Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Avi Kivity:
 "Changes include additional instruction emulation, page-crossing MMIO,
  faster dirty logging, preventing the watchdog from killing a stopped
  guest, module autoload, a new MSI ABI, and some minor optimizations
  and fixes.  Outside x86 we have a small s390 and a very large ppc
  update.

  Regarding the new (for kvm) rebaseless workflow, some of the patches
  that were merged before we switch trees had to be rebased, while
  others are true pulls.  In either case the signoffs should be correct
  now."

Fix up trivial conflicts in Documentation/feature-removal-schedule.txt
arch/powerpc/kvm/book3s_segment.S and arch/x86/include/asm/kvm_para.h.

I suspect the kvm_para.h resolution ends up doing the "do I have cpuid"
check effectively twice (it was done differently in two different
commits), but better safe than sorry ;)

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (125 commits)
  KVM: make asm-generic/kvm_para.h have an ifdef __KERNEL__ block
  KVM: s390: onereg for timer related registers
  KVM: s390: epoch difference and TOD programmable field
  KVM: s390: KVM_GET/SET_ONEREG for s390
  KVM: s390: add capability indicating COW support
  KVM: Fix mmu_reload() clash with nested vmx event injection
  KVM: MMU: Don't use RCU for lockless shadow walking
  KVM: VMX: Optimize %ds, %es reload
  KVM: VMX: Fix %ds/%es clobber
  KVM: x86 emulator: convert bsf/bsr instructions to emulate_2op_SrcV_nobyte()
  KVM: VMX: unlike vmcs on fail path
  KVM: PPC: Emulator: clean up SPR reads and writes
  KVM: PPC: Emulator: clean up instruction parsing
  kvm/powerpc: Add new ioctl to retreive server MMU infos
  kvm/book3s: Make kernel emulated H_PUT_TCE available for "PR" KVM
  KVM: PPC: bookehv: Fix r8/r13 storing in level exception handler
  KVM: PPC: Book3S: Enable IRQs during exit handling
  KVM: PPC: Fix PR KVM on POWER7 bare metal
  KVM: PPC: Fix stbux emulation
  KVM: PPC: bookehv: Use lwz/stw instead of PPC_LL/PPC_STL for 32-bit fields
  ...

124 files changed, 5419 insertions, 1968 deletions

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 50d82ae09e2a..4ba1eb7590a7 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -588,3 +588,10 @@ Why:	Remount currently allows changing bound subsystems and
 	replaced with conventional fsnotify.
 
 ----------------------------
+
+What:	KVM debugfs statistics
+When:	2013
+Why:	KVM tracepoints provide mostly equivalent information in a much more
+        flexible fashion.
+
+----------------------------
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6386f8c0482e..930126698a0f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2,6 +2,7 @@ The Definitive KVM (Kernel-based Virtual Machine) API Documentation
 ===================================================================
 
 1. General description
+----------------------
 
 The kvm API is a set of ioctls that are issued to control various aspects
 of a virtual machine.  The ioctls belong to three classes
@@ -23,7 +24,9 @@ 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 descriptors
+-------------------
 
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
@@ -41,7 +44,9 @@ not cause harm to the host, their actual behavior is not guaranteed by
 the API.  The only supported use is one virtual machine per process,
 and one vcpu per thread.
 
+
 3. Extensions
+-------------
 
 As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
 incompatible change are allowed.  However, there is an extension
@@ -53,7 +58,9 @@ Instead, kvm defines extension identifiers and a facility to query
 whether a particular extension identifier is available.  If it is, a
 set of ioctls is available for application use.
 
+
 4. API description
+------------------
 
 This section describes ioctls that can be used to control kvm guests.
 For each ioctl, the following information is provided along with a
@@ -75,6 +82,7 @@ description:
   Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
       are not detailed, but errors with specific meanings are.
 
+
 4.1 KVM_GET_API_VERSION
 
 Capability: basic
@@ -90,6 +98,7 @@ supported.  Applications should refuse to run if KVM_GET_API_VERSION
 returns a value other than 12.  If this check passes, all ioctls
 described as 'basic' will be available.
 
+
 4.2 KVM_CREATE_VM
 
 Capability: basic
@@ -109,6 +118,7 @@ In order to create user controlled virtual machines on S390, check
 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
 privileged user (CAP_SYS_ADMIN).
 
+
 4.3 KVM_GET_MSR_INDEX_LIST
 
 Capability: basic
@@ -135,6 +145,7 @@ Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
 not returned in the MSR list, as different vcpus can have a different number
 of banks, as set via the KVM_X86_SETUP_MCE ioctl.
 
+
 4.4 KVM_CHECK_EXTENSION
 
 Capability: basic
@@ -149,6 +160,7 @@ receives an integer that describes the extension availability.
 Generally 0 means no and 1 means yes, but some extensions may report
 additional information in the integer return value.
 
+
 4.5 KVM_GET_VCPU_MMAP_SIZE
 
 Capability: basic
@@ -161,6 +173,7 @@ The KVM_RUN ioctl (cf.) communicates with userspace via a shared
 memory region.  This ioctl returns the size of that region.  See the
 KVM_RUN documentation for details.
 
+
 4.6 KVM_SET_MEMORY_REGION
 
 Capability: basic
@@ -171,6 +184,7 @@ Returns: 0 on success, -1 on error
 
 This ioctl is obsolete and has been removed.
 
+
 4.7 KVM_CREATE_VCPU
 
 Capability: basic
@@ -223,6 +237,7 @@ machines, the resulting vcpu fd can be memory mapped at page offset
 KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
 cpu's hardware control block.
 
+
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
 
 Capability: basic
@@ -246,6 +261,7 @@ since the last call to this ioctl.  Bit 0 is the first page in the
 memory slot.  Ensure the entire structure is cleared to avoid padding
 issues.
 
+
 4.9 KVM_SET_MEMORY_ALIAS
 
 Capability: basic
@@ -256,6 +272,7 @@ Returns: 0 (success), -1 (error)
 
 This ioctl is obsolete and has been removed.
 
+
 4.10 KVM_RUN
 
 Capability: basic
@@ -272,6 +289,7 @@ obtained by mmap()ing the vcpu fd at offset 0, with the size given by
 KVM_GET_VCPU_MMAP_SIZE.  The parameter block is formatted as a 'struct
 kvm_run' (see below).
 
+
 4.11 KVM_GET_REGS
 
 Capability: basic
@@ -292,6 +310,7 @@ struct kvm_regs {
 	__u64 rip, rflags;
 };
 
+
 4.12 KVM_SET_REGS
 
 Capability: basic
@@ -304,6 +323,7 @@ Writes the general purpose registers into the vcpu.
 
 See KVM_GET_REGS for the data structure.
 
+
 4.13 KVM_GET_SREGS
 
 Capability: basic
@@ -331,6 +351,7 @@ interrupt_bitmap is a bitmap of pending external interrupts.  At most
 one bit may be set.  This interrupt has been acknowledged by the APIC
 but not yet injected into the cpu core.
 
+
 4.14 KVM_SET_SREGS
 
 Capability: basic
@@ -342,6 +363,7 @@ Returns: 0 on success, -1 on error
 Writes special registers into the vcpu.  See KVM_GET_SREGS for the
 data structures.
 
+
 4.15 KVM_TRANSLATE
 
 Capability: basic
@@ -365,6 +387,7 @@ struct kvm_translation {
 	__u8  pad[5];
 };
 
+
 4.16 KVM_INTERRUPT
 
 Capability: basic
@@ -413,6 +436,7 @@ c) KVM_INTERRUPT_SET_LEVEL
 Note that any value for 'irq' other than the ones stated above is invalid
 and incurs unexpected behavior.
 
+
 4.17 KVM_DEBUG_GUEST
 
 Capability: basic
@@ -423,6 +447,7 @@ Returns: -1 on error
 
 Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
 
+
 4.18 KVM_GET_MSRS
 
 Capability: basic
@@ -451,6 +476,7 @@ Application code should set the 'nmsrs' member (which indicates the
 size of the entries array) and the 'index' member of each array entry.
 kvm will fill in the 'data' member.
 
+
 4.19 KVM_SET_MSRS
 
 Capability: basic
@@ -466,6 +492,7 @@ Application code should set the 'nmsrs' member (which indicates the
 size of the entries array), and the 'index' and 'data' members of each
 array entry.
 
+
 4.20 KVM_SET_CPUID
 
 Capability: basic
@@ -494,6 +521,7 @@ struct kvm_cpuid {
 	struct kvm_cpuid_entry entries[0];
 };
 
+
 4.21 KVM_SET_SIGNAL_MASK
 
 Capability: basic
@@ -516,6 +544,7 @@ struct kvm_signal_mask {
 	__u8  sigset[0];
 };
 
+
 4.22 KVM_GET_FPU
 
 Capability: basic
@@ -541,6 +570,7 @@ struct kvm_fpu {
 	__u32 pad2;
 };
 
+
 4.23 KVM_SET_FPU
 
 Capability: basic
@@ -566,6 +596,7 @@ struct kvm_fpu {
 	__u32 pad2;
 };
 
+
 4.24 KVM_CREATE_IRQCHIP
 
 Capability: KVM_CAP_IRQCHIP
@@ -579,6 +610,7 @@ ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a
 local APIC.  IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23
 only go to the IOAPIC.  On ia64, a IOSAPIC is created.
 
+
 4.25 KVM_IRQ_LINE
 
 Capability: KVM_CAP_IRQCHIP
@@ -600,6 +632,7 @@ struct kvm_irq_level {
 	__u32 level;           /* 0 or 1 */
 };
 
+
 4.26 KVM_GET_IRQCHIP
 
 Capability: KVM_CAP_IRQCHIP
@@ -621,6 +654,7 @@ struct kvm_irqchip {
 	} chip;
 };
 
+
 4.27 KVM_SET_IRQCHIP
 
 Capability: KVM_CAP_IRQCHIP
@@ -642,6 +676,7 @@ struct kvm_irqchip {
 	} chip;
 };
 
+
 4.28 KVM_XEN_HVM_CONFIG
 
 Capability: KVM_CAP_XEN_HVM
@@ -666,6 +701,7 @@ struct kvm_xen_hvm_config {
 	__u8 pad2[30];
 };
 
+
 4.29 KVM_GET_CLOCK
 
 Capability: KVM_CAP_ADJUST_CLOCK
@@ -684,6 +720,7 @@ struct kvm_clock_data {
 	__u32 pad[9];
 };
 
+
 4.30 KVM_SET_CLOCK
 
 Capability: KVM_CAP_ADJUST_CLOCK
@@ -702,6 +739,7 @@ struct kvm_clock_data {
 	__u32 pad[9];
 };
 
+
 4.31 KVM_GET_VCPU_EVENTS
 
 Capability: KVM_CAP_VCPU_EVENTS
@@ -741,6 +779,7 @@ struct kvm_vcpu_events {
 KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
 interrupt.shadow contains a valid state. Otherwise, this field is undefined.
 
+
 4.32 KVM_SET_VCPU_EVENTS
 
 Capability: KVM_CAP_VCPU_EVENTS
@@ -767,6 +806,7 @@ If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
 the flags field to signal that interrupt.shadow contains a valid state and
 shall be written into the VCPU.
 
+
 4.33 KVM_GET_DEBUGREGS
 
 Capability: KVM_CAP_DEBUGREGS
@@ -785,6 +825,7 @@ struct kvm_debugregs {
 	__u64 reserved[9];
 };
 
+
 4.34 KVM_SET_DEBUGREGS
 
 Capability: KVM_CAP_DEBUGREGS
@@ -798,6 +839,7 @@ Writes debug registers into the vcpu.
 See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
 yet and must be cleared on entry.
 
+
 4.35 KVM_SET_USER_MEMORY_REGION
 
 Capability: KVM_CAP_USER_MEM
@@ -844,6 +886,7 @@ It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
 The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
 allocation and is deprecated.
 
+
 4.36 KVM_SET_TSS_ADDR
 
 Capability: KVM_CAP_SET_TSS_ADDR
@@ -862,6 +905,7 @@ This ioctl is required on Intel-based hosts.  This is needed on Intel hardware
 because of a quirk in the virtualization implementation (see the internals
 documentation when it pops into existence).
 
+
 4.37 KVM_ENABLE_CAP
 
 Capability: KVM_CAP_ENABLE_CAP
@@ -897,6 +941,7 @@ function properly, this is the place to put them.
        __u8  pad[64];
 };
 
+
 4.38 KVM_GET_MP_STATE
 
 Capability: KVM_CAP_MP_STATE
@@ -927,6 +972,7 @@ Possible values are:
 This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
 irqchip, the multiprocessing state must be maintained by userspace.
 
+
 4.39 KVM_SET_MP_STATE
 
 Capability: KVM_CAP_MP_STATE
@@ -941,6 +987,7 @@ arguments.
 This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
 irqchip, the multiprocessing state must be maintained by userspace.
 
+
 4.40 KVM_SET_IDENTITY_MAP_ADDR
 
 Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
@@ -959,6 +1006,7 @@ This ioctl is required on Intel-based hosts.  This is needed on Intel hardware
 because of a quirk in the virtualization implementation (see the internals
 documentation when it pops into existence).
 
+
 4.41 KVM_SET_BOOT_CPU_ID
 
 Capability: KVM_CAP_SET_BOOT_CPU_ID
@@ -971,6 +1019,7 @@ Define which vcpu is the Bootstrap Processor (BSP).  Values are the same
 as the vcpu id in KVM_CREATE_VCPU.  If this ioctl is not called, the default
 is vcpu 0.
 
+
 4.42 KVM_GET_XSAVE
 
 Capability: KVM_CAP_XSAVE
@@ -985,6 +1034,7 @@ struct kvm_xsave {
 
 This ioctl would copy current vcpu's xsave struct to the userspace.
 
+
 4.43 KVM_SET_XSAVE
 
 Capability: KVM_CAP_XSAVE
@@ -999,6 +1049,7 @@ struct kvm_xsave {
 
 This ioctl would copy userspace's xsave struct to the kernel.
 
+
 4.44 KVM_GET_XCRS
 
 Capability: KVM_CAP_XCRS
@@ -1022,6 +1073,7 @@ struct kvm_xcrs {
 
 This ioctl would copy current vcpu's xcrs to the userspace.
 
+
 4.45 KVM_SET_XCRS
 
 Capability: KVM_CAP_XCRS
@@ -1045,6 +1097,7 @@ struct kvm_xcrs {
 
 This ioctl would set vcpu's xcr to the value userspace specified.
 
+
 4.46 KVM_GET_SUPPORTED_CPUID
 
 Capability: KVM_CAP_EXT_CPUID
@@ -1119,6 +1172,7 @@ support.  Instead it is reported via
 if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
 feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
 
+
 4.47 KVM_PPC_GET_PVINFO
 
 Capability: KVM_CAP_PPC_GET_PVINFO
@@ -1142,6 +1196,7 @@ of 4 instructions that make up a hypercall.
 If any additional field gets added to this structure later on, a bit for that
 additional piece of information will be set in the flags bitmap.
 
+
 4.48 KVM_ASSIGN_PCI_DEVICE
 
 Capability: KVM_CAP_DEVICE_ASSIGNMENT
@@ -1185,6 +1240,7 @@ Only PCI header type 0 devices with PCI BAR resources are supported by
 device assignment.  The user requesting this ioctl must have read/write
 access to the PCI sysfs resource files associated with the device.
 
+
 4.49 KVM_DEASSIGN_PCI_DEVICE
 
 Capability: KVM_CAP_DEVICE_DEASSIGNMENT
@@ -1198,6 +1254,7 @@ Ends PCI device assignment, releasing all associated resources.
 See KVM_CAP_DEVICE_ASSIGNMENT for the data structure. Only assigned_dev_id is
 used in kvm_assigned_pci_dev to identify the device.
 
+
 4.50 KVM_ASSIGN_DEV_IRQ
 
 Capability: KVM_CAP_ASSIGN_DEV_IRQ
@@ -1231,6 +1288,7 @@ The following flags are defined:
 It is not valid to specify multiple types per host or guest IRQ. However, the
 IRQ type of host and guest can differ or can even be null.
 
+
 4.51 KVM_DEASSIGN_DEV_IRQ
 
 Capability: KVM_CAP_ASSIGN_DEV_IRQ
@@ -1245,6 +1303,7 @@ See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
 by assigned_dev_id, flags must correspond to the IRQ type specified on
 KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
 
+
 4.52 KVM_SET_GSI_ROUTING
 
 Capability: KVM_CAP_IRQ_ROUTING
@@ -1293,6 +1352,7 @@ struct kvm_irq_routing_msi {
 	__u32 pad;
 };
 
+
 4.53 KVM_ASSIGN_SET_MSIX_NR
 
 Capability: KVM_CAP_DEVICE_MSIX
@@ -1314,6 +1374,7 @@ struct kvm_assigned_msix_nr {
 
 #define KVM_MAX_MSIX_PER_DEV		256
 
+
 4.54 KVM_ASSIGN_SET_MSIX_ENTRY
 
 Capability: KVM_CAP_DEVICE_MSIX
@@ -1332,7 +1393,8 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
-4.54 KVM_SET_TSC_KHZ
+
+4.55 KVM_SET_TSC_KHZ
 
 Capability: KVM_CAP_TSC_CONTROL
 Architectures: x86
@@ -1343,7 +1405,8 @@ Returns: 0 on success, -1 on error
 Specifies the tsc frequency for the virtual machine. The unit of the
 frequency is KHz.
 
-4.55 KVM_GET_TSC_KHZ
+
+4.56 KVM_GET_TSC_KHZ
 
 Capability: KVM_CAP_GET_TSC_KHZ
 Architectures: x86
@@ -1355,7 +1418,8 @@ Returns the tsc frequency of the guest. The unit of the return value is
 KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
 error.
 
-4.56 KVM_GET_LAPIC
+
+4.57 KVM_GET_LAPIC
 
 Capability: KVM_CAP_IRQCHIP
 Architectures: x86
@@ -1371,7 +1435,8 @@ struct kvm_lapic_state {
 Reads the Local APIC registers and copies them into the input argument.  The
 data format and layout are the same as documented in the architecture manual.
 
-4.57 KVM_SET_LAPIC
+
+4.58 KVM_SET_LAPIC
 
 Capability: KVM_CAP_IRQCHIP
 Architectures: x86
@@ -1387,7 +1452,8 @@ struct kvm_lapic_state {
 Copies the input argument into the the Local APIC registers.  The data format
 and layout are the same as documented in the architecture manual.
 
-4.58 KVM_IOEVENTFD
+
+4.59 KVM_IOEVENTFD
 
 Capability: KVM_CAP_IOEVENTFD
 Architectures: all
@@ -1417,7 +1483,8 @@ The following flags are defined:
 If datamatch flag is set, the event will be signaled only if the written value
 to the registered address is equal to datamatch in struct kvm_ioeventfd.
 
-4.59 KVM_DIRTY_TLB
+
+4.60 KVM_DIRTY_TLB
 
 Capability: KVM_CAP_SW_TLB
 Architectures: ppc
@@ -1449,7 +1516,8 @@ The "num_dirty" field is a performance hint for KVM to determine whether it
 should skip processing the bitmap and just invalidate everything.  It must
 be set to the number of set bits in the bitmap.
 
-4.60 KVM_ASSIGN_SET_INTX_MASK
+
+4.61 KVM_ASSIGN_SET_INTX_MASK
 
 Capability: KVM_CAP_PCI_2_3
 Architectures: x86
@@ -1482,6 +1550,7 @@ See KVM_ASSIGN_DEV_IRQ for the data structure.  The target device is specified
 by assigned_dev_id.  In the flags field, only KVM_DEV_ASSIGN_MASK_INTX is
 evaluated.
 
+
 4.62 KVM_CREATE_SPAPR_TCE
 
 Capability: KVM_CAP_SPAPR_TCE
@@ -1517,6 +1586,7 @@ the entries written by kernel-handled H_PUT_TCE calls, and also lets
 userspace update the TCE table directly which is useful in some
 circumstances.
 
+
 4.63 KVM_ALLOCATE_RMA
 
 Capability: KVM_CAP_PPC_RMA
@@ -1549,6 +1619,7 @@ is supported; 2 if the processor requires all virtual machines to have
 an RMA, or 1 if the processor can use an RMA but doesn't require it,
 because it supports the Virtual RMA (VRMA) facility.
 
+
 4.64 KVM_NMI
 
 Capability: KVM_CAP_USER_NMI
@@ -1574,6 +1645,7 @@ following algorithm:
 Some guests configure the LINT1 NMI input to cause a panic, aiding in
 debugging.
 
+
 4.65 KVM_S390_UCAS_MAP
 
 Capability: KVM_CAP_S390_UCONTROL
@@ -1593,6 +1665,7 @@ This ioctl maps the memory at "user_addr" with the length "length" to
 the vcpu's address space starting at "vcpu_addr". All parameters need to
 be alligned by 1 megabyte.
 
+
 4.66 KVM_S390_UCAS_UNMAP
 
 Capability: KVM_CAP_S390_UCONTROL
@@ -1612,6 +1685,7 @@ This ioctl unmaps the memory in the vcpu's address space starting at
 "vcpu_addr" with the length "length". The field "user_addr" is ignored.
 All parameters need to be alligned by 1 megabyte.
 
+
 4.67 KVM_S390_VCPU_FAULT
 
 Capability: KVM_CAP_S390_UCONTROL
@@ -1628,6 +1702,7 @@ table upfront. This is useful to handle validity intercepts for user
 controlled virtual machines to fault in the virtual cpu's lowcore pages
 prior to calling the KVM_RUN ioctl.
 
+
 4.68 KVM_SET_ONE_REG
 
 Capability: KVM_CAP_ONE_REG
@@ -1653,6 +1728,7 @@ registers, find a list below:
         |                       |
   PPC   | KVM_REG_PPC_HIOR      | 64
 
+
 4.69 KVM_GET_ONE_REG
 
 Capability: KVM_CAP_ONE_REG
@@ -1669,7 +1745,193 @@ at the memory location pointed to by "addr".
 The list of registers accessible using this interface is identical to the
 list in 4.64.
 
+
+4.70 KVM_KVMCLOCK_CTRL
+
+Capability: KVM_CAP_KVMCLOCK_CTRL
+Architectures: Any that implement pvclocks (currently x86 only)
+Type: vcpu ioctl
+Parameters: None
+Returns: 0 on success, -1 on error
+
+This signals to the host kernel that the specified guest is being paused by
+userspace.  The host will set a flag in the pvclock structure that is checked
+from the soft lockup watchdog.  The flag is part of the pvclock structure that
+is shared between guest and host, specifically the second bit of the flags
+field of the pvclock_vcpu_time_info structure.  It will be set exclusively by
+the host and read/cleared exclusively by the guest.  The guest operation of
+checking and clearing the flag must an atomic operation so
+load-link/store-conditional, or equivalent must be used.  There are two cases
+where the guest will clear the flag: when the soft lockup watchdog timer resets
+itself or when a soft lockup is detected.  This ioctl can be called any time
+after pausing the vcpu, but before it is resumed.
+
+
+4.71 KVM_SIGNAL_MSI
+
+Capability: KVM_CAP_SIGNAL_MSI
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_msi (in)
+Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
+
+Directly inject a MSI message. Only valid with in-kernel irqchip that handles
+MSI messages.
+
+struct kvm_msi {
+	__u32 address_lo;
+	__u32 address_hi;
+	__u32 data;
+	__u32 flags;
+	__u8  pad[16];
+};
+
+No flags are defined so far. The corresponding field must be 0.
+
+
+4.71 KVM_CREATE_PIT2
+
+Capability: KVM_CAP_PIT2
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pit_config (in)
+Returns: 0 on success, -1 on error
+
+Creates an in-kernel device model for the i8254 PIT. This call is only valid
+after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
+parameters have to be passed:
+
+struct kvm_pit_config {
+	__u32 flags;
+	__u32 pad[15];
+};
+
+Valid flags are:
+
+#define KVM_PIT_SPEAKER_DUMMY     1 /* emulate speaker port stub */
+
+PIT timer interrupts may use a per-VM kernel thread for injection. If it
+exists, this thread will have a name of the following pattern:
+
+kvm-pit/<owner-process-pid>
+
+When running a guest with elevated priorities, the scheduling parameters of
+this thread may have to be adjusted accordingly.
+
+This IOCTL replaces the obsolete KVM_CREATE_PIT.
+
+
+4.72 KVM_GET_PIT2
+
+Capability: KVM_CAP_PIT_STATE2
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pit_state2 (out)
+Returns: 0 on success, -1 on error
+
+Retrieves the state of the in-kernel PIT model. Only valid after
+KVM_CREATE_PIT2. The state is returned in the following structure:
+
+struct kvm_pit_state2 {
+	struct kvm_pit_channel_state channels[3];
+	__u32 flags;
+	__u32 reserved[9];
+};
+
+Valid flags are:
+
+/* disable PIT in HPET legacy mode */
+#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
+
+This IOCTL replaces the obsolete KVM_GET_PIT.
+
+
+4.73 KVM_SET_PIT2
+
+Capability: KVM_CAP_PIT_STATE2
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pit_state2 (in)
+Returns: 0 on success, -1 on error
+
+Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
+See KVM_GET_PIT2 for details on struct kvm_pit_state2.
+
+This IOCTL replaces the obsolete KVM_SET_PIT.
+
+
+4.74 KVM_PPC_GET_SMMU_INFO
+
+Capability: KVM_CAP_PPC_GET_SMMU_INFO
+Architectures: powerpc
+Type: vm ioctl
+Parameters: None
+Returns: 0 on success, -1 on error
+
+This populates and returns a structure describing the features of
+the "Server" class MMU emulation supported by KVM.
+This can in turn be used by userspace to generate the appropariate
+device-tree properties for the guest operating system.
+
+The structure contains some global informations, followed by an
+array of supported segment page sizes:
+
+      struct kvm_ppc_smmu_info {
+	     __u64 flags;
+	     __u32 slb_size;
+	     __u32 pad;
+	     struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+      };
+
+The supported flags are:
+
+    - KVM_PPC_PAGE_SIZES_REAL:
+        When that flag is set, guest page sizes must "fit" the backing
+        store page sizes. When not set, any page size in the list can
+        be used regardless of how they are backed by userspace.
+
+    - KVM_PPC_1T_SEGMENTS
+        The emulated MMU supports 1T segments in addition to the
+        standard 256M ones.
+
+The "slb_size" field indicates how many SLB entries are supported
+
+The "sps" array contains 8 entries indicating the supported base
+page sizes for a segment in increasing order. Each entry is defined
+as follow:
+
+   struct kvm_ppc_one_seg_page_size {
+	__u32 page_shift;	/* Base page shift of segment (or 0) */
+	__u32 slb_enc;		/* SLB encoding for BookS */
+	struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+   };
+
+An entry with a "page_shift" of 0 is unused. Because the array is
+organized in increasing order, a lookup can stop when encoutering
+such an entry.
+
+The "slb_enc" field provides the encoding to use in the SLB for the
+page size. The bits are in positions such as the value can directly
+be OR'ed into the "vsid" argument of the slbmte instruction.
+
+The "enc" array is a list which for each of those segment base page
+size provides the list of supported actual page sizes (which can be
+only larger or equal to the base page size), along with the
+corresponding encoding in the hash PTE. Similarily, the array is
+8 entries sorted by increasing sizes and an entry with a "0" shift
+is an empty entry and a terminator:
+
+   struct kvm_ppc_one_page_size {
+	__u32 page_shift;	/* Page shift (or 0) */
+	__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
+   };
+
+The "pte_enc" field provides a value that can OR'ed into the hash
+PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
+into the hash PTE second double word).
+
 5. The kvm_run structure
+------------------------
 
 Application code obtains a pointer to the kvm_run structure by
 mmap()ing a vcpu fd.  From that point, application code can control
@@ -1910,7 +2172,9 @@ and usually define the validity of a groups of registers. (e.g. one bit
 
 };
 
+
 6. Capabilities that can be enabled
+-----------------------------------
 
 There are certain capabilities that change the behavior of the virtual CPU when
 enabled. To enable them, please see section 4.37. Below you can find a list of
@@ -1926,6 +2190,7 @@ The following information is provided along with the description:
   Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
       are not detailed, but errors with specific meanings are.
 
+
 6.1 KVM_CAP_PPC_OSI
 
 Architectures: ppc
@@ -1939,6 +2204,7 @@ between the guest and the host.
 
 When this capability is enabled, KVM_EXIT_OSI can occur.
 
+
 6.2 KVM_CAP_PPC_PAPR
 
 Architectures: ppc
@@ -1957,6 +2223,7 @@ HTAB invisible to the guest.
 
 When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
 
+
 6.3 KVM_CAP_SW_TLB
 
 Architectures: ppc
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 882068538c9c..83afe65d4966 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -10,11 +10,15 @@ a guest.
 KVM cpuid functions are:
 
 function: KVM_CPUID_SIGNATURE (0x40000000)
-returns : eax = 0,
+returns : eax = 0x40000001,
           ebx = 0x4b4d564b,
           ecx = 0x564b4d56,
           edx = 0x4d.
 Note that this value in ebx, ecx and edx corresponds to the string "KVMKVMKVM".
+The value in eax corresponds to the maximum cpuid function present in this leaf,
+and will be updated if more functions are added in the future.
+Note also that old hosts set eax value to 0x0. This should
+be interpreted as if the value was 0x40000001.
 This function queries the presence of KVM cpuid leafs.
 
 
diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index 50317809113d..96b41bd97523 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -109,6 +109,10 @@ MSR_KVM_SYSTEM_TIME_NEW:  0x4b564d01
 		     0      |	   24      | multiple cpus are guaranteed to
 			    |		   | be monotonic
 		-------------------------------------------------------------
+			    |		   | guest vcpu has been paused by
+		     1	    |	  N/A	   | the host
+			    |		   | See 4.70 in api.txt
+		-------------------------------------------------------------
 
 	Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid
 	leaf prior to usage.
diff --git a/arch/alpha/include/asm/kvm_para.h b/arch/alpha/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/alpha/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/arm/include/asm/kvm_para.h b/arch/arm/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/arm/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/avr32/include/asm/kvm_para.h b/arch/avr32/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/avr32/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/blackfin/include/asm/kvm_para.h b/arch/blackfin/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/blackfin/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/c6x/include/asm/kvm_para.h b/arch/c6x/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/c6x/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/frv/include/asm/kvm_para.h b/arch/frv/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/frv/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/h8300/include/asm/kvm_para.h b/arch/h8300/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/h8300/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/hexagon/include/asm/kvm_para.h b/arch/hexagon/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/hexagon/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index e35b3a84a40b..6d6a5ac48d85 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -365,6 +365,7 @@ struct thash_cb {
 };
 
 struct kvm_vcpu_stat {
+	u32 halt_wakeup;
 };
 
 struct kvm_vcpu_arch {
@@ -448,6 +449,8 @@ struct kvm_vcpu_arch {
 	char log_buf[VMM_LOG_LEN];
 	union context host;
 	union context guest;
+
+	char mmio_data[8];
 };
 
 struct kvm_vm_stat {
diff --git a/arch/ia64/include/asm/kvm_para.h b/arch/ia64/include/asm/kvm_para.h
index 1588aee781a2..2019cb99335e 100644
--- a/arch/ia64/include/asm/kvm_para.h
+++ b/arch/ia64/include/asm/kvm_para.h
@@ -26,6 +26,11 @@ static inline unsigned int kvm_arch_para_features(void)
 	return 0;
 }
 
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
 #endif
 
 #endif
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 463fb3bbe11e..bd77cb507c1c 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -232,12 +232,12 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if ((p->addr & PAGE_MASK) == IOAPIC_DEFAULT_BASE_ADDRESS)
 		goto mmio;
 	vcpu->mmio_needed = 1;
-	vcpu->mmio_phys_addr = kvm_run->mmio.phys_addr = p->addr;
-	vcpu->mmio_size = kvm_run->mmio.len = p->size;
+	vcpu->mmio_fragments[0].gpa = kvm_run->mmio.phys_addr = p->addr;
+	vcpu->mmio_fragments[0].len = kvm_run->mmio.len = p->size;
 	vcpu->mmio_is_write = kvm_run->mmio.is_write = !p->dir;
 
 	if (vcpu->mmio_is_write)
-		memcpy(vcpu->mmio_data, &p->data, p->size);
+		memcpy(vcpu->arch.mmio_data, &p->data, p->size);
 	memcpy(kvm_run->mmio.data, &p->data, p->size);
 	kvm_run->exit_reason = KVM_EXIT_MMIO;
 	return 0;
@@ -719,7 +719,7 @@ static void kvm_set_mmio_data(struct kvm_vcpu *vcpu)
 	struct kvm_mmio_req *p = kvm_get_vcpu_ioreq(vcpu);
 
 	if (!vcpu->mmio_is_write)
-		memcpy(&p->data, vcpu->mmio_data, 8);
+		memcpy(&p->data, vcpu->arch.mmio_data, 8);
 	p->state = STATE_IORESP_READY;
 }
 
@@ -739,7 +739,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	if (vcpu->mmio_needed) {
-		memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+		memcpy(vcpu->arch.mmio_data, kvm_run->mmio.data, 8);
 		kvm_set_mmio_data(vcpu);
 		vcpu->mmio_read_completed = 1;
 		vcpu->mmio_needed = 0;
@@ -1872,21 +1872,6 @@ void kvm_arch_hardware_unsetup(void)
 {
 }
 
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
-{
-	int me;
-	int cpu = vcpu->cpu;
-
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
-
-	me = get_cpu();
-	if (cpu != me && (unsigned) cpu < nr_cpu_ids && cpu_online(cpu))
-		if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
-			smp_send_reschedule(cpu);
-	put_cpu();
-}
-
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
 {
 	return __apic_accept_irq(vcpu, irq->vector);
@@ -1956,6 +1941,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		(kvm_highest_pending_irq(vcpu) != -1);
 }
 
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
+{
+	return (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests));
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
diff --git a/arch/m68k/include/asm/kvm_para.h b/arch/m68k/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/m68k/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/microblaze/include/asm/kvm_para.h b/arch/microblaze/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/microblaze/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/mips/include/asm/kvm_para.h b/arch/mips/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/mips/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/mn10300/include/asm/kvm_para.h b/arch/mn10300/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/mn10300/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/openrisc/include/asm/kvm_para.h b/arch/openrisc/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/openrisc/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/parisc/include/asm/kvm_para.h b/arch/parisc/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/parisc/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index b9219e99bd2a..50d82c8a037f 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -168,6 +168,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_LWSYNC			ASM_CONST(0x0000000008000000)
 #define CPU_FTR_NOEXECUTE		ASM_CONST(0x0000000010000000)
 #define CPU_FTR_INDEXED_DCR		ASM_CONST(0x0000000020000000)
+#define CPU_FTR_EMB_HV			ASM_CONST(0x0000000040000000)
 
 /*
  * Add the 64-bit processor unique features in the top half of the word;
@@ -376,7 +377,8 @@ extern const char *powerpc_base_platform;
 #define CPU_FTRS_47X	(CPU_FTRS_440x6)
 #define CPU_FTRS_E200	(CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
-	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE)
+	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DEBUG_LVL_EXC)
 #define CPU_FTRS_E500	(CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \
 	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_NOEXECUTE)
@@ -385,15 +387,15 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_E500MC	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
-	    CPU_FTR_DBELL)
+	    CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
 #define CPU_FTRS_E5500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
-	    CPU_FTR_DEBUG_LVL_EXC)
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
 #define CPU_FTRS_E6500	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
 	    CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
-	    CPU_FTR_DEBUG_LVL_EXC)
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
 #define CPU_FTRS_GENERIC_32	(CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
@@ -486,8 +488,10 @@ enum {
 	    CPU_FTRS_E200 |
 #endif
 #ifdef CONFIG_E500
-	    CPU_FTRS_E500 | CPU_FTRS_E500_2 | CPU_FTRS_E500MC |
-	    CPU_FTRS_E5500 | CPU_FTRS_E6500 |
+	    CPU_FTRS_E500 | CPU_FTRS_E500_2 |
+#endif
+#ifdef CONFIG_PPC_E500MC
+	    CPU_FTRS_E500MC | CPU_FTRS_E5500 | CPU_FTRS_E6500 |
 #endif
 	    0,
 };
@@ -531,9 +535,12 @@ enum {
 	    CPU_FTRS_E200 &
 #endif
 #ifdef CONFIG_E500
-	    CPU_FTRS_E500 & CPU_FTRS_E500_2 & CPU_FTRS_E500MC &
-	    CPU_FTRS_E5500 & CPU_FTRS_E6500 &
+	    CPU_FTRS_E500 & CPU_FTRS_E500_2 &
+#endif
+#ifdef CONFIG_PPC_E500MC
+	    CPU_FTRS_E500MC & CPU_FTRS_E5500 & CPU_FTRS_E6500 &
 #endif
+	    ~CPU_FTR_EMB_HV &	/* can be removed at runtime */
 	    CPU_FTRS_POSSIBLE,
 };
 #endif /* __powerpc64__ */
diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index efa74ac44a35..154c067761b1 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -19,6 +19,9 @@
 
 #define PPC_DBELL_MSG_BRDCAST	(0x04000000)
 #define PPC_DBELL_TYPE(x)	(((x) & 0xf) << (63-36))
+#define PPC_DBELL_TYPE_MASK	PPC_DBELL_TYPE(0xf)
+#define PPC_DBELL_LPID(x)	((x) << (63 - 49))
+#define PPC_DBELL_PIR_MASK	0x3fff
 enum ppc_dbell {
 	PPC_DBELL = 0,		/* doorbell */
 	PPC_DBELL_CRIT = 1,	/* critical doorbell */
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 612252388190..423cf9eaf4a4 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -133,6 +133,16 @@
 #define H_PP1			(1UL<<(63-62))
 #define H_PP2			(1UL<<(63-63))
 
+/* Flags for H_REGISTER_VPA subfunction field */
+#define H_VPA_FUNC_SHIFT	(63-18)	/* Bit posn of subfunction code */
+#define H_VPA_FUNC_MASK		7UL
+#define H_VPA_REG_VPA		1UL	/* Register Virtual Processor Area */
+#define H_VPA_REG_DTL		2UL	/* Register Dispatch Trace Log */
+#define H_VPA_REG_SLB		3UL	/* Register SLB shadow buffer */
+#define H_VPA_DEREG_VPA		5UL	/* Deregister Virtual Processor Area */
+#define H_VPA_DEREG_DTL		6UL	/* Deregister Dispatch Trace Log */
+#define H_VPA_DEREG_SLB		7UL	/* Deregister SLB shadow buffer */
+
 /* VASI States */
 #define H_VASI_INVALID          0
 #define H_VASI_ENABLED          1
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 51010bfc792e..c9aac24b02e2 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -33,6 +33,7 @@
 extern void __replay_interrupt(unsigned int vector);
 
 extern void timer_interrupt(struct pt_regs *);
+extern void performance_monitor_exception(struct pt_regs *regs);
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index b921c3f48928..1bea4d8ea6f4 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -277,6 +277,7 @@ struct kvm_sync_regs {
 #define KVM_CPU_E500V2		2
 #define KVM_CPU_3S_32		3
 #define KVM_CPU_3S_64		4
+#define KVM_CPU_E500MC		5
 
 /* for KVM_CAP_SPAPR_TCE */
 struct kvm_create_spapr_tce {
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 7b1f0e0fc653..76fdcfef0889 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -20,6 +20,16 @@
 #ifndef __POWERPC_KVM_ASM_H__
 #define __POWERPC_KVM_ASM_H__
 
+#ifdef __ASSEMBLY__
+#ifdef CONFIG_64BIT
+#define PPC_STD(sreg, offset, areg)  std sreg, (offset)(areg)
+#define PPC_LD(treg, offset, areg)   ld treg, (offset)(areg)
+#else
+#define PPC_STD(sreg, offset, areg)  stw sreg, (offset+4)(areg)
+#define PPC_LD(treg, offset, areg)   lwz treg, (offset+4)(areg)
+#endif
+#endif
+
 /* IVPR must be 64KiB-aligned. */
 #define VCPU_SIZE_ORDER 4
 #define VCPU_SIZE_LOG   (VCPU_SIZE_ORDER + 12)
@@ -48,6 +58,14 @@
 #define BOOKE_INTERRUPT_SPE_FP_DATA 33
 #define BOOKE_INTERRUPT_SPE_FP_ROUND 34
 #define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
+#define BOOKE_INTERRUPT_DOORBELL 36
+#define BOOKE_INTERRUPT_DOORBELL_CRITICAL 37
+
+/* booke_hv */
+#define BOOKE_INTERRUPT_GUEST_DBELL 38
+#define BOOKE_INTERRUPT_GUEST_DBELL_CRIT 39
+#define BOOKE_INTERRUPT_HV_SYSCALL 40
+#define BOOKE_INTERRUPT_HV_PRIV 41
 
 /* book3s */
 
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index fd07f43d6622..f0e0c6a66d97 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -453,4 +453,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 
 #define INS_DCBZ			0x7c0007ec
 
+/* LPIDs we support with this build -- runtime limit may be lower */
+#define KVMPPC_NR_LPIDS			(LPID_RSVD + 1)
+
 #endif /* __ASM_KVM_BOOK3S_H__ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 1f2f5b6156bd..88609b23b775 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -79,6 +79,9 @@ struct kvmppc_host_state {
 	u8 napping;
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
+	u8 hwthread_req;
+	u8 hwthread_state;
+
 	struct kvm_vcpu *kvm_vcpu;
 	struct kvmppc_vcore *kvm_vcore;
 	unsigned long xics_phys;
@@ -122,4 +125,9 @@ struct kvmppc_book3s_shadow_vcpu {
 
 #endif /*__ASSEMBLY__ */
 
+/* Values for kvm_state */
+#define KVM_HWTHREAD_IN_KERNEL	0
+#define KVM_HWTHREAD_IN_NAP	1
+#define KVM_HWTHREAD_IN_KVM	2
+
 #endif /* __ASM_KVM_BOOK3S_ASM_H__ */
diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h
index a90e09188777..b7cd3356a532 100644
--- a/arch/powerpc/include/asm/kvm_booke.h
+++ b/arch/powerpc/include/asm/kvm_booke.h
@@ -23,6 +23,9 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 
+/* LPIDs we support with this build -- runtime limit may be lower */
+#define KVMPPC_NR_LPIDS                        64
+
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
 	vcpu->arch.gpr[num] = val;
diff --git a/arch/powerpc/include/asm/kvm_booke_hv_asm.h b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
new file mode 100644
index 000000000000..30a600fa1b6a
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_booke_hv_asm.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_KVM_BOOKE_HV_ASM_H
+#define ASM_KVM_BOOKE_HV_ASM_H
+
+#ifdef __ASSEMBLY__
+
+/*
+ * All exceptions from guest state must go through KVM
+ * (except for those which are delivered directly to the guest) --
+ * there are no exceptions for which we fall through directly to
+ * the normal host handler.
+ *
+ * Expected inputs (normal exceptions):
+ *   SCRATCH0 = saved r10
+ *   r10 = thread struct
+ *   r11 = appropriate SRR1 variant (currently used as scratch)
+ *   r13 = saved CR
+ *   *(r10 + THREAD_NORMSAVE(0)) = saved r11
+ *   *(r10 + THREAD_NORMSAVE(2)) = saved r13
+ *
+ * Expected inputs (crit/mcheck/debug exceptions):
+ *   appropriate SCRATCH = saved r8
+ *   r8 = exception level stack frame
+ *   r9 = *(r8 + _CCR) = saved CR
+ *   r11 = appropriate SRR1 variant (currently used as scratch)
+ *   *(r8 + GPR9) = saved r9
+ *   *(r8 + GPR10) = saved r10 (r10 not yet clobbered)
+ *   *(r8 + GPR11) = saved r11
+ */
+.macro DO_KVM intno srr1
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+	mtocrf	0x80, r11	/* check MSR[GS] without clobbering reg */
+	bf	3, kvmppc_resume_\intno\()_\srr1
+	b	kvmppc_handler_\intno\()_\srr1
+kvmppc_resume_\intno\()_\srr1:
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
+.endm
+
+#endif /*__ASSEMBLY__ */
+#endif /* ASM_KVM_BOOKE_HV_ASM_H */
diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
deleted file mode 100644
index 8cd50a514271..000000000000
--- a/arch/powerpc/include/asm/kvm_e500.h
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
- *
- * Author: Yu Liu, <yu.liu@freescale.com>
- *
- * Description:
- * This file is derived from arch/powerpc/include/asm/kvm_44x.h,
- * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_KVM_E500_H__
-#define __ASM_KVM_E500_H__
-
-#include <linux/kvm_host.h>
-
-#define BOOKE_INTERRUPT_SIZE 36
-
-#define E500_PID_NUM   3
-#define E500_TLB_NUM   2
-
-#define E500_TLB_VALID 1
-#define E500_TLB_DIRTY 2
-
-struct tlbe_ref {
-	pfn_t pfn;
-	unsigned int flags; /* E500_TLB_* */
-};
-
-struct tlbe_priv {
-	struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
-};
-
-struct vcpu_id_table;
-
-struct kvmppc_e500_tlb_params {
-	int entries, ways, sets;
-};
-
-struct kvmppc_vcpu_e500 {
-	/* Unmodified copy of the guest's TLB -- shared with host userspace. */
-	struct kvm_book3e_206_tlb_entry *gtlb_arch;
-
-	/* Starting entry number in gtlb_arch[] */
-	int gtlb_offset[E500_TLB_NUM];
-
-	/* KVM internal information associated with each guest TLB entry */
-	struct tlbe_priv *gtlb_priv[E500_TLB_NUM];
-
-	struct kvmppc_e500_tlb_params gtlb_params[E500_TLB_NUM];
-
-	unsigned int gtlb_nv[E500_TLB_NUM];
-
-	/*
-	 * information associated with each host TLB entry --
-	 * TLB1 only for now.  If/when guest TLB1 entries can be
-	 * mapped with host TLB0, this will be used for that too.
-	 *
-	 * We don't want to use this for guest TLB0 because then we'd
-	 * have the overhead of doing the translation again even if
-	 * the entry is still in the guest TLB (e.g. we swapped out
-	 * and back, and our host TLB entries got evicted).
-	 */
-	struct tlbe_ref *tlb_refs[E500_TLB_NUM];
-	unsigned int host_tlb1_nv;
-
-	u32 host_pid[E500_PID_NUM];
-	u32 pid[E500_PID_NUM];
-	u32 svr;
-
-	/* vcpu id table */
-	struct vcpu_id_table *idt;
-
-	u32 l1csr0;
-	u32 l1csr1;
-	u32 hid0;
-	u32 hid1;
-	u32 tlb0cfg;
-	u32 tlb1cfg;
-	u64 mcar;
-
-	struct page **shared_tlb_pages;
-	int num_shared_tlb_pages;
-
-	struct kvm_vcpu vcpu;
-};
-
-static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
-{
-	return container_of(vcpu, struct kvmppc_vcpu_e500, vcpu);
-}
-
-#endif /* __ASM_KVM_E500_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 52eb9c1f4fe0..d848cdc49715 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -82,7 +82,7 @@ struct kvm_vcpu;
 
 struct lppaca;
 struct slb_shadow;
-struct dtl;
+struct dtl_entry;
 
 struct kvm_vm_stat {
 	u32 remote_tlb_flush;
@@ -106,6 +106,8 @@ struct kvm_vcpu_stat {
 	u32 dec_exits;
 	u32 ext_intr_exits;
 	u32 halt_wakeup;
+	u32 dbell_exits;
+	u32 gdbell_exits;
 #ifdef CONFIG_PPC_BOOK3S
 	u32 pf_storage;
 	u32 pf_instruc;
@@ -140,6 +142,7 @@ enum kvm_exit_types {
 	EMULATED_TLBSX_EXITS,
 	EMULATED_TLBWE_EXITS,
 	EMULATED_RFI_EXITS,
+	EMULATED_RFCI_EXITS,
 	DEC_EXITS,
 	EXT_INTR_EXITS,
 	HALT_WAKEUP,
@@ -147,6 +150,8 @@ enum kvm_exit_types {
 	FP_UNAVAIL,
 	DEBUG_EXITS,
 	TIMEINGUEST,
+	DBELL_EXITS,
+	GDBELL_EXITS,
 	__NUMBER_OF_KVM_EXIT_TYPES
 };
 
@@ -217,10 +222,10 @@ struct kvm_arch_memory_slot {
 };
 
 struct kvm_arch {
+	unsigned int lpid;
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	unsigned long hpt_virt;
 	struct revmap_entry *revmap;
-	unsigned int lpid;
 	unsigned int host_lpid;
 	unsigned long host_lpcr;
 	unsigned long sdr1;
@@ -232,7 +237,6 @@ struct kvm_arch {
 	unsigned long vrma_slb_v;
 	int rma_setup_done;
 	int using_mmu_notifiers;
-	struct list_head spapr_tce_tables;
 	spinlock_t slot_phys_lock;
 	unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
 	int slot_npages[KVM_MEM_SLOTS_NUM];
@@ -240,6 +244,9 @@ struct kvm_arch {
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 	struct kvmppc_linear_info *hpt_li;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct list_head spapr_tce_tables;
+#endif
 };
 
 /*
@@ -263,6 +270,9 @@ struct kvmppc_vcore {
 	struct list_head runnable_threads;
 	spinlock_t lock;
 	wait_queue_head_t wq;
+	u64 stolen_tb;
+	u64 preempt_tb;
+	struct kvm_vcpu *runner;
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
@@ -274,6 +284,19 @@ struct kvmppc_vcore {
 #define VCORE_EXITING	2
 #define VCORE_SLEEPING	3
 
+/*
+ * Struct used to manage memory for a virtual processor area
+ * registered by a PAPR guest.  There are three types of area
+ * that a guest can register.
+ */
+struct kvmppc_vpa {
+	void *pinned_addr;	/* Address in kernel linear mapping */
+	void *pinned_end;	/* End of region */
+	unsigned long next_gpa;	/* Guest phys addr for update */
+	unsigned long len;	/* Number of bytes required */
+	u8 update_pending;	/* 1 => update pinned_addr from next_gpa */
+};
+
 struct kvmppc_pte {
 	ulong eaddr;
 	u64 vpage;
@@ -345,6 +368,17 @@ struct kvm_vcpu_arch {
 	u64 vsr[64];
 #endif
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	u32 host_mas4;
+	u32 host_mas6;
+	u32 shadow_epcr;
+	u32 epcr;
+	u32 shadow_msrp;
+	u32 eplc;
+	u32 epsc;
+	u32 oldpir;
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S
 	/* For Gekko paired singles */
 	u32 qpr[32];
@@ -370,6 +404,7 @@ struct kvm_vcpu_arch {
 #endif
 	u32 vrsave; /* also USPRG0 */
 	u32 mmucr;
+	/* shadow_msr is unused for BookE HV */
 	ulong shadow_msr;
 	ulong csrr0;
 	ulong csrr1;
@@ -426,8 +461,12 @@ struct kvm_vcpu_arch {
 	ulong fault_esr;
 	ulong queued_dear;
 	ulong queued_esr;
+	u32 tlbcfg[4];
+	u32 mmucfg;
+	u32 epr;
 #endif
 	gpa_t paddr_accessed;
+	gva_t vaddr_accessed;
 
 	u8 io_gpr; /* GPR used as IO source/target */
 	u8 mmio_is_bigendian;
@@ -453,11 +492,6 @@ struct kvm_vcpu_arch {
 	u8 prodded;
 	u32 last_inst;
 
-	struct lppaca *vpa;
-	struct slb_shadow *slb_shadow;
-	struct dtl *dtl;
-	struct dtl *dtl_end;
-
 	wait_queue_head_t *wqp;
 	struct kvmppc_vcore *vcore;
 	int ret;
@@ -482,6 +516,14 @@ struct kvm_vcpu_arch {
 	struct task_struct *run_task;
 	struct kvm_run *kvm_run;
 	pgd_t *pgdir;
+
+	spinlock_t vpa_update_lock;
+	struct kvmppc_vpa vpa;
+	struct kvmppc_vpa dtl;
+	struct dtl_entry *dtl_ptr;
+	unsigned long dtl_index;
+	u64 stolen_logged;
+	struct kvmppc_vpa slb_shadow;
 #endif
 };
 
@@ -498,4 +540,6 @@ struct kvm_vcpu_arch {
 #define KVM_MMIO_REG_QPR	0x0040
 #define KVM_MMIO_REG_FQPR	0x0060
 
+#define __KVM_HAVE_ARCH_WQP
+
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 7b754e743003..c18916bff689 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -206,6 +206,11 @@ static inline unsigned int kvm_arch_para_features(void)
 	return r;
 }
 
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* __POWERPC_KVM_PARA_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 9d6dee0f7d48..f68c22fa2fce 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -95,7 +95,7 @@ extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 extern void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
-extern void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
+extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(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);
@@ -107,8 +107,10 @@ extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
 
 extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                   unsigned int op, int *advance);
-extern int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs);
-extern int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
+extern int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn,
+				     ulong val);
+extern int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn,
+				     ulong *val);
 
 extern int kvmppc_booke_init(void);
 extern void kvmppc_booke_exit(void);
@@ -126,6 +128,8 @@ extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
+extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+			     unsigned long ioba, unsigned long tce);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
 extern struct kvmppc_linear_info *kvm_alloc_rma(void);
@@ -138,6 +142,11 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
+extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
+				      struct kvm_ppc_smmu_info *info);
+
+extern int kvmppc_bookehv_init(void);
+extern void kvmppc_bookehv_exit(void);
 
 /*
  * Cuts out inst bits with ordering according to spec.
@@ -204,4 +213,9 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
 			     struct kvm_dirty_tlb *cfg);
 
+long kvmppc_alloc_lpid(void);
+void kvmppc_claim_lpid(long lpid);
+void kvmppc_free_lpid(long lpid);
+void kvmppc_init_lpid(unsigned long nr_lpids);
+
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index cdb5421877e2..eeabcdbc30f7 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -104,6 +104,8 @@
 #define MAS4_TSIZED_MASK	0x00000f80	/* Default TSIZE */
 #define MAS4_TSIZED_SHIFT	7
 
+#define MAS5_SGS		0x80000000
+
 #define MAS6_SPID0		0x3FFF0000
 #define MAS6_SPID1		0x00007FFE
 #define MAS6_ISIZE(x)		MAS1_TSIZE(x)
@@ -118,6 +120,10 @@
 
 #define MAS7_RPN		0xFFFFFFFF
 
+#define MAS8_TGS		0x80000000 /* Guest space */
+#define MAS8_VF			0x40000000 /* Virtualization Fault */
+#define MAS8_TLPID		0x000000ff
+
 /* Bit definitions for MMUCFG */
 #define MMUCFG_MAVN	0x00000003	/* MMU Architecture Version Number */
 #define MMUCFG_MAVN_V1	0x00000000	/* v1.0 */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 55e85631c42e..413a5eaef56c 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -240,6 +240,9 @@ struct thread_struct {
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	void*		kvm_shadow_vcpu; /* KVM internal data */
 #endif /* CONFIG_KVM_BOOK3S_32_HANDLER */
+#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
+	struct kvm_vcpu	*kvm_vcpu;
+#endif
 #ifdef CONFIG_PPC64
 	unsigned long	dscr;
 	int		dscr_inherit;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 9d7f0fb69028..f0cb7f461b9d 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -257,7 +257,9 @@
 #define   LPCR_LPES_SH	2
 #define   LPCR_RMI     0x00000002      /* real mode is cache inhibit */
 #define   LPCR_HDICE   0x00000001      /* Hyp Decr enable (HV,PR,EE) */
+#ifndef SPRN_LPID
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
+#endif
 #define   LPID_RSVD	0x3ff		/* Reserved LPID for partn switching */
 #define	SPRN_HMER	0x150	/* Hardware m? error recovery */
 #define	SPRN_HMEER	0x151	/* Hardware m? enable error recovery */
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 8a97aa7289d3..2d916c4982c5 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -56,18 +56,30 @@
 #define SPRN_SPRG7W	0x117	/* Special Purpose Register General 7 Write */
 #define SPRN_EPCR	0x133	/* Embedded Processor Control Register */
 #define SPRN_DBCR2	0x136	/* Debug Control Register 2 */
+#define SPRN_MSRP	0x137	/* MSR Protect Register */
 #define SPRN_IAC3	0x13A	/* Instruction Address Compare 3 */
 #define SPRN_IAC4	0x13B	/* Instruction Address Compare 4 */
 #define SPRN_DVC1	0x13E	/* Data Value Compare Register 1 */
 #define SPRN_DVC2	0x13F	/* Data Value Compare Register 2 */
+#define SPRN_LPID	0x152	/* Logical Partition ID */
 #define SPRN_MAS8	0x155	/* MMU Assist Register 8 */
 #define SPRN_TLB0PS	0x158	/* TLB 0 Page Size Register */
 #define SPRN_TLB1PS	0x159	/* TLB 1 Page Size Register */
 #define SPRN_MAS5_MAS6	0x15c	/* MMU Assist Register 5 || 6 */
 #define SPRN_MAS8_MAS1	0x15d	/* MMU Assist Register 8 || 1 */
 #define SPRN_EPTCFG	0x15e	/* Embedded Page Table Config */
+#define SPRN_GSPRG0	0x170	/* Guest SPRG0 */
+#define SPRN_GSPRG1	0x171	/* Guest SPRG1 */
+#define SPRN_GSPRG2	0x172	/* Guest SPRG2 */
+#define SPRN_GSPRG3	0x173	/* Guest SPRG3 */
 #define SPRN_MAS7_MAS3	0x174	/* MMU Assist Register 7 || 3 */
 #define SPRN_MAS0_MAS1	0x175	/* MMU Assist Register 0 || 1 */
+#define SPRN_GSRR0	0x17A	/* Guest SRR0 */
+#define SPRN_GSRR1	0x17B	/* Guest SRR1 */
+#define SPRN_GEPR	0x17C	/* Guest EPR */
+#define SPRN_GDEAR	0x17D	/* Guest DEAR */
+#define SPRN_GPIR	0x17E	/* Guest PIR */
+#define SPRN_GESR	0x17F	/* Guest Exception Syndrome Register */
 #define SPRN_IVOR0	0x190	/* Interrupt Vector Offset Register 0 */
 #define SPRN_IVOR1	0x191	/* Interrupt Vector Offset Register 1 */
 #define SPRN_IVOR2	0x192	/* Interrupt Vector Offset Register 2 */
@@ -88,6 +100,13 @@
 #define SPRN_IVOR39	0x1B1	/* Interrupt Vector Offset Register 39 */
 #define SPRN_IVOR40	0x1B2	/* Interrupt Vector Offset Register 40 */
 #define SPRN_IVOR41	0x1B3	/* Interrupt Vector Offset Register 41 */
+#define SPRN_GIVOR2	0x1B8	/* Guest IVOR2 */
+#define SPRN_GIVOR3	0x1B9	/* Guest IVOR3 */
+#define SPRN_GIVOR4	0x1BA	/* Guest IVOR4 */
+#define SPRN_GIVOR8	0x1BB	/* Guest IVOR8 */
+#define SPRN_GIVOR13	0x1BC	/* Guest IVOR13 */
+#define SPRN_GIVOR14	0x1BD	/* Guest IVOR14 */
+#define SPRN_GIVPR	0x1BF	/* Guest IVPR */
 #define SPRN_SPEFSCR	0x200	/* SPE & Embedded FP Status & Control */
 #define SPRN_BBEAR	0x201	/* Branch Buffer Entry Address Register */
 #define SPRN_BBTAR	0x202	/* Branch Buffer Target Address Register */
@@ -240,6 +259,10 @@
 #define MCSR_LDG	0x00002000UL /* Guarded Load */
 #define MCSR_TLBSYNC	0x00000002UL /* Multiple tlbsyncs detected */
 #define MCSR_BSL2_ERR	0x00000001UL /* Backside L2 cache error */
+
+#define MSRP_UCLEP	0x04000000 /* Protect MSR[UCLE] */
+#define MSRP_DEP	0x00000200 /* Protect MSR[DE] */
+#define MSRP_PMMP	0x00000004 /* Protect MSR[PMM] */
 #endif
 
 #ifdef CONFIG_E200
@@ -594,6 +617,17 @@
 #define SPRN_EPCR_DMIUH		0x00400000	/* Disable MAS Interrupt updates
 						 * for hypervisor */
 
+/* Bit definitions for EPLC/EPSC */
+#define EPC_EPR		0x80000000 /* 1 = user, 0 = kernel */
+#define EPC_EPR_SHIFT	31
+#define EPC_EAS		0x40000000 /* Address Space */
+#define EPC_EAS_SHIFT	30
+#define EPC_EGS		0x20000000 /* 1 = guest, 0 = hypervisor */
+#define EPC_EGS_SHIFT	29
+#define EPC_ELPID	0x00ff0000
+#define EPC_ELPID_SHIFT	16
+#define EPC_EPID	0x00003fff
+#define EPC_EPID_SHIFT	0
 
 /*
  * The IBM-403 is an even more odd special case, as it is much
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 1a6320290d26..200d763a0a67 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -17,6 +17,7 @@ extern struct task_struct *_switch(struct thread_struct *prev,
 				   struct thread_struct *next);
 
 extern void giveup_fpu(struct task_struct *);
+extern void load_up_fpu(void);
 extern void disable_kernel_fp(void);
 extern void enable_kernel_fp(void);
 extern void flush_fp_to_thread(struct task_struct *);
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 2136f58a54e8..3b4b4a8da922 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -23,6 +23,7 @@
 extern unsigned long tb_ticks_per_jiffy;
 extern unsigned long tb_ticks_per_usec;
 extern unsigned long tb_ticks_per_sec;
+extern struct clock_event_device decrementer_clockevent;
 
 struct rtc_time;
 extern void to_tm(int tim, struct rtc_time * tm);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4554dc2fe857..52c7ad78242e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -116,6 +116,9 @@ int main(void)
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
 #endif
+#ifdef CONFIG_KVM_BOOKE_HV
+	DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu));
+#endif
 
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
@@ -383,6 +386,7 @@ int main(void)
 #ifdef CONFIG_KVM
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
+	DEFINE(VCPU_GUEST_PID, offsetof(struct kvm_vcpu, arch.pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
 	DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
 	DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr));
@@ -425,9 +429,11 @@ int main(void)
 	DEFINE(VCPU_SHARED_MAS4, offsetof(struct kvm_vcpu_arch_shared, mas4));
 	DEFINE(VCPU_SHARED_MAS6, offsetof(struct kvm_vcpu_arch_shared, mas6));
 
+	DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
+	DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
+
 	/* book3s */
 #ifdef CONFIG_KVM_BOOK3S_64_HV
-	DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
 	DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
 	DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
 	DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
@@ -440,9 +446,9 @@ int main(void)
 	DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
 	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
 	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
+	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
 #endif
 #ifdef CONFIG_PPC_BOOK3S
-	DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
 	DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
 	DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
 	DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
@@ -457,7 +463,6 @@ int main(void)
 	DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions));
 	DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded));
 	DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded));
-	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
 	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
 	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
 	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
@@ -533,6 +538,8 @@ int main(void)
 	HSTATE_FIELD(HSTATE_NAPPING, napping);
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
+	HSTATE_FIELD(HSTATE_HWTHREAD_REQ, hwthread_req);
+	HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state);
 	HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
 	HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
 	HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
@@ -593,6 +600,12 @@ int main(void)
 	DEFINE(VCPU_HOST_SPEFSCR, offsetof(struct kvm_vcpu, arch.host_spefscr));
 #endif
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	DEFINE(VCPU_HOST_MAS4, offsetof(struct kvm_vcpu, arch.host_mas4));
+	DEFINE(VCPU_HOST_MAS6, offsetof(struct kvm_vcpu, arch.host_mas6));
+	DEFINE(VCPU_EPLC, offsetof(struct kvm_vcpu, arch.eplc));
+#endif
+
 #ifdef CONFIG_KVM_EXIT_TIMING
 	DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
 						arch.timing_exit.tv32.tbu));
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 8053db02b85e..69fdd2322a66 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -73,6 +73,7 @@ _GLOBAL(__setup_cpu_e500v2)
 	mtlr	r4
 	blr
 _GLOBAL(__setup_cpu_e500mc)
+	mr	r5, r4
 	mflr	r4
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f7bed44ee165..1c06d2971545 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -63,11 +63,13 @@ BEGIN_FTR_SECTION
 	GET_PACA(r13)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
-	lbz	r0,PACAPROCSTART(r13)
-	cmpwi	r0,0x80
-	bne	1f
-	li	r0,1
-	stb	r0,PACAPROCSTART(r13)
+	li	r0,KVM_HWTHREAD_IN_KERNEL
+	stb	r0,HSTATE_HWTHREAD_STATE(r13)
+	/* Order setting hwthread_state vs. testing hwthread_req */
+	sync
+	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
+	cmpwi	r0,0
+	beq	1f
 	b	kvm_start_guest
 1:
 #endif
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 22d608e8bb7d..7a2e5e421abf 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -248,10 +248,11 @@ _ENTRY(_start);
 
 interrupt_base:
 	/* Critical Input Interrupt */
-	CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception)
+	CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
 
 	/* Machine Check Interrupt */
-	CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+	CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \
+			   machine_check_exception)
 	MCHECK_EXCEPTION(0x0210, MachineCheckA, machine_check_exception)
 
 	/* Data Storage Interrupt */
@@ -261,7 +262,8 @@ interrupt_base:
 	INSTRUCTION_STORAGE_EXCEPTION
 
 	/* External Input Interrupt */
-	EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+	EXCEPTION(0x0500, BOOKE_INTERRUPT_EXTERNAL, ExternalInput, \
+		  do_IRQ, EXC_XFER_LITE)
 
 	/* Alignment Interrupt */
 	ALIGNMENT_EXCEPTION
@@ -273,29 +275,32 @@ interrupt_base:
 #ifdef CONFIG_PPC_FPU
 	FP_UNAVAILABLE_EXCEPTION
 #else
-	EXCEPTION(0x2010, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x2010, BOOKE_INTERRUPT_FP_UNAVAIL, \
+		  FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
 #endif
 	/* System Call Interrupt */
 	START_EXCEPTION(SystemCall)
-	NORMAL_EXCEPTION_PROLOG
+	NORMAL_EXCEPTION_PROLOG(BOOKE_INTERRUPT_SYSCALL)
 	EXC_XFER_EE_LITE(0x0c00, DoSyscall)
 
 	/* Auxiliary Processor Unavailable Interrupt */
-	EXCEPTION(0x2020, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x2020, BOOKE_INTERRUPT_AP_UNAVAIL, \
+		  AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
 
 	/* Decrementer Interrupt */
 	DECREMENTER_EXCEPTION
 
 	/* Fixed Internal Timer Interrupt */
 	/* TODO: Add FIT support */
-	EXCEPTION(0x1010, FixedIntervalTimer, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x1010, BOOKE_INTERRUPT_FIT, FixedIntervalTimer, \
+		  unknown_exception, EXC_XFER_EE)
 
 	/* Watchdog Timer Interrupt */
 	/* TODO: Add watchdog support */
 #ifdef CONFIG_BOOKE_WDT
-	CRITICAL_EXCEPTION(0x1020, WatchdogTimer, WatchdogException)
+	CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, WatchdogException)
 #else
-	CRITICAL_EXCEPTION(0x1020, WatchdogTimer, unknown_exception)
+	CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, unknown_exception)
 #endif
 
 	/* Data TLB Error Interrupt */
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 0e4175388f47..5f051eeb93a2 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -2,6 +2,9 @@
 #define __HEAD_BOOKE_H__
 
 #include <asm/ptrace.h>	/* for STACK_FRAME_REGS_MARKER */
+#include <asm/kvm_asm.h>
+#include <asm/kvm_booke_hv_asm.h>
+
 /*
  * Macros used for common Book-e exception handling
  */
@@ -28,14 +31,15 @@
  */
 #define THREAD_NORMSAVE(offset)	(THREAD_NORMSAVES + (offset * 4))
 
-#define NORMAL_EXCEPTION_PROLOG						     \
+#define NORMAL_EXCEPTION_PROLOG(intno)						     \
 	mtspr	SPRN_SPRG_WSCRATCH0, r10;	/* save one register */	     \
 	mfspr	r10, SPRN_SPRG_THREAD;					     \
 	stw	r11, THREAD_NORMSAVE(0)(r10);				     \
 	stw	r13, THREAD_NORMSAVE(2)(r10);				     \
 	mfcr	r13;			/* save CR in r13 for now	   */\
-	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel    */\
-	andi.	r11,r11,MSR_PR;						     \
+	mfspr	r11, SPRN_SRR1;		                                     \
+	DO_KVM	BOOKE_INTERRUPT_##intno SPRN_SRR1;			     \
+	andi.	r11, r11, MSR_PR;	/* check whether user or kernel    */\
 	mr	r11, r1;						     \
 	beq	1f;							     \
 	/* if from user, start at top of this thread's kernel stack */       \
@@ -113,7 +117,7 @@
  * registers as the normal prolog above. Instead we use a portion of the
  * critical/machine check exception stack at low physical addresses.
  */
-#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, exc_level_srr0, exc_level_srr1) \
+#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, intno, exc_level_srr0, exc_level_srr1) \
 	mtspr	SPRN_SPRG_WSCRATCH_##exc_level,r8;			     \
 	BOOKE_LOAD_EXC_LEVEL_STACK(exc_level);/* r8 points to the exc_level stack*/ \
 	stw	r9,GPR9(r8);		/* save various registers	   */\
@@ -121,8 +125,9 @@
 	stw	r10,GPR10(r8);						     \
 	stw	r11,GPR11(r8);						     \
 	stw	r9,_CCR(r8);		/* save CR on stack		   */\
-	mfspr	r10,exc_level_srr1;	/* check whether user or kernel    */\
-	andi.	r10,r10,MSR_PR;						     \
+	mfspr	r11,exc_level_srr1;	/* check whether user or kernel    */\
+	DO_KVM	BOOKE_INTERRUPT_##intno exc_level_srr1;		             \
+	andi.	r11,r11,MSR_PR;						     \
 	mfspr	r11,SPRN_SPRG_THREAD;	/* if from user, start at top of   */\
 	lwz	r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
 	addi	r11,r11,EXC_LVL_FRAME_OVERHEAD;	/* allocate stack frame    */\
@@ -162,12 +167,30 @@
 	SAVE_4GPRS(3, r11);						     \
 	SAVE_2GPRS(7, r11)
 
-#define CRITICAL_EXCEPTION_PROLOG \
-		EXC_LEVEL_EXCEPTION_PROLOG(CRIT, SPRN_CSRR0, SPRN_CSRR1)
+#define CRITICAL_EXCEPTION_PROLOG(intno) \
+		EXC_LEVEL_EXCEPTION_PROLOG(CRIT, intno, SPRN_CSRR0, SPRN_CSRR1)
 #define DEBUG_EXCEPTION_PROLOG \
-		EXC_LEVEL_EXCEPTION_PROLOG(DBG, SPRN_DSRR0, SPRN_DSRR1)
+		EXC_LEVEL_EXCEPTION_PROLOG(DBG, DEBUG, SPRN_DSRR0, SPRN_DSRR1)
 #define MCHECK_EXCEPTION_PROLOG \
-		EXC_LEVEL_EXCEPTION_PROLOG(MC, SPRN_MCSRR0, SPRN_MCSRR1)
+		EXC_LEVEL_EXCEPTION_PROLOG(MC, MACHINE_CHECK, \
+			SPRN_MCSRR0, SPRN_MCSRR1)
+
+/*
+ * Guest Doorbell -- this is a bit odd in that uses GSRR0/1 despite
+ * being delivered to the host.  This exception can only happen
+ * inside a KVM guest -- so we just handle up to the DO_KVM rather
+ * than try to fit this into one of the existing prolog macros.
+ */
+#define GUEST_DOORBELL_EXCEPTION \
+	START_EXCEPTION(GuestDoorbell);					     \
+	mtspr	SPRN_SPRG_WSCRATCH0, r10;	/* save one register */	     \
+	mfspr	r10, SPRN_SPRG_THREAD;					     \
+	stw	r11, THREAD_NORMSAVE(0)(r10);				     \
+	mfspr	r11, SPRN_SRR1;		                                     \
+	stw	r13, THREAD_NORMSAVE(2)(r10);				     \
+	mfcr	r13;			/* save CR in r13 for now	   */\
+	DO_KVM	BOOKE_INTERRUPT_GUEST_DBELL SPRN_GSRR1;			     \
+	trap
 
 /*
  * Exception vectors.
@@ -181,16 +204,16 @@ label:
 	.long	func;						\
 	.long	ret_from_except_full
 
-#define EXCEPTION(n, label, hdlr, xfer)				\
+#define EXCEPTION(n, intno, label, hdlr, xfer)			\
 	START_EXCEPTION(label);					\
-	NORMAL_EXCEPTION_PROLOG;				\
+	NORMAL_EXCEPTION_PROLOG(intno);				\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
 	xfer(n, hdlr)
 
-#define CRITICAL_EXCEPTION(n, label, hdlr)			\
-	START_EXCEPTION(label);					\
-	CRITICAL_EXCEPTION_PROLOG;				\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
+#define CRITICAL_EXCEPTION(n, intno, label, hdlr)			\
+	START_EXCEPTION(label);						\
+	CRITICAL_EXCEPTION_PROLOG(intno);				\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
 	EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
 			  NOCOPY, crit_transfer_to_handler, \
 			  ret_from_crit_exc)
@@ -302,7 +325,7 @@ label:
 
 #define DEBUG_CRIT_EXCEPTION						      \
 	START_EXCEPTION(DebugCrit);					      \
-	CRITICAL_EXCEPTION_PROLOG;					      \
+	CRITICAL_EXCEPTION_PROLOG(DEBUG);				      \
 									      \
 	/*								      \
 	 * If there is a single step or branch-taken exception in an	      \
@@ -355,7 +378,7 @@ label:
 
 #define DATA_STORAGE_EXCEPTION						      \
 	START_EXCEPTION(DataStorage)					      \
-	NORMAL_EXCEPTION_PROLOG;					      \
+	NORMAL_EXCEPTION_PROLOG(DATA_STORAGE);		      \
 	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
 	stw	r5,_ESR(r11);						      \
 	mfspr	r4,SPRN_DEAR;		/* Grab the DEAR */		      \
@@ -363,7 +386,7 @@ label:
 
 #define INSTRUCTION_STORAGE_EXCEPTION					      \
 	START_EXCEPTION(InstructionStorage)				      \
-	NORMAL_EXCEPTION_PROLOG;					      \
+	NORMAL_EXCEPTION_PROLOG(INST_STORAGE);		      \
 	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
 	stw	r5,_ESR(r11);						      \
 	mr      r4,r12;                 /* Pass SRR0 as arg2 */		      \
@@ -372,7 +395,7 @@ label:
 
 #define ALIGNMENT_EXCEPTION						      \
 	START_EXCEPTION(Alignment)					      \
-	NORMAL_EXCEPTION_PROLOG;					      \
+	NORMAL_EXCEPTION_PROLOG(ALIGNMENT);		      \
 	mfspr   r4,SPRN_DEAR;           /* Grab the DEAR and save it */	      \
 	stw     r4,_DEAR(r11);						      \
 	addi    r3,r1,STACK_FRAME_OVERHEAD;				      \
@@ -380,7 +403,7 @@ label:
 
 #define PROGRAM_EXCEPTION						      \
 	START_EXCEPTION(Program)					      \
-	NORMAL_EXCEPTION_PROLOG;					      \
+	NORMAL_EXCEPTION_PROLOG(PROGRAM);		      \
 	mfspr	r4,SPRN_ESR;		/* Grab the ESR and save it */	      \
 	stw	r4,_ESR(r11);						      \
 	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
@@ -388,7 +411,7 @@ label:
 
 #define DECREMENTER_EXCEPTION						      \
 	START_EXCEPTION(Decrementer)					      \
-	NORMAL_EXCEPTION_PROLOG;					      \
+	NORMAL_EXCEPTION_PROLOG(DECREMENTER);		      \
 	lis     r0,TSR_DIS@h;           /* Setup the DEC interrupt mask */    \
 	mtspr   SPRN_TSR,r0;		/* Clear the DEC interrupt */	      \
 	addi    r3,r1,STACK_FRAME_OVERHEAD;				      \
@@ -396,7 +419,7 @@ label:
 
 #define FP_UNAVAILABLE_EXCEPTION					      \
 	START_EXCEPTION(FloatingPointUnavailable)			      \
-	NORMAL_EXCEPTION_PROLOG;					      \
+	NORMAL_EXCEPTION_PROLOG(FP_UNAVAIL);		      \
 	beq	1f;							      \
 	bl	load_up_fpu;		/* if from user, just load it up */   \
 	b	fast_exception_return;					      \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index de80e0f9a2bd..1f4434a38608 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -301,19 +301,20 @@ _ENTRY(__early_start)
 
 interrupt_base:
 	/* Critical Input Interrupt */
-	CRITICAL_EXCEPTION(0x0100, CriticalInput, unknown_exception)
+	CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
 
 	/* Machine Check Interrupt */
 #ifdef CONFIG_E200
 	/* no RFMCI, MCSRRs on E200 */
-	CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+	CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \
+			   machine_check_exception)
 #else
 	MCHECK_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
 #endif
 
 	/* Data Storage Interrupt */
 	START_EXCEPTION(DataStorage)
-	NORMAL_EXCEPTION_PROLOG
+	NORMAL_EXCEPTION_PROLOG(DATA_STORAGE)
 	mfspr	r5,SPRN_ESR		/* Grab the ESR, save it, pass arg3 */
 	stw	r5,_ESR(r11)
 	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
@@ -328,7 +329,7 @@ interrupt_base:
 	INSTRUCTION_STORAGE_EXCEPTION
 
 	/* External Input Interrupt */
-	EXCEPTION(0x0500, ExternalInput, do_IRQ, EXC_XFER_LITE)
+	EXCEPTION(0x0500, EXTERNAL, ExternalInput, do_IRQ, EXC_XFER_LITE)
 
 	/* Alignment Interrupt */
 	ALIGNMENT_EXCEPTION
@@ -342,32 +343,36 @@ interrupt_base:
 #else
 #ifdef CONFIG_E200
 	/* E200 treats 'normal' floating point instructions as FP Unavail exception */
-	EXCEPTION(0x0800, FloatingPointUnavailable, program_check_exception, EXC_XFER_EE)
+	EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
+		  program_check_exception, EXC_XFER_EE)
 #else
-	EXCEPTION(0x0800, FloatingPointUnavailable, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, \
+		  unknown_exception, EXC_XFER_EE)
 #endif
 #endif
 
 	/* System Call Interrupt */
 	START_EXCEPTION(SystemCall)
-	NORMAL_EXCEPTION_PROLOG
+	NORMAL_EXCEPTION_PROLOG(SYSCALL)
 	EXC_XFER_EE_LITE(0x0c00, DoSyscall)
 
 	/* Auxiliary Processor Unavailable Interrupt */
-	EXCEPTION(0x2900, AuxillaryProcessorUnavailable, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x2900, AP_UNAVAIL, AuxillaryProcessorUnavailable, \
+		  unknown_exception, EXC_XFER_EE)
 
 	/* Decrementer Interrupt */
 	DECREMENTER_EXCEPTION
 
 	/* Fixed Internal Timer Interrupt */
 	/* TODO: Add FIT support */
-	EXCEPTION(0x3100, FixedIntervalTimer, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x3100, FIT, FixedIntervalTimer, \
+		  unknown_exception, EXC_XFER_EE)
 
 	/* Watchdog Timer Interrupt */
 #ifdef CONFIG_BOOKE_WDT
-	CRITICAL_EXCEPTION(0x3200, WatchdogTimer, WatchdogException)
+	CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, WatchdogException)
 #else
-	CRITICAL_EXCEPTION(0x3200, WatchdogTimer, unknown_exception)
+	CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, unknown_exception)
 #endif
 
 	/* Data TLB Error Interrupt */
@@ -375,10 +380,16 @@ interrupt_base:
 	mtspr	SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
 	mfspr	r10, SPRN_SPRG_THREAD
 	stw	r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+	mfspr	r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
 	stw	r12, THREAD_NORMSAVE(1)(r10)
 	stw	r13, THREAD_NORMSAVE(2)(r10)
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
+	DO_KVM	BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1
 	mfspr	r10, SPRN_DEAR		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -463,10 +474,16 @@ interrupt_base:
 	mtspr	SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
 	mfspr	r10, SPRN_SPRG_THREAD
 	stw	r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+	mfspr	r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
 	stw	r12, THREAD_NORMSAVE(1)(r10)
 	stw	r13, THREAD_NORMSAVE(2)(r10)
 	mfcr	r13
 	stw	r13, THREAD_NORMSAVE(3)(r10)
+	DO_KVM	BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1
 	mfspr	r10, SPRN_SRR0		/* Get faulting address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -538,36 +555,54 @@ interrupt_base:
 #ifdef CONFIG_SPE
 	/* SPE Unavailable */
 	START_EXCEPTION(SPEUnavailable)
-	NORMAL_EXCEPTION_PROLOG
+	NORMAL_EXCEPTION_PROLOG(SPE_UNAVAIL)
 	bne	load_up_spe
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_EE_LITE(0x2010, KernelSPE)
 #else
-	EXCEPTION(0x2020, SPEUnavailable, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, \
+		  unknown_exception, EXC_XFER_EE)
 #endif /* CONFIG_SPE */
 
 	/* SPE Floating Point Data */
 #ifdef CONFIG_SPE
-	EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE);
+	EXCEPTION(0x2030, SPE_FP_DATA, SPEFloatingPointData, \
+		  SPEFloatingPointException, EXC_XFER_EE);
 
 	/* SPE Floating Point Round */
-	EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE)
+	EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
+		  SPEFloatingPointRoundException, EXC_XFER_EE)
 #else
-	EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
-	EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x2040, SPE_FP_DATA, SPEFloatingPointData, \
+		  unknown_exception, EXC_XFER_EE)
+	EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, \
+		  unknown_exception, EXC_XFER_EE)
 #endif /* CONFIG_SPE */
 
 	/* Performance Monitor */
-	EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD)
+	EXCEPTION(0x2060, PERFORMANCE_MONITOR, PerformanceMonitor, \
+		  performance_monitor_exception, EXC_XFER_STD)
 
-	EXCEPTION(0x2070, Doorbell, doorbell_exception, EXC_XFER_STD)
+	EXCEPTION(0x2070, DOORBELL, Doorbell, doorbell_exception, EXC_XFER_STD)
 
-	CRITICAL_EXCEPTION(0x2080, CriticalDoorbell, unknown_exception)
+	CRITICAL_EXCEPTION(0x2080, DOORBELL_CRITICAL, \
+			   CriticalDoorbell, unknown_exception)
 
 	/* Debug Interrupt */
 	DEBUG_DEBUG_EXCEPTION
 	DEBUG_CRIT_EXCEPTION
 
+	GUEST_DOORBELL_EXCEPTION
+
+	CRITICAL_EXCEPTION(0, GUEST_DBELL_CRIT, CriticalGuestDoorbell, \
+			   unknown_exception)
+
+	/* Hypercall */
+	EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception, EXC_XFER_EE)
+
+	/* Embedded Hypervisor Privilege */
+	EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception, EXC_XFER_EE)
+
 /*
  * Local functions
  */
@@ -871,8 +906,31 @@ _GLOBAL(__setup_e500mc_ivors)
 	mtspr	SPRN_IVOR36,r3
 	li	r3,CriticalDoorbell@l
 	mtspr	SPRN_IVOR37,r3
+
+	/*
+	 * We only want to touch IVOR38-41 if we're running on hardware
+	 * that supports category E.HV.  The architectural way to determine
+	 * this is MMUCFG[LPIDSIZE].
+	 */
+	mfspr	r3, SPRN_MMUCFG
+	andis.	r3, r3, MMUCFG_LPIDSIZE@h
+	beq	no_hv
+	li	r3,GuestDoorbell@l
+	mtspr	SPRN_IVOR38,r3
+	li	r3,CriticalGuestDoorbell@l
+	mtspr	SPRN_IVOR39,r3
+	li	r3,Hypercall@l
+	mtspr	SPRN_IVOR40,r3
+	li	r3,Ehvpriv@l
+	mtspr	SPRN_IVOR41,r3
+skip_hv_ivors:
 	sync
 	blr
+no_hv:
+	lwz	r3, CPU_SPEC_FEATURES(r5)
+	rlwinm	r3, r3, 0, ~CPU_FTR_EMB_HV
+	stw	r3, CPU_SPEC_FEATURES(r5)
+	b	skip_hv_ivors
 
 #ifdef CONFIG_SPE
 /*
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 0cdc9a392839..7140d838339e 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -16,6 +16,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
 #include <asm/hw_irq.h>
+#include <asm/kvm_book3s_asm.h>
 
 #undef DEBUG
 
@@ -81,6 +82,12 @@ _GLOBAL(power7_idle)
 	std	r9,_MSR(r1)
 	std	r1,PACAR1(r13)
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	/* Tell KVM we're napping */
+	li	r4,KVM_HWTHREAD_IN_NAP
+	stb	r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
+
 	/* Magic NAP mode enter sequence */
 	std	r0,0(r1)
 	ptesync
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 786a2700ec2d..d1f2aafcbe8c 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -190,3 +190,7 @@ EXPORT_SYMBOL(__arch_hweight16);
 EXPORT_SYMBOL(__arch_hweight32);
 EXPORT_SYMBOL(__arch_hweight64);
 #endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+EXPORT_SYMBOL_GPL(mmu_psize_defs);
+#endif
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2c42cd72d0f5..99a995c2a3f2 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -100,7 +100,7 @@ static int decrementer_set_next_event(unsigned long evt,
 static void decrementer_set_mode(enum clock_event_mode mode,
 				 struct clock_event_device *dev);
 
-static struct clock_event_device decrementer_clockevent = {
+struct clock_event_device decrementer_clockevent = {
 	.name           = "decrementer",
 	.rating         = 200,
 	.irq            = 0,
@@ -108,6 +108,7 @@ static struct clock_event_device decrementer_clockevent = {
 	.set_mode       = decrementer_set_mode,
 	.features       = CLOCK_EVT_FEAT_ONESHOT,
 };
+EXPORT_SYMBOL(decrementer_clockevent);
 
 DEFINE_PER_CPU(u64, decrementers_next_tb);
 static DEFINE_PER_CPU(struct clock_event_device, decrementers);
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 7b612a76c701..50e7dbc7356c 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -29,15 +29,18 @@
 #include <asm/kvm_ppc.h>
 
 #include "44x_tlb.h"
+#include "booke.h"
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	kvmppc_booke_vcpu_load(vcpu, cpu);
 	kvmppc_44x_tlb_load(vcpu);
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvmppc_44x_tlb_put(vcpu);
+	kvmppc_booke_vcpu_put(vcpu);
 }
 
 int kvmppc_core_check_processor_compat(void)
@@ -160,6 +163,15 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
 
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	return 0;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+}
+
 static int __init kvmppc_44x_init(void)
 {
 	int r;
diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c
index 549bb2c9a47a..c8c61578fdfc 100644
--- a/arch/powerpc/kvm/44x_emulate.c
+++ b/arch/powerpc/kvm/44x_emulate.c
@@ -37,22 +37,19 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
-	int dcrn;
-	int ra;
-	int rb;
-	int rc;
-	int rs;
-	int rt;
-	int ws;
+	int dcrn = get_dcrn(inst);
+	int ra = get_ra(inst);
+	int rb = get_rb(inst);
+	int rc = get_rc(inst);
+	int rs = get_rs(inst);
+	int rt = get_rt(inst);
+	int ws = get_ws(inst);
 
 	switch (get_op(inst)) {
 	case 31:
 		switch (get_xop(inst)) {
 
 		case XOP_MFDCR:
-			dcrn = get_dcrn(inst);
-			rt = get_rt(inst);
-
 			/* The guest may access CPR0 registers to determine the timebase
 			 * frequency, and it must know the real host frequency because it
 			 * can directly access the timebase registers.
@@ -88,9 +85,6 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 
 		case XOP_MTDCR:
-			dcrn = get_dcrn(inst);
-			rs = get_rs(inst);
-
 			/* emulate some access in kernel */
 			switch (dcrn) {
 			case DCRN_CPR0_CONFIG_ADDR:
@@ -108,17 +102,10 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 
 		case XOP_TLBWE:
-			ra = get_ra(inst);
-			rs = get_rs(inst);
-			ws = get_ws(inst);
 			emulated = kvmppc_44x_emul_tlbwe(vcpu, ra, rs, ws);
 			break;
 
 		case XOP_TLBSX:
-			rt = get_rt(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-			rc = get_rc(inst);
 			emulated = kvmppc_44x_emul_tlbsx(vcpu, rt, ra, rb, rc);
 			break;
 
@@ -141,41 +128,41 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
 	case SPRN_PID:
-		kvmppc_set_pid(vcpu, kvmppc_get_gpr(vcpu, rs)); break;
+		kvmppc_set_pid(vcpu, spr_val); break;
 	case SPRN_MMUCR:
-		vcpu->arch.mmucr = kvmppc_get_gpr(vcpu, rs); break;
+		vcpu->arch.mmucr = spr_val; break;
 	case SPRN_CCR0:
-		vcpu->arch.ccr0 = kvmppc_get_gpr(vcpu, rs); break;
+		vcpu->arch.ccr0 = spr_val; break;
 	case SPRN_CCR1:
-		vcpu->arch.ccr1 = kvmppc_get_gpr(vcpu, rs); break;
+		vcpu->arch.ccr1 = spr_val; break;
 	default:
-		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
+		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
 	case SPRN_PID:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.pid); break;
+		*spr_val = vcpu->arch.pid; break;
 	case SPRN_MMUCR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucr); break;
+		*spr_val = vcpu->arch.mmucr; break;
 	case SPRN_CCR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr0); break;
+		*spr_val = vcpu->arch.ccr0; break;
 	case SPRN_CCR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr1); break;
+		*spr_val = vcpu->arch.ccr1; break;
 	default:
-		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
+		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 8f64709ae331..f4dacb9c57fa 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -90,6 +90,9 @@ config KVM_BOOK3S_64_PR
 	depends on KVM_BOOK3S_64 && !KVM_BOOK3S_64_HV
 	select KVM_BOOK3S_PR
 
+config KVM_BOOKE_HV
+	bool
+
 config KVM_440
 	bool "KVM support for PowerPC 440 processors"
 	depends on EXPERIMENTAL && 44x
@@ -106,7 +109,7 @@ config KVM_440
 
 config KVM_EXIT_TIMING
 	bool "Detailed exit timing"
-	depends on KVM_440 || KVM_E500
+	depends on KVM_440 || KVM_E500V2 || KVM_E500MC
 	---help---
 	  Calculate elapsed time for every exit/enter cycle. A per-vcpu
 	  report is available in debugfs kvm/vm#_vcpu#_timing.
@@ -115,14 +118,29 @@ config KVM_EXIT_TIMING
 
 	  If unsure, say N.
 
-config KVM_E500
-	bool "KVM support for PowerPC E500 processors"
-	depends on EXPERIMENTAL && E500
+config KVM_E500V2
+	bool "KVM support for PowerPC E500v2 processors"
+	depends on EXPERIMENTAL && E500 && !PPC_E500MC
 	select KVM
 	select KVM_MMIO
 	---help---
 	  Support running unmodified E500 guest kernels in virtual machines on
-	  E500 host processors.
+	  E500v2 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_E500MC
+	bool "KVM support for PowerPC E500MC/E5500 processors"
+	depends on EXPERIMENTAL && PPC_E500MC
+	select KVM
+	select KVM_MMIO
+	select KVM_BOOKE_HV
+	---help---
+	  Support running unmodified E500MC/E5500 (32-bit) guest kernels in
+	  virtual machines on E500MC/E5500 host processors.
 
 	  This module provides access to the hardware capabilities through
 	  a character device node named /dev/kvm.
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 3688aeecc4b2..c2a08636e6d4 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -36,7 +36,17 @@ kvm-e500-objs := \
 	e500.o \
 	e500_tlb.o \
 	e500_emulate.o
-kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs)
+kvm-objs-$(CONFIG_KVM_E500V2) := $(kvm-e500-objs)
+
+kvm-e500mc-objs := \
+	$(common-objs-y) \
+	booke.o \
+	booke_emulate.o \
+	bookehv_interrupts.o \
+	e500mc.o \
+	e500_tlb.o \
+	e500_emulate.o
+kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 
 kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
 	../../../virt/kvm/coalesced_mmio.o \
@@ -44,6 +54,7 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
 	book3s_paired_singles.o \
 	book3s_pr.o \
 	book3s_pr_papr.o \
+	book3s_64_vio_hv.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
 	book3s_mmu_hpte.o \
@@ -68,6 +79,7 @@ kvm-book3s_64-module-objs := \
 	powerpc.o \
 	emulate.o \
 	book3s.o \
+	book3s_64_vio.o \
 	$(kvm-book3s_64-objs-y)
 
 kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs)
@@ -88,7 +100,8 @@ kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs)
 kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
 
 obj-$(CONFIG_KVM_440) += kvm.o
-obj-$(CONFIG_KVM_E500) += kvm.o
+obj-$(CONFIG_KVM_E500V2) += kvm.o
+obj-$(CONFIG_KVM_E500MC) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
 obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 7d54f4ed6d96..3f2a8360c857 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -258,7 +258,7 @@ static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority)
 	return true;
 }
 
-void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
+int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 {
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
 	unsigned long old_pending = vcpu->arch.pending_exceptions;
@@ -283,12 +283,17 @@ void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	/* Tell the guest about our interrupt status */
 	kvmppc_update_int_pending(vcpu, *pending, old_pending);
+
+	return 0;
 }
 
 pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa;
 
+	if (!(vcpu->arch.shared->msr & MSR_SF))
+		mp_pa = (uint32_t)mp_pa;
+
 	/* Magic page override */
 	if (unlikely(mp_pa) &&
 	    unlikely(((gfn << PAGE_SHIFT) & KVM_PAM) ==
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index c3beaeef3f60..80a577517584 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -36,13 +36,11 @@
 
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
-#define NR_LPIDS	(LPID_RSVD + 1)
-unsigned long lpid_inuse[BITS_TO_LONGS(NR_LPIDS)];
 
 long kvmppc_alloc_hpt(struct kvm *kvm)
 {
 	unsigned long hpt;
-	unsigned long lpid;
+	long lpid;
 	struct revmap_entry *rev;
 	struct kvmppc_linear_info *li;
 
@@ -72,14 +70,9 @@ long kvmppc_alloc_hpt(struct kvm *kvm)
 	}
 	kvm->arch.revmap = rev;
 
-	/* Allocate the guest's logical partition ID */
-	do {
-		lpid = find_first_zero_bit(lpid_inuse, NR_LPIDS);
-		if (lpid >= NR_LPIDS) {
-			pr_err("kvm_alloc_hpt: No LPIDs free\n");
-			goto out_freeboth;
-		}
-	} while (test_and_set_bit(lpid, lpid_inuse));
+	lpid = kvmppc_alloc_lpid();
+	if (lpid < 0)
+		goto out_freeboth;
 
 	kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18);
 	kvm->arch.lpid = lpid;
@@ -96,7 +89,7 @@ long kvmppc_alloc_hpt(struct kvm *kvm)
 
 void kvmppc_free_hpt(struct kvm *kvm)
 {
-	clear_bit(kvm->arch.lpid, lpid_inuse);
+	kvmppc_free_lpid(kvm->arch.lpid);
 	vfree(kvm->arch.revmap);
 	if (kvm->arch.hpt_li)
 		kvm_release_hpt(kvm->arch.hpt_li);
@@ -171,8 +164,7 @@ int kvmppc_mmu_hv_init(void)
 	if (!cpu_has_feature(CPU_FTR_HVMODE))
 		return -EINVAL;
 
-	memset(lpid_inuse, 0, sizeof(lpid_inuse));
-
+	/* POWER7 has 10-bit LPIDs, PPC970 and e500mc have 6-bit LPIDs */
 	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
 		host_lpid = mfspr(SPRN_LPID);	/* POWER7 */
 		rsvd_lpid = LPID_RSVD;
@@ -181,9 +173,11 @@ int kvmppc_mmu_hv_init(void)
 		rsvd_lpid = MAX_LPID_970;
 	}
 
-	set_bit(host_lpid, lpid_inuse);
+	kvmppc_init_lpid(rsvd_lpid + 1);
+
+	kvmppc_claim_lpid(host_lpid);
 	/* rsvd_lpid is reserved for use in partition switching */
-	set_bit(rsvd_lpid, lpid_inuse);
+	kvmppc_claim_lpid(rsvd_lpid);
 
 	return 0;
 }
@@ -452,7 +446,7 @@ static int instruction_is_store(unsigned int instr)
 }
 
 static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
-				  unsigned long gpa, int is_store)
+				  unsigned long gpa, gva_t ea, int is_store)
 {
 	int ret;
 	u32 last_inst;
@@ -499,6 +493,7 @@ static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 
 	vcpu->arch.paddr_accessed = gpa;
+	vcpu->arch.vaddr_accessed = ea;
 	return kvmppc_emulate_mmio(run, vcpu);
 }
 
@@ -552,7 +547,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* No memslot means it's an emulated MMIO region */
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
 		unsigned long gpa = (gfn << PAGE_SHIFT) | (ea & (psize - 1));
-		return kvmppc_hv_emulate_mmio(run, vcpu, gpa,
+		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
 					      dsisr & DSISR_ISSTORE);
 	}
 
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index f2e6e48ea463..56b983e7b738 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -90,8 +90,6 @@ slb_exit_skip_ ## num:
 	or      r10, r10, r12
 	slbie	r10
 
-	isync
-
 	/* Fill SLB with our shadow */
 
 	lbz	r12, SVCPU_SLB_MAX(r3)
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
new file mode 100644
index 000000000000..72ffc899c082
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -0,0 +1,150 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
+#include <linux/list.h>
+#include <linux/anon_inodes.h>
+
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu-hash64.h>
+#include <asm/hvcall.h>
+#include <asm/synch.h>
+#include <asm/ppc-opcode.h>
+#include <asm/kvm_host.h>
+#include <asm/udbg.h>
+
+#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+
+static long kvmppc_stt_npages(unsigned long window_size)
+{
+	return ALIGN((window_size >> SPAPR_TCE_SHIFT)
+		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
+}
+
+static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
+{
+	struct kvm *kvm = stt->kvm;
+	int i;
+
+	mutex_lock(&kvm->lock);
+	list_del(&stt->list);
+	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
+		__free_page(stt->pages[i]);
+	kfree(stt);
+	mutex_unlock(&kvm->lock);
+
+	kvm_put_kvm(kvm);
+}
+
+static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
+	struct page *page;
+
+	if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
+		return VM_FAULT_SIGBUS;
+
+	page = stt->pages[vmf->pgoff];
+	get_page(page);
+	vmf->page = page;
+	return 0;
+}
+
+static const struct vm_operations_struct kvm_spapr_tce_vm_ops = {
+	.fault = kvm_spapr_tce_fault,
+};
+
+static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	vma->vm_ops = &kvm_spapr_tce_vm_ops;
+	return 0;
+}
+
+static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
+{
+	struct kvmppc_spapr_tce_table *stt = filp->private_data;
+
+	release_spapr_tce_table(stt);
+	return 0;
+}
+
+static struct file_operations kvm_spapr_tce_fops = {
+	.mmap           = kvm_spapr_tce_mmap,
+	.release	= kvm_spapr_tce_release,
+};
+
+long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
+				   struct kvm_create_spapr_tce *args)
+{
+	struct kvmppc_spapr_tce_table *stt = NULL;
+	long npages;
+	int ret = -ENOMEM;
+	int i;
+
+	/* Check this LIOBN hasn't been previously allocated */
+	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt->liobn == args->liobn)
+			return -EBUSY;
+	}
+
+	npages = kvmppc_stt_npages(args->window_size);
+
+	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
+		      GFP_KERNEL);
+	if (!stt)
+		goto fail;
+
+	stt->liobn = args->liobn;
+	stt->window_size = args->window_size;
+	stt->kvm = kvm;
+
+	for (i = 0; i < npages; i++) {
+		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!stt->pages[i])
+			goto fail;
+	}
+
+	kvm_get_kvm(kvm);
+
+	mutex_lock(&kvm->lock);
+	list_add(&stt->list, &kvm->arch.spapr_tce_tables);
+
+	mutex_unlock(&kvm->lock);
+
+	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+				stt, O_RDWR);
+
+fail:
+	if (stt) {
+		for (i = 0; i < npages; i++)
+			if (stt->pages[i])
+				__free_page(stt->pages[i]);
+
+		kfree(stt);
+	}
+	return ret;
+}
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index ea0f8c537c28..30c2f3b134c6 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -38,6 +38,9 @@
 
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
 
+/* WARNING: This will be called in real-mode on HV KVM and virtual
+ *          mode on PR KVM
+ */
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 135663a3e4fc..b9a989dc76cc 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -87,6 +87,10 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
+	int rt = get_rt(inst);
+	int rs = get_rs(inst);
+	int ra = get_ra(inst);
+	int rb = get_rb(inst);
 
 	switch (get_op(inst)) {
 	case 19:
@@ -106,21 +110,22 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case 31:
 		switch (get_xop(inst)) {
 		case OP_31_XOP_MFMSR:
-			kvmppc_set_gpr(vcpu, get_rt(inst),
-				       vcpu->arch.shared->msr);
+			kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->msr);
 			break;
 		case OP_31_XOP_MTMSRD:
 		{
-			ulong rs = kvmppc_get_gpr(vcpu, get_rs(inst));
+			ulong rs_val = kvmppc_get_gpr(vcpu, rs);
 			if (inst & 0x10000) {
-				vcpu->arch.shared->msr &= ~(MSR_RI | MSR_EE);
-				vcpu->arch.shared->msr |= rs & (MSR_RI | MSR_EE);
+				ulong new_msr = vcpu->arch.shared->msr;
+				new_msr &= ~(MSR_RI | MSR_EE);
+				new_msr |= rs_val & (MSR_RI | MSR_EE);
+				vcpu->arch.shared->msr = new_msr;
 			} else
-				kvmppc_set_msr(vcpu, rs);
+				kvmppc_set_msr(vcpu, rs_val);
 			break;
 		}
 		case OP_31_XOP_MTMSR:
-			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst)));
+			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, rs));
 			break;
 		case OP_31_XOP_MFSR:
 		{
@@ -130,7 +135,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			if (vcpu->arch.mmu.mfsrin) {
 				u32 sr;
 				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
-				kvmppc_set_gpr(vcpu, get_rt(inst), sr);
+				kvmppc_set_gpr(vcpu, rt, sr);
 			}
 			break;
 		}
@@ -138,29 +143,29 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		{
 			int srnum;
 
-			srnum = (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf;
+			srnum = (kvmppc_get_gpr(vcpu, rb) >> 28) & 0xf;
 			if (vcpu->arch.mmu.mfsrin) {
 				u32 sr;
 				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
-				kvmppc_set_gpr(vcpu, get_rt(inst), sr);
+				kvmppc_set_gpr(vcpu, rt, sr);
 			}
 			break;
 		}
 		case OP_31_XOP_MTSR:
 			vcpu->arch.mmu.mtsrin(vcpu,
 				(inst >> 16) & 0xf,
-				kvmppc_get_gpr(vcpu, get_rs(inst)));
+				kvmppc_get_gpr(vcpu, rs));
 			break;
 		case OP_31_XOP_MTSRIN:
 			vcpu->arch.mmu.mtsrin(vcpu,
-				(kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf,
-				kvmppc_get_gpr(vcpu, get_rs(inst)));
+				(kvmppc_get_gpr(vcpu, rb) >> 28) & 0xf,
+				kvmppc_get_gpr(vcpu, rs));
 			break;
 		case OP_31_XOP_TLBIE:
 		case OP_31_XOP_TLBIEL:
 		{
 			bool large = (inst & 0x00200000) ? true : false;
-			ulong addr = kvmppc_get_gpr(vcpu, get_rb(inst));
+			ulong addr = kvmppc_get_gpr(vcpu, rb);
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
@@ -171,15 +176,15 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				return EMULATE_FAIL;
 
 			vcpu->arch.mmu.slbmte(vcpu,
-					kvmppc_get_gpr(vcpu, get_rs(inst)),
-					kvmppc_get_gpr(vcpu, get_rb(inst)));
+					kvmppc_get_gpr(vcpu, rs),
+					kvmppc_get_gpr(vcpu, rb));
 			break;
 		case OP_31_XOP_SLBIE:
 			if (!vcpu->arch.mmu.slbie)
 				return EMULATE_FAIL;
 
 			vcpu->arch.mmu.slbie(vcpu,
-					kvmppc_get_gpr(vcpu, get_rb(inst)));
+					kvmppc_get_gpr(vcpu, rb));
 			break;
 		case OP_31_XOP_SLBIA:
 			if (!vcpu->arch.mmu.slbia)
@@ -191,22 +196,22 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			if (!vcpu->arch.mmu.slbmfee) {
 				emulated = EMULATE_FAIL;
 			} else {
-				ulong t, rb;
+				ulong t, rb_val;
 
-				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
-				t = vcpu->arch.mmu.slbmfee(vcpu, rb);
-				kvmppc_set_gpr(vcpu, get_rt(inst), t);
+				rb_val = kvmppc_get_gpr(vcpu, rb);
+				t = vcpu->arch.mmu.slbmfee(vcpu, rb_val);
+				kvmppc_set_gpr(vcpu, rt, t);
 			}
 			break;
 		case OP_31_XOP_SLBMFEV:
 			if (!vcpu->arch.mmu.slbmfev) {
 				emulated = EMULATE_FAIL;
 			} else {
-				ulong t, rb;
+				ulong t, rb_val;
 
-				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
-				t = vcpu->arch.mmu.slbmfev(vcpu, rb);
-				kvmppc_set_gpr(vcpu, get_rt(inst), t);
+				rb_val = kvmppc_get_gpr(vcpu, rb);
+				t = vcpu->arch.mmu.slbmfev(vcpu, rb_val);
+				kvmppc_set_gpr(vcpu, rt, t);
 			}
 			break;
 		case OP_31_XOP_DCBA:
@@ -214,17 +219,17 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 		case OP_31_XOP_DCBZ:
 		{
-			ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst));
-			ulong ra = 0;
+			ulong rb_val = kvmppc_get_gpr(vcpu, rb);
+			ulong ra_val = 0;
 			ulong addr, vaddr;
 			u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };
 			u32 dsisr;
 			int r;
 
-			if (get_ra(inst))
-				ra = kvmppc_get_gpr(vcpu, get_ra(inst));
+			if (ra)
+				ra_val = kvmppc_get_gpr(vcpu, ra);
 
-			addr = (ra + rb) & ~31ULL;
+			addr = (ra_val + rb_val) & ~31ULL;
 			if (!(vcpu->arch.shared->msr & MSR_SF))
 				addr &= 0xffffffff;
 			vaddr = addr;
@@ -313,10 +318,9 @@ static struct kvmppc_bat *kvmppc_find_bat(struct kvm_vcpu *vcpu, int sprn)
 	return bat;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
-	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_SDR1:
@@ -428,7 +432,7 @@ unprivileged:
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
@@ -441,46 +445,46 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		struct kvmppc_bat *bat = kvmppc_find_bat(vcpu, sprn);
 
 		if (sprn % 2)
-			kvmppc_set_gpr(vcpu, rt, bat->raw >> 32);
+			*spr_val = bat->raw >> 32;
 		else
-			kvmppc_set_gpr(vcpu, rt, bat->raw);
+			*spr_val = bat->raw;
 
 		break;
 	}
 	case SPRN_SDR1:
 		if (!spr_allowed(vcpu, PRIV_HYPER))
 			goto unprivileged;
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
+		*spr_val = to_book3s(vcpu)->sdr1;
 		break;
 	case SPRN_DSISR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dsisr);
+		*spr_val = vcpu->arch.shared->dsisr;
 		break;
 	case SPRN_DAR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar);
+		*spr_val = vcpu->arch.shared->dar;
 		break;
 	case SPRN_HIOR:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hior);
+		*spr_val = to_book3s(vcpu)->hior;
 		break;
 	case SPRN_HID0:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[0]);
+		*spr_val = to_book3s(vcpu)->hid[0];
 		break;
 	case SPRN_HID1:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]);
+		*spr_val = to_book3s(vcpu)->hid[1];
 		break;
 	case SPRN_HID2:
 	case SPRN_HID2_GEKKO:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]);
+		*spr_val = to_book3s(vcpu)->hid[2];
 		break;
 	case SPRN_HID4:
 	case SPRN_HID4_GEKKO:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]);
+		*spr_val = to_book3s(vcpu)->hid[4];
 		break;
 	case SPRN_HID5:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]);
+		*spr_val = to_book3s(vcpu)->hid[5];
 		break;
 	case SPRN_CFAR:
 	case SPRN_PURR:
-		kvmppc_set_gpr(vcpu, rt, 0);
+		*spr_val = 0;
 		break;
 	case SPRN_GQR0:
 	case SPRN_GQR1:
@@ -490,8 +494,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_GQR5:
 	case SPRN_GQR6:
 	case SPRN_GQR7:
-		kvmppc_set_gpr(vcpu, rt,
-			       to_book3s(vcpu)->gqr[sprn - SPRN_GQR0]);
+		*spr_val = to_book3s(vcpu)->gqr[sprn - SPRN_GQR0];
 		break;
 	case SPRN_THRM1:
 	case SPRN_THRM2:
@@ -506,7 +509,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_PMC3_GEKKO:
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
-		kvmppc_set_gpr(vcpu, rt, 0);
+		*spr_val = 0;
 		break;
 	default:
 unprivileged:
@@ -565,23 +568,22 @@ u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst)
 ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst)
 {
 	ulong dar = 0;
-	ulong ra;
+	ulong ra = get_ra(inst);
+	ulong rb = get_rb(inst);
 
 	switch (get_op(inst)) {
 	case OP_LFS:
 	case OP_LFD:
 	case OP_STFD:
 	case OP_STFS:
-		ra = get_ra(inst);
 		if (ra)
 			dar = kvmppc_get_gpr(vcpu, ra);
 		dar += (s32)((s16)inst);
 		break;
 	case 31:
-		ra = get_ra(inst);
 		if (ra)
 			dar = kvmppc_get_gpr(vcpu, ra);
-		dar += kvmppc_get_gpr(vcpu, get_rb(inst));
+		dar += kvmppc_get_gpr(vcpu, rb);
 		break;
 	default:
 		printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 108d1f580177..c6af1d623839 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -60,12 +60,20 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu);
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
 	local_paca->kvm_hstate.kvm_vcpu = vcpu;
-	local_paca->kvm_hstate.kvm_vcore = vcpu->arch.vcore;
+	local_paca->kvm_hstate.kvm_vcore = vc;
+	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
+		vc->stolen_tb += mftb() - vc->preempt_tb;
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
+		vc->preempt_tb = mftb();
 }
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
@@ -134,6 +142,22 @@ static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
 	vpa->yield_count = 1;
 }
 
+/* Length for a per-processor buffer is passed in at offset 4 in the buffer */
+struct reg_vpa {
+	u32 dummy;
+	union {
+		u16 hword;
+		u32 word;
+	} length;
+};
+
+static int vpa_is_registered(struct kvmppc_vpa *vpap)
+{
+	if (vpap->update_pending)
+		return vpap->next_gpa != 0;
+	return vpap->pinned_addr != NULL;
+}
+
 static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 				       unsigned long flags,
 				       unsigned long vcpuid, unsigned long vpa)
@@ -142,88 +166,182 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 	unsigned long len, nb;
 	void *va;
 	struct kvm_vcpu *tvcpu;
-	int err = H_PARAMETER;
+	int err;
+	int subfunc;
+	struct kvmppc_vpa *vpap;
 
 	tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
 	if (!tvcpu)
 		return H_PARAMETER;
 
-	flags >>= 63 - 18;
-	flags &= 7;
-	if (flags == 0 || flags == 4)
-		return H_PARAMETER;
-	if (flags < 4) {
-		if (vpa & 0x7f)
+	subfunc = (flags >> H_VPA_FUNC_SHIFT) & H_VPA_FUNC_MASK;
+	if (subfunc == H_VPA_REG_VPA || subfunc == H_VPA_REG_DTL ||
+	    subfunc == H_VPA_REG_SLB) {
+		/* Registering new area - address must be cache-line aligned */
+		if ((vpa & (L1_CACHE_BYTES - 1)) || !vpa)
 			return H_PARAMETER;
-		if (flags >= 2 && !tvcpu->arch.vpa)
-			return H_RESOURCE;
-		/* registering new area; convert logical addr to real */
+
+		/* convert logical addr to kernel addr and read length */
 		va = kvmppc_pin_guest_page(kvm, vpa, &nb);
 		if (va == NULL)
 			return H_PARAMETER;
-		if (flags <= 1)
-			len = *(unsigned short *)(va + 4);
+		if (subfunc == H_VPA_REG_VPA)
+			len = ((struct reg_vpa *)va)->length.hword;
 		else
-			len = *(unsigned int *)(va + 4);
-		if (len > nb)
-			goto out_unpin;
-		switch (flags) {
-		case 1:		/* register VPA */
-			if (len < 640)
-				goto out_unpin;
-			if (tvcpu->arch.vpa)
-				kvmppc_unpin_guest_page(kvm, vcpu->arch.vpa);
-			tvcpu->arch.vpa = va;
-			init_vpa(vcpu, va);
-			break;
-		case 2:		/* register DTL */
-			if (len < 48)
-				goto out_unpin;
-			len -= len % 48;
-			if (tvcpu->arch.dtl)
-				kvmppc_unpin_guest_page(kvm, vcpu->arch.dtl);
-			tvcpu->arch.dtl = va;
-			tvcpu->arch.dtl_end = va + len;
+			len = ((struct reg_vpa *)va)->length.word;
+		kvmppc_unpin_guest_page(kvm, va);
+
+		/* Check length */
+		if (len > nb || len < sizeof(struct reg_vpa))
+			return H_PARAMETER;
+	} else {
+		vpa = 0;
+		len = 0;
+	}
+
+	err = H_PARAMETER;
+	vpap = NULL;
+	spin_lock(&tvcpu->arch.vpa_update_lock);
+
+	switch (subfunc) {
+	case H_VPA_REG_VPA:		/* register VPA */
+		if (len < sizeof(struct lppaca))
 			break;
-		case 3:		/* register SLB shadow buffer */
-			if (len < 16)
-				goto out_unpin;
-			if (tvcpu->arch.slb_shadow)
-				kvmppc_unpin_guest_page(kvm, vcpu->arch.slb_shadow);
-			tvcpu->arch.slb_shadow = va;
+		vpap = &tvcpu->arch.vpa;
+		err = 0;
+		break;
+
+	case H_VPA_REG_DTL:		/* register DTL */
+		if (len < sizeof(struct dtl_entry))
 			break;
-		}
-	} else {
-		switch (flags) {
-		case 5:		/* unregister VPA */
-			if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl)
-				return H_RESOURCE;
-			if (!tvcpu->arch.vpa)
-				break;
-			kvmppc_unpin_guest_page(kvm, tvcpu->arch.vpa);
-			tvcpu->arch.vpa = NULL;
+		len -= len % sizeof(struct dtl_entry);
+
+		/* Check that they have previously registered a VPA */
+		err = H_RESOURCE;
+		if (!vpa_is_registered(&tvcpu->arch.vpa))
 			break;
-		case 6:		/* unregister DTL */
-			if (!tvcpu->arch.dtl)
-				break;
-			kvmppc_unpin_guest_page(kvm, tvcpu->arch.dtl);
-			tvcpu->arch.dtl = NULL;
+
+		vpap = &tvcpu->arch.dtl;
+		err = 0;
+		break;
+
+	case H_VPA_REG_SLB:		/* register SLB shadow buffer */
+		/* Check that they have previously registered a VPA */
+		err = H_RESOURCE;
+		if (!vpa_is_registered(&tvcpu->arch.vpa))
 			break;
-		case 7:		/* unregister SLB shadow buffer */
-			if (!tvcpu->arch.slb_shadow)
-				break;
-			kvmppc_unpin_guest_page(kvm, tvcpu->arch.slb_shadow);
-			tvcpu->arch.slb_shadow = NULL;
+
+		vpap = &tvcpu->arch.slb_shadow;
+		err = 0;
+		break;
+
+	case H_VPA_DEREG_VPA:		/* deregister VPA */
+		/* Check they don't still have a DTL or SLB buf registered */
+		err = H_RESOURCE;
+		if (vpa_is_registered(&tvcpu->arch.dtl) ||
+		    vpa_is_registered(&tvcpu->arch.slb_shadow))
 			break;
-		}
+
+		vpap = &tvcpu->arch.vpa;
+		err = 0;
+		break;
+
+	case H_VPA_DEREG_DTL:		/* deregister DTL */
+		vpap = &tvcpu->arch.dtl;
+		err = 0;
+		break;
+
+	case H_VPA_DEREG_SLB:		/* deregister SLB shadow buffer */
+		vpap = &tvcpu->arch.slb_shadow;
+		err = 0;
+		break;
+	}
+
+	if (vpap) {
+		vpap->next_gpa = vpa;
+		vpap->len = len;
+		vpap->update_pending = 1;
 	}
-	return H_SUCCESS;
 
- out_unpin:
-	kvmppc_unpin_guest_page(kvm, va);
+	spin_unlock(&tvcpu->arch.vpa_update_lock);
+
 	return err;
 }
 
+static void kvmppc_update_vpa(struct kvm *kvm, struct kvmppc_vpa *vpap)
+{
+	void *va;
+	unsigned long nb;
+
+	vpap->update_pending = 0;
+	va = NULL;
+	if (vpap->next_gpa) {
+		va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb);
+		if (nb < vpap->len) {
+			/*
+			 * If it's now too short, it must be that userspace
+			 * has changed the mappings underlying guest memory,
+			 * so unregister the region.
+			 */
+			kvmppc_unpin_guest_page(kvm, va);
+			va = NULL;
+		}
+	}
+	if (vpap->pinned_addr)
+		kvmppc_unpin_guest_page(kvm, vpap->pinned_addr);
+	vpap->pinned_addr = va;
+	if (va)
+		vpap->pinned_end = va + vpap->len;
+}
+
+static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	if (vcpu->arch.vpa.update_pending) {
+		kvmppc_update_vpa(kvm, &vcpu->arch.vpa);
+		init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+	}
+	if (vcpu->arch.dtl.update_pending) {
+		kvmppc_update_vpa(kvm, &vcpu->arch.dtl);
+		vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
+		vcpu->arch.dtl_index = 0;
+	}
+	if (vcpu->arch.slb_shadow.update_pending)
+		kvmppc_update_vpa(kvm, &vcpu->arch.slb_shadow);
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+}
+
+static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
+				    struct kvmppc_vcore *vc)
+{
+	struct dtl_entry *dt;
+	struct lppaca *vpa;
+	unsigned long old_stolen;
+
+	dt = vcpu->arch.dtl_ptr;
+	vpa = vcpu->arch.vpa.pinned_addr;
+	old_stolen = vcpu->arch.stolen_logged;
+	vcpu->arch.stolen_logged = vc->stolen_tb;
+	if (!dt || !vpa)
+		return;
+	memset(dt, 0, sizeof(struct dtl_entry));
+	dt->dispatch_reason = 7;
+	dt->processor_id = vc->pcpu + vcpu->arch.ptid;
+	dt->timebase = mftb();
+	dt->enqueue_to_dispatch_time = vc->stolen_tb - old_stolen;
+	dt->srr0 = kvmppc_get_pc(vcpu);
+	dt->srr1 = vcpu->arch.shregs.msr;
+	++dt;
+	if (dt == vcpu->arch.dtl.pinned_end)
+		dt = vcpu->arch.dtl.pinned_addr;
+	vcpu->arch.dtl_ptr = dt;
+	/* order writing *dt vs. writing vpa->dtl_idx */
+	smp_wmb();
+	vpa->dtl_idx = ++vcpu->arch.dtl_index;
+}
+
 int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 {
 	unsigned long req = kvmppc_get_gpr(vcpu, 3);
@@ -468,6 +586,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	/* default to host PVR, since we can't spoof it */
 	vcpu->arch.pvr = mfspr(SPRN_PVR);
 	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	spin_lock_init(&vcpu->arch.vpa_update_lock);
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
@@ -486,6 +605,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 			INIT_LIST_HEAD(&vcore->runnable_threads);
 			spin_lock_init(&vcore->lock);
 			init_waitqueue_head(&vcore->wq);
+			vcore->preempt_tb = mftb();
 		}
 		kvm->arch.vcores[core] = vcore;
 	}
@@ -498,6 +618,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	++vcore->num_threads;
 	spin_unlock(&vcore->lock);
 	vcpu->arch.vcore = vcore;
+	vcpu->arch.stolen_logged = vcore->stolen_tb;
 
 	vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	kvmppc_sanity_check(vcpu);
@@ -512,12 +633,14 @@ out:
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.dtl)
-		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.dtl);
-	if (vcpu->arch.slb_shadow)
-		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.slb_shadow);
-	if (vcpu->arch.vpa)
-		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.vpa);
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	if (vcpu->arch.dtl.pinned_addr)
+		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.dtl.pinned_addr);
+	if (vcpu->arch.slb_shadow.pinned_addr)
+		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.slb_shadow.pinned_addr);
+	if (vcpu->arch.vpa.pinned_addr)
+		kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.vpa.pinned_addr);
+	spin_unlock(&vcpu->arch.vpa_update_lock);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
@@ -569,6 +692,45 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 	list_del(&vcpu->arch.run_list);
 }
 
+static int kvmppc_grab_hwthread(int cpu)
+{
+	struct paca_struct *tpaca;
+	long timeout = 1000;
+
+	tpaca = &paca[cpu];
+
+	/* Ensure the thread won't go into the kernel if it wakes */
+	tpaca->kvm_hstate.hwthread_req = 1;
+
+	/*
+	 * If the thread is already executing in the kernel (e.g. handling
+	 * a stray interrupt), wait for it to get back to nap mode.
+	 * The smp_mb() is to ensure that our setting of hwthread_req
+	 * is visible before we look at hwthread_state, so if this
+	 * races with the code at system_reset_pSeries and the thread
+	 * misses our setting of hwthread_req, we are sure to see its
+	 * setting of hwthread_state, and vice versa.
+	 */
+	smp_mb();
+	while (tpaca->kvm_hstate.hwthread_state == KVM_HWTHREAD_IN_KERNEL) {
+		if (--timeout <= 0) {
+			pr_err("KVM: couldn't grab cpu %d\n", cpu);
+			return -EBUSY;
+		}
+		udelay(1);
+	}
+	return 0;
+}
+
+static void kvmppc_release_hwthread(int cpu)
+{
+	struct paca_struct *tpaca;
+
+	tpaca = &paca[cpu];
+	tpaca->kvm_hstate.hwthread_req = 0;
+	tpaca->kvm_hstate.kvm_vcpu = NULL;
+}
+
 static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 {
 	int cpu;
@@ -588,8 +750,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (vcpu->arch.ptid) {
-		tpaca->cpu_start = 0x80;
-		wmb();
+		kvmppc_grab_hwthread(cpu);
 		xics_wake_cpu(cpu);
 		++vc->n_woken;
 	}
@@ -639,7 +800,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	struct kvm_vcpu *vcpu, *vcpu0, *vnext;
 	long ret;
 	u64 now;
-	int ptid;
+	int ptid, i;
 
 	/* don't start if any threads have a signal pending */
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
@@ -681,17 +842,29 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	vc->nap_count = 0;
 	vc->entry_exit_count = 0;
 	vc->vcore_state = VCORE_RUNNING;
+	vc->stolen_tb += mftb() - vc->preempt_tb;
 	vc->in_guest = 0;
 	vc->pcpu = smp_processor_id();
 	vc->napping_threads = 0;
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		kvmppc_start_thread(vcpu);
+		if (vcpu->arch.vpa.update_pending ||
+		    vcpu->arch.slb_shadow.update_pending ||
+		    vcpu->arch.dtl.update_pending)
+			kvmppc_update_vpas(vcpu);
+		kvmppc_create_dtl_entry(vcpu, vc);
+	}
+	/* Grab any remaining hw threads so they can't go into the kernel */
+	for (i = ptid; i < threads_per_core; ++i)
+		kvmppc_grab_hwthread(vc->pcpu + i);
 
 	preempt_disable();
 	spin_unlock(&vc->lock);
 
 	kvm_guest_enter();
 	__kvmppc_vcore_entry(NULL, vcpu0);
+	for (i = 0; i < threads_per_core; ++i)
+		kvmppc_release_hwthread(vc->pcpu + i);
 
 	spin_lock(&vc->lock);
 	/* disable sending of IPIs on virtual external irqs */
@@ -737,6 +910,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	spin_lock(&vc->lock);
  out:
 	vc->vcore_state = VCORE_INACTIVE;
+	vc->preempt_tb = mftb();
 	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
 				 arch.run_list) {
 		if (vcpu->arch.ret != RESUME_GUEST) {
@@ -835,6 +1009,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			spin_lock(&vc->lock);
 			continue;
 		}
+		vc->runner = vcpu;
 		n_ceded = 0;
 		list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
 			n_ceded += v->arch.ceded;
@@ -854,6 +1029,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 				wake_up(&v->arch.cpu_run);
 			}
 		}
+		vc->runner = NULL;
 	}
 
 	if (signal_pending(current)) {
@@ -917,115 +1093,6 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	return r;
 }
 
-static long kvmppc_stt_npages(unsigned long window_size)
-{
-	return ALIGN((window_size >> SPAPR_TCE_SHIFT)
-		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
-}
-
-static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
-{
-	struct kvm *kvm = stt->kvm;
-	int i;
-
-	mutex_lock(&kvm->lock);
-	list_del(&stt->list);
-	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
-		__free_page(stt->pages[i]);
-	kfree(stt);
-	mutex_unlock(&kvm->lock);
-
-	kvm_put_kvm(kvm);
-}
-
-static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
-	struct page *page;
-
-	if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
-		return VM_FAULT_SIGBUS;
-
-	page = stt->pages[vmf->pgoff];
-	get_page(page);
-	vmf->page = page;
-	return 0;
-}
-
-static const struct vm_operations_struct kvm_spapr_tce_vm_ops = {
-	.fault = kvm_spapr_tce_fault,
-};
-
-static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	vma->vm_ops = &kvm_spapr_tce_vm_ops;
-	return 0;
-}
-
-static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
-{
-	struct kvmppc_spapr_tce_table *stt = filp->private_data;
-
-	release_spapr_tce_table(stt);
-	return 0;
-}
-
-static struct file_operations kvm_spapr_tce_fops = {
-	.mmap           = kvm_spapr_tce_mmap,
-	.release	= kvm_spapr_tce_release,
-};
-
-long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
-				   struct kvm_create_spapr_tce *args)
-{
-	struct kvmppc_spapr_tce_table *stt = NULL;
-	long npages;
-	int ret = -ENOMEM;
-	int i;
-
-	/* Check this LIOBN hasn't been previously allocated */
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == args->liobn)
-			return -EBUSY;
-	}
-
-	npages = kvmppc_stt_npages(args->window_size);
-
-	stt = kzalloc(sizeof(*stt) + npages* sizeof(struct page *),
-		      GFP_KERNEL);
-	if (!stt)
-		goto fail;
-
-	stt->liobn = args->liobn;
-	stt->window_size = args->window_size;
-	stt->kvm = kvm;
-
-	for (i = 0; i < npages; i++) {
-		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!stt->pages[i])
-			goto fail;
-	}
-
-	kvm_get_kvm(kvm);
-
-	mutex_lock(&kvm->lock);
-	list_add(&stt->list, &kvm->arch.spapr_tce_tables);
-
-	mutex_unlock(&kvm->lock);
-
-	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR);
-
-fail:
-	if (stt) {
-		for (i = 0; i < npages; i++)
-			if (stt->pages[i])
-				__free_page(stt->pages[i]);
-
-		kfree(stt);
-	}
-	return ret;
-}
 
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
@@ -1108,6 +1175,38 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 	return fd;
 }
 
+static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
+				     int linux_psize)
+{
+	struct mmu_psize_def *def = &mmu_psize_defs[linux_psize];
+
+	if (!def->shift)
+		return;
+	(*sps)->page_shift = def->shift;
+	(*sps)->slb_enc = def->sllp;
+	(*sps)->enc[0].page_shift = def->shift;
+	(*sps)->enc[0].pte_enc = def->penc;
+	(*sps)++;
+}
+
+int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+{
+	struct kvm_ppc_one_seg_page_size *sps;
+
+	info->flags = KVM_PPC_PAGE_SIZES_REAL;
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+		info->flags |= KVM_PPC_1T_SEGMENTS;
+	info->slb_size = mmu_slb_size;
+
+	/* We only support these sizes for now, and no muti-size segments */
+	sps = &info->sps[0];
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_4K);
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_64K);
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_16M);
+
+	return 0;
+}
+
 /*
  * Get (and clear) the dirty memory log for a memory slot.
  */
@@ -1404,12 +1503,12 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	return EMULATE_FAIL;
 }
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index d3fb4df02c41..84035a528c80 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -68,19 +68,24 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	rotldi  r10,r10,16
 	mtmsrd  r10,1
 
-	/* Save host PMU registers and load guest PMU registers */
+	/* Save host PMU registers */
 	/* R4 is live here (vcpu pointer) but not r3 or r5 */
 	li	r3, 1
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
 	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable interrupts */
+	mfspr	r6, SPRN_MMCRA
+BEGIN_FTR_SECTION
+	/* On P7, clear MMCRA in order to disable SDAR updates */
+	li	r5, 0
+	mtspr	SPRN_MMCRA, r5
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	isync
 	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
 	lbz	r5, LPPACA_PMCINUSE(r3)
 	cmpwi	r5, 0
 	beq	31f			/* skip if not */
 	mfspr	r5, SPRN_MMCR1
-	mfspr	r6, SPRN_MMCRA
 	std	r7, HSTATE_MMCR(r13)
 	std	r5, HSTATE_MMCR + 8(r13)
 	std	r6, HSTATE_MMCR + 16(r13)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b70bf22a3ff3..a84aafce2a12 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -26,6 +26,7 @@
 #include <asm/hvcall.h>
 #include <asm/asm-offsets.h>
 #include <asm/exception-64s.h>
+#include <asm/kvm_book3s_asm.h>
 
 /*****************************************************************************
  *                                                                           *
@@ -82,6 +83,7 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 
 #define XICS_XIRR		4
 #define XICS_QIRR		0xc
+#define XICS_IPI		2	/* interrupt source # for IPIs */
 
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
@@ -94,26 +96,54 @@ kvm_start_guest:
 	subi	r1,r1,STACK_FRAME_OVERHEAD
 	ld	r2,PACATOC(r13)
 
-	/* were we napping due to cede? */
-	lbz	r0,HSTATE_NAPPING(r13)
-	cmpwi	r0,0
-	bne	kvm_end_cede
+	li	r0,KVM_HWTHREAD_IN_KVM
+	stb	r0,HSTATE_HWTHREAD_STATE(r13)
 
-	/* get vcpu pointer */
-	ld	r4, HSTATE_KVM_VCPU(r13)
+	/* NV GPR values from power7_idle() will no longer be valid */
+	li	r0,1
+	stb	r0,PACA_NAPSTATELOST(r13)
 
-	/* We got here with an IPI; clear it */
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r0, 0xff
-	li	r6, XICS_QIRR
-	li	r7, XICS_XIRR
-	lwzcix	r8, r5, r7		/* ack the interrupt */
+	/* get vcpu pointer, NULL if we have no vcpu to run */
+	ld	r4,HSTATE_KVM_VCPU(r13)
+	cmpdi	cr1,r4,0
+
+	/* Check the wake reason in SRR1 to see why we got here */
+	mfspr	r3,SPRN_SRR1
+	rlwinm	r3,r3,44-31,0x7		/* extract wake reason field */
+	cmpwi	r3,4			/* was it an external interrupt? */
+	bne	27f
+
+	/*
+	 * External interrupt - for now assume it is an IPI, since we
+	 * should never get any other interrupts sent to offline threads.
+	 * Only do this for secondary threads.
+	 */
+	beq	cr1,25f
+	lwz	r3,VCPU_PTID(r4)
+	cmpwi	r3,0
+	beq	27f
+25:	ld	r5,HSTATE_XICS_PHYS(r13)
+	li	r0,0xff
+	li	r6,XICS_QIRR
+	li	r7,XICS_XIRR
+	lwzcix	r8,r5,r7		/* get and ack the interrupt */
 	sync
-	stbcix	r0, r5, r6		/* clear it */
-	stwcix	r8, r5, r7		/* EOI it */
+	clrldi.	r9,r8,40		/* get interrupt source ID. */
+	beq	27f			/* none there? */
+	cmpwi	r9,XICS_IPI
+	bne	26f
+	stbcix	r0,r5,r6		/* clear IPI */
+26:	stwcix	r8,r5,r7		/* EOI the interrupt */
 
-	/* NV GPR values from power7_idle() will no longer be valid */
-	stb	r0, PACA_NAPSTATELOST(r13)
+27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
+
+	/* if we have no vcpu to run, go back to sleep */
+	beq	cr1,kvm_no_guest
+
+	/* were we napping due to cede? */
+	lbz	r0,HSTATE_NAPPING(r13)
+	cmpwi	r0,0
+	bne	kvm_end_cede
 
 .global kvmppc_hv_entry
 kvmppc_hv_entry:
@@ -129,24 +159,15 @@ kvmppc_hv_entry:
 	mflr	r0
 	std	r0, HSTATE_VMHANDLER(r13)
 
-	ld	r14, VCPU_GPR(r14)(r4)
-	ld	r15, VCPU_GPR(r15)(r4)
-	ld	r16, VCPU_GPR(r16)(r4)
-	ld	r17, VCPU_GPR(r17)(r4)
-	ld	r18, VCPU_GPR(r18)(r4)
-	ld	r19, VCPU_GPR(r19)(r4)
-	ld	r20, VCPU_GPR(r20)(r4)
-	ld	r21, VCPU_GPR(r21)(r4)
-	ld	r22, VCPU_GPR(r22)(r4)
-	ld	r23, VCPU_GPR(r23)(r4)
-	ld	r24, VCPU_GPR(r24)(r4)
-	ld	r25, VCPU_GPR(r25)(r4)
-	ld	r26, VCPU_GPR(r26)(r4)
-	ld	r27, VCPU_GPR(r27)(r4)
-	ld	r28, VCPU_GPR(r28)(r4)
-	ld	r29, VCPU_GPR(r29)(r4)
-	ld	r30, VCPU_GPR(r30)(r4)
-	ld	r31, VCPU_GPR(r31)(r4)
+	/* Set partition DABR */
+	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
+	li	r5,3
+	ld	r6,VCPU_DABR(r4)
+	mtspr	SPRN_DABRX,r5
+	mtspr	SPRN_DABR,r6
+BEGIN_FTR_SECTION
+	isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 	/* Load guest PMU registers */
 	/* R4 is live here (vcpu pointer) */
@@ -185,6 +206,25 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	/* Load up FP, VMX and VSX registers */
 	bl	kvmppc_load_fp
 
+	ld	r14, VCPU_GPR(r14)(r4)
+	ld	r15, VCPU_GPR(r15)(r4)
+	ld	r16, VCPU_GPR(r16)(r4)
+	ld	r17, VCPU_GPR(r17)(r4)
+	ld	r18, VCPU_GPR(r18)(r4)
+	ld	r19, VCPU_GPR(r19)(r4)
+	ld	r20, VCPU_GPR(r20)(r4)
+	ld	r21, VCPU_GPR(r21)(r4)
+	ld	r22, VCPU_GPR(r22)(r4)
+	ld	r23, VCPU_GPR(r23)(r4)
+	ld	r24, VCPU_GPR(r24)(r4)
+	ld	r25, VCPU_GPR(r25)(r4)
+	ld	r26, VCPU_GPR(r26)(r4)
+	ld	r27, VCPU_GPR(r27)(r4)
+	ld	r28, VCPU_GPR(r28)(r4)
+	ld	r29, VCPU_GPR(r29)(r4)
+	ld	r30, VCPU_GPR(r30)(r4)
+	ld	r31, VCPU_GPR(r31)(r4)
+
 BEGIN_FTR_SECTION
 	/* Switch DSCR to guest value */
 	ld	r5, VCPU_DSCR(r4)
@@ -226,12 +266,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mtspr	SPRN_DAR, r5
 	mtspr	SPRN_DSISR, r6
 
-	/* Set partition DABR */
-	li	r5,3
-	ld	r6,VCPU_DABR(r4)
-	mtspr	SPRN_DABRX,r5
-	mtspr	SPRN_DABR,r6
-
 BEGIN_FTR_SECTION
 	/* Restore AMR and UAMOR, set AMOR to all 1s */
 	ld	r5,VCPU_AMR(r4)
@@ -925,12 +959,6 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_AMR,r6
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
-	/* Restore host DABR and DABRX */
-	ld	r5,HSTATE_DABR(r13)
-	li	r6,7
-	mtspr	SPRN_DABR,r5
-	mtspr	SPRN_DABRX,r6
-
 	/* Switch DSCR back to host value */
 BEGIN_FTR_SECTION
 	mfspr	r8, SPRN_DSCR
@@ -969,6 +997,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	std	r5, VCPU_SPRG2(r9)
 	std	r6, VCPU_SPRG3(r9)
 
+	/* save FP state */
+	mr	r3, r9
+	bl	.kvmppc_save_fp
+
 	/* Increment yield count if they have a VPA */
 	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
 	cmpdi	r8, 0
@@ -983,6 +1015,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
 	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	mfspr	r6, SPRN_MMCRA
+BEGIN_FTR_SECTION
+	/* On P7, clear MMCRA in order to disable SDAR updates */
+	li	r7, 0
+	mtspr	SPRN_MMCRA, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	isync
 	beq	21f			/* if no VPA, save PMU stuff anyway */
 	lbz	r7, LPPACA_PMCINUSE(r8)
@@ -991,7 +1029,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
 	b	22f
 21:	mfspr	r5, SPRN_MMCR1
-	mfspr	r6, SPRN_MMCRA
 	std	r4, VCPU_MMCR(r9)
 	std	r5, VCPU_MMCR + 8(r9)
 	std	r6, VCPU_MMCR + 16(r9)
@@ -1016,17 +1053,20 @@ BEGIN_FTR_SECTION
 	stw	r11, VCPU_PMC + 28(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 22:
-	/* save FP state */
-	mr	r3, r9
-	bl	.kvmppc_save_fp
 
 	/* Secondary threads go off to take a nap on POWER7 */
 BEGIN_FTR_SECTION
-	lwz	r0,VCPU_PTID(r3)
+	lwz	r0,VCPU_PTID(r9)
 	cmpwi	r0,0
 	bne	secondary_nap
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+	/* Restore host DABR and DABRX */
+	ld	r5,HSTATE_DABR(r13)
+	li	r6,7
+	mtspr	SPRN_DABR,r5
+	mtspr	SPRN_DABRX,r6
+
 	/*
 	 * Reload DEC.  HDEC interrupts were disabled when
 	 * we reloaded the host's LPCR value.
@@ -1363,7 +1403,12 @@ bounce_ext_interrupt:
 
 _GLOBAL(kvmppc_h_set_dabr)
 	std	r4,VCPU_DABR(r3)
-	mtspr	SPRN_DABR,r4
+	/* Work around P7 bug where DABR can get corrupted on mtspr */
+1:	mtspr	SPRN_DABR,r4
+	mfspr	r5, SPRN_DABR
+	cmpd	r4, r5
+	bne	1b
+	isync
 	li	r3,0
 	blr
 
@@ -1445,8 +1490,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	 * Take a nap until a decrementer or external interrupt occurs,
 	 * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR
 	 */
-	li	r0,0x80
-	stb	r0,PACAPROCSTART(r13)
+	li	r0,1
+	stb	r0,HSTATE_HWTHREAD_REQ(r13)
 	mfspr	r5,SPRN_LPCR
 	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR,r5
@@ -1463,26 +1508,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 kvm_end_cede:
 	/* Woken by external or decrementer interrupt */
 	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
 
-	/* If we're a secondary thread and we got here by an IPI, ack it */
-	ld	r4,HSTATE_KVM_VCPU(r13)
-	lwz	r3,VCPU_PTID(r4)
-	cmpwi	r3,0
-	beq	27f
-	mfspr	r3,SPRN_SRR1
-	rlwinm	r3,r3,44-31,0x7		/* extract wake reason field */
-	cmpwi	r3,4			/* was it an external interrupt? */
-	bne	27f
-	ld	r5, HSTATE_XICS_PHYS(r13)
-	li	r0,0xff
-	li	r6,XICS_QIRR
-	li	r7,XICS_XIRR
-	lwzcix	r8,r5,r7		/* ack the interrupt */
-	sync
-	stbcix	r0,r5,r6		/* clear it */
-	stwcix	r8,r5,r7		/* EOI it */
-27:
 	/* load up FP state */
 	bl	kvmppc_load_fp
 
@@ -1580,12 +1606,17 @@ secondary_nap:
 	stwcx.	r3, 0, r4
 	bne	51b
 
+kvm_no_guest:
+	li	r0, KVM_HWTHREAD_IN_NAP
+	stb	r0, HSTATE_HWTHREAD_STATE(r13)
+	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
+
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
 	isync
-	li	r0, 0
 	std	r0, HSTATE_SCRATCH0(r13)
 	ptesync
 	ld	r0, HSTATE_SCRATCH0(r13)
@@ -1599,8 +1630,8 @@ secondary_nap:
  * r3 = vcpu pointer
  */
 _GLOBAL(kvmppc_save_fp)
-	mfmsr	r9
-	ori	r8,r9,MSR_FP
+	mfmsr	r5
+	ori	r8,r5,MSR_FP
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	oris	r8,r8,MSR_VEC@h
@@ -1649,7 +1680,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	mfspr	r6,SPRN_VRSAVE
 	stw	r6,VCPU_VRSAVE(r3)
-	mtmsrd	r9
+	mtmsrd	r5
 	isync
 	blr
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 7759053d391b..a1baec340f7e 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -120,6 +120,7 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 	if (msr & MSR_POW) {
 		if (!vcpu->arch.pending_exceptions) {
 			kvm_vcpu_block(vcpu);
+			clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 			vcpu->stat.halt_wakeup++;
 
 			/* Unset POW bit after we woke up */
@@ -144,6 +145,21 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 		}
 	}
 
+	/*
+	 * When switching from 32 to 64-bit, we may have a stale 32-bit
+	 * magic page around, we need to flush it. Typically 32-bit magic
+	 * page will be instanciated when calling into RTAS. Note: We
+	 * assume that such transition only happens while in kernel mode,
+	 * ie, we never transition from user 32-bit to kernel 64-bit with
+	 * a 32-bit magic page around.
+	 */
+	if (vcpu->arch.magic_page_pa &&
+	    !(old_msr & MSR_PR) && !(old_msr & MSR_SF) && (msr & MSR_SF)) {
+		/* going from RTAS to normal kernel code */
+		kvmppc_mmu_pte_flush(vcpu, (uint32_t)vcpu->arch.magic_page_pa,
+				     ~0xFFFUL);
+	}
+
 	/* Preload FPU if it's enabled */
 	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
@@ -251,6 +267,9 @@ static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa;
 
+	if (!(vcpu->arch.shared->msr & MSR_SF))
+		mp_pa = (uint32_t)mp_pa;
+
 	if (unlikely(mp_pa) &&
 	    unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) {
 		return 1;
@@ -351,6 +370,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		/* MMIO */
 		vcpu->stat.mmio_exits++;
 		vcpu->arch.paddr_accessed = pte.raddr;
+		vcpu->arch.vaddr_accessed = pte.eaddr;
 		r = kvmppc_emulate_mmio(run, vcpu);
 		if ( r == RESUME_HOST_NV )
 			r = RESUME_HOST;
@@ -528,6 +548,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 
+	/* We get here with MSR.EE=0, so enable it to be a nice citizen */
+	__hard_irq_enable();
+
 	trace_kvm_book3s_exit(exit_nr, vcpu);
 	preempt_enable();
 	kvm_resched(vcpu);
@@ -617,10 +640,13 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 	/* We're good on these - the host merely wanted to get our attention */
 	case BOOK3S_INTERRUPT_DECREMENTER:
+	case BOOK3S_INTERRUPT_HV_DECREMENTER:
 		vcpu->stat.dec_exits++;
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_EXTERNAL:
+	case BOOK3S_INTERRUPT_EXTERNAL_LEVEL:
+	case BOOK3S_INTERRUPT_EXTERNAL_HV:
 		vcpu->stat.ext_intr_exits++;
 		r = RESUME_GUEST;
 		break;
@@ -628,6 +654,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_PROGRAM:
+	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
 	{
 		enum emulation_result er;
 		struct kvmppc_book3s_shadow_vcpu *svcpu;
@@ -1131,6 +1158,31 @@ out:
 	return r;
 }
 
+#ifdef CONFIG_PPC64
+int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
+{
+	/* No flags */
+	info->flags = 0;
+
+	/* SLB is always 64 entries */
+	info->slb_size = 64;
+
+	/* Standard 4k base page size segment */
+	info->sps[0].page_shift = 12;
+	info->sps[0].slb_enc = 0;
+	info->sps[0].enc[0].page_shift = 12;
+	info->sps[0].enc[0].pte_enc = 0;
+
+	/* Standard 16M large page size segment */
+	info->sps[1].page_shift = 24;
+	info->sps[1].slb_enc = SLB_VSID_L;
+	info->sps[1].enc[0].page_shift = 24;
+	info->sps[1].enc[0].pte_enc = 0;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				      struct kvm_userspace_memory_region *mem)
 {
@@ -1144,11 +1196,18 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
+#ifdef CONFIG_PPC64
+	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+#endif
+
 	return 0;
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
+#ifdef CONFIG_PPC64
+	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
+#endif
 }
 
 static int kvmppc_book3s_init(void)
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index b9589324797b..3ff9013d6e79 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -15,6 +15,8 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/anon_inodes.h>
+
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -98,6 +100,83 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+/* Request defs for kvmppc_h_pr_bulk_remove() */
+#define H_BULK_REMOVE_TYPE             0xc000000000000000ULL
+#define   H_BULK_REMOVE_REQUEST        0x4000000000000000ULL
+#define   H_BULK_REMOVE_RESPONSE       0x8000000000000000ULL
+#define   H_BULK_REMOVE_END            0xc000000000000000ULL
+#define H_BULK_REMOVE_CODE             0x3000000000000000ULL
+#define   H_BULK_REMOVE_SUCCESS        0x0000000000000000ULL
+#define   H_BULK_REMOVE_NOT_FOUND      0x1000000000000000ULL
+#define   H_BULK_REMOVE_PARM           0x2000000000000000ULL
+#define   H_BULK_REMOVE_HW             0x3000000000000000ULL
+#define H_BULK_REMOVE_RC               0x0c00000000000000ULL
+#define H_BULK_REMOVE_FLAGS            0x0300000000000000ULL
+#define   H_BULK_REMOVE_ABSOLUTE       0x0000000000000000ULL
+#define   H_BULK_REMOVE_ANDCOND        0x0100000000000000ULL
+#define   H_BULK_REMOVE_AVPN           0x0200000000000000ULL
+#define H_BULK_REMOVE_PTEX             0x00ffffffffffffffULL
+#define H_BULK_REMOVE_MAX_BATCH        4
+
+static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
+{
+	int i;
+	int paramnr = 4;
+	int ret = H_SUCCESS;
+
+	for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) {
+		unsigned long tsh = kvmppc_get_gpr(vcpu, paramnr+(2*i));
+		unsigned long tsl = kvmppc_get_gpr(vcpu, paramnr+(2*i)+1);
+		unsigned long pteg, rb, flags;
+		unsigned long pte[2];
+		unsigned long v = 0;
+
+		if ((tsh & H_BULK_REMOVE_TYPE) == H_BULK_REMOVE_END) {
+			break; /* Exit success */
+		} else if ((tsh & H_BULK_REMOVE_TYPE) !=
+			   H_BULK_REMOVE_REQUEST) {
+			ret = H_PARAMETER;
+			break; /* Exit fail */
+		}
+
+		tsh &= H_BULK_REMOVE_PTEX | H_BULK_REMOVE_FLAGS;
+		tsh |= H_BULK_REMOVE_RESPONSE;
+
+		if ((tsh & H_BULK_REMOVE_ANDCOND) &&
+		    (tsh & H_BULK_REMOVE_AVPN)) {
+			tsh |= H_BULK_REMOVE_PARM;
+			kvmppc_set_gpr(vcpu, paramnr+(2*i), tsh);
+			ret = H_PARAMETER;
+			break; /* Exit fail */
+		}
+
+		pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX);
+		copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+
+		/* tsl = AVPN */
+		flags = (tsh & H_BULK_REMOVE_FLAGS) >> 26;
+
+		if ((pte[0] & HPTE_V_VALID) == 0 ||
+		    ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != tsl) ||
+		    ((flags & H_ANDCOND) && (pte[0] & tsl) != 0)) {
+			tsh |= H_BULK_REMOVE_NOT_FOUND;
+		} else {
+			/* Splat the pteg in (userland) hpt */
+			copy_to_user((void __user *)pteg, &v, sizeof(v));
+
+			rb = compute_tlbie_rb(pte[0], pte[1],
+					      tsh & H_BULK_REMOVE_PTEX);
+			vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
+			tsh |= H_BULK_REMOVE_SUCCESS;
+			tsh |= (pte[1] & (HPTE_R_C | HPTE_R_R)) << 43;
+		}
+		kvmppc_set_gpr(vcpu, paramnr+(2*i), tsh);
+	}
+	kvmppc_set_gpr(vcpu, 3, ret);
+
+	return EMULATE_DONE;
+}
+
 static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags = kvmppc_get_gpr(vcpu, 4);
@@ -134,6 +213,20 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+{
+	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+	unsigned long tce = kvmppc_get_gpr(vcpu, 6);
+	long rc;
+
+	rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
 int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 {
 	switch (cmd) {
@@ -144,12 +237,12 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 	case H_PROTECT:
 		return kvmppc_h_pr_protect(vcpu);
 	case H_BULK_REMOVE:
-		/* We just flush all PTEs, so user space can
-		   handle the HPT modifications */
-		kvmppc_mmu_pte_flush(vcpu, 0, 0);
-		break;
+		return kvmppc_h_pr_bulk_remove(vcpu);
+	case H_PUT_TCE:
+		return kvmppc_h_pr_put_tce(vcpu);
 	case H_CEDE:
 		kvm_vcpu_block(vcpu);
+		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		vcpu->stat.halt_wakeup++;
 		return EMULATE_DONE;
 	}
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 6e6e9cef34a8..798491a268b3 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -128,24 +128,25 @@ no_dcbz32_on:
 	/* First clear RI in our current MSR value */
 	li	r0, MSR_RI
 	andc	r6, r6, r0
-	MTMSR_EERI(r6)
-	mtsrr0	r9
-	mtsrr1	r4
 
 	PPC_LL	r0, SVCPU_R0(r3)
 	PPC_LL	r1, SVCPU_R1(r3)
 	PPC_LL	r2, SVCPU_R2(r3)
-	PPC_LL	r4, SVCPU_R4(r3)
 	PPC_LL	r5, SVCPU_R5(r3)
-	PPC_LL	r6, SVCPU_R6(r3)
 	PPC_LL	r7, SVCPU_R7(r3)
 	PPC_LL	r8, SVCPU_R8(r3)
-	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r10, SVCPU_R10(r3)
 	PPC_LL	r11, SVCPU_R11(r3)
 	PPC_LL	r12, SVCPU_R12(r3)
 	PPC_LL	r13, SVCPU_R13(r3)
 
+	MTMSR_EERI(r6)
+	mtsrr0	r9
+	mtsrr1	r4
+
+	PPC_LL	r4, SVCPU_R4(r3)
+	PPC_LL	r6, SVCPU_R6(r3)
+	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r3, (SVCPU_R3)(r3)
 
 	RFI
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index ee9e1ee9c858..72f13f4a06e0 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -17,6 +17,8 @@
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
  *          Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ *          Scott Wood <scottwood@freescale.com>
+ *          Varun Sethi <varun.sethi@freescale.com>
  */
 
 #include <linux/errno.h>
@@ -30,9 +32,12 @@
 #include <asm/cputable.h>
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
-#include "timing.h"
 #include <asm/cacheflush.h>
+#include <asm/dbell.h>
+#include <asm/hw_irq.h>
+#include <asm/irq.h>
 
+#include "timing.h"
 #include "booke.h"
 
 unsigned long kvmppc_booke_handlers;
@@ -55,6 +60,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "dec",        VCPU_STAT(dec_exits) },
 	{ "ext_intr",   VCPU_STAT(ext_intr_exits) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+	{ "doorbell", VCPU_STAT(dbell_exits) },
+	{ "guest doorbell", VCPU_STAT(gdbell_exits) },
 	{ NULL }
 };
 
@@ -121,6 +128,10 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 {
 	u32 old_msr = vcpu->arch.shared->msr;
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	new_msr |= MSR_GS;
+#endif
+
 	vcpu->arch.shared->msr = new_msr;
 
 	kvmppc_mmu_msr_notify(vcpu, old_msr);
@@ -195,17 +206,87 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
 	clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
 }
 
+static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GSRR0, srr0);
+	mtspr(SPRN_GSRR1, srr1);
+#else
+	vcpu->arch.shared->srr0 = srr0;
+	vcpu->arch.shared->srr1 = srr1;
+#endif
+}
+
+static void set_guest_csrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+	vcpu->arch.csrr0 = srr0;
+	vcpu->arch.csrr1 = srr1;
+}
+
+static void set_guest_dsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) {
+		vcpu->arch.dsrr0 = srr0;
+		vcpu->arch.dsrr1 = srr1;
+	} else {
+		set_guest_csrr(vcpu, srr0, srr1);
+	}
+}
+
+static void set_guest_mcsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+	vcpu->arch.mcsrr0 = srr0;
+	vcpu->arch.mcsrr1 = srr1;
+}
+
+static unsigned long get_guest_dear(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	return mfspr(SPRN_GDEAR);
+#else
+	return vcpu->arch.shared->dar;
+#endif
+}
+
+static void set_guest_dear(struct kvm_vcpu *vcpu, unsigned long dear)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GDEAR, dear);
+#else
+	vcpu->arch.shared->dar = dear;
+#endif
+}
+
+static unsigned long get_guest_esr(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	return mfspr(SPRN_GESR);
+#else
+	return vcpu->arch.shared->esr;
+#endif
+}
+
+static void set_guest_esr(struct kvm_vcpu *vcpu, u32 esr)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GESR, esr);
+#else
+	vcpu->arch.shared->esr = esr;
+#endif
+}
+
 /* Deliver the interrupt of the corresponding priority, if possible. */
 static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                                         unsigned int priority)
 {
 	int allowed = 0;
-	ulong uninitialized_var(msr_mask);
+	ulong msr_mask = 0;
 	bool update_esr = false, update_dear = false;
 	ulong crit_raw = vcpu->arch.shared->critical;
 	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
 	bool crit;
 	bool keep_irq = false;
+	enum int_class int_class;
 
 	/* Truncate crit indicators in 32 bit mode */
 	if (!(vcpu->arch.shared->msr & MSR_SF)) {
@@ -241,46 +322,85 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_AP_UNAVAIL:
 	case BOOKE_IRQPRIO_ALIGNMENT:
 		allowed = 1;
-		msr_mask = MSR_CE|MSR_ME|MSR_DE;
+		msr_mask = MSR_CE | MSR_ME | MSR_DE;
+		int_class = INT_CLASS_NONCRIT;
 		break;
 	case BOOKE_IRQPRIO_CRITICAL:
-	case BOOKE_IRQPRIO_WATCHDOG:
+	case BOOKE_IRQPRIO_DBELL_CRIT:
 		allowed = vcpu->arch.shared->msr & MSR_CE;
+		allowed = allowed && !crit;
 		msr_mask = MSR_ME;
+		int_class = INT_CLASS_CRIT;
 		break;
 	case BOOKE_IRQPRIO_MACHINE_CHECK:
 		allowed = vcpu->arch.shared->msr & MSR_ME;
-		msr_mask = 0;
+		allowed = allowed && !crit;
+		int_class = INT_CLASS_MC;
 		break;
 	case BOOKE_IRQPRIO_DECREMENTER:
 	case BOOKE_IRQPRIO_FIT:
 		keep_irq = true;
 		/* fall through */
 	case BOOKE_IRQPRIO_EXTERNAL:
+	case BOOKE_IRQPRIO_DBELL:
 		allowed = vcpu->arch.shared->msr & MSR_EE;
 		allowed = allowed && !crit;
-		msr_mask = MSR_CE|MSR_ME|MSR_DE;
+		msr_mask = MSR_CE | MSR_ME | MSR_DE;
+		int_class = INT_CLASS_NONCRIT;
 		break;
 	case BOOKE_IRQPRIO_DEBUG:
 		allowed = vcpu->arch.shared->msr & MSR_DE;
+		allowed = allowed && !crit;
 		msr_mask = MSR_ME;
+		int_class = INT_CLASS_CRIT;
 		break;
 	}
 
 	if (allowed) {
-		vcpu->arch.shared->srr0 = vcpu->arch.pc;
-		vcpu->arch.shared->srr1 = vcpu->arch.shared->msr;
+		switch (int_class) {
+		case INT_CLASS_NONCRIT:
+			set_guest_srr(vcpu, vcpu->arch.pc,
+				      vcpu->arch.shared->msr);
+			break;
+		case INT_CLASS_CRIT:
+			set_guest_csrr(vcpu, vcpu->arch.pc,
+				       vcpu->arch.shared->msr);
+			break;
+		case INT_CLASS_DBG:
+			set_guest_dsrr(vcpu, vcpu->arch.pc,
+				       vcpu->arch.shared->msr);
+			break;
+		case INT_CLASS_MC:
+			set_guest_mcsrr(vcpu, vcpu->arch.pc,
+					vcpu->arch.shared->msr);
+			break;
+		}
+
 		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
 		if (update_esr == true)
-			vcpu->arch.shared->esr = vcpu->arch.queued_esr;
+			set_guest_esr(vcpu, vcpu->arch.queued_esr);
 		if (update_dear == true)
-			vcpu->arch.shared->dar = vcpu->arch.queued_dear;
+			set_guest_dear(vcpu, vcpu->arch.queued_dear);
 		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
 
 		if (!keep_irq)
 			clear_bit(priority, &vcpu->arch.pending_exceptions);
 	}
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	/*
+	 * If an interrupt is pending but masked, raise a guest doorbell
+	 * so that we are notified when the guest enables the relevant
+	 * MSR bit.
+	 */
+	if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_EE)
+		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_NONCRIT);
+	if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_CE)
+		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_CRIT);
+	if (vcpu->arch.pending_exceptions & BOOKE_IRQPRIO_MACHINE_CHECK)
+		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_MC);
+#endif
+
 	return allowed;
 }
 
@@ -305,7 +425,7 @@ static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
 	}
 
 	priority = __ffs(*pending);
-	while (priority <= BOOKE_IRQPRIO_MAX) {
+	while (priority < BOOKE_IRQPRIO_MAX) {
 		if (kvmppc_booke_irqprio_deliver(vcpu, priority))
 			break;
 
@@ -319,8 +439,9 @@ static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
 }
 
 /* Check pending exceptions and deliver one, if possible. */
-void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
+int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 {
+	int r = 0;
 	WARN_ON_ONCE(!irqs_disabled());
 
 	kvmppc_core_check_exceptions(vcpu);
@@ -328,16 +449,60 @@ void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.shared->msr & MSR_WE) {
 		local_irq_enable();
 		kvm_vcpu_block(vcpu);
+		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		local_irq_disable();
 
 		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
-		kvmppc_core_check_exceptions(vcpu);
+		r = 1;
 	};
+
+	return r;
+}
+
+/*
+ * Common checks before entering the guest world.  Call with interrupts
+ * disabled.
+ *
+ * returns !0 if a signal is pending and check_signal is true
+ */
+static int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
+{
+	int r = 0;
+
+	WARN_ON_ONCE(!irqs_disabled());
+	while (true) {
+		if (need_resched()) {
+			local_irq_enable();
+			cond_resched();
+			local_irq_disable();
+			continue;
+		}
+
+		if (signal_pending(current)) {
+			r = 1;
+			break;
+		}
+
+		if (kvmppc_core_prepare_to_enter(vcpu)) {
+			/* interrupts got enabled in between, so we
+			   are back at square 1 */
+			continue;
+		}
+
+		break;
+	}
+
+	return r;
 }
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
+#ifdef CONFIG_PPC_FPU
+	unsigned int fpscr;
+	int fpexc_mode;
+	u64 fpr[32];
+#endif
 
 	if (!vcpu->arch.sane) {
 		kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -345,17 +510,53 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	}
 
 	local_irq_disable();
-
-	kvmppc_core_prepare_to_enter(vcpu);
-
-	if (signal_pending(current)) {
+	if (kvmppc_prepare_to_enter(vcpu)) {
 		kvm_run->exit_reason = KVM_EXIT_INTR;
 		ret = -EINTR;
 		goto out;
 	}
 
 	kvm_guest_enter();
+
+#ifdef CONFIG_PPC_FPU
+	/* Save userspace FPU state in stack */
+	enable_kernel_fp();
+	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
+	fpscr = current->thread.fpscr.val;
+	fpexc_mode = current->thread.fpexc_mode;
+
+	/* Restore guest FPU state to thread */
+	memcpy(current->thread.fpr, vcpu->arch.fpr, sizeof(vcpu->arch.fpr));
+	current->thread.fpscr.val = vcpu->arch.fpscr;
+
+	/*
+	 * Since we can't trap on MSR_FP in GS-mode, we consider the guest
+	 * as always using the FPU.  Kernel usage of FP (via
+	 * enable_kernel_fp()) in this thread must not occur while
+	 * vcpu->fpu_active is set.
+	 */
+	vcpu->fpu_active = 1;
+
+	kvmppc_load_guest_fp(vcpu);
+#endif
+
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
+
+#ifdef CONFIG_PPC_FPU
+	kvmppc_save_guest_fp(vcpu);
+
+	vcpu->fpu_active = 0;
+
+	/* Save guest FPU state from thread */
+	memcpy(vcpu->arch.fpr, current->thread.fpr, sizeof(vcpu->arch.fpr));
+	vcpu->arch.fpscr = current->thread.fpscr.val;
+
+	/* Restore userspace FPU state from stack */
+	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
+	current->thread.fpscr.val = fpscr;
+	current->thread.fpexc_mode = fpexc_mode;
+#endif
+
 	kvm_guest_exit();
 
 out:
@@ -363,6 +564,84 @@ out:
 	return ret;
 }
 
+static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	enum emulation_result er;
+
+	er = kvmppc_emulate_instruction(run, vcpu);
+	switch (er) {
+	case EMULATE_DONE:
+		/* don't overwrite subtypes, just account kvm_stats */
+		kvmppc_account_exit_stat(vcpu, EMULATED_INST_EXITS);
+		/* Future optimization: only reload non-volatiles if
+		 * they were actually modified by emulation. */
+		return RESUME_GUEST_NV;
+
+	case EMULATE_DO_DCR:
+		run->exit_reason = KVM_EXIT_DCR;
+		return RESUME_HOST;
+
+	case EMULATE_FAIL:
+		printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
+		       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+		/* For debugging, encode the failing instruction and
+		 * report it to userspace. */
+		run->hw.hardware_exit_reason = ~0ULL << 32;
+		run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
+		kvmppc_core_queue_program(vcpu, ESR_PIL);
+		return RESUME_HOST;
+
+	default:
+		BUG();
+	}
+}
+
+static void kvmppc_fill_pt_regs(struct pt_regs *regs)
+{
+	ulong r1, ip, msr, lr;
+
+	asm("mr %0, 1" : "=r"(r1));
+	asm("mflr %0" : "=r"(lr));
+	asm("mfmsr %0" : "=r"(msr));
+	asm("bl 1f; 1: mflr %0" : "=r"(ip));
+
+	memset(regs, 0, sizeof(*regs));
+	regs->gpr[1] = r1;
+	regs->nip = ip;
+	regs->msr = msr;
+	regs->link = lr;
+}
+
+static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
+				     unsigned int exit_nr)
+{
+	struct pt_regs regs;
+
+	switch (exit_nr) {
+	case BOOKE_INTERRUPT_EXTERNAL:
+		kvmppc_fill_pt_regs(&regs);
+		do_IRQ(&regs);
+		break;
+	case BOOKE_INTERRUPT_DECREMENTER:
+		kvmppc_fill_pt_regs(&regs);
+		timer_interrupt(&regs);
+		break;
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3E_64)
+	case BOOKE_INTERRUPT_DOORBELL:
+		kvmppc_fill_pt_regs(&regs);
+		doorbell_exception(&regs);
+		break;
+#endif
+	case BOOKE_INTERRUPT_MACHINE_CHECK:
+		/* FIXME */
+		break;
+	case BOOKE_INTERRUPT_PERFORMANCE_MONITOR:
+		kvmppc_fill_pt_regs(&regs);
+		performance_monitor_exception(&regs);
+		break;
+	}
+}
+
 /**
  * kvmppc_handle_exit
  *
@@ -371,12 +650,14 @@ out:
 int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
-	enum emulation_result er;
 	int r = RESUME_HOST;
 
 	/* update before a new last_exit_type is rewritten */
 	kvmppc_update_timing_stats(vcpu);
 
+	/* restart interrupts if they were meant for the host */
+	kvmppc_restart_interrupt(vcpu, exit_nr);
+
 	local_irq_enable();
 
 	run->exit_reason = KVM_EXIT_UNKNOWN;
@@ -386,62 +667,74 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOKE_INTERRUPT_MACHINE_CHECK:
 		printk("MACHINE CHECK: %lx\n", mfspr(SPRN_MCSR));
 		kvmppc_dump_vcpu(vcpu);
+		/* For debugging, send invalid exit reason to user space */
+		run->hw.hardware_exit_reason = ~1ULL << 32;
+		run->hw.hardware_exit_reason |= mfspr(SPRN_MCSR);
 		r = RESUME_HOST;
 		break;
 
 	case BOOKE_INTERRUPT_EXTERNAL:
 		kvmppc_account_exit(vcpu, EXT_INTR_EXITS);
-		if (need_resched())
-			cond_resched();
 		r = RESUME_GUEST;
 		break;
 
 	case BOOKE_INTERRUPT_DECREMENTER:
-		/* Since we switched IVPR back to the host's value, the host
-		 * handled this interrupt the moment we enabled interrupts.
-		 * Now we just offer it a chance to reschedule the guest. */
 		kvmppc_account_exit(vcpu, DEC_EXITS);
-		if (need_resched())
-			cond_resched();
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_DOORBELL:
+		kvmppc_account_exit(vcpu, DBELL_EXITS);
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_GUEST_DBELL_CRIT:
+		kvmppc_account_exit(vcpu, GDBELL_EXITS);
+
+		/*
+		 * We are here because there is a pending guest interrupt
+		 * which could not be delivered as MSR_CE or MSR_ME was not
+		 * set.  Once we break from here we will retry delivery.
+		 */
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_GUEST_DBELL:
+		kvmppc_account_exit(vcpu, GDBELL_EXITS);
+
+		/*
+		 * We are here because there is a pending guest interrupt
+		 * which could not be delivered as MSR_EE was not set.  Once
+		 * we break from here we will retry delivery.
+		 */
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_PERFORMANCE_MONITOR:
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_HV_PRIV:
+		r = emulation_exit(run, vcpu);
+		break;
+
 	case BOOKE_INTERRUPT_PROGRAM:
-		if (vcpu->arch.shared->msr & MSR_PR) {
-			/* Program traps generated by user-level software must be handled
-			 * by the guest kernel. */
+		if (vcpu->arch.shared->msr & (MSR_PR | MSR_GS)) {
+			/*
+			 * Program traps generated by user-level software must
+			 * be handled by the guest kernel.
+			 *
+			 * In GS mode, hypervisor privileged instructions trap
+			 * on BOOKE_INTERRUPT_HV_PRIV, not here, so these are
+			 * actual program interrupts, handled by the guest.
+			 */
 			kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
 			r = RESUME_GUEST;
 			kvmppc_account_exit(vcpu, USR_PR_INST);
 			break;
 		}
 
-		er = kvmppc_emulate_instruction(run, vcpu);
-		switch (er) {
-		case EMULATE_DONE:
-			/* don't overwrite subtypes, just account kvm_stats */
-			kvmppc_account_exit_stat(vcpu, EMULATED_INST_EXITS);
-			/* Future optimization: only reload non-volatiles if
-			 * they were actually modified by emulation. */
-			r = RESUME_GUEST_NV;
-			break;
-		case EMULATE_DO_DCR:
-			run->exit_reason = KVM_EXIT_DCR;
-			r = RESUME_HOST;
-			break;
-		case EMULATE_FAIL:
-			/* XXX Deliver Program interrupt to guest. */
-			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
-			       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
-			/* For debugging, encode the failing instruction and
-			 * report it to userspace. */
-			run->hw.hardware_exit_reason = ~0ULL << 32;
-			run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
-			r = RESUME_HOST;
-			break;
-		default:
-			BUG();
-		}
+		r = emulation_exit(run, vcpu);
 		break;
 
 	case BOOKE_INTERRUPT_FP_UNAVAIL:
@@ -506,6 +799,21 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	case BOOKE_INTERRUPT_HV_SYSCALL:
+		if (!(vcpu->arch.shared->msr & MSR_PR)) {
+			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+		} else {
+			/*
+			 * hcall from guest userspace -- send privileged
+			 * instruction program check.
+			 */
+			kvmppc_core_queue_program(vcpu, ESR_PPR);
+		}
+
+		r = RESUME_GUEST;
+		break;
+#else
 	case BOOKE_INTERRUPT_SYSCALL:
 		if (!(vcpu->arch.shared->msr & MSR_PR) &&
 		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
@@ -519,6 +827,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_account_exit(vcpu, SYSCALL_EXITS);
 		r = RESUME_GUEST;
 		break;
+#endif
 
 	case BOOKE_INTERRUPT_DTLB_MISS: {
 		unsigned long eaddr = vcpu->arch.fault_dear;
@@ -526,7 +835,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		gpa_t gpaddr;
 		gfn_t gfn;
 
-#ifdef CONFIG_KVM_E500
+#ifdef CONFIG_KVM_E500V2
 		if (!(vcpu->arch.shared->msr & MSR_PR) &&
 		    (eaddr & PAGE_MASK) == vcpu->arch.magic_page_ea) {
 			kvmppc_map_magic(vcpu);
@@ -567,6 +876,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			/* Guest has mapped and accessed a page which is not
 			 * actually RAM. */
 			vcpu->arch.paddr_accessed = gpaddr;
+			vcpu->arch.vaddr_accessed = eaddr;
 			r = kvmppc_emulate_mmio(run, vcpu);
 			kvmppc_account_exit(vcpu, MMIO_EXITS);
 		}
@@ -634,15 +944,13 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		BUG();
 	}
 
-	local_irq_disable();
-
-	kvmppc_core_prepare_to_enter(vcpu);
-
+	/*
+	 * To avoid clobbering exit_reason, only check for signals if we
+	 * aren't already exiting to userspace for some other reason.
+	 */
 	if (!(r & RESUME_HOST)) {
-		/* To avoid clobbering exit_reason, only check for signals if
-		 * we aren't already exiting to userspace for some other
-		 * reason. */
-		if (signal_pending(current)) {
+		local_irq_disable();
+		if (kvmppc_prepare_to_enter(vcpu)) {
 			run->exit_reason = KVM_EXIT_INTR;
 			r = (-EINTR << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
 			kvmppc_account_exit(vcpu, SIGNAL_EXITS);
@@ -659,12 +967,15 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	int r;
 
 	vcpu->arch.pc = 0;
-	vcpu->arch.shared->msr = 0;
-	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
 	vcpu->arch.shared->pir = vcpu->vcpu_id;
 	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
+	kvmppc_set_msr(vcpu, 0);
 
+#ifndef CONFIG_KVM_BOOKE_HV
+	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
 	vcpu->arch.shadow_pid = 1;
+	vcpu->arch.shared->msr = 0;
+#endif
 
 	/* Eye-catching numbers so we know if the guest takes an interrupt
 	 * before it's programmed its own IVPR/IVORs. */
@@ -745,8 +1056,8 @@ static void get_sregs_base(struct kvm_vcpu *vcpu,
 	sregs->u.e.csrr0 = vcpu->arch.csrr0;
 	sregs->u.e.csrr1 = vcpu->arch.csrr1;
 	sregs->u.e.mcsr = vcpu->arch.mcsr;
-	sregs->u.e.esr = vcpu->arch.shared->esr;
-	sregs->u.e.dear = vcpu->arch.shared->dar;
+	sregs->u.e.esr = get_guest_esr(vcpu);
+	sregs->u.e.dear = get_guest_dear(vcpu);
 	sregs->u.e.tsr = vcpu->arch.tsr;
 	sregs->u.e.tcr = vcpu->arch.tcr;
 	sregs->u.e.dec = kvmppc_get_dec(vcpu, tb);
@@ -763,8 +1074,8 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
 	vcpu->arch.csrr0 = sregs->u.e.csrr0;
 	vcpu->arch.csrr1 = sregs->u.e.csrr1;
 	vcpu->arch.mcsr = sregs->u.e.mcsr;
-	vcpu->arch.shared->esr = sregs->u.e.esr;
-	vcpu->arch.shared->dar = sregs->u.e.dear;
+	set_guest_esr(vcpu, sregs->u.e.esr);
+	set_guest_dear(vcpu, sregs->u.e.dear);
 	vcpu->arch.vrsave = sregs->u.e.vrsave;
 	kvmppc_set_tcr(vcpu, sregs->u.e.tcr);
 
@@ -932,15 +1243,6 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 {
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
-{
-	return 0;
-}
-
-void kvmppc_core_destroy_vm(struct kvm *kvm)
-{
-}
-
 void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
 {
 	vcpu->arch.tcr = new_tcr;
@@ -968,8 +1270,19 @@ void kvmppc_decrementer_func(unsigned long data)
 	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
 }
 
+void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	current->thread.kvm_vcpu = vcpu;
+}
+
+void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	current->thread.kvm_vcpu = NULL;
+}
+
 int __init kvmppc_booke_init(void)
 {
+#ifndef CONFIG_KVM_BOOKE_HV
 	unsigned long ivor[16];
 	unsigned long max_ivor = 0;
 	int i;
@@ -1012,7 +1325,7 @@ int __init kvmppc_booke_init(void)
 	}
 	flush_icache_range(kvmppc_booke_handlers,
 	                   kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
-
+#endif /* !BOOKE_HV */
 	return 0;
 }
 
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 2fe202705a3f..ba61974c1e20 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_ppc.h>
+#include <asm/switch_to.h>
 #include "timing.h"
 
 /* interrupt priortity ordering */
@@ -48,7 +49,20 @@
 #define BOOKE_IRQPRIO_PERFORMANCE_MONITOR 19
 /* Internal pseudo-irqprio for level triggered externals */
 #define BOOKE_IRQPRIO_EXTERNAL_LEVEL 20
-#define BOOKE_IRQPRIO_MAX 20
+#define BOOKE_IRQPRIO_DBELL 21
+#define BOOKE_IRQPRIO_DBELL_CRIT 22
+#define BOOKE_IRQPRIO_MAX 23
+
+#define BOOKE_IRQMASK_EE ((1 << BOOKE_IRQPRIO_EXTERNAL_LEVEL) | \
+			  (1 << BOOKE_IRQPRIO_PERFORMANCE_MONITOR) | \
+			  (1 << BOOKE_IRQPRIO_DBELL) | \
+			  (1 << BOOKE_IRQPRIO_DECREMENTER) | \
+			  (1 << BOOKE_IRQPRIO_FIT) | \
+			  (1 << BOOKE_IRQPRIO_EXTERNAL))
+
+#define BOOKE_IRQMASK_CE ((1 << BOOKE_IRQPRIO_DBELL_CRIT) | \
+			  (1 << BOOKE_IRQPRIO_WATCHDOG) | \
+			  (1 << BOOKE_IRQPRIO_CRITICAL))
 
 extern unsigned long kvmppc_booke_handlers;
 
@@ -61,8 +75,8 @@ void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
 
 int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance);
-int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
-int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs);
+int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val);
+int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val);
 
 /* low-level asm code to transfer guest state */
 void kvmppc_load_guest_spe(struct kvm_vcpu *vcpu);
@@ -71,4 +85,46 @@ void kvmppc_save_guest_spe(struct kvm_vcpu *vcpu);
 /* high-level function, manages flags, host state */
 void kvmppc_vcpu_disable_spe(struct kvm_vcpu *vcpu);
 
+void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu);
+
+enum int_class {
+	INT_CLASS_NONCRIT,
+	INT_CLASS_CRIT,
+	INT_CLASS_MC,
+	INT_CLASS_DBG,
+};
+
+void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type);
+
+/*
+ * Load up guest vcpu FP state if it's needed.
+ * It also set the MSR_FP in thread so that host know
+ * we're holding FPU, and then host can help to save
+ * guest vcpu FP state if other threads require to use FPU.
+ * This simulates an FP unavailable fault.
+ *
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PPC_FPU
+	if (vcpu->fpu_active && !(current->thread.regs->msr & MSR_FP)) {
+		load_up_fpu();
+		current->thread.regs->msr |= MSR_FP;
+	}
+#endif
+}
+
+/*
+ * Save guest vcpu FP state into thread.
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PPC_FPU
+	if (vcpu->fpu_active && (current->thread.regs->msr & MSR_FP))
+		giveup_fpu(current);
+#endif
+}
 #endif /* __KVM_BOOKE_H__ */
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 3e652da36534..6c76397f2af4 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -40,8 +40,8 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
-	int rs;
-	int rt;
+	int rs = get_rs(inst);
+	int rt = get_rt(inst);
 
 	switch (get_op(inst)) {
 	case 19:
@@ -62,19 +62,16 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		switch (get_xop(inst)) {
 
 		case OP_31_XOP_MFMSR:
-			rt = get_rt(inst);
 			kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->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, kvmppc_get_gpr(vcpu, rs));
 			break;
 
 		case OP_31_XOP_WRTEE:
-			rs = get_rs(inst);
 			vcpu->arch.shared->msr = (vcpu->arch.shared->msr & ~MSR_EE)
 					| (kvmppc_get_gpr(vcpu, rs) & MSR_EE);
 			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
@@ -99,22 +96,32 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+/*
+ * NOTE: some of these registers are not emulated on BOOKE_HV (GS-mode).
+ * Their backing store is in real registers, and these functions
+ * will return the wrong result if called for them in another context
+ * (such as debugging).
+ */
+int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
-	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_DEAR:
-		vcpu->arch.shared->dar = spr_val; break;
+		vcpu->arch.shared->dar = spr_val;
+		break;
 	case SPRN_ESR:
-		vcpu->arch.shared->esr = spr_val; break;
+		vcpu->arch.shared->esr = spr_val;
+		break;
 	case SPRN_DBCR0:
-		vcpu->arch.dbcr0 = spr_val; break;
+		vcpu->arch.dbcr0 = spr_val;
+		break;
 	case SPRN_DBCR1:
-		vcpu->arch.dbcr1 = spr_val; break;
+		vcpu->arch.dbcr1 = spr_val;
+		break;
 	case SPRN_DBSR:
-		vcpu->arch.dbsr &= ~spr_val; break;
+		vcpu->arch.dbsr &= ~spr_val;
+		break;
 	case SPRN_TSR:
 		kvmppc_clr_tsr_bits(vcpu, spr_val);
 		break;
@@ -122,20 +129,29 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		kvmppc_set_tcr(vcpu, spr_val);
 		break;
 
-	/* Note: SPRG4-7 are user-readable. These values are
-	 * loaded into the real SPRGs when resuming the
-	 * guest. */
+	/*
+	 * Note: SPRG4-7 are user-readable.
+	 * These values are loaded into the real SPRGs when resuming the
+	 * guest (PR-mode only).
+	 */
 	case SPRN_SPRG4:
-		vcpu->arch.shared->sprg4 = spr_val; break;
+		vcpu->arch.shared->sprg4 = spr_val;
+		break;
 	case SPRN_SPRG5:
-		vcpu->arch.shared->sprg5 = spr_val; break;
+		vcpu->arch.shared->sprg5 = spr_val;
+		break;
 	case SPRN_SPRG6:
-		vcpu->arch.shared->sprg6 = spr_val; break;
+		vcpu->arch.shared->sprg6 = spr_val;
+		break;
 	case SPRN_SPRG7:
-		vcpu->arch.shared->sprg7 = spr_val; break;
+		vcpu->arch.shared->sprg7 = spr_val;
+		break;
 
 	case SPRN_IVPR:
 		vcpu->arch.ivpr = spr_val;
+#ifdef CONFIG_KVM_BOOKE_HV
+		mtspr(SPRN_GIVPR, spr_val);
+#endif
 		break;
 	case SPRN_IVOR0:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = spr_val;
@@ -145,6 +161,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		break;
 	case SPRN_IVOR2:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = spr_val;
+#ifdef CONFIG_KVM_BOOKE_HV
+		mtspr(SPRN_GIVOR2, spr_val);
+#endif
 		break;
 	case SPRN_IVOR3:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = spr_val;
@@ -163,6 +182,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		break;
 	case SPRN_IVOR8:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = spr_val;
+#ifdef CONFIG_KVM_BOOKE_HV
+		mtspr(SPRN_GIVOR8, spr_val);
+#endif
 		break;
 	case SPRN_IVOR9:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = spr_val;
@@ -193,75 +215,83 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	return emulated;
 }
 
-int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
 	case SPRN_IVPR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivpr); break;
+		*spr_val = vcpu->arch.ivpr;
+		break;
 	case SPRN_DEAR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar); break;
+		*spr_val = vcpu->arch.shared->dar;
+		break;
 	case SPRN_ESR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->esr); break;
+		*spr_val = vcpu->arch.shared->esr;
+		break;
 	case SPRN_DBCR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr0); break;
+		*spr_val = vcpu->arch.dbcr0;
+		break;
 	case SPRN_DBCR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break;
+		*spr_val = vcpu->arch.dbcr1;
+		break;
 	case SPRN_DBSR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break;
+		*spr_val = vcpu->arch.dbsr;
+		break;
 	case SPRN_TSR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tsr); break;
+		*spr_val = vcpu->arch.tsr;
+		break;
 	case SPRN_TCR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.tcr); break;
+		*spr_val = vcpu->arch.tcr;
+		break;
 
 	case SPRN_IVOR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
 		break;
 	case SPRN_IVOR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
 		break;
 	case SPRN_IVOR2:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
 		break;
 	case SPRN_IVOR3:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
 		break;
 	case SPRN_IVOR4:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
 		break;
 	case SPRN_IVOR5:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
 		break;
 	case SPRN_IVOR6:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
 		break;
 	case SPRN_IVOR7:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
 		break;
 	case SPRN_IVOR8:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
 		break;
 	case SPRN_IVOR9:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
 		break;
 	case SPRN_IVOR10:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
 		break;
 	case SPRN_IVOR11:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FIT]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
 		break;
 	case SPRN_IVOR12:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
 		break;
 	case SPRN_IVOR13:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
 		break;
 	case SPRN_IVOR14:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
 		break;
 	case SPRN_IVOR15:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
 		break;
 
 	default:
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index c8c4b878795a..8feec2ff3928 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -419,13 +419,13 @@ lightweight_exit:
 	 * written directly to the shared area, so we
 	 * need to reload them here with the guest's values.
 	 */
-	lwz	r3, VCPU_SHARED_SPRG4(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG4, r5)
 	mtspr	SPRN_SPRG4W, r3
-	lwz	r3, VCPU_SHARED_SPRG5(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG5, r5)
 	mtspr	SPRN_SPRG5W, r3
-	lwz	r3, VCPU_SHARED_SPRG6(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG6, r5)
 	mtspr	SPRN_SPRG6W, r3
-	lwz	r3, VCPU_SHARED_SPRG7(r5)
+	PPC_LD(r3, VCPU_SHARED_SPRG7, r5)
 	mtspr	SPRN_SPRG7W, r3
 
 #ifdef CONFIG_KVM_EXIT_TIMING
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
new file mode 100644
index 000000000000..6048a00515d7
--- /dev/null
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -0,0 +1,597 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
+ *
+ * Author: Varun Sethi <varun.sethi@freescale.com>
+ * Author: Scott Wood <scotwood@freescale.com>
+ *
+ * This file is derived from arch/powerpc/kvm/booke_interrupts.S
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/mmu-44x.h>
+#include <asm/page.h>
+#include <asm/asm-compat.h>
+#include <asm/asm-offsets.h>
+#include <asm/bitsperlong.h>
+#include <asm/thread_info.h>
+
+#include "../kernel/head_booke.h" /* for THREAD_NORMSAVE() */
+
+#define GET_VCPU(vcpu, thread)	\
+	PPC_LL	vcpu, THREAD_KVM_VCPU(thread)
+
+#define LONGBYTES		(BITS_PER_LONG / 8)
+
+#define VCPU_GPR(n)     	(VCPU_GPRS + (n * LONGBYTES))
+#define VCPU_GUEST_SPRG(n)	(VCPU_GUEST_SPRGS + (n * LONGBYTES))
+
+/* The host stack layout: */
+#define HOST_R1         (0 * LONGBYTES) /* Implied by stwu. */
+#define HOST_CALLEE_LR  (1 * LONGBYTES)
+#define HOST_RUN        (2 * LONGBYTES) /* struct kvm_run */
+/*
+ * r2 is special: it holds 'current', and it made nonvolatile in the
+ * kernel with the -ffixed-r2 gcc option.
+ */
+#define HOST_R2         (3 * LONGBYTES)
+#define HOST_CR         (4 * LONGBYTES)
+#define HOST_NV_GPRS    (5 * LONGBYTES)
+#define HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * LONGBYTES))
+#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + LONGBYTES)
+#define HOST_STACK_SIZE ((HOST_MIN_STACK_SIZE + 15) & ~15) /* Align. */
+#define HOST_STACK_LR   (HOST_STACK_SIZE + LONGBYTES) /* In caller stack frame. */
+
+#define NEED_EMU		0x00000001 /* emulation -- save nv regs */
+#define NEED_DEAR		0x00000002 /* save faulting DEAR */
+#define NEED_ESR		0x00000004 /* save faulting ESR */
+
+/*
+ * On entry:
+ * r4 = vcpu, r5 = srr0, r6 = srr1
+ * saved in vcpu: cr, ctr, r3-r13
+ */
+.macro kvm_handler_common intno, srr0, flags
+	/* Restore host stack pointer */
+	PPC_STL	r1, VCPU_GPR(r1)(r4)
+	PPC_STL	r2, VCPU_GPR(r2)(r4)
+	PPC_LL	r1, VCPU_HOST_STACK(r4)
+	PPC_LL	r2, HOST_R2(r1)
+
+	mfspr	r10, SPRN_PID
+	lwz	r8, VCPU_HOST_PID(r4)
+	PPC_LL	r11, VCPU_SHARED(r4)
+	PPC_STL	r14, VCPU_GPR(r14)(r4) /* We need a non-volatile GPR. */
+	li	r14, \intno
+
+	stw	r10, VCPU_GUEST_PID(r4)
+	mtspr	SPRN_PID, r8
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+	/* save exit time */
+1:	mfspr	r7, SPRN_TBRU
+	mfspr	r8, SPRN_TBRL
+	mfspr	r9, SPRN_TBRU
+	cmpw	r9, r7
+	stw	r8, VCPU_TIMING_EXIT_TBL(r4)
+	bne-	1b
+	stw	r9, VCPU_TIMING_EXIT_TBU(r4)
+#endif
+
+	oris	r8, r6, MSR_CE@h
+	PPC_STD(r6, VCPU_SHARED_MSR, r11)
+	ori	r8, r8, MSR_ME | MSR_RI
+	PPC_STL	r5, VCPU_PC(r4)
+
+	/*
+	 * Make sure CE/ME/RI are set (if appropriate for exception type)
+	 * whether or not the guest had it set.  Since mfmsr/mtmsr are
+	 * somewhat expensive, skip in the common case where the guest
+	 * had all these bits set (and thus they're still set if
+	 * appropriate for the exception type).
+	 */
+	cmpw	r6, r8
+	beq	1f
+	mfmsr	r7
+	.if	\srr0 != SPRN_MCSRR0 && \srr0 != SPRN_CSRR0
+	oris	r7, r7, MSR_CE@h
+	.endif
+	.if	\srr0 != SPRN_MCSRR0
+	ori	r7, r7, MSR_ME | MSR_RI
+	.endif
+	mtmsr	r7
+1:
+
+	.if	\flags & NEED_EMU
+	/*
+	 * This assumes you have external PID support.
+	 * To support a bookehv CPU without external PID, you'll
+	 * need to look up the TLB entry and create a temporary mapping.
+	 *
+	 * FIXME: we don't currently handle if the lwepx faults.  PR-mode
+	 * booke doesn't handle it either.  Since Linux doesn't use
+	 * broadcast tlbivax anymore, the only way this should happen is
+	 * if the guest maps its memory execute-but-not-read, or if we
+	 * somehow take a TLB miss in the middle of this entry code and
+	 * evict the relevant entry.  On e500mc, all kernel lowmem is
+	 * bolted into TLB1 large page mappings, and we don't use
+	 * broadcast invalidates, so we should not take a TLB miss here.
+	 *
+	 * Later we'll need to deal with faults here.  Disallowing guest
+	 * mappings that are execute-but-not-read could be an option on
+	 * e500mc, but not on chips with an LRAT if it is used.
+	 */
+
+	mfspr	r3, SPRN_EPLC	/* will already have correct ELPID and EGS */
+	PPC_STL	r15, VCPU_GPR(r15)(r4)
+	PPC_STL	r16, VCPU_GPR(r16)(r4)
+	PPC_STL	r17, VCPU_GPR(r17)(r4)
+	PPC_STL	r18, VCPU_GPR(r18)(r4)
+	PPC_STL	r19, VCPU_GPR(r19)(r4)
+	mr	r8, r3
+	PPC_STL	r20, VCPU_GPR(r20)(r4)
+	rlwimi	r8, r6, EPC_EAS_SHIFT - MSR_IR_LG, EPC_EAS
+	PPC_STL	r21, VCPU_GPR(r21)(r4)
+	rlwimi	r8, r6, EPC_EPR_SHIFT - MSR_PR_LG, EPC_EPR
+	PPC_STL	r22, VCPU_GPR(r22)(r4)
+	rlwimi	r8, r10, EPC_EPID_SHIFT, EPC_EPID
+	PPC_STL	r23, VCPU_GPR(r23)(r4)
+	PPC_STL	r24, VCPU_GPR(r24)(r4)
+	PPC_STL	r25, VCPU_GPR(r25)(r4)
+	PPC_STL	r26, VCPU_GPR(r26)(r4)
+	PPC_STL	r27, VCPU_GPR(r27)(r4)
+	PPC_STL	r28, VCPU_GPR(r28)(r4)
+	PPC_STL	r29, VCPU_GPR(r29)(r4)
+	PPC_STL	r30, VCPU_GPR(r30)(r4)
+	PPC_STL	r31, VCPU_GPR(r31)(r4)
+	mtspr	SPRN_EPLC, r8
+
+	/* disable preemption, so we are sure we hit the fixup handler */
+#ifdef CONFIG_PPC64
+	clrrdi	r8,r1,THREAD_SHIFT
+#else
+	rlwinm	r8,r1,0,0,31-THREAD_SHIFT       /* current thread_info */
+#endif
+	li	r7, 1
+	stw	r7, TI_PREEMPT(r8)
+
+	isync
+
+	/*
+	 * In case the read goes wrong, we catch it and write an invalid value
+	 * in LAST_INST instead.
+	 */
+1:	lwepx	r9, 0, r5
+2:
+.section .fixup, "ax"
+3:	li	r9, KVM_INST_FETCH_FAILED
+	b	2b
+.previous
+.section __ex_table,"a"
+	PPC_LONG_ALIGN
+	PPC_LONG 1b,3b
+.previous
+
+	mtspr	SPRN_EPLC, r3
+	li	r7, 0
+	stw	r7, TI_PREEMPT(r8)
+	stw	r9, VCPU_LAST_INST(r4)
+	.endif
+
+	.if	\flags & NEED_ESR
+	mfspr	r8, SPRN_ESR
+	PPC_STL	r8, VCPU_FAULT_ESR(r4)
+	.endif
+
+	.if	\flags & NEED_DEAR
+	mfspr	r9, SPRN_DEAR
+	PPC_STL	r9, VCPU_FAULT_DEAR(r4)
+	.endif
+
+	b	kvmppc_resume_host
+.endm
+
+/*
+ * For input register values, see arch/powerpc/include/asm/kvm_booke_hv_asm.h
+ */
+.macro kvm_handler intno srr0, srr1, flags
+_GLOBAL(kvmppc_handler_\intno\()_\srr1)
+	GET_VCPU(r11, r10)
+	PPC_STL r3, VCPU_GPR(r3)(r11)
+	mfspr	r3, SPRN_SPRG_RSCRATCH0
+	PPC_STL	r4, VCPU_GPR(r4)(r11)
+	PPC_LL	r4, THREAD_NORMSAVE(0)(r10)
+	PPC_STL	r5, VCPU_GPR(r5)(r11)
+	stw	r13, VCPU_CR(r11)
+	mfspr	r5, \srr0
+	PPC_STL	r3, VCPU_GPR(r10)(r11)
+	PPC_LL	r3, THREAD_NORMSAVE(2)(r10)
+	PPC_STL	r6, VCPU_GPR(r6)(r11)
+	PPC_STL	r4, VCPU_GPR(r11)(r11)
+	mfspr	r6, \srr1
+	PPC_STL	r7, VCPU_GPR(r7)(r11)
+	PPC_STL	r8, VCPU_GPR(r8)(r11)
+	PPC_STL	r9, VCPU_GPR(r9)(r11)
+	PPC_STL r3, VCPU_GPR(r13)(r11)
+	mfctr	r7
+	PPC_STL	r12, VCPU_GPR(r12)(r11)
+	PPC_STL	r7, VCPU_CTR(r11)
+	mr	r4, r11
+	kvm_handler_common \intno, \srr0, \flags
+.endm
+
+.macro kvm_lvl_handler intno scratch srr0, srr1, flags
+_GLOBAL(kvmppc_handler_\intno\()_\srr1)
+	mfspr	r10, SPRN_SPRG_THREAD
+	GET_VCPU(r11, r10)
+	PPC_STL r3, VCPU_GPR(r3)(r11)
+	mfspr	r3, \scratch
+	PPC_STL	r4, VCPU_GPR(r4)(r11)
+	PPC_LL	r4, GPR9(r8)
+	PPC_STL	r5, VCPU_GPR(r5)(r11)
+	stw	r9, VCPU_CR(r11)
+	mfspr	r5, \srr0
+	PPC_STL	r3, VCPU_GPR(r8)(r11)
+	PPC_LL	r3, GPR10(r8)
+	PPC_STL	r6, VCPU_GPR(r6)(r11)
+	PPC_STL	r4, VCPU_GPR(r9)(r11)
+	mfspr	r6, \srr1
+	PPC_LL	r4, GPR11(r8)
+	PPC_STL	r7, VCPU_GPR(r7)(r11)
+	PPC_STL r3, VCPU_GPR(r10)(r11)
+	mfctr	r7
+	PPC_STL	r12, VCPU_GPR(r12)(r11)
+	PPC_STL r13, VCPU_GPR(r13)(r11)
+	PPC_STL	r4, VCPU_GPR(r11)(r11)
+	PPC_STL	r7, VCPU_CTR(r11)
+	mr	r4, r11
+	kvm_handler_common \intno, \srr0, \flags
+.endm
+
+kvm_lvl_handler BOOKE_INTERRUPT_CRITICAL, \
+	SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_MACHINE_CHECK, \
+	SPRN_SPRG_RSCRATCH_MC, SPRN_MCSRR0, SPRN_MCSRR1, 0
+kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, \
+	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR)
+kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR
+kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \
+	SPRN_SRR0, SPRN_SRR1, (NEED_DEAR | NEED_ESR)
+kvm_handler BOOKE_INTERRUPT_PROGRAM, SPRN_SRR0, SPRN_SRR1, NEED_ESR
+kvm_handler BOOKE_INTERRUPT_FP_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SYSCALL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_AP_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_DECREMENTER, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_FIT, SPRN_SRR0, SPRN_SRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_WATCHDOG, \
+	SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_handler BOOKE_INTERRUPT_DTLB_MISS, \
+	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
+kvm_handler BOOKE_INTERRUPT_ITLB_MISS, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_FP_DATA, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_SPE_FP_ROUND, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_PERFORMANCE_MONITOR, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_DOORBELL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_DOORBELL_CRITICAL, \
+	SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_handler BOOKE_INTERRUPT_HV_PRIV, SPRN_SRR0, SPRN_SRR1, NEED_EMU
+kvm_handler BOOKE_INTERRUPT_HV_SYSCALL, SPRN_SRR0, SPRN_SRR1, 0
+kvm_handler BOOKE_INTERRUPT_GUEST_DBELL, SPRN_GSRR0, SPRN_GSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_GUEST_DBELL_CRIT, \
+	SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \
+	SPRN_SPRG_RSCRATCH_CRIT, SPRN_CSRR0, SPRN_CSRR1, 0
+kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \
+	SPRN_SPRG_RSCRATCH_DBG, SPRN_DSRR0, SPRN_DSRR1, 0
+
+
+/* Registers:
+ *  SPRG_SCRATCH0: guest r10
+ *  r4: vcpu pointer
+ *  r11: vcpu->arch.shared
+ *  r14: KVM exit number
+ */
+_GLOBAL(kvmppc_resume_host)
+	/* Save remaining volatile guest register state to vcpu. */
+	mfspr	r3, SPRN_VRSAVE
+	PPC_STL	r0, VCPU_GPR(r0)(r4)
+	mflr	r5
+	mfspr	r6, SPRN_SPRG4
+	PPC_STL	r5, VCPU_LR(r4)
+	mfspr	r7, SPRN_SPRG5
+	stw	r3, VCPU_VRSAVE(r4)
+	PPC_STD(r6, VCPU_SHARED_SPRG4, r11)
+	mfspr	r8, SPRN_SPRG6
+	PPC_STD(r7, VCPU_SHARED_SPRG5, r11)
+	mfspr	r9, SPRN_SPRG7
+	PPC_STD(r8, VCPU_SHARED_SPRG6, r11)
+	mfxer	r3
+	PPC_STD(r9, VCPU_SHARED_SPRG7, r11)
+
+	/* save guest MAS registers and restore host mas4 & mas6 */
+	mfspr	r5, SPRN_MAS0
+	PPC_STL	r3, VCPU_XER(r4)
+	mfspr	r6, SPRN_MAS1
+	stw	r5, VCPU_SHARED_MAS0(r11)
+	mfspr	r7, SPRN_MAS2
+	stw	r6, VCPU_SHARED_MAS1(r11)
+	PPC_STD(r7, VCPU_SHARED_MAS2, r11)
+	mfspr	r5, SPRN_MAS3
+	mfspr	r6, SPRN_MAS4
+	stw	r5, VCPU_SHARED_MAS7_3+4(r11)
+	mfspr	r7, SPRN_MAS6
+	stw	r6, VCPU_SHARED_MAS4(r11)
+	mfspr	r5, SPRN_MAS7
+	lwz	r6, VCPU_HOST_MAS4(r4)
+	stw	r7, VCPU_SHARED_MAS6(r11)
+	lwz	r8, VCPU_HOST_MAS6(r4)
+	mtspr	SPRN_MAS4, r6
+	stw	r5, VCPU_SHARED_MAS7_3+0(r11)
+	mtspr	SPRN_MAS6, r8
+	/* Enable MAS register updates via exception */
+	mfspr	r3, SPRN_EPCR
+	rlwinm	r3, r3, 0, ~SPRN_EPCR_DMIUH
+	mtspr	SPRN_EPCR, r3
+	isync
+
+	/* Switch to kernel stack and jump to handler. */
+	PPC_LL	r3, HOST_RUN(r1)
+	mr	r5, r14 /* intno */
+	mr	r14, r4 /* Save vcpu pointer. */
+	bl	kvmppc_handle_exit
+
+	/* Restore vcpu pointer and the nonvolatiles we used. */
+	mr	r4, r14
+	PPC_LL	r14, VCPU_GPR(r14)(r4)
+
+	andi.	r5, r3, RESUME_FLAG_NV
+	beq	skip_nv_load
+	PPC_LL	r15, VCPU_GPR(r15)(r4)
+	PPC_LL	r16, VCPU_GPR(r16)(r4)
+	PPC_LL	r17, VCPU_GPR(r17)(r4)
+	PPC_LL	r18, VCPU_GPR(r18)(r4)
+	PPC_LL	r19, VCPU_GPR(r19)(r4)
+	PPC_LL	r20, VCPU_GPR(r20)(r4)
+	PPC_LL	r21, VCPU_GPR(r21)(r4)
+	PPC_LL	r22, VCPU_GPR(r22)(r4)
+	PPC_LL	r23, VCPU_GPR(r23)(r4)
+	PPC_LL	r24, VCPU_GPR(r24)(r4)
+	PPC_LL	r25, VCPU_GPR(r25)(r4)
+	PPC_LL	r26, VCPU_GPR(r26)(r4)
+	PPC_LL	r27, VCPU_GPR(r27)(r4)
+	PPC_LL	r28, VCPU_GPR(r28)(r4)
+	PPC_LL	r29, VCPU_GPR(r29)(r4)
+	PPC_LL	r30, VCPU_GPR(r30)(r4)
+	PPC_LL	r31, VCPU_GPR(r31)(r4)
+skip_nv_load:
+	/* Should we return to the guest? */
+	andi.	r5, r3, RESUME_FLAG_HOST
+	beq	lightweight_exit
+
+	srawi	r3, r3, 2 /* Shift -ERR back down. */
+
+heavyweight_exit:
+	/* Not returning to guest. */
+	PPC_LL	r5, HOST_STACK_LR(r1)
+	lwz	r6, HOST_CR(r1)
+
+	/*
+	 * We already saved guest volatile register state; now save the
+	 * non-volatiles.
+	 */
+
+	PPC_STL	r15, VCPU_GPR(r15)(r4)
+	PPC_STL	r16, VCPU_GPR(r16)(r4)
+	PPC_STL	r17, VCPU_GPR(r17)(r4)
+	PPC_STL	r18, VCPU_GPR(r18)(r4)
+	PPC_STL	r19, VCPU_GPR(r19)(r4)
+	PPC_STL	r20, VCPU_GPR(r20)(r4)
+	PPC_STL	r21, VCPU_GPR(r21)(r4)
+	PPC_STL	r22, VCPU_GPR(r22)(r4)
+	PPC_STL	r23, VCPU_GPR(r23)(r4)
+	PPC_STL	r24, VCPU_GPR(r24)(r4)
+	PPC_STL	r25, VCPU_GPR(r25)(r4)
+	PPC_STL	r26, VCPU_GPR(r26)(r4)
+	PPC_STL	r27, VCPU_GPR(r27)(r4)
+	PPC_STL	r28, VCPU_GPR(r28)(r4)
+	PPC_STL	r29, VCPU_GPR(r29)(r4)
+	PPC_STL	r30, VCPU_GPR(r30)(r4)
+	PPC_STL	r31, VCPU_GPR(r31)(r4)
+
+	/* Load host non-volatile register state from host stack. */
+	PPC_LL	r14, HOST_NV_GPR(r14)(r1)
+	PPC_LL	r15, HOST_NV_GPR(r15)(r1)
+	PPC_LL	r16, HOST_NV_GPR(r16)(r1)
+	PPC_LL	r17, HOST_NV_GPR(r17)(r1)
+	PPC_LL	r18, HOST_NV_GPR(r18)(r1)
+	PPC_LL	r19, HOST_NV_GPR(r19)(r1)
+	PPC_LL	r20, HOST_NV_GPR(r20)(r1)
+	PPC_LL	r21, HOST_NV_GPR(r21)(r1)
+	PPC_LL	r22, HOST_NV_GPR(r22)(r1)
+	PPC_LL	r23, HOST_NV_GPR(r23)(r1)
+	PPC_LL	r24, HOST_NV_GPR(r24)(r1)
+	PPC_LL	r25, HOST_NV_GPR(r25)(r1)
+	PPC_LL	r26, HOST_NV_GPR(r26)(r1)
+	PPC_LL	r27, HOST_NV_GPR(r27)(r1)
+	PPC_LL	r28, HOST_NV_GPR(r28)(r1)
+	PPC_LL	r29, HOST_NV_GPR(r29)(r1)
+	PPC_LL	r30, HOST_NV_GPR(r30)(r1)
+	PPC_LL	r31, HOST_NV_GPR(r31)(r1)
+
+	/* Return to kvm_vcpu_run(). */
+	mtlr	r5
+	mtcr	r6
+	addi	r1, r1, HOST_STACK_SIZE
+	/* r3 still contains the return code from kvmppc_handle_exit(). */
+	blr
+
+/* Registers:
+ *  r3: kvm_run pointer
+ *  r4: vcpu pointer
+ */
+_GLOBAL(__kvmppc_vcpu_run)
+	stwu	r1, -HOST_STACK_SIZE(r1)
+	PPC_STL	r1, VCPU_HOST_STACK(r4)	/* Save stack pointer to vcpu. */
+
+	/* Save host state to stack. */
+	PPC_STL	r3, HOST_RUN(r1)
+	mflr	r3
+	mfcr	r5
+	PPC_STL	r3, HOST_STACK_LR(r1)
+
+	stw	r5, HOST_CR(r1)
+
+	/* Save host non-volatile register state to stack. */
+	PPC_STL	r14, HOST_NV_GPR(r14)(r1)
+	PPC_STL	r15, HOST_NV_GPR(r15)(r1)
+	PPC_STL	r16, HOST_NV_GPR(r16)(r1)
+	PPC_STL	r17, HOST_NV_GPR(r17)(r1)
+	PPC_STL	r18, HOST_NV_GPR(r18)(r1)
+	PPC_STL	r19, HOST_NV_GPR(r19)(r1)
+	PPC_STL	r20, HOST_NV_GPR(r20)(r1)
+	PPC_STL	r21, HOST_NV_GPR(r21)(r1)
+	PPC_STL	r22, HOST_NV_GPR(r22)(r1)
+	PPC_STL	r23, HOST_NV_GPR(r23)(r1)
+	PPC_STL	r24, HOST_NV_GPR(r24)(r1)
+	PPC_STL	r25, HOST_NV_GPR(r25)(r1)
+	PPC_STL	r26, HOST_NV_GPR(r26)(r1)
+	PPC_STL	r27, HOST_NV_GPR(r27)(r1)
+	PPC_STL	r28, HOST_NV_GPR(r28)(r1)
+	PPC_STL	r29, HOST_NV_GPR(r29)(r1)
+	PPC_STL	r30, HOST_NV_GPR(r30)(r1)
+	PPC_STL	r31, HOST_NV_GPR(r31)(r1)
+
+	/* Load guest non-volatiles. */
+	PPC_LL	r14, VCPU_GPR(r14)(r4)
+	PPC_LL	r15, VCPU_GPR(r15)(r4)
+	PPC_LL	r16, VCPU_GPR(r16)(r4)
+	PPC_LL	r17, VCPU_GPR(r17)(r4)
+	PPC_LL	r18, VCPU_GPR(r18)(r4)
+	PPC_LL	r19, VCPU_GPR(r19)(r4)
+	PPC_LL	r20, VCPU_GPR(r20)(r4)
+	PPC_LL	r21, VCPU_GPR(r21)(r4)
+	PPC_LL	r22, VCPU_GPR(r22)(r4)
+	PPC_LL	r23, VCPU_GPR(r23)(r4)
+	PPC_LL	r24, VCPU_GPR(r24)(r4)
+	PPC_LL	r25, VCPU_GPR(r25)(r4)
+	PPC_LL	r26, VCPU_GPR(r26)(r4)
+	PPC_LL	r27, VCPU_GPR(r27)(r4)
+	PPC_LL	r28, VCPU_GPR(r28)(r4)
+	PPC_LL	r29, VCPU_GPR(r29)(r4)
+	PPC_LL	r30, VCPU_GPR(r30)(r4)
+	PPC_LL	r31, VCPU_GPR(r31)(r4)
+
+
+lightweight_exit:
+	PPC_STL	r2, HOST_R2(r1)
+
+	mfspr	r3, SPRN_PID
+	stw	r3, VCPU_HOST_PID(r4)
+	lwz	r3, VCPU_GUEST_PID(r4)
+	mtspr	SPRN_PID, r3
+
+	PPC_LL	r11, VCPU_SHARED(r4)
+	/* Disable MAS register updates via exception */
+	mfspr	r3, SPRN_EPCR
+	oris	r3, r3, SPRN_EPCR_DMIUH@h
+	mtspr	SPRN_EPCR, r3
+	isync
+	/* Save host mas4 and mas6 and load guest MAS registers */
+	mfspr	r3, SPRN_MAS4
+	stw	r3, VCPU_HOST_MAS4(r4)
+	mfspr	r3, SPRN_MAS6
+	stw	r3, VCPU_HOST_MAS6(r4)
+	lwz	r3, VCPU_SHARED_MAS0(r11)
+	lwz	r5, VCPU_SHARED_MAS1(r11)
+	PPC_LD(r6, VCPU_SHARED_MAS2, r11)
+	lwz	r7, VCPU_SHARED_MAS7_3+4(r11)
+	lwz	r8, VCPU_SHARED_MAS4(r11)
+	mtspr	SPRN_MAS0, r3
+	mtspr	SPRN_MAS1, r5
+	mtspr	SPRN_MAS2, r6
+	mtspr	SPRN_MAS3, r7
+	mtspr	SPRN_MAS4, r8
+	lwz	r3, VCPU_SHARED_MAS6(r11)
+	lwz	r5, VCPU_SHARED_MAS7_3+0(r11)
+	mtspr	SPRN_MAS6, r3
+	mtspr	SPRN_MAS7, r5
+
+	/*
+	 * Host interrupt handlers may have clobbered these guest-readable
+	 * SPRGs, so we need to reload them here with the guest's values.
+	 */
+	lwz	r3, VCPU_VRSAVE(r4)
+	PPC_LD(r5, VCPU_SHARED_SPRG4, r11)
+	mtspr	SPRN_VRSAVE, r3
+	PPC_LD(r6, VCPU_SHARED_SPRG5, r11)
+	mtspr	SPRN_SPRG4W, r5
+	PPC_LD(r7, VCPU_SHARED_SPRG6, r11)
+	mtspr	SPRN_SPRG5W, r6
+	PPC_LD(r8, VCPU_SHARED_SPRG7, r11)
+	mtspr	SPRN_SPRG6W, r7
+	mtspr	SPRN_SPRG7W, r8
+
+	/* Load some guest volatiles. */
+	PPC_LL	r3, VCPU_LR(r4)
+	PPC_LL	r5, VCPU_XER(r4)
+	PPC_LL	r6, VCPU_CTR(r4)
+	lwz	r7, VCPU_CR(r4)
+	PPC_LL	r8, VCPU_PC(r4)
+	PPC_LD(r9, VCPU_SHARED_MSR, r11)
+	PPC_LL	r0, VCPU_GPR(r0)(r4)
+	PPC_LL	r1, VCPU_GPR(r1)(r4)
+	PPC_LL	r2, VCPU_GPR(r2)(r4)
+	PPC_LL	r10, VCPU_GPR(r10)(r4)
+	PPC_LL	r11, VCPU_GPR(r11)(r4)
+	PPC_LL	r12, VCPU_GPR(r12)(r4)
+	PPC_LL	r13, VCPU_GPR(r13)(r4)
+	mtlr	r3
+	mtxer	r5
+	mtctr	r6
+	mtsrr0	r8
+	mtsrr1	r9
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+	/* save enter time */
+1:
+	mfspr	r6, SPRN_TBRU
+	mfspr	r9, SPRN_TBRL
+	mfspr	r8, SPRN_TBRU
+	cmpw	r8, r6
+	stw	r9, VCPU_TIMING_LAST_ENTER_TBL(r4)
+	bne	1b
+	stw	r8, VCPU_TIMING_LAST_ENTER_TBU(r4)
+#endif
+
+	/*
+	 * Don't execute any instruction which can change CR after
+	 * below instruction.
+	 */
+	mtcr	r7
+
+	/* Finish loading guest volatiles and jump to guest. */
+	PPC_LL	r5, VCPU_GPR(r5)(r4)
+	PPC_LL	r6, VCPU_GPR(r6)(r4)
+	PPC_LL	r7, VCPU_GPR(r7)(r4)
+	PPC_LL	r8, VCPU_GPR(r8)(r4)
+	PPC_LL	r9, VCPU_GPR(r9)(r4)
+
+	PPC_LL	r3, VCPU_GPR(r3)(r4)
+	PPC_LL	r4, VCPU_GPR(r4)(r4)
+	rfi
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index ddcd896fa2ff..b479ed77c515 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -20,11 +20,282 @@
 #include <asm/reg.h>
 #include <asm/cputable.h>
 #include <asm/tlbflush.h>
-#include <asm/kvm_e500.h>
 #include <asm/kvm_ppc.h>
 
+#include "../mm/mmu_decl.h"
 #include "booke.h"
-#include "e500_tlb.h"
+#include "e500.h"
+
+struct id {
+	unsigned long val;
+	struct id **pentry;
+};
+
+#define NUM_TIDS 256
+
+/*
+ * This table provide mappings from:
+ * (guestAS,guestTID,guestPR) --> ID of physical cpu
+ * guestAS	[0..1]
+ * guestTID	[0..255]
+ * guestPR	[0..1]
+ * ID		[1..255]
+ * Each vcpu keeps one vcpu_id_table.
+ */
+struct vcpu_id_table {
+	struct id id[2][NUM_TIDS][2];
+};
+
+/*
+ * This table provide reversed mappings of vcpu_id_table:
+ * ID --> address of vcpu_id_table item.
+ * Each physical core has one pcpu_id_table.
+ */
+struct pcpu_id_table {
+	struct id *entry[NUM_TIDS];
+};
+
+static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
+
+/* This variable keeps last used shadow ID on local core.
+ * The valid range of shadow ID is [1..255] */
+static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
+
+/*
+ * Allocate a free shadow id and setup a valid sid mapping in given entry.
+ * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_setup_one(struct id *entry)
+{
+	unsigned long sid;
+	int ret = -1;
+
+	sid = ++(__get_cpu_var(pcpu_last_used_sid));
+	if (sid < NUM_TIDS) {
+		__get_cpu_var(pcpu_sids).entry[sid] = entry;
+		entry->val = sid;
+		entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
+		ret = sid;
+	}
+
+	/*
+	 * If sid == NUM_TIDS, we've run out of sids.  We return -1, and
+	 * the caller will invalidate everything and start over.
+	 *
+	 * sid > NUM_TIDS indicates a race, which we disable preemption to
+	 * avoid.
+	 */
+	WARN_ON(sid > NUM_TIDS);
+
+	return ret;
+}
+
+/*
+ * Check if given entry contain a valid shadow id mapping.
+ * An ID mapping is considered valid only if
+ * both vcpu and pcpu know this mapping.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+static inline int local_sid_lookup(struct id *entry)
+{
+	if (entry && entry->val != 0 &&
+	    __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
+	    entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
+		return entry->val;
+	return -1;
+}
+
+/* Invalidate all id mappings on local core -- call with preempt disabled */
+static inline void local_sid_destroy_all(void)
+{
+	__get_cpu_var(pcpu_last_used_sid) = 0;
+	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
+}
+
+static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
+	return vcpu_e500->idt;
+}
+
+static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->idt);
+	vcpu_e500->idt = NULL;
+}
+
+/* Map guest pid to shadow.
+ * We use PID to keep shadow of current guest non-zero PID,
+ * and use PID1 to keep shadow of guest zero PID.
+ * So that guest tlbe with TID=0 can be accessed at any time */
+static void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	preempt_disable();
+	vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu),
+			get_cur_pid(&vcpu_e500->vcpu),
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
+			get_cur_as(&vcpu_e500->vcpu), 0,
+			get_cur_pr(&vcpu_e500->vcpu), 1);
+	preempt_enable();
+}
+
+/* Invalidate all mappings on vcpu */
+static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/* Invalidate one ID mapping on vcpu */
+static inline void kvmppc_e500_id_table_reset_one(
+			       struct kvmppc_vcpu_e500 *vcpu_e500,
+			       int as, int pid, int pr)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+
+	BUG_ON(as >= 2);
+	BUG_ON(pid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	idt->id[as][pid][pr].val = 0;
+	idt->id[as][pid][pr].pentry = NULL;
+
+	/* Update shadow pid when mappings are changed */
+	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+}
+
+/*
+ * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
+ * This function first lookup if a valid mapping exists,
+ * if not, then creates a new one.
+ *
+ * The caller must have preemption disabled, and keep it that way until
+ * it has finished with the returned shadow id (either written into the
+ * TLB or arch.shadow_pid, or discarded).
+ */
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+				 unsigned int as, unsigned int gid,
+				 unsigned int pr, int avoid_recursion)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	int sid;
+
+	BUG_ON(as >= 2);
+	BUG_ON(gid >= NUM_TIDS);
+	BUG_ON(pr >= 2);
+
+	sid = local_sid_lookup(&idt->id[as][gid][pr]);
+
+	while (sid <= 0) {
+		/* No mapping yet */
+		sid = local_sid_setup_one(&idt->id[as][gid][pr]);
+		if (sid <= 0) {
+			_tlbil_all();
+			local_sid_destroy_all();
+		}
+
+		/* Update shadow pid when mappings are changed */
+		if (!avoid_recursion)
+			kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+
+	return sid;
+}
+
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+				      struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	return kvmppc_e500_get_sid(to_e500(vcpu), get_tlb_ts(gtlbe),
+				   get_tlb_tid(gtlbe), get_cur_pr(vcpu), 0);
+}
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	if (vcpu->arch.pid != pid) {
+		vcpu_e500->pid[0] = vcpu->arch.pid = pid;
+		kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	}
+}
+
+/* gtlbe must not be mapped by more than one host tlbe */
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+                           struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	struct vcpu_id_table *idt = vcpu_e500->idt;
+	unsigned int pr, tid, ts, pid;
+	u32 val, eaddr;
+	unsigned long flags;
+
+	ts = get_tlb_ts(gtlbe);
+	tid = get_tlb_tid(gtlbe);
+
+	preempt_disable();
+
+	/* One guest ID may be mapped to two shadow IDs */
+	for (pr = 0; pr < 2; pr++) {
+		/*
+		 * The shadow PID can have a valid mapping on at most one
+		 * host CPU.  In the common case, it will be valid on this
+		 * CPU, in which case we do a local invalidation of the
+		 * specific address.
+		 *
+		 * If the shadow PID is not valid on the current host CPU,
+		 * we invalidate the entire shadow PID.
+		 */
+		pid = local_sid_lookup(&idt->id[ts][tid][pr]);
+		if (pid <= 0) {
+			kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
+			continue;
+		}
+
+		/*
+		 * The guest is invalidating a 4K entry which is in a PID
+		 * that has a valid shadow mapping on this host CPU.  We
+		 * search host TLB to invalidate it's shadow TLB entry,
+		 * similar to __tlbil_va except that we need to look in AS1.
+		 */
+		val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
+		eaddr = get_tlb_eaddr(gtlbe);
+
+		local_irq_save(flags);
+
+		mtspr(SPRN_MAS6, val);
+		asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
+		val = mfspr(SPRN_MAS1);
+		if (val & MAS1_VALID) {
+			mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+			asm volatile("tlbwe");
+		}
+
+		local_irq_restore(flags);
+	}
+
+	preempt_enable();
+}
+
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kvmppc_e500_id_table_reset_all(vcpu_e500);
+}
+
+void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+{
+	/* Recalc shadow pid since MSR changes */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
+}
 
 void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
 {
@@ -36,17 +307,20 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	kvmppc_e500_tlb_load(vcpu, cpu);
+	kvmppc_booke_vcpu_load(vcpu, cpu);
+
+	/* Shadow PID may be expired on local core */
+	kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvmppc_e500_tlb_put(vcpu);
-
 #ifdef CONFIG_SPE
 	if (vcpu->arch.shadow_msr & MSR_SPE)
 		kvmppc_vcpu_disable_spe(vcpu);
 #endif
+
+	kvmppc_booke_vcpu_put(vcpu);
 }
 
 int kvmppc_core_check_processor_compat(void)
@@ -61,6 +335,23 @@ int kvmppc_core_check_processor_compat(void)
 	return r;
 }
 
+static void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	struct kvm_book3e_206_tlb_entry *tlbe;
+
+	/* Insert large initial mapping for guest. */
+	tlbe = get_entry(vcpu_e500, 1, 0);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
+	tlbe->mas2 = 0;
+	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
+
+	/* 4K map for serial output. Used by kernel wrapper. */
+	tlbe = get_entry(vcpu_e500, 1, 1);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
+	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+}
+
 int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -76,32 +367,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
-int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
-                               struct kvm_translation *tr)
-{
-	int index;
-	gva_t eaddr;
-	u8 pid;
-	u8 as;
-
-	eaddr = tr->linear_address;
-	pid = (tr->linear_address >> 32) & 0xff;
-	as = (tr->linear_address >> 40) & 0x1;
-
-	index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
-	if (index < 0) {
-		tr->valid = 0;
-		return 0;
-	}
-
-	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
-	/* XXX what does "writeable" and "usermode" even mean? */
-	tr->valid = 1;
-
-	return 0;
-}
-
 void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -115,19 +380,6 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
 	sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
 
-	sregs->u.e.mas0 = vcpu->arch.shared->mas0;
-	sregs->u.e.mas1 = vcpu->arch.shared->mas1;
-	sregs->u.e.mas2 = vcpu->arch.shared->mas2;
-	sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
-	sregs->u.e.mas4 = vcpu->arch.shared->mas4;
-	sregs->u.e.mas6 = vcpu->arch.shared->mas6;
-
-	sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG);
-	sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg;
-	sregs->u.e.tlbcfg[1] = vcpu_e500->tlb1cfg;
-	sregs->u.e.tlbcfg[2] = 0;
-	sregs->u.e.tlbcfg[3] = 0;
-
 	sregs->u.e.ivor_high[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
 	sregs->u.e.ivor_high[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
 	sregs->u.e.ivor_high[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
@@ -135,11 +387,13 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
 
 	kvmppc_get_sregs_ivor(vcpu, sregs);
+	kvmppc_get_sregs_e500_tlb(vcpu, sregs);
 }
 
 int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int ret;
 
 	if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
 		vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
@@ -147,14 +401,9 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
 	}
 
-	if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
-		vcpu->arch.shared->mas0 = sregs->u.e.mas0;
-		vcpu->arch.shared->mas1 = sregs->u.e.mas1;
-		vcpu->arch.shared->mas2 = sregs->u.e.mas2;
-		vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
-		vcpu->arch.shared->mas4 = sregs->u.e.mas4;
-		vcpu->arch.shared->mas6 = sregs->u.e.mas6;
-	}
+	ret = kvmppc_set_sregs_e500_tlb(vcpu, sregs);
+	if (ret < 0)
+		return ret;
 
 	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
 		return 0;
@@ -193,9 +442,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+		goto uninit_vcpu;
+
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
-		goto uninit_vcpu;
+		goto uninit_id;
 
 	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
 	if (!vcpu->arch.shared)
@@ -205,6 +457,8 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
 uninit_tlb:
 	kvmppc_e500_tlb_uninit(vcpu_e500);
+uninit_id:
+	kvmppc_e500_id_table_free(vcpu_e500);
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_vcpu:
@@ -218,11 +472,21 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
 	free_page((unsigned long)vcpu->arch.shared);
-	kvm_vcpu_uninit(vcpu);
 	kvmppc_e500_tlb_uninit(vcpu_e500);
+	kvmppc_e500_id_table_free(vcpu_e500);
+	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	return 0;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+}
+
 static int __init kvmppc_e500_init(void)
 {
 	int r, i;
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
new file mode 100644
index 000000000000..aa8b81428bf4
--- /dev/null
+++ b/arch/powerpc/kvm/e500.h
@@ -0,0 +1,306 @@
+/*
+ * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu <yu.liu@freescale.com>
+ *         Scott Wood <scottwood@freescale.com>
+ *         Ashish Kalra <ashish.kalra@freescale.com>
+ *         Varun Sethi <varun.sethi@freescale.com>
+ *
+ * Description:
+ * This file is based on arch/powerpc/kvm/44x_tlb.h and
+ * arch/powerpc/include/asm/kvm_44x.h by Hollis Blanchard <hollisb@us.ibm.com>,
+ * Copyright IBM Corp. 2007-2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef KVM_E500_H
+#define KVM_E500_H
+
+#include <linux/kvm_host.h>
+#include <asm/mmu-book3e.h>
+#include <asm/tlb.h>
+
+#define E500_PID_NUM   3
+#define E500_TLB_NUM   2
+
+#define E500_TLB_VALID 1
+#define E500_TLB_DIRTY 2
+#define E500_TLB_BITMAP 4
+
+struct tlbe_ref {
+	pfn_t pfn;
+	unsigned int flags; /* E500_TLB_* */
+};
+
+struct tlbe_priv {
+	struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
+};
+
+#ifdef CONFIG_KVM_E500V2
+struct vcpu_id_table;
+#endif
+
+struct kvmppc_e500_tlb_params {
+	int entries, ways, sets;
+};
+
+struct kvmppc_vcpu_e500 {
+	struct kvm_vcpu vcpu;
+
+	/* Unmodified copy of the guest's TLB -- shared with host userspace. */
+	struct kvm_book3e_206_tlb_entry *gtlb_arch;
+
+	/* Starting entry number in gtlb_arch[] */
+	int gtlb_offset[E500_TLB_NUM];
+
+	/* KVM internal information associated with each guest TLB entry */
+	struct tlbe_priv *gtlb_priv[E500_TLB_NUM];
+
+	struct kvmppc_e500_tlb_params gtlb_params[E500_TLB_NUM];
+
+	unsigned int gtlb_nv[E500_TLB_NUM];
+
+	/*
+	 * information associated with each host TLB entry --
+	 * TLB1 only for now.  If/when guest TLB1 entries can be
+	 * mapped with host TLB0, this will be used for that too.
+	 *
+	 * We don't want to use this for guest TLB0 because then we'd
+	 * have the overhead of doing the translation again even if
+	 * the entry is still in the guest TLB (e.g. we swapped out
+	 * and back, and our host TLB entries got evicted).
+	 */
+	struct tlbe_ref *tlb_refs[E500_TLB_NUM];
+	unsigned int host_tlb1_nv;
+
+	u32 svr;
+	u32 l1csr0;
+	u32 l1csr1;
+	u32 hid0;
+	u32 hid1;
+	u64 mcar;
+
+	struct page **shared_tlb_pages;
+	int num_shared_tlb_pages;
+
+	u64 *g2h_tlb1_map;
+	unsigned int *h2g_tlb1_rmap;
+
+	/* Minimum and maximum address mapped my TLB1 */
+	unsigned long tlb1_min_eaddr;
+	unsigned long tlb1_max_eaddr;
+
+#ifdef CONFIG_KVM_E500V2
+	u32 pid[E500_PID_NUM];
+
+	/* vcpu id table */
+	struct vcpu_id_table *idt;
+#endif
+};
+
+static inline struct kvmppc_vcpu_e500 *to_e500(struct kvm_vcpu *vcpu)
+{
+	return container_of(vcpu, struct kvmppc_vcpu_e500, vcpu);
+}
+
+
+/* This geometry is the legacy default -- can be overridden by userspace */
+#define KVM_E500_TLB0_WAY_SIZE		128
+#define KVM_E500_TLB0_WAY_NUM		2
+
+#define KVM_E500_TLB0_SIZE  (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
+#define KVM_E500_TLB1_SIZE  16
+
+#define index_of(tlbsel, esel)	(((tlbsel) << 16) | ((esel) & 0xFFFF))
+#define tlbsel_of(index)	((index) >> 16)
+#define esel_of(index)		((index) & 0xFFFF)
+
+#define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
+#define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
+#define MAS2_ATTRIB_MASK \
+	  (MAS2_X0 | MAS2_X1)
+#define MAS3_ATTRIB_MASK \
+	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
+	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
+
+int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500,
+				ulong value);
+int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu);
+int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu);
+int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb);
+int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int rt, int ra, int rb);
+int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb);
+int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500);
+void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500);
+
+void kvmppc_get_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+
+
+#ifdef CONFIG_KVM_E500V2
+unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
+				 unsigned int as, unsigned int gid,
+				 unsigned int pr, int avoid_recursion);
+#endif
+
+/* TLB helper functions */
+static inline unsigned int
+get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return (tlbe->mas1 >> 7) & 0x1f;
+}
+
+static inline gva_t get_tlb_eaddr(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return tlbe->mas2 & 0xfffff000;
+}
+
+static inline u64 get_tlb_bytes(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	unsigned int pgsize = get_tlb_size(tlbe);
+	return 1ULL << 10 << pgsize;
+}
+
+static inline gva_t get_tlb_end(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	u64 bytes = get_tlb_bytes(tlbe);
+	return get_tlb_eaddr(tlbe) + bytes - 1;
+}
+
+static inline u64 get_tlb_raddr(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return tlbe->mas7_3 & ~0xfffULL;
+}
+
+static inline unsigned int
+get_tlb_tid(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return (tlbe->mas1 >> 16) & 0xff;
+}
+
+static inline unsigned int
+get_tlb_ts(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return (tlbe->mas1 >> 12) & 0x1;
+}
+
+static inline unsigned int
+get_tlb_v(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return (tlbe->mas1 >> 31) & 0x1;
+}
+
+static inline unsigned int
+get_tlb_iprot(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return (tlbe->mas1 >> 30) & 0x1;
+}
+
+static inline unsigned int
+get_tlb_tsize(const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return (tlbe->mas1 & MAS1_TSIZE_MASK) >> MAS1_TSIZE_SHIFT;
+}
+
+static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.pid & 0xff;
+}
+
+static inline unsigned int get_cur_as(struct kvm_vcpu *vcpu)
+{
+	return !!(vcpu->arch.shared->msr & (MSR_IS | MSR_DS));
+}
+
+static inline unsigned int get_cur_pr(struct kvm_vcpu *vcpu)
+{
+	return !!(vcpu->arch.shared->msr & MSR_PR);
+}
+
+static inline unsigned int get_cur_spid(const struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.shared->mas6 >> 16) & 0xff;
+}
+
+static inline unsigned int get_cur_sas(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.shared->mas6 & 0x1;
+}
+
+static inline unsigned int get_tlb_tlbsel(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Manual says that tlbsel has 2 bits wide.
+	 * Since we only have two TLBs, only lower bit is used.
+	 */
+	return (vcpu->arch.shared->mas0 >> 28) & 0x1;
+}
+
+static inline unsigned int get_tlb_nv_bit(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.shared->mas0 & 0xfff;
+}
+
+static inline unsigned int get_tlb_esel_bit(const struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.shared->mas0 >> 16) & 0xfff;
+}
+
+static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
+			const struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	gpa_t gpa;
+
+	if (!get_tlb_v(tlbe))
+		return 0;
+
+#ifndef CONFIG_KVM_BOOKE_HV
+	/* Does it match current guest AS? */
+	/* XXX what about IS != DS? */
+	if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
+		return 0;
+#endif
+
+	gpa = get_tlb_raddr(tlbe);
+	if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
+		/* Mapping is not for RAM. */
+		return 0;
+
+	return 1;
+}
+
+static inline struct kvm_book3e_206_tlb_entry *get_entry(
+	struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
+{
+	int offset = vcpu_e500->gtlb_offset[tlbsel];
+	return &vcpu_e500->gtlb_arch[offset + entry];
+}
+
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+			   struct kvm_book3e_206_tlb_entry *gtlbe);
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+#define kvmppc_e500_get_tlb_stid(vcpu, gtlbe)       get_tlb_tid(gtlbe)
+#define get_tlbmiss_tid(vcpu)           get_cur_pid(vcpu)
+#define get_tlb_sts(gtlbe)              (gtlbe->mas1 & MAS1_TS)
+#else
+unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
+				      struct kvm_book3e_206_tlb_entry *gtlbe);
+
+static inline unsigned int get_tlbmiss_tid(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	unsigned int tidseld = (vcpu->arch.shared->mas4 >> 16) & 0xf;
+
+	return vcpu_e500->pid[tidseld];
+}
+
+/* Force TS=1 for all guest mappings. */
+#define get_tlb_sts(gtlbe)              (MAS1_TS)
+#endif /* !BOOKE_HV */
+
+#endif /* KVM_E500_H */
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 6d0b2bd54fb0..8b99e076dc81 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -14,27 +14,96 @@
 
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
-#include <asm/kvm_e500.h>
+#include <asm/dbell.h>
 
 #include "booke.h"
-#include "e500_tlb.h"
+#include "e500.h"
 
+#define XOP_MSGSND  206
+#define XOP_MSGCLR  238
 #define XOP_TLBIVAX 786
 #define XOP_TLBSX   914
 #define XOP_TLBRE   946
 #define XOP_TLBWE   978
+#define XOP_TLBILX  18
+
+#ifdef CONFIG_KVM_E500MC
+static int dbell2prio(ulong param)
+{
+	int msg = param & PPC_DBELL_TYPE_MASK;
+	int prio = -1;
+
+	switch (msg) {
+	case PPC_DBELL_TYPE(PPC_DBELL):
+		prio = BOOKE_IRQPRIO_DBELL;
+		break;
+	case PPC_DBELL_TYPE(PPC_DBELL_CRIT):
+		prio = BOOKE_IRQPRIO_DBELL_CRIT;
+		break;
+	default:
+		break;
+	}
+
+	return prio;
+}
+
+static int kvmppc_e500_emul_msgclr(struct kvm_vcpu *vcpu, int rb)
+{
+	ulong param = vcpu->arch.gpr[rb];
+	int prio = dbell2prio(param);
+
+	if (prio < 0)
+		return EMULATE_FAIL;
+
+	clear_bit(prio, &vcpu->arch.pending_exceptions);
+	return EMULATE_DONE;
+}
+
+static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb)
+{
+	ulong param = vcpu->arch.gpr[rb];
+	int prio = dbell2prio(rb);
+	int pir = param & PPC_DBELL_PIR_MASK;
+	int i;
+	struct kvm_vcpu *cvcpu;
+
+	if (prio < 0)
+		return EMULATE_FAIL;
+
+	kvm_for_each_vcpu(i, cvcpu, vcpu->kvm) {
+		int cpir = cvcpu->arch.shared->pir;
+		if ((param & PPC_DBELL_MSG_BRDCAST) || (cpir == pir)) {
+			set_bit(prio, &cvcpu->arch.pending_exceptions);
+			kvm_vcpu_kick(cvcpu);
+		}
+	}
+
+	return EMULATE_DONE;
+}
+#endif
 
 int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
 	int emulated = EMULATE_DONE;
-	int ra;
-	int rb;
+	int ra = get_ra(inst);
+	int rb = get_rb(inst);
+	int rt = get_rt(inst);
 
 	switch (get_op(inst)) {
 	case 31:
 		switch (get_xop(inst)) {
 
+#ifdef CONFIG_KVM_E500MC
+		case XOP_MSGSND:
+			emulated = kvmppc_e500_emul_msgsnd(vcpu, rb);
+			break;
+
+		case XOP_MSGCLR:
+			emulated = kvmppc_e500_emul_msgclr(vcpu, rb);
+			break;
+#endif
+
 		case XOP_TLBRE:
 			emulated = kvmppc_e500_emul_tlbre(vcpu);
 			break;
@@ -44,13 +113,14 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 
 		case XOP_TLBSX:
-			rb = get_rb(inst);
 			emulated = kvmppc_e500_emul_tlbsx(vcpu,rb);
 			break;
 
+		case XOP_TLBILX:
+			emulated = kvmppc_e500_emul_tlbilx(vcpu, rt, ra, rb);
+			break;
+
 		case XOP_TLBIVAX:
-			ra = get_ra(inst);
-			rb = get_rb(inst);
 			emulated = kvmppc_e500_emul_tlbivax(vcpu, ra, rb);
 			break;
 
@@ -70,52 +140,63 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
-	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
+#ifndef CONFIG_KVM_BOOKE_HV
 	case SPRN_PID:
 		kvmppc_set_pid(vcpu, spr_val);
 		break;
 	case SPRN_PID1:
 		if (spr_val != 0)
 			return EMULATE_FAIL;
-		vcpu_e500->pid[1] = spr_val; break;
+		vcpu_e500->pid[1] = spr_val;
+		break;
 	case SPRN_PID2:
 		if (spr_val != 0)
 			return EMULATE_FAIL;
-		vcpu_e500->pid[2] = spr_val; break;
+		vcpu_e500->pid[2] = spr_val;
+		break;
 	case SPRN_MAS0:
-		vcpu->arch.shared->mas0 = spr_val; break;
+		vcpu->arch.shared->mas0 = spr_val;
+		break;
 	case SPRN_MAS1:
-		vcpu->arch.shared->mas1 = spr_val; break;
+		vcpu->arch.shared->mas1 = spr_val;
+		break;
 	case SPRN_MAS2:
-		vcpu->arch.shared->mas2 = spr_val; break;
+		vcpu->arch.shared->mas2 = spr_val;
+		break;
 	case SPRN_MAS3:
 		vcpu->arch.shared->mas7_3 &= ~(u64)0xffffffff;
 		vcpu->arch.shared->mas7_3 |= spr_val;
 		break;
 	case SPRN_MAS4:
-		vcpu->arch.shared->mas4 = spr_val; break;
+		vcpu->arch.shared->mas4 = spr_val;
+		break;
 	case SPRN_MAS6:
-		vcpu->arch.shared->mas6 = spr_val; break;
+		vcpu->arch.shared->mas6 = spr_val;
+		break;
 	case SPRN_MAS7:
 		vcpu->arch.shared->mas7_3 &= (u64)0xffffffff;
 		vcpu->arch.shared->mas7_3 |= (u64)spr_val << 32;
 		break;
+#endif
 	case SPRN_L1CSR0:
 		vcpu_e500->l1csr0 = spr_val;
 		vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
 		break;
 	case SPRN_L1CSR1:
-		vcpu_e500->l1csr1 = spr_val; break;
+		vcpu_e500->l1csr1 = spr_val;
+		break;
 	case SPRN_HID0:
-		vcpu_e500->hid0 = spr_val; break;
+		vcpu_e500->hid0 = spr_val;
+		break;
 	case SPRN_HID1:
-		vcpu_e500->hid1 = spr_val; break;
+		vcpu_e500->hid1 = spr_val;
+		break;
 
 	case SPRN_MMUCSR0:
 		emulated = kvmppc_e500_emul_mt_mmucsr0(vcpu_e500,
@@ -135,81 +216,112 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_IVOR35:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val;
 		break;
-
+#ifdef CONFIG_KVM_BOOKE_HV
+	case SPRN_IVOR36:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL] = spr_val;
+		break;
+	case SPRN_IVOR37:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT] = spr_val;
+		break;
+#endif
 	default:
-		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
+		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
-	unsigned long val;
 
 	switch (sprn) {
+#ifndef CONFIG_KVM_BOOKE_HV
 	case SPRN_PID:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[0]); break;
+		*spr_val = vcpu_e500->pid[0];
+		break;
 	case SPRN_PID1:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[1]); break;
+		*spr_val = vcpu_e500->pid[1];
+		break;
 	case SPRN_PID2:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[2]); break;
+		*spr_val = vcpu_e500->pid[2];
+		break;
 	case SPRN_MAS0:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas0); break;
+		*spr_val = vcpu->arch.shared->mas0;
+		break;
 	case SPRN_MAS1:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas1); break;
+		*spr_val = vcpu->arch.shared->mas1;
+		break;
 	case SPRN_MAS2:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas2); break;
+		*spr_val = vcpu->arch.shared->mas2;
+		break;
 	case SPRN_MAS3:
-		val = (u32)vcpu->arch.shared->mas7_3;
-		kvmppc_set_gpr(vcpu, rt, val);
+		*spr_val = (u32)vcpu->arch.shared->mas7_3;
 		break;
 	case SPRN_MAS4:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas4); break;
+		*spr_val = vcpu->arch.shared->mas4;
+		break;
 	case SPRN_MAS6:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas6); break;
+		*spr_val = vcpu->arch.shared->mas6;
+		break;
 	case SPRN_MAS7:
-		val = vcpu->arch.shared->mas7_3 >> 32;
-		kvmppc_set_gpr(vcpu, rt, val);
+		*spr_val = vcpu->arch.shared->mas7_3 >> 32;
 		break;
+#endif
 	case SPRN_TLB0CFG:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;
+		*spr_val = vcpu->arch.tlbcfg[0];
+		break;
 	case SPRN_TLB1CFG:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb1cfg); break;
+		*spr_val = vcpu->arch.tlbcfg[1];
+		break;
 	case SPRN_L1CSR0:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break;
+		*spr_val = vcpu_e500->l1csr0;
+		break;
 	case SPRN_L1CSR1:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr1); break;
+		*spr_val = vcpu_e500->l1csr1;
+		break;
 	case SPRN_HID0:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid0); break;
+		*spr_val = vcpu_e500->hid0;
+		break;
 	case SPRN_HID1:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid1); break;
+		*spr_val = vcpu_e500->hid1;
+		break;
 	case SPRN_SVR:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->svr); break;
+		*spr_val = vcpu_e500->svr;
+		break;
 
 	case SPRN_MMUCSR0:
-		kvmppc_set_gpr(vcpu, rt, 0); break;
+		*spr_val = 0;
+		break;
 
 	case SPRN_MMUCFG:
-		kvmppc_set_gpr(vcpu, rt, mfspr(SPRN_MMUCFG)); break;
+		*spr_val = vcpu->arch.mmucfg;
+		break;
 
 	/* extra exceptions */
 	case SPRN_IVOR32:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
 		break;
 	case SPRN_IVOR33:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
 		break;
 	case SPRN_IVOR34:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
 		break;
 	case SPRN_IVOR35:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]);
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+		break;
+#ifdef CONFIG_KVM_BOOKE_HV
+	case SPRN_IVOR36:
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL];
+		break;
+	case SPRN_IVOR37:
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT];
 		break;
+#endif
 	default:
-		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
+		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, spr_val);
 	}
 
 	return emulated;
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 6e53e4164de1..c510fc961302 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -2,6 +2,9 @@
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Yu Liu, yu.liu@freescale.com
+ *         Scott Wood, scottwood@freescale.com
+ *         Ashish Kalra, ashish.kalra@freescale.com
+ *         Varun Sethi, varun.sethi@freescale.com
  *
  * Description:
  * This file is based on arch/powerpc/kvm/44x_tlb.c,
@@ -26,210 +29,15 @@
 #include <linux/vmalloc.h>
 #include <linux/hugetlb.h>
 #include <asm/kvm_ppc.h>
-#include <asm/kvm_e500.h>
 
-#include "../mm/mmu_decl.h"
-#include "e500_tlb.h"
+#include "e500.h"
 #include "trace.h"
 #include "timing.h"
 
 #define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
 
-struct id {
-	unsigned long val;
-	struct id **pentry;
-};
-
-#define NUM_TIDS 256
-
-/*
- * This table provide mappings from:
- * (guestAS,guestTID,guestPR) --> ID of physical cpu
- * guestAS	[0..1]
- * guestTID	[0..255]
- * guestPR	[0..1]
- * ID		[1..255]
- * Each vcpu keeps one vcpu_id_table.
- */
-struct vcpu_id_table {
-	struct id id[2][NUM_TIDS][2];
-};
-
-/*
- * This table provide reversed mappings of vcpu_id_table:
- * ID --> address of vcpu_id_table item.
- * Each physical core has one pcpu_id_table.
- */
-struct pcpu_id_table {
-	struct id *entry[NUM_TIDS];
-};
-
-static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
-
-/* This variable keeps last used shadow ID on local core.
- * The valid range of shadow ID is [1..255] */
-static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
-
 static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
 
-static struct kvm_book3e_206_tlb_entry *get_entry(
-	struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
-{
-	int offset = vcpu_e500->gtlb_offset[tlbsel];
-	return &vcpu_e500->gtlb_arch[offset + entry];
-}
-
-/*
- * Allocate a free shadow id and setup a valid sid mapping in given entry.
- * A mapping is only valid when vcpu_id_table and pcpu_id_table are match.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static inline int local_sid_setup_one(struct id *entry)
-{
-	unsigned long sid;
-	int ret = -1;
-
-	sid = ++(__get_cpu_var(pcpu_last_used_sid));
-	if (sid < NUM_TIDS) {
-		__get_cpu_var(pcpu_sids).entry[sid] = entry;
-		entry->val = sid;
-		entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
-		ret = sid;
-	}
-
-	/*
-	 * If sid == NUM_TIDS, we've run out of sids.  We return -1, and
-	 * the caller will invalidate everything and start over.
-	 *
-	 * sid > NUM_TIDS indicates a race, which we disable preemption to
-	 * avoid.
-	 */
-	WARN_ON(sid > NUM_TIDS);
-
-	return ret;
-}
-
-/*
- * Check if given entry contain a valid shadow id mapping.
- * An ID mapping is considered valid only if
- * both vcpu and pcpu know this mapping.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static inline int local_sid_lookup(struct id *entry)
-{
-	if (entry && entry->val != 0 &&
-	    __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
-	    entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
-		return entry->val;
-	return -1;
-}
-
-/* Invalidate all id mappings on local core -- call with preempt disabled */
-static inline void local_sid_destroy_all(void)
-{
-	__get_cpu_var(pcpu_last_used_sid) = 0;
-	memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
-}
-
-static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL);
-	return vcpu_e500->idt;
-}
-
-static void kvmppc_e500_id_table_free(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	kfree(vcpu_e500->idt);
-}
-
-/* Invalidate all mappings on vcpu */
-static void kvmppc_e500_id_table_reset_all(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	memset(vcpu_e500->idt, 0, sizeof(struct vcpu_id_table));
-
-	/* Update shadow pid when mappings are changed */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-/* Invalidate one ID mapping on vcpu */
-static inline void kvmppc_e500_id_table_reset_one(
-			       struct kvmppc_vcpu_e500 *vcpu_e500,
-			       int as, int pid, int pr)
-{
-	struct vcpu_id_table *idt = vcpu_e500->idt;
-
-	BUG_ON(as >= 2);
-	BUG_ON(pid >= NUM_TIDS);
-	BUG_ON(pr >= 2);
-
-	idt->id[as][pid][pr].val = 0;
-	idt->id[as][pid][pr].pentry = NULL;
-
-	/* Update shadow pid when mappings are changed */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-/*
- * Map guest (vcpu,AS,ID,PR) to physical core shadow id.
- * This function first lookup if a valid mapping exists,
- * if not, then creates a new one.
- *
- * The caller must have preemption disabled, and keep it that way until
- * it has finished with the returned shadow id (either written into the
- * TLB or arch.shadow_pid, or discarded).
- */
-static unsigned int kvmppc_e500_get_sid(struct kvmppc_vcpu_e500 *vcpu_e500,
-					unsigned int as, unsigned int gid,
-					unsigned int pr, int avoid_recursion)
-{
-	struct vcpu_id_table *idt = vcpu_e500->idt;
-	int sid;
-
-	BUG_ON(as >= 2);
-	BUG_ON(gid >= NUM_TIDS);
-	BUG_ON(pr >= 2);
-
-	sid = local_sid_lookup(&idt->id[as][gid][pr]);
-
-	while (sid <= 0) {
-		/* No mapping yet */
-		sid = local_sid_setup_one(&idt->id[as][gid][pr]);
-		if (sid <= 0) {
-			_tlbil_all();
-			local_sid_destroy_all();
-		}
-
-		/* Update shadow pid when mappings are changed */
-		if (!avoid_recursion)
-			kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-	}
-
-	return sid;
-}
-
-/* Map guest pid to shadow.
- * We use PID to keep shadow of current guest non-zero PID,
- * and use PID1 to keep shadow of guest zero PID.
- * So that guest tlbe with TID=0 can be accessed at any time */
-void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	preempt_disable();
-	vcpu_e500->vcpu.arch.shadow_pid = kvmppc_e500_get_sid(vcpu_e500,
-			get_cur_as(&vcpu_e500->vcpu),
-			get_cur_pid(&vcpu_e500->vcpu),
-			get_cur_pr(&vcpu_e500->vcpu), 1);
-	vcpu_e500->vcpu.arch.shadow_pid1 = kvmppc_e500_get_sid(vcpu_e500,
-			get_cur_as(&vcpu_e500->vcpu), 0,
-			get_cur_pr(&vcpu_e500->vcpu), 1);
-	preempt_enable();
-}
-
 static inline unsigned int gtlb0_get_next_victim(
 		struct kvmppc_vcpu_e500 *vcpu_e500)
 {
@@ -258,6 +66,7 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
 	/* Mask off reserved bits. */
 	mas3 &= MAS3_ATTRIB_MASK;
 
+#ifndef CONFIG_KVM_BOOKE_HV
 	if (!usermode) {
 		/* Guest is in supervisor mode,
 		 * so we need to translate guest
@@ -265,8 +74,9 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
 		mas3 &= ~E500_TLB_USER_PERM_MASK;
 		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
 	}
-
-	return mas3 | E500_TLB_SUPER_PERM_MASK;
+	mas3 |= E500_TLB_SUPER_PERM_MASK;
+#endif
+	return mas3;
 }
 
 static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
@@ -292,7 +102,16 @@ static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
 	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
 	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
 	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_MAS8, stlbe->mas8);
+#endif
 	asm volatile("isync; tlbwe" : : : "memory");
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	/* Must clear mas8 for other host tlbwe's */
+	mtspr(SPRN_MAS8, 0);
+	isync();
+#endif
 	local_irq_restore(flags);
 
 	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
@@ -337,6 +156,7 @@ static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 }
 
+#ifdef CONFIG_KVM_E500V2
 void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -361,75 +181,41 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
 	preempt_enable();
 }
-
-void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
-	/* Shadow PID may be expired on local core */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-}
-
-void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
-{
-}
+#endif
 
 static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
 				int tlbsel, int esel)
 {
 	struct kvm_book3e_206_tlb_entry *gtlbe =
 		get_entry(vcpu_e500, tlbsel, esel);
-	struct vcpu_id_table *idt = vcpu_e500->idt;
-	unsigned int pr, tid, ts, pid;
-	u32 val, eaddr;
-	unsigned long flags;
-
-	ts = get_tlb_ts(gtlbe);
-	tid = get_tlb_tid(gtlbe);
-
-	preempt_disable();
-
-	/* One guest ID may be mapped to two shadow IDs */
-	for (pr = 0; pr < 2; pr++) {
-		/*
-		 * The shadow PID can have a valid mapping on at most one
-		 * host CPU.  In the common case, it will be valid on this
-		 * CPU, in which case (for TLB0) we do a local invalidation
-		 * of the specific address.
-		 *
-		 * If the shadow PID is not valid on the current host CPU, or
-		 * if we're invalidating a TLB1 entry, we invalidate the
-		 * entire shadow PID.
-		 */
-		if (tlbsel == 1 ||
-		    (pid = local_sid_lookup(&idt->id[ts][tid][pr])) <= 0) {
-			kvmppc_e500_id_table_reset_one(vcpu_e500, ts, tid, pr);
-			continue;
-		}
 
-		/*
-		 * The guest is invalidating a TLB0 entry which is in a PID
-		 * that has a valid shadow mapping on this host CPU.  We
-		 * search host TLB0 to invalidate it's shadow TLB entry,
-		 * similar to __tlbil_va except that we need to look in AS1.
-		 */
-		val = (pid << MAS6_SPID_SHIFT) | MAS6_SAS;
-		eaddr = get_tlb_eaddr(gtlbe);
+	if (tlbsel == 1 &&
+	    vcpu_e500->gtlb_priv[1][esel].ref.flags & E500_TLB_BITMAP) {
+		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
+		int hw_tlb_indx;
+		unsigned long flags;
 
 		local_irq_save(flags);
-
-		mtspr(SPRN_MAS6, val);
-		asm volatile("tlbsx 0, %[eaddr]" : : [eaddr] "r" (eaddr));
-		val = mfspr(SPRN_MAS1);
-		if (val & MAS1_VALID) {
-			mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+		while (tmp) {
+			hw_tlb_indx = __ilog2_u64(tmp & -tmp);
+			mtspr(SPRN_MAS0,
+			      MAS0_TLBSEL(1) |
+			      MAS0_ESEL(to_htlb1_esel(hw_tlb_indx)));
+			mtspr(SPRN_MAS1, 0);
 			asm volatile("tlbwe");
+			vcpu_e500->h2g_tlb1_rmap[hw_tlb_indx] = 0;
+			tmp &= tmp - 1;
 		}
-
+		mb();
+		vcpu_e500->g2h_tlb1_map[esel] = 0;
+		vcpu_e500->gtlb_priv[1][esel].ref.flags &= ~E500_TLB_BITMAP;
 		local_irq_restore(flags);
+
+		return;
 	}
 
-	preempt_enable();
+	/* Guest tlbe is backed by at most one host tlbe per shadow pid. */
+	kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
 }
 
 static int tlb0_set_base(gva_t addr, int sets, int ways)
@@ -475,6 +261,9 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 		set_base = gtlb0_set_base(vcpu_e500, eaddr);
 		size = vcpu_e500->gtlb_params[0].ways;
 	} else {
+		if (eaddr < vcpu_e500->tlb1_min_eaddr ||
+				eaddr > vcpu_e500->tlb1_max_eaddr)
+			return -1;
 		set_base = 0;
 	}
 
@@ -530,6 +319,16 @@ static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 	}
 }
 
+static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	if (vcpu_e500->g2h_tlb1_map)
+		memset(vcpu_e500->g2h_tlb1_map,
+		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries, 0);
+	if (vcpu_e500->h2g_tlb1_rmap)
+		memset(vcpu_e500->h2g_tlb1_rmap,
+		       sizeof(unsigned int) * host_tlb_params[1].entries, 0);
+}
+
 static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int tlbsel = 0;
@@ -547,7 +346,7 @@ static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
 	int stlbsel = 1;
 	int i;
 
-	kvmppc_e500_id_table_reset_all(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
 
 	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
 		struct tlbe_ref *ref =
@@ -562,19 +361,18 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		unsigned int eaddr, int as)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	unsigned int victim, pidsel, tsized;
+	unsigned int victim, tsized;
 	int tlbsel;
 
 	/* since we only have two TLBs, only lower bit is used. */
 	tlbsel = (vcpu->arch.shared->mas4 >> 28) & 0x1;
 	victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
-	pidsel = (vcpu->arch.shared->mas4 >> 16) & 0xf;
 	tsized = (vcpu->arch.shared->mas4 >> 7) & 0x1f;
 
 	vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
 		| MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
 	vcpu->arch.shared->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
-		| MAS1_TID(vcpu_e500->pid[pidsel])
+		| MAS1_TID(get_tlbmiss_tid(vcpu))
 		| MAS1_TSIZE(tsized);
 	vcpu->arch.shared->mas2 = (eaddr & MAS2_EPN)
 		| (vcpu->arch.shared->mas4 & MAS2_ATTRIB_MASK);
@@ -586,23 +384,26 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 
 /* TID must be supplied by the caller */
 static inline void kvmppc_e500_setup_stlbe(
-	struct kvmppc_vcpu_e500 *vcpu_e500,
+	struct kvm_vcpu *vcpu,
 	struct kvm_book3e_206_tlb_entry *gtlbe,
 	int tsize, struct tlbe_ref *ref, u64 gvaddr,
 	struct kvm_book3e_206_tlb_entry *stlbe)
 {
 	pfn_t pfn = ref->pfn;
+	u32 pr = vcpu->arch.shared->msr & MSR_PR;
 
 	BUG_ON(!(ref->flags & E500_TLB_VALID));
 
-	/* Force TS=1 IPROT=0 for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(tsize) | MAS1_TS | MAS1_VALID;
-	stlbe->mas2 = (gvaddr & MAS2_EPN)
-		| e500_shadow_mas2_attrib(gtlbe->mas2,
-				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
-	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT)
-		| e500_shadow_mas3_attrib(gtlbe->mas7_3,
-				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
+	/* Force IPROT=0 for all guest mappings. */
+	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
+	stlbe->mas2 = (gvaddr & MAS2_EPN) |
+		      e500_shadow_mas2_attrib(gtlbe->mas2, pr);
+	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
+#endif
 }
 
 static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -736,7 +537,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	kvmppc_e500_ref_release(ref);
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
-	kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, ref, gvaddr, stlbe);
+	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
+				ref, gvaddr, stlbe);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
@@ -760,7 +562,7 @@ static void kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 /* XXX for both one-one and one-to-many , for now use TLB1 */
 static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
-		struct kvm_book3e_206_tlb_entry *stlbe)
+		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
 {
 	struct tlbe_ref *ref;
 	unsigned int victim;
@@ -773,15 +575,74 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	ref = &vcpu_e500->tlb_refs[1][victim];
 	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, ref);
 
+	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << victim;
+	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+	if (vcpu_e500->h2g_tlb1_rmap[victim]) {
+		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[victim];
+		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << victim);
+	}
+	vcpu_e500->h2g_tlb1_rmap[victim] = esel;
+
 	return victim;
 }
 
-void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+static void kvmppc_recalc_tlb1map_range(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int size = vcpu_e500->gtlb_params[1].entries;
+	unsigned int offset;
+	gva_t eaddr;
+	int i;
+
+	vcpu_e500->tlb1_min_eaddr = ~0UL;
+	vcpu_e500->tlb1_max_eaddr = 0;
+	offset = vcpu_e500->gtlb_offset[1];
+
+	for (i = 0; i < size; i++) {
+		struct kvm_book3e_206_tlb_entry *tlbe =
+			&vcpu_e500->gtlb_arch[offset + i];
+
+		if (!get_tlb_v(tlbe))
+			continue;
+
+		eaddr = get_tlb_eaddr(tlbe);
+		vcpu_e500->tlb1_min_eaddr =
+				min(vcpu_e500->tlb1_min_eaddr, eaddr);
+
+		eaddr = get_tlb_end(tlbe);
+		vcpu_e500->tlb1_max_eaddr =
+				max(vcpu_e500->tlb1_max_eaddr, eaddr);
+	}
+}
+
+static int kvmppc_need_recalc_tlb1map_range(struct kvmppc_vcpu_e500 *vcpu_e500,
+				struct kvm_book3e_206_tlb_entry *gtlbe)
 {
+	unsigned long start, end, size;
+
+	size = get_tlb_bytes(gtlbe);
+	start = get_tlb_eaddr(gtlbe) & ~(size - 1);
+	end = start + size - 1;
+
+	return vcpu_e500->tlb1_min_eaddr == start ||
+			vcpu_e500->tlb1_max_eaddr == end;
+}
+
+/* This function is supposed to be called for a adding a new valid tlb entry */
+static void kvmppc_set_tlb1map_range(struct kvm_vcpu *vcpu,
+				struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	unsigned long start, end, size;
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
-	/* Recalc shadow pid since MSR changes */
-	kvmppc_e500_recalc_shadow_pid(vcpu_e500);
+	if (!get_tlb_v(gtlbe))
+		return;
+
+	size = get_tlb_bytes(gtlbe);
+	start = get_tlb_eaddr(gtlbe) & ~(size - 1);
+	end = start + size - 1;
+
+	vcpu_e500->tlb1_min_eaddr = min(vcpu_e500->tlb1_min_eaddr, start);
+	vcpu_e500->tlb1_max_eaddr = max(vcpu_e500->tlb1_max_eaddr, end);
 }
 
 static inline int kvmppc_e500_gtlbe_invalidate(
@@ -794,6 +655,9 @@ static inline int kvmppc_e500_gtlbe_invalidate(
 	if (unlikely(get_tlb_iprot(gtlbe)))
 		return -1;
 
+	if (tlbsel == 1 && kvmppc_need_recalc_tlb1map_range(vcpu_e500, gtlbe))
+		kvmppc_recalc_tlb1map_range(vcpu_e500);
+
 	gtlbe->mas1 = 0;
 
 	return 0;
@@ -811,7 +675,7 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
 
 	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_id_table_reset_all(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
 
 	return EMULATE_DONE;
 }
@@ -844,7 +708,59 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
 	}
 
 	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_id_table_reset_all(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
+
+	return EMULATE_DONE;
+}
+
+static void tlbilx_all(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
+		       int pid, int rt)
+{
+	struct kvm_book3e_206_tlb_entry *tlbe;
+	int tid, esel;
+
+	/* invalidate all entries */
+	for (esel = 0; esel < vcpu_e500->gtlb_params[tlbsel].entries; esel++) {
+		tlbe = get_entry(vcpu_e500, tlbsel, esel);
+		tid = get_tlb_tid(tlbe);
+		if (rt == 0 || tid == pid) {
+			inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+		}
+	}
+}
+
+static void tlbilx_one(struct kvmppc_vcpu_e500 *vcpu_e500, int pid,
+		       int ra, int rb)
+{
+	int tlbsel, esel;
+	gva_t ea;
+
+	ea = kvmppc_get_gpr(&vcpu_e500->vcpu, rb);
+	if (ra)
+		ea += kvmppc_get_gpr(&vcpu_e500->vcpu, ra);
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, -1);
+		if (esel >= 0) {
+			inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
+			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
+			break;
+		}
+	}
+}
+
+int kvmppc_e500_emul_tlbilx(struct kvm_vcpu *vcpu, int rt, int ra, int rb)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int pid = get_cur_spid(vcpu);
+
+	if (rt == 0 || rt == 1) {
+		tlbilx_all(vcpu_e500, 0, pid, rt);
+		tlbilx_all(vcpu_e500, 1, pid, rt);
+	} else if (rt == 3) {
+		tlbilx_one(vcpu_e500, pid, ra, rb);
+	}
 
 	return EMULATE_DONE;
 }
@@ -929,9 +845,7 @@ static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
 	int stid;
 
 	preempt_disable();
-	stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
-				   get_tlb_tid(gtlbe),
-				   get_cur_pr(&vcpu_e500->vcpu), 0);
+	stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);
 
 	stlbe->mas1 |= MAS1_TID(stid);
 	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
@@ -941,16 +855,21 @@ static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct kvm_book3e_206_tlb_entry *gtlbe;
-	int tlbsel, esel;
+	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
+	int tlbsel, esel, stlbsel, sesel;
+	int recal = 0;
 
 	tlbsel = get_tlb_tlbsel(vcpu);
 	esel = get_tlb_esel(vcpu, tlbsel);
 
 	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
 
-	if (get_tlb_v(gtlbe))
+	if (get_tlb_v(gtlbe)) {
 		inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
+		if ((tlbsel == 1) &&
+			kvmppc_need_recalc_tlb1map_range(vcpu_e500, gtlbe))
+			recal = 1;
+	}
 
 	gtlbe->mas1 = vcpu->arch.shared->mas1;
 	gtlbe->mas2 = vcpu->arch.shared->mas2;
@@ -959,10 +878,20 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	trace_kvm_booke206_gtlb_write(vcpu->arch.shared->mas0, gtlbe->mas1,
 	                              gtlbe->mas2, gtlbe->mas7_3);
 
+	if (tlbsel == 1) {
+		/*
+		 * If a valid tlb1 entry is overwritten then recalculate the
+		 * min/max TLB1 map address range otherwise no need to look
+		 * in tlb1 array.
+		 */
+		if (recal)
+			kvmppc_recalc_tlb1map_range(vcpu_e500);
+		else
+			kvmppc_set_tlb1map_range(vcpu, gtlbe);
+	}
+
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
-		struct kvm_book3e_206_tlb_entry stlbe;
-		int stlbsel, sesel;
 		u64 eaddr;
 		u64 raddr;
 
@@ -989,7 +918,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 			 * are mapped on the fly. */
 			stlbsel = 1;
 			sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
-					raddr >> PAGE_SHIFT, gtlbe, &stlbe);
+				    raddr >> PAGE_SHIFT, gtlbe, &stlbe, esel);
 			break;
 
 		default:
@@ -1003,6 +932,48 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
+				  gva_t eaddr, unsigned int pid, int as)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int esel, tlbsel;
+
+	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
+		esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
+		if (esel >= 0)
+			return index_of(tlbsel, esel);
+	}
+
+	return -1;
+}
+
+/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
+int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
+                               struct kvm_translation *tr)
+{
+	int index;
+	gva_t eaddr;
+	u8 pid;
+	u8 as;
+
+	eaddr = tr->linear_address;
+	pid = (tr->linear_address >> 32) & 0xff;
+	as = (tr->linear_address >> 40) & 0x1;
+
+	index = kvmppc_e500_tlb_search(vcpu, eaddr, pid, as);
+	if (index < 0) {
+		tr->valid = 0;
+		return 0;
+	}
+
+	tr->physical_address = kvmppc_mmu_xlate(vcpu, index, eaddr);
+	/* XXX what does "writeable" and "usermode" even mean? */
+	tr->valid = 1;
+
+	return 0;
+}
+
+
 int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
 	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
@@ -1066,7 +1037,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 		sesel = 0; /* unused */
 		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
-		kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, BOOK3E_PAGESZ_4K,
+		kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
 					&priv->ref, eaddr, &stlbe);
 		break;
 
@@ -1075,7 +1046,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 
 		stlbsel = 1;
 		sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn,
-					     gtlbe, &stlbe);
+					     gtlbe, &stlbe, esel);
 		break;
 	}
 
@@ -1087,52 +1058,13 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
 }
 
-int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
-				gva_t eaddr, unsigned int pid, int as)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	int esel, tlbsel;
-
-	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
-		esel = kvmppc_e500_tlb_index(vcpu_e500, eaddr, tlbsel, pid, as);
-		if (esel >= 0)
-			return index_of(tlbsel, esel);
-	}
-
-	return -1;
-}
-
-void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
-	if (vcpu->arch.pid != pid) {
-		vcpu_e500->pid[0] = vcpu->arch.pid = pid;
-		kvmppc_e500_recalc_shadow_pid(vcpu_e500);
-	}
-}
-
-void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	struct kvm_book3e_206_tlb_entry *tlbe;
-
-	/* Insert large initial mapping for guest. */
-	tlbe = get_entry(vcpu_e500, 1, 0);
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
-	tlbe->mas2 = 0;
-	tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
-
-	/* 4K map for serial output. Used by kernel wrapper. */
-	tlbe = get_entry(vcpu_e500, 1, 1);
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
-	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
-	tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
-}
-
 static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int i;
 
+	clear_tlb1_bitmap(vcpu_e500);
+	kfree(vcpu_e500->g2h_tlb1_map);
+
 	clear_tlb_refs(vcpu_e500);
 	kfree(vcpu_e500->gtlb_priv[0]);
 	kfree(vcpu_e500->gtlb_priv[1]);
@@ -1155,6 +1087,36 @@ static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 	vcpu_e500->gtlb_arch = NULL;
 }
 
+void kvmppc_get_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	sregs->u.e.mas0 = vcpu->arch.shared->mas0;
+	sregs->u.e.mas1 = vcpu->arch.shared->mas1;
+	sregs->u.e.mas2 = vcpu->arch.shared->mas2;
+	sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
+	sregs->u.e.mas4 = vcpu->arch.shared->mas4;
+	sregs->u.e.mas6 = vcpu->arch.shared->mas6;
+
+	sregs->u.e.mmucfg = vcpu->arch.mmucfg;
+	sregs->u.e.tlbcfg[0] = vcpu->arch.tlbcfg[0];
+	sregs->u.e.tlbcfg[1] = vcpu->arch.tlbcfg[1];
+	sregs->u.e.tlbcfg[2] = 0;
+	sregs->u.e.tlbcfg[3] = 0;
+}
+
+int kvmppc_set_sregs_e500_tlb(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
+		vcpu->arch.shared->mas0 = sregs->u.e.mas0;
+		vcpu->arch.shared->mas1 = sregs->u.e.mas1;
+		vcpu->arch.shared->mas2 = sregs->u.e.mas2;
+		vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
+		vcpu->arch.shared->mas4 = sregs->u.e.mas4;
+		vcpu->arch.shared->mas6 = sregs->u.e.mas6;
+	}
+
+	return 0;
+}
+
 int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 			      struct kvm_config_tlb *cfg)
 {
@@ -1163,6 +1125,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	char *virt;
 	struct page **pages;
 	struct tlbe_priv *privs[2] = {};
+	u64 *g2h_bitmap = NULL;
 	size_t array_len;
 	u32 sets;
 	int num_pages, ret, i;
@@ -1224,10 +1187,16 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	if (!privs[0] || !privs[1])
 		goto err_put_page;
 
+	g2h_bitmap = kzalloc(sizeof(u64) * params.tlb_sizes[1],
+	                     GFP_KERNEL);
+	if (!g2h_bitmap)
+		goto err_put_page;
+
 	free_gtlb(vcpu_e500);
 
 	vcpu_e500->gtlb_priv[0] = privs[0];
 	vcpu_e500->gtlb_priv[1] = privs[1];
+	vcpu_e500->g2h_tlb1_map = g2h_bitmap;
 
 	vcpu_e500->gtlb_arch = (struct kvm_book3e_206_tlb_entry *)
 		(virt + (cfg->array & (PAGE_SIZE - 1)));
@@ -1238,14 +1207,16 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	vcpu_e500->gtlb_offset[0] = 0;
 	vcpu_e500->gtlb_offset[1] = params.tlb_sizes[0];
 
-	vcpu_e500->tlb0cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	vcpu->arch.mmucfg = mfspr(SPRN_MMUCFG) & ~MMUCFG_LPIDSIZE;
+
+	vcpu->arch.tlbcfg[0] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
 	if (params.tlb_sizes[0] <= 2048)
-		vcpu_e500->tlb0cfg |= params.tlb_sizes[0];
-	vcpu_e500->tlb0cfg |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
+		vcpu->arch.tlbcfg[0] |= params.tlb_sizes[0];
+	vcpu->arch.tlbcfg[0] |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
 
-	vcpu_e500->tlb1cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
-	vcpu_e500->tlb1cfg |= params.tlb_sizes[1];
-	vcpu_e500->tlb1cfg |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
+	vcpu->arch.tlbcfg[1] &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+	vcpu->arch.tlbcfg[1] |= params.tlb_sizes[1];
+	vcpu->arch.tlbcfg[1] |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
 
 	vcpu_e500->shared_tlb_pages = pages;
 	vcpu_e500->num_shared_tlb_pages = num_pages;
@@ -1256,6 +1227,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	vcpu_e500->gtlb_params[1].ways = params.tlb_sizes[1];
 	vcpu_e500->gtlb_params[1].sets = 1;
 
+	kvmppc_recalc_tlb1map_range(vcpu_e500);
 	return 0;
 
 err_put_page:
@@ -1274,13 +1246,14 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
 			     struct kvm_dirty_tlb *dirty)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-
+	kvmppc_recalc_tlb1map_range(vcpu_e500);
 	clear_tlb_refs(vcpu_e500);
 	return 0;
 }
 
 int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
+	struct kvm_vcpu *vcpu = &vcpu_e500->vcpu;
 	int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
 	int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;
 
@@ -1357,22 +1330,32 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	if (!vcpu_e500->gtlb_priv[1])
 		goto err;
 
-	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+	vcpu_e500->g2h_tlb1_map = kzalloc(sizeof(unsigned int) *
+					  vcpu_e500->gtlb_params[1].entries,
+					  GFP_KERNEL);
+	if (!vcpu_e500->g2h_tlb1_map)
+		goto err;
+
+	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
+					   host_tlb_params[1].entries,
+					   GFP_KERNEL);
+	if (!vcpu_e500->h2g_tlb1_rmap)
 		goto err;
 
 	/* Init TLB configuration register */
-	vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) &
+	vcpu->arch.tlbcfg[0] = mfspr(SPRN_TLB0CFG) &
 			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
-	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[0].entries;
-	vcpu_e500->tlb0cfg |=
+	vcpu->arch.tlbcfg[0] |= vcpu_e500->gtlb_params[0].entries;
+	vcpu->arch.tlbcfg[0] |=
 		vcpu_e500->gtlb_params[0].ways << TLBnCFG_ASSOC_SHIFT;
 
-	vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) &
+	vcpu->arch.tlbcfg[1] = mfspr(SPRN_TLB1CFG) &
 			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
-	vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[1].entries;
-	vcpu_e500->tlb0cfg |=
+	vcpu->arch.tlbcfg[1] |= vcpu_e500->gtlb_params[1].entries;
+	vcpu->arch.tlbcfg[1] |=
 		vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT;
 
+	kvmppc_recalc_tlb1map_range(vcpu_e500);
 	return 0;
 
 err:
@@ -1385,8 +1368,7 @@ err:
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	free_gtlb(vcpu_e500);
-	kvmppc_e500_id_table_free(vcpu_e500);
-
+	kfree(vcpu_e500->h2g_tlb1_rmap);
 	kfree(vcpu_e500->tlb_refs[0]);
 	kfree(vcpu_e500->tlb_refs[1]);
 }
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
deleted file mode 100644
index 5c6d2d7bf058..000000000000
--- a/arch/powerpc/kvm/e500_tlb.h
+++ /dev/null
@@ -1,174 +0,0 @@
-/*
- * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
- *
- * Author: Yu Liu, yu.liu@freescale.com
- *
- * Description:
- * This file is based on arch/powerpc/kvm/44x_tlb.h,
- * by Hollis Blanchard <hollisb@us.ibm.com>.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- */
-
-#ifndef __KVM_E500_TLB_H__
-#define __KVM_E500_TLB_H__
-
-#include <linux/kvm_host.h>
-#include <asm/mmu-book3e.h>
-#include <asm/tlb.h>
-#include <asm/kvm_e500.h>
-
-/* This geometry is the legacy default -- can be overridden by userspace */
-#define KVM_E500_TLB0_WAY_SIZE		128
-#define KVM_E500_TLB0_WAY_NUM		2
-
-#define KVM_E500_TLB0_SIZE  (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
-#define KVM_E500_TLB1_SIZE  16
-
-#define index_of(tlbsel, esel)	(((tlbsel) << 16) | ((esel) & 0xFFFF))
-#define tlbsel_of(index)	((index) >> 16)
-#define esel_of(index)		((index) & 0xFFFF)
-
-#define E500_TLB_USER_PERM_MASK (MAS3_UX|MAS3_UR|MAS3_UW)
-#define E500_TLB_SUPER_PERM_MASK (MAS3_SX|MAS3_SR|MAS3_SW)
-#define MAS2_ATTRIB_MASK \
-	  (MAS2_X0 | MAS2_X1)
-#define MAS3_ATTRIB_MASK \
-	  (MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3 \
-	   | E500_TLB_USER_PERM_MASK | E500_TLB_SUPER_PERM_MASK)
-
-extern void kvmppc_dump_tlbs(struct kvm_vcpu *);
-extern int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *, ulong);
-extern int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *);
-extern int kvmppc_e500_emul_tlbre(struct kvm_vcpu *);
-extern int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *, int, int);
-extern int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *, int);
-extern int kvmppc_e500_tlb_search(struct kvm_vcpu *, gva_t, unsigned int, int);
-extern void kvmppc_e500_tlb_put(struct kvm_vcpu *);
-extern void kvmppc_e500_tlb_load(struct kvm_vcpu *, int);
-extern int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *);
-extern void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *);
-extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
-extern void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *);
-
-/* TLB helper functions */
-static inline unsigned int
-get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return (tlbe->mas1 >> 7) & 0x1f;
-}
-
-static inline gva_t get_tlb_eaddr(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return tlbe->mas2 & 0xfffff000;
-}
-
-static inline u64 get_tlb_bytes(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	unsigned int pgsize = get_tlb_size(tlbe);
-	return 1ULL << 10 << pgsize;
-}
-
-static inline gva_t get_tlb_end(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	u64 bytes = get_tlb_bytes(tlbe);
-	return get_tlb_eaddr(tlbe) + bytes - 1;
-}
-
-static inline u64 get_tlb_raddr(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return tlbe->mas7_3 & ~0xfffULL;
-}
-
-static inline unsigned int
-get_tlb_tid(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return (tlbe->mas1 >> 16) & 0xff;
-}
-
-static inline unsigned int
-get_tlb_ts(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return (tlbe->mas1 >> 12) & 0x1;
-}
-
-static inline unsigned int
-get_tlb_v(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return (tlbe->mas1 >> 31) & 0x1;
-}
-
-static inline unsigned int
-get_tlb_iprot(const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return (tlbe->mas1 >> 30) & 0x1;
-}
-
-static inline unsigned int get_cur_pid(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.pid & 0xff;
-}
-
-static inline unsigned int get_cur_as(struct kvm_vcpu *vcpu)
-{
-	return !!(vcpu->arch.shared->msr & (MSR_IS | MSR_DS));
-}
-
-static inline unsigned int get_cur_pr(struct kvm_vcpu *vcpu)
-{
-	return !!(vcpu->arch.shared->msr & MSR_PR);
-}
-
-static inline unsigned int get_cur_spid(const struct kvm_vcpu *vcpu)
-{
-	return (vcpu->arch.shared->mas6 >> 16) & 0xff;
-}
-
-static inline unsigned int get_cur_sas(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.shared->mas6 & 0x1;
-}
-
-static inline unsigned int get_tlb_tlbsel(const struct kvm_vcpu *vcpu)
-{
-	/*
-	 * Manual says that tlbsel has 2 bits wide.
-	 * Since we only have two TLBs, only lower bit is used.
-	 */
-	return (vcpu->arch.shared->mas0 >> 28) & 0x1;
-}
-
-static inline unsigned int get_tlb_nv_bit(const struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.shared->mas0 & 0xfff;
-}
-
-static inline unsigned int get_tlb_esel_bit(const struct kvm_vcpu *vcpu)
-{
-	return (vcpu->arch.shared->mas0 >> 16) & 0xfff;
-}
-
-static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
-			const struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	gpa_t gpa;
-
-	if (!get_tlb_v(tlbe))
-		return 0;
-
-	/* Does it match current guest AS? */
-	/* XXX what about IS != DS? */
-	if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
-		return 0;
-
-	gpa = get_tlb_raddr(tlbe);
-	if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
-		/* Mapping is not for RAM. */
-		return 0;
-
-	return 1;
-}
-
-#endif /* __KVM_E500_TLB_H__ */
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
new file mode 100644
index 000000000000..fe6c1de6b701
--- /dev/null
+++ b/arch/powerpc/kvm/e500mc.c
@@ -0,0 +1,342 @@
+/*
+ * Copyright (C) 2010 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Varun Sethi, <varun.sethi@freescale.com>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/e500.c,
+ * by Yu Liu <yu.liu@freescale.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/dbell.h>
+
+#include "booke.h"
+#include "e500.h"
+
+void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type)
+{
+	enum ppc_dbell dbell_type;
+	unsigned long tag;
+
+	switch (type) {
+	case INT_CLASS_NONCRIT:
+		dbell_type = PPC_G_DBELL;
+		break;
+	case INT_CLASS_CRIT:
+		dbell_type = PPC_G_DBELL_CRIT;
+		break;
+	case INT_CLASS_MC:
+		dbell_type = PPC_G_DBELL_MC;
+		break;
+	default:
+		WARN_ONCE(1, "%s: unknown int type %d\n", __func__, type);
+		return;
+	}
+
+
+	tag = PPC_DBELL_LPID(vcpu->kvm->arch.lpid) | vcpu->vcpu_id;
+	mb();
+	ppc_msgsnd(dbell_type, 0, tag);
+}
+
+/* gtlbe must not be mapped by more than one host tlb entry */
+void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
+			   struct kvm_book3e_206_tlb_entry *gtlbe)
+{
+	unsigned int tid, ts;
+	u32 val, eaddr, lpid;
+	unsigned long flags;
+
+	ts = get_tlb_ts(gtlbe);
+	tid = get_tlb_tid(gtlbe);
+	lpid = vcpu_e500->vcpu.kvm->arch.lpid;
+
+	/* We search the host TLB to invalidate its shadow TLB entry */
+	val = (tid << 16) | ts;
+	eaddr = get_tlb_eaddr(gtlbe);
+
+	local_irq_save(flags);
+
+	mtspr(SPRN_MAS6, val);
+	mtspr(SPRN_MAS5, MAS5_SGS | lpid);
+
+	asm volatile("tlbsx 0, %[eaddr]\n" : : [eaddr] "r" (eaddr));
+	val = mfspr(SPRN_MAS1);
+	if (val & MAS1_VALID) {
+		mtspr(SPRN_MAS1, val & ~MAS1_VALID);
+		asm volatile("tlbwe");
+	}
+	mtspr(SPRN_MAS5, 0);
+	/* NOTE: tlbsx also updates mas8, so clear it for host tlbwe */
+	mtspr(SPRN_MAS8, 0);
+	isync();
+
+	local_irq_restore(flags);
+}
+
+void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	mtspr(SPRN_MAS5, MAS5_SGS | vcpu_e500->vcpu.kvm->arch.lpid);
+	asm volatile("tlbilxlpid");
+	mtspr(SPRN_MAS5, 0);
+	local_irq_restore(flags);
+}
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+	vcpu->arch.pid = pid;
+}
+
+void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
+{
+}
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	kvmppc_booke_vcpu_load(vcpu, cpu);
+
+	mtspr(SPRN_LPID, vcpu->kvm->arch.lpid);
+	mtspr(SPRN_EPCR, vcpu->arch.shadow_epcr);
+	mtspr(SPRN_GPIR, vcpu->vcpu_id);
+	mtspr(SPRN_MSRP, vcpu->arch.shadow_msrp);
+	mtspr(SPRN_EPLC, vcpu->arch.eplc);
+	mtspr(SPRN_EPSC, vcpu->arch.epsc);
+
+	mtspr(SPRN_GIVPR, vcpu->arch.ivpr);
+	mtspr(SPRN_GIVOR2, vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]);
+	mtspr(SPRN_GIVOR8, vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]);
+	mtspr(SPRN_GSPRG0, (unsigned long)vcpu->arch.shared->sprg0);
+	mtspr(SPRN_GSPRG1, (unsigned long)vcpu->arch.shared->sprg1);
+	mtspr(SPRN_GSPRG2, (unsigned long)vcpu->arch.shared->sprg2);
+	mtspr(SPRN_GSPRG3, (unsigned long)vcpu->arch.shared->sprg3);
+
+	mtspr(SPRN_GSRR0, vcpu->arch.shared->srr0);
+	mtspr(SPRN_GSRR1, vcpu->arch.shared->srr1);
+
+	mtspr(SPRN_GEPR, vcpu->arch.epr);
+	mtspr(SPRN_GDEAR, vcpu->arch.shared->dar);
+	mtspr(SPRN_GESR, vcpu->arch.shared->esr);
+
+	if (vcpu->arch.oldpir != mfspr(SPRN_PIR))
+		kvmppc_e500_tlbil_all(vcpu_e500);
+
+	kvmppc_load_guest_fp(vcpu);
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.eplc = mfspr(SPRN_EPLC);
+	vcpu->arch.epsc = mfspr(SPRN_EPSC);
+
+	vcpu->arch.shared->sprg0 = mfspr(SPRN_GSPRG0);
+	vcpu->arch.shared->sprg1 = mfspr(SPRN_GSPRG1);
+	vcpu->arch.shared->sprg2 = mfspr(SPRN_GSPRG2);
+	vcpu->arch.shared->sprg3 = mfspr(SPRN_GSPRG3);
+
+	vcpu->arch.shared->srr0 = mfspr(SPRN_GSRR0);
+	vcpu->arch.shared->srr1 = mfspr(SPRN_GSRR1);
+
+	vcpu->arch.epr = mfspr(SPRN_GEPR);
+	vcpu->arch.shared->dar = mfspr(SPRN_GDEAR);
+	vcpu->arch.shared->esr = mfspr(SPRN_GESR);
+
+	vcpu->arch.oldpir = mfspr(SPRN_PIR);
+
+	kvmppc_booke_vcpu_put(vcpu);
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	int r;
+
+	if (strcmp(cur_cpu_spec->cpu_name, "e500mc") == 0)
+		r = 0;
+	else if (strcmp(cur_cpu_spec->cpu_name, "e5500") == 0)
+		r = 0;
+	else
+		r = -ENOTSUPP;
+
+	return r;
+}
+
+int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	vcpu->arch.shadow_epcr = SPRN_EPCR_DSIGS | SPRN_EPCR_DGTMI | \
+				 SPRN_EPCR_DUVD;
+	vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP;
+	vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT);
+	vcpu->arch.epsc = vcpu->arch.eplc;
+
+	vcpu->arch.pvr = mfspr(SPRN_PVR);
+	vcpu_e500->svr = mfspr(SPRN_SVR);
+
+	vcpu->arch.cpu_type = KVM_CPU_E500MC;
+
+	return 0;
+}
+
+void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	sregs->u.e.features |= KVM_SREGS_E_ARCH206_MMU | KVM_SREGS_E_PM |
+			       KVM_SREGS_E_PC;
+	sregs->u.e.impl_id = KVM_SREGS_E_IMPL_FSL;
+
+	sregs->u.e.impl.fsl.features = 0;
+	sregs->u.e.impl.fsl.svr = vcpu_e500->svr;
+	sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
+	sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
+
+	kvmppc_get_sregs_e500_tlb(vcpu, sregs);
+
+	sregs->u.e.ivor_high[3] =
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+	sregs->u.e.ivor_high[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL];
+	sregs->u.e.ivor_high[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT];
+
+	kvmppc_get_sregs_ivor(vcpu, sregs);
+}
+
+int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	int ret;
+
+	if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
+		vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
+		vcpu_e500->hid0 = sregs->u.e.impl.fsl.hid0;
+		vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
+	}
+
+	ret = kvmppc_set_sregs_e500_tlb(vcpu, sregs);
+	if (ret < 0)
+		return ret;
+
+	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
+		return 0;
+
+	if (sregs->u.e.features & KVM_SREGS_E_PM) {
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] =
+			sregs->u.e.ivor_high[3];
+	}
+
+	if (sregs->u.e.features & KVM_SREGS_E_PC) {
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL] =
+			sregs->u.e.ivor_high[4];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DBELL_CRIT] =
+			sregs->u.e.ivor_high[5];
+	}
+
+	return kvmppc_set_sregs_ivor(vcpu, sregs);
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500;
+	struct kvm_vcpu *vcpu;
+	int err;
+
+	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu_e500) {
+		err = -ENOMEM;
+		goto out;
+	}
+	vcpu = &vcpu_e500->vcpu;
+
+	/* Invalid PIR value -- this LPID dosn't have valid state on any cpu */
+	vcpu->arch.oldpir = 0xffffffff;
+
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	err = kvmppc_e500_tlb_init(vcpu_e500);
+	if (err)
+		goto uninit_vcpu;
+
+	vcpu->arch.shared = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	if (!vcpu->arch.shared)
+		goto uninit_tlb;
+
+	return vcpu;
+
+uninit_tlb:
+	kvmppc_e500_tlb_uninit(vcpu_e500);
+uninit_vcpu:
+	kvm_vcpu_uninit(vcpu);
+
+free_vcpu:
+	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+out:
+	return ERR_PTR(err);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	free_page((unsigned long)vcpu->arch.shared);
+	kvmppc_e500_tlb_uninit(vcpu_e500);
+	kvm_vcpu_uninit(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	int lpid;
+
+	lpid = kvmppc_alloc_lpid();
+	if (lpid < 0)
+		return lpid;
+
+	kvm->arch.lpid = lpid;
+	return 0;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+	kvmppc_free_lpid(kvm->arch.lpid);
+}
+
+static int __init kvmppc_e500mc_init(void)
+{
+	int r;
+
+	r = kvmppc_booke_init();
+	if (r)
+		return r;
+
+	kvmppc_init_lpid(64);
+	kvmppc_claim_lpid(0); /* host */
+
+	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+}
+
+static void __exit kvmppc_e500mc_exit(void)
+{
+	kvmppc_booke_exit();
+}
+
+module_init(kvmppc_e500mc_init);
+module_exit(kvmppc_e500mc_exit);
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 968f40101883..f90e86dea7a2 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kvm_host.h>
+#include <linux/clockchips.h>
 
 #include <asm/reg.h>
 #include <asm/time.h>
@@ -35,7 +36,9 @@
 #define OP_TRAP 3
 #define OP_TRAP_64 2
 
+#define OP_31_XOP_TRAP      4
 #define OP_31_XOP_LWZX      23
+#define OP_31_XOP_TRAP_64   68
 #define OP_31_XOP_LBZX      87
 #define OP_31_XOP_STWX      151
 #define OP_31_XOP_STBX      215
@@ -102,8 +105,12 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 	 */
 
 	dec_time = vcpu->arch.dec;
-	dec_time *= 1000;
-	do_div(dec_time, tb_ticks_per_usec);
+	/*
+	 * Guest timebase ticks at the same frequency as host decrementer.
+	 * So use the host decrementer calculations for decrementer emulation.
+	 */
+	dec_time = dec_time << decrementer_clockevent.shift;
+	do_div(dec_time, decrementer_clockevent.mult);
 	dec_nsec = do_div(dec_time, NSEC_PER_SEC);
 	hrtimer_start(&vcpu->arch.dec_timer,
 		ktime_set(dec_time, dec_nsec), HRTIMER_MODE_REL);
@@ -141,14 +148,13 @@ u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb)
 int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	u32 inst = kvmppc_get_last_inst(vcpu);
-	u32 ea;
-	int ra;
-	int rb;
-	int rs;
-	int rt;
-	int sprn;
+	int ra = get_ra(inst);
+	int rs = get_rs(inst);
+	int rt = get_rt(inst);
+	int sprn = get_sprn(inst);
 	enum emulation_result emulated = EMULATE_DONE;
 	int advance = 1;
+	ulong spr_val = 0;
 
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
@@ -170,173 +176,143 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	case 31:
 		switch (get_xop(inst)) {
 
+		case OP_31_XOP_TRAP:
+#ifdef CONFIG_64BIT
+		case OP_31_XOP_TRAP_64:
+#endif
+#ifdef CONFIG_PPC_BOOK3S
+			kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP);
+#else
+			kvmppc_core_queue_program(vcpu,
+					vcpu->arch.shared->esr | ESR_PTR);
+#endif
+			advance = 0;
+			break;
 		case OP_31_XOP_LWZX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 			break;
 
 		case OP_31_XOP_LBZX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 			break;
 
 		case OP_31_XOP_LBZUX:
-			rt = get_rt(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
-			ea = kvmppc_get_gpr(vcpu, rb);
-			if (ra)
-				ea += kvmppc_get_gpr(vcpu, ra);
-
 			emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
-			kvmppc_set_gpr(vcpu, ra, ea);
+			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 			break;
 
 		case OP_31_XOP_STWX:
-			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               4, 1);
 			break;
 
 		case OP_31_XOP_STBX:
-			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               1, 1);
 			break;
 
 		case OP_31_XOP_STBUX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
-			ea = kvmppc_get_gpr(vcpu, rb);
-			if (ra)
-				ea += kvmppc_get_gpr(vcpu, ra);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               1, 1);
-			kvmppc_set_gpr(vcpu, rs, ea);
+			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 			break;
 
 		case OP_31_XOP_LHAX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
 			break;
 
 		case OP_31_XOP_LHZX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 			break;
 
 		case OP_31_XOP_LHZUX:
-			rt = get_rt(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
-			ea = kvmppc_get_gpr(vcpu, rb);
-			if (ra)
-				ea += kvmppc_get_gpr(vcpu, ra);
-
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-			kvmppc_set_gpr(vcpu, ra, ea);
+			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 			break;
 
 		case OP_31_XOP_MFSPR:
-			sprn = get_sprn(inst);
-			rt = get_rt(inst);
-
 			switch (sprn) {
 			case SPRN_SRR0:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr0);
+				spr_val = vcpu->arch.shared->srr0;
 				break;
 			case SPRN_SRR1:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr1);
+				spr_val = vcpu->arch.shared->srr1;
 				break;
 			case SPRN_PVR:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.pvr); break;
+				spr_val = vcpu->arch.pvr;
+				break;
 			case SPRN_PIR:
-				kvmppc_set_gpr(vcpu, rt, vcpu->vcpu_id); break;
+				spr_val = vcpu->vcpu_id;
+				break;
 			case SPRN_MSSSR0:
-				kvmppc_set_gpr(vcpu, rt, 0); break;
+				spr_val = 0;
+				break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
 			 * In fact, we probably will never see these traps. */
 			case SPRN_TBWL:
-				kvmppc_set_gpr(vcpu, rt, get_tb() >> 32); break;
+				spr_val = get_tb() >> 32;
+				break;
 			case SPRN_TBWU:
-				kvmppc_set_gpr(vcpu, rt, get_tb()); break;
+				spr_val = get_tb();
+				break;
 
 			case SPRN_SPRG0:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg0);
+				spr_val = vcpu->arch.shared->sprg0;
 				break;
 			case SPRN_SPRG1:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg1);
+				spr_val = vcpu->arch.shared->sprg1;
 				break;
 			case SPRN_SPRG2:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg2);
+				spr_val = vcpu->arch.shared->sprg2;
 				break;
 			case SPRN_SPRG3:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg3);
+				spr_val = vcpu->arch.shared->sprg3;
 				break;
 			/* Note: SPRG4-7 are user-readable, so we don't get
 			 * a trap. */
 
 			case SPRN_DEC:
-			{
-				kvmppc_set_gpr(vcpu, rt,
-					       kvmppc_get_dec(vcpu, get_tb()));
+				spr_val = kvmppc_get_dec(vcpu, get_tb());
 				break;
-			}
 			default:
-				emulated = kvmppc_core_emulate_mfspr(vcpu, sprn, rt);
-				if (emulated == EMULATE_FAIL) {
-					printk("mfspr: unknown spr %x\n", sprn);
-					kvmppc_set_gpr(vcpu, rt, 0);
+				emulated = kvmppc_core_emulate_mfspr(vcpu, sprn,
+								     &spr_val);
+				if (unlikely(emulated == EMULATE_FAIL)) {
+					printk(KERN_INFO "mfspr: unknown spr "
+						"0x%x\n", sprn);
 				}
 				break;
 			}
+			kvmppc_set_gpr(vcpu, rt, spr_val);
 			kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS);
 			break;
 
 		case OP_31_XOP_STHX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 1);
 			break;
 
 		case OP_31_XOP_STHUX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
-			ea = kvmppc_get_gpr(vcpu, rb);
-			if (ra)
-				ea += kvmppc_get_gpr(vcpu, ra);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 1);
-			kvmppc_set_gpr(vcpu, ra, ea);
+			kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 			break;
 
 		case OP_31_XOP_MTSPR:
-			sprn = get_sprn(inst);
-			rs = get_rs(inst);
+			spr_val = kvmppc_get_gpr(vcpu, rs);
 			switch (sprn) {
 			case SPRN_SRR0:
-				vcpu->arch.shared->srr0 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->srr0 = spr_val;
 				break;
 			case SPRN_SRR1:
-				vcpu->arch.shared->srr1 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->srr1 = spr_val;
 				break;
 
 			/* XXX We need to context-switch the timebase for
@@ -347,27 +323,29 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_MSSSR0: break;
 
 			case SPRN_DEC:
-				vcpu->arch.dec = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.dec = spr_val;
 				kvmppc_emulate_dec(vcpu);
 				break;
 
 			case SPRN_SPRG0:
-				vcpu->arch.shared->sprg0 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg0 = spr_val;
 				break;
 			case SPRN_SPRG1:
-				vcpu->arch.shared->sprg1 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg1 = spr_val;
 				break;
 			case SPRN_SPRG2:
-				vcpu->arch.shared->sprg2 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg2 = spr_val;
 				break;
 			case SPRN_SPRG3:
-				vcpu->arch.shared->sprg3 = kvmppc_get_gpr(vcpu, rs);
+				vcpu->arch.shared->sprg3 = spr_val;
 				break;
 
 			default:
-				emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, rs);
+				emulated = kvmppc_core_emulate_mtspr(vcpu, sprn,
+								     spr_val);
 				if (emulated == EMULATE_FAIL)
-					printk("mtspr: unknown spr %x\n", sprn);
+					printk(KERN_INFO "mtspr: unknown spr "
+						"0x%x\n", sprn);
 				break;
 			}
 			kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS);
@@ -382,7 +360,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_LWBRX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 4, 0);
 			break;
 
@@ -390,25 +367,16 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_STWBRX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               4, 0);
 			break;
 
 		case OP_31_XOP_LHBRX:
-			rt = get_rt(inst);
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 0);
 			break;
 
 		case OP_31_XOP_STHBRX:
-			rs = get_rs(inst);
-			ra = get_ra(inst);
-			rb = get_rb(inst);
-
 			emulated = kvmppc_handle_store(run, vcpu,
 						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 0);
@@ -421,99 +389,78 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		break;
 
 	case OP_LWZ:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		break;
 
 	case OP_LWZU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_LBZ:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
 		break;
 
 	case OP_LBZU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_STW:
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               4, 1);
 		break;
 
 	case OP_STWU:
-		ra = get_ra(inst);
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               4, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_STB:
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               1, 1);
 		break;
 
 	case OP_STBU:
-		ra = get_ra(inst);
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               1, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_LHZ:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
 		break;
 
 	case OP_LHZU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_LHA:
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
 		break;
 
 	case OP_LHAU:
-		ra = get_ra(inst);
-		rt = get_rt(inst);
 		emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	case OP_STH:
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               2, 1);
 		break;
 
 	case OP_STHU:
-		ra = get_ra(inst);
-		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
 		                               2, 1);
-		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
 		break;
 
 	default:
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 00d7e345b3fe..1493c8de947b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -43,6 +43,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 	       v->requests;
 }
 
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 {
 	int nr = kvmppc_get_gpr(vcpu, 11);
@@ -74,7 +79,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 	}
 	case HC_VENDOR_KVM | KVM_HC_FEATURES:
 		r = HC_EV_SUCCESS;
-#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500)
+#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500V2)
 		/* XXX Missing magic page on 44x */
 		r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
 #endif
@@ -109,6 +114,11 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 		goto out;
 #endif
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	if (!cpu_has_feature(CPU_FTR_EMB_HV))
+		goto out;
+#endif
+
 	r = true;
 
 out:
@@ -225,7 +235,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
-#ifdef CONFIG_KVM_E500
+#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
 	case KVM_CAP_SW_TLB:
 #endif
 		r = 1;
@@ -234,10 +244,12 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
 #endif
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 		r = 1;
 		break;
+#endif /* CONFIG_PPC_BOOK3S_64 */
+#ifdef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_CAP_PPC_SMT:
 		r = threads_per_core;
 		break;
@@ -267,6 +279,11 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+#ifdef CONFIG_PPC_BOOK3S_64
+	case KVM_CAP_PPC_GET_SMMU_INFO:
+		r = 1;
+		break;
+#endif
 	default:
 		r = 0;
 		break;
@@ -588,21 +605,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return r;
 }
 
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
-{
-	int me;
-	int cpu = vcpu->cpu;
-
-	me = get_cpu();
-	if (waitqueue_active(vcpu->arch.wqp)) {
-		wake_up_interruptible(vcpu->arch.wqp);
-		vcpu->stat.halt_wakeup++;
-	} else if (cpu != me && cpu != -1) {
-		smp_send_reschedule(vcpu->cpu);
-	}
-	put_cpu();
-}
-
 int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 {
 	if (irq->irq == KVM_INTERRUPT_UNSET) {
@@ -611,6 +613,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 	}
 
 	kvmppc_core_queue_external(vcpu, irq);
+
 	kvm_vcpu_kick(vcpu);
 
 	return 0;
@@ -633,7 +636,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
-#ifdef CONFIG_KVM_E500
+#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
 	case KVM_CAP_SW_TLB: {
 		struct kvm_config_tlb cfg;
 		void __user *user_ptr = (void __user *)(uintptr_t)cap->args[0];
@@ -710,7 +713,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 
-#ifdef CONFIG_KVM_E500
+#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
 	case KVM_DIRTY_TLB: {
 		struct kvm_dirty_tlb dirty;
 		r = -EFAULT;
@@ -720,7 +723,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 #endif
-
 	default:
 		r = -EINVAL;
 	}
@@ -777,7 +779,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 		break;
 	}
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CREATE_SPAPR_TCE: {
 		struct kvm_create_spapr_tce create_tce;
 		struct kvm *kvm = filp->private_data;
@@ -788,7 +790,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce);
 		goto out;
 	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
 	case KVM_ALLOCATE_RMA: {
 		struct kvm *kvm = filp->private_data;
 		struct kvm_allocate_rma rma;
@@ -800,6 +804,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	case KVM_PPC_GET_SMMU_INFO: {
+		struct kvm *kvm = filp->private_data;
+		struct kvm_ppc_smmu_info info;
+
+		memset(&info, 0, sizeof(info));
+		r = kvm_vm_ioctl_get_smmu_info(kvm, &info);
+		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
+			r = -EFAULT;
+		break;
+	}
+#endif /* CONFIG_PPC_BOOK3S_64 */
 	default:
 		r = -ENOTTY;
 	}
@@ -808,6 +824,40 @@ out:
 	return r;
 }
 
+static unsigned long lpid_inuse[BITS_TO_LONGS(KVMPPC_NR_LPIDS)];
+static unsigned long nr_lpids;
+
+long kvmppc_alloc_lpid(void)
+{
+	long lpid;
+
+	do {
+		lpid = find_first_zero_bit(lpid_inuse, KVMPPC_NR_LPIDS);
+		if (lpid >= nr_lpids) {
+			pr_err("%s: No LPIDs free\n", __func__);
+			return -ENOMEM;
+		}
+	} while (test_and_set_bit(lpid, lpid_inuse));
+
+	return lpid;
+}
+
+void kvmppc_claim_lpid(long lpid)
+{
+	set_bit(lpid, lpid_inuse);
+}
+
+void kvmppc_free_lpid(long lpid)
+{
+	clear_bit(lpid, lpid_inuse);
+}
+
+void kvmppc_init_lpid(unsigned long nr_lpids_param)
+{
+	nr_lpids = min_t(unsigned long, KVMPPC_NR_LPIDS, nr_lpids_param);
+	memset(lpid_inuse, 0, sizeof(lpid_inuse));
+}
+
 int kvm_arch_init(void *opaque)
 {
 	return 0;
diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h
index 8167d42a776f..bf191e72b2d8 100644
--- a/arch/powerpc/kvm/timing.h
+++ b/arch/powerpc/kvm/timing.h
@@ -93,6 +93,12 @@ static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type)
 	case SIGNAL_EXITS:
 		vcpu->stat.signal_exits++;
 		break;
+	case DBELL_EXITS:
+		vcpu->stat.dbell_exits++;
+		break;
+	case GDBELL_EXITS:
+		vcpu->stat.gdbell_exits++;
+		break;
 	}
 }
 
diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index 96076676e224..bdcbe0f8dd7b 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -52,4 +52,9 @@ struct kvm_sync_regs {
 	__u32 acrs[16];	/* access registers */
 	__u64 crs[16];	/* control registers */
 };
+
+#define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)
+#define KVM_REG_S390_EPOCHDIFF	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x2)
+#define KVM_REG_S390_CPU_TIMER  (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x3)
+#define KVM_REG_S390_CLOCK_COMP (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x4)
 #endif
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 7343872890a2..dd17537b9a9d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -148,6 +148,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_sigp_restart;
 	u32 diagnose_10;
 	u32 diagnose_44;
+	u32 diagnose_9c;
 };
 
 struct kvm_s390_io_info {
diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h
index 6964db226f83..a98832961035 100644
--- a/arch/s390/include/asm/kvm_para.h
+++ b/arch/s390/include/asm/kvm_para.h
@@ -149,6 +149,11 @@ static inline unsigned int kvm_arch_para_features(void)
 	return 0;
 }
 
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
 #endif
 
 #endif /* __S390_KVM_PARA_H */
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index fed7bee650a0..bf238c55740b 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -48,6 +48,7 @@ int sclp_cpu_deconfigure(u8 cpu);
 void sclp_facilities_detect(void);
 unsigned long long sclp_get_rnmax(void);
 unsigned long long sclp_get_rzm(void);
+u8 sclp_get_fac85(void);
 int sclp_sdias_blk_count(void);
 int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
 int sclp_chp_configure(struct chp_id chpid);
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index a353f0ea45c2..b23d9ac77dfc 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -47,9 +47,30 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
 	vcpu->stat.diagnose_44++;
-	vcpu_put(vcpu);
-	yield();
-	vcpu_load(vcpu);
+	kvm_vcpu_on_spin(vcpu);
+	return 0;
+}
+
+static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu *tcpu;
+	int tid;
+	int i;
+
+	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+	vcpu->stat.diagnose_9c++;
+	VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid);
+
+	if (tid == vcpu->vcpu_id)
+		return 0;
+
+	kvm_for_each_vcpu(i, tcpu, kvm)
+		if (tcpu->vcpu_id == tid) {
+			kvm_vcpu_yield_to(tcpu);
+			break;
+		}
+
 	return 0;
 }
 
@@ -89,6 +110,8 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 		return diag_release_pages(vcpu);
 	case 0x44:
 		return __diag_time_slice_end(vcpu);
+	case 0x9c:
+		return __diag_time_slice_end_directed(vcpu);
 	case 0x308:
 		return __diag_ipl_functions(vcpu);
 	default:
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 361456577c6f..979cbe55bf5e 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -101,6 +101,7 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 }
 
 static intercept_handler_t instruction_handlers[256] = {
+	[0x01] = kvm_s390_handle_01,
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 217ce44395a4..664766d0c83c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -28,6 +28,7 @@
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
+#include <asm/sclp.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -74,6 +75,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
 	{ "diagnose_10", VCPU_STAT(diagnose_10) },
 	{ "diagnose_44", VCPU_STAT(diagnose_44) },
+	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
 	{ NULL }
 };
 
@@ -133,8 +135,16 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_S390_UCONTROL:
 #endif
 	case KVM_CAP_SYNC_REGS:
+	case KVM_CAP_ONE_REG:
 		r = 1;
 		break;
+	case KVM_CAP_NR_VCPUS:
+	case KVM_CAP_MAX_VCPUS:
+		r = KVM_MAX_VCPUS;
+		break;
+	case KVM_CAP_S390_COW:
+		r = sclp_get_fac85() & 0x2;
+		break;
 	default:
 		r = 0;
 	}
@@ -423,6 +433,71 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
+{
+	/* kvm common code refers to this, but never calls it */
+	BUG();
+	return 0;
+}
+
+static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
+					   struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_S390_TODPR:
+		r = put_user(vcpu->arch.sie_block->todpr,
+			     (u32 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_EPOCHDIFF:
+		r = put_user(vcpu->arch.sie_block->epoch,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CPU_TIMER:
+		r = put_user(vcpu->arch.sie_block->cputm,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CLOCK_COMP:
+		r = put_user(vcpu->arch.sie_block->ckc,
+			     (u64 __user *)reg->addr);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
+static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
+					   struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_S390_TODPR:
+		r = get_user(vcpu->arch.sie_block->todpr,
+			     (u32 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_EPOCHDIFF:
+		r = get_user(vcpu->arch.sie_block->epoch,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CPU_TIMER:
+		r = get_user(vcpu->arch.sie_block->cputm,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CLOCK_COMP:
+		r = get_user(vcpu->arch.sie_block->ckc,
+			     (u64 __user *)reg->addr);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
 static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 {
 	kvm_s390_vcpu_initial_reset(vcpu);
@@ -753,6 +828,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_S390_INITIAL_RESET:
 		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
 		break;
+	case KVM_SET_ONE_REG:
+	case KVM_GET_ONE_REG: {
+		struct kvm_one_reg reg;
+		r = -EFAULT;
+		if (copy_from_user(&reg, argp, sizeof(reg)))
+			break;
+		if (ioctl == KVM_SET_ONE_REG)
+			r = kvm_arch_vcpu_ioctl_set_one_reg(vcpu, &reg);
+		else
+			r = kvm_arch_vcpu_ioctl_get_one_reg(vcpu, &reg);
+		break;
+	}
 #ifdef CONFIG_KVM_S390_UCONTROL
 	case KVM_S390_UCAS_MAP: {
 		struct kvm_s390_ucas_mapping ucasmap;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index ff28f9d1c9eb..2294377975e8 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -79,6 +79,7 @@ int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index e5a45dbd26ac..68a6b2ed16bf 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -380,3 +380,34 @@ int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
+static int handle_sckpf(struct kvm_vcpu *vcpu)
+{
+	u32 value;
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+
+	if (vcpu->run->s.regs.gprs[0] & 0x00000000ffff0000)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_SPECIFICATION);
+
+	value = vcpu->run->s.regs.gprs[0] & 0x000000000000ffff;
+	vcpu->arch.sie_block->todpr = value;
+
+	return 0;
+}
+
+static intercept_handler_t x01_handlers[256] = {
+	[0x07] = handle_sckpf,
+};
+
+int kvm_s390_handle_01(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
diff --git a/arch/score/include/asm/kvm_para.h b/arch/score/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/score/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/sh/include/asm/kvm_para.h b/arch/sh/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/sh/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/sparc/include/asm/kvm_para.h b/arch/sparc/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/sparc/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/tile/include/asm/kvm_para.h b/arch/tile/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/tile/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/um/include/asm/kvm_para.h b/arch/um/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/um/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/unicore32/include/asm/kvm_para.h b/arch/unicore32/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/unicore32/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index c222e1a1b12a..1ac46c22dd50 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -200,7 +200,7 @@ typedef u32 __attribute__((vector_size(16))) sse128_t;
 
 /* Type, address-of, and value of an instruction's operand. */
 struct operand {
-	enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_NONE } type;
+	enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
 	unsigned int bytes;
 	union {
 		unsigned long orig_val;
@@ -213,12 +213,14 @@ struct operand {
 			unsigned seg;
 		} mem;
 		unsigned xmm;
+		unsigned mm;
 	} addr;
 	union {
 		unsigned long val;
 		u64 val64;
 		char valptr[sizeof(unsigned long) + 2];
 		sse128_t vec_val;
+		u64 mm_val;
 	};
 };
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e5b97be12d2a..db7c1f2709a2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -173,6 +173,9 @@ enum {
 #define DR7_FIXED_1	0x00000400
 #define DR7_VOLATILE	0xffff23ff
 
+/* apic attention bits */
+#define KVM_APIC_CHECK_VAPIC	0
+
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
  * enough memory for a single page fault in a cache.
@@ -238,8 +241,6 @@ struct kvm_mmu_page {
 #endif
 
 	int write_flooding_count;
-
-	struct rcu_head rcu;
 };
 
 struct kvm_pio_request {
@@ -338,6 +339,7 @@ struct kvm_vcpu_arch {
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
+	unsigned long apic_attention;
 	int32_t apic_arb_prio;
 	int mp_state;
 	int sipi_vector;
@@ -537,8 +539,6 @@ struct kvm_arch {
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
 
-	atomic_t reader_counter;
-
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
 	#endif
@@ -713,8 +713,9 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 
 int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
-int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
-			       struct kvm_memory_slot *slot);
+void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+				     struct kvm_memory_slot *slot,
+				     gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 183922e13de1..63ab1661d00e 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -95,6 +95,14 @@ struct kvm_vcpu_pv_apf_data {
 extern void kvmclock_init(void);
 extern int kvm_register_clock(char *txt);
 
+#ifdef CONFIG_KVM_CLOCK
+bool kvm_check_and_clear_guest_paused(void);
+#else
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+#endif /* CONFIG_KVMCLOCK */
 
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
  * trap that we will then rewrite to the appropriate instruction.
@@ -173,14 +181,16 @@ static inline int kvm_para_available(void)
 	if (boot_cpu_data.cpuid_level < 0)
 		return 0;	/* So we don't blow up on old processors */
 
-	cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
-	memcpy(signature + 0, &ebx, 4);
-	memcpy(signature + 4, &ecx, 4);
-	memcpy(signature + 8, &edx, 4);
-	signature[12] = 0;
+	if (cpu_has_hypervisor) {
+		cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
+		memcpy(signature + 0, &ebx, 4);
+		memcpy(signature + 4, &ecx, 4);
+		memcpy(signature + 8, &edx, 4);
+		signature[12] = 0;
 
-	if (strcmp(signature, "KVMKVMKVM") == 0)
-		return 1;
+		if (strcmp(signature, "KVMKVMKVM") == 0)
+			return 1;
+	}
 
 	return 0;
 }
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 35f2d1948ada..6167fd798188 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -40,5 +40,6 @@ struct pvclock_wall_clock {
 } __attribute__((__packed__));
 
 #define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
+#define PVCLOCK_GUEST_STOPPED	(1 << 1)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index f8492da65bfc..086eb58c6e80 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -22,6 +22,7 @@
 #include <asm/msr.h>
 #include <asm/apic.h>
 #include <linux/percpu.h>
+#include <linux/hardirq.h>
 
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
@@ -114,6 +115,25 @@ static void kvm_get_preset_lpj(void)
 	preset_lpj = lpj;
 }
 
+bool kvm_check_and_clear_guest_paused(void)
+{
+	bool ret = false;
+	struct pvclock_vcpu_time_info *src;
+
+	/*
+	 * per_cpu() is safe here because this function is only called from
+	 * timer functions where preemption is already disabled.
+	 */
+	WARN_ON(!in_atomic());
+	src = &__get_cpu_var(hv_clock);
+	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
+		__this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED);
+		ret = true;
+	}
+
+	return ret;
+}
+
 static struct clocksource kvm_clock = {
 	.name = "kvm-clock",
 	.read = kvm_clock_get_cycles,
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 1a7fe868f375..a28f338843ea 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -36,6 +36,7 @@ config KVM
 	select TASKSTATS
 	select TASK_DELAY_ACCT
 	select PERF_EVENTS
+	select HAVE_KVM_MSI
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9fed5bedaad6..7df1c6d839fb 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -247,7 +247,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 7.0.ebx */
 	const u32 kvm_supported_word9_x86_features =
-		F(FSGSBASE) | F(BMI1) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS);
+		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
+		F(BMI2) | F(ERMS) | F(RTM);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
@@ -397,7 +398,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	case KVM_CPUID_SIGNATURE: {
 		char signature[12] = "KVMKVMKVM\0\0";
 		u32 *sigptr = (u32 *)signature;
-		entry->eax = 0;
+		entry->eax = KVM_CPUID_FEATURES;
 		entry->ebx = sigptr[0];
 		entry->ecx = sigptr[1];
 		entry->edx = sigptr[2];
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 83756223f8aa..f95d242ee9f7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -142,6 +142,10 @@
 #define Src2FS      (OpFS << Src2Shift)
 #define Src2GS      (OpGS << Src2Shift)
 #define Src2Mask    (OpMask << Src2Shift)
+#define Mmx         ((u64)1 << 40)  /* MMX Vector instruction */
+#define Aligned     ((u64)1 << 41)  /* Explicitly aligned (e.g. MOVDQA) */
+#define Unaligned   ((u64)1 << 42)  /* Explicitly unaligned (e.g. MOVDQU) */
+#define Avx         ((u64)1 << 43)  /* Advanced Vector Extensions */
 
 #define X2(x...) x, x
 #define X3(x...) X2(x), x
@@ -557,6 +561,29 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector,
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg);
 }
 
+/*
+ * x86 defines three classes of vector instructions: explicitly
+ * aligned, explicitly unaligned, and the rest, which change behaviour
+ * depending on whether they're AVX encoded or not.
+ *
+ * Also included is CMPXCHG16B which is not a vector instruction, yet it is
+ * subject to the same check.
+ */
+static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
+{
+	if (likely(size < 16))
+		return false;
+
+	if (ctxt->d & Aligned)
+		return true;
+	else if (ctxt->d & Unaligned)
+		return false;
+	else if (ctxt->d & Avx)
+		return false;
+	else
+		return true;
+}
+
 static int __linearize(struct x86_emulate_ctxt *ctxt,
 		     struct segmented_address addr,
 		     unsigned size, bool write, bool fetch,
@@ -621,6 +648,8 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
 	}
 	if (fetch ? ctxt->mode != X86EMUL_MODE_PROT64 : ctxt->ad_bytes != 8)
 		la &= (u32)-1;
+	if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
+		return emulate_gp(ctxt, 0);
 	*linear = la;
 	return X86EMUL_CONTINUE;
 bad:
@@ -859,6 +888,40 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 	ctxt->ops->put_fpu(ctxt);
 }
 
+static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+{
+	ctxt->ops->get_fpu(ctxt);
+	switch (reg) {
+	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
+	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
+	case 2: asm("movq %%mm2, %0" : "=m"(*data)); break;
+	case 3: asm("movq %%mm3, %0" : "=m"(*data)); break;
+	case 4: asm("movq %%mm4, %0" : "=m"(*data)); break;
+	case 5: asm("movq %%mm5, %0" : "=m"(*data)); break;
+	case 6: asm("movq %%mm6, %0" : "=m"(*data)); break;
+	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
+	default: BUG();
+	}
+	ctxt->ops->put_fpu(ctxt);
+}
+
+static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+{
+	ctxt->ops->get_fpu(ctxt);
+	switch (reg) {
+	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
+	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
+	case 2: asm("movq %0, %%mm2" : : "m"(*data)); break;
+	case 3: asm("movq %0, %%mm3" : : "m"(*data)); break;
+	case 4: asm("movq %0, %%mm4" : : "m"(*data)); break;
+	case 5: asm("movq %0, %%mm5" : : "m"(*data)); break;
+	case 6: asm("movq %0, %%mm6" : : "m"(*data)); break;
+	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
+	default: BUG();
+	}
+	ctxt->ops->put_fpu(ctxt);
+}
+
 static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 				    struct operand *op)
 {
@@ -875,6 +938,13 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 		read_sse_reg(ctxt, &op->vec_val, reg);
 		return;
 	}
+	if (ctxt->d & Mmx) {
+		reg &= 7;
+		op->type = OP_MM;
+		op->bytes = 8;
+		op->addr.mm = reg;
+		return;
+	}
 
 	op->type = OP_REG;
 	if (ctxt->d & ByteOp) {
@@ -902,7 +972,6 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 		ctxt->modrm_rm = base_reg = (ctxt->rex_prefix & 1) << 3; /* REG.B */
 	}
 
-	ctxt->modrm = insn_fetch(u8, ctxt);
 	ctxt->modrm_mod |= (ctxt->modrm & 0xc0) >> 6;
 	ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3;
 	ctxt->modrm_rm |= (ctxt->modrm & 0x07);
@@ -920,6 +989,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 			read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm);
 			return rc;
 		}
+		if (ctxt->d & Mmx) {
+			op->type = OP_MM;
+			op->bytes = 8;
+			op->addr.xmm = ctxt->modrm_rm & 7;
+			return rc;
+		}
 		fetch_register_operand(op);
 		return rc;
 	}
@@ -1387,6 +1462,9 @@ static int writeback(struct x86_emulate_ctxt *ctxt)
 	case OP_XMM:
 		write_sse_reg(ctxt, &ctxt->dst.vec_val, ctxt->dst.addr.xmm);
 		break;
+	case OP_MM:
+		write_mmx_reg(ctxt, &ctxt->dst.mm_val, ctxt->dst.addr.mm);
+		break;
 	case OP_NONE:
 		/* no writeback */
 		break;
@@ -2790,7 +2868,7 @@ static int em_rdpmc(struct x86_emulate_ctxt *ctxt)
 
 static int em_mov(struct x86_emulate_ctxt *ctxt)
 {
-	ctxt->dst.val = ctxt->src.val;
+	memcpy(ctxt->dst.valptr, ctxt->src.valptr, ctxt->op_bytes);
 	return X86EMUL_CONTINUE;
 }
 
@@ -2870,12 +2948,6 @@ static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt)
 	return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg);
 }
 
-static int em_movdqu(struct x86_emulate_ctxt *ctxt)
-{
-	memcpy(&ctxt->dst.vec_val, &ctxt->src.vec_val, ctxt->op_bytes);
-	return X86EMUL_CONTINUE;
-}
-
 static int em_invlpg(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
@@ -3061,35 +3133,13 @@ static int em_btc(struct x86_emulate_ctxt *ctxt)
 
 static int em_bsf(struct x86_emulate_ctxt *ctxt)
 {
-	u8 zf;
-
-	__asm__ ("bsf %2, %0; setz %1"
-		 : "=r"(ctxt->dst.val), "=q"(zf)
-		 : "r"(ctxt->src.val));
-
-	ctxt->eflags &= ~X86_EFLAGS_ZF;
-	if (zf) {
-		ctxt->eflags |= X86_EFLAGS_ZF;
-		/* Disable writeback. */
-		ctxt->dst.type = OP_NONE;
-	}
+	emulate_2op_SrcV_nobyte(ctxt, "bsf");
 	return X86EMUL_CONTINUE;
 }
 
 static int em_bsr(struct x86_emulate_ctxt *ctxt)
 {
-	u8 zf;
-
-	__asm__ ("bsr %2, %0; setz %1"
-		 : "=r"(ctxt->dst.val), "=q"(zf)
-		 : "r"(ctxt->src.val));
-
-	ctxt->eflags &= ~X86_EFLAGS_ZF;
-	if (zf) {
-		ctxt->eflags |= X86_EFLAGS_ZF;
-		/* Disable writeback. */
-		ctxt->dst.type = OP_NONE;
-	}
+	emulate_2op_SrcV_nobyte(ctxt, "bsr");
 	return X86EMUL_CONTINUE;
 }
 
@@ -3286,8 +3336,8 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 		      .check_perm = (_p) }
 #define N    D(0)
 #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
-#define G(_f, _g) { .flags = ((_f) | Group), .u.group = (_g) }
-#define GD(_f, _g) { .flags = ((_f) | GroupDual), .u.gdual = (_g) }
+#define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
+#define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
 #define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
 #define II(_f, _e, _i) \
 	{ .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i }
@@ -3307,25 +3357,25 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 		I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
 
 static struct opcode group7_rm1[] = {
-	DI(SrcNone | ModRM | Priv, monitor),
-	DI(SrcNone | ModRM | Priv, mwait),
+	DI(SrcNone | Priv, monitor),
+	DI(SrcNone | Priv, mwait),
 	N, N, N, N, N, N,
 };
 
 static struct opcode group7_rm3[] = {
-	DIP(SrcNone | ModRM | Prot | Priv, vmrun,   check_svme_pa),
-	II(SrcNone | ModRM | Prot | VendorSpecific, em_vmmcall, vmmcall),
-	DIP(SrcNone | ModRM | Prot | Priv, vmload,  check_svme_pa),
-	DIP(SrcNone | ModRM | Prot | Priv, vmsave,  check_svme_pa),
-	DIP(SrcNone | ModRM | Prot | Priv, stgi,    check_svme),
-	DIP(SrcNone | ModRM | Prot | Priv, clgi,    check_svme),
-	DIP(SrcNone | ModRM | Prot | Priv, skinit,  check_svme),
-	DIP(SrcNone | ModRM | Prot | Priv, invlpga, check_svme),
+	DIP(SrcNone | Prot | Priv,		vmrun,		check_svme_pa),
+	II(SrcNone  | Prot | VendorSpecific,	em_vmmcall,	vmmcall),
+	DIP(SrcNone | Prot | Priv,		vmload,		check_svme_pa),
+	DIP(SrcNone | Prot | Priv,		vmsave,		check_svme_pa),
+	DIP(SrcNone | Prot | Priv,		stgi,		check_svme),
+	DIP(SrcNone | Prot | Priv,		clgi,		check_svme),
+	DIP(SrcNone | Prot | Priv,		skinit,		check_svme),
+	DIP(SrcNone | Prot | Priv,		invlpga,	check_svme),
 };
 
 static struct opcode group7_rm7[] = {
 	N,
-	DIP(SrcNone | ModRM, rdtscp, check_rdtsc),
+	DIP(SrcNone, rdtscp, check_rdtsc),
 	N, N, N, N, N, N,
 };
 
@@ -3341,81 +3391,86 @@ static struct opcode group1[] = {
 };
 
 static struct opcode group1A[] = {
-	I(DstMem | SrcNone | ModRM | Mov | Stack, em_pop), N, N, N, N, N, N, N,
+	I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N,
 };
 
 static struct opcode group3[] = {
-	I(DstMem | SrcImm | ModRM, em_test),
-	I(DstMem | SrcImm | ModRM, em_test),
-	I(DstMem | SrcNone | ModRM | Lock, em_not),
-	I(DstMem | SrcNone | ModRM | Lock, em_neg),
-	I(SrcMem | ModRM, em_mul_ex),
-	I(SrcMem | ModRM, em_imul_ex),
-	I(SrcMem | ModRM, em_div_ex),
-	I(SrcMem | ModRM, em_idiv_ex),
+	I(DstMem | SrcImm, em_test),
+	I(DstMem | SrcImm, em_test),
+	I(DstMem | SrcNone | Lock, em_not),
+	I(DstMem | SrcNone | Lock, em_neg),
+	I(SrcMem, em_mul_ex),
+	I(SrcMem, em_imul_ex),
+	I(SrcMem, em_div_ex),
+	I(SrcMem, em_idiv_ex),
 };
 
 static struct opcode group4[] = {
-	I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45),
-	I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45),
+	I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
+	I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
 	N, N, N, N, N, N,
 };
 
 static struct opcode group5[] = {
-	I(DstMem | SrcNone | ModRM | Lock, em_grp45),
-	I(DstMem | SrcNone | ModRM | Lock, em_grp45),
-	I(SrcMem | ModRM | Stack, em_grp45),
-	I(SrcMemFAddr | ModRM | ImplicitOps | Stack, em_call_far),
-	I(SrcMem | ModRM | Stack, em_grp45),
-	I(SrcMemFAddr | ModRM | ImplicitOps, em_grp45),
-	I(SrcMem | ModRM | Stack, em_grp45), N,
+	I(DstMem | SrcNone | Lock,		em_grp45),
+	I(DstMem | SrcNone | Lock,		em_grp45),
+	I(SrcMem | Stack,			em_grp45),
+	I(SrcMemFAddr | ImplicitOps | Stack,	em_call_far),
+	I(SrcMem | Stack,			em_grp45),
+	I(SrcMemFAddr | ImplicitOps,		em_grp45),
+	I(SrcMem | Stack,			em_grp45), N,
 };
 
 static struct opcode group6[] = {
-	DI(ModRM | Prot,        sldt),
-	DI(ModRM | Prot,        str),
-	DI(ModRM | Prot | Priv, lldt),
-	DI(ModRM | Prot | Priv, ltr),
+	DI(Prot,	sldt),
+	DI(Prot,	str),
+	DI(Prot | Priv,	lldt),
+	DI(Prot | Priv,	ltr),
 	N, N, N, N,
 };
 
 static struct group_dual group7 = { {
-	DI(ModRM | Mov | DstMem | Priv, sgdt),
-	DI(ModRM | Mov | DstMem | Priv, sidt),
-	II(ModRM | SrcMem | Priv, em_lgdt, lgdt),
-	II(ModRM | SrcMem | Priv, em_lidt, lidt),
-	II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N,
-	II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw),
-	II(SrcMem | ModRM | ByteOp | Priv | NoAccess, em_invlpg, invlpg),
+	DI(Mov | DstMem | Priv,			sgdt),
+	DI(Mov | DstMem | Priv,			sidt),
+	II(SrcMem | Priv,			em_lgdt, lgdt),
+	II(SrcMem | Priv,			em_lidt, lidt),
+	II(SrcNone | DstMem | Mov,		em_smsw, smsw), N,
+	II(SrcMem16 | Mov | Priv,		em_lmsw, lmsw),
+	II(SrcMem | ByteOp | Priv | NoAccess,	em_invlpg, invlpg),
 }, {
-	I(SrcNone | ModRM | Priv | VendorSpecific, em_vmcall),
+	I(SrcNone | Priv | VendorSpecific,	em_vmcall),
 	EXT(0, group7_rm1),
 	N, EXT(0, group7_rm3),
-	II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N,
-	II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7),
+	II(SrcNone | DstMem | Mov,		em_smsw, smsw), N,
+	II(SrcMem16 | Mov | Priv,		em_lmsw, lmsw),
+	EXT(0, group7_rm7),
 } };
 
 static struct opcode group8[] = {
 	N, N, N, N,
-	I(DstMem | SrcImmByte | ModRM, em_bt),
-	I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_bts),
-	I(DstMem | SrcImmByte | ModRM | Lock, em_btr),
-	I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_btc),
+	I(DstMem | SrcImmByte,				em_bt),
+	I(DstMem | SrcImmByte | Lock | PageTable,	em_bts),
+	I(DstMem | SrcImmByte | Lock,			em_btr),
+	I(DstMem | SrcImmByte | Lock | PageTable,	em_btc),
 };
 
 static struct group_dual group9 = { {
-	N, I(DstMem64 | ModRM | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N,
+	N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N,
 }, {
 	N, N, N, N, N, N, N, N,
 } };
 
 static struct opcode group11[] = {
-	I(DstMem | SrcImm | ModRM | Mov | PageTable, em_mov),
+	I(DstMem | SrcImm | Mov | PageTable, em_mov),
 	X7(D(Undefined)),
 };
 
 static struct gprefix pfx_0f_6f_0f_7f = {
-	N, N, N, I(Sse, em_movdqu),
+	I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
+};
+
+static struct gprefix pfx_vmovntpx = {
+	I(0, em_mov), N, N, N,
 };
 
 static struct opcode opcode_table[256] = {
@@ -3464,10 +3519,10 @@ static struct opcode opcode_table[256] = {
 	/* 0x70 - 0x7F */
 	X16(D(SrcImmByte)),
 	/* 0x80 - 0x87 */
-	G(ByteOp | DstMem | SrcImm | ModRM | Group, group1),
-	G(DstMem | SrcImm | ModRM | Group, group1),
-	G(ByteOp | DstMem | SrcImm | ModRM | No64 | Group, group1),
-	G(DstMem | SrcImmByte | ModRM | Group, group1),
+	G(ByteOp | DstMem | SrcImm, group1),
+	G(DstMem | SrcImm, group1),
+	G(ByteOp | DstMem | SrcImm | No64, group1),
+	G(DstMem | SrcImmByte, group1),
 	I2bv(DstMem | SrcReg | ModRM, em_test),
 	I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg),
 	/* 0x88 - 0x8F */
@@ -3549,7 +3604,8 @@ static struct opcode twobyte_table[256] = {
 	IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write),
 	IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write),
 	N, N, N, N,
-	N, N, N, N, N, N, N, N,
+	N, N, N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx),
+	N, N, N, N,
 	/* 0x30 - 0x3F */
 	II(ImplicitOps | Priv, em_wrmsr, wrmsr),
 	IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc),
@@ -3897,17 +3953,16 @@ done_prefixes:
 	}
 	ctxt->d = opcode.flags;
 
+	if (ctxt->d & ModRM)
+		ctxt->modrm = insn_fetch(u8, ctxt);
+
 	while (ctxt->d & GroupMask) {
 		switch (ctxt->d & GroupMask) {
 		case Group:
-			ctxt->modrm = insn_fetch(u8, ctxt);
-			--ctxt->_eip;
 			goffset = (ctxt->modrm >> 3) & 7;
 			opcode = opcode.u.group[goffset];
 			break;
 		case GroupDual:
-			ctxt->modrm = insn_fetch(u8, ctxt);
-			--ctxt->_eip;
 			goffset = (ctxt->modrm >> 3) & 7;
 			if ((ctxt->modrm >> 6) == 3)
 				opcode = opcode.u.gdual->mod3[goffset];
@@ -3960,6 +4015,8 @@ done_prefixes:
 
 	if (ctxt->d & Sse)
 		ctxt->op_bytes = 16;
+	else if (ctxt->d & Mmx)
+		ctxt->op_bytes = 8;
 
 	/* ModRM and SIB bytes. */
 	if (ctxt->d & ModRM) {
@@ -4030,6 +4087,35 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
 	return false;
 }
 
+static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
+{
+	bool fault = false;
+
+	ctxt->ops->get_fpu(ctxt);
+	asm volatile("1: fwait \n\t"
+		     "2: \n\t"
+		     ".pushsection .fixup,\"ax\" \n\t"
+		     "3: \n\t"
+		     "movb $1, %[fault] \n\t"
+		     "jmp 2b \n\t"
+		     ".popsection \n\t"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [fault]"+qm"(fault));
+	ctxt->ops->put_fpu(ctxt);
+
+	if (unlikely(fault))
+		return emulate_exception(ctxt, MF_VECTOR, 0, false);
+
+	return X86EMUL_CONTINUE;
+}
+
+static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
+				       struct operand *op)
+{
+	if (op->type == OP_MM)
+		read_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
+}
+
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 {
 	struct x86_emulate_ops *ops = ctxt->ops;
@@ -4054,18 +4140,31 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		goto done;
 	}
 
-	if ((ctxt->d & Sse)
-	    && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)
-		|| !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
+	if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)))
+	    || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
 		rc = emulate_ud(ctxt);
 		goto done;
 	}
 
-	if ((ctxt->d & Sse) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
+	if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
 		rc = emulate_nm(ctxt);
 		goto done;
 	}
 
+	if (ctxt->d & Mmx) {
+		rc = flush_pending_x87_faults(ctxt);
+		if (rc != X86EMUL_CONTINUE)
+			goto done;
+		/*
+		 * Now that we know the fpu is exception safe, we can fetch
+		 * operands from it.
+		 */
+		fetch_possible_mmx_operand(ctxt, &ctxt->src);
+		fetch_possible_mmx_operand(ctxt, &ctxt->src2);
+		if (!(ctxt->d & Mov))
+			fetch_possible_mmx_operand(ctxt, &ctxt->dst);
+	}
+
 	if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_PRE_EXCEPT);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index d68f99df690c..adba28f88d1a 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -34,7 +34,6 @@
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
-#include <linux/workqueue.h>
 
 #include "irq.h"
 #include "i8254.h"
@@ -249,7 +248,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 		/* in this case, we had multiple outstanding pit interrupts
 		 * that we needed to inject.  Reinject
 		 */
-		queue_work(ps->pit->wq, &ps->pit->expired);
+		queue_kthread_work(&ps->pit->worker, &ps->pit->expired);
 	ps->irq_ack = 1;
 	spin_unlock(&ps->inject_lock);
 }
@@ -270,7 +269,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 static void destroy_pit_timer(struct kvm_pit *pit)
 {
 	hrtimer_cancel(&pit->pit_state.pit_timer.timer);
-	cancel_work_sync(&pit->expired);
+	flush_kthread_work(&pit->expired);
 }
 
 static bool kpit_is_periodic(struct kvm_timer *ktimer)
@@ -284,7 +283,7 @@ static struct kvm_timer_ops kpit_ops = {
 	.is_periodic = kpit_is_periodic,
 };
 
-static void pit_do_work(struct work_struct *work)
+static void pit_do_work(struct kthread_work *work)
 {
 	struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
 	struct kvm *kvm = pit->kvm;
@@ -328,7 +327,7 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 
 	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
 		atomic_inc(&ktimer->pending);
-		queue_work(pt->wq, &pt->expired);
+		queue_kthread_work(&pt->worker, &pt->expired);
 	}
 
 	if (ktimer->t_ops->is_periodic(ktimer)) {
@@ -353,7 +352,7 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 
 	/* TODO The new value only affected after the retriggered */
 	hrtimer_cancel(&pt->timer);
-	cancel_work_sync(&ps->pit->expired);
+	flush_kthread_work(&ps->pit->expired);
 	pt->period = interval;
 	ps->is_periodic = is_period;
 
@@ -669,6 +668,8 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;
 	struct kvm_kpit_state *pit_state;
+	struct pid *pid;
+	pid_t pid_nr;
 	int ret;
 
 	pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL);
@@ -685,14 +686,20 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	mutex_lock(&pit->pit_state.lock);
 	spin_lock_init(&pit->pit_state.inject_lock);
 
-	pit->wq = create_singlethread_workqueue("kvm-pit-wq");
-	if (!pit->wq) {
+	pid = get_pid(task_tgid(current));
+	pid_nr = pid_vnr(pid);
+	put_pid(pid);
+
+	init_kthread_worker(&pit->worker);
+	pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker,
+				       "kvm-pit/%d", pid_nr);
+	if (IS_ERR(pit->worker_task)) {
 		mutex_unlock(&pit->pit_state.lock);
 		kvm_free_irq_source_id(kvm, pit->irq_source_id);
 		kfree(pit);
 		return NULL;
 	}
-	INIT_WORK(&pit->expired, pit_do_work);
+	init_kthread_work(&pit->expired, pit_do_work);
 
 	kvm->arch.vpit = pit;
 	pit->kvm = kvm;
@@ -736,7 +743,7 @@ fail:
 	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);
-	destroy_workqueue(pit->wq);
+	kthread_stop(pit->worker_task);
 	kfree(pit);
 	return NULL;
 }
@@ -756,10 +763,10 @@ void kvm_free_pit(struct kvm *kvm)
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
 		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
 		hrtimer_cancel(timer);
-		cancel_work_sync(&kvm->arch.vpit->expired);
+		flush_kthread_work(&kvm->arch.vpit->expired);
+		kthread_stop(kvm->arch.vpit->worker_task);
 		kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id);
 		mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-		destroy_workqueue(kvm->arch.vpit->wq);
 		kfree(kvm->arch.vpit);
 	}
 }
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 51a97426e791..fdf40425ea1d 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -1,6 +1,8 @@
 #ifndef __I8254_H
 #define __I8254_H
 
+#include <linux/kthread.h>
+
 #include "iodev.h"
 
 struct kvm_kpit_channel_state {
@@ -39,8 +41,9 @@ struct kvm_pit {
 	struct kvm_kpit_state pit_state;
 	int irq_source_id;
 	struct kvm_irq_mask_notifier mask_notifier;
-	struct workqueue_struct *wq;
-	struct work_struct expired;
+	struct kthread_worker worker;
+	struct task_struct *worker_task;
+	struct kthread_work expired;
 };
 
 #define KVM_PIT_BASE_ADDRESS	    0x40
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 858432287ab6..93c15743f1ee 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -92,6 +92,11 @@ static inline int apic_test_and_clear_vector(int vec, void *bitmap)
 	return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
 }
 
+static inline int apic_test_vector(int vec, void *bitmap)
+{
+	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
 static inline void apic_set_vector(int vec, void *bitmap)
 {
 	set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -480,7 +485,6 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 static void apic_set_eoi(struct kvm_lapic *apic)
 {
 	int vector = apic_find_highest_isr(apic);
-	int trigger_mode;
 	/*
 	 * Not every write EOI will has corresponding ISR,
 	 * one example is when Kernel check timer on setup_IO_APIC
@@ -491,12 +495,15 @@ static void apic_set_eoi(struct kvm_lapic *apic)
 	apic_clear_vector(vector, apic->regs + APIC_ISR);
 	apic_update_ppr(apic);
 
-	if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR))
-		trigger_mode = IOAPIC_LEVEL_TRIG;
-	else
-		trigger_mode = IOAPIC_EDGE_TRIG;
-	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI))
+	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+		int trigger_mode;
+		if (apic_test_vector(vector, apic->regs + APIC_TMR))
+			trigger_mode = IOAPIC_LEVEL_TRIG;
+		else
+			trigger_mode = IOAPIC_EDGE_TRIG;
 		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
+	}
 	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
 }
 
@@ -1081,6 +1088,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	apic_update_ppr(apic);
 
 	vcpu->arch.apic_arb_prio = 0;
+	vcpu->arch.apic_attention = 0;
 
 	apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
 		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
@@ -1280,7 +1288,7 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 	u32 data;
 	void *vapic;
 
-	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
+	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
 	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
@@ -1297,7 +1305,7 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic;
 	void *vapic;
 
-	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
+	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
 	apic = vcpu->arch.apic;
@@ -1317,10 +1325,11 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 
 void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
 {
-	if (!irqchip_in_kernel(vcpu->kvm))
-		return;
-
 	vcpu->arch.apic->vapic_addr = vapic_addr;
+	if (vapic_addr)
+		__set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+	else
+		__clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
 }
 
 int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4cb164268846..72102e0ab7cb 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -135,8 +135,6 @@ module_param(dbg, bool, 0644);
 #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
 			| PT64_NX_MASK)
 
-#define PTE_LIST_EXT 4
-
 #define ACC_EXEC_MASK    1
 #define ACC_WRITE_MASK   PT_WRITABLE_MASK
 #define ACC_USER_MASK    PT_USER_MASK
@@ -151,6 +149,9 @@ module_param(dbg, bool, 0644);
 
 #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
 
+/* make pte_list_desc fit well in cache line */
+#define PTE_LIST_EXT 3
+
 struct pte_list_desc {
 	u64 *sptes[PTE_LIST_EXT];
 	struct pte_list_desc *more;
@@ -550,19 +551,29 @@ static u64 mmu_spte_get_lockless(u64 *sptep)
 
 static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
 {
-	rcu_read_lock();
-	atomic_inc(&vcpu->kvm->arch.reader_counter);
-
-	/* Increase the counter before walking shadow page table */
-	smp_mb__after_atomic_inc();
+	/*
+	 * Prevent page table teardown by making any free-er wait during
+	 * kvm_flush_remote_tlbs() IPI to all active vcpus.
+	 */
+	local_irq_disable();
+	vcpu->mode = READING_SHADOW_PAGE_TABLES;
+	/*
+	 * Make sure a following spte read is not reordered ahead of the write
+	 * to vcpu->mode.
+	 */
+	smp_mb();
 }
 
 static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
 {
-	/* Decrease the counter after walking shadow page table finished */
-	smp_mb__before_atomic_dec();
-	atomic_dec(&vcpu->kvm->arch.reader_counter);
-	rcu_read_unlock();
+	/*
+	 * Make sure the write to vcpu->mode is not reordered in front of
+	 * reads to sptes.  If it does, kvm_commit_zap_page() can see us
+	 * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
+	 */
+	smp_mb();
+	vcpu->mode = OUTSIDE_GUEST_MODE;
+	local_irq_enable();
 }
 
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
@@ -841,32 +852,6 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
 	return count;
 }
 
-static u64 *pte_list_next(unsigned long *pte_list, u64 *spte)
-{
-	struct pte_list_desc *desc;
-	u64 *prev_spte;
-	int i;
-
-	if (!*pte_list)
-		return NULL;
-	else if (!(*pte_list & 1)) {
-		if (!spte)
-			return (u64 *)*pte_list;
-		return NULL;
-	}
-	desc = (struct pte_list_desc *)(*pte_list & ~1ul);
-	prev_spte = NULL;
-	while (desc) {
-		for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) {
-			if (prev_spte == spte)
-				return desc->sptes[i];
-			prev_spte = desc->sptes[i];
-		}
-		desc = desc->more;
-	}
-	return NULL;
-}
-
 static void
 pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc,
 			   int i, struct pte_list_desc *prev_desc)
@@ -987,11 +972,6 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	return pte_list_add(vcpu, spte, rmapp);
 }
 
-static u64 *rmap_next(unsigned long *rmapp, u64 *spte)
-{
-	return pte_list_next(rmapp, spte);
-}
-
 static void rmap_remove(struct kvm *kvm, u64 *spte)
 {
 	struct kvm_mmu_page *sp;
@@ -1004,106 +984,201 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 	pte_list_remove(spte, rmapp);
 }
 
+/*
+ * Used by the following functions to iterate through the sptes linked by a
+ * rmap.  All fields are private and not assumed to be used outside.
+ */
+struct rmap_iterator {
+	/* private fields */
+	struct pte_list_desc *desc;	/* holds the sptep if not NULL */
+	int pos;			/* index of the sptep */
+};
+
+/*
+ * Iteration must be started by this function.  This should also be used after
+ * removing/dropping sptes from the rmap link because in such cases the
+ * information in the itererator may not be valid.
+ *
+ * Returns sptep if found, NULL otherwise.
+ */
+static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter)
+{
+	if (!rmap)
+		return NULL;
+
+	if (!(rmap & 1)) {
+		iter->desc = NULL;
+		return (u64 *)rmap;
+	}
+
+	iter->desc = (struct pte_list_desc *)(rmap & ~1ul);
+	iter->pos = 0;
+	return iter->desc->sptes[iter->pos];
+}
+
+/*
+ * Must be used with a valid iterator: e.g. after rmap_get_first().
+ *
+ * Returns sptep if found, NULL otherwise.
+ */
+static u64 *rmap_get_next(struct rmap_iterator *iter)
+{
+	if (iter->desc) {
+		if (iter->pos < PTE_LIST_EXT - 1) {
+			u64 *sptep;
+
+			++iter->pos;
+			sptep = iter->desc->sptes[iter->pos];
+			if (sptep)
+				return sptep;
+		}
+
+		iter->desc = iter->desc->more;
+
+		if (iter->desc) {
+			iter->pos = 0;
+			/* desc->sptes[0] cannot be NULL */
+			return iter->desc->sptes[iter->pos];
+		}
+	}
+
+	return NULL;
+}
+
 static void drop_spte(struct kvm *kvm, u64 *sptep)
 {
 	if (mmu_spte_clear_track_bits(sptep))
 		rmap_remove(kvm, sptep);
 }
 
-int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
-			       struct kvm_memory_slot *slot)
+static int __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, int level)
 {
-	unsigned long *rmapp;
-	u64 *spte;
-	int i, write_protected = 0;
-
-	rmapp = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot);
-	spte = rmap_next(rmapp, NULL);
-	while (spte) {
-		BUG_ON(!(*spte & PT_PRESENT_MASK));
-		rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
-		if (is_writable_pte(*spte)) {
-			mmu_spte_update(spte, *spte & ~PT_WRITABLE_MASK);
-			write_protected = 1;
+	u64 *sptep;
+	struct rmap_iterator iter;
+	int write_protected = 0;
+
+	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
+		BUG_ON(!(*sptep & PT_PRESENT_MASK));
+		rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);
+
+		if (!is_writable_pte(*sptep)) {
+			sptep = rmap_get_next(&iter);
+			continue;
 		}
-		spte = rmap_next(rmapp, spte);
-	}
 
-	/* check for huge page mappings */
-	for (i = PT_DIRECTORY_LEVEL;
-	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
-		rmapp = __gfn_to_rmap(gfn, i, slot);
-		spte = rmap_next(rmapp, NULL);
-		while (spte) {
-			BUG_ON(!(*spte & PT_PRESENT_MASK));
-			BUG_ON(!is_large_pte(*spte));
-			pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
-			if (is_writable_pte(*spte)) {
-				drop_spte(kvm, spte);
-				--kvm->stat.lpages;
-				spte = NULL;
-				write_protected = 1;
-			}
-			spte = rmap_next(rmapp, spte);
+		if (level == PT_PAGE_TABLE_LEVEL) {
+			mmu_spte_update(sptep, *sptep & ~PT_WRITABLE_MASK);
+			sptep = rmap_get_next(&iter);
+		} else {
+			BUG_ON(!is_large_pte(*sptep));
+			drop_spte(kvm, sptep);
+			--kvm->stat.lpages;
+			sptep = rmap_get_first(*rmapp, &iter);
 		}
+
+		write_protected = 1;
 	}
 
 	return write_protected;
 }
 
+/**
+ * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages
+ * @kvm: kvm instance
+ * @slot: slot to protect
+ * @gfn_offset: start of the BITS_PER_LONG pages we care about
+ * @mask: indicates which pages we should protect
+ *
+ * Used when we do not need to care about huge page mappings: e.g. during dirty
+ * logging we do not have any such mappings.
+ */
+void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+				     struct kvm_memory_slot *slot,
+				     gfn_t gfn_offset, unsigned long mask)
+{
+	unsigned long *rmapp;
+
+	while (mask) {
+		rmapp = &slot->rmap[gfn_offset + __ffs(mask)];
+		__rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL);
+
+		/* clear the first set bit */
+		mask &= mask - 1;
+	}
+}
+
 static int rmap_write_protect(struct kvm *kvm, u64 gfn)
 {
 	struct kvm_memory_slot *slot;
+	unsigned long *rmapp;
+	int i;
+	int write_protected = 0;
 
 	slot = gfn_to_memslot(kvm, gfn);
-	return kvm_mmu_rmap_write_protect(kvm, gfn, slot);
+
+	for (i = PT_PAGE_TABLE_LEVEL;
+	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+		rmapp = __gfn_to_rmap(gfn, i, slot);
+		write_protected |= __rmap_write_protect(kvm, rmapp, i);
+	}
+
+	return write_protected;
 }
 
 static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			   unsigned long data)
 {
-	u64 *spte;
+	u64 *sptep;
+	struct rmap_iterator iter;
 	int need_tlb_flush = 0;
 
-	while ((spte = rmap_next(rmapp, NULL))) {
-		BUG_ON(!(*spte & PT_PRESENT_MASK));
-		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte);
-		drop_spte(kvm, spte);
+	while ((sptep = rmap_get_first(*rmapp, &iter))) {
+		BUG_ON(!(*sptep & PT_PRESENT_MASK));
+		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", sptep, *sptep);
+
+		drop_spte(kvm, sptep);
 		need_tlb_flush = 1;
 	}
+
 	return need_tlb_flush;
 }
 
 static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			     unsigned long data)
 {
+	u64 *sptep;
+	struct rmap_iterator iter;
 	int need_flush = 0;
-	u64 *spte, new_spte;
+	u64 new_spte;
 	pte_t *ptep = (pte_t *)data;
 	pfn_t new_pfn;
 
 	WARN_ON(pte_huge(*ptep));
 	new_pfn = pte_pfn(*ptep);
-	spte = rmap_next(rmapp, NULL);
-	while (spte) {
-		BUG_ON(!is_shadow_present_pte(*spte));
-		rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
+
+	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
+		BUG_ON(!is_shadow_present_pte(*sptep));
+		rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", sptep, *sptep);
+
 		need_flush = 1;
+
 		if (pte_write(*ptep)) {
-			drop_spte(kvm, spte);
-			spte = rmap_next(rmapp, NULL);
+			drop_spte(kvm, sptep);
+			sptep = rmap_get_first(*rmapp, &iter);
 		} else {
-			new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
+			new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
 			new_spte |= (u64)new_pfn << PAGE_SHIFT;
 
 			new_spte &= ~PT_WRITABLE_MASK;
 			new_spte &= ~SPTE_HOST_WRITEABLE;
 			new_spte &= ~shadow_accessed_mask;
-			mmu_spte_clear_track_bits(spte);
-			mmu_spte_set(spte, new_spte);
-			spte = rmap_next(rmapp, spte);
+
+			mmu_spte_clear_track_bits(sptep);
+			mmu_spte_set(sptep, new_spte);
+			sptep = rmap_get_next(&iter);
 		}
 	}
+
 	if (need_flush)
 		kvm_flush_remote_tlbs(kvm);
 
@@ -1162,7 +1237,8 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			 unsigned long data)
 {
-	u64 *spte;
+	u64 *sptep;
+	struct rmap_iterator iter;
 	int young = 0;
 
 	/*
@@ -1175,25 +1251,24 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	if (!shadow_accessed_mask)
 		return kvm_unmap_rmapp(kvm, rmapp, data);
 
-	spte = rmap_next(rmapp, NULL);
-	while (spte) {
-		int _young;
-		u64 _spte = *spte;
-		BUG_ON(!(_spte & PT_PRESENT_MASK));
-		_young = _spte & PT_ACCESSED_MASK;
-		if (_young) {
+	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
+	     sptep = rmap_get_next(&iter)) {
+		BUG_ON(!(*sptep & PT_PRESENT_MASK));
+
+		if (*sptep & PT_ACCESSED_MASK) {
 			young = 1;
-			clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
+			clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)sptep);
 		}
-		spte = rmap_next(rmapp, spte);
 	}
+
 	return young;
 }
 
 static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			      unsigned long data)
 {
-	u64 *spte;
+	u64 *sptep;
+	struct rmap_iterator iter;
 	int young = 0;
 
 	/*
@@ -1204,16 +1279,14 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	if (!shadow_accessed_mask)
 		goto out;
 
-	spte = rmap_next(rmapp, NULL);
-	while (spte) {
-		u64 _spte = *spte;
-		BUG_ON(!(_spte & PT_PRESENT_MASK));
-		young = _spte & PT_ACCESSED_MASK;
-		if (young) {
+	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
+	     sptep = rmap_get_next(&iter)) {
+		BUG_ON(!(*sptep & PT_PRESENT_MASK));
+
+		if (*sptep & PT_ACCESSED_MASK) {
 			young = 1;
 			break;
 		}
-		spte = rmap_next(rmapp, spte);
 	}
 out:
 	return young;
@@ -1865,10 +1938,11 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
 
 static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	u64 *parent_pte;
+	u64 *sptep;
+	struct rmap_iterator iter;
 
-	while ((parent_pte = pte_list_next(&sp->parent_ptes, NULL)))
-		drop_parent_pte(sp, parent_pte);
+	while ((sptep = rmap_get_first(sp->parent_ptes, &iter)))
+		drop_parent_pte(sp, sptep);
 }
 
 static int mmu_zap_unsync_children(struct kvm *kvm,
@@ -1925,30 +1999,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 	return ret;
 }
 
-static void kvm_mmu_isolate_pages(struct list_head *invalid_list)
-{
-	struct kvm_mmu_page *sp;
-
-	list_for_each_entry(sp, invalid_list, link)
-		kvm_mmu_isolate_page(sp);
-}
-
-static void free_pages_rcu(struct rcu_head *head)
-{
-	struct kvm_mmu_page *next, *sp;
-
-	sp = container_of(head, struct kvm_mmu_page, rcu);
-	while (sp) {
-		if (!list_empty(&sp->link))
-			next = list_first_entry(&sp->link,
-				      struct kvm_mmu_page, link);
-		else
-			next = NULL;
-		kvm_mmu_free_page(sp);
-		sp = next;
-	}
-}
-
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list)
 {
@@ -1957,17 +2007,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	if (list_empty(invalid_list))
 		return;
 
-	kvm_flush_remote_tlbs(kvm);
-
-	if (atomic_read(&kvm->arch.reader_counter)) {
-		kvm_mmu_isolate_pages(invalid_list);
-		sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
-		list_del_init(invalid_list);
+	/*
+	 * wmb: make sure everyone sees our modifications to the page tables
+	 * rmb: make sure we see changes to vcpu->mode
+	 */
+	smp_mb();
 
-		trace_kvm_mmu_delay_free_pages(sp);
-		call_rcu(&sp->rcu, free_pages_rcu);
-		return;
-	}
+	/*
+	 * Wait for all vcpus to exit guest mode and/or lockless shadow
+	 * page table walks.
+	 */
+	kvm_flush_remote_tlbs(kvm);
 
 	do {
 		sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
@@ -1975,7 +2025,6 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 		kvm_mmu_isolate_page(sp);
 		kvm_mmu_free_page(sp);
 	} while (!list_empty(invalid_list));
-
 }
 
 /*
@@ -3554,7 +3603,7 @@ static bool detect_write_flooding(struct kvm_mmu_page *sp)
 	 * Skip write-flooding detected for the sp whose level is 1, because
 	 * it can become unsync, then the guest page is not write-protected.
 	 */
-	if (sp->role.level == 1)
+	if (sp->role.level == PT_PAGE_TABLE_LEVEL)
 		return false;
 
 	return ++sp->write_flooding_count >= 3;
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 715da5a19a5b..7d7d0b9e23eb 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -192,7 +192,8 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	struct kvm_memory_slot *slot;
 	unsigned long *rmapp;
-	u64 *spte;
+	u64 *sptep;
+	struct rmap_iterator iter;
 
 	if (sp->role.direct || sp->unsync || sp->role.invalid)
 		return;
@@ -200,13 +201,12 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slot = gfn_to_memslot(kvm, sp->gfn);
 	rmapp = &slot->rmap[sp->gfn - slot->base_gfn];
 
-	spte = rmap_next(rmapp, NULL);
-	while (spte) {
-		if (is_writable_pte(*spte))
+	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
+	     sptep = rmap_get_next(&iter)) {
+		if (is_writable_pte(*sptep))
 			audit_printk(kvm, "shadow page has writable "
 				     "mappings: gfn %llx role %x\n",
 				     sp->gfn, sp->role.word);
-		spte = rmap_next(rmapp, spte);
 	}
 }
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index df5a70311be8..34f970937ef1 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -658,7 +658,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
 {
 	int offset = 0;
 
-	WARN_ON(sp->role.level != 1);
+	WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
 
 	if (PTTYPE == 32)
 		offset = sp->role.quadrant << PT64_LEVEL_BITS;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e334389e1c75..f75af406b268 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -22,6 +22,7 @@
 #include "x86.h"
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/kernel.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
@@ -42,6 +43,12 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+static const struct x86_cpu_id svm_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_SVM),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
+
 #define IOPM_ALLOC_ORDER 2
 #define MSRPM_ALLOC_ORDER 1
 
@@ -3240,6 +3247,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
 	svm_clear_vintr(svm);
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	mark_dirty(svm->vmcb, VMCB_INTR);
+	++svm->vcpu.stat.irq_window_exits;
 	/*
 	 * If the user space waits to inject interrupts, exit as soon as
 	 * possible
@@ -3247,7 +3255,6 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
 	if (!irqchip_in_kernel(svm->vcpu.kvm) &&
 	    kvm_run->request_interrupt_window &&
 	    !kvm_cpu_has_interrupt(&svm->vcpu)) {
-		++svm->vcpu.stat.irq_window_exits;
 		kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
 		return 0;
 	}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4ff0ab9bc3c8..32eb58866292 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -27,6 +27,7 @@
 #include <linux/highmem.h>
 #include <linux/sched.h>
 #include <linux/moduleparam.h>
+#include <linux/mod_devicetable.h>
 #include <linux/ftrace_event.h>
 #include <linux/slab.h>
 #include <linux/tboot.h>
@@ -51,6 +52,12 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+static const struct x86_cpu_id vmx_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_VMX),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+
 static bool __read_mostly enable_vpid = 1;
 module_param_named(vpid, enable_vpid, bool, 0444);
 
@@ -386,6 +393,9 @@ struct vcpu_vmx {
 	struct {
 		int           loaded;
 		u16           fs_sel, gs_sel, ldt_sel;
+#ifdef CONFIG_X86_64
+		u16           ds_sel, es_sel;
+#endif
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 	} host_state;
@@ -1411,6 +1421,11 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	}
 
 #ifdef CONFIG_X86_64
+	savesegment(ds, vmx->host_state.ds_sel);
+	savesegment(es, vmx->host_state.es_sel);
+#endif
+
+#ifdef CONFIG_X86_64
 	vmcs_writel(HOST_FS_BASE, read_msr(MSR_FS_BASE));
 	vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE));
 #else
@@ -1450,6 +1465,19 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 	}
 	if (vmx->host_state.fs_reload_needed)
 		loadsegment(fs, vmx->host_state.fs_sel);
+#ifdef CONFIG_X86_64
+	if (unlikely(vmx->host_state.ds_sel | vmx->host_state.es_sel)) {
+		loadsegment(ds, vmx->host_state.ds_sel);
+		loadsegment(es, vmx->host_state.es_sel);
+	}
+#else
+	/*
+	 * The sysexit path does not restore ds/es, so we must set them to
+	 * a reasonable value ourselves.
+	 */
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
+#endif
 	reload_tss();
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
@@ -3633,8 +3661,18 @@ static void vmx_set_constant_host_state(void)
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
+#ifdef CONFIG_X86_64
+	/*
+	 * Load null selectors, so we can avoid reloading them in
+	 * __vmx_load_host_state(), in case userspace uses the null selectors
+	 * too (the expected case).
+	 */
+	vmcs_write16(HOST_DS_SELECTOR, 0);
+	vmcs_write16(HOST_ES_SELECTOR, 0);
+#else
 	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
 	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
+#endif
 	vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
 	vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8);  /* 22.2.4 */
 
@@ -6256,7 +6294,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
 	vmx->loaded_vmcs->launched = 1;
 
 	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
@@ -6343,7 +6380,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	return &vmx->vcpu;
 
 free_vmcs:
-	free_vmcs(vmx->loaded_vmcs->vmcs);
+	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
 uninit_vcpu:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 185a2b823a2d..be6d54929fa7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2147,6 +2147,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_PCI_2_3:
+	case KVM_CAP_KVMCLOCK_CTRL:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2597,6 +2598,23 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 	return r;
 }
 
+/*
+ * kvm_set_guest_paused() indicates to the guest kernel that it has been
+ * stopped by the hypervisor.  This function will be called from the host only.
+ * EINVAL is returned when the host attempts to set the flag for a guest that
+ * does not support pv clocks.
+ */
+static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
+{
+	struct pvclock_vcpu_time_info *src = &vcpu->arch.hv_clock;
+	if (!vcpu->arch.time_page)
+		return -EINVAL;
+	src->flags |= PVCLOCK_GUEST_STOPPED;
+	mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT);
+	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+	return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -2873,6 +2891,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = vcpu->arch.virtual_tsc_khz;
 		goto out;
 	}
+	case KVM_KVMCLOCK_CTRL: {
+		r = kvm_set_guest_paused(vcpu);
+		goto out;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -3045,57 +3067,32 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 }
 
 /**
- * write_protect_slot - write protect a slot for dirty logging
- * @kvm: the kvm instance
- * @memslot: the slot we protect
- * @dirty_bitmap: the bitmap indicating which pages are dirty
- * @nr_dirty_pages: the number of dirty pages
+ * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
+ * @kvm: kvm instance
+ * @log: slot id and address to which we copy the log
  *
- * We have two ways to find all sptes to protect:
- * 1. Use kvm_mmu_slot_remove_write_access() which walks all shadow pages and
- *    checks ones that have a spte mapping a page in the slot.
- * 2. Use kvm_mmu_rmap_write_protect() for each gfn found in the bitmap.
+ * We need to keep it in mind that VCPU threads can write to the bitmap
+ * concurrently.  So, to avoid losing data, we keep the following order for
+ * each bit:
  *
- * Generally speaking, if there are not so many dirty pages compared to the
- * number of shadow pages, we should use the latter.
+ *   1. Take a snapshot of the bit and clear it if needed.
+ *   2. Write protect the corresponding page.
+ *   3. Flush TLB's if needed.
+ *   4. Copy the snapshot to the userspace.
  *
- * Note that letting others write into a page marked dirty in the old bitmap
- * by using the remaining tlb entry is not a problem.  That page will become
- * write protected again when we flush the tlb and then be reported dirty to
- * the user space by copying the old bitmap.
- */
-static void write_protect_slot(struct kvm *kvm,
-			       struct kvm_memory_slot *memslot,
-			       unsigned long *dirty_bitmap,
-			       unsigned long nr_dirty_pages)
-{
-	spin_lock(&kvm->mmu_lock);
-
-	/* Not many dirty pages compared to # of shadow pages. */
-	if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) {
-		unsigned long gfn_offset;
-
-		for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) {
-			unsigned long gfn = memslot->base_gfn + gfn_offset;
-
-			kvm_mmu_rmap_write_protect(kvm, gfn, memslot);
-		}
-		kvm_flush_remote_tlbs(kvm);
-	} else
-		kvm_mmu_slot_remove_write_access(kvm, memslot->id);
-
-	spin_unlock(&kvm->mmu_lock);
-}
-
-/*
- * Get (and clear) the dirty memory log for a memory slot.
+ * Between 2 and 3, the guest may write to the page using the remaining TLB
+ * entry.  This is not a problem because the page will be reported dirty at
+ * step 4 using the snapshot taken before and step 3 ensures that successive
+ * writes will be logged for the next call.
  */
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
-				      struct kvm_dirty_log *log)
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
 	int r;
 	struct kvm_memory_slot *memslot;
-	unsigned long n, nr_dirty_pages;
+	unsigned long n, i;
+	unsigned long *dirty_bitmap;
+	unsigned long *dirty_bitmap_buffer;
+	bool is_dirty = false;
 
 	mutex_lock(&kvm->slots_lock);
 
@@ -3104,49 +3101,42 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);
+
+	dirty_bitmap = memslot->dirty_bitmap;
 	r = -ENOENT;
-	if (!memslot->dirty_bitmap)
+	if (!dirty_bitmap)
 		goto out;
 
 	n = kvm_dirty_bitmap_bytes(memslot);
-	nr_dirty_pages = memslot->nr_dirty_pages;
 
-	/* If nothing is dirty, don't bother messing with page tables. */
-	if (nr_dirty_pages) {
-		struct kvm_memslots *slots, *old_slots;
-		unsigned long *dirty_bitmap, *dirty_bitmap_head;
+	dirty_bitmap_buffer = dirty_bitmap + n / sizeof(long);
+	memset(dirty_bitmap_buffer, 0, n);
 
-		dirty_bitmap = memslot->dirty_bitmap;
-		dirty_bitmap_head = memslot->dirty_bitmap_head;
-		if (dirty_bitmap == dirty_bitmap_head)
-			dirty_bitmap_head += n / sizeof(long);
-		memset(dirty_bitmap_head, 0, n);
+	spin_lock(&kvm->mmu_lock);
 
-		r = -ENOMEM;
-		slots = kmemdup(kvm->memslots, sizeof(*kvm->memslots), GFP_KERNEL);
-		if (!slots)
-			goto out;
+	for (i = 0; i < n / sizeof(long); i++) {
+		unsigned long mask;
+		gfn_t offset;
 
-		memslot = id_to_memslot(slots, log->slot);
-		memslot->nr_dirty_pages = 0;
-		memslot->dirty_bitmap = dirty_bitmap_head;
-		update_memslots(slots, NULL);
+		if (!dirty_bitmap[i])
+			continue;
 
-		old_slots = kvm->memslots;
-		rcu_assign_pointer(kvm->memslots, slots);
-		synchronize_srcu_expedited(&kvm->srcu);
-		kfree(old_slots);
+		is_dirty = true;
 
-		write_protect_slot(kvm, memslot, dirty_bitmap, nr_dirty_pages);
+		mask = xchg(&dirty_bitmap[i], 0);
+		dirty_bitmap_buffer[i] = mask;
 
-		r = -EFAULT;
-		if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n))
-			goto out;
-	} else {
-		r = -EFAULT;
-		if (clear_user(log->dirty_bitmap, n))
-			goto out;
+		offset = i * BITS_PER_LONG;
+		kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask);
 	}
+	if (is_dirty)
+		kvm_flush_remote_tlbs(kvm);
+
+	spin_unlock(&kvm->mmu_lock);
+
+	r = -EFAULT;
+	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
+		goto out;
 
 	r = 0;
 out:
@@ -3728,9 +3718,8 @@ struct read_write_emulator_ops {
 static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
 {
 	if (vcpu->mmio_read_completed) {
-		memcpy(val, vcpu->mmio_data, bytes);
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
-			       vcpu->mmio_phys_addr, *(u64 *)val);
+			       vcpu->mmio_fragments[0].gpa, *(u64 *)val);
 		vcpu->mmio_read_completed = 0;
 		return 1;
 	}
@@ -3766,8 +3755,9 @@ static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 			   void *val, int bytes)
 {
-	memcpy(vcpu->mmio_data, val, bytes);
-	memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8);
+	struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
+
+	memcpy(vcpu->run->mmio.data, frag->data, frag->len);
 	return X86EMUL_CONTINUE;
 }
 
@@ -3794,10 +3784,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
 	gpa_t gpa;
 	int handled, ret;
 	bool write = ops->write;
-
-	if (ops->read_write_prepare &&
-		  ops->read_write_prepare(vcpu, val, bytes))
-		return X86EMUL_CONTINUE;
+	struct kvm_mmio_fragment *frag;
 
 	ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
 
@@ -3823,15 +3810,19 @@ mmio:
 	bytes -= handled;
 	val += handled;
 
-	vcpu->mmio_needed = 1;
-	vcpu->run->exit_reason = KVM_EXIT_MMIO;
-	vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
-	vcpu->mmio_size = bytes;
-	vcpu->run->mmio.len = min(vcpu->mmio_size, 8);
-	vcpu->run->mmio.is_write = vcpu->mmio_is_write = write;
-	vcpu->mmio_index = 0;
+	while (bytes) {
+		unsigned now = min(bytes, 8U);
 
-	return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
+		frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
+		frag->gpa = gpa;
+		frag->data = val;
+		frag->len = now;
+
+		gpa += now;
+		val += now;
+		bytes -= now;
+	}
+	return X86EMUL_CONTINUE;
 }
 
 int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
@@ -3840,10 +3831,18 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 			struct read_write_emulator_ops *ops)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	gpa_t gpa;
+	int rc;
+
+	if (ops->read_write_prepare &&
+		  ops->read_write_prepare(vcpu, val, bytes))
+		return X86EMUL_CONTINUE;
+
+	vcpu->mmio_nr_fragments = 0;
 
 	/* Crossing a page boundary? */
 	if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
-		int rc, now;
+		int now;
 
 		now = -addr & ~PAGE_MASK;
 		rc = emulator_read_write_onepage(addr, val, now, exception,
@@ -3856,8 +3855,25 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 		bytes -= now;
 	}
 
-	return emulator_read_write_onepage(addr, val, bytes, exception,
-					   vcpu, ops);
+	rc = emulator_read_write_onepage(addr, val, bytes, exception,
+					 vcpu, ops);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (!vcpu->mmio_nr_fragments)
+		return rc;
+
+	gpa = vcpu->mmio_fragments[0].gpa;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+	vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+	vcpu->run->mmio.phys_addr = gpa;
+
+	return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
 }
 
 static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt,
@@ -5263,10 +5279,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_deliver_pmi(vcpu);
 	}
 
-	r = kvm_mmu_reload(vcpu);
-	if (unlikely(r))
-		goto out;
-
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
 		inject_pending_event(vcpu);
 
@@ -5282,6 +5294,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	r = kvm_mmu_reload(vcpu);
+	if (unlikely(r)) {
+		kvm_x86_ops->cancel_injection(vcpu);
+		goto out;
+	}
+
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
@@ -5456,33 +5474,55 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+/*
+ * Implements the following, as a state machine:
+ *
+ * read:
+ *   for each fragment
+ *     write gpa, len
+ *     exit
+ *     copy data
+ *   execute insn
+ *
+ * write:
+ *   for each fragment
+ *      write gpa, len
+ *      copy data
+ *      exit
+ */
 static int complete_mmio(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
+	struct kvm_mmio_fragment *frag;
 	int r;
 
 	if (!(vcpu->arch.pio.count || vcpu->mmio_needed))
 		return 1;
 
 	if (vcpu->mmio_needed) {
-		vcpu->mmio_needed = 0;
+		/* Complete previous fragment */
+		frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
 		if (!vcpu->mmio_is_write)
-			memcpy(vcpu->mmio_data + vcpu->mmio_index,
-			       run->mmio.data, 8);
-		vcpu->mmio_index += 8;
-		if (vcpu->mmio_index < vcpu->mmio_size) {
-			run->exit_reason = KVM_EXIT_MMIO;
-			run->mmio.phys_addr = vcpu->mmio_phys_addr + vcpu->mmio_index;
-			memcpy(run->mmio.data, vcpu->mmio_data + vcpu->mmio_index, 8);
-			run->mmio.len = min(vcpu->mmio_size - vcpu->mmio_index, 8);
-			run->mmio.is_write = vcpu->mmio_is_write;
-			vcpu->mmio_needed = 1;
-			return 0;
+			memcpy(frag->data, run->mmio.data, frag->len);
+		if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+			vcpu->mmio_needed = 0;
+			if (vcpu->mmio_is_write)
+				return 1;
+			vcpu->mmio_read_completed = 1;
+			goto done;
 		}
+		/* Initiate next fragment */
+		++frag;
+		run->exit_reason = KVM_EXIT_MMIO;
+		run->mmio.phys_addr = frag->gpa;
 		if (vcpu->mmio_is_write)
-			return 1;
-		vcpu->mmio_read_completed = 1;
+			memcpy(run->mmio.data, frag->data, frag->len);
+		run->mmio.len = frag->len;
+		run->mmio.is_write = vcpu->mmio_is_write;
+		return 0;
+
 	}
+done:
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6399,21 +6439,9 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		 kvm_cpu_has_interrupt(vcpu));
 }
 
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
-	int me;
-	int cpu = vcpu->cpu;
-
-	if (waitqueue_active(&vcpu->wq)) {
-		wake_up_interruptible(&vcpu->wq);
-		++vcpu->stat.halt_wakeup;
-	}
-
-	me = get_cpu();
-	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
-		if (kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE)
-			smp_send_reschedule(cpu);
-	put_cpu();
+	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
 }
 
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index cb80c293cdd8..3d1134ddb885 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -64,7 +64,7 @@ static inline int is_pse(struct kvm_vcpu *vcpu)
 
 static inline int is_paging(struct kvm_vcpu *vcpu)
 {
-	return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
+	return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG));
 }
 
 static inline u32 bit(int bitno)
diff --git a/arch/xtensa/include/asm/kvm_para.h b/arch/xtensa/include/asm/kvm_para.h
new file mode 100644
index 000000000000..14fab8f0b957
--- /dev/null
+++ b/arch/xtensa/include/asm/kvm_para.h
@@ -0,0 +1 @@
+#include <asm-generic/kvm_para.h>
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index 36506366158d..766cb7b19b40 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -17,6 +17,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/memory.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <asm/chpid.h>
 #include <asm/sclp.h>
@@ -38,7 +39,8 @@ struct read_info_sccb {
 	u64	facilities;		/* 48-55 */
 	u8	_reserved2[84 - 56];	/* 56-83 */
 	u8	fac84;			/* 84 */
-	u8	_reserved3[91 - 85];	/* 85-90 */
+	u8	fac85;			/* 85 */
+	u8	_reserved3[91 - 86];	/* 86-90 */
 	u8	flags;			/* 91 */
 	u8	_reserved4[100 - 92];	/* 92-99 */
 	u32	rnsize2;		/* 100-103 */
@@ -51,6 +53,7 @@ static int __initdata early_read_info_sccb_valid;
 
 u64 sclp_facilities;
 static u8 sclp_fac84;
+static u8 sclp_fac85;
 static unsigned long long rzm;
 static unsigned long long rnmax;
 
@@ -112,6 +115,7 @@ void __init sclp_facilities_detect(void)
 	sccb = &early_read_info_sccb;
 	sclp_facilities = sccb->facilities;
 	sclp_fac84 = sccb->fac84;
+	sclp_fac85 = sccb->fac85;
 	rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2;
 	rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2;
 	rzm <<= 20;
@@ -127,6 +131,12 @@ unsigned long long sclp_get_rzm(void)
 	return rzm;
 }
 
+u8 sclp_get_fac85(void)
+{
+	return sclp_fac85;
+}
+EXPORT_SYMBOL_GPL(sclp_get_fac85);
+
 /*
  * This function will be called after sclp_facilities_detect(), which gets
  * called from early.c code. Therefore the sccb should have valid contents.
diff --git a/include/asm-generic/kvm_para.h b/include/asm-generic/kvm_para.h
new file mode 100644
index 000000000000..5cba37f9eae1
--- /dev/null
+++ b/include/asm-generic/kvm_para.h
@@ -0,0 +1,22 @@
+#ifndef _ASM_GENERIC_KVM_PARA_H
+#define _ASM_GENERIC_KVM_PARA_H
+
+#ifdef __KERNEL__
+
+/*
+ * This function is used by architectures that support kvm to avoid issuing
+ * false soft lockup messages.
+ */
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+#endif	/* _KERNEL__ */
+
+#endif
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 6c322a90b92f..09f2b3aa2da7 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -449,6 +449,30 @@ struct kvm_ppc_pvinfo {
 	__u8  pad[108];
 };
 
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ	8
+
+struct kvm_ppc_one_page_size {
+	__u32 page_shift;	/* Page shift (or 0) */
+	__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+	__u32 page_shift;	/* Base page shift of segment (or 0) */
+	__u32 slb_enc;		/* SLB encoding for BookS */
+	struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL		0x00000001
+#define KVM_PPC_1T_SEGMENTS		0x00000002
+
+struct kvm_ppc_smmu_info {
+	__u64 flags;
+	__u32 slb_size;
+	__u32 pad;
+	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -589,6 +613,10 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_S390_UCONTROL 73
 #define KVM_CAP_SYNC_REGS 74
 #define KVM_CAP_PCI_2_3 75
+#define KVM_CAP_KVMCLOCK_CTRL 76
+#define KVM_CAP_SIGNAL_MSI 77
+#define KVM_CAP_PPC_GET_SMMU_INFO 78
+#define KVM_CAP_S390_COW 79
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -714,6 +742,14 @@ struct kvm_one_reg {
 	__u64 addr;
 };
 
+struct kvm_msi {
+	__u32 address_lo;
+	__u32 address_hi;
+	__u32 data;
+	__u32 flags;
+	__u8  pad[16];
+};
+
 /*
  * ioctls for VM fds
  */
@@ -788,6 +824,10 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_PCI_2_3 */
 #define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
 				       struct kvm_assigned_pci_dev)
+/* Available with KVM_CAP_SIGNAL_MSI */
+#define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
+/* Available with KVM_CAP_PPC_GET_SMMU_INFO */
+#define KVM_PPC_GET_SMMU_INFO	  _IOR(KVMIO,  0xa6, struct kvm_ppc_smmu_info)
 
 /*
  * ioctls for vcpu fds
@@ -859,6 +899,8 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_ONE_REG */
 #define KVM_GET_ONE_REG		  _IOW(KVMIO,  0xab, struct kvm_one_reg)
 #define KVM_SET_ONE_REG		  _IOW(KVMIO,  0xac, struct kvm_one_reg)
+/* VM is being stopped by host */
+#define KVM_KVMCLOCK_CTRL	  _IO(KVMIO,   0xad)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 72cbf08d45fb..c4464356b35b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -35,6 +35,20 @@
 #endif
 
 /*
+ * If we support unaligned MMIO, at most one fragment will be split into two:
+ */
+#ifdef KVM_UNALIGNED_MMIO
+#  define KVM_EXTRA_MMIO_FRAGMENTS 1
+#else
+#  define KVM_EXTRA_MMIO_FRAGMENTS 0
+#endif
+
+#define KVM_USER_MMIO_SIZE 8
+
+#define KVM_MAX_MMIO_FRAGMENTS \
+	(KVM_MMIO_SIZE / KVM_USER_MMIO_SIZE + KVM_EXTRA_MMIO_FRAGMENTS)
+
+/*
  * vcpu->requests bit members
  */
 #define KVM_REQ_TLB_FLUSH          0
@@ -68,10 +82,11 @@ struct kvm_io_range {
 	struct kvm_io_device *dev;
 };
 
+#define NR_IOBUS_DEVS 1000
+
 struct kvm_io_bus {
 	int                   dev_count;
-#define NR_IOBUS_DEVS 300
-	struct kvm_io_range range[NR_IOBUS_DEVS];
+	struct kvm_io_range range[];
 };
 
 enum kvm_bus {
@@ -113,7 +128,18 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 enum {
 	OUTSIDE_GUEST_MODE,
 	IN_GUEST_MODE,
-	EXITING_GUEST_MODE
+	EXITING_GUEST_MODE,
+	READING_SHADOW_PAGE_TABLES,
+};
+
+/*
+ * Sometimes a large or cross-page mmio needs to be broken up into separate
+ * exits for userspace servicing.
+ */
+struct kvm_mmio_fragment {
+	gpa_t gpa;
+	void *data;
+	unsigned len;
 };
 
 struct kvm_vcpu {
@@ -143,10 +169,9 @@ struct kvm_vcpu {
 	int mmio_needed;
 	int mmio_read_completed;
 	int mmio_is_write;
-	int mmio_size;
-	int mmio_index;
-	unsigned char mmio_data[KVM_MMIO_SIZE];
-	gpa_t mmio_phys_addr;
+	int mmio_cur_fragment;
+	int mmio_nr_fragments;
+	struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS];
 #endif
 
 #ifdef CONFIG_KVM_ASYNC_PF
@@ -178,8 +203,6 @@ struct kvm_memory_slot {
 	unsigned long flags;
 	unsigned long *rmap;
 	unsigned long *dirty_bitmap;
-	unsigned long *dirty_bitmap_head;
-	unsigned long nr_dirty_pages;
 	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
 	int user_alloc;
@@ -438,6 +461,8 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			     gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
+bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
@@ -506,6 +531,7 @@ int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
@@ -521,6 +547,15 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
+static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+{
+#ifdef __KVM_HAVE_ARCH_WQP
+	return vcpu->arch.wqp;
+#else
+	return &vcpu->wq;
+#endif
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
 void kvm_arch_destroy_vm(struct kvm *kvm);
 void kvm_free_all_assigned_devices(struct kvm *kvm);
@@ -769,6 +804,8 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			unsigned flags);
 void kvm_free_irq_routing(struct kvm *kvm);
 
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
 #else
 
 static inline void kvm_free_irq_routing(struct kvm *kvm) {}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index df30ee08bdd4..e5e1d85b8c7c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -24,6 +24,7 @@
 #include <linux/sysctl.h>
 
 #include <asm/irq_regs.h>
+#include <linux/kvm_para.h>
 #include <linux/perf_event.h>
 
 int watchdog_enabled = 1;
@@ -280,6 +281,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			__this_cpu_write(softlockup_touch_sync, false);
 			sched_clock_tick();
 		}
+
+		/* Clear the guest paused flag on watchdog reset */
+		kvm_check_and_clear_guest_paused();
 		__touch_watchdog();
 		return HRTIMER_RESTART;
 	}
@@ -292,6 +296,14 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	 */
 	duration = is_softlockup(touch_ts);
 	if (unlikely(duration)) {
+		/*
+		 * If a virtual machine is stopped by the host it can look to
+		 * the watchdog like a soft lockup, check to see if the host
+		 * stopped the vm before we issue the warning
+		 */
+		if (kvm_check_and_clear_guest_paused())
+			return HRTIMER_RESTART;
+
 		/* only warn once */
 		if (__this_cpu_read(soft_watchdog_warn) == true)
 			return HRTIMER_RESTART;
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index f63ccb0a5982..28694f4a9139 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -18,3 +18,6 @@ config KVM_MMIO
 
 config KVM_ASYNC_PF
        bool
+
+config HAVE_KVM_MSI
+       bool
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index dcaf272c26c0..26fd54dc459e 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -254,13 +254,17 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
 	}
 }
 
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+	smp_rmb();
+	return test_bit(vector, ioapic->handled_vectors);
+}
+
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
-	smp_rmb();
-	if (!test_bit(vector, ioapic->handled_vectors))
-		return;
 	spin_lock(&ioapic->lock);
 	__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
 	spin_unlock(&ioapic->lock);
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 0b190c34ccc3..32872a09b63f 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -71,6 +71,7 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 		int short_hand, int dest, int dest_mode);
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
 int kvm_ioapic_init(struct kvm *kvm);
 void kvm_ioapic_destroy(struct kvm *kvm);
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 9f614b4e365f..a6a0365475ed 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -138,6 +138,20 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+	struct kvm_kernel_irq_routing_entry route;
+
+	if (!irqchip_in_kernel(kvm) || msi->flags != 0)
+		return -EINVAL;
+
+	route.msi.address_lo = msi->address_lo;
+	route.msi.address_hi = msi->address_hi;
+	route.msi.data = msi->data;
+
+	return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1);
+}
+
 /*
  * Return value:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9739b533ca2e..7e140683ff14 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -522,12 +522,11 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 		return;
 
 	if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE)
-		vfree(memslot->dirty_bitmap_head);
+		vfree(memslot->dirty_bitmap);
 	else
-		kfree(memslot->dirty_bitmap_head);
+		kfree(memslot->dirty_bitmap);
 
 	memslot->dirty_bitmap = NULL;
-	memslot->dirty_bitmap_head = NULL;
 }
 
 /*
@@ -611,8 +610,7 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 
 /*
  * Allocation size is twice as large as the actual dirty bitmap size.
- * This makes it possible to do double buffering: see x86's
- * kvm_vm_ioctl_get_dirty_log().
+ * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed.
  */
 static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
@@ -627,8 +625,6 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
-	memslot->dirty_bitmap_head = memslot->dirty_bitmap;
-	memslot->nr_dirty_pages = 0;
 #endif /* !CONFIG_S390 */
 	return 0;
 }
@@ -1477,8 +1473,8 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 
-		if (!test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap))
-			memslot->nr_dirty_pages++;
+		/* TODO: introduce set_bit_le() and use it */
+		test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 
@@ -1515,6 +1511,30 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	finish_wait(&vcpu->wq, &wait);
 }
 
+#ifndef CONFIG_S390
+/*
+ * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode.
+ */
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+	int me;
+	int cpu = vcpu->cpu;
+	wait_queue_head_t *wqp;
+
+	wqp = kvm_arch_vcpu_wq(vcpu);
+	if (waitqueue_active(wqp)) {
+		wake_up_interruptible(wqp);
+		++vcpu->stat.halt_wakeup;
+	}
+
+	me = get_cpu();
+	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
+		if (kvm_arch_vcpu_should_kick(vcpu))
+			smp_send_reschedule(cpu);
+	put_cpu();
+}
+#endif /* !CONFIG_S390 */
+
 void kvm_resched(struct kvm_vcpu *vcpu)
 {
 	if (!need_resched())
@@ -1523,6 +1543,31 @@ void kvm_resched(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_resched);
 
+bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
+{
+	struct pid *pid;
+	struct task_struct *task = NULL;
+
+	rcu_read_lock();
+	pid = rcu_dereference(target->pid);
+	if (pid)
+		task = get_pid_task(target->pid, PIDTYPE_PID);
+	rcu_read_unlock();
+	if (!task)
+		return false;
+	if (task->flags & PF_VCPU) {
+		put_task_struct(task);
+		return false;
+	}
+	if (yield_to(task, 1)) {
+		put_task_struct(task);
+		return true;
+	}
+	put_task_struct(task);
+	return false;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
 	struct kvm *kvm = me->kvm;
@@ -1541,8 +1586,6 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	 */
 	for (pass = 0; pass < 2 && !yielded; pass++) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			struct task_struct *task = NULL;
-			struct pid *pid;
 			if (!pass && i < last_boosted_vcpu) {
 				i = last_boosted_vcpu;
 				continue;
@@ -1552,24 +1595,11 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (waitqueue_active(&vcpu->wq))
 				continue;
-			rcu_read_lock();
-			pid = rcu_dereference(vcpu->pid);
-			if (pid)
-				task = get_pid_task(vcpu->pid, PIDTYPE_PID);
-			rcu_read_unlock();
-			if (!task)
-				continue;
-			if (task->flags & PF_VCPU) {
-				put_task_struct(task);
-				continue;
-			}
-			if (yield_to(task, 1)) {
-				put_task_struct(task);
+			if (kvm_vcpu_yield_to(vcpu)) {
 				kvm->last_boosted_vcpu = i;
 				yielded = 1;
 				break;
 			}
-			put_task_struct(task);
 		}
 	}
 }
@@ -2040,6 +2070,17 @@ static long kvm_vm_ioctl(struct file *filp,
 		mutex_unlock(&kvm->lock);
 		break;
 #endif
+#ifdef CONFIG_HAVE_KVM_MSI
+	case KVM_SIGNAL_MSI: {
+		struct kvm_msi msi;
+
+		r = -EFAULT;
+		if (copy_from_user(&msi, argp, sizeof msi))
+			goto out;
+		r = kvm_send_userspace_msi(kvm, &msi);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)
@@ -2168,6 +2209,9 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 	case KVM_CAP_SET_BOOT_CPU_ID:
 #endif
 	case KVM_CAP_INTERNAL_ERROR_DATA:
+#ifdef CONFIG_HAVE_KVM_MSI
+	case KVM_CAP_SIGNAL_MSI:
+#endif
 		return 1;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQ_ROUTING:
@@ -2394,9 +2438,6 @@ int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
 int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
 			  gpa_t addr, int len)
 {
-	if (bus->dev_count == NR_IOBUS_DEVS)
-		return -ENOSPC;
-
 	bus->range[bus->dev_count++] = (struct kvm_io_range) {
 		.addr = addr,
 		.len = len,
@@ -2496,12 +2537,15 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-	if (bus->dev_count > NR_IOBUS_DEVS-1)
+	if (bus->dev_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
 
-	new_bus = kmemdup(bus, sizeof(struct kvm_io_bus), GFP_KERNEL);
+	new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count + 1) *
+			  sizeof(struct kvm_io_range)), GFP_KERNEL);
 	if (!new_bus)
 		return -ENOMEM;
+	memcpy(new_bus, bus, sizeof(*bus) + (bus->dev_count *
+	       sizeof(struct kvm_io_range)));
 	kvm_io_bus_insert_dev(new_bus, dev, addr, len);
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
@@ -2518,27 +2562,25 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-
-	new_bus = kmemdup(bus, sizeof(*bus), GFP_KERNEL);
-	if (!new_bus)
-		return -ENOMEM;
-
 	r = -ENOENT;
-	for (i = 0; i < new_bus->dev_count; i++)
-		if (new_bus->range[i].dev == dev) {
+	for (i = 0; i < bus->dev_count; i++)
+		if (bus->range[i].dev == dev) {
 			r = 0;
-			new_bus->dev_count--;
-			new_bus->range[i] = new_bus->range[new_bus->dev_count];
-			sort(new_bus->range, new_bus->dev_count,
-			     sizeof(struct kvm_io_range),
-			     kvm_io_bus_sort_cmp, NULL);
 			break;
 		}
 
-	if (r) {
-		kfree(new_bus);
+	if (r)
 		return r;
-	}
+
+	new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count - 1) *
+			  sizeof(struct kvm_io_range)), GFP_KERNEL);
+	if (!new_bus)
+		return -ENOMEM;
+
+	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
+	new_bus->dev_count--;
+	memcpy(new_bus->range + i, bus->range + i + 1,
+	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
 
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);