next-20140724/tip

71 files changed, 2095 insertions, 1975 deletions

diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 63177e4cb66d..b9a5685a990e 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -99,10 +99,6 @@ static int arc_pmu_event_init(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int ret;
 
-	/* ARC 700 PMU does not support sampling events */
-	if (is_sampling_event(event))
-		return -ENOENT;
-
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		if (event->attr.config >= PERF_COUNT_HW_MAX)
@@ -298,6 +294,9 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		.read		= arc_pmu_read,
 	};
 
+	/* ARC 700 PMU does not support sampling events */
+	arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
 
 	return ret;
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 974e55496db3..ea2032013cc2 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -389,14 +389,6 @@ static int bfin_pmu_event_init(struct perf_event *event)
 	if (attr->exclude_hv || attr->exclude_idle)
 		return -EPERM;
 
-	/*
-	 * All of the on-chip counters are "limited", in that they have
-	 * no interrupts, and are therefore unable to do sampling without
-	 * further work and timer assistance.
-	 */
-	if (hwc->sample_period)
-		return -EINVAL;
-
 	ret = 0;
 	switch (attr->type) {
 	case PERF_TYPE_RAW:
@@ -490,6 +482,13 @@ static int __init bfin_pmu_init(void)
 {
 	int ret;
 
+	/*
+	 * All of the on-chip counters are "limited", in that they have
+	 * no interrupts, and are therefore unable to do sampling without
+	 * further work and timer assistance.
+	 */
+	pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
 		perf_cpu_notifier(bfin_pmu_notifier);
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 5cc4d4dcf3cf..02c08737f6aa 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -568,16 +568,6 @@ static int _hw_perf_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	/*
-	 * Early cores have "limited" counters - they have no overflow
-	 * interrupts - and so are unable to do sampling without extra work
-	 * and timer assistance.
-	 */
-	if (metag_pmu->max_period == 0) {
-		if (hwc->sample_period)
-			return -EINVAL;
-	}
-
-	/*
 	 * Don't assign an index until the event is placed into the hardware.
 	 * -1 signifies that we're still deciding where to put it. On SMP
 	 * systems each core has its own set of counters, so we can't do any
@@ -866,6 +856,15 @@ static int __init init_hw_perf_events(void)
 	pr_info("enabled with %s PMU driver, %d counters available\n",
 			metag_pmu->name, metag_pmu->max_events);
 
+	/*
+	 * Early cores have "limited" counters - they have no overflow
+	 * interrupts - and so are unable to do sampling without extra work
+	 * and timer assistance.
+	 */
+	if (metag_pmu->max_period == 0) {
+		metag_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	}
+
 	/* Initialise the active events and reservation mutex */
 	atomic_set(&metag_pmu->active_events, 0);
 	mutex_init(&metag_pmu->reserve_mutex);
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index e71d712afb79..88e83368bbf5 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -22,6 +22,7 @@ config OPENRISC
 	select GENERIC_STRNLEN_USER
 	select MODULES_USE_ELF_RELA
 	select HAVE_DEBUG_STACKOVERFLOW
+	select OR1K_PIC
 
 config MMU
 	def_bool y
diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h
index eb612b1865d2..b84634cc95eb 100644
--- a/arch/openrisc/include/asm/irq.h
+++ b/arch/openrisc/include/asm/irq.h
@@ -24,4 +24,7 @@
 
 #define NO_IRQ		(-1)
 
+void handle_IRQ(unsigned int, struct pt_regs *);
+extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
+
 #endif /* __ASM_OPENRISC_IRQ_H__ */
diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c
index 8ec77bc9f1e7..967eb1430203 100644
--- a/arch/openrisc/kernel/irq.c
+++ b/arch/openrisc/kernel/irq.c
@@ -16,11 +16,10 @@
 
 #include <linux/interrupt.h>
 #include <linux/init.h>
-#include <linux/of.h>
 #include <linux/ftrace.h>
 #include <linux/irq.h>
+#include <linux/irqchip.h>
 #include <linux/export.h>
-#include <linux/irqdomain.h>
 #include <linux/irqflags.h>
 
 /* read interrupt enabled status */
@@ -37,150 +36,31 @@ void arch_local_irq_restore(unsigned long flags)
 }
 EXPORT_SYMBOL(arch_local_irq_restore);
 
-
-/* OR1K PIC implementation */
-
-/* We're a couple of cycles faster than the generic implementations with
- * these 'fast' versions.
- */
-
-static void or1k_pic_mask(struct irq_data *data)
-{
-	mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq));
-}
-
-static void or1k_pic_unmask(struct irq_data *data)
-{
-	mtspr(SPR_PICMR, mfspr(SPR_PICMR) | (1UL << data->hwirq));
-}
-
-static void or1k_pic_ack(struct irq_data *data)
-{
-	/* EDGE-triggered interrupts need to be ack'ed in order to clear
-	 * the latch.
-	 * LEVEL-triggered interrupts do not need to be ack'ed; however,
-	 * ack'ing the interrupt has no ill-effect and is quicker than
-	 * trying to figure out what type it is...
-	 */
-
-	/* The OpenRISC 1000 spec says to write a 1 to the bit to ack the
-	 * interrupt, but the OR1200 does this backwards and requires a 0
-	 * to be written...
-	 */
-
-#ifdef CONFIG_OR1K_1200
-	/* There are two oddities with the OR1200 PIC implementation:
-	 * i)  LEVEL-triggered interrupts are latched and need to be cleared
-	 * ii) the interrupt latch is cleared by writing a 0 to the bit,
-	 *     as opposed to a 1 as mandated by the spec
-	 */
-
-	mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq));
-#else
-	WARN(1, "Interrupt handling possibly broken\n");
-	mtspr(SPR_PICSR, (1UL << data->hwirq));
-#endif
-}
-
-static void or1k_pic_mask_ack(struct irq_data *data)
-{
-	/* Comments for pic_ack apply here, too */
-
-#ifdef CONFIG_OR1K_1200
-	mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq));
-	mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq));
-#else
-	WARN(1, "Interrupt handling possibly broken\n");
-	mtspr(SPR_PICMR, (1UL << data->hwirq));
-	mtspr(SPR_PICSR, (1UL << data->hwirq));
-#endif
-}
-
-#if 0
-static int or1k_pic_set_type(struct irq_data *data, unsigned int flow_type)
-{
-	/* There's nothing to do in the PIC configuration when changing
-	 * flow type.  Level and edge-triggered interrupts are both
-	 * supported, but it's PIC-implementation specific which type
-	 * is handled. */
-
-	return irq_setup_alt_chip(data, flow_type);
-}
-#endif
-
-static struct irq_chip or1k_dev = {
-	.name = "or1k-PIC",
-	.irq_unmask = or1k_pic_unmask,
-	.irq_mask = or1k_pic_mask,
-	.irq_ack = or1k_pic_ack,
-	.irq_mask_ack = or1k_pic_mask_ack,
-};
-
-static struct irq_domain *root_domain;
-
-static inline int pic_get_irq(int first)
-{
-	int hwirq;
-
-	hwirq = ffs(mfspr(SPR_PICSR) >> first);
-	if (!hwirq)
-		return NO_IRQ;
-	else
-		hwirq = hwirq + first -1;
-
-	return irq_find_mapping(root_domain, hwirq);
-}
-
-
-static int or1k_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
+void __init init_IRQ(void)
 {
-	irq_set_chip_and_handler_name(irq, &or1k_dev,
-				      handle_level_irq, "level");
-	irq_set_status_flags(irq, IRQ_LEVEL | IRQ_NOPROBE);
-
-	return 0;
+	irqchip_init();
 }
 
-static const struct irq_domain_ops or1k_irq_domain_ops = {
-	.xlate = irq_domain_xlate_onecell,
-	.map = or1k_map,
-};
-
-/*
- * This sets up the IRQ domain for the PIC built in to the OpenRISC
- * 1000 CPU.  This is the "root" domain as these are the interrupts
- * that directly trigger an exception in the CPU.
- */
-static void __init or1k_irq_init(void)
-{
-	struct device_node *intc = NULL;
-
-	/* The interrupt controller device node is mandatory */
-	intc = of_find_compatible_node(NULL, NULL, "opencores,or1k-pic");
-	BUG_ON(!intc);
-
-	/* Disable all interrupts until explicitly requested */
-	mtspr(SPR_PICMR, (0UL));
-
-	root_domain = irq_domain_add_linear(intc, 32,
-					    &or1k_irq_domain_ops, NULL);
-}
+static void (*handle_arch_irq)(struct pt_regs *);
 
-void __init init_IRQ(void)
+void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
 {
-	or1k_irq_init();
+	handle_arch_irq = handle_irq;
 }
 
-void __irq_entry do_IRQ(struct pt_regs *regs)
+void handle_IRQ(unsigned int irq, struct pt_regs *regs)
 {
-	int irq = -1;
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	irq_enter();
 
-	while ((irq = pic_get_irq(irq + 1)) != NO_IRQ)
-		generic_handle_irq(irq);
+	generic_handle_irq(irq);
 
 	irq_exit();
 	set_irq_regs(old_regs);
 }
+
+void __irq_entry do_IRQ(struct pt_regs *regs)
+{
+	handle_arch_irq(regs);
+}
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index e0766b82e165..66d0f179650f 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -387,8 +387,7 @@ static int h_24x7_event_init(struct perf_event *event)
 	    event->attr.exclude_hv     ||
 	    event->attr.exclude_idle   ||
 	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    is_sampling_event(event)) /* no sampling */
+	    event->attr.exclude_guest)
 		return -EINVAL;
 
 	/* no branch sampling */
@@ -513,6 +512,9 @@ static int hv_24x7_init(void)
 	if (!hv_page_cache)
 		return -ENOMEM;
 
+	/* sampling not supported */
+	h_24x7_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
 	if (r)
 		return r;
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index c9d399a2df82..15fc76c93022 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -210,8 +210,7 @@ static int h_gpci_event_init(struct perf_event *event)
 	    event->attr.exclude_hv     ||
 	    event->attr.exclude_idle   ||
 	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    is_sampling_event(event)) /* no sampling */
+	    event->attr.exclude_guest)
 		return -EINVAL;
 
 	/* no branch sampling */
@@ -284,6 +283,9 @@ static int hv_gpci_init(void)
 		return -ENODEV;
 	}
 
+	/* sampling not supported */
+	h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1);
 	if (r)
 		return r;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index ea75d011a6fc..d3194de7ae1e 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -411,12 +411,6 @@ static int cpumf_pmu_event_init(struct perf_event *event)
 	case PERF_TYPE_HARDWARE:
 	case PERF_TYPE_HW_CACHE:
 	case PERF_TYPE_RAW:
-		/* The CPU measurement counter facility does not have overflow
-		 * interrupts to do sampling.  Sampling must be provided by
-		 * external means, for example, by timers.
-		 */
-		if (is_sampling_event(event))
-			return -ENOENT;
 		err = __hw_perf_event_init(event);
 		break;
 	default:
@@ -681,6 +675,12 @@ static int __init cpumf_pmu_init(void)
 		goto out;
 	}
 
+	/* The CPU measurement counter facility does not have overflow
+	 * interrupts to do sampling.  Sampling must be provided by
+	 * external means, for example, by timers.
+	 */
+	cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
 	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
 	if (rc) {
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 02331672b6db..7cfd7f153966 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -129,14 +129,6 @@ static int __hw_perf_event_init(struct perf_event *event)
 		return -ENODEV;
 
 	/*
-	 * All of the on-chip counters are "limited", in that they have
-	 * no interrupts, and are therefore unable to do sampling without
-	 * further work and timer assistance.
-	 */
-	if (hwc->sample_period)
-		return -EINVAL;
-
-	/*
 	 * See if we need to reserve the counter.
 	 *
 	 * If no events are currently in use, then we have to take a
@@ -392,6 +384,13 @@ int register_sh_pmu(struct sh_pmu *_pmu)
 
 	pr_info("Performance Events: %s support registered\n", _pmu->name);
 
+	/*
+	 * All of the on-chip counters are "limited", in that they have
+	 * no interrupts, and are therefore unable to do sampling without
+	 * further work and timer assistance.
+	 */
+	pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
 	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ac5a788d2432..cb61ac7a2b7a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -432,6 +432,7 @@ config X86_INTEL_CE
 	bool "CE4100 TV platform"
 	depends on PCI
 	depends on PCI_GODIRECT
+	depends on X86_IO_APIC
 	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
 	select X86_REBOOTFIXUPS
@@ -838,6 +839,7 @@ config X86_IO_APIC
 	def_bool y
 	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
 	select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+	select IRQ_DOMAIN
 
 config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
 	bool "Reroute for broken boot IRQs"
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 33f71b01fd22..c65fd9650467 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -15,12 +15,9 @@ endif
 # that way we can complain to the user if the CPU is insufficient.
 #
 # The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For
-# older versions of GCC, we need to play evil and unreliable tricks to
-# attempt to ensure that our asm(".code16gcc") is first in the asm
-# output.
-CODE16GCC_CFLAGS := -m32 -include $(srctree)/arch/x86/boot/code16gcc.h \
-		    $(call cc-option, -fno-toplevel-reorder,\
-		      $(call cc-option, -fno-unit-at-a-time))
+# older versions of GCC, include an *assembly* header to make sure that
+# gcc doesn't play any games behind our back.
+CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h
 M16_CFLAGS	 := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))
 
 REALMODE_CFLAGS	:= $(M16_CFLAGS) -g -Os -D__KERNEL__ \
diff --git a/arch/x86/boot/code16gcc.h b/arch/x86/boot/code16gcc.h
index d93e48010b61..5ff426535397 100644
--- a/arch/x86/boot/code16gcc.h
+++ b/arch/x86/boot/code16gcc.h
@@ -1,15 +1,11 @@
-/*
- * code16gcc.h
- *
- * This file is -include'd when compiling 16-bit C code.
- * Note: this asm() needs to be emitted before gcc emits any code.
- * Depending on gcc version, this requires -fno-unit-at-a-time or
- * -fno-toplevel-reorder.
- *
- * Hopefully gcc will eventually have a real -m16 option so we can
- * drop this hack long term.
- */
+#
+# code16gcc.h
+#
+# This file is added to the assembler via -Wa when compiling 16-bit C code.
+# This is done this way instead via asm() to make sure gcc does not reorder
+# things around us.
+#
+# gcc 4.9+ has a real -m16 option so we can drop this hack long term.
+#
 
-#ifndef __ASSEMBLY__
-asm(".code16gcc");
-#endif
+	.code16gcc
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 0a3f9c9f98d5..473bdbee378a 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -161,6 +161,20 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
 		: : "i" (0), ## input)
 
+/*
+ * This is similar to alternative_input. But it has two features and
+ * respective instructions.
+ *
+ * If CPU has feature2, newinstr2 is used.
+ * Otherwise, if CPU has feature1, newinstr1 is used.
+ * Otherwise, oldinstr is used.
+ */
+#define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2,	     \
+			   feature2, input...)				     \
+	asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1,	     \
+		newinstr2, feature2)					     \
+		: : "i" (0), ## input)
+
 /* Like alternative_input, but with a single output argument */
 #define alternative_io(oldinstr, newinstr, feature, output, input...)	\
 	asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)		\
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 19b0ebafcd3e..a8a637d56902 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -85,21 +85,13 @@ static inline bool apic_from_smp_config(void)
 #include <asm/paravirt.h>
 #endif
 
-#ifdef CONFIG_X86_64
-extern int is_vsmp_box(void);
-#else
-static inline int is_vsmp_box(void)
-{
-	return 0;
-}
-#endif
 extern int setup_profiling_timer(unsigned int);
 
 static inline void native_apic_mem_write(u32 reg, u32 v)
 {
 	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
 
-	alternative_io("movl %0, %1", "xchgl %0, %1", X86_FEATURE_11AP,
+	alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
 		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
 		       ASM_OUTPUT2("0" (v), "m" (*addr)));
 }
@@ -502,8 +494,6 @@ static inline unsigned default_get_apic_id(unsigned long x)
 #define DEFAULT_TRAMPOLINE_PHYS_HIGH		0x469
 
 #ifdef CONFIG_X86_64
-extern int default_acpi_madt_oem_check(char *, char *);
-
 extern void apic_send_IPI_self(int vector);
 
 DECLARE_PER_CPU(int, x2apic_extra_bits);
@@ -552,6 +542,8 @@ static inline int default_apic_id_valid(int apicid)
 	return (apicid < 255);
 }
 
+extern int default_acpi_madt_oem_check(char *, char *);
+
 extern void default_setup_apic_routing(void);
 
 extern struct apic apic_noop;
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 5c7198cca5ed..0f4460b5636d 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -99,7 +99,7 @@
 #if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
- * For either of these options x86 doesn't have a strong TSO memory
+ * For this option x86 doesn't have a strong TSO memory
  * model and we should fall back to full barriers.
  */
 
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index d47786acb016..99c105d78b7e 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -4,6 +4,8 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
+#define __HAVE_ARCH_CMPXCHG 1
+
 /*
  * Non-existant functions to indicate usage errors at link time
  * (or compile-time if the compiler implements __compiletime_error().
@@ -143,7 +145,6 @@ extern void __add_wrong_size(void)
 # include <asm/cmpxchg_64.h>
 #endif
 
-#ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)						\
 	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
@@ -152,7 +153,6 @@ extern void __add_wrong_size(void)
 
 #define cmpxchg_local(ptr, old, new)					\
 	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
-#endif
 
 /*
  * xadd() adds "inc" to "*ptr" and atomically returns the previous
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index f8bf2eecab86..f7e142926481 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -34,8 +34,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
 		     : "memory");
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #ifdef CONFIG_X86_CMPXCHG64
 #define cmpxchg64(ptr, o, n)						\
 	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 614be87f1a9b..1af94697aae5 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -6,8 +6,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 	*ptr = val;
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define cmpxchg64(ptr, o, n)						\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e265ff95d16d..bb9b258d60e7 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,7 +8,7 @@
 #include <asm/required-features.h>
 #endif
 
-#define NCAPINTS	10	/* N 32-bit words worth of info */
+#define NCAPINTS	11	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -18,213 +18,218 @@
  */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		(0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		(0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		(0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		(0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	(0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		(0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	(0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		(0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		(0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	(0*32+15) /* CMOV instructions */
+#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
 					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		(0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	(0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		(0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	(0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		(0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	(0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	(0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		(0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	(0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	(0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		(0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		(0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	(0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		(0*32+31) /* Pending Break Enable */
+#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	(1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	(1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	(1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	(1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	(1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	(2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	(2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	(2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	(3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	(3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
+#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
 /* cpu types for specific tunings: */
-#define X86_FEATURE_K8		(3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		(3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		(3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		(3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
-#define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	(3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	(3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_11AP	(3*32+19) /* "" Bad local APIC aka 11AP */
-#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	(3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
-#define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	(3*32+28) /* APERFMPERF */
-#define X86_FEATURE_EAGER_FPU	(3*32+29) /* "eagerfpu" Non lazy FPU restore */
-#define X86_FEATURE_NONSTOP_TSC_S3 (3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
+/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
+/* free, was #define X86_FEATURE_11AP	( 3*32+19) * "" Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
+/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
+#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	(4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	(4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	(4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	(4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		(4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		(4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		(4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		(4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		(4*32+10) /* Context ID */
-#define X86_FEATURE_FMA		(4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	(4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	(4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	(4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	(4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		(4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	(4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	(4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	(4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	(4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      (4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	(4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		(4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	(4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	(4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	(4*32+31) /* Running on a hypervisor */
+#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
+#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
+#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	(5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	(5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	(5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	(5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	(5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	(5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		(5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	(5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		(5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	(5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
 
 /* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	(6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	(6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		(6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	(6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	(6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		(6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	(6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	(6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		(6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		(6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		(6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	(6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		(6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  (6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_PERFCTR_L2	(6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
  * CPUID levels like 0x6, 0xA etc, word 7
  */
-#define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(7*32+ 1) /* Always Running APIC Timer */
-#define X86_FEATURE_CPB		(7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		(7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_XSAVEOPT	(7*32+ 4) /* Optimized Xsave */
-#define X86_FEATURE_PLN		(7*32+ 5) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(7*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_DTHERM	(7*32+ 7) /* Digital Thermal Sensor */
-#define X86_FEATURE_HW_PSTATE	(7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK (7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_IDA		( 7*32+ 0) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	( 7*32+ 1) /* Always Running APIC Timer */
+#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_PLN		( 7*32+ 5) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		( 7*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_DTHERM	( 7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
 /* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        (8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         (8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        (8*32+ 4) /* Intel Virtual Processor ID */
-#define X86_FEATURE_NPT		(8*32+ 5) /* AMD Nested Page Table support */
-#define X86_FEATURE_LBRV	(8*32+ 6) /* AMD LBR Virtualization support */
-#define X86_FEATURE_SVML	(8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
-#define X86_FEATURE_NRIPS	(8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_NPT		( 8*32+ 5) /* AMD Nested Page Table support */
+#define X86_FEATURE_LBRV	( 8*32+ 6) /* AMD LBR Virtualization support */
+#define X86_FEATURE_SVML	( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
+#define X86_FEATURE_NRIPS	( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	(9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	(9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		(9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	(9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	(9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	(9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_MPX		(9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_AVX512F	(9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_RDSEED	(9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX		(9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP	(9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_CLFLUSHOPT	(9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_AVX512PF	(9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER	(9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	(9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
+
+/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
+#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
+#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
+#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
+#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
 
 /*
  * BUG word(s)
@@ -234,8 +239,11 @@
 #define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
 #define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
 #define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* AMD Erratum 400 */
+#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -245,6 +253,12 @@
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
 
+/*
+ * In order to save room, we index into this array by doing
+ * X86_BUG_<name> - NCAPINTS*32.
+ */
+extern const char * const x86_bug_flags[NBUGINTS*32];
+
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
@@ -301,7 +315,6 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_avx		boot_cpu_has(X86_FEATURE_AVX)
 #define cpu_has_avx2		boot_cpu_has(X86_FEATURE_AVX2)
 #define cpu_has_ht		boot_cpu_has(X86_FEATURE_HT)
-#define cpu_has_mp		boot_cpu_has(X86_FEATURE_MP)
 #define cpu_has_nx		boot_cpu_has(X86_FEATURE_NX)
 #define cpu_has_k6_mtrr		boot_cpu_has(X86_FEATURE_K6_MTRR)
 #define cpu_has_cyrix_arr	boot_cpu_has(X86_FEATURE_CYRIX_ARR)
@@ -328,6 +341,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
 #define cpu_has_xsaveopt	boot_cpu_has(X86_FEATURE_XSAVEOPT)
+#define cpu_has_xsaves		boot_cpu_has(X86_FEATURE_XSAVES)
 #define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
@@ -347,9 +361,6 @@ extern const char * const x86_power_flags[32];
 #undef  cpu_has_pae
 #define cpu_has_pae		___BUG___
 
-#undef  cpu_has_mp
-#define cpu_has_mp		1
-
 #undef  cpu_has_k6_mtrr
 #define cpu_has_k6_mtrr		0
 
@@ -539,20 +550,20 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 #define static_cpu_has_safe(bit)	boot_cpu_has(bit)
 #endif
 
-#define cpu_has_bug(c, bit)	cpu_has(c, (bit))
-#define set_cpu_bug(c, bit)	set_cpu_cap(c, (bit))
-#define clear_cpu_bug(c, bit)	clear_cpu_cap(c, (bit));
+#define cpu_has_bug(c, bit)		cpu_has(c, (bit))
+#define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))
+#define clear_cpu_bug(c, bit)		clear_cpu_cap(c, (bit))
 
-#define static_cpu_has_bug(bit)	static_cpu_has((bit))
-#define boot_cpu_has_bug(bit)	cpu_has_bug(&boot_cpu_data, (bit))
+#define static_cpu_has_bug(bit)		static_cpu_has((bit))
+#define static_cpu_has_bug_safe(bit)	static_cpu_has_safe((bit))
+#define boot_cpu_has_bug(bit)		cpu_has_bug(&boot_cpu_data, (bit))
 
-#define MAX_CPU_FEATURES	(NCAPINTS * 32)
-#define cpu_have_feature	boot_cpu_has
+#define MAX_CPU_FEATURES		(NCAPINTS * 32)
+#define cpu_have_feature		boot_cpu_has
 
-#define CPU_FEATURE_TYPEFMT	"x86,ven%04Xfam%04Xmod%04X"
-#define CPU_FEATURE_TYPEVAL	boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
-				boot_cpu_data.x86_model
+#define CPU_FEATURE_TYPEFMT		"x86,ven%04Xfam%04Xmod%04X"
+#define CPU_FEATURE_TYPEVAL		boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
+					boot_cpu_data.x86_model
 
 #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
-
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 115e3689cd53..412ececa00b9 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -293,7 +293,7 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. "m" is a random variable that should be in L1 */
-	if (unlikely(static_cpu_has_safe(X86_FEATURE_FXSAVE_LEAK))) {
+	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
 		asm volatile(
 			"fnclex\n\t"
 			"emms\n\t"
@@ -508,9 +508,12 @@ static inline void user_fpu_begin(void)
 
 static inline void __save_fpu(struct task_struct *tsk)
 {
-	if (use_xsave())
-		xsave_state(&tsk->thread.fpu.state->xsave, -1);
-	else
+	if (use_xsave()) {
+		if (unlikely(system_state == SYSTEM_BOOTING))
+			xsave_state_booting(&tsk->thread.fpu.state->xsave, -1);
+		else
+			xsave_state(&tsk->thread.fpu.state->xsave, -1);
+	} else
 		fpu_fxsave(&tsk->thread.fpu);
 }
 
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 230853da4ec0..0f5fb6b6567e 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -40,9 +40,6 @@ typedef struct {
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
-/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
-#define MAX_HARDIRQS_PER_CPU NR_VECTORS
-
 #define __ARCH_IRQ_STAT
 
 #define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index a20365953bf8..ccffa53750a8 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -67,4 +67,9 @@ struct legacy_pic {
 extern struct legacy_pic *legacy_pic;
 extern struct legacy_pic null_legacy_pic;
 
+static inline int nr_legacy_irqs(void)
+{
+	return legacy_pic->nr_legacy_irqs;
+}
+
 #endif /* _ASM_X86_I8259_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 90f97b4b9347..0aeed5ca356e 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -98,6 +98,8 @@ struct IR_IO_APIC_route_entry {
 #define IOAPIC_AUTO     -1
 #define IOAPIC_EDGE     0
 #define IOAPIC_LEVEL    1
+#define	IOAPIC_MAP_ALLOC		0x1
+#define	IOAPIC_MAP_CHECK		0x2
 
 #ifdef CONFIG_X86_IO_APIC
 
@@ -118,9 +120,6 @@ extern int mp_irq_entries;
 /* MP IRQ source entries */
 extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
-/* non-0 if default (table-less) MP configuration */
-extern int mpc_default_type;
-
 /* Older SiS APIC requires we rewrite the index register */
 extern int sis_apic_bug;
 
@@ -133,9 +132,6 @@ extern int noioapicquirk;
 /* -1 if "noapic" boot option passed */
 extern int noioapicreroute;
 
-/* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
-extern int timer_through_8259;
-
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -145,24 +141,17 @@ extern int timer_through_8259;
 
 struct io_apic_irq_attr;
 struct irq_cfg;
-extern int io_apic_set_pci_routing(struct device *dev, int irq,
-		 struct io_apic_irq_attr *irq_attr);
-void setup_IO_APIC_irq_extra(u32 gsi);
 extern void ioapic_insert_resources(void);
 
 extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
 				     unsigned int, int,
 				     struct io_apic_irq_attr *);
-extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
-				     unsigned int, int,
-				     struct io_apic_irq_attr *);
 extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
 
 extern void native_compose_msi_msg(struct pci_dev *pdev,
 				   unsigned int irq, unsigned int dest,
 				   struct msi_msg *msg, u8 hpet_id);
 extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
-int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
 
 extern int save_ioapic_entries(void);
 extern void mask_ioapic_entries(void);
@@ -171,15 +160,40 @@ extern int restore_ioapic_entries(void);
 extern void setup_ioapic_ids_from_mpc(void);
 extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
+enum ioapic_domain_type {
+	IOAPIC_DOMAIN_INVALID,
+	IOAPIC_DOMAIN_LEGACY,
+	IOAPIC_DOMAIN_STRICT,
+	IOAPIC_DOMAIN_DYNAMIC,
+};
+
+struct device_node;
+struct irq_domain;
+struct irq_domain_ops;
+
+struct ioapic_domain_cfg {
+	enum ioapic_domain_type		type;
+	const struct irq_domain_ops	*ops;
+	struct device_node		*dev;
+};
+
 struct mp_ioapic_gsi{
 	u32 gsi_base;
 	u32 gsi_end;
 };
-extern struct mp_ioapic_gsi  mp_gsi_routing[];
 extern u32 gsi_top;
-int mp_find_ioapic(u32 gsi);
-int mp_find_ioapic_pin(int ioapic, u32 gsi);
-void __init mp_register_ioapic(int id, u32 address, u32 gsi_base);
+
+extern int mp_find_ioapic(u32 gsi);
+extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
+extern u32 mp_pin_to_gsi(int ioapic, int pin);
+extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
+extern void mp_unmap_irq(int irq);
+extern void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
+				      struct ioapic_domain_cfg *cfg);
+extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
+			    irq_hw_number_t hwirq);
+extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
+extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node);
 extern void __init pre_init_apic_IRQ0(void);
 
 extern void mp_save_irq(struct mpc_intsrc *m);
@@ -217,14 +231,12 @@ extern void io_apic_eoi(unsigned int apic, unsigned int vector);
 
 #define io_apic_assign_pci_irqs 0
 #define setup_ioapic_ids_from_mpc x86_init_noop
-static const int timer_through_8259 = 0;
 static inline void ioapic_insert_resources(void) { }
 #define gsi_top (NR_IRQS_LEGACY)
 static inline int mp_find_ioapic(u32 gsi) { return 0; }
-
-struct io_apic_irq_attr;
-static inline int io_apic_set_pci_routing(struct device *dev, int irq,
-		 struct io_apic_irq_attr *irq_attr) { return 0; }
+static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
+static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
+static inline void mp_unmap_irq(int irq) { }
 
 static inline int save_ioapic_entries(void)
 {
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index a55c7efcc4ed..0f555cc31984 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -13,7 +13,7 @@
 #define RTC_ALWAYS_BCD	1	/* RTC operates in binary mode */
 #endif
 
-#if defined(CONFIG_X86_32) && defined(__HAVE_ARCH_CMPXCHG)
+#if defined(CONFIG_X86_32)
 /*
  * This lock provides nmi access to the CMOS/RTC registers.  It has some
  * special properties.  It is owned by a CPU and stores the index register
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index f5a617956735..7bef40a01a1d 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -40,8 +40,6 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES];
 extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
 extern unsigned int boot_cpu_physical_apicid;
-extern unsigned int max_physical_apicid;
-extern int mpc_default_type;
 extern unsigned long mp_lapic_addr;
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -88,15 +86,6 @@ static inline void early_reserve_e820_mpc_new(void) { }
 #endif
 
 int generic_processor_info(int apicid, int version);
-#ifdef CONFIG_ACPI
-extern void mp_register_ioapic(int id, u32 address, u32 gsi_base);
-extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
-				   u32 gsi);
-extern void mp_config_acpi_legacy_irqs(void);
-struct device;
-extern int mp_register_gsi(struct device *dev, u32 gsi, int edge_level,
-				 int active_high_low);
-#endif /* CONFIG_ACPI */
 
 #define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_LOCAL_APIC)
 
@@ -163,6 +152,4 @@ extern physid_mask_t phys_cpu_present_map;
 
 extern int generic_mps_oem_check(struct mpc_table *, char *, char *);
 
-extern int default_acpi_madt_oem_check(char *, char *);
-
 #endif /* _ASM_X86_MPSPEC_H */
diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h
index 0208c3c2cbc6..85e6cda45a02 100644
--- a/arch/x86/include/asm/mutex_32.h
+++ b/arch/x86/include/asm/mutex_32.h
@@ -100,23 +100,11 @@ do {								\
 static inline int __mutex_fastpath_trylock(atomic_t *count,
 					   int (*fail_fn)(atomic_t *))
 {
-	/*
-	 * We have two variants here. The cmpxchg based one is the best one
-	 * because it never induce a false contention state.  It is included
-	 * here because architectures using the inc/dec algorithms over the
-	 * xchg ones are much more likely to support cmpxchg natively.
-	 *
-	 * If not we fall back to the spinlock based variant - that is
-	 * just as efficient (and simpler) as a 'destructive' probing of
-	 * the mutex state would be.
-	 */
-#ifdef __HAVE_ARCH_CMPXCHG
+	/* cmpxchg because it never induces a false contention state. */
 	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
+
 	return 0;
-#else
-	return fail_fn(count);
-#endif
 }
 
 #endif /* _ASM_X86_MUTEX_32_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 1da25a5f96f9..a1410db38a1a 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -43,7 +43,7 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
 	if (!current_set_polling_and_test()) {
-		if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) {
+		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
 			mb();
 			clflush((void *)&current_thread_info()->flags);
 			mb();
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a4ea02351f4d..2c8d3b8e7fcb 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -386,8 +386,8 @@ struct bndcsr_struct {
 
 struct xsave_hdr_struct {
 	u64 xstate_bv;
-	u64 reserved1[2];
-	u64 reserved2[5];
+	u64 xcomp_bv;
+	u64 reserved[6];
 } __attribute__((packed));
 
 struct xsave_struct {
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index fbeb06ed0eaa..1d081ac1cd69 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -26,12 +26,10 @@
 extern int of_ioapic;
 extern u64 initial_dtb;
 extern void add_dtb(u64 data);
-extern void x86_add_irq_domains(void);
 void x86_of_pci_init(void);
 void x86_dtb_init(void);
 #else
 static inline void add_dtb(u64 data) { }
-static inline void x86_add_irq_domains(void) { }
 static inline void x86_of_pci_init(void) { }
 static inline void x86_dtb_init(void) { }
 #define of_ioapic 0
diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h
index 70f46f07f94e..ae0e241e228b 100644
--- a/arch/x86/include/asm/qrwlock.h
+++ b/arch/x86/include/asm/qrwlock.h
@@ -3,7 +3,7 @@
 
 #include <asm-generic/qrwlock_types.h>
 
-#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+#ifndef CONFIG_X86_PPRO_FENCE
 #define queue_write_unlock queue_write_unlock
 static inline void queue_write_unlock(struct qrwlock *lock)
 {
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 0b46ef261c77..2d60a7813dfe 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -73,6 +73,7 @@
 #define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD	(is_uv1_hub() ?			\
 		UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD :			\
 		UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD)
+/* assuming UV3 is the same */
 
 #define BAU_MISC_CONTROL_MULT_MASK	3
 
@@ -93,6 +94,8 @@
 #define SOFTACK_MSHIFT UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT
 #define SOFTACK_PSHIFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT
 #define SOFTACK_TIMEOUT_PERIOD UV_INTD_SOFT_ACK_TIMEOUT_PERIOD
+#define PREFETCH_HINT_SHFT UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_PREFETCH_HINT_SHFT
+#define SB_STATUS_SHFT UV3H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
 #define write_gmmr	uv_write_global_mmr64
 #define write_lmmr	uv_write_local_mmr
 #define read_lmmr	uv_read_local_mmr
@@ -322,8 +325,9 @@ struct uv1_bau_msg_header {
 /*
  * UV2 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
  * see figure 9-2 of harp_sys.pdf
+ * assuming UV3 is the same
  */
-struct uv2_bau_msg_header {
+struct uv2_3_bau_msg_header {
 	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
 	/* bits 14:0 */				/* in uvhub map */
 	unsigned int	dest_subnodeid:5;	/* must be 0x10, for the LB */
@@ -395,7 +399,7 @@ struct bau_desc {
 	 */
 	union bau_msg_header {
 		struct uv1_bau_msg_header	uv1_hdr;
-		struct uv2_bau_msg_header	uv2_hdr;
+		struct uv2_3_bau_msg_header	uv2_3_hdr;
 	} header;
 
 	struct bau_msg_payload			payload;
@@ -631,11 +635,6 @@ struct bau_control {
 	struct hub_and_pnode	*thp;
 };
 
-static inline unsigned long read_mmr_uv2_status(void)
-{
-	return read_lmmr(UV2H_LB_BAU_SB_ACTIVATION_STATUS_2);
-}
-
 static inline void write_mmr_data_broadcast(int pnode, unsigned long mmr_image)
 {
 	write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image);
@@ -760,7 +759,11 @@ static inline int atomic_read_short(const struct atomic_short *v)
  */
 static inline int atom_asr(short i, struct atomic_short *v)
 {
-	return i + xadd(&v->counter, i);
+	short __i = i;
+	asm volatile(LOCK_PREFIX "xaddw %0, %1"
+			: "+r" (i), "+m" (v->counter)
+			: : "memory");
+	return i + __i;
 }
 
 /*
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 30be253dd283..8021bd28c0f1 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -18,15 +18,15 @@ struct vdso_image {
 
 	unsigned long alt, alt_len;
 
-	unsigned long sym_end_mapping;  /* Total size of the mapping */
-
-	unsigned long sym_vvar_page;
-	unsigned long sym_hpet_page;
-	unsigned long sym_VDSO32_NOTE_MASK;
-	unsigned long sym___kernel_sigreturn;
-	unsigned long sym___kernel_rt_sigreturn;
-	unsigned long sym___kernel_vsyscall;
-	unsigned long sym_VDSO32_SYSENTER_RETURN;
+	long sym_vvar_start;  /* Negative offset to the vvar area */
+
+	long sym_vvar_page;
+	long sym_hpet_page;
+	long sym_VDSO32_NOTE_MASK;
+	long sym___kernel_sigreturn;
+	long sym___kernel_rt_sigreturn;
+	long sym___kernel_vsyscall;
+	long sym_VDSO32_SYSENTER_RETURN;
 };
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index d949ef28c48b..7e7a79ada658 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -52,24 +52,170 @@ extern void xsave_init(void);
 extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 extern int init_fpu(struct task_struct *child);
 
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+#define xstate_fault	".section .fixup,\"ax\"\n"	\
+			"3:  movl $-1,%[err]\n"		\
+			"    jmp  2b\n"			\
+			".previous\n"			\
+			_ASM_EXTABLE(1b, 3b)		\
+			: [err] "=r" (err)
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
 {
-	int err;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XSAVES"\n\t"
+			"2:\n\t"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+	else
+		asm volatile("1:"XSAVE"\n\t"
+			"2:\n\t"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+
+	asm volatile(xstate_fault
+		     : "0" (0)
+		     : "memory");
+
+	return err;
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0)
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XRSTORS"\n\t"
+			"2:\n\t"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+	else
+		asm volatile("1:"XRSTOR"\n\t"
+			"2:\n\t"
+			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			:   "memory");
+
+	asm volatile(xstate_fault
+		     : "0" (0)
+		     : "memory");
+
+	return err;
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline int xsave_state(struct xsave_struct *fx, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	/*
+	 * If xsaves is enabled, xsaves replaces xsaveopt because
+	 * it supports compact format and supervisor states in addition to
+	 * modified optimization in xsaveopt.
+	 *
+	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
+	 * because xsaveopt supports modified optimization which is not
+	 * supported by xsave.
+	 *
+	 * If none of xsaves and xsaveopt is enabled, use xsave.
+	 */
+	alternative_input_2(
+		"1:"XSAVE,
+		"1:"XSAVEOPT,
+		X86_FEATURE_XSAVEOPT,
+		"1:"XSAVES,
+		X86_FEATURE_XSAVES,
+		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
+		"memory");
+	asm volatile("2:\n\t"
+		     xstate_fault
+		     : "0" (0)
 		     : "memory");
 
 	return err;
 }
 
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
+{
+	int err = 0;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+
+	/*
+	 * Use xrstors to restore context if it is enabled. xrstors supports
+	 * compacted format of xsave area which is not supported by xrstor.
+	 */
+	alternative_input(
+		"1: " XRSTOR,
+		"1: " XRSTORS,
+		X86_FEATURE_XSAVES,
+		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+		: "memory");
+
+	asm volatile("2:\n"
+		     xstate_fault
+		     : "0" (0)
+		     : "memory");
+
+	return err;
+}
+
+/*
+ * Save xstate context for old process during context switch.
+ */
+static inline void fpu_xsave(struct fpu *fpu)
+{
+	xsave_state(&fpu->state->xsave, -1);
+}
+
+/*
+ * Restore xstate context for new process during context switch.
+ */
+static inline int fpu_xrstor_checking(struct xsave_struct *fx)
+{
+	return xrstor_state(fx, -1);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
 static inline int xsave_user(struct xsave_struct __user *buf)
 {
 	int err;
@@ -83,69 +229,34 @@ static inline int xsave_user(struct xsave_struct __user *buf)
 		return -EFAULT;
 
 	__asm__ __volatile__(ASM_STAC "\n"
-			     "1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+			     "1:"XSAVE"\n"
 			     "2: " ASM_CLAC "\n"
-			     ".section .fixup,\"ax\"\n"
-			     "3:  movl $-1,%[err]\n"
-			     "    jmp  2b\n"
-			     ".previous\n"
-			     _ASM_EXTABLE(1b,3b)
-			     : [err] "=r" (err)
+			     xstate_fault
 			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
 			     : "memory");
 	return err;
 }
 
+/*
+ * Restore xstate from user space xsave area.
+ */
 static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
 {
-	int err;
+	int err = 0;
 	struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
 
 	__asm__ __volatile__(ASM_STAC "\n"
-			     "1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+			     "1:"XRSTOR"\n"
 			     "2: " ASM_CLAC "\n"
-			     ".section .fixup,\"ax\"\n"
-			     "3:  movl $-1,%[err]\n"
-			     "    jmp  2b\n"
-			     ".previous\n"
-			     _ASM_EXTABLE(1b,3b)
-			     : [err] "=r" (err)
+			     xstate_fault
 			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
 			     : "memory");	/* memory required? */
 	return err;
 }
 
-static inline void xrstor_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
-		     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		     :   "memory");
-}
-
-static inline void xsave_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
+void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
+void setup_xstate_comp(void);
 
-	asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x27\n\t"
-		     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		     :   "memory");
-}
-
-static inline void fpu_xsave(struct fpu *fpu)
-{
-	/* This, however, we can work around by forcing the compiler to select
-	   an addressing mode that doesn't require extended registers. */
-	alternative_input(
-		".byte " REX_PREFIX "0x0f,0xae,0x27",
-		".byte " REX_PREFIX "0x0f,0xae,0x37",
-		X86_FEATURE_XSAVEOPT,
-		[fx] "D" (&fpu->state->xsave), "a" (-1), "d" (-1) :
-		"memory");
-}
 #endif
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index fcf2b3ae1bf0..5cd1569518ef 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -297,6 +297,8 @@
 #define MSR_IA32_TSC_ADJUST             0x0000003b
 #define MSR_IA32_BNDCFGS		0x00000d90
 
+#define MSR_IA32_XSS			0x00000da0
+
 #define FEATURE_CONTROL_LOCKED				(1<<0)
 #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
 #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 86281ffb96d6..b436fc735aa4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <linux/dmi.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
@@ -43,6 +44,7 @@
 #include <asm/io.h>
 #include <asm/mpspec.h>
 #include <asm/smp.h>
+#include <asm/i8259.h>
 
 #include "sleep.h" /* To include x86_acpi_suspend_lowlevel */
 static int __initdata acpi_force = 0;
@@ -74,10 +76,6 @@ int acpi_fix_pin2_polarity __initdata;
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #endif
 
-#ifndef __HAVE_ARCH_CMPXCHG
-#warning ACPI uses CMPXCHG, i486 and later hardware
-#endif
-
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */
@@ -97,44 +95,7 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = {
 	0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
 };
 
-static unsigned int gsi_to_irq(unsigned int gsi)
-{
-	unsigned int irq = gsi + NR_IRQS_LEGACY;
-	unsigned int i;
-
-	for (i = 0; i < NR_IRQS_LEGACY; i++) {
-		if (isa_irq_to_gsi[i] == gsi) {
-			return i;
-		}
-	}
-
-	/* Provide an identity mapping of gsi == irq
-	 * except on truly weird platforms that have
-	 * non isa irqs in the first 16 gsis.
-	 */
-	if (gsi >= NR_IRQS_LEGACY)
-		irq = gsi;
-	else
-		irq = gsi_top + gsi;
-
-	return irq;
-}
-
-static u32 irq_to_gsi(int irq)
-{
-	unsigned int gsi;
-
-	if (irq < NR_IRQS_LEGACY)
-		gsi = isa_irq_to_gsi[irq];
-	else if (irq < gsi_top)
-		gsi = irq;
-	else if (irq < (gsi_top + NR_IRQS_LEGACY))
-		gsi = irq - gsi_top;
-	else
-		gsi = 0xffffffff;
-
-	return gsi;
-}
+#define	ACPI_INVALID_GSI		INT_MIN
 
 /*
  * This is just a simple wrapper around early_ioremap(),
@@ -345,11 +306,145 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e
 #endif				/*CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_IO_APIC
+#define MP_ISA_BUS		0
+
+static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
+					  u32 gsi)
+{
+	int ioapic;
+	int pin;
+	struct mpc_intsrc mp_irq;
+
+	/*
+	 * Convert 'gsi' to 'ioapic.pin'.
+	 */
+	ioapic = mp_find_ioapic(gsi);
+	if (ioapic < 0)
+		return;
+	pin = mp_find_ioapic_pin(ioapic, gsi);
+
+	/*
+	 * TBD: This check is for faulty timer entries, where the override
+	 *      erroneously sets the trigger to level, resulting in a HUGE
+	 *      increase of timer interrupts!
+	 */
+	if ((bus_irq == 0) && (trigger == 3))
+		trigger = 1;
+
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (trigger << 2) | polarity;
+	mp_irq.srcbus = MP_ISA_BUS;
+	mp_irq.srcbusirq = bus_irq;	/* IRQ */
+	mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */
+	mp_irq.dstirq = pin;	/* INTIN# */
+
+	mp_save_irq(&mp_irq);
+
+	/*
+	 * Reset default identity mapping if gsi is also an legacy IRQ,
+	 * otherwise there will be more than one entry with the same GSI
+	 * and acpi_isa_irq_to_gsi() may give wrong result.
+	 */
+	if (gsi < nr_legacy_irqs() && isa_irq_to_gsi[gsi] == gsi)
+		isa_irq_to_gsi[gsi] = ACPI_INVALID_GSI;
+	isa_irq_to_gsi[bus_irq] = gsi;
+}
+
+static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
+			int polarity)
+{
+#ifdef CONFIG_X86_MPPARSE
+	struct mpc_intsrc mp_irq;
+	struct pci_dev *pdev;
+	unsigned char number;
+	unsigned int devfn;
+	int ioapic;
+	u8 pin;
+
+	if (!acpi_ioapic)
+		return 0;
+	if (!dev || !dev_is_pci(dev))
+		return 0;
+
+	pdev = to_pci_dev(dev);
+	number = pdev->bus->number;
+	devfn = pdev->devfn;
+	pin = pdev->pin;
+	/* print the entry should happen on mptable identically */
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+	mp_irq.srcbus = number;
+	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+	ioapic = mp_find_ioapic(gsi);
+	mp_irq.dstapic = mpc_ioapic_id(ioapic);
+	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
+
+	mp_save_irq(&mp_irq);
+#endif
+	return 0;
+}
+
+static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
+			   int polarity)
+{
+	int irq, node;
+
+	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
+		return gsi;
+
+	/* Don't set up the ACPI SCI because it's already set up */
+	if (acpi_gbl_FADT.sci_interrupt == gsi)
+		return gsi;
+
+	trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
+	polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
+	node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+	if (mp_set_gsi_attr(gsi, trigger, polarity, node)) {
+		pr_warn("Failed to set pin attr for GSI%d\n", gsi);
+		return -1;
+	}
+
+	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC);
+	if (irq < 0)
+		return irq;
+
+	if (enable_update_mptable)
+		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
+
+	return irq;
+}
+
+static void mp_unregister_gsi(u32 gsi)
+{
+	int irq;
+
+	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
+		return;
+
+	if (acpi_gbl_FADT.sci_interrupt == gsi)
+		return;
+
+	irq = mp_map_gsi_to_irq(gsi, 0);
+	if (irq > 0)
+		mp_unmap_irq(irq);
+}
+
+static struct irq_domain_ops acpi_irqdomain_ops = {
+	.map = mp_irqdomain_map,
+	.unmap = mp_irqdomain_unmap,
+};
 
 static int __init
 acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 {
 	struct acpi_madt_io_apic *ioapic = NULL;
+	struct ioapic_domain_cfg cfg = {
+		.type = IOAPIC_DOMAIN_DYNAMIC,
+		.ops = &acpi_irqdomain_ops,
+	};
 
 	ioapic = (struct acpi_madt_io_apic *)header;
 
@@ -358,8 +453,12 @@ acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 
 	acpi_table_print_madt_entry(header);
 
-	mp_register_ioapic(ioapic->id,
-			   ioapic->address, ioapic->global_irq_base);
+	/* Statically assign IRQ numbers for IOAPICs hosting legacy IRQs */
+	if (ioapic->global_irq_base < nr_legacy_irqs())
+		cfg.type = IOAPIC_DOMAIN_LEGACY;
+
+	mp_register_ioapic(ioapic->id, ioapic->address, ioapic->global_irq_base,
+			   &cfg);
 
 	return 0;
 }
@@ -382,11 +481,6 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 	if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK)
 		polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
 
-	/*
-	 * mp_config_acpi_legacy_irqs() already setup IRQs < 16
-	 * If GSI is < 16, this will update its flags,
-	 * else it will create a new mp_irqs[] entry.
-	 */
 	mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
 
 	/*
@@ -508,25 +602,28 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
 	outb(new >> 8, 0x4d1);
 }
 
-int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
+int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
-	*irq = gsi_to_irq(gsi);
+	int irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
 
-#ifdef CONFIG_X86_IO_APIC
-	if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC)
-		setup_IO_APIC_irq_extra(gsi);
-#endif
+	if (irq >= 0) {
+		*irqp = irq;
+		return 0;
+	}
 
-	return 0;
+	return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
 
 int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi)
 {
-	if (isa_irq >= 16)
-		return -1;
-	*gsi = irq_to_gsi(isa_irq);
-	return 0;
+	if (isa_irq < nr_legacy_irqs() &&
+	    isa_irq_to_gsi[isa_irq] != ACPI_INVALID_GSI) {
+		*gsi = isa_irq_to_gsi[isa_irq];
+		return 0;
+	}
+
+	return -1;
 }
 
 static int acpi_register_gsi_pic(struct device *dev, u32 gsi,
@@ -546,15 +643,25 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi,
 static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 				    int trigger, int polarity)
 {
+	int irq = gsi;
+
 #ifdef CONFIG_X86_IO_APIC
-	gsi = mp_register_gsi(dev, gsi, trigger, polarity);
+	irq = mp_register_gsi(dev, gsi, trigger, polarity);
 #endif
 
-	return gsi;
+	return irq;
+}
+
+static void acpi_unregister_gsi_ioapic(u32 gsi)
+{
+#ifdef CONFIG_X86_IO_APIC
+	mp_unregister_gsi(gsi);
+#endif
 }
 
 int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
 			   int trigger, int polarity) = acpi_register_gsi_pic;
+void (*__acpi_unregister_gsi)(u32 gsi) = NULL;
 
 #ifdef CONFIG_ACPI_SLEEP
 int (*acpi_suspend_lowlevel)(void) = x86_acpi_suspend_lowlevel;
@@ -568,32 +675,22 @@ int (*acpi_suspend_lowlevel)(void);
  */
 int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 {
-	unsigned int irq;
-	unsigned int plat_gsi = gsi;
-
-	plat_gsi = (*__acpi_register_gsi)(dev, gsi, trigger, polarity);
-	irq = gsi_to_irq(plat_gsi);
-
-	return irq;
+	return __acpi_register_gsi(dev, gsi, trigger, polarity);
 }
 EXPORT_SYMBOL_GPL(acpi_register_gsi);
 
 void acpi_unregister_gsi(u32 gsi)
 {
+	if (__acpi_unregister_gsi)
+		__acpi_unregister_gsi(gsi);
 }
 EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
 
-void __init acpi_set_irq_model_pic(void)
-{
-	acpi_irq_model = ACPI_IRQ_MODEL_PIC;
-	__acpi_register_gsi = acpi_register_gsi_pic;
-	acpi_ioapic = 0;
-}
-
-void __init acpi_set_irq_model_ioapic(void)
+static void __init acpi_set_irq_model_ioapic(void)
 {
 	acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC;
 	__acpi_register_gsi = acpi_register_gsi_ioapic;
+	__acpi_unregister_gsi = acpi_unregister_gsi_ioapic;
 	acpi_ioapic = 1;
 }
 
@@ -829,9 +926,8 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 	 * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value).
 	 */
 
-	count =
-	    acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
-				  acpi_parse_lapic_addr_ovr, 0);
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
+				      acpi_parse_lapic_addr_ovr, 0);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX
 		       "Error parsing LAPIC address override entry\n");
@@ -856,9 +952,8 @@ static int __init acpi_parse_madt_lapic_entries(void)
 	 * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value).
 	 */
 
-	count =
-	    acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
-				  acpi_parse_lapic_addr_ovr, 0);
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
+				      acpi_parse_lapic_addr_ovr, 0);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX
 		       "Error parsing LAPIC address override entry\n");
@@ -886,11 +981,10 @@ static int __init acpi_parse_madt_lapic_entries(void)
 		return count;
 	}
 
-	x2count =
-	    acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI,
-				  acpi_parse_x2apic_nmi, 0);
-	count =
-	    acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0);
+	x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI,
+					acpi_parse_x2apic_nmi, 0);
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI,
+				      acpi_parse_lapic_nmi, 0);
 	if (count < 0 || x2count < 0) {
 		printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
@@ -901,44 +995,7 @@ static int __init acpi_parse_madt_lapic_entries(void)
 #endif				/* CONFIG_X86_LOCAL_APIC */
 
 #ifdef	CONFIG_X86_IO_APIC
-#define MP_ISA_BUS		0
-
-void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
-{
-	int ioapic;
-	int pin;
-	struct mpc_intsrc mp_irq;
-
-	/*
-	 * Convert 'gsi' to 'ioapic.pin'.
-	 */
-	ioapic = mp_find_ioapic(gsi);
-	if (ioapic < 0)
-		return;
-	pin = mp_find_ioapic_pin(ioapic, gsi);
-
-	/*
-	 * TBD: This check is for faulty timer entries, where the override
-	 *      erroneously sets the trigger to level, resulting in a HUGE
-	 *      increase of timer interrupts!
-	 */
-	if ((bus_irq == 0) && (trigger == 3))
-		trigger = 1;
-
-	mp_irq.type = MP_INTSRC;
-	mp_irq.irqtype = mp_INT;
-	mp_irq.irqflag = (trigger << 2) | polarity;
-	mp_irq.srcbus = MP_ISA_BUS;
-	mp_irq.srcbusirq = bus_irq;	/* IRQ */
-	mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */
-	mp_irq.dstirq = pin;	/* INTIN# */
-
-	mp_save_irq(&mp_irq);
-
-	isa_irq_to_gsi[bus_irq] = gsi;
-}
-
-void __init mp_config_acpi_legacy_irqs(void)
+static void __init mp_config_acpi_legacy_irqs(void)
 {
 	int i;
 	struct mpc_intsrc mp_irq;
@@ -956,7 +1013,7 @@ void __init mp_config_acpi_legacy_irqs(void)
 	 * Use the default configuration for the IRQs 0-15.  Unless
 	 * overridden by (MADT) interrupt source override entries.
 	 */
-	for (i = 0; i < 16; i++) {
+	for (i = 0; i < nr_legacy_irqs(); i++) {
 		int ioapic, pin;
 		unsigned int dstapic;
 		int idx;
@@ -1004,84 +1061,6 @@ void __init mp_config_acpi_legacy_irqs(void)
 	}
 }
 
-static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
-			int polarity)
-{
-#ifdef CONFIG_X86_MPPARSE
-	struct mpc_intsrc mp_irq;
-	struct pci_dev *pdev;
-	unsigned char number;
-	unsigned int devfn;
-	int ioapic;
-	u8 pin;
-
-	if (!acpi_ioapic)
-		return 0;
-	if (!dev || !dev_is_pci(dev))
-		return 0;
-
-	pdev = to_pci_dev(dev);
-	number = pdev->bus->number;
-	devfn = pdev->devfn;
-	pin = pdev->pin;
-	/* print the entry should happen on mptable identically */
-	mp_irq.type = MP_INTSRC;
-	mp_irq.irqtype = mp_INT;
-	mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
-				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
-	mp_irq.srcbus = number;
-	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
-	ioapic = mp_find_ioapic(gsi);
-	mp_irq.dstapic = mpc_ioapic_id(ioapic);
-	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
-
-	mp_save_irq(&mp_irq);
-#endif
-	return 0;
-}
-
-int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
-{
-	int ioapic;
-	int ioapic_pin;
-	struct io_apic_irq_attr irq_attr;
-	int ret;
-
-	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
-		return gsi;
-
-	/* Don't set up the ACPI SCI because it's already set up */
-	if (acpi_gbl_FADT.sci_interrupt == gsi)
-		return gsi;
-
-	ioapic = mp_find_ioapic(gsi);
-	if (ioapic < 0) {
-		printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi);
-		return gsi;
-	}
-
-	ioapic_pin = mp_find_ioapic_pin(ioapic, gsi);
-
-	if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
-		printk(KERN_ERR "Invalid reference to IOAPIC pin "
-		       "%d-%d\n", mpc_ioapic_id(ioapic),
-		       ioapic_pin);
-		return gsi;
-	}
-
-	if (enable_update_mptable)
-		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
-
-	set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
-			     trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
-			     polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
-	ret = io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
-	if (ret < 0)
-		gsi = INT_MIN;
-
-	return gsi;
-}
-
 /*
  * Parse IOAPIC related entries in MADT
  * returns 0 on success, < 0 on error
@@ -1111,9 +1090,8 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 		return -ENODEV;
 	}
 
-	count =
-	    acpi_table_parse_madt(ACPI_MADT_TYPE_IO_APIC, acpi_parse_ioapic,
-				  MAX_IO_APICS);
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_IO_APIC, acpi_parse_ioapic,
+				      MAX_IO_APICS);
 	if (!count) {
 		printk(KERN_ERR PREFIX "No IOAPIC entries present\n");
 		return -ENODEV;
@@ -1122,9 +1100,8 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 		return count;
 	}
 
-	count =
-	    acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr,
-				  nr_irqs);
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE,
+				      acpi_parse_int_src_ovr, nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX
 		       "Error parsing interrupt source overrides entry\n");
@@ -1143,9 +1120,8 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 	/* Fill in identity legacy mappings where no override */
 	mp_config_acpi_legacy_irqs();
 
-	count =
-	    acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src,
-				  nr_irqs);
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE,
+				      acpi_parse_nmi_src, nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ad28db7e6bde..6b35d308688c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -67,7 +67,7 @@ EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
 /*
  * The highest APIC ID seen during enumeration.
  */
-unsigned int max_physical_apicid;
+static unsigned int max_physical_apicid;
 
 /*
  * Bitmask of physically existing CPUs:
@@ -2451,51 +2451,6 @@ static void apic_pm_activate(void) { }
 
 #ifdef CONFIG_X86_64
 
-static int apic_cluster_num(void)
-{
-	int i, clusters, zeros;
-	unsigned id;
-	u16 *bios_cpu_apicid;
-	DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
-
-	bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
-	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
-
-	for (i = 0; i < nr_cpu_ids; i++) {
-		/* are we being called early in kernel startup? */
-		if (bios_cpu_apicid) {
-			id = bios_cpu_apicid[i];
-		} else if (i < nr_cpu_ids) {
-			if (cpu_present(i))
-				id = per_cpu(x86_bios_cpu_apicid, i);
-			else
-				continue;
-		} else
-			break;
-
-		if (id != BAD_APICID)
-			__set_bit(APIC_CLUSTERID(id), clustermap);
-	}
-
-	/* Problem:  Partially populated chassis may not have CPUs in some of
-	 * the APIC clusters they have been allocated.  Only present CPUs have
-	 * x86_bios_cpu_apicid entries, thus causing zeroes in the bitmap.
-	 * Since clusters are allocated sequentially, count zeros only if
-	 * they are bounded by ones.
-	 */
-	clusters = 0;
-	zeros = 0;
-	for (i = 0; i < NUM_APIC_CLUSTERS; i++) {
-		if (test_bit(i, clustermap)) {
-			clusters += 1 + zeros;
-			zeros = 0;
-		} else
-			++zeros;
-	}
-
-	return clusters;
-}
-
 static int multi_checked;
 static int multi;
 
@@ -2540,20 +2495,7 @@ static void dmi_check_multi(void)
 int apic_is_clustered_box(void)
 {
 	dmi_check_multi();
-	if (multi)
-		return 1;
-
-	if (!is_vsmp_box())
-		return 0;
-
-	/*
-	 * ScaleMP vSMPowered boxes have one cluster per board and TSCs are
-	 * not guaranteed to be synced between boards
-	 */
-	if (apic_cluster_num() > 1)
-		return 1;
-
-	return 0;
+	return multi;
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 81e08eff05ee..a44dce8cc559 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -31,6 +31,7 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/syscore_ops.h>
+#include <linux/irqdomain.h>
 #include <linux/msi.h>
 #include <linux/htirq.h>
 #include <linux/freezer.h>
@@ -62,6 +63,16 @@
 
 #define __apicdebuginit(type) static type __init
 
+#define	for_each_ioapic(idx)		\
+	for ((idx) = 0; (idx) < nr_ioapics; (idx)++)
+#define	for_each_ioapic_reverse(idx)	\
+	for ((idx) = nr_ioapics - 1; (idx) >= 0; (idx)--)
+#define	for_each_pin(idx, pin)		\
+	for ((pin) = 0; (pin) < ioapics[(idx)].nr_registers; (pin)++)
+#define	for_each_ioapic_pin(idx, pin)	\
+	for_each_ioapic((idx))		\
+		for_each_pin((idx), (pin))
+
 #define for_each_irq_pin(entry, head) \
 	for (entry = head; entry; entry = entry->next)
 
@@ -73,6 +84,17 @@ int sis_apic_bug = -1;
 
 static DEFINE_RAW_SPINLOCK(ioapic_lock);
 static DEFINE_RAW_SPINLOCK(vector_lock);
+static DEFINE_MUTEX(ioapic_mutex);
+static unsigned int ioapic_dynirq_base;
+static int ioapic_initialized;
+
+struct mp_pin_info {
+	int trigger;
+	int polarity;
+	int node;
+	int set;
+	u32 count;
+};
 
 static struct ioapic {
 	/*
@@ -87,7 +109,9 @@ static struct ioapic {
 	struct mpc_ioapic mp_config;
 	/* IO APIC gsi routing info */
 	struct mp_ioapic_gsi  gsi_config;
-	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
+	struct ioapic_domain_cfg irqdomain_cfg;
+	struct irq_domain *irqdomain;
+	struct mp_pin_info *pin_info;
 } ioapics[MAX_IO_APICS];
 
 #define mpc_ioapic_ver(ioapic_idx)	ioapics[ioapic_idx].mp_config.apicver
@@ -107,6 +131,41 @@ struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
 	return &ioapics[ioapic_idx].gsi_config;
 }
 
+static inline int mp_ioapic_pin_count(int ioapic)
+{
+	struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic);
+
+	return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
+}
+
+u32 mp_pin_to_gsi(int ioapic, int pin)
+{
+	return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin;
+}
+
+/*
+ * Initialize all legacy IRQs and all pins on the first IOAPIC
+ * if we have legacy interrupt controller. Kernel boot option "pirq="
+ * may rely on non-legacy pins on the first IOAPIC.
+ */
+static inline int mp_init_irq_at_boot(int ioapic, int irq)
+{
+	if (!nr_legacy_irqs())
+		return 0;
+
+	return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs());
+}
+
+static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin)
+{
+	return ioapics[ioapic_idx].pin_info + pin;
+}
+
+static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic)
+{
+	return ioapics[ioapic].irqdomain;
+}
+
 int nr_ioapics;
 
 /* The one past the highest gsi number used */
@@ -118,9 +177,6 @@ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 /* # of MP IRQ source entries */
 int mp_irq_entries;
 
-/* GSI interrupts */
-static int nr_irqs_gsi = NR_IRQS_LEGACY;
-
 #ifdef CONFIG_EISA
 int mp_bus_id_to_type[MAX_MP_BUSSES];
 #endif
@@ -149,8 +205,7 @@ static int __init parse_noapic(char *str)
 }
 early_param("noapic", parse_noapic);
 
-static int io_apic_setup_irq_pin(unsigned int irq, int node,
-				 struct io_apic_irq_attr *attr);
+static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
 
 /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
 void mp_save_irq(struct mpc_intsrc *m)
@@ -182,19 +237,15 @@ static struct irq_pin_list *alloc_irq_pin_list(int node)
 	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
-
-/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY];
-
 int __init arch_early_irq_init(void)
 {
 	struct irq_cfg *cfg;
-	int count, node, i;
+	int i, node = cpu_to_node(0);
 
-	if (!legacy_pic->nr_legacy_irqs)
+	if (!nr_legacy_irqs())
 		io_apic_irqs = ~0UL;
 
-	for (i = 0; i < nr_ioapics; i++) {
+	for_each_ioapic(i) {
 		ioapics[i].saved_registers =
 			kzalloc(sizeof(struct IO_APIC_route_entry) *
 				ioapics[i].nr_registers, GFP_KERNEL);
@@ -202,28 +253,20 @@ int __init arch_early_irq_init(void)
 			pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
 	}
 
-	cfg = irq_cfgx;
-	count = ARRAY_SIZE(irq_cfgx);
-	node = cpu_to_node(0);
-
-	for (i = 0; i < count; i++) {
-		irq_set_chip_data(i, &cfg[i]);
-		zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
-		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
-		/*
-		 * For legacy IRQ's, start with assigning irq0 to irq15 to
-		 * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
-		 */
-		if (i < legacy_pic->nr_legacy_irqs) {
-			cfg[i].vector = IRQ0_VECTOR + i;
-			cpumask_setall(cfg[i].domain);
-		}
+	/*
+	 * For legacy IRQ's, start with assigning irq0 to irq15 to
+	 * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
+	 */
+	for (i = 0; i < nr_legacy_irqs(); i++) {
+		cfg = alloc_irq_and_cfg_at(i, node);
+		cfg->vector = IRQ0_VECTOR + i;
+		cpumask_setall(cfg->domain);
 	}
 
 	return 0;
 }
 
-static struct irq_cfg *irq_cfg(unsigned int irq)
+static inline struct irq_cfg *irq_cfg(unsigned int irq)
 {
 	return irq_get_chip_data(irq);
 }
@@ -265,7 +308,7 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
 	if (res < 0) {
 		if (res != -EEXIST)
 			return NULL;
-		cfg = irq_get_chip_data(at);
+		cfg = irq_cfg(at);
 		if (cfg)
 			return cfg;
 	}
@@ -425,6 +468,21 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi
 	return 0;
 }
 
+static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
+{
+	struct irq_pin_list **last, *entry;
+
+	last = &cfg->irq_2_pin;
+	for_each_irq_pin(entry, cfg->irq_2_pin)
+		if (entry->apic == apic && entry->pin == pin) {
+			*last = entry->next;
+			kfree(entry);
+			return;
+		} else {
+			last = &entry->next;
+		}
+}
+
 static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	if (__add_pin_to_irq_node(cfg, node, apic, pin))
@@ -627,9 +685,8 @@ static void clear_IO_APIC (void)
 {
 	int apic, pin;
 
-	for (apic = 0; apic < nr_ioapics; apic++)
-		for (pin = 0; pin < ioapics[apic].nr_registers; pin++)
-			clear_IO_APIC_pin(apic, pin);
+	for_each_ioapic_pin(apic, pin)
+		clear_IO_APIC_pin(apic, pin);
 }
 
 #ifdef CONFIG_X86_32
@@ -678,13 +735,13 @@ int save_ioapic_entries(void)
 	int apic, pin;
 	int err = 0;
 
-	for (apic = 0; apic < nr_ioapics; apic++) {
+	for_each_ioapic(apic) {
 		if (!ioapics[apic].saved_registers) {
 			err = -ENOMEM;
 			continue;
 		}
 
-		for (pin = 0; pin < ioapics[apic].nr_registers; pin++)
+		for_each_pin(apic, pin)
 			ioapics[apic].saved_registers[pin] =
 				ioapic_read_entry(apic, pin);
 	}
@@ -699,11 +756,11 @@ void mask_ioapic_entries(void)
 {
 	int apic, pin;
 
-	for (apic = 0; apic < nr_ioapics; apic++) {
+	for_each_ioapic(apic) {
 		if (!ioapics[apic].saved_registers)
 			continue;
 
-		for (pin = 0; pin < ioapics[apic].nr_registers; pin++) {
+		for_each_pin(apic, pin) {
 			struct IO_APIC_route_entry entry;
 
 			entry = ioapics[apic].saved_registers[pin];
@@ -722,11 +779,11 @@ int restore_ioapic_entries(void)
 {
 	int apic, pin;
 
-	for (apic = 0; apic < nr_ioapics; apic++) {
+	for_each_ioapic(apic) {
 		if (!ioapics[apic].saved_registers)
 			continue;
 
-		for (pin = 0; pin < ioapics[apic].nr_registers; pin++)
+		for_each_pin(apic, pin)
 			ioapic_write_entry(apic, pin,
 					   ioapics[apic].saved_registers[pin]);
 	}
@@ -785,7 +842,7 @@ static int __init find_isa_irq_apic(int irq, int type)
 	if (i < mp_irq_entries) {
 		int ioapic_idx;
 
-		for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
+		for_each_ioapic(ioapic_idx)
 			if (mpc_ioapic_id(ioapic_idx) == mp_irqs[i].dstapic)
 				return ioapic_idx;
 	}
@@ -799,7 +856,7 @@ static int __init find_isa_irq_apic(int irq, int type)
  */
 static int EISA_ELCR(unsigned int irq)
 {
-	if (irq < legacy_pic->nr_legacy_irqs) {
+	if (irq < nr_legacy_irqs()) {
 		unsigned int port = 0x4d0 + (irq >> 3);
 		return (inb(port) >> (irq & 7)) & 1;
 	}
@@ -939,29 +996,101 @@ static int irq_trigger(int idx)
 	return trigger;
 }
 
-static int pin_2_irq(int idx, int apic, int pin)
+static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin)
+{
+	int irq = -1;
+	int ioapic = (int)(long)domain->host_data;
+	int type = ioapics[ioapic].irqdomain_cfg.type;
+
+	switch (type) {
+	case IOAPIC_DOMAIN_LEGACY:
+		/*
+		 * Dynamically allocate IRQ number for non-ISA IRQs in the first 16
+		 * GSIs on some weird platforms.
+		 */
+		if (gsi < nr_legacy_irqs())
+			irq = irq_create_mapping(domain, pin);
+		else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
+			irq = gsi;
+		break;
+	case IOAPIC_DOMAIN_STRICT:
+		if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
+			irq = gsi;
+		break;
+	case IOAPIC_DOMAIN_DYNAMIC:
+		irq = irq_create_mapping(domain, pin);
+		break;
+	default:
+		WARN(1, "ioapic: unknown irqdomain type %d\n", type);
+		break;
+	}
+
+	return irq > 0 ? irq : -1;
+}
+
+static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
+			     unsigned int flags)
 {
 	int irq;
-	int bus = mp_irqs[idx].srcbus;
-	struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(apic);
+	struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
+	struct mp_pin_info *info = mp_pin_info(ioapic, pin);
+
+	if (!domain)
+		return -1;
+
+	mutex_lock(&ioapic_mutex);
 
 	/*
-	 * Debugging check, we are in big trouble if this message pops up!
+	 * Don't use irqdomain to manage ISA IRQs because there may be
+	 * multiple IOAPIC pins sharing the same ISA IRQ number and
+	 * irqdomain only supports 1:1 mapping between IOAPIC pin and
+	 * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used
+	 * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
+	 * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are
+	 * available, and some BIOSes may use MP Interrupt Source records
+	 * to override IRQ numbers for PIRQs instead of reprogramming
+	 * the interrupt routing logic. Thus there may be multiple pins
+	 * sharing the same legacy IRQ number when ACPI is disabled.
 	 */
-	if (mp_irqs[idx].dstirq != pin)
-		pr_err("broken BIOS or MPTABLE parser, ayiee!!\n");
-
-	if (test_bit(bus, mp_bus_not_pci)) {
+	if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].srcbusirq;
+		if (flags & IOAPIC_MAP_ALLOC) {
+			if (info->count == 0 &&
+			    mp_irqdomain_map(domain, irq, pin) != 0)
+				irq = -1;
+
+			/* special handling for timer IRQ0 */
+			if (irq == 0)
+				info->count++;
+		}
 	} else {
-		u32 gsi = gsi_cfg->gsi_base + pin;
+		irq = irq_find_mapping(domain, pin);
+		if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC))
+			irq = alloc_irq_from_domain(domain, gsi, pin);
+	}
 
-		if (gsi >= NR_IRQS_LEGACY)
-			irq = gsi;
-		else
-			irq = gsi_top + gsi;
+	if (flags & IOAPIC_MAP_ALLOC) {
+		if (irq > 0)
+			info->count++;
+		else if (info->count == 0)
+			info->set = 0;
 	}
 
+	mutex_unlock(&ioapic_mutex);
+
+	return irq > 0 ? irq : -1;
+}
+
+static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
+{
+	u32 gsi = mp_pin_to_gsi(ioapic, pin);
+
+	/*
+	 * Debugging check, we are in big trouble if this message pops up!
+	 */
+	if (mp_irqs[idx].dstirq != pin)
+		pr_err("broken BIOS or MPTABLE parser, ayiee!!\n");
+
 #ifdef CONFIG_X86_32
 	/*
 	 * PCI IRQ command line redirection. Yes, limits are hardcoded.
@@ -972,16 +1101,58 @@ static int pin_2_irq(int idx, int apic, int pin)
 				apic_printk(APIC_VERBOSE, KERN_DEBUG
 						"disabling PIRQ%d\n", pin-16);
 			} else {
-				irq = pirq_entries[pin-16];
+				int irq = pirq_entries[pin-16];
 				apic_printk(APIC_VERBOSE, KERN_DEBUG
 						"using PIRQ%d -> IRQ %d\n",
 						pin-16, irq);
+				return irq;
 			}
 		}
 	}
 #endif
 
-	return irq;
+	return  mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+}
+
+int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
+{
+	int ioapic, pin, idx;
+
+	ioapic = mp_find_ioapic(gsi);
+	if (ioapic < 0)
+		return -1;
+
+	pin = mp_find_ioapic_pin(ioapic, gsi);
+	idx = find_irq_entry(ioapic, pin, mp_INT);
+	if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
+		return -1;
+
+	return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+}
+
+void mp_unmap_irq(int irq)
+{
+	struct irq_data *data = irq_get_irq_data(irq);
+	struct mp_pin_info *info;
+	int ioapic, pin;
+
+	if (!data || !data->domain)
+		return;
+
+	ioapic = (int)(long)data->domain->host_data;
+	pin = (int)data->hwirq;
+	info = mp_pin_info(ioapic, pin);
+
+	mutex_lock(&ioapic_mutex);
+	if (--info->count == 0) {
+		info->set = 0;
+		if (irq < nr_legacy_irqs() &&
+		    ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY)
+			mp_irqdomain_unmap(data->domain, irq);
+		else
+			irq_dispose_mapping(irq);
+	}
+	mutex_unlock(&ioapic_mutex);
 }
 
 /*
@@ -991,7 +1162,7 @@ static int pin_2_irq(int idx, int apic, int pin)
 int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
 				struct io_apic_irq_attr *irq_attr)
 {
-	int ioapic_idx, i, best_guess = -1;
+	int irq, i, best_ioapic = -1, best_idx = -1;
 
 	apic_printk(APIC_DEBUG,
 		    "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
@@ -1001,44 +1172,56 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
 			    "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
 		return -1;
 	}
+
 	for (i = 0; i < mp_irq_entries; i++) {
 		int lbus = mp_irqs[i].srcbus;
+		int ioapic_idx, found = 0;
 
-		for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
+		if (bus != lbus || mp_irqs[i].irqtype != mp_INT ||
+		    slot != ((mp_irqs[i].srcbusirq >> 2) & 0x1f))
+			continue;
+
+		for_each_ioapic(ioapic_idx)
 			if (mpc_ioapic_id(ioapic_idx) == mp_irqs[i].dstapic ||
-			    mp_irqs[i].dstapic == MP_APIC_ALL)
+			    mp_irqs[i].dstapic == MP_APIC_ALL) {
+				found = 1;
 				break;
+			}
+		if (!found)
+			continue;
 
-		if (!test_bit(lbus, mp_bus_not_pci) &&
-		    !mp_irqs[i].irqtype &&
-		    (bus == lbus) &&
-		    (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i, ioapic_idx, mp_irqs[i].dstirq);
+		/* Skip ISA IRQs */
+		irq = pin_2_irq(i, ioapic_idx, mp_irqs[i].dstirq, 0);
+		if (irq > 0 && !IO_APIC_IRQ(irq))
+			continue;
 
-			if (!(ioapic_idx || IO_APIC_IRQ(irq)))
-				continue;
+		if (pin == (mp_irqs[i].srcbusirq & 3)) {
+			best_idx = i;
+			best_ioapic = ioapic_idx;
+			goto out;
+		}
 
-			if (pin == (mp_irqs[i].srcbusirq & 3)) {
-				set_io_apic_irq_attr(irq_attr, ioapic_idx,
-						     mp_irqs[i].dstirq,
-						     irq_trigger(i),
-						     irq_polarity(i));
-				return irq;
-			}
-			/*
-			 * Use the first all-but-pin matching entry as a
-			 * best-guess fuzzy result for broken mptables.
-			 */
-			if (best_guess < 0) {
-				set_io_apic_irq_attr(irq_attr, ioapic_idx,
-						     mp_irqs[i].dstirq,
-						     irq_trigger(i),
-						     irq_polarity(i));
-				best_guess = irq;
-			}
+		/*
+		 * Use the first all-but-pin matching entry as a
+		 * best-guess fuzzy result for broken mptables.
+		 */
+		if (best_idx < 0) {
+			best_idx = i;
+			best_ioapic = ioapic_idx;
 		}
 	}
-	return best_guess;
+	if (best_idx < 0)
+		return -1;
+
+out:
+	irq = pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq,
+			IOAPIC_MAP_ALLOC);
+	if (irq > 0)
+		set_io_apic_irq_attr(irq_attr, best_ioapic,
+				     mp_irqs[best_idx].dstirq,
+				     irq_trigger(best_idx),
+				     irq_polarity(best_idx));
+	return irq;
 }
 EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
@@ -1198,7 +1381,7 @@ void __setup_vector_irq(int cpu)
 	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_active_irq(irq) {
-		cfg = irq_get_chip_data(irq);
+		cfg = irq_cfg(irq);
 		if (!cfg)
 			continue;
 
@@ -1227,12 +1410,10 @@ static inline int IO_APIC_irq_trigger(int irq)
 {
 	int apic, idx, pin;
 
-	for (apic = 0; apic < nr_ioapics; apic++) {
-		for (pin = 0; pin < ioapics[apic].nr_registers; pin++) {
-			idx = find_irq_entry(apic, pin, mp_INT);
-			if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
-				return irq_trigger(idx);
-		}
+	for_each_ioapic_pin(apic, pin) {
+		idx = find_irq_entry(apic, pin, mp_INT);
+		if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin, 0)))
+			return irq_trigger(idx);
 	}
 	/*
          * nonexistent IRQs are edge default
@@ -1330,95 +1511,29 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
 	}
 
 	ioapic_register_intr(irq, cfg, attr->trigger);
-	if (irq < legacy_pic->nr_legacy_irqs)
+	if (irq < nr_legacy_irqs())
 		legacy_pic->mask(irq);
 
 	ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry);
 }
 
-static bool __init io_apic_pin_not_connected(int idx, int ioapic_idx, int pin)
-{
-	if (idx != -1)
-		return false;
-
-	apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n",
-		    mpc_ioapic_id(ioapic_idx), pin);
-	return true;
-}
-
-static void __init __io_apic_setup_irqs(unsigned int ioapic_idx)
-{
-	int idx, node = cpu_to_node(0);
-	struct io_apic_irq_attr attr;
-	unsigned int pin, irq;
-
-	for (pin = 0; pin < ioapics[ioapic_idx].nr_registers; pin++) {
-		idx = find_irq_entry(ioapic_idx, pin, mp_INT);
-		if (io_apic_pin_not_connected(idx, ioapic_idx, pin))
-			continue;
-
-		irq = pin_2_irq(idx, ioapic_idx, pin);
-
-		if ((ioapic_idx > 0) && (irq > 16))
-			continue;
-
-		/*
-		 * Skip the timer IRQ if there's a quirk handler
-		 * installed and if it returns 1:
-		 */
-		if (apic->multi_timer_check &&
-		    apic->multi_timer_check(ioapic_idx, irq))
-			continue;
-
-		set_io_apic_irq_attr(&attr, ioapic_idx, pin, irq_trigger(idx),
-				     irq_polarity(idx));
-
-		io_apic_setup_irq_pin(irq, node, &attr);
-	}
-}
-
 static void __init setup_IO_APIC_irqs(void)
 {
-	unsigned int ioapic_idx;
+	unsigned int ioapic, pin;
+	int idx;
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
-	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
-		__io_apic_setup_irqs(ioapic_idx);
-}
-
-/*
- * 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 ioapic_idx = 0, pin, idx, irq, node = cpu_to_node(0);
-	struct io_apic_irq_attr attr;
-
-	/*
-	 * Convert 'gsi' to 'ioapic.pin'.
-	 */
-	ioapic_idx = mp_find_ioapic(gsi);
-	if (ioapic_idx < 0)
-		return;
-
-	pin = mp_find_ioapic_pin(ioapic_idx, gsi);
-	idx = find_irq_entry(ioapic_idx, pin, mp_INT);
-	if (idx == -1)
-		return;
-
-	irq = pin_2_irq(idx, ioapic_idx, pin);
-
-	/* Only handle the non legacy irqs on secondary ioapics */
-	if (ioapic_idx == 0 || irq < NR_IRQS_LEGACY)
-		return;
-
-	set_io_apic_irq_attr(&attr, ioapic_idx, pin, irq_trigger(idx),
-			     irq_polarity(idx));
-
-	io_apic_setup_irq_pin_once(irq, node, &attr);
+	for_each_ioapic_pin(ioapic, pin) {
+		idx = find_irq_entry(ioapic, pin, mp_INT);
+		if (idx < 0)
+			apic_printk(APIC_VERBOSE,
+				    KERN_DEBUG " apic %d pin %d not connected\n",
+				    mpc_ioapic_id(ioapic), pin);
+		else
+			pin_2_irq(idx, ioapic, pin,
+				  ioapic ? 0 : IOAPIC_MAP_ALLOC);
+	}
 }
 
 /*
@@ -1586,7 +1701,7 @@ __apicdebuginit(void) print_IO_APICs(void)
 	struct irq_chip *chip;
 
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
-	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
+	for_each_ioapic(ioapic_idx)
 		printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
 		       mpc_ioapic_id(ioapic_idx),
 		       ioapics[ioapic_idx].nr_registers);
@@ -1597,7 +1712,7 @@ __apicdebuginit(void) print_IO_APICs(void)
 	 */
 	printk(KERN_INFO "testing the IO APIC.......................\n");
 
-	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
+	for_each_ioapic(ioapic_idx)
 		print_IO_APIC(ioapic_idx);
 
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
@@ -1608,7 +1723,7 @@ __apicdebuginit(void) print_IO_APICs(void)
 		if (chip != &ioapic_chip)
 			continue;
 
-		cfg = irq_get_chip_data(irq);
+		cfg = irq_cfg(irq);
 		if (!cfg)
 			continue;
 		entry = cfg->irq_2_pin;
@@ -1758,7 +1873,7 @@ __apicdebuginit(void) print_PIC(void)
 	unsigned int v;
 	unsigned long flags;
 
-	if (!legacy_pic->nr_legacy_irqs)
+	if (!nr_legacy_irqs())
 		return;
 
 	printk(KERN_DEBUG "\nprinting PIC contents\n");
@@ -1828,26 +1943,22 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 void __init enable_IO_APIC(void)
 {
 	int i8259_apic, i8259_pin;
-	int apic;
+	int apic, pin;
 
-	if (!legacy_pic->nr_legacy_irqs)
+	if (!nr_legacy_irqs())
 		return;
 
-	for(apic = 0; apic < nr_ioapics; apic++) {
-		int pin;
+	for_each_ioapic_pin(apic, pin) {
 		/* See if any of the pins is in ExtINT mode */
-		for (pin = 0; pin < ioapics[apic].nr_registers; pin++) {
-			struct IO_APIC_route_entry entry;
-			entry = ioapic_read_entry(apic, pin);
+		struct IO_APIC_route_entry entry = ioapic_read_entry(apic, pin);
 
-			/* If the interrupt line is enabled and in ExtInt mode
-			 * I have found the pin where the i8259 is connected.
-			 */
-			if ((entry.mask == 0) && (entry.delivery_mode == dest_ExtINT)) {
-				ioapic_i8259.apic = apic;
-				ioapic_i8259.pin  = pin;
-				goto found_i8259;
-			}
+		/* If the interrupt line is enabled and in ExtInt mode
+		 * I have found the pin where the i8259 is connected.
+		 */
+		if ((entry.mask == 0) && (entry.delivery_mode == dest_ExtINT)) {
+			ioapic_i8259.apic = apic;
+			ioapic_i8259.pin  = pin;
+			goto found_i8259;
 		}
 	}
  found_i8259:
@@ -1919,7 +2030,7 @@ void disable_IO_APIC(void)
 	 */
 	clear_IO_APIC();
 
-	if (!legacy_pic->nr_legacy_irqs)
+	if (!nr_legacy_irqs())
 		return;
 
 	x86_io_apic_ops.disable();
@@ -1950,7 +2061,7 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void)
 	/*
 	 * Set the IOAPIC ID to the value stored in the MPC table.
 	 */
-	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) {
+	for_each_ioapic(ioapic_idx) {
 		/* Read the register 0 value */
 		raw_spin_lock_irqsave(&ioapic_lock, flags);
 		reg_00.raw = io_apic_read(ioapic_idx, 0);
@@ -2123,7 +2234,7 @@ static unsigned int startup_ioapic_irq(struct irq_data *data)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	if (irq < legacy_pic->nr_legacy_irqs) {
+	if (irq < nr_legacy_irqs()) {
 		legacy_pic->mask(irq);
 		if (legacy_pic->irq_pending(irq))
 			was_pending = 1;
@@ -2225,7 +2336,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
 			goto unlock;
 		}
-		__this_cpu_write(vector_irq[vector], -1);
+		__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
 unlock:
 		raw_spin_unlock(&desc->lock);
 	}
@@ -2253,7 +2364,7 @@ static void irq_complete_move(struct irq_cfg *cfg)
 
 void irq_force_complete_move(int irq)
 {
-	struct irq_cfg *cfg = irq_get_chip_data(irq);
+	struct irq_cfg *cfg = irq_cfg(irq);
 
 	if (!cfg)
 		return;
@@ -2514,26 +2625,15 @@ static inline void init_IO_APIC_traps(void)
 	struct irq_cfg *cfg;
 	unsigned int irq;
 
-	/*
-	 * NOTE! The local APIC isn't very good at handling
-	 * multiple interrupts at the same interrupt level.
-	 * As the interrupt level is determined by taking the
-	 * vector number and shifting that right by 4, we
-	 * want to spread these out a bit so that they don't
-	 * all fall in the same interrupt level.
-	 *
-	 * Also, we've got to be careful not to trash gate
-	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
-	 */
 	for_each_active_irq(irq) {
-		cfg = irq_get_chip_data(irq);
+		cfg = irq_cfg(irq);
 		if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
 			 * so default to an old-fashioned 8259
 			 * interrupt if we can..
 			 */
-			if (irq < legacy_pic->nr_legacy_irqs)
+			if (irq < nr_legacy_irqs())
 				legacy_pic->make_irq(irq);
 			else
 				/* Strange. Oh, well.. */
@@ -2649,8 +2749,6 @@ static int __init disable_timer_pin_setup(char *arg)
 }
 early_param("disable_timer_pin_1", disable_timer_pin_setup);
 
-int timer_through_8259 __initdata;
-
 /*
  * This code may look a bit paranoid, but it's supposed to cooperate with
  * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
@@ -2661,7 +2759,7 @@ int timer_through_8259 __initdata;
  */
 static inline void __init check_timer(void)
 {
-	struct irq_cfg *cfg = irq_get_chip_data(0);
+	struct irq_cfg *cfg = irq_cfg(0);
 	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
@@ -2755,7 +2853,6 @@ static inline void __init check_timer(void)
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
-			timer_through_8259 = 1;
 			goto out;
 		}
 		/*
@@ -2827,15 +2924,54 @@ out:
  */
 #define PIC_IRQS	(1UL << PIC_CASCADE_IR)
 
+static int mp_irqdomain_create(int ioapic)
+{
+	size_t size;
+	int hwirqs = mp_ioapic_pin_count(ioapic);
+	struct ioapic *ip = &ioapics[ioapic];
+	struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg;
+	struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic);
+
+	size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic);
+	ip->pin_info = kzalloc(size, GFP_KERNEL);
+	if (!ip->pin_info)
+		return -ENOMEM;
+
+	if (cfg->type == IOAPIC_DOMAIN_INVALID)
+		return 0;
+
+	ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops,
+					      (void *)(long)ioapic);
+	if(!ip->irqdomain) {
+		kfree(ip->pin_info);
+		ip->pin_info = NULL;
+		return -ENOMEM;
+	}
+
+	if (cfg->type == IOAPIC_DOMAIN_LEGACY ||
+	    cfg->type == IOAPIC_DOMAIN_STRICT)
+		ioapic_dynirq_base = max(ioapic_dynirq_base,
+					 gsi_cfg->gsi_end + 1);
+
+	if (gsi_cfg->gsi_base == 0)
+		irq_set_default_host(ip->irqdomain);
+
+	return 0;
+}
+
 void __init setup_IO_APIC(void)
 {
+	int ioapic;
 
 	/*
 	 * calling enable_IO_APIC() is moved to setup_local_APIC for BP
 	 */
-	io_apic_irqs = legacy_pic->nr_legacy_irqs ? ~PIC_IRQS : ~0UL;
+	io_apic_irqs = nr_legacy_irqs() ? ~PIC_IRQS : ~0UL;
 
 	apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
+	for_each_ioapic(ioapic)
+		BUG_ON(mp_irqdomain_create(ioapic));
+
 	/*
          * Set up IO-APIC IRQ routing.
          */
@@ -2844,8 +2980,10 @@ void __init setup_IO_APIC(void)
 	sync_Arb_IDs();
 	setup_IO_APIC_irqs();
 	init_IO_APIC_traps();
-	if (legacy_pic->nr_legacy_irqs)
+	if (nr_legacy_irqs())
 		check_timer();
+
+	ioapic_initialized = 1;
 }
 
 /*
@@ -2880,7 +3018,7 @@ static void ioapic_resume(void)
 {
 	int ioapic_idx;
 
-	for (ioapic_idx = nr_ioapics - 1; ioapic_idx >= 0; ioapic_idx--)
+	for_each_ioapic_reverse(ioapic_idx)
 		resume_ioapic_id(ioapic_idx);
 
 	restore_ioapic_entries();
@@ -2926,7 +3064,7 @@ int arch_setup_hwirq(unsigned int irq, int node)
 
 void arch_teardown_hwirq(unsigned int irq)
 {
-	struct irq_cfg *cfg = irq_get_chip_data(irq);
+	struct irq_cfg *cfg = irq_cfg(irq);
 	unsigned long flags;
 
 	free_remapped_irq(irq);
@@ -3053,7 +3191,7 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 	if (!irq_offset)
 		write_msi_msg(irq, &msg);
 
-	setup_remapped_irq(irq, irq_get_chip_data(irq), chip);
+	setup_remapped_irq(irq, irq_cfg(irq), chip);
 
 	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
 
@@ -3192,7 +3330,7 @@ int default_setup_hpet_msi(unsigned int irq, unsigned int id)
 
 	hpet_msi_write(irq_get_handler_data(irq), &msg);
 	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-	setup_remapped_irq(irq, irq_get_chip_data(irq), chip);
+	setup_remapped_irq(irq, irq_cfg(irq), chip);
 
 	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
 	return 0;
@@ -3303,27 +3441,6 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 	return ret;
 }
 
-int io_apic_setup_irq_pin_once(unsigned int irq, int node,
-			       struct io_apic_irq_attr *attr)
-{
-	unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin;
-	int ret;
-	struct IO_APIC_route_entry orig_entry;
-
-	/* Avoid redundant programming */
-	if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) {
-		pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin);
-		orig_entry = ioapic_read_entry(attr->ioapic, pin);
-		if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity)
-			return 0;
-		return -EBUSY;
-	}
-	ret = io_apic_setup_irq_pin(irq, node, attr);
-	if (!ret)
-		set_bit(pin, ioapics[ioapic_idx].pin_programmed);
-	return ret;
-}
-
 static int __init io_apic_get_redir_entries(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
@@ -3340,20 +3457,13 @@ static int __init io_apic_get_redir_entries(int ioapic)
 	return reg_01.bits.entries + 1;
 }
 
-static void __init probe_nr_irqs_gsi(void)
-{
-	int nr;
-
-	nr = gsi_top + NR_IRQS_LEGACY;
-	if (nr > nr_irqs_gsi)
-		nr_irqs_gsi = nr;
-
-	printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
-}
-
 unsigned int arch_dynirq_lower_bound(unsigned int from)
 {
-	return from < nr_irqs_gsi ? nr_irqs_gsi : from;
+	/*
+	 * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use
+	 * gsi_top if ioapic_dynirq_base hasn't been initialized yet.
+	 */
+	return ioapic_initialized ? ioapic_dynirq_base : gsi_top;
 }
 
 int __init arch_probe_nr_irqs(void)
@@ -3363,33 +3473,17 @@ int __init arch_probe_nr_irqs(void)
 	if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
 		nr_irqs = NR_VECTORS * nr_cpu_ids;
 
-	nr = nr_irqs_gsi + 8 * nr_cpu_ids;
+	nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
 #if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
 	/*
 	 * for MSI and HT dyn irq
 	 */
-	nr += nr_irqs_gsi * 16;
+	nr += gsi_top * 16;
 #endif
 	if (nr < nr_irqs)
 		nr_irqs = nr;
 
-	return NR_IRQS_LEGACY;
-}
-
-int io_apic_set_pci_routing(struct device *dev, int irq,
-			    struct io_apic_irq_attr *irq_attr)
-{
-	int node;
-
-	if (!IO_APIC_IRQ(irq)) {
-		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
-			    irq_attr->ioapic);
-		return -EINVAL;
-	}
-
-	node = dev ? dev_to_node(dev) : cpu_to_node(0);
-
-	return io_apic_setup_irq_pin_once(irq, node, irq_attr);
+	return 0;
 }
 
 #ifdef CONFIG_X86_32
@@ -3483,9 +3577,8 @@ static u8 __init io_apic_unique_id(u8 id)
 	DECLARE_BITMAP(used, 256);
 
 	bitmap_zero(used, 256);
-	for (i = 0; i < nr_ioapics; i++) {
+	for_each_ioapic(i)
 		__set_bit(mpc_ioapic_id(i), used);
-	}
 	if (!test_bit(id, used))
 		return id;
 	return find_first_zero_bit(used, 256);
@@ -3543,14 +3636,13 @@ void __init setup_ioapic_dest(void)
 	if (skip_ioapic_setup == 1)
 		return;
 
-	for (ioapic = 0; ioapic < nr_ioapics; ioapic++)
-	for (pin = 0; pin < ioapics[ioapic].nr_registers; pin++) {
+	for_each_ioapic_pin(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))
+		irq = pin_2_irq(irq_entry, ioapic, pin, 0);
+		if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq))
 			continue;
 
 		idata = irq_get_irq_data(irq);
@@ -3573,29 +3665,33 @@ void __init setup_ioapic_dest(void)
 
 static struct resource *ioapic_resources;
 
-static struct resource * __init ioapic_setup_resources(int nr_ioapics)
+static struct resource * __init ioapic_setup_resources(void)
 {
 	unsigned long n;
 	struct resource *res;
 	char *mem;
-	int i;
+	int i, num = 0;
 
-	if (nr_ioapics <= 0)
+	for_each_ioapic(i)
+		num++;
+	if (num == 0)
 		return NULL;
 
 	n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
-	n *= nr_ioapics;
+	n *= num;
 
 	mem = alloc_bootmem(n);
 	res = (void *)mem;
 
-	mem += sizeof(struct resource) * nr_ioapics;
+	mem += sizeof(struct resource) * num;
 
-	for (i = 0; i < nr_ioapics; i++) {
-		res[i].name = mem;
-		res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	num = 0;
+	for_each_ioapic(i) {
+		res[num].name = mem;
+		res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 		snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
 		mem += IOAPIC_RESOURCE_NAME_SIZE;
+		num++;
 	}
 
 	ioapic_resources = res;
@@ -3609,8 +3705,8 @@ void __init native_io_apic_init_mappings(void)
 	struct resource *ioapic_res;
 	int i;
 
-	ioapic_res = ioapic_setup_resources(nr_ioapics);
-	for (i = 0; i < nr_ioapics; i++) {
+	ioapic_res = ioapic_setup_resources();
+	for_each_ioapic(i) {
 		if (smp_found_config) {
 			ioapic_phys = mpc_ioapic_addr(i);
 #ifdef CONFIG_X86_32
@@ -3641,8 +3737,6 @@ fake_ioapic_page:
 		ioapic_res->end = ioapic_phys + IO_APIC_SLOT_SIZE - 1;
 		ioapic_res++;
 	}
-
-	probe_nr_irqs_gsi();
 }
 
 void __init ioapic_insert_resources(void)
@@ -3657,7 +3751,7 @@ void __init ioapic_insert_resources(void)
 		return;
 	}
 
-	for (i = 0; i < nr_ioapics; i++) {
+	for_each_ioapic(i) {
 		insert_resource(&iomem_resource, r);
 		r++;
 	}
@@ -3665,16 +3759,15 @@ void __init ioapic_insert_resources(void)
 
 int mp_find_ioapic(u32 gsi)
 {
-	int i = 0;
+	int i;
 
 	if (nr_ioapics == 0)
 		return -1;
 
 	/* Find the IOAPIC that manages this GSI. */
-	for (i = 0; i < nr_ioapics; i++) {
+	for_each_ioapic(i) {
 		struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(i);
-		if ((gsi >= gsi_cfg->gsi_base)
-		    && (gsi <= gsi_cfg->gsi_end))
+		if (gsi >= gsi_cfg->gsi_base && gsi <= gsi_cfg->gsi_end)
 			return i;
 	}
 
@@ -3686,7 +3779,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
 {
 	struct mp_ioapic_gsi *gsi_cfg;
 
-	if (WARN_ON(ioapic == -1))
+	if (WARN_ON(ioapic < 0))
 		return -1;
 
 	gsi_cfg = mp_ioapic_gsi_routing(ioapic);
@@ -3729,7 +3822,8 @@ static __init int bad_ioapic_register(int idx)
 	return 0;
 }
 
-void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
+void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
+			       struct ioapic_domain_cfg *cfg)
 {
 	int idx = 0;
 	int entries;
@@ -3743,6 +3837,8 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	ioapics[idx].mp_config.type = MP_IOAPIC;
 	ioapics[idx].mp_config.flags = MPC_APIC_USABLE;
 	ioapics[idx].mp_config.apicaddr = address;
+	ioapics[idx].irqdomain = NULL;
+	ioapics[idx].irqdomain_cfg = *cfg;
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
 
@@ -3779,6 +3875,93 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	nr_ioapics++;
 }
 
+int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
+		     irq_hw_number_t hwirq)
+{
+	int ioapic = (int)(long)domain->host_data;
+	struct mp_pin_info *info = mp_pin_info(ioapic, hwirq);
+	struct io_apic_irq_attr attr;
+
+	/*
+	 * Skip the timer IRQ if there's a quirk handler installed and if it
+	 * returns 1:
+	 */
+	if (apic->multi_timer_check &&
+	    apic->multi_timer_check(ioapic, virq))
+		return 0;
+
+	/* Get default attribute if not set by caller yet */
+	if (!info->set) {
+		u32 gsi = mp_pin_to_gsi(ioapic, hwirq);
+
+		if (acpi_get_override_irq(gsi, &info->trigger,
+					  &info->polarity) < 0) {
+			/*
+			 * PCI interrupts are always polarity one level
+			 * triggered.
+			 */
+			info->trigger = 1;
+			info->polarity = 1;
+		}
+		info->node = NUMA_NO_NODE;
+		info->set = 1;
+	}
+	set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger,
+			     info->polarity);
+
+	return io_apic_setup_irq_pin(virq, info->node, &attr);
+}
+
+void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
+{
+	struct irq_data *data = irq_get_irq_data(virq);
+	struct irq_cfg *cfg = irq_cfg(virq);
+	int ioapic = (int)(long)domain->host_data;
+	int pin = (int)data->hwirq;
+
+	/*
+	 * Skip the timer IRQ if there's a quirk handler installed and if it
+	 * returns 1:
+	 */
+	if (apic->multi_timer_check &&
+	    apic->multi_timer_check(ioapic, virq))
+		return;
+
+	ioapic_mask_entry(ioapic, pin);
+	__remove_pin_from_irq(cfg, ioapic, pin);
+	WARN_ON(cfg->irq_2_pin != NULL);
+	arch_teardown_hwirq(virq);
+}
+
+int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
+{
+	int ret = 0;
+	int ioapic, pin;
+	struct mp_pin_info *info;
+
+	ioapic = mp_find_ioapic(gsi);
+	if (ioapic < 0)
+		return -ENODEV;
+
+	pin = mp_find_ioapic_pin(ioapic, gsi);
+	info = mp_pin_info(ioapic, pin);
+	trigger = trigger ? 1 : 0;
+	polarity = polarity ? 1 : 0;
+
+	mutex_lock(&ioapic_mutex);
+	if (!info->set) {
+		info->trigger = trigger;
+		info->polarity = polarity;
+		info->node = node;
+		info->set = 1;
+	} else if (info->trigger != trigger || info->polarity != polarity) {
+		ret = -EBUSY;
+	}
+	mutex_unlock(&ioapic_mutex);
+
+	return ret;
+}
+
 /* Enable IOAPIC early just for system timer */
 void __init pre_init_apic_IRQ0(void)
 {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ce8b8ff0e0ef..bc360d3df60e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -8,6 +8,7 @@
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
+#include <asm/smp.h>
 #include <asm/pci-direct.h>
 
 #ifdef CONFIG_X86_64
@@ -50,7 +51,6 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
 	return wrmsr_safe_regs(gprs);
 }
 
-#ifdef CONFIG_X86_32
 /*
  *	B step AMD K6 before B 9730xxxx have hardware bugs that can cause
  *	misexecution of code under Linux. Owners of such processors should
@@ -70,6 +70,7 @@ __asm__(".globl vide\n\t.align 4\nvide: ret");
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
 /*
  * General Systems BIOSen alias the cpu frequency registers
  * of the Elan at 0x000df000. Unfortuantly, one of the Linux
@@ -83,11 +84,12 @@ static void init_amd_k5(struct cpuinfo_x86 *c)
 		if (inl(CBAR) & CBAR_ENB)
 			outl(0 | CBAR_KEY, CBAR);
 	}
+#endif
 }
 
-
 static void init_amd_k6(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
 	u32 l, h;
 	int mbytes = get_num_physpages() >> (20-PAGE_SHIFT);
 
@@ -176,10 +178,44 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		/* placeholder for any needed mods */
 		return;
 	}
+#endif
 }
 
-static void amd_k7_smp_check(struct cpuinfo_x86 *c)
+static void init_amd_k7(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
+	u32 l, h;
+
+	/*
+	 * Bit 15 of Athlon specific MSR 15, needs to be 0
+	 * to enable SSE on Palomino/Morgan/Barton CPU's.
+	 * If the BIOS didn't enable it already, enable it here.
+	 */
+	if (c->x86_model >= 6 && c->x86_model <= 10) {
+		if (!cpu_has(c, X86_FEATURE_XMM)) {
+			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
+			msr_clear_bit(MSR_K7_HWCR, 15);
+			set_cpu_cap(c, X86_FEATURE_XMM);
+		}
+	}
+
+	/*
+	 * It's been determined by AMD that Athlons since model 8 stepping 1
+	 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
+	 * As per AMD technical note 27212 0.2
+	 */
+	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
+		rdmsr(MSR_K7_CLK_CTL, l, h);
+		if ((l & 0xfff00000) != 0x20000000) {
+			printk(KERN_INFO
+			    "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
+					l, ((l & 0x000fffff)|0x20000000));
+			wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
+		}
+	}
+
+	set_cpu_cap(c, X86_FEATURE_K7);
+
 	/* calling is from identify_secondary_cpu() ? */
 	if (!c->cpu_index)
 		return;
@@ -207,7 +243,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c)
 	if (((c->x86_model == 6) && (c->x86_mask >= 2)) ||
 	    ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
 	     (c->x86_model > 7))
-		if (cpu_has_mp)
+		if (cpu_has(c, X86_FEATURE_MP))
 			return;
 
 	/* If we get here, not a certified SMP capable AMD system. */
@@ -219,45 +255,8 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c)
 	WARN_ONCE(1, "WARNING: This combination of AMD"
 		" processors is not suitable for SMP.\n");
 	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
-}
-
-static void init_amd_k7(struct cpuinfo_x86 *c)
-{
-	u32 l, h;
-
-	/*
-	 * Bit 15 of Athlon specific MSR 15, needs to be 0
-	 * to enable SSE on Palomino/Morgan/Barton CPU's.
-	 * If the BIOS didn't enable it already, enable it here.
-	 */
-	if (c->x86_model >= 6 && c->x86_model <= 10) {
-		if (!cpu_has(c, X86_FEATURE_XMM)) {
-			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
-			msr_clear_bit(MSR_K7_HWCR, 15);
-			set_cpu_cap(c, X86_FEATURE_XMM);
-		}
-	}
-
-	/*
-	 * It's been determined by AMD that Athlons since model 8 stepping 1
-	 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
-	 * As per AMD technical note 27212 0.2
-	 */
-	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
-		rdmsr(MSR_K7_CLK_CTL, l, h);
-		if ((l & 0xfff00000) != 0x20000000) {
-			printk(KERN_INFO
-			    "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
-					l, ((l & 0x000fffff)|0x20000000));
-			wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
-		}
-	}
-
-	set_cpu_cap(c, X86_FEATURE_K7);
-
-	amd_k7_smp_check(c);
-}
 #endif
+}
 
 #ifdef CONFIG_NUMA
 /*
@@ -446,6 +445,26 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c)
 
 static void bsp_init_amd(struct cpuinfo_x86 *c)
 {
+
+#ifdef CONFIG_X86_64
+	if (c->x86 >= 0xf) {
+		unsigned long long tseg;
+
+		/*
+		 * Split up direct mapping around the TSEG SMM area.
+		 * Don't do it for gbpages because there seems very little
+		 * benefit in doing so.
+		 */
+		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+			unsigned long pfn = tseg >> PAGE_SHIFT;
+
+			printk(KERN_DEBUG "tseg: %010llx\n", tseg);
+			if (pfn_range_is_mapped(pfn, pfn + 1))
+				set_memory_4k((unsigned long)__va(tseg), 1);
+		}
+	}
+#endif
+
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
 
 		if (c->x86 > 0x10 ||
@@ -515,101 +534,74 @@ static const int amd_erratum_383[];
 static const int amd_erratum_400[];
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
-static void init_amd(struct cpuinfo_x86 *c)
+static void init_amd_k8(struct cpuinfo_x86 *c)
 {
-	u32 dummy;
-	unsigned long long value;
-
-#ifdef CONFIG_SMP
-	/*
-	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
-	 * bit 6 of msr C001_0015
-	 *
-	 * Errata 63 for SH-B3 steppings
-	 * Errata 122 for all steppings (F+ have it disabled by default)
-	 */
-	if (c->x86 == 0xf)
-		msr_set_bit(MSR_K7_HWCR, 6);
-#endif
+	u32 level;
+	u64 value;
 
-	early_init_amd(c);
+	/* On C+ stepping K8 rep microcode works well for copy/memset */
+	level = cpuid_eax(1);
+	if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
 	/*
-	 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
-	 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
+	 * Some BIOSes incorrectly force this feature, but only K8 revision D
+	 * (model = 0x14) and later actually support it.
+	 * (AMD Erratum #110, docId: 25759).
 	 */
-	clear_cpu_cap(c, 0*32+31);
-
-#ifdef CONFIG_X86_64
-	/* On C+ stepping K8 rep microcode works well for copy/memset */
-	if (c->x86 == 0xf) {
-		u32 level;
-
-		level = cpuid_eax(1);
-		if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
-			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-
-		/*
-		 * Some BIOSes incorrectly force this feature, but only K8
-		 * revision D (model = 0x14) and later actually support it.
-		 * (AMD Erratum #110, docId: 25759).
-		 */
-		if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
-			clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
-			if (!rdmsrl_amd_safe(0xc001100d, &value)) {
-				value &= ~(1ULL << 32);
-				wrmsrl_amd_safe(0xc001100d, value);
-			}
+	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+		clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
+		if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+			value &= ~BIT_64(32);
+			wrmsrl_amd_safe(0xc001100d, value);
 		}
-
 	}
-	if (c->x86 >= 0x10)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
-	/* get apicid instead of initial apic id from cpuid */
-	c->apicid = hard_smp_processor_id();
-#else
+	if (!c->x86_model_id[0])
+		strcpy(c->x86_model_id, "Hammer");
+}
+
+static void init_amd_gh(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+	/* do this for boot cpu */
+	if (c == &boot_cpu_data)
+		check_enable_amd_mmconf_dmi();
+
+	fam10h_check_enable_mmcfg();
+#endif
 
 	/*
-	 *	FIXME: We should handle the K5 here. Set up the write
-	 *	range and also turn on MSR 83 bits 4 and 31 (write alloc,
-	 *	no bus pipeline)
+	 * Disable GART TLB Walk Errors on Fam10h. We do this here because this
+	 * is always needed when GART is enabled, even in a kernel which has no
+	 * MCE support built in. BIOS should disable GartTlbWlk Errors already.
+	 * If it doesn't, we do it here as suggested by the BKDG.
+	 *
+	 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
 	 */
+	msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
 
-	switch (c->x86) {
-	case 4:
-		init_amd_k5(c);
-		break;
-	case 5:
-		init_amd_k6(c);
-		break;
-	case 6: /* An Athlon/Duron */
-		init_amd_k7(c);
-		break;
-	}
+	/*
+	 * On family 10h BIOS may not have properly enabled WC+ support, causing
+	 * it to be converted to CD memtype. This may result in performance
+	 * degradation for certain nested-paging guests. Prevent this conversion
+	 * by clearing bit 24 in MSR_AMD64_BU_CFG2.
+	 *
+	 * NOTE: we want to use the _safe accessors so as not to #GP kvm
+	 * guests on older kvm hosts.
+	 */
+	msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
 
-	/* K6s reports MCEs but don't actually have all the MSRs */
-	if (c->x86 < 6)
-		clear_cpu_cap(c, X86_FEATURE_MCE);
-#endif
+	if (cpu_has_amd_erratum(c, amd_erratum_383))
+		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+}
 
-	/* Enable workaround for FXSAVE leak */
-	if (c->x86 >= 6)
-		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
-
-	if (!c->x86_model_id[0]) {
-		switch (c->x86) {
-		case 0xf:
-			/* Should distinguish Models here, but this is only
-			   a fallback anyways. */
-			strcpy(c->x86_model_id, "Hammer");
-			break;
-		}
-	}
+static void init_amd_bd(struct cpuinfo_x86 *c)
+{
+	u64 value;
 
 	/* re-enable TopologyExtensions if switched off by BIOS */
-	if ((c->x86 == 0x15) &&
-	    (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
 	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
 
 		if (msr_set_bit(0xc0011005, 54) > 0) {
@@ -625,14 +617,60 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 * The way access filter has a performance penalty on some workloads.
 	 * Disable it on the affected CPUs.
 	 */
-	if ((c->x86 == 0x15) &&
-	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
-
+	if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
 		if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) {
 			value |= 0x1E;
 			wrmsrl_safe(0xc0011021, value);
 		}
 	}
+}
+
+static void init_amd(struct cpuinfo_x86 *c)
+{
+	u32 dummy;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
+	 * bit 6 of msr C001_0015
+	 *
+	 * Errata 63 for SH-B3 steppings
+	 * Errata 122 for all steppings (F+ have it disabled by default)
+	 */
+	if (c->x86 == 0xf)
+		msr_set_bit(MSR_K7_HWCR, 6);
+#endif
+
+	early_init_amd(c);
+
+	/*
+	 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+	 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
+	 */
+	clear_cpu_cap(c, 0*32+31);
+
+	if (c->x86 >= 0x10)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	/* get apicid instead of initial apic id from cpuid */
+	c->apicid = hard_smp_processor_id();
+
+	/* K6s reports MCEs but don't actually have all the MSRs */
+	if (c->x86 < 6)
+		clear_cpu_cap(c, X86_FEATURE_MCE);
+
+	switch (c->x86) {
+	case 4:    init_amd_k5(c); break;
+	case 5:    init_amd_k6(c); break;
+	case 6:	   init_amd_k7(c); break;
+	case 0xf:  init_amd_k8(c); break;
+	case 0x10: init_amd_gh(c); break;
+	case 0x15: init_amd_bd(c); break;
+	}
+
+	/* Enable workaround for FXSAVE leak */
+	if (c->x86 >= 6)
+		set_cpu_bug(c, X86_BUG_FXSAVE_LEAK);
 
 	cpu_detect_cache_sizes(c);
 
@@ -656,33 +694,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
 	}
 
-#ifdef CONFIG_X86_64
-	if (c->x86 == 0x10) {
-		/* do this for boot cpu */
-		if (c == &boot_cpu_data)
-			check_enable_amd_mmconf_dmi();
-
-		fam10h_check_enable_mmcfg();
-	}
-
-	if (c == &boot_cpu_data && c->x86 >= 0xf) {
-		unsigned long long tseg;
-
-		/*
-		 * Split up direct mapping around the TSEG SMM area.
-		 * Don't do it for gbpages because there seems very little
-		 * benefit in doing so.
-		 */
-		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
-			unsigned long pfn = tseg >> PAGE_SHIFT;
-
-			printk(KERN_DEBUG "tseg: %010llx\n", tseg);
-			if (pfn_range_is_mapped(pfn, pfn + 1))
-				set_memory_4k((unsigned long)__va(tseg), 1);
-		}
-	}
-#endif
-
 	/*
 	 * Family 0x12 and above processors have APIC timer
 	 * running in deep C states.
@@ -690,34 +701,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 > 0x11)
 		set_cpu_cap(c, X86_FEATURE_ARAT);
 
-	if (c->x86 == 0x10) {
-		/*
-		 * Disable GART TLB Walk Errors on Fam10h. We do this here
-		 * because this is always needed when GART is enabled, even in a
-		 * kernel which has no MCE support built in.
-		 * BIOS should disable GartTlbWlk Errors already. If
-		 * it doesn't, do it here as suggested by the BKDG.
-		 *
-		 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
-		 */
-		msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
-
-		/*
-		 * On family 10h BIOS may not have properly enabled WC+ support,
-		 * causing it to be converted to CD memtype. This may result in
-		 * performance degradation for certain nested-paging guests.
-		 * Prevent this conversion by clearing bit 24 in
-		 * MSR_AMD64_BU_CFG2.
-		 *
-		 * NOTE: we want to use the _safe accessors so as not to #GP kvm
-		 * guests on older kvm hosts.
-		 */
-		msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
-
-		if (cpu_has_amd_erratum(c, amd_erratum_383))
-			set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
-	}
-
 	if (cpu_has_amd_erratum(c, amd_erratum_400))
 		set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index ef1b93f18ed1..ce31eeada362 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -148,6 +148,7 @@ static int __init x86_xsave_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 	setup_clear_cpu_cap(X86_FEATURE_AVX);
 	setup_clear_cpu_cap(X86_FEATURE_AVX2);
 	return 1;
@@ -161,6 +162,13 @@ static int __init x86_xsaveopt_setup(char *s)
 }
 __setup("noxsaveopt", x86_xsaveopt_setup);
 
+static int __init x86_xsaves_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	return 1;
+}
+__setup("noxsaves", x86_xsaves_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
 static int disable_x86_serial_nr = 1;
@@ -634,6 +642,15 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[9] = ebx;
 	}
 
+	/* Extended state features: level 0x0000000d */
+	if (c->cpuid_level >= 0x0000000d) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_capability[10] = eax;
+	}
+
 	/* AMD-defined flags: level 0x80000001 */
 	xlvl = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = xlvl;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f9e4fdd3b877..9483ee5b3991 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -253,7 +253,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 */
 	if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
 	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
-		set_cpu_cap(c, X86_FEATURE_11AP);
+		set_cpu_bug(c, X86_BUG_11AP);
 
 
 #ifdef CONFIG_X86_INTEL_USERCOPY
@@ -402,7 +402,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	if (c->x86 == 6 && cpu_has_clflush &&
 	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
-		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
+		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9a79c8dbd8e8..4fc57975acc1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2385,6 +2385,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			threshold_cpu_callback(action, cpu);
 		mce_device_remove(cpu);
 		mce_intel_hcpu_update(cpu);
+
+		/* intentionally ignoring frozen here */
+		if (!(action & CPU_TASKS_FROZEN))
+			cmci_rediscover();
 		break;
 	case CPU_DOWN_PREPARE:
 		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
@@ -2396,11 +2400,6 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	}
 
-	if (action == CPU_POST_DEAD) {
-		/* intentionally ignoring frozen here */
-		cmci_rediscover();
-	}
-
 	return NOTIFY_OK;
 }
 
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index 2bf616505499..e2b22df964cd 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -1,23 +1,25 @@
 #!/bin/sh
 #
-# Generate the x86_cap_flags[] array from include/asm/cpufeature.h
+# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h
 #
 
 IN=$1
 OUT=$2
 
-TABS="$(printf '\t\t\t\t\t')"
-trap 'rm "$OUT"' EXIT
+function dump_array()
+{
+	ARRAY=$1
+	SIZE=$2
+	PFX=$3
+	POSTFIX=$4
 
-(
-	echo "#ifndef _ASM_X86_CPUFEATURE_H"
-	echo "#include <asm/cpufeature.h>"
-	echo "#endif"
-	echo ""
-	echo "const char * const x86_cap_flags[NCAPINTS*32] = {"
+	PFX_SZ=$(echo $PFX | wc -c)
+	TABS="$(printf '\t\t\t\t\t')"
+
+	echo "const char * const $ARRAY[$SIZE] = {"
 
-	# Iterate through any input lines starting with #define X86_FEATURE_
-	sed -n -e 's/\t/ /g' -e 's/^ *# *define *X86_FEATURE_//p' $IN |
+	# Iterate through any input lines starting with #define $PFX
+	sed -n -e 's/\t/ /g' -e "s/^ *# *define *$PFX//p" $IN |
 	while read i
 	do
 		# Name is everything up to the first whitespace
@@ -31,11 +33,32 @@ trap 'rm "$OUT"' EXIT
 		# Name is uppercase, VALUE is all lowercase
 		VALUE="$(echo "$VALUE" | tr A-Z a-z)"
 
-		TABCOUNT=$(( ( 5*8 - 14 - $(echo "$NAME" | wc -c) ) / 8 ))
-		printf "\t[%s]%.*s = %s,\n" \
-			"X86_FEATURE_$NAME" "$TABCOUNT" "$TABS" "$VALUE"
+        if [ -n "$POSTFIX" ]; then
+            T=$(( $PFX_SZ + $(echo $POSTFIX | wc -c) + 2 ))
+	        TABS="$(printf '\t\t\t\t\t\t')"
+		    TABCOUNT=$(( ( 6*8 - ($T + 1) - $(echo "$NAME" | wc -c) ) / 8 ))
+		    printf "\t[%s - %s]%.*s = %s,\n" "$PFX$NAME" "$POSTFIX" "$TABCOUNT" "$TABS" "$VALUE"
+        else
+		    TABCOUNT=$(( ( 5*8 - ($PFX_SZ + 1) - $(echo "$NAME" | wc -c) ) / 8 ))
+            printf "\t[%s]%.*s = %s,\n" "$PFX$NAME" "$TABCOUNT" "$TABS" "$VALUE"
+        fi
 	done
 	echo "};"
+}
+
+trap 'rm "$OUT"' EXIT
+
+(
+	echo "#ifndef _ASM_X86_CPUFEATURE_H"
+	echo "#include <asm/cpufeature.h>"
+	echo "#endif"
+	echo ""
+
+	dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" ""
+	echo ""
+
+	dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32"
+
 ) > $OUT
 
 trap - EXIT
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 3bbdf4cd38b9..30790d798e6b 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -294,31 +294,41 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
 			cpu_to_node(cpu));
 }
 
-static void amd_uncore_cpu_up_prepare(unsigned int cpu)
+static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 {
-	struct amd_uncore *uncore;
+	struct amd_uncore *uncore_nb = NULL, *uncore_l2;
 
 	if (amd_uncore_nb) {
-		uncore = amd_uncore_alloc(cpu);
-		uncore->cpu = cpu;
-		uncore->num_counters = NUM_COUNTERS_NB;
-		uncore->rdpmc_base = RDPMC_BASE_NB;
-		uncore->msr_base = MSR_F15H_NB_PERF_CTL;
-		uncore->active_mask = &amd_nb_active_mask;
-		uncore->pmu = &amd_nb_pmu;
-		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+		uncore_nb = amd_uncore_alloc(cpu);
+		if (!uncore_nb)
+			goto fail;
+		uncore_nb->cpu = cpu;
+		uncore_nb->num_counters = NUM_COUNTERS_NB;
+		uncore_nb->rdpmc_base = RDPMC_BASE_NB;
+		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
+		uncore_nb->active_mask = &amd_nb_active_mask;
+		uncore_nb->pmu = &amd_nb_pmu;
+		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
 	}
 
 	if (amd_uncore_l2) {
-		uncore = amd_uncore_alloc(cpu);
-		uncore->cpu = cpu;
-		uncore->num_counters = NUM_COUNTERS_L2;
-		uncore->rdpmc_base = RDPMC_BASE_L2;
-		uncore->msr_base = MSR_F16H_L2I_PERF_CTL;
-		uncore->active_mask = &amd_l2_active_mask;
-		uncore->pmu = &amd_l2_pmu;
-		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+		uncore_l2 = amd_uncore_alloc(cpu);
+		if (!uncore_l2)
+			goto fail;
+		uncore_l2->cpu = cpu;
+		uncore_l2->num_counters = NUM_COUNTERS_L2;
+		uncore_l2->rdpmc_base = RDPMC_BASE_L2;
+		uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
+		uncore_l2->active_mask = &amd_l2_active_mask;
+		uncore_l2->pmu = &amd_l2_pmu;
+		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
 	}
+
+	return 0;
+
+fail:
+	kfree(uncore_nb);
+	return -ENOMEM;
 }
 
 static struct amd_uncore *
@@ -441,7 +451,7 @@ static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
 
 	if (!--uncore->refcnt)
 		kfree(uncore);
-	*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
+	*per_cpu_ptr(uncores, cpu) = NULL;
 }
 
 static void amd_uncore_cpu_dead(unsigned int cpu)
@@ -461,7 +471,8 @@ amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
-		amd_uncore_cpu_up_prepare(cpu);
+		if (amd_uncore_cpu_up_prepare(cpu))
+			return notifier_from_errno(-ENOMEM);
 		break;
 
 	case CPU_STARTING:
@@ -501,20 +512,33 @@ static void __init init_cpu_already_online(void *dummy)
 	amd_uncore_cpu_online(cpu);
 }
 
+static void cleanup_cpu_online(void *dummy)
+{
+	unsigned int cpu = smp_processor_id();
+
+	amd_uncore_cpu_dead(cpu);
+}
+
 static int __init amd_uncore_init(void)
 {
-	unsigned int cpu;
+	unsigned int cpu, cpu2;
 	int ret = -ENODEV;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
-		return -ENODEV;
+		goto fail_nodev;
 
 	if (!cpu_has_topoext)
-		return -ENODEV;
+		goto fail_nodev;
 
 	if (cpu_has_perfctr_nb) {
 		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
-		perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+		if (!amd_uncore_nb) {
+			ret = -ENOMEM;
+			goto fail_nb;
+		}
+		ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+		if (ret)
+			goto fail_nb;
 
 		printk(KERN_INFO "perf: AMD NB counters detected\n");
 		ret = 0;
@@ -522,20 +546,28 @@ static int __init amd_uncore_init(void)
 
 	if (cpu_has_perfctr_l2) {
 		amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
-		perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+		if (!amd_uncore_l2) {
+			ret = -ENOMEM;
+			goto fail_l2;
+		}
+		ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+		if (ret)
+			goto fail_l2;
 
 		printk(KERN_INFO "perf: AMD L2I counters detected\n");
 		ret = 0;
 	}
 
 	if (ret)
-		return -ENODEV;
+		goto fail_nodev;
 
 	cpu_notifier_register_begin();
 
 	/* init cpus already online before registering for hotplug notifier */
 	for_each_online_cpu(cpu) {
-		amd_uncore_cpu_up_prepare(cpu);
+		ret = amd_uncore_cpu_up_prepare(cpu);
+		if (ret)
+			goto fail_online;
 		smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
 	}
 
@@ -543,5 +575,30 @@ static int __init amd_uncore_init(void)
 	cpu_notifier_register_done();
 
 	return 0;
+
+
+fail_online:
+	for_each_online_cpu(cpu2) {
+		if (cpu2 == cpu)
+			break;
+		smp_call_function_single(cpu, cleanup_cpu_online, NULL, 1);
+	}
+	cpu_notifier_register_done();
+
+	/* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */
+	amd_uncore_nb = amd_uncore_l2 = NULL;
+	if (cpu_has_perfctr_l2)
+		perf_pmu_unregister(&amd_l2_pmu);
+fail_l2:
+	if (cpu_has_perfctr_nb)
+		perf_pmu_unregister(&amd_nb_pmu);
+	if (amd_uncore_l2)
+		free_percpu(amd_uncore_l2);
+fail_nb:
+	if (amd_uncore_nb)
+		free_percpu(amd_uncore_nb);
+
+fail_nodev:
+	return ret;
 }
 device_initcall(amd_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index ae6552a0701f..cfc6f9dfcd90 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2947,10 +2947,7 @@ again:
 		 * extra registers. If we failed to take an extra
 		 * register, try the alternative.
 		 */
-		if (idx % 2)
-			idx--;
-		else
-			idx++;
+		idx ^= 1;
 		if (idx != reg1->idx % 6) {
 			if (idx == 2)
 				config1 >>= 8;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 06fe3ed8b851..5433658e598d 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -97,6 +97,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		if (cpu_has(c, i) && x86_cap_flags[i] != NULL)
 			seq_printf(m, " %s", x86_cap_flags[i]);
 
+	seq_printf(m, "\nbugs\t\t:");
+	for (i = 0; i < 32*NBUGINTS; i++) {
+		unsigned int bug_bit = 32*NCAPINTS + i;
+
+		if (cpu_has_bug(c, bug_bit) && x86_bug_flags[i])
+			seq_printf(m, " %s", x86_bug_flags[i]);
+	}
+
 	seq_printf(m, "\nbogomips\t: %lu.%02lu\n",
 		   c->loops_per_jiffy/(500000/HZ),
 		   (c->loops_per_jiffy/(5000/HZ)) % 100);
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index b6f794aa1693..4a8013d55947 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -38,7 +38,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
 		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
 		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
-		{ X86_FEATURE_XSAVEOPT,		CR_EAX,	0, 0x0000000d, 1 },
 		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },
 		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
 		{ X86_FEATURE_PROC_FEEDBACK,	CR_EDX,11, 0x80000007, 0 },
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 7db54b5d5f86..3d3503351242 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -21,6 +21,7 @@
 #include <asm/apic.h>
 #include <asm/pci_x86.h>
 #include <asm/setup.h>
+#include <asm/i8259.h>
 
 __initdata u64 initial_dtb;
 char __initdata cmd_line[COMMAND_LINE_SIZE];
@@ -165,82 +166,6 @@ static void __init dtb_lapic_setup(void)
 #ifdef CONFIG_X86_IO_APIC
 static unsigned int ioapic_id;
 
-static void __init dtb_add_ioapic(struct device_node *dn)
-{
-	struct resource r;
-	int ret;
-
-	ret = of_address_to_resource(dn, 0, &r);
-	if (ret) {
-		printk(KERN_ERR "Can't obtain address from node %s.\n",
-				dn->full_name);
-		return;
-	}
-	mp_register_ioapic(++ioapic_id, r.start, gsi_top);
-}
-
-static void __init dtb_ioapic_setup(void)
-{
-	struct device_node *dn;
-
-	for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic")
-		dtb_add_ioapic(dn);
-
-	if (nr_ioapics) {
-		of_ioapic = 1;
-		return;
-	}
-	printk(KERN_ERR "Error: No information about IO-APIC in OF.\n");
-}
-#else
-static void __init dtb_ioapic_setup(void) {}
-#endif
-
-static void __init dtb_apic_setup(void)
-{
-	dtb_lapic_setup();
-	dtb_ioapic_setup();
-}
-
-#ifdef CONFIG_OF_FLATTREE
-static void __init x86_flattree_get_config(void)
-{
-	u32 size, map_len;
-	void *dt;
-
-	if (!initial_dtb)
-		return;
-
-	map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
-
-	initial_boot_params = dt = early_memremap(initial_dtb, map_len);
-	size = of_get_flat_dt_size();
-	if (map_len < size) {
-		early_iounmap(dt, map_len);
-		initial_boot_params = dt = early_memremap(initial_dtb, size);
-		map_len = size;
-	}
-
-	unflatten_and_copy_device_tree();
-	early_iounmap(dt, map_len);
-}
-#else
-static inline void x86_flattree_get_config(void) { }
-#endif
-
-void __init x86_dtb_init(void)
-{
-	x86_flattree_get_config();
-
-	if (!of_have_populated_dt())
-		return;
-
-	dtb_setup_hpet();
-	dtb_apic_setup();
-}
-
-#ifdef CONFIG_X86_IO_APIC
-
 struct of_ioapic_type {
 	u32 out_type;
 	u32 trigger;
@@ -276,10 +201,8 @@ static int ioapic_xlate(struct irq_domain *domain,
 			const u32 *intspec, u32 intsize,
 			irq_hw_number_t *out_hwirq, u32 *out_type)
 {
-	struct io_apic_irq_attr attr;
 	struct of_ioapic_type *it;
-	u32 line, idx;
-	int rc;
+	u32 line, idx, gsi;
 
 	if (WARN_ON(intsize < 2))
 		return -EINVAL;
@@ -291,13 +214,10 @@ static int ioapic_xlate(struct irq_domain *domain,
 
 	it = &of_ioapic_type[intspec[1]];
 
-	idx = (u32) domain->host_data;
-	set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity);
-
-	rc = io_apic_setup_irq_pin_once(irq_find_mapping(domain, line),
-					cpu_to_node(0), &attr);
-	if (rc)
-		return rc;
+	idx = (u32)(long)domain->host_data;
+	gsi = mp_pin_to_gsi(idx, line);
+	if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0)))
+		return -EBUSY;
 
 	*out_hwirq = line;
 	*out_type = it->out_type;
@@ -305,81 +225,86 @@ static int ioapic_xlate(struct irq_domain *domain,
 }
 
 const struct irq_domain_ops ioapic_irq_domain_ops = {
+	.map = mp_irqdomain_map,
+	.unmap = mp_irqdomain_unmap,
 	.xlate = ioapic_xlate,
 };
 
-static void dt_add_ioapic_domain(unsigned int ioapic_num,
-		struct device_node *np)
+static void __init dtb_add_ioapic(struct device_node *dn)
 {
-	struct irq_domain *id;
-	struct mp_ioapic_gsi *gsi_cfg;
+	struct resource r;
 	int ret;
-	int num;
-
-	gsi_cfg = mp_ioapic_gsi_routing(ioapic_num);
-	num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
-
-	id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops,
-			(void *)ioapic_num);
-	BUG_ON(!id);
-	if (gsi_cfg->gsi_base == 0) {
-		/*
-		 * The first NR_IRQS_LEGACY irq descs are allocated in
-		 * early_irq_init() and need just a mapping. The
-		 * remaining irqs need both. All of them are preallocated
-		 * and assigned so we can keep the 1:1 mapping which the ioapic
-		 * is having.
-		 */
-		irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY);
-
-		if (num > NR_IRQS_LEGACY) {
-			ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY,
-					NR_IRQS_LEGACY, num - NR_IRQS_LEGACY);
-			if (ret)
-				pr_err("Error creating mapping for the "
-						"remaining IRQs: %d\n", ret);
-		}
-		irq_set_default_host(id);
-	} else {
-		ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num);
-		if (ret)
-			pr_err("Error creating IRQ mapping: %d\n", ret);
+	struct ioapic_domain_cfg cfg = {
+		.type = IOAPIC_DOMAIN_DYNAMIC,
+		.ops = &ioapic_irq_domain_ops,
+		.dev = dn,
+	};
+
+	ret = of_address_to_resource(dn, 0, &r);
+	if (ret) {
+		printk(KERN_ERR "Can't obtain address from node %s.\n",
+				dn->full_name);
+		return;
 	}
+	mp_register_ioapic(++ioapic_id, r.start, gsi_top, &cfg);
 }
 
-static void __init ioapic_add_ofnode(struct device_node *np)
+static void __init dtb_ioapic_setup(void)
 {
-	struct resource r;
-	int i, ret;
+	struct device_node *dn;
 
-	ret = of_address_to_resource(np, 0, &r);
-	if (ret) {
-		printk(KERN_ERR "Failed to obtain address for %s\n",
-				np->full_name);
+	for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic")
+		dtb_add_ioapic(dn);
+
+	if (nr_ioapics) {
+		of_ioapic = 1;
 		return;
 	}
+	printk(KERN_ERR "Error: No information about IO-APIC in OF.\n");
+}
+#else
+static void __init dtb_ioapic_setup(void) {}
+#endif
 
-	for (i = 0; i < nr_ioapics; i++) {
-		if (r.start == mpc_ioapic_addr(i)) {
-			dt_add_ioapic_domain(i, np);
-			return;
-		}
-	}
-	printk(KERN_ERR "IOxAPIC at %s is not registered.\n", np->full_name);
+static void __init dtb_apic_setup(void)
+{
+	dtb_lapic_setup();
+	dtb_ioapic_setup();
 }
 
-void __init x86_add_irq_domains(void)
+#ifdef CONFIG_OF_FLATTREE
+static void __init x86_flattree_get_config(void)
 {
-	struct device_node *dp;
+	u32 size, map_len;
+	void *dt;
 
-	if (!of_have_populated_dt())
+	if (!initial_dtb)
 		return;
 
-	for_each_node_with_property(dp, "interrupt-controller") {
-		if (of_device_is_compatible(dp, "intel,ce4100-ioapic"))
-			ioapic_add_ofnode(dp);
+	map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
+
+	initial_boot_params = dt = early_memremap(initial_dtb, map_len);
+	size = of_get_flat_dt_size();
+	if (map_len < size) {
+		early_iounmap(dt, map_len);
+		initial_boot_params = dt = early_memremap(initial_dtb, size);
+		map_len = size;
 	}
+
+	unflatten_and_copy_device_tree();
+	early_iounmap(dt, map_len);
 }
 #else
-void __init x86_add_irq_domains(void) { }
+static inline void x86_flattree_get_config(void) { }
 #endif
+
+void __init x86_dtb_init(void)
+{
+	x86_flattree_get_config();
+
+	if (!of_have_populated_dt())
+		return;
+
+	dtb_setup_hpet();
+	dtb_apic_setup();
+}
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 7e3f1d950b65..c5781f55f1a1 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -207,7 +207,6 @@ ENDPROC(native_usergs_sysret64)
  */
 	.macro XCPT_FRAME start=1 offset=0
 	INTR_FRAME \start, RIP+\offset-ORIG_RAX
-	/*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/
 	.endm
 
 /*
@@ -287,21 +286,21 @@ ENDPROC(native_usergs_sysret64)
 ENTRY(save_paranoid)
 	XCPT_FRAME 1 RDI+8
 	cld
-	movq_cfi rdi, RDI+8
-	movq_cfi rsi, RSI+8
+	movq %rdi, RDI+8(%rsp)
+	movq %rsi, RSI+8(%rsp)
 	movq_cfi rdx, RDX+8
 	movq_cfi rcx, RCX+8
 	movq_cfi rax, RAX+8
-	movq_cfi r8, R8+8
-	movq_cfi r9, R9+8
-	movq_cfi r10, R10+8
-	movq_cfi r11, R11+8
+	movq %r8, R8+8(%rsp)
+	movq %r9, R9+8(%rsp)
+	movq %r10, R10+8(%rsp)
+	movq %r11, R11+8(%rsp)
 	movq_cfi rbx, RBX+8
-	movq_cfi rbp, RBP+8
-	movq_cfi r12, R12+8
-	movq_cfi r13, R13+8
-	movq_cfi r14, R14+8
-	movq_cfi r15, R15+8
+	movq %rbp, RBP+8(%rsp)
+	movq %r12, R12+8(%rsp)
+	movq %r13, R13+8(%rsp)
+	movq %r14, R14+8(%rsp)
+	movq %r15, R15+8(%rsp)
 	movl $1,%ebx
 	movl $MSR_GS_BASE,%ecx
 	rdmsr
@@ -1394,21 +1393,21 @@ ENTRY(error_entry)
 	CFI_ADJUST_CFA_OFFSET 15*8
 	/* oldrax contains error code */
 	cld
-	movq_cfi rdi, RDI+8
-	movq_cfi rsi, RSI+8
-	movq_cfi rdx, RDX+8
-	movq_cfi rcx, RCX+8
-	movq_cfi rax, RAX+8
-	movq_cfi  r8,  R8+8
-	movq_cfi  r9,  R9+8
-	movq_cfi r10, R10+8
-	movq_cfi r11, R11+8
+	movq %rdi, RDI+8(%rsp)
+	movq %rsi, RSI+8(%rsp)
+	movq %rdx, RDX+8(%rsp)
+	movq %rcx, RCX+8(%rsp)
+	movq %rax, RAX+8(%rsp)
+	movq  %r8,  R8+8(%rsp)
+	movq  %r9,  R9+8(%rsp)
+	movq %r10, R10+8(%rsp)
+	movq %r11, R11+8(%rsp)
 	movq_cfi rbx, RBX+8
-	movq_cfi rbp, RBP+8
-	movq_cfi r12, R12+8
-	movq_cfi r13, R13+8
-	movq_cfi r14, R14+8
-	movq_cfi r15, R15+8
+	movq %rbp, RBP+8(%rsp)
+	movq %r12, R12+8(%rsp)
+	movq %r13, R13+8(%rsp)
+	movq %r14, R14+8(%rsp)
+	movq %r15, R15+8(%rsp)
 	xorl %ebx,%ebx
 	testl $3,CS+8(%rsp)
 	je error_kernelspace
@@ -1426,6 +1425,7 @@ error_sti:
  * compat mode. Check for these here too.
  */
 error_kernelspace:
+	CFI_REL_OFFSET rcx, RCX+8
 	incl %ebx
 	leaq irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index d5dd80814419..a9a4229f6161 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -375,7 +375,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	/*
 	 * These bits must be zero.
 	 */
-	xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+	memset(xsave_hdr->reserved, 0, 48);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 7f50156542fb..1e6cff5814fa 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -78,7 +78,7 @@ void __init init_ISA_irqs(void)
 #endif
 	legacy_pic->init(0);
 
-	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
+	for (i = 0; i < nr_legacy_irqs(); i++)
 		irq_set_chip_and_handler_name(i, chip, handle_level_irq, name);
 }
 
@@ -87,12 +87,6 @@ void __init init_IRQ(void)
 	int i;
 
 	/*
-	 * We probably need a better place for this, but it works for
-	 * now ...
-	 */
-	x86_add_irq_domains();
-
-	/*
 	 * 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
@@ -100,7 +94,7 @@ void __init init_IRQ(void)
 	 * then this vector space can be freed and re-used dynamically as the
 	 * irq's migrate etc.
 	 */
-	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
+	for (i = 0; i < nr_legacy_irqs(); i++)
 		per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i;
 
 	x86_init.irqs.intr_init();
@@ -121,7 +115,7 @@ void setup_vector_irq(int cpu)
 	 * legacy PIC, for the new cpu that is coming online, setup the static
 	 * legacy vector to irq mapping:
 	 */
-	for (irq = 0; irq < legacy_pic->nr_legacy_irqs; irq++)
+	for (irq = 0; irq < nr_legacy_irqs(); irq++)
 		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
 #endif
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index d2b56489d70f..fde86d2b79f8 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/smp.h>
 #include <linux/pci.h>
+#include <linux/irqdomain.h>
 
 #include <asm/mtrr.h>
 #include <asm/mpspec.h>
@@ -67,7 +68,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 		boot_cpu_physical_apicid = m->apicid;
 	}
 
-	printk(KERN_INFO "Processor #%d%s\n", m->apicid, bootup_cpu);
+	pr_info("Processor #%d%s\n", m->apicid, bootup_cpu);
 	generic_processor_info(apicid, m->apicver);
 }
 
@@ -87,9 +88,8 @@ static void __init MP_bus_info(struct mpc_bus *m)
 
 #if MAX_MP_BUSSES < 256
 	if (m->busid >= MAX_MP_BUSSES) {
-		printk(KERN_WARNING "MP table busid value (%d) for bustype %s "
-		       " is too large, max. supported is %d\n",
-		       m->busid, str, MAX_MP_BUSSES - 1);
+		pr_warn("MP table busid value (%d) for bustype %s is too large, max. supported is %d\n",
+			m->busid, str, MAX_MP_BUSSES - 1);
 		return;
 	}
 #endif
@@ -110,19 +110,29 @@ static void __init MP_bus_info(struct mpc_bus *m)
 		mp_bus_id_to_type[m->busid] = MP_BUS_EISA;
 #endif
 	} else
-		printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str);
+		pr_warn("Unknown bustype %s - ignoring\n", str);
 }
 
+static struct irq_domain_ops mp_ioapic_irqdomain_ops = {
+	.map = mp_irqdomain_map,
+	.unmap = mp_irqdomain_unmap,
+};
+
 static void __init MP_ioapic_info(struct mpc_ioapic *m)
 {
+	struct ioapic_domain_cfg cfg = {
+		.type = IOAPIC_DOMAIN_LEGACY,
+		.ops = &mp_ioapic_irqdomain_ops,
+	};
+
 	if (m->flags & MPC_APIC_USABLE)
-		mp_register_ioapic(m->apicid, m->apicaddr, gsi_top);
+		mp_register_ioapic(m->apicid, m->apicaddr, gsi_top, &cfg);
 }
 
 static void __init print_mp_irq_info(struct mpc_intsrc *mp_irq)
 {
-	apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
-		" IRQ %02x, APIC ID %x, APIC INT %02x\n",
+	apic_printk(APIC_VERBOSE,
+		"Int: type %d, pol %d, trig %d, bus %02x, IRQ %02x, APIC ID %x, APIC INT %02x\n",
 		mp_irq->irqtype, mp_irq->irqflag & 3,
 		(mp_irq->irqflag >> 2) & 3, mp_irq->srcbus,
 		mp_irq->srcbusirq, mp_irq->dstapic, mp_irq->dstirq);
@@ -135,8 +145,8 @@ static inline void __init MP_ioapic_info(struct mpc_ioapic *m) {}
 
 static void __init MP_lintsrc_info(struct mpc_lintsrc *m)
 {
-	apic_printk(APIC_VERBOSE, "Lint: type %d, pol %d, trig %d, bus %02x,"
-		" IRQ %02x, APIC ID %x, APIC LINT %02x\n",
+	apic_printk(APIC_VERBOSE,
+		"Lint: type %d, pol %d, trig %d, bus %02x, IRQ %02x, APIC ID %x, APIC LINT %02x\n",
 		m->irqtype, m->irqflag & 3, (m->irqflag >> 2) & 3, m->srcbusid,
 		m->srcbusirq, m->destapic, m->destapiclint);
 }
@@ -148,34 +158,33 @@ static int __init smp_check_mpc(struct mpc_table *mpc, char *oem, char *str)
 {
 
 	if (memcmp(mpc->signature, MPC_SIGNATURE, 4)) {
-		printk(KERN_ERR "MPTABLE: bad signature [%c%c%c%c]!\n",
+		pr_err("MPTABLE: bad signature [%c%c%c%c]!\n",
 		       mpc->signature[0], mpc->signature[1],
 		       mpc->signature[2], mpc->signature[3]);
 		return 0;
 	}
 	if (mpf_checksum((unsigned char *)mpc, mpc->length)) {
-		printk(KERN_ERR "MPTABLE: checksum error!\n");
+		pr_err("MPTABLE: checksum error!\n");
 		return 0;
 	}
 	if (mpc->spec != 0x01 && mpc->spec != 0x04) {
-		printk(KERN_ERR "MPTABLE: bad table version (%d)!!\n",
-		       mpc->spec);
+		pr_err("MPTABLE: bad table version (%d)!!\n", mpc->spec);
 		return 0;
 	}
 	if (!mpc->lapic) {
-		printk(KERN_ERR "MPTABLE: null local APIC address!\n");
+		pr_err("MPTABLE: null local APIC address!\n");
 		return 0;
 	}
 	memcpy(oem, mpc->oem, 8);
 	oem[8] = 0;
-	printk(KERN_INFO "MPTABLE: OEM ID: %s\n", oem);
+	pr_info("MPTABLE: OEM ID: %s\n", oem);
 
 	memcpy(str, mpc->productid, 12);
 	str[12] = 0;
 
-	printk(KERN_INFO "MPTABLE: Product ID: %s\n", str);
+	pr_info("MPTABLE: Product ID: %s\n", str);
 
-	printk(KERN_INFO "MPTABLE: APIC at: 0x%X\n", mpc->lapic);
+	pr_info("MPTABLE: APIC at: 0x%X\n", mpc->lapic);
 
 	return 1;
 }
@@ -188,8 +197,8 @@ static void skip_entry(unsigned char **ptr, int *count, int size)
 
 static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt)
 {
-	printk(KERN_ERR "Your mptable is wrong, contact your HW vendor!\n"
-		"type %x\n", *mpt);
+	pr_err("Your mptable is wrong, contact your HW vendor!\n");
+	pr_cont("type %x\n", *mpt);
 	print_hex_dump(KERN_ERR, "  ", DUMP_PREFIX_ADDRESS, 16,
 			1, mpc, mpc->length, 1);
 }
@@ -259,7 +268,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 	}
 
 	if (!num_processors)
-		printk(KERN_ERR "MPTABLE: no processors registered!\n");
+		pr_err("MPTABLE: no processors registered!\n");
 	return num_processors;
 }
 
@@ -295,16 +304,13 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 	 *  If it does, we assume it's valid.
 	 */
 	if (mpc_default_type == 5) {
-		printk(KERN_INFO "ISA/PCI bus type with no IRQ information... "
-		       "falling back to ELCR\n");
+		pr_info("ISA/PCI bus type with no IRQ information... falling back to ELCR\n");
 
 		if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) ||
 		    ELCR_trigger(13))
-			printk(KERN_ERR "ELCR contains invalid data... "
-			       "not using ELCR\n");
+			pr_err("ELCR contains invalid data... not using ELCR\n");
 		else {
-			printk(KERN_INFO
-			       "Using ELCR to identify PCI interrupts\n");
+			pr_info("Using ELCR to identify PCI interrupts\n");
 			ELCR_fallback = 1;
 		}
 	}
@@ -353,7 +359,7 @@ static void __init construct_ioapic_table(int mpc_default_type)
 	bus.busid = 0;
 	switch (mpc_default_type) {
 	default:
-		printk(KERN_ERR "???\nUnknown standard configuration %d\n",
+		pr_err("???\nUnknown standard configuration %d\n",
 		       mpc_default_type);
 		/* fall through */
 	case 1:
@@ -462,8 +468,8 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
 #ifdef CONFIG_X86_LOCAL_APIC
 		smp_found_config = 0;
 #endif
-		printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"
-			"... disabling SMP support. (tell your hw vendor)\n");
+		pr_err("BIOS bug, MP table errors detected!...\n");
+		pr_cont("... disabling SMP support. (tell your hw vendor)\n");
 		early_iounmap(mpc, size);
 		return -1;
 	}
@@ -481,8 +487,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
 	if (!mp_irq_entries) {
 		struct mpc_bus bus;
 
-		printk(KERN_ERR "BIOS bug, no explicit IRQ entries, "
-		       "using default mptable. (tell your hw vendor)\n");
+		pr_err("BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n");
 
 		bus.type = MP_BUS;
 		bus.busid = 0;
@@ -516,14 +521,14 @@ void __init default_get_smp_config(unsigned int early)
 	if (acpi_lapic && acpi_ioapic)
 		return;
 
-	printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
-	       mpf->specification);
+	pr_info("Intel MultiProcessor Specification v1.%d\n",
+		mpf->specification);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
 	if (mpf->feature2 & (1 << 7)) {
-		printk(KERN_INFO "    IMCR and PIC compatibility mode.\n");
+		pr_info("    IMCR and PIC compatibility mode.\n");
 		pic_mode = 1;
 	} else {
-		printk(KERN_INFO "    Virtual Wire compatibility mode.\n");
+		pr_info("    Virtual Wire compatibility mode.\n");
 		pic_mode = 0;
 	}
 #endif
@@ -539,8 +544,7 @@ void __init default_get_smp_config(unsigned int early)
 			return;
 		}
 
-		printk(KERN_INFO "Default MP configuration #%d\n",
-		       mpf->feature1);
+		pr_info("Default MP configuration #%d\n", mpf->feature1);
 		construct_default_ISA_mptable(mpf->feature1);
 
 	} else if (mpf->physptr) {
@@ -550,7 +554,7 @@ void __init default_get_smp_config(unsigned int early)
 		BUG();
 
 	if (!early)
-		printk(KERN_INFO "Processors: %d\n", num_processors);
+		pr_info("Processors: %d\n", num_processors);
 	/*
 	 * Only use the first configuration found.
 	 */
@@ -583,10 +587,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 #endif
 			mpf_found = mpf;
 
-			printk(KERN_INFO "found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n",
-			       (unsigned long long) virt_to_phys(mpf),
-			       (unsigned long long) virt_to_phys(mpf) +
-			       sizeof(*mpf) - 1, mpf);
+			pr_info("found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n",
+				(unsigned long long) virt_to_phys(mpf),
+				(unsigned long long) virt_to_phys(mpf) +
+				sizeof(*mpf) - 1, mpf);
 
 			mem = virt_to_phys(mpf);
 			memblock_reserve(mem, sizeof(*mpf));
@@ -735,7 +739,7 @@ static int  __init replace_intsrc_all(struct mpc_table *mpc,
 	int nr_m_spare = 0;
 	unsigned char *mpt = ((unsigned char *)mpc) + count;
 
-	printk(KERN_INFO "mpc_length %x\n", mpc->length);
+	pr_info("mpc_length %x\n", mpc->length);
 	while (count < mpc->length) {
 		switch (*mpt) {
 		case MP_PROCESSOR:
@@ -862,13 +866,13 @@ static int __init update_mp_table(void)
 	if (!smp_check_mpc(mpc, oem, str))
 		return 0;
 
-	printk(KERN_INFO "mpf: %llx\n", (u64)virt_to_phys(mpf));
-	printk(KERN_INFO "physptr: %x\n", mpf->physptr);
+	pr_info("mpf: %llx\n", (u64)virt_to_phys(mpf));
+	pr_info("physptr: %x\n", mpf->physptr);
 
 	if (mpc_new_phys && mpc->length > mpc_new_length) {
 		mpc_new_phys = 0;
-		printk(KERN_INFO "mpc_new_length is %ld, please use alloc_mptable=8k\n",
-			 mpc_new_length);
+		pr_info("mpc_new_length is %ld, please use alloc_mptable=8k\n",
+			mpc_new_length);
 	}
 
 	if (!mpc_new_phys) {
@@ -879,10 +883,10 @@ static int __init update_mp_table(void)
 		mpc->checksum = 0xff;
 		new = mpf_checksum((unsigned char *)mpc, mpc->length);
 		if (old == new) {
-			printk(KERN_INFO "mpc is readonly, please try alloc_mptable instead\n");
+			pr_info("mpc is readonly, please try alloc_mptable instead\n");
 			return 0;
 		}
-		printk(KERN_INFO "use in-position replacing\n");
+		pr_info("use in-position replacing\n");
 	} else {
 		mpf->physptr = mpc_new_phys;
 		mpc_new = phys_to_virt(mpc_new_phys);
@@ -892,7 +896,7 @@ static int __init update_mp_table(void)
 		if (mpc_new_phys - mpf->physptr) {
 			struct mpf_intel *mpf_new;
 			/* steal 16 bytes from [0, 1k) */
-			printk(KERN_INFO "mpf new: %x\n", 0x400 - 16);
+			pr_info("mpf new: %x\n", 0x400 - 16);
 			mpf_new = phys_to_virt(0x400 - 16);
 			memcpy(mpf_new, mpf, 16);
 			mpf = mpf_new;
@@ -900,7 +904,7 @@ static int __init update_mp_table(void)
 		}
 		mpf->checksum = 0;
 		mpf->checksum -= mpf_checksum((unsigned char *)mpf, 16);
-		printk(KERN_INFO "physptr new: %x\n", mpf->physptr);
+		pr_info("physptr new: %x\n", mpf->physptr);
 	}
 
 	/*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 4505e2a950d8..f804dc935d2a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -93,6 +93,7 @@ void arch_task_cache_init(void)
         	kmem_cache_create("task_xstate", xstate_size,
 				  __alignof__(union thread_xstate),
 				  SLAB_PANIC | SLAB_NOTRACK, NULL);
+	setup_xstate_comp();
 }
 
 /*
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ea030319b321..56b0c338061e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -234,9 +234,6 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	return ns;
 }
 
-/* XXX surely we already have this someplace in the kernel?! */
-#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d))
-
 static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 {
 	unsigned long long tsc_now, ns_now;
@@ -259,7 +256,9 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 	 * time function is continuous; see the comment near struct
 	 * cyc2ns_data.
 	 */
-	data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz);
+	data->cyc2ns_mul =
+		DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR,
+				  cpu_khz);
 	data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
 	data->cyc2ns_offset = ns_now -
 		mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a4b451c6addf..940b142cc11f 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -8,6 +8,7 @@
 
 #include <linux/bootmem.h>
 #include <linux/compat.h>
+#include <linux/cpu.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
 #include <asm/sigframe.h>
@@ -24,7 +25,9 @@ u64 pcntxt_mask;
 struct xsave_struct *init_xstate_buf;
 
 static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
-static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
+static unsigned int *xstate_offsets, *xstate_sizes;
+static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
+static unsigned int xstate_features;
 
 /*
  * If a processor implementation discern that a processor state component is
@@ -283,7 +286,7 @@ sanitize_restored_xstate(struct task_struct *tsk,
 
 	if (use_xsave()) {
 		/* These bits must be zero. */
-		xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+		memset(xsave_hdr->reserved, 0, 48);
 
 		/*
 		 * Init the state that is not present in the memory
@@ -479,6 +482,52 @@ static void __init setup_xstate_features(void)
 }
 
 /*
+ * This function sets up offsets and sizes of all extended states in
+ * xsave area. This supports both standard format and compacted format
+ * of the xsave aread.
+ *
+ * Input: void
+ * Output: void
+ */
+void setup_xstate_comp(void)
+{
+	unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
+	int i;
+
+	/*
+	 * The FP xstates and SSE xstates are legacy states. They are always
+	 * in the fixed offsets in the xsave area in either compacted form
+	 * or standard form.
+	 */
+	xstate_comp_offsets[0] = 0;
+	xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);
+
+	if (!cpu_has_xsaves) {
+		for (i = 2; i < xstate_features; i++) {
+			if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
+				xstate_comp_offsets[i] = xstate_offsets[i];
+				xstate_comp_sizes[i] = xstate_sizes[i];
+			}
+		}
+		return;
+	}
+
+	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+	for (i = 2; i < xstate_features; i++) {
+		if (test_bit(i, (unsigned long *)&pcntxt_mask))
+			xstate_comp_sizes[i] = xstate_sizes[i];
+		else
+			xstate_comp_sizes[i] = 0;
+
+		if (i > 2)
+			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
+					+ xstate_comp_sizes[i-1];
+
+	}
+}
+
+/*
  * setup the xstate image representing the init state
  */
 static void __init setup_init_fpu_buf(void)
@@ -496,15 +545,21 @@ static void __init setup_init_fpu_buf(void)
 
 	setup_xstate_features();
 
+	if (cpu_has_xsaves) {
+		init_xstate_buf->xsave_hdr.xcomp_bv =
+						(u64)1 << 63 | pcntxt_mask;
+		init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
+	}
+
 	/*
 	 * Init all the features state with header_bv being 0x0
 	 */
-	xrstor_state(init_xstate_buf, -1);
+	xrstor_state_booting(init_xstate_buf, -1);
 	/*
 	 * Dump the init state again. This is to identify the init state
 	 * of any feature which is not represented by all zero's.
 	 */
-	xsave_state(init_xstate_buf, -1);
+	xsave_state_booting(init_xstate_buf, -1);
 }
 
 static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
@@ -520,6 +575,30 @@ static int __init eager_fpu_setup(char *s)
 }
 __setup("eagerfpu=", eager_fpu_setup);
 
+
+/*
+ * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
+ */
+static void __init init_xstate_size(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	int i;
+
+	if (!cpu_has_xsaves) {
+		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+		xstate_size = ebx;
+		return;
+	}
+
+	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+	for (i = 2; i < 64; i++) {
+		if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
+			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+			xstate_size += eax;
+		}
+	}
+}
+
 /*
  * Enable and initialize the xsave feature.
  */
@@ -551,8 +630,7 @@ static void __init xstate_enable_boot_cpu(void)
 	/*
 	 * Recompute the context size for enabled features
 	 */
-	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-	xstate_size = ebx;
+	init_xstate_size();
 
 	update_regset_xstate_info(xstate_size, pcntxt_mask);
 	prepare_fx_sw_frame();
@@ -572,8 +650,9 @@ static void __init xstate_enable_boot_cpu(void)
 		}
 	}
 
-	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n",
-		pcntxt_mask, xstate_size);
+	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
+		pcntxt_mask, xstate_size,
+		cpu_has_xsaves ? "compacted form" : "standard form");
 }
 
 /*
@@ -635,3 +714,26 @@ void eager_fpu_init(void)
 	else
 		fxrstor_checking(&init_xstate_buf->i387);
 }
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Inputs:
+ *	xsave: base address of the xsave area;
+ *	xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
+ *	etc.)
+ * Output:
+ *	address of the state in the xsave area.
+ */
+void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
+{
+	int feature = fls64(xstate) - 1;
+	if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
+		return NULL;
+
+	return (void *)xsave + xstate_comp_offsets[feature];
+}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 36642793e315..1dbade870f90 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -577,6 +577,8 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 
 static const char nx_warning[] = KERN_CRIT
 "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
+static const char smep_warning[] = KERN_CRIT
+"unable to execute userspace code (SMEP?) (uid: %d)\n";
 
 static void
 show_fault_oops(struct pt_regs *regs, unsigned long error_code,
@@ -597,6 +599,10 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 
 		if (pte && pte_present(*pte) && !pte_exec(*pte))
 			printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
+		if (pte && pte_present(*pte) && pte_exec(*pte) &&
+				(pgd_flags(*pgd) & _PAGE_USER) &&
+				(read_cr4() & X86_CR4_SMEP))
+			printk(smep_warning, from_kuid(&init_user_ns, current_uid()));
 	}
 
 	printk(KERN_ALERT "BUG: unable to handle kernel ");
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 5075371ab593..cfd1b132b8e3 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -448,7 +448,7 @@ static void probe_pci_root_info(struct pci_root_info *info,
 		return;
 
 	size = sizeof(*info->res) * info->res_num;
-	info->res = kzalloc(size, GFP_KERNEL);
+	info->res = kzalloc_node(size, GFP_KERNEL, info->sd.node);
 	if (!info->res) {
 		info->res_num = 0;
 		return;
@@ -456,7 +456,7 @@ static void probe_pci_root_info(struct pci_root_info *info,
 
 	size = sizeof(*info->res_offset) * info->res_num;
 	info->res_num = 0;
-	info->res_offset = kzalloc(size, GFP_KERNEL);
+	info->res_offset = kzalloc_node(size, GFP_KERNEL, info->sd.node);
 	if (!info->res_offset) {
 		kfree(info->res);
 		info->res = NULL;
@@ -499,7 +499,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 	if (node != NUMA_NO_NODE && !node_online(node))
 		node = NUMA_NO_NODE;
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	info = kzalloc_node(sizeof(*info), GFP_KERNEL, node);
 	if (!info) {
 		printk(KERN_WARNING "pci_bus %04x:%02x: "
 		       "ignored (out of memory)\n", domain, busnum);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 84b9d672843d..09fece368592 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -208,27 +208,31 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
 
 static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 {
-	u8 pin;
-	struct io_apic_irq_attr irq_attr;
+	int polarity;
 
-	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
+		polarity = 0; /* active high */
+	else
+		polarity = 1; /* active low */
 
 	/*
 	 * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
 	 * IOAPIC RTE entries, so we just enable RTE for the device.
 	 */
-	irq_attr.ioapic = mp_find_ioapic(dev->irq);
-	irq_attr.ioapic_pin = dev->irq;
-	irq_attr.trigger = 1; /* level */
-	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
-		irq_attr.polarity = 0; /* active high */
-	else
-		irq_attr.polarity = 1; /* active low */
-	io_apic_set_pci_routing(&dev->dev, dev->irq, &irq_attr);
+	if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev)))
+		return -EBUSY;
+	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
+		return -EBUSY;
 
 	return 0;
 }
 
+static void intel_mid_pci_irq_disable(struct pci_dev *dev)
+{
+	if (dev->irq > 0)
+		mp_unmap_irq(dev->irq);
+}
+
 struct pci_ops intel_mid_pci_ops = {
 	.read = pci_read,
 	.write = pci_write,
@@ -245,6 +249,7 @@ int __init intel_mid_pci_init(void)
 	pr_info("Intel MID platform detected, using MID PCI ops\n");
 	pci_mmcfg_late_init();
 	pcibios_enable_irq = intel_mid_pci_irq_enable;
+	pcibios_disable_irq = intel_mid_pci_irq_disable;
 	pci_root_ops = intel_mid_pci_ops;
 	pci_soc_mode = 1;
 	/* Continue with standard init */
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 84112f55dd7a..748cfe8ab322 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -26,6 +26,7 @@ static int acer_tm360_irqrouting;
 static struct irq_routing_table *pirq_table;
 
 static int pirq_enable_irq(struct pci_dev *dev);
+static void pirq_disable_irq(struct pci_dev *dev);
 
 /*
  * Never use: 0, 1, 2 (timer, keyboard, and cascade)
@@ -53,7 +54,7 @@ struct irq_router_handler {
 };
 
 int (*pcibios_enable_irq)(struct pci_dev *dev) = pirq_enable_irq;
-void (*pcibios_disable_irq)(struct pci_dev *dev) = NULL;
+void (*pcibios_disable_irq)(struct pci_dev *dev) = pirq_disable_irq;
 
 /*
  *  Check passed address for the PCI IRQ Routing Table signature
@@ -1186,7 +1187,7 @@ void pcibios_penalize_isa_irq(int irq, int active)
 
 static int pirq_enable_irq(struct pci_dev *dev)
 {
-	u8 pin;
+	u8 pin = 0;
 
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 	if (pin && !pcibios_lookup_irq(dev, 1)) {
@@ -1227,8 +1228,6 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
-				io_apic_set_pci_routing(&dev->dev, irq,
-							 &irq_attr);
 				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
@@ -1254,3 +1253,11 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	}
 	return 0;
 }
+
+static void pirq_disable_irq(struct pci_dev *dev)
+{
+	if (io_apic_assign_pci_irqs && dev->irq) {
+		mp_unmap_irq(dev->irq);
+		dev->irq = 0;
+	}
+}
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 905956f16465..093f5f4272d3 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -23,6 +23,7 @@
 #include <xen/features.h>
 #include <xen/events.h>
 #include <asm/xen/pci.h>
+#include <asm/i8259.h>
 
 static int xen_pcifront_enable_irq(struct pci_dev *dev)
 {
@@ -40,7 +41,7 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev)
 	/* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/
 	pirq = gsi;
 
-	if (gsi < NR_IRQS_LEGACY)
+	if (gsi < nr_legacy_irqs())
 		share = 0;
 
 	rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront");
@@ -511,7 +512,7 @@ int __init pci_xen_initial_domain(void)
 	xen_setup_acpi_sci();
 	__acpi_register_gsi = acpi_register_gsi_xen;
 	/* Pre-allocate legacy irqs */
-	for (irq = 0; irq < NR_IRQS_LEGACY; irq++) {
+	for (irq = 0; irq < nr_legacy_irqs(); irq++) {
 		int trigger, polarity;
 
 		if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
@@ -522,7 +523,7 @@ int __init pci_xen_initial_domain(void)
 			true /* Map GSI to PIRQ */);
 	}
 	if (0 == nr_ioapics) {
-		for (irq = 0; irq < NR_IRQS_LEGACY; irq++)
+		for (irq = 0; irq < nr_legacy_irqs(); irq++)
 			xen_bind_pirq_gsi_to_irq(irq, irq, 0, "xt-pic");
 	}
 	return 0;
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 8244f5ec2f4c..701fd5843c87 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -135,14 +135,10 @@ static void __init sdv_arch_setup(void)
 	sdv_serial_fixup();
 }
 
-#ifdef CONFIG_X86_IO_APIC
 static void sdv_pci_init(void)
 {
 	x86_of_pci_init();
-	/* We can't set this earlier, because we need to calibrate the timer */
-	legacy_pic = &null_legacy_pic;
 }
-#endif
 
 /*
  * CE4100 specific x86_init function overrides and early setup
@@ -155,7 +151,9 @@ void __init x86_ce4100_early_setup(void)
 	x86_init.resources.probe_roms = x86_init_noop;
 	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
 	x86_init.mpparse.find_smp_config = x86_init_noop;
+	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
 	x86_init.pci.init = ce4100_pci_init;
+	x86_init.pci.init_irq = sdv_pci_init;
 
 	/*
 	 * By default, the reboot method is ACPI which is supported by the
@@ -166,10 +164,5 @@ void __init x86_ce4100_early_setup(void)
 	 */
 	reboot_type = BOOT_KBD;
 
-#ifdef CONFIG_X86_IO_APIC
-	x86_init.pci.init_irq = sdv_pci_init;
-	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
-#endif
-
 	pm_power_off = ce4100_power_off;
 }
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
index 973cf3bfa9fd..0b283d4d0ad7 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -26,28 +26,18 @@ static struct platform_device wdt_dev = {
 
 static int tangier_probe(struct platform_device *pdev)
 {
-	int ioapic;
-	int irq;
+	int gsi;
 	struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
-	struct io_apic_irq_attr irq_attr = { 0 };
 
 	if (!pdata)
 		return -EINVAL;
 
-	irq = pdata->irq;
-	ioapic = mp_find_ioapic(irq);
-	if (ioapic >= 0) {
-		int ret;
-		irq_attr.ioapic = ioapic;
-		irq_attr.ioapic_pin = irq;
-		irq_attr.trigger = 1;
-		/* irq_attr.polarity = 0; -> Active high */
-		ret = io_apic_set_pci_routing(NULL, irq, &irq_attr);
-		if (ret)
-			return ret;
-	} else {
+	/* IOAPIC builds identity mapping between GSI and IRQ on MID */
+	gsi = pdata->irq;
+	if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) ||
+	    mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) {
 		dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
-			 irq);
+			 gsi);
 		return -EINVAL;
 	}
 
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 994c40bd7cb7..3c53a90fdb18 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -432,9 +432,8 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 	struct sfi_table_simple *sb;
 	struct sfi_device_table_entry *pentry;
 	struct devs_id *dev = NULL;
-	int num, i;
-	int ioapic;
-	struct io_apic_irq_attr irq_attr;
+	int num, i, ret;
+	int polarity;
 
 	sb = (struct sfi_table_simple *)table;
 	num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
@@ -448,35 +447,30 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 			 * devices, but they have separate RTE entry in IOAPIC
 			 * so we have to enable them one by one here
 			 */
-			ioapic = mp_find_ioapic(irq);
-			if (ioapic >= 0) {
-				irq_attr.ioapic = ioapic;
-				irq_attr.ioapic_pin = irq;
-				irq_attr.trigger = 1;
-				if (intel_mid_identify_cpu() ==
-						INTEL_MID_CPU_CHIP_TANGIER) {
-					if (!strncmp(pentry->name,
-							"r69001-ts-i2c", 13))
-						/* active low */
-						irq_attr.polarity = 1;
-					else if (!strncmp(pentry->name,
-							"synaptics_3202", 14))
-						/* active low */
-						irq_attr.polarity = 1;
-					else if (irq == 41)
-						/* fast_int_1 */
-						irq_attr.polarity = 1;
-					else
-						/* active high */
-						irq_attr.polarity = 0;
-				} else {
-					/* PNW and CLV go with active low */
-					irq_attr.polarity = 1;
-				}
-				io_apic_set_pci_routing(NULL, irq, &irq_attr);
+			if (intel_mid_identify_cpu() ==
+					INTEL_MID_CPU_CHIP_TANGIER) {
+				if (!strncmp(pentry->name, "r69001-ts-i2c", 13))
+					/* active low */
+					polarity = 1;
+				else if (!strncmp(pentry->name,
+						"synaptics_3202", 14))
+					/* active low */
+					polarity = 1;
+				else if (irq == 41)
+					/* fast_int_1 */
+					polarity = 1;
+				else
+					/* active high */
+					polarity = 0;
+			} else {
+				/* PNW and CLV go with active low */
+				polarity = 1;
 			}
-		} else {
-			irq = 0; /* No irq */
+
+			ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE);
+			if (ret == 0)
+				ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC);
+			WARN_ON(ret < 0);
 		}
 
 		dev = get_device_id(pentry->type, pentry->name);
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index bcd1a703e3e6..2a8a74f3bd76 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/sfi.h>
 #include <linux/io.h>
+#include <linux/irqdomain.h>
 
 #include <asm/io_apic.h>
 #include <asm/mpspec.h>
@@ -70,19 +71,26 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table)
 #endif /* CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_IO_APIC
+static struct irq_domain_ops sfi_ioapic_irqdomain_ops = {
+	.map = mp_irqdomain_map,
+};
 
 static int __init sfi_parse_ioapic(struct sfi_table_header *table)
 {
 	struct sfi_table_simple *sb;
 	struct sfi_apic_table_entry *pentry;
 	int i, num;
+	struct ioapic_domain_cfg cfg = {
+		.type = IOAPIC_DOMAIN_STRICT,
+		.ops = &sfi_ioapic_irqdomain_ops,
+	};
 
 	sb = (struct sfi_table_simple *)table;
 	num = SFI_GET_NUM_ENTRIES(sb, struct sfi_apic_table_entry);
 	pentry = (struct sfi_apic_table_entry *)sb->pentry;
 
 	for (i = 0; i < num; i++) {
-		mp_register_ioapic(i, pentry->phys_addr, gsi_top);
+		mp_register_ioapic(i, pentry->phys_addr, gsi_top, &cfg);
 		pentry++;
 	}
 
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index dfe605ac1bcd..ed161c6e278b 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1,7 +1,7 @@
 /*
  *	SGI UltraViolet TLB flush routines.
  *
- *	(c) 2008-2012 Cliff Wickman <cpw@sgi.com>, SGI.
+ *	(c) 2008-2014 Cliff Wickman <cpw@sgi.com>, SGI.
  *
  *	This code is released under the GNU General Public License version 2 or
  *	later.
@@ -451,7 +451,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 
 /*
  * The reverse of the above; converts a duration in ns to a duration in cycles.
- */ 
+ */
 static inline unsigned long long ns_2_cycles(unsigned long long ns)
 {
 	struct cyc2ns_data *data = cyc2ns_read_begin();
@@ -563,7 +563,7 @@ static int uv1_wait_completion(struct bau_desc *bau_desc,
  * UV2 could have an extra bit of status in the ACTIVATION_STATUS_2 register.
  * But not currently used.
  */
-static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc)
+static unsigned long uv2_3_read_status(unsigned long offset, int rshft, int desc)
 {
 	unsigned long descriptor_status;
 
@@ -606,7 +606,7 @@ int handle_uv2_busy(struct bau_control *bcp)
 	return FLUSH_GIVEUP;
 }
 
-static int uv2_wait_completion(struct bau_desc *bau_desc,
+static int uv2_3_wait_completion(struct bau_desc *bau_desc,
 				unsigned long mmr_offset, int right_shift,
 				struct bau_control *bcp, long try)
 {
@@ -616,7 +616,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
 	long busy_reps = 0;
 	struct ptc_stats *stat = bcp->statp;
 
-	descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc);
+	descriptor_stat = uv2_3_read_status(mmr_offset, right_shift, desc);
 
 	/* spin on the status MMR, waiting for it to go idle */
 	while (descriptor_stat != UV2H_DESC_IDLE) {
@@ -658,8 +658,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
 				/* not to hammer on the clock */
 				busy_reps = 0;
 				ttm = get_cycles();
-				if ((ttm - bcp->send_message) >
-						bcp->timeout_interval)
+				if ((ttm - bcp->send_message) > bcp->timeout_interval)
 					return handle_uv2_busy(bcp);
 			}
 			/*
@@ -667,8 +666,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
 			 */
 			cpu_relax();
 		}
-		descriptor_stat = uv2_read_status(mmr_offset, right_shift,
-									desc);
+		descriptor_stat = uv2_3_read_status(mmr_offset, right_shift, desc);
 	}
 	bcp->conseccompletes++;
 	return FLUSH_COMPLETE;
@@ -679,8 +677,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
  * which register to read and position in that register based on cpu in
  * current hub.
  */
-static int wait_completion(struct bau_desc *bau_desc,
-				struct bau_control *bcp, long try)
+static int wait_completion(struct bau_desc *bau_desc, struct bau_control *bcp, long try)
 {
 	int right_shift;
 	unsigned long mmr_offset;
@@ -695,11 +692,9 @@ static int wait_completion(struct bau_desc *bau_desc,
 	}
 
 	if (bcp->uvhub_version == 1)
-		return uv1_wait_completion(bau_desc, mmr_offset, right_shift,
-								bcp, try);
+		return uv1_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try);
 	else
-		return uv2_wait_completion(bau_desc, mmr_offset, right_shift,
-								bcp, try);
+		return uv2_3_wait_completion(bau_desc, mmr_offset, right_shift, bcp, try);
 }
 
 /*
@@ -888,7 +883,7 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp,
 	struct ptc_stats *stat = bcp->statp;
 	struct bau_control *hmaster = bcp->uvhub_master;
 	struct uv1_bau_msg_header *uv1_hdr = NULL;
-	struct uv2_bau_msg_header *uv2_hdr = NULL;
+	struct uv2_3_bau_msg_header *uv2_3_hdr = NULL;
 
 	if (bcp->uvhub_version == 1) {
 		uv1 = 1;
@@ -902,27 +897,28 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp,
 	if (uv1)
 		uv1_hdr = &bau_desc->header.uv1_hdr;
 	else
-		uv2_hdr = &bau_desc->header.uv2_hdr;
+		/* uv2 and uv3 */
+		uv2_3_hdr = &bau_desc->header.uv2_3_hdr;
 
 	do {
 		if (try == 0) {
 			if (uv1)
 				uv1_hdr->msg_type = MSG_REGULAR;
 			else
-				uv2_hdr->msg_type = MSG_REGULAR;
+				uv2_3_hdr->msg_type = MSG_REGULAR;
 			seq_number = bcp->message_number++;
 		} else {
 			if (uv1)
 				uv1_hdr->msg_type = MSG_RETRY;
 			else
-				uv2_hdr->msg_type = MSG_RETRY;
+				uv2_3_hdr->msg_type = MSG_RETRY;
 			stat->s_retry_messages++;
 		}
 
 		if (uv1)
 			uv1_hdr->sequence = seq_number;
 		else
-			uv2_hdr->sequence = seq_number;
+			uv2_3_hdr->sequence = seq_number;
 		index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
 		bcp->send_message = get_cycles();
 
@@ -1080,8 +1076,10 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
  * done.  The returned pointer is valid till preemption is re-enabled.
  */
 const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
-				struct mm_struct *mm, unsigned long start,
-				unsigned long end, unsigned int cpu)
+						struct mm_struct *mm,
+						unsigned long start,
+						unsigned long end,
+						unsigned int cpu)
 {
 	int locals = 0;
 	int remotes = 0;
@@ -1268,6 +1266,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 		if (bcp->uvhub_version == 2)
 			process_uv2_message(&msgdesc, bcp);
 		else
+			/* no error workaround for uv1 or uv3 */
 			bau_process_message(&msgdesc, bcp, 1);
 
 		msg++;
@@ -1325,8 +1324,12 @@ static void __init enable_timeouts(void)
 		 */
 		mmr_image |= (1L << SOFTACK_MSHIFT);
 		if (is_uv2_hub()) {
+			/* do not touch the legacy mode bit */
 			/* hw bug workaround; do not use extended status */
 			mmr_image &= ~(1L << UV2_EXT_SHFT);
+		} else if (is_uv3_hub()) {
+			mmr_image &= ~(1L << PREFETCH_HINT_SHFT);
+			mmr_image |= (1L << SB_STATUS_SHFT);
 		}
 		write_mmr_misc_control(pnode, mmr_image);
 	}
@@ -1692,7 +1695,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 	struct bau_desc *bau_desc;
 	struct bau_desc *bd2;
 	struct uv1_bau_msg_header *uv1_hdr;
-	struct uv2_bau_msg_header *uv2_hdr;
+	struct uv2_3_bau_msg_header *uv2_3_hdr;
 	struct bau_control *bcp;
 
 	/*
@@ -1739,15 +1742,15 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 			 */
 		} else {
 			/*
-			 * BIOS uses legacy mode, but UV2 hardware always
+			 * BIOS uses legacy mode, but uv2 and uv3 hardware always
 			 * uses native mode for selective broadcasts.
 			 */
-			uv2_hdr = &bd2->header.uv2_hdr;
-			uv2_hdr->swack_flag =	1;
-			uv2_hdr->base_dest_nasid =
+			uv2_3_hdr = &bd2->header.uv2_3_hdr;
+			uv2_3_hdr->swack_flag =	1;
+			uv2_3_hdr->base_dest_nasid =
 						UV_PNODE_TO_NASID(base_pnode);
-			uv2_hdr->dest_subnodeid =	UV_LB_SUBNODEID;
-			uv2_hdr->command =		UV_NET_ENDPOINT_INTD;
+			uv2_3_hdr->dest_subnodeid =	UV_LB_SUBNODEID;
+			uv2_3_hdr->command =		UV_NET_ENDPOINT_INTD;
 		}
 	}
 	for_each_present_cpu(cpu) {
@@ -1858,6 +1861,7 @@ static int calculate_destination_timeout(void)
 		ts_ns *= (mult1 * mult2);
 		ret = ts_ns / 1000;
 	} else {
+		/* same destination timeout for uv2 and uv3 */
 		/* 4 bits  0/1 for 10/80us base, 3 bits of multiplier */
 		mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL);
 		mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT;
@@ -2012,8 +2016,10 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 			bcp->uvhub_version = 1;
 		else if (is_uv2_hub())
 			bcp->uvhub_version = 2;
+		else if (is_uv3_hub())
+			bcp->uvhub_version = 3;
 		else {
-			printk(KERN_EMERG "uvhub version not 1 or 2\n");
+			printk(KERN_EMERG "uvhub version not 1, 2 or 3\n");
 			return 1;
 		}
 		bcp->uvhub_master = *hmasterp;
@@ -2138,9 +2144,10 @@ static int __init uv_bau_init(void)
 	}
 
 	vector = UV_BAU_MESSAGE;
-	for_each_possible_blade(uvhub)
+	for_each_possible_blade(uvhub) {
 		if (uv_blade_nr_possible_cpus(uvhub))
 			init_uvhub(uvhub, vector, uv_base_pnode);
+	}
 
 	alloc_intr_gate(vector, uv_bau_message_intr1);
 
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 61b04fe36e66..5a4affe025e8 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -10,7 +10,7 @@ VDSO32-$(CONFIG_X86_32)		:= y
 VDSO32-$(CONFIG_COMPAT)		:= y
 
 # files to link into the vdso
-vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vdso-fakesections.o
+vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
 
 # files to link into kernel
 obj-y				+= vma.o
@@ -37,7 +37,8 @@ vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
 obj-y += $(vdso_img_objs)
 targets += $(vdso_img_cfiles)
 targets += $(vdso_img_sodbg)
-.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c)
+.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) \
+	$(vdso_img-y:%=$(obj)/vdso%.so)
 
 export CPPFLAGS_vdso.lds += -P -C
 
@@ -54,10 +55,10 @@ hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
 define cmd_vdso2c
-	$(obj)/vdso2c $< $@
+	$(obj)/vdso2c $< $(<:%.dbg=%) $@
 endef
 
-$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso2c FORCE
+$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 	$(call if_changed,vdso2c)
 
 #
@@ -113,6 +114,10 @@ $(obj)/%-x32.o: $(obj)/%.o FORCE
 
 targets += vdsox32.lds $(vobjx32s-y)
 
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg
+	$(call if_changed,objcopy)
+
 $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
 
@@ -134,7 +139,7 @@ override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
 
 targets += vdso32/vdso32.lds
 targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o)
-targets += vdso32/vclock_gettime.o vdso32/vdso-fakesections.o
+targets += vdso32/vclock_gettime.o
 
 $(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
 
@@ -156,7 +161,6 @@ $(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
 $(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
 				 $(obj)/vdso32/vdso32.lds \
 				 $(obj)/vdso32/vclock_gettime.o \
-				 $(obj)/vdso32/vdso-fakesections.o \
 				 $(obj)/vdso32/note.o \
 				 $(obj)/vdso32/%.o
 	$(call if_changed,vdso)
diff --git a/arch/x86/vdso/vdso-fakesections.c b/arch/x86/vdso/vdso-fakesections.c
deleted file mode 100644
index aa5fbfab20a5..000000000000
--- a/arch/x86/vdso/vdso-fakesections.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright 2014 Andy Lutomirski
- * Subject to the GNU Public License, v.2
- *
- * String table for loadable section headers.  See vdso2c.h for why
- * this exists.
- */
-
-const char fake_shstrtab[] __attribute__((section(".fake_shstrtab"))) =
-	".hash\0"
-	".dynsym\0"
-	".dynstr\0"
-	".gnu.version\0"
-	".gnu.version_d\0"
-	".dynamic\0"
-	".rodata\0"
-	".fake_shstrtab\0"  /* Yay, self-referential code. */
-	".note\0"
-	".eh_frame_hdr\0"
-	".eh_frame\0"
-	".text";
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index 9197544eea9a..de2c921025f5 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -18,6 +18,25 @@
 
 SECTIONS
 {
+	/*
+	 * User/kernel shared data is before the vDSO.  This may be a little
+	 * uglier than putting it after the vDSO, but it avoids issues with
+	 * non-allocatable things that dangle past the end of the PT_LOAD
+	 * segment.
+	 */
+
+	vvar_start = . - 2 * PAGE_SIZE;
+	vvar_page = vvar_start;
+
+	/* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset;
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+#undef EMIT_VVAR
+
+	hpet_page = vvar_start + PAGE_SIZE;
+
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
@@ -74,31 +93,6 @@ SECTIONS
 	.altinstructions	: { *(.altinstructions) }	:text
 	.altinstr_replacement	: { *(.altinstr_replacement) }	:text
 
-	/*
-	 * The remainder of the vDSO consists of special pages that are
-	 * shared between the kernel and userspace.  It needs to be at the
-	 * end so that it doesn't overlap the mapping of the actual
-	 * vDSO image.
-	 */
-
-	. = ALIGN(PAGE_SIZE);
-	vvar_page = .;
-
-	/* Place all vvars at the offsets in asm/vvar.h. */
-#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset;
-#define __VVAR_KERNEL_LDS
-#include <asm/vvar.h>
-#undef __VVAR_KERNEL_LDS
-#undef EMIT_VVAR
-
-	. = vvar_page + PAGE_SIZE;
-
-	hpet_page = .;
-	. = . + PAGE_SIZE;
-
-	. = ALIGN(PAGE_SIZE);
-	end_mapping = .;
-
 	/DISCARD/ : {
 		*(.discard)
 		*(.discard.*)
diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/vdso/vdso2c.c
index 238dbe82776e..8627db24a7f6 100644
--- a/arch/x86/vdso/vdso2c.c
+++ b/arch/x86/vdso/vdso2c.c
@@ -1,3 +1,53 @@
+/*
+ * vdso2c - A vdso image preparation tool
+ * Copyright (c) 2014 Andy Lutomirski and others
+ * Licensed under the GPL v2
+ *
+ * vdso2c requires stripped and unstripped input.  It would be trivial
+ * to fully strip the input in here, but, for reasons described below,
+ * we need to write a section table.  Doing this is more or less
+ * equivalent to dropping all non-allocatable sections, but it's
+ * easier to let objcopy handle that instead of doing it ourselves.
+ * If we ever need to do something fancier than what objcopy provides,
+ * it would be straightforward to add here.
+ *
+ * We're keep a section table for a few reasons:
+ *
+ * The Go runtime had a couple of bugs: it would read the section
+ * table to try to figure out how many dynamic symbols there were (it
+ * shouldn't have looked at the section table at all) and, if there
+ * were no SHT_SYNDYM section table entry, it would use an
+ * uninitialized value for the number of symbols.  An empty DYNSYM
+ * table would work, but I see no reason not to write a valid one (and
+ * keep full performance for old Go programs).  This hack is only
+ * needed on x86_64.
+ *
+ * The bug was introduced on 2012-08-31 by:
+ * https://code.google.com/p/go/source/detail?r=56ea40aac72b
+ * and was fixed on 2014-06-13 by:
+ * https://code.google.com/p/go/source/detail?r=fc1cd5e12595
+ *
+ * Binutils has issues debugging the vDSO: it reads the section table to
+ * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which
+ * would break build-id if we removed the section table.  Binutils
+ * also requires that shstrndx != 0.  See:
+ * https://sourceware.org/bugzilla/show_bug.cgi?id=17064
+ *
+ * elfutils might not look for PT_NOTE if there is a section table at
+ * all.  I don't know whether this matters for any practical purpose.
+ *
+ * For simplicity, rather than hacking up a partial section table, we
+ * just write a mostly complete one.  We omit non-dynamic symbols,
+ * though, since they're rather large.
+ *
+ * Once binutils gets fixed, we might be able to drop this for all but
+ * the 64-bit vdso, since build-id only works in kernel RPMs, and
+ * systems that update to new enough kernel RPMs will likely update
+ * binutils in sync.  build-id has never worked for home-built kernel
+ * RPMs without manual symlinking, and I suspect that no one ever does
+ * that.
+ */
+
 #include <inttypes.h>
 #include <stdint.h>
 #include <unistd.h>
@@ -20,9 +70,9 @@ const char *outfilename;
 
 /* Symbols that we need in vdso2c. */
 enum {
+	sym_vvar_start,
 	sym_vvar_page,
 	sym_hpet_page,
-	sym_end_mapping,
 	sym_VDSO_FAKE_SECTION_TABLE_START,
 	sym_VDSO_FAKE_SECTION_TABLE_END,
 };
@@ -38,9 +88,9 @@ struct vdso_sym {
 };
 
 struct vdso_sym required_syms[] = {
+	[sym_vvar_start] = {"vvar_start", true},
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_hpet_page] = {"hpet_page", true},
-	[sym_end_mapping] = {"end_mapping", true},
 	[sym_VDSO_FAKE_SECTION_TABLE_START] = {
 		"VDSO_FAKE_SECTION_TABLE_START", false
 	},
@@ -61,7 +111,8 @@ static void fail(const char *format, ...)
 	va_start(ap, format);
 	fprintf(stderr, "Error: ");
 	vfprintf(stderr, format, ap);
-	unlink(outfilename);
+	if (outfilename)
+		unlink(outfilename);
 	exit(1);
 	va_end(ap);
 }
@@ -96,9 +147,11 @@ extern void bad_put_le(void);
 
 #define NSYMS (sizeof(required_syms) / sizeof(required_syms[0]))
 
-#define BITSFUNC3(name, bits) name##bits
-#define BITSFUNC2(name, bits) BITSFUNC3(name, bits)
-#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS)
+#define BITSFUNC3(name, bits, suffix) name##bits##suffix
+#define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix)
+#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS, )
+
+#define INT_BITS BITSFUNC2(int, ELF_BITS, _t)
 
 #define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
 #define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
@@ -112,30 +165,53 @@ extern void bad_put_le(void);
 #include "vdso2c.h"
 #undef ELF_BITS
 
-static void go(void *addr, size_t len, FILE *outfile, const char *name)
+static void go(void *raw_addr, size_t raw_len,
+	       void *stripped_addr, size_t stripped_len,
+	       FILE *outfile, const char *name)
 {
-	Elf64_Ehdr *hdr = (Elf64_Ehdr *)addr;
+	Elf64_Ehdr *hdr = (Elf64_Ehdr *)raw_addr;
 
 	if (hdr->e_ident[EI_CLASS] == ELFCLASS64) {
-		go64(addr, len, outfile, name);
+		go64(raw_addr, raw_len, stripped_addr, stripped_len,
+		     outfile, name);
 	} else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) {
-		go32(addr, len, outfile, name);
+		go32(raw_addr, raw_len, stripped_addr, stripped_len,
+		     outfile, name);
 	} else {
 		fail("unknown ELF class\n");
 	}
 }
 
+static void map_input(const char *name, void **addr, size_t *len, int prot)
+{
+	off_t tmp_len;
+
+	int fd = open(name, O_RDONLY);
+	if (fd == -1)
+		err(1, "%s", name);
+
+	tmp_len = lseek(fd, 0, SEEK_END);
+	if (tmp_len == (off_t)-1)
+		err(1, "lseek");
+	*len = (size_t)tmp_len;
+
+	*addr = mmap(NULL, tmp_len, prot, MAP_PRIVATE, fd, 0);
+	if (*addr == MAP_FAILED)
+		err(1, "mmap");
+
+	close(fd);
+}
+
 int main(int argc, char **argv)
 {
-	int fd;
-	off_t len;
-	void *addr;
+	size_t raw_len, stripped_len;
+	void *raw_addr, *stripped_addr;
 	FILE *outfile;
 	char *name, *tmp;
 	int namelen;
 
-	if (argc != 3) {
-		printf("Usage: vdso2c INPUT OUTPUT\n");
+	if (argc != 4) {
+		printf("Usage: vdso2c RAW_INPUT STRIPPED_INPUT OUTPUT\n");
 		return 1;
 	}
 
@@ -143,7 +219,7 @@ int main(int argc, char **argv)
 	 * Figure out the struct name.  If we're writing to a .so file,
 	 * generate raw output insted.
 	 */
-	name = strdup(argv[2]);
+	name = strdup(argv[3]);
 	namelen = strlen(name);
 	if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) {
 		name = NULL;
@@ -159,26 +235,18 @@ int main(int argc, char **argv)
 				*tmp = '_';
 	}
 
-	fd = open(argv[1], O_RDONLY);
-	if (fd == -1)
-		err(1, "%s", argv[1]);
-
-	len = lseek(fd, 0, SEEK_END);
-	if (len == (off_t)-1)
-		err(1, "lseek");
-
-	addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
-	if (addr == MAP_FAILED)
-		err(1, "mmap");
+	map_input(argv[1], &raw_addr, &raw_len, PROT_READ);
+	map_input(argv[2], &stripped_addr, &stripped_len, PROT_READ);
 
-	outfilename = argv[2];
+	outfilename = argv[3];
 	outfile = fopen(outfilename, "w");
 	if (!outfile)
 		err(1, "%s", argv[2]);
 
-	go(addr, (size_t)len, outfile, name);
+	go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name);
 
-	munmap(addr, len);
+	munmap(raw_addr, raw_len);
+	munmap(stripped_addr, stripped_len);
 	fclose(outfile);
 
 	return 0;
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h
index 11b65d4f9414..fd57829b30d8 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/vdso/vdso2c.h
@@ -4,139 +4,23 @@
  * are built for 32-bit userspace.
  */
 
-/*
- * We're writing a section table for a few reasons:
- *
- * The Go runtime had a couple of bugs: it would read the section
- * table to try to figure out how many dynamic symbols there were (it
- * shouldn't have looked at the section table at all) and, if there
- * were no SHT_SYNDYM section table entry, it would use an
- * uninitialized value for the number of symbols.  An empty DYNSYM
- * table would work, but I see no reason not to write a valid one (and
- * keep full performance for old Go programs).  This hack is only
- * needed on x86_64.
- *
- * The bug was introduced on 2012-08-31 by:
- * https://code.google.com/p/go/source/detail?r=56ea40aac72b
- * and was fixed on 2014-06-13 by:
- * https://code.google.com/p/go/source/detail?r=fc1cd5e12595
- *
- * Binutils has issues debugging the vDSO: it reads the section table to
- * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which
- * would break build-id if we removed the section table.  Binutils
- * also requires that shstrndx != 0.  See:
- * https://sourceware.org/bugzilla/show_bug.cgi?id=17064
- *
- * elfutils might not look for PT_NOTE if there is a section table at
- * all.  I don't know whether this matters for any practical purpose.
- *
- * For simplicity, rather than hacking up a partial section table, we
- * just write a mostly complete one.  We omit non-dynamic symbols,
- * though, since they're rather large.
- *
- * Once binutils gets fixed, we might be able to drop this for all but
- * the 64-bit vdso, since build-id only works in kernel RPMs, and
- * systems that update to new enough kernel RPMs will likely update
- * binutils in sync.  build-id has never worked for home-built kernel
- * RPMs without manual symlinking, and I suspect that no one ever does
- * that.
- */
-struct BITSFUNC(fake_sections)
-{
-	ELF(Shdr) *table;
-	unsigned long table_offset;
-	int count, max_count;
-
-	int in_shstrndx;
-	unsigned long shstr_offset;
-	const char *shstrtab;
-	size_t shstrtab_len;
-
-	int out_shstrndx;
-};
-
-static unsigned int BITSFUNC(find_shname)(struct BITSFUNC(fake_sections) *out,
-					  const char *name)
-{
-	const char *outname = out->shstrtab;
-	while (outname - out->shstrtab < out->shstrtab_len) {
-		if (!strcmp(name, outname))
-			return (outname - out->shstrtab) + out->shstr_offset;
-		outname += strlen(outname) + 1;
-	}
-
-	if (*name)
-		printf("Warning: could not find output name \"%s\"\n", name);
-	return out->shstr_offset + out->shstrtab_len - 1;  /* Use a null. */
-}
-
-static void BITSFUNC(init_sections)(struct BITSFUNC(fake_sections) *out)
-{
-	if (!out->in_shstrndx)
-		fail("didn't find the fake shstrndx\n");
-
-	memset(out->table, 0, out->max_count * sizeof(ELF(Shdr)));
-
-	if (out->max_count < 1)
-		fail("we need at least two fake output sections\n");
-
-	PUT_LE(&out->table[0].sh_type, SHT_NULL);
-	PUT_LE(&out->table[0].sh_name, BITSFUNC(find_shname)(out, ""));
-
-	out->count = 1;
-}
-
-static void BITSFUNC(copy_section)(struct BITSFUNC(fake_sections) *out,
-				   int in_idx, const ELF(Shdr) *in,
-				   const char *name)
-{
-	uint64_t flags = GET_LE(&in->sh_flags);
-
-	bool copy = flags & SHF_ALLOC &&
-		(GET_LE(&in->sh_size) ||
-		 (GET_LE(&in->sh_type) != SHT_RELA &&
-		  GET_LE(&in->sh_type) != SHT_REL)) &&
-		strcmp(name, ".altinstructions") &&
-		strcmp(name, ".altinstr_replacement");
-
-	if (!copy)
-		return;
-
-	if (out->count >= out->max_count)
-		fail("too many copied sections (max = %d)\n", out->max_count);
-
-	if (in_idx == out->in_shstrndx)
-		out->out_shstrndx = out->count;
-
-	out->table[out->count] = *in;
-	PUT_LE(&out->table[out->count].sh_name,
-	       BITSFUNC(find_shname)(out, name));
-
-	/* elfutils requires that a strtab have the correct type. */
-	if (!strcmp(name, ".fake_shstrtab"))
-		PUT_LE(&out->table[out->count].sh_type, SHT_STRTAB);
-
-	out->count++;
-}
-
-static void BITSFUNC(go)(void *addr, size_t len,
+static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
+			 void *stripped_addr, size_t stripped_len,
 			 FILE *outfile, const char *name)
 {
 	int found_load = 0;
 	unsigned long load_size = -1;  /* Work around bogus warning */
-	unsigned long data_size;
-	ELF(Ehdr) *hdr = (ELF(Ehdr) *)addr;
+	unsigned long mapping_size;
+	ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr;
 	int i;
 	unsigned long j;
 	ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
 		*alt_sec = NULL;
 	ELF(Dyn) *dyn = 0, *dyn_end = 0;
 	const char *secstrings;
-	uint64_t syms[NSYMS] = {};
-
-	struct BITSFUNC(fake_sections) fake_sections = {};
+	INT_BITS syms[NSYMS] = {};
 
-	ELF(Phdr) *pt = (ELF(Phdr) *)(addr + GET_LE(&hdr->e_phoff));
+	ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
 
 	/* Walk the segment table. */
 	for (i = 0; i < GET_LE(&hdr->e_phnum); i++) {
@@ -154,14 +38,16 @@ static void BITSFUNC(go)(void *addr, size_t len,
 			load_size = GET_LE(&pt[i].p_memsz);
 			found_load = 1;
 		} else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) {
-			dyn = addr + GET_LE(&pt[i].p_offset);
-			dyn_end = addr + GET_LE(&pt[i].p_offset) +
+			dyn = raw_addr + GET_LE(&pt[i].p_offset);
+			dyn_end = raw_addr + GET_LE(&pt[i].p_offset) +
 				GET_LE(&pt[i].p_memsz);
 		}
 	}
 	if (!found_load)
 		fail("no PT_LOAD seg\n");
-	data_size = (load_size + 4095) / 4096 * 4096;
+
+	if (stripped_len < load_size)
+		fail("stripped input is too short\n");
 
 	/* Walk the dynamic table */
 	for (i = 0; dyn + i < dyn_end &&
@@ -173,11 +59,11 @@ static void BITSFUNC(go)(void *addr, size_t len,
 	}
 
 	/* Walk the section table */
-	secstrings_hdr = addr + GET_LE(&hdr->e_shoff) +
+	secstrings_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
 		GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx);
-	secstrings = addr + GET_LE(&secstrings_hdr->sh_offset);
+	secstrings = raw_addr + GET_LE(&secstrings_hdr->sh_offset);
 	for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
-		ELF(Shdr) *sh = addr + GET_LE(&hdr->e_shoff) +
+		ELF(Shdr) *sh = raw_addr + GET_LE(&hdr->e_shoff) +
 			GET_LE(&hdr->e_shentsize) * i;
 		if (GET_LE(&sh->sh_type) == SHT_SYMTAB)
 			symtab_hdr = sh;
@@ -190,7 +76,7 @@ static void BITSFUNC(go)(void *addr, size_t len,
 	if (!symtab_hdr)
 		fail("no symbol table\n");
 
-	strtab_hdr = addr + GET_LE(&hdr->e_shoff) +
+	strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
 		GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link);
 
 	/* Walk the symbol table */
@@ -198,9 +84,9 @@ static void BITSFUNC(go)(void *addr, size_t len,
 	     i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
 	     i++) {
 		int k;
-		ELF(Sym) *sym = addr + GET_LE(&symtab_hdr->sh_offset) +
+		ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
 			GET_LE(&symtab_hdr->sh_entsize) * i;
-		const char *name = addr + GET_LE(&strtab_hdr->sh_offset) +
+		const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
 			GET_LE(&sym->st_name);
 
 		for (k = 0; k < NSYMS; k++) {
@@ -209,51 +95,17 @@ static void BITSFUNC(go)(void *addr, size_t len,
 					fail("duplicate symbol %s\n",
 					     required_syms[k].name);
 				}
+
+				/*
+				 * Careful: we use negative addresses, but
+				 * st_value is unsigned, so we rely
+				 * on syms[k] being a signed type of the
+				 * correct width.
+				 */
 				syms[k] = GET_LE(&sym->st_value);
 			}
 		}
-
-		if (!strcmp(name, "fake_shstrtab")) {
-			ELF(Shdr) *sh;
-
-			fake_sections.in_shstrndx = GET_LE(&sym->st_shndx);
-			fake_sections.shstrtab = addr + GET_LE(&sym->st_value);
-			fake_sections.shstrtab_len = GET_LE(&sym->st_size);
-			sh = addr + GET_LE(&hdr->e_shoff) +
-				GET_LE(&hdr->e_shentsize) *
-				fake_sections.in_shstrndx;
-			fake_sections.shstr_offset = GET_LE(&sym->st_value) -
-				GET_LE(&sh->sh_addr);
-		}
-	}
-
-	/* Build the output section table. */
-	if (!syms[sym_VDSO_FAKE_SECTION_TABLE_START] ||
-	    !syms[sym_VDSO_FAKE_SECTION_TABLE_END])
-		fail("couldn't find fake section table\n");
-	if ((syms[sym_VDSO_FAKE_SECTION_TABLE_END] -
-	     syms[sym_VDSO_FAKE_SECTION_TABLE_START]) % sizeof(ELF(Shdr)))
-		fail("fake section table size isn't a multiple of sizeof(Shdr)\n");
-	fake_sections.table = addr + syms[sym_VDSO_FAKE_SECTION_TABLE_START];
-	fake_sections.table_offset = syms[sym_VDSO_FAKE_SECTION_TABLE_START];
-	fake_sections.max_count = (syms[sym_VDSO_FAKE_SECTION_TABLE_END] -
-				   syms[sym_VDSO_FAKE_SECTION_TABLE_START]) /
-		sizeof(ELF(Shdr));
-
-	BITSFUNC(init_sections)(&fake_sections);
-	for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
-		ELF(Shdr) *sh = addr + GET_LE(&hdr->e_shoff) +
-			GET_LE(&hdr->e_shentsize) * i;
-		BITSFUNC(copy_section)(&fake_sections, i, sh,
-				       secstrings + GET_LE(&sh->sh_name));
 	}
-	if (!fake_sections.out_shstrndx)
-		fail("didn't generate shstrndx?!?\n");
-
-	PUT_LE(&hdr->e_shoff, fake_sections.table_offset);
-	PUT_LE(&hdr->e_shentsize, sizeof(ELF(Shdr)));
-	PUT_LE(&hdr->e_shnum, fake_sections.count);
-	PUT_LE(&hdr->e_shstrndx, fake_sections.out_shstrndx);
 
 	/* Validate mapping addresses. */
 	for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
@@ -263,21 +115,23 @@ static void BITSFUNC(go)(void *addr, size_t len,
 		if (syms[i] % 4096)
 			fail("%s must be a multiple of 4096\n",
 			     required_syms[i].name);
-		if (syms[i] < data_size)
-			fail("%s must be after the text mapping\n",
+		if (syms[sym_vvar_start] > syms[i] + 4096)
+			fail("%s underruns begin_vvar\n",
 			     required_syms[i].name);
-		if (syms[sym_end_mapping] < syms[i] + 4096)
-			fail("%s overruns end_mapping\n",
+		if (syms[i] + 4096 > 0)
+			fail("%s is on the wrong side of the vdso text\n",
 			     required_syms[i].name);
 	}
-	if (syms[sym_end_mapping] % 4096)
-		fail("end_mapping must be a multiple of 4096\n");
+	if (syms[sym_vvar_start] % 4096)
+		fail("vvar_begin must be a multiple of 4096\n");
 
 	if (!name) {
-		fwrite(addr, load_size, 1, outfile);
+		fwrite(stripped_addr, stripped_len, 1, outfile);
 		return;
 	}
 
+	mapping_size = (stripped_len + 4095) / 4096 * 4096;
+
 	fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n");
 	fprintf(outfile, "#include <linux/linkage.h>\n");
 	fprintf(outfile, "#include <asm/page_types.h>\n");
@@ -285,20 +139,21 @@ static void BITSFUNC(go)(void *addr, size_t len,
 	fprintf(outfile, "\n");
 	fprintf(outfile,
 		"static unsigned char raw_data[%lu] __page_aligned_data = {",
-		data_size);
-	for (j = 0; j < load_size; j++) {
+		mapping_size);
+	for (j = 0; j < stripped_len; j++) {
 		if (j % 10 == 0)
 			fprintf(outfile, "\n\t");
-		fprintf(outfile, "0x%02X, ", (int)((unsigned char *)addr)[j]);
+		fprintf(outfile, "0x%02X, ",
+			(int)((unsigned char *)stripped_addr)[j]);
 	}
 	fprintf(outfile, "\n};\n\n");
 
 	fprintf(outfile, "static struct page *pages[%lu];\n\n",
-		data_size / 4096);
+		mapping_size / 4096);
 
 	fprintf(outfile, "const struct vdso_image %s = {\n", name);
 	fprintf(outfile, "\t.data = raw_data,\n");
-	fprintf(outfile, "\t.size = %lu,\n", data_size);
+	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
 	fprintf(outfile, "\t.text_mapping = {\n");
 	fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
 	fprintf(outfile, "\t\t.pages = pages,\n");
@@ -311,8 +166,8 @@ static void BITSFUNC(go)(void *addr, size_t len,
 	}
 	for (i = 0; i < NSYMS; i++) {
 		if (required_syms[i].export && syms[i])
-			fprintf(outfile, "\t.sym_%s = 0x%" PRIx64 ",\n",
-				required_syms[i].name, syms[i]);
+			fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n",
+				required_syms[i].name, (int64_t)syms[i]);
 	}
 	fprintf(outfile, "};\n");
 }
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 5a5176de8d0a..dbef622bb5af 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -93,7 +93,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long addr;
+	unsigned long addr, text_start;
 	int ret = 0;
 	static struct page *no_pages[] = {NULL};
 	static struct vm_special_mapping vvar_mapping = {
@@ -103,26 +103,28 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
-				 image->sym_end_mapping);
+				 image->size - image->sym_vvar_start);
 	} else {
 		addr = 0;
 	}
 
 	down_write(&mm->mmap_sem);
 
-	addr = get_unmapped_area(NULL, addr, image->sym_end_mapping, 0, 0);
+	addr = get_unmapped_area(NULL, addr,
+				 image->size - image->sym_vvar_start, 0, 0);
 	if (IS_ERR_VALUE(addr)) {
 		ret = addr;
 		goto up_fail;
 	}
 
-	current->mm->context.vdso = (void __user *)addr;
+	text_start = addr - image->sym_vvar_start;
+	current->mm->context.vdso = (void __user *)text_start;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
 	 */
 	vma = _install_special_mapping(mm,
-				       addr,
+				       text_start,
 				       image->size,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
@@ -134,8 +136,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	}
 
 	vma = _install_special_mapping(mm,
-				       addr + image->size,
-				       image->sym_end_mapping - image->size,
+				       addr,
+				       -image->sym_vvar_start,
 				       VM_READ,
 				       &vvar_mapping);
 
@@ -146,7 +148,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 
 	if (image->sym_vvar_page)
 		ret = remap_pfn_range(vma,
-				      addr + image->sym_vvar_page,
+				      text_start + image->sym_vvar_page,
 				      __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
 				      PAGE_SIZE,
 				      PAGE_READONLY);
@@ -157,7 +159,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 #ifdef CONFIG_HPET_TIMER
 	if (hpet_address && image->sym_hpet_page) {
 		ret = io_remap_pfn_range(vma,
-			addr + image->sym_hpet_page,
+			text_start + image->sym_hpet_page,
 			hpet_address >> PAGE_SHIFT,
 			PAGE_SIZE,
 			pgprot_noncached(PAGE_READONLY));