall back to generic behavior for traps:
-	 * Override generic MP-table parsing:
+	 * Override the default platform setup functions
 	 */
-	x86_quirks = &visws_x86_quirks;
+	x86_init.resources.memory_setup = visws_memory_setup;
+	x86_init.mpparse.get_smp_config = visws_get_smp_config;
+	x86_init.mpparse.find_smp_config = visws_find_smp_config;
+	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;
 
 	/*
 	 * Install reboot quirks:
@@ -400,12 +380,10 @@ static __init void cobalt_init(void)
 		co_apic_read(CO_APIC_ID));
 }
 
-static int __init visws_trap_init(void)
+static void __init visws_trap_init(void)
 {
 	lithium_init();
 	cobalt_init();
-
-	return 1;
 }
 
 /*
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 95a7289e4b0c..31e6f6cfe53e 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -817,15 +817,15 @@ static inline int __init activate_vmi(void)
 		vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm);
 		vmi_timer_ops.cancel_alarm =
 			 vmi_get_function(VMI_CALL_CancelAlarm);
-		pv_time_ops.time_init = vmi_time_init;
-		pv_time_ops.get_wallclock = vmi_get_wallclock;
-		pv_time_ops.set_wallclock = vmi_set_wallclock;
+		x86_init.timers.timer_init = vmi_time_init;
 #ifdef CONFIG_X86_LOCAL_APIC
-		pv_apic_ops.setup_boot_clock = vmi_time_bsp_init;
-		pv_apic_ops.setup_secondary_clock = vmi_time_ap_init;
+		x86_init.timers.setup_percpu_clockev = vmi_time_bsp_init;
+		x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init;
 #endif
 		pv_time_ops.sched_clock = vmi_sched_clock;
-		pv_time_ops.get_tsc_khz = vmi_tsc_khz;
+		x86_platform.calibrate_tsc = vmi_tsc_khz;
+		x86_platform.get_wallclock = vmi_get_wallclock;
+		x86_platform.set_wallclock = vmi_set_wallclock;
 
 		/* We have true wallclock functions; disable CMOS clock sync */
 		no_sync_cmos_clock = 1;
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index 2b3eb82efeeb..611b9e2360d3 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -68,7 +68,7 @@ unsigned long long vmi_sched_clock(void)
 	return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
 }
 
-/* paravirt_ops.get_tsc_khz = vmi_tsc_khz */
+/* x86_platform.calibrate_tsc = vmi_tsc_khz */
 unsigned long vmi_tsc_khz(void)
 {
 	unsigned long long khz;
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 25ee06a80aad..cf53a78e2dcf 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -87,6 +87,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
 	vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
 	vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
 	vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic;
+	vsyscall_gtod_data.wall_time_coarse = __current_kernel_time();
 	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
new file mode 100644
index 000000000000..4449a4a2c2ed
--- /dev/null
+++ b/arch/x86/kernel/x86_init.c
@@ -0,0 +1,75 @@
+/*
+ * Copyright (C) 2009 Thomas Gleixner <tglx@linutronix.de>
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+#include <linux/init.h>
+
+#include <asm/bios_ebda.h>
+#include <asm/paravirt.h>
+#include <asm/mpspec.h>
+#include <asm/setup.h>
+#include <asm/apic.h>
+#include <asm/e820.h>
+#include <asm/time.h>
+#include <asm/irq.h>
+#include <asm/tsc.h>
+
+void __cpuinit x86_init_noop(void) { }
+void __init x86_init_uint_noop(unsigned int unused) { }
+void __init x86_init_pgd_noop(pgd_t *unused) { }
+
+/*
+ * The platform setup functions are preset with the default functions
+ * for standard PC hardware.
+ */
+struct x86_init_ops x86_init __initdata = {
+
+	.resources = {
+		.probe_roms		= x86_init_noop,
+		.reserve_resources	= reserve_standard_io_resources,
+		.memory_setup		= default_machine_specific_memory_setup,
+	},
+
+	.mpparse = {
+		.mpc_record		= x86_init_uint_noop,
+		.setup_ioapic_ids	= x86_init_noop,
+		.mpc_apic_id		= default_mpc_apic_id,
+		.smp_read_mpc_oem	= default_smp_read_mpc_oem,
+		.mpc_oem_bus_info	= default_mpc_oem_bus_info,
+		.find_smp_config	= default_find_smp_config,
+		.get_smp_config		= default_get_smp_config,
+	},
+
+	.irqs = {
+		.pre_vector_init	= init_ISA_irqs,
+		.intr_init		= native_init_IRQ,
+		.trap_init		= x86_init_noop,
+	},
+
+	.oem = {
+		.arch_setup		= x86_init_noop,
+		.banner			= default_banner,
+	},
+
+	.paging = {
+		.pagetable_setup_start	= native_pagetable_setup_start,
+		.pagetable_setup_done	= native_pagetable_setup_done,
+	},
+
+	.timers = {
+		.setup_percpu_clockev	= setup_boot_APIC_clock,
+		.tsc_pre_init		= x86_init_noop,
+		.timer_init		= hpet_time_init,
+	},
+};
+
+struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
+	.setup_percpu_clockev		= setup_secondary_APIC_clock,
+};
+
+struct x86_platform_ops x86_platform = {
+	.calibrate_tsc			= native_calibrate_tsc,
+	.get_wallclock			= mach_get_cmos_time,
+	.set_wallclock			= mach_set_rtc_mmss,
+};