Merge commit 'v2.6.30-rc5' into x86/mm

Merge reason: this branch was on a .30-rc2 base - sync it up with
              all the latest fixes.

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

46 files changed, 213 insertions, 110 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c9086e6307a5..df9e885eee14 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -277,6 +277,7 @@ config SPARSE_IRQ
 config NUMA_MIGRATE_IRQ_DESC
 	bool "Move irq desc when changing irq smp_affinity"
 	depends on SPARSE_IRQ && NUMA
+	depends on BROKEN
 	default n
 	---help---
 	  This enables moving irq_desc to cpu/node that irq will use handled.
@@ -664,6 +665,7 @@ config MAXSMP
 
 config NR_CPUS
 	int "Maximum number of CPUs" if SMP && !MAXSMP
+	range 2 8 if SMP && X86_32 && !X86_BIGSMP
 	range 2 512 if SMP && !MAXSMP
 	default "1" if !SMP
 	default "4096" if MAXSMP
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index f05d8c91d9e5..8c86b72afdc2 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -153,7 +153,7 @@ endif
 
 boot := arch/x86/boot
 
-BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage install
+BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage
 
 PHONY += bzImage $(BOOT_TARGETS)
 
@@ -171,6 +171,10 @@ bzImage: vmlinux
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
+PHONY += install
+install:
+	$(Q)$(MAKE) $(build)=$(boot) $@
+
 PHONY += vdso_install
 vdso_install:
 	$(Q)$(MAKE) $(build)=arch/x86/vdso $@
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index efac92fd1efb..085a8c35f149 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -129,21 +129,12 @@ asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename,
 			      struct stat64 __user *statbuf, int flag)
 {
 	struct kstat stat;
-	int error = -EINVAL;
+	int error;
 
-	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
-		goto out;
-
-	if (flag & AT_SYMLINK_NOFOLLOW)
-		error = vfs_lstat_fd(dfd, filename, &stat);
-	else
-		error = vfs_stat_fd(dfd, filename, &stat);
-
-	if (!error)
-		error = cp_stat64(statbuf, &stat);
-
-out:
-	return error;
+	error = vfs_fstatat(dfd, filename, &stat, flag);
+	if (error)
+		return error;
+	return cp_stat64(statbuf, &stat);
 }
 
 /*
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 5623c50d67b2..c45f415ce315 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -37,7 +37,7 @@ extern gate_desc idt_table[];
 struct gdt_page {
 	struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU(struct gdt_page, gdt_page);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 {
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 039db6aa8e02..37555e52f980 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -26,7 +26,7 @@ typedef struct {
 #endif
 } ____cacheline_aligned irq_cpustat_t;
 
-DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+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
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 563933e06a35..4f8c199584e7 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -137,6 +137,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
 enum mcp_flags {
 	MCP_TIMESTAMP = (1 << 0),	/* log time stamp */
 	MCP_UC = (1 << 1),		/* log uncorrected errors */
+	MCP_DONTLOG = (1 << 2),		/* only clear, don't log */
 };
 extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index fcf4d92e7e04..c2cceae709c8 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -138,7 +138,7 @@ extern struct tss_struct	doublefault_tss;
 extern __u32			cleared_cpu_caps[NCAPINTS];
 
 #ifdef CONFIG_SMP
-DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
 #define cpu_data(cpu)		per_cpu(cpu_info, cpu)
 #define current_cpu_data	__get_cpu_var(cpu_info)
 #else
@@ -270,7 +270,7 @@ struct tss_struct {
 
 } ____cacheline_aligned;
 
-DECLARE_PER_CPU(struct tss_struct, init_tss);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss);
 
 /*
  * Save the original ist values for checking stack pointers during debugging
@@ -393,7 +393,7 @@ union irq_stack_union {
 	};
 };
 
-DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union);
 DECLARE_INIT_PER_CPU(irq_stack_union);
 
 DECLARE_PER_CPU(char *, irq_stack_ptr);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index d3539f998f88..16a5c84b0329 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -152,7 +152,7 @@ struct tlb_state {
 	struct mm_struct *active_mm;
 	int state;
 };
-DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 
 static inline void reset_lazy_tlbstate(void)
 {
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 892b119dba6f..f44b49abca49 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -200,7 +200,7 @@ static inline void arch_fix_phys_package_id(int num, u32 slot)
 }
 
 struct pci_bus;
-void set_pci_bus_resources_arch_default(struct pci_bus *b);
+void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
 #define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 42c33cebf00f..8c0be0902dac 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -49,10 +49,10 @@
 #define IVHD_DEV_EXT_SELECT             0x46
 #define IVHD_DEV_EXT_SELECT_RANGE       0x47
 
-#define IVHD_FLAG_HT_TUN_EN             0x00
-#define IVHD_FLAG_PASSPW_EN             0x01
-#define IVHD_FLAG_RESPASSPW_EN          0x02
-#define IVHD_FLAG_ISOC_EN               0x03
+#define IVHD_FLAG_HT_TUN_EN_MASK        0x01
+#define IVHD_FLAG_PASSPW_EN_MASK        0x02
+#define IVHD_FLAG_RESPASSPW_EN_MASK     0x04
+#define IVHD_FLAG_ISOC_EN_MASK          0x08
 
 #define IVMD_FLAG_EXCL_RANGE            0x08
 #define IVMD_FLAG_UNITY_MAP             0x01
@@ -569,19 +569,19 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	 * First set the recommended feature enable bits from ACPI
 	 * into the IOMMU control registers
 	 */
-	h->flags & IVHD_FLAG_HT_TUN_EN ?
+	h->flags & IVHD_FLAG_HT_TUN_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
 		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
 
-	h->flags & IVHD_FLAG_PASSPW_EN ?
+	h->flags & IVHD_FLAG_PASSPW_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
 		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
 
-	h->flags & IVHD_FLAG_RESPASSPW_EN ?
+	h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
 		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
 
-	h->flags & IVHD_FLAG_ISOC_EN ?
+	h->flags & IVHD_FLAG_ISOC_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
 		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index a2789e42e162..30da617d18e4 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3670,12 +3670,14 @@ int arch_setup_hpet_msi(unsigned int irq)
 {
 	int ret;
 	struct msi_msg msg;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	ret = msi_compose_msg(NULL, irq, &msg);
 	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");
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index d6bd62407152..ce4fbfa315a1 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -138,7 +138,7 @@ int __init check_nmi_watchdog(void)
 	if (!prev_nmi_count)
 		goto error;
 
-	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL);
+	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL|__GFP_ZERO);
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
 #ifdef CONFIG_SMP
@@ -414,7 +414,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		touched = 1;
 	}
 
-	if (cpumask_test_cpu(cpu, backtrace_mask)) {
+	/* We can be called before check_nmi_watchdog, hence NULL check. */
+	if (backtrace_mask != NULL && cpumask_test_cpu(cpu, backtrace_mask)) {
 		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
 
 		spin_lock(&lock);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index de1a50af807b..2bda69352976 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -19,6 +19,7 @@
 #include <linux/timer.h>
 #include <linux/cpu.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -34,6 +35,17 @@ DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type uv_system_type;
 
+static int early_get_nodeid(void)
+{
+	union uvh_node_id_u node_id;
+	unsigned long *mmr;
+
+	mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
+	node_id.v = *mmr;
+	early_iounmap(mmr, sizeof(*mmr));
+	return node_id.s.node_id;
+}
+
 static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strcmp(oem_id, "SGI")) {
@@ -42,6 +54,8 @@ static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 		else if (!strcmp(oem_table_id, "UVX"))
 			uv_system_type = UV_X2APIC;
 		else if (!strcmp(oem_table_id, "UVH")) {
+			__get_cpu_var(x2apic_extra_bits) =
+				early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1);
 			uv_system_type = UV_NON_UNIQUE_APIC;
 			return 1;
 		}
@@ -638,6 +652,7 @@ void __init uv_system_init(void)
 		if (uv_node_to_blade[nid] >= 0)
 			continue;
 		paddr = node_start_pfn(nid) << PAGE_SHIFT;
+		paddr = uv_soc_phys_ram_to_gpa(paddr);
 		pnode = (paddr >> m_val) & pnode_mask;
 		blade = boot_pnode_to_blade(pnode);
 		uv_node_to_blade[nid] = blade;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c4f667896c28..c1caefc82e62 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1203,6 +1203,8 @@ void __cpuinit cpu_init(void)
 	load_TR_desc();
 	load_LDT(&init_mm.context);
 
+	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+
 #ifdef CONFIG_DOUBLEFAULT
 	/* Set up doublefault TSS pointer in the GDT */
 	__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index ecdb682ab516..208ecf6643df 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -65,14 +65,18 @@ enum {
 struct acpi_cpufreq_data {
 	struct acpi_processor_performance *acpi_data;
 	struct cpufreq_frequency_table *freq_table;
-	unsigned int max_freq;
 	unsigned int resume;
 	unsigned int cpu_feature;
-	u64 saved_aperf, saved_mperf;
 };
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
+struct acpi_msr_data {
+	u64 saved_aperf, saved_mperf;
+};
+
+static DEFINE_PER_CPU(struct acpi_msr_data, msr_data);
+
 DEFINE_TRACE(power_mark);
 
 /* acpi_perf_data is a pointer to percpu data. */
@@ -287,11 +291,11 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 		return 0;
 
 	cur.aperf.whole = readin.aperf.whole -
-				per_cpu(drv_data, cpu)->saved_aperf;
+				per_cpu(msr_data, cpu).saved_aperf;
 	cur.mperf.whole = readin.mperf.whole -
-				per_cpu(drv_data, cpu)->saved_mperf;
-	per_cpu(drv_data, cpu)->saved_aperf = readin.aperf.whole;
-	per_cpu(drv_data, cpu)->saved_mperf = readin.mperf.whole;
+				per_cpu(msr_data, cpu).saved_mperf;
+	per_cpu(msr_data, cpu).saved_aperf = readin.aperf.whole;
+	per_cpu(msr_data, cpu).saved_mperf = readin.mperf.whole;
 
 #ifdef __i386__
 	/*
@@ -335,7 +339,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 
 #endif
 
-	retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100;
+	retval = (policy->cpuinfo.max_freq * perf_percent) / 100;
 
 	return retval;
 }
@@ -688,16 +692,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	/* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
 	if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
 	    policy->cpuinfo.transition_latency > 20 * 1000) {
-		static int print_once;
 		policy->cpuinfo.transition_latency = 20 * 1000;
-		if (!print_once) {
-			print_once = 1;
-			printk(KERN_INFO "Capping off P-state tranision latency"
-				" at 20 uS\n");
-		}
+			printk_once(KERN_INFO "Capping off P-state tranision"
+				    " latency at 20 uS\n");
 	}
 
-	data->max_freq = perf->states[0].core_frequency * 1000;
 	/* table init */
 	for (i = 0; i < perf->state_count; i++) {
 		if (i > 0 && perf->states[i].core_frequency >=
@@ -716,6 +715,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (result)
 		goto err_freqfree;
 
+	if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
+		printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
+
 	switch (perf->control_register.space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_IO:
 		/* Current speed is unknown and not detectable by IO port */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 863f89568b1a..6fb0b359d2a5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -239,9 +239,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		 * Don't get the IP here because it's unlikely to
 		 * have anything to do with the actual error location.
 		 */
-
-		mce_log(&m);
-		add_taint(TAINT_MACHINE_CHECK);
+		if (!(flags & MCP_DONTLOG)) {
+			mce_log(&m);
+			add_taint(TAINT_MACHINE_CHECK);
+		}
 
 		/*
 		 * Clear state for this bank.
@@ -452,13 +453,14 @@ void mce_log_therm_throt_event(__u64 status)
  */
 
 static int check_interval = 5 * 60; /* 5 minutes */
-static int next_interval; /* in jiffies */
+static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
 static void mcheck_timer(unsigned long);
 static DEFINE_PER_CPU(struct timer_list, mce_timer);
 
 static void mcheck_timer(unsigned long data)
 {
 	struct timer_list *t = &per_cpu(mce_timer, data);
+	int *n;
 
 	WARN_ON(smp_processor_id() != data);
 
@@ -470,14 +472,14 @@ static void mcheck_timer(unsigned long data)
 	 * Alert userspace if needed.  If we logged an MCE, reduce the
 	 * polling interval, otherwise increase the polling interval.
 	 */
+	n = &__get_cpu_var(next_interval);
 	if (mce_notify_user()) {
-		next_interval = max(next_interval/2, HZ/100);
+		*n = max(*n/2, HZ/100);
 	} else {
-		next_interval = min(next_interval * 2,
-				(int)round_jiffies_relative(check_interval*HZ));
+		*n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
 	}
 
-	t->expires = jiffies + next_interval;
+	t->expires = jiffies + *n;
 	add_timer(t);
 }
 
@@ -584,7 +586,7 @@ static void mce_init(void *dummy)
 	 * Log the machine checks left over from the previous reset.
 	 */
 	bitmap_fill(all_banks, MAX_NR_BANKS);
-	machine_check_poll(MCP_UC, &all_banks);
+	machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks);
 
 	set_in_cr4(X86_CR4_MCE);
 
@@ -632,14 +634,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
 static void mce_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
+	int *n = &__get_cpu_var(next_interval);
 
-	/* data race harmless because everyone sets to the same value */
-	if (!next_interval)
-		next_interval = check_interval * HZ;
-	if (!next_interval)
+	*n = check_interval * HZ;
+	if (!*n)
 		return;
 	setup_timer(t, mcheck_timer, smp_processor_id());
-	t->expires = round_jiffies(jiffies + next_interval);
+	t->expires = round_jiffies(jiffies + *n);
 	add_timer(t);
 }
 
@@ -907,7 +908,6 @@ static void mce_cpu_restart(void *data)
 /* Reinit MCEs after user configuration changes */
 static void mce_restart(void)
 {
-	next_interval = check_interval * HZ;
 	on_each_cpu(mce_cpu_restart, NULL, 1);
 }
 
@@ -1110,7 +1110,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		t->expires = round_jiffies(jiffies + next_interval);
+		t->expires = round_jiffies(jiffies +
+						__get_cpu_var(next_interval));
 		add_timer_on(t, cpu);
 		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
 		break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index d6b72df89d69..cef3ee30744b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -151,10 +151,11 @@ static void print_update(char *type, int *hdr, int num)
 static void cmci_discover(int banks, int boot)
 {
 	unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+	unsigned long flags;
 	int hdr = 0;
 	int i;
 
-	spin_lock(&cmci_discover_lock);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++) {
 		u64 val;
 
@@ -184,7 +185,7 @@ static void cmci_discover(int banks, int boot)
 			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
 		}
 	}
-	spin_unlock(&cmci_discover_lock);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 	if (hdr)
 		printk(KERN_CONT "\n");
 }
@@ -211,13 +212,14 @@ void cmci_recheck(void)
  */
 void cmci_clear(void)
 {
+	unsigned long flags;
 	int i;
 	int banks;
 	u64 val;
 
 	if (!cmci_supported(&banks))
 		return;
-	spin_lock(&cmci_discover_lock);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++) {
 		if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
 			continue;
@@ -227,7 +229,7 @@ void cmci_clear(void)
 		wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
 		__clear_bit(i, __get_cpu_var(mce_banks_owned));
 	}
-	spin_unlock(&cmci_discover_lock);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index f93047fed791..d5e30397246b 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpumask_weight(cpu_sibling_mask(cpu)));
+			   cpumask_weight(cpu_core_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index ef2c3563357d..006281302925 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1074,12 +1074,13 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	u64 addr;
 	u64 start;
 
-	start = startt;
-	while (size < sizet && (start + 1))
+	for (start = startt; ; start += size) {
 		start = find_e820_area_size(start, &size, align);
-
-	if (size < sizet)
-		return 0;
+		if (!(start + 1))
+			return 0;
+		if (size >= sizet)
+			break;
+	}
 
 #ifdef CONFIG_X86_32
 	if (start >= MAXMEM)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a331ec38af9e..38946c6e8433 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1410,7 +1410,10 @@ ENTRY(paranoid_exit)
 paranoid_swapgs:
 	TRACE_IRQS_IRETQ 0
 	SWAPGS_UNSAFE_STACK
+	RESTORE_ALL 8
+	jmp irq_return
 paranoid_restore:
+	TRACE_IRQS_IRETQ 0
 	RESTORE_ALL 8
 	jmp irq_return
 paranoid_userspace:
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 648b3a2a3a44..81408b93f887 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -236,6 +236,10 @@ static void hpet_stop_counter(void)
 	unsigned long cfg = hpet_readl(HPET_CFG);
 	cfg &= ~HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
+}
+
+static void hpet_reset_counter(void)
+{
 	hpet_writel(0, HPET_COUNTER);
 	hpet_writel(0, HPET_COUNTER + 4);
 }
@@ -250,6 +254,7 @@ static void hpet_start_counter(void)
 static void hpet_restart_counter(void)
 {
 	hpet_stop_counter();
+	hpet_reset_counter();
 	hpet_start_counter();
 }
 
@@ -309,7 +314,7 @@ 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;
+	unsigned long cfg, cmp, now;
 	uint64_t delta;
 
 	switch (mode) {
@@ -317,12 +322,23 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		hpet_stop_counter();
 		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
 		delta >>= evt->shift;
+		now = hpet_readl(HPET_COUNTER);
+		cmp = now + (unsigned long) delta;
 		cfg = hpet_readl(HPET_Tn_CFG(timer));
 		/* Make sure we use edge triggered interrupts */
 		cfg &= ~HPET_TN_LEVEL;
 		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
 		       HPET_TN_SETVAL | HPET_TN_32BIT;
 		hpet_writel(cfg, HPET_Tn_CFG(timer));
+		hpet_writel(cmp, HPET_Tn_CMP(timer));
+		udelay(1);
+		/*
+		 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
+		 * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
+		 * bit is automatically cleared after the first write.
+		 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
+		 * Publication # 24674)
+		 */
 		hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer));
 		hpet_start_counter();
 		hpet_print_config();
@@ -722,7 +738,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 /*
  * Clock source related code
  */
-static cycle_t read_hpet(void)
+static cycle_t read_hpet(struct clocksource *cs)
 {
 	return (cycle_t)hpet_readl(HPET_COUNTER);
 }
@@ -756,7 +772,7 @@ static int hpet_clocksource_register(void)
 	hpet_restart_counter();
 
 	/* Verify whether hpet counter works */
-	t1 = read_hpet();
+	t1 = hpet_readl(HPET_COUNTER);
 	rdtscll(start);
 
 	/*
@@ -770,7 +786,7 @@ static int hpet_clocksource_register(void)
 		rdtscll(now);
 	} while ((now - start) < 200000UL);
 
-	if (t1 == read_hpet()) {
+	if (t1 == hpet_readl(HPET_COUNTER)) {
 		printk(KERN_WARNING
 		       "HPET counter not counting. HPET disabled\n");
 		return -ENODEV;
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 3475440baa54..c2e0bb0890d4 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -129,7 +129,7 @@ void __init setup_pit_timer(void)
  * to just read by itself. So use jiffies to emulate a free
  * running counter:
  */
-static cycle_t pit_read(void)
+static cycle_t pit_read(struct clocksource *cs)
 {
 	static int old_count;
 	static u32 old_jifs;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 137f2e8132df..223af43f1526 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -77,6 +77,11 @@ static cycle_t kvm_clock_read(void)
 	return ret;
 }
 
+static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
+{
+	return kvm_clock_read();
+}
+
 /*
  * If we don't do that, there is the possibility that the guest
  * will calibrate under heavy load - thus, getting a lower lpj -
@@ -107,7 +112,7 @@ static void kvm_get_preset_lpj(void)
 
 static struct clocksource kvm_clock = {
 	.name = "kvm-clock",
-	.read = kvm_clock_read,
+	.read = kvm_clock_get_cycles,
 	.rating = 400,
 	.mask = CLOCKSOURCE_MASK(64),
 	.mult = 1 << KVM_SCALE,
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index e7368c1da01d..c1c429d00130 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -194,7 +194,7 @@ void machine_kexec(struct kimage *image)
 				       unsigned int preserve_context);
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		save_processor_state();
 #endif
 
@@ -253,7 +253,7 @@ void machine_kexec(struct kimage *image)
 					   image->preserve_context);
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		restore_processor_state();
 #endif
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 89cea4d44679..84c3bf209e98 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -274,7 +274,7 @@ void machine_kexec(struct kimage *image)
 	int save_ftrace_enabled;
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		save_processor_state();
 #endif
 
@@ -333,7 +333,7 @@ void machine_kexec(struct kimage *image)
 				       image->preserve_context);
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		restore_processor_state();
 #endif
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index e95022e4f5d5..7563b31b4f03 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -261,8 +261,6 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev)
 {
 	if (hpet_force_user)
 		old_ich_force_enable_hpet(dev);
-	else
-		hpet_print_force_info();
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 7a567ebe6361..d57de05dc430 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -699,7 +699,7 @@ static struct clocksource clocksource_tsc;
  * code, which is necessary to support wrapping clocksources like pm
  * timer.
  */
-static cycle_t read_tsc(void)
+static cycle_t read_tsc(struct clocksource *cs)
 {
 	cycle_t ret = (cycle_t)get_cycles();
 
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 2ffb6c53326e..583f11d5c480 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -29,7 +29,7 @@
 
 #define RTC_NAME		"sgi_rtc"
 
-static cycle_t uv_read_rtc(void);
+static cycle_t uv_read_rtc(struct clocksource *cs);
 static int uv_rtc_next_event(unsigned long, struct clock_event_device *);
 static void uv_rtc_timer_setup(enum clock_event_mode,
 				struct clock_event_device *);
@@ -123,7 +123,7 @@ 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() && !uv_intr_pending(pnode));
+	return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode));
 }
 
 /*
@@ -256,7 +256,7 @@ static int uv_rtc_unset_timer(int cpu)
 
 	spin_lock_irqsave(&head->lock, flags);
 
-	if (head->next_cpu == bcpu && uv_read_rtc() >= *t)
+	if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t)
 		rc = 1;
 
 	*t = ULLONG_MAX;
@@ -278,7 +278,7 @@ static int uv_rtc_unset_timer(int cpu)
 /*
  * Read the RTC.
  */
-static cycle_t uv_read_rtc(void)
+static cycle_t uv_read_rtc(struct clocksource *cs)
 {
 	return (cycle_t)uv_read_local_mmr(UVH_RTC);
 }
@@ -291,7 +291,7 @@ static int uv_rtc_next_event(unsigned long delta,
 {
 	int ced_cpu = cpumask_first(ced->cpumask);
 
-	return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc());
+	return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc(NULL));
 }
 
 /*
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index d303369a7bad..2b3eb82efeeb 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -283,7 +283,7 @@ void __devinit vmi_time_ap_init(void)
 /** vmi clocksource */
 static struct clocksource clocksource_vmi;
 
-static cycle_t read_real_cycles(void)
+static cycle_t read_real_cycles(struct clocksource *cs)
 {
 	cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
 	return max(ret, clocksource_vmi.cycle_last);
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 0a5b04aa98f1..c5ee17e8c6d9 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -89,7 +89,7 @@ int save_i387_xstate(void __user *buf)
 
 	if (!used_math())
 		return 0;
-	clear_used_math(); /* trigger finit */
+
 	if (task_thread_info(tsk)->status & TS_USEDFPU) {
 		/*
 	 	 * Start with clearing the user buffer. This will present a
@@ -114,6 +114,8 @@ int save_i387_xstate(void __user *buf)
 			return -1;
 	}
 
+	clear_used_math(); /* trigger finit */
+
 	if (task_thread_info(tsk)->status & TS_XSAVE) {
 		struct _fpstate __user *fx = buf;
 		struct _xstate __user *x = buf;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2a36f7f7c4c7..b6caf1329b1b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1248,7 +1248,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
 	sp->gfn = gfn;
 	sp->role = role;
-	sp->global = role.cr4_pge;
+	sp->global = 0;
 	hlist_add_head(&sp->hash_link, bucket);
 	if (!direct) {
 		if (rmap_write_protect(vcpu->kvm, gfn))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8ca100a9ecac..7c1ce5ac6131 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2775,6 +2775,9 @@ out:
 
 void kvm_arch_exit(void)
 {
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
+					    CPUFREQ_TRANSITION_NOTIFIER);
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
 }
@@ -4159,6 +4162,11 @@ EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.time_page) {
+		kvm_release_page_dirty(vcpu->arch.time_page);
+		vcpu->arch.time_page = NULL;
+	}
+
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index a2085368a3dc..ca7ec44bafc3 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -663,7 +663,7 @@ static unsigned long lguest_tsc_khz(void)
 
 /* If we can't use the TSC, the kernel falls back to our lower-priority
  * "lguest_clock", where we read the time value given to us by the Host. */
-static cycle_t lguest_clock_read(void)
+static cycle_t lguest_clock_read(struct clocksource *cs)
 {
 	unsigned long sec, nsec;
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 4d67c33a2e16..95f5ecf2be50 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -7,6 +7,7 @@
 #include <asm/page.h>
 #include <asm/page_types.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
@@ -366,8 +367,23 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 #endif
 
 #ifdef CONFIG_X86_64
-	if (!after_bootmem)
+	if (!after_bootmem && !start) {
+		pud_t *pud;
+		pmd_t *pmd;
+
 		mmu_cr4_features = read_cr4();
+
+		/*
+		 * _brk_end cannot change anymore, but it and _end may be
+		 * located on different 2M pages. cleanup_highmap(), however,
+		 * can only consider _end when it runs, so destroy any
+		 * mappings beyond _brk_end here.
+		 */
+		pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
+		pmd = pmd_offset(pud, _brk_end - 1);
+		while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
+			pmd_clear(pmd);
+	}
 #endif
 	__flush_tlb_all();
 
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 4f115e00486b..50dc802a1c46 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -87,7 +87,7 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 {
 	struct kmmio_probe *p;
 	list_for_each_entry_rcu(p, &kmmio_probes, list) {
-		if (addr >= p->addr && addr <= (p->addr + p->len))
+		if (addr >= p->addr && addr < (p->addr + p->len))
 			return p;
 	}
 	return NULL;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 3daefa04ace5..d2530062fe00 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -257,7 +257,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 }
 #endif
 
-static unsigned long calculate_numa_remap_pages(void)
+static __init unsigned long calculate_numa_remap_pages(void)
 {
 	int nid;
 	unsigned long size, reserve_pages = 0;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index d73aaa892371..2d05a12029dc 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -188,6 +188,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
 
+	if (!end)
+		return;
+
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 16ae70fc57e7..29a0e37114f8 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -216,7 +216,7 @@ int __init get_memcfg_from_srat(void)
 
 	if (num_memory_chunks == 0) {
 		printk(KERN_WARNING
-			 "could not finy any ACPI SRAT memory areas.\n");
+			 "could not find any ACPI SRAT memory areas.\n");
 		goto out_fail;
 	}
 
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index c7d272b8574c..01765955baaf 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -28,6 +28,7 @@ int acpi_numa __initdata;
 static struct acpi_table_slit *acpi_slit;
 
 static nodemask_t nodes_parsed __initdata;
+static nodemask_t cpu_nodes_parsed __initdata;
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
 static struct bootnode nodes_add[MAX_NUMNODES];
 static int found_add_area __initdata;
@@ -141,6 +142,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 
 	apic_id = pa->apic_id;
 	apicid_to_node[apic_id] = node;
+	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
 	       pxm, apic_id, node);
@@ -174,6 +176,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	else
 		apic_id = pa->apic_id;
 	apicid_to_node[apic_id] = node;
+	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
 	       pxm, apic_id, node);
@@ -358,6 +361,7 @@ static void __init unparse_node(int node)
 {
 	int i;
 	node_clear(node, nodes_parsed);
+	node_clear(node, cpu_nodes_parsed);
 	for (i = 0; i < MAX_LOCAL_APIC; i++) {
 		if (apicid_to_node[i] == node)
 			apicid_to_node[i] = NUMA_NO_NODE;
@@ -402,7 +406,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 	}
 
-	node_possible_map = nodes_parsed;
+	/* Account for nodes with cpus and no memory */
+	nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed);
 
 	/* Finally register nodes */
 	for_each_node_mask(i, node_possible_map)
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 9bb09823b362..f893d6a6e803 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -94,12 +94,16 @@ struct pci_root_info {
 static int pci_root_num;
 static struct pci_root_info pci_root_info[PCI_ROOT_NR];
 
-void set_pci_bus_resources_arch_default(struct pci_bus *b)
+void x86_pci_root_bus_res_quirks(struct pci_bus *b)
 {
 	int i;
 	int j;
 	struct pci_root_info *info;
 
+	/* don't go for it if _CRS is used */
+	if (pci_probe & PCI_USE__CRS)
+		return;
+
 	/* if only one root bus, don't need to anything */
 	if (pci_root_num < 2)
 		return;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 8c362b96b644..2202b6257b82 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -147,10 +147,13 @@ static void __devinit pcibios_fixup_device_resources(struct pci_dev *dev)
  *  are examined.
  */
 
-void __devinit  pcibios_fixup_bus(struct pci_bus *b)
+void __devinit pcibios_fixup_bus(struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
+	/* root bus? */
+	if (!b->parent)
+		x86_pci_root_bus_res_quirks(b);
 	pci_read_bridge_bases(b);
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index f1817f71e009..a85bef20a3b9 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -238,6 +238,10 @@ void __init pcibios_resource_survey(void)
  */
 fs_initcall(pcibios_assign_resources);
 
+void __weak x86_pci_root_bus_res_quirks(struct pci_bus *b)
+{
+}
+
 /*
  *  If we set up a device for bus mastering, we need to check the latency
  *  timer as certain crappy BIOSes forget to set it properly.
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 905bb526b133..5fa10bb9604f 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -375,7 +375,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
 		if (!fixmem32)
 			return AE_OK;
 		if ((mcfg_res->start >= fixmem32->address) &&
-		    (mcfg_res->end < (fixmem32->address +
+		    (mcfg_res->end <= (fixmem32->address +
 				      fixmem32->address_length))) {
 			mcfg_res->flags = 1;
 			return AE_CTRL_TERMINATE;
@@ -392,7 +392,7 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res,
 		return AE_OK;
 
 	if ((mcfg_res->start >= address.minimum) &&
-	    (mcfg_res->end < (address.minimum + address.address_length))) {
+	    (mcfg_res->end <= (address.minimum + address.address_length))) {
 		mcfg_res->flags = 1;
 		return AE_CTRL_TERMINATE;
 	}
@@ -439,7 +439,7 @@ static int __init is_mmconf_reserved(check_reserved_t is_reserved,
 	u64 old_size = size;
 	int valid = 0;
 
-	while (!is_reserved(addr, addr + size - 1, E820_RESERVED)) {
+	while (!is_reserved(addr, addr + size, E820_RESERVED)) {
 		size >>= 1;
 		if (size < (16UL<<20))
 			break;
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index d9d35824c56f..6a40b78b46aa 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -104,11 +104,13 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
 	if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
-		BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
-			     offsetof(struct timespec, tv_nsec) ||
-			     sizeof(*tv) != sizeof(struct timespec));
-		do_realtime((struct timespec *)tv);
-		tv->tv_usec /= 1000;
+		if (likely(tv != NULL)) {
+			BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
+				     offsetof(struct timespec, tv_nsec) ||
+				     sizeof(*tv) != sizeof(struct timespec));
+			do_realtime((struct timespec *)tv);
+			tv->tv_usec /= 1000;
+		}
 		if (unlikely(tz != NULL)) {
 			/* Avoid memcpy. Some old compilers fail to inline it */
 			tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 9842b1212407..e25a78e1113a 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1794,6 +1794,11 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
 
+	reserve_early(__pa(xen_start_info->pt_base),
+		      __pa(xen_start_info->pt_base +
+			   xen_start_info->nr_pt_frames * PAGE_SIZE),
+		      "XEN PAGETABLES");
+
 	return swapper_pg_dir;
 }
 #endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 14f240623497..0a5aa44299a5 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -213,6 +213,11 @@ cycle_t xen_clocksource_read(void)
 	return ret;
 }
 
+static cycle_t xen_clocksource_get_cycles(struct clocksource *cs)
+{
+	return xen_clocksource_read();
+}
+
 static void xen_read_wallclock(struct timespec *ts)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -241,7 +246,7 @@ int xen_set_wallclock(unsigned long now)
 static struct clocksource xen_clocksource __read_mostly = {
 	.name = "xen",
 	.rating = 400,
-	.read = xen_clocksource_read,
+	.read = xen_clocksource_get_cycles,
 	.mask = ~0,
 	.mult = 1<<XEN_SHIFT,		/* time directly in nanoseconds */
 	.shift = XEN_SHIFT,