Merge branch 'linus' into x86/cleanups

Pull in upstream changes so we can apply depending patches.

28 files changed, 172 insertions, 74 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ded848c20e05..e75907601a41 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -976,6 +976,8 @@ static int __init acpi_parse_madt_lapic_entries(void)
 {
 	int count;
 	int x2count = 0;
+	int ret;
+	struct acpi_subtable_proc madt_proc[2];
 
 	if (!cpu_has_apic)
 		return -ENODEV;
@@ -999,10 +1001,22 @@ static int __init acpi_parse_madt_lapic_entries(void)
 				      acpi_parse_sapic, MAX_LOCAL_APIC);
 
 	if (!count) {
-		x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
-					acpi_parse_x2apic, MAX_LOCAL_APIC);
-		count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
-					acpi_parse_lapic, MAX_LOCAL_APIC);
+		memset(madt_proc, 0, sizeof(madt_proc));
+		madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC;
+		madt_proc[0].handler = acpi_parse_lapic;
+		madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC;
+		madt_proc[1].handler = acpi_parse_x2apic;
+		ret = acpi_table_parse_entries_array(ACPI_SIG_MADT,
+				sizeof(struct acpi_table_madt),
+				madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC);
+		if (ret < 0) {
+			printk(KERN_ERR PREFIX
+					"Error parsing LAPIC/X2APIC entries\n");
+			return ret;
+		}
+
+		x2count = madt_proc[0].count;
+		count = madt_proc[1].count;
 	}
 	if (!count && !x2count) {
 		printk(KERN_ERR PREFIX "No LAPIC entries present\n");
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 836d11b92811..861bc59c8f25 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -361,7 +361,11 @@ int __init arch_probe_nr_irqs(void)
 	if (nr < nr_irqs)
 		nr_irqs = nr;
 
-	return nr_legacy_irqs();
+	/*
+	 * We don't know if PIC is present at this point so we need to do
+	 * probe() to get the right number of legacy IRQs.
+	 */
+	return legacy_pic->probe();
 }
 
 #ifdef	CONFIG_X86_IO_APIC
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4a70fc6d400a..a8816b325162 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -352,6 +352,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
+	unsigned int socket_id, core_complex_id;
 
 	bits = c->x86_coreid_bits;
 	/* Low order bits define the core id (index of core in socket) */
@@ -361,6 +362,18 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
 	amd_get_topology(c);
+
+	/*
+	 * Fix percpu cpu_llc_id here as LLC topology is different
+	 * for Fam17h systems.
+	 */
+	 if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
+		return;
+
+	socket_id	= (c->apicid >> bits) - 1;
+	core_complex_id	= (c->apicid & ((1 << bits) - 1)) >> 3;
+
+	per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4ddd780aeac9..c2b7522cbf35 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -273,10 +273,9 @@ __setup("nosmap", setup_disable_smap);
 
 static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 {
-	unsigned long eflags;
+	unsigned long eflags = native_save_fl();
 
 	/* This should have been cleared long ago */
-	raw_local_save_flags(eflags);
 	BUG_ON(eflags & X86_EFLAGS_AC);
 
 	if (cpu_has(c, X86_FEATURE_SMAP)) {
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 98a13db5f4be..209ac1e7d1f0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -97,6 +97,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		switch (c->x86_model) {
 		case 0x27:	/* Penwell */
 		case 0x35:	/* Cloverview */
+		case 0x4a:	/* Merrifield */
 			set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3);
 			break;
 		default:
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 7fc27f1cca58..b3e94ef461fd 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -698,3 +698,4 @@ int __init microcode_init(void)
 	return error;
 
 }
+late_initcall(microcode_init);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4562cf070c27..2bf79d7c97df 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 499f533dd3cc..d0e35ebb2adb 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
@@ -387,7 +387,7 @@ struct cpu_hw_events {
 /* Check flags and event code/umask, and set the HSW N/A flag */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
 	__EVENT_CONSTRAINT(code, n, 			\
-			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
 
 
@@ -627,6 +627,7 @@ struct x86_perf_task_context {
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
+	int tos;
 	int lbr_callstack_users;
 	int lbr_stack_state;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f63360be2238..e2a430021e46 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
-	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 377e8f8ed391..a316ca96f1b6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
 {
 	if (event->attach_state & PERF_ATTACH_TASK)
-		return perf_cgroup_from_task(event->hw.target);
+		return perf_cgroup_from_task(event->hw.target, event->ctx);
 
 	return event->cgrp;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index bfd0b717e944..659f01e165d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 	}
 
 	mask = x86_pmu.lbr_nr - 1;
-	tos = intel_pmu_lbr_tos();
+	tos = task_ctx->tos;
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
@@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
@@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 81431c0f0614..ed446bdcbf31 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -107,12 +107,6 @@ static ssize_t __rapl_##_var##_show(struct kobject *kobj,	\
 static struct kobj_attribute format_attr_##_var =		\
 	__ATTR(_name, 0444, __rapl_##_var##_show, NULL)
 
-#define RAPL_EVENT_DESC(_name, _config)				\
-{								\
-	.attr	= __ATTR(_name, 0444, rapl_event_show, NULL),	\
-	.config	= _config,					\
-}
-
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
 #define RAPL_EVENT_ATTR_STR(_name, v, str)				\
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
index f32ac13934f2..ec863b9a9f78 100644
--- a/arch/x86/kernel/cpu/perf_event_msr.c
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -163,10 +163,9 @@ again:
 		goto again;
 
 	delta = now - prev;
-	if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
-		delta <<= 32;
-		delta >>= 32; /* sign extend */
-	}
+	if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
+		delta = sign_extend64(delta, 31);
+
 	local64_add(now - prev, &event->count);
 }
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index ef29b742cea7..31c6a60505e6 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -385,20 +385,19 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
  */
 void fpu__init_prepare_fx_sw_frame(void)
 {
-	int fsave_header_size = sizeof(struct fregs_state);
 	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
 
-	if (config_enabled(CONFIG_X86_32))
-		size += fsave_header_size;
-
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
 	fx_sw_reserved.extended_size = size;
 	fx_sw_reserved.xfeatures = xfeatures_mask;
 	fx_sw_reserved.xstate_size = xstate_size;
 
-	if (config_enabled(CONFIG_IA32_EMULATION)) {
+	if (config_enabled(CONFIG_IA32_EMULATION) ||
+	    config_enabled(CONFIG_X86_32)) {
+		int fsave_header_size = sizeof(struct fregs_state);
+
 		fx_sw_reserved_ia32 = fx_sw_reserved;
-		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+		fx_sw_reserved_ia32.extended_size = size + fsave_header_size;
 	}
 }
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 6454f2731b56..70fc312221fc 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -694,7 +694,6 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return NULL;
 
-	xsave = &current->thread.fpu.state.xsave;
 	/*
 	 * We should not ever be requesting features that we
 	 * have not enabled.  Remember that pcntxt_mask is
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8b7b0a51e742..311bcf338f07 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -556,6 +556,7 @@ void ftrace_replace_code(int enable)
 	run_sync();
 
 	report = "updating code";
+	count = 0;
 
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
@@ -563,11 +564,13 @@ void ftrace_replace_code(int enable)
 		ret = add_update(rec, enable);
 		if (ret)
 			goto remove_breakpoints;
+		count++;
 	}
 
 	run_sync();
 
 	report = "removing breakpoints";
+	count = 0;
 
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
@@ -575,6 +578,7 @@ void ftrace_replace_code(int enable)
 		ret = finish_update(rec, enable);
 		if (ret)
 			goto remove_breakpoints;
+		count++;
 	}
 
 	run_sync();
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 1d40ca8a73f2..ffdc0e860390 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -65,6 +65,9 @@ startup_64:
 	 * tables and then reload them.
 	 */
 
+	/* Sanitize CPU configuration */
+	call verify_cpu
+
 	/*
 	 * Compute the delta between the address I am compiled to run at and the
 	 * address I am actually running at.
@@ -174,6 +177,9 @@ ENTRY(secondary_startup_64)
 	 * after the boot processor executes this code.
 	 */
 
+	/* Sanitize CPU configuration */
+	call verify_cpu
+
 	movq	$(init_level4_pgt - __START_KERNEL_map), %rax
 1:
 
@@ -288,6 +294,8 @@ ENTRY(secondary_startup_64)
 	pushq	%rax		# target address in negative space
 	lretq
 
+#include "verify_cpu.S"
+
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 16cb827a5b27..be22f5a2192e 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -295,16 +295,11 @@ static void unmask_8259A(void)
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-static void init_8259A(int auto_eoi)
+static int probe_8259A(void)
 {
 	unsigned long flags;
 	unsigned char probe_val = ~(1 << PIC_CASCADE_IR);
 	unsigned char new_val;
-
-	i8259A_auto_eoi = auto_eoi;
-
-	raw_spin_lock_irqsave(&i8259A_lock, flags);
-
 	/*
 	 * Check to see if we have a PIC.
 	 * Mask all except the cascade and read
@@ -312,16 +307,28 @@ static void init_8259A(int auto_eoi)
 	 * have a PIC, we will read 0xff as opposed to the
 	 * value we wrote.
 	 */
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
+
 	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
 	outb(probe_val, PIC_MASTER_IMR);
 	new_val = inb(PIC_MASTER_IMR);
 	if (new_val != probe_val) {
 		printk(KERN_INFO "Using NULL legacy PIC\n");
 		legacy_pic = &null_legacy_pic;
-		raw_spin_unlock_irqrestore(&i8259A_lock, flags);
-		return;
 	}
 
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
+	return nr_legacy_irqs();
+}
+
+static void init_8259A(int auto_eoi)
+{
+	unsigned long flags;
+
+	i8259A_auto_eoi = auto_eoi;
+
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
+
 	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
 
 	/*
@@ -379,6 +386,10 @@ static int legacy_pic_irq_pending_noop(unsigned int irq)
 {
 	return 0;
 }
+static int legacy_pic_probe(void)
+{
+	return 0;
+}
 
 struct legacy_pic null_legacy_pic = {
 	.nr_legacy_irqs = 0,
@@ -388,6 +399,7 @@ struct legacy_pic null_legacy_pic = {
 	.mask_all = legacy_pic_noop,
 	.restore_mask = legacy_pic_noop,
 	.init = legacy_pic_int_noop,
+	.probe = legacy_pic_probe,
 	.irq_pending = legacy_pic_irq_pending_noop,
 	.make_irq = legacy_pic_uint_noop,
 };
@@ -400,6 +412,7 @@ struct legacy_pic default_legacy_pic = {
 	.mask_all = mask_8259A,
 	.restore_mask = unmask_8259A,
 	.init = init_8259A,
+	.probe = probe_8259A,
 	.irq_pending = i8259A_irq_pending,
 	.make_irq = make_8259A_irq,
 };
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index dc5fa6a1e8d6..3512ba607361 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -1,7 +1,7 @@
 /*
  * x86 specific code for irq_work
  *
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2c7aafa70702..2bd81e302427 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -32,6 +32,7 @@
 static int kvmclock = 1;
 static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
 static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
+static cycle_t kvm_sched_clock_offset;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -92,6 +93,29 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
 	return kvm_clock_read();
 }
 
+static cycle_t kvm_sched_clock_read(void)
+{
+	return kvm_clock_read() - kvm_sched_clock_offset;
+}
+
+static inline void kvm_sched_clock_init(bool stable)
+{
+	if (!stable) {
+		pv_time_ops.sched_clock = kvm_clock_read;
+		return;
+	}
+
+	kvm_sched_clock_offset = kvm_clock_read();
+	pv_time_ops.sched_clock = kvm_sched_clock_read;
+	set_sched_clock_stable();
+
+	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
+			kvm_sched_clock_offset);
+
+	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
+	         sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+}
+
 /*
  * If we don't do that, there is the possibility that the guest
  * will calibrate under heavy load - thus, getting a lower lpj -
@@ -248,7 +272,17 @@ void __init kvmclock_init(void)
 		memblock_free(mem, size);
 		return;
 	}
-	pv_time_ops.sched_clock = kvm_clock_read;
+
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+
+	cpu = get_cpu();
+	vcpu_time = &hv_clock[cpu].pvti;
+	flags = pvclock_read_flags(vcpu_time);
+
+	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
+	put_cpu();
+
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
@@ -265,16 +299,6 @@ void __init kvmclock_init(void)
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
-
-	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
-		pvclock_set_flags(~0);
-
-	cpu = get_cpu();
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-	if (flags & PVCLOCK_COUNTS_FROM_ZERO)
-		set_sched_clock_stable();
-	put_cpu();
 }
 
 int __init kvm_setup_vsyscall_timeinfo(void)
diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c
index ff3c3101d003..d1d35ccffed3 100644
--- a/arch/x86/kernel/livepatch.c
+++ b/arch/x86/kernel/livepatch.c
@@ -42,7 +42,6 @@ int klp_write_module_reloc(struct module *mod, unsigned long type,
 	bool readonly;
 	unsigned long val;
 	unsigned long core = (unsigned long)mod->module_core;
-	unsigned long core_ro_size = mod->core_ro_size;
 	unsigned long core_size = mod->core_size;
 
 	switch (type) {
@@ -70,10 +69,12 @@ int klp_write_module_reloc(struct module *mod, unsigned long type,
 		/* loc does not point to any symbol inside the module */
 		return -EINVAL;
 
-	if (loc < core + core_ro_size)
+	readonly = false;
+
+#ifdef CONFIG_DEBUG_SET_MODULE_RONX
+	if (loc < core + mod->core_ro_size)
 		readonly = true;
-	else
-		readonly = false;
+#endif
 
 	/* determine if the relocation spans a page boundary */
 	numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2;
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 94ea120fa21f..87e1762e2bca 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -278,6 +278,12 @@ trace:
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
+	/*
+	 * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not
+	 * set (see include/asm/ftrace.h and include/linux/ftrace.h).  Only the
+	 * ip and parent ip are used and the list function is called when
+	 * function tracing is enabled.
+	 */
 	call   *ftrace_trace_function
 
 	restore_mcount_regs
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index cd99433b8ba1..6ba014c61d62 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -90,7 +90,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 again:
 	page = NULL;
 	/* CMA can be used only in the context which permits sleeping */
-	if (flag & __GFP_WAIT) {
+	if (gfpflags_allow_blocking(flag)) {
 		page = dma_alloc_from_contiguous(dev, count, get_order(size));
 		if (page && page_to_phys(page) + size > dma_mask) {
 			dma_release_from_contiguous(dev, page, count);
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 4f00b63d7ff3..14415aff1813 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -4,10 +4,22 @@
  */
 #include <linux/platform_device.h>
 #include <linux/module.h>
+#include <linux/ioport.h>
+
+static int found(u64 start, u64 end, void *data)
+{
+	return 1;
+}
 
 static __init int register_e820_pmem(void)
 {
+	char *pmem = "Persistent Memory (legacy)";
 	struct platform_device *pdev;
+	int rc;
+
+	rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found);
+	if (rc <= 0)
+		return 0;
 
 	/*
 	 * See drivers/nvdimm/e820.c for the implementation, this is
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a1e4da98c8f0..d2bbe343fda7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1188,7 +1188,7 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	clone_pgd_range(initial_page_table,
 			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
+			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
 #endif
 
 	tboot_probe();
@@ -1250,8 +1250,6 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled(EFI_BOOT))
 		efi_apply_memmap_quirks();
 #endif
-
-	microcode_init();
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b7ffb7c00075..cb6282c3638f 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -690,12 +690,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	signal_setup_done(failed, ksig, stepping);
 }
 
-#ifdef CONFIG_X86_32
-#define NR_restart_syscall	__NR_restart_syscall
-#else /* !CONFIG_X86_32 */
-#define NR_restart_syscall	\
-	test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
-#endif /* CONFIG_X86_32 */
+static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
+{
+#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64)
+	return __NR_restart_syscall;
+#else /* !CONFIG_X86_32 && CONFIG_X86_64 */
+	return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall :
+		__NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
+#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */
+}
 
 /*
  * Note that 'init' is a special process: it doesn't get signals it doesn't
@@ -724,7 +727,7 @@ void do_signal(struct pt_regs *regs)
 			break;
 
 		case -ERESTART_RESTARTBLOCK:
-			regs->ax = NR_restart_syscall;
+			regs->ax = get_nr_restart_syscall(regs);
 			regs->ip -= 2;
 			break;
 		}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4df777710ab7..f2281e9cfdbe 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid)
  */
 #define UDELAY_10MS_DEFAULT 10000
 
-static unsigned int init_udelay = INT_MAX;
+static unsigned int init_udelay = UINT_MAX;
 
 static int __init cpu_init_udelay(char *str)
 {
@@ -522,14 +522,15 @@ early_param("cpu_init_udelay", cpu_init_udelay);
 static void __init smp_quirk_init_udelay(void)
 {
 	/* if cmdline changed it from default, leave it alone */
-	if (init_udelay != INT_MAX)
+	if (init_udelay != UINT_MAX)
 		return;
 
 	/* if modern processor, use no delay */
 	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
 		init_udelay = 0;
-
+		return;
+	}
 	/* else, use legacy delay */
 	init_udelay = UDELAY_10MS_DEFAULT;
 }
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index b9242bacbe59..4cf401f581e7 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -34,10 +34,11 @@
 #include <asm/msr-index.h>
 
 verify_cpu:
-	pushfl				# Save caller passed flags
-	pushl	$0			# Kill any dangerous flags
-	popfl
+	pushf				# Save caller passed flags
+	push	$0			# Kill any dangerous flags
+	popf
 
+#ifndef __x86_64__
 	pushfl				# standard way to check for cpuid
 	popl	%eax
 	movl	%eax,%ebx
@@ -48,6 +49,7 @@ verify_cpu:
 	popl	%eax
 	cmpl	%eax,%ebx
 	jz	verify_cpu_no_longmode	# cpu has no cpuid
+#endif
 
 	movl	$0x0,%eax		# See if cpuid 1 is implemented
 	cpuid
@@ -130,10 +132,10 @@ verify_cpu_sse_test:
 	jmp	verify_cpu_sse_test	# try again
 
 verify_cpu_no_longmode:
-	popfl				# Restore caller passed flags
+	popf				# Restore caller passed flags
 	movl $1,%eax
 	ret
 verify_cpu_sse_ok:
-	popfl				# Restore caller passed flags
+	popf				# Restore caller passed flags
 	xorl %eax, %eax
 	ret