21 files changed, 207 insertions, 128 deletions

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 74a847835ba..69fd72aa559 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -15,7 +15,6 @@
 
 #ifdef CONFIG_X86_32
 #include <asm/pgtable.h>
-#include <asm/pgtable_32.h>
 #endif
 
 #include "realmode/wakeup.h"
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index fbbc4dadecc..0e4f24c2a74 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -189,8 +189,8 @@
  *   Intel Order Number 241704-001.  Microsoft Part Number 781-110-X01.
  *
  * [This document is available free from Intel by calling 800.628.8686 (fax
- * 916.356.6100) or 800.548.4725; or via anonymous ftp from
- * ftp://ftp.intel.com/pub/IAL/software_specs/apmv11.doc.  It is also
+ * 916.356.6100) or 800.548.4725; or from
+ * http://www.microsoft.com/whdc/archive/amp_12.mspx  It is also
  * available from Microsoft by calling 206.882.8080.]
  *
  * APM 1.2 Reference:
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index cd8da247dda..a2baafb2fe6 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -701,6 +701,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 		per_cpu(acfreq_data, policy->cpu) = NULL;
 		acpi_processor_unregister_performance(data->acpi_data,
 						      policy->cpu);
+		kfree(data->freq_table);
 		kfree(data);
 	}
 
diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
index 733093d6043..141abebc451 100644
--- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
+++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c
@@ -393,7 +393,7 @@ static struct cpufreq_driver nforce2_driver = {
  * Detects nForce2 A2 and C1 stepping
  *
  */
-static unsigned int nforce2_detect_chipset(void)
+static int nforce2_detect_chipset(void)
 {
 	nforce2_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA,
 					PCI_DEVICE_ID_NVIDIA_NFORCE2,
diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c
index fc09f142d94..d9f51367666 100644
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ b/arch/x86/kernel/cpu/cpufreq/longrun.c
@@ -35,7 +35,7 @@ static unsigned int longrun_low_freq, longrun_high_freq;
  * Reads the current LongRun policy by access to MSR_TMTA_LONGRUN_FLAGS
  * and MSR_TMTA_LONGRUN_CTRL
  */
-static void __init longrun_get_policy(struct cpufreq_policy *policy)
+static void __cpuinit longrun_get_policy(struct cpufreq_policy *policy)
 {
 	u32 msr_lo, msr_hi;
 
@@ -165,7 +165,7 @@ static unsigned int longrun_get(unsigned int cpu)
  * TMTA rules:
  * performance_pctg = (target_freq - low_freq)/(high_freq - low_freq)
  */
-static unsigned int __cpuinit longrun_determine_freqs(unsigned int *low_freq,
+static int __cpuinit longrun_determine_freqs(unsigned int *low_freq,
 						      unsigned int *high_freq)
 {
 	u32 msr_lo, msr_hi;
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 12cd823c8d0..17ad0336621 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -327,6 +327,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 	l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
 
 	l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
 static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index fe73c1844a9..ed6310183ef 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -49,7 +49,6 @@ static unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 {
 	unsigned long offset, addr = (unsigned long)from;
-	int type = in_nmi() ? KM_NMI : KM_IRQ0;
 	unsigned long size, len = 0;
 	struct page *page;
 	void *map;
@@ -63,9 +62,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 		offset = addr & (PAGE_SIZE - 1);
 		size = min(PAGE_SIZE - offset, n - len);
 
-		map = kmap_atomic(page, type);
+		map = kmap_atomic(page);
 		memcpy(to, map+offset, size);
-		kunmap_atomic(map, type);
+		kunmap_atomic(map);
 		put_page(page);
 
 		len  += size;
@@ -238,6 +237,7 @@ struct x86_pmu {
 	 * Intel DebugStore bits
 	 */
 	int		bts, pebs;
+	int		bts_active, pebs_active;
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
@@ -381,7 +381,7 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
-static int reserve_ds_buffers(void);
+static void reserve_ds_buffers(void);
 static void release_ds_buffers(void);
 
 static void hw_perf_event_destroy(struct perf_event *event)
@@ -478,7 +478,7 @@ static int x86_setup_perfctr(struct perf_event *event)
 	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
 	    (hwc->sample_period == 1)) {
 		/* BTS is not supported by this architecture. */
-		if (!x86_pmu.bts)
+		if (!x86_pmu.bts_active)
 			return -EOPNOTSUPP;
 
 		/* BTS is currently only allowed for user-mode. */
@@ -497,12 +497,13 @@ static int x86_pmu_hw_config(struct perf_event *event)
 		int precise = 0;
 
 		/* Support for constant skid */
-		if (x86_pmu.pebs)
+		if (x86_pmu.pebs_active) {
 			precise++;
 
-		/* Support for IP fixup */
-		if (x86_pmu.lbr_nr)
-			precise++;
+			/* Support for IP fixup */
+			if (x86_pmu.lbr_nr)
+				precise++;
+		}
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
@@ -544,11 +545,8 @@ static int __x86_pmu_event_init(struct perf_event *event)
 		if (atomic_read(&active_events) == 0) {
 			if (!reserve_pmc_hardware())
 				err = -EBUSY;
-			else {
-				err = reserve_ds_buffers();
-				if (err)
-					release_pmc_hardware();
-			}
+			else
+				reserve_ds_buffers();
 		}
 		if (!err)
 			atomic_inc(&active_events);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 4977f9c400e..b7dcd9f2b8a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -74,6 +74,107 @@ static void fini_debug_store_on_cpu(int cpu)
 	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
 }
 
+static int alloc_pebs_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	int node = cpu_to_node(cpu);
+	int max, thresh = 1; /* always use a single PEBS record */
+	void *buffer;
+
+	if (!x86_pmu.pebs)
+		return 0;
+
+	buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+	if (unlikely(!buffer))
+		return -ENOMEM;
+
+	max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+
+	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+	ds->pebs_index = ds->pebs_buffer_base;
+	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
+		max * x86_pmu.pebs_record_size;
+
+	ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
+		thresh * x86_pmu.pebs_record_size;
+
+	return 0;
+}
+
+static void release_pebs_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds || !x86_pmu.pebs)
+		return;
+
+	kfree((void *)(unsigned long)ds->pebs_buffer_base);
+	ds->pebs_buffer_base = 0;
+}
+
+static int alloc_bts_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	int node = cpu_to_node(cpu);
+	int max, thresh;
+	void *buffer;
+
+	if (!x86_pmu.bts)
+		return 0;
+
+	buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+	if (unlikely(!buffer))
+		return -ENOMEM;
+
+	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+	thresh = max / 16;
+
+	ds->bts_buffer_base = (u64)(unsigned long)buffer;
+	ds->bts_index = ds->bts_buffer_base;
+	ds->bts_absolute_maximum = ds->bts_buffer_base +
+		max * BTS_RECORD_SIZE;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+		thresh * BTS_RECORD_SIZE;
+
+	return 0;
+}
+
+static void release_bts_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds || !x86_pmu.bts)
+		return;
+
+	kfree((void *)(unsigned long)ds->bts_buffer_base);
+	ds->bts_buffer_base = 0;
+}
+
+static int alloc_ds_buffer(int cpu)
+{
+	int node = cpu_to_node(cpu);
+	struct debug_store *ds;
+
+	ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node);
+	if (unlikely(!ds))
+		return -ENOMEM;
+
+	per_cpu(cpu_hw_events, cpu).ds = ds;
+
+	return 0;
+}
+
+static void release_ds_buffer(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+
+	if (!ds)
+		return;
+
+	per_cpu(cpu_hw_events, cpu).ds = NULL;
+	kfree(ds);
+}
+
 static void release_ds_buffers(void)
 {
 	int cpu;
@@ -82,93 +183,77 @@ static void release_ds_buffers(void)
 		return;
 
 	get_online_cpus();
-
 	for_each_online_cpu(cpu)
 		fini_debug_store_on_cpu(cpu);
 
 	for_each_possible_cpu(cpu) {
-		struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-		if (!ds)
-			continue;
-
-		per_cpu(cpu_hw_events, cpu).ds = NULL;
-
-		kfree((void *)(unsigned long)ds->pebs_buffer_base);
-		kfree((void *)(unsigned long)ds->bts_buffer_base);
-		kfree(ds);
+		release_pebs_buffer(cpu);
+		release_bts_buffer(cpu);
+		release_ds_buffer(cpu);
 	}
-
 	put_online_cpus();
 }
 
-static int reserve_ds_buffers(void)
+static void reserve_ds_buffers(void)
 {
-	int cpu, err = 0;
+	int bts_err = 0, pebs_err = 0;
+	int cpu;
+
+	x86_pmu.bts_active = 0;
+	x86_pmu.pebs_active = 0;
 
 	if (!x86_pmu.bts && !x86_pmu.pebs)
-		return 0;
+		return;
+
+	if (!x86_pmu.bts)
+		bts_err = 1;
+
+	if (!x86_pmu.pebs)
+		pebs_err = 1;
 
 	get_online_cpus();
 
 	for_each_possible_cpu(cpu) {
-		struct debug_store *ds;
-		void *buffer;
-		int max, thresh;
+		if (alloc_ds_buffer(cpu)) {
+			bts_err = 1;
+			pebs_err = 1;
+		}
+
+		if (!bts_err && alloc_bts_buffer(cpu))
+			bts_err = 1;
 
-		err = -ENOMEM;
-		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
-		if (unlikely(!ds))
+		if (!pebs_err && alloc_pebs_buffer(cpu))
+			pebs_err = 1;
+
+		if (bts_err && pebs_err)
 			break;
-		per_cpu(cpu_hw_events, cpu).ds = ds;
-
-		if (x86_pmu.bts) {
-			buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
-			if (unlikely(!buffer))
-				break;
-
-			max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
-			thresh = max / 16;
-
-			ds->bts_buffer_base = (u64)(unsigned long)buffer;
-			ds->bts_index = ds->bts_buffer_base;
-			ds->bts_absolute_maximum = ds->bts_buffer_base +
-				max * BTS_RECORD_SIZE;
-			ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
-				thresh * BTS_RECORD_SIZE;
-		}
+	}
 
-		if (x86_pmu.pebs) {
-			buffer = kzalloc(PEBS_BUFFER_SIZE, GFP_KERNEL);
-			if (unlikely(!buffer))
-				break;
-
-			max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
-
-			ds->pebs_buffer_base = (u64)(unsigned long)buffer;
-			ds->pebs_index = ds->pebs_buffer_base;
-			ds->pebs_absolute_maximum = ds->pebs_buffer_base +
-				max * x86_pmu.pebs_record_size;
-			/*
-			 * Always use single record PEBS
-			 */
-			ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
-				x86_pmu.pebs_record_size;
-		}
+	if (bts_err) {
+		for_each_possible_cpu(cpu)
+			release_bts_buffer(cpu);
+	}
 
-		err = 0;
+	if (pebs_err) {
+		for_each_possible_cpu(cpu)
+			release_pebs_buffer(cpu);
 	}
 
-	if (err)
-		release_ds_buffers();
-	else {
+	if (bts_err && pebs_err) {
+		for_each_possible_cpu(cpu)
+			release_ds_buffer(cpu);
+	} else {
+		if (x86_pmu.bts && !bts_err)
+			x86_pmu.bts_active = 1;
+
+		if (x86_pmu.pebs && !pebs_err)
+			x86_pmu.pebs_active = 1;
+
 		for_each_online_cpu(cpu)
 			init_debug_store_on_cpu(cpu);
 	}
 
 	put_online_cpus();
-
-	return err;
 }
 
 /*
@@ -233,7 +318,7 @@ static int intel_pmu_drain_bts_buffer(void)
 	if (!event)
 		return 0;
 
-	if (!ds)
+	if (!x86_pmu.bts_active)
 		return 0;
 
 	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
@@ -503,7 +588,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	struct pebs_record_core *at, *top;
 	int n;
 
-	if (!ds || !x86_pmu.pebs)
+	if (!x86_pmu.pebs_active)
 		return;
 
 	at  = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
@@ -545,7 +630,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	u64 status = 0;
 	int bit, n;
 
-	if (!ds || !x86_pmu.pebs)
+	if (!x86_pmu.pebs_active)
 		return;
 
 	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
@@ -630,9 +715,8 @@ static void intel_ds_init(void)
 
 #else /* CONFIG_CPU_SUP_INTEL */
 
-static int reserve_ds_buffers(void)
+static void reserve_ds_buffers(void)
 {
-	return 0;
 }
 
 static void release_ds_buffers(void)
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index 67414550c3c..d5cd13945d5 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -61,7 +61,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!is_crashed_pfn_valid(pfn))
 		return -EFAULT;
 
-	vaddr = kmap_atomic_pfn(pfn, KM_PTE0);
+	vaddr = kmap_atomic_pfn(pfn);
 
 	if (!userbuf) {
 		memcpy(buf, (vaddr + offset), csize);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 0f6376ffa2d..1bc7f75a5bd 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -82,11 +82,11 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		if (kstack_end(stack))
 			break;
 		if (i && ((i % STACKSLOTS_PER_LINE) == 0))
-			printk("\n%s", log_lvl);
-		printk(" %08lx", *stack++);
+			printk(KERN_CONT "\n");
+		printk(KERN_CONT " %08lx", *stack++);
 		touch_nmi_watchdog();
 	}
-	printk("\n");
+	printk(KERN_CONT "\n");
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 57a21f11c79..6a340485249 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -265,20 +265,20 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		if (stack >= irq_stack && stack <= irq_stack_end) {
 			if (stack == irq_stack_end) {
 				stack = (unsigned long *) (irq_stack_end[-1]);
-				printk(" <EOI> ");
+				printk(KERN_CONT " <EOI> ");
 			}
 		} else {
 		if (((long) stack & (THREAD_SIZE-1)) == 0)
 			break;
 		}
 		if (i && ((i % STACKSLOTS_PER_LINE) == 0))
-			printk("\n%s", log_lvl);
-		printk(" %016lx", *stack++);
+			printk(KERN_CONT "\n");
+		printk(KERN_CONT " %016lx", *stack++);
 		touch_nmi_watchdog();
 	}
 	preempt_enable();
 
-	printk("\n");
+	printk(KERN_CONT "\n");
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index aff0b3c2750..ae03cab4352 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -713,7 +713,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 
 	switch (action & 0xf) {
 	case CPU_ONLINE:
-		INIT_DELAYED_WORK_ON_STACK(&work.work, hpet_work);
+		INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
 		init_completion(&work.complete);
 		/* FIXME: add schedule_work_on() */
 		schedule_delayed_work_on(cpu, &work.work, 0);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 50fbbe60e50..64668dbf00a 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -60,9 +60,6 @@ union irq_ctx {
 static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
 static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
 
-static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, hardirq_stack, THREAD_SIZE);
-static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, softirq_stack, THREAD_SIZE);
-
 static void call_on_stack(void *func, void *stack)
 {
 	asm volatile("xchgl	%%ebx,%%esp	\n"
@@ -128,7 +125,7 @@ void __cpuinit irq_ctx_init(int cpu)
 	if (per_cpu(hardirq_ctx, cpu))
 		return;
 
-	irqctx = &per_cpu(hardirq_stack, cpu);
+	irqctx = (union irq_ctx *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER);
 	irqctx->tinfo.task		= NULL;
 	irqctx->tinfo.exec_domain	= NULL;
 	irqctx->tinfo.cpu		= cpu;
@@ -137,7 +134,7 @@ void __cpuinit irq_ctx_init(int cpu)
 
 	per_cpu(hardirq_ctx, cpu) = irqctx;
 
-	irqctx = &per_cpu(softirq_stack, cpu);
+	irqctx = (union irq_ctx *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER);
 	irqctx->tinfo.task		= NULL;
 	irqctx->tinfo.exec_domain	= NULL;
 	irqctx->tinfo.cpu		= cpu;
@@ -150,11 +147,6 @@ void __cpuinit irq_ctx_init(int cpu)
 	       cpu, per_cpu(hardirq_ctx, cpu),  per_cpu(softirq_ctx, cpu));
 }
 
-void irq_ctx_exit(int cpu)
-{
-	per_cpu(hardirq_ctx, cpu) = NULL;
-}
-
 asmlinkage void do_softirq(void)
 {
 	unsigned long flags;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index eb9b76c716c..ca43ce31a19 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -128,13 +128,15 @@ static struct clocksource kvm_clock = {
 static int kvm_register_clock(char *txt)
 {
 	int cpu = smp_processor_id();
-	int low, high;
+	int low, high, ret;
+
 	low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
 	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
+	ret = native_write_msr_safe(msr_kvm_system_time, low, high);
 	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
 	       cpu, high, low, txt);
 
-	return native_write_msr_safe(msr_kvm_system_time, low, high);
+	return ret;
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 0b3d37e8360..1cca374a2ba 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -12,7 +12,7 @@
  *	Software Developer's Manual
  *	Order Number 253668 or free download from:
  *
- *	http://developer.intel.com/design/pentium4/manuals/253668.htm
+ *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
  *
  *	For more information, go to http://www.urbanmyth.org/microcode
  *
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 356170262a9..dcb65cc0a05 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -12,7 +12,7 @@
  *	Software Developer's Manual
  *	Order Number 253668 or free download from:
  *
- *	http://developer.intel.com/design/pentium4/manuals/253668.htm
+ *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
  *
  *	For more information, go to http://www.urbanmyth.org/microcode
  *
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 70c4872cd8a..45892dc4b72 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -801,7 +801,8 @@ void ptrace_disable(struct task_struct *child)
 static const struct user_regset_view user_x86_32_view; /* Initialized below. */
 #endif
 
-long arch_ptrace(struct task_struct *child, long request, long addr, long data)
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
 {
 	int ret;
 	unsigned long __user *datap = (unsigned long __user *)data;
@@ -812,8 +813,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		unsigned long tmp;
 
 		ret = -EIO;
-		if ((addr & (sizeof(data) - 1)) || addr < 0 ||
-		    addr >= sizeof(struct user))
+		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user))
 			break;
 
 		tmp = 0;  /* Default return condition */
@@ -830,8 +830,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 
 	case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
 		ret = -EIO;
-		if ((addr & (sizeof(data) - 1)) || addr < 0 ||
-		    addr >= sizeof(struct user))
+		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user))
 			break;
 
 		if (addr < sizeof(struct user_regs_struct))
@@ -888,17 +887,17 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
 	case PTRACE_GET_THREAD_AREA:
-		if (addr < 0)
+		if ((int) addr < 0)
 			return -EIO;
 		ret = do_get_thread_area(child, addr,
-					 (struct user_desc __user *) data);
+					(struct user_desc __user *)data);
 		break;
 
 	case PTRACE_SET_THREAD_AREA:
-		if (addr < 0)
+		if ((int) addr < 0)
 			return -EIO;
 		ret = do_set_thread_area(child, addr,
-					 (struct user_desc __user *) data, 0);
+					(struct user_desc __user *)data, 0);
 		break;
 #endif
 
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 239427ca02a..bab3b9e6f66 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -82,7 +82,8 @@ static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
 static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
 {
 	u64 delta = native_read_tsc() - shadow->tsc_timestamp;
-	return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
+	return pvclock_scale_delta(delta, shadow->tsc_to_nsec_mul,
+				   shadow->tsc_shift);
 }
 
 /*
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f7f53dcd3e0..c495aa8d481 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -635,7 +635,7 @@ void native_machine_shutdown(void)
 	/* O.K Now that I'm on the appropriate processor,
 	 * stop all of the others.
 	 */
-	smp_send_stop();
+	stop_other_cpus();
 #endif
 
 	lapic_shutdown();
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d801210945d..513deac7228 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -159,10 +159,10 @@ asmlinkage void smp_reboot_interrupt(void)
 	irq_exit();
 }
 
-static void native_smp_send_stop(void)
+static void native_stop_other_cpus(int wait)
 {
 	unsigned long flags;
-	unsigned long wait;
+	unsigned long timeout;
 
 	if (reboot_force)
 		return;
@@ -179,9 +179,12 @@ static void native_smp_send_stop(void)
 	if (num_online_cpus() > 1) {
 		apic->send_IPI_allbutself(REBOOT_VECTOR);
 
-		/* Don't wait longer than a second */
-		wait = USEC_PER_SEC;
-		while (num_online_cpus() > 1 && wait--)
+		/*
+		 * Don't wait longer than a second if the caller
+		 * didn't ask us to wait.
+		 */
+		timeout = USEC_PER_SEC;
+		while (num_online_cpus() > 1 && (wait || timeout--))
 			udelay(1);
 	}
 
@@ -227,7 +230,7 @@ struct smp_ops smp_ops = {
 	.smp_prepare_cpus	= native_smp_prepare_cpus,
 	.smp_cpus_done		= native_smp_cpus_done,
 
-	.smp_send_stop		= native_smp_send_stop,
+	.stop_other_cpus	= native_stop_other_cpus,
 	.smp_send_reschedule	= native_smp_send_reschedule,
 
 	.cpu_up			= native_cpu_up,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6af118511b4..083e99d1b7d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -747,7 +747,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
 		.done	= COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
 	};
 
-	INIT_WORK_ON_STACK(&c_idle.work, do_fork_idle);
+	INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
 
 	alternatives_smp_switch(1);
 
@@ -1373,7 +1373,6 @@ void play_dead_common(void)
 {
 	idle_task_exit();
 	reset_lazy_tlbstate();
-	irq_ctx_exit(raw_smp_processor_id());
 	c1e_remove_cpu(raw_smp_processor_id());
 
 	mb();