Merge branch 'x86/urgent' into x86/mce2

33 files changed, 137 insertions, 175 deletions

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 10d6cc3fd05..e1983fa025d 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -174,28 +174,8 @@ config IOMMU_LEAK
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
-config MMIOTRACE
-	bool "Memory mapped IO tracing"
-	depends on DEBUG_KERNEL && PCI
-	select TRACING
-	help
-	  Mmiotrace traces Memory Mapped I/O access and is meant for
-	  debugging and reverse engineering. It is called from the ioremap
-	  implementation and works via page faults. Tracing is disabled by
-	  default and can be enabled at run-time.
-
-	  See Documentation/tracers/mmiotrace.txt.
-	  If you are not helping to develop drivers, say N.
-
-config MMIOTRACE_TEST
-	tristate "Test module for mmiotrace"
-	depends on MMIOTRACE && m
-	help
-	  This is a dumb module for testing mmiotrace. It is very dangerous
-	  as it will write garbage to IO memory starting at a given address.
-	  However, it should be safe to use on e.g. unused portion of VRAM.
-
-	  Say N, unless you absolutely know what you are doing.
+config HAVE_MMIOTRACE_SUPPORT
+	def_bool y
 
 #
 # IO delay types:
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 256b00b6189..5a0d76dc56a 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -418,9 +418,9 @@ ENTRY(ia32_syscall)
 	orl   $TS_COMPAT,TI_status(%r10)
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
 	jnz ia32_tracesys
-ia32_do_syscall:	
 	cmpl $(IA32_NR_syscalls-1),%eax
-	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
+	ja ia32_badsys
+ia32_do_call:
 	IA32_ARG_FIXUP
 	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 ia32_sysret:
@@ -435,7 +435,9 @@ ia32_tracesys:
 	call syscall_trace_enter
 	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
-	jmp ia32_do_syscall
+	cmpl $(IA32_NR_syscalls-1),%eax
+	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
+	jmp ia32_do_call
 END(ia32_syscall)
 
 ia32_badsys:
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index d2e3bf3608a..886c9402ec4 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -9,6 +9,13 @@
 #include <linux/types.h>
 #include <linux/ioctl.h>
 
+/* Select x86 specific features in <linux/kvm.h> */
+#define __KVM_HAVE_PIT
+#define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_DEVICE_ASSIGNMENT
+#define __KVM_HAVE_MSI
+#define __KVM_HAVE_USER_NMI
+
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
 
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 07f1af494ca..105fb90a063 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -32,8 +32,6 @@ static inline void get_memcfg_numa(void)
 	get_memcfg_numa_flat();
 }
 
-extern int early_pfn_to_nid(unsigned long pfn);
-
 extern void resume_map_numa_kva(pgd_t *pgd);
 
 #else /* !CONFIG_NUMA */
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index a5b3817d4b9..a29f48c2a32 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -40,8 +40,6 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
 #define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +	\
 				 NODE_DATA(nid)->node_spanned_pages)
 
-extern int early_pfn_to_nid(unsigned long pfn);
-
 #ifdef CONFIG_NUMA_EMU
 #define FAKE_NODE_MIN_SIZE	(64 * 1024 * 1024)
 #define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a660eceaa27..e299287e8e3 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -1389,6 +1389,7 @@ static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
 {
 	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
 }
+#define __raw_spin_is_contended	__raw_spin_is_contended
 
 static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
 {
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index d17c91981da..8247e94ac6b 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -245,6 +245,7 @@ static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
 {
 	return __ticket_spin_is_contended(lock);
 }
+#define __raw_spin_is_contended	__raw_spin_is_contended
 
 static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
 {
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 707c1f6f95f..a60c1f3bcb8 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -156,11 +156,11 @@ static int __init acpi_sleep_setup(char *str)
 #ifdef CONFIG_HIBERNATION
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
 			acpi_no_s4_hw_signature();
+		if (strncmp(str, "s4_nonvs", 8) == 0)
+			acpi_s4_no_nvs();
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
-		if (strncmp(str, "s4_nonvs", 8) == 0)
-			acpi_s4_no_nvs();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index bcc293423a7..96258d9dc97 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -13,7 +13,6 @@
 	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
 	 */
 ENTRY(wakeup_long64)
-wakeup_long64:
 	movq	saved_magic, %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
@@ -34,16 +33,12 @@ wakeup_long64:
 
 	movq	saved_rip, %rax
 	jmp	*%rax
+ENDPROC(wakeup_long64)
 
 bogus_64_magic:
 	jmp	bogus_64_magic
 
-	.align 2
-	.p2align 4,,15
-.globl do_suspend_lowlevel
-	.type	do_suspend_lowlevel,@function
-do_suspend_lowlevel:
-.LFB5:
+ENTRY(do_suspend_lowlevel)
 	subq	$8, %rsp
 	xorl	%eax, %eax
 	call	save_processor_state
@@ -67,7 +62,7 @@ do_suspend_lowlevel:
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	movq	$.L97, saved_rip(%rip)
+	movq	$resume_point, saved_rip(%rip)
 
 	movq	%rsp, saved_rsp
 	movq	%rbp, saved_rbp
@@ -78,14 +73,12 @@ do_suspend_lowlevel:
 	addq	$8, %rsp
 	movl	$3, %edi
 	xorl	%eax, %eax
-	jmp	acpi_enter_sleep_state
-.L97:
-	.p2align 4,,7
-.L99:
-	.align 4
-	movl	$24, %eax
-	movw	%ax, %ds
+	call	acpi_enter_sleep_state
+	/* in case something went wrong, restore the machine status and go on */
+	jmp	resume_point
 
+	.align 4
+resume_point:
 	/* We don't restore %rax, it must be 0 anyway */
 	movq	$saved_context, %rax
 	movq	saved_context_cr4(%rax), %rbx
@@ -117,12 +110,9 @@ do_suspend_lowlevel:
 	xorl	%eax, %eax
 	addq	$8, %rsp
 	jmp	restore_processor_state
-.LFE5:
-.Lfe5:
-	.size	do_suspend_lowlevel, .Lfe5-do_suspend_lowlevel
-	
+ENDPROC(do_suspend_lowlevel)
+
 .data
-ALIGN
 ENTRY(saved_rbp)	.quad	0
 ENTRY(saved_rsi)	.quad	0
 ENTRY(saved_rdi)	.quad	0
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 98807bb095a..266ec6c18b6 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1192,6 +1192,7 @@ static int suspend(int vetoable)
 	device_suspend(PMSG_SUSPEND);
 	local_irq_disable();
 	device_power_down(PMSG_SUSPEND);
+	sysdev_suspend(PMSG_SUSPEND);
 
 	local_irq_enable();
 
@@ -1208,6 +1209,7 @@ static int suspend(int vetoable)
 	if (err != APM_SUCCESS)
 		apm_error("suspend", err);
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
+	sysdev_resume();
 	device_power_up(PMSG_RESUME);
 	local_irq_enable();
 	device_resume(PMSG_RESUME);
@@ -1228,6 +1230,7 @@ static void standby(void)
 
 	local_irq_disable();
 	device_power_down(PMSG_SUSPEND);
+	sysdev_suspend(PMSG_SUSPEND);
 	local_irq_enable();
 
 	err = set_system_power_state(APM_STATE_STANDBY);
@@ -1235,6 +1238,7 @@ static void standby(void)
 		apm_error("standby", err);
 
 	local_irq_disable();
+	sysdev_resume();
 	device_power_up(PMSG_RESUME);
 	local_irq_enable();
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index efae3b22a0f..65792c2cc46 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -245,17 +245,6 @@ config X86_E_POWERSAVER
 
 comment "shared options"
 
-config X86_ACPI_CPUFREQ_PROC_INTF
-	bool "/proc/acpi/processor/../performance interface (deprecated)"
-	depends on PROC_FS
-	depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI
-	help
-	  This enables the deprecated /proc/acpi/processor/../performance
-	  interface. While it is helpful for debugging, the generic,
-	  cross-architecture cpufreq interfaces should be used.
-
-	  If in doubt, say N.
-
 config X86_SPEEDSTEP_LIB
 	tristate
 	default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 5c28b37dea1..6428aa17b40 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -939,10 +939,25 @@ static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
 	free_cpumask_var(data->acpi_data.shared_cpu_map);
 }
 
+static int get_transition_latency(struct powernow_k8_data *data)
+{
+	int max_latency = 0;
+	int i;
+	for (i = 0; i < data->acpi_data.state_count; i++) {
+		int cur_latency = data->acpi_data.states[i].transition_latency
+			+ data->acpi_data.states[i].bus_master_latency;
+		if (cur_latency > max_latency)
+			max_latency = cur_latency;
+	}
+	/* value in usecs, needs to be in nanoseconds */
+	return 1000 * max_latency;
+}
+
 #else
 static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; }
 static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; }
 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; }
+static int get_transition_latency(struct powernow_k8_data *data) { return 0; }
 #endif /* CONFIG_X86_POWERNOW_K8_ACPI */
 
 /* Take a frequency, and issue the fid/vid transition command */
@@ -1142,8 +1157,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	data->cpu = pol->cpu;
 	data->currpstate = HW_PSTATE_INVALID;
 
-	rc = powernow_k8_cpu_init_acpi(data);
-	if (rc) {
+	if (powernow_k8_cpu_init_acpi(data)) {
 		/*
 		 * Use the PSB BIOS structure. This is only availabe on
 		 * an UP version, and is deprecated by AMD.
@@ -1161,19 +1175,28 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 			       "ACPI maintainers and complain to your BIOS "
 			       "vendor.\n");
 #endif
-			goto err_out;
+			kfree(data);
+			return -ENODEV;
 		}
 		if (pol->cpu != 0) {
 			printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for "
 			       "CPU other than CPU0. Complain to your BIOS "
 			       "vendor.\n");
-			goto err_out;
+			kfree(data);
+			return -ENODEV;
 		}
 		rc = find_psb_table(data);
 		if (rc) {
-			goto err_out;
+			kfree(data);
+			return -ENODEV;
 		}
-	}
+		/* Take a crude guess here.
+		 * That guess was in microseconds, so multiply with 1000 */
+		pol->cpuinfo.transition_latency = (
+			 ((data->rvo + 8) * data->vstable * VST_UNITS_20US) +
+			 ((1 << data->irt) * 30)) * 1000;
+	} else /* ACPI _PSS objects available */
+		pol->cpuinfo.transition_latency = get_transition_latency(data);
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
@@ -1204,11 +1227,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
 	data->available_cores = pol->cpus;
 
-	/* Take a crude guess here.
-	 * That guess was in microseconds, so multiply with 1000 */
-	pol->cpuinfo.transition_latency = (((data->rvo + 8) * data->vstable * VST_UNITS_20US)
-	    + (3 * (1 << data->irt) * 10)) * 1000;
-
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate);
 	else
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 0625993bf95..a4a7c686ce9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -614,7 +614,7 @@ static void mce_cpu_quirks(struct cpuinfo_x86 *c)
 
 }
 
-static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
+static void mce_cpu_features(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 0069c653f4e..e82c8208b81 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -121,7 +121,7 @@ static long threshold_restart_bank(void *_tr)
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
-void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
+void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
 	unsigned int bank, block;
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 7f7f1015ef1..1b1491a76b5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -30,7 +30,7 @@ asmlinkage void smp_thermal_interrupt(void)
 	irq_exit();
 }
 
-static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c)
+static void intel_init_thermal(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
 	int tm2 = 0;
@@ -84,7 +84,7 @@ static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c)
 	return;
 }
 
-void __cpuinit mce_intel_feature_init(struct cpuinfo_x86 *c)
+void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_thermal(c);
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1b43086b097..231bdd3c5b1 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -488,20 +488,21 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	 * ignore such a protection.
 	 */
 	asm volatile(
-		"1: " _ASM_MOV " (%[parent_old]), %[old]\n"
-		"2: " _ASM_MOV " %[return_hooker], (%[parent_replaced])\n"
+		"1: " _ASM_MOV " (%[parent]), %[old]\n"
+		"2: " _ASM_MOV " %[return_hooker], (%[parent])\n"
 		"   movl $0, %[faulted]\n"
+		"3:\n"
 
 		".section .fixup, \"ax\"\n"
-		"3: movl $1, %[faulted]\n"
+		"4: movl $1, %[faulted]\n"
+		"   jmp 3b\n"
 		".previous\n"
 
-		_ASM_EXTABLE(1b, 3b)
-		_ASM_EXTABLE(2b, 3b)
+		_ASM_EXTABLE(1b, 4b)
+		_ASM_EXTABLE(2b, 4b)
 
-		: [parent_replaced] "=r" (parent), [old] "=r" (old),
-		  [faulted] "=r" (faulted)
-		: [parent_old] "0" (parent), [return_hooker] "r" (return_hooker)
+		: [old] "=r" (old), [faulted] "=r" (faulted)
+		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
 		: "memory"
 	);
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 5c8da2c2c18..a00545fe5cd 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -899,7 +899,7 @@ static unsigned long hpet_rtc_flags;
 static int hpet_prev_update_sec;
 static struct rtc_time hpet_alarm_time;
 static unsigned long hpet_pie_count;
-static unsigned long hpet_t1_cmp;
+static u32 hpet_t1_cmp;
 static unsigned long hpet_default_delta;
 static unsigned long hpet_pie_delta;
 static unsigned long hpet_pie_limit;
@@ -907,6 +907,14 @@ static unsigned long hpet_pie_limit;
 static rtc_irq_handler irq_handler;
 
 /*
+ * Check that the hpet counter c1 is ahead of the c2
+ */
+static inline int hpet_cnt_ahead(u32 c1, u32 c2)
+{
+	return (s32)(c2 - c1) < 0;
+}
+
+/*
  * Registers a IRQ handler.
  */
 int hpet_register_irq_handler(rtc_irq_handler handler)
@@ -1077,7 +1085,7 @@ static void hpet_rtc_timer_reinit(void)
 		hpet_t1_cmp += delta;
 		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
 		lost_ints++;
-	} while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
+	} while (!hpet_cnt_ahead(hpet_t1_cmp, hpet_readl(HPET_COUNTER)));
 
 	if (lost_ints) {
 		if (hpet_rtc_flags & RTC_PIE)
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index e6e695acd72..241ec3923f6 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -115,7 +115,7 @@ unsigned long __init calibrate_cpu(void)
 
 static struct irqaction irq0 = {
 	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING,
+	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER,
 	.mask		= CPU_MASK_NONE,
 	.name		= "timer"
 };
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index c4c1f9e0940..e5b088fffa4 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -202,7 +202,7 @@ static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
 static struct irqaction vmi_clock_action  = {
 	.name 		= "vmi-timer",
 	.handler 	= vmi_timer_interrupt,
-	.flags 		= IRQF_DISABLED | IRQF_NOBALANCING,
+	.flags 		= IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
 	.mask 		= CPU_MASK_ALL,
 };
 
@@ -283,10 +283,13 @@ void __devinit vmi_time_ap_init(void)
 #endif
 
 /** vmi clocksource */
+static struct clocksource clocksource_vmi;
 
 static cycle_t read_real_cycles(void)
 {
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+	cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+	return ret >= clocksource_vmi.cycle_last ?
+		ret : clocksource_vmi.cycle_last;
 }
 
 static struct clocksource clocksource_vmi = {
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index e665d1c623c..72bd275a9b5 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -207,7 +207,7 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps)
 	hrtimer_add_expires_ns(&pt->timer, pt->period);
 	pt->scheduled = hrtimer_get_expires_ns(&pt->timer);
 	if (pt->period)
-		ps->channels[0].count_load_time = hrtimer_get_expires(&pt->timer);
+		ps->channels[0].count_load_time = ktime_get();
 
 	return (pt->period == 0 ? 0 : 1);
 }
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index c019b8edcdb..cf17ed52f6f 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -87,13 +87,6 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
 
-void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
-	kvm_apic_timer_intr_post(vcpu, vec);
-	/* TODO: PIT, RTC etc. */
-}
-EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
-
 void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
 {
 	__kvm_migrate_apic_timer(vcpu);
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 2bf32a03cee..82579ee538d 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -89,7 +89,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 
 void kvm_pic_reset(struct kvm_kpic_state *s);
 
-void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index afac68c0815..f0b67f2cdd6 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -35,6 +35,12 @@
 #include "kvm_cache_regs.h"
 #include "irq.h"
 
+#ifndef CONFIG_X86_64
+#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
+#else
+#define mod_64(x, y) ((x) % (y))
+#endif
+
 #define PRId64 "d"
 #define PRIx64 "llx"
 #define PRIu64 "u"
@@ -511,52 +517,22 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 
 static u32 apic_get_tmcct(struct kvm_lapic *apic)
 {
-	u64 counter_passed;
-	ktime_t passed, now;
+	ktime_t remaining;
+	s64 ns;
 	u32 tmcct;
 
 	ASSERT(apic != NULL);
 
-	now = apic->timer.dev.base->get_time();
-	tmcct = apic_get_reg(apic, APIC_TMICT);
-
 	/* if initial count is 0, current count should also be 0 */
-	if (tmcct == 0)
+	if (apic_get_reg(apic, APIC_TMICT) == 0)
 		return 0;
 
-	if (unlikely(ktime_to_ns(now) <=
-		ktime_to_ns(apic->timer.last_update))) {
-		/* Wrap around */
-		passed = ktime_add(( {
-				    (ktime_t) {
-				    .tv64 = KTIME_MAX -
-				    (apic->timer.last_update).tv64}; }
-				   ), now);
-		apic_debug("time elapsed\n");
-	} else
-		passed = ktime_sub(now, apic->timer.last_update);
-
-	counter_passed = div64_u64(ktime_to_ns(passed),
-				   (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
-
-	if (counter_passed > tmcct) {
-		if (unlikely(!apic_lvtt_period(apic))) {
-			/* one-shot timers stick at 0 until reset */
-			tmcct = 0;
-		} else {
-			/*
-			 * periodic timers reset to APIC_TMICT when they
-			 * hit 0. The while loop simulates this happening N
-			 * times. (counter_passed %= tmcct) would also work,
-			 * but might be slower or not work on 32-bit??
-			 */
-			while (counter_passed > tmcct)
-				counter_passed -= tmcct;
-			tmcct -= counter_passed;
-		}
-	} else {
-		tmcct -= counter_passed;
-	}
+	remaining = hrtimer_expires_remaining(&apic->timer.dev);
+	if (ktime_to_ns(remaining) < 0)
+		remaining = ktime_set(0, 0);
+
+	ns = mod_64(ktime_to_ns(remaining), apic->timer.period);
+	tmcct = div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
 
 	return tmcct;
 }
@@ -653,8 +629,6 @@ static void start_apic_timer(struct kvm_lapic *apic)
 {
 	ktime_t now = apic->timer.dev.base->get_time();
 
-	apic->timer.last_update = now;
-
 	apic->timer.period = apic_get_reg(apic, APIC_TMICT) *
 		    APIC_BUS_CYCLE_NS * apic->timer.divide_count;
 	atomic_set(&apic->timer.pending, 0);
@@ -1110,16 +1084,6 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 	}
 }
 
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-
-	if (apic && apic_lvt_vector(apic, APIC_LVTT) == vec)
-		apic->timer.last_update = ktime_add_ns(
-				apic->timer.last_update,
-				apic->timer.period);
-}
-
 int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 {
 	int vector = kvm_apic_has_interrupt(vcpu);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 81858881287..45ab6ee7120 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -12,7 +12,6 @@ struct kvm_lapic {
 		atomic_t pending;
 		s64 period;	/* unit: ns */
 		u32 divide_count;
-		ktime_t last_update;
 		struct hrtimer dev;
 	} timer;
 	struct kvm_vcpu *vcpu;
@@ -42,7 +41,6 @@ void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
 void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
 int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 
 void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 83f11c7474a..2d4477c7147 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1698,8 +1698,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 	if (largepage)
 		spte |= PT_PAGE_SIZE_MASK;
 	if (mt_mask) {
-		mt_mask = get_memory_type(vcpu, gfn) <<
-			  kvm_x86_ops->get_mt_mask_shift();
+		if (!kvm_is_mmio_pfn(pfn)) {
+			mt_mask = get_memory_type(vcpu, gfn) <<
+				kvm_x86_ops->get_mt_mask_shift();
+			mt_mask |= VMX_EPT_IGMT_BIT;
+		} else
+			mt_mask = MTRR_TYPE_UNCACHABLE <<
+				kvm_x86_ops->get_mt_mask_shift();
 		spte |= mt_mask;
 	}
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1452851ae25..a9e769e4e25 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1600,7 +1600,6 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu)
 	/* Okay, we can deliver the interrupt: grab it and update PIC state. */
 	intr_vector = kvm_cpu_get_interrupt(vcpu);
 	svm_inject_irq(svm, intr_vector);
-	kvm_timer_intr_post(vcpu, intr_vector);
 out:
 	update_cr8_intercept(vcpu);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6259d746764..7611af57682 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -903,6 +903,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 		data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	default:
+		vmx_load_host_state(to_vmx(vcpu));
 		msr = find_msr_entry(to_vmx(vcpu), msr_index);
 		if (msr) {
 			data = msr->data;
@@ -3285,7 +3286,6 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
 	}
 	if (vcpu->arch.interrupt.pending) {
 		vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
-		kvm_timer_intr_post(vcpu, vcpu->arch.interrupt.nr);
 		if (kvm_cpu_has_interrupt(vcpu))
 			enable_irq_window(vcpu);
 	}
@@ -3687,8 +3687,7 @@ static int __init vmx_init(void)
 	if (vm_need_ept()) {
 		bypass_guest_pf = 0;
 		kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
-			VMX_EPT_WRITABLE_MASK |
-			VMX_EPT_IGMT_BIT);
+			VMX_EPT_WRITABLE_MASK);
 		kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
 				VMX_EPT_EXECUTABLE_MASK,
 				VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cc17546a240..758b7a155ae 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -967,7 +967,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
-	case KVM_CAP_CLOCKSOURCE:
 	case KVM_CAP_PIT:
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
@@ -992,6 +991,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IOMMU:
 		r = iommu_found();
 		break;
+	case KVM_CAP_CLOCKSOURCE:
+		r = boot_cpu_has(X86_FEATURE_CONSTANT_TSC);
+		break;
 	default:
 		r = 0;
 		break;
@@ -4127,9 +4129,13 @@ static void kvm_free_vcpus(struct kvm *kvm)
 
 }
 
-void kvm_arch_destroy_vm(struct kvm *kvm)
+void kvm_arch_sync_events(struct kvm *kvm)
 {
 	kvm_free_all_assigned_devices(kvm);
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
 	kvm_iommu_unmap_guest(kvm);
 	kvm_free_pit(kvm);
 	kfree(kvm->arch.vpic);
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index a265a7c6319..50b59187112 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -96,7 +96,7 @@ void __init trap_init_hook(void)
 
 static struct irqaction irq0  = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
 	.mask = CPU_MASK_NONE,
 	.name = "timer"
 };
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index d914a7996a6..8e5118371f0 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -56,7 +56,7 @@ void __init trap_init_hook(void)
 
 static struct irqaction irq0 = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
 	.mask = CPU_MASK_NONE,
 	.name = "timer"
 };
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 90dfae511a4..c76ef1d701c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -603,8 +603,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
 	si_code = SEGV_MAPERR;
 
-	if (notify_page_fault(regs))
-		return;
 	if (unlikely(kmmio_fault(regs, address)))
 		return;
 
@@ -634,6 +632,9 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		if (spurious_fault(address, error_code))
 			return;
 
+		/* kprobes don't want to hook the spurious faults. */
+		if (notify_page_fault(regs))
+			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
 		 * fault we could otherwise deadlock.
@@ -641,6 +642,9 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		goto bad_area_nosemaphore;
 	}
 
+	/* kprobes don't want to hook the spurious faults. */
+	if (notify_page_fault(regs))
+		return;
 
 	/*
 	 * It's safe to allow irq's after cr2 has been saved and the
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 71a14f89f89..f3516da035d 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -145,7 +145,7 @@ int __init compute_hash_shift(struct bootnode *nodes, int numnodes,
 	return shift;
 }
 
-int early_pfn_to_nid(unsigned long pfn)
+int __meminit  __early_pfn_to_nid(unsigned long pfn)
 {
 	return phys_to_nid(pfn << PAGE_SHIFT);
 }
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 8ca0d8566fc..7be47d1a97e 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -508,18 +508,13 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 #endif
 
 	/*
-	 * Install the new, split up pagetable. Important details here:
+	 * Install the new, split up pagetable.
 	 *
-	 * On Intel the NX bit of all levels must be cleared to make a
-	 * page executable. See section 4.13.2 of Intel 64 and IA-32
-	 * Architectures Software Developer's Manual).
-	 *
-	 * Mark the entry present. The current mapping might be
-	 * set to not present, which we preserved above.
+	 * We use the standard kernel pagetable protections for the new
+	 * pagetable protections, the actual ptes set above control the
+	 * primary protection behavior:
 	 */
-	ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte)));
-	pgprot_val(ref_prot) |= _PAGE_PRESENT;
-	__set_pmd_pte(kpte, address, mk_pte(base, ref_prot));
+	__set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
 	base = NULL;
 
 out_unlock: