Merge branch 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (202 commits)
  MAINTAINERS: update KVM entry
  KVM: correct error-handling code
  KVM: fix compile warnings on s390
  KVM: VMX: Check cpl before emulating debug register access
  KVM: fix misreporting of coalesced interrupts by kvm tracer
  KVM: x86: drop duplicate kvm_flush_remote_tlb calls
  KVM: VMX: call vmx_load_host_state() only if msr is cached
  KVM: VMX: Conditionally reload debug register 6
  KVM: Use thread debug register storage instead of kvm specific data
  KVM guest: do not batch pte updates from interrupt context
  KVM: Fix coalesced interrupt reporting in IOAPIC
  KVM guest: fix bogus wallclock physical address calculation
  KVM: VMX: Fix cr8 exiting control clobbering by EPT
  KVM: Optimize kvm_mmu_unprotect_page_virt() for tdp
  KVM: Document KVM_CAP_IRQCHIP
  KVM: Protect update_cr8_intercept() when running without an apic
  KVM: VMX: Fix EPT with WP bit change during paging
  KVM: Use kvm_{read,write}_guest_virt() to read and write segment descriptors
  KVM: x86 emulator: Add adc and sbb missing decoder flags
  KVM: Add missing #include
  ...

Documentation/ioctl/ioctl-number.txt

@@ -193,7 +193,7 @@ Code	Seq#	Include File		Comments
 0xAD	00	Netfilter device	in development:
 					<mailto:rusty@rustcorp.com.au>	
 0xAE	all	linux/kvm.h		Kernel-based Virtual Machine
-					<mailto:kvm-devel@lists.sourceforge.net>
+					<mailto:kvm@vger.kernel.org>
 0xB0	all	RATIO devices		in development:
 					<mailto:vgo@ratio.de>
 0xB1	00-1F	PPPoX			<mailto:mostrows@styx.uwaterloo.ca>

Documentation/kernel-parameters.txt

@@ -57,6 +57,7 @@ parameter is applicable:
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
 	JOY	Appropriate joystick support is enabled.
+	KVM	Kernel Virtual Machine support is enabled.
 	LIBATA  Libata driver is enabled
 	LP	Printer support is enabled.
 	LOOP	Loopback device support is enabled.
@@ -1098,6 +1099,44 @@ and is between 256 and 4096 characters. It is defined in the file
 	kstack=N	[X86] Print N words from the kernel stack
 			in oops dumps.
 
+	kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
+			Default is 0 (don't ignore, but inject #GP)
+
+	kvm.oos_shadow=	[KVM] Disable out-of-sync shadow paging.
+			Default is 1 (enabled)
+
+	kvm-amd.nested=	[KVM,AMD] Allow nested virtualization in KVM/SVM.
+			Default is 0 (off)
+
+	kvm-amd.npt=	[KVM,AMD] Disable nested paging (virtualized MMU)
+			for all guests.
+			Default is 1 (enabled) if in 64bit or 32bit-PAE mode
+
+	kvm-intel.bypass_guest_pf=
+			[KVM,Intel] Disables bypassing of guest page faults
+			on Intel chips. Default is 1 (enabled)
+
+	kvm-intel.ept=	[KVM,Intel] Disable extended page tables
+			(virtualized MMU) support on capable Intel chips.
+			Default is 1 (enabled)
+
+	kvm-intel.emulate_invalid_guest_state=
+			[KVM,Intel] Enable emulation of invalid guest states
+			Default is 0 (disabled)
+
+	kvm-intel.flexpriority=
+			[KVM,Intel] Disable FlexPriority feature (TPR shadow).
+			Default is 1 (enabled)
+
+	kvm-intel.unrestricted_guest=
+			[KVM,Intel] Disable unrestricted guest feature
+			(virtualized real and unpaged mode) on capable
+			Intel chips. Default is 1 (enabled)
+
+	kvm-intel.vpid=	[KVM,Intel] Disable Virtual Processor Identification
+			feature (tagged TLBs) on capable Intel chips.
+			Default is 1 (enabled)
+
 	l2cr=		[PPC]
 
 	l3cr=		[PPC]

MAINTAINERS

@@ -2926,6 +2926,7 @@ F:	include/linux/sunrpc/
 
 KERNEL VIRTUAL MACHINE (KVM)
 M:	Avi Kivity <avi@redhat.com>
+M:	Marcelo Tosatti <mtosatti@redhat.com>
 L:	kvm@vger.kernel.org
 W:	http://kvm.qumranet.com
 S:	Supported

arch/ia64/include/asm/kvm_host.h

@@ -235,7 +235,8 @@ struct kvm_vm_data {
 #define KVM_REQ_PTC_G		32
 #define KVM_REQ_RESUME		33
 
-#define KVM_PAGES_PER_HPAGE	1
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	1
 
 struct kvm;
 struct kvm_vcpu;
@@ -465,7 +466,6 @@ struct kvm_arch {
 	unsigned long	metaphysical_rr4;
 	unsigned long	vmm_init_rr;
 
-	int		online_vcpus;
 	int		is_sn2;
 
 	struct kvm_ioapic *vioapic;

arch/ia64/include/asm/kvm_para.h

@@ -19,9 +19,13 @@
  *
  */
 
+#ifdef __KERNEL__
+
 static inline unsigned int kvm_arch_para_features(void)
 {
 	return 0;
 }
 
 #endif
+
+#endif

arch/ia64/kvm/Kconfig

 #
 # KVM configuration
 #
-config HAVE_KVM
-	bool
 
-config HAVE_KVM_IRQCHIP
-       bool
-       default y
+source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
@@ -28,6 +24,8 @@ config KVM
 	depends on PCI
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select HAVE_KVM_IRQCHIP
+	select KVM_APIC_ARCHITECTURE
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
@@ -49,9 +47,6 @@ config KVM_INTEL
 	  Provides support for KVM on Itanium 2 processors equipped with the VT
 	  extensions.
 
-config KVM_TRACE
-       bool
-
 source drivers/virtio/Kconfig
 
 endif # VIRTUALIZATION

arch/ia64/kvm/kvm-ia64.c

@@ -210,16 +210,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 }
 
-static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
-					gpa_t addr, int len, int is_write)
-{
-	struct kvm_io_device *dev;
-
-	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len, is_write);
-
-	return dev;
-}
-
 static int handle_vm_error(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
@@ -231,6 +221,7 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct kvm_mmio_req *p;
 	struct kvm_io_device *mmio_dev;
+	int r;
 
 	p = kvm_get_vcpu_ioreq(vcpu);
 
@@ -247,16 +238,13 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->exit_reason = KVM_EXIT_MMIO;
 	return 0;
 mmio:
-	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr, p->size, !p->dir);
-	if (mmio_dev) {
-		if (!p->dir)
-			kvm_iodevice_write(mmio_dev, p->addr, p->size,
-						&p->data);
+	if (p->dir)
+		r = kvm_io_bus_read(&vcpu->kvm->mmio_bus, p->addr,
+				    p->size, &p->data);
 	else
-			kvm_iodevice_read(mmio_dev, p->addr, p->size,
-						&p->data);
-
-	} else
+		r = kvm_io_bus_write(&vcpu->kvm->mmio_bus, p->addr,
+				     p->size, &p->data);
+	if (r)
 		printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr);
 	p->state = STATE_IORESP_READY;
 
@@ -337,13 +325,12 @@ static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
 {
 	union ia64_lid lid;
 	int i;
+	struct kvm_vcpu *vcpu;
 
-	for (i = 0; i < kvm->arch.online_vcpus; i++) {
-		if (kvm->vcpus[i]) {
-			lid.val = VCPU_LID(kvm->vcpus[i]);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		lid.val = VCPU_LID(vcpu);
 		if (lid.id == id && lid.eid == eid)
-				return kvm->vcpus[i];
-		}
+			return vcpu;
 	}
 
 	return NULL;
@@ -409,21 +396,21 @@ static int handle_global_purge(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	struct kvm *kvm = vcpu->kvm;
 	struct call_data call_data;
 	int i;
+	struct kvm_vcpu *vcpui;
 
 	call_data.ptc_g_data = p->u.ptc_g_data;
 
-	for (i = 0; i < kvm->arch.online_vcpus; i++) {
-		if (!kvm->vcpus[i] || kvm->vcpus[i]->arch.mp_state ==
-						KVM_MP_STATE_UNINITIALIZED ||
-					vcpu == kvm->vcpus[i])
+	kvm_for_each_vcpu(i, vcpui, kvm) {
+		if (vcpui->arch.mp_state == KVM_MP_STATE_UNINITIALIZED ||
+				vcpu == vcpui)
 			continue;
 
-		if (waitqueue_active(&kvm->vcpus[i]->wq))
-			wake_up_interruptible(&kvm->vcpus[i]->wq);
+		if (waitqueue_active(&vcpui->wq))
+			wake_up_interruptible(&vcpui->wq);
 
-		if (kvm->vcpus[i]->cpu != -1) {
-			call_data.vcpu = kvm->vcpus[i];
-			smp_call_function_single(kvm->vcpus[i]->cpu,
+		if (vcpui->cpu != -1) {
+			call_data.vcpu = vcpui;
+			smp_call_function_single(vcpui->cpu,
 					vcpu_global_purge, &call_data, 1);
 		} else
 			printk(KERN_WARNING"kvm: Uninit vcpu received ipi!\n");
@@ -852,8 +839,6 @@ struct  kvm *kvm_arch_create_vm(void)
 
 	kvm_init_vm(kvm);
 
-	kvm->arch.online_vcpus = 0;
-
 	return kvm;
 
 }
@@ -1000,10 +985,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->irq_lock);
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 				    irq_event.irq, irq_event.level);
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->irq_lock);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,
@@ -1216,7 +1201,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	if (IS_ERR(vmm_vcpu))
 		return PTR_ERR(vmm_vcpu);
 
-	if (vcpu->vcpu_id == 0) {
+	if (kvm_vcpu_is_bsp(vcpu)) {
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 		/*Set entry address for first run.*/
@@ -1224,7 +1209,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 		/*Initialize itc offset for vcpus*/
 		itc_offset = 0UL - kvm_get_itc(vcpu);
-		for (i = 0; i < kvm->arch.online_vcpus; i++) {
+		for (i = 0; i < KVM_MAX_VCPUS; i++) {
 			v = (struct kvm_vcpu *)((char *)vcpu +
 					sizeof(struct kvm_vcpu_data) * i);
 			v->arch.itc_offset = itc_offset;
@@ -1356,8 +1341,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 		goto fail;
 	}
 
-	kvm->arch.online_vcpus++;
-
 	return vcpu;
 fail:
 	return ERR_PTR(r);
@@ -1952,19 +1935,6 @@ int kvm_highest_pending_irq(struct kvm_vcpu *vcpu)
     return find_highest_bits((int *)&vpd->irr[0]);
 }
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
-{
-	if (kvm_highest_pending_irq(vcpu) != -1)
-		return 1;
-	return 0;
-}
-
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	/* do real check here */
-	return 1;
-}
-
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.timer_fired;
@@ -1977,7 +1947,8 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE;
+	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) ||
+		(kvm_highest_pending_irq(vcpu) != -1);
 }
 
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,

arch/ia64/kvm/vcpu.c

@@ -830,8 +830,8 @@ static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
 
 	kvm = (struct kvm *)KVM_VM_BASE;
 
-	if (vcpu->vcpu_id == 0) {
-		for (i = 0; i < kvm->arch.online_vcpus; i++) {
+	if (kvm_vcpu_is_bsp(vcpu)) {
+		for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) {
 			v = (struct kvm_vcpu *)((char *)vcpu +
 					sizeof(struct kvm_vcpu_data) * i);
 			VMX(v, itc_offset) = itc_offset;

arch/powerpc/include/asm/kvm_host.h

@@ -34,7 +34,8 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
 /* We don't currently support large pages. */
-#define KVM_PAGES_PER_HPAGE (1UL << 31)
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
 
 struct kvm;
 struct kvm_run;
@@ -153,7 +154,6 @@ struct kvm_vcpu_arch {
 	u32 pid;
 	u32 swap_pid;
 
-	u32 pvr;
 	u32 ccr0;
 	u32 ccr1;
 	u32 dbcr0;

arch/powerpc/kvm/44x.c

@@ -138,7 +138,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
 
-static int kvmppc_44x_init(void)
+static int __init kvmppc_44x_init(void)
 {
 	int r;
 
@@ -149,7 +149,7 @@ static int kvmppc_44x_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), THIS_MODULE);
 }
 
-static void kvmppc_44x_exit(void)
+static void __exit kvmppc_44x_exit(void)
 {
 	kvmppc_booke_exit();
 }

arch/powerpc/kvm/44x_tlb.c

@@ -30,6 +30,7 @@
 #include "timing.h"
 
 #include "44x_tlb.h"
+#include "trace.h"
 
 #ifndef PPC44x_TLBE_SIZE
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_4K
@@ -263,7 +264,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 
 	/* XXX set tlb_44x_index to stlb_index? */
 
-	KVMTRACE_1D(STLB_INVAL, &vcpu_44x->vcpu, stlb_index, handler);
+	trace_kvm_stlb_inval(stlb_index);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
@@ -365,8 +366,8 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 	/* Insert shadow mapping into hardware TLB. */
 	kvmppc_44x_tlbe_set_modified(vcpu_44x, victim);
 	kvmppc_44x_tlbwe(victim, &stlbe);
-	KVMTRACE_5D(STLB_WRITE, vcpu, victim, stlbe.tid, stlbe.word0, stlbe.word1,
-	            stlbe.word2, handler);
+	trace_kvm_stlb_write(victim, stlbe.tid, stlbe.word0, stlbe.word1,
+			     stlbe.word2);
 }
 
 /* For a particular guest TLB entry, invalidate the corresponding host TLB
@@ -485,8 +486,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, gtlb_index, tlbe->tid, tlbe->word0,
-	            tlbe->word1, tlbe->word2, handler);
+	trace_kvm_gtlb_write(gtlb_index, tlbe->tid, tlbe->word0, tlbe->word1,
+			     tlbe->word2);
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
 	return EMULATE_DONE;

arch/powerpc/kvm/Kconfig

@@ -2,8 +2,7 @@
 # KVM configuration
 #
 
-config HAVE_KVM_IRQCHIP
-       bool
+source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
@@ -59,17 +58,6 @@ config KVM_E500
 
 	  If unsure, say N.
 
-config KVM_TRACE
-	bool "KVM trace support"
-	depends on KVM && MARKERS && SYSFS
-	select RELAY
-	select DEBUG_FS
-	default n
-	---help---
-	  This option allows reading a trace of kvm-related events through
-	  relayfs.  Note the ABI is not considered stable and will be
-	  modified in future updates.
-
 source drivers/virtio/Kconfig
 
 endif # VIRTUALIZATION

arch/powerpc/kvm/Makefile

@@ -8,7 +8,9 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm
 
 common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
-common-objs-$(CONFIG_KVM_TRACE)  += $(addprefix ../../../virt/kvm/, kvm_trace.o)
+CFLAGS_44x_tlb.o  := -I.
+CFLAGS_e500_tlb.o := -I.
+CFLAGS_emulate.o  := -I.
 
 kvm-objs := $(common-objs-y) powerpc.o emulate.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o

arch/powerpc/kvm/booke.c

@@ -520,7 +520,7 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return kvmppc_core_vcpu_translate(vcpu, tr);
 }
 
-int kvmppc_booke_init(void)
+int __init kvmppc_booke_init(void)
 {
 	unsigned long ivor[16];
 	unsigned long max_ivor = 0;

arch/powerpc/kvm/e500.c

@@ -60,9 +60,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvmppc_e500_tlb_setup(vcpu_e500);
 
-	/* Use the same core vertion as host's */
-	vcpu->arch.pvr = mfspr(SPRN_PVR);
-
 	return 0;
 }
 
@@ -132,7 +129,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-static int kvmppc_e500_init(void)
+static int __init kvmppc_e500_init(void)
 {
 	int r, i;
 	unsigned long ivor[3];
@@ -160,7 +157,7 @@ static int kvmppc_e500_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
 }
 
-static void kvmppc_e500_exit(void)
+static void __init kvmppc_e500_exit(void)
 {
 	kvmppc_booke_exit();
 }

arch/powerpc/kvm/e500_emulate.c

@@ -180,6 +180,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_MMUCSR0:
 		vcpu->arch.gpr[rt] = 0; break;
 
+	case SPRN_MMUCFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_MMUCFG); break;
+
 	/* extra exceptions */
 	case SPRN_IVOR32:
 		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];

arch/powerpc/kvm/e500_tlb.c

@@ -22,6 +22,7 @@
 
 #include "../mm/mmu_decl.h"
 #include "e500_tlb.h"
+#include "trace.h"
 
 #define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
 
@@ -224,9 +225,8 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
 	stlbe->mas1 = 0;
-	KVMTRACE_5D(STLB_INVAL, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_inval(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -269,7 +269,7 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 	tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
 	victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
 	pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
-	tsized = (vcpu_e500->mas4 >> 8) & 0xf;
+	tsized = (vcpu_e500->mas4 >> 7) & 0x1f;
 
 	vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
 		| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
@@ -309,7 +309,7 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
 
 	/* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(BOOKE_PAGESZ_4K)
+	stlbe->mas1 = MAS1_TSIZE(BOOK3E_PAGESZ_4K)
 		| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
 	stlbe->mas2 = (gvaddr & MAS2_EPN)
 		| e500_shadow_mas2_attrib(gtlbe->mas2,
@@ -319,9 +319,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 				vcpu_e500->vcpu.arch.msr & MSR_PR);
 	stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
 
-	KVMTRACE_5D(STLB_WRITE, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
@@ -535,9 +534,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	gtlbe->mas3 = vcpu_e500->mas3;
 	gtlbe->mas7 = vcpu_e500->mas7;
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, vcpu_e500->mas0,
-			gtlbe->mas1, gtlbe->mas2, gtlbe->mas3, gtlbe->mas7,
-			handler);
+	trace_kvm_gtlb_write(vcpu_e500->mas0, gtlbe->mas1, gtlbe->mas2,
+			     gtlbe->mas3, gtlbe->mas7);
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
@@ -545,7 +543,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		case 0:
 			/* TLB0 */
 			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
-			gtlbe->mas1 |= MAS1_TSIZE(BOOKE_PAGESZ_4K);
+			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 
 			stlbsel = 0;
 			sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);
@@ -679,14 +677,14 @@ void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 	/* Insert large initial mapping for guest. */
 	tlbe = &vcpu_e500->guest_tlb[1][0];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_256M);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
 	tlbe->mas2 = 0;
 	tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;
 
 	/* 4K map for serial output. Used by kernel wrapper. */
 	tlbe = &vcpu_e500->guest_tlb[1][1];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_4K);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
 	tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;

arch/powerpc/kvm/e500_tlb.h

@@ -16,7 +16,7 @@
 #define __KVM_E500_TLB_H__
 
 #include <linux/kvm_host.h>
-#include <asm/mmu-fsl-booke.h>
+#include <asm/mmu-book3e.h>
 #include <asm/tlb.h>
 #include <asm/kvm_e500.h>
 
@@ -59,7 +59,7 @@ extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
 /* TLB helper functions */
 static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
 {
-	return (tlbe->mas1 >> 8) & 0xf;
+	return (tlbe->mas1 >> 7) & 0x1f;
 }
 
 static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
@@ -70,7 +70,7 @@ static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
 static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
 {
 	unsigned int pgsize = get_tlb_size(tlbe);
-	return 1ULL << 10 << (pgsize << 1);
+	return 1ULL << 10 << pgsize;
 }
 
 static inline gva_t get_tlb_end(const struct tlbe *tlbe)

arch/powerpc/kvm/emulate.c

@@ -29,6 +29,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
 #include "timing.h"
+#include "trace.h"
 
 #define OP_TRAP 3
 
@@ -187,7 +188,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_SRR1:
 				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
 			case SPRN_PVR:
-				vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PVR); break;
+			case SPRN_PIR:
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PIR); break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
@@ -417,7 +420,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	}
 
-	KVMTRACE_3D(PPC_INSTR, vcpu, inst, (int)vcpu->arch.pc, emulated, entryexit);
+	trace_kvm_ppc_instr(inst, vcpu->arch.pc, emulated);
 
 	if (advance)
 		vcpu->arch.pc += 4; /* Advance past emulated instruction. */

arch/powerpc/kvm/powerpc.c

@@ -31,25 +31,17 @@
 #include "timing.h"
 #include "../mm/mmu_decl.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn;
 }
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
-{
-	return !!(v->arch.pending_exceptions);
-}
-
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	/* do real check here */
-	return 1;
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !(v->arch.msr & MSR_WE);
+	return !(v->arch.msr & MSR_WE) || !!(v->arch.pending_exceptions);
 }
 
 
@@ -122,13 +114,17 @@ struct kvm *kvm_arch_create_vm(void)
 static void kvmppc_free_vcpus(struct kvm *kvm)
 {
 	unsigned int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arch_vcpu_free(vcpu);
 
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm_arch_vcpu_free(kvm->vcpus[i]);
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
 		kvm->vcpus[i] = NULL;
-		}
-	}
+
+	atomic_set(&kvm->online_vcpus, 0);
+	mutex_unlock(&kvm->lock);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)

arch/powerpc/kvm/trace.h

+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+
+/*
+ * Tracepoint for guest mode entry.
+ */
+TRACE_EVENT(kvm_ppc_instr,
+	TP_PROTO(unsigned int inst, unsigned long pc, unsigned int emulate),
+	TP_ARGS(inst, pc, emulate),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	inst		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned int,	emulate		)
+	),
+
+	TP_fast_assign(
+		__entry->inst		= inst;
+		__entry->pc		= pc;
+		__entry->emulate	= emulate;
+	),
+
+	TP_printk("inst %u pc 0x%lx emulate %u\n",
+		  __entry->inst, __entry->pc, __entry->emulate)
+);
+
+TRACE_EVENT(kvm_stlb_inval,
+	TP_PROTO(unsigned int stlb_index),
+	TP_ARGS(stlb_index),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	stlb_index	)
+	),
+
+	TP_fast_assign(
+		__entry->stlb_index	= stlb_index;
+	),
+
+	TP_printk("stlb_index %u", __entry->stlb_index)
+);
+
+TRACE_EVENT(kvm_stlb_write,
+	TP_PROTO(unsigned int victim, unsigned int tid, unsigned int word0,
+		 unsigned int word1, unsigned int word2),
+	TP_ARGS(victim, tid, word0, word1, word2),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	victim		)
+		__field(	unsigned int,	tid		)
+		__field(	unsigned int,	word0		)
+		__field(	unsigned int,	word1		)
+		__field(	unsigned int,	word2		)
+	),
+
+	TP_fast_assign(
+		__entry->victim		= victim;
+		__entry->tid		= tid;
+		__entry->word0		= word0;
+		__entry->word1		= word1;
+		__entry->word2		= word2;
+	),
+
+	TP_printk("victim %u tid %u w0 %u w1 %u w2 %u",
+		__entry->victim, __entry->tid, __entry->word0,
+		__entry->word1, __entry->word2)
+);
+
+TRACE_EVENT(kvm_gtlb_write,
+	TP_PROTO(unsigned int gtlb_index, unsigned int tid, unsigned int word0,
+		 unsigned int word1, unsigned int word2),
+	TP_ARGS(gtlb_index, tid, word0, word1, word2),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	gtlb_index	)
+		__field(	unsigned int,	tid		)
+		__field(	unsigned int,	word0		)
+		__field(	unsigned int,	word1		)
+		__field(	unsigned int,	word2		)
+	),
+
+	TP_fast_assign(
+		__entry->gtlb_index	= gtlb_index;
+		__entry->tid		= tid;
+		__entry->word0		= word0;
+		__entry->word1		= word1;
+		__entry->word2		= word2;
+	),
+
+	TP_printk("gtlb_index %u tid %u w0 %u w1 %u w2 %u",
+		__entry->gtlb_index, __entry->tid, __entry->word0,
+		__entry->word1, __entry->word2)
+);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/s390/include/asm/kvm.h

@@ -15,15 +15,6 @@
  */
 #include <linux/types.h>
 
-/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
-struct kvm_pic_state {
-	/* no PIC for s390 */
-};
-
-struct kvm_ioapic_state {
-	/* no IOAPIC for s390 */
-};
-
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* general purpose regs for s390 */

arch/s390/include/asm/kvm_host.h

 /*
  * asm-s390/kvm_host.h - definition for kernel virtual machines on s390
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -40,7 +40,11 @@ struct sca_block {
 	struct sca_entry cpu[64];
 } __attribute__((packed));
 
-#define KVM_PAGES_PER_HPAGE 256
+#define KVM_NR_PAGE_SIZES 2
+#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + ((x) - 1) * 8)
+#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
 #define CPUSTAT_HOST       0x80000000
 #define CPUSTAT_WAIT       0x10000000
@@ -182,8 +186,9 @@ struct kvm_s390_interrupt_info {
 };
 
 /* for local_interrupt.action_flags */
-#define ACTION_STORE_ON_STOP 1
-#define ACTION_STOP_ON_STOP  2
+#define ACTION_STORE_ON_STOP		(1<<0)
+#define ACTION_STOP_ON_STOP		(1<<1)
+#define ACTION_RELOADVCPU_ON_STOP	(1<<2)
 
 struct kvm_s390_local_interrupt {
 	spinlock_t lock;
@@ -227,8 +232,6 @@ struct kvm_vm_stat {
 };
 
 struct kvm_arch{
-	unsigned long guest_origin;
-	unsigned long guest_memsize;
 	struct sca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;

arch/s390/include/asm/kvm_para.h

@@ -13,6 +13,8 @@
 #ifndef __S390_KVM_PARA_H
 #define __S390_KVM_PARA_H
 
+#ifdef __KERNEL__
+
 /*
  * Hypercalls for KVM on s390. The calling convention is similar to the
  * s390 ABI, so we use R2-R6 for parameters 1-5. In addition we use R1
@@ -147,4 +149,6 @@ static inline unsigned int kvm_arch_para_features(void)
 	return 0;
 }
 
+#endif
+
 #endif /* __S390_KVM_PARA_H */

arch/s390/kvm/Kconfig

 #
 # KVM configuration
 #
-config HAVE_KVM
-       bool
-
-config HAVE_KVM_IRQCHIP
-       bool
+source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
@@ -38,9 +34,6 @@ config KVM
 
 	  If unsure, say N.
 
-config KVM_TRACE
-       bool
-
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/virtio/Kconfig

arch/s390/kvm/gaccess.h

 /*
  * gaccess.h -  access guest memory
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -16,13 +16,14 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 #include <asm/uaccess.h>
+#include "kvm-s390.h"
 
 static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
 					       unsigned long guestaddr)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestaddr < 2 * PAGE_SIZE)
 		guestaddr += prefix;
@@ -158,8 +159,8 @@ static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest,
 				const void *from, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
 		goto slowpath;
@@ -209,8 +210,8 @@ static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
 				  unsigned long guestsrc, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
 		goto slowpath;
@@ -244,8 +245,8 @@ static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu,
 					 unsigned long guestdest,
 					 const void *from, unsigned long n)
 {
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestdest + n > memsize)
 		return -EFAULT;
@@ -262,8 +263,8 @@ static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to,
 					   unsigned long guestsrc,
 					   unsigned long n)
 {
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestsrc + n > memsize)
 		return -EFAULT;

arch/s390/kvm/intercept.c

 /*
  * intercept.c - in-kernel handling for sie intercepts
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -128,7 +128,7 @@ static int handle_noop(struct kvm_vcpu *vcpu)
 
 static int handle_stop(struct kvm_vcpu *vcpu)
 {
-	int rc;
+	int rc = 0;
 
 	vcpu->stat.exit_stop_request++;
 	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
@@ -141,12 +141,18 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 			rc = -ENOTSUPP;
 	}
 
+	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP;
+		rc = SIE_INTERCEPT_RERUNVCPU;
+		vcpu->run->exit_reason = KVM_EXIT_INTR;
+	}
+
 	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
 		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
 		rc = -ENOTSUPP;
-	} else
-		rc = 0;
+	}
+
 	spin_unlock_bh(&vcpu->arch.local_int.lock);
 	return rc;
 }
@@ -158,9 +164,9 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.exit_validity++;
 	if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix
-		<= vcpu->kvm->arch.guest_memsize - 2*PAGE_SIZE)){
+		<= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) {
 		rc = fault_in_pages_writeable((char __user *)
-			 vcpu->kvm->arch.guest_origin +
+			 vcpu->arch.sie_block->gmsor +
 			 vcpu->arch.sie_block->prefix,
 			 2*PAGE_SIZE);
 		if (rc)

arch/s390/kvm/interrupt.c

@@ -283,7 +283,7 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
@@ -320,12 +320,6 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 	return rc;
 }
 
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	/* do real check here */
-	return 1;
-}
-
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	return 0;

arch/s390/kvm/kvm-s390.c

 /*
  * s390host.c --  hosting zSeries kernel virtual machines
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -10,6 +10,7 @@
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  *               Heiko Carstens <heiko.carstens@de.ibm.com>
+ *               Christian Ehrhardt <ehrhardt@de.ibm.com>
  */
 
 #include <linux/compiler.h>
@@ -210,13 +211,17 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 static void kvm_free_vcpus(struct kvm *kvm)
 {
 	unsigned int i;
+	struct kvm_vcpu *vcpu;
 
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm_arch_vcpu_destroy(kvm->vcpus[i]);
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arch_vcpu_destroy(vcpu);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
 		kvm->vcpus[i] = NULL;
-		}
-	}
+
+	atomic_set(&kvm->online_vcpus, 0);
+	mutex_unlock(&kvm->lock);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)
@@ -278,16 +283,10 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->gbea = 1;
 }
 
-/* The current code can have up to 256 pages for virtio */
-#define VIRTIODESCSPACE (256ul * 4096ul)
-
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
-	vcpu->arch.sie_block->gmslm = vcpu->kvm->arch.guest_memsize +
-				      vcpu->kvm->arch.guest_origin +
-				      VIRTIODESCSPACE - 1ul;
-	vcpu->arch.sie_block->gmsor = vcpu->kvm->arch.guest_origin;
+	set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests);
 	vcpu->arch.sie_block->ecb   = 2;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	vcpu->arch.sie_block->fac   = (int) (long) facilities;
@@ -319,8 +318,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	BUG_ON(!kvm->arch.sca);
 	if (!kvm->arch.sca->cpu[id].sda)
 		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
-	else
-		BUG_ON(!kvm->vcpus[id]); /* vcpu does already exist */
 	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
 	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
 
@@ -490,9 +487,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	vcpu_load(vcpu);
 
+rerun_vcpu:
+	if (vcpu->requests)
+		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+			kvm_s390_vcpu_set_mem(vcpu);
+
 	/* verify, that memory has been registered */
-	if (!vcpu->kvm->arch.guest_memsize) {
+	if (!vcpu->arch.sie_block->gmslm) {
 		vcpu_put(vcpu);
+		VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu");
 		return -EINVAL;
 	}
 
@@ -509,6 +512,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr;
 		break;
 	case KVM_EXIT_UNKNOWN:
+	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
 		break;
 	default:
@@ -522,8 +526,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		rc = kvm_handle_sie_intercept(vcpu);
 	} while (!signal_pending(current) && !rc);
 
-	if (signal_pending(current) && !rc)
+	if (rc == SIE_INTERCEPT_RERUNVCPU)
+		goto rerun_vcpu;
+
+	if (signal_pending(current) && !rc) {
+		kvm_run->exit_reason = KVM_EXIT_INTR;
 		rc = -EINTR;
+	}
 
 	if (rc == -ENOTSUPP) {
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
@@ -676,6 +685,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				int user_alloc)
 {
 	int i;
+	struct kvm_vcpu *vcpu;
 
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
@@ -684,7 +694,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	   vmas. It is okay to mmap() and munmap() stuff in this slot after
 	   doing this call at any time */
 
-	if (mem->slot || kvm->arch.guest_memsize)
+	if (mem->slot)
 		return -EINVAL;
 
 	if (mem->guest_phys_addr)
@@ -699,36 +709,14 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	if (!user_alloc)
 		return -EINVAL;
 
-	/* lock all vcpus */
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (!kvm->vcpus[i])
+	/* request update of sie control block for all available vcpus */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
 			continue;
-		if (!mutex_trylock(&kvm->vcpus[i]->mutex))
-			goto fail_out;
-	}
-
-	kvm->arch.guest_origin = mem->userspace_addr;
-	kvm->arch.guest_memsize = mem->memory_size;
-
-	/* update sie control blocks, and unlock all vcpus */
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm->vcpus[i]->arch.sie_block->gmsor =
-				kvm->arch.guest_origin;
-			kvm->vcpus[i]->arch.sie_block->gmslm =
-				kvm->arch.guest_memsize +
-				kvm->arch.guest_origin +
-				VIRTIODESCSPACE - 1ul;
-			mutex_unlock(&kvm->vcpus[i]->mutex);
-		}
+		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
 	}
 
 	return 0;
-
-fail_out:
-	for (; i >= 0; i--)
-		mutex_unlock(&kvm->vcpus[i]->mutex);
-	return -EINVAL;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)

arch/s390/kvm/kvm-s390.h

 /*
  * kvm_s390.h -  definition for kvm on s390
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -9,6 +9,7 @@
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
+ *               Christian Ehrhardt <ehrhardt@de.ibm.com>
  */
 
 #ifndef ARCH_S390_KVM_S390_H
@@ -18,8 +19,13 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+/* The current code can have up to 256 pages for virtio */
+#define VIRTIODESCSPACE (256ul * 4096ul)
+
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
+/* negativ values are error codes, positive values for internal conditions */
+#define SIE_INTERCEPT_RERUNVCPU		(1<<0)
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
 
 #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
@@ -50,6 +56,30 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
+int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
+
+static inline int kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.sie_block->gmslm
+		- vcpu->arch.sie_block->gmsor
+		- VIRTIODESCSPACE + 1ul;
+}
+
+static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
+{
+	struct kvm_memory_slot *mem;
+
+	down_read(&vcpu->kvm->slots_lock);
+	mem = &vcpu->kvm->memslots[0];
+
+	vcpu->arch.sie_block->gmsor = mem->userspace_addr;
+	vcpu->arch.sie_block->gmslm =
+		mem->userspace_addr +
+		(mem->npages << PAGE_SHIFT) +
+		VIRTIODESCSPACE - 1ul;
+
+	up_read(&vcpu->kvm->slots_lock);
+}
 
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);

arch/s390/kvm/sigp.c

 /*
  * sigp.c - handlinge interprocessor communication
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -9,6 +9,7 @@
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
+ *               Christian Ehrhardt <ehrhardt@de.ibm.com>
  */
 
 #include <linux/kvm.h>
@@ -107,46 +108,57 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	return rc;
 }
 
-static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store)
+static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
-	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_interrupt_info *inti;
-	int rc;
-
-	if (cpu_addr >= KVM_MAX_VCPUS)
-		return 3; /* not operational */
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
 	if (!inti)
 		return -ENOMEM;
-
 	inti->type = KVM_S390_SIGP_STOP;
 
-	spin_lock(&fi->lock);
-	li = fi->local_int[cpu_addr];
-	if (li == NULL) {
-		rc = 3; /* not operational */
-		kfree(inti);
-		goto unlock;
-	}
 	spin_lock_bh(&li->lock);
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
-	if (store)
-		li->action_bits |= ACTION_STORE_ON_STOP;
-	li->action_bits |= ACTION_STOP_ON_STOP;
+	li->action_bits |= action;
 	if (waitqueue_active(&li->wq))
 		wake_up_interruptible(&li->wq);
 	spin_unlock_bh(&li->lock);
-	rc = 0; /* order accepted */
+
+	return 0; /* order accepted */
+}
+
+static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = 3; /* not operational */
+		goto unlock;
+	}
+
+	rc = __inject_sigp_stop(li, action);
+
 unlock:
 	spin_unlock(&fi->lock);
 	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
 	return rc;
 }
 
+int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	return __inject_sigp_stop(li, action);
+}
+
 static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 {
 	int rc;
@@ -177,9 +189,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
 	if ((copy_from_guest(vcpu, &tmp,
-		(u64) (address + vcpu->kvm->arch.guest_origin) , 1)) ||
+		(u64) (address + vcpu->arch.sie_block->gmsor) , 1)) ||
 	   (copy_from_guest(vcpu, &tmp, (u64) (address +
-			vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) {
+			vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) {
 		*reg |= SIGP_STAT_INVALID_PARAMETER;
 		return 1; /* invalid parameter */
 	}
@@ -262,11 +274,11 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		break;
 	case SIGP_STOP:
 		vcpu->stat.instruction_sigp_stop++;
-		rc = __sigp_stop(vcpu, cpu_addr, 0);
+		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP);
 		break;
 	case SIGP_STOP_STORE_STATUS:
 		vcpu->stat.instruction_sigp_stop++;
-		rc = __sigp_stop(vcpu, cpu_addr, 1);
+		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP);
 		break;
 	case SIGP_SET_ARCH:
 		vcpu->stat.instruction_sigp_arch++;

arch/x86/include/asm/apicdef.h

@@ -15,6 +15,7 @@
 
 #define	APIC_LVR	0x30
 #define		APIC_LVR_MASK		0xFF00FF
+#define		APIC_LVR_DIRECTED_EOI	(1 << 24)
 #define		GET_APIC_VERSION(x)	((x) & 0xFFu)
 #define		GET_APIC_MAXLVT(x)	(((x) >> 16) & 0xFFu)
 #ifdef CONFIG_X86_32
@@ -41,6 +42,7 @@
 #define		APIC_DFR_CLUSTER		0x0FFFFFFFul
 #define		APIC_DFR_FLAT			0xFFFFFFFFul
 #define	APIC_SPIV	0xF0
+#define		APIC_SPIV_DIRECTED_EOI		(1 << 12)
 #define		APIC_SPIV_FOCUS_DISABLED	(1 << 9)
 #define		APIC_SPIV_APIC_ENABLED		(1 << 8)
 #define	APIC_ISR	0x100

arch/x86/include/asm/kvm.h

@@ -17,6 +17,8 @@
 #define __KVM_HAVE_USER_NMI
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_MSIX
+#define __KVM_HAVE_MCE
+#define __KVM_HAVE_PIT_STATE2
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -236,6 +238,14 @@ struct kvm_pit_state {
 	struct kvm_pit_channel_state channels[3];
 };
 
+#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+
+struct kvm_pit_state2 {
+	struct kvm_pit_channel_state channels[3];
+	__u32 flags;
+	__u32 reserved[9];
+};
+
 struct kvm_reinject_control {
 	__u8 pit_reinject;
 	__u8 reserved[31];

arch/x86/include/asm/kvm_host.h

@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/mmu_notifier.h>
+#include <linux/tracepoint.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
@@ -37,12 +38,14 @@
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
 				  0xFFFFFF0000000000ULL)
 
+#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST				\
+	(X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
 #define KVM_GUEST_CR0_MASK						\
-	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
-	 | X86_CR0_NW | X86_CR0_CD)
+	(KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST				\
+	(X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
 #define KVM_VM_CR0_ALWAYS_ON						\
-	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
-	 | X86_CR0_MP)
+	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
 #define KVM_GUEST_CR4_MASK						\
 	(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
@@ -51,12 +54,12 @@
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
-/* shadow tables are PAE even on non-PAE hosts */
-#define KVM_HPAGE_SHIFT 21
-#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
-#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
-
-#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
+/* KVM Hugepage definitions for x86 */
+#define KVM_NR_PAGE_SIZES	3
+#define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + (((x) - 1) * 9))
+#define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1
@@ -120,6 +123,10 @@ enum kvm_reg {
 	NR_VCPU_REGS
 };
 
+enum kvm_reg_ex {
+	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+};
+
 enum {
 	VCPU_SREG_ES,
 	VCPU_SREG_CS,
@@ -131,7 +138,7 @@ enum {
 	VCPU_SREG_LDTR,
 };
 
-#include <asm/kvm_x86_emulate.h>
+#include <asm/kvm_emulate.h>
 
 #define KVM_NR_MEM_OBJS 40
 
@@ -308,7 +315,6 @@ struct kvm_vcpu_arch {
 	struct {
 		gfn_t gfn;	/* presumed gfn during guest pte update */
 		pfn_t pfn;	/* pfn corresponding to that gfn */
-		int largepage;
 		unsigned long mmu_seq;
 	} update_pte;
 
@@ -334,16 +340,6 @@ struct kvm_vcpu_arch {
 		u8 nr;
 	} interrupt;
 
-	struct {
-		int vm86_active;
-		u8 save_iopl;
-		struct kvm_save_segment {
-			u16 selector;
-			unsigned long base;
-			u32 limit;
-			u32 ar;
-		} tr, es, ds, fs, gs;
-	} rmode;
 	int halt_request; /* real mode on Intel only */
 
 	int cpuid_nent;
@@ -366,13 +362,15 @@ struct kvm_vcpu_arch {
 	u32 pat;
 
 	int switch_db_regs;
-	unsigned long host_db[KVM_NR_DB_REGS];
-	unsigned long host_dr6;
-	unsigned long host_dr7;
 	unsigned long db[KVM_NR_DB_REGS];
 	unsigned long dr6;
 	unsigned long dr7;
 	unsigned long eff_db[KVM_NR_DB_REGS];
+
+	u64 mcg_cap;
+	u64 mcg_status;
+	u64 mcg_ctl;
+	u64 *mce_banks;
 };
 
 struct kvm_mem_alias {
@@ -409,6 +407,7 @@ struct kvm_arch{
 
 	struct page *ept_identity_pagetable;
 	bool ept_identity_pagetable_done;
+	gpa_t ept_identity_map_addr;
 
 	unsigned long irq_sources_bitmap;
 	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
@@ -526,6 +525,9 @@ struct kvm_x86_ops {
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+	bool (*gb_page_enable)(void);
+
+	const struct trace_print_flags *exit_reasons_str;
 };
 
 extern struct kvm_x86_ops *kvm_x86_ops;
@@ -618,6 +620,7 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
 			   u32 error_code);
+bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
 int kvm_pic_set_irq(void *opaque, int irq, int level);
 
@@ -752,8 +755,6 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
 }
 
-#define MSR_IA32_TIME_STAMP_COUNTER		0x010
-
 #define TSS_IOPB_BASE_OFFSET 0x66
 #define TSS_BASE_SIZE 0x68
 #define TSS_IOPB_SIZE (65536 / 8)
@@ -796,5 +797,8 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
+int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/include/asm/kvm_para.h

 #ifndef _ASM_X86_KVM_PARA_H
 #define _ASM_X86_KVM_PARA_H
 
+#include <linux/types.h>
+
 /* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
  * should be used to determine that a VM is running under KVM.
  */

arch/x86/include/asm/msr-index.h

@@ -374,6 +374,7 @@
 /* AMD-V MSRs */
 
 #define MSR_VM_CR                       0xc0010114
+#define MSR_VM_IGNNE                    0xc0010115
 #define MSR_VM_HSAVE_PA                 0xc0010117
 
 #endif /* _ASM_X86_MSR_INDEX_H */

arch/x86/include/asm/vmx.h

@@ -55,6 +55,7 @@
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
 
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
@@ -351,9 +352,16 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_EPT_EXTENT_CONTEXT			1
 #define VMX_EPT_EXTENT_GLOBAL			2
+
+#define VMX_EPT_EXECUTE_ONLY_BIT		(1ull)
+#define VMX_EPT_PAGE_WALK_4_BIT			(1ull << 6)
+#define VMX_EPTP_UC_BIT				(1ull << 8)
+#define VMX_EPTP_WB_BIT				(1ull << 14)
+#define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #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

arch/x86/kernel/kvm.c

@@ -34,7 +34,6 @@
 struct kvm_para_state {
 	u8 mmu_queue[MMU_QUEUE_SIZE];
 	int mmu_queue_len;
-	enum paravirt_lazy_mode mode;
 };
 
 static DEFINE_PER_CPU(struct kvm_para_state, para_state);
@@ -77,7 +76,7 @@ static void kvm_deferred_mmu_op(void *buffer, int len)
 {
 	struct kvm_para_state *state = kvm_para_state();
 
-	if (state->mode != PARAVIRT_LAZY_MMU) {
+	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) {
 		kvm_mmu_op(buffer, len);
 		return;
 	}
@@ -185,10 +184,7 @@ static void kvm_release_pt(unsigned long pfn)
 
 static void kvm_enter_lazy_mmu(void)
 {
-	struct kvm_para_state *state = kvm_para_state();
-
 	paravirt_enter_lazy_mmu();
-	state->mode = paravirt_get_lazy_mode();
 }
 
 static void kvm_leave_lazy_mmu(void)
@@ -197,7 +193,6 @@ static void kvm_leave_lazy_mmu(void)
 
 	mmu_queue_flush(state);
 	paravirt_leave_lazy_mmu();
-	state->mode = paravirt_get_lazy_mode();
 }
 
 static void __init paravirt_ops_setup(void)

arch/x86/kernel/kvmclock.c

@@ -50,8 +50,8 @@ static unsigned long kvm_get_wallclock(void)
 	struct timespec ts;
 	int low, high;
 
-	low = (int)__pa(&wall_clock);
-	high = ((u64)__pa(&wall_clock) >> 32);
+	low = (int)__pa_symbol(&wall_clock);
+	high = ((u64)__pa_symbol(&wall_clock) >> 32);
 	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
 
 	vcpu_time = &get_cpu_var(hv_clock);

arch/x86/kvm/Kconfig

 #
 # KVM configuration
 #
-config HAVE_KVM
-       bool
 
-config HAVE_KVM_IRQCHIP
-       bool
-       default y
+source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
@@ -29,6 +25,9 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
+	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_EVENTFD
+	select KVM_APIC_ARCHITECTURE
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
@@ -63,18 +62,6 @@ config KVM_AMD
 	  To compile this as a module, choose M here: the module
 	  will be called kvm-amd.
 
-config KVM_TRACE
-	bool "KVM trace support"
-	depends on KVM && SYSFS
-	select MARKERS
-	select RELAY
-	select DEBUG_FS
-	default n
-	---help---
-	  This option allows reading a trace of kvm-related events through
-	  relayfs.  Note the ABI is not considered stable and will be
-	  modified in future updates.
-
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/lguest/Kconfig

arch/x86/kvm/Makefile

-#
-# Makefile for Kernel-based Virtual Machine module
-#
-
-common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
-                coalesced_mmio.o irq_comm.o)
-ifeq ($(CONFIG_KVM_TRACE),y)
-common-objs += $(addprefix ../../../virt/kvm/, kvm_trace.o)
-endif
-ifeq ($(CONFIG_IOMMU_API),y)
-common-objs += $(addprefix ../../../virt/kvm/, iommu.o)
-endif
 
 EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm
 
-kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o \
+CFLAGS_x86.o := -I.
+CFLAGS_svm.o := -I.
+CFLAGS_vmx.o := -I.
+
+kvm-y			+= $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
+				coalesced_mmio.o irq_comm.o eventfd.o)
+kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
+
+kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o timer.o
+kvm-intel-y		+= vmx.o
+kvm-amd-y		+= svm.o
+
 obj-$(CONFIG_KVM)	+= kvm.o
-kvm-intel-objs = vmx.o
 obj-$(CONFIG_KVM_INTEL)	+= kvm-intel.o
-kvm-amd-objs = svm.o
 obj-$(CONFIG_KVM_AMD)	+= kvm-amd.o

arch/x86/kvm/x86_emulate.c → arch/x86/kvm/emulate.c

 /******************************************************************************
- * x86_emulate.c
+ * emulate.c
  *
  * Generic x86 (32-bit and 64-bit) instruction decoder and emulator.
  *
@@ -30,7 +30,9 @@
 #define DPRINTF(x...) do {} while (0)
 #endif
 #include <linux/module.h>
-#include <asm/kvm_x86_emulate.h>
+#include <asm/kvm_emulate.h>
+
+#include "mmu.h"		/* for is_long_mode() */
 
 /*
  * Opcode effective-address decode tables.
@@ -60,6 +62,7 @@
 #define SrcImmByte  (6<<4)	/* 8-bit sign-extended immediate operand. */
 #define SrcOne      (7<<4)	/* Implied '1' */
 #define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
+#define SrcImmU     (9<<4)      /* Immediate operand, unsigned */
 #define SrcMask     (0xf<<4)
 /* Generic ModRM decode. */
 #define ModRM       (1<<8)
@@ -97,11 +100,11 @@ static u32 opcode_table[256] = {
 	/* 0x10 - 0x17 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
-	0, 0, 0, 0,
+	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0,
 	/* 0x18 - 0x1F */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
-	0, 0, 0, 0,
+	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0,
 	/* 0x20 - 0x27 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
@@ -195,7 +198,7 @@ static u32 opcode_table[256] = {
 	ByteOp | SrcImmUByte, SrcImmUByte,
 	/* 0xE8 - 0xEF */
 	SrcImm | Stack, SrcImm | ImplicitOps,
-	SrcImm | Src2Imm16, SrcImmByte | ImplicitOps,
+	SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	/* 0xF0 - 0xF7 */
@@ -208,7 +211,7 @@ static u32 opcode_table[256] = {
 
 static u32 twobyte_table[256] = {
 	/* 0x00 - 0x0F */
-	0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0,
+	0, Group | GroupDual | Group7, 0, 0, 0, ImplicitOps, ImplicitOps, 0,
 	ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
 	/* 0x10 - 0x1F */
 	0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0,
@@ -216,7 +219,9 @@ static u32 twobyte_table[256] = {
 	ModRM | ImplicitOps, ModRM, ModRM | ImplicitOps, ModRM, 0, 0, 0, 0,
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x30 - 0x3F */
-	ImplicitOps, 0, ImplicitOps, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	ImplicitOps, 0, ImplicitOps, 0,
+	ImplicitOps, ImplicitOps, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x40 - 0x47 */
 	DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,
 	DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,
@@ -319,8 +324,11 @@ static u32 group2_table[] = {
 };
 
 /* EFLAGS bit definitions. */
+#define EFLG_VM (1<<17)
+#define EFLG_RF (1<<16)
 #define EFLG_OF (1<<11)
 #define EFLG_DF (1<<10)
+#define EFLG_IF (1<<9)
 #define EFLG_SF (1<<7)
 #define EFLG_ZF (1<<6)
 #define EFLG_AF (1<<4)
@@ -1027,6 +1035,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->src.type = OP_MEM;
 		break;
 	case SrcImm:
+	case SrcImmU:
 		c->src.type = OP_IMM;
 		c->src.ptr = (unsigned long *)c->eip;
 		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
@@ -1044,6 +1053,19 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			c->src.val = insn_fetch(s32, 4, c->eip);
 			break;
 		}
+		if ((c->d & SrcMask) == SrcImmU) {
+			switch (c->src.bytes) {
+			case 1:
+				c->src.val &= 0xff;
+				break;
+			case 2:
+				c->src.val &= 0xffff;
+				break;
+			case 4:
+				c->src.val &= 0xffffffff;
+				break;
+			}
+		}
 		break;
 	case SrcImmByte:
 	case SrcImmUByte:
@@ -1375,6 +1397,217 @@ static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
 		ctxt->interruptibility = mask;
 }
 
+static inline void
+setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
+	struct kvm_segment *cs, struct kvm_segment *ss)
+{
+	memset(cs, 0, sizeof(struct kvm_segment));
+	kvm_x86_ops->get_segment(ctxt->vcpu, cs, VCPU_SREG_CS);
+	memset(ss, 0, sizeof(struct kvm_segment));
+
+	cs->l = 0;		/* will be adjusted later */
+	cs->base = 0;		/* flat segment */
+	cs->g = 1;		/* 4kb granularity */
+	cs->limit = 0xffffffff;	/* 4GB limit */
+	cs->type = 0x0b;	/* Read, Execute, Accessed */
+	cs->s = 1;
+	cs->dpl = 0;		/* will be adjusted later */
+	cs->present = 1;
+	cs->db = 1;
+
+	ss->unusable = 0;
+	ss->base = 0;		/* flat segment */
+	ss->limit = 0xffffffff;	/* 4GB limit */
+	ss->g = 1;		/* 4kb granularity */
+	ss->s = 1;
+	ss->type = 0x03;	/* Read/Write, Accessed */
+	ss->db = 1;		/* 32bit stack segment */
+	ss->dpl = 0;
+	ss->present = 1;
+}
+
+static int
+emulate_syscall(struct x86_emulate_ctxt *ctxt)
+{
+	struct decode_cache *c = &ctxt->decode;
+	struct kvm_segment cs, ss;
+	u64 msr_data;
+
+	/* syscall is not available in real mode */
+	if (c->lock_prefix || ctxt->mode == X86EMUL_MODE_REAL
+		|| !(ctxt->vcpu->arch.cr0 & X86_CR0_PE))
+		return -1;
+
+	setup_syscalls_segments(ctxt, &cs, &ss);
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data);
+	msr_data >>= 32;
+	cs.selector = (u16)(msr_data & 0xfffc);
+	ss.selector = (u16)(msr_data + 8);
+
+	if (is_long_mode(ctxt->vcpu)) {
+		cs.db = 0;
+		cs.l = 1;
+	}
+	kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS);
+	kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS);
+
+	c->regs[VCPU_REGS_RCX] = c->eip;
+	if (is_long_mode(ctxt->vcpu)) {
+#ifdef CONFIG_X86_64
+		c->regs[VCPU_REGS_R11] = ctxt->eflags & ~EFLG_RF;
+
+		kvm_x86_ops->get_msr(ctxt->vcpu,
+			ctxt->mode == X86EMUL_MODE_PROT64 ?
+			MSR_LSTAR : MSR_CSTAR, &msr_data);
+		c->eip = msr_data;
+
+		kvm_x86_ops->get_msr(ctxt->vcpu, MSR_SYSCALL_MASK, &msr_data);
+		ctxt->eflags &= ~(msr_data | EFLG_RF);
+#endif
+	} else {
+		/* legacy mode */
+		kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data);
+		c->eip = (u32)msr_data;
+
+		ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
+	}
+
+	return 0;
+}
+
+static int
+emulate_sysenter(struct x86_emulate_ctxt *ctxt)
+{
+	struct decode_cache *c = &ctxt->decode;
+	struct kvm_segment cs, ss;
+	u64 msr_data;
+
+	/* inject #UD if LOCK prefix is used */
+	if (c->lock_prefix)
+		return -1;
+
+	/* inject #GP if in real mode or paging is disabled */
+	if (ctxt->mode == X86EMUL_MODE_REAL ||
+		!(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) {
+		kvm_inject_gp(ctxt->vcpu, 0);
+		return -1;
+	}
+
+	/* XXX sysenter/sysexit have not been tested in 64bit mode.
+	* Therefore, we inject an #UD.
+	*/
+	if (ctxt->mode == X86EMUL_MODE_PROT64)
+		return -1;
+
+	setup_syscalls_segments(ctxt, &cs, &ss);
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data);
+	switch (ctxt->mode) {
+	case X86EMUL_MODE_PROT32:
+		if ((msr_data & 0xfffc) == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		break;
+	case X86EMUL_MODE_PROT64:
+		if (msr_data == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		break;
+	}
+
+	ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
+	cs.selector = (u16)msr_data;
+	cs.selector &= ~SELECTOR_RPL_MASK;
+	ss.selector = cs.selector + 8;
+	ss.selector &= ~SELECTOR_RPL_MASK;
+	if (ctxt->mode == X86EMUL_MODE_PROT64
+		|| is_long_mode(ctxt->vcpu)) {
+		cs.db = 0;
+		cs.l = 1;
+	}
+
+	kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS);
+	kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS);
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_EIP, &msr_data);
+	c->eip = msr_data;
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_ESP, &msr_data);
+	c->regs[VCPU_REGS_RSP] = msr_data;
+
+	return 0;
+}
+
+static int
+emulate_sysexit(struct x86_emulate_ctxt *ctxt)
+{
+	struct decode_cache *c = &ctxt->decode;
+	struct kvm_segment cs, ss;
+	u64 msr_data;
+	int usermode;
+
+	/* inject #UD if LOCK prefix is used */
+	if (c->lock_prefix)
+		return -1;
+
+	/* inject #GP if in real mode or paging is disabled */
+	if (ctxt->mode == X86EMUL_MODE_REAL
+		|| !(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) {
+		kvm_inject_gp(ctxt->vcpu, 0);
+		return -1;
+	}
+
+	/* sysexit must be called from CPL 0 */
+	if (kvm_x86_ops->get_cpl(ctxt->vcpu) != 0) {
+		kvm_inject_gp(ctxt->vcpu, 0);
+		return -1;
+	}
+
+	setup_syscalls_segments(ctxt, &cs, &ss);
+
+	if ((c->rex_prefix & 0x8) != 0x0)
+		usermode = X86EMUL_MODE_PROT64;
+	else
+		usermode = X86EMUL_MODE_PROT32;
+
+	cs.dpl = 3;
+	ss.dpl = 3;
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data);
+	switch (usermode) {
+	case X86EMUL_MODE_PROT32:
+		cs.selector = (u16)(msr_data + 16);
+		if ((msr_data & 0xfffc) == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		ss.selector = (u16)(msr_data + 24);
+		break;
+	case X86EMUL_MODE_PROT64:
+		cs.selector = (u16)(msr_data + 32);
+		if (msr_data == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		ss.selector = cs.selector + 8;
+		cs.db = 0;
+		cs.l = 1;
+		break;
+	}
+	cs.selector |= SELECTOR_RPL_MASK;
+	ss.selector |= SELECTOR_RPL_MASK;
+
+	kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS);
+	kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS);
+
+	c->eip = ctxt->vcpu->arch.regs[VCPU_REGS_RDX];
+	c->regs[VCPU_REGS_RSP] = ctxt->vcpu->arch.regs[VCPU_REGS_RCX];
+
+	return 0;
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
@@ -1970,6 +2203,12 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			goto cannot_emulate;
 		}
 		break;
+	case 0x05: 		/* syscall */
+		if (emulate_syscall(ctxt) == -1)
+			goto cannot_emulate;
+		else
+			goto writeback;
+		break;
 	case 0x06:
 		emulate_clts(ctxt->vcpu);
 		c->dst.type = OP_NONE;
@@ -2036,6 +2275,18 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;
 		break;
+	case 0x34:		/* sysenter */
+		if (emulate_sysenter(ctxt) == -1)
+			goto cannot_emulate;
+		else
+			goto writeback;
+		break;
+	case 0x35:		/* sysexit */
+		if (emulate_sysexit(ctxt) == -1)
+			goto cannot_emulate;
+		else
+			goto writeback;
+		break;
 	case 0x40 ... 0x4f:	/* cmov */
 		c->dst.val = c->dst.orig_val = c->src.val;
 		if (!test_cc(c->b, ctxt->eflags))

arch/x86/kvm/i8254.c

@@ -231,7 +231,7 @@ int pit_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
 
-	if (pit && vcpu->vcpu_id == 0 && pit->pit_state.irq_ack)
+	if (pit && kvm_vcpu_is_bsp(vcpu) && pit->pit_state.irq_ack)
 		return atomic_read(&pit->pit_state.pit_timer.pending);
 	return 0;
 }
@@ -252,7 +252,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 	struct kvm_pit *pit = vcpu->kvm->arch.vpit;
 	struct hrtimer *timer;
 
-	if (vcpu->vcpu_id != 0 || !pit)
+	if (!kvm_vcpu_is_bsp(vcpu) || !pit)
 		return;
 
 	timer = &pit->pit_state.pit_timer.timer;
@@ -294,7 +294,7 @@ static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period)
 	pt->timer.function = kvm_timer_fn;
 	pt->t_ops = &kpit_ops;
 	pt->kvm = ps->pit->kvm;
-	pt->vcpu_id = 0;
+	pt->vcpu = pt->kvm->bsp_vcpu;
 
 	atomic_set(&pt->pending, 0);
 	ps->irq_ack = 1;
@@ -332,33 +332,62 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 	case 1:
         /* FIXME: enhance mode 4 precision */
 	case 4:
+		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) {
 			create_pit_timer(ps, val, 0);
+		}
 		break;
 	case 2:
 	case 3:
+		if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){
 			create_pit_timer(ps, val, 1);
+		}
 		break;
 	default:
 		destroy_pit_timer(&ps->pit_timer);
 	}
 }
 
-void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val)
+void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start)
 {
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
+	u8 saved_mode;
+	if (hpet_legacy_start) {
+		/* save existing mode for later reenablement */
+		saved_mode = kvm->arch.vpit->pit_state.channels[0].mode;
+		kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */
 		pit_load_count(kvm, channel, val);
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+		kvm->arch.vpit->pit_state.channels[0].mode = saved_mode;
+	} else {
+		pit_load_count(kvm, channel, val);
+	}
+}
+
+static inline struct kvm_pit *dev_to_pit(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pit, dev);
 }
 
-static void pit_ioport_write(struct kvm_io_device *this,
+static inline struct kvm_pit *speaker_to_pit(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pit, speaker_dev);
+}
+
+static inline int pit_in_range(gpa_t addr)
+{
+	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
+		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
+}
+
+static int pit_ioport_write(struct kvm_io_device *this,
 			    gpa_t addr, int len, const void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int channel, access;
 	struct kvm_kpit_channel_state *s;
 	u32 val = *(u32 *) data;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
 
 	val  &= 0xff;
 	addr &= KVM_PIT_CHANNEL_MASK;
@@ -421,16 +450,19 @@ static void pit_ioport_write(struct kvm_io_device *this,
 	}
 
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static void pit_ioport_read(struct kvm_io_device *this,
+static int pit_ioport_read(struct kvm_io_device *this,
 			   gpa_t addr, int len, void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int ret, count;
 	struct kvm_kpit_channel_state *s;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
 
 	addr &= KVM_PIT_CHANNEL_MASK;
 	s = &pit_state->channels[addr];
@@ -485,37 +517,36 @@ static void pit_ioport_read(struct kvm_io_device *this,
 	memcpy(data, (char *)&ret, len);
 
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static int pit_in_range(struct kvm_io_device *this, gpa_t addr,
-			int len, int is_write)
-{
-	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
-		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
-}
-
-static void speaker_ioport_write(struct kvm_io_device *this,
+static int speaker_ioport_write(struct kvm_io_device *this,
 				gpa_t addr, int len, const void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	u32 val = *(u32 *) data;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
 
 	mutex_lock(&pit_state->lock);
 	pit_state->speaker_data_on = (val >> 1) & 1;
 	pit_set_gate(kvm, 2, val & 1);
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static void speaker_ioport_read(struct kvm_io_device *this,
+static int speaker_ioport_read(struct kvm_io_device *this,
 			       gpa_t addr, int len, void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	unsigned int refresh_clock;
 	int ret;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
 
 	/* Refresh clock toggles at about 15us. We approximate as 2^14ns. */
 	refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1;
@@ -527,12 +558,7 @@ static void speaker_ioport_read(struct kvm_io_device *this,
 		len = sizeof(ret);
 	memcpy(data, (char *)&ret, len);
 	mutex_unlock(&pit_state->lock);
-}
-
-static int speaker_in_range(struct kvm_io_device *this, gpa_t addr,
-			    int len, int is_write)
-{
-	return (addr == KVM_SPEAKER_BASE_ADDRESS);
+	return 0;
 }
 
 void kvm_pit_reset(struct kvm_pit *pit)
@@ -541,6 +567,7 @@ void kvm_pit_reset(struct kvm_pit *pit)
 	struct kvm_kpit_channel_state *c;
 
 	mutex_lock(&pit->pit_state.lock);
+	pit->pit_state.flags = 0;
 	for (i = 0; i < 3; i++) {
 		c = &pit->pit_state.channels[i];
 		c->mode = 0xff;
@@ -563,10 +590,22 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 	}
 }
 
-struct kvm_pit *kvm_create_pit(struct kvm *kvm)
+static const struct kvm_io_device_ops pit_dev_ops = {
+	.read     = pit_ioport_read,
+	.write    = pit_ioport_write,
+};
+
+static const struct kvm_io_device_ops speaker_dev_ops = {
+	.read     = speaker_ioport_read,
+	.write    = speaker_ioport_write,
+};
+
+/* Caller must have writers lock on slots_lock */
+struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;
 	struct kvm_kpit_state *pit_state;
+	int ret;
 
 	pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL);
 	if (!pit)
@@ -582,19 +621,6 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	mutex_lock(&pit->pit_state.lock);
 	spin_lock_init(&pit->pit_state.inject_lock);
 
-	/* Initialize PIO device */
-	pit->dev.read = pit_ioport_read;
-	pit->dev.write = pit_ioport_write;
-	pit->dev.in_range = pit_in_range;
-	pit->dev.private = pit;
-	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
-
-	pit->speaker_dev.read = speaker_ioport_read;
-	pit->speaker_dev.write = speaker_ioport_write;
-	pit->speaker_dev.in_range = speaker_in_range;
-	pit->speaker_dev.private = pit;
-	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
-
 	kvm->arch.vpit = pit;
 	pit->kvm = kvm;
 
@@ -613,7 +639,30 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	pit->mask_notifier.func = pit_mask_notifer;
 	kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
 
+	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
+	ret = __kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
+	if (ret < 0)
+		goto fail;
+
+	if (flags & KVM_PIT_SPEAKER_DUMMY) {
+		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
+		ret = __kvm_io_bus_register_dev(&kvm->pio_bus,
+						&pit->speaker_dev);
+		if (ret < 0)
+			goto fail_unregister;
+	}
+
 	return pit;
+
+fail_unregister:
+	__kvm_io_bus_unregister_dev(&kvm->pio_bus, &pit->dev);
+
+fail:
+	if (pit->irq_source_id >= 0)
+		kvm_free_irq_source_id(kvm, pit->irq_source_id);
+
+	kfree(pit);
+	return NULL;
 }
 
 void kvm_free_pit(struct kvm *kvm)
@@ -623,6 +672,8 @@ void kvm_free_pit(struct kvm *kvm)
 	if (kvm->arch.vpit) {
 		kvm_unregister_irq_mask_notifier(kvm, 0,
 					       &kvm->arch.vpit->mask_notifier);
+		kvm_unregister_irq_ack_notifier(kvm,
+				&kvm->arch.vpit->pit_state.irq_ack_notifier);
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
 		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
 		hrtimer_cancel(timer);
@@ -637,10 +688,10 @@ static void __inject_pit_timer_intr(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->irq_lock);
 	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
 	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->irq_lock);
 
 	/*
 	 * Provides NMI watchdog support via Virtual Wire mode.
@@ -652,11 +703,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm)
 	 * VCPU0, and only if its LVT0 is in EXTINT mode.
 	 */
 	if (kvm->arch.vapics_in_nmi_mode > 0)
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (vcpu)
+		kvm_for_each_vcpu(i, vcpu, kvm)
 			kvm_apic_nmi_wd_deliver(vcpu);
-		}
 }
 
 void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
@@ -665,7 +713,7 @@ void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_kpit_state *ps;
 
-	if (vcpu && pit) {
+	if (pit) {
 		int inject = 0;
 		ps = &pit->pit_state;
 

arch/x86/kvm/i8254.h

@@ -21,6 +21,7 @@ struct kvm_kpit_channel_state {
 
 struct kvm_kpit_state {
 	struct kvm_kpit_channel_state channels[3];
+	u32 flags;
 	struct kvm_timer pit_timer;
 	bool is_periodic;
 	u32    speaker_data_on;
@@ -49,8 +50,8 @@ struct kvm_pit {
 #define KVM_PIT_CHANNEL_MASK	    0x3
 
 void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu);
-void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val);
-struct kvm_pit *kvm_create_pit(struct kvm *kvm);
+void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start);
+struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags);
 void kvm_free_pit(struct kvm *kvm);
 void kvm_pit_reset(struct kvm_pit *pit);
 

arch/x86/kvm/i8259.c

@@ -30,50 +30,24 @@
 #include "irq.h"
 
 #include <linux/kvm_host.h>
-
-static void pic_lock(struct kvm_pic *s)
-	__acquires(&s->lock)
-{
-	spin_lock(&s->lock);
-}
-
-static void pic_unlock(struct kvm_pic *s)
-	__releases(&s->lock)
-{
-	struct kvm *kvm = s->kvm;
-	unsigned acks = s->pending_acks;
-	bool wakeup = s->wakeup_needed;
-	struct kvm_vcpu *vcpu;
-
-	s->pending_acks = 0;
-	s->wakeup_needed = false;
-
-	spin_unlock(&s->lock);
-
-	while (acks) {
-		kvm_notify_acked_irq(kvm, SELECT_PIC(__ffs(acks)),
-				     __ffs(acks));
-		acks &= acks - 1;
-	}
-
-	if (wakeup) {
-		vcpu = s->kvm->vcpus[0];
-		if (vcpu)
-			kvm_vcpu_kick(vcpu);
-	}
-}
+#include "trace.h"
 
 static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
 {
 	s->isr &= ~(1 << irq);
 	s->isr_ack |= (1 << irq);
+	if (s != &s->pics_state->pics[0])
+		irq += 8;
+	kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq);
 }
 
 void kvm_pic_clear_isr_ack(struct kvm *kvm)
 {
 	struct kvm_pic *s = pic_irqchip(kvm);
+	spin_lock(&s->lock);
 	s->pics[0].isr_ack = 0xff;
 	s->pics[1].isr_ack = 0xff;
+	spin_unlock(&s->lock);
 }
 
 /*
@@ -174,9 +148,9 @@ static void pic_update_irq(struct kvm_pic *s)
 
 void kvm_pic_update_irq(struct kvm_pic *s)
 {
-	pic_lock(s);
+	spin_lock(&s->lock);
 	pic_update_irq(s);
-	pic_unlock(s);
+	spin_unlock(&s->lock);
 }
 
 int kvm_pic_set_irq(void *opaque, int irq, int level)
@@ -184,12 +158,14 @@ int kvm_pic_set_irq(void *opaque, int irq, int level)
 	struct kvm_pic *s = opaque;
 	int ret = -1;
 
-	pic_lock(s);
+	spin_lock(&s->lock);
 	if (irq >= 0 && irq < PIC_NUM_PINS) {
 		ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
 		pic_update_irq(s);
+		trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
+				      s->pics[irq >> 3].imr, ret == 0);
 	}
-	pic_unlock(s);
+	spin_unlock(&s->lock);
 
 	return ret;
 }
@@ -217,7 +193,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 	int irq, irq2, intno;
 	struct kvm_pic *s = pic_irqchip(kvm);
 
-	pic_lock(s);
+	spin_lock(&s->lock);
 	irq = pic_get_irq(&s->pics[0]);
 	if (irq >= 0) {
 		pic_intack(&s->pics[0], irq);
@@ -242,8 +218,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 		intno = s->pics[0].irq_base + irq;
 	}
 	pic_update_irq(s);
-	pic_unlock(s);
-	kvm_notify_acked_irq(kvm, SELECT_PIC(irq), irq);
+	spin_unlock(&s->lock);
 
 	return intno;
 }
@@ -252,7 +227,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
 {
 	int irq, irqbase, n;
 	struct kvm *kvm = s->pics_state->irq_request_opaque;
-	struct kvm_vcpu *vcpu0 = kvm->vcpus[0];
+	struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu;
 
 	if (s == &s->pics_state->pics[0])
 		irqbase = 0;
@@ -263,7 +238,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
 		if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0))
 			if (s->irr & (1 << irq) || s->isr & (1 << irq)) {
 				n = irq + irqbase;
-				s->pics_state->pending_acks |= 1 << n;
+				kvm_notify_acked_irq(kvm, SELECT_PIC(n), n);
 			}
 	}
 	s->last_irr = 0;
@@ -428,8 +403,7 @@ static u32 elcr_ioport_read(void *opaque, u32 addr1)
 	return s->elcr;
 }
 
-static int picdev_in_range(struct kvm_io_device *this, gpa_t addr,
-			   int len, int is_write)
+static int picdev_in_range(gpa_t addr)
 {
 	switch (addr) {
 	case 0x20:
@@ -444,18 +418,25 @@ static int picdev_in_range(struct kvm_io_device *this, gpa_t addr,
 	}
 }
 
-static void picdev_write(struct kvm_io_device *this,
+static inline struct kvm_pic *to_pic(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pic, dev);
+}
+
+static int picdev_write(struct kvm_io_device *this,
 			 gpa_t addr, int len, const void *val)
 {
-	struct kvm_pic *s = this->private;
+	struct kvm_pic *s = to_pic(this);
 	unsigned char data = *(unsigned char *)val;
+	if (!picdev_in_range(addr))
+		return -EOPNOTSUPP;
 
 	if (len != 1) {
 		if (printk_ratelimit())
 			printk(KERN_ERR "PIC: non byte write\n");
-		return;
+		return 0;
 	}
-	pic_lock(s);
+	spin_lock(&s->lock);
 	switch (addr) {
 	case 0x20:
 	case 0x21:
@@ -468,21 +449,24 @@ static void picdev_write(struct kvm_io_device *this,
 		elcr_ioport_write(&s->pics[addr & 1], addr, data);
 		break;
 	}
-	pic_unlock(s);
+	spin_unlock(&s->lock);
+	return 0;
 }
 
-static void picdev_read(struct kvm_io_device *this,
+static int picdev_read(struct kvm_io_device *this,
 		       gpa_t addr, int len, void *val)
 {
-	struct kvm_pic *s = this->private;
+	struct kvm_pic *s = to_pic(this);
 	unsigned char data = 0;
+	if (!picdev_in_range(addr))
+		return -EOPNOTSUPP;
 
 	if (len != 1) {
 		if (printk_ratelimit())
 			printk(KERN_ERR "PIC: non byte read\n");
-		return;
+		return 0;
 	}
-	pic_lock(s);
+	spin_lock(&s->lock);
 	switch (addr) {
 	case 0x20:
 	case 0x21:
@@ -496,7 +480,8 @@ static void picdev_read(struct kvm_io_device *this,
 		break;
 	}
 	*(unsigned char *)val = data;
-	pic_unlock(s);
+	spin_unlock(&s->lock);
+	return 0;
 }
 
 /*
@@ -505,20 +490,27 @@ static void picdev_read(struct kvm_io_device *this,
 static void pic_irq_request(void *opaque, int level)
 {
 	struct kvm *kvm = opaque;
-	struct kvm_vcpu *vcpu = kvm->vcpus[0];
+	struct kvm_vcpu *vcpu = kvm->bsp_vcpu;
 	struct kvm_pic *s = pic_irqchip(kvm);
 	int irq = pic_get_irq(&s->pics[0]);
 
 	s->output = level;
 	if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) {
 		s->pics[0].isr_ack &= ~(1 << irq);
-		s->wakeup_needed = true;
+		kvm_vcpu_kick(vcpu);
 	}
 }
 
+static const struct kvm_io_device_ops picdev_ops = {
+	.read     = picdev_read,
+	.write    = picdev_write,
+};
+
 struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 {
 	struct kvm_pic *s;
+	int ret;
+
 	s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL);
 	if (!s)
 		return NULL;
@@ -534,10 +526,12 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 	/*
 	 * Initialize PIO device
 	 */
-	s->dev.read = picdev_read;
-	s->dev.write = picdev_write;
-	s->dev.in_range = picdev_in_range;
-	s->dev.private = s;
-	kvm_io_bus_register_dev(&kvm->pio_bus, &s->dev);
+	kvm_iodevice_init(&s->dev, &picdev_ops);
+	ret = kvm_io_bus_register_dev(kvm, &kvm->pio_bus, &s->dev);
+	if (ret < 0) {
+		kfree(s);
+		return NULL;
+	}
+
 	return s;
 }

arch/x86/kvm/irq.h

@@ -63,7 +63,6 @@ struct kvm_kpic_state {
 
 struct kvm_pic {
 	spinlock_t lock;
-	bool wakeup_needed;
 	unsigned pending_acks;
 	struct kvm *kvm;
 	struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */

arch/x86/kvm/kvm_cache_regs.h

@@ -29,4 +29,13 @@ static inline void kvm_rip_write(struct kvm_vcpu *vcpu, unsigned long val)
 	kvm_register_write(vcpu, VCPU_REGS_RIP, val);
 }
 
+static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
+{
+	if (!test_bit(VCPU_EXREG_PDPTR,
+		      (unsigned long *)&vcpu->arch.regs_avail))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR);
+
+	return vcpu->arch.pdptrs[index];
+}
+
 #endif

arch/x86/kvm/kvm_svm.h

-#ifndef __KVM_SVM_H
-#define __KVM_SVM_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/kvm_host.h>
-#include <asm/msr.h>
-
-#include <asm/svm.h>
-
-static const u32 host_save_user_msrs[] = {
-#ifdef CONFIG_X86_64
-	MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
-	MSR_FS_BASE,
-#endif
-	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
-};
-
-#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
-
-struct kvm_vcpu;
-
-struct vcpu_svm {
-	struct kvm_vcpu vcpu;
-	struct vmcb *vmcb;
-	unsigned long vmcb_pa;
-	struct svm_cpu_data *svm_data;
-	uint64_t asid_generation;
-
-	u64 next_rip;
-
-	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
-	u64 host_gs_base;
-	unsigned long host_cr2;
-
-	u32 *msrpm;
-	struct vmcb *hsave;
-	u64 hsave_msr;
-
-	u64 nested_vmcb;
-
-	/* These are the merged vectors */
-	u32 *nested_msrpm;
-
-	/* gpa pointers to the real vectors */
-	u64 nested_vmcb_msrpm;
-};
-
-#endif
-

arch/x86/kvm/kvm_timer.h

@@ -6,7 +6,7 @@ struct kvm_timer {
 	bool reinject;
 	struct kvm_timer_ops *t_ops;
 	struct kvm *kvm;
-	int vcpu_id;
+	struct kvm_vcpu *vcpu;
 };
 
 struct kvm_timer_ops {

arch/x86/kvm/lapic.h

@@ -12,6 +12,7 @@ struct kvm_lapic {
 	struct kvm_timer lapic_timer;
 	u32 divide_count;
 	struct kvm_vcpu *vcpu;
+	bool irr_pending;
 	struct page *regs_page;
 	void *regs;
 	gpa_t vapic_addr;
@@ -28,6 +29,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
 u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
+void kvm_apic_set_version(struct kvm_vcpu *vcpu);
 
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
 int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
@@ -44,4 +46,6 @@ void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
 
+int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 #endif

arch/x86/kvm/mmu.h

@@ -37,6 +37,8 @@
 #define PT32_ROOT_LEVEL 2
 #define PT32E_ROOT_LEVEL 3
 
+int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
+
 static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
@@ -75,7 +77,7 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
 	return vcpu->arch.cr0 & X86_CR0_PG;
 }
 
-static inline int is_present_pte(unsigned long pte)
+static inline int is_present_gpte(unsigned long pte)
 {
 	return pte & PT_PRESENT_MASK;
 }

arch/x86/kvm/mmutrace.h

+#if !defined(_TRACE_KVMMMU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVMMMU_H
+
+#include <linux/tracepoint.h>
+#include <linux/ftrace_event.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvmmmu
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE mmutrace
+
+#define KVM_MMU_PAGE_FIELDS \
+	__field(__u64, gfn) \
+	__field(__u32, role) \
+	__field(__u32, root_count) \
+	__field(__u32, unsync)
+
+#define KVM_MMU_PAGE_ASSIGN(sp)			     \
+	__entry->gfn = sp->gfn;			     \
+	__entry->role = sp->role.word;		     \
+	__entry->root_count = sp->root_count;        \
+	__entry->unsync = sp->unsync;
+
+#define KVM_MMU_PAGE_PRINTK() ({				        \
+	const char *ret = p->buffer + p->len;				\
+	static const char *access_str[] = {			        \
+		"---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux"  \
+	};							        \
+	union kvm_mmu_page_role role;				        \
+								        \
+	role.word = __entry->role;					\
+									\
+	trace_seq_printf(p, "sp gfn %llx %u/%u q%u%s %s%s %spge"	\
+			 " %snxe root %u %s%c",				\
+			 __entry->gfn, role.level, role.glevels,	\
+			 role.quadrant,					\
+			 role.direct ? " direct" : "",			\
+			 access_str[role.access],			\
+			 role.invalid ? " invalid" : "",		\
+			 role.cr4_pge ? "" : "!",			\
+			 role.nxe ? "" : "!",				\
+			 __entry->root_count,				\
+			 __entry->unsync ? "unsync" : "sync", 0);	\
+	ret;								\
+		})
+
+#define kvm_mmu_trace_pferr_flags       \
+	{ PFERR_PRESENT_MASK, "P" },	\
+	{ PFERR_WRITE_MASK, "W" },	\
+	{ PFERR_USER_MASK, "U" },	\
+	{ PFERR_RSVD_MASK, "RSVD" },	\
+	{ PFERR_FETCH_MASK, "F" }
+
+/*
+ * A pagetable walk has started
+ */
+TRACE_EVENT(
+	kvm_mmu_pagetable_walk,
+	TP_PROTO(u64 addr, int write_fault, int user_fault, int fetch_fault),
+	TP_ARGS(addr, write_fault, user_fault, fetch_fault),
+
+	TP_STRUCT__entry(
+		__field(__u64, addr)
+		__field(__u32, pferr)
+	),
+
+	TP_fast_assign(
+		__entry->addr = addr;
+		__entry->pferr = (!!write_fault << 1) | (!!user_fault << 2)
+		                 | (!!fetch_fault << 4);
+	),
+
+	TP_printk("addr %llx pferr %x %s", __entry->addr, __entry->pferr,
+		  __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags))
+);
+
+
+/* We just walked a paging element */
+TRACE_EVENT(
+	kvm_mmu_paging_element,
+	TP_PROTO(u64 pte, int level),
+	TP_ARGS(pte, level),
+
+	TP_STRUCT__entry(
+		__field(__u64, pte)
+		__field(__u32, level)
+		),
+
+	TP_fast_assign(
+		__entry->pte = pte;
+		__entry->level = level;
+		),
+
+	TP_printk("pte %llx level %u", __entry->pte, __entry->level)
+);
+
+/* We set a pte accessed bit */
+TRACE_EVENT(
+	kvm_mmu_set_accessed_bit,
+	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+	TP_ARGS(table_gfn, index, size),
+
+	TP_STRUCT__entry(
+		__field(__u64, gpa)
+		),
+
+	TP_fast_assign(
+		__entry->gpa = ((u64)table_gfn << PAGE_SHIFT)
+				+ index * size;
+		),
+
+	TP_printk("gpa %llx", __entry->gpa)
+);
+
+/* We set a pte dirty bit */
+TRACE_EVENT(
+	kvm_mmu_set_dirty_bit,
+	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+	TP_ARGS(table_gfn, index, size),
+
+	TP_STRUCT__entry(
+		__field(__u64, gpa)
+		),
+
+	TP_fast_assign(
+		__entry->gpa = ((u64)table_gfn << PAGE_SHIFT)
+				+ index * size;
+		),
+
+	TP_printk("gpa %llx", __entry->gpa)
+);
+
+TRACE_EVENT(
+	kvm_mmu_walker_error,
+	TP_PROTO(u32 pferr),
+	TP_ARGS(pferr),
+
+	TP_STRUCT__entry(
+		__field(__u32, pferr)
+		),
+
+	TP_fast_assign(
+		__entry->pferr = pferr;
+		),
+
+	TP_printk("pferr %x %s", __entry->pferr,
+		  __print_flags(__entry->pferr, "|", kvm_mmu_trace_pferr_flags))
+);
+
+TRACE_EVENT(
+	kvm_mmu_get_page,
+	TP_PROTO(struct kvm_mmu_page *sp, bool created),
+	TP_ARGS(sp, created),
+
+	TP_STRUCT__entry(
+		KVM_MMU_PAGE_FIELDS
+		__field(bool, created)
+		),
+
+	TP_fast_assign(
+		KVM_MMU_PAGE_ASSIGN(sp)
+		__entry->created = created;
+		),
+
+	TP_printk("%s %s", KVM_MMU_PAGE_PRINTK(),
+		  __entry->created ? "new" : "existing")
+);
+
+TRACE_EVENT(
+	kvm_mmu_sync_page,
+	TP_PROTO(struct kvm_mmu_page *sp),
+	TP_ARGS(sp),
+
+	TP_STRUCT__entry(
+		KVM_MMU_PAGE_FIELDS
+		),
+
+	TP_fast_assign(
+		KVM_MMU_PAGE_ASSIGN(sp)
+		),
+
+	TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+);
+
+TRACE_EVENT(
+	kvm_mmu_unsync_page,
+	TP_PROTO(struct kvm_mmu_page *sp),
+	TP_ARGS(sp),
+
+	TP_STRUCT__entry(
+		KVM_MMU_PAGE_FIELDS
+		),
+
+	TP_fast_assign(
+		KVM_MMU_PAGE_ASSIGN(sp)
+		),
+
+	TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+);
+
+TRACE_EVENT(
+	kvm_mmu_zap_page,
+	TP_PROTO(struct kvm_mmu_page *sp),
+	TP_ARGS(sp),
+
+	TP_STRUCT__entry(
+		KVM_MMU_PAGE_FIELDS
+		),
+
+	TP_fast_assign(
+		KVM_MMU_PAGE_ASSIGN(sp)
+		),
+
+	TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+);
+
+#endif /* _TRACE_KVMMMU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/x86/kvm/timer.c

@@ -9,12 +9,16 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
 	int restart_timer = 0;
 	wait_queue_head_t *q = &vcpu->wq;
 
+	/*
+	 * There is a race window between reading and incrementing, but we do
+	 * not care about potentially loosing timer events in the !reinject
+	 * case anyway.
+	 */
+	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
+		atomic_inc(&ktimer->pending);
 		/* FIXME: this code should not know anything about vcpus */
-	if (!atomic_inc_and_test(&ktimer->pending))
 		set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
-
-	if (!ktimer->reinject)
-		atomic_set(&ktimer->pending, 1);
+	}
 
 	if (waitqueue_active(q))
 		wake_up_interruptible(q);
@@ -33,7 +37,7 @@ enum hrtimer_restart kvm_timer_fn(struct hrtimer *data)
 	struct kvm_vcpu *vcpu;
 	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
 
-	vcpu = ktimer->kvm->vcpus[ktimer->vcpu_id];
+	vcpu = ktimer->vcpu;
 	if (!vcpu)
 		return HRTIMER_NORESTART;
 

arch/x86/kvm/trace.h

+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+#define TRACE_INCLUDE_PATH arch/x86/kvm
+#define TRACE_INCLUDE_FILE trace
+
+/*
+ * Tracepoint for guest mode entry.
+ */
+TRACE_EVENT(kvm_entry,
+	TP_PROTO(unsigned int vcpu_id),
+	TP_ARGS(vcpu_id),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	vcpu_id		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	= vcpu_id;
+	),
+
+	TP_printk("vcpu %u", __entry->vcpu_id)
+);
+
+/*
+ * Tracepoint for hypercall.
+ */
+TRACE_EVENT(kvm_hypercall,
+	TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1,
+		 unsigned long a2, unsigned long a3),
+	TP_ARGS(nr, a0, a1, a2, a3),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long, 	nr		)
+		__field(	unsigned long,	a0		)
+		__field(	unsigned long,	a1		)
+		__field(	unsigned long,	a2		)
+		__field(	unsigned long,	a3		)
+	),
+
+	TP_fast_assign(
+		__entry->nr		= nr;
+		__entry->a0		= a0;
+		__entry->a1		= a1;
+		__entry->a2		= a2;
+		__entry->a3		= a3;
+	),
+
+	TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx",
+		 __entry->nr, __entry->a0, __entry->a1,  __entry->a2,
+		 __entry->a3)
+);
+
+/*
+ * Tracepoint for PIO.
+ */
+TRACE_EVENT(kvm_pio,
+	TP_PROTO(unsigned int rw, unsigned int port, unsigned int size,
+		 unsigned int count),
+	TP_ARGS(rw, port, size, count),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int, 	rw		)
+		__field(	unsigned int, 	port		)
+		__field(	unsigned int, 	size		)
+		__field(	unsigned int,	count		)
+	),
+
+	TP_fast_assign(
+		__entry->rw		= rw;
+		__entry->port		= port;
+		__entry->size		= size;
+		__entry->count		= count;
+	),
+
+	TP_printk("pio_%s at 0x%x size %d count %d",
+		  __entry->rw ? "write" : "read",
+		  __entry->port, __entry->size, __entry->count)
+);
+
+/*
+ * Tracepoint for cpuid.
+ */
+TRACE_EVENT(kvm_cpuid,
+	TP_PROTO(unsigned int function, unsigned long rax, unsigned long rbx,
+		 unsigned long rcx, unsigned long rdx),
+	TP_ARGS(function, rax, rbx, rcx, rdx),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	function	)
+		__field(	unsigned long,	rax		)
+		__field(	unsigned long,	rbx		)
+		__field(	unsigned long,	rcx		)
+		__field(	unsigned long,	rdx		)
+	),
+
+	TP_fast_assign(
+		__entry->function	= function;
+		__entry->rax		= rax;
+		__entry->rbx		= rbx;
+		__entry->rcx		= rcx;
+		__entry->rdx		= rdx;
+	),
+
+	TP_printk("func %x rax %lx rbx %lx rcx %lx rdx %lx",
+		  __entry->function, __entry->rax,
+		  __entry->rbx, __entry->rcx, __entry->rdx)
+);
+
+#define AREG(x) { APIC_##x, "APIC_" #x }
+
+#define kvm_trace_symbol_apic						    \
+	AREG(ID), AREG(LVR), AREG(TASKPRI), AREG(ARBPRI), AREG(PROCPRI),    \
+	AREG(EOI), AREG(RRR), AREG(LDR), AREG(DFR), AREG(SPIV), AREG(ISR),  \
+	AREG(TMR), AREG(IRR), AREG(ESR), AREG(ICR), AREG(ICR2), AREG(LVTT), \
+	AREG(LVTTHMR), AREG(LVTPC), AREG(LVT0), AREG(LVT1), AREG(LVTERR),   \
+	AREG(TMICT), AREG(TMCCT), AREG(TDCR), AREG(SELF_IPI), AREG(EFEAT),  \
+	AREG(ECTRL)
+/*
+ * Tracepoint for apic access.
+ */
+TRACE_EVENT(kvm_apic,
+	TP_PROTO(unsigned int rw, unsigned int reg, unsigned int val),
+	TP_ARGS(rw, reg, val),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	rw		)
+		__field(	unsigned int,	reg		)
+		__field(	unsigned int,	val		)
+	),
+
+	TP_fast_assign(
+		__entry->rw		= rw;
+		__entry->reg		= reg;
+		__entry->val		= val;
+	),
+
+	TP_printk("apic_%s %s = 0x%x",
+		  __entry->rw ? "write" : "read",
+		  __print_symbolic(__entry->reg, kvm_trace_symbol_apic),
+		  __entry->val)
+);
+
+#define trace_kvm_apic_read(reg, val)		trace_kvm_apic(0, reg, val)
+#define trace_kvm_apic_write(reg, val)		trace_kvm_apic(1, reg, val)
+
+/*
+ * Tracepoint for kvm guest exit:
+ */
+TRACE_EVENT(kvm_exit,
+	TP_PROTO(unsigned int exit_reason, unsigned long guest_rip),
+	TP_ARGS(exit_reason, guest_rip),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_reason	)
+		__field(	unsigned long,	guest_rip	)
+	),
+
+	TP_fast_assign(
+		__entry->exit_reason	= exit_reason;
+		__entry->guest_rip	= guest_rip;
+	),
+
+	TP_printk("reason %s rip 0x%lx",
+		 ftrace_print_symbols_seq(p, __entry->exit_reason,
+					  kvm_x86_ops->exit_reasons_str),
+		 __entry->guest_rip)
+);
+
+/*
+ * Tracepoint for kvm interrupt injection:
+ */
+TRACE_EVENT(kvm_inj_virq,
+	TP_PROTO(unsigned int irq),
+	TP_ARGS(irq),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+	),
+
+	TP_printk("irq %u", __entry->irq)
+);
+
+/*
+ * Tracepoint for page fault.
+ */
+TRACE_EVENT(kvm_page_fault,
+	TP_PROTO(unsigned long fault_address, unsigned int error_code),
+	TP_ARGS(fault_address, error_code),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	fault_address	)
+		__field(	unsigned int,	error_code	)
+	),
+
+	TP_fast_assign(
+		__entry->fault_address	= fault_address;
+		__entry->error_code	= error_code;
+	),
+
+	TP_printk("address %lx error_code %x",
+		  __entry->fault_address, __entry->error_code)
+);
+
+/*
+ * Tracepoint for guest MSR access.
+ */
+TRACE_EVENT(kvm_msr,
+	TP_PROTO(unsigned int rw, unsigned int ecx, unsigned long data),
+	TP_ARGS(rw, ecx, data),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	rw		)
+		__field(	unsigned int,	ecx		)
+		__field(	unsigned long,	data		)
+	),
+
+	TP_fast_assign(
+		__entry->rw		= rw;
+		__entry->ecx		= ecx;
+		__entry->data		= data;
+	),
+
+	TP_printk("msr_%s %x = 0x%lx",
+		  __entry->rw ? "write" : "read",
+		  __entry->ecx, __entry->data)
+);
+
+#define trace_kvm_msr_read(ecx, data)		trace_kvm_msr(0, ecx, data)
+#define trace_kvm_msr_write(ecx, data)		trace_kvm_msr(1, ecx, data)
+
+/*
+ * Tracepoint for guest CR access.
+ */
+TRACE_EVENT(kvm_cr,
+	TP_PROTO(unsigned int rw, unsigned int cr, unsigned long val),
+	TP_ARGS(rw, cr, val),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	rw		)
+		__field(	unsigned int,	cr		)
+		__field(	unsigned long,	val		)
+	),
+
+	TP_fast_assign(
+		__entry->rw		= rw;
+		__entry->cr		= cr;
+		__entry->val		= val;
+	),
+
+	TP_printk("cr_%s %x = 0x%lx",
+		  __entry->rw ? "write" : "read",
+		  __entry->cr, __entry->val)
+);
+
+#define trace_kvm_cr_read(cr, val)		trace_kvm_cr(0, cr, val)
+#define trace_kvm_cr_write(cr, val)		trace_kvm_cr(1, cr, val)
+
+TRACE_EVENT(kvm_pic_set_irq,
+	    TP_PROTO(__u8 chip, __u8 pin, __u8 elcr, __u8 imr, bool coalesced),
+	    TP_ARGS(chip, pin, elcr, imr, coalesced),
+
+	TP_STRUCT__entry(
+		__field(	__u8,		chip		)
+		__field(	__u8,		pin		)
+		__field(	__u8,		elcr		)
+		__field(	__u8,		imr		)
+		__field(	bool,		coalesced	)
+	),
+
+	TP_fast_assign(
+		__entry->chip		= chip;
+		__entry->pin		= pin;
+		__entry->elcr		= elcr;
+		__entry->imr		= imr;
+		__entry->coalesced	= coalesced;
+	),
+
+	TP_printk("chip %u pin %u (%s%s)%s",
+		  __entry->chip, __entry->pin,
+		  (__entry->elcr & (1 << __entry->pin)) ? "level":"edge",
+		  (__entry->imr & (1 << __entry->pin)) ? "|masked":"",
+		  __entry->coalesced ? " (coalesced)" : "")
+);
+
+#define kvm_apic_dst_shorthand		\
+	{0x0, "dst"},			\
+	{0x1, "self"},			\
+	{0x2, "all"},			\
+	{0x3, "all-but-self"}
+
+TRACE_EVENT(kvm_apic_ipi,
+	    TP_PROTO(__u32 icr_low, __u32 dest_id),
+	    TP_ARGS(icr_low, dest_id),
+
+	TP_STRUCT__entry(
+		__field(	__u32,		icr_low		)
+		__field(	__u32,		dest_id		)
+	),
+
+	TP_fast_assign(
+		__entry->icr_low	= icr_low;
+		__entry->dest_id	= dest_id;
+	),
+
+	TP_printk("dst %x vec %u (%s|%s|%s|%s|%s)",
+		  __entry->dest_id, (u8)__entry->icr_low,
+		  __print_symbolic((__entry->icr_low >> 8 & 0x7),
+				   kvm_deliver_mode),
+		  (__entry->icr_low & (1<<11)) ? "logical" : "physical",
+		  (__entry->icr_low & (1<<14)) ? "assert" : "de-assert",
+		  (__entry->icr_low & (1<<15)) ? "level" : "edge",
+		  __print_symbolic((__entry->icr_low >> 18 & 0x3),
+				   kvm_apic_dst_shorthand))
+);
+
+TRACE_EVENT(kvm_apic_accept_irq,
+	    TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec, bool coalesced),
+	    TP_ARGS(apicid, dm, tm, vec, coalesced),
+
+	TP_STRUCT__entry(
+		__field(	__u32,		apicid		)
+		__field(	__u16,		dm		)
+		__field(	__u8,		tm		)
+		__field(	__u8,		vec		)
+		__field(	bool,		coalesced	)
+	),
+
+	TP_fast_assign(
+		__entry->apicid		= apicid;
+		__entry->dm		= dm;
+		__entry->tm		= tm;
+		__entry->vec		= vec;
+		__entry->coalesced	= coalesced;
+	),
+
+	TP_printk("apicid %x vec %u (%s|%s)%s",
+		  __entry->apicid, __entry->vec,
+		  __print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode),
+		  __entry->tm ? "level" : "edge",
+		  __entry->coalesced ? " (coalesced)" : "")
+);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/x86/kvm/x86.h

@@ -31,4 +31,8 @@ static inline bool kvm_exception_is_soft(unsigned int nr)
 {
 	return (nr == BP_VECTOR) || (nr == OF_VECTOR);
 }
+
+struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
+                                             u32 function, u32 index);
+
 #endif

arch/x86/mm/highmem_32.c

@@ -104,6 +104,7 @@ EXPORT_SYMBOL(kunmap);
 EXPORT_SYMBOL(kmap_atomic);
 EXPORT_SYMBOL(kunmap_atomic);
 EXPORT_SYMBOL(kmap_atomic_prot);
+EXPORT_SYMBOL(kmap_atomic_to_page);
 
 void __init set_highmem_pages_init(void)
 {

include/asm-generic/Kbuild.asm

@@ -3,6 +3,11 @@ ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h \
 header-y  += kvm.h
 endif
 
+ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm_para.h \
+		  $(srctree)/include/asm-$(SRCARCH)/kvm_para.h),)
+header-y  += kvm_para.h
+endif
+
 ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/a.out.h \
       		  $(srctree)/include/asm-$(SRCARCH)/a.out.h),)
 unifdef-y += a.out.h

include/linux/Kbuild

@@ -268,6 +268,10 @@ ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h \
       		  $(srctree)/include/asm-$(SRCARCH)/kvm.h),)
 unifdef-y += kvm.h
 endif
+ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm_para.h \
+		  $(srctree)/include/asm-$(SRCARCH)/kvm_para.h),)
+unifdef-y += kvm_para.h
+endif
 unifdef-y += llc.h
 unifdef-y += loop.h
 unifdef-y += lp.h

include/linux/kvm_para.h

@@ -13,6 +13,7 @@
 #define KVM_ENOSYS		1000
 #define KVM_EFAULT		EFAULT
 #define KVM_E2BIG		E2BIG
+#define KVM_EPERM		EPERM
 
 #define KVM_HC_VAPIC_POLL_IRQ		1
 #define KVM_HC_MMU_OP			2

mm/hugetlb.c

@@ -234,6 +234,7 @@ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
 
 	return 1UL << (hstate->order + PAGE_SHIFT);
 }
+EXPORT_SYMBOL_GPL(vma_kernel_pagesize);
 
 /*
  * Return the page size being used by the MMU to back a VMA. In the majority

virt/kvm/Kconfig

+# KVM common configuration items and defaults
+
+config HAVE_KVM
+       bool
+
+config HAVE_KVM_IRQCHIP
+       bool
+
+config HAVE_KVM_EVENTFD
+       bool
+       select EVENTFD
+
+config KVM_APIC_ARCHITECTURE
+       bool

virt/kvm/coalesced_mmio.h

@@ -12,6 +12,7 @@
 struct kvm_coalesced_mmio_dev {
 	struct kvm_io_device dev;
 	struct kvm *kvm;
+	spinlock_t lock;
 	int nb_zones;
 	struct kvm_coalesced_mmio_zone zone[KVM_COALESCED_MMIO_ZONE_MAX];
 };