Merge branch 'kvm-updates/2.6.34' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.34' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (145 commits)
  KVM: x86: Add KVM_CAP_X86_ROBUST_SINGLESTEP
  KVM: VMX: Update instruction length on intercepted BP
  KVM: Fix emulate_sys[call, enter, exit]()'s fault handling
  KVM: Fix segment descriptor loading
  KVM: Fix load_guest_segment_descriptor() to inject page fault
  KVM: x86 emulator: Forbid modifying CS segment register by mov instruction
  KVM: Convert kvm->requests_lock to raw_spinlock_t
  KVM: Convert i8254/i8259 locks to raw_spinlocks
  KVM: x86 emulator: disallow opcode 82 in 64-bit mode
  KVM: x86 emulator: code style cleanup
  KVM: Plan obsolescence of kernel allocated slots, paravirt mmu
  KVM: x86 emulator: Add LOCK prefix validity checking
  KVM: x86 emulator: Check CPL level during privilege instruction emulation
  KVM: x86 emulator: Fix popf emulation
  KVM: x86 emulator: Check IOPL level during io instruction emulation
  KVM: x86 emulator: fix memory access during x86 emulation
  KVM: x86 emulator: Add Virtual-8086 mode of emulation
  KVM: x86 emulator: Add group9 instruction decoding
  KVM: x86 emulator: Add group8 instruction decoding
  KVM: do not store wqh in irqfd
  ...

Trivial conflicts in Documentation/feature-removal-schedule.txt

Documentation/feature-removal-schedule.txt

@@ -556,3 +556,35 @@ Why:	udev fully replaces this special file system that only contains CAPI
 	NCCI TTY device nodes. User space (pppdcapiplugin) works without
 	noticing the difference.
 Who:	Jan Kiszka <jan.kiszka@web.de>
+
+----------------------------
+
+What:	KVM memory aliases support
+When:	July 2010
+Why:	Memory aliasing support is used for speeding up guest vga access
+	through the vga windows.
+
+	Modern userspace no longer uses this feature, so it's just bitrotted
+	code and can be removed with no impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM kernel-allocated memory slots
+When:	July 2010
+Why:	Since 2.6.25, kvm supports user-allocated memory slots, which are
+	much more flexible than kernel-allocated slots.  All current userspace
+	supports the newer interface and this code can be removed with no
+	impact.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:	KVM paravirt mmu host support
+When:	January 2011
+Why:	The paravirt mmu host support is slower than non-paravirt mmu, both
+	on newer and older hardware.  It is already not exposed to the guest,
+	and kept only for live migration purposes.
+Who:	Avi Kivity <avi@redhat.com>
+
+----------------------------

Documentation/kvm/api.txt

@@ -23,12 +23,12 @@ of a virtual machine.  The ioctls belong to three classes
    Only run vcpu ioctls from the same thread that was used to create the
    vcpu.
 
-2. File descritpors
+2. File descriptors
 
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
 can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
-handle will create a VM file descripror which can be used to issue VM
+handle will create a VM file descriptor which can be used to issue VM
 ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
 and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
 fd can be used to control the vcpu, including the important task of
@@ -643,7 +643,7 @@ Type: vm ioctl
 Parameters: struct kvm_clock_data (in)
 Returns: 0 on success, -1 on error
 
-Sets the current timestamp of kvmclock to the valued specific in its parameter.
+Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
@@ -795,11 +795,11 @@ Unused.
 			__u64 data_offset; /* relative to kvm_run start */
 		} io;
 
-If exit_reason is KVM_EXIT_IO_IN or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_IO, then the vcpu has
 executed a port I/O instruction which could not be satisfied by kvm.
 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
 where kvm expects application code to place the data for the next
-KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a patcked array.
+KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
 
 		struct {
 			struct kvm_debug_exit_arch arch;
@@ -815,7 +815,7 @@ Unused.
 			__u8  is_write;
 		} mmio;
 
-If exit_reason is KVM_EXIT_MMIO or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_MMIO, then the vcpu has
 executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.

MAINTAINERS

@@ -3173,7 +3173,7 @@ F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
-M:	Hollis Blanchard <hollisb@us.ibm.com>
+M:	Alexander Graf <agraf@suse.de>
 L:	kvm-ppc@vger.kernel.org
 W:	http://kvm.qumranet.com
 S:	Supported

arch/ia64/kvm/Kconfig

@@ -26,6 +26,7 @@ config KVM
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
 	select KVM_APIC_ARCHITECTURE
+	select KVM_MMIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/ia64/kvm/kvm-ia64.c

@@ -241,10 +241,10 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 0;
 mmio:
 	if (p->dir)
-		r = kvm_io_bus_read(&vcpu->kvm->mmio_bus, p->addr,
+		r = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, p->addr,
 				    p->size, &p->data);
 	else
-		r = kvm_io_bus_write(&vcpu->kvm->mmio_bus, p->addr,
+		r = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, p->addr,
 				     p->size, &p->data);
 	if (r)
 		printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr);
@@ -636,12 +636,9 @@ static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
 static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	union context *host_ctx, *guest_ctx;
-	int r;
+	int r, idx;
 
-	/*
-	 * down_read() may sleep and return with interrupts enabled
-	 */
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 again:
 	if (signal_pending(current)) {
@@ -663,7 +660,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (r < 0)
 		goto vcpu_run_fail;
 
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	kvm_guest_enter();
 
 	/*
@@ -687,7 +684,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_guest_exit();
 	preempt_enable();
 
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	r = kvm_handle_exit(kvm_run, vcpu);
 
@@ -697,10 +694,10 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 out:
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (r > 0) {
 		kvm_resched(vcpu);
-		down_read(&vcpu->kvm->slots_lock);
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		goto again;
 	}
 
@@ -971,7 +968,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
-			kfree(kvm->arch.vioapic);
+			kvm_ioapic_destroy(kvm);
 			goto out;
 		}
 		break;
@@ -1377,12 +1374,14 @@ static void free_kvm(struct kvm *kvm)
 
 static void kvm_release_vm_pages(struct kvm *kvm)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int i, j;
 	unsigned long base_gfn;
 
-	for (i = 0; i < kvm->nmemslots; i++) {
-		memslot = &kvm->memslots[i];
+	slots = rcu_dereference(kvm->memslots);
+	for (i = 0; i < slots->nmemslots; i++) {
+		memslot = &slots->memslots[i];
 		base_gfn = memslot->base_gfn;
 
 		for (j = 0; j < memslot->npages; j++) {
@@ -1405,6 +1404,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vioapic);
 	kvm_release_vm_pages(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->srcu);
 	free_kvm(kvm);
 }
 
@@ -1576,15 +1576,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	return r;
 }
 
-int kvm_arch_set_memory_region(struct kvm *kvm,
-		struct kvm_userspace_memory_region *mem,
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
+		struct kvm_userspace_memory_region *mem,
 		int user_alloc)
 {
 	unsigned long i;
 	unsigned long pfn;
-	int npages = mem->memory_size >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+	int npages = memslot->npages;
 	unsigned long base_gfn = memslot->base_gfn;
 
 	if (base_gfn + npages > (KVM_MAX_MEM_SIZE >> PAGE_SHIFT))
@@ -1608,6 +1608,14 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+		struct kvm_userspace_memory_region *mem,
+		struct kvm_memory_slot old,
+		int user_alloc)
+{
+	return;
+}
+
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
 	kvm_flush_remote_tlbs(kvm);
@@ -1802,7 +1810,7 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_MEMORY_SLOTS)
 		goto out;
 
-	memslot = &kvm->memslots[log->slot];
+	memslot = &kvm->memslots->memslots[log->slot];
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -1827,6 +1835,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
+	mutex_lock(&kvm->slots_lock);
 	spin_lock(&kvm->arch.dirty_log_lock);
 
 	r = kvm_ia64_sync_dirty_log(kvm, log);
@@ -1840,12 +1849,13 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
 		kvm_flush_remote_tlbs(kvm);
-		memslot = &kvm->memslots[log->slot];
+		memslot = &kvm->memslots->memslots[log->slot];
 		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
 		memset(memslot->dirty_bitmap, 0, n);
 	}
 	r = 0;
 out:
+	mutex_unlock(&kvm->slots_lock);
 	spin_unlock(&kvm->arch.dirty_log_lock);
 	return r;
 }

arch/ia64/kvm/kvm_fw.c

@@ -75,7 +75,7 @@ static void set_pal_result(struct kvm_vcpu *vcpu,
 	struct exit_ctl_data *p;
 
 	p = kvm_get_exit_data(vcpu);
-	if (p && p->exit_reason == EXIT_REASON_PAL_CALL) {
+	if (p->exit_reason == EXIT_REASON_PAL_CALL) {
 		p->u.pal_data.ret = result;
 		return ;
 	}
@@ -87,7 +87,7 @@ static void set_sal_result(struct kvm_vcpu *vcpu,
 	struct exit_ctl_data *p;
 
 	p = kvm_get_exit_data(vcpu);
-	if (p && p->exit_reason == EXIT_REASON_SAL_CALL) {
+	if (p->exit_reason == EXIT_REASON_SAL_CALL) {
 		p->u.sal_data.ret = result;
 		return ;
 	}
@@ -322,7 +322,7 @@ static  u64 kvm_get_pal_call_index(struct kvm_vcpu *vcpu)
 	struct exit_ctl_data *p;
 
 	p = kvm_get_exit_data(vcpu);
-	if (p && (p->exit_reason == EXIT_REASON_PAL_CALL))
+	if (p->exit_reason == EXIT_REASON_PAL_CALL)
 		index = p->u.pal_data.gr28;
 
 	return index;
@@ -646,18 +646,16 @@ static void kvm_get_sal_call_data(struct kvm_vcpu *vcpu, u64 *in0, u64 *in1,
 
 	p = kvm_get_exit_data(vcpu);
 
-	if (p) {
-		if (p->exit_reason == EXIT_REASON_SAL_CALL) {
-			*in0 = p->u.sal_data.in0;
-			*in1 = p->u.sal_data.in1;
-			*in2 = p->u.sal_data.in2;
-			*in3 = p->u.sal_data.in3;
-			*in4 = p->u.sal_data.in4;
-			*in5 = p->u.sal_data.in5;
-			*in6 = p->u.sal_data.in6;
-			*in7 = p->u.sal_data.in7;
-			return ;
-		}
+	if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+		*in0 = p->u.sal_data.in0;
+		*in1 = p->u.sal_data.in1;
+		*in2 = p->u.sal_data.in2;
+		*in3 = p->u.sal_data.in3;
+		*in4 = p->u.sal_data.in4;
+		*in5 = p->u.sal_data.in5;
+		*in6 = p->u.sal_data.in6;
+		*in7 = p->u.sal_data.in7;
+		return ;
 	}
 	*in0 = 0;
 }

arch/ia64/kvm/mmio.c

@@ -316,8 +316,8 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
 		return;
 	} else {
 		inst_type = -1;
-		panic_vm(vcpu, "Unsupported MMIO access instruction! \
-				Bunld[0]=0x%lx, Bundle[1]=0x%lx\n",
+		panic_vm(vcpu, "Unsupported MMIO access instruction! "
+				"Bunld[0]=0x%lx, Bundle[1]=0x%lx\n",
 				bundle.i64[0], bundle.i64[1]);
 	}
 

arch/ia64/kvm/vcpu.c

@@ -1639,8 +1639,8 @@ void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val)
 	 * Otherwise panic
 	 */
 	if (val & (IA64_PSR_PK | IA64_PSR_IS | IA64_PSR_VM))
-		panic_vm(vcpu, "Only support guests with vpsr.pk =0 \
-				& vpsr.is=0\n");
+		panic_vm(vcpu, "Only support guests with vpsr.pk =0 "
+				"& vpsr.is=0\n");
 
 	/*
 	 * For those IA64_PSR bits: id/da/dd/ss/ed/ia

arch/powerpc/include/asm/kvm_asm.h

@@ -97,4 +97,10 @@
 #define RESUME_HOST             RESUME_FLAG_HOST
 #define RESUME_HOST_NV          (RESUME_FLAG_HOST|RESUME_FLAG_NV)
 
+#define KVM_GUEST_MODE_NONE	0
+#define KVM_GUEST_MODE_GUEST	1
+#define KVM_GUEST_MODE_SKIP	2
+
+#define KVM_INST_FETCH_FAILED	-1
+
 #endif /* __POWERPC_KVM_ASM_H__ */

arch/powerpc/include/asm/kvm_book3s.h

@@ -22,7 +22,7 @@
 
 #include <linux/types.h>
 #include <linux/kvm_host.h>
-#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_64_asm.h>
 
 struct kvmppc_slb {
 	u64 esid;
@@ -33,7 +33,8 @@ struct kvmppc_slb {
 	bool Ks;
 	bool Kp;
 	bool nx;
-	bool large;
+	bool large;	/* PTEs are 16MB */
+	bool tb;	/* 1TB segment */
 	bool class;
 };
 
@@ -69,6 +70,7 @@ struct kvmppc_sid_map {
 
 struct kvmppc_vcpu_book3s {
 	struct kvm_vcpu vcpu;
+	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
 	struct kvmppc_slb slb[64];
 	struct {
@@ -89,6 +91,7 @@ struct kvmppc_vcpu_book3s {
 	u64 vsid_next;
 	u64 vsid_max;
 	int context_id;
+	ulong prog_flags; /* flags to inject when giving a 700 trap */
 };
 
 #define CONTEXT_HOST		0
@@ -119,6 +122,10 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 
 extern u32 kvmppc_trampoline_lowmem;
 extern u32 kvmppc_trampoline_enter;
+extern void kvmppc_rmcall(ulong srr0, ulong srr1);
+extern void kvmppc_load_up_fpu(void);
+extern void kvmppc_load_up_altivec(void);
+extern void kvmppc_load_up_vsx(void);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {

arch/powerpc/include/asm/kvm_book3s_64_asm.h

@@ -20,6 +20,8 @@
 #ifndef __ASM_KVM_BOOK3S_ASM_H__
 #define __ASM_KVM_BOOK3S_ASM_H__
 
+#ifdef __ASSEMBLY__
+
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 
 #include <asm/kvm_asm.h>
@@ -55,4 +57,20 @@ kvmppc_resume_\intno:
 
 #endif /* CONFIG_KVM_BOOK3S_64_HANDLER */
 
+#else  /*__ASSEMBLY__ */
+
+struct kvmppc_book3s_shadow_vcpu {
+	ulong gpr[14];
+	u32 cr;
+	u32 xer;
+	ulong host_r1;
+	ulong host_r2;
+	ulong handler;
+	ulong scratch0;
+	ulong scratch1;
+	ulong vmhandler;
+};
+
+#endif /*__ASSEMBLY__ */
+
 #endif /* __ASM_KVM_BOOK3S_ASM_H__ */

arch/powerpc/include/asm/kvm_e500.h

@@ -52,9 +52,12 @@ struct kvmppc_vcpu_e500 {
 	u32 mas5;
 	u32 mas6;
 	u32 mas7;
+	u32 l1csr0;
 	u32 l1csr1;
 	u32 hid0;
 	u32 hid1;
+	u32 tlb0cfg;
+	u32 tlb1cfg;
 
 	struct kvm_vcpu vcpu;
 };

arch/powerpc/include/asm/kvm_host.h

@@ -167,23 +167,40 @@ struct kvm_vcpu_arch {
 	ulong trampoline_lowmem;
 	ulong trampoline_enter;
 	ulong highmem_handler;
+	ulong rmcall;
 	ulong host_paca_phys;
 	struct kvmppc_mmu mmu;
 #endif
 
-	u64 fpr[32];
 	ulong gpr[32];
 
+	u64 fpr[32];
+	u32 fpscr;
+
+#ifdef CONFIG_ALTIVEC
+	vector128 vr[32];
+	vector128 vscr;
+#endif
+
+#ifdef CONFIG_VSX
+	u64 vsr[32];
+#endif
+
 	ulong pc;
-	u32 cr;
 	ulong ctr;
 	ulong lr;
+
+#ifdef CONFIG_BOOKE
 	ulong xer;
+	u32 cr;
+#endif
 
 	ulong msr;
 #ifdef CONFIG_PPC64
 	ulong shadow_msr;
+	ulong shadow_srr1;
 	ulong hflags;
+	ulong guest_owned_ext;
 #endif
 	u32 mmucr;
 	ulong sprg0;
@@ -242,6 +259,8 @@ struct kvm_vcpu_arch {
 #endif
 	ulong fault_dear;
 	ulong fault_esr;
+	ulong queued_dear;
+	ulong queued_esr;
 	gpa_t paddr_accessed;
 
 	u8 io_gpr; /* GPR used as IO source/target */

arch/powerpc/include/asm/kvm_ppc.h

@@ -28,6 +28,9 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/kvm_book3s.h>
+#endif
 
 enum emulation_result {
 	EMULATE_DONE,         /* no further processing */
@@ -80,8 +83,9 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
 extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
-extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                        struct kvm_interrupt *irq);
 
@@ -95,4 +99,81 @@ extern void kvmppc_booke_exit(void);
 
 extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 
+#ifdef CONFIG_PPC_BOOK3S
+
+/* We assume we're always acting on the current vcpu */
+
+static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
+{
+	if ( num < 14 ) {
+		get_paca()->shadow_vcpu.gpr[num] = val;
+		to_book3s(vcpu)->shadow_vcpu.gpr[num] = val;
+	} else
+		vcpu->arch.gpr[num] = val;
+}
+
+static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
+{
+	if ( num < 14 )
+		return get_paca()->shadow_vcpu.gpr[num];
+	else
+		return vcpu->arch.gpr[num];
+}
+
+static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
+{
+	get_paca()->shadow_vcpu.cr = val;
+	to_book3s(vcpu)->shadow_vcpu.cr = val;
+}
+
+static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
+{
+	return get_paca()->shadow_vcpu.cr;
+}
+
+static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
+{
+	get_paca()->shadow_vcpu.xer = val;
+	to_book3s(vcpu)->shadow_vcpu.xer = val;
+}
+
+static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
+{
+	return get_paca()->shadow_vcpu.xer;
+}
+
+#else
+
+static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
+{
+	vcpu->arch.gpr[num] = val;
+}
+
+static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
+{
+	return vcpu->arch.gpr[num];
+}
+
+static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
+{
+	vcpu->arch.cr = val;
+}
+
+static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cr;
+}
+
+static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
+{
+	vcpu->arch.xer = val;
+}
+
+static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.xer;
+}
+
+#endif
+
 #endif /* __POWERPC_KVM_PPC_H__ */

arch/powerpc/include/asm/paca.h

@@ -19,6 +19,9 @@
 #include <asm/mmu.h>
 #include <asm/page.h>
 #include <asm/exception-64e.h>
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include <asm/kvm_book3s_64_asm.h>
+#endif
 
 register struct paca_struct *local_paca asm("r13");
 
@@ -135,6 +138,8 @@ struct paca_struct {
 		u64     esid;
 		u64     vsid;
 	} kvm_slb[64];			/* guest SLB */
+	/* We use this to store guest state in */
+	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 	u8 kvm_slb_max;			/* highest used guest slb entry */
 	u8 kvm_in_guest;		/* are we inside the guest? */
 #endif

arch/powerpc/include/asm/reg.h

@@ -426,6 +426,10 @@
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
 #define   SRR1_WAKETHERM	0x00100000 /* Thermal management interrupt */
+#define   SRR1_PROGFPE		0x00100000 /* Floating Point Enabled */
+#define   SRR1_PROGPRIV		0x00040000 /* Privileged instruction */
+#define   SRR1_PROGTRAP		0x00020000 /* Trap */
+#define   SRR1_PROGADDR		0x00010000 /* SRR0 contains subsequent addr */
 #define SPRN_HSRR0	0x13A	/* Save/Restore Register 0 */
 #define SPRN_HSRR1	0x13B	/* Save/Restore Register 1 */
 

arch/powerpc/kernel/asm-offsets.c

@@ -194,6 +194,30 @@ int main(void)
 	DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest));
 	DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb));
 	DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max));
+	DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr));
+	DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer));
+	DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0]));
+	DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1]));
+	DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2]));
+	DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3]));
+	DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4]));
+	DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5]));
+	DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6]));
+	DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7]));
+	DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8]));
+	DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9]));
+	DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10]));
+	DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11]));
+	DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12]));
+	DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13]));
+	DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1));
+	DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2));
+	DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct,
+					    shadow_vcpu.vmhandler));
+	DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct,
+					   shadow_vcpu.scratch0));
+	DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct,
+					   shadow_vcpu.scratch1));
 #endif
 #endif /* CONFIG_PPC64 */
 
@@ -389,8 +413,6 @@ int main(void)
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
-	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
-	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
 	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
 	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
 	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
@@ -411,11 +433,16 @@ int main(void)
 	DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2));
 	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
+	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
 	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
+	DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
-#endif
+#else
+	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
+	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
+#endif /* CONFIG_PPC64 */
 #endif
 #ifdef CONFIG_44x
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);

arch/powerpc/kernel/ppc_ksyms.c

@@ -107,6 +107,7 @@ EXPORT_SYMBOL(giveup_altivec);
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_VSX
 EXPORT_SYMBOL(giveup_vsx);
+EXPORT_SYMBOL_GPL(__giveup_vsx);
 #endif /* CONFIG_VSX */
 #ifdef CONFIG_SPE
 EXPORT_SYMBOL(giveup_spe);

arch/powerpc/kvm/44x_emulate.c

@@ -65,13 +65,14 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 */
 			switch (dcrn) {
 			case DCRN_CPR0_CONFIG_ADDR:
-				vcpu->arch.gpr[rt] = vcpu->arch.cpr0_cfgaddr;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.cpr0_cfgaddr);
 				break;
 			case DCRN_CPR0_CONFIG_DATA:
 				local_irq_disable();
 				mtdcr(DCRN_CPR0_CONFIG_ADDR,
 					  vcpu->arch.cpr0_cfgaddr);
-				vcpu->arch.gpr[rt] = mfdcr(DCRN_CPR0_CONFIG_DATA);
+				kvmppc_set_gpr(vcpu, rt,
+					       mfdcr(DCRN_CPR0_CONFIG_DATA));
 				local_irq_enable();
 				break;
 			default:
@@ -93,11 +94,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			/* emulate some access in kernel */
 			switch (dcrn) {
 			case DCRN_CPR0_CONFIG_ADDR:
-				vcpu->arch.cpr0_cfgaddr = vcpu->arch.gpr[rs];
+				vcpu->arch.cpr0_cfgaddr = kvmppc_get_gpr(vcpu, rs);
 				break;
 			default:
 				run->dcr.dcrn = dcrn;
-				run->dcr.data = vcpu->arch.gpr[rs];
+				run->dcr.data = kvmppc_get_gpr(vcpu, rs);
 				run->dcr.is_write = 1;
 				vcpu->arch.dcr_needed = 1;
 				kvmppc_account_exit(vcpu, DCR_EXITS);
@@ -146,13 +147,13 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 
 	switch (sprn) {
 	case SPRN_PID:
-		kvmppc_set_pid(vcpu, vcpu->arch.gpr[rs]); break;
+		kvmppc_set_pid(vcpu, kvmppc_get_gpr(vcpu, rs)); break;
 	case SPRN_MMUCR:
-		vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.mmucr = kvmppc_get_gpr(vcpu, rs); break;
 	case SPRN_CCR0:
-		vcpu->arch.ccr0 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.ccr0 = kvmppc_get_gpr(vcpu, rs); break;
 	case SPRN_CCR1:
-		vcpu->arch.ccr1 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.ccr1 = kvmppc_get_gpr(vcpu, rs); break;
 	default:
 		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
 	}
@@ -167,13 +168,13 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_PID:
-		vcpu->arch.gpr[rt] = vcpu->arch.pid; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.pid); break;
 	case SPRN_MMUCR:
-		vcpu->arch.gpr[rt] = vcpu->arch.mmucr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucr); break;
 	case SPRN_CCR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.ccr0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr0); break;
 	case SPRN_CCR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.ccr1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr1); break;
 	default:
 		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
 	}

arch/powerpc/kvm/44x_tlb.c

@@ -439,7 +439,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	struct kvmppc_44x_tlbe *tlbe;
 	unsigned int gtlb_index;
 
-	gtlb_index = vcpu->arch.gpr[ra];
+	gtlb_index = kvmppc_get_gpr(vcpu, ra);
 	if (gtlb_index > KVM44x_GUEST_TLB_SIZE) {
 		printk("%s: index %d\n", __func__, gtlb_index);
 		kvmppc_dump_vcpu(vcpu);
@@ -455,15 +455,15 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	switch (ws) {
 	case PPC44x_TLB_PAGEID:
 		tlbe->tid = get_mmucr_stid(vcpu);
-		tlbe->word0 = vcpu->arch.gpr[rs];
+		tlbe->word0 = kvmppc_get_gpr(vcpu, rs);
 		break;
 
 	case PPC44x_TLB_XLAT:
-		tlbe->word1 = vcpu->arch.gpr[rs];
+		tlbe->word1 = kvmppc_get_gpr(vcpu, rs);
 		break;
 
 	case PPC44x_TLB_ATTRIB:
-		tlbe->word2 = vcpu->arch.gpr[rs];
+		tlbe->word2 = kvmppc_get_gpr(vcpu, rs);
 		break;
 
 	default:
@@ -500,18 +500,20 @@ int kvmppc_44x_emul_tlbsx(struct kvm_vcpu *vcpu, u8 rt, u8 ra, u8 rb, u8 rc)
 	unsigned int as = get_mmucr_sts(vcpu);
 	unsigned int pid = get_mmucr_stid(vcpu);
 
-	ea = vcpu->arch.gpr[rb];
+	ea = kvmppc_get_gpr(vcpu, rb);
 	if (ra)
-		ea += vcpu->arch.gpr[ra];
+		ea += kvmppc_get_gpr(vcpu, ra);
 
 	gtlb_index = kvmppc_44x_tlb_index(vcpu, ea, pid, as);
 	if (rc) {
+		u32 cr = kvmppc_get_cr(vcpu);
+
 		if (gtlb_index < 0)
-			vcpu->arch.cr &= ~0x20000000;
+			kvmppc_set_cr(vcpu, cr & ~0x20000000);
 		else
-			vcpu->arch.cr |= 0x20000000;
+			kvmppc_set_cr(vcpu, cr | 0x20000000);
 	}
-	vcpu->arch.gpr[rt] = gtlb_index;
+	kvmppc_set_gpr(vcpu, rt, gtlb_index);
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS);
 	return EMULATE_DONE;

arch/powerpc/kvm/Kconfig

@@ -20,6 +20,7 @@ config KVM
 	bool
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select KVM_MMIO
 
 config KVM_BOOK3S_64_HANDLER
 	bool

arch/powerpc/kvm/book3s_64_emulate.c

@@ -65,11 +65,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case 31:
 		switch (get_xop(inst)) {
 		case OP_31_XOP_MFMSR:
-			vcpu->arch.gpr[get_rt(inst)] = vcpu->arch.msr;
+			kvmppc_set_gpr(vcpu, get_rt(inst), vcpu->arch.msr);
 			break;
 		case OP_31_XOP_MTMSRD:
 		{
-			ulong rs = vcpu->arch.gpr[get_rs(inst)];
+			ulong rs = kvmppc_get_gpr(vcpu, get_rs(inst));
 			if (inst & 0x10000) {
 				vcpu->arch.msr &= ~(MSR_RI | MSR_EE);
 				vcpu->arch.msr |= rs & (MSR_RI | MSR_EE);
@@ -78,30 +78,30 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 		}
 		case OP_31_XOP_MTMSR:
-			kvmppc_set_msr(vcpu, vcpu->arch.gpr[get_rs(inst)]);
+			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst)));
 			break;
 		case OP_31_XOP_MFSRIN:
 		{
 			int srnum;
 
-			srnum = (vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf;
+			srnum = (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf;
 			if (vcpu->arch.mmu.mfsrin) {
 				u32 sr;
 				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
-				vcpu->arch.gpr[get_rt(inst)] = sr;
+				kvmppc_set_gpr(vcpu, get_rt(inst), sr);
 			}
 			break;
 		}
 		case OP_31_XOP_MTSRIN:
 			vcpu->arch.mmu.mtsrin(vcpu,
-				(vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf,
-				vcpu->arch.gpr[get_rs(inst)]);
+				(kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf,
+				kvmppc_get_gpr(vcpu, get_rs(inst)));
 			break;
 		case OP_31_XOP_TLBIE:
 		case OP_31_XOP_TLBIEL:
 		{
 			bool large = (inst & 0x00200000) ? true : false;
-			ulong addr = vcpu->arch.gpr[get_rb(inst)];
+			ulong addr = kvmppc_get_gpr(vcpu, get_rb(inst));
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
@@ -111,14 +111,16 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			if (!vcpu->arch.mmu.slbmte)
 				return EMULATE_FAIL;
 
-			vcpu->arch.mmu.slbmte(vcpu, vcpu->arch.gpr[get_rs(inst)],
-						vcpu->arch.gpr[get_rb(inst)]);
+			vcpu->arch.mmu.slbmte(vcpu,
+					kvmppc_get_gpr(vcpu, get_rs(inst)),
+					kvmppc_get_gpr(vcpu, get_rb(inst)));
 			break;
 		case OP_31_XOP_SLBIE:
 			if (!vcpu->arch.mmu.slbie)
 				return EMULATE_FAIL;
 
-			vcpu->arch.mmu.slbie(vcpu, vcpu->arch.gpr[get_rb(inst)]);
+			vcpu->arch.mmu.slbie(vcpu,
+					kvmppc_get_gpr(vcpu, get_rb(inst)));
 			break;
 		case OP_31_XOP_SLBIA:
 			if (!vcpu->arch.mmu.slbia)
@@ -132,9 +134,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			} else {
 				ulong t, rb;
 
-				rb = vcpu->arch.gpr[get_rb(inst)];
+				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
 				t = vcpu->arch.mmu.slbmfee(vcpu, rb);
-				vcpu->arch.gpr[get_rt(inst)] = t;
+				kvmppc_set_gpr(vcpu, get_rt(inst), t);
 			}
 			break;
 		case OP_31_XOP_SLBMFEV:
@@ -143,20 +145,20 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			} else {
 				ulong t, rb;
 
-				rb = vcpu->arch.gpr[get_rb(inst)];
+				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
 				t = vcpu->arch.mmu.slbmfev(vcpu, rb);
-				vcpu->arch.gpr[get_rt(inst)] = t;
+				kvmppc_set_gpr(vcpu, get_rt(inst), t);
 			}
 			break;
 		case OP_31_XOP_DCBZ:
 		{
-			ulong rb =  vcpu->arch.gpr[get_rb(inst)];
+			ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst));
 			ulong ra = 0;
 			ulong addr;
 			u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };
 
 			if (get_ra(inst))
-				ra = vcpu->arch.gpr[get_ra(inst)];
+				ra = kvmppc_get_gpr(vcpu, get_ra(inst));
 
 			addr = (ra + rb) & ~31ULL;
 			if (!(vcpu->arch.msr & MSR_SF))
@@ -233,43 +235,44 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val)
 int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 {
 	int emulated = EMULATE_DONE;
+	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_SDR1:
-		to_book3s(vcpu)->sdr1 = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->sdr1 = spr_val;
 		break;
 	case SPRN_DSISR:
-		to_book3s(vcpu)->dsisr = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->dsisr = spr_val;
 		break;
 	case SPRN_DAR:
-		vcpu->arch.dear = vcpu->arch.gpr[rs];
+		vcpu->arch.dear = spr_val;
 		break;
 	case SPRN_HIOR:
-		to_book3s(vcpu)->hior = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hior = spr_val;
 		break;
 	case SPRN_IBAT0U ... SPRN_IBAT3L:
 	case SPRN_IBAT4U ... SPRN_IBAT7L:
 	case SPRN_DBAT0U ... SPRN_DBAT3L:
 	case SPRN_DBAT4U ... SPRN_DBAT7L:
-		kvmppc_write_bat(vcpu, sprn, (u32)vcpu->arch.gpr[rs]);
+		kvmppc_write_bat(vcpu, sprn, (u32)spr_val);
 		/* BAT writes happen so rarely that we're ok to flush
 		 * everything here */
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
 		break;
 	case SPRN_HID0:
-		to_book3s(vcpu)->hid[0] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[0] = spr_val;
 		break;
 	case SPRN_HID1:
-		to_book3s(vcpu)->hid[1] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[1] = spr_val;
 		break;
 	case SPRN_HID2:
-		to_book3s(vcpu)->hid[2] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[2] = spr_val;
 		break;
 	case SPRN_HID4:
-		to_book3s(vcpu)->hid[4] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[4] = spr_val;
 		break;
 	case SPRN_HID5:
-		to_book3s(vcpu)->hid[5] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[5] = spr_val;
 		/* guest HID5 set can change is_dcbz32 */
 		if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
 		    (mfmsr() & MSR_HV))
@@ -299,38 +302,38 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_SDR1:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->sdr1;
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
 		break;
 	case SPRN_DSISR:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->dsisr;
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->dsisr);
 		break;
 	case SPRN_DAR:
-		vcpu->arch.gpr[rt] = vcpu->arch.dear;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear);
 		break;
 	case SPRN_HIOR:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hior;
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hior);
 		break;
 	case SPRN_HID0:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[0];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[0]);
 		break;
 	case SPRN_HID1:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[1];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]);
 		break;
 	case SPRN_HID2:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[2];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]);
 		break;
 	case SPRN_HID4:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[4];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]);
 		break;
 	case SPRN_HID5:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[5];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]);
 		break;
 	case SPRN_THRM1:
 	case SPRN_THRM2:
 	case SPRN_THRM3:
 	case SPRN_CTRLF:
 	case SPRN_CTRLT:
-		vcpu->arch.gpr[rt] = 0;
+		kvmppc_set_gpr(vcpu, rt, 0);
 		break;
 	default:
 		printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn);

arch/powerpc/kvm/book3s_64_exports.c

@@ -22,3 +22,11 @@
 
 EXPORT_SYMBOL_GPL(kvmppc_trampoline_enter);
 EXPORT_SYMBOL_GPL(kvmppc_trampoline_lowmem);
+EXPORT_SYMBOL_GPL(kvmppc_rmcall);
+EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu);
+#ifdef CONFIG_ALTIVEC
+EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec);
+#endif
+#ifdef CONFIG_VSX
+EXPORT_SYMBOL_GPL(kvmppc_load_up_vsx);
+#endif

arch/powerpc/kvm/book3s_64_mmu.c

@@ -54,7 +54,7 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
 		if (!vcpu_book3s->slb[i].valid)
 			continue;
 
-		if (vcpu_book3s->slb[i].large)
+		if (vcpu_book3s->slb[i].tb)
 			cmp_esid = esid_1t;
 
 		if (vcpu_book3s->slb[i].esid == cmp_esid)
@@ -65,9 +65,10 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
 		eaddr, esid, esid_1t);
 	for (i = 0; i < vcpu_book3s->slb_nr; i++) {
 	    if (vcpu_book3s->slb[i].vsid)
-		dprintk("  %d: %c%c %llx %llx\n", i,
+		dprintk("  %d: %c%c%c %llx %llx\n", i,
 			vcpu_book3s->slb[i].valid ? 'v' : ' ',
 			vcpu_book3s->slb[i].large ? 'l' : ' ',
+			vcpu_book3s->slb[i].tb    ? 't' : ' ',
 			vcpu_book3s->slb[i].esid,
 			vcpu_book3s->slb[i].vsid);
 	}
@@ -84,7 +85,7 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	if (!slb)
 		return 0;
 
-	if (slb->large)
+	if (slb->tb)
 		return (((u64)eaddr >> 12) & 0xfffffff) |
 		       (((u64)slb->vsid) << 28);
 
@@ -309,7 +310,8 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 	slbe = &vcpu_book3s->slb[slb_nr];
 
 	slbe->large = (rs & SLB_VSID_L) ? 1 : 0;
-	slbe->esid  = slbe->large ? esid_1t : esid;
+	slbe->tb    = (rs & SLB_VSID_B_1T) ? 1 : 0;
+	slbe->esid  = slbe->tb ? esid_1t : esid;
 	slbe->vsid  = rs >> 12;
 	slbe->valid = (rb & SLB_ESID_V) ? 1 : 0;
 	slbe->Ks    = (rs & SLB_VSID_KS) ? 1 : 0;

arch/powerpc/kvm/book3s_64_rmhandlers.S

@@ -45,36 +45,25 @@ kvmppc_trampoline_\intno:
 	 * To distinguish, we check a magic byte in the PACA
 	 */
 	mfspr	r13, SPRN_SPRG_PACA		/* r13 = PACA */
-	std	r12, (PACA_EXMC + EX_R12)(r13)
+	std	r12, PACA_KVM_SCRATCH0(r13)
 	mfcr	r12
-	stw	r12, (PACA_EXMC + EX_CCR)(r13)
+	stw	r12, PACA_KVM_SCRATCH1(r13)
 	lbz	r12, PACA_KVM_IN_GUEST(r13)
-	cmpwi	r12, 0
+	cmpwi	r12, KVM_GUEST_MODE_NONE
 	bne	..kvmppc_handler_hasmagic_\intno
 	/* No KVM guest? Then jump back to the Linux handler! */
-	lwz	r12, (PACA_EXMC + EX_CCR)(r13)
+	lwz	r12, PACA_KVM_SCRATCH1(r13)
 	mtcr	r12
-	ld	r12, (PACA_EXMC + EX_R12)(r13)
+	ld	r12, PACA_KVM_SCRATCH0(r13)
 	mfspr	r13, SPRN_SPRG_SCRATCH0		/* r13 = original r13 */
 	b	kvmppc_resume_\intno		/* Get back original handler */
 
 	/* Now we know we're handling a KVM guest */
 ..kvmppc_handler_hasmagic_\intno:
-	/* Unset guest state */
-	li	r12, 0
-	stb	r12, PACA_KVM_IN_GUEST(r13)
 
-	std	r1, (PACA_EXMC+EX_R9)(r13)
-	std	r10, (PACA_EXMC+EX_R10)(r13)
-	std	r11, (PACA_EXMC+EX_R11)(r13)
-	std	r2, (PACA_EXMC+EX_R13)(r13)
-
-	mfsrr0	r10
-	mfsrr1	r11
-
-	/* Restore R1/R2 so we can handle faults */
-	ld	r1, PACAR1(r13)
-	ld	r2, (PACA_EXMC+EX_SRR0)(r13)
+	/* Should we just skip the faulting instruction? */
+	cmpwi	r12, KVM_GUEST_MODE_SKIP
+	beq	kvmppc_handler_skip_ins
 
 	/* Let's store which interrupt we're handling */
 	li	r12, \intno
@@ -101,24 +90,108 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PERFMON
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALTIVEC
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_VSX
 
+/*
+ * Bring us back to the faulting code, but skip the
+ * faulting instruction.
+ *
+ * This is a generic exit path from the interrupt
+ * trampolines above.
+ *
+ * Input Registers:
+ *
+ * R12               = free
+ * R13               = PACA
+ * PACA.KVM.SCRATCH0 = guest R12
+ * PACA.KVM.SCRATCH1 = guest CR
+ * SPRG_SCRATCH0     = guest R13
+ *
+ */
+kvmppc_handler_skip_ins:
+
+	/* Patch the IP to the next instruction */
+	mfsrr0	r12
+	addi	r12, r12, 4
+	mtsrr0	r12
+
+	/* Clean up all state */
+	lwz	r12, PACA_KVM_SCRATCH1(r13)
+	mtcr	r12
+	ld	r12, PACA_KVM_SCRATCH0(r13)
+	mfspr	r13, SPRN_SPRG_SCRATCH0
+
+	/* And get back into the code */
+	RFI
+
 /*
  * This trampoline brings us back to a real mode handler
  *
  * Input Registers:
  *
- * R6 = SRR0
- * R7 = SRR1
+ * R5 = SRR0
+ * R6 = SRR1
  * LR = real-mode IP
  *
  */
 .global kvmppc_handler_lowmem_trampoline
 kvmppc_handler_lowmem_trampoline:
 
-	mtsrr0	r6
-	mtsrr1	r7
+	mtsrr0	r5
+	mtsrr1	r6
 	blr
 kvmppc_handler_lowmem_trampoline_end:
 
+/*
+ * Call a function in real mode
+ *
+ * Input Registers:
+ *
+ * R3 = function
+ * R4 = MSR
+ * R5 = CTR
+ *
+ */
+_GLOBAL(kvmppc_rmcall)
+	mtmsr	r4		/* Disable relocation, so mtsrr
+				   doesn't get interrupted */
+	mtctr	r5
+	mtsrr0	r3
+	mtsrr1	r4
+	RFI
+
+/*
+ * Activate current's external feature (FPU/Altivec/VSX)
+ */
+#define define_load_up(what) 				\
+							\
+_GLOBAL(kvmppc_load_up_ ## what);			\
+	subi	r1, r1, INT_FRAME_SIZE;			\
+	mflr	r3;					\
+	std	r3, _LINK(r1);				\
+	mfmsr	r4;					\
+	std	r31, GPR3(r1);				\
+	mr	r31, r4;				\
+	li	r5, MSR_DR;				\
+	oris	r5, r5, MSR_EE@h;			\
+	andc	r4, r4, r5;				\
+	mtmsr	r4;					\
+							\
+	bl	.load_up_ ## what;			\
+							\
+	mtmsr	r31;					\
+	ld	r3, _LINK(r1);				\
+	ld	r31, GPR3(r1);				\
+	addi	r1, r1, INT_FRAME_SIZE;			\
+	mtlr	r3;					\
+	blr
+
+define_load_up(fpu)
+#ifdef CONFIG_ALTIVEC
+define_load_up(altivec)
+#endif
+#ifdef CONFIG_VSX
+define_load_up(vsx)
+#endif
+
 .global kvmppc_trampoline_lowmem
 kvmppc_trampoline_lowmem:
 	.long kvmppc_handler_lowmem_trampoline - _stext

arch/powerpc/kvm/book3s_64_slb.S

@@ -31,7 +31,7 @@
 #define REBOLT_SLB_ENTRY(num) \
 	ld	r10, SHADOW_SLB_ESID(num)(r11); \
 	cmpdi	r10, 0; \
-	beq	slb_exit_skip_1; \
+	beq	slb_exit_skip_ ## num; \
 	oris	r10, r10, SLB_ESID_V@h; \
 	ld	r9, SHADOW_SLB_VSID(num)(r11); \
 	slbmte	r9, r10; \
@@ -51,23 +51,21 @@ kvmppc_handler_trampoline_enter:
 	 *
 	 * MSR = ~IR|DR
 	 * R13 = PACA
+	 * R1 = host R1
+	 * R2 = host R2
 	 * R9 = guest IP
 	 * R10 = guest MSR
-	 * R11 = free
-	 * R12 = free
-	 * PACA[PACA_EXMC + EX_R9] = guest R9
-	 * PACA[PACA_EXMC + EX_R10] = guest R10
-	 * PACA[PACA_EXMC + EX_R11] = guest R11
-	 * PACA[PACA_EXMC + EX_R12] = guest R12
-	 * PACA[PACA_EXMC + EX_R13] = guest R13
-	 * PACA[PACA_EXMC + EX_CCR] = guest CR
-	 * PACA[PACA_EXMC + EX_R3] = guest XER
+	 * all other GPRS = free
+	 * PACA[KVM_CR] = guest CR
+	 * PACA[KVM_XER] = guest XER
 	 */
 
 	mtsrr0	r9
 	mtsrr1	r10
 
-	mtspr	SPRN_SPRG_SCRATCH0, r0
+	/* Activate guest mode, so faults get handled by KVM */
+	li	r11, KVM_GUEST_MODE_GUEST
+	stb	r11, PACA_KVM_IN_GUEST(r13)
 
 	/* Remove LPAR shadow entries */
 
@@ -131,20 +129,27 @@ slb_do_enter:
 
 	/* Enter guest */
 
-	mfspr	r0, SPRN_SPRG_SCRATCH0
-
-	ld	r9, (PACA_EXMC+EX_R9)(r13)
-	ld	r10, (PACA_EXMC+EX_R10)(r13)
-	ld	r12, (PACA_EXMC+EX_R12)(r13)
-
-	lwz	r11, (PACA_EXMC+EX_CCR)(r13)
+	ld	r0, (PACA_KVM_R0)(r13)
+	ld	r1, (PACA_KVM_R1)(r13)
+	ld	r2, (PACA_KVM_R2)(r13)
+	ld	r3, (PACA_KVM_R3)(r13)
+	ld	r4, (PACA_KVM_R4)(r13)
+	ld	r5, (PACA_KVM_R5)(r13)
+	ld	r6, (PACA_KVM_R6)(r13)
+	ld	r7, (PACA_KVM_R7)(r13)
+	ld	r8, (PACA_KVM_R8)(r13)
+	ld	r9, (PACA_KVM_R9)(r13)
+	ld	r10, (PACA_KVM_R10)(r13)
+	ld	r12, (PACA_KVM_R12)(r13)
+
+	lwz	r11, (PACA_KVM_CR)(r13)
 	mtcr	r11
 
-	ld	r11, (PACA_EXMC+EX_R3)(r13)
+	ld	r11, (PACA_KVM_XER)(r13)
 	mtxer	r11
 
-	ld	r11, (PACA_EXMC+EX_R11)(r13)
-	ld	r13, (PACA_EXMC+EX_R13)(r13)
+	ld	r11, (PACA_KVM_R11)(r13)
+	ld	r13, (PACA_KVM_R13)(r13)
 
 	RFI
 kvmppc_handler_trampoline_enter_end:
@@ -162,28 +167,54 @@ kvmppc_handler_trampoline_exit:
 
 	/* Register usage at this point:
 	 *
-	 * SPRG_SCRATCH0 = guest R13
-	 * R01           = host R1
-	 * R02           = host R2
-	 * R10           = guest PC
-	 * R11           = guest MSR
-	 * R12           = exit handler id
-	 * R13           = PACA
-	 * PACA.exmc.CCR  = guest CR
-	 * PACA.exmc.R9  = guest R1
-	 * PACA.exmc.R10 = guest R10
-	 * PACA.exmc.R11 = guest R11
-	 * PACA.exmc.R12 = guest R12
-	 * PACA.exmc.R13 = guest R2
+	 * SPRG_SCRATCH0     = guest R13
+	 * R12               = exit handler id
+	 * R13               = PACA
+	 * PACA.KVM.SCRATCH0 = guest R12
+	 * PACA.KVM.SCRATCH1 = guest CR
 	 *
 	 */
 
 	/* Save registers */
 
-	std	r0, (PACA_EXMC+EX_SRR0)(r13)
-	std	r9, (PACA_EXMC+EX_R3)(r13)
-	std	r10, (PACA_EXMC+EX_LR)(r13)
-	std	r11, (PACA_EXMC+EX_DAR)(r13)
+	std	r0, PACA_KVM_R0(r13)
+	std	r1, PACA_KVM_R1(r13)
+	std	r2, PACA_KVM_R2(r13)
+	std	r3, PACA_KVM_R3(r13)
+	std	r4, PACA_KVM_R4(r13)
+	std	r5, PACA_KVM_R5(r13)
+	std	r6, PACA_KVM_R6(r13)
+	std	r7, PACA_KVM_R7(r13)
+	std	r8, PACA_KVM_R8(r13)
+	std	r9, PACA_KVM_R9(r13)
+	std	r10, PACA_KVM_R10(r13)
+	std	r11, PACA_KVM_R11(r13)
+
+	/* Restore R1/R2 so we can handle faults */
+	ld	r1, PACA_KVM_HOST_R1(r13)
+	ld	r2, PACA_KVM_HOST_R2(r13)
+
+	/* Save guest PC and MSR in GPRs */
+	mfsrr0	r3
+	mfsrr1	r4
+
+	/* Get scratch'ed off registers */
+	mfspr	r9, SPRN_SPRG_SCRATCH0
+	std	r9, PACA_KVM_R13(r13)
+
+	ld	r8, PACA_KVM_SCRATCH0(r13)
+	std	r8, PACA_KVM_R12(r13)
+
+	lwz	r7, PACA_KVM_SCRATCH1(r13)
+	stw	r7, PACA_KVM_CR(r13)
+
+	/* Save more register state  */
+
+	mfxer	r6
+	stw	r6, PACA_KVM_XER(r13)
+
+	mfdar	r5
+	mfdsisr	r6
 
 	/*
 	 * In order for us to easily get the last instruction,
@@ -202,17 +233,28 @@ kvmppc_handler_trampoline_exit:
 
 ld_last_inst:
 	/* Save off the guest instruction we're at */
+
+	/* Set guest mode to 'jump over instruction' so if lwz faults
+	 * we'll just continue at the next IP. */
+	li	r9, KVM_GUEST_MODE_SKIP
+	stb	r9, PACA_KVM_IN_GUEST(r13)
+
 	/*    1) enable paging for data */
 	mfmsr	r9
 	ori	r11, r9, MSR_DR			/* Enable paging for data */
 	mtmsr	r11
 	/*    2) fetch the instruction */
-	lwz	r0, 0(r10)
+	li	r0, KVM_INST_FETCH_FAILED	/* In case lwz faults */
+	lwz	r0, 0(r3)
 	/*    3) disable paging again */
 	mtmsr	r9
 
 no_ld_last_inst:
 
+	/* Unset guest mode */
+	li	r9, KVM_GUEST_MODE_NONE
+	stb	r9, PACA_KVM_IN_GUEST(r13)
+
 	/* Restore bolted entries from the shadow and fix it along the way */
 
 	/* We don't store anything in entry 0, so we don't need to take care of it */
@@ -233,29 +275,27 @@ no_ld_last_inst:
 
 slb_do_exit:
 
-	/* Restore registers */
-
-	ld	r11, (PACA_EXMC+EX_DAR)(r13)
-	ld	r10, (PACA_EXMC+EX_LR)(r13)
-	ld	r9, (PACA_EXMC+EX_R3)(r13)
-
-	/* Save last inst */
-	stw	r0, (PACA_EXMC+EX_LR)(r13)
-
-	/* Save DAR and DSISR before going to paged mode */
-	mfdar	r0
-	std	r0, (PACA_EXMC+EX_DAR)(r13)
-	mfdsisr	r0
-	stw	r0, (PACA_EXMC+EX_DSISR)(r13)
+	/* Register usage at this point:
+	 *
+	 * R0         = guest last inst
+	 * R1         = host R1
+	 * R2         = host R2
+	 * R3         = guest PC
+	 * R4         = guest MSR
+	 * R5         = guest DAR
+	 * R6         = guest DSISR
+	 * R12        = exit handler id
+	 * R13        = PACA
+	 * PACA.KVM.* = guest *
+	 *
+	 */
 
 	/* RFI into the highmem handler */
-	mfmsr	r0
-	ori	r0, r0, MSR_IR|MSR_DR|MSR_RI	/* Enable paging */
-	mtsrr1	r0
-	ld	r0, PACASAVEDMSR(r13)		/* Highmem handler address */
-	mtsrr0	r0
-
-	mfspr	r0, SPRN_SPRG_SCRATCH0
+	mfmsr	r7
+	ori	r7, r7, MSR_IR|MSR_DR|MSR_RI	/* Enable paging */
+	mtsrr1	r7
+	ld	r8, PACA_KVM_VMHANDLER(r13)	/* Highmem handler address */
+	mtsrr0	r8
 
 	RFI
 kvmppc_handler_trampoline_exit_end:

arch/powerpc/kvm/booke.c

@@ -69,10 +69,10 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
 
 	for (i = 0; i < 32; i += 4) {
 		printk("gpr%02d: %08lx %08lx %08lx %08lx\n", i,
-		       vcpu->arch.gpr[i],
-		       vcpu->arch.gpr[i+1],
-		       vcpu->arch.gpr[i+2],
-		       vcpu->arch.gpr[i+3]);
+		       kvmppc_get_gpr(vcpu, i),
+		       kvmppc_get_gpr(vcpu, i+1),
+		       kvmppc_get_gpr(vcpu, i+2),
+		       kvmppc_get_gpr(vcpu, i+3));
 	}
 }
 
@@ -82,8 +82,32 @@ static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu,
 	set_bit(priority, &vcpu->arch.pending_exceptions);
 }
 
-void kvmppc_core_queue_program(struct kvm_vcpu *vcpu)
+static void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu,
+                                        ulong dear_flags, ulong esr_flags)
 {
+	vcpu->arch.queued_dear = dear_flags;
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
+}
+
+static void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu,
+                                           ulong dear_flags, ulong esr_flags)
+{
+	vcpu->arch.queued_dear = dear_flags;
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE);
+}
+
+static void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu,
+                                           ulong esr_flags)
+{
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE);
+}
+
+void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags)
+{
+	vcpu->arch.queued_esr = esr_flags;
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM);
 }
 
@@ -97,6 +121,11 @@ int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
 	return test_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
 }
 
+void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
+{
+	clear_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
+}
+
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
@@ -109,14 +138,19 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 {
 	int allowed = 0;
 	ulong msr_mask;
+	bool update_esr = false, update_dear = false;
 
 	switch (priority) {
-	case BOOKE_IRQPRIO_PROGRAM:
 	case BOOKE_IRQPRIO_DTLB_MISS:
-	case BOOKE_IRQPRIO_ITLB_MISS:
-	case BOOKE_IRQPRIO_SYSCALL:
 	case BOOKE_IRQPRIO_DATA_STORAGE:
+		update_dear = true;
+		/* fall through */
 	case BOOKE_IRQPRIO_INST_STORAGE:
+	case BOOKE_IRQPRIO_PROGRAM:
+		update_esr = true;
+		/* fall through */
+	case BOOKE_IRQPRIO_ITLB_MISS:
+	case BOOKE_IRQPRIO_SYSCALL:
 	case BOOKE_IRQPRIO_FP_UNAVAIL:
 	case BOOKE_IRQPRIO_SPE_UNAVAIL:
 	case BOOKE_IRQPRIO_SPE_FP_DATA:
@@ -151,6 +185,10 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		vcpu->arch.srr0 = vcpu->arch.pc;
 		vcpu->arch.srr1 = vcpu->arch.msr;
 		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
+		if (update_esr == true)
+			vcpu->arch.esr = vcpu->arch.queued_esr;
+		if (update_dear == true)
+			vcpu->arch.dear = vcpu->arch.queued_dear;
 		kvmppc_set_msr(vcpu, vcpu->arch.msr & msr_mask);
 
 		clear_bit(priority, &vcpu->arch.pending_exceptions);
@@ -223,8 +261,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		if (vcpu->arch.msr & MSR_PR) {
 			/* Program traps generated by user-level software must be handled
 			 * by the guest kernel. */
-			vcpu->arch.esr = vcpu->arch.fault_esr;
-			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM);
+			kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
 			r = RESUME_GUEST;
 			kvmppc_account_exit(vcpu, USR_PR_INST);
 			break;
@@ -280,16 +317,14 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 
 	case BOOKE_INTERRUPT_DATA_STORAGE:
-		vcpu->arch.dear = vcpu->arch.fault_dear;
-		vcpu->arch.esr = vcpu->arch.fault_esr;
-		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE);
+		kvmppc_core_queue_data_storage(vcpu, vcpu->arch.fault_dear,
+		                               vcpu->arch.fault_esr);
 		kvmppc_account_exit(vcpu, DSI_EXITS);
 		r = RESUME_GUEST;
 		break;
 
 	case BOOKE_INTERRUPT_INST_STORAGE:
-		vcpu->arch.esr = vcpu->arch.fault_esr;
-		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE);
+		kvmppc_core_queue_inst_storage(vcpu, vcpu->arch.fault_esr);
 		kvmppc_account_exit(vcpu, ISI_EXITS);
 		r = RESUME_GUEST;
 		break;
@@ -310,9 +345,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		gtlb_index = kvmppc_mmu_dtlb_index(vcpu, eaddr);
 		if (gtlb_index < 0) {
 			/* The guest didn't have a mapping for it. */
-			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
-			vcpu->arch.dear = vcpu->arch.fault_dear;
-			vcpu->arch.esr = vcpu->arch.fault_esr;
+			kvmppc_core_queue_dtlb_miss(vcpu,
+			                            vcpu->arch.fault_dear,
+			                            vcpu->arch.fault_esr);
 			kvmppc_mmu_dtlb_miss(vcpu);
 			kvmppc_account_exit(vcpu, DTLB_REAL_MISS_EXITS);
 			r = RESUME_GUEST;
@@ -426,7 +461,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pc = 0;
 	vcpu->arch.msr = 0;
-	vcpu->arch.gpr[1] = (16<<20) - 8; /* -8 for the callee-save LR slot */
+	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
 
 	vcpu->arch.shadow_pid = 1;
 
@@ -444,10 +479,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	int i;
 
 	regs->pc = vcpu->arch.pc;
-	regs->cr = vcpu->arch.cr;
+	regs->cr = kvmppc_get_cr(vcpu);
 	regs->ctr = vcpu->arch.ctr;
 	regs->lr = vcpu->arch.lr;
-	regs->xer = vcpu->arch.xer;
+	regs->xer = kvmppc_get_xer(vcpu);
 	regs->msr = vcpu->arch.msr;
 	regs->srr0 = vcpu->arch.srr0;
 	regs->srr1 = vcpu->arch.srr1;
@@ -461,7 +496,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->sprg7 = vcpu->arch.sprg6;
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
-		regs->gpr[i] = vcpu->arch.gpr[i];
+		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
 
 	return 0;
 }
@@ -471,10 +506,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	int i;
 
 	vcpu->arch.pc = regs->pc;
-	vcpu->arch.cr = regs->cr;
+	kvmppc_set_cr(vcpu, regs->cr);
 	vcpu->arch.ctr = regs->ctr;
 	vcpu->arch.lr = regs->lr;
-	vcpu->arch.xer = regs->xer;
+	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
 	vcpu->arch.srr0 = regs->srr0;
 	vcpu->arch.srr1 = regs->srr1;
@@ -486,8 +521,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.sprg6 = regs->sprg5;
 	vcpu->arch.sprg7 = regs->sprg6;
 
-	for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++)
-		vcpu->arch.gpr[i] = regs->gpr[i];
+	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
+		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
 
 	return 0;
 }

arch/powerpc/kvm/booke_emulate.c

@@ -62,20 +62,20 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		case OP_31_XOP_MFMSR:
 			rt = get_rt(inst);
-			vcpu->arch.gpr[rt] = vcpu->arch.msr;
+			kvmppc_set_gpr(vcpu, rt, vcpu->arch.msr);
 			kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS);
 			break;
 
 		case OP_31_XOP_MTMSR:
 			rs = get_rs(inst);
 			kvmppc_set_exit_type(vcpu, EMULATED_MTMSR_EXITS);
-			kvmppc_set_msr(vcpu, vcpu->arch.gpr[rs]);
+			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, rs));
 			break;
 
 		case OP_31_XOP_WRTEE:
 			rs = get_rs(inst);
 			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
-							 | (vcpu->arch.gpr[rs] & MSR_EE);
+					| (kvmppc_get_gpr(vcpu, rs) & MSR_EE);
 			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
 			break;
 
@@ -101,22 +101,23 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 {
 	int emulated = EMULATE_DONE;
+	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_DEAR:
-		vcpu->arch.dear = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dear = spr_val; break;
 	case SPRN_ESR:
-		vcpu->arch.esr = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.esr = spr_val; break;
 	case SPRN_DBCR0:
-		vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dbcr0 = spr_val; break;
 	case SPRN_DBCR1:
-		vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dbcr1 = spr_val; break;
 	case SPRN_DBSR:
-		vcpu->arch.dbsr &= ~vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dbsr &= ~spr_val; break;
 	case SPRN_TSR:
-		vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break;
+		vcpu->arch.tsr &= ~spr_val; break;
 	case SPRN_TCR:
-		vcpu->arch.tcr = vcpu->arch.gpr[rs];
+		vcpu->arch.tcr = spr_val;
 		kvmppc_emulate_dec(vcpu);
 		break;
 
@@ -124,64 +125,64 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	 * loaded into the real SPRGs when resuming the
 	 * guest. */
 	case SPRN_SPRG4:
-		vcpu->arch.sprg4 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg4 = spr_val; break;
 	case SPRN_SPRG5:
-		vcpu->arch.sprg5 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg5 = spr_val; break;
 	case SPRN_SPRG6:
-		vcpu->arch.sprg6 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg6 = spr_val; break;
 	case SPRN_SPRG7:
-		vcpu->arch.sprg7 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg7 = spr_val; break;
 
 	case SPRN_IVPR:
-		vcpu->arch.ivpr = vcpu->arch.gpr[rs];
+		vcpu->arch.ivpr = spr_val;
 		break;
 	case SPRN_IVOR0:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = spr_val;
 		break;
 	case SPRN_IVOR1:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = spr_val;
 		break;
 	case SPRN_IVOR2:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = spr_val;
 		break;
 	case SPRN_IVOR3:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = spr_val;
 		break;
 	case SPRN_IVOR4:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = spr_val;
 		break;
 	case SPRN_IVOR5:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = spr_val;
 		break;
 	case SPRN_IVOR6:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = spr_val;
 		break;
 	case SPRN_IVOR7:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = spr_val;
 		break;
 	case SPRN_IVOR8:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = spr_val;
 		break;
 	case SPRN_IVOR9:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = spr_val;
 		break;
 	case SPRN_IVOR10:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = spr_val;
 		break;
 	case SPRN_IVOR11:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = spr_val;
 		break;
 	case SPRN_IVOR12:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = spr_val;
 		break;
 	case SPRN_IVOR13:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = spr_val;
 		break;
 	case SPRN_IVOR14:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = spr_val;
 		break;
 	case SPRN_IVOR15:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = spr_val;
 		break;
 
 	default:
@@ -197,65 +198,65 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_IVPR:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivpr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivpr); break;
 	case SPRN_DEAR:
-		vcpu->arch.gpr[rt] = vcpu->arch.dear; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear); break;
 	case SPRN_ESR:
-		vcpu->arch.gpr[rt] = vcpu->arch.esr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.esr); break;
 	case SPRN_DBCR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr0); break;
 	case SPRN_DBCR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break;
 	case SPRN_DBSR:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbsr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break;
 
 	case SPRN_IVOR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]);
 		break;
 	case SPRN_IVOR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK]);
 		break;
 	case SPRN_IVOR2:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]);
 		break;
 	case SPRN_IVOR3:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE]);
 		break;
 	case SPRN_IVOR4:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL]);
 		break;
 	case SPRN_IVOR5:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT]);
 		break;
 	case SPRN_IVOR6:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM]);
 		break;
 	case SPRN_IVOR7:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL]);
 		break;
 	case SPRN_IVOR8:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]);
 		break;
 	case SPRN_IVOR9:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL]);
 		break;
 	case SPRN_IVOR10:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER]);
 		break;
 	case SPRN_IVOR11:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FIT]);
 		break;
 	case SPRN_IVOR12:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG]);
 		break;
 	case SPRN_IVOR13:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]);
 		break;
 	case SPRN_IVOR14:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]);
 		break;
 	case SPRN_IVOR15:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]);
 		break;
 
 	default:

arch/powerpc/kvm/e500.c

@@ -60,6 +60,12 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvmppc_e500_tlb_setup(vcpu_e500);
 
+	/* Registers init */
+	vcpu->arch.pvr = mfspr(SPRN_PVR);
+
+	/* Since booke kvm only support one core, update all vcpus' PIR to 0 */
+	vcpu->vcpu_id = 0;
+
 	return 0;
 }
 

arch/powerpc/kvm/e500_emulate.c

@@ -74,54 +74,59 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
+	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_PID:
 		vcpu_e500->pid[0] = vcpu->arch.shadow_pid =
-			vcpu->arch.pid = vcpu->arch.gpr[rs];
+			vcpu->arch.pid = spr_val;
 		break;
 	case SPRN_PID1:
-		vcpu_e500->pid[1] = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->pid[1] = spr_val; break;
 	case SPRN_PID2:
-		vcpu_e500->pid[2] = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->pid[2] = spr_val; break;
 	case SPRN_MAS0:
-		vcpu_e500->mas0 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas0 = spr_val; break;
 	case SPRN_MAS1:
-		vcpu_e500->mas1 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas1 = spr_val; break;
 	case SPRN_MAS2:
-		vcpu_e500->mas2 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas2 = spr_val; break;
 	case SPRN_MAS3:
-		vcpu_e500->mas3 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas3 = spr_val; break;
 	case SPRN_MAS4:
-		vcpu_e500->mas4 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas4 = spr_val; break;
 	case SPRN_MAS6:
-		vcpu_e500->mas6 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas6 = spr_val; break;
 	case SPRN_MAS7:
-		vcpu_e500->mas7 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas7 = spr_val; break;
+	case SPRN_L1CSR0:
+		vcpu_e500->l1csr0 = spr_val;
+		vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
+		break;
 	case SPRN_L1CSR1:
-		vcpu_e500->l1csr1 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->l1csr1 = spr_val; break;
 	case SPRN_HID0:
-		vcpu_e500->hid0 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->hid0 = spr_val; break;
 	case SPRN_HID1:
-		vcpu_e500->hid1 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->hid1 = spr_val; break;
 
 	case SPRN_MMUCSR0:
 		emulated = kvmppc_e500_emul_mt_mmucsr0(vcpu_e500,
-				vcpu->arch.gpr[rs]);
+				spr_val);
 		break;
 
 	/* extra exceptions */
 	case SPRN_IVOR32:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = spr_val;
 		break;
 	case SPRN_IVOR33:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = spr_val;
 		break;
 	case SPRN_IVOR34:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = spr_val;
 		break;
 	case SPRN_IVOR35:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val;
 		break;
 
 	default:
@@ -138,63 +143,57 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_PID:
-		vcpu->arch.gpr[rt] = vcpu_e500->pid[0]; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[0]); break;
 	case SPRN_PID1:
-		vcpu->arch.gpr[rt] = vcpu_e500->pid[1]; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[1]); break;
 	case SPRN_PID2:
-		vcpu->arch.gpr[rt] = vcpu_e500->pid[2]; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[2]); break;
 	case SPRN_MAS0:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas0); break;
 	case SPRN_MAS1:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas1); break;
 	case SPRN_MAS2:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas2; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas2); break;
 	case SPRN_MAS3:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas3; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas3); break;
 	case SPRN_MAS4:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas4; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas4); break;
 	case SPRN_MAS6:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas6; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas6); break;
 	case SPRN_MAS7:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas7; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7); break;
 
 	case SPRN_TLB0CFG:
-		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB0CFG);
-		vcpu->arch.gpr[rt] &= ~0xfffUL;
-		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[0];
-		break;
-
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;
 	case SPRN_TLB1CFG:
-		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB1CFG);
-		vcpu->arch.gpr[rt] &= ~0xfffUL;
-		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[1];
-		break;
-
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb1cfg); break;
+	case SPRN_L1CSR0:
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break;
 	case SPRN_L1CSR1:
-		vcpu->arch.gpr[rt] = vcpu_e500->l1csr1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr1); break;
 	case SPRN_HID0:
-		vcpu->arch.gpr[rt] = vcpu_e500->hid0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid0); break;
 	case SPRN_HID1:
-		vcpu->arch.gpr[rt] = vcpu_e500->hid1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid1); break;
 
 	case SPRN_MMUCSR0:
-		vcpu->arch.gpr[rt] = 0; break;
+		kvmppc_set_gpr(vcpu, rt, 0); break;
 
 	case SPRN_MMUCFG:
-		vcpu->arch.gpr[rt] = mfspr(SPRN_MMUCFG); break;
+		kvmppc_set_gpr(vcpu, rt, mfspr(SPRN_MMUCFG)); break;
 
 	/* extra exceptions */
 	case SPRN_IVOR32:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]);
 		break;
 	case SPRN_IVOR33:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]);
 		break;
 	case SPRN_IVOR34:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]);
 		break;
 	case SPRN_IVOR35:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]);
 		break;
 	default:
 		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);

arch/powerpc/kvm/e500_tlb.c

@@ -417,7 +417,7 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
 	int esel, tlbsel;
 	gva_t ea;
 
-	ea = ((ra) ? vcpu->arch.gpr[ra] : 0) + vcpu->arch.gpr[rb];
+	ea = ((ra) ? kvmppc_get_gpr(vcpu, ra) : 0) + kvmppc_get_gpr(vcpu, rb);
 
 	ia = (ea >> 2) & 0x1;
 
@@ -470,7 +470,7 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
 	struct tlbe *gtlbe = NULL;
 	gva_t ea;
 
-	ea = vcpu->arch.gpr[rb];
+	ea = kvmppc_get_gpr(vcpu, rb);
 
 	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
 		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
@@ -728,6 +728,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	if (vcpu_e500->shadow_pages[1] == NULL)
 		goto err_out_page0;
 
+	/* Init TLB configuration register */
+	vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) & ~0xfffUL;
+	vcpu_e500->tlb0cfg |= vcpu_e500->guest_tlb_size[0];
+	vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) & ~0xfffUL;
+	vcpu_e500->tlb1cfg |= vcpu_e500->guest_tlb_size[1];
+
 	return 0;
 
 err_out_page0:

arch/powerpc/kvm/powerpc.c

@@ -137,6 +137,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvmppc_free_vcpus(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm);
 }
 
@@ -165,14 +166,24 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-int kvm_arch_set_memory_region(struct kvm *kvm,
-                               struct kvm_userspace_memory_region *mem,
-                               struct kvm_memory_slot old,
-                               int user_alloc)
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+                                   struct kvm_memory_slot *memslot,
+                                   struct kvm_memory_slot old,
+                                   struct kvm_userspace_memory_region *mem,
+                                   int user_alloc)
 {
 	return 0;
 }
 
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+               struct kvm_userspace_memory_region *mem,
+               struct kvm_memory_slot old,
+               int user_alloc)
+{
+       return;
+}
+
+
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
 }
@@ -260,34 +271,35 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu,
                                      struct kvm_run *run)
 {
-	ulong *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
-	*gpr = run->dcr.data;
+	kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, run->dcr.data);
 }
 
 static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
                                       struct kvm_run *run)
 {
-	ulong *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
+	ulong gpr;
 
-	if (run->mmio.len > sizeof(*gpr)) {
+	if (run->mmio.len > sizeof(gpr)) {
 		printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len);
 		return;
 	}
 
 	if (vcpu->arch.mmio_is_bigendian) {
 		switch (run->mmio.len) {
-		case 4: *gpr = *(u32 *)run->mmio.data; break;
-		case 2: *gpr = *(u16 *)run->mmio.data; break;
-		case 1: *gpr = *(u8 *)run->mmio.data; break;
+		case 4: gpr = *(u32 *)run->mmio.data; break;
+		case 2: gpr = *(u16 *)run->mmio.data; break;
+		case 1: gpr = *(u8 *)run->mmio.data; break;
 		}
 	} else {
 		/* Convert BE data from userland back to LE. */
 		switch (run->mmio.len) {
-		case 4: *gpr = ld_le32((u32 *)run->mmio.data); break;
-		case 2: *gpr = ld_le16((u16 *)run->mmio.data); break;
-		case 1: *gpr = *(u8 *)run->mmio.data; break;
+		case 4: gpr = ld_le32((u32 *)run->mmio.data); break;
+		case 2: gpr = ld_le16((u16 *)run->mmio.data); break;
+		case 1: gpr = *(u8 *)run->mmio.data; break;
 		}
 	}
+
+	kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
 }
 
 int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,

arch/s390/kvm/kvm-s390.c

@@ -242,6 +242,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_physmem(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm);
 }
 
@@ -690,14 +691,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 }
 
 /* Section: memory related */
-int kvm_arch_set_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				struct kvm_memory_slot old,
-				int user_alloc)
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_memory_slot old,
+				   struct kvm_userspace_memory_region *mem,
+				   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
 	   page boundary in userland and which has to end at a page boundary.
@@ -720,14 +719,23 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	if (!user_alloc)
 		return -EINVAL;
 
+	return 0;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old,
+				int user_alloc)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
 	/* 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;
 		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
 	}
-
-	return 0;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)

arch/s390/kvm/kvm-s390.h

@@ -67,10 +67,14 @@ static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
 
 static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
 {
+	int idx;
 	struct kvm_memory_slot *mem;
+	struct kvm_memslots *memslots;
 
-	down_read(&vcpu->kvm->slots_lock);
-	mem = &vcpu->kvm->memslots[0];
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	memslots = rcu_dereference(vcpu->kvm->memslots);
+
+	mem = &memslots->memslots[0];
 
 	vcpu->arch.sie_block->gmsor = mem->userspace_addr;
 	vcpu->arch.sie_block->gmslm =
@@ -78,7 +82,7 @@ static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
 		(mem->npages << PAGE_SHIFT) +
 		VIRTIODESCSPACE - 1ul;
 
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 }
 
 /* implemented in priv.c */

arch/x86/include/asm/Kbuild

@@ -11,6 +11,7 @@ header-y += sigcontext32.h
 header-y += ucontext.h
 header-y += processor-flags.h
 header-y += hw_breakpoint.h
+header-y += hyperv.h
 
 unifdef-y += e820.h
 unifdef-y += ist.h

arch/x86/include/asm/hyperv.h

+#ifndef _ASM_X86_KVM_HYPERV_H
+#define _ASM_X86_KVM_HYPERV_H
+
+#include <linux/types.h>
+
+/*
+ * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
+ * is set by CPUID(HvCpuIdFunctionVersionAndFeatures).
+ */
+#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS	0x40000000
+#define HYPERV_CPUID_INTERFACE			0x40000001
+#define HYPERV_CPUID_VERSION			0x40000002
+#define HYPERV_CPUID_FEATURES			0x40000003
+#define HYPERV_CPUID_ENLIGHTMENT_INFO		0x40000004
+#define HYPERV_CPUID_IMPLEMENT_LIMITS		0x40000005
+
+/*
+ * Feature identification. EAX indicates which features are available
+ * to the partition based upon the current partition privileges.
+ */
+
+/* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */
+#define HV_X64_MSR_VP_RUNTIME_AVAILABLE		(1 << 0)
+/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
+#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE	(1 << 1)
+/*
+ * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
+ * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
+ */
+#define HV_X64_MSR_SYNIC_AVAILABLE		(1 << 2)
+/*
+ * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through
+ * HV_X64_MSR_STIMER3_COUNT) available
+ */
+#define HV_X64_MSR_SYNTIMER_AVAILABLE		(1 << 3)
+/*
+ * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR)
+ * are available
+ */
+#define HV_X64_MSR_APIC_ACCESS_AVAILABLE	(1 << 4)
+/* Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) available*/
+#define HV_X64_MSR_HYPERCALL_AVAILABLE		(1 << 5)
+/* Access virtual processor index MSR (HV_X64_MSR_VP_INDEX) available*/
+#define HV_X64_MSR_VP_INDEX_AVAILABLE		(1 << 6)
+/* Virtual system reset MSR (HV_X64_MSR_RESET) is available*/
+#define HV_X64_MSR_RESET_AVAILABLE		(1 << 7)
+ /*
+  * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE,
+  * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE,
+  * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available
+  */
+#define HV_X64_MSR_STAT_PAGES_AVAILABLE		(1 << 8)
+
+/*
+ * Feature identification: EBX indicates which flags were specified at
+ * partition creation. The format is the same as the partition creation
+ * flag structure defined in section Partition Creation Flags.
+ */
+#define HV_X64_CREATE_PARTITIONS		(1 << 0)
+#define HV_X64_ACCESS_PARTITION_ID		(1 << 1)
+#define HV_X64_ACCESS_MEMORY_POOL		(1 << 2)
+#define HV_X64_ADJUST_MESSAGE_BUFFERS		(1 << 3)
+#define HV_X64_POST_MESSAGES			(1 << 4)
+#define HV_X64_SIGNAL_EVENTS			(1 << 5)
+#define HV_X64_CREATE_PORT			(1 << 6)
+#define HV_X64_CONNECT_PORT			(1 << 7)
+#define HV_X64_ACCESS_STATS			(1 << 8)
+#define HV_X64_DEBUGGING			(1 << 11)
+#define HV_X64_CPU_POWER_MANAGEMENT		(1 << 12)
+#define HV_X64_CONFIGURE_PROFILER		(1 << 13)
+
+/*
+ * Feature identification. EDX indicates which miscellaneous features
+ * are available to the partition.
+ */
+/* The MWAIT instruction is available (per section MONITOR / MWAIT) */
+#define HV_X64_MWAIT_AVAILABLE				(1 << 0)
+/* Guest debugging support is available */
+#define HV_X64_GUEST_DEBUGGING_AVAILABLE		(1 << 1)
+/* Performance Monitor support is available*/
+#define HV_X64_PERF_MONITOR_AVAILABLE			(1 << 2)
+/* Support for physical CPU dynamic partitioning events is available*/
+#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE	(1 << 3)
+/*
+ * Support for passing hypercall input parameter block via XMM
+ * registers is available
+ */
+#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE		(1 << 4)
+/* Support for a virtual guest idle state is available */
+#define HV_X64_GUEST_IDLE_STATE_AVAILABLE		(1 << 5)
+
+/*
+ * Implementation recommendations. Indicates which behaviors the hypervisor
+ * recommends the OS implement for optimal performance.
+ */
+ /*
+  * Recommend using hypercall for address space switches rather
+  * than MOV to CR3 instruction
+  */
+#define HV_X64_MWAIT_RECOMMENDED		(1 << 0)
+/* Recommend using hypercall for local TLB flushes rather
+ * than INVLPG or MOV to CR3 instructions */
+#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED	(1 << 1)
+/*
+ * Recommend using hypercall for remote TLB flushes rather
+ * than inter-processor interrupts
+ */
+#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED	(1 << 2)
+/*
+ * Recommend using MSRs for accessing APIC registers
+ * EOI, ICR and TPR rather than their memory-mapped counterparts
+ */
+#define HV_X64_APIC_ACCESS_RECOMMENDED		(1 << 3)
+/* Recommend using the hypervisor-provided MSR to initiate a system RESET */
+#define HV_X64_SYSTEM_RESET_RECOMMENDED		(1 << 4)
+/*
+ * Recommend using relaxed timing for this partition. If used,
+ * the VM should disable any watchdog timeouts that rely on the
+ * timely delivery of external interrupts
+ */
+#define HV_X64_RELAXED_TIMING_RECOMMENDED	(1 << 5)
+
+/* MSR used to identify the guest OS. */
+#define HV_X64_MSR_GUEST_OS_ID			0x40000000
+
+/* MSR used to setup pages used to communicate with the hypervisor. */
+#define HV_X64_MSR_HYPERCALL			0x40000001
+
+/* MSR used to provide vcpu index */
+#define HV_X64_MSR_VP_INDEX			0x40000002
+
+/* Define the virtual APIC registers */
+#define HV_X64_MSR_EOI				0x40000070
+#define HV_X64_MSR_ICR				0x40000071
+#define HV_X64_MSR_TPR				0x40000072
+#define HV_X64_MSR_APIC_ASSIST_PAGE		0x40000073
+
+/* Define synthetic interrupt controller model specific registers. */
+#define HV_X64_MSR_SCONTROL			0x40000080
+#define HV_X64_MSR_SVERSION			0x40000081
+#define HV_X64_MSR_SIEFP			0x40000082
+#define HV_X64_MSR_SIMP				0x40000083
+#define HV_X64_MSR_EOM				0x40000084
+#define HV_X64_MSR_SINT0			0x40000090
+#define HV_X64_MSR_SINT1			0x40000091
+#define HV_X64_MSR_SINT2			0x40000092
+#define HV_X64_MSR_SINT3			0x40000093
+#define HV_X64_MSR_SINT4			0x40000094
+#define HV_X64_MSR_SINT5			0x40000095
+#define HV_X64_MSR_SINT6			0x40000096
+#define HV_X64_MSR_SINT7			0x40000097
+#define HV_X64_MSR_SINT8			0x40000098
+#define HV_X64_MSR_SINT9			0x40000099
+#define HV_X64_MSR_SINT10			0x4000009A
+#define HV_X64_MSR_SINT11			0x4000009B
+#define HV_X64_MSR_SINT12			0x4000009C
+#define HV_X64_MSR_SINT13			0x4000009D
+#define HV_X64_MSR_SINT14			0x4000009E
+#define HV_X64_MSR_SINT15			0x4000009F
+
+
+#define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
+#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
+#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
+		(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
+
+/* Declare the various hypercall operations. */
+#define HV_X64_HV_NOTIFY_LONG_SPIN_WAIT		0x0008
+
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE		0x00000001
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT	12
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_MASK	\
+		(~((1ull << HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+#define HV_PROCESSOR_POWER_STATE_C0		0
+#define HV_PROCESSOR_POWER_STATE_C1		1
+#define HV_PROCESSOR_POWER_STATE_C2		2
+#define HV_PROCESSOR_POWER_STATE_C3		3
+
+/* hypercall status code */
+#define HV_STATUS_SUCCESS			0
+#define HV_STATUS_INVALID_HYPERCALL_CODE	2
+#define HV_STATUS_INVALID_HYPERCALL_INPUT	3
+#define HV_STATUS_INVALID_ALIGNMENT		4
+
+#endif

arch/x86/include/asm/kvm_emulate.h

@@ -54,13 +54,23 @@ struct x86_emulate_ctxt;
 struct x86_emulate_ops {
 	/*
 	 * read_std: Read bytes of standard (non-emulated/special) memory.
-	 *           Used for instruction fetch, stack operations, and others.
+	 *           Used for descriptor reading.
 	 *  @addr:  [IN ] Linear address from which to read.
 	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
 	 *  @bytes: [IN ] Number of bytes to read from memory.
 	 */
 	int (*read_std)(unsigned long addr, void *val,
-			unsigned int bytes, struct kvm_vcpu *vcpu);
+			unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+
+	/*
+	 * fetch: Read bytes of standard (non-emulated/special) memory.
+	 *        Used for instruction fetch.
+	 *  @addr:  [IN ] Linear address from which to read.
+	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*fetch)(unsigned long addr, void *val,
+			unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
 
 	/*
 	 * read_emulated: Read bytes from emulated/special memory area.
@@ -74,7 +84,7 @@ struct x86_emulate_ops {
 			     struct kvm_vcpu *vcpu);
 
 	/*
-	 * write_emulated: Read bytes from emulated/special memory area.
+	 * write_emulated: Write bytes to emulated/special memory area.
 	 *  @addr:  [IN ] Linear address to which to write.
 	 *  @val:   [IN ] Value to write to memory (low-order bytes used as
 	 *                required).
@@ -168,6 +178,7 @@ struct x86_emulate_ctxt {
 
 /* Execution mode, passed to the emulator. */
 #define X86EMUL_MODE_REAL     0	/* Real mode.             */
+#define X86EMUL_MODE_VM86     1	/* Virtual 8086 mode.     */
 #define X86EMUL_MODE_PROT16   2	/* 16-bit protected mode. */
 #define X86EMUL_MODE_PROT32   4	/* 32-bit protected mode. */
 #define X86EMUL_MODE_PROT64   8	/* 64-bit (long) mode.    */

arch/x86/include/asm/kvm_host.h

@@ -25,7 +25,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
 
-#define KVM_MAX_VCPUS 16
+#define KVM_MAX_VCPUS 64
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -38,19 +38,6 @@
 #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						\
-	(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						\
-	(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)
-#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
-
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
@@ -256,7 +243,8 @@ struct kvm_mmu {
 	void (*new_cr3)(struct kvm_vcpu *vcpu);
 	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
 	void (*free)(struct kvm_vcpu *vcpu);
-	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
+	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
+			    u32 *error);
 	void (*prefetch_page)(struct kvm_vcpu *vcpu,
 			      struct kvm_mmu_page *page);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -282,13 +270,15 @@ struct kvm_vcpu_arch {
 	u32 regs_dirty;
 
 	unsigned long cr0;
+	unsigned long cr0_guest_owned_bits;
 	unsigned long cr2;
 	unsigned long cr3;
 	unsigned long cr4;
+	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
 	u32 hflags;
 	u64 pdptrs[4]; /* pae */
-	u64 shadow_efer;
+	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
 	int32_t apic_arb_prio;
@@ -374,17 +364,27 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	u16 singlestep_cs;
 	unsigned long singlestep_rip;
+	/* fields used by HYPER-V emulation */
+	u64 hv_vapic;
 };
 
 struct kvm_mem_alias {
 	gfn_t base_gfn;
 	unsigned long npages;
 	gfn_t target_gfn;
+#define KVM_ALIAS_INVALID     1UL
+	unsigned long flags;
 };
 
-struct kvm_arch{
-	int naliases;
+#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION
+
+struct kvm_mem_aliases {
 	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
+	int naliases;
+};
+
+struct kvm_arch {
+	struct kvm_mem_aliases *aliases;
 
 	unsigned int n_free_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -416,6 +416,10 @@ struct kvm_arch{
 	s64 kvmclock_offset;
 
 	struct kvm_xen_hvm_config xen_hvm_config;
+
+	/* fields used by HYPER-V emulation */
+	u64 hv_guest_os_id;
+	u64 hv_hypercall;
 };
 
 struct kvm_vm_stat {
@@ -471,6 +475,7 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
+	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	/* Create, but do not attach this VCPU */
 	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
@@ -492,6 +497,7 @@ struct kvm_x86_ops {
 	void (*set_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
+	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -501,12 +507,13 @@ struct kvm_x86_ops {
 	void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
 	void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
 	void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr);
-	void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value,
-		       int *exception);
+	int (*get_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long *dest);
+	int (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+	void (*fpu_activate)(struct kvm_vcpu *vcpu);
+	void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
 
 	void (*tlb_flush)(struct kvm_vcpu *vcpu);
 
@@ -531,7 +538,8 @@ 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);
+	int (*get_lpage_level)(void);
+	bool (*rdtscp_supported)(void);
 
 	const struct trace_print_flags *exit_reasons_str;
 };
@@ -606,8 +614,7 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
 		    unsigned long value);
 
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
-int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-				int type_bits, int seg);
+int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
 
@@ -653,6 +660,10 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
@@ -666,6 +677,7 @@ void kvm_disable_tdp(void);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
 int complete_pio(struct kvm_vcpu *vcpu);
+bool kvm_check_iopl(struct kvm_vcpu *vcpu);
 
 struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn);
 

arch/x86/include/asm/kvm_para.h

@@ -2,6 +2,7 @@
 #define _ASM_X86_KVM_PARA_H
 
 #include <linux/types.h>
+#include <asm/hyperv.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/svm.h

@@ -313,7 +313,7 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_EXIT_ERR		-1
 
-#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */
+#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
 
 #define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
 #define SVM_VMRUN  ".byte 0x0f, 0x01, 0xd8"

arch/x86/include/asm/vmx.h

@@ -53,6 +53,7 @@
  */
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
+#define SECONDARY_EXEC_RDTSCP			0x00000008
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
@@ -251,6 +252,7 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
 #define EXIT_REASON_PAUSE_INSTRUCTION   40
 #define EXIT_REASON_MCE_DURING_VMENTRY	 41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
@@ -362,6 +364,7 @@ enum vmcs_field {
 #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_1GB_PAGE_BIT			(1ull << 17)
 #define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
@@ -374,7 +377,7 @@ enum vmcs_field {
 #define VMX_EPT_READABLE_MASK			0x1ull
 #define VMX_EPT_WRITABLE_MASK			0x2ull
 #define VMX_EPT_EXECUTABLE_MASK			0x4ull
-#define VMX_EPT_IGMT_BIT    			(1ull << 6)
+#define VMX_EPT_IPAT_BIT    			(1ull << 6)
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
 

arch/x86/kernel/vsyscall_64.c

@@ -301,7 +301,8 @@ static int __init vsyscall_init(void)
 	register_sysctl_table(kernel_root_table2);
 #endif
 	on_each_cpu(cpu_vsyscall_init, NULL, 1);
-	hotcpu_notifier(cpu_vsyscall_notifier, 0);
+	/* notifier priority > KVM */
+	hotcpu_notifier(cpu_vsyscall_notifier, 30);
 	return 0;
 }
 

arch/x86/kvm/Kconfig

@@ -29,6 +29,7 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
 	select USER_RETURN_NOTIFIER
+	select KVM_MMIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/x86/kvm/i8254.c

@@ -242,11 +242,11 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
 	struct kvm_kpit_state *ps = container_of(kian, struct kvm_kpit_state,
 						 irq_ack_notifier);
-	spin_lock(&ps->inject_lock);
+	raw_spin_lock(&ps->inject_lock);
 	if (atomic_dec_return(&ps->pit_timer.pending) < 0)
 		atomic_inc(&ps->pit_timer.pending);
 	ps->irq_ack = 1;
-	spin_unlock(&ps->inject_lock);
+	raw_spin_unlock(&ps->inject_lock);
 }
 
 void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
@@ -605,7 +605,7 @@ static const struct kvm_io_device_ops speaker_dev_ops = {
 	.write    = speaker_ioport_write,
 };
 
-/* Caller must have writers lock on slots_lock */
+/* Caller must hold slots_lock */
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;
@@ -624,7 +624,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 
 	mutex_init(&pit->pit_state.lock);
 	mutex_lock(&pit->pit_state.lock);
-	spin_lock_init(&pit->pit_state.inject_lock);
+	raw_spin_lock_init(&pit->pit_state.inject_lock);
 
 	kvm->arch.vpit = pit;
 	pit->kvm = kvm;
@@ -645,13 +645,13 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	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);
+	ret = kvm_io_bus_register_dev(kvm, 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,
+		ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS,
 						&pit->speaker_dev);
 		if (ret < 0)
 			goto fail_unregister;
@@ -660,11 +660,12 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	return pit;
 
 fail_unregister:
-	__kvm_io_bus_unregister_dev(&kvm->pio_bus, &pit->dev);
+	kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
 
 fail:
-	if (pit->irq_source_id >= 0)
-		kvm_free_irq_source_id(kvm, pit->irq_source_id);
+	kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+	kvm_unregister_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
+	kvm_free_irq_source_id(kvm, pit->irq_source_id);
 
 	kfree(pit);
 	return NULL;
@@ -723,12 +724,12 @@ void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
 		/* Try to inject pending interrupts when
 		 * last one has been acked.
 		 */
-		spin_lock(&ps->inject_lock);
+		raw_spin_lock(&ps->inject_lock);
 		if (atomic_read(&ps->pit_timer.pending) && ps->irq_ack) {
 			ps->irq_ack = 0;
 			inject = 1;
 		}
-		spin_unlock(&ps->inject_lock);
+		raw_spin_unlock(&ps->inject_lock);
 		if (inject)
 			__inject_pit_timer_intr(kvm);
 	}

arch/x86/kvm/i8254.h

@@ -27,7 +27,7 @@ struct kvm_kpit_state {
 	u32    speaker_data_on;
 	struct mutex lock;
 	struct kvm_pit *pit;
-	spinlock_t inject_lock;
+	raw_spinlock_t inject_lock;
 	unsigned long irq_ack;
 	struct kvm_irq_ack_notifier irq_ack_notifier;
 };

arch/x86/kvm/i8259.c

@@ -44,18 +44,19 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
 	 * Other interrupt may be delivered to PIC while lock is dropped but
 	 * it should be safe since PIC state is already updated at this stage.
 	 */
-	spin_unlock(&s->pics_state->lock);
+	raw_spin_unlock(&s->pics_state->lock);
 	kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq);
-	spin_lock(&s->pics_state->lock);
+	raw_spin_lock(&s->pics_state->lock);
 }
 
 void kvm_pic_clear_isr_ack(struct kvm *kvm)
 {
 	struct kvm_pic *s = pic_irqchip(kvm);
-	spin_lock(&s->lock);
+
+	raw_spin_lock(&s->lock);
 	s->pics[0].isr_ack = 0xff;
 	s->pics[1].isr_ack = 0xff;
-	spin_unlock(&s->lock);
+	raw_spin_unlock(&s->lock);
 }
 
 /*
@@ -156,9 +157,9 @@ static void pic_update_irq(struct kvm_pic *s)
 
 void kvm_pic_update_irq(struct kvm_pic *s)
 {
-	spin_lock(&s->lock);
+	raw_spin_lock(&s->lock);
 	pic_update_irq(s);
-	spin_unlock(&s->lock);
+	raw_spin_unlock(&s->lock);
 }
 
 int kvm_pic_set_irq(void *opaque, int irq, int level)
@@ -166,14 +167,14 @@ int kvm_pic_set_irq(void *opaque, int irq, int level)
 	struct kvm_pic *s = opaque;
 	int ret = -1;
 
-	spin_lock(&s->lock);
+	raw_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);
 	}
-	spin_unlock(&s->lock);
+	raw_spin_unlock(&s->lock);
 
 	return ret;
 }
@@ -203,7 +204,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 	int irq, irq2, intno;
 	struct kvm_pic *s = pic_irqchip(kvm);
 
-	spin_lock(&s->lock);
+	raw_spin_lock(&s->lock);
 	irq = pic_get_irq(&s->pics[0]);
 	if (irq >= 0) {
 		pic_intack(&s->pics[0], irq);
@@ -228,7 +229,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 		intno = s->pics[0].irq_base + irq;
 	}
 	pic_update_irq(s);
-	spin_unlock(&s->lock);
+	raw_spin_unlock(&s->lock);
 
 	return intno;
 }
@@ -442,7 +443,7 @@ static int picdev_write(struct kvm_io_device *this,
 			printk(KERN_ERR "PIC: non byte write\n");
 		return 0;
 	}
-	spin_lock(&s->lock);
+	raw_spin_lock(&s->lock);
 	switch (addr) {
 	case 0x20:
 	case 0x21:
@@ -455,7 +456,7 @@ static int picdev_write(struct kvm_io_device *this,
 		elcr_ioport_write(&s->pics[addr & 1], addr, data);
 		break;
 	}
-	spin_unlock(&s->lock);
+	raw_spin_unlock(&s->lock);
 	return 0;
 }
 
@@ -472,7 +473,7 @@ static int picdev_read(struct kvm_io_device *this,
 			printk(KERN_ERR "PIC: non byte read\n");
 		return 0;
 	}
-	spin_lock(&s->lock);
+	raw_spin_lock(&s->lock);
 	switch (addr) {
 	case 0x20:
 	case 0x21:
@@ -486,7 +487,7 @@ static int picdev_read(struct kvm_io_device *this,
 		break;
 	}
 	*(unsigned char *)val = data;
-	spin_unlock(&s->lock);
+	raw_spin_unlock(&s->lock);
 	return 0;
 }
 
@@ -520,7 +521,7 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 	s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL);
 	if (!s)
 		return NULL;
-	spin_lock_init(&s->lock);
+	raw_spin_lock_init(&s->lock);
 	s->kvm = kvm;
 	s->pics[0].elcr_mask = 0xf8;
 	s->pics[1].elcr_mask = 0xde;
@@ -533,7 +534,9 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 	 * Initialize PIO device
 	 */
 	kvm_iodevice_init(&s->dev, &picdev_ops);
-	ret = kvm_io_bus_register_dev(kvm, &kvm->pio_bus, &s->dev);
+	mutex_lock(&kvm->slots_lock);
+	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &s->dev);
+	mutex_unlock(&kvm->slots_lock);
 	if (ret < 0) {
 		kfree(s);
 		return NULL;
@@ -541,3 +544,14 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 
 	return s;
 }
+
+void kvm_destroy_pic(struct kvm *kvm)
+{
+	struct kvm_pic *vpic = kvm->arch.vpic;
+
+	if (vpic) {
+		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev);
+		kvm->arch.vpic = NULL;
+		kfree(vpic);
+	}
+}

arch/x86/kvm/irq.h

@@ -62,7 +62,7 @@ struct kvm_kpic_state {
 };
 
 struct kvm_pic {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	unsigned pending_acks;
 	struct kvm *kvm;
 	struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */
@@ -75,6 +75,7 @@ struct kvm_pic {
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);
+void kvm_destroy_pic(struct kvm *kvm);
 int kvm_pic_read_irq(struct kvm *kvm);
 void kvm_pic_update_irq(struct kvm_pic *s);
 void kvm_pic_clear_isr_ack(struct kvm *kvm);

arch/x86/kvm/kvm_cache_regs.h

 #ifndef ASM_KVM_CACHE_REGS_H
 #define ASM_KVM_CACHE_REGS_H
 
+#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
+#define KVM_POSSIBLE_CR4_GUEST_BITS				  \
+	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_PGE)
+
 static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
 					      enum kvm_reg reg)
 {
@@ -38,4 +43,30 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 	return vcpu->arch.pdptrs[index];
 }
 
+static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask)
+{
+	ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS;
+	if (tmask & vcpu->arch.cr0_guest_owned_bits)
+		kvm_x86_ops->decache_cr0_guest_bits(vcpu);
+	return vcpu->arch.cr0 & mask;
+}
+
+static inline ulong kvm_read_cr0(struct kvm_vcpu *vcpu)
+{
+	return kvm_read_cr0_bits(vcpu, ~0UL);
+}
+
+static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
+{
+	ulong tmask = mask & KVM_POSSIBLE_CR4_GUEST_BITS;
+	if (tmask & vcpu->arch.cr4_guest_owned_bits)
+		kvm_x86_ops->decache_cr4_guest_bits(vcpu);
+	return vcpu->arch.cr4 & mask;
+}
+
+static inline ulong kvm_read_cr4(struct kvm_vcpu *vcpu)
+{
+	return kvm_read_cr4_bits(vcpu, ~0UL);
+}
+
 #endif

arch/x86/kvm/lapic.c

@@ -1246,3 +1246,34 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 
 	return 0;
 }
+
+int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return 1;
+
+	/* if this is ICR write vector before command */
+	if (reg == APIC_ICR)
+		apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
+	return apic_reg_write(apic, reg, (u32)data);
+}
+
+int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u32 low, high = 0;
+
+	if (!irqchip_in_kernel(vcpu->kvm))
+		return 1;
+
+	if (apic_reg_read(apic, reg, 4, &low))
+		return 1;
+	if (reg == APIC_ICR)
+		apic_reg_read(apic, APIC_ICR2, 4, &high);
+
+	*data = (((u64)high) << 32) | low;
+
+	return 0;
+}