Merge branch 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm:
  x86: KVM geust: make setup_secondary_clock definition dependent on local apic
  KVM: MMU: Allow more than PAGES_PER_HPAGE write protections per large page
  KVM: avoid fx_init() schedule in atomic
  KVM: Avoid spurious execeptions after setting registers
  KVM: PIT: support mode 4
  KVM: x86 emulator: disable writeback on lmsw
  KVM: ppc: deliver INTERRUPT_FP_UNAVAIL to the guest
  KVM: ppc: Handle guest idle by emulating MSR[WE] writes
  KVM: x86: task switch: fix wrong bit setting for the busy flag
  KVM: VMX: Enable EPT feature for KVM
  KVM: VMX: Prepare an identity page table for EPT in real mode
  KVM: Export necessary function for EPT
  KVM: MMU: Remove #ifdef CONFIG_X86_64 to support 4 level EPT
  KVM: MMU: Add EPT support
  KVM: Add kvm_x86_ops get_tdp_level()
  KVM: MMU: Move some definitions to a header file
  KVM: VMX: EPT Feature Detection

arch/powerpc/kvm/booke_guest.c

@@ -49,6 +49,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "inst_emu",   VCPU_STAT(emulated_inst_exits) },
 	{ "dec",        VCPU_STAT(dec_exits) },
 	{ "ext_intr",   VCPU_STAT(ext_intr_exits) },
+	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ NULL }
 };
 
@@ -338,6 +339,11 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		}
 		break;
 
+	case BOOKE_INTERRUPT_FP_UNAVAIL:
+		kvmppc_queue_exception(vcpu, exit_nr);
+		r = RESUME_GUEST;
+		break;
+
 	case BOOKE_INTERRUPT_DATA_STORAGE:
 		vcpu->arch.dear = vcpu->arch.fault_dear;
 		vcpu->arch.esr = vcpu->arch.fault_esr;

arch/powerpc/kvm/powerpc.c

@@ -36,13 +36,12 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	/* XXX implement me */
-	return 0;
+	return !!(v->arch.pending_exceptions);
 }
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return 1;
+	return !(v->arch.msr & MSR_WE);
 }
 
 
@@ -214,6 +213,11 @@ static void kvmppc_decrementer_func(unsigned long data)
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
 
 	kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_DECREMENTER);
+
+	if (waitqueue_active(&vcpu->wq)) {
+		wake_up_interruptible(&vcpu->wq);
+		vcpu->stat.halt_wakeup++;
+	}
 }
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
@@ -339,6 +343,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	int r;
 	sigset_t sigsaved;
 
+	vcpu_load(vcpu);
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
@@ -363,12 +369,20 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
+	vcpu_put(vcpu);
+
 	return r;
 }
 
 int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 {
 	kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_EXTERNAL);
+
+	if (waitqueue_active(&vcpu->wq)) {
+		wake_up_interruptible(&vcpu->wq);
+		vcpu->stat.halt_wakeup++;
+	}
+
 	return 0;
 }
 

arch/x86/kernel/kvmclock.c

@@ -133,6 +133,7 @@ static int kvm_register_clock(void)
 	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
 }
 
+#ifdef CONFIG_X86_LOCAL_APIC
 static void kvm_setup_secondary_clock(void)
 {
 	/*
@@ -143,6 +144,7 @@ static void kvm_setup_secondary_clock(void)
 	/* ok, done with our trickery, call native */
 	setup_secondary_APIC_clock();
 }
+#endif
 
 /*
  * After the clock is registered, the host will keep writing to the
@@ -177,7 +179,9 @@ void __init kvmclock_init(void)
 		pv_time_ops.get_wallclock = kvm_get_wallclock;
 		pv_time_ops.set_wallclock = kvm_set_wallclock;
 		pv_time_ops.sched_clock = kvm_clock_read;
+#ifdef CONFIG_X86_LOCAL_APIC
 		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+#endif
 		machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
 		machine_ops.crash_shutdown  = kvm_crash_shutdown;

arch/x86/kvm/i8254.c

@@ -288,6 +288,8 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 	 * mode 1 is one shot, mode 2 is period, otherwise del timer */
 	switch (ps->channels[0].mode) {
 	case 1:
+        /* FIXME: enhance mode 4 precision */
+	case 4:
 		create_pit_timer(&ps->pit_timer, val, 0);
 		break;
 	case 2:

arch/x86/kvm/mmu.c

@@ -79,36 +79,6 @@ static int dbg = 1;
 	}
 #endif
 
-#define PT64_PT_BITS 9
-#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
-#define PT32_PT_BITS 10
-#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS)
-
-#define PT_WRITABLE_SHIFT 1
-
-#define PT_PRESENT_MASK (1ULL << 0)
-#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
-#define PT_USER_MASK (1ULL << 2)
-#define PT_PWT_MASK (1ULL << 3)
-#define PT_PCD_MASK (1ULL << 4)
-#define PT_ACCESSED_MASK (1ULL << 5)
-#define PT_DIRTY_MASK (1ULL << 6)
-#define PT_PAGE_SIZE_MASK (1ULL << 7)
-#define PT_PAT_MASK (1ULL << 7)
-#define PT_GLOBAL_MASK (1ULL << 8)
-#define PT64_NX_SHIFT 63
-#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT)
-
-#define PT_PAT_SHIFT 7
-#define PT_DIR_PAT_SHIFT 12
-#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT)
-
-#define PT32_DIR_PSE36_SIZE 4
-#define PT32_DIR_PSE36_SHIFT 13
-#define PT32_DIR_PSE36_MASK \
-	(((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
-
-
 #define PT_FIRST_AVAIL_BITS_SHIFT 9
 #define PT64_SECOND_AVAIL_BITS_SHIFT 52
 
@@ -154,10 +124,6 @@ static int dbg = 1;
 #define PFERR_USER_MASK (1U << 2)
 #define PFERR_FETCH_MASK (1U << 4)
 
-#define PT64_ROOT_LEVEL 4
-#define PT32_ROOT_LEVEL 2
-#define PT32E_ROOT_LEVEL 3
-
 #define PT_DIRECTORY_LEVEL 2
 #define PT_PAGE_TABLE_LEVEL 1
 
@@ -186,6 +152,12 @@ static struct kmem_cache *mmu_page_header_cache;
 
 static u64 __read_mostly shadow_trap_nonpresent_pte;
 static u64 __read_mostly shadow_notrap_nonpresent_pte;
+static u64 __read_mostly shadow_base_present_pte;
+static u64 __read_mostly shadow_nx_mask;
+static u64 __read_mostly shadow_x_mask;	/* mutual exclusive with nx_mask */
+static u64 __read_mostly shadow_user_mask;
+static u64 __read_mostly shadow_accessed_mask;
+static u64 __read_mostly shadow_dirty_mask;
 
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
 {
@@ -194,6 +166,23 @@ void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_nonpresent_ptes);
 
+void kvm_mmu_set_base_ptes(u64 base_pte)
+{
+	shadow_base_present_pte = base_pte;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
+
+void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
+		u64 dirty_mask, u64 nx_mask, u64 x_mask)
+{
+	shadow_user_mask = user_mask;
+	shadow_accessed_mask = accessed_mask;
+	shadow_dirty_mask = dirty_mask;
+	shadow_nx_mask = nx_mask;
+	shadow_x_mask = x_mask;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
+
 static int is_write_protection(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.cr0 & X86_CR0_WP;
@@ -232,7 +221,7 @@ static int is_writeble_pte(unsigned long pte)
 
 static int is_dirty_pte(unsigned long pte)
 {
-	return pte & PT_DIRTY_MASK;
+	return pte & shadow_dirty_mask;
 }
 
 static int is_rmap_pte(u64 pte)
@@ -387,7 +376,6 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn)
 
 	write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
 	*write_count += 1;
-	WARN_ON(*write_count > KVM_PAGES_PER_HPAGE);
 }
 
 static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
@@ -547,7 +535,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 		return;
 	sp = page_header(__pa(spte));
 	pfn = spte_to_pfn(*spte);
-	if (*spte & PT_ACCESSED_MASK)
+	if (*spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
 	if (is_writeble_pte(*spte))
 		kvm_release_pfn_dirty(pfn);
@@ -1073,17 +1061,17 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 	 * whether the guest actually used the pte (in order to detect
 	 * demand paging).
 	 */
-	spte = PT_PRESENT_MASK | PT_DIRTY_MASK;
+	spte = shadow_base_present_pte | shadow_dirty_mask;
 	if (!speculative)
 		pte_access |= PT_ACCESSED_MASK;
 	if (!dirty)
 		pte_access &= ~ACC_WRITE_MASK;
-	if (!(pte_access & ACC_EXEC_MASK))
-		spte |= PT64_NX_MASK;
-
-	spte |= PT_PRESENT_MASK;
+	if (pte_access & ACC_EXEC_MASK)
+		spte |= shadow_x_mask;
+	else
+		spte |= shadow_nx_mask;
 	if (pte_access & ACC_USER_MASK)
-		spte |= PT_USER_MASK;
+		spte |= shadow_user_mask;
 	if (largepage)
 		spte |= PT_PAGE_SIZE_MASK;
 
@@ -1188,8 +1176,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 				return -ENOMEM;
 			}
 
-			table[index] = __pa(new_table->spt) | PT_PRESENT_MASK
-				| PT_WRITABLE_MASK | PT_USER_MASK;
+			table[index] = __pa(new_table->spt)
+				| PT_PRESENT_MASK | PT_WRITABLE_MASK
+				| shadow_user_mask | shadow_x_mask;
 		}
 		table_addr = table[index] & PT64_BASE_ADDR_MASK;
 	}
@@ -1244,7 +1233,6 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 		return;
 	spin_lock(&vcpu->kvm->mmu_lock);
-#ifdef CONFIG_X86_64
 	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
@@ -1256,7 +1244,6 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
 		spin_unlock(&vcpu->kvm->mmu_lock);
 		return;
 	}
-#endif
 	for (i = 0; i < 4; ++i) {
 		hpa_t root = vcpu->arch.mmu.pae_root[i];
 
@@ -1282,7 +1269,6 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 
 	root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
 
-#ifdef CONFIG_X86_64
 	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
@@ -1297,7 +1283,6 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		vcpu->arch.mmu.root_hpa = root;
 		return;
 	}
-#endif
 	metaphysical = !is_paging(vcpu);
 	if (tdp_enabled)
 		metaphysical = 1;
@@ -1377,7 +1362,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
 	spin_lock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_free_some_pages(vcpu);
 	r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
-			 largepage, gfn, pfn, TDP_ROOT_LEVEL);
+			 largepage, gfn, pfn, kvm_x86_ops->get_tdp_level());
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
 	return r;
@@ -1484,7 +1469,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	context->page_fault = tdp_page_fault;
 	context->free = nonpaging_free;
 	context->prefetch_page = nonpaging_prefetch_page;
-	context->shadow_root_level = TDP_ROOT_LEVEL;
+	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
 	context->root_hpa = INVALID_PAGE;
 
 	if (!is_paging(vcpu)) {
@@ -1633,7 +1618,7 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
 {
 	u64 *spte = vcpu->arch.last_pte_updated;
 
-	return !!(spte && (*spte & PT_ACCESSED_MASK));
+	return !!(spte && (*spte & shadow_accessed_mask));
 }
 
 static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,

arch/x86/kvm/mmu.h

@@ -3,11 +3,38 @@
 
 #include <linux/kvm_host.h>
 
-#ifdef CONFIG_X86_64
-#define TDP_ROOT_LEVEL PT64_ROOT_LEVEL
-#else
-#define TDP_ROOT_LEVEL PT32E_ROOT_LEVEL
-#endif
+#define PT64_PT_BITS 9
+#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
+#define PT32_PT_BITS 10
+#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS)
+
+#define PT_WRITABLE_SHIFT 1
+
+#define PT_PRESENT_MASK (1ULL << 0)
+#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
+#define PT_USER_MASK (1ULL << 2)
+#define PT_PWT_MASK (1ULL << 3)
+#define PT_PCD_MASK (1ULL << 4)
+#define PT_ACCESSED_MASK (1ULL << 5)
+#define PT_DIRTY_MASK (1ULL << 6)
+#define PT_PAGE_SIZE_MASK (1ULL << 7)
+#define PT_PAT_MASK (1ULL << 7)
+#define PT_GLOBAL_MASK (1ULL << 8)
+#define PT64_NX_SHIFT 63
+#define PT64_NX_MASK (1ULL << PT64_NX_SHIFT)
+
+#define PT_PAT_SHIFT 7
+#define PT_DIR_PAT_SHIFT 12
+#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT)
+
+#define PT32_DIR_PSE36_SIZE 4
+#define PT32_DIR_PSE36_SHIFT 13
+#define PT32_DIR_PSE36_MASK \
+	(((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
+
+#define PT64_ROOT_LEVEL 4
+#define PT32_ROOT_LEVEL 2
+#define PT32E_ROOT_LEVEL 3
 
 static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 {

arch/x86/kvm/svm.c

@@ -1863,6 +1863,15 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
+static int get_npt_level(void)
+{
+#ifdef CONFIG_X86_64
+	return PT64_ROOT_LEVEL;
+#else
+	return PT32E_ROOT_LEVEL;
+#endif
+}
+
 static struct kvm_x86_ops svm_x86_ops = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -1920,6 +1929,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.inject_pending_vectors = do_interrupt_requests,
 
 	.set_tss_addr = svm_set_tss_addr,
+	.get_tdp_level = get_npt_level,
 };
 
 static int __init svm_init(void)

arch/x86/kvm/vmx.h

@@ -35,6 +35,8 @@
 #define CPU_BASED_MWAIT_EXITING                 0x00000400
 #define CPU_BASED_RDPMC_EXITING                 0x00000800
 #define CPU_BASED_RDTSC_EXITING                 0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING		0x00008000
+#define CPU_BASED_CR3_STORE_EXITING		0x00010000
 #define CPU_BASED_CR8_LOAD_EXITING              0x00080000
 #define CPU_BASED_CR8_STORE_EXITING             0x00100000
 #define CPU_BASED_TPR_SHADOW                    0x00200000
@@ -49,6 +51,7 @@
  * Definitions of Secondary Processor-Based VM-Execution Controls.
  */
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT               0x00000002
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 
@@ -100,10 +103,22 @@ enum vmcs_field {
 	VIRTUAL_APIC_PAGE_ADDR_HIGH     = 0x00002013,
 	APIC_ACCESS_ADDR		= 0x00002014,
 	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
+	EPT_POINTER                     = 0x0000201a,
+	EPT_POINTER_HIGH                = 0x0000201b,
+	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
+	GUEST_PHYSICAL_ADDRESS_HIGH     = 0x00002401,
 	VMCS_LINK_POINTER               = 0x00002800,
 	VMCS_LINK_POINTER_HIGH          = 0x00002801,
 	GUEST_IA32_DEBUGCTL             = 0x00002802,
 	GUEST_IA32_DEBUGCTL_HIGH        = 0x00002803,
+	GUEST_PDPTR0                    = 0x0000280a,
+	GUEST_PDPTR0_HIGH               = 0x0000280b,
+	GUEST_PDPTR1                    = 0x0000280c,
+	GUEST_PDPTR1_HIGH               = 0x0000280d,
+	GUEST_PDPTR2                    = 0x0000280e,
+	GUEST_PDPTR2_HIGH               = 0x0000280f,
+	GUEST_PDPTR3                    = 0x00002810,
+	GUEST_PDPTR3_HIGH               = 0x00002811,
 	PIN_BASED_VM_EXEC_CONTROL       = 0x00004000,
 	CPU_BASED_VM_EXEC_CONTROL       = 0x00004002,
 	EXCEPTION_BITMAP                = 0x00004004,
@@ -226,6 +241,8 @@ enum vmcs_field {
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
+#define EXIT_REASON_EPT_VIOLATION       48
+#define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_WBINVD		54
 
 /*
@@ -316,15 +333,36 @@ enum vmcs_field {
 #define MSR_IA32_VMX_CR4_FIXED1                 0x489
 #define MSR_IA32_VMX_VMCS_ENUM                  0x48a
 #define MSR_IA32_VMX_PROCBASED_CTLS2            0x48b
+#define MSR_IA32_VMX_EPT_VPID_CAP               0x48c
 
 #define MSR_IA32_FEATURE_CONTROL                0x3a
 #define MSR_IA32_FEATURE_CONTROL_LOCKED         0x1
 #define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED  0x4
 
 #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	9
+#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	10
 
 #define VMX_NR_VPIDS				(1 << 16)
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
 #define VMX_VPID_EXTENT_ALL_CONTEXT		2
 
+#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
+#define VMX_EPT_EXTENT_CONTEXT			1
+#define VMX_EPT_EXTENT_GLOBAL			2
+#define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
+#define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
+#define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
+#define VMX_EPT_DEFAULT_GAW			3
+#define VMX_EPT_MAX_GAW				0x4
+#define VMX_EPT_MT_EPTE_SHIFT			3
+#define VMX_EPT_GAW_EPTP_SHIFT			3
+#define VMX_EPT_DEFAULT_MT			0x6ull
+#define VMX_EPT_READABLE_MASK			0x1ull
+#define VMX_EPT_WRITABLE_MASK			0x2ull
+#define VMX_EPT_EXECUTABLE_MASK			0x4ull
+#define VMX_EPT_FAKE_ACCESSED_MASK		(1ull << 62)
+#define VMX_EPT_FAKE_DIRTY_MASK			(1ull << 63)
+
+#define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
+
 #endif

arch/x86/kvm/x86.c

@@ -2417,6 +2417,9 @@ int kvm_arch_init(void *opaque)
 
 	kvm_x86_ops = ops;
 	kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
+	kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
+	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
+			PT_DIRTY_MASK, PT64_NX_MASK, 0);
 	return 0;
 
 out:
@@ -3019,6 +3022,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 
 	kvm_x86_ops->decache_regs(vcpu);
 
+	vcpu->arch.exception.pending = false;
+
 	vcpu_put(vcpu);
 
 	return 0;
@@ -3481,7 +3486,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	}
 
 	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
-		cseg_desc.type &= ~(1 << 8); //clear the B flag
+		cseg_desc.type &= ~(1 << 1); //clear the B flag
 		save_guest_segment_descriptor(vcpu, tr_seg.selector,
 					      &cseg_desc);
 	}
@@ -3507,7 +3512,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	}
 
 	if (reason != TASK_SWITCH_IRET) {
-		nseg_desc.type |= (1 << 8);
+		nseg_desc.type |= (1 << 1);
 		save_guest_segment_descriptor(vcpu, tss_selector,
 					      &nseg_desc);
 	}
@@ -3698,10 +3703,19 @@ void fx_init(struct kvm_vcpu *vcpu)
 {
 	unsigned after_mxcsr_mask;
 
+	/*
+	 * Touch the fpu the first time in non atomic context as if
+	 * this is the first fpu instruction the exception handler
+	 * will fire before the instruction returns and it'll have to
+	 * allocate ram with GFP_KERNEL.
+	 */
+	if (!used_math())
+		fx_save(&vcpu->arch.host_fx_image);
+
 	/* Initialize guest FPU by resetting ours and saving into guest's */
 	preempt_disable();
 	fx_save(&vcpu->arch.host_fx_image);
-	fpu_init();
+	fx_finit();
 	fx_save(&vcpu->arch.guest_fx_image);
 	fx_restore(&vcpu->arch.host_fx_image);
 	preempt_enable();
@@ -3906,6 +3920,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_physmem(kvm);
 	if (kvm->arch.apic_access_page)
 		put_page(kvm->arch.apic_access_page);
+	if (kvm->arch.ept_identity_pagetable)
+		put_page(kvm->arch.ept_identity_pagetable);
 	kfree(kvm);
 }
 

arch/x86/kvm/x86_emulate.c

@@ -1761,6 +1761,7 @@ twobyte_insn:
 		case 6: /* lmsw */
 			realmode_lmsw(ctxt->vcpu, (u16)c->src.val,
 				      &ctxt->eflags);
+			c->dst.type = OP_NONE;
 			break;
 		case 7: /* invlpg*/
 			emulate_invlpg(ctxt->vcpu, memop);

include/asm-powerpc/kvm_host.h

@@ -59,6 +59,7 @@ struct kvm_vcpu_stat {
 	u32 emulated_inst_exits;
 	u32 dec_exits;
 	u32 ext_intr_exits;
+	u32 halt_wakeup;
 };
 
 struct tlbe {

include/asm-powerpc/kvm_ppc.h

@@ -77,12 +77,17 @@ static inline void kvmppc_clear_exception(struct kvm_vcpu *vcpu, int exception)
 	clear_bit(priority, &vcpu->arch.pending_exceptions);
 }
 
+/* Helper function for "full" MSR writes. No need to call this if only EE is
+ * changing. */
 static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 {
 	if ((new_msr & MSR_PR) != (vcpu->arch.msr & MSR_PR))
 		kvmppc_mmu_priv_switch(vcpu, new_msr & MSR_PR);
 
 	vcpu->arch.msr = new_msr;
+
+	if (vcpu->arch.msr & MSR_WE)
+		kvm_vcpu_block(vcpu);
 }
 
 #endif /* __POWERPC_KVM_PPC_H__ */

include/asm-x86/kvm_host.h

@@ -314,6 +314,9 @@ struct kvm_arch{
 	struct page *apic_access_page;
 
 	gpa_t wall_clock;
+
+	struct page *ept_identity_pagetable;
+	bool ept_identity_pagetable_done;
 };
 
 struct kvm_vm_stat {
@@ -422,6 +425,7 @@ struct kvm_x86_ops {
 				       struct kvm_run *run);
 
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
+	int (*get_tdp_level)(void);
 };
 
 extern struct kvm_x86_ops *kvm_x86_ops;
@@ -433,6 +437,9 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
 int kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
+void kvm_mmu_set_base_ptes(u64 base_pte);
+void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
+		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
@@ -620,7 +627,7 @@ static inline void fx_restore(struct i387_fxsave_struct *image)
 	asm("fxrstor (%0)":: "r" (image));
 }
 
-static inline void fpu_init(void)
+static inline void fx_finit(void)
 {
 	asm("finit");
 }
@@ -644,6 +651,7 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 #define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
 #define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
 #define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
+#define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
 #define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
 
 #define MSR_IA32_TIME_STAMP_COUNTER		0x010

virt/kvm/kvm_main.c

@@ -522,6 +522,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 		return bad_hva();
 	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
 }
+EXPORT_SYMBOL_GPL(gfn_to_hva);
 
 /*
  * Requires current->mm->mmap_sem to be held