Merge branch 'x86/urgent' into x86/core

20 files changed, 63 insertions, 119 deletions

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index ba4781b93890..fdb45df608b6 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -175,28 +175,8 @@ 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/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index d2e3bf3608af..886c9402ec45 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 07f1af494ca5..105fb90a0635 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 a5b3817d4b9e..a29f48c2a322 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/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index c12823eb55b5..160b3ab11e7a 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -837,7 +837,7 @@ void clear_local_APIC(void)
 	}
 
 	/* lets not touch this if we didn't frob it */
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL)
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
 	if (maxlvt >= 5) {
 		v = apic_read(APIC_LVTTHMR);
 		apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index fb039cd345d8..6428aa17b40e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1157,8 +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.
@@ -1176,17 +1175,20 @@ 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 */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 1c838032fd37..25cf624eccb7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -295,11 +295,11 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 		 * If we know that the error was in user space, send a
 		 * SIGBUS.  Otherwise, panic if tolerance is low.
 		 *
-		 * do_exit() takes an awful lot of locks and has a slight
+		 * force_sig() takes an awful lot of locks and has a slight
 		 * risk of deadlocking.
 		 */
 		if (user_space) {
-			do_exit(SIGBUS);
+			force_sig(SIGBUS, current);
 		} else if (panic_on_oops || tolerant < 2) {
 			mce_panic("Uncorrected machine check",
 				&panicm, mcestart);
@@ -734,6 +734,7 @@ __setup("mce=", mcheck_enable);
 static int mce_resume(struct sys_device *dev)
 {
 	mce_init(NULL);
+	mce_cpu_features(&current_cpu_data);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index fec79ad85dc6..646da41a620a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -111,9 +111,6 @@ void cpu_idle(void)
 			check_pgt_cache();
 			rmb();
 
-			if (rcu_pending(cpu))
-				rcu_check_callbacks(cpu, 0);
-
 			if (cpu_is_offline(cpu))
 				play_dead();
 
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index a4791ef412d1..9cd28c04952a 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -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 e665d1c623ca..72bd275a9b5c 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 c019b8edcdb7..cf17ed52f6fb 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 2bf32a03ceec..82579ee538d0 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 afac68c0815c..f0b67f2cdd69 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 81858881287e..45ab6ee71209 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 83f11c7474a1..2d4477c71473 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 1452851ae258..a9e769e4e251 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 6259d7467648..7611af576829 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 cc17546a2406..758b7a155ae9 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/mm/numa_64.c b/arch/x86/mm/numa_64.c
index deb1c1ab7868..64c9cf043cdd 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -166,7 +166,7 @@ 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 8ca0d8566fc8..7be47d1a97e4 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: