Merge commit 'v2.6.34-rc1' into for-linus

86 files changed, 5630 insertions, 3434 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 036d28adf59..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>
@@ -49,6 +50,7 @@ EXPORT_SYMBOL(acpi_disabled);
 
 #ifdef	CONFIG_X86_64
 # include <asm/proto.h>
+# include <asm/numa_64.h>
 #endif				/* X86 */
 
 #define BAD_MADT_ENTRY(entry, end) (					    \
@@ -446,6 +448,12 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
 int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
 {
 	*irq = gsi;
+
+#ifdef CONFIG_X86_IO_APIC
+	if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC)
+		setup_IO_APIC_irq_extra(gsi);
+#endif
+
 	return 0;
 }
 
@@ -473,7 +481,8 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 		plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity);
 	}
 #endif
-	acpi_gsi_to_irq(plat_gsi, &irq);
+	irq = plat_gsi;
+
 	return irq;
 }
 
@@ -482,6 +491,25 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
  */
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 
+static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+{
+#ifdef CONFIG_ACPI_NUMA
+	int nid;
+
+	nid = acpi_get_node(handle);
+	if (nid == -1 || !node_online(nid))
+		return;
+#ifdef CONFIG_X86_64
+	apicid_to_node[physid] = nid;
+	numa_set_node(cpu, nid);
+#else /* CONFIG_X86_32 */
+	apicid_2_node[physid] = nid;
+	cpu_to_node_map[cpu] = nid;
+#endif
+
+#endif
+}
+
 static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -540,6 +568,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
 	}
 
 	cpu = cpumask_first(new_map);
+	acpi_map_cpu2node(handle, cpu, physid);
 
 	*pcpu = cpu;
 	retval = 0;
@@ -1185,9 +1214,6 @@ static void __init acpi_process_madt(void)
 		if (!error) {
 			acpi_lapic = 1;
 
-#ifdef CONFIG_X86_BIGSMP
-			generic_bigsmp_probe();
-#endif
 			/*
 			 * Parse MADT IO-APIC entries
 			 */
@@ -1197,8 +1223,6 @@ static void __init acpi_process_madt(void)
 				acpi_ioapic = 1;
 
 				smp_found_config = 1;
-				if (apic->setup_apic_routing)
-					apic->setup_apic_routing();
 			}
 		}
 		if (error == -EINVAL) {
@@ -1349,14 +1373,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
 	 },
 	{
 	 .callback = force_acpi_ht,
-	 .ident = "ASUS P2B-DS",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
-		     DMI_MATCH(DMI_BOARD_NAME, "P2B-DS"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
 	 .ident = "ASUS CUR-DLS",
 	 .matches = {
 		     DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
@@ -1609,6 +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/alternative.c b/arch/x86/kernel/alternative.c
index de7353c0ce9..3a4bf35c179 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
+#include <linux/stop_machine.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
@@ -205,7 +206,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 					 struct alt_instr *end)
 {
 	struct alt_instr *a;
-	char insnbuf[MAX_PATCH_LEN];
+	u8 insnbuf[MAX_PATCH_LEN];
 
 	DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
 	for (a = start; a < end; a++) {
@@ -223,6 +224,8 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 		}
 #endif
 		memcpy(insnbuf, a->replacement, a->replacementlen);
+		if (*insnbuf == 0xe8 && a->replacementlen == 5)
+		    *(s32 *)(insnbuf + 1) += a->replacement - a->instr;
 		add_nops(insnbuf + a->replacementlen,
 			 a->instrlen - a->replacementlen);
 		text_poke_early(instr, insnbuf, a->instrlen);
@@ -390,6 +393,24 @@ void alternatives_smp_switch(int smp)
 	mutex_unlock(&smp_alt);
 }
 
+/* Return 1 if the address range is reserved for smp-alternatives */
+int alternatives_text_reserved(void *start, void *end)
+{
+	struct smp_alt_module *mod;
+	u8 **ptr;
+	u8 *text_start = start;
+	u8 *text_end = end;
+
+	list_for_each_entry(mod, &smp_alt_modules, next) {
+		if (mod->text > text_end || mod->text_end < text_start)
+			continue;
+		for (ptr = mod->locks; ptr < mod->locks_end; ptr++)
+			if (text_start <= *ptr && text_end >= *ptr)
+				return 1;
+	}
+
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_PARAVIRT
@@ -552,3 +573,62 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
 	local_irq_restore(flags);
 	return addr;
 }
+
+/*
+ * Cross-modifying kernel text with stop_machine().
+ * This code originally comes from immediate value.
+ */
+static atomic_t stop_machine_first;
+static int wrote_text;
+
+struct text_poke_params {
+	void *addr;
+	const void *opcode;
+	size_t len;
+};
+
+static int __kprobes stop_machine_text_poke(void *data)
+{
+	struct text_poke_params *tpp = data;
+
+	if (atomic_dec_and_test(&stop_machine_first)) {
+		text_poke(tpp->addr, tpp->opcode, tpp->len);
+		smp_wmb();	/* Make sure other cpus see that this has run */
+		wrote_text = 1;
+	} else {
+		while (!wrote_text)
+			cpu_relax();
+		smp_mb();	/* Load wrote_text before following execution */
+	}
+
+	flush_icache_range((unsigned long)tpp->addr,
+			   (unsigned long)tpp->addr + tpp->len);
+	return 0;
+}
+
+/**
+ * text_poke_smp - Update instructions on a live kernel on SMP
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Modify multi-byte instruction by using stop_machine() on SMP. This allows
+ * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying
+ * should be allowed, since stop_machine() does _not_ protect code against
+ * NMI and MCE.
+ *
+ * Note: Must be called under get_online_cpus() and text_mutex.
+ */
+void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
+{
+	struct text_poke_params tpp;
+
+	tpp.addr = addr;
+	tpp.opcode = opcode;
+	tpp.len = len;
+	atomic_set(&stop_machine_first, 1);
+	wrote_text = 0;
+	stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+	return addr;
+}
+
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 23824fef789..adb0ba02570 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -980,7 +980,7 @@ static int alloc_new_range(struct dma_ops_domain *dma_dom,
 {
 	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
 	struct amd_iommu *iommu;
-	int i;
+	unsigned long i;
 
 #ifdef CONFIG_IOMMU_STRESS
 	populate = false;
@@ -1489,11 +1489,14 @@ static void __detach_device(struct device *dev)
 {
 	struct iommu_dev_data *dev_data = get_dev_data(dev);
 	struct iommu_dev_data *alias_data;
+	struct protection_domain *domain;
 	unsigned long flags;
 
 	BUG_ON(!dev_data->domain);
 
-	spin_lock_irqsave(&dev_data->domain->lock, flags);
+	domain = dev_data->domain;
+
+	spin_lock_irqsave(&domain->lock, flags);
 
 	if (dev_data->alias != dev) {
 		alias_data = get_dev_data(dev_data->alias);
@@ -1504,13 +1507,15 @@ static void __detach_device(struct device *dev)
 	if (atomic_dec_and_test(&dev_data->bind))
 		do_detach(dev);
 
-	spin_unlock_irqrestore(&dev_data->domain->lock, flags);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	/*
 	 * If we run in passthrough mode the device must be assigned to the
-	 * passthrough domain if it is detached from any other domain
+	 * passthrough domain if it is detached from any other domain.
+	 * Make sure we can deassign from the pt_domain itself.
 	 */
-	if (iommu_pass_through && dev_data->domain == NULL)
+	if (iommu_pass_through &&
+	    (dev_data->domain == NULL && domain != pt_domain))
 		__attach_device(dev, pt_domain);
 }
 
@@ -2218,6 +2223,12 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 /*
  * The function which clues the AMD IOMMU driver into dma_ops.
  */
+
+void __init amd_iommu_init_api(void)
+{
+	register_iommu(&amd_iommu_ops);
+}
+
 int __init amd_iommu_init_dma_ops(void)
 {
 	struct amd_iommu *iommu;
@@ -2253,8 +2264,6 @@ int __init amd_iommu_init_dma_ops(void)
 	/* Make the driver finally visible to the drivers */
 	dma_ops = &amd_iommu_dma_ops;
 
-	register_iommu(&amd_iommu_ops);
-
 	amd_iommu_stats_init();
 
 	return 0;
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index fb490ce7dd5..9dc91b43147 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1292,9 +1292,12 @@ static int __init amd_iommu_init(void)
 		ret = amd_iommu_init_passthrough();
 	else
 		ret = amd_iommu_init_dma_ops();
+
 	if (ret)
 		goto free;
 
+	amd_iommu_init_api();
+
 	amd_iommu_init_notifier();
 
 	enable_iommus();
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 3987e4408f7..00187f1fcfb 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -581,7 +581,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 		res = (((u64)(*deltatsc)) * pm_100ms);
 		do_div(res, deltapm);
 		apic_printk(APIC_VERBOSE, "TSC delta adjusted to "
-					  "PM-Timer: %lu (%ld) \n",
+					  "PM-Timer: %lu (%ld)\n",
 					(unsigned long)res, *deltatsc);
 		*deltatsc = (long)res;
 	}
@@ -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:
@@ -1641,9 +1641,7 @@ int __init APIC_init_uniprocessor(void)
 #endif
 
 	enable_IR_x2apic();
-#ifdef CONFIG_X86_64
 	default_setup_apic_routing();
-#endif
 
 	verify_local_APIC();
 	connect_bsp_APIC();
@@ -1891,21 +1889,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	if (apicid > max_physical_apicid)
 		max_physical_apicid = apicid;
 
-#ifdef CONFIG_X86_32
-	if (num_processors > 8) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (!APIC_XAPIC(version)) {
-				def_to_bigsmp = 0;
-				break;
-			}
-			/* If P4 and above fall through */
-		case X86_VENDOR_AMD:
-			def_to_bigsmp = 1;
-		}
-	}
-#endif
-
 #if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
 	early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
 	early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
@@ -2035,7 +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)
@@ -2079,7 +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 53243ca7816..e4e0ddcb154 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -73,8 +73,8 @@
  */
 int sis_apic_bug = -1;
 
-static DEFINE_SPINLOCK(ioapic_lock);
-static DEFINE_SPINLOCK(vector_lock);
+static DEFINE_RAW_SPINLOCK(ioapic_lock);
+static DEFINE_RAW_SPINLOCK(vector_lock);
 
 /*
  * # of IRQ routing registers
@@ -94,8 +94,6 @@ 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;
 
@@ -140,33 +138,10 @@ static struct irq_pin_list *get_one_free_irq_2_pin(int node)
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
 #ifdef CONFIG_SPARSE_IRQ
-static struct irq_cfg irq_cfgx[] = {
+static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY];
 #else
-static struct irq_cfg irq_cfgx[NR_IRQS] = {
+static struct irq_cfg irq_cfgx[NR_IRQS];
 #endif
-	[0]  = { .vector = IRQ0_VECTOR,  },
-	[1]  = { .vector = IRQ1_VECTOR,  },
-	[2]  = { .vector = IRQ2_VECTOR,  },
-	[3]  = { .vector = IRQ3_VECTOR,  },
-	[4]  = { .vector = IRQ4_VECTOR,  },
-	[5]  = { .vector = IRQ5_VECTOR,  },
-	[6]  = { .vector = IRQ6_VECTOR,  },
-	[7]  = { .vector = IRQ7_VECTOR,  },
-	[8]  = { .vector = IRQ8_VECTOR,  },
-	[9]  = { .vector = IRQ9_VECTOR,  },
-	[10] = { .vector = IRQ10_VECTOR, },
-	[11] = { .vector = IRQ11_VECTOR, },
-	[12] = { .vector = IRQ12_VECTOR, },
-	[13] = { .vector = IRQ13_VECTOR, },
-	[14] = { .vector = IRQ14_VECTOR, },
-	[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)
 {
@@ -176,6 +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);
@@ -185,8 +165,14 @@ 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_legacy_irqs)
-			cpumask_setall(cfg[i].domain);
+		/*
+		 * For legacy IRQ's, start with assigning irq0 to irq15 to
+		 * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
+		 */
+		if (i < legacy_pic->nr_legacy_irqs) {
+			cfg[i].vector = IRQ0_VECTOR + i;
+			cpumask_set_cpu(0, cfg[i].domain);
+		}
 	}
 
 	return 0;
@@ -406,7 +392,7 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
 	struct irq_pin_list *entry;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	for_each_irq_pin(entry, cfg->irq_2_pin) {
 		unsigned int reg;
 		int pin;
@@ -415,11 +401,11 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
 		reg = io_apic_read(entry->apic, 0x10 + pin*2);
 		/* Is the remote IRR bit set? */
 		if (reg & IO_APIC_REDIR_REMOTE_IRR) {
-			spin_unlock_irqrestore(&ioapic_lock, flags);
+			raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 			return true;
 		}
 	}
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return false;
 }
@@ -433,10 +419,10 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
 {
 	union entry_union eu;
 	unsigned long flags;
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
 	eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 	return eu.entry;
 }
 
@@ -459,9 +445,9 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	__ioapic_write_entry(apic, pin, e);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
 /*
@@ -474,10 +460,10 @@ static void ioapic_mask_entry(int apic, int pin)
 	unsigned long flags;
 	union entry_union eu = { .entry.mask = 1 };
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
 	io_apic_write(apic, 0x11 + 2*pin, eu.w2);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
 /*
@@ -604,9 +590,9 @@ static void mask_IO_APIC_irq_desc(struct irq_desc *desc)
 
 	BUG_ON(!cfg);
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	__mask_IO_APIC_irq(cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
 static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
@@ -614,9 +600,9 @@ static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
 	struct irq_cfg *cfg = desc->chip_data;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	__unmask_IO_APIC_irq(cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
 static void mask_IO_APIC_irq(unsigned int irq)
@@ -865,7 +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;
 	}
@@ -1140,12 +1126,12 @@ void lock_vector_lock(void)
 	/* Used to the online set of cpus does not change
 	 * during assign_irq_vector.
 	 */
-	spin_lock(&vector_lock);
+	raw_spin_lock(&vector_lock);
 }
 
 void unlock_vector_lock(void)
 {
-	spin_unlock(&vector_lock);
+	raw_spin_unlock(&vector_lock);
 }
 
 static int
@@ -1162,7 +1148,8 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
+	static int current_offset = VECTOR_OFFSET_START % 8;
 	unsigned int old_vector;
 	int cpu, err;
 	cpumask_var_t tmp_mask;
@@ -1198,7 +1185,7 @@ next:
 		if (vector >= first_system_vector) {
 			/* If out of vectors on large boxen, must share them. */
 			offset = (offset + 1) % 8;
-			vector = FIRST_DEVICE_VECTOR + offset;
+			vector = FIRST_EXTERNAL_VECTOR + offset;
 		}
 		if (unlikely(current_vector == vector))
 			continue;
@@ -1232,9 +1219,9 @@ int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
 	int err;
 	unsigned long flags;
 
-	spin_lock_irqsave(&vector_lock, flags);
+	raw_spin_lock_irqsave(&vector_lock, flags);
 	err = __assign_irq_vector(irq, cfg, mask);
-	spin_unlock_irqrestore(&vector_lock, flags);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
 	return err;
 }
 
@@ -1268,11 +1255,16 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 void __setup_vector_irq(int cpu)
 {
 	/* Initialize vector_irq on a new cpu */
-	/* This function must be called with vector_lock held */
 	int irq, vector;
 	struct irq_cfg *cfg;
 	struct irq_desc *desc;
 
+	/*
+	 * vector_lock will make sure that we don't run into irq vector
+	 * assignments that might be happening on another cpu in parallel,
+	 * while we setup our initial vector to irq mappings.
+	 */
+	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_irq_desc(irq, desc) {
 		cfg = desc->chip_data;
@@ -1291,6 +1283,7 @@ void __setup_vector_irq(int cpu)
 		if (!cpumask_test_cpu(cpu, cfg->domain))
 			per_cpu(vector_irq, cpu)[vector] = -1;
 	}
+	raw_spin_unlock(&vector_lock);
 }
 
 static struct irq_chip ioapic_chip;
@@ -1440,6 +1433,14 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
 
 	cfg = desc->chip_data;
 
+	/*
+	 * For legacy irqs, cfg->domain starts with cpu 0 for legacy
+	 * controllers like 8259. Now that IO-APIC can handle this irq, update
+	 * the 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()))
 		return;
 
@@ -1461,8 +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);
 }
@@ -1473,7 +1474,7 @@ static struct {
 
 static void __init setup_IO_APIC_irqs(void)
 {
-	int apic_id = 0, pin, idx, irq;
+	int apic_id, pin, idx, irq;
 	int notcon = 0;
 	struct irq_desc *desc;
 	struct irq_cfg *cfg;
@@ -1481,14 +1482,7 @@ static void __init setup_IO_APIC_irqs(void)
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
-#ifdef CONFIG_ACPI
-	if (!acpi_disabled && acpi_ioapic) {
-		apic_id = mp_find_ioapic(0);
-		if (apic_id < 0)
-			apic_id = 0;
-	}
-#endif
-
+	for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
 	for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
 		idx = find_irq_entry(apic_id, pin, mp_INT);
 		if (idx == -1) {
@@ -1510,6 +1504,9 @@ static void __init setup_IO_APIC_irqs(void)
 
 		irq = pin_2_irq(idx, apic_id, pin);
 
+		if ((apic_id > 0) && (irq > 16))
+			continue;
+
 		/*
 		 * Skip the timer IRQ if there's a quirk handler
 		 * installed and if it returns 1:
@@ -1539,6 +1536,56 @@ static void __init setup_IO_APIC_irqs(void)
 }
 
 /*
+ * for the gsit that is not in first ioapic
+ * but could not use acpi_register_gsi()
+ * like some special sci in IBM x3330
+ */
+void setup_IO_APIC_irq_extra(u32 gsi)
+{
+	int apic_id = 0, pin, idx, irq;
+	int node = cpu_to_node(boot_cpu_id);
+	struct irq_desc *desc;
+	struct irq_cfg *cfg;
+
+	/*
+	 * Convert 'gsi' to 'ioapic.pin'.
+	 */
+	apic_id = mp_find_ioapic(gsi);
+	if (apic_id < 0)
+		return;
+
+	pin = mp_find_ioapic_pin(apic_id, gsi);
+	idx = find_irq_entry(apic_id, pin, mp_INT);
+	if (idx == -1)
+		return;
+
+	irq = pin_2_irq(idx, apic_id, pin);
+#ifdef CONFIG_SPARSE_IRQ
+	desc = irq_to_desc(irq);
+	if (desc)
+		return;
+#endif
+	desc = irq_to_desc_alloc_node(irq, node);
+	if (!desc) {
+		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+		return;
+	}
+
+	cfg = desc->chip_data;
+	add_pin_to_irq_node(cfg, node, apic_id, pin);
+
+	if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
+		pr_debug("Pin %d-%d already programmed\n",
+			 mp_ioapics[apic_id].apicid, pin);
+		return;
+	}
+	set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
+
+	setup_IO_APIC_irq(apic_id, pin, irq, desc,
+			irq_trigger(idx), irq_polarity(idx));
+}
+
+/*
  * Set up the timer pin, possibly with the 8259A-master behind.
  */
 static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin,
@@ -1601,14 +1648,14 @@ __apicdebuginit(void) print_IO_APIC(void)
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	reg_00.raw = io_apic_read(apic, 0);
 	reg_01.raw = io_apic_read(apic, 1);
 	if (reg_01.bits.version >= 0x10)
 		reg_02.raw = io_apic_read(apic, 2);
 	if (reg_01.bits.version >= 0x20)
 		reg_03.raw = io_apic_read(apic, 3);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	printk("\n");
 	printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].apicid);
@@ -1647,7 +1694,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	printk(KERN_DEBUG ".... IRQ redirection table:\n");
 
 	printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol"
-			  " Stat Dmod Deli Vect:   \n");
+			  " Stat Dmod Deli Vect:\n");
 
 	for (i = 0; i <= reg_01.bits.entries; i++) {
 		struct IO_APIC_route_entry entry;
@@ -1825,12 +1872,12 @@ __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");
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
 	v = inb(0xa1) << 8 | inb(0x21);
 	printk(KERN_DEBUG "... PIC  IMR: %04x\n", v);
@@ -1844,7 +1891,7 @@ __apicdebuginit(void) print_PIC(void)
 	outb(0x0a,0xa0);
 	outb(0x0a,0x20);
 
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 
 	printk(KERN_DEBUG "... PIC  ISR: %04x\n", v);
 
@@ -1903,13 +1950,13 @@ void __init enable_IO_APIC(void)
 	 * The number of IO-APIC IRQ registers (== #pins):
 	 */
 	for (apic = 0; apic < nr_ioapics; apic++) {
-		spin_lock_irqsave(&ioapic_lock, flags);
+		raw_spin_lock_irqsave(&ioapic_lock, flags);
 		reg_01.raw = io_apic_read(apic, 1);
-		spin_unlock_irqrestore(&ioapic_lock, flags);
+		raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 		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++) {
@@ -1966,7 +2013,7 @@ void disable_IO_APIC(void)
 	 */
 	clear_IO_APIC();
 
-	if (!nr_legacy_irqs)
+	if (!legacy_pic->nr_legacy_irqs)
 		return;
 
 	/*
@@ -2045,9 +2092,9 @@ void __init setup_ioapic_ids_from_mpc(void)
 	for (apic_id = 0; apic_id < nr_ioapics; apic_id++) {
 
 		/* Read the register 0 value */
-		spin_lock_irqsave(&ioapic_lock, flags);
+		raw_spin_lock_irqsave(&ioapic_lock, flags);
 		reg_00.raw = io_apic_read(apic_id, 0);
-		spin_unlock_irqrestore(&ioapic_lock, flags);
+		raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 		old_id = mp_ioapics[apic_id].apicid;
 
@@ -2106,16 +2153,16 @@ void __init setup_ioapic_ids_from_mpc(void)
 			mp_ioapics[apic_id].apicid);
 
 		reg_00.bits.ID = mp_ioapics[apic_id].apicid;
-		spin_lock_irqsave(&ioapic_lock, flags);
+		raw_spin_lock_irqsave(&ioapic_lock, flags);
 		io_apic_write(apic_id, 0, reg_00.raw);
-		spin_unlock_irqrestore(&ioapic_lock, flags);
+		raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 		/*
 		 * Sanity check
 		 */
-		spin_lock_irqsave(&ioapic_lock, flags);
+		raw_spin_lock_irqsave(&ioapic_lock, flags);
 		reg_00.raw = io_apic_read(apic_id, 0);
-		spin_unlock_irqrestore(&ioapic_lock, flags);
+		raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 		if (reg_00.bits.ID != mp_ioapics[apic_id].apicid)
 			printk("could not set ID!\n");
 		else
@@ -2198,15 +2245,15 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
 	unsigned long flags;
 	struct irq_cfg *cfg;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
-	if (irq < nr_legacy_irqs) {
-		disable_8259A_irq(irq);
-		if (i8259A_irq_pending(irq))
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	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);
 	__unmask_IO_APIC_irq(cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return was_pending;
 }
@@ -2217,9 +2264,9 @@ static int ioapic_retrigger_irq(unsigned int irq)
 	struct irq_cfg *cfg = irq_cfg(irq);
 	unsigned long flags;
 
-	spin_lock_irqsave(&vector_lock, flags);
+	raw_spin_lock_irqsave(&vector_lock, flags);
 	apic->send_IPI_mask(cpumask_of(cpumask_first(cfg->domain)), cfg->vector);
-	spin_unlock_irqrestore(&vector_lock, flags);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
 	return 1;
 }
@@ -2312,14 +2359,14 @@ set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 	irq = desc->irq;
 	cfg = desc->chip_data;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	ret = set_desc_affinity(desc, mask, &dest);
 	if (!ret) {
 		/* Only the high 8 bits are valid. */
 		dest = SET_APIC_LOGICAL_ID(dest);
 		__target_IO_APIC_irq(irq, dest, cfg);
 	}
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return ret;
 }
@@ -2554,9 +2601,9 @@ static void eoi_ioapic_irq(struct irq_desc *desc)
 	irq = desc->irq;
 	cfg = desc->chip_data;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	__eoi_ioapic_irq(irq, cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
 static void ack_apic_level(unsigned int irq)
@@ -2734,8 +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;
@@ -2892,7 +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());
 
 	/*
@@ -2905,7 +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;
@@ -2964,7 +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);
@@ -2987,14 +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;
 		}
@@ -3002,7 +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");
 	}
@@ -3021,22 +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();
@@ -3078,7 +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");
 	/*
@@ -3089,7 +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();
 }
 
@@ -3138,13 +3185,13 @@ static int ioapic_resume(struct sys_device *dev)
 	data = container_of(dev, struct sysfs_ioapic_data, dev);
 	entry = data->entry;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	reg_00.raw = io_apic_read(dev->id, 0);
 	if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
 		reg_00.bits.ID = mp_ioapics[dev->id].apicid;
 		io_apic_write(dev->id, 0, reg_00.raw);
 	}
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 	for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
 		ioapic_write_entry(dev->id, i, entry[i]);
 
@@ -3207,7 +3254,7 @@ unsigned int create_irq_nr(unsigned int irq_want, int node)
 	if (irq_want < nr_irqs_gsi)
 		irq_want = nr_irqs_gsi;
 
-	spin_lock_irqsave(&vector_lock, flags);
+	raw_spin_lock_irqsave(&vector_lock, flags);
 	for (new = irq_want; new < nr_irqs; new++) {
 		desc_new = irq_to_desc_alloc_node(new, node);
 		if (!desc_new) {
@@ -3226,14 +3273,11 @@ unsigned int create_irq_nr(unsigned int irq_want, int node)
 			irq = new;
 		break;
 	}
-	spin_unlock_irqrestore(&vector_lock, flags);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+	if (irq > 0)
+		dynamic_irq_init_keep_chip_data(irq);
 
-	if (irq > 0) {
-		dynamic_irq_init(irq);
-		/* restore it, in case dynamic_irq_init clear it */
-		if (desc_new)
-			desc_new->chip_data = cfg_new;
-	}
 	return irq;
 }
 
@@ -3255,20 +3299,13 @@ int create_irq(void)
 void destroy_irq(unsigned int irq)
 {
 	unsigned long flags;
-	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
-	/* store it, in case dynamic_irq_cleanup clear it */
-	desc = irq_to_desc(irq);
-	cfg = desc->chip_data;
-	dynamic_irq_cleanup(irq);
-	/* connect back irq_cfg */
-	desc->chip_data = cfg;
+	dynamic_irq_cleanup_keep_chip_data(irq);
 
 	free_irte(irq);
-	spin_lock_irqsave(&vector_lock, flags);
-	__clear_irq_vector(irq, cfg);
-	spin_unlock_irqrestore(&vector_lock, flags);
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	__clear_irq_vector(irq, get_irq_chip_data(irq));
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
 }
 
 /*
@@ -3805,9 +3842,9 @@ int __init io_apic_get_redir_entries (int ioapic)
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	reg_01.raw = io_apic_read(ioapic, 1);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return reg_01.bits.entries;
 }
@@ -3890,7 +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",
@@ -3969,9 +4006,9 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
 	if (physids_empty(apic_id_map))
 		apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map);
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	reg_00.raw = io_apic_read(ioapic, 0);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	if (apic_id >= get_physical_broadcast()) {
 		printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying "
@@ -4005,10 +4042,10 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
 	if (reg_00.bits.ID != apic_id) {
 		reg_00.bits.ID = apic_id;
 
-		spin_lock_irqsave(&ioapic_lock, flags);
+		raw_spin_lock_irqsave(&ioapic_lock, flags);
 		io_apic_write(ioapic, 0, reg_00.raw);
 		reg_00.raw = io_apic_read(ioapic, 0);
-		spin_unlock_irqrestore(&ioapic_lock, flags);
+		raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 		/* Sanity check */
 		if (reg_00.bits.ID != apic_id) {
@@ -4029,9 +4066,9 @@ int __init io_apic_get_version(int ioapic)
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ioapic_lock, flags);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	reg_01.raw = io_apic_read(ioapic, 1);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return reg_01.bits.version;
 }
@@ -4063,27 +4100,23 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 #ifdef CONFIG_SMP
 void __init setup_ioapic_dest(void)
 {
-	int pin, ioapic = 0, irq, irq_entry;
+	int pin, ioapic, irq, irq_entry;
 	struct irq_desc *desc;
 	const struct cpumask *mask;
 
 	if (skip_ioapic_setup == 1)
 		return;
 
-#ifdef CONFIG_ACPI
-	if (!acpi_disabled && acpi_ioapic) {
-		ioapic = mp_find_ioapic(0);
-		if (ioapic < 0)
-			ioapic = 0;
-	}
-#endif
-
+	for (ioapic = 0; ioapic < nr_ioapics; ioapic++)
 	for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
 		irq_entry = find_irq_entry(ioapic, pin, mp_INT);
 		if (irq_entry == -1)
 			continue;
 		irq = pin_2_irq(irq_entry, ioapic, pin);
 
+		if ((ioapic > 0) && (irq > 16))
+			continue;
+
 		desc = irq_to_desc(irq);
 
 		/*
@@ -4268,3 +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 0159a69396c..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);
 	}
 
@@ -416,13 +416,13 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 
 	/* We can be called before check_nmi_watchdog, hence NULL check. */
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
+		static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */
 
-		spin_lock(&lock);
+		raw_spin_lock(&lock);
 		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
 		show_regs(regs);
 		dump_stack();
-		spin_unlock(&lock);
+		raw_spin_unlock(&lock);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 
 		rc = 1;
@@ -438,8 +438,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		 * Ayiee, looks like this CPU is stuck ...
 		 * wait a few IRQs (5 seconds) before doing the oops ...
 		 */
-		__this_cpu_inc(per_cpu_var(alert_counter));
-		if (__this_cpu_read(per_cpu_var(alert_counter)) == 5 * nmi_hz)
+		__this_cpu_inc(alert_counter);
+		if (__this_cpu_read(alert_counter) == 5 * nmi_hz)
 			/*
 			 * die_nmi will return ONLY if NOTIFY_STOP happens..
 			 */
@@ -447,7 +447,7 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 				regs, panic_on_timeout);
 	} else {
 		__get_cpu_var(last_irq_sum) = sum;
-		__this_cpu_write(per_cpu_var(alert_counter), 0);
+		__this_cpu_write(alert_counter, 0);
 	}
 
 	/* see if the nmi watchdog went off */
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 98c4665f251..3e28401f161 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -225,7 +225,7 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc)
 
 	mpc_record = 0;
 	printk(KERN_INFO
-		"Found an OEM MPC table at %8p - parsing it ... \n", oemtable);
+		"Found an OEM MPC table at %8p - parsing it...\n", oemtable);
 
 	if (memcmp(oemtable->signature, MPC_OEM_SIGNATURE, 4)) {
 		printk(KERN_WARNING
@@ -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/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 1a6559f6768..99d2fe01608 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -52,7 +52,32 @@ static int __init print_ipi_mode(void)
 }
 late_initcall(print_ipi_mode);
 
-void default_setup_apic_routing(void)
+void __init default_setup_apic_routing(void)
+{
+	int version = apic_version[boot_cpu_physical_apicid];
+
+	if (num_possible_cpus() > 8) {
+		switch (boot_cpu_data.x86_vendor) {
+		case X86_VENDOR_INTEL:
+			if (!APIC_XAPIC(version)) {
+				def_to_bigsmp = 0;
+				break;
+			}
+			/* If P4 and above fall through */
+		case X86_VENDOR_AMD:
+			def_to_bigsmp = 1;
+		}
+	}
+
+#ifdef CONFIG_X86_BIGSMP
+	generic_bigsmp_probe();
+#endif
+
+	if (apic->setup_apic_routing)
+		apic->setup_apic_routing();
+}
+
+static void setup_apic_flat_routing(void)
 {
 #ifdef CONFIG_X86_IO_APIC
 	printk(KERN_INFO
@@ -103,7 +128,7 @@ struct apic apic_default = {
 	.init_apic_ldr			= default_init_apic_ldr,
 
 	.ioapic_phys_id_map		= default_ioapic_phys_id_map,
-	.setup_apic_routing		= default_setup_apic_routing,
+	.setup_apic_routing		= setup_apic_flat_routing,
 	.multi_timer_check		= NULL,
 	.apicid_to_node			= default_apicid_to_node,
 	.cpu_to_logical_apicid		= default_cpu_to_logical_apicid,
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 450fe2064a1..83e9be4778e 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -67,7 +67,7 @@ void __init default_setup_apic_routing(void)
 	}
 #endif
 
-	if (apic == &apic_flat && num_processors > 8)
+	if (apic == &apic_flat && num_possible_cpus() > 8)
 			apic = &apic_physflat;
 
 	printk(KERN_INFO "Setting APIC routing to %s\n", apic->name);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 21db3cbea7d..3740c8a4eae 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -5,7 +5,7 @@
  *
  * SGI UV APIC functions (note: not an Intel compatible APIC)
  *
- * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2009 Silicon Graphics, Inc. All rights reserved.
  */
 #include <linux/cpumask.h>
 #include <linux/hardirq.h>
@@ -20,6 +20,8 @@
 #include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/pci.h>
+#include <linux/kdebug.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -34,10 +36,13 @@
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
+#define PR_DEVEL(fmt, args...)	pr_devel("%s: " fmt, __func__, args)
+
 static enum uv_system_type uv_system_type;
 static u64 gru_start_paddr, gru_end_paddr;
 int uv_min_hub_revision_id;
 EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
+static DEFINE_SPINLOCK(uv_nmi_lock);
 
 static inline bool is_GRU_range(u64 start, u64 end)
 {
@@ -71,6 +76,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	if (!strcmp(oem_id, "SGI")) {
 		nodeid = early_get_nodeid();
 		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
+		x86_platform.nmi_init = uv_nmi_init;
 		if (!strcmp(oem_table_id, "UVL"))
 			uv_system_type = UV_LEGACY_APIC;
 		else if (!strcmp(oem_table_id, "UVX"))
@@ -482,7 +488,7 @@ static void uv_heartbeat(unsigned long ignored)
 
 static void __cpuinit uv_heartbeat_enable(int cpu)
 {
-	if (!uv_cpu_hub_info(cpu)->scir.enabled) {
+	while (!uv_cpu_hub_info(cpu)->scir.enabled) {
 		struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer;
 
 		uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY);
@@ -490,11 +496,10 @@ static void __cpuinit uv_heartbeat_enable(int cpu)
 		timer->expires = jiffies + SCIR_CPU_HB_INTERVAL;
 		add_timer_on(timer, cpu);
 		uv_cpu_hub_info(cpu)->scir.enabled = 1;
-	}
 
-	/* check boot cpu */
-	if (!uv_cpu_hub_info(0)->scir.enabled)
-		uv_heartbeat_enable(0);
+		/* also ensure that boot cpu is enabled */
+		cpu = 0;
+	}
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -553,6 +558,30 @@ late_initcall(uv_init_heartbeat);
 
 #endif /* !CONFIG_HOTPLUG_CPU */
 
+/* Direct Legacy VGA I/O traffic to designated IOH */
+int uv_set_vga_state(struct pci_dev *pdev, bool decode,
+		      unsigned int command_bits, bool change_bridge)
+{
+	int domain, bus, rc;
+
+	PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n",
+			pdev->devfn, decode, command_bits, change_bridge);
+
+	if (!change_bridge)
+		return 0;
+
+	if ((command_bits & PCI_COMMAND_IO) == 0)
+		return 0;
+
+	domain = pci_domain_nr(pdev->bus);
+	bus = pdev->bus->number;
+
+	rc = uv_bios_set_legacy_vga_target(decode, domain, bus);
+	PR_DEVEL("vga decode %d %x:%x, rc: %d\n", decode, domain, bus, rc);
+
+	return rc;
+}
+
 /*
  * Called on each cpu to initialize the per_cpu UV data area.
  * FIXME: hotplug not supported yet
@@ -569,6 +598,46 @@ void __cpuinit uv_cpu_init(void)
 		set_x2apic_extra_bits(uv_hub_info->pnode);
 }
 
+/*
+ * When NMI is received, print a stack trace.
+ */
+int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
+{
+	if (reason != DIE_NMI_IPI)
+		return NOTIFY_OK;
+	/*
+	 * Use a lock so only one cpu prints at a time
+	 * to prevent intermixed output.
+	 */
+	spin_lock(&uv_nmi_lock);
+	pr_info("NMI stack dump cpu %u:\n", smp_processor_id());
+	dump_stack();
+	spin_unlock(&uv_nmi_lock);
+
+	return NOTIFY_STOP;
+}
+
+static struct notifier_block uv_dump_stack_nmi_nb = {
+	.notifier_call	= uv_handle_nmi
+};
+
+void uv_register_nmi_notifier(void)
+{
+	if (register_die_notifier(&uv_dump_stack_nmi_nb))
+		printk(KERN_WARNING "UV NMI handler failed to register\n");
+}
+
+void uv_nmi_init(void)
+{
+	unsigned int value;
+
+	/*
+	 * Unmask NMI on all cpus
+	 */
+	value = apic_read(APIC_LVT1) | APIC_DM_NMI;
+	value &= ~APIC_LVT_MASKED;
+	apic_write(APIC_LVT1, value);
+}
 
 void __init uv_system_init(void)
 {
@@ -634,8 +703,8 @@ void __init uv_system_init(void)
 	}
 
 	uv_bios_init();
-	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
-			    &sn_coherency_id, &sn_region_size);
+	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id,
+			    &sn_region_size, &system_serial_number);
 	uv_rtc_init();
 
 	for_each_present_cpu(cpu) {
@@ -690,5 +759,9 @@ void __init uv_system_init(void)
 
 	uv_cpu_init();
 	uv_scir_register_cpu_notifier();
+	uv_register_nmi_notifier();
 	proc_mkdir("sgi_uv", NULL);
+
+	/* register Legacy VGA I/O redirection handler */
+	pci_register_set_vga_state(uv_set_vga_state);
 }
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index b5b6b23bce5..031aa887b0e 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1992,8 +1992,8 @@ static int __init apm_is_horked_d850md(const struct dmi_system_id *d)
 		apm_info.disabled = 1;
 		printk(KERN_INFO "%s machine detected. "
 		       "Disabling APM.\n", d->ident);
-		printk(KERN_INFO "This bug is fixed in bios P15 which is available for \n");
-		printk(KERN_INFO "download from support.intel.com \n");
+		printk(KERN_INFO "This bug is fixed in bios P15 which is available for\n");
+		printk(KERN_INFO "download from support.intel.com\n");
 	}
 	return 0;
 }
diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index b0206a211b0..8bc57baaa9a 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -15,8 +15,8 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  *
- *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
- *  Copyright (c) Russ Anderson
+ *  Copyright (c) 2008-2009 Silicon Graphics, Inc.  All Rights Reserved.
+ *  Copyright (c) Russ Anderson <rja@sgi.com>
  */
 
 #include <linux/efi.h>
@@ -30,6 +30,7 @@ static struct uv_systab uv_systab;
 s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 {
 	struct uv_systab *tab = &uv_systab;
+	s64 ret;
 
 	if (!tab->function)
 		/*
@@ -37,9 +38,11 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 		 */
 		return BIOS_STATUS_UNIMPLEMENTED;
 
-	return efi_call6((void *)__va(tab->function),
-					(u64)which, a1, a2, a3, a4, a5);
+	ret = efi_call6((void *)__va(tab->function), (u64)which,
+			a1, a2, a3, a4, a5);
+	return ret;
 }
+EXPORT_SYMBOL_GPL(uv_bios_call);
 
 s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 					u64 a4, u64 a5)
@@ -73,11 +76,14 @@ long sn_coherency_id;
 EXPORT_SYMBOL_GPL(sn_coherency_id);
 long sn_region_size;
 EXPORT_SYMBOL_GPL(sn_region_size);
+long system_serial_number;
+EXPORT_SYMBOL_GPL(system_serial_number);
 int uv_type;
+EXPORT_SYMBOL_GPL(uv_type);
 
 
 s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
-		long *region)
+		long *region, long *ssn)
 {
 	s64 ret;
 	u64 v0, v1;
@@ -97,8 +103,11 @@ s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
 		*coher = part.coherence_id;
 	if (region)
 		*region = part.region_size;
+	if (ssn)
+		*ssn = v1;
 	return ret;
 }
+EXPORT_SYMBOL_GPL(uv_bios_get_sn_info);
 
 int
 uv_bios_mq_watchlist_alloc(unsigned long addr, unsigned int mq_size,
@@ -154,6 +163,25 @@ s64 uv_bios_freq_base(u64 clock_type, u64 *ticks_per_second)
 }
 EXPORT_SYMBOL_GPL(uv_bios_freq_base);
 
+/*
+ * uv_bios_set_legacy_vga_target - Set Legacy VGA I/O Target
+ * @decode: true to enable target, false to disable target
+ * @domain: PCI domain number
+ * @bus: PCI bus number
+ *
+ * Returns:
+ *    0: Success
+ *    -EINVAL: Invalid domain or bus number
+ *    -ENOSYS: Capability not available
+ *    -EBUSY: Legacy VGA I/O cannot be retargeted at this time
+ */
+int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus)
+{
+	return uv_bios_call(UV_BIOS_SET_LEGACY_VGA_TARGET,
+				(u64)decode, (u64)domain, (u64)bus, 0, 0);
+}
+EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target);
+
 
 #ifdef CONFIG_EFI
 void uv_bios_init(void)
@@ -185,4 +213,3 @@ void uv_bios_init(void)
 
 void uv_bios_init(void) { }
 #endif
-
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 1d2cb383410..c202b62f367 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -19,8 +19,6 @@ obj-y			+= vmware.o hypervisor.o sched.o
 obj-$(CONFIG_X86_32)	+= bugs.o cmpxchg.o
 obj-$(CONFIG_X86_64)	+= bugs_64.o
 
-obj-$(CONFIG_X86_CPU_DEBUG)		+= cpu_debug.o
-
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel.o
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
 obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 468489b57aa..97ad79cdf68 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -32,6 +32,10 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
 		{ X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
 		{ X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 },
+		{ X86_FEATURE_NPT,   CR_EDX, 0, 0x8000000a },
+		{ X86_FEATURE_LBRV,  CR_EDX, 1, 0x8000000a },
+		{ X86_FEATURE_SVML,  CR_EDX, 2, 0x8000000a },
+		{ X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a },
 		{ 0, 0, 0, 0 }
 	};
 
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
deleted file mode 100644
index b368cd86299..00000000000
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ /dev/null
@@ -1,688 +0,0 @@
-/*
- * CPU x86 architecture debug code
- *
- * Copyright(C) 2009 Jaswinder Singh Rajput
- *
- * For licencing details see kernel-base/COPYING
- */
-
-#include <linux/interrupt.h>
-#include <linux/compiler.h>
-#include <linux/seq_file.h>
-#include <linux/debugfs.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/signal.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-
-#include <asm/cpu_debug.h>
-#include <asm/paravirt.h>
-#include <asm/system.h>
-#include <asm/traps.h>
-#include <asm/apic.h>
-#include <asm/desc.h>
-
-static DEFINE_PER_CPU(struct cpu_cpuX_base [CPU_REG_ALL_BIT], cpud_arr);
-static DEFINE_PER_CPU(struct cpu_private * [MAX_CPU_FILES], cpud_priv_arr);
-static DEFINE_PER_CPU(int, cpud_priv_count);
-
-static DEFINE_MUTEX(cpu_debug_lock);
-
-static struct dentry *cpu_debugfs_dir;
-
-static struct cpu_debug_base cpu_base[] = {
-	{ "mc",		CPU_MC,		0	},
-	{ "monitor",	CPU_MONITOR,	0	},
-	{ "time",	CPU_TIME,	0	},
-	{ "pmc",	CPU_PMC,	1	},
-	{ "platform",	CPU_PLATFORM,	0	},
-	{ "apic",	CPU_APIC,	0	},
-	{ "poweron",	CPU_POWERON,	0	},
-	{ "control",	CPU_CONTROL,	0	},
-	{ "features",	CPU_FEATURES,	0	},
-	{ "lastbranch",	CPU_LBRANCH,	0	},
-	{ "bios",	CPU_BIOS,	0	},
-	{ "freq",	CPU_FREQ,	0	},
-	{ "mtrr",	CPU_MTRR,	0	},
-	{ "perf",	CPU_PERF,	0	},
-	{ "cache",	CPU_CACHE,	0	},
-	{ "sysenter",	CPU_SYSENTER,	0	},
-	{ "therm",	CPU_THERM,	0	},
-	{ "misc",	CPU_MISC,	0	},
-	{ "debug",	CPU_DEBUG,	0	},
-	{ "pat",	CPU_PAT,	0	},
-	{ "vmx",	CPU_VMX,	0	},
-	{ "call",	CPU_CALL,	0	},
-	{ "base",	CPU_BASE,	0	},
-	{ "ver",	CPU_VER,	0	},
-	{ "conf",	CPU_CONF,	0	},
-	{ "smm",	CPU_SMM,	0	},
-	{ "svm",	CPU_SVM,	0	},
-	{ "osvm",	CPU_OSVM,	0	},
-	{ "tss",	CPU_TSS,	0	},
-	{ "cr",		CPU_CR,		0	},
-	{ "dt",		CPU_DT,		0	},
-	{ "registers",	CPU_REG_ALL,	0	},
-};
-
-static struct cpu_file_base cpu_file[] = {
-	{ "index",	CPU_REG_ALL,	0	},
-	{ "value",	CPU_REG_ALL,	1	},
-};
-
-/* CPU Registers Range */
-static struct cpu_debug_range cpu_reg_range[] = {
-	{ 0x00000000, 0x00000001, CPU_MC,	},
-	{ 0x00000006, 0x00000007, CPU_MONITOR,	},
-	{ 0x00000010, 0x00000010, CPU_TIME,	},
-	{ 0x00000011, 0x00000013, CPU_PMC,	},
-	{ 0x00000017, 0x00000017, CPU_PLATFORM,	},
-	{ 0x0000001B, 0x0000001B, CPU_APIC,	},
-	{ 0x0000002A, 0x0000002B, CPU_POWERON,	},
-	{ 0x0000002C, 0x0000002C, CPU_FREQ,	},
-	{ 0x0000003A, 0x0000003A, CPU_CONTROL,	},
-	{ 0x00000040, 0x00000047, CPU_LBRANCH,	},
-	{ 0x00000060, 0x00000067, CPU_LBRANCH,	},
-	{ 0x00000079, 0x00000079, CPU_BIOS,	},
-	{ 0x00000088, 0x0000008A, CPU_CACHE,	},
-	{ 0x0000008B, 0x0000008B, CPU_BIOS,	},
-	{ 0x0000009B, 0x0000009B, CPU_MONITOR,	},
-	{ 0x000000C1, 0x000000C4, CPU_PMC,	},
-	{ 0x000000CD, 0x000000CD, CPU_FREQ,	},
-	{ 0x000000E7, 0x000000E8, CPU_PERF,	},
-	{ 0x000000FE, 0x000000FE, CPU_MTRR,	},
-
-	{ 0x00000116, 0x0000011E, CPU_CACHE,	},
-	{ 0x00000174, 0x00000176, CPU_SYSENTER,	},
-	{ 0x00000179, 0x0000017B, CPU_MC,	},
-	{ 0x00000186, 0x00000189, CPU_PMC,	},
-	{ 0x00000198, 0x00000199, CPU_PERF,	},
-	{ 0x0000019A, 0x0000019A, CPU_TIME,	},
-	{ 0x0000019B, 0x0000019D, CPU_THERM,	},
-	{ 0x000001A0, 0x000001A0, CPU_MISC,	},
-	{ 0x000001C9, 0x000001C9, CPU_LBRANCH,	},
-	{ 0x000001D7, 0x000001D8, CPU_LBRANCH,	},
-	{ 0x000001D9, 0x000001D9, CPU_DEBUG,	},
-	{ 0x000001DA, 0x000001E0, CPU_LBRANCH,	},
-
-	{ 0x00000200, 0x0000020F, CPU_MTRR,	},
-	{ 0x00000250, 0x00000250, CPU_MTRR,	},
-	{ 0x00000258, 0x00000259, CPU_MTRR,	},
-	{ 0x00000268, 0x0000026F, CPU_MTRR,	},
-	{ 0x00000277, 0x00000277, CPU_PAT,	},
-	{ 0x000002FF, 0x000002FF, CPU_MTRR,	},
-
-	{ 0x00000300, 0x00000311, CPU_PMC,	},
-	{ 0x00000345, 0x00000345, CPU_PMC,	},
-	{ 0x00000360, 0x00000371, CPU_PMC,	},
-	{ 0x0000038D, 0x00000390, CPU_PMC,	},
-	{ 0x000003A0, 0x000003BE, CPU_PMC,	},
-	{ 0x000003C0, 0x000003CD, CPU_PMC,	},
-	{ 0x000003E0, 0x000003E1, CPU_PMC,	},
-	{ 0x000003F0, 0x000003F2, CPU_PMC,	},
-
-	{ 0x00000400, 0x00000417, CPU_MC,	},
-	{ 0x00000480, 0x0000048B, CPU_VMX,	},
-
-	{ 0x00000600, 0x00000600, CPU_DEBUG,	},
-	{ 0x00000680, 0x0000068F, CPU_LBRANCH,	},
-	{ 0x000006C0, 0x000006CF, CPU_LBRANCH,	},
-
-	{ 0x000107CC, 0x000107D3, CPU_PMC,	},
-
-	{ 0xC0000080, 0xC0000080, CPU_FEATURES,	},
-	{ 0xC0000081, 0xC0000084, CPU_CALL,	},
-	{ 0xC0000100, 0xC0000102, CPU_BASE,	},
-	{ 0xC0000103, 0xC0000103, CPU_TIME,	},
-
-	{ 0xC0010000, 0xC0010007, CPU_PMC,	},
-	{ 0xC0010010, 0xC0010010, CPU_CONF,	},
-	{ 0xC0010015, 0xC0010015, CPU_CONF,	},
-	{ 0xC0010016, 0xC001001A, CPU_MTRR,	},
-	{ 0xC001001D, 0xC001001D, CPU_MTRR,	},
-	{ 0xC001001F, 0xC001001F, CPU_CONF,	},
-	{ 0xC0010030, 0xC0010035, CPU_BIOS,	},
-	{ 0xC0010044, 0xC0010048, CPU_MC,	},
-	{ 0xC0010050, 0xC0010056, CPU_SMM,	},
-	{ 0xC0010058, 0xC0010058, CPU_CONF,	},
-	{ 0xC0010060, 0xC0010060, CPU_CACHE,	},
-	{ 0xC0010061, 0xC0010068, CPU_SMM,	},
-	{ 0xC0010069, 0xC001006B, CPU_SMM,	},
-	{ 0xC0010070, 0xC0010071, CPU_SMM,	},
-	{ 0xC0010111, 0xC0010113, CPU_SMM,	},
-	{ 0xC0010114, 0xC0010118, CPU_SVM,	},
-	{ 0xC0010140, 0xC0010141, CPU_OSVM,	},
-	{ 0xC0011022, 0xC0011023, CPU_CONF,	},
-};
-
-static int is_typeflag_valid(unsigned cpu, unsigned flag)
-{
-	int i;
-
-	/* Standard Registers should be always valid */
-	if (flag >= CPU_TSS)
-		return 1;
-
-	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
-		if (cpu_reg_range[i].flag == flag)
-			return 1;
-	}
-
-	/* Invalid */
-	return 0;
-}
-
-static unsigned get_cpu_range(unsigned cpu, unsigned *min, unsigned *max,
-			      int index, unsigned flag)
-{
-	if (cpu_reg_range[index].flag == flag) {
-		*min = cpu_reg_range[index].min;
-		*max = cpu_reg_range[index].max;
-	} else
-		*max = 0;
-
-	return *max;
-}
-
-/* This function can also be called with seq = NULL for printk */
-static void print_cpu_data(struct seq_file *seq, unsigned type,
-			   u32 low, u32 high)
-{
-	struct cpu_private *priv;
-	u64 val = high;
-
-	if (seq) {
-		priv = seq->private;
-		if (priv->file) {
-			val = (val << 32) | low;
-			seq_printf(seq, "0x%llx\n", val);
-		} else
-			seq_printf(seq, " %08x: %08x_%08x\n",
-				   type, high, low);
-	} else
-		printk(KERN_INFO " %08x: %08x_%08x\n", type, high, low);
-}
-
-/* This function can also be called with seq = NULL for printk */
-static void print_msr(struct seq_file *seq, unsigned cpu, unsigned flag)
-{
-	unsigned msr, msr_min, msr_max;
-	struct cpu_private *priv;
-	u32 low, high;
-	int i;
-
-	if (seq) {
-		priv = seq->private;
-		if (priv->file) {
-			if (!rdmsr_safe_on_cpu(priv->cpu, priv->reg,
-					       &low, &high))
-				print_cpu_data(seq, priv->reg, low, high);
-			return;
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
-		if (!get_cpu_range(cpu, &msr_min, &msr_max, i, flag))
-			continue;
-
-		for (msr = msr_min; msr <= msr_max; msr++) {
-			if (rdmsr_safe_on_cpu(cpu, msr, &low, &high))
-				continue;
-			print_cpu_data(seq, msr, low, high);
-		}
-	}
-}
-
-static void print_tss(void *arg)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	struct seq_file *seq = arg;
-	unsigned int seg;
-
-	seq_printf(seq, " RAX\t: %016lx\n", regs->ax);
-	seq_printf(seq, " RBX\t: %016lx\n", regs->bx);
-	seq_printf(seq, " RCX\t: %016lx\n", regs->cx);
-	seq_printf(seq, " RDX\t: %016lx\n", regs->dx);
-
-	seq_printf(seq, " RSI\t: %016lx\n", regs->si);
-	seq_printf(seq, " RDI\t: %016lx\n", regs->di);
-	seq_printf(seq, " RBP\t: %016lx\n", regs->bp);
-	seq_printf(seq, " ESP\t: %016lx\n", regs->sp);
-
-#ifdef CONFIG_X86_64
-	seq_printf(seq, " R08\t: %016lx\n", regs->r8);
-	seq_printf(seq, " R09\t: %016lx\n", regs->r9);
-	seq_printf(seq, " R10\t: %016lx\n", regs->r10);
-	seq_printf(seq, " R11\t: %016lx\n", regs->r11);
-	seq_printf(seq, " R12\t: %016lx\n", regs->r12);
-	seq_printf(seq, " R13\t: %016lx\n", regs->r13);
-	seq_printf(seq, " R14\t: %016lx\n", regs->r14);
-	seq_printf(seq, " R15\t: %016lx\n", regs->r15);
-#endif
-
-	asm("movl %%cs,%0" : "=r" (seg));
-	seq_printf(seq, " CS\t:             %04x\n", seg);
-	asm("movl %%ds,%0" : "=r" (seg));
-	seq_printf(seq, " DS\t:             %04x\n", seg);
-	seq_printf(seq, " SS\t:             %04lx\n", regs->ss & 0xffff);
-	asm("movl %%es,%0" : "=r" (seg));
-	seq_printf(seq, " ES\t:             %04x\n", seg);
-	asm("movl %%fs,%0" : "=r" (seg));
-	seq_printf(seq, " FS\t:             %04x\n", seg);
-	asm("movl %%gs,%0" : "=r" (seg));
-	seq_printf(seq, " GS\t:             %04x\n", seg);
-
-	seq_printf(seq, " EFLAGS\t: %016lx\n", regs->flags);
-
-	seq_printf(seq, " EIP\t: %016lx\n", regs->ip);
-}
-
-static void print_cr(void *arg)
-{
-	struct seq_file *seq = arg;
-
-	seq_printf(seq, " cr0\t: %016lx\n", read_cr0());
-	seq_printf(seq, " cr2\t: %016lx\n", read_cr2());
-	seq_printf(seq, " cr3\t: %016lx\n", read_cr3());
-	seq_printf(seq, " cr4\t: %016lx\n", read_cr4_safe());
-#ifdef CONFIG_X86_64
-	seq_printf(seq, " cr8\t: %016lx\n", read_cr8());
-#endif
-}
-
-static void print_desc_ptr(char *str, struct seq_file *seq, struct desc_ptr dt)
-{
-	seq_printf(seq, " %s\t: %016llx\n", str, (u64)(dt.address | dt.size));
-}
-
-static void print_dt(void *seq)
-{
-	struct desc_ptr dt;
-	unsigned long ldt;
-
-	/* IDT */
-	store_idt((struct desc_ptr *)&dt);
-	print_desc_ptr("IDT", seq, dt);
-
-	/* GDT */
-	store_gdt((struct desc_ptr *)&dt);
-	print_desc_ptr("GDT", seq, dt);
-
-	/* LDT */
-	store_ldt(ldt);
-	seq_printf(seq, " LDT\t: %016lx\n", ldt);
-
-	/* TR */
-	store_tr(ldt);
-	seq_printf(seq, " TR\t: %016lx\n", ldt);
-}
-
-static void print_dr(void *arg)
-{
-	struct seq_file *seq = arg;
-	unsigned long dr;
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		/* Ignore db4, db5 */
-		if ((i == 4) || (i == 5))
-			continue;
-		get_debugreg(dr, i);
-		seq_printf(seq, " dr%d\t: %016lx\n", i, dr);
-	}
-
-	seq_printf(seq, "\n MSR\t:\n");
-}
-
-static void print_apic(void *arg)
-{
-	struct seq_file *seq = arg;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	seq_printf(seq, " LAPIC\t:\n");
-	seq_printf(seq, " ID\t\t: %08x\n",  apic_read(APIC_ID) >> 24);
-	seq_printf(seq, " LVR\t\t: %08x\n",  apic_read(APIC_LVR));
-	seq_printf(seq, " TASKPRI\t: %08x\n",  apic_read(APIC_TASKPRI));
-	seq_printf(seq, " ARBPRI\t\t: %08x\n",  apic_read(APIC_ARBPRI));
-	seq_printf(seq, " PROCPRI\t: %08x\n",  apic_read(APIC_PROCPRI));
-	seq_printf(seq, " LDR\t\t: %08x\n",  apic_read(APIC_LDR));
-	seq_printf(seq, " DFR\t\t: %08x\n",  apic_read(APIC_DFR));
-	seq_printf(seq, " SPIV\t\t: %08x\n",  apic_read(APIC_SPIV));
-	seq_printf(seq, " ISR\t\t: %08x\n",  apic_read(APIC_ISR));
-	seq_printf(seq, " ESR\t\t: %08x\n",  apic_read(APIC_ESR));
-	seq_printf(seq, " ICR\t\t: %08x\n",  apic_read(APIC_ICR));
-	seq_printf(seq, " ICR2\t\t: %08x\n",  apic_read(APIC_ICR2));
-	seq_printf(seq, " LVTT\t\t: %08x\n",  apic_read(APIC_LVTT));
-	seq_printf(seq, " LVTTHMR\t: %08x\n",  apic_read(APIC_LVTTHMR));
-	seq_printf(seq, " LVTPC\t\t: %08x\n",  apic_read(APIC_LVTPC));
-	seq_printf(seq, " LVT0\t\t: %08x\n",  apic_read(APIC_LVT0));
-	seq_printf(seq, " LVT1\t\t: %08x\n",  apic_read(APIC_LVT1));
-	seq_printf(seq, " LVTERR\t\t: %08x\n",  apic_read(APIC_LVTERR));
-	seq_printf(seq, " TMICT\t\t: %08x\n",  apic_read(APIC_TMICT));
-	seq_printf(seq, " TMCCT\t\t: %08x\n",  apic_read(APIC_TMCCT));
-	seq_printf(seq, " TDCR\t\t: %08x\n",  apic_read(APIC_TDCR));
-	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
-		unsigned int i, v, maxeilvt;
-
-		v = apic_read(APIC_EFEAT);
-		maxeilvt = (v >> 16) & 0xff;
-		seq_printf(seq, " EFEAT\t\t: %08x\n", v);
-		seq_printf(seq, " ECTRL\t\t: %08x\n", apic_read(APIC_ECTRL));
-
-		for (i = 0; i < maxeilvt; i++) {
-			v = apic_read(APIC_EILVTn(i));
-			seq_printf(seq, " EILVT%d\t\t: %08x\n", i, v);
-		}
-	}
-#endif /* CONFIG_X86_LOCAL_APIC */
-	seq_printf(seq, "\n MSR\t:\n");
-}
-
-static int cpu_seq_show(struct seq_file *seq, void *v)
-{
-	struct cpu_private *priv = seq->private;
-
-	if (priv == NULL)
-		return -EINVAL;
-
-	switch (cpu_base[priv->type].flag) {
-	case CPU_TSS:
-		smp_call_function_single(priv->cpu, print_tss, seq, 1);
-		break;
-	case CPU_CR:
-		smp_call_function_single(priv->cpu, print_cr, seq, 1);
-		break;
-	case CPU_DT:
-		smp_call_function_single(priv->cpu, print_dt, seq, 1);
-		break;
-	case CPU_DEBUG:
-		if (priv->file == CPU_INDEX_BIT)
-			smp_call_function_single(priv->cpu, print_dr, seq, 1);
-		print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
-		break;
-	case CPU_APIC:
-		if (priv->file == CPU_INDEX_BIT)
-			smp_call_function_single(priv->cpu, print_apic, seq, 1);
-		print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
-		break;
-
-	default:
-		print_msr(seq, priv->cpu, cpu_base[priv->type].flag);
-		break;
-	}
-	seq_printf(seq, "\n");
-
-	return 0;
-}
-
-static void *cpu_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	if (*pos == 0) /* One time is enough ;-) */
-		return seq;
-
-	return NULL;
-}
-
-static void *cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	(*pos)++;
-
-	return cpu_seq_start(seq, pos);
-}
-
-static void cpu_seq_stop(struct seq_file *seq, void *v)
-{
-}
-
-static const struct seq_operations cpu_seq_ops = {
-	.start		= cpu_seq_start,
-	.next		= cpu_seq_next,
-	.stop		= cpu_seq_stop,
-	.show		= cpu_seq_show,
-};
-
-static int cpu_seq_open(struct inode *inode, struct file *file)
-{
-	struct cpu_private *priv = inode->i_private;
-	struct seq_file *seq;
-	int err;
-
-	err = seq_open(file, &cpu_seq_ops);
-	if (!err) {
-		seq = file->private_data;
-		seq->private = priv;
-	}
-
-	return err;
-}
-
-static int write_msr(struct cpu_private *priv, u64 val)
-{
-	u32 low, high;
-
-	high = (val >> 32) & 0xffffffff;
-	low = val & 0xffffffff;
-
-	if (!wrmsr_safe_on_cpu(priv->cpu, priv->reg, low, high))
-		return 0;
-
-	return -EPERM;
-}
-
-static int write_cpu_register(struct cpu_private *priv, const char *buf)
-{
-	int ret = -EPERM;
-	u64 val;
-
-	ret = strict_strtoull(buf, 0, &val);
-	if (ret < 0)
-		return ret;
-
-	/* Supporting only MSRs */
-	if (priv->type < CPU_TSS_BIT)
-		return write_msr(priv, val);
-
-	return ret;
-}
-
-static ssize_t cpu_write(struct file *file, const char __user *ubuf,
-			     size_t count, loff_t *off)
-{
-	struct seq_file *seq = file->private_data;
-	struct cpu_private *priv = seq->private;
-	char buf[19];
-
-	if ((priv == NULL) || (count >= sizeof(buf)))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, count))
-		return -EFAULT;
-
-	buf[count] = 0;
-
-	if ((cpu_base[priv->type].write) && (cpu_file[priv->file].write))
-		if (!write_cpu_register(priv, buf))
-			return count;
-
-	return -EACCES;
-}
-
-static const struct file_operations cpu_fops = {
-	.owner		= THIS_MODULE,
-	.open		= cpu_seq_open,
-	.read		= seq_read,
-	.write		= cpu_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
-static int cpu_create_file(unsigned cpu, unsigned type, unsigned reg,
-			   unsigned file, struct dentry *dentry)
-{
-	struct cpu_private *priv = NULL;
-
-	/* Already intialized */
-	if (file == CPU_INDEX_BIT)
-		if (per_cpu(cpud_arr[type].init, cpu))
-			return 0;
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv == NULL)
-		return -ENOMEM;
-
-	priv->cpu = cpu;
-	priv->type = type;
-	priv->reg = reg;
-	priv->file = file;
-	mutex_lock(&cpu_debug_lock);
-	per_cpu(cpud_priv_arr[type], cpu) = priv;
-	per_cpu(cpud_priv_count, cpu)++;
-	mutex_unlock(&cpu_debug_lock);
-
-	if (file)
-		debugfs_create_file(cpu_file[file].name, S_IRUGO,
-				    dentry, (void *)priv, &cpu_fops);
-	else {
-		debugfs_create_file(cpu_base[type].name, S_IRUGO,
-				    per_cpu(cpud_arr[type].dentry, cpu),
-				    (void *)priv, &cpu_fops);
-		mutex_lock(&cpu_debug_lock);
-		per_cpu(cpud_arr[type].init, cpu) = 1;
-		mutex_unlock(&cpu_debug_lock);
-	}
-
-	return 0;
-}
-
-static int cpu_init_regfiles(unsigned cpu, unsigned int type, unsigned reg,
-			     struct dentry *dentry)
-{
-	unsigned file;
-	int err = 0;
-
-	for (file = 0; file <  ARRAY_SIZE(cpu_file); file++) {
-		err = cpu_create_file(cpu, type, reg, file, dentry);
-		if (err)
-			return err;
-	}
-
-	return err;
-}
-
-static int cpu_init_msr(unsigned cpu, unsigned type, struct dentry *dentry)
-{
-	struct dentry *cpu_dentry = NULL;
-	unsigned reg, reg_min, reg_max;
-	int i, err = 0;
-	char reg_dir[12];
-	u32 low, high;
-
-	for (i = 0; i < ARRAY_SIZE(cpu_reg_range); i++) {
-		if (!get_cpu_range(cpu, &reg_min, &reg_max, i,
-				   cpu_base[type].flag))
-			continue;
-
-		for (reg = reg_min; reg <= reg_max; reg++) {
-			if (rdmsr_safe_on_cpu(cpu, reg, &low, &high))
-				continue;
-
-			sprintf(reg_dir, "0x%x", reg);
-			cpu_dentry = debugfs_create_dir(reg_dir, dentry);
-			err = cpu_init_regfiles(cpu, type, reg, cpu_dentry);
-			if (err)
-				return err;
-		}
-	}
-
-	return err;
-}
-
-static int cpu_init_allreg(unsigned cpu, struct dentry *dentry)
-{
-	struct dentry *cpu_dentry = NULL;
-	unsigned type;
-	int err = 0;
-
-	for (type = 0; type <  ARRAY_SIZE(cpu_base) - 1; type++) {
-		if (!is_typeflag_valid(cpu, cpu_base[type].flag))
-			continue;
-		cpu_dentry = debugfs_create_dir(cpu_base[type].name, dentry);
-		per_cpu(cpud_arr[type].dentry, cpu) = cpu_dentry;
-
-		if (type < CPU_TSS_BIT)
-			err = cpu_init_msr(cpu, type, cpu_dentry);
-		else
-			err = cpu_create_file(cpu, type, 0, CPU_INDEX_BIT,
-					      cpu_dentry);
-		if (err)
-			return err;
-	}
-
-	return err;
-}
-
-static int cpu_init_cpu(void)
-{
-	struct dentry *cpu_dentry = NULL;
-	struct cpuinfo_x86 *cpui;
-	char cpu_dir[12];
-	unsigned cpu;
-	int err = 0;
-
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		cpui = &cpu_data(cpu);
-		if (!cpu_has(cpui, X86_FEATURE_MSR))
-			continue;
-
-		sprintf(cpu_dir, "cpu%d", cpu);
-		cpu_dentry = debugfs_create_dir(cpu_dir, cpu_debugfs_dir);
-		err = cpu_init_allreg(cpu, cpu_dentry);
-
-		pr_info("cpu%d(%d) debug files %d\n",
-			cpu, nr_cpu_ids, per_cpu(cpud_priv_count, cpu));
-		if (per_cpu(cpud_priv_count, cpu) > MAX_CPU_FILES) {
-			pr_err("Register files count %d exceeds limit %d\n",
-				per_cpu(cpud_priv_count, cpu), MAX_CPU_FILES);
-			per_cpu(cpud_priv_count, cpu) = MAX_CPU_FILES;
-			err = -ENFILE;
-		}
-		if (err)
-			return err;
-	}
-
-	return err;
-}
-
-static int __init cpu_debug_init(void)
-{
-	cpu_debugfs_dir = debugfs_create_dir("cpu", arch_debugfs_dir);
-
-	return cpu_init_cpu();
-}
-
-static void __exit cpu_debug_exit(void)
-{
-	int i, cpu;
-
-	if (cpu_debugfs_dir)
-		debugfs_remove_recursive(cpu_debugfs_dir);
-
-	for (cpu = 0; cpu <  nr_cpu_ids; cpu++)
-		for (i = 0; i < per_cpu(cpud_priv_count, cpu); i++)
-			kfree(per_cpu(cpud_priv_arr[i], cpu));
-}
-
-module_init(cpu_debug_init);
-module_exit(cpu_debug_exit);
-
-MODULE_AUTHOR("Jaswinder Singh Rajput");
-MODULE_DESCRIPTION("CPU Debug module");
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index f138c6c389b..870e6cc6ad2 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -10,6 +10,20 @@ if CPU_FREQ
 
 comment "CPUFreq processor drivers"
 
+config X86_PCC_CPUFREQ
+	tristate "Processor Clocking Control interface driver"
+	depends on ACPI && ACPI_PROCESSOR
+	help
+	  This driver adds support for the PCC interface.
+
+	  For details, take a look at:
+	  <file:Documentation/cpu-freq/pcc-cpufreq.txt>.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pcc-cpufreq.
+
+	  If in doubt, say N.
+
 config X86_ACPI_CPUFREQ
 	tristate "ACPI Processor P-States driver"
 	select CPU_FREQ_TABLE
diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile
index 509296df294..1840c0a5170 100644
--- a/arch/x86/kernel/cpu/cpufreq/Makefile
+++ b/arch/x86/kernel/cpu/cpufreq/Makefile
@@ -4,6 +4,7 @@
 
 obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o
+obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
 obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
 obj-$(CONFIG_X86_LONGHAUL)		+= longhaul.o
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
new file mode 100644
index 00000000000..ff36d2979a9
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
@@ -0,0 +1,620 @@
+/*
+ *  pcc-cpufreq.c - Processor Clocking Control firmware cpufreq interface
+ *
+ *  Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
+ *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *	Nagananda Chumbalkar <nagananda.chumbalkar@hp.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.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or NON
+ *  INFRINGEMENT. See the GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <linux/cpufreq.h>
+#include <linux/compiler.h>
+
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+
+#include <acpi/processor.h>
+
+#define PCC_VERSION 	"1.00.00"
+#define POLL_LOOPS 	300
+
+#define CMD_COMPLETE 	0x1
+#define CMD_GET_FREQ 	0x0
+#define CMD_SET_FREQ 	0x1
+
+#define BUF_SZ		4
+
+#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER,	\
+					     "pcc-cpufreq", msg)
+
+struct pcc_register_resource {
+	u8 descriptor;
+	u16 length;
+	u8 space_id;
+	u8 bit_width;
+	u8 bit_offset;
+	u8 access_size;
+	u64 address;
+} __attribute__ ((packed));
+
+struct pcc_memory_resource {
+	u8 descriptor;
+	u16 length;
+	u8 space_id;
+	u8 resource_usage;
+	u8 type_specific;
+	u64 granularity;
+	u64 minimum;
+	u64 maximum;
+	u64 translation_offset;
+	u64 address_length;
+} __attribute__ ((packed));
+
+static struct cpufreq_driver pcc_cpufreq_driver;
+
+struct pcc_header {
+	u32 signature;
+	u16 length;
+	u8 major;
+	u8 minor;
+	u32 features;
+	u16 command;
+	u16 status;
+	u32 latency;
+	u32 minimum_time;
+	u32 maximum_time;
+	u32 nominal;
+	u32 throttled_frequency;
+	u32 minimum_frequency;
+};
+
+static void __iomem *pcch_virt_addr;
+static struct pcc_header __iomem *pcch_hdr;
+
+static DEFINE_SPINLOCK(pcc_lock);
+
+static struct acpi_generic_address doorbell;
+
+static u64 doorbell_preserve;
+static u64 doorbell_write;
+
+static u8 OSC_UUID[16] = {0x63, 0x9B, 0x2C, 0x9F, 0x70, 0x91, 0x49, 0x1f,
+			  0xBB, 0x4F, 0xA5, 0x98, 0x2F, 0xA1, 0xB5, 0x46};
+
+struct pcc_cpu {
+	u32 input_offset;
+	u32 output_offset;
+};
+
+static struct pcc_cpu *pcc_cpu_info;
+
+static int pcc_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+				     policy->cpuinfo.max_freq);
+	return 0;
+}
+
+static inline void pcc_cmd(void)
+{
+	u64 doorbell_value;
+	int i;
+
+	acpi_read(&doorbell_value, &doorbell);
+	acpi_write((doorbell_value & doorbell_preserve) | doorbell_write,
+		   &doorbell);
+
+	for (i = 0; i < POLL_LOOPS; i++) {
+		if (ioread16(&pcch_hdr->status) & CMD_COMPLETE)
+			break;
+	}
+}
+
+static inline void pcc_clear_mapping(void)
+{
+	if (pcch_virt_addr)
+		iounmap(pcch_virt_addr);
+	pcch_virt_addr = NULL;
+}
+
+static unsigned int pcc_get_freq(unsigned int cpu)
+{
+	struct pcc_cpu *pcc_cpu_data;
+	unsigned int curr_freq;
+	unsigned int freq_limit;
+	u16 status;
+	u32 input_buffer;
+	u32 output_buffer;
+
+	spin_lock(&pcc_lock);
+
+	dprintk("get: get_freq for CPU %d\n", cpu);
+	pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
+
+	input_buffer = 0x1;
+	iowrite32(input_buffer,
+			(pcch_virt_addr + pcc_cpu_data->input_offset));
+	iowrite16(CMD_GET_FREQ, &pcch_hdr->command);
+
+	pcc_cmd();
+
+	output_buffer =
+		ioread32(pcch_virt_addr + pcc_cpu_data->output_offset);
+
+	/* Clear the input buffer - we are done with the current command */
+	memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ);
+
+	status = ioread16(&pcch_hdr->status);
+	if (status != CMD_COMPLETE) {
+		dprintk("get: FAILED: for CPU %d, status is %d\n",
+			cpu, status);
+		goto cmd_incomplete;
+	}
+	iowrite16(0, &pcch_hdr->status);
+	curr_freq = (((ioread32(&pcch_hdr->nominal) * (output_buffer & 0xff))
+			/ 100) * 1000);
+
+	dprintk("get: SUCCESS: (virtual) output_offset for cpu %d is "
+		"0x%x, contains a value of: 0x%x. Speed is: %d MHz\n",
+		cpu, (pcch_virt_addr + pcc_cpu_data->output_offset),
+		output_buffer, curr_freq);
+
+	freq_limit = (output_buffer >> 8) & 0xff;
+	if (freq_limit != 0xff) {
+		dprintk("get: frequency for cpu %d is being temporarily"
+			" capped at %d\n", cpu, curr_freq);
+	}
+
+	spin_unlock(&pcc_lock);
+	return curr_freq;
+
+cmd_incomplete:
+	iowrite16(0, &pcch_hdr->status);
+	spin_unlock(&pcc_lock);
+	return -EINVAL;
+}
+
+static int pcc_cpufreq_target(struct cpufreq_policy *policy,
+			      unsigned int target_freq,
+			      unsigned int relation)
+{
+	struct pcc_cpu *pcc_cpu_data;
+	struct cpufreq_freqs freqs;
+	u16 status;
+	u32 input_buffer;
+	int cpu;
+
+	spin_lock(&pcc_lock);
+	cpu = policy->cpu;
+	pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
+
+	dprintk("target: CPU %d should go to target freq: %d "
+		"(virtual) input_offset is 0x%x\n",
+		cpu, target_freq,
+		(pcch_virt_addr + pcc_cpu_data->input_offset));
+
+	freqs.new = target_freq;
+	freqs.cpu = cpu;
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	input_buffer = 0x1 | (((target_freq * 100)
+			       / (ioread32(&pcch_hdr->nominal) * 1000)) << 8);
+	iowrite32(input_buffer,
+			(pcch_virt_addr + pcc_cpu_data->input_offset));
+	iowrite16(CMD_SET_FREQ, &pcch_hdr->command);
+
+	pcc_cmd();
+
+	/* Clear the input buffer - we are done with the current command */
+	memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ);
+
+	status = ioread16(&pcch_hdr->status);
+	if (status != CMD_COMPLETE) {
+		dprintk("target: FAILED for cpu %d, with status: 0x%x\n",
+			cpu, status);
+		goto cmd_incomplete;
+	}
+	iowrite16(0, &pcch_hdr->status);
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	dprintk("target: was SUCCESSFUL for cpu %d\n", cpu);
+	spin_unlock(&pcc_lock);
+
+	return 0;
+
+cmd_incomplete:
+	iowrite16(0, &pcch_hdr->status);
+	spin_unlock(&pcc_lock);
+	return -EINVAL;
+}
+
+static int pcc_get_offset(int cpu)
+{
+	acpi_status status;
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *pccp, *offset;
+	struct pcc_cpu *pcc_cpu_data;
+	struct acpi_processor *pr;
+	int ret = 0;
+
+	pr = per_cpu(processors, cpu);
+	pcc_cpu_data = per_cpu_ptr(pcc_cpu_info, cpu);
+
+	status = acpi_evaluate_object(pr->handle, "PCCP", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	pccp = buffer.pointer;
+	if (!pccp || pccp->type != ACPI_TYPE_PACKAGE) {
+		ret = -ENODEV;
+		goto out_free;
+	};
+
+	offset = &(pccp->package.elements[0]);
+	if (!offset || offset->type != ACPI_TYPE_INTEGER) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	pcc_cpu_data->input_offset = offset->integer.value;
+
+	offset = &(pccp->package.elements[1]);
+	if (!offset || offset->type != ACPI_TYPE_INTEGER) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	pcc_cpu_data->output_offset = offset->integer.value;
+
+	memset_io((pcch_virt_addr + pcc_cpu_data->input_offset), 0, BUF_SZ);
+	memset_io((pcch_virt_addr + pcc_cpu_data->output_offset), 0, BUF_SZ);
+
+	dprintk("pcc_get_offset: for CPU %d: pcc_cpu_data "
+		"input_offset: 0x%x, pcc_cpu_data output_offset: 0x%x\n",
+		cpu, pcc_cpu_data->input_offset, pcc_cpu_data->output_offset);
+out_free:
+	kfree(buffer.pointer);
+	return ret;
+}
+
+static int __init pcc_cpufreq_do_osc(acpi_handle *handle)
+{
+	acpi_status status;
+	struct acpi_object_list input;
+	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object in_params[4];
+	union acpi_object *out_obj;
+	u32 capabilities[2];
+	u32 errors;
+	u32 supported;
+	int ret = 0;
+
+	input.count = 4;
+	input.pointer = in_params;
+	input.count = 4;
+	input.pointer = in_params;
+	in_params[0].type               = ACPI_TYPE_BUFFER;
+	in_params[0].buffer.length      = 16;
+	in_params[0].buffer.pointer     = OSC_UUID;
+	in_params[1].type               = ACPI_TYPE_INTEGER;
+	in_params[1].integer.value      = 1;
+	in_params[2].type               = ACPI_TYPE_INTEGER;
+	in_params[2].integer.value      = 2;
+	in_params[3].type               = ACPI_TYPE_BUFFER;
+	in_params[3].buffer.length      = 8;
+	in_params[3].buffer.pointer     = (u8 *)&capabilities;
+
+	capabilities[0] = OSC_QUERY_ENABLE;
+	capabilities[1] = 0x1;
+
+	status = acpi_evaluate_object(*handle, "_OSC", &input, &output);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	if (!output.length)
+		return -ENODEV;
+
+	out_obj = output.pointer;
+	if (out_obj->type != ACPI_TYPE_BUFFER) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
+	if (errors) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	supported = *((u32 *)(out_obj->buffer.pointer + 4));
+	if (!(supported & 0x1)) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	kfree(output.pointer);
+	capabilities[0] = 0x0;
+	capabilities[1] = 0x1;
+
+	status = acpi_evaluate_object(*handle, "_OSC", &input, &output);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	if (!output.length)
+		return -ENODEV;
+
+	out_obj = output.pointer;
+	if (out_obj->type != ACPI_TYPE_BUFFER) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
+	if (errors) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	supported = *((u32 *)(out_obj->buffer.pointer + 4));
+	if (!(supported & 0x1)) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+out_free:
+	kfree(output.pointer);
+	return ret;
+}
+
+static int __init pcc_cpufreq_probe(void)
+{
+	acpi_status status;
+	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+	struct pcc_memory_resource *mem_resource;
+	struct pcc_register_resource *reg_resource;
+	union acpi_object *out_obj, *member;
+	acpi_handle handle, osc_handle;
+	int ret = 0;
+
+	status = acpi_get_handle(NULL, "\\_SB", &handle);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	status = acpi_get_handle(handle, "_OSC", &osc_handle);
+	if (ACPI_SUCCESS(status)) {
+		ret = pcc_cpufreq_do_osc(&osc_handle);
+		if (ret)
+			dprintk("probe: _OSC evaluation did not succeed\n");
+		/* Firmware's use of _OSC is optional */
+		ret = 0;
+	}
+
+	status = acpi_evaluate_object(handle, "PCCH", NULL, &output);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	out_obj = output.pointer;
+	if (out_obj->type != ACPI_TYPE_PACKAGE) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	member = &out_obj->package.elements[0];
+	if (member->type != ACPI_TYPE_BUFFER) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	mem_resource = (struct pcc_memory_resource *)member->buffer.pointer;
+
+	dprintk("probe: mem_resource descriptor: 0x%x,"
+		" length: %d, space_id: %d, resource_usage: %d,"
+		" type_specific: %d, granularity: 0x%llx,"
+		" minimum: 0x%llx, maximum: 0x%llx,"
+		" translation_offset: 0x%llx, address_length: 0x%llx\n",
+		mem_resource->descriptor, mem_resource->length,
+		mem_resource->space_id, mem_resource->resource_usage,
+		mem_resource->type_specific, mem_resource->granularity,
+		mem_resource->minimum, mem_resource->maximum,
+		mem_resource->translation_offset,
+		mem_resource->address_length);
+
+	if (mem_resource->space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	pcch_virt_addr = ioremap_nocache(mem_resource->minimum,
+					mem_resource->address_length);
+	if (pcch_virt_addr == NULL) {
+		dprintk("probe: could not map shared mem region\n");
+		goto out_free;
+	}
+	pcch_hdr = pcch_virt_addr;
+
+	dprintk("probe: PCCH header (virtual) addr: 0x%p\n", pcch_hdr);
+	dprintk("probe: PCCH header is at physical address: 0x%llx,"
+		" signature: 0x%x, length: %d bytes, major: %d, minor: %d,"
+		" supported features: 0x%x, command field: 0x%x,"
+		" status field: 0x%x, nominal latency: %d us\n",
+		mem_resource->minimum, ioread32(&pcch_hdr->signature),
+		ioread16(&pcch_hdr->length), ioread8(&pcch_hdr->major),
+		ioread8(&pcch_hdr->minor), ioread32(&pcch_hdr->features),
+		ioread16(&pcch_hdr->command), ioread16(&pcch_hdr->status),
+		ioread32(&pcch_hdr->latency));
+
+	dprintk("probe: min time between commands: %d us,"
+		" max time between commands: %d us,"
+		" nominal CPU frequency: %d MHz,"
+		" minimum CPU frequency: %d MHz,"
+		" minimum CPU frequency without throttling: %d MHz\n",
+		ioread32(&pcch_hdr->minimum_time),
+		ioread32(&pcch_hdr->maximum_time),
+		ioread32(&pcch_hdr->nominal),
+		ioread32(&pcch_hdr->throttled_frequency),
+		ioread32(&pcch_hdr->minimum_frequency));
+
+	member = &out_obj->package.elements[1];
+	if (member->type != ACPI_TYPE_BUFFER) {
+		ret = -ENODEV;
+		goto pcch_free;
+	}
+
+	reg_resource = (struct pcc_register_resource *)member->buffer.pointer;
+
+	doorbell.space_id = reg_resource->space_id;
+	doorbell.bit_width = reg_resource->bit_width;
+	doorbell.bit_offset = reg_resource->bit_offset;
+	doorbell.access_width = 64;
+	doorbell.address = reg_resource->address;
+
+	dprintk("probe: doorbell: space_id is %d, bit_width is %d, "
+		"bit_offset is %d, access_width is %d, address is 0x%llx\n",
+		doorbell.space_id, doorbell.bit_width, doorbell.bit_offset,
+		doorbell.access_width, reg_resource->address);
+
+	member = &out_obj->package.elements[2];
+	if (member->type != ACPI_TYPE_INTEGER) {
+		ret = -ENODEV;
+		goto pcch_free;
+	}
+
+	doorbell_preserve = member->integer.value;
+
+	member = &out_obj->package.elements[3];
+	if (member->type != ACPI_TYPE_INTEGER) {
+		ret = -ENODEV;
+		goto pcch_free;
+	}
+
+	doorbell_write = member->integer.value;
+
+	dprintk("probe: doorbell_preserve: 0x%llx,"
+		" doorbell_write: 0x%llx\n",
+		doorbell_preserve, doorbell_write);
+
+	pcc_cpu_info = alloc_percpu(struct pcc_cpu);
+	if (!pcc_cpu_info) {
+		ret = -ENOMEM;
+		goto pcch_free;
+	}
+
+	printk(KERN_DEBUG "pcc-cpufreq: (v%s) driver loaded with frequency"
+	       " limits: %d MHz, %d MHz\n", PCC_VERSION,
+	       ioread32(&pcch_hdr->minimum_frequency),
+	       ioread32(&pcch_hdr->nominal));
+	kfree(output.pointer);
+	return ret;
+pcch_free:
+	pcc_clear_mapping();
+out_free:
+	kfree(output.pointer);
+	return ret;
+}
+
+static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	unsigned int cpu = policy->cpu;
+	unsigned int result = 0;
+
+	if (!pcch_virt_addr) {
+		result = -1;
+		goto pcch_null;
+	}
+
+	result = pcc_get_offset(cpu);
+	if (result) {
+		dprintk("init: PCCP evaluation failed\n");
+		goto free;
+	}
+
+	policy->max = policy->cpuinfo.max_freq =
+		ioread32(&pcch_hdr->nominal) * 1000;
+	policy->min = policy->cpuinfo.min_freq =
+		ioread32(&pcch_hdr->minimum_frequency) * 1000;
+	policy->cur = pcc_get_freq(cpu);
+
+	dprintk("init: policy->max is %d, policy->min is %d\n",
+		policy->max, policy->min);
+
+	return 0;
+free:
+	pcc_clear_mapping();
+	free_percpu(pcc_cpu_info);
+pcch_null:
+	return result;
+}
+
+static int pcc_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	return 0;
+}
+
+static struct cpufreq_driver pcc_cpufreq_driver = {
+	.flags = CPUFREQ_CONST_LOOPS,
+	.get = pcc_get_freq,
+	.verify = pcc_cpufreq_verify,
+	.target = pcc_cpufreq_target,
+	.init = pcc_cpufreq_cpu_init,
+	.exit = pcc_cpufreq_cpu_exit,
+	.name = "pcc-cpufreq",
+	.owner = THIS_MODULE,
+};
+
+static int __init pcc_cpufreq_init(void)
+{
+	int ret;
+
+	if (acpi_disabled)
+		return 0;
+
+	ret = pcc_cpufreq_probe();
+	if (ret) {
+		dprintk("pcc_cpufreq_init: PCCH evaluation failed\n");
+		return ret;
+	}
+
+	ret = cpufreq_register_driver(&pcc_cpufreq_driver);
+
+	return ret;
+}
+
+static void __exit pcc_cpufreq_exit(void)
+{
+	cpufreq_unregister_driver(&pcc_cpufreq_driver);
+
+	pcc_clear_mapping();
+
+	free_percpu(pcc_cpu_info);
+}
+
+MODULE_AUTHOR("Matthew Garrett, Naga Chumbalkar");
+MODULE_VERSION(PCC_VERSION);
+MODULE_DESCRIPTION("Processor Clocking Control interface driver");
+MODULE_LICENSE("GPL");
+
+late_initcall(pcc_cpufreq_init);
+module_exit(pcc_cpufreq_exit);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index f125e5c551c..d360b56e982 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -806,7 +806,7 @@ static int find_psb_table(struct powernow_k8_data *data)
 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data,
 		unsigned int index)
 {
-	acpi_integer control;
+	u64 control;
 
 	if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE))
 		return;
@@ -824,7 +824,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 {
 	struct cpufreq_frequency_table *powernow_table;
 	int ret_val = -ENODEV;
-	acpi_integer control, status;
+	u64 control, status;
 
 	if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
 		dprintk("register performance failed: bad ACPI data\n");
@@ -948,7 +948,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 		u32 fid;
 		u32 vid;
 		u32 freq, index;
-		acpi_integer status, control;
+		u64 status, control;
 
 		if (data->exttype) {
 			status =  data->acpi_data.states[i].status;
@@ -1356,6 +1356,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
 
 	kfree(data->powernow_table);
 	kfree(data);
+	per_cpu(powernow_data, pol->cpu) = NULL;
 
 	return 0;
 }
@@ -1375,7 +1376,7 @@ static unsigned int powernowk8_get(unsigned int cpu)
 	int err;
 
 	if (!data)
-		return -EINVAL;
+		return 0;
 
 	smp_call_function_single(cpu, query_values_on_cpu, &err, true);
 	if (err)
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index fc6c8ef92dc..b3eeb66c0a5 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -18,6 +18,7 @@
 #include <asm/processor.h>
 #include <linux/smp.h>
 #include <asm/k8.h>
+#include <asm/smp.h>
 
 #define LVL_1_INST	1
 #define LVL_1_DATA	2
@@ -31,6 +32,8 @@ struct _cache_table {
 	short size;
 };
 
+#define MB(x)	((x) * 1024)
+
 /* All the cache descriptor types we care about (no TLB or
    trace cache entries) */
 
@@ -44,9 +47,9 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
 	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x23, LVL_3,      1024 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x25, LVL_3,      2048 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x29, LVL_3,      4096 },	/* 8-way set assoc, sectored cache, 64 byte line size */
+	{ 0x23, LVL_3,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
+	{ 0x25, LVL_3,      MB(2) },	/* 8-way set assoc, sectored cache, 64 byte line size */
+	{ 0x29, LVL_3,      MB(4) },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x2c, LVL_1_DATA, 32 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x30, LVL_1_INST, 32 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x39, LVL_2,      128 },	/* 4-way set assoc, sectored cache, 64 byte line size */
@@ -59,16 +62,16 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x41, LVL_2,      128 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x42, LVL_2,      256 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x43, LVL_2,      512 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x44, LVL_2,      1024 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x45, LVL_2,      2048 },	/* 4-way set assoc, 32 byte line size */
-	{ 0x46, LVL_3,      4096 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x47, LVL_3,      8192 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x49, LVL_3,      4096 },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4a, LVL_3,      6144 },	/* 12-way set assoc, 64 byte line size */
-	{ 0x4b, LVL_3,      8192 },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4c, LVL_3,     12288 },	/* 12-way set assoc, 64 byte line size */
-	{ 0x4d, LVL_3,     16384 },	/* 16-way set assoc, 64 byte line size */
-	{ 0x4e, LVL_2,      6144 },	/* 24-way set assoc, 64 byte line size */
+	{ 0x44, LVL_2,      MB(1) },	/* 4-way set assoc, 32 byte line size */
+	{ 0x45, LVL_2,      MB(2) },	/* 4-way set assoc, 32 byte line size */
+	{ 0x46, LVL_3,      MB(4) },	/* 4-way set assoc, 64 byte line size */
+	{ 0x47, LVL_3,      MB(8) },	/* 8-way set assoc, 64 byte line size */
+	{ 0x49, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
+	{ 0x4a, LVL_3,      MB(6) },	/* 12-way set assoc, 64 byte line size */
+	{ 0x4b, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
+	{ 0x4c, LVL_3,      MB(12) },	/* 12-way set assoc, 64 byte line size */
+	{ 0x4d, LVL_3,      MB(16) },	/* 16-way set assoc, 64 byte line size */
+	{ 0x4e, LVL_2,      MB(6) },	/* 24-way set assoc, 64 byte line size */
 	{ 0x60, LVL_1_DATA, 16 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */
@@ -77,34 +80,34 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x71, LVL_TRACE,  16 },	/* 8-way set assoc */
 	{ 0x72, LVL_TRACE,  32 },	/* 8-way set assoc */
 	{ 0x73, LVL_TRACE,  64 },	/* 8-way set assoc */
-	{ 0x78, LVL_2,    1024 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x79, LVL_2,     128 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7a, LVL_2,     256 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7b, LVL_2,     512 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7c, LVL_2,    1024 },	/* 8-way set assoc, sectored cache, 64 byte line size */
-	{ 0x7d, LVL_2,    2048 },	/* 8-way set assoc, 64 byte line size */
-	{ 0x7f, LVL_2,     512 },	/* 2-way set assoc, 64 byte line size */
-	{ 0x82, LVL_2,     256 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x83, LVL_2,     512 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x84, LVL_2,    1024 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x85, LVL_2,    2048 },	/* 8-way set assoc, 32 byte line size */
-	{ 0x86, LVL_2,     512 },	/* 4-way set assoc, 64 byte line size */
-	{ 0x87, LVL_2,    1024 },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd0, LVL_3,     512 },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd1, LVL_3,    1024 },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd2, LVL_3,    2048 },	/* 4-way set assoc, 64 byte line size */
-	{ 0xd6, LVL_3,    1024 },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd7, LVL_3,    2048 },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd8, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
-	{ 0xdc, LVL_3,    2048 },	/* 12-way set assoc, 64 byte line size */
-	{ 0xdd, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
-	{ 0xde, LVL_3,    8192 },	/* 12-way set assoc, 64 byte line size */
-	{ 0xe2, LVL_3,    2048 },	/* 16-way set assoc, 64 byte line size */
-	{ 0xe3, LVL_3,    4096 },	/* 16-way set assoc, 64 byte line size */
-	{ 0xe4, LVL_3,    8192 },	/* 16-way set assoc, 64 byte line size */
-	{ 0xea, LVL_3,    12288 },	/* 24-way set assoc, 64 byte line size */
-	{ 0xeb, LVL_3,    18432 },	/* 24-way set assoc, 64 byte line size */
-	{ 0xec, LVL_3,    24576 },	/* 24-way set assoc, 64 byte line size */
+	{ 0x78, LVL_2,      MB(1) },	/* 4-way set assoc, 64 byte line size */
+	{ 0x79, LVL_2,      128 },	/* 8-way set assoc, sectored cache, 64 byte line size */
+	{ 0x7a, LVL_2,      256 },	/* 8-way set assoc, sectored cache, 64 byte line size */
+	{ 0x7b, LVL_2,      512 },	/* 8-way set assoc, sectored cache, 64 byte line size */
+	{ 0x7c, LVL_2,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
+	{ 0x7d, LVL_2,      MB(2) },	/* 8-way set assoc, 64 byte line size */
+	{ 0x7f, LVL_2,      512 },	/* 2-way set assoc, 64 byte line size */
+	{ 0x82, LVL_2,      256 },	/* 8-way set assoc, 32 byte line size */
+	{ 0x83, LVL_2,      512 },	/* 8-way set assoc, 32 byte line size */
+	{ 0x84, LVL_2,      MB(1) },	/* 8-way set assoc, 32 byte line size */
+	{ 0x85, LVL_2,      MB(2) },	/* 8-way set assoc, 32 byte line size */
+	{ 0x86, LVL_2,      512 },	/* 4-way set assoc, 64 byte line size */
+	{ 0x87, LVL_2,      MB(1) },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd0, LVL_3,      512 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd1, LVL_3,      MB(1) },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd2, LVL_3,      MB(2) },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd6, LVL_3,      MB(1) },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd7, LVL_3,      MB(2) },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd8, LVL_3,      MB(4) },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdc, LVL_3,      MB(2) },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdd, LVL_3,      MB(4) },	/* 12-way set assoc, 64 byte line size */
+	{ 0xde, LVL_3,      MB(8) },	/* 12-way set assoc, 64 byte line size */
+	{ 0xe2, LVL_3,      MB(2) },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe3, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe4, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
+	{ 0xea, LVL_3,      MB(12) },	/* 24-way set assoc, 64 byte line size */
+	{ 0xeb, LVL_3,      MB(18) },	/* 24-way set assoc, 64 byte line size */
+	{ 0xec, LVL_3,      MB(24) },	/* 24-way set assoc, 64 byte line size */
 	{ 0x00, 0, 0}
 };
 
@@ -150,7 +153,8 @@ struct _cpuid4_info {
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
 	unsigned long size;
-	unsigned long can_disable;
+	bool can_disable;
+	unsigned int l3_indices;
 	DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
 };
 
@@ -160,7 +164,8 @@ struct _cpuid4_info_regs {
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
 	unsigned long size;
-	unsigned long can_disable;
+	bool can_disable;
+	unsigned int l3_indices;
 };
 
 unsigned short			num_cache_leaves;
@@ -290,6 +295,36 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 		(ebx->split.ways_of_associativity + 1) - 1;
 }
 
+struct _cache_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct _cpuid4_info *, char *);
+	ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
+};
+
+#ifdef CONFIG_CPU_SUP_AMD
+static unsigned int __cpuinit amd_calc_l3_indices(void)
+{
+	/*
+	 * We're called over smp_call_function_single() and therefore
+	 * are on the correct cpu.
+	 */
+	int cpu = smp_processor_id();
+	int node = cpu_to_node(cpu);
+	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	unsigned int sc0, sc1, sc2, sc3;
+	u32 val = 0;
+
+	pci_read_config_dword(dev, 0x1C4, &val);
+
+	/* calculate subcache sizes */
+	sc0 = !(val & BIT(0));
+	sc1 = !(val & BIT(4));
+	sc2 = !(val & BIT(8))  + !(val & BIT(9));
+	sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+	return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+}
+
 static void __cpuinit
 amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
 {
@@ -299,12 +334,103 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
 	if (boot_cpu_data.x86 == 0x11)
 		return;
 
-	/* see erratum #382 */
-	if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8))
+	/* see errata #382 and #388 */
+	if ((boot_cpu_data.x86 == 0x10) &&
+	    ((boot_cpu_data.x86_model < 0x8) ||
+	     (boot_cpu_data.x86_mask  < 0x1)))
 		return;
 
-	this_leaf->can_disable = 1;
+	this_leaf->can_disable = true;
+	this_leaf->l3_indices  = amd_calc_l3_indices();
+}
+
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+				  unsigned int index)
+{
+	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+	int node = amd_get_nb_id(cpu);
+	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	unsigned int reg = 0;
+
+	if (!this_leaf->can_disable)
+		return -EINVAL;
+
+	if (!dev)
+		return -EINVAL;
+
+	pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
+	return sprintf(buf, "0x%08x\n", reg);
+}
+
+#define SHOW_CACHE_DISABLE(index)					\
+static ssize_t								\
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf)	\
+{									\
+	return show_cache_disable(this_leaf, buf, index);		\
 }
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
+
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+	const char *buf, size_t count, unsigned int index)
+{
+	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+	int node = amd_get_nb_id(cpu);
+	struct pci_dev *dev = node_to_k8_nb_misc(node);
+	unsigned long val = 0;
+
+#define SUBCACHE_MASK	(3UL << 20)
+#define SUBCACHE_INDEX	0xfff
+
+	if (!this_leaf->can_disable)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!dev)
+		return -EINVAL;
+
+	if (strict_strtoul(buf, 10, &val) < 0)
+		return -EINVAL;
+
+	/* do not allow writes outside of allowed bits */
+	if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
+	    ((val & SUBCACHE_INDEX) > this_leaf->l3_indices))
+		return -EINVAL;
+
+	val |= BIT(30);
+	pci_write_config_dword(dev, 0x1BC + index * 4, val);
+	/*
+	 * We need to WBINVD on a core on the node containing the L3 cache which
+	 * indices we disable therefore a simple wbinvd() is not sufficient.
+	 */
+	wbinvd_on_cpu(cpu);
+	pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31));
+	return count;
+}
+
+#define STORE_CACHE_DISABLE(index)					\
+static ssize_t								\
+store_cache_disable_##index(struct _cpuid4_info *this_leaf,		\
+			    const char *buf, size_t count)		\
+{									\
+	return store_cache_disable(this_leaf, buf, count, index);	\
+}
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+		show_cache_disable_0, store_cache_disable_0);
+static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
+		show_cache_disable_1, store_cache_disable_1);
+
+#else	/* CONFIG_CPU_SUP_AMD */
+static void __cpuinit
+amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+{
+};
+#endif /* CONFIG_CPU_SUP_AMD */
 
 static int
 __cpuinit cpuid4_cache_lookup_regs(int index,
@@ -711,82 +837,6 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
 #define to_object(k)	container_of(k, struct _index_kobject, kobj)
 #define to_attr(a)	container_of(a, struct _cache_attr, attr)
 
-static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
-				  unsigned int index)
-{
-	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
-	int node = cpu_to_node(cpu);
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
-	unsigned int reg = 0;
-
-	if (!this_leaf->can_disable)
-		return -EINVAL;
-
-	if (!dev)
-		return -EINVAL;
-
-	pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
-	return sprintf(buf, "%x\n", reg);
-}
-
-#define SHOW_CACHE_DISABLE(index)					\
-static ssize_t								\
-show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf)  	\
-{									\
-	return show_cache_disable(this_leaf, buf, index);		\
-}
-SHOW_CACHE_DISABLE(0)
-SHOW_CACHE_DISABLE(1)
-
-static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
-	const char *buf, size_t count, unsigned int index)
-{
-	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
-	int node = cpu_to_node(cpu);
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
-	unsigned long val = 0;
-	unsigned int scrubber = 0;
-
-	if (!this_leaf->can_disable)
-		return -EINVAL;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	if (!dev)
-		return -EINVAL;
-
-	if (strict_strtoul(buf, 10, &val) < 0)
-		return -EINVAL;
-
-	val |= 0xc0000000;
-
-	pci_read_config_dword(dev, 0x58, &scrubber);
-	scrubber &= ~0x1f000000;
-	pci_write_config_dword(dev, 0x58, scrubber);
-
-	pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
-	wbinvd();
-	pci_write_config_dword(dev, 0x1BC + index * 4, val);
-	return count;
-}
-
-#define STORE_CACHE_DISABLE(index)					\
-static ssize_t								\
-store_cache_disable_##index(struct _cpuid4_info *this_leaf,	     	\
-			    const char *buf, size_t count)		\
-{									\
-	return store_cache_disable(this_leaf, buf, count, index);	\
-}
-STORE_CACHE_DISABLE(0)
-STORE_CACHE_DISABLE(1)
-
-struct _cache_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct _cpuid4_info *, char *);
-	ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
-};
-
 #define define_one_ro(_name) \
 static struct _cache_attr _name = \
 	__ATTR(_name, 0444, show_##_name, NULL)
@@ -801,23 +851,28 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
-		show_cache_disable_0, store_cache_disable_0);
-static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
-		show_cache_disable_1, store_cache_disable_1);
+#define DEFAULT_SYSFS_CACHE_ATTRS	\
+	&type.attr,			\
+	&level.attr,			\
+	&coherency_line_size.attr,	\
+	&physical_line_partition.attr,	\
+	&ways_of_associativity.attr,	\
+	&number_of_sets.attr,		\
+	&size.attr,			\
+	&shared_cpu_map.attr,		\
+	&shared_cpu_list.attr
 
 static struct attribute *default_attrs[] = {
-	&type.attr,
-	&level.attr,
-	&coherency_line_size.attr,
-	&physical_line_partition.attr,
-	&ways_of_associativity.attr,
-	&number_of_sets.attr,
-	&size.attr,
-	&shared_cpu_map.attr,
-	&shared_cpu_list.attr,
+	DEFAULT_SYSFS_CACHE_ATTRS,
+	NULL
+};
+
+static struct attribute *default_l3_attrs[] = {
+	DEFAULT_SYSFS_CACHE_ATTRS,
+#ifdef CONFIG_CPU_SUP_AMD
 	&cache_disable_0.attr,
 	&cache_disable_1.attr,
+#endif
 	NULL
 };
 
@@ -848,7 +903,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	return ret;
 }
 
-static struct sysfs_ops sysfs_ops = {
+static const struct sysfs_ops sysfs_ops = {
 	.show   = show,
 	.store  = store,
 };
@@ -908,6 +963,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	unsigned int cpu = sys_dev->id;
 	unsigned long i, j;
 	struct _index_kobject *this_object;
+	struct _cpuid4_info   *this_leaf;
 	int retval;
 
 	retval = cpuid4_cache_sysfs_init(cpu);
@@ -926,6 +982,14 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 		this_object = INDEX_KOBJECT_PTR(cpu, i);
 		this_object->cpu = cpu;
 		this_object->index = i;
+
+		this_leaf = CPUID4_INFO_IDX(cpu, i);
+
+		if (this_leaf->can_disable)
+			ktype_cache.default_attrs = default_l3_attrs;
+		else
+			ktype_cache.default_attrs = default_attrs;
+
 		retval = kobject_init_and_add(&(this_object->kobj),
 					      &ktype_cache,
 					      per_cpu(ici_cache_kobject, cpu),
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a8aacd4b513..28cba46bf32 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2044,6 +2044,7 @@ static __init void mce_init_banks(void)
 		struct mce_bank *b = &mce_banks[i];
 		struct sysdev_attribute *a = &b->attr;
 
+		sysfs_attr_init(&a->attr);
 		a->attr.name	= b->attrname;
 		snprintf(b->attrname, ATTR_LEN, "bank%d", i);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 83a3d1f4efc..cda932ca3ad 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -388,7 +388,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	return ret;
 }
 
-static struct sysfs_ops threshold_ops = {
+static const struct sysfs_ops threshold_ops = {
 	.show			= show,
 	.store			= store,
 };
diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile
index f4361b56f8e..ad9e5ed8118 100644
--- a/arch/x86/kernel/cpu/mtrr/Makefile
+++ b/arch/x86/kernel/cpu/mtrr/Makefile
@@ -1,3 +1,3 @@
-obj-y		:= main.o if.o generic.o state.o cleanup.o
+obj-y		:= main.o if.o generic.o cleanup.o
 obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o
 
diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c
index 33af14110df..92ba9cd31c9 100644
--- a/arch/x86/kernel/cpu/mtrr/amd.c
+++ b/arch/x86/kernel/cpu/mtrr/amd.c
@@ -108,7 +108,7 @@ amd_validate_add_page(unsigned long base, unsigned long size, unsigned int type)
 	return 0;
 }
 
-static struct mtrr_ops amd_mtrr_ops = {
+static const struct mtrr_ops amd_mtrr_ops = {
 	.vendor            = X86_VENDOR_AMD,
 	.set               = amd_set_mtrr,
 	.get               = amd_get_mtrr,
diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c
index de89f14eff3..316fe3e60a9 100644
--- a/arch/x86/kernel/cpu/mtrr/centaur.c
+++ b/arch/x86/kernel/cpu/mtrr/centaur.c
@@ -110,7 +110,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t
 	return 0;
 }
 
-static struct mtrr_ops centaur_mtrr_ops = {
+static const struct mtrr_ops centaur_mtrr_ops = {
 	.vendor            = X86_VENDOR_CENTAUR,
 	.set               = centaur_set_mcr,
 	.get               = centaur_get_mcr,
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 09b1698e046..06130b52f01 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -22,10 +22,10 @@
 #include <linux/pci.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
-#include <linux/sort.h>
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/kvm_para.h>
+#include <linux/range.h>
 
 #include <asm/processor.h>
 #include <asm/e820.h>
@@ -34,11 +34,6 @@
 
 #include "mtrr.h"
 
-struct res_range {
-	unsigned long	start;
-	unsigned long	end;
-};
-
 struct var_mtrr_range_state {
 	unsigned long	base_pfn;
 	unsigned long	size_pfn;
@@ -56,7 +51,7 @@ struct var_mtrr_state {
 /* Should be related to MTRR_VAR_RANGES nums */
 #define RANGE_NUM				256
 
-static struct res_range __initdata		range[RANGE_NUM];
+static struct range __initdata		range[RANGE_NUM];
 static int __initdata				nr_range;
 
 static struct var_mtrr_range_state __initdata	range_state[RANGE_NUM];
@@ -64,152 +59,11 @@ static struct var_mtrr_range_state __initdata	range_state[RANGE_NUM];
 static int __initdata debug_print;
 #define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0)
 
-
-static int __init
-add_range(struct res_range *range, int nr_range,
-	  unsigned long start, unsigned long end)
-{
-	/* Out of slots: */
-	if (nr_range >= RANGE_NUM)
-		return nr_range;
-
-	range[nr_range].start = start;
-	range[nr_range].end = end;
-
-	nr_range++;
-
-	return nr_range;
-}
-
-static int __init
-add_range_with_merge(struct res_range *range, int nr_range,
-		     unsigned long start, unsigned long end)
-{
-	int i;
-
-	/* Try to merge it with old one: */
-	for (i = 0; i < nr_range; i++) {
-		unsigned long final_start, final_end;
-		unsigned long common_start, common_end;
-
-		if (!range[i].end)
-			continue;
-
-		common_start = max(range[i].start, start);
-		common_end = min(range[i].end, end);
-		if (common_start > common_end + 1)
-			continue;
-
-		final_start = min(range[i].start, start);
-		final_end = max(range[i].end, end);
-
-		range[i].start = final_start;
-		range[i].end =  final_end;
-		return nr_range;
-	}
-
-	/* Need to add it: */
-	return add_range(range, nr_range, start, end);
-}
-
-static void __init
-subtract_range(struct res_range *range, unsigned long start, unsigned long end)
-{
-	int i, j;
-
-	for (j = 0; j < RANGE_NUM; j++) {
-		if (!range[j].end)
-			continue;
-
-		if (start <= range[j].start && end >= range[j].end) {
-			range[j].start = 0;
-			range[j].end = 0;
-			continue;
-		}
-
-		if (start <= range[j].start && end < range[j].end &&
-		    range[j].start < end + 1) {
-			range[j].start = end + 1;
-			continue;
-		}
-
-
-		if (start > range[j].start && end >= range[j].end &&
-		    range[j].end > start - 1) {
-			range[j].end = start - 1;
-			continue;
-		}
-
-		if (start > range[j].start && end < range[j].end) {
-			/* Find the new spare: */
-			for (i = 0; i < RANGE_NUM; i++) {
-				if (range[i].end == 0)
-					break;
-			}
-			if (i < RANGE_NUM) {
-				range[i].end = range[j].end;
-				range[i].start = end + 1;
-			} else {
-				printk(KERN_ERR "run of slot in ranges\n");
-			}
-			range[j].end = start - 1;
-			continue;
-		}
-	}
-}
-
-static int __init cmp_range(const void *x1, const void *x2)
-{
-	const struct res_range *r1 = x1;
-	const struct res_range *r2 = x2;
-	long start1, start2;
-
-	start1 = r1->start;
-	start2 = r2->start;
-
-	return start1 - start2;
-}
-
-static int __init clean_sort_range(struct res_range *range, int az)
-{
-	int i, j, k = az - 1, nr_range = 0;
-
-	for (i = 0; i < k; i++) {
-		if (range[i].end)
-			continue;
-		for (j = k; j > i; j--) {
-			if (range[j].end) {
-				k = j;
-				break;
-			}
-		}
-		if (j == i)
-			break;
-		range[i].start = range[k].start;
-		range[i].end   = range[k].end;
-		range[k].start = 0;
-		range[k].end   = 0;
-		k--;
-	}
-	/* count it */
-	for (i = 0; i < az; i++) {
-		if (!range[i].end) {
-			nr_range = i;
-			break;
-		}
-	}
-
-	/* sort them */
-	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
-
-	return nr_range;
-}
-
 #define BIOS_BUG_MSG KERN_WARNING \
 	"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
 
 static int __init
-x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
+x86_get_mtrr_mem_range(struct range *range, int nr_range,
 		       unsigned long extra_remove_base,
 		       unsigned long extra_remove_size)
 {
@@ -223,14 +77,14 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 			continue;
 		base = range_state[i].base_pfn;
 		size = range_state[i].size_pfn;
-		nr_range = add_range_with_merge(range, nr_range, base,
-						base + size - 1);
+		nr_range = add_range_with_merge(range, RANGE_NUM, nr_range,
+						base, base + size);
 	}
 	if (debug_print) {
 		printk(KERN_DEBUG "After WB checking\n");
 		for (i = 0; i < nr_range; i++)
-			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
-				 range[i].start, range[i].end + 1);
+			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+				 range[i].start, range[i].end);
 	}
 
 	/* Take out UC ranges: */
@@ -252,19 +106,19 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 			size -= (1<<(20-PAGE_SHIFT)) - base;
 			base = 1<<(20-PAGE_SHIFT);
 		}
-		subtract_range(range, base, base + size - 1);
+		subtract_range(range, RANGE_NUM, base, base + size);
 	}
 	if (extra_remove_size)
-		subtract_range(range, extra_remove_base,
-				 extra_remove_base + extra_remove_size  - 1);
+		subtract_range(range, RANGE_NUM, extra_remove_base,
+				 extra_remove_base + extra_remove_size);
 
 	if  (debug_print) {
 		printk(KERN_DEBUG "After UC checking\n");
 		for (i = 0; i < RANGE_NUM; i++) {
 			if (!range[i].end)
 				continue;
-			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
-				 range[i].start, range[i].end + 1);
+			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+				 range[i].start, range[i].end);
 		}
 	}
 
@@ -273,26 +127,22 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 	if  (debug_print) {
 		printk(KERN_DEBUG "After sorting\n");
 		for (i = 0; i < nr_range; i++)
-			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
-				 range[i].start, range[i].end + 1);
+			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+				 range[i].start, range[i].end);
 	}
 
-	/* clear those is not used */
-	for (i = nr_range; i < RANGE_NUM; i++)
-		memset(&range[i], 0, sizeof(range[i]));
-
 	return nr_range;
 }
 
 #ifdef CONFIG_MTRR_SANITIZER
 
-static unsigned long __init sum_ranges(struct res_range *range, int nr_range)
+static unsigned long __init sum_ranges(struct range *range, int nr_range)
 {
 	unsigned long sum = 0;
 	int i;
 
 	for (i = 0; i < nr_range; i++)
-		sum += range[i].end + 1 - range[i].start;
+		sum += range[i].end - range[i].start;
 
 	return sum;
 }
@@ -621,7 +471,7 @@ static int __init parse_mtrr_spare_reg(char *arg)
 early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg);
 
 static int __init
-x86_setup_var_mtrrs(struct res_range *range, int nr_range,
+x86_setup_var_mtrrs(struct range *range, int nr_range,
 		    u64 chunk_size, u64 gran_size)
 {
 	struct var_mtrr_state var_state;
@@ -639,7 +489,7 @@ x86_setup_var_mtrrs(struct res_range *range, int nr_range,
 	/* Write the range: */
 	for (i = 0; i < nr_range; i++) {
 		set_var_mtrr_range(&var_state, range[i].start,
-				   range[i].end - range[i].start + 1);
+				   range[i].end - range[i].start);
 	}
 
 	/* Write the last range: */
@@ -742,7 +592,7 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
 		      unsigned long x_remove_base,
 		      unsigned long x_remove_size, int i)
 {
-	static struct res_range range_new[RANGE_NUM];
+	static struct range range_new[RANGE_NUM];
 	unsigned long range_sums_new;
 	static int nr_range_new;
 	int num_reg;
@@ -869,10 +719,10 @@ int __init mtrr_cleanup(unsigned address_bits)
 	 * [0, 1M) should always be covered by var mtrr with WB
 	 * and fixed mtrrs should take effect before var mtrr for it:
 	 */
-	nr_range = add_range_with_merge(range, nr_range, 0,
-					(1ULL<<(20 - PAGE_SHIFT)) - 1);
+	nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
+					1ULL<<(20 - PAGE_SHIFT));
 	/* Sort the ranges: */
-	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+	sort_range(range, nr_range);
 
 	range_sums = sum_ranges(range, nr_range);
 	printk(KERN_INFO "total RAM covered: %ldM\n",
@@ -1089,9 +939,9 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 	nr_range = 0;
 	if (mtrr_tom2) {
 		range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT));
-		range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1;
-		if (highest_pfn < range[nr_range].end + 1)
-			highest_pfn = range[nr_range].end + 1;
+		range[nr_range].end = mtrr_tom2 >> PAGE_SHIFT;
+		if (highest_pfn < range[nr_range].end)
+			highest_pfn = range[nr_range].end;
 		nr_range++;
 	}
 	nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0);
@@ -1103,15 +953,15 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* Check the holes: */
 	for (i = 0; i < nr_range - 1; i++) {
-		if (range[i].end + 1 < range[i+1].start)
-			total_trim_size += real_trim_memory(range[i].end + 1,
+		if (range[i].end < range[i+1].start)
+			total_trim_size += real_trim_memory(range[i].end,
 							    range[i+1].start);
 	}
 
 	/* Check the top: */
 	i = nr_range - 1;
-	if (range[i].end + 1 < end_pfn)
-		total_trim_size += real_trim_memory(range[i].end + 1,
+	if (range[i].end < end_pfn)
+		total_trim_size += real_trim_memory(range[i].end,
 							 end_pfn);
 
 	if (total_trim_size) {
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index 228d982ce09..68a3343e579 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -265,7 +265,7 @@ static void cyrix_set_all(void)
 	post_set();
 }
 
-static struct mtrr_ops cyrix_mtrr_ops = {
+static const struct mtrr_ops cyrix_mtrr_ops = {
 	.vendor            = X86_VENDOR_CYRIX,
 	.set_all	   = cyrix_set_all,
 	.set               = cyrix_set_arr,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 55da0c5f68d..9aa5dc76ff4 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -464,7 +464,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 		tmp |= ~((1<<(hi - 1)) - 1);
 
 		if (tmp != mask_lo) {
-			WARN_ONCE(1, KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n");
+			printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
 			mask_lo = tmp;
 		}
 	}
@@ -570,7 +570,7 @@ static unsigned long set_mtrr_state(void)
 
 
 static unsigned long cr4;
-static DEFINE_SPINLOCK(set_atomicity_lock);
+static DEFINE_RAW_SPINLOCK(set_atomicity_lock);
 
 /*
  * Since we are disabling the cache don't allow any interrupts,
@@ -590,7 +590,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	 * changes to the way the kernel boots
 	 */
 
-	spin_lock(&set_atomicity_lock);
+	raw_spin_lock(&set_atomicity_lock);
 
 	/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
 	cr0 = read_cr0() | X86_CR0_CD;
@@ -627,7 +627,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 	/* Restore value of CR4 */
 	if (cpu_has_pge)
 		write_cr4(cr4);
-	spin_unlock(&set_atomicity_lock);
+	raw_spin_unlock(&set_atomicity_lock);
 }
 
 static void generic_set_all(void)
@@ -752,7 +752,7 @@ int positive_have_wrcomb(void)
 /*
  * Generic structure...
  */
-struct mtrr_ops generic_mtrr_ops = {
+const struct mtrr_ops generic_mtrr_ops = {
 	.use_intel_if		= 1,
 	.set_all		= generic_set_all,
 	.get			= generic_get_mtrr,
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 84e83de5457..79556bd9b60 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -60,14 +60,14 @@ static DEFINE_MUTEX(mtrr_mutex);
 u64 size_or_mask, size_and_mask;
 static bool mtrr_aps_delayed_init;
 
-static struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM];
+static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM];
 
-struct mtrr_ops *mtrr_if;
+const struct mtrr_ops *mtrr_if;
 
 static void set_mtrr(unsigned int reg, unsigned long base,
 		     unsigned long size, mtrr_type type);
 
-void set_mtrr_ops(struct mtrr_ops *ops)
+void set_mtrr_ops(const struct mtrr_ops *ops)
 {
 	if (ops->vendor && ops->vendor < X86_VENDOR_NUM)
 		mtrr_ops[ops->vendor] = ops;
@@ -145,6 +145,7 @@ struct set_mtrr_data {
 
 /**
  * ipi_handler - Synchronisation handler. Executed by "other" CPUs.
+ * @info: pointer to mtrr configuration data
  *
  * Returns nothing.
  */
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index a501dee9a87..df5e41f31a2 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -32,7 +32,7 @@ extern int generic_get_free_region(unsigned long base, unsigned long size,
 extern int generic_validate_add_page(unsigned long base, unsigned long size,
 				     unsigned int type);
 
-extern struct mtrr_ops generic_mtrr_ops;
+extern const struct mtrr_ops generic_mtrr_ops;
 
 extern int positive_have_wrcomb(void);
 
@@ -53,10 +53,10 @@ void fill_mtrr_var_range(unsigned int index,
 		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
 void get_mtrr_state(void);
 
-extern void set_mtrr_ops(struct mtrr_ops *ops);
+extern void set_mtrr_ops(const struct mtrr_ops *ops);
 
 extern u64 size_or_mask, size_and_mask;
-extern struct mtrr_ops *mtrr_if;
+extern const struct mtrr_ops *mtrr_if;
 
 #define is_cpu(vnd)	(mtrr_if && mtrr_if->vendor == X86_VENDOR_##vnd)
 #define use_intel()	(mtrr_if && mtrr_if->use_intel_if == 1)
diff --git a/arch/x86/kernel/cpu/mtrr/state.c b/arch/x86/kernel/cpu/mtrr/state.c
deleted file mode 100644
index dfc80b4e6b0..00000000000
--- a/arch/x86/kernel/cpu/mtrr/state.c
+++ /dev/null
@@ -1,94 +0,0 @@
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/mm.h>
-
-#include <asm/processor-cyrix.h>
-#include <asm/processor-flags.h>
-#include <asm/mtrr.h>
-#include <asm/msr.h>
-
-#include "mtrr.h"
-
-/* Put the processor into a state where MTRRs can be safely set */
-void set_mtrr_prepare_save(struct set_mtrr_context *ctxt)
-{
-	unsigned int cr0;
-
-	/* Disable interrupts locally */
-	local_irq_save(ctxt->flags);
-
-	if (use_intel() || is_cpu(CYRIX)) {
-
-		/* Save value of CR4 and clear Page Global Enable (bit 7) */
-		if (cpu_has_pge) {
-			ctxt->cr4val = read_cr4();
-			write_cr4(ctxt->cr4val & ~X86_CR4_PGE);
-		}
-
-		/*
-		 * Disable and flush caches. Note that wbinvd flushes the TLBs
-		 * as a side-effect
-		 */
-		cr0 = read_cr0() | X86_CR0_CD;
-		wbinvd();
-		write_cr0(cr0);
-		wbinvd();
-
-		if (use_intel()) {
-			/* Save MTRR state */
-			rdmsr(MSR_MTRRdefType, ctxt->deftype_lo, ctxt->deftype_hi);
-		} else {
-			/*
-			 * Cyrix ARRs -
-			 * everything else were excluded at the top
-			 */
-			ctxt->ccr3 = getCx86(CX86_CCR3);
-		}
-	}
-}
-
-void set_mtrr_cache_disable(struct set_mtrr_context *ctxt)
-{
-	if (use_intel()) {
-		/* Disable MTRRs, and set the default type to uncached */
-		mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo & 0xf300UL,
-		      ctxt->deftype_hi);
-	} else {
-		if (is_cpu(CYRIX)) {
-			/* Cyrix ARRs - everything else were excluded at the top */
-			setCx86(CX86_CCR3, (ctxt->ccr3 & 0x0f) | 0x10);
-		}
-	}
-}
-
-/* Restore the processor after a set_mtrr_prepare */
-void set_mtrr_done(struct set_mtrr_context *ctxt)
-{
-	if (use_intel() || is_cpu(CYRIX)) {
-
-		/* Flush caches and TLBs */
-		wbinvd();
-
-		/* Restore MTRRdefType */
-		if (use_intel()) {
-			/* Intel (P6) standard MTRRs */
-			mtrr_wrmsr(MSR_MTRRdefType, ctxt->deftype_lo,
-				   ctxt->deftype_hi);
-		} else {
-			/*
-			 * Cyrix ARRs -
-			 * everything else was excluded at the top
-			 */
-			setCx86(CX86_CCR3, ctxt->ccr3);
-		}
-
-		/* Enable caches */
-		write_cr0(read_cr0() & 0xbfffffff);
-
-		/* Restore value of CR4 */
-		if (cpu_has_pge)
-			write_cr4(ctxt->cr4val);
-	}
-	/* Re-enable interrupts locally (if enabled previously) */
-	local_irq_restore(ctxt->flags);
-}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8c1c07073cc..b1fbdeecf6c 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -7,6 +7,7 @@
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
  *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
+ *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
  *  For licencing details see kernel-base/COPYING
  */
@@ -22,6 +23,7 @@
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
 #include <linux/cpu.h>
+#include <linux/bitops.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -68,26 +70,59 @@ struct debug_store {
 	u64	pebs_event_reset[MAX_PEBS_EVENTS];
 };
 
+struct event_constraint {
+	union {
+		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+		u64		idxmsk64[1];
+	};
+	int	code;
+	int	cmask;
+	int	weight;
+};
+
+struct amd_nb {
+	int nb_id;  /* NorthBridge id */
+	int refcnt; /* reference count */
+	struct perf_event *owners[X86_PMC_IDX_MAX];
+	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
+};
+
 struct cpu_hw_events {
-	struct perf_event	*events[X86_PMC_IDX_MAX];
-	unsigned long		used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	unsigned long		interrupts;
 	int			enabled;
 	struct debug_store	*ds;
-};
 
-struct event_constraint {
-	unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
-	int		code;
+	int			n_events;
+	int			n_added;
+	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
+	u64			tags[X86_PMC_IDX_MAX];
+	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+	struct amd_nb		*amd_nb;
 };
 
-#define EVENT_CONSTRAINT(c, m) { .code = (c), .idxmsk[0] = (m) }
-#define EVENT_CONSTRAINT_END  { .code = 0, .idxmsk[0] = 0 }
+#define __EVENT_CONSTRAINT(c, n, m, w) {\
+	{ .idxmsk64[0] = (n) },		\
+	.code = (c),			\
+	.cmask = (m),			\
+	.weight = (w),			\
+}
+
+#define EVENT_CONSTRAINT(c, n, m)	\
+	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
 
-#define for_each_event_constraint(e, c) \
-	for ((e) = (c); (e)->idxmsk[0]; (e)++)
+#define INTEL_EVENT_CONSTRAINT(c, n)	\
+	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
 
+#define FIXED_EVENT_CONSTRAINT(c, n)	\
+	EVENT_CONSTRAINT(c, n, INTEL_ARCH_FIXED_MASK)
+
+#define EVENT_CONSTRAINT_END		\
+	EVENT_CONSTRAINT(0, 0, 0)
+
+#define for_each_event_constraint(e, c)	\
+	for ((e) = (c); (e)->cmask; (e)++)
 
 /*
  * struct x86_pmu - generic x86 pmu
@@ -114,8 +149,14 @@ struct x86_pmu {
 	u64		intel_ctrl;
 	void		(*enable_bts)(u64 config);
 	void		(*disable_bts)(void);
-	int		(*get_event_idx)(struct cpu_hw_events *cpuc,
-					 struct hw_perf_event *hwc);
+
+	struct event_constraint *
+			(*get_event_constraints)(struct cpu_hw_events *cpuc,
+						 struct perf_event *event);
+
+	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
+						 struct perf_event *event);
+	struct event_constraint *event_constraints;
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -124,111 +165,8 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
 };
 
-static const struct event_constraint *event_constraints;
-
-/*
- * Not sure about some of these
- */
-static const u64 p6_perfmon_event_map[] =
-{
-  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0079,
-  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0f2e,
-  [PERF_COUNT_HW_CACHE_MISSES]		= 0x012e,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
-  [PERF_COUNT_HW_BUS_CYCLES]		= 0x0062,
-};
-
-static u64 p6_pmu_event_map(int hw_event)
-{
-	return p6_perfmon_event_map[hw_event];
-}
-
-/*
- * Event setting that is specified not to count anything.
- * We use this to effectively disable a counter.
- *
- * L2_RQSTS with 0 MESI unit mask.
- */
-#define P6_NOP_EVENT			0x0000002EULL
-
-static u64 p6_pmu_raw_event(u64 hw_event)
-{
-#define P6_EVNTSEL_EVENT_MASK		0x000000FFULL
-#define P6_EVNTSEL_UNIT_MASK		0x0000FF00ULL
-#define P6_EVNTSEL_EDGE_MASK		0x00040000ULL
-#define P6_EVNTSEL_INV_MASK		0x00800000ULL
-#define P6_EVNTSEL_REG_MASK		0xFF000000ULL
-
-#define P6_EVNTSEL_MASK			\
-	(P6_EVNTSEL_EVENT_MASK |	\
-	 P6_EVNTSEL_UNIT_MASK  |	\
-	 P6_EVNTSEL_EDGE_MASK  |	\
-	 P6_EVNTSEL_INV_MASK   |	\
-	 P6_EVNTSEL_REG_MASK)
-
-	return hw_event & P6_EVNTSEL_MASK;
-}
-
-static const struct event_constraint intel_p6_event_constraints[] =
-{
-	EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
-	EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
-	EVENT_CONSTRAINT(0x11, 0x1),	/* FP_ASSIST */
-	EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
-	EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
-	EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
-	EVENT_CONSTRAINT_END
-};
-
-/*
- * Intel PerfMon v3. Used on Core2 and later.
- */
-static const u64 intel_perfmon_event_map[] =
-{
-  [PERF_COUNT_HW_CPU_CYCLES]		= 0x003c,
-  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x4f2e,
-  [PERF_COUNT_HW_CACHE_MISSES]		= 0x412e,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
-  [PERF_COUNT_HW_BUS_CYCLES]		= 0x013c,
-};
-
-static const struct event_constraint intel_core_event_constraints[] =
-{
-	EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
-	EVENT_CONSTRAINT(0x11, 0x2),	/* FP_ASSIST */
-	EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
-	EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
-	EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
-	EVENT_CONSTRAINT(0x18, 0x1),	/* IDLE_DURING_DIV */
-	EVENT_CONSTRAINT(0x19, 0x2),	/* DELAYED_BYPASS */
-	EVENT_CONSTRAINT(0xa1, 0x1),	/* RS_UOPS_DISPATCH_CYCLES */
-	EVENT_CONSTRAINT(0xcb, 0x1),	/* MEM_LOAD_RETIRED */
-	EVENT_CONSTRAINT_END
-};
-
-static const struct event_constraint intel_nehalem_event_constraints[] =
-{
-	EVENT_CONSTRAINT(0x40, 0x3),	/* L1D_CACHE_LD */
-	EVENT_CONSTRAINT(0x41, 0x3),	/* L1D_CACHE_ST */
-	EVENT_CONSTRAINT(0x42, 0x3),	/* L1D_CACHE_LOCK */
-	EVENT_CONSTRAINT(0x43, 0x3),	/* L1D_ALL_REF */
-	EVENT_CONSTRAINT(0x4e, 0x3),	/* L1D_PREFETCH */
-	EVENT_CONSTRAINT(0x4c, 0x3),	/* LOAD_HIT_PRE */
-	EVENT_CONSTRAINT(0x51, 0x3),	/* L1D */
-	EVENT_CONSTRAINT(0x52, 0x3),	/* L1D_CACHE_PREFETCH_LOCK_FB_HIT */
-	EVENT_CONSTRAINT(0x53, 0x3),	/* L1D_CACHE_LOCK_FB_HIT */
-	EVENT_CONSTRAINT(0xc5, 0x3),	/* CACHE_LOCK_CYCLES */
-	EVENT_CONSTRAINT_END
-};
-
-static u64 intel_pmu_event_map(int hw_event)
-{
-	return intel_perfmon_event_map[hw_event];
-}
+static int x86_perf_event_set_period(struct perf_event *event,
+			     struct hw_perf_event *hwc, int idx);
 
 /*
  * Generalized hw caching related hw_event table, filled
@@ -245,424 +183,6 @@ static u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX];
 
-static __initconst u64 nehalem_hw_cache_event_ids
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
-		[ C(RESULT_MISS)   ] = 0x024e, /* L1D_PREFETCH.MISS            */
-	},
- },
- [ C(L1I ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                    */
-		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                   */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
-		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
-		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
-		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
-	},
- },
- [ C(DTLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI   (alias)  */
-		[ C(RESULT_MISS)   ] = 0x0108, /* DTLB_LOAD_MISSES.ANY         */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI   (alias)  */
-		[ C(RESULT_MISS)   ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS  */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(ITLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P           */
-		[ C(RESULT_MISS)   ] = 0x20c8, /* ITLB_MISS_RETIRED            */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
- [ C(BPU ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
-		[ C(RESULT_MISS)   ] = 0x03e8, /* BPU_CLEARS.ANY               */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
-};
-
-static __initconst u64 core2_hw_cache_event_ids
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI          */
-		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE       */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI          */
-		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE       */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS      */
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(L1I ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS                  */
-		[ C(RESULT_MISS)   ] = 0x0081, /* L1I.MISSES                 */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
-		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
-		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(DTLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI  (alias) */
-		[ C(RESULT_MISS)   ] = 0x0208, /* DTLB_MISSES.MISS_LD        */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI  (alias) */
-		[ C(RESULT_MISS)   ] = 0x0808, /* DTLB_MISSES.MISS_ST        */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(ITLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
-		[ C(RESULT_MISS)   ] = 0x1282, /* ITLBMISSES                 */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
- [ C(BPU ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
-		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
-};
-
-static __initconst u64 atom_hw_cache_event_ids
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD               */
-		[ C(RESULT_MISS)   ] = 0,
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST               */
-		[ C(RESULT_MISS)   ] = 0,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(L1I ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                  */
-		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                 */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
-		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
-		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(DTLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI  (alias) */
-		[ C(RESULT_MISS)   ] = 0x0508, /* DTLB_MISSES.MISS_LD        */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI  (alias) */
-		[ C(RESULT_MISS)   ] = 0x0608, /* DTLB_MISSES.MISS_ST        */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(ITLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
-		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES                */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
- [ C(BPU ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
-		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
-};
-
-static u64 intel_pmu_raw_event(u64 hw_event)
-{
-#define CORE_EVNTSEL_EVENT_MASK		0x000000FFULL
-#define CORE_EVNTSEL_UNIT_MASK		0x0000FF00ULL
-#define CORE_EVNTSEL_EDGE_MASK		0x00040000ULL
-#define CORE_EVNTSEL_INV_MASK		0x00800000ULL
-#define CORE_EVNTSEL_REG_MASK		0xFF000000ULL
-
-#define CORE_EVNTSEL_MASK		\
-	(CORE_EVNTSEL_EVENT_MASK |	\
-	 CORE_EVNTSEL_UNIT_MASK  |	\
-	 CORE_EVNTSEL_EDGE_MASK  |	\
-	 CORE_EVNTSEL_INV_MASK  |	\
-	 CORE_EVNTSEL_REG_MASK)
-
-	return hw_event & CORE_EVNTSEL_MASK;
-}
-
-static __initconst u64 amd_hw_cache_event_ids
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
-		[ C(RESULT_MISS)   ] = 0,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts  */
-		[ C(RESULT_MISS)   ] = 0x0167, /* Data Prefetcher :cancelled */
-	},
- },
- [ C(L1I ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches  */
-		[ C(RESULT_MISS)   ] = 0x0081, /* Instruction cache misses   */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */
-		[ C(RESULT_MISS)   ] = 0x037E, /* L2 Cache Misses : IC+DC     */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback           */
-		[ C(RESULT_MISS)   ] = 0,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(DTLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0046, /* L1 DTLB and L2 DLTB Miss   */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
-	},
- },
- [ C(ITLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes        */
-		[ C(RESULT_MISS)   ] = 0x0085, /* Instr. fetch ITLB misses   */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
- [ C(BPU ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr.      */
-		[ C(RESULT_MISS)   ] = 0x00c3, /* Retired Mispredicted BI    */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
-};
-
-/*
- * AMD Performance Monitor K7 and later.
- */
-static const u64 amd_perfmon_event_map[] =
-{
-  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
-  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0080,
-  [PERF_COUNT_HW_CACHE_MISSES]		= 0x0081,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
-};
-
-static u64 amd_pmu_event_map(int hw_event)
-{
-	return amd_perfmon_event_map[hw_event];
-}
-
-static u64 amd_pmu_raw_event(u64 hw_event)
-{
-#define K7_EVNTSEL_EVENT_MASK	0x7000000FFULL
-#define K7_EVNTSEL_UNIT_MASK	0x00000FF00ULL
-#define K7_EVNTSEL_EDGE_MASK	0x000040000ULL
-#define K7_EVNTSEL_INV_MASK	0x000800000ULL
-#define K7_EVNTSEL_REG_MASK	0x0FF000000ULL
-
-#define K7_EVNTSEL_MASK			\
-	(K7_EVNTSEL_EVENT_MASK |	\
-	 K7_EVNTSEL_UNIT_MASK  |	\
-	 K7_EVNTSEL_EDGE_MASK  |	\
-	 K7_EVNTSEL_INV_MASK   |	\
-	 K7_EVNTSEL_REG_MASK)
-
-	return hw_event & K7_EVNTSEL_MASK;
-}
-
 /*
  * Propagate event elapsed time into the generic event.
  * Can only be executed on the CPU where the event is active.
@@ -914,42 +434,6 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
 	return 0;
 }
 
-static void intel_pmu_enable_bts(u64 config)
-{
-	unsigned long debugctlmsr;
-
-	debugctlmsr = get_debugctlmsr();
-
-	debugctlmsr |= X86_DEBUGCTL_TR;
-	debugctlmsr |= X86_DEBUGCTL_BTS;
-	debugctlmsr |= X86_DEBUGCTL_BTINT;
-
-	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
-		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
-
-	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
-		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
-
-	update_debugctlmsr(debugctlmsr);
-}
-
-static void intel_pmu_disable_bts(void)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	unsigned long debugctlmsr;
-
-	if (!cpuc->ds)
-		return;
-
-	debugctlmsr = get_debugctlmsr();
-
-	debugctlmsr &=
-		~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
-		  X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
-
-	update_debugctlmsr(debugctlmsr);
-}
-
 /*
  * Setup the hardware configuration for a given attr_type
  */
@@ -988,6 +472,8 @@ static int __hw_perf_event_init(struct perf_event *event)
 	hwc->config = ARCH_PERFMON_EVENTSEL_INT;
 
 	hwc->idx = -1;
+	hwc->last_cpu = -1;
+	hwc->last_tag = ~0ULL;
 
 	/*
 	 * Count user and OS events unless requested not to.
@@ -1056,216 +542,323 @@ static int __hw_perf_event_init(struct perf_event *event)
 	return 0;
 }
 
-static void p6_pmu_disable_all(void)
+static void x86_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	u64 val;
-
-	if (!cpuc->enabled)
-		return;
+	int idx;
 
-	cpuc->enabled = 0;
-	barrier();
+	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+		u64 val;
 
-	/* p6 only has one enable register */
-	rdmsrl(MSR_P6_EVNTSEL0, val);
-	val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
-	wrmsrl(MSR_P6_EVNTSEL0, val);
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+		rdmsrl(x86_pmu.eventsel + idx, val);
+		if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
+			continue;
+		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+		wrmsrl(x86_pmu.eventsel + idx, val);
+	}
 }
 
-static void intel_pmu_disable_all(void)
+void hw_perf_disable(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	if (!x86_pmu_initialized())
+		return;
+
 	if (!cpuc->enabled)
 		return;
 
+	cpuc->n_added = 0;
 	cpuc->enabled = 0;
 	barrier();
 
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
-
-	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
-		intel_pmu_disable_bts();
+	x86_pmu.disable_all();
 }
 
-static void amd_pmu_disable_all(void)
+static void x86_pmu_enable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx;
 
-	if (!cpuc->enabled)
-		return;
-
-	cpuc->enabled = 0;
-	/*
-	 * ensure we write the disable before we start disabling the
-	 * events proper, so that amd_pmu_enable_event() does the
-	 * right thing.
-	 */
-	barrier();
-
 	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+		struct perf_event *event = cpuc->events[idx];
 		u64 val;
 
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
-		rdmsrl(MSR_K7_EVNTSEL0 + idx, val);
-		if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
-			continue;
-		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
-		wrmsrl(MSR_K7_EVNTSEL0 + idx, val);
+
+		val = event->hw.config;
+		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+		wrmsrl(x86_pmu.eventsel + idx, val);
 	}
 }
 
-void hw_perf_disable(void)
+static const struct pmu pmu;
+
+static inline int is_x86_event(struct perf_event *event)
 {
-	if (!x86_pmu_initialized())
-		return;
-	return x86_pmu.disable_all();
+	return event->pmu == &pmu;
 }
 
-static void p6_pmu_enable_all(void)
+static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	unsigned long val;
+	struct event_constraint *c, *constraints[X86_PMC_IDX_MAX];
+	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	int i, j, w, wmax, num = 0;
+	struct hw_perf_event *hwc;
 
-	if (cpuc->enabled)
-		return;
+	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 
-	cpuc->enabled = 1;
-	barrier();
+	for (i = 0; i < n; i++) {
+		constraints[i] =
+		  x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+	}
 
-	/* p6 only has one enable register */
-	rdmsrl(MSR_P6_EVNTSEL0, val);
-	val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-	wrmsrl(MSR_P6_EVNTSEL0, val);
-}
+	/*
+	 * fastpath, try to reuse previous register
+	 */
+	for (i = 0; i < n; i++) {
+		hwc = &cpuc->event_list[i]->hw;
+		c = constraints[i];
 
-static void intel_pmu_enable_all(void)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+		/* never assigned */
+		if (hwc->idx == -1)
+			break;
 
-	if (cpuc->enabled)
-		return;
+		/* constraint still honored */
+		if (!test_bit(hwc->idx, c->idxmsk))
+			break;
 
-	cpuc->enabled = 1;
-	barrier();
+		/* not already used */
+		if (test_bit(hwc->idx, used_mask))
+			break;
+
+		set_bit(hwc->idx, used_mask);
+		if (assign)
+			assign[i] = hwc->idx;
+	}
+	if (i == n)
+		goto done;
+
+	/*
+	 * begin slow path
+	 */
+
+	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+
+	/*
+	 * weight = number of possible counters
+	 *
+	 * 1    = most constrained, only works on one counter
+	 * wmax = least constrained, works on any counter
+	 *
+	 * assign events to counters starting with most
+	 * constrained events.
+	 */
+	wmax = x86_pmu.num_events;
+
+	/*
+	 * when fixed event counters are present,
+	 * wmax is incremented by 1 to account
+	 * for one more choice
+	 */
+	if (x86_pmu.num_events_fixed)
+		wmax++;
 
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+	for (w = 1, num = n; num && w <= wmax; w++) {
+		/* for each event */
+		for (i = 0; num && i < n; i++) {
+			c = constraints[i];
+			hwc = &cpuc->event_list[i]->hw;
 
-	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
-		struct perf_event *event =
-			cpuc->events[X86_PMC_IDX_FIXED_BTS];
+			if (c->weight != w)
+				continue;
 
-		if (WARN_ON_ONCE(!event))
-			return;
+			for_each_set_bit(j, c->idxmsk, X86_PMC_IDX_MAX) {
+				if (!test_bit(j, used_mask))
+					break;
+			}
+
+			if (j == X86_PMC_IDX_MAX)
+				break;
+
+			set_bit(j, used_mask);
 
-		intel_pmu_enable_bts(event->hw.config);
+			if (assign)
+				assign[i] = j;
+			num--;
+		}
+	}
+done:
+	/*
+	 * scheduling failed or is just a simulation,
+	 * free resources if necessary
+	 */
+	if (!assign || num) {
+		for (i = 0; i < n; i++) {
+			if (x86_pmu.put_event_constraints)
+				x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
+		}
 	}
+	return num ? -ENOSPC : 0;
 }
 
-static void amd_pmu_enable_all(void)
+/*
+ * dogrp: true if must collect siblings events (group)
+ * returns total number of events and error code
+ */
+static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	int idx;
+	struct perf_event *event;
+	int n, max_count;
 
-	if (cpuc->enabled)
-		return;
+	max_count = x86_pmu.num_events + x86_pmu.num_events_fixed;
 
-	cpuc->enabled = 1;
-	barrier();
+	/* current number of events already accepted */
+	n = cpuc->n_events;
 
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
-		struct perf_event *event = cpuc->events[idx];
-		u64 val;
+	if (is_x86_event(leader)) {
+		if (n >= max_count)
+			return -ENOSPC;
+		cpuc->event_list[n] = leader;
+		n++;
+	}
+	if (!dogrp)
+		return n;
 
-		if (!test_bit(idx, cpuc->active_mask))
+	list_for_each_entry(event, &leader->sibling_list, group_entry) {
+		if (!is_x86_event(event) ||
+		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 
-		val = event->hw.config;
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-		wrmsrl(MSR_K7_EVNTSEL0 + idx, val);
-	}
-}
+		if (n >= max_count)
+			return -ENOSPC;
 
-void hw_perf_enable(void)
-{
-	if (!x86_pmu_initialized())
-		return;
-	x86_pmu.enable_all();
+		cpuc->event_list[n] = event;
+		n++;
+	}
+	return n;
 }
 
-static inline u64 intel_pmu_get_status(void)
+static inline void x86_assign_hw_event(struct perf_event *event,
+				struct cpu_hw_events *cpuc, int i)
 {
-	u64 status;
+	struct hw_perf_event *hwc = &event->hw;
 
-	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+	hwc->idx = cpuc->assign[i];
+	hwc->last_cpu = smp_processor_id();
+	hwc->last_tag = ++cpuc->tags[i];
 
-	return status;
+	if (hwc->idx == X86_PMC_IDX_FIXED_BTS) {
+		hwc->config_base = 0;
+		hwc->event_base	= 0;
+	} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
+		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+		/*
+		 * We set it so that event_base + idx in wrmsr/rdmsr maps to
+		 * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
+		 */
+		hwc->event_base =
+			MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
+	} else {
+		hwc->config_base = x86_pmu.eventsel;
+		hwc->event_base  = x86_pmu.perfctr;
+	}
 }
 
-static inline void intel_pmu_ack_status(u64 ack)
+static inline int match_prev_assignment(struct hw_perf_event *hwc,
+					struct cpu_hw_events *cpuc,
+					int i)
 {
-	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+	return hwc->idx == cpuc->assign[i] &&
+		hwc->last_cpu == smp_processor_id() &&
+		hwc->last_tag == cpuc->tags[i];
 }
 
-static inline void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
-	(void)checking_wrmsrl(hwc->config_base + idx,
-			      hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
-}
+static void x86_pmu_stop(struct perf_event *event);
 
-static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+void hw_perf_enable(void)
 {
-	(void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
-}
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct perf_event *event;
+	struct hw_perf_event *hwc;
+	int i;
 
-static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
-{
-	int idx = __idx - X86_PMC_IDX_FIXED;
-	u64 ctrl_val, mask;
+	if (!x86_pmu_initialized())
+		return;
 
-	mask = 0xfULL << (idx * 4);
+	if (cpuc->enabled)
+		return;
 
-	rdmsrl(hwc->config_base, ctrl_val);
-	ctrl_val &= ~mask;
-	(void)checking_wrmsrl(hwc->config_base, ctrl_val);
-}
+	if (cpuc->n_added) {
+		/*
+		 * apply assignment obtained either from
+		 * hw_perf_group_sched_in() or x86_pmu_enable()
+		 *
+		 * step1: save events moving to new counters
+		 * step2: reprogram moved events into new counters
+		 */
+		for (i = 0; i < cpuc->n_events; i++) {
 
-static inline void
-p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	u64 val = P6_NOP_EVENT;
+			event = cpuc->event_list[i];
+			hwc = &event->hw;
 
-	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+			/*
+			 * we can avoid reprogramming counter if:
+			 * - assigned same counter as last time
+			 * - running on same CPU as last time
+			 * - no other event has used the counter since
+			 */
+			if (hwc->idx == -1 ||
+			    match_prev_assignment(hwc, cpuc, i))
+				continue;
 
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
-}
+			x86_pmu_stop(event);
 
-static inline void
-intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
-{
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
-		intel_pmu_disable_bts();
-		return;
-	}
+			hwc->idx = -1;
+		}
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_disable_fixed(hwc, idx);
-		return;
+		for (i = 0; i < cpuc->n_events; i++) {
+
+			event = cpuc->event_list[i];
+			hwc = &event->hw;
+
+			if (hwc->idx == -1) {
+				x86_assign_hw_event(event, cpuc, i);
+				x86_perf_event_set_period(event, hwc, hwc->idx);
+			}
+			/*
+			 * need to mark as active because x86_pmu_disable()
+			 * clear active_mask and events[] yet it preserves
+			 * idx
+			 */
+			set_bit(hwc->idx, cpuc->active_mask);
+			cpuc->events[hwc->idx] = event;
+
+			x86_pmu.enable(hwc, hwc->idx);
+			perf_event_update_userpage(event);
+		}
+		cpuc->n_added = 0;
+		perf_events_lapic_init();
 	}
 
-	x86_pmu_disable_event(hwc, idx);
+	cpuc->enabled = 1;
+	barrier();
+
+	x86_pmu.enable_all();
+}
+
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+	(void)checking_wrmsrl(hwc->config_base + idx,
+			      hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
 }
 
-static inline void
-amd_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
 {
-	x86_pmu_disable_event(hwc, idx);
+	(void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
 }
 
 static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -1326,220 +919,60 @@ x86_perf_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
-{
-	int idx = __idx - X86_PMC_IDX_FIXED;
-	u64 ctrl_val, bits, mask;
-	int err;
-
-	/*
-	 * Enable IRQ generation (0x8),
-	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
-	 * if requested:
-	 */
-	bits = 0x8ULL;
-	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
-		bits |= 0x2;
-	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
-		bits |= 0x1;
-
-	/*
-	 * ANY bit is supported in v3 and up
-	 */
-	if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
-		bits |= 0x4;
-
-	bits <<= (idx * 4);
-	mask = 0xfULL << (idx * 4);
-
-	rdmsrl(hwc->config_base, ctrl_val);
-	ctrl_val &= ~mask;
-	ctrl_val |= bits;
-	err = checking_wrmsrl(hwc->config_base, ctrl_val);
-}
-
-static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	u64 val;
-
-	val = hwc->config;
 	if (cpuc->enabled)
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
+		__x86_pmu_enable_event(hwc, idx);
 }
 
-
-static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
-{
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
-		if (!__get_cpu_var(cpu_hw_events).enabled)
-			return;
-
-		intel_pmu_enable_bts(hwc->config);
-		return;
-	}
-
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc, idx);
-		return;
-	}
-
-	x86_pmu_enable_event(hwc, idx);
-}
-
-static void amd_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+/*
+ * activate a single event
+ *
+ * The event is added to the group of enabled events
+ * but only if it can be scehduled with existing events.
+ *
+ * Called with PMU disabled. If successful and return value 1,
+ * then guaranteed to call perf_enable() and hw_perf_enable()
+ */
+static int x86_pmu_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc;
+	int assign[X86_PMC_IDX_MAX];
+	int n, n0, ret;
 
-	if (cpuc->enabled)
-		x86_pmu_enable_event(hwc, idx);
-}
-
-static int fixed_mode_idx(struct hw_perf_event *hwc)
-{
-	unsigned int hw_event;
-
-	hw_event = hwc->config & ARCH_PERFMON_EVENT_MASK;
-
-	if (unlikely((hw_event ==
-		      x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
-		     (hwc->sample_period == 1)))
-		return X86_PMC_IDX_FIXED_BTS;
+	hwc = &event->hw;
 
-	if (!x86_pmu.num_events_fixed)
-		return -1;
+	n0 = cpuc->n_events;
+	n = collect_events(cpuc, event, false);
+	if (n < 0)
+		return n;
 
+	ret = x86_schedule_events(cpuc, n, assign);
+	if (ret)
+		return ret;
 	/*
-	 * fixed counters do not take all possible filters
+	 * copy new assignment, now we know it is possible
+	 * will be used by hw_perf_enable()
 	 */
-	if (hwc->config & ARCH_PERFMON_EVENT_FILTER_MASK)
-		return -1;
+	memcpy(cpuc->assign, assign, n*sizeof(int));
 
-	if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
-		return X86_PMC_IDX_FIXED_INSTRUCTIONS;
-	if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES)))
-		return X86_PMC_IDX_FIXED_CPU_CYCLES;
-	if (unlikely(hw_event == x86_pmu.event_map(PERF_COUNT_HW_BUS_CYCLES)))
-		return X86_PMC_IDX_FIXED_BUS_CYCLES;
+	cpuc->n_events = n;
+	cpuc->n_added  = n - n0;
 
-	return -1;
-}
-
-/*
- * generic counter allocator: get next free counter
- */
-static int
-gen_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
-{
-	int idx;
-
-	idx = find_first_zero_bit(cpuc->used_mask, x86_pmu.num_events);
-	return idx == x86_pmu.num_events ? -1 : idx;
-}
-
-/*
- * intel-specific counter allocator: check event constraints
- */
-static int
-intel_get_event_idx(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
-{
-	const struct event_constraint *event_constraint;
-	int i, code;
-
-	if (!event_constraints)
-		goto skip;
-
-	code = hwc->config & CORE_EVNTSEL_EVENT_MASK;
-
-	for_each_event_constraint(event_constraint, event_constraints) {
-		if (code == event_constraint->code) {
-			for_each_bit(i, event_constraint->idxmsk, X86_PMC_IDX_MAX) {
-				if (!test_and_set_bit(i, cpuc->used_mask))
-					return i;
-			}
-			return -1;
-		}
-	}
-skip:
-	return gen_get_event_idx(cpuc, hwc);
-}
-
-static int
-x86_schedule_event(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
-{
-	int idx;
-
-	idx = fixed_mode_idx(hwc);
-	if (idx == X86_PMC_IDX_FIXED_BTS) {
-		/* BTS is already occupied. */
-		if (test_and_set_bit(idx, cpuc->used_mask))
-			return -EAGAIN;
-
-		hwc->config_base	= 0;
-		hwc->event_base		= 0;
-		hwc->idx		= idx;
-	} else if (idx >= 0) {
-		/*
-		 * Try to get the fixed event, if that is already taken
-		 * then try to get a generic event:
-		 */
-		if (test_and_set_bit(idx, cpuc->used_mask))
-			goto try_generic;
-
-		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		/*
-		 * We set it so that event_base + idx in wrmsr/rdmsr maps to
-		 * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
-		 */
-		hwc->event_base =
-			MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
-		hwc->idx = idx;
-	} else {
-		idx = hwc->idx;
-		/* Try to get the previous generic event again */
-		if (idx == -1 || test_and_set_bit(idx, cpuc->used_mask)) {
-try_generic:
-			idx = x86_pmu.get_event_idx(cpuc, hwc);
-			if (idx == -1)
-				return -EAGAIN;
-
-			set_bit(idx, cpuc->used_mask);
-			hwc->idx = idx;
-		}
-		hwc->config_base = x86_pmu.eventsel;
-		hwc->event_base  = x86_pmu.perfctr;
-	}
-
-	return idx;
+	return 0;
 }
 
-/*
- * Find a PMC slot for the freshly enabled / scheduled in event:
- */
-static int x86_pmu_enable(struct perf_event *event)
+static int x86_pmu_start(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int idx;
-
-	idx = x86_schedule_event(cpuc, hwc);
-	if (idx < 0)
-		return idx;
 
-	perf_events_lapic_init();
-
-	x86_pmu.disable(hwc, idx);
+	if (hwc->idx == -1)
+		return -EAGAIN;
 
-	cpuc->events[idx] = event;
-	set_bit(idx, cpuc->active_mask);
-
-	x86_perf_event_set_period(event, hwc, idx);
-	x86_pmu.enable(hwc, idx);
-
-	perf_event_update_userpage(event);
+	x86_perf_event_set_period(event, hwc, hwc->idx);
+	x86_pmu.enable(hwc, hwc->idx);
 
 	return 0;
 }
@@ -1583,7 +1016,7 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d: overflow:   %016llx\n", cpu, overflow);
 		pr_info("CPU#%d: fixed:      %016llx\n", cpu, fixed);
 	}
-	pr_info("CPU#%d: used:       %016llx\n", cpu, *(u64 *)cpuc->used_mask);
+	pr_info("CPU#%d: active:       %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
 	for (idx = 0; idx < x86_pmu.num_events; idx++) {
 		rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
@@ -1607,67 +1040,7 @@ void perf_event_print_debug(void)
 	local_irq_restore(flags);
 }
 
-static void intel_pmu_drain_bts_buffer(struct cpu_hw_events *cpuc)
-{
-	struct debug_store *ds = cpuc->ds;
-	struct bts_record {
-		u64	from;
-		u64	to;
-		u64	flags;
-	};
-	struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
-	struct bts_record *at, *top;
-	struct perf_output_handle handle;
-	struct perf_event_header header;
-	struct perf_sample_data data;
-	struct pt_regs regs;
-
-	if (!event)
-		return;
-
-	if (!ds)
-		return;
-
-	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
-	top = (struct bts_record *)(unsigned long)ds->bts_index;
-
-	if (top <= at)
-		return;
-
-	ds->bts_index = ds->bts_buffer_base;
-
-
-	data.period	= event->hw.last_period;
-	data.addr	= 0;
-	data.raw	= NULL;
-	regs.ip		= 0;
-
-	/*
-	 * Prepare a generic sample, i.e. fill in the invariant fields.
-	 * We will overwrite the from and to address before we output
-	 * the sample.
-	 */
-	perf_prepare_sample(&header, &data, event, &regs);
-
-	if (perf_output_begin(&handle, event,
-			      header.size * (top - at), 1, 1))
-		return;
-
-	for (; at < top; at++) {
-		data.ip		= at->from;
-		data.addr	= at->to;
-
-		perf_output_sample(&handle, &header, &data, event);
-	}
-
-	perf_output_end(&handle);
-
-	/* There's new data available. */
-	event->hw.interrupts++;
-	event->pending_kill = POLL_IN;
-}
-
-static void x86_pmu_disable(struct perf_event *event)
+static void x86_pmu_stop(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
@@ -1681,183 +1054,38 @@ static void x86_pmu_disable(struct perf_event *event)
 	x86_pmu.disable(hwc, idx);
 
 	/*
-	 * Make sure the cleared pointer becomes visible before we
-	 * (potentially) free the event:
-	 */
-	barrier();
-
-	/*
 	 * Drain the remaining delta count out of a event
 	 * that we are disabling:
 	 */
 	x86_perf_event_update(event, hwc, idx);
 
-	/* Drain the remaining BTS records. */
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS))
-		intel_pmu_drain_bts_buffer(cpuc);
-
 	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
-
-	perf_event_update_userpage(event);
-}
-
-/*
- * Save and restart an expired event. Called by NMI contexts,
- * so it has to be careful about preempting normal event ops:
- */
-static int intel_pmu_save_and_restart(struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-	int ret;
-
-	x86_perf_event_update(event, hwc, idx);
-	ret = x86_perf_event_set_period(event, hwc, idx);
-
-	if (event->state == PERF_EVENT_STATE_ACTIVE)
-		intel_pmu_enable_event(hwc, idx);
-
-	return ret;
 }
 
-static void intel_pmu_reset(void)
-{
-	struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds;
-	unsigned long flags;
-	int idx;
-
-	if (!x86_pmu.num_events)
-		return;
-
-	local_irq_save(flags);
-
-	printk("clearing PMU state on CPU#%d\n", smp_processor_id());
-
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
-		checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
-		checking_wrmsrl(x86_pmu.perfctr  + idx, 0ull);
-	}
-	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
-		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
-	}
-	if (ds)
-		ds->bts_index = ds->bts_buffer_base;
-
-	local_irq_restore(flags);
-}
-
-static int p6_pmu_handle_irq(struct pt_regs *regs)
-{
-	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
-	struct perf_event *event;
-	struct hw_perf_event *hwc;
-	int idx, handled = 0;
-	u64 val;
-
-	data.addr = 0;
-	data.raw = NULL;
-
-	cpuc = &__get_cpu_var(cpu_hw_events);
-
-	for (idx = 0; idx < x86_pmu.num_events; idx++) {
-		if (!test_bit(idx, cpuc->active_mask))
-			continue;
-
-		event = cpuc->events[idx];
-		hwc = &event->hw;
-
-		val = x86_perf_event_update(event, hwc, idx);
-		if (val & (1ULL << (x86_pmu.event_bits - 1)))
-			continue;
-
-		/*
-		 * event overflow
-		 */
-		handled		= 1;
-		data.period	= event->hw.last_period;
-
-		if (!x86_perf_event_set_period(event, hwc, idx))
-			continue;
-
-		if (perf_event_overflow(event, 1, &data, regs))
-			p6_pmu_disable_event(hwc, idx);
-	}
-
-	if (handled)
-		inc_irq_stat(apic_perf_irqs);
-
-	return handled;
-}
-
-/*
- * This handler is triggered by the local APIC, so the APIC IRQ handling
- * rules apply:
- */
-static int intel_pmu_handle_irq(struct pt_regs *regs)
+static void x86_pmu_disable(struct perf_event *event)
 {
-	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc;
-	int bit, loops;
-	u64 ack, status;
-
-	data.addr = 0;
-	data.raw = NULL;
-
-	cpuc = &__get_cpu_var(cpu_hw_events);
-
-	perf_disable();
-	intel_pmu_drain_bts_buffer(cpuc);
-	status = intel_pmu_get_status();
-	if (!status) {
-		perf_enable();
-		return 0;
-	}
-
-	loops = 0;
-again:
-	if (++loops > 100) {
-		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
-		perf_event_print_debug();
-		intel_pmu_reset();
-		perf_enable();
-		return 1;
-	}
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int i;
 
-	inc_irq_stat(apic_perf_irqs);
-	ack = status;
-	for_each_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
-		struct perf_event *event = cpuc->events[bit];
+	x86_pmu_stop(event);
 
-		clear_bit(bit, (unsigned long *) &status);
-		if (!test_bit(bit, cpuc->active_mask))
-			continue;
+	for (i = 0; i < cpuc->n_events; i++) {
+		if (event == cpuc->event_list[i]) {
 
-		if (!intel_pmu_save_and_restart(event))
-			continue;
+			if (x86_pmu.put_event_constraints)
+				x86_pmu.put_event_constraints(cpuc, event);
 
-		data.period = event->hw.last_period;
+			while (++i < cpuc->n_events)
+				cpuc->event_list[i-1] = cpuc->event_list[i];
 
-		if (perf_event_overflow(event, 1, &data, regs))
-			intel_pmu_disable_event(&event->hw, bit);
+			--cpuc->n_events;
+			break;
+		}
 	}
-
-	intel_pmu_ack_status(ack);
-
-	/*
-	 * Repeat if there is more work to be done:
-	 */
-	status = intel_pmu_get_status();
-	if (status)
-		goto again;
-
-	perf_enable();
-
-	return 1;
+	perf_event_update_userpage(event);
 }
 
-static int amd_pmu_handle_irq(struct pt_regs *regs)
+static int x86_pmu_handle_irq(struct pt_regs *regs)
 {
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
@@ -1892,7 +1120,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			amd_pmu_disable_event(hwc, idx);
+			x86_pmu.disable(hwc, idx);
 	}
 
 	if (handled)
@@ -1975,194 +1203,137 @@ static __read_mostly struct notifier_block perf_event_nmi_notifier = {
 	.priority		= 1
 };
 
-static __initconst struct x86_pmu p6_pmu = {
-	.name			= "p6",
-	.handle_irq		= p6_pmu_handle_irq,
-	.disable_all		= p6_pmu_disable_all,
-	.enable_all		= p6_pmu_enable_all,
-	.enable			= p6_pmu_enable_event,
-	.disable		= p6_pmu_disable_event,
-	.eventsel		= MSR_P6_EVNTSEL0,
-	.perfctr		= MSR_P6_PERFCTR0,
-	.event_map		= p6_pmu_event_map,
-	.raw_event		= p6_pmu_raw_event,
-	.max_events		= ARRAY_SIZE(p6_perfmon_event_map),
-	.apic			= 1,
-	.max_period		= (1ULL << 31) - 1,
-	.version		= 0,
-	.num_events		= 2,
-	/*
-	 * Events have 40 bits implemented. However they are designed such
-	 * that bits [32-39] are sign extensions of bit 31. As such the
-	 * effective width of a event for P6-like PMU is 32 bits only.
-	 *
-	 * See IA-32 Intel Architecture Software developer manual Vol 3B
-	 */
-	.event_bits		= 32,
-	.event_mask		= (1ULL << 32) - 1,
-	.get_event_idx		= intel_get_event_idx,
-};
+static struct event_constraint unconstrained;
+static struct event_constraint emptyconstraint;
 
-static __initconst struct x86_pmu intel_pmu = {
-	.name			= "Intel",
-	.handle_irq		= intel_pmu_handle_irq,
-	.disable_all		= intel_pmu_disable_all,
-	.enable_all		= intel_pmu_enable_all,
-	.enable			= intel_pmu_enable_event,
-	.disable		= intel_pmu_disable_event,
-	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
-	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
-	.event_map		= intel_pmu_event_map,
-	.raw_event		= intel_pmu_raw_event,
-	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
-	.apic			= 1,
-	/*
-	 * Intel PMCs cannot be accessed sanely above 32 bit width,
-	 * so we install an artificial 1<<31 period regardless of
-	 * the generic event period:
-	 */
-	.max_period		= (1ULL << 31) - 1,
-	.enable_bts		= intel_pmu_enable_bts,
-	.disable_bts		= intel_pmu_disable_bts,
-	.get_event_idx		= intel_get_event_idx,
-};
+static struct event_constraint *
+x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	struct event_constraint *c;
 
-static __initconst struct x86_pmu amd_pmu = {
-	.name			= "AMD",
-	.handle_irq		= amd_pmu_handle_irq,
-	.disable_all		= amd_pmu_disable_all,
-	.enable_all		= amd_pmu_enable_all,
-	.enable			= amd_pmu_enable_event,
-	.disable		= amd_pmu_disable_event,
-	.eventsel		= MSR_K7_EVNTSEL0,
-	.perfctr		= MSR_K7_PERFCTR0,
-	.event_map		= amd_pmu_event_map,
-	.raw_event		= amd_pmu_raw_event,
-	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_events		= 4,
-	.event_bits		= 48,
-	.event_mask		= (1ULL << 48) - 1,
-	.apic			= 1,
-	/* use highest bit to detect overflow */
-	.max_period		= (1ULL << 47) - 1,
-	.get_event_idx		= gen_get_event_idx,
-};
+	if (x86_pmu.event_constraints) {
+		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			if ((event->hw.config & c->cmask) == c->code)
+				return c;
+		}
+	}
+
+	return &unconstrained;
+}
 
-static __init int p6_pmu_init(void)
+static int x86_event_sched_in(struct perf_event *event,
+			  struct perf_cpu_context *cpuctx)
 {
-	switch (boot_cpu_data.x86_model) {
-	case 1:
-	case 3:  /* Pentium Pro */
-	case 5:
-	case 6:  /* Pentium II */
-	case 7:
-	case 8:
-	case 11: /* Pentium III */
-		event_constraints = intel_p6_event_constraints;
-		break;
-	case 9:
-	case 13:
-		/* Pentium M */
-		event_constraints = intel_p6_event_constraints;
-		break;
-	default:
-		pr_cont("unsupported p6 CPU model %d ",
-			boot_cpu_data.x86_model);
-		return -ENODEV;
-	}
+	int ret = 0;
 
-	x86_pmu = p6_pmu;
+	event->state = PERF_EVENT_STATE_ACTIVE;
+	event->oncpu = smp_processor_id();
+	event->tstamp_running += event->ctx->time - event->tstamp_stopped;
 
-	return 0;
+	if (!is_x86_event(event))
+		ret = event->pmu->enable(event);
+
+	if (!ret && !is_software_event(event))
+		cpuctx->active_oncpu++;
+
+	if (!ret && event->attr.exclusive)
+		cpuctx->exclusive = 1;
+
+	return ret;
 }
 
-static __init int intel_pmu_init(void)
+static void x86_event_sched_out(struct perf_event *event,
+			    struct perf_cpu_context *cpuctx)
 {
-	union cpuid10_edx edx;
-	union cpuid10_eax eax;
-	unsigned int unused;
-	unsigned int ebx;
-	int version;
-
-	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-		/* check for P6 processor family */
-	   if (boot_cpu_data.x86 == 6) {
-		return p6_pmu_init();
-	   } else {
-		return -ENODEV;
-	   }
-	}
+	event->state = PERF_EVENT_STATE_INACTIVE;
+	event->oncpu = -1;
 
-	/*
-	 * Check whether the Architectural PerfMon supports
-	 * Branch Misses Retired hw_event or not.
-	 */
-	cpuid(10, &eax.full, &ebx, &unused, &edx.full);
-	if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
-		return -ENODEV;
+	if (!is_x86_event(event))
+		event->pmu->disable(event);
 
-	version = eax.split.version_id;
-	if (version < 2)
-		return -ENODEV;
+	event->tstamp_running -= event->ctx->time - event->tstamp_stopped;
 
-	x86_pmu				= intel_pmu;
-	x86_pmu.version			= version;
-	x86_pmu.num_events		= eax.split.num_events;
-	x86_pmu.event_bits		= eax.split.bit_width;
-	x86_pmu.event_mask		= (1ULL << eax.split.bit_width) - 1;
+	if (!is_software_event(event))
+		cpuctx->active_oncpu--;
 
-	/*
-	 * Quirk: v2 perfmon does not report fixed-purpose events, so
-	 * assume at least 3 events:
-	 */
-	x86_pmu.num_events_fixed	= max((int)edx.split.num_events_fixed, 3);
+	if (event->attr.exclusive || !cpuctx->active_oncpu)
+		cpuctx->exclusive = 0;
+}
 
+/*
+ * Called to enable a whole group of events.
+ * Returns 1 if the group was enabled, or -EAGAIN if it could not be.
+ * Assumes the caller has disabled interrupts and has
+ * frozen the PMU with hw_perf_save_disable.
+ *
+ * called with PMU disabled. If successful and return value 1,
+ * then guaranteed to call perf_enable() and hw_perf_enable()
+ */
+int hw_perf_group_sched_in(struct perf_event *leader,
+	       struct perf_cpu_context *cpuctx,
+	       struct perf_event_context *ctx)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct perf_event *sub;
+	int assign[X86_PMC_IDX_MAX];
+	int n0, n1, ret;
+
+	/* n0 = total number of events */
+	n0 = collect_events(cpuc, leader, true);
+	if (n0 < 0)
+		return n0;
+
+	ret = x86_schedule_events(cpuc, n0, assign);
+	if (ret)
+		return ret;
+
+	ret = x86_event_sched_in(leader, cpuctx);
+	if (ret)
+		return ret;
+
+	n1 = 1;
+	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
+		if (sub->state > PERF_EVENT_STATE_OFF) {
+			ret = x86_event_sched_in(sub, cpuctx);
+			if (ret)
+				goto undo;
+			++n1;
+		}
+	}
 	/*
-	 * Install the hw-cache-events table:
+	 * copy new assignment, now we know it is possible
+	 * will be used by hw_perf_enable()
 	 */
-	switch (boot_cpu_data.x86_model) {
-	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
-	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
-	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
-	case 29: /* six-core 45 nm xeon "Dunnington" */
-		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
-		       sizeof(hw_cache_event_ids));
-
-		pr_cont("Core2 events, ");
-		event_constraints = intel_core_event_constraints;
-		break;
-	default:
-	case 26:
-		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
-		       sizeof(hw_cache_event_ids));
+	memcpy(cpuc->assign, assign, n0*sizeof(int));
 
-		event_constraints = intel_nehalem_event_constraints;
-		pr_cont("Nehalem/Corei7 events, ");
-		break;
-	case 28:
-		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
-		       sizeof(hw_cache_event_ids));
+	cpuc->n_events  = n0;
+	cpuc->n_added   = n1;
+	ctx->nr_active += n1;
 
-		pr_cont("Atom events, ");
-		break;
+	/*
+	 * 1 means successful and events are active
+	 * This is not quite true because we defer
+	 * actual activation until hw_perf_enable() but
+	 * this way we* ensure caller won't try to enable
+	 * individual events
+	 */
+	return 1;
+undo:
+	x86_event_sched_out(leader, cpuctx);
+	n0  = 1;
+	list_for_each_entry(sub, &leader->sibling_list, group_entry) {
+		if (sub->state == PERF_EVENT_STATE_ACTIVE) {
+			x86_event_sched_out(sub, cpuctx);
+			if (++n0 == n1)
+				break;
+		}
 	}
-	return 0;
+	return ret;
 }
 
-static __init int amd_pmu_init(void)
-{
-	/* Performance-monitoring supported from K7 and later: */
-	if (boot_cpu_data.x86 < 6)
-		return -ENODEV;
-
-	x86_pmu = amd_pmu;
-
-	/* Events are common for all AMDs */
-	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
-	       sizeof(hw_cache_event_ids));
-
-	return 0;
-}
+#include "perf_event_amd.c"
+#include "perf_event_p6.c"
+#include "perf_event_intel.c"
 
 static void __init pmu_check_apic(void)
 {
@@ -2220,6 +1391,10 @@ void __init init_hw_perf_events(void)
 	perf_events_lapic_init();
 	register_die_notifier(&perf_event_nmi_notifier);
 
+	unconstrained = (struct event_constraint)
+		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
+				   0, x86_pmu.num_events);
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.event_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_events);
@@ -2237,50 +1412,79 @@ static inline void x86_pmu_read(struct perf_event *event)
 static const struct pmu pmu = {
 	.enable		= x86_pmu_enable,
 	.disable	= x86_pmu_disable,
+	.start		= x86_pmu_start,
+	.stop		= x86_pmu_stop,
 	.read		= x86_pmu_read,
 	.unthrottle	= x86_pmu_unthrottle,
 };
 
-static int
-validate_event(struct cpu_hw_events *cpuc, struct perf_event *event)
-{
-	struct hw_perf_event fake_event = event->hw;
-
-	if (event->pmu && event->pmu != &pmu)
-		return 0;
-
-	return x86_schedule_event(cpuc, &fake_event) >= 0;
-}
-
+/*
+ * validate a single event group
+ *
+ * validation include:
+ *	- check events are compatible which each other
+ *	- events do not compete for the same counter
+ *	- number of events <= number of counters
+ *
+ * validation ensures the group can be loaded onto the
+ * PMU if it was the only group available.
+ */
 static int validate_group(struct perf_event *event)
 {
-	struct perf_event *sibling, *leader = event->group_leader;
-	struct cpu_hw_events fake_pmu;
+	struct perf_event *leader = event->group_leader;
+	struct cpu_hw_events *fake_cpuc;
+	int ret, n;
 
-	memset(&fake_pmu, 0, sizeof(fake_pmu));
+	ret = -ENOMEM;
+	fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO);
+	if (!fake_cpuc)
+		goto out;
+
+	/*
+	 * the event is not yet connected with its
+	 * siblings therefore we must first collect
+	 * existing siblings, then add the new event
+	 * before we can simulate the scheduling
+	 */
+	ret = -ENOSPC;
+	n = collect_events(fake_cpuc, leader, true);
+	if (n < 0)
+		goto out_free;
 
-	if (!validate_event(&fake_pmu, leader))
-		return -ENOSPC;
+	fake_cpuc->n_events = n;
+	n = collect_events(fake_cpuc, event, false);
+	if (n < 0)
+		goto out_free;
 
-	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
-		if (!validate_event(&fake_pmu, sibling))
-			return -ENOSPC;
-	}
+	fake_cpuc->n_events = n;
 
-	if (!validate_event(&fake_pmu, event))
-		return -ENOSPC;
+	ret = x86_schedule_events(fake_cpuc, n, NULL);
 
-	return 0;
+out_free:
+	kfree(fake_cpuc);
+out:
+	return ret;
 }
 
 const struct pmu *hw_perf_event_init(struct perf_event *event)
 {
+	const struct pmu *tmp;
 	int err;
 
 	err = __hw_perf_event_init(event);
 	if (!err) {
+		/*
+		 * we temporarily connect event to its pmu
+		 * such that validate_group() can classify
+		 * it as an x86 event using is_x86_event()
+		 */
+		tmp = event->pmu;
+		event->pmu = &pmu;
+
 		if (event->group_leader != event)
 			err = validate_group(event);
+
+		event->pmu = tmp;
 	}
 	if (err) {
 		if (event->destroy)
@@ -2304,7 +1508,6 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 
 static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
 static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
-static DEFINE_PER_CPU(int, in_ignored_frame);
 
 
 static void
@@ -2320,10 +1523,6 @@ static void backtrace_warning(void *data, char *msg)
 
 static int backtrace_stack(void *data, char *name)
 {
-	per_cpu(in_ignored_frame, smp_processor_id()) =
-			x86_is_stack_id(NMI_STACK, name) ||
-			x86_is_stack_id(DEBUG_STACK, name);
-
 	return 0;
 }
 
@@ -2331,9 +1530,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry *entry = data;
 
-	if (per_cpu(in_ignored_frame, smp_processor_id()))
-		return;
-
 	if (reliable)
 		callchain_store(entry, addr);
 }
@@ -2440,9 +1636,6 @@ perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	is_user = user_mode(regs);
 
-	if (!current || current->pid == 0)
-		return;
-
 	if (is_user && current->state != TASK_RUNNING)
 		return;
 
@@ -2472,4 +1665,25 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 void hw_perf_event_setup_online(int cpu)
 {
 	init_debug_store_on_cpu(cpu);
+
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		amd_pmu_cpu_online(cpu);
+		break;
+	default:
+		return;
+	}
+}
+
+void hw_perf_event_setup_offline(int cpu)
+{
+	init_debug_store_on_cpu(cpu);
+
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		amd_pmu_cpu_offline(cpu);
+		break;
+	default:
+		return;
+	}
 }
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
new file mode 100644
index 00000000000..8f3dbfda3c4
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -0,0 +1,416 @@
+#ifdef CONFIG_CPU_SUP_AMD
+
+static DEFINE_RAW_SPINLOCK(amd_nb_lock);
+
+static __initconst u64 amd_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
+		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts  */
+		[ C(RESULT_MISS)   ] = 0x0167, /* Data Prefetcher :cancelled */
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches  */
+		[ C(RESULT_MISS)   ] = 0x0081, /* Instruction cache misses   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */
+		[ C(RESULT_MISS)   ] = 0x037E, /* L2 Cache Misses : IC+DC     */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback           */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
+		[ C(RESULT_MISS)   ] = 0x0046, /* L1 DTLB and L2 DLTB Miss   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes        */
+		[ C(RESULT_MISS)   ] = 0x0085, /* Instr. fetch ITLB misses   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr.      */
+		[ C(RESULT_MISS)   ] = 0x00c3, /* Retired Mispredicted BI    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+/*
+ * AMD Performance Monitor K7 and later.
+ */
+static const u64 amd_perfmon_event_map[] =
+{
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0080,
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x0081,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+};
+
+static u64 amd_pmu_event_map(int hw_event)
+{
+	return amd_perfmon_event_map[hw_event];
+}
+
+static u64 amd_pmu_raw_event(u64 hw_event)
+{
+#define K7_EVNTSEL_EVENT_MASK	0xF000000FFULL
+#define K7_EVNTSEL_UNIT_MASK	0x00000FF00ULL
+#define K7_EVNTSEL_EDGE_MASK	0x000040000ULL
+#define K7_EVNTSEL_INV_MASK	0x000800000ULL
+#define K7_EVNTSEL_REG_MASK	0x0FF000000ULL
+
+#define K7_EVNTSEL_MASK			\
+	(K7_EVNTSEL_EVENT_MASK |	\
+	 K7_EVNTSEL_UNIT_MASK  |	\
+	 K7_EVNTSEL_EDGE_MASK  |	\
+	 K7_EVNTSEL_INV_MASK   |	\
+	 K7_EVNTSEL_REG_MASK)
+
+	return hw_event & K7_EVNTSEL_MASK;
+}
+
+/*
+ * AMD64 events are detected based on their event codes.
+ */
+static inline int amd_is_nb_event(struct hw_perf_event *hwc)
+{
+	return (hwc->config & 0xe0) == 0xe0;
+}
+
+static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
+				      struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct amd_nb *nb = cpuc->amd_nb;
+	int i;
+
+	/*
+	 * only care about NB events
+	 */
+	if (!(nb && amd_is_nb_event(hwc)))
+		return;
+
+	/*
+	 * need to scan whole list because event may not have
+	 * been assigned during scheduling
+	 *
+	 * no race condition possible because event can only
+	 * be removed on one CPU at a time AND PMU is disabled
+	 * when we come here
+	 */
+	for (i = 0; i < x86_pmu.num_events; i++) {
+		if (nb->owners[i] == event) {
+			cmpxchg(nb->owners+i, event, NULL);
+			break;
+		}
+	}
+}
+
+ /*
+  * AMD64 NorthBridge events need special treatment because
+  * counter access needs to be synchronized across all cores
+  * of a package. Refer to BKDG section 3.12
+  *
+  * NB events are events measuring L3 cache, Hypertransport
+  * traffic. They are identified by an event code >= 0xe00.
+  * They measure events on the NorthBride which is shared
+  * by all cores on a package. NB events are counted on a
+  * shared set of counters. When a NB event is programmed
+  * in a counter, the data actually comes from a shared
+  * counter. Thus, access to those counters needs to be
+  * synchronized.
+  *
+  * We implement the synchronization such that no two cores
+  * can be measuring NB events using the same counters. Thus,
+  * we maintain a per-NB allocation table. The available slot
+  * is propagated using the event_constraint structure.
+  *
+  * We provide only one choice for each NB event based on
+  * the fact that only NB events have restrictions. Consequently,
+  * if a counter is available, there is a guarantee the NB event
+  * will be assigned to it. If no slot is available, an empty
+  * constraint is returned and scheduling will eventually fail
+  * for this event.
+  *
+  * Note that all cores attached the same NB compete for the same
+  * counters to host NB events, this is why we use atomic ops. Some
+  * multi-chip CPUs may have more than one NB.
+  *
+  * Given that resources are allocated (cmpxchg), they must be
+  * eventually freed for others to use. This is accomplished by
+  * calling amd_put_event_constraints().
+  *
+  * Non NB events are not impacted by this restriction.
+  */
+static struct event_constraint *
+amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct amd_nb *nb = cpuc->amd_nb;
+	struct perf_event *old = NULL;
+	int max = x86_pmu.num_events;
+	int i, j, k = -1;
+
+	/*
+	 * if not NB event or no NB, then no constraints
+	 */
+	if (!(nb && amd_is_nb_event(hwc)))
+		return &unconstrained;
+
+	/*
+	 * detect if already present, if so reuse
+	 *
+	 * cannot merge with actual allocation
+	 * because of possible holes
+	 *
+	 * event can already be present yet not assigned (in hwc->idx)
+	 * because of successive calls to x86_schedule_events() from
+	 * hw_perf_group_sched_in() without hw_perf_enable()
+	 */
+	for (i = 0; i < max; i++) {
+		/*
+		 * keep track of first free slot
+		 */
+		if (k == -1 && !nb->owners[i])
+			k = i;
+
+		/* already present, reuse */
+		if (nb->owners[i] == event)
+			goto done;
+	}
+	/*
+	 * not present, so grab a new slot
+	 * starting either at:
+	 */
+	if (hwc->idx != -1) {
+		/* previous assignment */
+		i = hwc->idx;
+	} else if (k != -1) {
+		/* start from free slot found */
+		i = k;
+	} else {
+		/*
+		 * event not found, no slot found in
+		 * first pass, try again from the
+		 * beginning
+		 */
+		i = 0;
+	}
+	j = i;
+	do {
+		old = cmpxchg(nb->owners+i, NULL, event);
+		if (!old)
+			break;
+		if (++i == max)
+			i = 0;
+	} while (i != j);
+done:
+	if (!old)
+		return &nb->event_constraints[i];
+
+	return &emptyconstraint;
+}
+
+static __initconst struct x86_pmu amd_pmu = {
+	.name			= "AMD",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= x86_pmu_enable_all,
+	.enable			= x86_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.eventsel		= MSR_K7_EVNTSEL0,
+	.perfctr		= MSR_K7_PERFCTR0,
+	.event_map		= amd_pmu_event_map,
+	.raw_event		= amd_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
+	.num_events		= 4,
+	.event_bits		= 48,
+	.event_mask		= (1ULL << 48) - 1,
+	.apic			= 1,
+	/* use highest bit to detect overflow */
+	.max_period		= (1ULL << 47) - 1,
+	.get_event_constraints	= amd_get_event_constraints,
+	.put_event_constraints	= amd_put_event_constraints
+};
+
+static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
+{
+	struct amd_nb *nb;
+	int i;
+
+	nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL);
+	if (!nb)
+		return NULL;
+
+	memset(nb, 0, sizeof(*nb));
+	nb->nb_id = nb_id;
+
+	/*
+	 * initialize all possible NB constraints
+	 */
+	for (i = 0; i < x86_pmu.num_events; i++) {
+		set_bit(i, nb->event_constraints[i].idxmsk);
+		nb->event_constraints[i].weight = 1;
+	}
+	return nb;
+}
+
+static void amd_pmu_cpu_online(int cpu)
+{
+	struct cpu_hw_events *cpu1, *cpu2;
+	struct amd_nb *nb = NULL;
+	int i, nb_id;
+
+	if (boot_cpu_data.x86_max_cores < 2)
+		return;
+
+	/*
+	 * function may be called too early in the
+	 * boot process, in which case nb_id is bogus
+	 */
+	nb_id = amd_get_nb_id(cpu);
+	if (nb_id == BAD_APICID)
+		return;
+
+	cpu1 = &per_cpu(cpu_hw_events, cpu);
+	cpu1->amd_nb = NULL;
+
+	raw_spin_lock(&amd_nb_lock);
+
+	for_each_online_cpu(i) {
+		cpu2 = &per_cpu(cpu_hw_events, i);
+		nb = cpu2->amd_nb;
+		if (!nb)
+			continue;
+		if (nb->nb_id == nb_id)
+			goto found;
+	}
+
+	nb = amd_alloc_nb(cpu, nb_id);
+	if (!nb) {
+		pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
+		raw_spin_unlock(&amd_nb_lock);
+		return;
+	}
+found:
+	nb->refcnt++;
+	cpu1->amd_nb = nb;
+
+	raw_spin_unlock(&amd_nb_lock);
+}
+
+static void amd_pmu_cpu_offline(int cpu)
+{
+	struct cpu_hw_events *cpuhw;
+
+	if (boot_cpu_data.x86_max_cores < 2)
+		return;
+
+	cpuhw = &per_cpu(cpu_hw_events, cpu);
+
+	raw_spin_lock(&amd_nb_lock);
+
+	if (--cpuhw->amd_nb->refcnt == 0)
+		kfree(cpuhw->amd_nb);
+
+	cpuhw->amd_nb = NULL;
+
+	raw_spin_unlock(&amd_nb_lock);
+}
+
+static __init int amd_pmu_init(void)
+{
+	/* Performance-monitoring supported from K7 and later: */
+	if (boot_cpu_data.x86 < 6)
+		return -ENODEV;
+
+	x86_pmu = amd_pmu;
+
+	/* Events are common for all AMDs */
+	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
+	       sizeof(hw_cache_event_ids));
+
+	/*
+	 * explicitly initialize the boot cpu, other cpus will get
+	 * the cpu hotplug callbacks from smp_init()
+	 */
+	amd_pmu_cpu_online(smp_processor_id());
+	return 0;
+}
+
+#else /* CONFIG_CPU_SUP_AMD */
+
+static int amd_pmu_init(void)
+{
+	return 0;
+}
+
+static void amd_pmu_cpu_online(int cpu)
+{
+}
+
+static void amd_pmu_cpu_offline(int cpu)
+{
+}
+
+#endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
new file mode 100644
index 00000000000..977e7544738
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -0,0 +1,971 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+/*
+ * Intel PerfMon v3. Used on Core2 and later.
+ */
+static const u64 intel_perfmon_event_map[] =
+{
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x003c,
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x4f2e,
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x412e,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+  [PERF_COUNT_HW_BUS_CYCLES]		= 0x013c,
+};
+
+static struct event_constraint intel_core_event_constraints[] =
+{
+	INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
+	INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
+	INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
+	INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
+	INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
+	INTEL_EVENT_CONSTRAINT(0xc1, 0x1), /* FP_COMP_INSTR_RET */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_core2_event_constraints[] =
+{
+	FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+	FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
+	INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
+	INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
+	INTEL_EVENT_CONSTRAINT(0x13, 0x2), /* DIV */
+	INTEL_EVENT_CONSTRAINT(0x14, 0x1), /* CYCLES_DIV_BUSY */
+	INTEL_EVENT_CONSTRAINT(0x18, 0x1), /* IDLE_DURING_DIV */
+	INTEL_EVENT_CONSTRAINT(0x19, 0x2), /* DELAYED_BYPASS */
+	INTEL_EVENT_CONSTRAINT(0xa1, 0x1), /* RS_UOPS_DISPATCH_CYCLES */
+	INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_nehalem_event_constraints[] =
+{
+	FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+	FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
+	INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
+	INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
+	INTEL_EVENT_CONSTRAINT(0x43, 0x3), /* L1D_ALL_REF */
+	INTEL_EVENT_CONSTRAINT(0x48, 0x3), /* L1D_PEND_MISS */
+	INTEL_EVENT_CONSTRAINT(0x4e, 0x3), /* L1D_PREFETCH */
+	INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
+	INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_westmere_event_constraints[] =
+{
+	FIXED_EVENT_CONSTRAINT(0xc0, (0xf|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+	FIXED_EVENT_CONSTRAINT(0x3c, (0xf|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
+	INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
+	INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint intel_gen_event_constraints[] =
+{
+	FIXED_EVENT_CONSTRAINT(0xc0, (0x3|(1ULL<<32))), /* INSTRUCTIONS_RETIRED */
+	FIXED_EVENT_CONSTRAINT(0x3c, (0x3|(1ULL<<33))), /* UNHALTED_CORE_CYCLES */
+	EVENT_CONSTRAINT_END
+};
+
+static u64 intel_pmu_event_map(int hw_event)
+{
+	return intel_perfmon_event_map[hw_event];
+}
+
+static __initconst u64 westmere_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
+		[ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPL                     */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
+		[ C(RESULT_MISS)   ] = 0x0251, /* L1D.M_REPL                   */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
+		[ C(RESULT_MISS)   ] = 0x024e, /* L1D_PREFETCH.MISS            */
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                    */
+		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
+		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
+		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
+		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
+		[ C(RESULT_MISS)   ] = 0x0108, /* DTLB_LOAD_MISSES.ANY         */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
+		[ C(RESULT_MISS)   ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS  */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P           */
+		[ C(RESULT_MISS)   ] = 0x0185, /* ITLB_MISSES.ANY              */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0x03e8, /* BPU_CLEARS.ANY               */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst u64 nehalem_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
+		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
+		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
+		[ C(RESULT_MISS)   ] = 0x024e, /* L1D_PREFETCH.MISS            */
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                    */
+		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS               */
+		[ C(RESULT_MISS)   ] = 0x0224, /* L2_RQSTS.LD_MISS             */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS                */
+		[ C(RESULT_MISS)   ] = 0x0824, /* L2_RQSTS.RFO_MISS            */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference                */
+		[ C(RESULT_MISS)   ] = 0x412e, /* LLC Misses                   */
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI   (alias)  */
+		[ C(RESULT_MISS)   ] = 0x0108, /* DTLB_LOAD_MISSES.ANY         */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI   (alias)  */
+		[ C(RESULT_MISS)   ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS  */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P           */
+		[ C(RESULT_MISS)   ] = 0x20c8, /* ITLB_MISS_RETIRED            */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0x03e8, /* BPU_CLEARS.ANY               */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst u64 core2_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI          */
+		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE       */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI          */
+		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE       */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x104e, /* L1D_PREFETCH.REQUESTS      */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* L1I.READS                  */
+		[ C(RESULT_MISS)   ] = 0x0081, /* L1I.MISSES                 */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0208, /* DTLB_MISSES.MISS_LD        */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0808, /* DTLB_MISSES.MISS_ST        */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
+		[ C(RESULT_MISS)   ] = 0x1282, /* ITLBMISSES                 */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
+		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst u64 atom_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE.LD               */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE.ST               */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS                  */
+		[ C(RESULT_MISS)   ] = 0x0280, /* L1I.MISSES                 */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f29, /* L2_LD.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x4129, /* L2_LD.ISTATE               */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4f2A, /* L2_ST.MESI                 */
+		[ C(RESULT_MISS)   ] = 0x412A, /* L2_ST.ISTATE               */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2140, /* L1D_CACHE_LD.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0508, /* DTLB_MISSES.MISS_LD        */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x2240, /* L1D_CACHE_ST.MESI  (alias) */
+		[ C(RESULT_MISS)   ] = 0x0608, /* DTLB_MISSES.MISS_ST        */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P         */
+		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES                */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY        */
+		[ C(RESULT_MISS)   ] = 0x00c5, /* BP_INST_RETIRED.MISPRED    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static u64 intel_pmu_raw_event(u64 hw_event)
+{
+#define CORE_EVNTSEL_EVENT_MASK		0x000000FFULL
+#define CORE_EVNTSEL_UNIT_MASK		0x0000FF00ULL
+#define CORE_EVNTSEL_EDGE_MASK		0x00040000ULL
+#define CORE_EVNTSEL_INV_MASK		0x00800000ULL
+#define CORE_EVNTSEL_REG_MASK		0xFF000000ULL
+
+#define CORE_EVNTSEL_MASK		\
+	(INTEL_ARCH_EVTSEL_MASK |	\
+	 INTEL_ARCH_UNIT_MASK   |	\
+	 INTEL_ARCH_EDGE_MASK   |	\
+	 INTEL_ARCH_INV_MASK    |	\
+	 INTEL_ARCH_CNT_MASK)
+
+	return hw_event & CORE_EVNTSEL_MASK;
+}
+
+static void intel_pmu_enable_bts(u64 config)
+{
+	unsigned long debugctlmsr;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr |= X86_DEBUGCTL_TR;
+	debugctlmsr |= X86_DEBUGCTL_BTS;
+	debugctlmsr |= X86_DEBUGCTL_BTINT;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
+		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
+		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
+
+	update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_bts(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	unsigned long debugctlmsr;
+
+	if (!cpuc->ds)
+		return;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr &=
+		~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
+		  X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
+
+	update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+
+	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+		intel_pmu_disable_bts();
+}
+
+static void intel_pmu_enable_all(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+
+	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+		struct perf_event *event =
+			cpuc->events[X86_PMC_IDX_FIXED_BTS];
+
+		if (WARN_ON_ONCE(!event))
+			return;
+
+		intel_pmu_enable_bts(event->hw.config);
+	}
+}
+
+static inline u64 intel_pmu_get_status(void)
+{
+	u64 status;
+
+	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+
+	return status;
+}
+
+static inline void intel_pmu_ack_status(u64 ack)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+}
+
+static inline void
+intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
+{
+	int idx = __idx - X86_PMC_IDX_FIXED;
+	u64 ctrl_val, mask;
+
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	(void)checking_wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void intel_pmu_drain_bts_buffer(void)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct bts_record {
+		u64	from;
+		u64	to;
+		u64	flags;
+	};
+	struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
+	struct bts_record *at, *top;
+	struct perf_output_handle handle;
+	struct perf_event_header header;
+	struct perf_sample_data data;
+	struct pt_regs regs;
+
+	if (!event)
+		return;
+
+	if (!ds)
+		return;
+
+	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+	top = (struct bts_record *)(unsigned long)ds->bts_index;
+
+	if (top <= at)
+		return;
+
+	ds->bts_index = ds->bts_buffer_base;
+
+
+	data.period	= event->hw.last_period;
+	data.addr	= 0;
+	data.raw	= NULL;
+	regs.ip		= 0;
+
+	/*
+	 * Prepare a generic sample, i.e. fill in the invariant fields.
+	 * We will overwrite the from and to address before we output
+	 * the sample.
+	 */
+	perf_prepare_sample(&header, &data, event, &regs);
+
+	if (perf_output_begin(&handle, event,
+			      header.size * (top - at), 1, 1))
+		return;
+
+	for (; at < top; at++) {
+		data.ip		= at->from;
+		data.addr	= at->to;
+
+		perf_output_sample(&handle, &header, &data, event);
+	}
+
+	perf_output_end(&handle);
+
+	/* There's new data available. */
+	event->hw.interrupts++;
+	event->pending_kill = POLL_IN;
+}
+
+static inline void
+intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+		intel_pmu_disable_bts();
+		intel_pmu_drain_bts_buffer();
+		return;
+	}
+
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		intel_pmu_disable_fixed(hwc, idx);
+		return;
+	}
+
+	x86_pmu_disable_event(hwc, idx);
+}
+
+static inline void
+intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
+{
+	int idx = __idx - X86_PMC_IDX_FIXED;
+	u64 ctrl_val, bits, mask;
+	int err;
+
+	/*
+	 * Enable IRQ generation (0x8),
+	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
+	 * if requested:
+	 */
+	bits = 0x8ULL;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
+		bits |= 0x2;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+		bits |= 0x1;
+
+	/*
+	 * ANY bit is supported in v3 and up
+	 */
+	if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
+		bits |= 0x4;
+
+	bits <<= (idx * 4);
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	ctrl_val |= bits;
+	err = checking_wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+		if (!__get_cpu_var(cpu_hw_events).enabled)
+			return;
+
+		intel_pmu_enable_bts(hwc->config);
+		return;
+	}
+
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		intel_pmu_enable_fixed(hwc, idx);
+		return;
+	}
+
+	__x86_pmu_enable_event(hwc, idx);
+}
+
+/*
+ * Save and restart an expired event. Called by NMI contexts,
+ * so it has to be careful about preempting normal event ops:
+ */
+static int intel_pmu_save_and_restart(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	int ret;
+
+	x86_perf_event_update(event, hwc, idx);
+	ret = x86_perf_event_set_period(event, hwc, idx);
+
+	return ret;
+}
+
+static void intel_pmu_reset(void)
+{
+	struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds;
+	unsigned long flags;
+	int idx;
+
+	if (!x86_pmu.num_events)
+		return;
+
+	local_irq_save(flags);
+
+	printk("clearing PMU state on CPU#%d\n", smp_processor_id());
+
+	for (idx = 0; idx < x86_pmu.num_events; idx++) {
+		checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
+		checking_wrmsrl(x86_pmu.perfctr  + idx, 0ull);
+	}
+	for (idx = 0; idx < x86_pmu.num_events_fixed; idx++) {
+		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+	}
+	if (ds)
+		ds->bts_index = ds->bts_buffer_base;
+
+	local_irq_restore(flags);
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int intel_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	int bit, loops;
+	u64 ack, status;
+
+	data.addr = 0;
+	data.raw = NULL;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+
+	perf_disable();
+	intel_pmu_drain_bts_buffer();
+	status = intel_pmu_get_status();
+	if (!status) {
+		perf_enable();
+		return 0;
+	}
+
+	loops = 0;
+again:
+	if (++loops > 100) {
+		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
+		perf_event_print_debug();
+		intel_pmu_reset();
+		perf_enable();
+		return 1;
+	}
+
+	inc_irq_stat(apic_perf_irqs);
+	ack = status;
+	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+		struct perf_event *event = cpuc->events[bit];
+
+		clear_bit(bit, (unsigned long *) &status);
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+
+		if (!intel_pmu_save_and_restart(event))
+			continue;
+
+		data.period = event->hw.last_period;
+
+		if (perf_event_overflow(event, 1, &data, regs))
+			intel_pmu_disable_event(&event->hw, bit);
+	}
+
+	intel_pmu_ack_status(ack);
+
+	/*
+	 * Repeat if there is more work to be done:
+	 */
+	status = intel_pmu_get_status();
+	if (status)
+		goto again;
+
+	perf_enable();
+
+	return 1;
+}
+
+static struct event_constraint bts_constraint =
+	EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
+
+static struct event_constraint *
+intel_special_constraints(struct perf_event *event)
+{
+	unsigned int hw_event;
+
+	hw_event = event->hw.config & INTEL_ARCH_EVENT_MASK;
+
+	if (unlikely((hw_event ==
+		      x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
+		     (event->hw.sample_period == 1))) {
+
+		return &bts_constraint;
+	}
+	return NULL;
+}
+
+static struct event_constraint *
+intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	c = intel_special_constraints(event);
+	if (c)
+		return c;
+
+	return x86_get_event_constraints(cpuc, event);
+}
+
+static __initconst struct x86_pmu core_pmu = {
+	.name			= "core",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= x86_pmu_enable_all,
+	.enable			= x86_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.raw_event		= intel_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32 bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL << 31) - 1,
+	.get_event_constraints	= intel_get_event_constraints,
+	.event_constraints	= intel_core_event_constraints,
+};
+
+static __initconst struct x86_pmu intel_pmu = {
+	.name			= "Intel",
+	.handle_irq		= intel_pmu_handle_irq,
+	.disable_all		= intel_pmu_disable_all,
+	.enable_all		= intel_pmu_enable_all,
+	.enable			= intel_pmu_enable_event,
+	.disable		= intel_pmu_disable_event,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.raw_event		= intel_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32 bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL << 31) - 1,
+	.enable_bts		= intel_pmu_enable_bts,
+	.disable_bts		= intel_pmu_disable_bts,
+	.get_event_constraints	= intel_get_event_constraints
+};
+
+static __init int intel_pmu_init(void)
+{
+	union cpuid10_edx edx;
+	union cpuid10_eax eax;
+	unsigned int unused;
+	unsigned int ebx;
+	int version;
+
+	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+		/* check for P6 processor family */
+	   if (boot_cpu_data.x86 == 6) {
+		return p6_pmu_init();
+	   } else {
+		return -ENODEV;
+	   }
+	}
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Branch Misses Retired hw_event or not.
+	 */
+	cpuid(10, &eax.full, &ebx, &unused, &edx.full);
+	if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
+		return -ENODEV;
+
+	version = eax.split.version_id;
+	if (version < 2)
+		x86_pmu = core_pmu;
+	else
+		x86_pmu = intel_pmu;
+
+	x86_pmu.version			= version;
+	x86_pmu.num_events		= eax.split.num_events;
+	x86_pmu.event_bits		= eax.split.bit_width;
+	x86_pmu.event_mask		= (1ULL << eax.split.bit_width) - 1;
+
+	/*
+	 * Quirk: v2 perfmon does not report fixed-purpose events, so
+	 * assume at least 3 events:
+	 */
+	if (version > 1)
+		x86_pmu.num_events_fixed = max((int)edx.split.num_events_fixed, 3);
+
+	/*
+	 * Install the hw-cache-events table:
+	 */
+	switch (boot_cpu_data.x86_model) {
+	case 14: /* 65 nm core solo/duo, "Yonah" */
+		pr_cont("Core events, ");
+		break;
+
+	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
+	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
+	case 29: /* six-core 45 nm xeon "Dunnington" */
+		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		x86_pmu.event_constraints = intel_core2_event_constraints;
+		pr_cont("Core2 events, ");
+		break;
+
+	case 26: /* 45 nm nehalem, "Bloomfield" */
+	case 30: /* 45 nm nehalem, "Lynnfield" */
+		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		x86_pmu.event_constraints = intel_nehalem_event_constraints;
+		pr_cont("Nehalem/Corei7 events, ");
+		break;
+	case 28:
+		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		x86_pmu.event_constraints = intel_gen_event_constraints;
+		pr_cont("Atom events, ");
+		break;
+
+	case 37: /* 32 nm nehalem, "Clarkdale" */
+	case 44: /* 32 nm nehalem, "Gulftown" */
+		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		x86_pmu.event_constraints = intel_westmere_event_constraints;
+		pr_cont("Westmere events, ");
+		break;
+	default:
+		/*
+		 * default constraints for v2 and up
+		 */
+		x86_pmu.event_constraints = intel_gen_event_constraints;
+		pr_cont("generic architected perfmon, ");
+	}
+	return 0;
+}
+
+#else /* CONFIG_CPU_SUP_INTEL */
+
+static int intel_pmu_init(void)
+{
+	return 0;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
new file mode 100644
index 00000000000..1ca5ba078af
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -0,0 +1,157 @@
+#ifdef CONFIG_CPU_SUP_INTEL
+
+/*
+ * Not sure about some of these
+ */
+static const u64 p6_perfmon_event_map[] =
+{
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x0079,
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0f2e,
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x012e,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+  [PERF_COUNT_HW_BUS_CYCLES]		= 0x0062,
+};
+
+static u64 p6_pmu_event_map(int hw_event)
+{
+	return p6_perfmon_event_map[hw_event];
+}
+
+/*
+ * Event setting that is specified not to count anything.
+ * We use this to effectively disable a counter.
+ *
+ * L2_RQSTS with 0 MESI unit mask.
+ */
+#define P6_NOP_EVENT			0x0000002EULL
+
+static u64 p6_pmu_raw_event(u64 hw_event)
+{
+#define P6_EVNTSEL_EVENT_MASK		0x000000FFULL
+#define P6_EVNTSEL_UNIT_MASK		0x0000FF00ULL
+#define P6_EVNTSEL_EDGE_MASK		0x00040000ULL
+#define P6_EVNTSEL_INV_MASK		0x00800000ULL
+#define P6_EVNTSEL_REG_MASK		0xFF000000ULL
+
+#define P6_EVNTSEL_MASK			\
+	(P6_EVNTSEL_EVENT_MASK |	\
+	 P6_EVNTSEL_UNIT_MASK  |	\
+	 P6_EVNTSEL_EDGE_MASK  |	\
+	 P6_EVNTSEL_INV_MASK   |	\
+	 P6_EVNTSEL_REG_MASK)
+
+	return hw_event & P6_EVNTSEL_MASK;
+}
+
+static struct event_constraint p6_event_constraints[] =
+{
+	INTEL_EVENT_CONSTRAINT(0xc1, 0x1),	/* FLOPS */
+	INTEL_EVENT_CONSTRAINT(0x10, 0x1),	/* FP_COMP_OPS_EXE */
+	INTEL_EVENT_CONSTRAINT(0x11, 0x1),	/* FP_ASSIST */
+	INTEL_EVENT_CONSTRAINT(0x12, 0x2),	/* MUL */
+	INTEL_EVENT_CONSTRAINT(0x13, 0x2),	/* DIV */
+	INTEL_EVENT_CONSTRAINT(0x14, 0x1),	/* CYCLES_DIV_BUSY */
+	EVENT_CONSTRAINT_END
+};
+
+static void p6_pmu_disable_all(void)
+{
+	u64 val;
+
+	/* p6 only has one enable register */
+	rdmsrl(MSR_P6_EVNTSEL0, val);
+	val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsrl(MSR_P6_EVNTSEL0, val);
+}
+
+static void p6_pmu_enable_all(void)
+{
+	unsigned long val;
+
+	/* p6 only has one enable register */
+	rdmsrl(MSR_P6_EVNTSEL0, val);
+	val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsrl(MSR_P6_EVNTSEL0, val);
+}
+
+static inline void
+p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	u64 val = P6_NOP_EVENT;
+
+	if (cpuc->enabled)
+		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+
+	(void)checking_wrmsrl(hwc->config_base + idx, val);
+}
+
+static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	u64 val;
+
+	val = hwc->config;
+	if (cpuc->enabled)
+		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+
+	(void)checking_wrmsrl(hwc->config_base + idx, val);
+}
+
+static __initconst struct x86_pmu p6_pmu = {
+	.name			= "p6",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= p6_pmu_disable_all,
+	.enable_all		= p6_pmu_enable_all,
+	.enable			= p6_pmu_enable_event,
+	.disable		= p6_pmu_disable_event,
+	.eventsel		= MSR_P6_EVNTSEL0,
+	.perfctr		= MSR_P6_PERFCTR0,
+	.event_map		= p6_pmu_event_map,
+	.raw_event		= p6_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(p6_perfmon_event_map),
+	.apic			= 1,
+	.max_period		= (1ULL << 31) - 1,
+	.version		= 0,
+	.num_events		= 2,
+	/*
+	 * Events have 40 bits implemented. However they are designed such
+	 * that bits [32-39] are sign extensions of bit 31. As such the
+	 * effective width of a event for P6-like PMU is 32 bits only.
+	 *
+	 * See IA-32 Intel Architecture Software developer manual Vol 3B
+	 */
+	.event_bits		= 32,
+	.event_mask		= (1ULL << 32) - 1,
+	.get_event_constraints	= x86_get_event_constraints,
+	.event_constraints	= p6_event_constraints,
+};
+
+static __init int p6_pmu_init(void)
+{
+	switch (boot_cpu_data.x86_model) {
+	case 1:
+	case 3:  /* Pentium Pro */
+	case 5:
+	case 6:  /* Pentium II */
+	case 7:
+	case 8:
+	case 11: /* Pentium III */
+	case 9:
+	case 13:
+		/* Pentium M */
+		break;
+	default:
+		pr_cont("unsupported p6 CPU model %d ",
+			boot_cpu_data.x86_model);
+		return -ENODEV;
+	}
+
+	x86_pmu = p6_pmu;
+
+	return 0;
+}
+
+#endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 898df9719af..74f4e85a572 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -115,17 +115,6 @@ int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
 
 	return !test_bit(counter, perfctr_nmi_owner);
 }
-
-/* checks the an msr for availability */
-int avail_to_resrv_perfctr_nmi(unsigned int msr)
-{
-	unsigned int counter;
-
-	counter = nmi_perfctr_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
-
-	return !test_bit(counter, perfctr_nmi_owner);
-}
 EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
 
 int reserve_perfctr_nmi(unsigned int msr)
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index cb27fd6136c..83e5e628de7 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -229,7 +229,7 @@ static void __exit cpuid_exit(void)
 	for_each_online_cpu(cpu)
 		cpuid_device_destroy(cpu);
 	class_destroy(cpuid_class);
-	unregister_chrdev(CPUID_MAJOR, "cpu/cpuid");
+	__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
 	unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
 }
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index ae775ca47b2..11540a189d9 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -18,11 +18,6 @@
 
 #include "dumpstack.h"
 
-/* Just a stub for now */
-int x86_is_stack_id(int id, char *name)
-{
-	return 0;
-}
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 0ad9597073f..dce99abb449 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -33,11 +33,6 @@ static char x86_stack_ids[][8] = {
 #endif
 };
 
-int x86_is_stack_id(int id, char *name)
-{
-	return x86_stack_ids[id - 1] == name;
-}
-
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 					 unsigned *usedp, char **idp)
 {
@@ -291,6 +286,7 @@ void show_registers(struct pt_regs *regs)
 
 	sp = regs->sp;
 	printk("CPU %d ", cpu);
+	print_modules();
 	__show_regs(regs, 1);
 	printk("Process %s (pid: %d, threadinfo %p, task %p)\n",
 		cur->comm, cur->pid, task_thread_info(cur), cur);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index a1a7876cadc..740b440fbd7 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -12,21 +12,13 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
-#include <linux/ioport.h>
-#include <linux/string.h>
-#include <linux/kexec.h>
-#include <linux/module.h>
-#include <linux/mm.h>
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/firmware-map.h>
 
-#include <asm/pgtable.h>
-#include <asm/page.h>
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
-#include <asm/trampoline.h>
 
 /*
  * The e820 map is the map that gets modified e.g. with command line parameters
@@ -517,11 +509,19 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
 			     int checktype)
 {
 	int i;
+	u64 end;
 	u64 real_removed_size = 0;
 
 	if (size > (ULLONG_MAX - start))
 		size = ULLONG_MAX - start;
 
+	end = start + size;
+	printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
+		       (unsigned long long) start,
+		       (unsigned long long) end);
+	e820_print_type(old_type);
+	printk(KERN_CONT "\n");
+
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
 		u64 final_start, final_end;
@@ -722,319 +722,44 @@ core_initcall(e820_mark_nvs_memory);
 #endif
 
 /*
- * Early reserved memory areas.
- */
-#define MAX_EARLY_RES 32
-
-struct early_res {
-	u64 start, end;
-	char name[16];
-	char overlap_ok;
-};
-static struct early_res early_res[MAX_EARLY_RES] __initdata = {
-	{ 0, PAGE_SIZE, "BIOS data page", 1 },	/* BIOS data page */
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_TRAMPOLINE)
-	/*
-	 * But first pinch a few for the stack/trampoline stuff
-	 * FIXME: Don't need the extra page at 4K, but need to fix
-	 * trampoline before removing it. (see the GDT stuff)
-	 */
-	{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE", 1 },
-#endif
-
-	{}
-};
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
-	int i;
-	struct early_res *r;
-
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		r = &early_res[i];
-		if (end > r->start && start < r->end)
-			break;
-	}
-
-	return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
-	int j;
-
-	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
-		;
-
-	memmove(&early_res[i], &early_res[i + 1],
-	       (j - 1 - i) * sizeof(struct early_res));
-
-	early_res[j - 1].end = 0;
-}
-
-/*
- * Split any existing ranges that:
- *  1) are marked 'overlap_ok', and
- *  2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range.  Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
+ * Find a free area with specified alignment in a specific range.
  */
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
 {
 	int i;
-	struct early_res *r;
-	u64 lower_start, lower_end;
-	u64 upper_start, upper_end;
-	char name[16];
 
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		r = &early_res[i];
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		u64 addr;
+		u64 ei_start, ei_last;
 
-		/* Continue past non-overlapping ranges */
-		if (end <= r->start || start >= r->end)
+		if (ei->type != E820_RAM)
 			continue;
 
-		/*
-		 * Leave non-ok overlaps as is; let caller
-		 * panic "Overlapping early reservations"
-		 * when it hits this overlap.
-		 */
-		if (!r->overlap_ok)
-			return;
-
-		/*
-		 * We have an ok overlap.  We will drop it from the early
-		 * reservation map, and add back in any non-overlapping
-		 * portions (lower or upper) as separate, overlap_ok,
-		 * non-overlapping ranges.
-		 */
-
-		/* 1. Note any non-overlapping (lower or upper) ranges. */
-		strncpy(name, r->name, sizeof(name) - 1);
-
-		lower_start = lower_end = 0;
-		upper_start = upper_end = 0;
-		if (r->start < start) {
-		 	lower_start = r->start;
-			lower_end = start;
-		}
-		if (r->end > end) {
-			upper_start = end;
-			upper_end = r->end;
-		}
-
-		/* 2. Drop the original ok overlapping range */
-		drop_range(i);
-
-		i--;		/* resume for-loop on copied down entry */
-
-		/* 3. Add back in any non-overlapping ranges. */
-		if (lower_end)
-			reserve_early_overlap_ok(lower_start, lower_end, name);
-		if (upper_end)
-			reserve_early_overlap_ok(upper_start, upper_end, name);
-	}
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
-						int overlap_ok)
-{
-	int i;
-	struct early_res *r;
-
-	i = find_overlapped_early(start, end);
-	if (i >= MAX_EARLY_RES)
-		panic("Too many early reservations");
-	r = &early_res[i];
-	if (r->end)
-		panic("Overlapping early reservations "
-		      "%llx-%llx %s to %llx-%llx %s\n",
-		      start, end - 1, name?name:"", r->start,
-		      r->end - 1, r->name);
-	r->start = start;
-	r->end = end;
-	r->overlap_ok = overlap_ok;
-	if (name)
-		strncpy(r->name, name, sizeof(r->name) - 1);
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first.  We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 1);
-}
-
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
-{
-	if (start >= end)
-		return;
-
-	drop_overlaps_that_are_ok(start, end);
-	__reserve_early(start, end, name, 0);
-}
-
-void __init free_early(u64 start, u64 end)
-{
-	struct early_res *r;
-	int i;
-
-	i = find_overlapped_early(start, end);
-	r = &early_res[i];
-	if (i >= MAX_EARLY_RES || r->end != end || r->start != start)
-		panic("free_early on not reserved area: %llx-%llx!",
-			 start, end - 1);
-
-	drop_range(i);
-}
-
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
-	int i, count;
-	u64 final_start, final_end;
-
-	count  = 0;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++)
-		count++;
-
-	printk(KERN_INFO "(%d early reservations) ==> bootmem [%010llx - %010llx]\n",
-			 count, start, end);
-	for (i = 0; i < count; i++) {
-		struct early_res *r = &early_res[i];
-		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
-			r->start, r->end, r->name);
-		final_start = max(start, r->start);
-		final_end = min(end, r->end);
-		if (final_start >= final_end) {
-			printk(KERN_CONT "\n");
-			continue;
-		}
-		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
-			final_start, final_end);
-		reserve_bootmem_generic(final_start, final_end - final_start,
-				BOOTMEM_DEFAULT);
-	}
-}
+		ei_last = ei->addr + ei->size;
+		ei_start = ei->addr;
+		addr = find_early_area(ei_start, ei_last, start, end,
+					 size, align);
 
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
-	int i;
-	u64 addr = *addrp;
-	int changed = 0;
-	struct early_res *r;
-again:
-	i = find_overlapped_early(addr, addr + size);
-	r = &early_res[i];
-	if (i < MAX_EARLY_RES && r->end) {
-		*addrp = addr = round_up(r->end, align);
-		changed = 1;
-		goto again;
+		if (addr != -1ULL)
+			return addr;
 	}
-	return changed;
+	return -1ULL;
 }
 
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align)
 {
-	int i;
-	u64 addr = *addrp, last;
-	u64 size = *sizep;
-	int changed = 0;
-again:
-	last = addr + size;
-	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
-		struct early_res *r = &early_res[i];
-		if (last > r->start && addr < r->start) {
-			size = r->start - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last > r->end && addr < r->end) {
-			addr = round_up(r->end, align);
-			size = last - addr;
-			changed = 1;
-			goto again;
-		}
-		if (last <= r->end && addr >= r->start) {
-			(*sizep)++;
-			return 0;
-		}
-	}
-	if (changed) {
-		*addrp = addr;
-		*sizep = size;
-	}
-	return changed;
+	return find_e820_area(start, end, size, align);
 }
 
-/*
- * Find a free area with specified alignment in a specific range.
- */
-u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
+u64 __init get_max_mapped(void)
 {
-	int i;
+	u64 end = max_pfn_mapped;
 
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		u64 addr, last;
-		u64 ei_last;
+	end <<= PAGE_SHIFT;
 
-		if (ei->type != E820_RAM)
-			continue;
-		addr = round_up(ei->addr, align);
-		ei_last = ei->addr + ei->size;
-		if (addr < start)
-			addr = round_up(start, align);
-		if (addr >= ei_last)
-			continue;
-		while (bad_addr(&addr, size, align) && addr+size <= ei_last)
-			;
-		last = addr + size;
-		if (last > ei_last)
-			continue;
-		if (last > end)
-			continue;
-		return addr;
-	}
-	return -1ULL;
+	return end;
 }
-
 /*
  * Find next free range after *start
  */
@@ -1044,25 +769,19 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
-		u64 addr, last;
-		u64 ei_last;
+		u64 addr;
+		u64 ei_start, ei_last;
 
 		if (ei->type != E820_RAM)
 			continue;
-		addr = round_up(ei->addr, align);
+
 		ei_last = ei->addr + ei->size;
-		if (addr < start)
-			addr = round_up(start, align);
-		if (addr >= ei_last)
-			continue;
-		*sizep = ei_last - addr;
-		while (bad_addr_size(&addr, sizep, align) &&
-			addr + *sizep <= ei_last)
-			;
-		last = addr + *sizep;
-		if (last > ei_last)
-			continue;
-		return addr;
+		ei_start = ei->addr;
+		addr = find_early_area_size(ei_start, ei_last, start,
+					 sizep, align);
+
+		if (addr != -1ULL)
+			return addr;
 	}
 
 	return -1ULL;
@@ -1421,6 +1140,8 @@ void __init e820_reserve_resources_late(void)
 			end = MAX_RESOURCE_SIZE;
 		if (start >= end)
 			continue;
+		printk(KERN_DEBUG "reserve RAM buffer: %016llx - %016llx ",
+			       start, end);
 		reserve_region_with_split(&iomem_resource, start, end,
 					  "RAM buffer");
 	}
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index cdcfb122f25..c2fa9b8b497 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -362,7 +362,7 @@ void __init efi_init(void)
 		printk(KERN_ERR PFX "Could not map the firmware vendor!\n");
 	early_iounmap(tmp, 2);
 
-	printk(KERN_INFO "EFI v%u.%.02u by %s \n",
+	printk(KERN_INFO "EFI v%u.%.02u by %s\n",
 	       efi.systab->hdr.revision >> 16,
 	       efi.systab->hdr.revision & 0xffff, vendor);
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 30968924543..cd37469b54e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -30,14 +30,32 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+/*
+ * modifying_code is set to notify NMIs that they need to use
+ * memory barriers when entering or exiting. But we don't want
+ * to burden NMIs with unnecessary memory barriers when code
+ * modification is not being done (which is most of the time).
+ *
+ * A mutex is already held when ftrace_arch_code_modify_prepare
+ * and post_process are called. No locks need to be taken here.
+ *
+ * Stop machine will make sure currently running NMIs are done
+ * and new NMIs will see the updated variable before we need
+ * to worry about NMIs doing memory barriers.
+ */
+static int modifying_code __read_mostly;
+static DEFINE_PER_CPU(int, save_modifying_code);
+
 int ftrace_arch_code_modify_prepare(void)
 {
 	set_kernel_text_rw();
+	modifying_code = 1;
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
 {
+	modifying_code = 0;
 	set_kernel_text_ro();
 	return 0;
 }
@@ -149,6 +167,11 @@ static void ftrace_mod_code(void)
 
 void ftrace_nmi_enter(void)
 {
+	__get_cpu_var(save_modifying_code) = modifying_code;
+
+	if (!__get_cpu_var(save_modifying_code))
+		return;
+
 	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
 		smp_rmb();
 		ftrace_mod_code();
@@ -160,6 +183,9 @@ void ftrace_nmi_enter(void)
 
 void ftrace_nmi_exit(void)
 {
+	if (!__get_cpu_var(save_modifying_code))
+		return;
+
 	/* Finish all executions before clearing nmi_running */
 	smp_mb();
 	atomic_dec(&nmi_running);
@@ -484,13 +510,3 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-#ifdef CONFIG_FTRACE_SYSCALLS
-
-extern unsigned long *sys_call_table;
-
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return (unsigned long)(&sys_call_table)[nr];
-}
-#endif
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 5051b94c906..adedeef1ded 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,6 +29,16 @@ static void __init i386_default_early_setup(void)
 
 void __init i386_start_kernel(void)
 {
+#ifdef CONFIG_X86_TRAMPOLINE
+	/*
+	 * But first pinch a few for the stack/trampoline stuff
+	 * FIXME: Don't need the extra page at 4K, but need to fix
+	 * trampoline before removing it. (see the GDT stuff)
+	 */
+	reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE,
+					 "EX TRAMPOLINE");
+#endif
+
 	reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS");
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 7fd318bac59..37c3d4b17d8 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -442,8 +442,8 @@ is386:	movl $2,%ecx		# set MP
 	 */
 	cmpb $0,ready
 	jne 1f
-	movl $per_cpu__gdt_page,%eax
-	movl $per_cpu__stack_canary,%ecx
+	movl $gdt_page,%eax
+	movl $stack_canary,%ecx
 	movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
 	shrl $16, %ecx
 	movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
@@ -706,7 +706,7 @@ idt_descr:
 	.word 0				# 32 bit align gdt_desc.address
 ENTRY(early_gdt_descr)
 	.word GDT_ENTRIES*8-1
-	.long per_cpu__gdt_page		/* Overwritten for secondary CPUs */
+	.long gdt_page			/* Overwritten for secondary CPUs */
 
 /*
  * The boot_gdt must mirror the equivalent in setup.S and is
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ba6e6588460..ee4fa1bfcb3 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -34,6 +34,8 @@
  */
 unsigned long				hpet_address;
 u8					hpet_blockid; /* OS timer block num */
+u8					hpet_msi_disable;
+
 #ifdef CONFIG_PCI_MSI
 static unsigned long			hpet_num_timers;
 #endif
@@ -264,7 +266,7 @@ static void hpet_resume_device(void)
 	force_hpet_resume();
 }
 
-static void hpet_resume_counter(void)
+static void hpet_resume_counter(struct clocksource *cs)
 {
 	hpet_resume_device();
 	hpet_restart_counter();
@@ -596,6 +598,9 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 	unsigned int num_timers_used = 0;
 	int i;
 
+	if (hpet_msi_disable)
+		return;
+
 	if (boot_cpu_has(X86_FEATURE_ARAT))
 		return;
 	id = hpet_readl(HPET_ID);
@@ -928,6 +933,9 @@ static __init int hpet_late_init(void)
 	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
 	hpet_print_config();
 
+	if (hpet_msi_disable)
+		return 0;
+
 	if (boot_cpu_has(X86_FEATURE_ARAT))
 		return 0;
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 05d5fec64a9..dca2802c666 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -212,25 +212,6 @@ static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
 
-/*
- * Store a breakpoint's encoded address, length, and type.
- */
-static int arch_store_info(struct perf_event *bp)
-{
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)
-				kallsyms_lookup_name(info->name);
-	if (info->address)
-		return 0;
-
-	return -EINVAL;
-}
-
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
@@ -362,10 +343,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp,
 		return ret;
 	}
 
-	ret = arch_store_info(bp);
-
-	if (ret < 0)
-		return ret;
+	/*
+	 * For kernel-addresses, either the address or symbol name can be
+	 * specified.
+	 */
+	if (info->name)
+		info->address = (unsigned long)
+				kallsyms_lookup_name(info->name);
 	/*
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
@@ -502,8 +486,6 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		rcu_read_lock();
 
 		bp = per_cpu(bp_per_reg[i], cpu);
-		if (bp)
-			rc = NOTIFY_DONE;
 		/*
 		 * Reset the 'i'th TRAP bit in dr6 to denote completion of
 		 * exception handling
@@ -522,7 +504,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 
 		rcu_read_unlock();
 	}
-	if (dr6 & (~DR_TRAP_BITS))
+	/*
+	 * Further processing in do_debug() is needed for a) user-space
+	 * breakpoints (to generate signals) and b) when the system has
+	 * taken exception due to multiple causes
+	 */
+	if ((current->thread.debugreg6 & DR_TRAP_BITS) ||
+	    (dr6 & (~DR_TRAP_BITS)))
 		rc = NOTIFY_DONE;
 
 	set_debugreg(dr7, 7);
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index f2f8540a7f3..c01a2b846d4 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -164,6 +164,11 @@ int init_fpu(struct task_struct *tsk)
 	return 0;
 }
 
+/*
+ * The xstateregs_active() routine is the same as the fpregs_active() routine,
+ * as the "regset->n" for the xstate regset will be updated based on the feature
+ * capabilites supported by the xsave.
+ */
 int fpregs_active(struct task_struct *target, const struct user_regset *regset)
 {
 	return tsk_used_math(target) ? regset->n : 0;
@@ -204,8 +209,6 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (ret)
 		return ret;
 
-	set_stopped_child_used_math(target);
-
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &target->thread.xstate->fxsave, 0, -1);
 
@@ -224,6 +227,68 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	return ret;
 }
 
+int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	ret = init_fpu(target);
+	if (ret)
+		return ret;
+
+	/*
+	 * Copy the 48bytes defined by the software first into the xstate
+	 * memory layout in the thread struct, so that we can copy the entire
+	 * xstateregs to the user using one user_regset_copyout().
+	 */
+	memcpy(&target->thread.xstate->fxsave.sw_reserved,
+	       xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
+
+	/*
+	 * Copy the xstate memory layout.
+	 */
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.xstate->xsave, 0, -1);
+	return ret;
+}
+
+int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+	struct xsave_hdr_struct *xsave_hdr;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	ret = init_fpu(target);
+	if (ret)
+		return ret;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.xstate->xsave, 0, -1);
+
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask;
+
+	xsave_hdr = &target->thread.xstate->xsave.xsave_hdr;
+
+	xsave_hdr->xstate_bv &= pcntxt_mask;
+	/*
+	 * These bits must be zero.
+	 */
+	xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+
+	return ret;
+}
+
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
 
 /*
@@ -404,8 +469,6 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	if (ret)
 		return ret;
 
-	set_stopped_child_used_math(target);
-
 	if (!HAVE_HWFP)
 		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
 
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index df89102bef8..fb725ee15f5 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -32,8 +32,14 @@
  */
 
 static int i8259A_auto_eoi;
-DEFINE_SPINLOCK(i8259A_lock);
+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",
@@ -63,51 +69,51 @@ 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;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 	cached_irq_mask |= mask;
 	if (irq & 8)
 		outb(cached_slave_mask, PIC_SLAVE_IMR);
 	else
 		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	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;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 	cached_irq_mask &= mask;
 	if (irq & 8)
 		outb(cached_slave_mask, PIC_SLAVE_IMR);
 	else
 		outb(cached_master_mask, PIC_MASTER_IMR);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	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;
 	int ret;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 	if (irq < 8)
 		ret = inb(PIC_MASTER_CMD) & mask;
 	else
 		ret = inb(PIC_SLAVE_CMD) & (mask >> 8);
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 
 	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);
@@ -150,7 +156,7 @@ static void mask_and_ack_8259A(unsigned int irq)
 	unsigned int irqmask = 1 << irq;
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 	/*
 	 * Lightweight spurious IRQ detection. We do not want
 	 * to overdo spurious IRQ handling - it's usually a sign
@@ -183,7 +189,7 @@ handle_real_irq:
 		outb(cached_master_mask, PIC_MASTER_IMR);
 		outb(0x60+irq, PIC_MASTER_CMD);	/* 'Specific EOI to master */
 	}
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 	return;
 
 spurious_8259A_irq:
@@ -281,37 +287,37 @@ static int __init i8259A_init_sysfs(void)
 
 device_initcall(i8259A_init_sysfs);
 
-void mask_8259A(void)
+static void mask_8259A(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
 	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
 	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
 
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-void unmask_8259A(void)
+static void unmask_8259A(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
 	outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
 	outb(cached_slave_mask, PIC_SLAVE_IMR);	  /* restore slave IRQ mask */
 
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-void init_8259A(int auto_eoi)
+static void init_8259A(int auto_eoi)
 {
 	unsigned long flags;
 
 	i8259A_auto_eoi = auto_eoi;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
 	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
 	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
@@ -356,5 +362,49 @@ void init_8259A(int auto_eoi)
 	outb(cached_master_mask, PIC_MASTER_IMR); /* restore master IRQ mask */
 	outb(cached_slave_mask, PIC_SLAVE_IMR);	  /* restore slave IRQ mask */
 
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	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 d5932226614..ef257fc2921 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -84,24 +84,7 @@ static struct irqaction irq2 = {
 };
 
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... IRQ0_VECTOR - 1] = -1,
-	[IRQ0_VECTOR] = 0,
-	[IRQ1_VECTOR] = 1,
-	[IRQ2_VECTOR] = 2,
-	[IRQ3_VECTOR] = 3,
-	[IRQ4_VECTOR] = 4,
-	[IRQ5_VECTOR] = 5,
-	[IRQ6_VECTOR] = 6,
-	[IRQ7_VECTOR] = 7,
-	[IRQ8_VECTOR] = 8,
-	[IRQ9_VECTOR] = 9,
-	[IRQ10_VECTOR] = 10,
-	[IRQ11_VECTOR] = 11,
-	[IRQ12_VECTOR] = 12,
-	[IRQ13_VECTOR] = 13,
-	[IRQ14_VECTOR] = 14,
-	[IRQ15_VECTOR] = 15,
-	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
+	[0 ... NR_VECTORS - 1] = -1,
 };
 
 int vector_used_by_percpu_irq(unsigned int vector)
@@ -123,12 +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;
@@ -142,6 +125,19 @@ void __init init_ISA_irqs(void)
 
 void __init init_IRQ(void)
 {
+	int i;
+
+	/*
+	 * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
+	 * If these IRQ's are handled by legacy interrupt-controllers like PIC,
+	 * then this configuration will likely be static after the boot. If
+	 * these IRQ's are handled by more mordern controllers like IO-APIC,
+	 * then this vector space can be freed and re-used dynamically as the
+	 * irq's migrate etc.
+	 */
+	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/kgdb.c b/arch/x86/kernel/kgdb.c
index dd74fe7273b..bfba6019d76 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -42,6 +42,7 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
@@ -204,40 +205,81 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 
 static struct hw_breakpoint {
 	unsigned		enabled;
-	unsigned		type;
-	unsigned		len;
 	unsigned long		addr;
+	int			len;
+	int			type;
+	struct perf_event	**pev;
 } breakinfo[4];
 
 static void kgdb_correct_hw_break(void)
 {
-	unsigned long dr7;
-	int correctit = 0;
-	int breakbit;
 	int breakno;
 
-	get_debugreg(dr7, 7);
 	for (breakno = 0; breakno < 4; breakno++) {
-		breakbit = 2 << (breakno << 1);
-		if (!(dr7 & breakbit) && breakinfo[breakno].enabled) {
-			correctit = 1;
-			dr7 |= breakbit;
-			dr7 &= ~(0xf0000 << (breakno << 2));
-			dr7 |= ((breakinfo[breakno].len << 2) |
-				 breakinfo[breakno].type) <<
-			       ((breakno << 2) + 16);
-			set_debugreg(breakinfo[breakno].addr, breakno);
-
-		} else {
-			if ((dr7 & breakbit) && !breakinfo[breakno].enabled) {
-				correctit = 1;
-				dr7 &= ~breakbit;
-				dr7 &= ~(0xf0000 << (breakno << 2));
-			}
-		}
+		struct perf_event *bp;
+		struct arch_hw_breakpoint *info;
+		int val;
+		int cpu = raw_smp_processor_id();
+		if (!breakinfo[breakno].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		info = counter_arch_bp(bp);
+		if (bp->attr.disabled != 1)
+			continue;
+		bp->attr.bp_addr = breakinfo[breakno].addr;
+		bp->attr.bp_len = breakinfo[breakno].len;
+		bp->attr.bp_type = breakinfo[breakno].type;
+		info->address = breakinfo[breakno].addr;
+		info->len = breakinfo[breakno].len;
+		info->type = breakinfo[breakno].type;
+		val = arch_install_hw_breakpoint(bp);
+		if (!val)
+			bp->attr.disabled = 0;
+	}
+	hw_breakpoint_restore();
+}
+
+static int hw_break_reserve_slot(int breakno)
+{
+	int cpu;
+	int cnt = 0;
+	struct perf_event **pevent;
+
+	for_each_online_cpu(cpu) {
+		cnt++;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_reserve_bp_slot(*pevent))
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	for_each_online_cpu(cpu) {
+		cnt--;
+		if (!cnt)
+			break;
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		dbg_release_bp_slot(*pevent);
 	}
-	if (correctit)
-		set_debugreg(dr7, 7);
+	return -1;
+}
+
+static int hw_break_release_slot(int breakno)
+{
+	struct perf_event **pevent;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		pevent = per_cpu_ptr(breakinfo[breakno].pev, cpu);
+		if (dbg_release_bp_slot(*pevent))
+			/*
+			 * The debugger is responisble for handing the retry on
+			 * remove failure.
+			 */
+			return -1;
+	}
+	return 0;
 }
 
 static int
@@ -251,6 +293,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 	if (i == 4)
 		return -1;
 
+	if (hw_break_release_slot(i)) {
+		printk(KERN_ERR "Cannot remove hw breakpoint at %lx\n", addr);
+		return -1;
+	}
 	breakinfo[i].enabled = 0;
 
 	return 0;
@@ -259,15 +305,23 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 static void kgdb_remove_all_hw_break(void)
 {
 	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
 
-	for (i = 0; i < 4; i++)
-		memset(&breakinfo[i], 0, sizeof(struct hw_breakpoint));
+	for (i = 0; i < 4; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled == 1)
+			continue;
+		arch_uninstall_hw_breakpoint(bp);
+		bp->attr.disabled = 1;
+	}
 }
 
 static int
 kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 {
-	unsigned type;
 	int i;
 
 	for (i = 0; i < 4; i++)
@@ -278,27 +332,42 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
 
 	switch (bptype) {
 	case BP_HARDWARE_BREAKPOINT:
-		type = 0;
-		len  = 1;
+		len = 1;
+		breakinfo[i].type = X86_BREAKPOINT_EXECUTE;
 		break;
 	case BP_WRITE_WATCHPOINT:
-		type = 1;
+		breakinfo[i].type = X86_BREAKPOINT_WRITE;
 		break;
 	case BP_ACCESS_WATCHPOINT:
-		type = 3;
+		breakinfo[i].type = X86_BREAKPOINT_RW;
 		break;
 	default:
 		return -1;
 	}
-
-	if (len == 1 || len == 2 || len == 4)
-		breakinfo[i].len  = len - 1;
-	else
+	switch (len) {
+	case 1:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_1;
+		break;
+	case 2:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_2;
+		break;
+	case 4:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_4;
+		break;
+#ifdef CONFIG_X86_64
+	case 8:
+		breakinfo[i].len = X86_BREAKPOINT_LEN_8;
+		break;
+#endif
+	default:
 		return -1;
-
-	breakinfo[i].enabled = 1;
+	}
 	breakinfo[i].addr = addr;
-	breakinfo[i].type = type;
+	if (hw_break_reserve_slot(i)) {
+		breakinfo[i].addr = 0;
+		return -1;
+	}
+	breakinfo[i].enabled = 1;
 
 	return 0;
 }
@@ -313,8 +382,21 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype)
  */
 void kgdb_disable_hw_debug(struct pt_regs *regs)
 {
+	int i;
+	int cpu = raw_smp_processor_id();
+	struct perf_event *bp;
+
 	/* Disable hardware debugging while we are in kgdb: */
 	set_debugreg(0UL, 7);
+	for (i = 0; i < 4; i++) {
+		if (!breakinfo[i].enabled)
+			continue;
+		bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
+		if (bp->attr.disabled == 1)
+			continue;
+		arch_uninstall_hw_breakpoint(bp);
+		bp->attr.disabled = 1;
+	}
 }
 
 /**
@@ -378,7 +460,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 			       struct pt_regs *linux_regs)
 {
 	unsigned long addr;
-	unsigned long dr6;
 	char *ptr;
 	int newPC;
 
@@ -404,20 +485,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 				   raw_smp_processor_id());
 		}
 
-		get_debugreg(dr6, 6);
-		if (!(dr6 & 0x4000)) {
-			int breakno;
-
-			for (breakno = 0; breakno < 4; breakno++) {
-				if (dr6 & (1 << breakno) &&
-				    breakinfo[breakno].type == 0) {
-					/* Set restore flag: */
-					linux_regs->flags |= X86_EFLAGS_RF;
-					break;
-				}
-			}
-		}
-		set_debugreg(0UL, 6);
 		kgdb_correct_hw_break();
 
 		return 0;
@@ -485,8 +552,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 		break;
 
 	case DIE_DEBUG:
-		if (atomic_read(&kgdb_cpu_doing_single_step) ==
-		    raw_smp_processor_id()) {
+		if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
 			if (user_mode(regs))
 				return single_step_cont(regs, args);
 			break;
@@ -539,7 +605,42 @@ static struct notifier_block kgdb_notifier = {
  */
 int kgdb_arch_init(void)
 {
-	return register_die_notifier(&kgdb_notifier);
+	int i, cpu;
+	int ret;
+	struct perf_event_attr attr;
+	struct perf_event **pevent;
+
+	ret = register_die_notifier(&kgdb_notifier);
+	if (ret != 0)
+		return ret;
+	/*
+	 * Pre-allocate the hw breakpoint structions in the non-atomic
+	 * portion of kgdb because this operation requires mutexs to
+	 * complete.
+	 */
+	attr.bp_addr = (unsigned long)kgdb_arch_init;
+	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.bp_len = HW_BREAKPOINT_LEN_1;
+	attr.bp_type = HW_BREAKPOINT_W;
+	attr.disabled = 1;
+	for (i = 0; i < 4; i++) {
+		breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL);
+		if (IS_ERR(breakinfo[i].pev)) {
+			printk(KERN_ERR "kgdb: Could not allocate hw breakpoints\n");
+			breakinfo[i].pev = NULL;
+			kgdb_arch_exit();
+			return -1;
+		}
+		for_each_online_cpu(cpu) {
+			pevent = per_cpu_ptr(breakinfo[i].pev, cpu);
+			pevent[0]->hw.sample_period = 1;
+			if (pevent[0]->destroy != NULL) {
+				pevent[0]->destroy = NULL;
+				release_bp_slot(*pevent);
+			}
+		}
+	}
+	return ret;
 }
 
 /**
@@ -550,6 +651,13 @@ int kgdb_arch_init(void)
  */
 void kgdb_arch_exit(void)
 {
+	int i;
+	for (i = 0; i < 4; i++) {
+		if (breakinfo[i].pev) {
+			unregister_wide_hw_breakpoint(breakinfo[i].pev);
+			breakinfo[i].pev = NULL;
+		}
+	}
 	unregister_die_notifier(&kgdb_notifier);
 }
 
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 5b8c7505b3b..b43bbaebe2c 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -49,6 +49,7 @@
 #include <linux/module.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/ftrace.h>
 
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
@@ -106,16 +107,22 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {
 };
 const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
 
-/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
-static void __kprobes set_jmp_op(void *from, void *to)
+static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
 {
-	struct __arch_jmp_op {
-		char op;
+	struct __arch_relative_insn {
+		u8 op;
 		s32 raddr;
-	} __attribute__((packed)) * jop;
-	jop = (struct __arch_jmp_op *)from;
-	jop->raddr = (s32)((long)(to) - ((long)(from) + 5));
-	jop->op = RELATIVEJUMP_INSTRUCTION;
+	} __attribute__((packed)) *insn;
+
+	insn = (struct __arch_relative_insn *)from;
+	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
+	insn->op = op;
+}
+
+/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
+static void __kprobes synthesize_reljump(void *from, void *to)
+{
+	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
 }
 
 /*
@@ -202,7 +209,7 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 	/*
 	 *  Basically, kp->ainsn.insn has an original instruction.
 	 *  However, RIP-relative instruction can not do single-stepping
-	 *  at different place, fix_riprel() tweaks the displacement of
+	 *  at different place, __copy_instruction() tweaks the displacement of
 	 *  that instruction. In that case, we can't recover the instruction
 	 *  from the kp->ainsn.insn.
 	 *
@@ -284,21 +291,37 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
 }
 
 /*
- * Adjust the displacement if the instruction uses the %rip-relative
- * addressing mode.
+ * Copy an instruction and adjust the displacement if the instruction
+ * uses the %rip-relative addressing mode.
  * If it does, Return the address of the 32-bit displacement word.
  * If not, return null.
  * Only applicable to 64-bit x86.
  */
-static void __kprobes fix_riprel(struct kprobe *p)
+static int __kprobes __copy_instruction(u8 *dest, u8 *src, int recover)
 {
-#ifdef CONFIG_X86_64
 	struct insn insn;
-	kernel_insn_init(&insn, p->ainsn.insn);
+	int ret;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
+	kernel_insn_init(&insn, src);
+	if (recover) {
+		insn_get_opcode(&insn);
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
+			ret = recover_probed_instruction(buf,
+							 (unsigned long)src);
+			if (ret)
+				return 0;
+			kernel_insn_init(&insn, buf);
+		}
+	}
+	insn_get_length(&insn);
+	memcpy(dest, insn.kaddr, insn.length);
+
+#ifdef CONFIG_X86_64
 	if (insn_rip_relative(&insn)) {
 		s64 newdisp;
 		u8 *disp;
+		kernel_insn_init(&insn, dest);
 		insn_get_displacement(&insn);
 		/*
 		 * The copied instruction uses the %rip-relative addressing
@@ -312,20 +335,23 @@ static void __kprobes fix_riprel(struct kprobe *p)
 		 * extension of the original signed 32-bit displacement would
 		 * have given.
 		 */
-		newdisp = (u8 *) p->addr + (s64) insn.displacement.value -
-			  (u8 *) p->ainsn.insn;
+		newdisp = (u8 *) src + (s64) insn.displacement.value -
+			  (u8 *) dest;
 		BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check.  */
-		disp = (u8 *) p->ainsn.insn + insn_offset_displacement(&insn);
+		disp = (u8 *) dest + insn_offset_displacement(&insn);
 		*(s32 *) disp = (s32) newdisp;
 	}
 #endif
+	return insn.length;
 }
 
 static void __kprobes arch_copy_kprobe(struct kprobe *p)
 {
-	memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-
-	fix_riprel(p);
+	/*
+	 * Copy an instruction without recovering int3, because it will be
+	 * put by another subsystem.
+	 */
+	__copy_instruction(p->ainsn.insn, p->addr, 0);
 
 	if (can_boost(p->addr))
 		p->ainsn.boostable = 0;
@@ -337,6 +363,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
+	if (alternatives_text_reserved(p->addr, p->addr))
+		return -EINVAL;
+
 	if (!can_probe((unsigned long)p->addr))
 		return -EILSEQ;
 	/* insn: must be on special executable page on x86. */
@@ -403,18 +432,6 @@ static void __kprobes restore_btf(void)
 		update_debugctlmsr(current->thread.debugctlmsr);
 }
 
-static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
-{
-	clear_btf();
-	regs->flags |= X86_EFLAGS_TF;
-	regs->flags &= ~X86_EFLAGS_IF;
-	/* single step inline if the instruction is an int3 */
-	if (p->opcode == BREAKPOINT_INSTRUCTION)
-		regs->ip = (unsigned long)p->addr;
-	else
-		regs->ip = (unsigned long)p->ainsn.insn;
-}
-
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
@@ -426,20 +443,50 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	*sara = (unsigned long) &kretprobe_trampoline;
 }
 
+#ifdef CONFIG_OPTPROBES
+static int  __kprobes setup_detour_execution(struct kprobe *p,
+					     struct pt_regs *regs,
+					     int reenter);
+#else
+#define setup_detour_execution(p, regs, reenter) (0)
+#endif
+
 static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs,
-				       struct kprobe_ctlblk *kcb)
+				       struct kprobe_ctlblk *kcb, int reenter)
 {
-#if !defined(CONFIG_PREEMPT) || defined(CONFIG_FREEZER)
+	if (setup_detour_execution(p, regs, reenter))
+		return;
+
+#if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.boostable == 1 && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
-		reset_current_kprobe();
+		if (!reenter)
+			reset_current_kprobe();
+		/*
+		 * Reentering boosted probe doesn't reset current_kprobe,
+		 * nor set current_kprobe, because it doesn't use single
+		 * stepping.
+		 */
 		regs->ip = (unsigned long)p->ainsn.insn;
 		preempt_enable_no_resched();
 		return;
 	}
 #endif
-	prepare_singlestep(p, regs);
-	kcb->kprobe_status = KPROBE_HIT_SS;
+	if (reenter) {
+		save_previous_kprobe(kcb);
+		set_current_kprobe(p, regs, kcb);
+		kcb->kprobe_status = KPROBE_REENTER;
+	} else
+		kcb->kprobe_status = KPROBE_HIT_SS;
+	/* Prepare real single stepping */
+	clear_btf();
+	regs->flags |= X86_EFLAGS_TF;
+	regs->flags &= ~X86_EFLAGS_IF;
+	/* single step inline if the instruction is an int3 */
+	if (p->opcode == BREAKPOINT_INSTRUCTION)
+		regs->ip = (unsigned long)p->addr;
+	else
+		regs->ip = (unsigned long)p->ainsn.insn;
 }
 
 /*
@@ -453,11 +500,8 @@ static int __kprobes reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
 	case KPROBE_HIT_ACTIVE:
-		save_previous_kprobe(kcb);
-		set_current_kprobe(p, regs, kcb);
 		kprobes_inc_nmissed_count(p);
-		prepare_singlestep(p, regs);
-		kcb->kprobe_status = KPROBE_REENTER;
+		setup_singlestep(p, regs, kcb, 1);
 		break;
 	case KPROBE_HIT_SS:
 		/* A probe has been hit in the codepath leading up to, or just
@@ -532,13 +576,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			 * more here.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
-				setup_singlestep(p, regs, kcb);
+				setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
 	} else if (kprobe_running()) {
 		p = __get_cpu_var(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
-			setup_singlestep(p, regs, kcb);
+			setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
 	} /* else: not a kprobe fault; let the kernel handle it */
@@ -547,6 +591,69 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	return 0;
 }
 
+#ifdef CONFIG_X86_64
+#define SAVE_REGS_STRING		\
+	/* Skip cs, ip, orig_ax. */	\
+	"	subq $24, %rsp\n"	\
+	"	pushq %rdi\n"		\
+	"	pushq %rsi\n"		\
+	"	pushq %rdx\n"		\
+	"	pushq %rcx\n"		\
+	"	pushq %rax\n"		\
+	"	pushq %r8\n"		\
+	"	pushq %r9\n"		\
+	"	pushq %r10\n"		\
+	"	pushq %r11\n"		\
+	"	pushq %rbx\n"		\
+	"	pushq %rbp\n"		\
+	"	pushq %r12\n"		\
+	"	pushq %r13\n"		\
+	"	pushq %r14\n"		\
+	"	pushq %r15\n"
+#define RESTORE_REGS_STRING		\
+	"	popq %r15\n"		\
+	"	popq %r14\n"		\
+	"	popq %r13\n"		\
+	"	popq %r12\n"		\
+	"	popq %rbp\n"		\
+	"	popq %rbx\n"		\
+	"	popq %r11\n"		\
+	"	popq %r10\n"		\
+	"	popq %r9\n"		\
+	"	popq %r8\n"		\
+	"	popq %rax\n"		\
+	"	popq %rcx\n"		\
+	"	popq %rdx\n"		\
+	"	popq %rsi\n"		\
+	"	popq %rdi\n"		\
+	/* Skip orig_ax, ip, cs */	\
+	"	addq $24, %rsp\n"
+#else
+#define SAVE_REGS_STRING		\
+	/* Skip cs, ip, orig_ax and gs. */	\
+	"	subl $16, %esp\n"	\
+	"	pushl %fs\n"		\
+	"	pushl %ds\n"		\
+	"	pushl %es\n"		\
+	"	pushl %eax\n"		\
+	"	pushl %ebp\n"		\
+	"	pushl %edi\n"		\
+	"	pushl %esi\n"		\
+	"	pushl %edx\n"		\
+	"	pushl %ecx\n"		\
+	"	pushl %ebx\n"
+#define RESTORE_REGS_STRING		\
+	"	popl %ebx\n"		\
+	"	popl %ecx\n"		\
+	"	popl %edx\n"		\
+	"	popl %esi\n"		\
+	"	popl %edi\n"		\
+	"	popl %ebp\n"		\
+	"	popl %eax\n"		\
+	/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
+	"	addl $24, %esp\n"
+#endif
+
 /*
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
@@ -560,65 +667,16 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			/* We don't bother saving the ss register */
 			"	pushq %rsp\n"
 			"	pushfq\n"
-			/*
-			 * Skip cs, ip, orig_ax.
-			 * trampoline_handler() will plug in these values
-			 */
-			"	subq $24, %rsp\n"
-			"	pushq %rdi\n"
-			"	pushq %rsi\n"
-			"	pushq %rdx\n"
-			"	pushq %rcx\n"
-			"	pushq %rax\n"
-			"	pushq %r8\n"
-			"	pushq %r9\n"
-			"	pushq %r10\n"
-			"	pushq %r11\n"
-			"	pushq %rbx\n"
-			"	pushq %rbp\n"
-			"	pushq %r12\n"
-			"	pushq %r13\n"
-			"	pushq %r14\n"
-			"	pushq %r15\n"
+			SAVE_REGS_STRING
 			"	movq %rsp, %rdi\n"
 			"	call trampoline_handler\n"
 			/* Replace saved sp with true return address. */
 			"	movq %rax, 152(%rsp)\n"
-			"	popq %r15\n"
-			"	popq %r14\n"
-			"	popq %r13\n"
-			"	popq %r12\n"
-			"	popq %rbp\n"
-			"	popq %rbx\n"
-			"	popq %r11\n"
-			"	popq %r10\n"
-			"	popq %r9\n"
-			"	popq %r8\n"
-			"	popq %rax\n"
-			"	popq %rcx\n"
-			"	popq %rdx\n"
-			"	popq %rsi\n"
-			"	popq %rdi\n"
-			/* Skip orig_ax, ip, cs */
-			"	addq $24, %rsp\n"
+			RESTORE_REGS_STRING
 			"	popfq\n"
 #else
 			"	pushf\n"
-			/*
-			 * Skip cs, ip, orig_ax and gs.
-			 * trampoline_handler() will plug in these values
-			 */
-			"	subl $16, %esp\n"
-			"	pushl %fs\n"
-			"	pushl %es\n"
-			"	pushl %ds\n"
-			"	pushl %eax\n"
-			"	pushl %ebp\n"
-			"	pushl %edi\n"
-			"	pushl %esi\n"
-			"	pushl %edx\n"
-			"	pushl %ecx\n"
-			"	pushl %ebx\n"
+			SAVE_REGS_STRING
 			"	movl %esp, %eax\n"
 			"	call trampoline_handler\n"
 			/* Move flags to cs */
@@ -626,15 +684,7 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 			"	movl %edx, 52(%esp)\n"
 			/* Replace saved flags with true return address. */
 			"	movl %eax, 56(%esp)\n"
-			"	popl %ebx\n"
-			"	popl %ecx\n"
-			"	popl %edx\n"
-			"	popl %esi\n"
-			"	popl %edi\n"
-			"	popl %ebp\n"
-			"	popl %eax\n"
-			/* Skip ds, es, fs, gs, orig_ax and ip */
-			"	addl $24, %esp\n"
+			RESTORE_REGS_STRING
 			"	popf\n"
 #endif
 			"	ret\n");
@@ -802,8 +852,8 @@ static void __kprobes resume_execution(struct kprobe *p,
 			 * These instructions can be executed directly if it
 			 * jumps back to correct address.
 			 */
-			set_jmp_op((void *)regs->ip,
-				   (void *)orig_ip + (regs->ip - copy_ip));
+			synthesize_reljump((void *)regs->ip,
+				(void *)orig_ip + (regs->ip - copy_ip));
 			p->ainsn.boostable = 1;
 		} else {
 			p->ainsn.boostable = -1;
@@ -1030,6 +1080,358 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	return 0;
 }
 
+
+#ifdef CONFIG_OPTPROBES
+
+/* Insert a call instruction at address 'from', which calls address 'to'.*/
+static void __kprobes synthesize_relcall(void *from, void *to)
+{
+	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
+}
+
+/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
+static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr,
+					  unsigned long val)
+{
+#ifdef CONFIG_X86_64
+	*addr++ = 0x48;
+	*addr++ = 0xbf;
+#else
+	*addr++ = 0xb8;
+#endif
+	*(unsigned long *)addr = val;
+}
+
+void __kprobes kprobes_optinsn_template_holder(void)
+{
+	asm volatile (
+			".global optprobe_template_entry\n"
+			"optprobe_template_entry: \n"
+#ifdef CONFIG_X86_64
+			/* We don't bother saving the ss register */
+			"	pushq %rsp\n"
+			"	pushfq\n"
+			SAVE_REGS_STRING
+			"	movq %rsp, %rsi\n"
+			".global optprobe_template_val\n"
+			"optprobe_template_val: \n"
+			ASM_NOP5
+			ASM_NOP5
+			".global optprobe_template_call\n"
+			"optprobe_template_call: \n"
+			ASM_NOP5
+			/* Move flags to rsp */
+			"	movq 144(%rsp), %rdx\n"
+			"	movq %rdx, 152(%rsp)\n"
+			RESTORE_REGS_STRING
+			/* Skip flags entry */
+			"	addq $8, %rsp\n"
+			"	popfq\n"
+#else /* CONFIG_X86_32 */
+			"	pushf\n"
+			SAVE_REGS_STRING
+			"	movl %esp, %edx\n"
+			".global optprobe_template_val\n"
+			"optprobe_template_val: \n"
+			ASM_NOP5
+			".global optprobe_template_call\n"
+			"optprobe_template_call: \n"
+			ASM_NOP5
+			RESTORE_REGS_STRING
+			"	addl $4, %esp\n"	/* skip cs */
+			"	popf\n"
+#endif
+			".global optprobe_template_end\n"
+			"optprobe_template_end: \n");
+}
+
+#define TMPL_MOVE_IDX \
+	((long)&optprobe_template_val - (long)&optprobe_template_entry)
+#define TMPL_CALL_IDX \
+	((long)&optprobe_template_call - (long)&optprobe_template_entry)
+#define TMPL_END_IDX \
+	((long)&optprobe_template_end - (long)&optprobe_template_entry)
+
+#define INT3_SIZE sizeof(kprobe_opcode_t)
+
+/* Optimized kprobe call back function: called from optinsn */
+static void __kprobes optimized_callback(struct optimized_kprobe *op,
+					 struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+	preempt_disable();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(&op->kp);
+	} else {
+		/* Save skipped registers */
+#ifdef CONFIG_X86_64
+		regs->cs = __KERNEL_CS;
+#else
+		regs->cs = __KERNEL_CS | get_kernel_rpl();
+		regs->gs = 0;
+#endif
+		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;
+		regs->orig_ax = ~0UL;
+
+		__get_cpu_var(current_kprobe) = &op->kp;
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		opt_pre_handler(&op->kp, regs);
+		__get_cpu_var(current_kprobe) = NULL;
+	}
+	preempt_enable_no_resched();
+}
+
+static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
+{
+	int len = 0, ret;
+
+	while (len < RELATIVEJUMP_SIZE) {
+		ret = __copy_instruction(dest + len, src + len, 1);
+		if (!ret || !can_boost(dest + len))
+			return -EINVAL;
+		len += ret;
+	}
+	/* Check whether the address range is reserved */
+	if (ftrace_text_reserved(src, src + len - 1) ||
+	    alternatives_text_reserved(src, src + len - 1))
+		return -EBUSY;
+
+	return len;
+}
+
+/* Check whether insn is indirect jump */
+static int __kprobes insn_is_indirect_jump(struct insn *insn)
+{
+	return ((insn->opcode.bytes[0] == 0xff &&
+		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
+		insn->opcode.bytes[0] == 0xea);	/* Segment based jump */
+}
+
+/* Check whether insn jumps into specified address range */
+static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
+{
+	unsigned long target = 0;
+
+	switch (insn->opcode.bytes[0]) {
+	case 0xe0:	/* loopne */
+	case 0xe1:	/* loope */
+	case 0xe2:	/* loop */
+	case 0xe3:	/* jcxz */
+	case 0xe9:	/* near relative jump */
+	case 0xeb:	/* short relative jump */
+		break;
+	case 0x0f:
+		if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */
+			break;
+		return 0;
+	default:
+		if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */
+			break;
+		return 0;
+	}
+	target = (unsigned long)insn->next_byte + insn->immediate.value;
+
+	return (start <= target && target <= start + len);
+}
+
+/* Decode whole function to ensure any instructions don't jump into target */
+static int __kprobes can_optimize(unsigned long paddr)
+{
+	int ret;
+	unsigned long addr, size = 0, offset = 0;
+	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
+	/* Dummy buffers for lookup_symbol_attrs */
+	static char __dummy_buf[KSYM_NAME_LEN];
+
+	/* Lookup symbol including addr */
+	if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf))
+		return 0;
+
+	/* Check there is enough space for a relative jump. */
+	if (size - offset < RELATIVEJUMP_SIZE)
+		return 0;
+
+	/* Decode instructions */
+	addr = paddr - offset;
+	while (addr < paddr - offset + size) { /* Decode until function end */
+		if (search_exception_tables(addr))
+			/*
+			 * Since some fixup code will jumps into this function,
+			 * we can't optimize kprobe in this function.
+			 */
+			return 0;
+		kernel_insn_init(&insn, (void *)addr);
+		insn_get_opcode(&insn);
+		if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) {
+			ret = recover_probed_instruction(buf, addr);
+			if (ret)
+				return 0;
+			kernel_insn_init(&insn, buf);
+		}
+		insn_get_length(&insn);
+		/* Recover address */
+		insn.kaddr = (void *)addr;
+		insn.next_byte = (void *)(addr + insn.length);
+		/* Check any instructions don't jump into target */
+		if (insn_is_indirect_jump(&insn) ||
+		    insn_jump_into_range(&insn, paddr + INT3_SIZE,
+					 RELATIVE_ADDR_SIZE))
+			return 0;
+		addr += insn.length;
+	}
+
+	return 1;
+}
+
+/* Check optimized_kprobe can actually be optimized. */
+int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
+{
+	int i;
+	struct kprobe *p;
+
+	for (i = 1; i < op->optinsn.size; i++) {
+		p = get_kprobe(op->kp.addr + i);
+		if (p && !kprobe_disabled(p))
+			return -EEXIST;
+	}
+
+	return 0;
+}
+
+/* Check the addr is within the optimized instructions. */
+int __kprobes arch_within_optimized_kprobe(struct optimized_kprobe *op,
+					   unsigned long addr)
+{
+	return ((unsigned long)op->kp.addr <= addr &&
+		(unsigned long)op->kp.addr + op->optinsn.size > addr);
+}
+
+/* Free optimized instruction slot */
+static __kprobes
+void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
+{
+	if (op->optinsn.insn) {
+		free_optinsn_slot(op->optinsn.insn, dirty);
+		op->optinsn.insn = NULL;
+		op->optinsn.size = 0;
+	}
+}
+
+void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
+{
+	__arch_remove_optimized_kprobe(op, 1);
+}
+
+/*
+ * Copy replacing target instructions
+ * Target instructions MUST be relocatable (checked inside)
+ */
+int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
+{
+	u8 *buf;
+	int ret;
+	long rel;
+
+	if (!can_optimize((unsigned long)op->kp.addr))
+		return -EILSEQ;
+
+	op->optinsn.insn = get_optinsn_slot();
+	if (!op->optinsn.insn)
+		return -ENOMEM;
+
+	/*
+	 * Verify if the address gap is in 2GB range, because this uses
+	 * a relative jump.
+	 */
+	rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE;
+	if (abs(rel) > 0x7fffffff)
+		return -ERANGE;
+
+	buf = (u8 *)op->optinsn.insn;
+
+	/* Copy instructions into the out-of-line buffer */
+	ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
+	if (ret < 0) {
+		__arch_remove_optimized_kprobe(op, 0);
+		return ret;
+	}
+	op->optinsn.size = ret;
+
+	/* Copy arch-dep-instance from template */
+	memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
+
+	/* Set probe information */
+	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
+
+	/* Set probe function call */
+	synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback);
+
+	/* Set returning jmp instruction at the tail of out-of-line buffer */
+	synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
+			   (u8 *)op->kp.addr + op->optinsn.size);
+
+	flush_icache_range((unsigned long) buf,
+			   (unsigned long) buf + TMPL_END_IDX +
+			   op->optinsn.size + RELATIVEJUMP_SIZE);
+	return 0;
+}
+
+/* Replace a breakpoint (int3) with a relative jump.  */
+int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
+{
+	unsigned char jmp_code[RELATIVEJUMP_SIZE];
+	s32 rel = (s32)((long)op->optinsn.insn -
+			((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
+	/* Backup instructions which will be replaced by jump address */
+	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
+	       RELATIVE_ADDR_SIZE);
+
+	jmp_code[0] = RELATIVEJUMP_OPCODE;
+	*(s32 *)(&jmp_code[1]) = rel;
+
+	/*
+	 * text_poke_smp doesn't support NMI/MCE code modifying.
+	 * However, since kprobes itself also doesn't support NMI/MCE
+	 * code probing, it's not a problem.
+	 */
+	text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE);
+	return 0;
+}
+
+/* Replace a relative jump with a breakpoint (int3).  */
+void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
+{
+	u8 buf[RELATIVEJUMP_SIZE];
+
+	/* Set int3 to first byte for kprobes */
+	buf[0] = BREAKPOINT_INSTRUCTION;
+	memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+	text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
+}
+
+static int  __kprobes setup_detour_execution(struct kprobe *p,
+					     struct pt_regs *regs,
+					     int reenter)
+{
+	struct optimized_kprobe *op;
+
+	if (p->flags & KPROBE_FLAG_OPTIMIZED) {
+		/* This kprobe is really able to run optimized path. */
+		op = container_of(p, struct optimized_kprobe, kp);
+		/* Detour through copied instructions */
+		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
+		if (!reenter)
+			reset_current_kprobe();
+		preempt_enable_no_resched();
+		return 1;
+	}
+	return 0;
+}
+#endif
+
 int __init arch_init_kprobes(void)
 {
 	return 0;
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 37542b67c57..e1af7c055c7 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -36,9 +36,6 @@ MODULE_LICENSE("GPL v2");
 #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000
 #define UCODE_UCODE_TYPE           0x00000001
 
-const struct firmware *firmware;
-static int supported_cpu;
-
 struct equiv_cpu_entry {
 	u32	installed_cpu;
 	u32	fixed_errata_mask;
@@ -77,12 +74,15 @@ static struct equiv_cpu_entry *equiv_cpu_table;
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 dummy;
 
-	if (!supported_cpu)
-		return -1;
-
 	memset(csig, 0, sizeof(*csig));
+	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
+		pr_warning("microcode: CPU%d: AMD CPU family 0x%x not "
+			   "supported\n", cpu, c->x86);
+		return -1;
+	}
 	rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
 	pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev);
 	return 0;
@@ -294,10 +294,14 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 {
+	const char *fw_name = "amd-ucode/microcode_amd.bin";
+	const struct firmware *firmware;
 	enum ucode_state ret;
 
-	if (firmware == NULL)
+	if (request_firmware(&firmware, fw_name, device)) {
+		printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
 		return UCODE_NFOUND;
+	}
 
 	if (*(u32 *)firmware->data != UCODE_MAGIC) {
 		pr_err("invalid UCODE_MAGIC (0x%08x)\n",
@@ -307,6 +311,8 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 
 	ret = generic_load_microcode(cpu, firmware->data, firmware->size);
 
+	release_firmware(firmware);
+
 	return ret;
 }
 
@@ -325,31 +331,7 @@ static void microcode_fini_cpu_amd(int cpu)
 	uci->mc = NULL;
 }
 
-void init_microcode_amd(struct device *device)
-{
-	const char *fw_name = "amd-ucode/microcode_amd.bin";
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	WARN_ON(c->x86_vendor != X86_VENDOR_AMD);
-
-	if (c->x86 < 0x10) {
-		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
-		return;
-	}
-	supported_cpu = 1;
-
-	if (request_firmware(&firmware, fw_name, device))
-		pr_err("failed to load file %s\n", fw_name);
-}
-
-void fini_microcode_amd(void)
-{
-	release_firmware(firmware);
-}
-
 static struct microcode_ops microcode_amd_ops = {
-	.init				  = init_microcode_amd,
-	.fini				  = fini_microcode_amd,
 	.request_microcode_user           = request_microcode_user,
 	.request_microcode_fw             = request_microcode_fw,
 	.collect_cpu_info                 = collect_cpu_info_amd,
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 0c863243309..cceb5bc3c3c 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -521,9 +521,6 @@ static int __init microcode_init(void)
 		return PTR_ERR(microcode_pdev);
 	}
 
-	if (microcode_ops->init)
-		microcode_ops->init(&microcode_pdev->dev);
-
 	get_online_cpus();
 	mutex_lock(&microcode_mutex);
 
@@ -566,9 +563,6 @@ static void __exit microcode_exit(void)
 
 	platform_device_unregister(microcode_pdev);
 
-	if (microcode_ops->fini)
-		microcode_ops->fini();
-
 	microcode_ops = NULL;
 
 	pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index ebd193e476c..85a343e2893 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -328,7 +328,7 @@ static int apply_microcode(int cpu)
 		       cpu_num, mc_intel->hdr.rev);
 		return -1;
 	}
-	pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x \n",
+	pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n",
 		cpu_num, val[1],
 		mc_intel->hdr.date & 0xffff,
 		mc_intel->hdr.date >> 24,
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 712d15fdc41..71825806cd4 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -7,6 +7,8 @@
 #include <linux/string.h>
 #include <linux/pci.h>
 #include <linux/dmi.h>
+#include <linux/range.h>
+
 #include <asm/pci-direct.h>
 #include <linux/sort.h>
 #include <asm/io.h>
@@ -30,11 +32,6 @@ static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = {
 	{ 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 },
 };
 
-struct range {
-	u64 start;
-	u64 end;
-};
-
 static int __cpuinit cmp_range(const void *x1, const void *x2)
 {
 	const struct range *r1 = x1;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 40b54ceb68b..a2c1edd2d3a 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -359,13 +359,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 		x86_init.mpparse.mpc_record(1);
 	}
 
-#ifdef CONFIG_X86_BIGSMP
-	generic_bigsmp_probe();
-#endif
-
-	if (apic->setup_apic_routing)
-		apic->setup_apic_routing();
-
 	if (!num_processors)
 		printk(KERN_ERR "MPTABLE: no processors registered!\n");
 	return num_processors;
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/msr.c b/arch/x86/kernel/msr.c
index 4bd93c9b2b2..206735ac8cb 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -285,7 +285,7 @@ static void __exit msr_exit(void)
 	for_each_online_cpu(cpu)
 		msr_device_destroy(cpu);
 	class_destroy(msr_class);
-	unregister_chrdev(MSR_MAJOR, "cpu/msr");
+	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
 	unregister_hotcpu_notifier(&msr_class_cpu_notifier);
 }
 
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/paravirt.c b/arch/x86/kernel/paravirt.c
index 1b1739d1631..1db183ed7c0 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -428,10 +428,6 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.ptep_modify_prot_start = __ptep_modify_prot_start,
 	.ptep_modify_prot_commit = __ptep_modify_prot_commit,
 
-#ifdef CONFIG_HIGHPTE
-	.kmap_atomic_pte = kmap_atomic,
-#endif
-
 #if PAGETABLE_LEVELS >= 3
 #ifdef CONFIG_X86_PAE
 	.set_pte_atomic = native_set_pte_atomic,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 75e14e21f61..1aa966c565f 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -65,7 +65,7 @@ int dma_set_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_64) && !defined(CONFIG_NUMA)
 static __initdata void *dma32_bootmem_ptr;
 static unsigned long dma32_bootmem_size __initdata = (128ULL<<20);
 
@@ -116,14 +116,21 @@ static void __init dma32_free_bootmem(void)
 	dma32_bootmem_ptr = NULL;
 	dma32_bootmem_size = 0;
 }
+#else
+void __init dma32_reserve_bootmem(void)
+{
+}
+static void __init dma32_free_bootmem(void)
+{
+}
+
 #endif
 
 void __init pci_iommu_alloc(void)
 {
-#ifdef CONFIG_X86_64
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
-#endif
+
 	if (pci_swiotlb_detect())
 		goto out;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 02c3ee013cc..02d678065d7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -92,6 +92,13 @@ void exit_thread(void)
 	}
 }
 
+void show_regs(struct pt_regs *regs)
+{
+	show_registers(regs);
+	show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs),
+		   regs->bp);
+}
+
 void show_regs_common(void)
 {
 	const char *board, *product;
@@ -115,18 +122,6 @@ void flush_thread(void)
 {
 	struct task_struct *tsk = current;
 
-#ifdef CONFIG_X86_64
-	if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
-		clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
-		if (test_tsk_thread_flag(tsk, TIF_IA32)) {
-			clear_tsk_thread_flag(tsk, TIF_IA32);
-		} else {
-			set_tsk_thread_flag(tsk, TIF_IA32);
-			current_thread_info()->status |= TS_COMPAT;
-		}
-	}
-#endif
-
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 	/*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 37ad1e046aa..f6c62667e30 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -174,12 +174,6 @@ void __show_regs(struct pt_regs *regs, int all)
 			d6, d7);
 }
 
-void show_regs(struct pt_regs *regs)
-{
-	show_registers(regs);
-	show_trace(NULL, regs, &regs->sp, regs->bp);
-}
-
 void release_thread(struct task_struct *dead_task)
 {
 	BUG_ON(dead_task->mm);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index f9e033150cd..dc9690b4c4c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -211,12 +211,6 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
 }
 
-void show_regs(struct pt_regs *regs)
-{
-	show_registers(regs);
-	show_trace(NULL, regs, (void *)(regs + 1), regs->bp);
-}
-
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
@@ -521,6 +515,18 @@ void set_personality_64bit(void)
 	current->personality &= ~READ_IMPLIES_EXEC;
 }
 
+void set_personality_ia32(void)
+{
+	/* inherit personality from parent */
+
+	/* Make sure to be in 32bit mode */
+	set_thread_flag(TIF_IA32);
+	current->personality |= force_personality32;
+
+	/* Prepare the first "return" to user space */
+	current_thread_info()->status |= TS_COMPAT;
+}
+
 unsigned long get_wchan(struct task_struct *p)
 {
 	unsigned long stack;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 017d937639f..2d96aab82a4 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -48,6 +48,7 @@ enum x86_regset {
 	REGSET_FP,
 	REGSET_XFP,
 	REGSET_IOPERM64 = REGSET_XFP,
+	REGSET_XSTATE,
 	REGSET_TLS,
 	REGSET_IOPERM32,
 };
@@ -140,30 +141,6 @@ static const int arg_offs_table[] = {
 #endif
 };
 
-/**
- * regs_get_argument_nth() - get Nth argument at function call
- * @regs:	pt_regs which contains registers at function entry.
- * @n:		argument number.
- *
- * regs_get_argument_nth() returns @n th argument of a function call.
- * Since usually the kernel stack will be changed right after function entry,
- * you must use this at function entry. If the @n th entry is NOT in the
- * kernel stack or pt_regs, this returns 0.
- */
-unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n)
-{
-	if (n < ARRAY_SIZE(arg_offs_table))
-		return *(unsigned long *)((char *)regs + arg_offs_table[n]);
-	else {
-		/*
-		 * The typical case: arg n is on the stack.
-		 * (Note: stack[0] = return address, so skip it)
-		 */
-		n -= ARRAY_SIZE(arg_offs_table);
-		return regs_get_kernel_stack_nth(regs, 1 + n);
-	}
-}
-
 /*
  * does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.
@@ -702,7 +679,7 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
 	} else if (n == 6) {
 		val = thread->debugreg6;
 	 } else if (n == 7) {
-		val = ptrace_get_dr7(thread->ptrace_bps);
+		val = thread->ptrace_dr7;
 	}
 	return val;
 }
@@ -778,8 +755,11 @@ int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val)
 			return rc;
 	}
 	/* All that's left is DR7 */
-	if (n == 7)
+	if (n == 7) {
 		rc = ptrace_write_dr7(tsk, val);
+		if (!rc)
+			thread->ptrace_dr7 = val;
+	}
 
 ret_path:
 	return rc;
@@ -1584,7 +1564,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 #ifdef CONFIG_X86_64
 
-static const struct user_regset x86_64_regsets[] = {
+static struct user_regset x86_64_regsets[] __read_mostly = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(struct user_regs_struct) / sizeof(long),
@@ -1597,6 +1577,12 @@ static const struct user_regset x86_64_regsets[] = {
 		.size = sizeof(long), .align = sizeof(long),
 		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
+	[REGSET_XSTATE] = {
+		.core_note_type = NT_X86_XSTATE,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = xstateregs_active, .get = xstateregs_get,
+		.set = xstateregs_set
+	},
 	[REGSET_IOPERM64] = {
 		.core_note_type = NT_386_IOPERM,
 		.n = IO_BITMAP_LONGS,
@@ -1622,7 +1608,7 @@ static const struct user_regset_view user_x86_64_view = {
 #endif	/* CONFIG_X86_64 */
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-static const struct user_regset x86_32_regsets[] = {
+static struct user_regset x86_32_regsets[] __read_mostly = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(struct user_regs_struct32) / sizeof(u32),
@@ -1641,6 +1627,12 @@ static const struct user_regset x86_32_regsets[] = {
 		.size = sizeof(u32), .align = sizeof(u32),
 		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
+	[REGSET_XSTATE] = {
+		.core_note_type = NT_X86_XSTATE,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = xstateregs_active, .get = xstateregs_get,
+		.set = xstateregs_set
+	},
 	[REGSET_TLS] = {
 		.core_note_type = NT_386_TLS,
 		.n = GDT_ENTRY_TLS_ENTRIES, .bias = GDT_ENTRY_TLS_MIN,
@@ -1663,6 +1655,23 @@ static const struct user_regset_view user_x86_32_view = {
 };
 #endif
 
+/*
+ * This represents bytes 464..511 in the memory layout exported through
+ * the REGSET_XSTATE interface.
+ */
+u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+
+void update_regset_xstate_info(unsigned int size, u64 xstate_mask)
+{
+#ifdef CONFIG_X86_64
+	x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64);
+#endif
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+	x86_32_regsets[REGSET_XSTATE].n = size / sizeof(u64);
+#endif
+	xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask;
+}
+
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
 #ifdef CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 18093d7498f..12e9feaa2f7 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -491,6 +491,19 @@ void force_hpet_resume(void)
 		break;
 	}
 }
+
+/*
+ * HPET MSI on some boards (ATI SB700/SB800) has side effect on
+ * floppy DMA. Disable HPET MSI on such platforms.
+ */
+static void force_disable_hpet_msi(struct pci_dev *unused)
+{
+	hpet_msi_disable = 1;
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
+			 force_disable_hpet_msi);
+
 #endif
 
 #if defined(CONFIG_PCI) && defined(CONFIG_NUMA)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 1545bc0c984..8e1aac86b50 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -203,6 +203,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
 		},
 	},
+	{	/* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G*/
+		.callback = set_bios_reboot,
+		.ident = "Dell OptiPlex 760",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"),
+			DMI_MATCH(DMI_BOARD_NAME, "0G919G"),
+		},
+	},
 	{	/* Handle problems with rebooting on Dell 2400's */
 		.callback = set_bios_reboot,
 		.ident = "Dell PowerEdge 2400",
@@ -452,6 +461,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"),
 		},
 	},
+	{	/* Handle problems with rebooting on the iMac9,1. */
+		.callback = set_pci_reboot,
+		.ident = "Apple iMac9,1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f7b8b9894b2..5d7ba1a449b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -121,7 +121,9 @@
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
+#ifdef CONFIG_DMI
 RESERVE_BRK(dmi_alloc, 65536);
+#endif
 
 unsigned int boot_cpu_id __read_mostly;
 
@@ -642,23 +644,48 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
 			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
 		},
 	},
-	{
 	/*
-	 * AMI BIOS with low memory corruption was found on Intel DG45ID board.
-	 * It hase different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
+	 * AMI BIOS with low memory corruption was found on Intel DG45ID and
+	 * DG45FC boards.
+	 * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
 	 * match only DMI_BOARD_NAME and see if there is more bad products
 	 * with this vendor.
 	 */
+	{
 		.callback = dmi_low_memory_corruption,
 		.ident = "AMI BIOS",
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
 		},
 	},
+	{
+		.callback = dmi_low_memory_corruption,
+		.ident = "AMI BIOS",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
+		},
+	},
 #endif
 	{}
 };
 
+static void __init trim_bios_range(void)
+{
+	/*
+	 * A special case is the first 4Kb of memory;
+	 * This is a BIOS owned area, not kernel ram, but generally
+	 * not listed as such in the E820 table.
+	 */
+	e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+	/*
+	 * special case: Some BIOSen report the PC BIOS
+	 * area (640->1Mb) as ram even though it is not.
+	 * take them out.
+	 */
+	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+}
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -822,7 +849,7 @@ void __init setup_arch(char **cmdline_p)
 	insert_resource(&iomem_resource, &data_resource);
 	insert_resource(&iomem_resource, &bss_resource);
 
-
+	trim_bios_range();
 #ifdef CONFIG_X86_32
 	if (ppro_with_ram_bug()) {
 		e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
@@ -942,15 +969,11 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	initmem_init(0, max_pfn, acpi, k8);
+#ifndef CONFIG_NO_BOOTMEM
+	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+#endif
 
-#ifdef CONFIG_X86_64
-	/*
-	 * dma32_reserve_bootmem() allocates bootmem which may conflict
-	 * with the crashkernel command line, so do that after
-	 * reserve_crashkernel()
-	 */
 	dma32_reserve_bootmem();
-#endif
 
 	reserve_ibft_region();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 35abcb8b00e..ef6370b00e7 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -137,7 +137,13 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
+#ifdef CONFIG_NO_BOOTMEM
+	u64 start = __pa(ptr);
+	u64 end = start + size;
+	free_early_partial(start, end);
+#else
 	free_bootmem(__pa(ptr), size);
+#endif
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 678d0b8c26f..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];
@@ -241,6 +243,11 @@ static void __cpuinit smp_callin(void)
 	map_cpu_to_logical_apicid();
 
 	notify_cpu_starting(cpuid);
+
+	/*
+	 * Need to setup vector mappings before we enable interrupts.
+	 */
+	__setup_vector_irq(smp_processor_id());
 	/*
 	 * Get our bogomips.
 	 *
@@ -286,9 +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
@@ -315,15 +322,18 @@ notrace static void __cpuinit start_secondary(void *unused)
 	 */
 	ipi_call_lock();
 	lock_vector_lock();
-	__setup_vector_irq(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
 	unlock_vector_lock();
 	ipi_call_unlock();
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+	x86_platform.nmi_init();
 
 	/* 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();
@@ -1083,9 +1093,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_cpu_sibling_map(0);
 
 	enable_IR_x2apic();
-#ifdef CONFIG_X86_64
 	default_setup_apic_routing();
-#endif
 
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
@@ -1213,11 +1221,12 @@ __init void prefill_possible_map(void)
 
 	total_cpus = max_t(int, possible, num_processors + disabled_cpus);
 
-	if (possible > CONFIG_NR_CPUS) {
+	/* nr_cpu_ids could be reduced via nr_cpus= */
+	if (possible > nr_cpu_ids) {
 		printk(KERN_WARNING
 			"%d Processors exceeds NR_CPUS limit of %d\n",
-			possible, CONFIG_NR_CPUS);
-		possible = CONFIG_NR_CPUS;
+			possible, nr_cpu_ids);
+		possible = nr_cpu_ids;
 	}
 
 	printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n",
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index be2573448ed..fb5cc5e14cf 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -70,11 +70,11 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 		 * manually to deassert NMI lines for the watchdog if run
 		 * on an 82489DX-based system.
 		 */
-		spin_lock(&i8259A_lock);
+		raw_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);
+		raw_spin_unlock(&i8259A_lock);
 	}
 
 	global_clock_event->event_handler(global_clock_event);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 33399176512..1168e445418 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -534,6 +534,9 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 
 	get_debugreg(dr6, 6);
 
+	/* Filter out all the reserved bits which are preset to 1 */
+	dr6 &= ~DR6_RESERVED;
+
 	/* Catch kmemcheck conditions first of all! */
 	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
 		return;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 597683aa5ba..208a857c679 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -740,7 +740,7 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 }
 #endif
 
-static void resume_tsc(void)
+static void resume_tsc(struct clocksource *cs)
 {
 	clocksource_tsc.cycle_last = 0;
 }
@@ -806,7 +806,7 @@ static void __init check_system_tsc_reliable(void)
 	unsigned long res_low, res_high;
 
 	rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
-	/* Geode_LX - the OLPC CPU has a possibly a very reliable TSC */
+	/* Geode_LX - the OLPC CPU has a very reliable TSC */
 	if (res_low & RTSC_SUSP)
 		tsc_clocksource_reliable = 1;
 #endif
diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c
index 36afb98675a..309c70fb775 100644
--- a/arch/x86/kernel/uv_sysfs.c
+++ b/arch/x86/kernel/uv_sysfs.c
@@ -54,19 +54,19 @@ static int __init sgi_uv_sysfs_init(void)
 	if (!sgi_uv_kobj)
 		sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj);
 	if (!sgi_uv_kobj) {
-		printk(KERN_WARNING "kobject_create_and_add sgi_uv failed \n");
+		printk(KERN_WARNING "kobject_create_and_add sgi_uv failed\n");
 		return -EINVAL;
 	}
 
 	ret = sysfs_create_file(sgi_uv_kobj, &partition_id_attr.attr);
 	if (ret) {
-		printk(KERN_WARNING "sysfs_create_file partition_id failed \n");
+		printk(KERN_WARNING "sysfs_create_file partition_id failed\n");
 		return ret;
 	}
 
 	ret = sysfs_create_file(sgi_uv_kobj, &coherence_id_attr.attr);
 	if (ret) {
-		printk(KERN_WARNING "sysfs_create_file coherence_id failed \n");
+		printk(KERN_WARNING "sysfs_create_file coherence_id failed\n");
 		return ret;
 	}
 
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 3c84aa001c1..2b75ef638db 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -282,10 +282,21 @@ static int uv_rtc_unset_timer(int cpu, int force)
 
 /*
  * Read the RTC.
+ *
+ * Starting with HUB rev 2.0, the UV RTC register is replicated across all
+ * cachelines of it's own page.  This allows faster simultaneous reads
+ * from a given socket.
  */
 static cycle_t uv_read_rtc(struct clocksource *cs)
 {
-	return (cycle_t)uv_read_local_mmr(UVH_RTC);
+	unsigned long offset;
+
+	if (uv_get_min_hub_revision_id() == 1)
+		offset = 0;
+	else
+		offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
+
+	return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
 }
 
 /*
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 34a279a7471..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,
 };
 
 
@@ -559,7 +553,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	spin_lock_irqsave(&i8259A_lock, flags);
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
 	/* Find out what's interrupting in the PIIX4 master 8259 */
 	outb(0x0c, 0x20);		/* OCW3 Poll command */
@@ -596,7 +590,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 		outb(0x60 + realirq, 0x20);
 	}
 
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 
 	desc = irq_to_desc(realirq);
 
@@ -609,12 +603,12 @@ 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;
 
 out_unlock:
-	spin_unlock_irqrestore(&i8259A_lock, flags);
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 	return IRQ_NONE;
 }
 
@@ -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/vmi_32.c b/arch/x86/kernel/vmi_32.c
index d430e4c3019..7dd599deca4 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -33,6 +33,7 @@
 #include <asm/fixmap.h>
 #include <asm/apicdef.h>
 #include <asm/apic.h>
+#include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/timer.h>
 #include <asm/vmi_time.h>
@@ -266,30 +267,6 @@ static void vmi_nop(void)
 {
 }
 
-#ifdef CONFIG_HIGHPTE
-static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
-{
-	void *va = kmap_atomic(page, type);
-
-	/*
-	 * Internally, the VMI ROM must map virtual addresses to physical
-	 * addresses for processing MMU updates.  By the time MMU updates
-	 * are issued, this information is typically already lost.
-	 * Fortunately, the VMI provides a cache of mapping slots for active
-	 * page tables.
-	 *
-	 * We use slot zero for the linear mapping of physical memory, and
-	 * in HIGHPTE kernels, slot 1 and 2 for KM_PTE0 and KM_PTE1.
-	 *
-	 *  args:                 SLOT                 VA    COUNT PFN
-	 */
-	BUG_ON(type != KM_PTE0 && type != KM_PTE1);
-	vmi_ops.set_linear_mapping((type - KM_PTE0)+1, va, 1, page_to_pfn(page));
-
-	return va;
-}
-#endif
-
 static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn)
 {
 	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
@@ -640,6 +617,12 @@ static inline int __init activate_vmi(void)
 	u64 reloc;
 	const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
 
+	/*
+	 * Prevent page tables from being allocated in highmem, even if
+	 * CONFIG_HIGHPTE is enabled.
+	 */
+	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+
 	if (call_vrom_func(vmi_rom, vmi_init) != 0) {
 		printk(KERN_ERR "VMI ROM failed to initialize!");
 		return 0;
@@ -778,10 +761,6 @@ static inline int __init activate_vmi(void)
 
 	/* Set linear is needed in all cases */
 	vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping);
-#ifdef CONFIG_HIGHPTE
-	if (vmi_ops.set_linear_mapping)
-		pv_mmu_ops.kmap_atomic_pte = vmi_kmap_atomic_pte;
-#endif
 
 	/*
 	 * These MUST always be patched.  Don't support indirect jumps
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index 74c92bb194d..2f1ca561429 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -79,11 +79,7 @@ unsigned long vmi_tsc_khz(void)
 
 static inline unsigned int vmi_get_timer_vector(void)
 {
-#ifdef CONFIG_X86_IO_APIC
-	return FIRST_DEVICE_VECTOR;
-#else
-	return FIRST_EXTERNAL_VECTOR;
-#endif
+	return IRQ0_VECTOR;
 }
 
 /** vmi clockchip */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index f92a0da608c..44879df5569 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -341,7 +341,7 @@ SECTIONS
  * Per-cpu symbols which need to be offset from __per_cpu_load
  * for the boot processor.
  */
-#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load
 INIT_PER_CPU(gdt_page);
 INIT_PER_CPU(irq_stack_union);
 
@@ -352,7 +352,7 @@ INIT_PER_CPU(irq_stack_union);
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
 
 #ifdef CONFIG_SMP
-. = ASSERT((per_cpu__irq_stack_union == 0),
+. = ASSERT((irq_stack_union == 0),
            "irq_stack_union is not at start of per-cpu area");
 #endif
 
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 9055e5872ff..1c0c6ab9c60 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -301,7 +301,8 @@ static int __init vsyscall_init(void)
 	register_sysctl_table(kernel_root_table2);
 #endif
 	on_each_cpu(cpu_vsyscall_init, NULL, 1);
-	hotcpu_notifier(cpu_vsyscall_notifier, 0);
+	/* notifier priority > KVM */
+	hotcpu_notifier(cpu_vsyscall_notifier, 30);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 619f7f88b8c..693920b2249 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -26,7 +26,8 @@ EXPORT_SYMBOL(__put_user_2);
 EXPORT_SYMBOL(__put_user_4);
 EXPORT_SYMBOL(__put_user_8);
 
-EXPORT_SYMBOL(copy_user_generic);
+EXPORT_SYMBOL(copy_user_generic_string);
+EXPORT_SYMBOL(copy_user_generic_unrolled);
 EXPORT_SYMBOL(__copy_user_nocache);
 EXPORT_SYMBOL(_copy_from_user);
 EXPORT_SYMBOL(_copy_to_user);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index ccd179dec36..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>
@@ -70,16 +72,25 @@ 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 = {
 	.setup_percpu_clockev		= setup_secondary_APIC_clock,
 };
 
+static void default_nmi_init(void) { };
+
 struct x86_platform_ops x86_platform = {
 	.calibrate_tsc			= native_calibrate_tsc,
 	.get_wallclock			= mach_get_cmos_time,
 	.set_wallclock			= mach_set_rtc_mmss,
 	.iommu_shutdown			= iommu_shutdown_noop,
 	.is_untracked_pat_range		= is_ISA_range,
+	.nmi_init			= default_nmi_init
 };
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index c5ee17e8c6d..782c3a362ec 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -337,6 +337,7 @@ void __ref xsave_cntxt_init(void)
 	cpuid_count(0xd, 0, &eax, &ebx, &ecx, &edx);
 	xstate_size = ebx;
 
+	update_regset_xstate_info(xstate_size, pcntxt_mask);
 	prepare_fx_sw_frame();
 
 	setup_xstate_init();