Merge branch 'gfar' of master.kernel.org:/pub/scm/linux/kernel/git/galak/powerpc into upstream

6 files changed, 174 insertions, 40 deletions

diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 2db1ca4c680..04574a9d443 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -304,6 +304,7 @@ struct kvm {
 	int memory_config_version;
 	int busy;
 	unsigned long rmap_overflow;
+	struct list_head vm_list;
 };
 
 struct kvm_stat {
@@ -340,6 +341,7 @@ struct kvm_arch_ops {
 
 	struct kvm_vcpu *(*vcpu_load)(struct kvm_vcpu *vcpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
+	void (*vcpu_decache)(struct kvm_vcpu *vcpu);
 
 	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
 			       struct kvm_debug_guest *dbg);
@@ -558,7 +560,7 @@ static inline void load_gs(u16 sel)
 #ifndef load_ldt
 static inline void load_ldt(u16 sel)
 {
-	asm ("lldt %0" : : "g"(sel));
+	asm ("lldt %0" : : "rm"(sel));
 }
 #endif
 
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 099f0afd394..af866147ff2 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -34,6 +34,8 @@
 #include <linux/highmem.h>
 #include <linux/file.h>
 #include <asm/desc.h>
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
 
 #include "x86_emulate.h"
 #include "segment_descriptor.h"
@@ -41,6 +43,9 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+static DEFINE_SPINLOCK(kvm_lock);
+static LIST_HEAD(vm_list);
+
 struct kvm_arch_ops *kvm_arch_ops;
 struct kvm_stat kvm_stat;
 EXPORT_SYMBOL_GPL(kvm_stat);
@@ -230,9 +235,13 @@ static int kvm_dev_open(struct inode *inode, struct file *filp)
 		struct kvm_vcpu *vcpu = &kvm->vcpus[i];
 
 		mutex_init(&vcpu->mutex);
+		vcpu->cpu = -1;
 		vcpu->kvm = kvm;
 		vcpu->mmu.root_hpa = INVALID_PAGE;
 		INIT_LIST_HEAD(&vcpu->free_pages);
+		spin_lock(&kvm_lock);
+		list_add(&kvm->vm_list, &vm_list);
+		spin_unlock(&kvm_lock);
 	}
 	filp->private_data = kvm;
 	return 0;
@@ -272,7 +281,9 @@ static void kvm_free_physmem(struct kvm *kvm)
 
 static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
 {
-	vcpu_load(vcpu->kvm, vcpu_slot(vcpu));
+	if (!vcpu_load(vcpu->kvm, vcpu_slot(vcpu)))
+		return;
+
 	kvm_mmu_destroy(vcpu);
 	vcpu_put(vcpu);
 	kvm_arch_ops->vcpu_free(vcpu);
@@ -290,6 +301,9 @@ static int kvm_dev_release(struct inode *inode, struct file *filp)
 {
 	struct kvm *kvm = filp->private_data;
 
+	spin_lock(&kvm_lock);
+	list_del(&kvm->vm_list);
+	spin_unlock(&kvm_lock);
 	kvm_free_vcpus(kvm);
 	kvm_free_physmem(kvm);
 	kfree(kvm);
@@ -544,7 +558,6 @@ static int kvm_dev_ioctl_create_vcpu(struct kvm *kvm, int n)
 					   FX_IMAGE_ALIGN);
 	vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE;
 
-	vcpu->cpu = -1;  /* First load will set up TR */
 	r = kvm_arch_ops->vcpu_create(vcpu);
 	if (r < 0)
 		goto out_free_vcpus;
@@ -1360,6 +1373,9 @@ static int kvm_dev_ioctl_run(struct kvm *kvm, struct kvm_run *kvm_run)
 	if (!vcpu)
 		return -ENOENT;
 
+	/* re-sync apic's tpr */
+	vcpu->cr8 = kvm_run->cr8;
+
 	if (kvm_run->emulated) {
 		kvm_arch_ops->skip_emulated_instruction(vcpu);
 		kvm_run->emulated = 0;
@@ -2025,6 +2041,64 @@ static struct notifier_block kvm_reboot_notifier = {
 	.priority = 0,
 };
 
+/*
+ * Make sure that a cpu that is being hot-unplugged does not have any vcpus
+ * cached on it.
+ */
+static void decache_vcpus_on_cpu(int cpu)
+{
+	struct kvm *vm;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(vm, &vm_list, vm_list)
+		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+			vcpu = &vm->vcpus[i];
+			/*
+			 * If the vcpu is locked, then it is running on some
+			 * other cpu and therefore it is not cached on the
+			 * cpu in question.
+			 *
+			 * If it's not locked, check the last cpu it executed
+			 * on.
+			 */
+			if (mutex_trylock(&vcpu->mutex)) {
+				if (vcpu->cpu == cpu) {
+					kvm_arch_ops->vcpu_decache(vcpu);
+					vcpu->cpu = -1;
+				}
+				mutex_unlock(&vcpu->mutex);
+			}
+		}
+	spin_unlock(&kvm_lock);
+}
+
+static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
+			   void *v)
+{
+	int cpu = (long)v;
+
+	switch (val) {
+	case CPU_DEAD:
+	case CPU_UP_CANCELED:
+		decache_vcpus_on_cpu(cpu);
+		smp_call_function_single(cpu, kvm_arch_ops->hardware_disable,
+					 NULL, 0, 1);
+		break;
+	case CPU_UP_PREPARE:
+		smp_call_function_single(cpu, kvm_arch_ops->hardware_enable,
+					 NULL, 0, 1);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_cpu_notifier = {
+	.notifier_call = kvm_cpu_hotplug,
+	.priority = 20, /* must be > scheduler priority */
+};
+
 static __init void kvm_init_debug(void)
 {
 	struct kvm_stats_debugfs_item *p;
@@ -2044,6 +2118,30 @@ static void kvm_exit_debug(void)
 	debugfs_remove(debugfs_dir);
 }
 
+static int kvm_suspend(struct sys_device *dev, pm_message_t state)
+{
+	decache_vcpus_on_cpu(raw_smp_processor_id());
+	on_each_cpu(kvm_arch_ops->hardware_disable, 0, 0, 1);
+	return 0;
+}
+
+static int kvm_resume(struct sys_device *dev)
+{
+	on_each_cpu(kvm_arch_ops->hardware_enable, 0, 0, 1);
+	return 0;
+}
+
+static struct sysdev_class kvm_sysdev_class = {
+	set_kset_name("kvm"),
+	.suspend = kvm_suspend,
+	.resume = kvm_resume,
+};
+
+static struct sys_device kvm_sysdev = {
+	.id = 0,
+	.cls = &kvm_sysdev_class,
+};
+
 hpa_t bad_page_address;
 
 int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module)
@@ -2071,8 +2169,19 @@ int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module)
 	    return r;
 
 	on_each_cpu(kvm_arch_ops->hardware_enable, NULL, 0, 1);
+	r = register_cpu_notifier(&kvm_cpu_notifier);
+	if (r)
+		goto out_free_1;
 	register_reboot_notifier(&kvm_reboot_notifier);
 
+	r = sysdev_class_register(&kvm_sysdev_class);
+	if (r)
+		goto out_free_2;
+
+	r = sysdev_register(&kvm_sysdev);
+	if (r)
+		goto out_free_3;
+
 	kvm_chardev_ops.owner = module;
 
 	r = misc_register(&kvm_dev);
@@ -2084,7 +2193,13 @@ int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module)
 	return r;
 
 out_free:
+	sysdev_unregister(&kvm_sysdev);
+out_free_3:
+	sysdev_class_unregister(&kvm_sysdev_class);
+out_free_2:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
+	unregister_cpu_notifier(&kvm_cpu_notifier);
+out_free_1:
 	on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
 	kvm_arch_ops->hardware_unsetup();
 	return r;
@@ -2093,8 +2208,10 @@ out_free:
 void kvm_exit_arch(void)
 {
 	misc_deregister(&kvm_dev);
-
+	sysdev_unregister(&kvm_sysdev);
+	sysdev_class_unregister(&kvm_sysdev_class);
 	unregister_reboot_notifier(&kvm_reboot_notifier);
+	unregister_cpu_notifier(&kvm_cpu_notifier);
 	on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
 	kvm_arch_ops->hardware_unsetup();
 	kvm_arch_ops = NULL;
diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 149fa45fd9a..b6b90e9e130 100644
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -443,31 +443,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
 {
 	struct guest_walker walker;
-	pt_element_t guest_pte;
-	gpa_t gpa;
-
-	FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
-	guest_pte = *walker.ptep;
-	FNAME(release_walker)(&walker);
-
-	if (!is_present_pte(guest_pte))
-		return UNMAPPED_GVA;
-
-	if (walker.level == PT_DIRECTORY_LEVEL) {
-		ASSERT((guest_pte & PT_PAGE_SIZE_MASK));
-		ASSERT(PTTYPE == 64 || is_pse(vcpu));
+	gpa_t gpa = UNMAPPED_GVA;
+	int r;
 
-		gpa = (guest_pte & PT_DIR_BASE_ADDR_MASK) | (vaddr &
-			(PT_LEVEL_MASK(PT_PAGE_TABLE_LEVEL) | ~PAGE_MASK));
+	r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
 
-		if (PTTYPE == 32 && is_cpuid_PSE36())
-			gpa |= (guest_pte & PT32_DIR_PSE36_MASK) <<
-					(32 - PT32_DIR_PSE36_SHIFT);
-	} else {
-		gpa = (guest_pte & PT_BASE_ADDR_MASK);
-		gpa |= (vaddr & ~PAGE_MASK);
+	if (r) {
+		gpa = (gpa_t)walker.gfn << PAGE_SHIFT;
+		gpa |= vaddr & ~PAGE_MASK;
 	}
 
+	FNAME(release_walker)(&walker);
 	return gpa;
 }
 
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index 85f61dd1e93..83da4ea150a 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -528,7 +528,13 @@ static void init_vmcb(struct vmcb *vmcb)
 	save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK |
 		SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK;
 	save->cs.limit = 0xffff;
-	save->cs.base = 0xffff0000;
+	/*
+	 * cs.base should really be 0xffff0000, but vmx can't handle that, so
+	 * be consistent with it.
+	 *
+	 * Replace when we have real mode working for vmx.
+	 */
+	save->cs.base = 0xf0000;
 
 	save->gdtr.limit = 0xffff;
 	save->idtr.limit = 0xffff;
@@ -603,6 +609,10 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+static void svm_vcpu_decache(struct kvm_vcpu *vcpu)
+{
+}
+
 static void svm_cache_regs(struct kvm_vcpu *vcpu)
 {
 	vcpu->regs[VCPU_REGS_RAX] = vcpu->svm->vmcb->save.rax;
@@ -723,7 +733,7 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	}
 #endif
 	vcpu->svm->cr0 = cr0;
-	vcpu->svm->vmcb->save.cr0 = cr0 | CR0_PG_MASK;
+	vcpu->svm->vmcb->save.cr0 = cr0 | CR0_PG_MASK | CR0_WP_MASK;
 	vcpu->cr0 = cr0;
 }
 
@@ -1671,6 +1681,7 @@ static struct kvm_arch_ops svm_arch_ops = {
 
 	.vcpu_load = svm_vcpu_load,
 	.vcpu_put = svm_vcpu_put,
+	.vcpu_decache = svm_vcpu_decache,
 
 	.set_guest_debug = svm_guest_debug,
 	.get_msr = svm_get_msr,
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 27e05a77e21..1e640b89917 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -125,6 +125,15 @@ static void __vcpu_clear(void *arg)
 		per_cpu(current_vmcs, cpu) = NULL;
 }
 
+static void vcpu_clear(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->cpu != raw_smp_processor_id() && vcpu->cpu != -1)
+		smp_call_function_single(vcpu->cpu, __vcpu_clear, vcpu, 0, 1);
+	else
+		__vcpu_clear(vcpu);
+	vcpu->launched = 0;
+}
+
 static unsigned long vmcs_readl(unsigned long field)
 {
 	unsigned long value;
@@ -202,10 +211,8 @@ static struct kvm_vcpu *vmx_vcpu_load(struct kvm_vcpu *vcpu)
 
 	cpu = get_cpu();
 
-	if (vcpu->cpu != cpu) {
-		smp_call_function(__vcpu_clear, vcpu, 0, 1);
-		vcpu->launched = 0;
-	}
+	if (vcpu->cpu != cpu)
+		vcpu_clear(vcpu);
 
 	if (per_cpu(current_vmcs, cpu) != vcpu->vmcs) {
 		u8 error;
@@ -243,6 +250,11 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+static void vmx_vcpu_decache(struct kvm_vcpu *vcpu)
+{
+	vcpu_clear(vcpu);
+}
+
 static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
 	return vmcs_readl(GUEST_RFLAGS);
@@ -502,7 +514,7 @@ static __init int vmx_disabled_by_bios(void)
 	return (msr & 5) == 1; /* locked but not enabled */
 }
 
-static __init void hardware_enable(void *garbage)
+static void hardware_enable(void *garbage)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -1375,6 +1387,11 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
+static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+	return 0;
+}
 
 static int get_io_count(struct kvm_vcpu *vcpu, u64 *count)
 {
@@ -1635,6 +1652,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
 				      struct kvm_run *kvm_run) = {
 	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception,
 	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
+	[EXIT_REASON_TRIPLE_FAULT]            = handle_triple_fault,
 	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
 	[EXIT_REASON_CR_ACCESS]               = handle_cr,
 	[EXIT_REASON_DR_ACCESS]               = handle_dr,
@@ -1786,10 +1804,10 @@ again:
 		"kvm_vmx_return: "
 		/* Save guest registers, load host registers, keep flags */
 #ifdef CONFIG_X86_64
-		"xchg %3,     0(%%rsp) \n\t"
+		"xchg %3,     (%%rsp) \n\t"
 		"mov %%rax, %c[rax](%3) \n\t"
 		"mov %%rbx, %c[rbx](%3) \n\t"
-		"pushq 0(%%rsp); popq %c[rcx](%3) \n\t"
+		"pushq (%%rsp); popq %c[rcx](%3) \n\t"
 		"mov %%rdx, %c[rdx](%3) \n\t"
 		"mov %%rsi, %c[rsi](%3) \n\t"
 		"mov %%rdi, %c[rdi](%3) \n\t"
@@ -1804,24 +1822,24 @@ again:
 		"mov %%r15, %c[r15](%3) \n\t"
 		"mov %%cr2, %%rax   \n\t"
 		"mov %%rax, %c[cr2](%3) \n\t"
-		"mov 0(%%rsp), %3 \n\t"
+		"mov (%%rsp), %3 \n\t"
 
 		"pop  %%rcx; pop  %%r15; pop  %%r14; pop  %%r13; pop  %%r12;"
 		"pop  %%r11; pop  %%r10; pop  %%r9;  pop  %%r8;"
 		"pop  %%rbp; pop  %%rdi; pop  %%rsi;"
 		"pop  %%rdx; pop  %%rbx; pop  %%rax \n\t"
 #else
-		"xchg %3, 0(%%esp) \n\t"
+		"xchg %3, (%%esp) \n\t"
 		"mov %%eax, %c[rax](%3) \n\t"
 		"mov %%ebx, %c[rbx](%3) \n\t"
-		"pushl 0(%%esp); popl %c[rcx](%3) \n\t"
+		"pushl (%%esp); popl %c[rcx](%3) \n\t"
 		"mov %%edx, %c[rdx](%3) \n\t"
 		"mov %%esi, %c[rsi](%3) \n\t"
 		"mov %%edi, %c[rdi](%3) \n\t"
 		"mov %%ebp, %c[rbp](%3) \n\t"
 		"mov %%cr2, %%eax  \n\t"
 		"mov %%eax, %c[cr2](%3) \n\t"
-		"mov 0(%%esp), %3 \n\t"
+		"mov (%%esp), %3 \n\t"
 
 		"pop %%ecx; popa \n\t"
 #endif
@@ -1859,9 +1877,7 @@ again:
 	fx_restore(vcpu->host_fx_image);
 	vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0;
 
-#ifndef CONFIG_X86_64
 	asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
-#endif
 
 	/*
 	 * Profile KVM exit RIPs:
@@ -2012,6 +2028,7 @@ static struct kvm_arch_ops vmx_arch_ops = {
 
 	.vcpu_load = vmx_vcpu_load,
 	.vcpu_put = vmx_vcpu_put,
+	.vcpu_decache = vmx_vcpu_decache,
 
 	.set_guest_debug = set_guest_debug,
 	.get_msr = vmx_get_msr,
diff --git a/drivers/kvm/vmx.h b/drivers/kvm/vmx.h
index 4c0ab151836..d0dc93df411 100644
--- a/drivers/kvm/vmx.h
+++ b/drivers/kvm/vmx.h
@@ -180,6 +180,7 @@ enum vmcs_field {
 
 #define EXIT_REASON_EXCEPTION_NMI       0
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
+#define EXIT_REASON_TRIPLE_FAULT        2
 
 #define EXIT_REASON_PENDING_INTERRUPT   7