Merge branch 'linus' into x86/urgent

Merge reason: We want to queue up a dependent patch.

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

33 files changed, 444 insertions, 283 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 67e929b8987..87eee07da21 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -624,6 +624,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
 	}
 
 	hpet_address = hpet_tbl->address.address;
+	hpet_blockid = hpet_tbl->sequence;
 
 	/*
 	 * Some broken BIOSes advertise HPET at 0x0. We really do not
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index ca93638ba43..82e508677b9 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -78,12 +78,9 @@ int acpi_save_state_mem(void)
 #ifndef CONFIG_64BIT
 	store_gdt((struct desc_ptr *)&header->pmode_gdt);
 
-	header->pmode_efer_low = nx_enabled;
-	if (header->pmode_efer_low & 1) {
-		/* This is strange, why not save efer, always? */
-		rdmsr(MSR_EFER, header->pmode_efer_low,
-			header->pmode_efer_high);
-	}
+	if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low,
+		       &header->pmode_efer_high))
+		header->pmode_efer_low = header->pmode_efer_high = 0;
 #endif /* !CONFIG_64BIT */
 
 	header->pmode_cr0 = read_cr0();
@@ -119,29 +116,32 @@ void acpi_restore_state_mem(void)
 
 
 /**
- * acpi_reserve_bootmem - do _very_ early ACPI initialisation
+ * acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation
  *
  * We allocate a page from the first 1MB of memory for the wakeup
  * routine for when we come back from a sleep state. The
  * runtime allocator allows specification of <16MB pages, but not
  * <1MB pages.
  */
-void __init acpi_reserve_bootmem(void)
+void __init acpi_reserve_wakeup_memory(void)
 {
+	unsigned long mem;
+
 	if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) {
 		printk(KERN_ERR
 		       "ACPI: Wakeup code way too big, S3 disabled.\n");
 		return;
 	}
 
-	acpi_realmode = (unsigned long)alloc_bootmem_low(WAKEUP_SIZE);
+	mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE);
 
-	if (!acpi_realmode) {
+	if (mem == -1L) {
 		printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n");
 		return;
 	}
-
-	acpi_wakeup_address = virt_to_phys((void *)acpi_realmode);
+	acpi_realmode = (unsigned long) phys_to_virt(mem);
+	acpi_wakeup_address = mem;
+	reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP");
 }
 
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ad8c75b9e45..efb2b9cd132 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -647,7 +647,7 @@ static int __init calibrate_APIC_clock(void)
 	calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
 
 	apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
-	apic_printk(APIC_VERBOSE, "..... mult: %ld\n", lapic_clockevent.mult);
+	apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
 	apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
 		    calibration_result);
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c0b4468683f..d5d498fbee4 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3267,7 +3267,8 @@ void destroy_irq(unsigned int irq)
  * MSI message composition
  */
 #ifdef CONFIG_PCI_MSI
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
+static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
+			   struct msi_msg *msg, u8 hpet_id)
 {
 	struct irq_cfg *cfg;
 	int err;
@@ -3301,7 +3302,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 		irte.dest_id = IRTE_DEST(dest);
 
 		/* Set source-id of interrupt request */
-		set_msi_sid(&irte, pdev);
+		if (pdev)
+			set_msi_sid(&irte, pdev);
+		else
+			set_hpet_sid(&irte, hpet_id);
 
 		modify_irte(irq, &irte);
 
@@ -3466,7 +3470,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	int ret;
 	struct msi_msg msg;
 
-	ret = msi_compose_msg(dev, irq, &msg);
+	ret = msi_compose_msg(dev, irq, &msg, -1);
 	if (ret < 0)
 		return ret;
 
@@ -3599,7 +3603,7 @@ int arch_setup_dmar_msi(unsigned int irq)
 	int ret;
 	struct msi_msg msg;
 
-	ret = msi_compose_msg(NULL, irq, &msg);
+	ret = msi_compose_msg(NULL, irq, &msg, -1);
 	if (ret < 0)
 		return ret;
 	dmar_msi_write(irq, &msg);
@@ -3639,6 +3643,19 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 #endif /* CONFIG_SMP */
 
+static struct irq_chip ir_hpet_msi_type = {
+	.name = "IR-HPET_MSI",
+	.unmask = hpet_msi_unmask,
+	.mask = hpet_msi_mask,
+#ifdef CONFIG_INTR_REMAP
+	.ack = ir_ack_apic_edge,
+#ifdef CONFIG_SMP
+	.set_affinity = ir_set_msi_irq_affinity,
+#endif
+#endif
+	.retrigger = ioapic_retrigger_irq,
+};
+
 static struct irq_chip hpet_msi_type = {
 	.name = "HPET_MSI",
 	.unmask = hpet_msi_unmask,
@@ -3650,20 +3667,36 @@ static struct irq_chip hpet_msi_type = {
 	.retrigger = ioapic_retrigger_irq,
 };
 
-int arch_setup_hpet_msi(unsigned int irq)
+int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
 	int ret;
 	struct msi_msg msg;
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	ret = msi_compose_msg(NULL, irq, &msg);
+	if (intr_remapping_enabled) {
+		struct intel_iommu *iommu = map_hpet_to_ir(id);
+		int index;
+
+		if (!iommu)
+			return -1;
+
+		index = alloc_irte(iommu, irq, 1);
+		if (index < 0)
+			return -1;
+	}
+
+	ret = msi_compose_msg(NULL, irq, &msg, id);
 	if (ret < 0)
 		return ret;
 
 	hpet_msi_write(irq, &msg);
 	desc->status |= IRQ_MOVE_PCNTXT;
-	set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq,
-		"edge");
+	if (irq_remapped(irq))
+		set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
+					      handle_edge_irq, "edge");
+	else
+		set_irq_chip_and_handler_name(irq, &hpet_msi_type,
+					      handle_edge_irq, "edge");
 
 	return 0;
 }
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 07cdbdcd7a9..98c4665f251 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -264,11 +264,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc)
 static __init void early_check_numaq(void)
 {
 	/*
-	 * Find possible boot-time SMP configuration:
-	 */
-	early_find_smp_config();
-
-	/*
 	 * get boot-time SMP configuration:
 	 */
 	if (smp_found_config)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 130c4b93487..b684bb303cb 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -30,10 +30,22 @@
 #include <asm/apic.h>
 #include <asm/ipi.h>
 #include <asm/smp.h>
+#include <asm/x86_init.h>
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type uv_system_type;
+static u64 gru_start_paddr, gru_end_paddr;
+
+static inline bool is_GRU_range(u64 start, u64 end)
+{
+	return start >= gru_start_paddr && end <= gru_end_paddr;
+}
+
+static bool uv_is_untracked_pat_range(u64 start, u64 end)
+{
+	return is_ISA_range(start, end) || is_GRU_range(start, end);
+}
 
 static int early_get_nodeid(void)
 {
@@ -49,6 +61,7 @@ static int early_get_nodeid(void)
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strcmp(oem_id, "SGI")) {
+		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 		if (!strcmp(oem_table_id, "UVL"))
 			uv_system_type = UV_LEGACY_APIC;
 		else if (!strcmp(oem_table_id, "UVX"))
@@ -385,8 +398,12 @@ static __init void map_gru_high(int max_pnode)
 	int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
 
 	gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
-	if (gru.s.enable)
+	if (gru.s.enable) {
 		map_high("GRU", gru.s.base, shift, max_pnode, map_wb);
+		gru_start_paddr = ((u64)gru.s.base << shift);
+		gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1);
+
+	}
 }
 
 static __init void map_mmr_high(int max_pnode)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a4ec8b64754..c1afa990a6c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1136,7 +1136,7 @@ void __cpuinit cpu_init(void)
 	wrmsrl(MSR_KERNEL_GS_BASE, 0);
 	barrier();
 
-	check_efer();
+	x86_configure_nx();
 	if (cpu != 0)
 		enable_x2apic();
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 40e1835b35e..c900b73f922 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -263,8 +263,12 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
 	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE || !node_online(node))
+	if (node == NUMA_NO_NODE)
 		node = first_node(node_online_map);
+	else if (!node_online(node)) {
+		/* reuse the value from init_cpu_to_node() */
+		node = cpu_to_node(cpu);
+	}
 	numa_set_node(cpu, node);
 
 	printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node);
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 73c86db5acb..09b1698e046 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -170,6 +170,41 @@ static int __init cmp_range(const void *x1, const void *x2)
 	return start1 - start2;
 }
 
+static int __init clean_sort_range(struct res_range *range, int az)
+{
+	int i, j, k = az - 1, nr_range = 0;
+
+	for (i = 0; i < k; i++) {
+		if (range[i].end)
+			continue;
+		for (j = k; j > i; j--) {
+			if (range[j].end) {
+				k = j;
+				break;
+			}
+		}
+		if (j == i)
+			break;
+		range[i].start = range[k].start;
+		range[i].end   = range[k].end;
+		range[k].start = 0;
+		range[k].end   = 0;
+		k--;
+	}
+	/* count it */
+	for (i = 0; i < az; i++) {
+		if (!range[i].end) {
+			nr_range = i;
+			break;
+		}
+	}
+
+	/* sort them */
+	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+
+	return nr_range;
+}
+
 #define BIOS_BUG_MSG KERN_WARNING \
 	"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
 
@@ -223,22 +258,18 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 		subtract_range(range, extra_remove_base,
 				 extra_remove_base + extra_remove_size  - 1);
 
-	/* get new range num */
-	nr_range = 0;
-	for (i = 0; i < RANGE_NUM; i++) {
-		if (!range[i].end)
-			continue;
-		nr_range++;
-	}
 	if  (debug_print) {
 		printk(KERN_DEBUG "After UC checking\n");
-		for (i = 0; i < nr_range; i++)
+		for (i = 0; i < RANGE_NUM; i++) {
+			if (!range[i].end)
+				continue;
 			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
 				 range[i].start, range[i].end + 1);
+		}
 	}
 
 	/* sort the ranges */
-	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+	nr_range = clean_sort_range(range, RANGE_NUM);
 	if  (debug_print) {
 		printk(KERN_DEBUG "After sorting\n");
 		for (i = 0; i < nr_range; i++)
@@ -689,8 +720,6 @@ static int __init mtrr_need_cleanup(void)
 			continue;
 		if (!size)
 			type = MTRR_NUM_TYPES;
-		if (type == MTRR_TYPE_WRPROT)
-			type = MTRR_TYPE_UNCACHABLE;
 		num[type]++;
 	}
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 4deb8fc849d..63bca794c8f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -977,8 +977,8 @@ apicinterrupt UV_BAU_MESSAGE \
 #endif
 apicinterrupt LOCAL_TIMER_VECTOR \
 	apic_timer_interrupt smp_apic_timer_interrupt
-apicinterrupt GENERIC_INTERRUPT_VECTOR \
-	generic_interrupt smp_generic_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR \
+	x86_platform_ipi smp_x86_platform_ipi
 
 #ifdef CONFIG_SMP
 apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 5a1b9758fd6..30968924543 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -189,9 +189,26 @@ static void wait_for_nmi(void)
 	nmi_wait_count++;
 }
 
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
+{
+	return addr >= start && addr < end;
+}
+
 static int
 do_ftrace_mod_code(unsigned long ip, void *new_code)
 {
+	/*
+	 * On x86_64, kernel text mappings are mapped read-only with
+	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
+	 * of the kernel text mapping to modify the kernel text.
+	 *
+	 * For 32bit kernels, these mappings are same and we can use
+	 * kernel identity mapping to modify code.
+	 */
+	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
+		ip = (unsigned long)__va(__pa(ip));
+
 	mod_code_ip = (void *)ip;
 	mod_code_newcode = new_code;
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 050c278481b..7fd318bac59 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -18,6 +18,8 @@
 #include <asm/asm-offsets.h>
 #include <asm/setup.h>
 #include <asm/processor-flags.h>
+#include <asm/msr-index.h>
+#include <asm/cpufeature.h>
 #include <asm/percpu.h>
 
 /* Physical address */
@@ -297,25 +299,27 @@ ENTRY(startup_32_smp)
 	orl %edx,%eax
 	movl %eax,%cr4
 
-	btl $5, %eax		# check if PAE is enabled
-	jnc 6f
+	testb $X86_CR4_PAE, %al		# check if PAE is enabled
+	jz 6f
 
 	/* Check if extended functions are implemented */
 	movl $0x80000000, %eax
 	cpuid
-	cmpl $0x80000000, %eax
-	jbe 6f
+	/* Value must be in the range 0x80000001 to 0x8000ffff */
+	subl $0x80000001, %eax
+	cmpl $(0x8000ffff-0x80000001), %eax
+	ja 6f
 	mov $0x80000001, %eax
 	cpuid
 	/* Execute Disable bit supported? */
-	btl $20, %edx
+	btl $(X86_FEATURE_NX & 31), %edx
 	jnc 6f
 
 	/* Setup EFER (Extended Feature Enable Register) */
-	movl $0xc0000080, %ecx
+	movl $MSR_EFER, %ecx
 	rdmsr
 
-	btsl $11, %eax
+	btsl $_EFER_NX, %eax
 	/* Make changes effective */
 	wrmsr
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 22db86a3764..2d8b5035371 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -262,11 +262,11 @@ ENTRY(secondary_startup_64)
 	.quad	x86_64_start_kernel
 	ENTRY(initial_gs)
 	.quad	INIT_PER_CPU_VAR(irq_stack_union)
-	__FINITDATA
 
 	ENTRY(stack_start)
 	.quad  init_thread_union+THREAD_SIZE-8
 	.word  0
+	__FINITDATA
 
 bad_address:
 	jmp bad_address
@@ -340,6 +340,7 @@ ENTRY(name)
 	i = i + 1 ;					\
 	.endr
 
+	.data
 	/*
 	 * This default setting generates an ident mapping at address 0x100000
 	 * and a mapping for the kernel that precisely maps virtual address
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index dedc2bddf7a..ba6e6588460 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -33,6 +33,7 @@
  * HPET address is set in acpi/boot.c, when an ACPI entry exists
  */
 unsigned long				hpet_address;
+u8					hpet_blockid; /* OS timer block num */
 #ifdef CONFIG_PCI_MSI
 static unsigned long			hpet_num_timers;
 #endif
@@ -47,12 +48,12 @@ struct hpet_dev {
 	char				name[10];
 };
 
-unsigned long hpet_readl(unsigned long a)
+inline unsigned int hpet_readl(unsigned int a)
 {
 	return readl(hpet_virt_address + a);
 }
 
-static inline void hpet_writel(unsigned long d, unsigned long a)
+static inline void hpet_writel(unsigned int d, unsigned int a)
 {
 	writel(d, hpet_virt_address + a);
 }
@@ -167,7 +168,7 @@ do {								\
 
 static void hpet_reserve_msi_timers(struct hpet_data *hd);
 
-static void hpet_reserve_platform_timers(unsigned long id)
+static void hpet_reserve_platform_timers(unsigned int id)
 {
 	struct hpet __iomem *hpet = hpet_virt_address;
 	struct hpet_timer __iomem *timer = &hpet->hpet_timers[2];
@@ -205,7 +206,7 @@ static void hpet_reserve_platform_timers(unsigned long id)
 
 }
 #else
-static void hpet_reserve_platform_timers(unsigned long id) { }
+static void hpet_reserve_platform_timers(unsigned int id) { }
 #endif
 
 /*
@@ -246,7 +247,7 @@ static void hpet_reset_counter(void)
 
 static void hpet_start_counter(void)
 {
-	unsigned long cfg = hpet_readl(HPET_CFG);
+	unsigned int cfg = hpet_readl(HPET_CFG);
 	cfg |= HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
 }
@@ -271,7 +272,7 @@ static void hpet_resume_counter(void)
 
 static void hpet_enable_legacy_int(void)
 {
-	unsigned long cfg = hpet_readl(HPET_CFG);
+	unsigned int cfg = hpet_readl(HPET_CFG);
 
 	cfg |= HPET_CFG_LEGACY;
 	hpet_writel(cfg, HPET_CFG);
@@ -314,7 +315,7 @@ static int hpet_setup_msi_irq(unsigned int irq);
 static void hpet_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt, int timer)
 {
-	unsigned long cfg, cmp, now;
+	unsigned int cfg, cmp, now;
 	uint64_t delta;
 
 	switch (mode) {
@@ -323,7 +324,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
 		delta >>= evt->shift;
 		now = hpet_readl(HPET_COUNTER);
-		cmp = now + (unsigned long) delta;
+		cmp = now + (unsigned int) delta;
 		cfg = hpet_readl(HPET_Tn_CFG(timer));
 		/* Make sure we use edge triggered interrupts */
 		cfg &= ~HPET_TN_LEVEL;
@@ -339,7 +340,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
 		 * Publication # 24674)
 		 */
-		hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer));
+		hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer));
 		hpet_start_counter();
 		hpet_print_config();
 		break;
@@ -383,13 +384,24 @@ static int hpet_next_event(unsigned long delta,
 	hpet_writel(cnt, HPET_Tn_CMP(timer));
 
 	/*
-	 * We need to read back the CMP register to make sure that
-	 * what we wrote hit the chip before we compare it to the
-	 * counter.
+	 * We need to read back the CMP register on certain HPET
+	 * implementations (ATI chipsets) which seem to delay the
+	 * transfer of the compare register into the internal compare
+	 * logic. With small deltas this might actually be too late as
+	 * the counter could already be higher than the compare value
+	 * at that point and we would wait for the next hpet interrupt
+	 * forever. We found out that reading the CMP register back
+	 * forces the transfer so we can rely on the comparison with
+	 * the counter register below. If the read back from the
+	 * compare register does not match the value we programmed
+	 * then we might have a real hardware problem. We can not do
+	 * much about it here, but at least alert the user/admin with
+	 * a prominent warning.
 	 */
-	WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt);
+	WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
+		  KERN_WARNING "hpet: compare register read back failed.\n");
 
-	return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
+	return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
 }
 
 static void hpet_legacy_set_mode(enum clock_event_mode mode,
@@ -415,7 +427,7 @@ static struct hpet_dev	*hpet_devs;
 void hpet_msi_unmask(unsigned int irq)
 {
 	struct hpet_dev *hdev = get_irq_data(irq);
-	unsigned long cfg;
+	unsigned int cfg;
 
 	/* unmask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
@@ -425,7 +437,7 @@ void hpet_msi_unmask(unsigned int irq)
 
 void hpet_msi_mask(unsigned int irq)
 {
-	unsigned long cfg;
+	unsigned int cfg;
 	struct hpet_dev *hdev = get_irq_data(irq);
 
 	/* mask it */
@@ -467,7 +479,7 @@ static int hpet_msi_next_event(unsigned long delta,
 
 static int hpet_setup_msi_irq(unsigned int irq)
 {
-	if (arch_setup_hpet_msi(irq)) {
+	if (arch_setup_hpet_msi(irq, hpet_blockid)) {
 		destroy_irq(irq);
 		return -EINVAL;
 	}
@@ -584,6 +596,8 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 	unsigned int num_timers_used = 0;
 	int i;
 
+	if (boot_cpu_has(X86_FEATURE_ARAT))
+		return;
 	id = hpet_readl(HPET_ID);
 
 	num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT);
@@ -598,7 +612,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 
 	for (i = start_timer; i < num_timers - RESERVE_TIMERS; i++) {
 		struct hpet_dev *hdev = &hpet_devs[num_timers_used];
-		unsigned long cfg = hpet_readl(HPET_Tn_CFG(i));
+		unsigned int cfg = hpet_readl(HPET_Tn_CFG(i));
 
 		/* Only consider HPET timer with MSI support */
 		if (!(cfg & HPET_TN_FSB_CAP))
@@ -813,7 +827,7 @@ static int hpet_clocksource_register(void)
  */
 int __init hpet_enable(void)
 {
-	unsigned long id;
+	unsigned int id;
 	int i;
 
 	if (!is_hpet_capable())
@@ -872,10 +886,8 @@ int __init hpet_enable(void)
 
 	if (id & HPET_ID_LEGSUP) {
 		hpet_legacy_clockevent_register();
-		hpet_msi_capability_lookup(2);
 		return 1;
 	}
-	hpet_msi_capability_lookup(0);
 	return 0;
 
 out_nohpet:
@@ -908,9 +920,17 @@ static __init int hpet_late_init(void)
 	if (!hpet_virt_address)
 		return -ENODEV;
 
+	if (hpet_readl(HPET_ID) & HPET_ID_LEGSUP)
+		hpet_msi_capability_lookup(2);
+	else
+		hpet_msi_capability_lookup(0);
+
 	hpet_reserve_platform_timers(hpet_readl(HPET_ID));
 	hpet_print_config();
 
+	if (boot_cpu_has(X86_FEATURE_ARAT))
+		return 0;
+
 	for_each_online_cpu(cpu) {
 		hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);
 	}
@@ -925,7 +945,7 @@ fs_initcall(hpet_late_init);
 void hpet_disable(void)
 {
 	if (is_hpet_capable()) {
-		unsigned long cfg = hpet_readl(HPET_CFG);
+		unsigned int cfg = hpet_readl(HPET_CFG);
 
 		if (hpet_legacy_int_enabled) {
 			cfg &= ~HPET_CFG_LEGACY;
@@ -965,8 +985,8 @@ static int hpet_prev_update_sec;
 static struct rtc_time hpet_alarm_time;
 static unsigned long hpet_pie_count;
 static u32 hpet_t1_cmp;
-static unsigned long hpet_default_delta;
-static unsigned long hpet_pie_delta;
+static u32 hpet_default_delta;
+static u32 hpet_pie_delta;
 static unsigned long hpet_pie_limit;
 
 static rtc_irq_handler irq_handler;
@@ -1017,7 +1037,8 @@ EXPORT_SYMBOL_GPL(hpet_unregister_irq_handler);
  */
 int hpet_rtc_timer_init(void)
 {
-	unsigned long cfg, cnt, delta, flags;
+	unsigned int cfg, cnt, delta;
+	unsigned long flags;
 
 	if (!is_hpet_enabled())
 		return 0;
@@ -1027,7 +1048,7 @@ int hpet_rtc_timer_init(void)
 
 		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
 		clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT;
-		hpet_default_delta = (unsigned long) clc;
+		hpet_default_delta = clc;
 	}
 
 	if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit)
@@ -1113,7 +1134,7 @@ int hpet_set_periodic_freq(unsigned long freq)
 		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
 		do_div(clc, freq);
 		clc >>= hpet_clockevent.shift;
-		hpet_pie_delta = (unsigned long) clc;
+		hpet_pie_delta = clc;
 	}
 	return 1;
 }
@@ -1127,7 +1148,7 @@ EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq);
 
 static void hpet_rtc_timer_reinit(void)
 {
-	unsigned long cfg, delta;
+	unsigned int cfg, delta;
 	int lost_ints = -1;
 
 	if (unlikely(!hpet_rtc_flags)) {
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index fee6cc2b207..664bcb7384a 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -18,7 +18,7 @@
 atomic_t irq_err_count;
 
 /* Function pointer for generic interrupt vector handling */
-void (*generic_interrupt_extension)(void) = NULL;
+void (*x86_platform_ipi_callback)(void) = NULL;
 
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
@@ -72,10 +72,10 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
 	seq_printf(p, "  Performance pending work\n");
 #endif
-	if (generic_interrupt_extension) {
+	if (x86_platform_ipi_callback) {
 		seq_printf(p, "%*s: ", prec, "PLT");
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", irq_stats(j)->generic_irqs);
+			seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis);
 		seq_printf(p, "  Platform interrupts\n");
 	}
 #ifdef CONFIG_SMP
@@ -187,8 +187,8 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 	sum += irq_stats(cpu)->apic_perf_irqs;
 	sum += irq_stats(cpu)->apic_pending_irqs;
 #endif
-	if (generic_interrupt_extension)
-		sum += irq_stats(cpu)->generic_irqs;
+	if (x86_platform_ipi_callback)
+		sum += irq_stats(cpu)->x86_platform_ipis;
 #ifdef CONFIG_SMP
 	sum += irq_stats(cpu)->irq_resched_count;
 	sum += irq_stats(cpu)->irq_call_count;
@@ -251,9 +251,9 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 }
 
 /*
- * Handler for GENERIC_INTERRUPT_VECTOR.
+ * Handler for X86_PLATFORM_IPI_VECTOR.
  */
-void smp_generic_interrupt(struct pt_regs *regs)
+void smp_x86_platform_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -263,10 +263,10 @@ void smp_generic_interrupt(struct pt_regs *regs)
 
 	irq_enter();
 
-	inc_irq_stat(generic_irqs);
+	inc_irq_stat(x86_platform_ipis);
 
-	if (generic_interrupt_extension)
-		generic_interrupt_extension();
+	if (x86_platform_ipi_callback)
+		x86_platform_ipi_callback();
 
 	irq_exit();
 
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 40f30773fb2..d5932226614 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -200,8 +200,8 @@ static void __init apic_intr_init(void)
 	/* self generated IPI for local APIC timer */
 	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
-	/* generic IPI for platform specific use */
-	alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
+	/* IPI for X86 platform specific use */
+	alloc_intr_gate(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi);
 
 	/* IPI vectors for APIC spurious and error interrupts */
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index c843f8406da..a3fa43ba5d3 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -158,8 +158,7 @@ int machine_kexec_prepare(struct kimage *image)
 {
 	int error;
 
-	if (nx_enabled)
-		set_pages_x(image->control_code_page, 1);
+	set_pages_x(image->control_code_page, 1);
 	error = machine_kexec_alloc_page_tables(image);
 	if (error)
 		return error;
@@ -173,8 +172,7 @@ int machine_kexec_prepare(struct kimage *image)
  */
 void machine_kexec_cleanup(struct kimage *image)
 {
-	if (nx_enabled)
-		set_pages_nx(image->control_code_page, 1);
+	set_pages_nx(image->control_code_page, 1);
 	machine_kexec_free_page_tables(image);
 }
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index f4c538b681c..63123d90210 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -33,6 +33,9 @@ MODULE_LICENSE("GPL v2");
 #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000
 #define UCODE_UCODE_TYPE           0x00000001
 
+const struct firmware *firmware;
+static int supported_cpu;
+
 struct equiv_cpu_entry {
 	u32	installed_cpu;
 	u32	fixed_errata_mask;
@@ -71,17 +74,14 @@ static struct equiv_cpu_entry *equiv_cpu_table;
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 dummy;
 
-	memset(csig, 0, sizeof(*csig));
-	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-		printk(KERN_WARNING "microcode: CPU%d: AMD CPU family 0x%x not "
-		       "supported\n", cpu, c->x86);
+	if (!supported_cpu)
 		return -1;
-	}
+
+	memset(csig, 0, sizeof(*csig));
 	rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
-	printk(KERN_INFO "microcode: CPU%d: patch_level=0x%x\n", cpu, csig->rev);
+	pr_info("microcode: CPU%d: patch_level=0x%x\n", cpu, csig->rev);
 	return 0;
 }
 
@@ -103,22 +103,15 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
 		i++;
 	}
 
-	if (!equiv_cpu_id) {
-		printk(KERN_WARNING "microcode: CPU%d: cpu revision "
-		       "not listed in equivalent cpu table\n", cpu);
+	if (!equiv_cpu_id)
 		return 0;
-	}
 
-	if (mc_header->processor_rev_id != equiv_cpu_id) {
-		printk(KERN_ERR	"microcode: CPU%d: patch mismatch "
-		       "(processor_rev_id: %x, equiv_cpu_id: %x)\n",
-		       cpu, mc_header->processor_rev_id, equiv_cpu_id);
+	if (mc_header->processor_rev_id != equiv_cpu_id)
 		return 0;
-	}
 
 	/* ucode might be chipset specific -- currently we don't support this */
 	if (mc_header->nb_dev_id || mc_header->sb_dev_id) {
-		printk(KERN_ERR "microcode: CPU%d: loading of chipset "
+		pr_err(KERN_ERR "microcode: CPU%d: loading of chipset "
 		       "specific code not yet supported\n", cpu);
 		return 0;
 	}
@@ -148,14 +141,12 @@ static int apply_microcode_amd(int cpu)
 
 	/* check current patch id and patch's id for match */
 	if (rev != mc_amd->hdr.patch_id) {
-		printk(KERN_ERR "microcode: CPU%d: update failed "
+		pr_err("microcode: CPU%d: update failed "
 		       "(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id);
 		return -1;
 	}
 
-	printk(KERN_INFO "microcode: CPU%d: updated (new patch_level=0x%x)\n",
-	       cpu, rev);
-
+	pr_info("microcode: CPU%d: updated (new patch_level=0x%x)\n", cpu, rev);
 	uci->cpu_sig.rev = rev;
 
 	return 0;
@@ -178,18 +169,15 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 		return NULL;
 
 	if (section_hdr[0] != UCODE_UCODE_TYPE) {
-		printk(KERN_ERR "microcode: error: invalid type field in "
+		pr_err("microcode: error: invalid type field in "
 		       "container file section header\n");
 		return NULL;
 	}
 
 	total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8));
 
-	printk(KERN_DEBUG "microcode: size %u, total_size %u\n",
-	       size, total_size);
-
 	if (total_size > size || total_size > UCODE_MAX_SIZE) {
-		printk(KERN_ERR "microcode: error: size mismatch\n");
+		pr_err("microcode: error: size mismatch\n");
 		return NULL;
 	}
 
@@ -218,15 +206,14 @@ static int install_equiv_cpu_table(const u8 *buf)
 	size = buf_pos[2];
 
 	if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
-		printk(KERN_ERR "microcode: error: invalid type field in "
+		pr_err("microcode: error: invalid type field in "
 		       "container file section header\n");
 		return 0;
 	}
 
 	equiv_cpu_table = (struct equiv_cpu_entry *) vmalloc(size);
 	if (!equiv_cpu_table) {
-		printk(KERN_ERR "microcode: failed to allocate "
-		       "equivalent CPU table\n");
+		pr_err("microcode: failed to allocate equivalent CPU table\n");
 		return 0;
 	}
 
@@ -259,8 +246,7 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 	offset = install_equiv_cpu_table(ucode_ptr);
 	if (!offset) {
-		printk(KERN_ERR "microcode: failed to create "
-		       "equivalent cpu table\n");
+		pr_err("microcode: failed to create equivalent cpu table\n");
 		return UCODE_ERROR;
 	}
 
@@ -308,33 +294,27 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
 
 static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 {
-	const char *fw_name = "amd-ucode/microcode_amd.bin";
-	const struct firmware *firmware;
 	enum ucode_state ret;
 
-	if (request_firmware(&firmware, fw_name, device)) {
-		printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
+	if (firmware == NULL)
 		return UCODE_NFOUND;
-	}
 
 	if (*(u32 *)firmware->data != UCODE_MAGIC) {
-		printk(KERN_ERR "microcode: invalid UCODE_MAGIC (0x%08x)\n",
+		pr_err("microcode: invalid UCODE_MAGIC (0x%08x)\n",
 		       *(u32 *)firmware->data);
 		return UCODE_ERROR;
 	}
 
 	ret = generic_load_microcode(cpu, firmware->data, firmware->size);
 
-	release_firmware(firmware);
-
 	return ret;
 }
 
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-	printk(KERN_INFO "microcode: AMD microcode update via "
-	       "/dev/cpu/microcode not supported\n");
+	pr_info("microcode: AMD microcode update via "
+		"/dev/cpu/microcode not supported\n");
 	return UCODE_ERROR;
 }
 
@@ -346,7 +326,32 @@ static void microcode_fini_cpu_amd(int cpu)
 	uci->mc = NULL;
 }
 
+void init_microcode_amd(struct device *device)
+{
+	const char *fw_name = "amd-ucode/microcode_amd.bin";
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	WARN_ON(c->x86_vendor != X86_VENDOR_AMD);
+
+	if (c->x86 < 0x10) {
+		pr_warning("microcode: AMD CPU family 0x%x not supported\n",
+			   c->x86);
+		return;
+	}
+	supported_cpu = 1;
+
+	if (request_firmware(&firmware, fw_name, device))
+		pr_err("microcode: failed to load file %s\n", fw_name);
+}
+
+void fini_microcode_amd(void)
+{
+	release_firmware(firmware);
+}
+
 static struct microcode_ops microcode_amd_ops = {
+	.init				  = init_microcode_amd,
+	.fini				  = fini_microcode_amd,
 	.request_microcode_user           = request_microcode_user,
 	.request_microcode_fw             = request_microcode_fw,
 	.collect_cpu_info                 = collect_cpu_info_amd,
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 2bcad3926ed..e68aae39786 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -391,7 +391,7 @@ static enum ucode_state microcode_update_cpu(int cpu)
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	enum ucode_state ustate;
 
-	if (uci->valid)
+	if (uci->valid && uci->mc)
 		ustate = microcode_resume_cpu(cpu);
 	else
 		ustate = microcode_init_cpu(cpu);
@@ -518,6 +518,9 @@ static int __init microcode_init(void)
 		return PTR_ERR(microcode_pdev);
 	}
 
+	if (microcode_ops->init)
+		microcode_ops->init(&microcode_pdev->dev);
+
 	get_online_cpus();
 	mutex_lock(&microcode_mutex);
 
@@ -561,6 +564,9 @@ static void __exit microcode_exit(void)
 
 	platform_device_unregister(microcode_pdev);
 
+	if (microcode_ops->fini)
+		microcode_ops->fini();
+
 	microcode_ops = NULL;
 
 	pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 5be95ef4ffe..35a57c963df 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -667,36 +667,18 @@ void __init default_get_smp_config(unsigned int early)
 	 */
 }
 
-static void __init smp_reserve_bootmem(struct mpf_intel *mpf)
+static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
-#ifdef CONFIG_X86_32
-	/*
-	 * We cannot access to MPC table to compute table size yet,
-	 * as only few megabytes from the bottom is mapped now.
-	 * PC-9800's MPC table places on the very last of physical
-	 * memory; so that simply reserving PAGE_SIZE from mpf->physptr
-	 * yields BUG() in reserve_bootmem.
-	 * also need to make sure physptr is below than max_low_pfn
-	 * we don't need reserve the area above max_low_pfn
-	 */
-	unsigned long end = max_low_pfn * PAGE_SIZE;
 
-	if (mpf->physptr < end) {
-		if (mpf->physptr + size > end)
-			size = end - mpf->physptr;
-		reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT);
-	}
-#else
-	reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT);
-#endif
+	reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc");
 }
 
-static int __init smp_scan_config(unsigned long base, unsigned long length,
-				  unsigned reserve)
+static int __init smp_scan_config(unsigned long base, unsigned long length)
 {
 	unsigned int *bp = phys_to_virt(base);
 	struct mpf_intel *mpf;
+	unsigned long mem;
 
 	apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
 			bp, length);
@@ -717,12 +699,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 			printk(KERN_INFO "found SMP MP-table at [%p] %llx\n",
 			       mpf, (u64)virt_to_phys(mpf));
 
-			if (!reserve)
-				return 1;
-			reserve_bootmem_generic(virt_to_phys(mpf), sizeof(*mpf),
-						BOOTMEM_DEFAULT);
+			mem = virt_to_phys(mpf);
+			reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf");
 			if (mpf->physptr)
-				smp_reserve_bootmem(mpf);
+				smp_reserve_memory(mpf);
 
 			return 1;
 		}
@@ -732,7 +712,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
 	return 0;
 }
 
-void __init default_find_smp_config(unsigned int reserve)
+void __init default_find_smp_config(void)
 {
 	unsigned int address;
 
@@ -744,9 +724,9 @@ void __init default_find_smp_config(unsigned int reserve)
 	 * 2) Scan the top 1K of base RAM
 	 * 3) Scan the 64K of bios
 	 */
-	if (smp_scan_config(0x0, 0x400, reserve) ||
-	    smp_scan_config(639 * 0x400, 0x400, reserve) ||
-	    smp_scan_config(0xF0000, 0x10000, reserve))
+	if (smp_scan_config(0x0, 0x400) ||
+	    smp_scan_config(639 * 0x400, 0x400) ||
+	    smp_scan_config(0xF0000, 0x10000))
 		return;
 	/*
 	 * If it is an SMP machine we should know now, unless the
@@ -767,7 +747,7 @@ void __init default_find_smp_config(unsigned int reserve)
 
 	address = get_bios_ebda();
 	if (address)
-		smp_scan_config(address, 0x400, reserve);
+		smp_scan_config(address, 0x400);
 }
 
 #ifdef CONFIG_X86_IO_APIC
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 744508e7cfd..5e2ba634ea1 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -9,6 +9,7 @@
 #include <linux/pm.h>
 #include <linux/clockchips.h>
 #include <linux/random.h>
+#include <linux/user-return-notifier.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/system.h>
@@ -209,6 +210,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 */
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
+	propagate_user_return_notify(prev_p, next_p);
 }
 
 int sys_fork(struct pt_regs *regs)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a98fe88fab6..c95c8f4e790 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -349,26 +349,42 @@ out:
 	return err;
 }
 
-void
-start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
+static void
+start_thread_common(struct pt_regs *regs, unsigned long new_ip,
+		    unsigned long new_sp,
+		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
 {
 	loadsegment(fs, 0);
-	loadsegment(es, 0);
-	loadsegment(ds, 0);
+	loadsegment(es, _ds);
+	loadsegment(ds, _ds);
 	load_gs_index(0);
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
 	percpu_write(old_rsp, new_sp);
-	regs->cs		= __USER_CS;
-	regs->ss		= __USER_DS;
-	regs->flags		= 0x200;
+	regs->cs		= _cs;
+	regs->ss		= _ss;
+	regs->flags		= X86_EFLAGS_IF;
 	set_fs(USER_DS);
 	/*
 	 * Free the old FP and other extended state
 	 */
 	free_thread_xstate(current);
 }
-EXPORT_SYMBOL_GPL(start_thread);
+
+void
+start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
+{
+	start_thread_common(regs, new_ip, new_sp,
+			    __USER_CS, __USER_DS, 0);
+}
+
+#ifdef CONFIG_IA32_EMULATION
+void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
+{
+	start_thread_common(regs, new_ip, new_sp,
+			    __USER32_CS, __USER32_DS, __USER32_DS);
+}
+#endif
 
 /*
  *	switch_to(x,y) should switch tasks from x to y.
diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c
index 61a837743fe..201eab63b05 100644
--- a/arch/x86/kernel/reboot_fixups_32.c
+++ b/arch/x86/kernel/reboot_fixups_32.c
@@ -80,6 +80,7 @@ void mach_reboot_fixups(void)
 			continue;
 
 		cur->reboot_fixup(dev);
+		pci_dev_put(dev);
 	}
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 82e88cdda9b..946a311a25c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -106,6 +106,7 @@
 #include <asm/percpu.h>
 #include <asm/topology.h>
 #include <asm/apicdef.h>
+#include <asm/k8.h>
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
@@ -487,42 +488,11 @@ static void __init reserve_early_setup_data(void)
 
 #ifdef CONFIG_KEXEC
 
-/**
- * Reserve @size bytes of crashkernel memory at any suitable offset.
- *
- * @size: Size of the crashkernel memory to reserve.
- * Returns the base address on success, and -1ULL on failure.
- */
-static
-unsigned long long __init find_and_reserve_crashkernel(unsigned long long size)
-{
-	const unsigned long long alignment = 16<<20; 	/* 16M */
-	unsigned long long start = 0LL;
-
-	while (1) {
-		int ret;
-
-		start = find_e820_area(start, ULONG_MAX, size, alignment);
-		if (start == -1ULL)
-			return start;
-
-		/* try to reserve it */
-		ret = reserve_bootmem_generic(start, size, BOOTMEM_EXCLUSIVE);
-		if (ret >= 0)
-			return start;
-
-		start += alignment;
-	}
-}
-
 static inline unsigned long long get_total_mem(void)
 {
 	unsigned long long total;
 
-	total = max_low_pfn - min_low_pfn;
-#ifdef CONFIG_HIGHMEM
-	total += highend_pfn - highstart_pfn;
-#endif
+	total = max_pfn - min_low_pfn;
 
 	return total << PAGE_SHIFT;
 }
@@ -542,21 +512,25 @@ static void __init reserve_crashkernel(void)
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
-		crash_base = find_and_reserve_crashkernel(crash_size);
+		const unsigned long long alignment = 16<<20;	/* 16M */
+
+		crash_base = find_e820_area(alignment, ULONG_MAX, crash_size,
+				 alignment);
 		if (crash_base == -1ULL) {
-			pr_info("crashkernel reservation failed. "
-				"No suitable area found.\n");
+			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
 	} else {
-		ret = reserve_bootmem_generic(crash_base, crash_size,
-					BOOTMEM_EXCLUSIVE);
-		if (ret < 0) {
-			pr_info("crashkernel reservation failed - "
-				"memory is in use\n");
+		unsigned long long start;
+
+		start = find_e820_area(crash_base, ULONG_MAX, crash_size,
+				 1<<20);
+		if (start != crash_base) {
+			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;
 		}
 	}
+	reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL");
 
 	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
 			"for crashkernel (System RAM: %ldMB)\n",
@@ -699,6 +673,9 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
 
 void __init setup_arch(char **cmdline_p)
 {
+	int acpi = 0;
+	int k8 = 0;
+
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
@@ -791,21 +768,18 @@ void __init setup_arch(char **cmdline_p)
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
-#ifdef CONFIG_X86_64
 	/*
-	 * Must call this twice: Once just to detect whether hardware doesn't
-	 * support NX (so that the early EHCI debug console setup can safely
-	 * call set_fixmap(), and then again after parsing early parameters to
-	 * honor the respective command line option.
+	 * x86_configure_nx() is called before parse_early_param() to detect
+	 * whether hardware doesn't support NX (so that the early EHCI debug
+	 * console setup can safely call set_fixmap()). It may then be called
+	 * again from within noexec_setup() during parsing early parameters
+	 * to honor the respective command line option.
 	 */
-	check_efer();
-#endif
+	x86_configure_nx();
 
 	parse_early_param();
 
-#ifdef CONFIG_X86_64
-	check_efer();
-#endif
+	x86_report_nx();
 
 	/* Must be before kernel pagetables are setup */
 	vmi_activate();
@@ -901,6 +875,13 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_brk();
 
+#ifdef CONFIG_ACPI_SLEEP
+	/*
+	 * Reserve low memory region for sleep support.
+	 * even before init_memory_mapping
+	 */
+	acpi_reserve_wakeup_memory();
+#endif
 	init_gbpages();
 
 	/* max_pfn_mapped is updated here */
@@ -927,6 +908,8 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_initrd();
 
+	reserve_crashkernel();
+
 	vsmp_init();
 
 	io_delay_init();
@@ -938,27 +921,24 @@ void __init setup_arch(char **cmdline_p)
 
 	early_acpi_boot_init();
 
+	/*
+	 * Find and reserve possible boot-time SMP configuration:
+	 */
+	find_smp_config();
+
 #ifdef CONFIG_ACPI_NUMA
 	/*
 	 * Parse SRAT to discover nodes.
 	 */
-	acpi_numa_init();
+	acpi = acpi_numa_init();
 #endif
 
-	initmem_init(0, max_pfn);
-
-#ifdef CONFIG_ACPI_SLEEP
-	/*
-	 * Reserve low memory region for sleep support.
-	 */
-	acpi_reserve_bootmem();
+#ifdef CONFIG_K8_NUMA
+	if (!acpi)
+		k8 = !k8_numa_init(0, max_pfn);
 #endif
-	/*
-	 * Find and reserve possible boot-time SMP configuration:
-	 */
-	find_smp_config();
 
-	reserve_crashkernel();
+	initmem_init(0, max_pfn, acpi, k8);
 
 #ifdef CONFIG_X86_64
 	/*
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index fbf3b07c856..74fe6d86dc5 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -19,6 +19,7 @@
 #include <linux/stddef.h>
 #include <linux/personality.h>
 #include <linux/uaccess.h>
+#include <linux/user-return-notifier.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
@@ -863,6 +864,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 		if (current->replacement_session_keyring)
 			key_replace_session_keyring();
 	}
+	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
+		fire_user_return_notifiers();
 
 #ifdef CONFIG_X86_32
 	clear_thread_flag(TIF_IRET);
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 0157cd26d7c..70c2125d55b 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -336,3 +336,4 @@ ENTRY(sys_call_table)
 	.long sys_pwritev
 	.long sys_rt_tgsigqueueinfo	/* 335 */
 	.long sys_perf_event_open
+	.long sys_recvmmsg
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 1740c85e24b..364d015efeb 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -817,10 +817,8 @@ static int __init uv_init_blade(int blade)
 	 */
 	apicid = blade_to_first_apicid(blade);
 	pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG);
-	if ((pa & 0xff) != UV_BAU_MESSAGE) {
-		uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
+	uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
 				      ((apicid << 32) | UV_BAU_MESSAGE));
-	}
 	return 0;
 }
 
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 583f11d5c48..3c84aa001c1 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -74,7 +74,7 @@ struct uv_rtc_timer_head {
  */
 static struct uv_rtc_timer_head		**blade_info __read_mostly;
 
-static int				uv_rtc_enable;
+static int				uv_rtc_evt_enable;
 
 /*
  * Hardware interface routines
@@ -90,7 +90,7 @@ static void uv_rtc_send_IPI(int cpu)
 	pnode = uv_apicid_to_pnode(apicid);
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	      (apicid << UVH_IPI_INT_APIC_ID_SHFT) |
-	      (GENERIC_INTERRUPT_VECTOR << UVH_IPI_INT_VECTOR_SHFT);
+	      (X86_PLATFORM_IPI_VECTOR << UVH_IPI_INT_VECTOR_SHFT);
 
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }
@@ -115,7 +115,7 @@ static int uv_setup_intr(int cpu, u64 expires)
 	uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS,
 		UVH_EVENT_OCCURRED0_RTC1_MASK);
 
-	val = (GENERIC_INTERRUPT_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) |
+	val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) |
 		((u64)cpu_physical_id(cpu) << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT);
 
 	/* Set configuration */
@@ -123,7 +123,10 @@ static int uv_setup_intr(int cpu, u64 expires)
 	/* Initialize comparator value */
 	uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires);
 
-	return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode));
+	if (uv_read_rtc(NULL) <= expires)
+		return 0;
+
+	return !uv_intr_pending(pnode);
 }
 
 /*
@@ -223,6 +226,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 
 	next_cpu = head->next_cpu;
 	*t = expires;
+
 	/* Will this one be next to go off? */
 	if (next_cpu < 0 || bcpu == next_cpu ||
 			expires < head->cpu[next_cpu].expires) {
@@ -231,7 +235,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 			*t = ULLONG_MAX;
 			uv_rtc_find_next_timer(head, pnode);
 			spin_unlock_irqrestore(&head->lock, flags);
-			return 1;
+			return -ETIME;
 		}
 	}
 
@@ -244,7 +248,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
  *
  * Returns 1 if this timer was pending.
  */
-static int uv_rtc_unset_timer(int cpu)
+static int uv_rtc_unset_timer(int cpu, int force)
 {
 	int pnode = uv_cpu_to_pnode(cpu);
 	int bid = uv_cpu_to_blade_id(cpu);
@@ -256,14 +260,15 @@ static int uv_rtc_unset_timer(int cpu)
 
 	spin_lock_irqsave(&head->lock, flags);
 
-	if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t)
+	if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force)
 		rc = 1;
 
-	*t = ULLONG_MAX;
-
-	/* Was the hardware setup for this timer? */
-	if (head->next_cpu == bcpu)
-		uv_rtc_find_next_timer(head, pnode);
+	if (rc) {
+		*t = ULLONG_MAX;
+		/* Was the hardware setup for this timer? */
+		if (head->next_cpu == bcpu)
+			uv_rtc_find_next_timer(head, pnode);
+	}
 
 	spin_unlock_irqrestore(&head->lock, flags);
 
@@ -310,32 +315,32 @@ static void uv_rtc_timer_setup(enum clock_event_mode mode,
 		break;
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
-		uv_rtc_unset_timer(ced_cpu);
+		uv_rtc_unset_timer(ced_cpu, 1);
 		break;
 	}
 }
 
 static void uv_rtc_interrupt(void)
 {
-	struct clock_event_device *ced = &__get_cpu_var(cpu_ced);
 	int cpu = smp_processor_id();
+	struct clock_event_device *ced = &per_cpu(cpu_ced, cpu);
 
 	if (!ced || !ced->event_handler)
 		return;
 
-	if (uv_rtc_unset_timer(cpu) != 1)
+	if (uv_rtc_unset_timer(cpu, 0) != 1)
 		return;
 
 	ced->event_handler(ced);
 }
 
-static int __init uv_enable_rtc(char *str)
+static int __init uv_enable_evt_rtc(char *str)
 {
-	uv_rtc_enable = 1;
+	uv_rtc_evt_enable = 1;
 
 	return 1;
 }
-__setup("uvrtc", uv_enable_rtc);
+__setup("uvrtcevt", uv_enable_evt_rtc);
 
 static __init void uv_rtc_register_clockevents(struct work_struct *dummy)
 {
@@ -350,27 +355,32 @@ static __init int uv_rtc_setup_clock(void)
 {
 	int rc;
 
-	if (!uv_rtc_enable || !is_uv_system() || generic_interrupt_extension)
+	if (!is_uv_system())
 		return -ENODEV;
 
-	generic_interrupt_extension = uv_rtc_interrupt;
-
 	clocksource_uv.mult = clocksource_hz2mult(sn_rtc_cycles_per_second,
 				clocksource_uv.shift);
 
+	/* If single blade, prefer tsc */
+	if (uv_num_possible_blades() == 1)
+		clocksource_uv.rating = 250;
+
 	rc = clocksource_register(&clocksource_uv);
-	if (rc) {
-		generic_interrupt_extension = NULL;
+	if (rc)
+		printk(KERN_INFO "UV RTC clocksource failed rc %d\n", rc);
+	else
+		printk(KERN_INFO "UV RTC clocksource registered freq %lu MHz\n",
+			sn_rtc_cycles_per_second/(unsigned long)1E6);
+
+	if (rc || !uv_rtc_evt_enable || x86_platform_ipi_callback)
 		return rc;
-	}
 
 	/* Setup and register clockevents */
 	rc = uv_rtc_allocate_timers();
-	if (rc) {
-		clocksource_unregister(&clocksource_uv);
-		generic_interrupt_extension = NULL;
-		return rc;
-	}
+	if (rc)
+		goto error;
+
+	x86_platform_ipi_callback = uv_rtc_interrupt;
 
 	clock_event_device_uv.mult = div_sc(sn_rtc_cycles_per_second,
 				NSEC_PER_SEC, clock_event_device_uv.shift);
@@ -383,11 +393,19 @@ static __init int uv_rtc_setup_clock(void)
 
 	rc = schedule_on_each_cpu(uv_rtc_register_clockevents);
 	if (rc) {
-		clocksource_unregister(&clocksource_uv);
-		generic_interrupt_extension = NULL;
+		x86_platform_ipi_callback = NULL;
 		uv_rtc_deallocate_timers();
+		goto error;
 	}
 
+	printk(KERN_INFO "UV RTC clockevents registered\n");
+
+	return 0;
+
+error:
+	clocksource_unregister(&clocksource_uv);
+	printk(KERN_INFO "UV RTC clockevents failed rc %d\n", rc);
+
 	return rc;
 }
 arch_initcall(uv_rtc_setup_clock);
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index abda6f53e71..34a279a7471 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -197,7 +197,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 	apic_version[m->apicid] = ver;
 }
 
-static void __init visws_find_smp_config(unsigned int reserve)
+static void __init visws_find_smp_config(void)
 {
 	struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS);
 	unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS));
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index 611b9e2360d..74c92bb194d 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -226,7 +226,7 @@ static void __devinit vmi_time_init_clockevent(void)
 	evt->min_delta_ns = clockevent_delta2ns(1, evt);
 	evt->cpumask = cpumask_of(cpu);
 
-	printk(KERN_WARNING "vmi: registering clock event %s. mult=%lu shift=%u\n",
+	printk(KERN_WARNING "vmi: registering clock event %s. mult=%u shift=%u\n",
 	       evt->name, evt->mult, evt->shift);
 	clockevents_register_device(evt);
 }
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3c68fe2d46c..f3f2104408d 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -41,6 +41,32 @@ ENTRY(phys_startup_64)
 jiffies_64 = jiffies;
 #endif
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+/*
+ * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA
+ * we retain large page mappings for boundaries spanning kernel text, rodata
+ * and data sections.
+ *
+ * However, kernel identity mappings will have different RWX permissions
+ * to the pages mapping to text and to the pages padding (which are freed) the
+ * text section. Hence kernel identity mappings will be broken to smaller
+ * pages. For 64-bit, kernel text and kernel identity mappings are different,
+ * so we can enable protection checks that come with CONFIG_DEBUG_RODATA,
+ * as well as retain 2MB large page mappings for kernel text.
+ */
+#define X64_ALIGN_DEBUG_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
+
+#define X64_ALIGN_DEBUG_RODATA_END				\
+		. = ALIGN(HPAGE_SIZE);				\
+		__end_rodata_hpage_align = .;
+
+#else
+
+#define X64_ALIGN_DEBUG_RODATA_BEGIN
+#define X64_ALIGN_DEBUG_RODATA_END
+
+#endif
+
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(7);          /* RWE */
@@ -90,7 +116,9 @@ SECTIONS
 
 	EXCEPTION_TABLE(16) :text = 0x9090
 
+	X64_ALIGN_DEBUG_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
+	X64_ALIGN_DEBUG_RODATA_END
 
 	/* Data */
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
@@ -107,13 +135,13 @@ SECTIONS
 
 		PAGE_ALIGNED_DATA(PAGE_SIZE)
 
-		CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES)
+		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 
 		DATA_DATA
 		CONSTRUCTORS
 
 		/* rarely changed data like cpu maps */
-		READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES)
+		READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES)
 
 		/* End of data section */
 		_edata = .;
@@ -137,12 +165,12 @@ SECTIONS
 		*(.vsyscall_0)
 	} :user
 
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	. = ALIGN(L1_CACHE_BYTES);
 	.vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
 		*(.vsyscall_fn)
 	}
 
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	. = ALIGN(L1_CACHE_BYTES);
 	.vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
 		*(.vsyscall_gtod_data)
 	}
@@ -166,7 +194,7 @@ SECTIONS
 	}
 	vgetcpu_mode = VVIRT(.vgetcpu_mode);
 
-	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
+	. = ALIGN(L1_CACHE_BYTES);
 	.jiffies : AT(VLOAD(.jiffies)) {
 		*(.jiffies)
 	}
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 8cb4974ff59..9055e5872ff 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -73,7 +73,8 @@ void update_vsyscall_tz(void)
 	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 
-void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
+void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
+		     u32 mult)
 {
 	unsigned long flags;
 
@@ -82,7 +83,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
 	vsyscall_gtod_data.clock.vread = clock->vread;
 	vsyscall_gtod_data.clock.cycle_last = clock->cycle_last;
 	vsyscall_gtod_data.clock.mask = clock->mask;
-	vsyscall_gtod_data.clock.mult = clock->mult;
+	vsyscall_gtod_data.clock.mult = mult;
 	vsyscall_gtod_data.clock.shift = clock->shift;
 	vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
 	vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
@@ -237,7 +238,7 @@ static ctl_table kernel_table2[] = {
 };
 
 static ctl_table kernel_root_table2[] = {
-	{ .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555,
+	{ .procname = "kernel", .mode = 0555,
 	  .child = kernel_table2 },
 	{}
 };
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index d11c5ff7c65..ccd179dec36 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -13,6 +13,7 @@
 #include <asm/e820.h>
 #include <asm/time.h>
 #include <asm/irq.h>
+#include <asm/pat.h>
 #include <asm/tsc.h>
 #include <asm/iommu.h>
 
@@ -80,4 +81,5 @@ struct x86_platform_ops x86_platform = {
 	.get_wallclock			= mach_get_cmos_time,
 	.set_wallclock			= mach_set_rtc_mmss,
 	.iommu_shutdown			= iommu_shutdown_noop,
+	.is_untracked_pat_range		= is_ISA_range,
 };