Merge branch 'kvm-updates/2.6.35' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.35' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (269 commits)
  KVM: x86: Add missing locking to arch specific vcpu ioctls
  KVM: PPC: Add missing vcpu_load()/vcpu_put() in vcpu ioctls
  KVM: MMU: Segregate shadow pages with different cr0.wp
  KVM: x86: Check LMA bit before set_efer
  KVM: Don't allow lmsw to clear cr0.pe
  KVM: Add cpuid.txt file
  KVM: x86: Tell the guest we'll warn it about tsc stability
  x86, paravirt: don't compute pvclock adjustments if we trust the tsc
  x86: KVM guest: Try using new kvm clock msrs
  KVM: x86: export paravirtual cpuid flags in KVM_GET_SUPPORTED_CPUID
  KVM: x86: add new KVMCLOCK cpuid feature
  KVM: x86: change msr numbers for kvmclock
  x86, paravirt: Add a global synchronization point for pvclock
  x86, paravirt: Enable pvclock flags in vcpu_time_info structure
  KVM: x86: Inject #GP with the right rip on efer writes
  KVM: SVM: Don't allow nested guest to VMMCALL into host
  KVM: x86: Fix exception reinjection forced to true
  KVM: Fix wallclock version writing race
  KVM: MMU: Don't read pdptrs with mmu spinlock held in mmu_alloc_roots
  KVM: VMX: enable VMXON check with SMX enabled (Intel TXT)
  ...

Documentation/kvm/api.txt

@@ -656,6 +656,7 @@ struct kvm_clock_data {
 4.29 KVM_GET_VCPU_EVENTS
 
 Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
 Architectures: x86
 Type: vm ioctl
 Parameters: struct kvm_vcpu_event (out)
@@ -676,7 +677,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 soft;
-		__u8 pad;
+		__u8 shadow;
 	} interrupt;
 	struct {
 		__u8 injected;
@@ -688,9 +689,13 @@ struct kvm_vcpu_events {
 	__u32 flags;
 };
 
+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.
+
 4.30 KVM_SET_VCPU_EVENTS
 
 Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
 Architectures: x86
 Type: vm ioctl
 Parameters: struct kvm_vcpu_event (in)
@@ -709,6 +714,183 @@ current in-kernel state. The bits are:
 KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
 KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
 
+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.
+
+4.32 KVM_GET_DEBUGREGS
+
+Capability: KVM_CAP_DEBUGREGS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_debugregs (out)
+Returns: 0 on success, -1 on error
+
+Reads debug registers from the vcpu.
+
+struct kvm_debugregs {
+	__u64 db[4];
+	__u64 dr6;
+	__u64 dr7;
+	__u64 flags;
+	__u64 reserved[9];
+};
+
+4.33 KVM_SET_DEBUGREGS
+
+Capability: KVM_CAP_DEBUGREGS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_debugregs (in)
+Returns: 0 on success, -1 on error
+
+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.
+
+4.34 KVM_SET_USER_MEMORY_REGION
+
+Capability: KVM_CAP_USER_MEM
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_userspace_memory_region (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_userspace_memory_region {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr; /* start of the userspace allocated memory */
+};
+
+/* for kvm_memory_region::flags */
+#define KVM_MEM_LOG_DIRTY_PAGES  1UL
+
+This ioctl allows the user to create or modify a guest physical memory
+slot.  When changing an existing slot, it may be moved in the guest
+physical memory space, or its flags may be modified.  It may not be
+resized.  Slots may not overlap in guest physical address space.
+
+Memory for the region is taken starting at the address denoted by the
+field userspace_addr, which must point at user addressable memory for
+the entire memory slot size.  Any object may back this memory, including
+anonymous memory, ordinary files, and hugetlbfs.
+
+It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
+be identical.  This allows large pages in the guest to be backed by large
+pages in the host.
+
+The flags field supports just one flag, KVM_MEM_LOG_DIRTY_PAGES, which
+instructs kvm to keep track of writes to memory within the slot.  See
+the KVM_GET_DIRTY_LOG ioctl.
+
+When the KVM_CAP_SYNC_MMU capability, changes in the backing of the memory
+region are automatically reflected into the guest.  For example, an mmap()
+that affects the region will be made visible immediately.  Another example
+is madvise(MADV_DROP).
+
+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.
+
+4.35 KVM_SET_TSS_ADDR
+
+Capability: KVM_CAP_SET_TSS_ADDR
+Architectures: x86
+Type: vm ioctl
+Parameters: unsigned long tss_address (in)
+Returns: 0 on success, -1 on error
+
+This ioctl defines the physical address of a three-page region in the guest
+physical address space.  The region must be within the first 4GB of the
+guest physical address space and must not conflict with any memory slot
+or any mmio address.  The guest may malfunction if it accesses this memory
+region.
+
+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).
+
+4.36 KVM_ENABLE_CAP
+
+Capability: KVM_CAP_ENABLE_CAP
+Architectures: ppc
+Type: vcpu ioctl
+Parameters: struct kvm_enable_cap (in)
+Returns: 0 on success; -1 on error
+
++Not all extensions are enabled by default. Using this ioctl the application
+can enable an extension, making it available to the guest.
+
+On systems that do not support this ioctl, it always fails. On systems that
+do support it, it only works for extensions that are supported for enablement.
+
+To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
+be used.
+
+struct kvm_enable_cap {
+       /* in */
+       __u32 cap;
+
+The capability that is supposed to get enabled.
+
+       __u32 flags;
+
+A bitfield indicating future enhancements. Has to be 0 for now.
+
+       __u64 args[4];
+
+Arguments for enabling a feature. If a feature needs initial values to
+function properly, this is the place to put them.
+
+       __u8  pad[64];
+};
+
+4.37 KVM_GET_MP_STATE
+
+Capability: KVM_CAP_MP_STATE
+Architectures: x86, ia64
+Type: vcpu ioctl
+Parameters: struct kvm_mp_state (out)
+Returns: 0 on success; -1 on error
+
+struct kvm_mp_state {
+	__u32 mp_state;
+};
+
+Returns the vcpu's current "multiprocessing state" (though also valid on
+uniprocessor guests).
+
+Possible values are:
+
+ - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running
+ - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
+                                 which has not yet received an INIT signal
+ - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
+                                 now ready for a SIPI
+ - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
+                                 is waiting for an interrupt
+ - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
+                                 accesible via KVM_GET_VCPU_EVENTS)
+
+This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
+irqchip, the multiprocessing state must be maintained by userspace.
+
+4.38 KVM_SET_MP_STATE
+
+Capability: KVM_CAP_MP_STATE
+Architectures: x86, ia64
+Type: vcpu ioctl
+Parameters: struct kvm_mp_state (in)
+Returns: 0 on success; -1 on error
+
+Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
+arguments.
+
+This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
+irqchip, the multiprocessing state must be maintained by userspace.
 
 5. The kvm_run structure
 
@@ -820,6 +1002,13 @@ executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
 
+NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO and KVM_EXIT_OSI, the corresponding
+operations are complete (and guest state is consistent) only after userspace
+has re-entered the kernel with KVM_RUN.  The kernel side will first finish
+incomplete operations and then check for pending signals.  Userspace
+can re-enter the guest with an unmasked signal pending to complete
+pending operations.
+
 		/* KVM_EXIT_HYPERCALL */
 		struct {
 			__u64 nr;
@@ -829,7 +1018,9 @@ true, and should be filled by application code otherwise.
 			__u32 pad;
 		} hypercall;
 
-Unused.
+Unused.  This was once used for 'hypercall to userspace'.  To implement
+such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
+Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
 
 		/* KVM_EXIT_TPR_ACCESS */
 		struct {
@@ -870,6 +1061,19 @@ s390 specific.
 
 powerpc specific.
 
+		/* KVM_EXIT_OSI */
+		struct {
+			__u64 gprs[32];
+		} osi;
+
+MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
+hypercalls and exit with this exit struct that contains all the guest gprs.
+
+If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
+Userspace can now handle the hypercall and when it's done modify the gprs as
+necessary. Upon guest entry all guest GPRs will then be replaced by the values
+in this struct.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};

Documentation/kvm/cpuid.txt

@@ -0,0 +1,42 @@
+KVM CPUID bits
+Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
+=====================================================
+
+A guest running on a kvm host, can check some of its features using
+cpuid. This is not always guaranteed to work, since userspace can
+mask-out some, or even all KVM-related cpuid features before launching
+a guest.
+
+KVM cpuid functions are:
+
+function: KVM_CPUID_SIGNATURE (0x40000000)
+returns : eax = 0,
+          ebx = 0x4b4d564b,
+          ecx = 0x564b4d56,
+          edx = 0x4d.
+Note that this value in ebx, ecx and edx corresponds to the string "KVMKVMKVM".
+This function queries the presence of KVM cpuid leafs.
+
+
+function: define KVM_CPUID_FEATURES (0x40000001)
+returns : ebx, ecx, edx = 0
+          eax = and OR'ed group of (1 << flag), where each flags is:
+
+
+flag                               || value || meaning
+=============================================================================
+KVM_FEATURE_CLOCKSOURCE            ||     0 || kvmclock available at msrs
+                                   ||       || 0x11 and 0x12.
+------------------------------------------------------------------------------
+KVM_FEATURE_NOP_IO_DELAY           ||     1 || not necessary to perform delays
+                                   ||       || on PIO operations.
+------------------------------------------------------------------------------
+KVM_FEATURE_MMU_OP                 ||     2 || deprecated.
+------------------------------------------------------------------------------
+KVM_FEATURE_CLOCKSOURCE2           ||     3 || kvmclock available at msrs
+                                   ||       || 0x4b564d00 and 0x4b564d01
+------------------------------------------------------------------------------
+KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
+                                   ||       || per-cpu warps are expected in
+                                   ||       || kvmclock.
+------------------------------------------------------------------------------

Documentation/kvm/mmu.txt

@@ -0,0 +1,304 @@
+The x86 kvm shadow mmu
+======================
+
+The mmu (in arch/x86/kvm, files mmu.[ch] and paging_tmpl.h) is responsible
+for presenting a standard x86 mmu to the guest, while translating guest
+physical addresses to host physical addresses.
+
+The mmu code attempts to satisfy the following requirements:
+
+- correctness: the guest should not be able to determine that it is running
+               on an emulated mmu except for timing (we attempt to comply
+               with the specification, not emulate the characteristics of
+               a particular implementation such as tlb size)
+- security:    the guest must not be able to touch host memory not assigned
+               to it
+- performance: minimize the performance penalty imposed by the mmu
+- scaling:     need to scale to large memory and large vcpu guests
+- hardware:    support the full range of x86 virtualization hardware
+- integration: Linux memory management code must be in control of guest memory
+               so that swapping, page migration, page merging, transparent
+               hugepages, and similar features work without change
+- dirty tracking: report writes to guest memory to enable live migration
+               and framebuffer-based displays
+- footprint:   keep the amount of pinned kernel memory low (most memory
+               should be shrinkable)
+- reliablity:  avoid multipage or GFP_ATOMIC allocations
+
+Acronyms
+========
+
+pfn   host page frame number
+hpa   host physical address
+hva   host virtual address
+gfn   guest frame number
+gpa   guest physical address
+gva   guest virtual address
+ngpa  nested guest physical address
+ngva  nested guest virtual address
+pte   page table entry (used also to refer generically to paging structure
+      entries)
+gpte  guest pte (referring to gfns)
+spte  shadow pte (referring to pfns)
+tdp   two dimensional paging (vendor neutral term for NPT and EPT)
+
+Virtual and real hardware supported
+===================================
+
+The mmu supports first-generation mmu hardware, which allows an atomic switch
+of the current paging mode and cr3 during guest entry, as well as
+two-dimensional paging (AMD's NPT and Intel's EPT).  The emulated hardware
+it exposes is the traditional 2/3/4 level x86 mmu, with support for global
+pages, pae, pse, pse36, cr0.wp, and 1GB pages.  Work is in progress to support
+exposing NPT capable hardware on NPT capable hosts.
+
+Translation
+===========
+
+The primary job of the mmu is to program the processor's mmu to translate
+addresses for the guest.  Different translations are required at different
+times:
+
+- when guest paging is disabled, we translate guest physical addresses to
+  host physical addresses (gpa->hpa)
+- when guest paging is enabled, we translate guest virtual addresses, to
+  guest physical addresses, to host physical addresses (gva->gpa->hpa)
+- when the guest launches a guest of its own, we translate nested guest
+  virtual addresses, to nested guest physical addresses, to guest physical
+  addresses, to host physical addresses (ngva->ngpa->gpa->hpa)
+
+The primary challenge is to encode between 1 and 3 translations into hardware
+that support only 1 (traditional) and 2 (tdp) translations.  When the
+number of required translations matches the hardware, the mmu operates in
+direct mode; otherwise it operates in shadow mode (see below).
+
+Memory
+======
+
+Guest memory (gpa) is part of the user address space of the process that is
+using kvm.  Userspace defines the translation between guest addresses and user
+addresses (gpa->hva); note that two gpas may alias to the same gva, but not
+vice versa.
+
+These gvas may be backed using any method available to the host: anonymous
+memory, file backed memory, and device memory.  Memory might be paged by the
+host at any time.
+
+Events
+======
+
+The mmu is driven by events, some from the guest, some from the host.
+
+Guest generated events:
+- writes to control registers (especially cr3)
+- invlpg/invlpga instruction execution
+- access to missing or protected translations
+
+Host generated events:
+- changes in the gpa->hpa translation (either through gpa->hva changes or
+  through hva->hpa changes)
+- memory pressure (the shrinker)
+
+Shadow pages
+============
+
+The principal data structure is the shadow page, 'struct kvm_mmu_page'.  A
+shadow page contains 512 sptes, which can be either leaf or nonleaf sptes.  A
+shadow page may contain a mix of leaf and nonleaf sptes.
+
+A nonleaf spte allows the hardware mmu to reach the leaf pages and
+is not related to a translation directly.  It points to other shadow pages.
+
+A leaf spte corresponds to either one or two translations encoded into
+one paging structure entry.  These are always the lowest level of the
+translation stack, with optional higher level translations left to NPT/EPT.
+Leaf ptes point at guest pages.
+
+The following table shows translations encoded by leaf ptes, with higher-level
+translations in parentheses:
+
+ Non-nested guests:
+  nonpaging:     gpa->hpa
+  paging:        gva->gpa->hpa
+  paging, tdp:   (gva->)gpa->hpa
+ Nested guests:
+  non-tdp:       ngva->gpa->hpa  (*)
+  tdp:           (ngva->)ngpa->gpa->hpa
+
+(*) the guest hypervisor will encode the ngva->gpa translation into its page
+    tables if npt is not present
+
+Shadow pages contain the following information:
+  role.level:
+    The level in the shadow paging hierarchy that this shadow page belongs to.
+    1=4k sptes, 2=2M sptes, 3=1G sptes, etc.
+  role.direct:
+    If set, leaf sptes reachable from this page are for a linear range.
+    Examples include real mode translation, large guest pages backed by small
+    host pages, and gpa->hpa translations when NPT or EPT is active.
+    The linear range starts at (gfn << PAGE_SHIFT) and its size is determined
+    by role.level (2MB for first level, 1GB for second level, 0.5TB for third
+    level, 256TB for fourth level)
+    If clear, this page corresponds to a guest page table denoted by the gfn
+    field.
+  role.quadrant:
+    When role.cr4_pae=0, the guest uses 32-bit gptes while the host uses 64-bit
+    sptes.  That means a guest page table contains more ptes than the host,
+    so multiple shadow pages are needed to shadow one guest page.
+    For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the
+    first or second 512-gpte block in the guest page table.  For second-level
+    page tables, each 32-bit gpte is converted to two 64-bit sptes
+    (since each first-level guest page is shadowed by two first-level
+    shadow pages) so role.quadrant takes values in the range 0..3.  Each
+    quadrant maps 1GB virtual address space.
+  role.access:
+    Inherited guest access permissions in the form uwx.  Note execute
+    permission is positive, not negative.
+  role.invalid:
+    The page is invalid and should not be used.  It is a root page that is
+    currently pinned (by a cpu hardware register pointing to it); once it is
+    unpinned it will be destroyed.
+  role.cr4_pae:
+    Contains the value of cr4.pae for which the page is valid (e.g. whether
+    32-bit or 64-bit gptes are in use).
+  role.cr4_nxe:
+    Contains the value of efer.nxe for which the page is valid.
+  role.cr0_wp:
+    Contains the value of cr0.wp for which the page is valid.
+  gfn:
+    Either the guest page table containing the translations shadowed by this
+    page, or the base page frame for linear translations.  See role.direct.
+  spt:
+    A pageful of 64-bit sptes containing the translations for this page.
+    Accessed by both kvm and hardware.
+    The page pointed to by spt will have its page->private pointing back
+    at the shadow page structure.
+    sptes in spt point either at guest pages, or at lower-level shadow pages.
+    Specifically, if sp1 and sp2 are shadow pages, then sp1->spt[n] may point
+    at __pa(sp2->spt).  sp2 will point back at sp1 through parent_pte.
+    The spt array forms a DAG structure with the shadow page as a node, and
+    guest pages as leaves.
+  gfns:
+    An array of 512 guest frame numbers, one for each present pte.  Used to
+    perform a reverse map from a pte to a gfn.
+  slot_bitmap:
+    A bitmap containing one bit per memory slot.  If the page contains a pte
+    mapping a page from memory slot n, then bit n of slot_bitmap will be set
+    (if a page is aliased among several slots, then it is not guaranteed that
+    all slots will be marked).
+    Used during dirty logging to avoid scanning a shadow page if none if its
+    pages need tracking.
+  root_count:
+    A counter keeping track of how many hardware registers (guest cr3 or
+    pdptrs) are now pointing at the page.  While this counter is nonzero, the
+    page cannot be destroyed.  See role.invalid.
+  multimapped:
+    Whether there exist multiple sptes pointing at this page.
+  parent_pte/parent_ptes:
+    If multimapped is zero, parent_pte points at the single spte that points at
+    this page's spt.  Otherwise, parent_ptes points at a data structure
+    with a list of parent_ptes.
+  unsync:
+    If true, then the translations in this page may not match the guest's
+    translation.  This is equivalent to the state of the tlb when a pte is
+    changed but before the tlb entry is flushed.  Accordingly, unsync ptes
+    are synchronized when the guest executes invlpg or flushes its tlb by
+    other means.  Valid for leaf pages.
+  unsync_children:
+    How many sptes in the page point at pages that are unsync (or have
+    unsynchronized children).
+  unsync_child_bitmap:
+    A bitmap indicating which sptes in spt point (directly or indirectly) at
+    pages that may be unsynchronized.  Used to quickly locate all unsychronized
+    pages reachable from a given page.
+
+Reverse map
+===========
+
+The mmu maintains a reverse mapping whereby all ptes mapping a page can be
+reached given its gfn.  This is used, for example, when swapping out a page.
+
+Synchronized and unsynchronized pages
+=====================================
+
+The guest uses two events to synchronize its tlb and page tables: tlb flushes
+and page invalidations (invlpg).
+
+A tlb flush means that we need to synchronize all sptes reachable from the
+guest's cr3.  This is expensive, so we keep all guest page tables write
+protected, and synchronize sptes to gptes when a gpte is written.
+
+A special case is when a guest page table is reachable from the current
+guest cr3.  In this case, the guest is obliged to issue an invlpg instruction
+before using the translation.  We take advantage of that by removing write
+protection from the guest page, and allowing the guest to modify it freely.
+We synchronize modified gptes when the guest invokes invlpg.  This reduces
+the amount of emulation we have to do when the guest modifies multiple gptes,
+or when the a guest page is no longer used as a page table and is used for
+random guest data.
+
+As a side effect we have to resynchronize all reachable unsynchronized shadow
+pages on a tlb flush.
+
+
+Reaction to events
+==================
+
+- guest page fault (or npt page fault, or ept violation)
+
+This is the most complicated event.  The cause of a page fault can be:
+
+  - a true guest fault (the guest translation won't allow the access) (*)
+  - access to a missing translation
+  - access to a protected translation
+    - when logging dirty pages, memory is write protected
+    - synchronized shadow pages are write protected (*)
+  - access to untranslatable memory (mmio)
+
+  (*) not applicable in direct mode
+
+Handling a page fault is performed as follows:
+
+ - if needed, walk the guest page tables to determine the guest translation
+   (gva->gpa or ngpa->gpa)
+   - if permissions are insufficient, reflect the fault back to the guest
+ - determine the host page
+   - if this is an mmio request, there is no host page; call the emulator
+     to emulate the instruction instead
+ - walk the shadow page table to find the spte for the translation,
+   instantiating missing intermediate page tables as necessary
+ - try to unsynchronize the page
+   - if successful, we can let the guest continue and modify the gpte
+ - emulate the instruction
+   - if failed, unshadow the page and let the guest continue
+ - update any translations that were modified by the instruction
+
+invlpg handling:
+
+  - walk the shadow page hierarchy and drop affected translations
+  - try to reinstantiate the indicated translation in the hope that the
+    guest will use it in the near future
+
+Guest control register updates:
+
+- mov to cr3
+  - look up new shadow roots
+  - synchronize newly reachable shadow pages
+
+- mov to cr0/cr4/efer
+  - set up mmu context for new paging mode
+  - look up new shadow roots
+  - synchronize newly reachable shadow pages
+
+Host translation updates:
+
+  - mmu notifier called with updated hva
+  - look up affected sptes through reverse map
+  - drop (or update) translations
+
+Further reading
+===============
+
+- NPT presentation from KVM Forum 2008
+  http://www.linux-kvm.org/wiki/images/c/c8/KvmForum2008%24kdf2008_21.pdf
+

arch/ia64/kvm/kvm-ia64.c

@@ -979,11 +979,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
+		r = -ENXIO;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 				    irq_event.irq, irq_event.level);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
+				r = -EFAULT;
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,
 							sizeof irq_event))
@@ -1379,7 +1381,7 @@ static void kvm_release_vm_pages(struct kvm *kvm)
 	int i, j;
 	unsigned long base_gfn;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 	for (i = 0; i < slots->nmemslots; i++) {
 		memslot = &slots->memslots[i];
 		base_gfn = memslot->base_gfn;
@@ -1535,8 +1537,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			goto out;
 
 		if (copy_to_user(user_stack, stack,
-				 sizeof(struct kvm_ia64_vcpu_stack)))
+				 sizeof(struct kvm_ia64_vcpu_stack))) {
+			r = -EFAULT;
 			goto out;
+		}
 
 		break;
 	}

arch/ia64/kvm/vmm.c

@@ -51,7 +51,7 @@ static int __init  kvm_vmm_init(void)
 	vmm_fpswa_interface = fpswa_interface;
 
 	/*Register vmm data to kvm side*/
-	return kvm_init(&vmm_info, 1024, THIS_MODULE);
+	return kvm_init(&vmm_info, 1024, 0, THIS_MODULE);
 }
 
 static void __exit kvm_vmm_exit(void)

arch/powerpc/include/asm/asm-compat.h

@@ -21,6 +21,7 @@
 /* operations for longs and pointers */
 #define PPC_LL		stringify_in_c(ld)
 #define PPC_STL		stringify_in_c(std)
+#define PPC_STLU	stringify_in_c(stdu)
 #define PPC_LCMPI	stringify_in_c(cmpdi)
 #define PPC_LONG	stringify_in_c(.llong)
 #define PPC_LONG_ALIGN	stringify_in_c(.balign 8)
@@ -44,6 +45,7 @@
 /* operations for longs and pointers */
 #define PPC_LL		stringify_in_c(lwz)
 #define PPC_STL		stringify_in_c(stw)
+#define PPC_STLU	stringify_in_c(stwu)
 #define PPC_LCMPI	stringify_in_c(cmpwi)
 #define PPC_LONG	stringify_in_c(.long)
 #define PPC_LONG_ALIGN	stringify_in_c(.balign 4)

arch/powerpc/include/asm/kvm.h

@@ -77,4 +77,14 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
+#define KVM_REG_MASK		0x001f
+#define KVM_REG_EXT_MASK	0xffe0
+#define KVM_REG_GPR		0x0000
+#define KVM_REG_FPR		0x0020
+#define KVM_REG_QPR		0x0040
+#define KVM_REG_FQPR		0x0060
+
+#define KVM_INTERRUPT_SET	-1U
+#define KVM_INTERRUPT_UNSET	-2U
+
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/include/asm/kvm_asm.h

@@ -88,6 +88,8 @@
 
 #define BOOK3S_HFLAG_DCBZ32			0x1
 #define BOOK3S_HFLAG_SLB			0x2
+#define BOOK3S_HFLAG_PAIRED_SINGLE		0x4
+#define BOOK3S_HFLAG_NATIVE_PS			0x8
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */

arch/powerpc/include/asm/kvm_book3s.h

@@ -22,46 +22,47 @@
 
 #include <linux/types.h>
 #include <linux/kvm_host.h>
-#include <asm/kvm_book3s_64_asm.h>
+#include <asm/kvm_book3s_asm.h>
 
 struct kvmppc_slb {
 	u64 esid;
 	u64 vsid;
 	u64 orige;
 	u64 origv;
-	bool valid;
-	bool Ks;
-	bool Kp;
-	bool nx;
-	bool large;	/* PTEs are 16MB */
-	bool tb;	/* 1TB segment */
-	bool class;
+	bool valid	: 1;
+	bool Ks		: 1;
+	bool Kp		: 1;
+	bool nx		: 1;
+	bool large	: 1;	/* PTEs are 16MB */
+	bool tb		: 1;	/* 1TB segment */
+	bool class	: 1;
 };
 
 struct kvmppc_sr {
 	u32 raw;
 	u32 vsid;
-	bool Ks;
-	bool Kp;
-	bool nx;
+	bool Ks		: 1;
+	bool Kp		: 1;
+	bool nx		: 1;
+	bool valid	: 1;
 };
 
 struct kvmppc_bat {
 	u64 raw;
 	u32 bepi;
 	u32 bepi_mask;
-	bool vs;
-	bool vp;
 	u32 brpn;
 	u8 wimg;
 	u8 pp;
+	bool vs		: 1;
+	bool vp		: 1;
 };
 
 struct kvmppc_sid_map {
 	u64 guest_vsid;
 	u64 guest_esid;
 	u64 host_vsid;
-	bool valid;
+	bool valid	: 1;
 };
 
 #define SID_MAP_BITS    9
@@ -70,7 +71,7 @@ struct kvmppc_sid_map {
 
 struct kvmppc_vcpu_book3s {
 	struct kvm_vcpu vcpu;
-	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
+	struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
 	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
 	struct kvmppc_slb slb[64];
 	struct {
@@ -82,9 +83,10 @@ struct kvmppc_vcpu_book3s {
 	struct kvmppc_bat ibat[8];
 	struct kvmppc_bat dbat[8];
 	u64 hid[6];
+	u64 gqr[8];
 	int slb_nr;
+	u32 dsisr;
 	u64 sdr1;
-	u64 dsisr;
 	u64 hior;
 	u64 msr_mask;
 	u64 vsid_first;
@@ -98,15 +100,15 @@ struct kvmppc_vcpu_book3s {
 #define CONTEXT_GUEST		1
 #define CONTEXT_GUEST_END	2
 
-#define VSID_REAL	0xfffffffffff00000
-#define VSID_REAL_DR	0xffffffffffe00000
-#define VSID_REAL_IR	0xffffffffffd00000
-#define VSID_BAT	0xffffffffffc00000
-#define VSID_PR		0x8000000000000000
+#define VSID_REAL	0x1fffffffffc00000ULL
+#define VSID_BAT	0x1fffffffffb00000ULL
+#define VSID_REAL_DR	0x2000000000000000ULL
+#define VSID_REAL_IR	0x4000000000000000ULL
+#define VSID_PR		0x8000000000000000ULL
 
-extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 ea, u64 ea_mask);
+extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask);
 extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask);
-extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end);
+extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end);
 extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr);
 extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
@@ -114,11 +116,13 @@ extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
 extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data);
-extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, bool data);
-extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr);
+extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
+extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
 extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 			   bool upper, u32 val);
+extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
+extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
 
 extern u32 kvmppc_trampoline_lowmem;
 extern u32 kvmppc_trampoline_enter;
@@ -126,6 +130,8 @@ extern void kvmppc_rmcall(ulong srr0, ulong srr1);
 extern void kvmppc_load_up_fpu(void);
 extern void kvmppc_load_up_altivec(void);
 extern void kvmppc_load_up_vsx(void);
+extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
+extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {
@@ -140,7 +146,108 @@ static inline ulong dsisr(void)
 }
 
 extern void kvm_return_point(void);
+static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu);
+
+static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
+{
+	if ( num < 14 ) {
+		to_svcpu(vcpu)->gpr[num] = val;
+		to_book3s(vcpu)->shadow_vcpu->gpr[num] = val;
+	} else
+		vcpu->arch.gpr[num] = val;
+}
+
+static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
+{
+	if ( num < 14 )
+		return to_svcpu(vcpu)->gpr[num];
+	else
+		return vcpu->arch.gpr[num];
+}
+
+static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
+{
+	to_svcpu(vcpu)->cr = val;
+	to_book3s(vcpu)->shadow_vcpu->cr = val;
+}
+
+static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
+{
+	return to_svcpu(vcpu)->cr;
+}
+
+static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
+{
+	to_svcpu(vcpu)->xer = val;
+	to_book3s(vcpu)->shadow_vcpu->xer = val;
+}
+
+static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
+{
+	return to_svcpu(vcpu)->xer;
+}
+
+static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
+{
+	to_svcpu(vcpu)->ctr = val;
+}
+
+static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
+{
+	return to_svcpu(vcpu)->ctr;
+}
+
+static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
+{
+	to_svcpu(vcpu)->lr = val;
+}
+
+static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
+{
+	return to_svcpu(vcpu)->lr;
+}
+
+static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
+{
+	to_svcpu(vcpu)->pc = val;
+}
+
+static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
+{
+	return to_svcpu(vcpu)->pc;
+}
+
+static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu);
+	struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
+
+	return svcpu->last_inst;
+}
+
+static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
+{
+	return to_svcpu(vcpu)->fault_dar;
+}
+
+/* Magic register values loaded into r3 and r4 before the 'sc' assembly
+ * instruction for the OSI hypercalls */
+#define OSI_SC_MAGIC_R3			0x113724FA
+#define OSI_SC_MAGIC_R4			0x77810F9B
 
 #define INS_DCBZ			0x7c0007ec
 
+/* Also add subarch specific defines */
+
+#ifdef CONFIG_PPC_BOOK3S_32
+#include <asm/kvm_book3s_32.h>
+#else
+#include <asm/kvm_book3s_64.h>
+#endif
+
 #endif /* __ASM_KVM_BOOK3S_H__ */

arch/powerpc/include/asm/kvm_book3s_32.h

@@ -0,0 +1,42 @@
+/*
+ * 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 SUSE Linux Products GmbH 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_BOOK3S_32_H__
+#define __ASM_KVM_BOOK3S_32_H__
+
+static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+{
+	return to_book3s(vcpu)->shadow_vcpu;
+}
+
+#define PTE_SIZE	12
+#define VSID_ALL	0
+#define SR_INVALID	0x00000001	/* VSID 1 should always be unused */
+#define SR_KP		0x20000000
+#define PTE_V		0x80000000
+#define PTE_SEC		0x00000040
+#define PTE_M		0x00000010
+#define PTE_R		0x00000100
+#define PTE_C		0x00000080
+
+#define SID_SHIFT	28
+#define ESID_MASK	0xf0000000
+#define VSID_MASK	0x00fffffff0000000ULL
+
+#endif /* __ASM_KVM_BOOK3S_32_H__ */

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -0,0 +1,28 @@
+/*
+ * 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 SUSE Linux Products GmbH 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_BOOK3S_64_H__
+#define __ASM_KVM_BOOK3S_64_H__
+
+static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+{
+	return &get_paca()->shadow_vcpu;
+}
+
+#endif /* __ASM_KVM_BOOK3S_64_H__ */

arch/powerpc/include/asm/kvm_book3s_64_asm.h → arch/powerpc/include/asm/kvm_book3s_asm.h

@@ -22,7 +22,7 @@
 
 #ifdef __ASSEMBLY__
 
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
 
 #include <asm/kvm_asm.h>
 
@@ -55,7 +55,7 @@ kvmppc_resume_\intno:
 .macro DO_KVM intno
 .endm
 
-#endif /* CONFIG_KVM_BOOK3S_64_HANDLER */
+#endif /* CONFIG_KVM_BOOK3S_HANDLER */
 
 #else  /*__ASSEMBLY__ */
 
@@ -63,12 +63,33 @@ struct kvmppc_book3s_shadow_vcpu {
 	ulong gpr[14];
 	u32 cr;
 	u32 xer;
+
+	u32 fault_dsisr;
+	u32 last_inst;
+	ulong ctr;
+	ulong lr;
+	ulong pc;
+	ulong shadow_srr1;
+	ulong fault_dar;
+
 	ulong host_r1;
 	ulong host_r2;
 	ulong handler;
 	ulong scratch0;
 	ulong scratch1;
 	ulong vmhandler;
+	u8 in_guest;
+
+#ifdef CONFIG_PPC_BOOK3S_32
+	u32     sr[16];			/* Guest SRs */
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	u8 slb_max;			/* highest used guest slb entry */
+	struct  {
+		u64     esid;
+		u64     vsid;
+	} slb[64];			/* guest SLB */
+#endif
 };
 
 #endif /*__ASSEMBLY__ */

arch/powerpc/include/asm/kvm_booke.h

@@ -0,0 +1,96 @@
+/*
+ * 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 SUSE Linux Products GmbH 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_BOOKE_H__
+#define __ASM_KVM_BOOKE_H__
+
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+
+static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
+{
+	vcpu->arch.gpr[num] = val;
+}
+
+static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
+{
+	return vcpu->arch.gpr[num];
+}
+
+static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
+{
+	vcpu->arch.cr = val;
+}
+
+static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cr;
+}
+
+static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
+{
+	vcpu->arch.xer = val;
+}
+
+static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.xer;
+}
+
+static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.last_inst;
+}
+
+static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
+{
+	vcpu->arch.ctr = val;
+}
+
+static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.ctr;
+}
+
+static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
+{
+	vcpu->arch.lr = val;
+}
+
+static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.lr;
+}
+
+static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
+{
+	vcpu->arch.pc = val;
+}
+
+static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.pc;
+}
+
+static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault_dear;
+}
+
+#endif /* __ASM_KVM_BOOKE_H__ */

arch/powerpc/include/asm/kvm_fpu.h

@@ -0,0 +1,85 @@
+/*
+ * 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 Novell Inc. 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_FPU_H__
+#define __ASM_KVM_FPU_H__
+
+#include <linux/types.h>
+
+extern void fps_fres(struct thread_struct *t, u32 *dst, u32 *src1);
+extern void fps_frsqrte(struct thread_struct *t, u32 *dst, u32 *src1);
+extern void fps_fsqrts(struct thread_struct *t, u32 *dst, u32 *src1);
+
+extern void fps_fadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
+extern void fps_fdivs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
+extern void fps_fmuls(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
+extern void fps_fsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
+
+extern void fps_fmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+		       u32 *src3);
+extern void fps_fmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+		       u32 *src3);
+extern void fps_fnmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+		        u32 *src3);
+extern void fps_fnmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+		        u32 *src3);
+extern void fps_fsel(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+		     u32 *src3);
+
+#define FPD_ONE_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \
+				u64 *dst, u64 *src1);
+#define FPD_TWO_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \
+				u64 *dst, u64 *src1, u64 *src2);
+#define FPD_THREE_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \
+				u64 *dst, u64 *src1, u64 *src2, u64 *src3);
+
+extern void fpd_fcmpu(u64 *fpscr, u32 *cr, u64 *src1, u64 *src2);
+extern void fpd_fcmpo(u64 *fpscr, u32 *cr, u64 *src1, u64 *src2);
+
+FPD_ONE_IN(fsqrts)
+FPD_ONE_IN(frsqrtes)
+FPD_ONE_IN(fres)
+FPD_ONE_IN(frsp)
+FPD_ONE_IN(fctiw)
+FPD_ONE_IN(fctiwz)
+FPD_ONE_IN(fsqrt)
+FPD_ONE_IN(fre)
+FPD_ONE_IN(frsqrte)
+FPD_ONE_IN(fneg)
+FPD_ONE_IN(fabs)
+FPD_TWO_IN(fadds)
+FPD_TWO_IN(fsubs)
+FPD_TWO_IN(fdivs)
+FPD_TWO_IN(fmuls)
+FPD_TWO_IN(fcpsgn)
+FPD_TWO_IN(fdiv)
+FPD_TWO_IN(fadd)
+FPD_TWO_IN(fmul)
+FPD_TWO_IN(fsub)
+FPD_THREE_IN(fmsubs)
+FPD_THREE_IN(fmadds)
+FPD_THREE_IN(fnmsubs)
+FPD_THREE_IN(fnmadds)
+FPD_THREE_IN(fsel)
+FPD_THREE_IN(fmsub)
+FPD_THREE_IN(fmadd)
+FPD_THREE_IN(fnmsub)
+FPD_THREE_IN(fnmadd)
+
+#endif

arch/powerpc/include/asm/kvm_host.h

@@ -66,7 +66,7 @@ struct kvm_vcpu_stat {
 	u32 dec_exits;
 	u32 ext_intr_exits;
 	u32 halt_wakeup;
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
 	u32 pf_storage;
 	u32 pf_instruc;
 	u32 sp_storage;
@@ -124,12 +124,12 @@ struct kvm_arch {
 };
 
 struct kvmppc_pte {
-	u64 eaddr;
+	ulong eaddr;
 	u64 vpage;
-	u64 raddr;
-	bool may_read;
-	bool may_write;
-	bool may_execute;
+	ulong raddr;
+	bool may_read		: 1;
+	bool may_write		: 1;
+	bool may_execute	: 1;
 };
 
 struct kvmppc_mmu {
@@ -145,7 +145,7 @@ struct kvmppc_mmu {
 	int  (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data);
 	void (*reset_msr)(struct kvm_vcpu *vcpu);
 	void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large);
-	int  (*esid_to_vsid)(struct kvm_vcpu *vcpu, u64 esid, u64 *vsid);
+	int  (*esid_to_vsid)(struct kvm_vcpu *vcpu, ulong esid, u64 *vsid);
 	u64  (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data);
 	bool (*is_dcbz32)(struct kvm_vcpu *vcpu);
 };
@@ -160,7 +160,7 @@ struct hpte_cache {
 struct kvm_vcpu_arch {
 	ulong host_stack;
 	u32 host_pid;
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
 	ulong host_msr;
 	ulong host_r2;
 	void *host_retip;
@@ -175,7 +175,7 @@ struct kvm_vcpu_arch {
 	ulong gpr[32];
 
 	u64 fpr[32];
-	u32 fpscr;
+	u64 fpscr;
 
 #ifdef CONFIG_ALTIVEC
 	vector128 vr[32];
@@ -186,19 +186,23 @@ struct kvm_vcpu_arch {
 	u64 vsr[32];
 #endif
 
+#ifdef CONFIG_PPC_BOOK3S
+	/* For Gekko paired singles */
+	u32 qpr[32];
+#endif
+
+#ifdef CONFIG_BOOKE
 	ulong pc;
 	ulong ctr;
 	ulong lr;
 
-#ifdef CONFIG_BOOKE
 	ulong xer;
 	u32 cr;
 #endif
 
 	ulong msr;
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
 	ulong shadow_msr;
-	ulong shadow_srr1;
 	ulong hflags;
 	ulong guest_owned_ext;
 #endif
@@ -253,20 +257,22 @@ struct kvm_vcpu_arch {
 	struct dentry *debugfs_exit_timing;
 #endif
 
+#ifdef CONFIG_BOOKE
 	u32 last_inst;
-#ifdef CONFIG_PPC64
-	ulong fault_dsisr;
-#endif
 	ulong fault_dear;
 	ulong fault_esr;
 	ulong queued_dear;
 	ulong queued_esr;
+#endif
 	gpa_t paddr_accessed;
 
 	u8 io_gpr; /* GPR used as IO source/target */
 	u8 mmio_is_bigendian;
+	u8 mmio_sign_extend;
 	u8 dcr_needed;
 	u8 dcr_is_write;
+	u8 osi_needed;
+	u8 osi_enabled;
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
@@ -275,7 +281,7 @@ struct kvm_vcpu_arch {
 	u64 dec_jiffies;
 	unsigned long pending_exceptions;
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
 	struct hpte_cache hpte_cache[HPTEG_CACHE_NUM];
 	int hpte_cache_offset;
 #endif

arch/powerpc/include/asm/kvm_ppc.h

@@ -30,6 +30,8 @@
 #include <linux/kvm_host.h>
 #ifdef CONFIG_PPC_BOOK3S
 #include <asm/kvm_book3s.h>
+#else
+#include <asm/kvm_booke.h>
 #endif
 
 enum emulation_result {
@@ -37,6 +39,7 @@ enum emulation_result {
 	EMULATE_DO_MMIO,      /* kvm_run filled with MMIO request */
 	EMULATE_DO_DCR,       /* kvm_run filled with DCR request */
 	EMULATE_FAIL,         /* can't emulate this instruction */
+	EMULATE_AGAIN,        /* something went wrong. go again */
 };
 
 extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
@@ -48,8 +51,11 @@ extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
 extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
                               unsigned int rt, unsigned int bytes,
                               int is_bigendian);
+extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                               unsigned int rt, unsigned int bytes,
+                               int is_bigendian);
 extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                               u32 val, unsigned int bytes, int is_bigendian);
+                               u64 val, unsigned int bytes, int is_bigendian);
 
 extern int kvmppc_emulate_instruction(struct kvm_run *run,
                                       struct kvm_vcpu *vcpu);
@@ -63,6 +69,7 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
 extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid);
 extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu);
+extern int kvmppc_mmu_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
@@ -88,6 +95,8 @@ extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                        struct kvm_interrupt *irq);
+extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
+                                         struct kvm_interrupt *irq);
 
 extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                   unsigned int op, int *advance);
@@ -99,81 +108,37 @@ extern void kvmppc_booke_exit(void);
 
 extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 
-#ifdef CONFIG_PPC_BOOK3S
-
-/* We assume we're always acting on the current vcpu */
-
-static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
-{
-	if ( num < 14 ) {
-		get_paca()->shadow_vcpu.gpr[num] = val;
-		to_book3s(vcpu)->shadow_vcpu.gpr[num] = val;
-	} else
-		vcpu->arch.gpr[num] = val;
-}
-
-static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
-{
-	if ( num < 14 )
-		return get_paca()->shadow_vcpu.gpr[num];
-	else
-		return vcpu->arch.gpr[num];
-}
-
-static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
-{
-	get_paca()->shadow_vcpu.cr = val;
-	to_book3s(vcpu)->shadow_vcpu.cr = val;
-}
-
-static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
-{
-	return get_paca()->shadow_vcpu.cr;
-}
-
-static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
-{
-	get_paca()->shadow_vcpu.xer = val;
-	to_book3s(vcpu)->shadow_vcpu.xer = val;
-}
-
-static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
+/*
+ * Cuts out inst bits with ordering according to spec.
+ * That means the leftmost bit is zero. All given bits are included.
+ */
+static inline u32 kvmppc_get_field(u64 inst, int msb, int lsb)
 {
-	return get_paca()->shadow_vcpu.xer;
-}
+	u32 r;
+	u32 mask;
 
-#else
+	BUG_ON(msb > lsb);
 
-static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
-{
-	vcpu->arch.gpr[num] = val;
-}
+	mask = (1 << (lsb - msb + 1)) - 1;
+	r = (inst >> (63 - lsb)) & mask;
 
-static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
-{
-	return vcpu->arch.gpr[num];
+	return r;
 }
 
-static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
+/*
+ * Replaces inst bits with ordering according to spec.
+ */
+static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value)
 {
-	vcpu->arch.cr = val;
-}
+	u32 r;
+	u32 mask;
 
-static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.cr;
-}
+	BUG_ON(msb > lsb);
 
-static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
-{
-	vcpu->arch.xer = val;
-}
+	mask = ((1 << (lsb - msb + 1)) - 1) << (63 - lsb);
+	r = (inst & ~mask) | ((value << (63 - lsb)) & mask);
 
-static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.xer;
+	return r;
 }
 
-#endif
-
 #endif /* __POWERPC_KVM_PPC_H__ */

arch/powerpc/include/asm/mmu_context.h

@@ -27,6 +27,8 @@ extern int __init_new_context(void);
 extern void __destroy_context(int context_id);
 static inline void mmu_context_init(void) { }
 #else
+extern unsigned long __init_new_context(void);
+extern void __destroy_context(unsigned long context_id);
 extern void mmu_context_init(void);
 #endif
 

arch/powerpc/include/asm/paca.h

@@ -23,7 +23,7 @@
 #include <asm/page.h>
 #include <asm/exception-64e.h>
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#include <asm/kvm_book3s_64_asm.h>
+#include <asm/kvm_book3s_asm.h>
 #endif
 
 register struct paca_struct *local_paca asm("r13");
@@ -137,15 +137,9 @@ struct paca_struct {
 	u64 startpurr;			/* PURR/TB value snapshot */
 	u64 startspurr;			/* SPURR value snapshot */
 
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-	struct  {
-		u64     esid;
-		u64     vsid;
-	} kvm_slb[64];			/* guest SLB */
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
 	/* We use this to store guest state in */
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
-	u8 kvm_slb_max;			/* highest used guest slb entry */
-	u8 kvm_in_guest;		/* are we inside the guest? */
 #endif
 };
 

arch/powerpc/include/asm/processor.h

@@ -229,6 +229,9 @@ struct thread_struct {
 	unsigned long	spefscr;	/* SPE & eFP status */
 	int		used_spe;	/* set if process has used spe */
 #endif /* CONFIG_SPE */
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
+	void*		kvm_shadow_vcpu; /* KVM internal data */
+#endif /* CONFIG_KVM_BOOK3S_32_HANDLER */
 };
 
 #define ARCH_MIN_TASKALIGN 16

arch/powerpc/include/asm/reg.h

@@ -293,10 +293,12 @@
 #define HID1_ABE	(1<<10)		/* 7450 Address Broadcast Enable */
 #define HID1_PS		(1<<16)		/* 750FX PLL selection */
 #define SPRN_HID2	0x3F8		/* Hardware Implementation Register 2 */
+#define SPRN_HID2_GEKKO	0x398		/* Gekko HID2 Register */
 #define SPRN_IABR	0x3F2	/* Instruction Address Breakpoint Register */
 #define SPRN_IABR2	0x3FA		/* 83xx */
 #define SPRN_IBCR	0x135		/* 83xx Insn Breakpoint Control Reg */
 #define SPRN_HID4	0x3F4		/* 970 HID4 */
+#define SPRN_HID4_GEKKO	0x3F3		/* Gekko HID4 */
 #define SPRN_HID5	0x3F6		/* 970 HID5 */
 #define SPRN_HID6	0x3F9	/* BE HID 6 */
 #define   HID6_LB	(0x0F<<12) /* Concurrent Large Page Modes */
@@ -465,6 +467,14 @@
 #define SPRN_VRSAVE	0x100	/* Vector Register Save Register */
 #define SPRN_XER	0x001	/* Fixed Point Exception Register */
 
+#define SPRN_MMCR0_GEKKO 0x3B8 /* Gekko Monitor Mode Control Register 0 */
+#define SPRN_MMCR1_GEKKO 0x3BC /* Gekko Monitor Mode Control Register 1 */
+#define SPRN_PMC1_GEKKO  0x3B9 /* Gekko Performance Monitor Control 1 */
+#define SPRN_PMC2_GEKKO  0x3BA /* Gekko Performance Monitor Control 2 */
+#define SPRN_PMC3_GEKKO  0x3BD /* Gekko Performance Monitor Control 3 */
+#define SPRN_PMC4_GEKKO  0x3BE /* Gekko Performance Monitor Control 4 */
+#define SPRN_WPAR_GEKKO  0x399 /* Gekko Write Pipe Address Register */
+
 #define SPRN_SCOMC	0x114	/* SCOM Access Control */
 #define SPRN_SCOMD	0x115	/* SCOM Access DATA */
 

arch/powerpc/kernel/asm-offsets.c

@@ -50,6 +50,9 @@
 #endif
 #ifdef CONFIG_KVM
 #include <linux/kvm_host.h>
+#ifndef CONFIG_BOOKE
+#include <asm/kvm_book3s.h>
+#endif
 #endif
 
 #ifdef CONFIG_PPC32
@@ -105,6 +108,9 @@ int main(void)
 	DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
 #endif /* CONFIG_SPE */
 #endif /* CONFIG_PPC64 */
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
+	DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
+#endif
 
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
@@ -191,33 +197,9 @@ int main(void)
 	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-	DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest));
-	DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb));
-	DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max));
-	DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr));
-	DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer));
-	DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0]));
-	DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1]));
-	DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2]));
-	DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3]));
-	DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4]));
-	DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5]));
-	DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6]));
-	DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7]));
-	DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8]));
-	DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9]));
-	DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10]));
-	DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11]));
-	DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12]));
-	DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13]));
-	DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1));
-	DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2));
-	DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct,
-					    shadow_vcpu.vmhandler));
-	DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct,
-					   shadow_vcpu.scratch0));
-	DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct,
-					   shadow_vcpu.scratch1));
+	DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
+	DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb));
+	DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max));
 #endif
 #endif /* CONFIG_PPC64 */
 
@@ -228,8 +210,8 @@ int main(void)
 	/* Interrupt register frame */
 	DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD);
 	DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
-#ifdef CONFIG_PPC64
 	DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
+#ifdef CONFIG_PPC64
 	/* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */
 	DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
 	DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
@@ -412,9 +394,6 @@ int main(void)
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
-	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
-	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
-	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
 	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
 	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
 	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
@@ -422,27 +401,68 @@ int main(void)
 	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
 
-	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
-	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
-	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
-
-	/* book3s_64 */
-#ifdef CONFIG_PPC64
-	DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
+	/* book3s */
+#ifdef CONFIG_PPC_BOOK3S
 	DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
-	DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2));
 	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
-	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
 	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
 	DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
+	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
+			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
+	DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr));
+	DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer));
+	DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr));
+	DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr));
+	DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc));
+	DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0]));
+	DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1]));
+	DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2]));
+	DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3]));
+	DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4]));
+	DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5]));
+	DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6]));
+	DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7]));
+	DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8]));
+	DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9]));
+	DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10]));
+	DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11]));
+	DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12]));
+	DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13]));
+	DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1));
+	DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2));
+	DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					 vmhandler));
+	DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					scratch0));
+	DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					scratch1));
+	DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					in_guest));
+	DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					   fault_dsisr));
+	DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					 fault_dar));
+	DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					 last_inst));
+	DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu,
+					   shadow_srr1));
+#ifdef CONFIG_PPC_BOOK3S_32
+	DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr));
+#endif
 #else
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
-#endif /* CONFIG_PPC64 */
+	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
+	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
+	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
+	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
+	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+#endif /* CONFIG_PPC_BOOK3S */
 #endif
 #ifdef CONFIG_44x
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);

arch/powerpc/kernel/head_32.S

@@ -33,6 +33,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 #include <asm/bug.h>
+#include <asm/kvm_book3s_asm.h>
 
 /* 601 only have IBAT; cr0.eq is set on 601 when using this macro */
 #define LOAD_BAT(n, reg, RA, RB)	\
@@ -303,6 +304,7 @@ __secondary_hold_acknowledge:
  */
 #define EXCEPTION(n, label, hdlr, xfer)		\
 	. = n;					\
+	DO_KVM n;				\
 label:						\
 	EXCEPTION_PROLOG;			\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;	\
@@ -358,6 +360,7 @@ i##n:								\
  *	-- paulus.
  */
 	. = 0x200
+	DO_KVM  0x200
 	mtspr	SPRN_SPRG_SCRATCH0,r10
 	mtspr	SPRN_SPRG_SCRATCH1,r11
 	mfcr	r10
@@ -381,6 +384,7 @@ i##n:								\
 
 /* Data access exception. */
 	. = 0x300
+	DO_KVM  0x300
 DataAccess:
 	EXCEPTION_PROLOG
 	mfspr	r10,SPRN_DSISR
@@ -397,6 +401,7 @@ DataAccess:
 
 /* Instruction access exception. */
 	. = 0x400
+	DO_KVM  0x400
 InstructionAccess:
 	EXCEPTION_PROLOG
 	andis.	r0,r9,0x4000		/* no pte found? */
@@ -413,6 +418,7 @@ InstructionAccess:
 
 /* Alignment exception */
 	. = 0x600
+	DO_KVM  0x600
 Alignment:
 	EXCEPTION_PROLOG
 	mfspr	r4,SPRN_DAR
@@ -427,6 +433,7 @@ Alignment:
 
 /* Floating-point unavailable */
 	. = 0x800
+	DO_KVM  0x800
 FPUnavailable:
 BEGIN_FTR_SECTION
 /*
@@ -450,6 +457,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE)
 
 /* System call */
 	. = 0xc00
+	DO_KVM  0xc00
 SystemCall:
 	EXCEPTION_PROLOG
 	EXC_XFER_EE_LITE(0xc00, DoSyscall)
@@ -467,9 +475,11 @@ SystemCall:
  * by executing an altivec instruction.
  */
 	. = 0xf00
+	DO_KVM  0xf00
 	b	PerformanceMonitor
 
 	. = 0xf20
+	DO_KVM  0xf20
 	b	AltiVecUnavailable
 
 /*
@@ -882,6 +892,10 @@ __secondary_start:
 	RFI
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
+#include "../kvm/book3s_rmhandlers.S"
+#endif
+
 /*
  * Those generic dummy functions are kept for CPUs not
  * included in CONFIG_6xx

arch/powerpc/kernel/head_64.S

@@ -37,7 +37,7 @@
 #include <asm/firmware.h>
 #include <asm/page_64.h>
 #include <asm/irqflags.h>
-#include <asm/kvm_book3s_64_asm.h>
+#include <asm/kvm_book3s_asm.h>
 
 /* The physical memory is layed out such that the secondary processor
  * spin code sits at 0x0000...0x00ff. On server, the vectors follow
@@ -169,7 +169,7 @@ exception_marker:
 /* KVM trampoline code needs to be close to the interrupt handlers */
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#include "../kvm/book3s_64_rmhandlers.S"
+#include "../kvm/book3s_rmhandlers.S"
 #endif
 
 _GLOBAL(generic_secondary_thread_init)

arch/powerpc/kernel/ppc_ksyms.c

@@ -101,6 +101,10 @@ EXPORT_SYMBOL(pci_dram_offset);
 EXPORT_SYMBOL(start_thread);
 EXPORT_SYMBOL(kernel_thread);
 
+#ifndef CONFIG_BOOKE
+EXPORT_SYMBOL_GPL(cvt_df);
+EXPORT_SYMBOL_GPL(cvt_fd);
+#endif
 EXPORT_SYMBOL(giveup_fpu);
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);

arch/powerpc/kvm/44x.c

@@ -147,7 +147,7 @@ static int __init kvmppc_44x_init(void)
 	if (r)
 		return r;
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), THIS_MODULE);
+	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE);
 }
 
 static void __exit kvmppc_44x_exit(void)

arch/powerpc/kvm/Kconfig

@@ -22,12 +22,34 @@ config KVM
 	select ANON_INODES
 	select KVM_MMIO
 
+config KVM_BOOK3S_HANDLER
+	bool
+
+config KVM_BOOK3S_32_HANDLER
+	bool
+	select KVM_BOOK3S_HANDLER
+
 config KVM_BOOK3S_64_HANDLER
 	bool
+	select KVM_BOOK3S_HANDLER
+
+config KVM_BOOK3S_32
+	tristate "KVM support for PowerPC book3s_32 processors"
+	depends on EXPERIMENTAL && PPC_BOOK3S_32 && !SMP && !PTE_64BIT
+	select KVM
+	select KVM_BOOK3S_32_HANDLER
+	---help---
+	  Support running unmodified book3s_32 guest kernels
+	  in virtual machines on book3s_32 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
 
 config KVM_BOOK3S_64
 	tristate "KVM support for PowerPC book3s_64 processors"
-	depends on EXPERIMENTAL && PPC64
+	depends on EXPERIMENTAL && PPC_BOOK3S_64
 	select KVM
 	select KVM_BOOK3S_64_HANDLER
 	---help---

arch/powerpc/kvm/Makefile

@@ -14,7 +14,7 @@ CFLAGS_emulate.o  := -I.
 
 common-objs-y += powerpc.o emulate.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
-obj-$(CONFIG_KVM_BOOK3S_64_HANDLER) += book3s_64_exports.o
+obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o
 
 AFLAGS_booke_interrupts.o := -I$(obj)
 
@@ -40,17 +40,31 @@ kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs)
 
 kvm-book3s_64-objs := \
 	$(common-objs-y) \
+	fpu.o \
+	book3s_paired_singles.o \
 	book3s.o \
-	book3s_64_emulate.o \
-	book3s_64_interrupts.o \
+	book3s_emulate.o \
+	book3s_interrupts.o \
 	book3s_64_mmu_host.o \
 	book3s_64_mmu.o \
 	book3s_32_mmu.o
 kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-objs)
 
+kvm-book3s_32-objs := \
+	$(common-objs-y) \
+	fpu.o \
+	book3s_paired_singles.o \
+	book3s.o \
+	book3s_emulate.o \
+	book3s_interrupts.o \
+	book3s_32_mmu_host.o \
+	book3s_32_mmu.o
+kvm-objs-$(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-$(CONFIG_KVM_BOOK3S_64) += kvm.o
+obj-$(CONFIG_KVM_BOOK3S_32) += kvm.o
 

arch/powerpc/kvm/book3s.c

@@ -16,6 +16,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -29,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
+#include <linux/highmem.h>
 
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
@@ -36,7 +38,15 @@
 /* #define EXIT_DEBUG_SIMPLE */
 /* #define DEBUG_EXT */
 
-static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
+static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
+			     ulong msr);
+
+/* Some compatibility defines */
+#ifdef CONFIG_PPC_BOOK3S_32
+#define MSR_USER32 MSR_USER
+#define MSR_USER64 MSR_USER
+#define HW_PAGE_SIZE PAGE_SIZE
+#endif
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exits",       VCPU_STAT(sum_exits) },
@@ -69,18 +79,26 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb));
-	memcpy(&get_paca()->shadow_vcpu, &to_book3s(vcpu)->shadow_vcpu,
+#ifdef CONFIG_PPC_BOOK3S_64
+	memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb));
+	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
 	       sizeof(get_paca()->shadow_vcpu));
-	get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max;
+	to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max;
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
+#endif
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb));
-	memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
+#ifdef CONFIG_PPC_BOOK3S_64
+	memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb));
+	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
 	       sizeof(get_paca()->shadow_vcpu));
-	to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max;
+	to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max;
+#endif
 
 	kvmppc_giveup_ext(vcpu, MSR_FP);
 	kvmppc_giveup_ext(vcpu, MSR_VEC);
@@ -131,18 +149,22 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 		}
 	}
 
-	if (((vcpu->arch.msr & (MSR_IR|MSR_DR)) != (old_msr & (MSR_IR|MSR_DR))) ||
-	    (vcpu->arch.msr & MSR_PR) != (old_msr & MSR_PR)) {
+	if ((vcpu->arch.msr & (MSR_PR|MSR_IR|MSR_DR)) !=
+		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
 		kvmppc_mmu_flush_segments(vcpu);
-		kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc);
+		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
 	}
+
+	/* Preload FPU if it's enabled */
+	if (vcpu->arch.msr & MSR_FP)
+		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 }
 
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
-	vcpu->arch.srr0 = vcpu->arch.pc;
+	vcpu->arch.srr0 = kvmppc_get_pc(vcpu);
 	vcpu->arch.srr1 = vcpu->arch.msr | flags;
-	vcpu->arch.pc = to_book3s(vcpu)->hior + vec;
+	kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec);
 	vcpu->arch.mmu.reset_msr(vcpu);
 }
 
@@ -218,6 +240,12 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
 }
 
+void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
+                                  struct kvm_interrupt *irq)
+{
+	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
+}
+
 int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 {
 	int deliver = 1;
@@ -302,7 +330,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 		printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions);
 #endif
 	priority = __ffs(*pending);
-	while (priority <= (sizeof(unsigned int) * 8)) {
+	while (priority < BOOK3S_IRQPRIO_MAX) {
 		if (kvmppc_book3s_irqprio_deliver(vcpu, priority) &&
 		    (priority != BOOK3S_IRQPRIO_DECREMENTER)) {
 			/* DEC interrupts get cleared by mtdec */
@@ -318,13 +346,18 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 
 void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 {
+	u32 host_pvr;
+
 	vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB;
 	vcpu->arch.pvr = pvr;
+#ifdef CONFIG_PPC_BOOK3S_64
 	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
 		kvmppc_mmu_book3s_64_init(vcpu);
 		to_book3s(vcpu)->hior = 0xfff00000;
 		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
-	} else {
+	} else
+#endif
+	{
 		kvmppc_mmu_book3s_32_init(vcpu);
 		to_book3s(vcpu)->hior = 0;
 		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
@@ -337,6 +370,32 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 	    !strcmp(cur_cpu_spec->platform, "ppc970"))
 		vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
 
+	/* Cell performs badly if MSR_FEx are set. So let's hope nobody
+	   really needs them in a VM on Cell and force disable them. */
+	if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be"))
+		to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1);
+
+#ifdef CONFIG_PPC_BOOK3S_32
+	/* 32 bit Book3S always has 32 byte dcbz */
+	vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
+#endif
+
+	/* On some CPUs we can execute paired single operations natively */
+	asm ( "mfpvr %0" : "=r"(host_pvr));
+	switch (host_pvr) {
+	case 0x00080200:	/* lonestar 2.0 */
+	case 0x00088202:	/* lonestar 2.2 */
+	case 0x70000100:	/* gekko 1.0 */
+	case 0x00080100:	/* gekko 2.0 */
+	case 0x00083203:	/* gekko 2.3a */
+	case 0x00083213:	/* gekko 2.3b */
+	case 0x00083204:	/* gekko 2.4 */
+	case 0x00083214:	/* gekko 2.4e (8SE) - retail HW2 */
+	case 0x00087200:	/* broadway */
+		vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS;
+		/* Enable HID2.PSE - in case we need it later */
+		mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29));
+	}
 }
 
 /* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
@@ -350,34 +409,29 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
  */
 static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
 {
-	bool touched = false;
-	hva_t hpage;
+	struct page *hpage;
+	u64 hpage_offset;
 	u32 *page;
 	int i;
 
-	hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
-	if (kvm_is_error_hva(hpage))
+	hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
+	if (is_error_page(hpage))
 		return;
 
-	hpage |= pte->raddr & ~PAGE_MASK;
-	hpage &= ~0xFFFULL;
-
-	page = vmalloc(HW_PAGE_SIZE);
-
-	if (copy_from_user(page, (void __user *)hpage, HW_PAGE_SIZE))
-		goto out;
+	hpage_offset = pte->raddr & ~PAGE_MASK;
+	hpage_offset &= ~0xFFFULL;
+	hpage_offset /= 4;
 
-	for (i=0; i < HW_PAGE_SIZE / 4; i++)
-		if ((page[i] & 0xff0007ff) == INS_DCBZ) {
-			page[i] &= 0xfffffff7; // reserved instruction, so we trap
-			touched = true;
-		}
+	get_page(hpage);
+	page = kmap_atomic(hpage, KM_USER0);
 
-	if (touched)
-		copy_to_user((void __user *)hpage, page, HW_PAGE_SIZE);
+	/* patch dcbz into reserved instruction, so we trap */
+	for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
+		if ((page[i] & 0xff0007ff) == INS_DCBZ)
+			page[i] &= 0xfffffff7;
 
-out:
-	vfree(page);
+	kunmap_atomic(page, KM_USER0);
+	put_page(hpage);
 }
 
 static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
@@ -391,15 +445,7 @@ static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
 	} else {
 		pte->eaddr = eaddr;
 		pte->raddr = eaddr & 0xffffffff;
-		pte->vpage = eaddr >> 12;
-		switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
-		case 0:
-			pte->vpage |= VSID_REAL;
-		case MSR_DR:
-			pte->vpage |= VSID_REAL_DR;
-		case MSR_IR:
-			pte->vpage |= VSID_REAL_IR;
-		}
+		pte->vpage = VSID_REAL | eaddr >> 12;
 		pte->may_read = true;
 		pte->may_write = true;
 		pte->may_execute = true;
@@ -434,55 +480,55 @@ static hva_t kvmppc_pte_to_hva(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte,
 	return kvmppc_bad_hva();
 }
 
-int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr)
+int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
+	      bool data)
 {
 	struct kvmppc_pte pte;
-	hva_t hva = eaddr;
 
 	vcpu->stat.st++;
 
-	if (kvmppc_xlate(vcpu, eaddr, false, &pte))
-		goto err;
+	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
+		return -ENOENT;
 
-	hva = kvmppc_pte_to_hva(vcpu, &pte, false);
-	if (kvm_is_error_hva(hva))
-		goto err;
+	*eaddr = pte.raddr;
 
-	if (copy_to_user((void __user *)hva, ptr, size)) {
-		printk(KERN_INFO "kvmppc_st at 0x%lx failed\n", hva);
-		goto err;
-	}
+	if (!pte.may_write)
+		return -EPERM;
 
-	return 0;
+	if (kvm_write_guest(vcpu->kvm, pte.raddr, ptr, size))
+		return EMULATE_DO_MMIO;
 
-err:
-	return -ENOENT;
+	return EMULATE_DONE;
 }
 
-int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr,
+int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 		      bool data)
 {
 	struct kvmppc_pte pte;
-	hva_t hva = eaddr;
+	hva_t hva = *eaddr;
 
 	vcpu->stat.ld++;
 
-	if (kvmppc_xlate(vcpu, eaddr, data, &pte))
-		goto err;
+	if (kvmppc_xlate(vcpu, *eaddr, data, &pte))
+		goto nopte;
+
+	*eaddr = pte.raddr;
 
 	hva = kvmppc_pte_to_hva(vcpu, &pte, true);
 	if (kvm_is_error_hva(hva))
-		goto err;
+		goto mmio;
 
 	if (copy_from_user(ptr, (void __user *)hva, size)) {
 		printk(KERN_INFO "kvmppc_ld at 0x%lx failed\n", hva);
-		goto err;
+		goto mmio;
 	}
 
-	return 0;
+	return EMULATE_DONE;
 
-err:
+nopte:
 	return -ENOENT;
+mmio:
+	return EMULATE_DO_MMIO;
 }
 
 static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
@@ -499,12 +545,11 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	int page_found = 0;
 	struct kvmppc_pte pte;
 	bool is_mmio = false;
+	bool dr = (vcpu->arch.msr & MSR_DR) ? true : false;
+	bool ir = (vcpu->arch.msr & MSR_IR) ? true : false;
+	u64 vsid;
 
-	if ( vec == BOOK3S_INTERRUPT_DATA_STORAGE ) {
-		relocated = (vcpu->arch.msr & MSR_DR);
-	} else {
-		relocated = (vcpu->arch.msr & MSR_IR);
-	}
+	relocated = data ? dr : ir;
 
 	/* Resolve real address if translation turned on */
 	if (relocated) {
@@ -516,14 +561,25 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.raddr = eaddr & 0xffffffff;
 		pte.eaddr = eaddr;
 		pte.vpage = eaddr >> 12;
-		switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
-		case 0:
-			pte.vpage |= VSID_REAL;
-		case MSR_DR:
-			pte.vpage |= VSID_REAL_DR;
-		case MSR_IR:
-			pte.vpage |= VSID_REAL_IR;
-		}
+	}
+
+	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	case 0:
+		pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12));
+		break;
+	case MSR_DR:
+	case MSR_IR:
+		vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
+
+		if ((vcpu->arch.msr & (MSR_DR|MSR_IR)) == MSR_DR)
+			pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12));
+		else
+			pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12));
+		pte.vpage |= vsid;
+
+		if (vsid == -1)
+			page_found = -EINVAL;
+		break;
 	}
 
 	if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
@@ -538,20 +594,20 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
-		vcpu->arch.dear = vcpu->arch.fault_dear;
-		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr;
-		vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL);
+		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+		to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr;
+		vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
-		vcpu->arch.dear = vcpu->arch.fault_dear;
-		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE;
+		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+		to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
 		to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT;
-		vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL);
+		vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
-		vcpu->arch.dear = vcpu->arch.fault_dear;
+		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
 		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
 	} else if (!is_mmio &&
 		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
@@ -583,11 +639,13 @@ static inline int get_fpr_index(int i)
 }
 
 /* Give up external provider (FPU, Altivec, VSX) */
-static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
+void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 {
 	struct thread_struct *t = &current->thread;
 	u64 *vcpu_fpr = vcpu->arch.fpr;
+#ifdef CONFIG_VSX
 	u64 *vcpu_vsx = vcpu->arch.vsr;
+#endif
 	u64 *thread_fpr = (u64*)t->fpr;
 	int i;
 
@@ -629,21 +687,65 @@ static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 	kvmppc_recalc_shadow_msr(vcpu);
 }
 
+static int kvmppc_read_inst(struct kvm_vcpu *vcpu)
+{
+	ulong srr0 = kvmppc_get_pc(vcpu);
+	u32 last_inst = kvmppc_get_last_inst(vcpu);
+	int ret;
+
+	ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
+	if (ret == -ENOENT) {
+		vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 33, 1);
+		vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 34, 36, 0);
+		vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0);
+		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
+		return EMULATE_AGAIN;
+	}
+
+	return EMULATE_DONE;
+}
+
+static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr)
+{
+
+	/* Need to do paired single emulation? */
+	if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE))
+		return EMULATE_DONE;
+
+	/* Read out the instruction */
+	if (kvmppc_read_inst(vcpu) == EMULATE_DONE)
+		/* Need to emulate */
+		return EMULATE_FAIL;
+
+	return EMULATE_AGAIN;
+}
+
 /* Handle external providers (FPU, Altivec, VSX) */
 static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 			     ulong msr)
 {
 	struct thread_struct *t = &current->thread;
 	u64 *vcpu_fpr = vcpu->arch.fpr;
+#ifdef CONFIG_VSX
 	u64 *vcpu_vsx = vcpu->arch.vsr;
+#endif
 	u64 *thread_fpr = (u64*)t->fpr;
 	int i;
 
+	/* When we have paired singles, we emulate in software */
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
+		return RESUME_GUEST;
+
 	if (!(vcpu->arch.msr & msr)) {
 		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 		return RESUME_GUEST;
 	}
 
+	/* We already own the ext */
+	if (vcpu->arch.guest_owned_ext & msr) {
+		return RESUME_GUEST;
+	}
+
 #ifdef DEBUG_EXT
 	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
 #endif
@@ -696,21 +798,33 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	run->ready_for_interrupt_injection = 1;
 #ifdef EXIT_DEBUG
 	printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n",
-		exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear,
-		kvmppc_get_dec(vcpu), vcpu->arch.msr);
+		exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu),
+		kvmppc_get_dec(vcpu), to_svcpu(vcpu)->shadow_srr1);
 #elif defined (EXIT_DEBUG_SIMPLE)
 	if ((exit_nr != 0x900) && (exit_nr != 0x500))
 		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n",
-			exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear,
+			exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu),
 			vcpu->arch.msr);
 #endif
 	kvm_resched(vcpu);
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
 		vcpu->stat.pf_instruc++;
+
+#ifdef CONFIG_PPC_BOOK3S_32
+		/* We set segments as unused segments when invalidating them. So
+		 * treat the respective fault as segment fault. */
+		if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]
+		    == SR_INVALID) {
+			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+			r = RESUME_GUEST;
+			break;
+		}
+#endif
+
 		/* only care about PTEG not found errors, but leave NX alone */
-		if (vcpu->arch.shadow_srr1 & 0x40000000) {
-			r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr);
+		if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) {
+			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
 			vcpu->stat.sp_instruc++;
 		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
 			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
@@ -719,37 +833,52 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 *     so we can't use the NX bit inside the guest. Let's cross our fingers,
 			 *     that no guest that needs the dcbz hack does NX.
 			 */
-			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
+			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
+			r = RESUME_GUEST;
 		} else {
-			vcpu->arch.msr |= vcpu->arch.shadow_srr1 & 0x58000000;
+			vcpu->arch.msr |= to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
+			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
 		}
 		break;
 	case BOOK3S_INTERRUPT_DATA_STORAGE:
+	{
+		ulong dar = kvmppc_get_fault_dar(vcpu);
 		vcpu->stat.pf_storage++;
+
+#ifdef CONFIG_PPC_BOOK3S_32
+		/* We set segments as unused segments when invalidating them. So
+		 * treat the respective fault as segment fault. */
+		if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) {
+			kvmppc_mmu_map_segment(vcpu, dar);
+			r = RESUME_GUEST;
+			break;
+		}
+#endif
+
 		/* The only case we need to handle is missing shadow PTEs */
-		if (vcpu->arch.fault_dsisr & DSISR_NOHPTE) {
-			r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.fault_dear, exit_nr);
+		if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
+			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
 		} else {
-			vcpu->arch.dear = vcpu->arch.fault_dear;
-			to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr;
+			vcpu->arch.dear = dar;
+			to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFULL);
+			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFUL);
 			r = RESUME_GUEST;
 		}
 		break;
+	}
 	case BOOK3S_INTERRUPT_DATA_SEGMENT:
-		if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.fault_dear) < 0) {
-			vcpu->arch.dear = vcpu->arch.fault_dear;
+		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) {
+			vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
 			kvmppc_book3s_queue_irqprio(vcpu,
 				BOOK3S_INTERRUPT_DATA_SEGMENT);
 		}
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_INST_SEGMENT:
-		if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc) < 0) {
+		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) {
 			kvmppc_book3s_queue_irqprio(vcpu,
 				BOOK3S_INTERRUPT_INST_SEGMENT);
 		}
@@ -764,18 +893,22 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		vcpu->stat.ext_intr_exits++;
 		r = RESUME_GUEST;
 		break;
+	case BOOK3S_INTERRUPT_PERFMON:
+		r = RESUME_GUEST;
+		break;
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
 		enum emulation_result er;
 		ulong flags;
 
-		flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
+program_interrupt:
+		flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
 
 		if (vcpu->arch.msr & MSR_PR) {
 #ifdef EXIT_DEBUG
-			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", vcpu->arch.pc, vcpu->arch.last_inst);
+			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
 #endif
-			if ((vcpu->arch.last_inst & 0xff0007ff) !=
+			if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) !=
 			    (INS_DCBZ & 0xfffffff7)) {
 				kvmppc_core_queue_program(vcpu, flags);
 				r = RESUME_GUEST;
@@ -789,33 +922,80 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		case EMULATE_DONE:
 			r = RESUME_GUEST_NV;
 			break;
+		case EMULATE_AGAIN:
+			r = RESUME_GUEST;
+			break;
 		case EMULATE_FAIL:
 			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
-			       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+			       __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
 			kvmppc_core_queue_program(vcpu, flags);
 			r = RESUME_GUEST;
 			break;
+		case EMULATE_DO_MMIO:
+			run->exit_reason = KVM_EXIT_MMIO;
+			r = RESUME_HOST_NV;
+			break;
 		default:
 			BUG();
 		}
 		break;
 	}
 	case BOOK3S_INTERRUPT_SYSCALL:
-#ifdef EXIT_DEBUG
-		printk(KERN_INFO "Syscall Nr %d\n", (int)kvmppc_get_gpr(vcpu, 0));
-#endif
-		vcpu->stat.syscall_exits++;
-		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-		r = RESUME_GUEST;
+		// XXX make user settable
+		if (vcpu->arch.osi_enabled &&
+		    (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) &&
+		    (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) {
+			u64 *gprs = run->osi.gprs;
+			int i;
+
+			run->exit_reason = KVM_EXIT_OSI;
+			for (i = 0; i < 32; i++)
+				gprs[i] = kvmppc_get_gpr(vcpu, i);
+			vcpu->arch.osi_needed = 1;
+			r = RESUME_HOST_NV;
+
+		} else {
+			vcpu->stat.syscall_exits++;
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			r = RESUME_GUEST;
+		}
 		break;
 	case BOOK3S_INTERRUPT_FP_UNAVAIL:
-		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_FP);
-		break;
 	case BOOK3S_INTERRUPT_ALTIVEC:
-		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VEC);
-		break;
 	case BOOK3S_INTERRUPT_VSX:
-		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VSX);
+	{
+		int ext_msr = 0;
+
+		switch (exit_nr) {
+		case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP;  break;
+		case BOOK3S_INTERRUPT_ALTIVEC:    ext_msr = MSR_VEC; break;
+		case BOOK3S_INTERRUPT_VSX:        ext_msr = MSR_VSX; break;
+		}
+
+		switch (kvmppc_check_ext(vcpu, exit_nr)) {
+		case EMULATE_DONE:
+			/* everything ok - let's enable the ext */
+			r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr);
+			break;
+		case EMULATE_FAIL:
+			/* we need to emulate this instruction */
+			goto program_interrupt;
+			break;
+		default:
+			/* nothing to worry about - go again */
+			break;
+		}
+		break;
+	}
+	case BOOK3S_INTERRUPT_ALIGNMENT:
+		if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
+			to_book3s(vcpu)->dsisr = kvmppc_alignment_dsisr(vcpu,
+				kvmppc_get_last_inst(vcpu));
+			vcpu->arch.dear = kvmppc_alignment_dar(vcpu,
+				kvmppc_get_last_inst(vcpu));
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+		}
+		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_MACHINE_CHECK:
 	case BOOK3S_INTERRUPT_TRACE:
@@ -825,7 +1005,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	default:
 		/* Ugh - bork here! What did we get? */
 		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
-			exit_nr, vcpu->arch.pc, vcpu->arch.shadow_srr1);
+			exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1);
 		r = RESUME_HOST;
 		BUG();
 		break;
@@ -852,7 +1032,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 
 #ifdef EXIT_DEBUG
-	printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, vcpu->arch.pc, r);
+	printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, kvmppc_get_pc(vcpu), r);
 #endif
 
 	return r;
@@ -867,10 +1047,12 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	regs->pc = vcpu->arch.pc;
+	vcpu_load(vcpu);
+
+	regs->pc = kvmppc_get_pc(vcpu);
 	regs->cr = kvmppc_get_cr(vcpu);
-	regs->ctr = vcpu->arch.ctr;
-	regs->lr = vcpu->arch.lr;
+	regs->ctr = kvmppc_get_ctr(vcpu);
+	regs->lr = kvmppc_get_lr(vcpu);
 	regs->xer = kvmppc_get_xer(vcpu);
 	regs->msr = vcpu->arch.msr;
 	regs->srr0 = vcpu->arch.srr0;
@@ -887,6 +1069,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
 
+	vcpu_put(vcpu);
+
 	return 0;
 }
 
@@ -894,10 +1078,12 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	vcpu->arch.pc = regs->pc;
+	vcpu_load(vcpu);
+
+	kvmppc_set_pc(vcpu, regs->pc);
 	kvmppc_set_cr(vcpu, regs->cr);
-	vcpu->arch.ctr = regs->ctr;
-	vcpu->arch.lr = regs->lr;
+	kvmppc_set_ctr(vcpu, regs->ctr);
+	kvmppc_set_lr(vcpu, regs->lr);
 	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
 	vcpu->arch.srr0 = regs->srr0;
@@ -913,6 +1099,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
 
+	vcpu_put(vcpu);
+
 	return 0;
 }
 
@@ -922,6 +1110,8 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
 
+	vcpu_load(vcpu);
+
 	sregs->pvr = vcpu->arch.pvr;
 
 	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
@@ -940,6 +1130,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 			sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
 		}
 	}
+
+	vcpu_put(vcpu);
+
 	return 0;
 }
 
@@ -949,6 +1142,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
 
+	vcpu_load(vcpu);
+
 	kvmppc_set_pvr(vcpu, sregs->pvr);
 
 	vcpu3s->sdr1 = sregs->u.s.sdr1;
@@ -975,6 +1170,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	/* Flush the MMU after messing with the segments */
 	kvmppc_mmu_pte_flush(vcpu, 0, 0);
+
+	vcpu_put(vcpu);
+
 	return 0;
 }
 
@@ -1042,24 +1240,33 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s;
 	struct kvm_vcpu *vcpu;
-	int err;
+	int err = -ENOMEM;
 
-	vcpu_book3s = (struct kvmppc_vcpu_book3s *)__get_free_pages( GFP_KERNEL | __GFP_ZERO,
-			get_order(sizeof(struct kvmppc_vcpu_book3s)));
-	if (!vcpu_book3s) {
-		err = -ENOMEM;
+	vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s));
+	if (!vcpu_book3s)
 		goto out;
-	}
+
+	memset(vcpu_book3s, 0, sizeof(struct kvmppc_vcpu_book3s));
+
+	vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *)
+		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
+	if (!vcpu_book3s->shadow_vcpu)
+		goto free_vcpu;
 
 	vcpu = &vcpu_book3s->vcpu;
 	err = kvm_vcpu_init(vcpu, kvm, id);
 	if (err)
-		goto free_vcpu;
+		goto free_shadow_vcpu;
 
 	vcpu->arch.host_retip = kvm_return_point;
 	vcpu->arch.host_msr = mfmsr();
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* default to book3s_64 (970fx) */
 	vcpu->arch.pvr = 0x3C0301;
+#else
+	/* default to book3s_32 (750) */
+	vcpu->arch.pvr = 0x84202;
+#endif
 	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
 	vcpu_book3s->slb_nr = 64;
 
@@ -1067,23 +1274,24 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
 	vcpu->arch.trampoline_enter = kvmppc_trampoline_enter;
 	vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
+#ifdef CONFIG_PPC_BOOK3S_64
 	vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall;
+#else
+	vcpu->arch.rmcall = (ulong)kvmppc_rmcall;
+#endif
 
 	vcpu->arch.shadow_msr = MSR_USER64;
 
-	err = __init_new_context();
+	err = kvmppc_mmu_init(vcpu);
 	if (err < 0)
-		goto free_vcpu;
-	vcpu_book3s->context_id = err;
-
-	vcpu_book3s->vsid_max = ((vcpu_book3s->context_id + 1) << USER_ESID_BITS) - 1;
-	vcpu_book3s->vsid_first = vcpu_book3s->context_id << USER_ESID_BITS;
-	vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+		goto free_shadow_vcpu;
 
 	return vcpu;
 
+free_shadow_vcpu:
+	kfree(vcpu_book3s->shadow_vcpu);
 free_vcpu:
-	free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s)));
+	vfree(vcpu_book3s);
 out:
 	return ERR_PTR(err);
 }
@@ -1092,9 +1300,9 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
-	__destroy_context(vcpu_book3s->context_id);
 	kvm_vcpu_uninit(vcpu);
-	free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s)));
+	kfree(vcpu_book3s->shadow_vcpu);
+	vfree(vcpu_book3s);
 }
 
 extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
@@ -1102,8 +1310,12 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
 	struct thread_struct ext_bkp;
+#ifdef CONFIG_ALTIVEC
 	bool save_vec = current->thread.used_vr;
+#endif
+#ifdef CONFIG_VSX
 	bool save_vsx = current->thread.used_vsr;
+#endif
 	ulong ext_msr;
 
 	/* No need to go into the guest when all we do is going out */
@@ -1144,6 +1356,10 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* XXX we get called with irq disabled - change that! */
 	local_irq_enable();
 
+	/* Preload FPU if it's enabled */
+	if (vcpu->arch.msr & MSR_FP)
+		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
+
 	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);
 
 	local_irq_disable();
@@ -1179,7 +1395,8 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 static int kvmppc_book3s_init(void)
 {
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), THIS_MODULE);
+	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
+			THIS_MODULE);
 }
 
 static void kvmppc_book3s_exit(void)

arch/powerpc/kvm/book3s_32_mmu.c

@@ -37,7 +37,7 @@
 #define dprintk(X...) do { } while(0)
 #endif
 
-#ifdef DEBUG_PTE
+#ifdef DEBUG_MMU_PTE
 #define dprintk_pte(X...) printk(KERN_INFO X)
 #else
 #define dprintk_pte(X...) do { } while(0)
@@ -45,6 +45,9 @@
 
 #define PTEG_FLAG_ACCESSED	0x00000100
 #define PTEG_FLAG_DIRTY		0x00000080
+#ifndef SID_SHIFT
+#define SID_SHIFT		28
+#endif
 
 static inline bool check_debug_ip(struct kvm_vcpu *vcpu)
 {
@@ -57,6 +60,8 @@ static inline bool check_debug_ip(struct kvm_vcpu *vcpu)
 
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  struct kvmppc_pte *pte, bool data);
+static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
+					     u64 *vsid);
 
 static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr)
 {
@@ -66,13 +71,14 @@ static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t e
 static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 					 bool data)
 {
-	struct kvmppc_sr *sre = find_sr(to_book3s(vcpu), eaddr);
+	u64 vsid;
 	struct kvmppc_pte pte;
 
 	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data))
 		return pte.vpage;
 
-	return (((u64)eaddr >> 12) & 0xffff) | (((u64)sre->vsid) << 16);
+	kvmppc_mmu_book3s_32_esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
+	return (((u64)eaddr >> 12) & 0xffff) | (vsid << 16);
 }
 
 static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu)
@@ -142,8 +148,13 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 				    bat->bepi_mask);
 		}
 		if ((eaddr & bat->bepi_mask) == bat->bepi) {
+			u64 vsid;
+			kvmppc_mmu_book3s_32_esid_to_vsid(vcpu,
+				eaddr >> SID_SHIFT, &vsid);
+			vsid <<= 16;
+			pte->vpage = (((u64)eaddr >> 12) & 0xffff) | vsid;
+
 			pte->raddr = bat->brpn | (eaddr & ~bat->bepi_mask);
-			pte->vpage = (eaddr >> 12) | VSID_BAT;
 			pte->may_read = bat->pp;
 			pte->may_write = bat->pp > 1;
 			pte->may_execute = true;
@@ -172,7 +183,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 	struct kvmppc_sr *sre;
 	hva_t ptegp;
 	u32 pteg[16];
-	u64 ptem = 0;
+	u32 ptem = 0;
 	int i;
 	int found = 0;
 
@@ -302,6 +313,7 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
 	/* And then put in the new SR */
 	sre->raw = value;
 	sre->vsid = (value & 0x0fffffff);
+	sre->valid = (value & 0x80000000) ? false : true;
 	sre->Ks = (value & 0x40000000) ? true : false;
 	sre->Kp = (value & 0x20000000) ? true : false;
 	sre->nx = (value & 0x10000000) ? true : false;
@@ -312,36 +324,48 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
 
 static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large)
 {
-	kvmppc_mmu_pte_flush(vcpu, ea, ~0xFFFULL);
+	kvmppc_mmu_pte_flush(vcpu, ea, 0x0FFFF000);
 }
 
-static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid,
+static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid)
 {
+	ulong ea = esid << SID_SHIFT;
+	struct kvmppc_sr *sr;
+	u64 gvsid = esid;
+
+	if (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+		sr = find_sr(to_book3s(vcpu), ea);
+		if (sr->valid)
+			gvsid = sr->vsid;
+	}
+
 	/* In case we only have one of MSR_IR or MSR_DR set, let's put
 	   that in the real-mode context (and hope RM doesn't access
 	   high memory) */
 	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
 	case 0:
-		*vsid = (VSID_REAL >> 16) | esid;
+		*vsid = VSID_REAL | esid;
 		break;
 	case MSR_IR:
-		*vsid = (VSID_REAL_IR >> 16) | esid;
+		*vsid = VSID_REAL_IR | gvsid;
 		break;
 	case MSR_DR:
-		*vsid = (VSID_REAL_DR >> 16) | esid;
+		*vsid = VSID_REAL_DR | gvsid;
 		break;
 	case MSR_DR|MSR_IR:
-	{
-		ulong ea;
-		ea = esid << SID_SHIFT;
-		*vsid = find_sr(to_book3s(vcpu), ea)->vsid;
+		if (!sr->valid)
+			return -1;
+
+		*vsid = sr->vsid;
 		break;
-	}
 	default:
 		BUG();
 	}
 
+	if (vcpu->arch.msr & MSR_PR)
+		*vsid |= VSID_PR;
+
 	return 0;
 }
 

arch/powerpc/kvm/book3s_32_mmu_host.c

@@ -0,0 +1,483 @@
+/*
+ * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
+ *
+ * Authors:
+ *     Alexander Graf <agraf@suse.de>
+ *
+ * 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.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu-hash32.h>
+#include <asm/machdep.h>
+#include <asm/mmu_context.h>
+#include <asm/hw_irq.h>
+
+/* #define DEBUG_MMU */
+/* #define DEBUG_SR */
+
+#ifdef DEBUG_MMU
+#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__)
+#else
+#define dprintk_mmu(a, ...) do { } while(0)
+#endif
+
+#ifdef DEBUG_SR
+#define dprintk_sr(a, ...) printk(KERN_INFO a, __VA_ARGS__)
+#else
+#define dprintk_sr(a, ...) do { } while(0)
+#endif
+
+#if PAGE_SHIFT != 12
+#error Unknown page size
+#endif
+
+#ifdef CONFIG_SMP
+#error XXX need to grab mmu_hash_lock
+#endif
+
+#ifdef CONFIG_PTE_64BIT
+#error Only 32 bit pages are supported for now
+#endif
+
+static ulong htab;
+static u32 htabmask;
+
+static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
+{
+	volatile u32 *pteg;
+
+	dprintk_mmu("KVM: Flushing SPTE: 0x%llx (0x%llx) -> 0x%llx\n",
+		    pte->pte.eaddr, pte->pte.vpage, pte->host_va);
+
+	pteg = (u32*)pte->slot;
+
+	pteg[0] = 0;
+	asm volatile ("sync");
+	asm volatile ("tlbie %0" : : "r" (pte->pte.eaddr) : "memory");
+	asm volatile ("sync");
+	asm volatile ("tlbsync");
+
+	pte->host_va = 0;
+
+	if (pte->pte.may_write)
+		kvm_release_pfn_dirty(pte->pfn);
+	else
+		kvm_release_pfn_clean(pte->pfn);
+}
+
+void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
+{
+	int i;
+
+	dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%x & 0x%x\n",
+		    vcpu->arch.hpte_cache_offset, guest_ea, ea_mask);
+	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
+
+	guest_ea &= ea_mask;
+	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if ((pte->pte.eaddr & ea_mask) == guest_ea) {
+			invalidate_pte(vcpu, pte);
+		}
+	}
+
+	/* Doing a complete flush -> start from scratch */
+	if (!ea_mask)
+		vcpu->arch.hpte_cache_offset = 0;
+}
+
+void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
+{
+	int i;
+
+	dprintk_mmu("KVM: Flushing %d Shadow vPTEs: 0x%llx & 0x%llx\n",
+		    vcpu->arch.hpte_cache_offset, guest_vp, vp_mask);
+	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
+
+	guest_vp &= vp_mask;
+	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if ((pte->pte.vpage & vp_mask) == guest_vp) {
+			invalidate_pte(vcpu, pte);
+		}
+	}
+}
+
+void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
+{
+	int i;
+
+	dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n",
+		    vcpu->arch.hpte_cache_offset, pa_start, pa_end);
+	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
+
+	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if ((pte->pte.raddr >= pa_start) &&
+		    (pte->pte.raddr < pa_end)) {
+			invalidate_pte(vcpu, pte);
+		}
+	}
+}
+
+struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data)
+{
+	int i;
+	u64 guest_vp;
+
+	guest_vp = vcpu->arch.mmu.ea_to_vp(vcpu, ea, false);
+	for (i=0; i<vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if (pte->pte.vpage == guest_vp)
+			return &pte->pte;
+	}
+
+	return NULL;
+}
+
+static int kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.hpte_cache_offset == HPTEG_CACHE_NUM)
+		kvmppc_mmu_pte_flush(vcpu, 0, 0);
+
+	return vcpu->arch.hpte_cache_offset++;
+}
+
+/* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using
+ * a hash, so we don't waste cycles on looping */
+static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
+{
+	return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
+}
+
+
+static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
+{
+	struct kvmppc_sid_map *map;
+	u16 sid_map_mask;
+
+	if (vcpu->arch.msr & MSR_PR)
+		gvsid |= VSID_PR;
+
+	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
+	map = &to_book3s(vcpu)->sid_map[sid_map_mask];
+	if (map->guest_vsid == gvsid) {
+		dprintk_sr("SR: Searching 0x%llx -> 0x%llx\n",
+			    gvsid, map->host_vsid);
+		return map;
+	}
+
+	map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask];
+	if (map->guest_vsid == gvsid) {
+		dprintk_sr("SR: Searching 0x%llx -> 0x%llx\n",
+			    gvsid, map->host_vsid);
+		return map;
+	}
+
+	dprintk_sr("SR: Searching 0x%llx -> not found\n", gvsid);
+	return NULL;
+}
+
+static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr,
+				bool primary)
+{
+	u32 page, hash;
+	ulong pteg = htab;
+
+	page = (eaddr & ~ESID_MASK) >> 12;
+
+	hash = ((vsid ^ page) << 6);
+	if (!primary)
+		hash = ~hash;
+
+	hash &= htabmask;
+
+	pteg |= hash;
+
+	dprintk_mmu("htab: %lx | hash: %x | htabmask: %x | pteg: %lx\n",
+		htab, hash, htabmask, pteg);
+
+	return (u32*)pteg;
+}
+
+extern char etext[];
+
+int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
+{
+	pfn_t hpaddr;
+	u64 va;
+	u64 vsid;
+	struct kvmppc_sid_map *map;
+	volatile u32 *pteg;
+	u32 eaddr = orig_pte->eaddr;
+	u32 pteg0, pteg1;
+	register int rr = 0;
+	bool primary = false;
+	bool evict = false;
+	int hpte_id;
+	struct hpte_cache *pte;
+
+	/* Get host physical address for gpa */
+	hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+	if (kvm_is_error_hva(hpaddr)) {
+		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
+				 orig_pte->eaddr);
+		return -EINVAL;
+	}
+	hpaddr <<= PAGE_SHIFT;
+
+	/* and write the mapping ea -> hpa into the pt */
+	vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
+	map = find_sid_vsid(vcpu, vsid);
+	if (!map) {
+		kvmppc_mmu_map_segment(vcpu, eaddr);
+		map = find_sid_vsid(vcpu, vsid);
+	}
+	BUG_ON(!map);
+
+	vsid = map->host_vsid;
+	va = (vsid << SID_SHIFT) | (eaddr & ~ESID_MASK);
+
+next_pteg:
+	if (rr == 16) {
+		primary = !primary;
+		evict = true;
+		rr = 0;
+	}
+
+	pteg = kvmppc_mmu_get_pteg(vcpu, vsid, eaddr, primary);
+
+	/* not evicting yet */
+	if (!evict && (pteg[rr] & PTE_V)) {
+		rr += 2;
+		goto next_pteg;
+	}
+
+	dprintk_mmu("KVM: old PTEG: %p (%d)\n", pteg, rr);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[0], pteg[1]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[2], pteg[3]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[4], pteg[5]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[6], pteg[7]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[8], pteg[9]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[10], pteg[11]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[12], pteg[13]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[14], pteg[15]);
+
+	pteg0 = ((eaddr & 0x0fffffff) >> 22) | (vsid << 7) | PTE_V |
+		(primary ? 0 : PTE_SEC);
+	pteg1 = hpaddr | PTE_M | PTE_R | PTE_C;
+
+	if (orig_pte->may_write) {
+		pteg1 |= PP_RWRW;
+		mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+	} else {
+		pteg1 |= PP_RWRX;
+	}
+
+	local_irq_disable();
+
+	if (pteg[rr]) {
+		pteg[rr] = 0;
+		asm volatile ("sync");
+	}
+	pteg[rr + 1] = pteg1;
+	pteg[rr] = pteg0;
+	asm volatile ("sync");
+
+	local_irq_enable();
+
+	dprintk_mmu("KVM: new PTEG: %p\n", pteg);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[0], pteg[1]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[2], pteg[3]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[4], pteg[5]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[6], pteg[7]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[8], pteg[9]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[10], pteg[11]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[12], pteg[13]);
+	dprintk_mmu("KVM:   %08x - %08x\n", pteg[14], pteg[15]);
+
+
+	/* Now tell our Shadow PTE code about the new page */
+
+	hpte_id = kvmppc_mmu_hpte_cache_next(vcpu);
+	pte = &vcpu->arch.hpte_cache[hpte_id];
+
+	dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%llx (0x%llx) -> %lx\n",
+		    orig_pte->may_write ? 'w' : '-',
+		    orig_pte->may_execute ? 'x' : '-',
+		    orig_pte->eaddr, (ulong)pteg, va,
+		    orig_pte->vpage, hpaddr);
+
+	pte->slot = (ulong)&pteg[rr];
+	pte->host_va = va;
+	pte->pte = *orig_pte;
+	pte->pfn = hpaddr >> PAGE_SHIFT;
+
+	return 0;
+}
+
+static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
+{
+	struct kvmppc_sid_map *map;
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	u16 sid_map_mask;
+	static int backwards_map = 0;
+
+	if (vcpu->arch.msr & MSR_PR)
+		gvsid |= VSID_PR;
+
+	/* We might get collisions that trap in preceding order, so let's
+	   map them differently */
+
+	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
+	if (backwards_map)
+		sid_map_mask = SID_MAP_MASK - sid_map_mask;
+
+	map = &to_book3s(vcpu)->sid_map[sid_map_mask];
+
+	/* Make sure we're taking the other map next time */
+	backwards_map = !backwards_map;
+
+	/* Uh-oh ... out of mappings. Let's flush! */
+	if (vcpu_book3s->vsid_next >= vcpu_book3s->vsid_max) {
+		vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+		memset(vcpu_book3s->sid_map, 0,
+		       sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
+		kvmppc_mmu_pte_flush(vcpu, 0, 0);
+		kvmppc_mmu_flush_segments(vcpu);
+	}
+	map->host_vsid = vcpu_book3s->vsid_next;
+
+	/* Would have to be 111 to be completely aligned with the rest of
+	   Linux, but that is just way too little space! */
+	vcpu_book3s->vsid_next+=1;
+
+	map->guest_vsid = gvsid;
+	map->valid = true;
+
+	return map;
+}
+
+int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
+{
+	u32 esid = eaddr >> SID_SHIFT;
+	u64 gvsid;
+	u32 sr;
+	struct kvmppc_sid_map *map;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+
+	if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
+		/* Invalidate an entry */
+		svcpu->sr[esid] = SR_INVALID;
+		return -ENOENT;
+	}
+
+	map = find_sid_vsid(vcpu, gvsid);
+	if (!map)
+		map = create_sid_map(vcpu, gvsid);
+
+	map->guest_esid = esid;
+	sr = map->host_vsid | SR_KP;
+	svcpu->sr[esid] = sr;
+
+	dprintk_sr("MMU: mtsr %d, 0x%x\n", esid, sr);
+
+	return 0;
+}
+
+void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+
+	dprintk_sr("MMU: flushing all segments (%d)\n", ARRAY_SIZE(svcpu->sr));
+	for (i = 0; i < ARRAY_SIZE(svcpu->sr); i++)
+		svcpu->sr[i] = SR_INVALID;
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvmppc_mmu_pte_flush(vcpu, 0, 0);
+	preempt_disable();
+	__destroy_context(to_book3s(vcpu)->context_id);
+	preempt_enable();
+}
+
+/* From mm/mmu_context_hash32.c */
+#define CTX_TO_VSID(ctx) (((ctx) * (897 * 16)) & 0xffffff)
+
+int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	int err;
+	ulong sdr1;
+
+	err = __init_new_context();
+	if (err < 0)
+		return -1;
+	vcpu3s->context_id = err;
+
+	vcpu3s->vsid_max = CTX_TO_VSID(vcpu3s->context_id + 1) - 1;
+	vcpu3s->vsid_first = CTX_TO_VSID(vcpu3s->context_id);
+
+#if 0 /* XXX still doesn't guarantee uniqueness */
+	/* We could collide with the Linux vsid space because the vsid
+	 * wraps around at 24 bits. We're safe if we do our own space
+	 * though, so let's always set the highest bit. */
+
+	vcpu3s->vsid_max |= 0x00800000;
+	vcpu3s->vsid_first |= 0x00800000;
+#endif
+	BUG_ON(vcpu3s->vsid_max < vcpu3s->vsid_first);
+
+	vcpu3s->vsid_next = vcpu3s->vsid_first;
+
+	/* Remember where the HTAB is */
+	asm ( "mfsdr1 %0" : "=r"(sdr1) );
+	htabmask = ((sdr1 & 0x1FF) << 16) | 0xFFC0;
+	htab = (ulong)__va(sdr1 & 0xffff0000);
+
+	return 0;
+}

arch/powerpc/kvm/book3s_32_sr.S

@@ -0,0 +1,143 @@
+/*
+ * 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 SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+/******************************************************************************
+ *                                                                            *
+ *                               Entry code                                   *
+ *                                                                            *
+ *****************************************************************************/
+
+.macro LOAD_GUEST_SEGMENTS
+
+	/* Required state:
+	 *
+	 * MSR = ~IR|DR
+	 * R1 = host R1
+	 * R2 = host R2
+	 * R3 = shadow vcpu
+	 * all other volatile GPRS = free
+	 * SVCPU[CR]  = guest CR
+	 * SVCPU[XER] = guest XER
+	 * SVCPU[CTR] = guest CTR
+	 * SVCPU[LR]  = guest LR
+	 */
+
+#define XCHG_SR(n)	lwz	r9, (SVCPU_SR+(n*4))(r3);  \
+			mtsr	n, r9
+
+	XCHG_SR(0)
+	XCHG_SR(1)
+	XCHG_SR(2)
+	XCHG_SR(3)
+	XCHG_SR(4)
+	XCHG_SR(5)
+	XCHG_SR(6)
+	XCHG_SR(7)
+	XCHG_SR(8)
+	XCHG_SR(9)
+	XCHG_SR(10)
+	XCHG_SR(11)
+	XCHG_SR(12)
+	XCHG_SR(13)
+	XCHG_SR(14)
+	XCHG_SR(15)
+
+	/* Clear BATs. */
+
+#define KVM_KILL_BAT(n, reg)		\
+        mtspr   SPRN_IBAT##n##U,reg;	\
+        mtspr   SPRN_IBAT##n##L,reg;	\
+        mtspr   SPRN_DBAT##n##U,reg;	\
+        mtspr   SPRN_DBAT##n##L,reg;	\
+
+        li	r9, 0
+	KVM_KILL_BAT(0, r9)
+	KVM_KILL_BAT(1, r9)
+	KVM_KILL_BAT(2, r9)
+	KVM_KILL_BAT(3, r9)
+
+.endm
+
+/******************************************************************************
+ *                                                                            *
+ *                               Exit code                                    *
+ *                                                                            *
+ *****************************************************************************/
+
+.macro LOAD_HOST_SEGMENTS
+
+	/* Register usage at this point:
+	 *
+	 * R1         = host R1
+	 * R2         = host R2
+	 * R12        = exit handler id
+	 * R13        = shadow vcpu - SHADOW_VCPU_OFF
+	 * SVCPU.*    = guest *
+	 * SVCPU[CR]  = guest CR
+	 * SVCPU[XER] = guest XER
+	 * SVCPU[CTR] = guest CTR
+	 * SVCPU[LR]  = guest LR
+	 *
+	 */
+
+	/* Restore BATs */
+
+	/* We only overwrite the upper part, so we only restoree
+	   the upper part. */
+#define KVM_LOAD_BAT(n, reg, RA, RB)	\
+	lwz	RA,(n*16)+0(reg);	\
+	lwz	RB,(n*16)+4(reg);	\
+	mtspr	SPRN_IBAT##n##U,RA;	\
+	mtspr	SPRN_IBAT##n##L,RB;	\
+	lwz	RA,(n*16)+8(reg);	\
+	lwz	RB,(n*16)+12(reg);	\
+	mtspr	SPRN_DBAT##n##U,RA;	\
+	mtspr	SPRN_DBAT##n##L,RB;	\
+
+	lis     r9, BATS@ha
+	addi    r9, r9, BATS@l
+	tophys(r9, r9)
+	KVM_LOAD_BAT(0, r9, r10, r11)
+	KVM_LOAD_BAT(1, r9, r10, r11)
+	KVM_LOAD_BAT(2, r9, r10, r11)
+	KVM_LOAD_BAT(3, r9, r10, r11)
+
+	/* Restore Segment Registers */
+
+	/* 0xc - 0xf */
+
+        li      r0, 4
+        mtctr   r0
+	LOAD_REG_IMMEDIATE(r3, 0x20000000 | (0x111 * 0xc))
+        lis     r4, 0xc000
+3:      mtsrin  r3, r4
+        addi    r3, r3, 0x111     /* increment VSID */
+        addis   r4, r4, 0x1000    /* address of next segment */
+        bdnz    3b
+
+	/* 0x0 - 0xb */
+
+	/* 'current->mm' needs to be in r4 */
+	tophys(r4, r2)
+	lwz	r4, MM(r4)
+	tophys(r4, r4)
+	/* This only clobbers r0, r3, r4 and r5 */
+	bl	switch_mmu_context
+
+.endm

arch/powerpc/kvm/book3s_64_mmu.c

@@ -232,7 +232,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 			}
 
 			dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
-				"-> 0x%llx\n",
+				"-> 0x%lx\n",
 				eaddr, avpn, gpte->vpage, gpte->raddr);
 			found = true;
 			break;
@@ -383,7 +383,7 @@ static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu)
 
 	if (vcpu->arch.msr & MSR_IR) {
 		kvmppc_mmu_flush_segments(vcpu);
-		kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc);
+		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
 	}
 }
 
@@ -439,37 +439,43 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
 	kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
 }
 
-static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid,
+static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid)
 {
+	ulong ea = esid << SID_SHIFT;
+	struct kvmppc_slb *slb;
+	u64 gvsid = esid;
+
+	if (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+		slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea);
+		if (slb)
+			gvsid = slb->vsid;
+	}
+
 	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
 	case 0:
-		*vsid = (VSID_REAL >> 16) | esid;
+		*vsid = VSID_REAL | esid;
 		break;
 	case MSR_IR:
-		*vsid = (VSID_REAL_IR >> 16) | esid;
+		*vsid = VSID_REAL_IR | gvsid;
 		break;
 	case MSR_DR:
-		*vsid = (VSID_REAL_DR >> 16) | esid;
+		*vsid = VSID_REAL_DR | gvsid;
 		break;
 	case MSR_DR|MSR_IR:
-	{
-		ulong ea;
-		struct kvmppc_slb *slb;
-		ea = esid << SID_SHIFT;
-		slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea);
-		if (slb)
-			*vsid = slb->vsid;
-		else
+		if (!slb)
 			return -ENOENT;
 
+		*vsid = gvsid;
 		break;
-	}
 	default:
 		BUG();
 		break;
 	}
 
+	if (vcpu->arch.msr & MSR_PR)
+		*vsid |= VSID_PR;
+
 	return 0;
 }
 

arch/powerpc/kvm/book3s_64_mmu_host.c

@@ -48,21 +48,25 @@
 
 static void invalidate_pte(struct hpte_cache *pte)
 {
-	dprintk_mmu("KVM: Flushing SPT %d: 0x%llx (0x%llx) -> 0x%llx\n",
-		    i, pte->pte.eaddr, pte->pte.vpage, pte->host_va);
+	dprintk_mmu("KVM: Flushing SPT: 0x%lx (0x%llx) -> 0x%llx\n",
+		    pte->pte.eaddr, pte->pte.vpage, pte->host_va);
 
 	ppc_md.hpte_invalidate(pte->slot, pte->host_va,
 			       MMU_PAGE_4K, MMU_SEGSIZE_256M,
 			       false);
 	pte->host_va = 0;
-	kvm_release_pfn_dirty(pte->pfn);
+
+	if (pte->pte.may_write)
+		kvm_release_pfn_dirty(pte->pfn);
+	else
+		kvm_release_pfn_clean(pte->pfn);
 }
 
-void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 guest_ea, u64 ea_mask)
+void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
 {
 	int i;
 
-	dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%llx & 0x%llx\n",
+	dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%lx & 0x%lx\n",
 		    vcpu->arch.hpte_cache_offset, guest_ea, ea_mask);
 	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
 
@@ -106,12 +110,12 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
 	}
 }
 
-void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end)
+void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
 {
 	int i;
 
-	dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n",
-		    vcpu->arch.hpte_cache_offset, guest_pa, pa_mask);
+	dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%lx & 0x%lx\n",
+		    vcpu->arch.hpte_cache_offset, pa_start, pa_end);
 	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
 
 	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
@@ -182,7 +186,7 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
 	map = &to_book3s(vcpu)->sid_map[sid_map_mask];
 	if (map->guest_vsid == gvsid) {
-		dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n",
+		dprintk_slb("SLB: Searching: 0x%llx -> 0x%llx\n",
 			    gvsid, map->host_vsid);
 		return map;
 	}
@@ -194,7 +198,8 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 		return map;
 	}
 
-	dprintk_slb("SLB: Searching 0x%llx -> not found\n", gvsid);
+	dprintk_slb("SLB: Searching %d/%d: 0x%llx -> not found\n",
+		    sid_map_mask, SID_MAP_MASK - sid_map_mask, gvsid);
 	return NULL;
 }
 
@@ -212,7 +217,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	/* Get host physical address for gpa */
 	hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
 	if (kvm_is_error_hva(hpaddr)) {
-		printk(KERN_INFO "Couldn't get guest page for gfn %llx!\n", orig_pte->eaddr);
+		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
 		return -EINVAL;
 	}
 	hpaddr <<= PAGE_SHIFT;
@@ -227,10 +232,16 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
 	map = find_sid_vsid(vcpu, vsid);
 	if (!map) {
-		kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr);
+		ret = kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr);
+		WARN_ON(ret < 0);
 		map = find_sid_vsid(vcpu, vsid);
 	}
-	BUG_ON(!map);
+	if (!map) {
+		printk(KERN_ERR "KVM: Segment map for 0x%llx (0x%lx) failed\n",
+				vsid, orig_pte->eaddr);
+		WARN_ON(true);
+		return -EINVAL;
+	}
 
 	vsid = map->host_vsid;
 	va = hpt_va(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
@@ -257,26 +268,26 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	if (ret < 0) {
 		/* If we couldn't map a primary PTE, try a secondary */
-#ifdef USE_SECONDARY
 		hash = ~hash;
+		vflags ^= HPTE_V_SECONDARY;
 		attempt++;
-		if (attempt % 2)
-			vflags = HPTE_V_SECONDARY;
-		else
-			vflags = 0;
-#else
-		attempt = 2;
-#endif
 		goto map_again;
 	} else {
 		int hpte_id = kvmppc_mmu_hpte_cache_next(vcpu);
 		struct hpte_cache *pte = &vcpu->arch.hpte_cache[hpte_id];
 
-		dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%lx (0x%llx) -> %lx\n",
+		dprintk_mmu("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx\n",
 			    ((rflags & HPTE_R_PP) == 3) ? '-' : 'w',
 			    (rflags & HPTE_R_N) ? '-' : 'x',
 			    orig_pte->eaddr, hpteg, va, orig_pte->vpage, hpaddr);
 
+		/* The ppc_md code may give us a secondary entry even though we
+		   asked for a primary. Fix up. */
+		if ((ret & _PTEIDX_SECONDARY) && !(vflags & HPTE_V_SECONDARY)) {
+			hash = ~hash;
+			hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
+		}
+
 		pte->slot = hpteg + (ret & 7);
 		pte->host_va = va;
 		pte->pte = *orig_pte;
@@ -321,6 +332,9 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 	map->guest_vsid = gvsid;
 	map->valid = true;
 
+	dprintk_slb("SLB: New mapping at %d: 0x%llx -> 0x%llx\n",
+		    sid_map_mask, gvsid, map->host_vsid);
+
 	return map;
 }
 
@@ -331,14 +345,14 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
 	int found_inval = -1;
 	int r;
 
-	if (!get_paca()->kvm_slb_max)
-		get_paca()->kvm_slb_max = 1;
+	if (!to_svcpu(vcpu)->slb_max)
+		to_svcpu(vcpu)->slb_max = 1;
 
 	/* Are we overwriting? */
-	for (i = 1; i < get_paca()->kvm_slb_max; i++) {
-		if (!(get_paca()->kvm_slb[i].esid & SLB_ESID_V))
+	for (i = 1; i < to_svcpu(vcpu)->slb_max; i++) {
+		if (!(to_svcpu(vcpu)->slb[i].esid & SLB_ESID_V))
 			found_inval = i;
-		else if ((get_paca()->kvm_slb[i].esid & ESID_MASK) == esid)
+		else if ((to_svcpu(vcpu)->slb[i].esid & ESID_MASK) == esid)
 			return i;
 	}
 
@@ -352,11 +366,11 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
 		max_slb_size = mmu_slb_size;
 
 	/* Overflowing -> purge */
-	if ((get_paca()->kvm_slb_max) == max_slb_size)
+	if ((to_svcpu(vcpu)->slb_max) == max_slb_size)
 		kvmppc_mmu_flush_segments(vcpu);
 
-	r = get_paca()->kvm_slb_max;
-	get_paca()->kvm_slb_max++;
+	r = to_svcpu(vcpu)->slb_max;
+	to_svcpu(vcpu)->slb_max++;
 
 	return r;
 }
@@ -374,7 +388,7 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 
 	if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
 		/* Invalidate an entry */
-		get_paca()->kvm_slb[slb_index].esid = 0;
+		to_svcpu(vcpu)->slb[slb_index].esid = 0;
 		return -ENOENT;
 	}
 
@@ -388,8 +402,8 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 	slb_vsid &= ~SLB_VSID_KP;
 	slb_esid |= slb_index;
 
-	get_paca()->kvm_slb[slb_index].esid = slb_esid;
-	get_paca()->kvm_slb[slb_index].vsid = slb_vsid;
+	to_svcpu(vcpu)->slb[slb_index].esid = slb_esid;
+	to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid;
 
 	dprintk_slb("slbmte %#llx, %#llx\n", slb_vsid, slb_esid);
 
@@ -398,11 +412,29 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 
 void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 {
-	get_paca()->kvm_slb_max = 1;
-	get_paca()->kvm_slb[0].esid = 0;
+	to_svcpu(vcpu)->slb_max = 1;
+	to_svcpu(vcpu)->slb[0].esid = 0;
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_pte_flush(vcpu, 0, 0);
+	__destroy_context(to_book3s(vcpu)->context_id);
+}
+
+int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	int err;
+
+	err = __init_new_context();
+	if (err < 0)
+		return -1;
+	vcpu3s->context_id = err;
+
+	vcpu3s->vsid_max = ((vcpu3s->context_id + 1) << USER_ESID_BITS) - 1;
+	vcpu3s->vsid_first = vcpu3s->context_id << USER_ESID_BITS;
+	vcpu3s->vsid_next = vcpu3s->vsid_first;
+
+	return 0;
 }

arch/powerpc/kvm/book3s_64_slb.S

@@ -44,8 +44,7 @@ slb_exit_skip_ ## num:
  *                                                                            *
  *****************************************************************************/
 
-.global kvmppc_handler_trampoline_enter
-kvmppc_handler_trampoline_enter:
+.macro LOAD_GUEST_SEGMENTS
 
 	/* Required state:
 	 *
@@ -53,20 +52,14 @@ kvmppc_handler_trampoline_enter:
 	 * R13 = PACA
 	 * R1 = host R1
 	 * R2 = host R2
-	 * R9 = guest IP
-	 * R10 = guest MSR
-	 * all other GPRS = free
-	 * PACA[KVM_CR] = guest CR
-	 * PACA[KVM_XER] = guest XER
+	 * R3 = shadow vcpu
+	 * all other volatile GPRS = free
+	 * SVCPU[CR]  = guest CR
+	 * SVCPU[XER] = guest XER
+	 * SVCPU[CTR] = guest CTR
+	 * SVCPU[LR]  = guest LR
 	 */
 
-	mtsrr0	r9
-	mtsrr1	r10
-
-	/* Activate guest mode, so faults get handled by KVM */
-	li	r11, KVM_GUEST_MODE_GUEST
-	stb	r11, PACA_KVM_IN_GUEST(r13)
-
 	/* Remove LPAR shadow entries */
 
 #if SLB_NUM_BOLTED == 3
@@ -101,14 +94,14 @@ kvmppc_handler_trampoline_enter:
 
 	/* Fill SLB with our shadow */
 
-	lbz	r12, PACA_KVM_SLB_MAX(r13)
+	lbz	r12, SVCPU_SLB_MAX(r3)
 	mulli	r12, r12, 16
-	addi	r12, r12, PACA_KVM_SLB
-	add	r12, r12, r13
+	addi	r12, r12, SVCPU_SLB
+	add	r12, r12, r3
 
 	/* for (r11 = kvm_slb; r11 < kvm_slb + kvm_slb_size; r11+=slb_entry) */
-	li	r11, PACA_KVM_SLB
-	add	r11, r11, r13
+	li	r11, SVCPU_SLB
+	add	r11, r11, r3
 
 slb_loop_enter:
 
@@ -127,34 +120,7 @@ slb_loop_enter_skip:
 
 slb_do_enter:
 
-	/* Enter guest */
-
-	ld	r0, (PACA_KVM_R0)(r13)
-	ld	r1, (PACA_KVM_R1)(r13)
-	ld	r2, (PACA_KVM_R2)(r13)
-	ld	r3, (PACA_KVM_R3)(r13)
-	ld	r4, (PACA_KVM_R4)(r13)
-	ld	r5, (PACA_KVM_R5)(r13)
-	ld	r6, (PACA_KVM_R6)(r13)
-	ld	r7, (PACA_KVM_R7)(r13)
-	ld	r8, (PACA_KVM_R8)(r13)
-	ld	r9, (PACA_KVM_R9)(r13)
-	ld	r10, (PACA_KVM_R10)(r13)
-	ld	r12, (PACA_KVM_R12)(r13)
-
-	lwz	r11, (PACA_KVM_CR)(r13)
-	mtcr	r11
-
-	ld	r11, (PACA_KVM_XER)(r13)
-	mtxer	r11
-
-	ld	r11, (PACA_KVM_R11)(r13)
-	ld	r13, (PACA_KVM_R13)(r13)
-
-	RFI
-kvmppc_handler_trampoline_enter_end:
-
-
+.endm
 
 /******************************************************************************
  *                                                                            *
@@ -162,99 +128,22 @@ kvmppc_handler_trampoline_enter_end:
  *                                                                            *
  *****************************************************************************/
 
-.global kvmppc_handler_trampoline_exit
-kvmppc_handler_trampoline_exit:
+.macro LOAD_HOST_SEGMENTS
 
 	/* Register usage at this point:
 	 *
-	 * SPRG_SCRATCH0     = guest R13
-	 * R12               = exit handler id
-	 * R13               = PACA
-	 * PACA.KVM.SCRATCH0 = guest R12
-	 * PACA.KVM.SCRATCH1 = guest CR
+	 * R1         = host R1
+	 * R2         = host R2
+	 * R12        = exit handler id
+	 * R13        = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64]
+	 * SVCPU.*    = guest *
+	 * SVCPU[CR]  = guest CR
+	 * SVCPU[XER] = guest XER
+	 * SVCPU[CTR] = guest CTR
+	 * SVCPU[LR]  = guest LR
 	 *
 	 */
 
-	/* Save registers */
-
-	std	r0, PACA_KVM_R0(r13)
-	std	r1, PACA_KVM_R1(r13)
-	std	r2, PACA_KVM_R2(r13)
-	std	r3, PACA_KVM_R3(r13)
-	std	r4, PACA_KVM_R4(r13)
-	std	r5, PACA_KVM_R5(r13)
-	std	r6, PACA_KVM_R6(r13)
-	std	r7, PACA_KVM_R7(r13)
-	std	r8, PACA_KVM_R8(r13)
-	std	r9, PACA_KVM_R9(r13)
-	std	r10, PACA_KVM_R10(r13)
-	std	r11, PACA_KVM_R11(r13)
-
-	/* Restore R1/R2 so we can handle faults */
-	ld	r1, PACA_KVM_HOST_R1(r13)
-	ld	r2, PACA_KVM_HOST_R2(r13)
-
-	/* Save guest PC and MSR in GPRs */
-	mfsrr0	r3
-	mfsrr1	r4
-
-	/* Get scratch'ed off registers */
-	mfspr	r9, SPRN_SPRG_SCRATCH0
-	std	r9, PACA_KVM_R13(r13)
-
-	ld	r8, PACA_KVM_SCRATCH0(r13)
-	std	r8, PACA_KVM_R12(r13)
-
-	lwz	r7, PACA_KVM_SCRATCH1(r13)
-	stw	r7, PACA_KVM_CR(r13)
-
-	/* Save more register state  */
-
-	mfxer	r6
-	stw	r6, PACA_KVM_XER(r13)
-
-	mfdar	r5
-	mfdsisr	r6
-
-	/*
-	 * In order for us to easily get the last instruction,
-	 * we got the #vmexit at, we exploit the fact that the
-	 * virtual layout is still the same here, so we can just
-	 * ld from the guest's PC address
-	 */
-
-	/* We only load the last instruction when it's safe */
-	cmpwi	r12, BOOK3S_INTERRUPT_DATA_STORAGE
-	beq	ld_last_inst
-	cmpwi	r12, BOOK3S_INTERRUPT_PROGRAM
-	beq	ld_last_inst
-
-	b	no_ld_last_inst
-
-ld_last_inst:
-	/* Save off the guest instruction we're at */
-
-	/* Set guest mode to 'jump over instruction' so if lwz faults
-	 * we'll just continue at the next IP. */
-	li	r9, KVM_GUEST_MODE_SKIP
-	stb	r9, PACA_KVM_IN_GUEST(r13)
-
-	/*    1) enable paging for data */
-	mfmsr	r9
-	ori	r11, r9, MSR_DR			/* Enable paging for data */
-	mtmsr	r11
-	/*    2) fetch the instruction */
-	li	r0, KVM_INST_FETCH_FAILED	/* In case lwz faults */
-	lwz	r0, 0(r3)
-	/*    3) disable paging again */
-	mtmsr	r9
-
-no_ld_last_inst:
-
-	/* Unset guest mode */
-	li	r9, KVM_GUEST_MODE_NONE
-	stb	r9, PACA_KVM_IN_GUEST(r13)
-
 	/* Restore bolted entries from the shadow and fix it along the way */
 
 	/* We don't store anything in entry 0, so we don't need to take care of it */
@@ -275,28 +164,4 @@ no_ld_last_inst:
 
 slb_do_exit:
 
-	/* Register usage at this point:
-	 *
-	 * R0         = guest last inst
-	 * R1         = host R1
-	 * R2         = host R2
-	 * R3         = guest PC
-	 * R4         = guest MSR
-	 * R5         = guest DAR
-	 * R6         = guest DSISR
-	 * R12        = exit handler id
-	 * R13        = PACA
-	 * PACA.KVM.* = guest *
-	 *
-	 */
-
-	/* RFI into the highmem handler */
-	mfmsr	r7
-	ori	r7, r7, MSR_IR|MSR_DR|MSR_RI	/* Enable paging */
-	mtsrr1	r7
-	ld	r8, PACA_KVM_VMHANDLER(r13)	/* Highmem handler address */
-	mtsrr0	r8
-
-	RFI
-kvmppc_handler_trampoline_exit_end:
-
+.endm

arch/powerpc/kvm/book3s_64_emulate.c → arch/powerpc/kvm/book3s_emulate.c

@@ -28,13 +28,16 @@
 #define OP_31_XOP_MFMSR		83
 #define OP_31_XOP_MTMSR		146
 #define OP_31_XOP_MTMSRD	178
+#define OP_31_XOP_MTSR		210
 #define OP_31_XOP_MTSRIN	242
 #define OP_31_XOP_TLBIEL	274
 #define OP_31_XOP_TLBIE		306
 #define OP_31_XOP_SLBMTE	402
 #define OP_31_XOP_SLBIE		434
 #define OP_31_XOP_SLBIA		498
+#define OP_31_XOP_MFSR		595
 #define OP_31_XOP_MFSRIN	659
+#define OP_31_XOP_DCBA		758
 #define OP_31_XOP_SLBMFEV	851
 #define OP_31_XOP_EIOIO		854
 #define OP_31_XOP_SLBMFEE	915
@@ -42,6 +45,24 @@
 /* DCBZ is actually 1014, but we patch it to 1010 so we get a trap */
 #define OP_31_XOP_DCBZ		1010
 
+#define OP_LFS			48
+#define OP_LFD			50
+#define OP_STFS			52
+#define OP_STFD			54
+
+#define SPRN_GQR0		912
+#define SPRN_GQR1		913
+#define SPRN_GQR2		914
+#define SPRN_GQR3		915
+#define SPRN_GQR4		916
+#define SPRN_GQR5		917
+#define SPRN_GQR6		918
+#define SPRN_GQR7		919
+
+/* Book3S_32 defines mfsrin(v) - but that messes up our abstract
+ * function pointers, so let's just disable the define. */
+#undef mfsrin
+
 int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
@@ -52,7 +73,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		switch (get_xop(inst)) {
 		case OP_19_XOP_RFID:
 		case OP_19_XOP_RFI:
-			vcpu->arch.pc = vcpu->arch.srr0;
+			kvmppc_set_pc(vcpu, vcpu->arch.srr0);
 			kvmppc_set_msr(vcpu, vcpu->arch.srr1);
 			*advance = 0;
 			break;
@@ -80,6 +101,18 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		case OP_31_XOP_MTMSR:
 			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst)));
 			break;
+		case OP_31_XOP_MFSR:
+		{
+			int srnum;
+
+			srnum = kvmppc_get_field(inst, 12 + 32, 15 + 32);
+			if (vcpu->arch.mmu.mfsrin) {
+				u32 sr;
+				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
+				kvmppc_set_gpr(vcpu, get_rt(inst), sr);
+			}
+			break;
+		}
 		case OP_31_XOP_MFSRIN:
 		{
 			int srnum;
@@ -92,6 +125,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			}
 			break;
 		}
+		case OP_31_XOP_MTSR:
+			vcpu->arch.mmu.mtsrin(vcpu,
+				(inst >> 16) & 0xf,
+				kvmppc_get_gpr(vcpu, get_rs(inst)));
+			break;
 		case OP_31_XOP_MTSRIN:
 			vcpu->arch.mmu.mtsrin(vcpu,
 				(kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf,
@@ -150,12 +188,17 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				kvmppc_set_gpr(vcpu, get_rt(inst), t);
 			}
 			break;
+		case OP_31_XOP_DCBA:
+			/* Gets treated as NOP */
+			break;
 		case OP_31_XOP_DCBZ:
 		{
 			ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst));
 			ulong ra = 0;
-			ulong addr;
+			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));
@@ -163,15 +206,25 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			addr = (ra + rb) & ~31ULL;
 			if (!(vcpu->arch.msr & MSR_SF))
 				addr &= 0xffffffff;
+			vaddr = addr;
+
+			r = kvmppc_st(vcpu, &addr, 32, zeros, true);
+			if ((r == -ENOENT) || (r == -EPERM)) {
+				*advance = 0;
+				vcpu->arch.dear = vaddr;
+				to_svcpu(vcpu)->fault_dar = vaddr;
+
+				dsisr = DSISR_ISSTORE;
+				if (r == -ENOENT)
+					dsisr |= DSISR_NOHPTE;
+				else if (r == -EPERM)
+					dsisr |= DSISR_PROTFAULT;
+
+				to_book3s(vcpu)->dsisr = dsisr;
+				to_svcpu(vcpu)->fault_dsisr = dsisr;
 
-			if (kvmppc_st(vcpu, addr, 32, zeros)) {
-				vcpu->arch.dear = addr;
-				vcpu->arch.fault_dear = addr;
-				to_book3s(vcpu)->dsisr = DSISR_PROTFAULT |
-						      DSISR_ISSTORE;
 				kvmppc_book3s_queue_irqprio(vcpu,
 					BOOK3S_INTERRUPT_DATA_STORAGE);
-				kvmppc_mmu_pte_flush(vcpu, addr, ~0xFFFULL);
 			}
 
 			break;
@@ -184,6 +237,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		emulated = EMULATE_FAIL;
 	}
 
+	if (emulated == EMULATE_FAIL)
+		emulated = kvmppc_emulate_paired_single(run, vcpu);
+
 	return emulated;
 }
 
@@ -207,6 +263,34 @@ void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper,
 	}
 }
 
+static u32 kvmppc_read_bat(struct kvm_vcpu *vcpu, int sprn)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_bat *bat;
+
+	switch (sprn) {
+	case SPRN_IBAT0U ... SPRN_IBAT3L:
+		bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2];
+		break;
+	case SPRN_IBAT4U ... SPRN_IBAT7L:
+		bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)];
+		break;
+	case SPRN_DBAT0U ... SPRN_DBAT3L:
+		bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2];
+		break;
+	case SPRN_DBAT4U ... SPRN_DBAT7L:
+		bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)];
+		break;
+	default:
+		BUG();
+	}
+
+	if (sprn % 2)
+		return bat->raw >> 32;
+	else
+		return bat->raw;
+}
+
 static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
@@ -217,13 +301,13 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val)
 		bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2];
 		break;
 	case SPRN_IBAT4U ... SPRN_IBAT7L:
-		bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT4U) / 2];
+		bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)];
 		break;
 	case SPRN_DBAT0U ... SPRN_DBAT3L:
 		bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2];
 		break;
 	case SPRN_DBAT4U ... SPRN_DBAT7L:
-		bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT4U) / 2];
+		bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)];
 		break;
 	default:
 		BUG();
@@ -258,6 +342,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		/* BAT writes happen so rarely that we're ok to flush
 		 * everything here */
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
+		kvmppc_mmu_flush_segments(vcpu);
 		break;
 	case SPRN_HID0:
 		to_book3s(vcpu)->hid[0] = spr_val;
@@ -268,7 +353,32 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_HID2:
 		to_book3s(vcpu)->hid[2] = spr_val;
 		break;
+	case SPRN_HID2_GEKKO:
+		to_book3s(vcpu)->hid[2] = spr_val;
+		/* HID2.PSE controls paired single on gekko */
+		switch (vcpu->arch.pvr) {
+		case 0x00080200:	/* lonestar 2.0 */
+		case 0x00088202:	/* lonestar 2.2 */
+		case 0x70000100:	/* gekko 1.0 */
+		case 0x00080100:	/* gekko 2.0 */
+		case 0x00083203:	/* gekko 2.3a */
+		case 0x00083213:	/* gekko 2.3b */
+		case 0x00083204:	/* gekko 2.4 */
+		case 0x00083214:	/* gekko 2.4e (8SE) - retail HW2 */
+		case 0x00087200:	/* broadway */
+			if (vcpu->arch.hflags & BOOK3S_HFLAG_NATIVE_PS) {
+				/* Native paired singles */
+			} else if (spr_val & (1 << 29)) { /* HID2.PSE */
+				vcpu->arch.hflags |= BOOK3S_HFLAG_PAIRED_SINGLE;
+				kvmppc_giveup_ext(vcpu, MSR_FP);
+			} else {
+				vcpu->arch.hflags &= ~BOOK3S_HFLAG_PAIRED_SINGLE;
+			}
+			break;
+		}
+		break;
 	case SPRN_HID4:
+	case SPRN_HID4_GEKKO:
 		to_book3s(vcpu)->hid[4] = spr_val;
 		break;
 	case SPRN_HID5:
@@ -278,12 +388,30 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		    (mfmsr() & MSR_HV))
 			vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
 		break;
+	case SPRN_GQR0:
+	case SPRN_GQR1:
+	case SPRN_GQR2:
+	case SPRN_GQR3:
+	case SPRN_GQR4:
+	case SPRN_GQR5:
+	case SPRN_GQR6:
+	case SPRN_GQR7:
+		to_book3s(vcpu)->gqr[sprn - SPRN_GQR0] = spr_val;
+		break;
 	case SPRN_ICTC:
 	case SPRN_THRM1:
 	case SPRN_THRM2:
 	case SPRN_THRM3:
 	case SPRN_CTRLF:
 	case SPRN_CTRLT:
+	case SPRN_L2CR:
+	case SPRN_MMCR0_GEKKO:
+	case SPRN_MMCR1_GEKKO:
+	case SPRN_PMC1_GEKKO:
+	case SPRN_PMC2_GEKKO:
+	case SPRN_PMC3_GEKKO:
+	case SPRN_PMC4_GEKKO:
+	case SPRN_WPAR_GEKKO:
 		break;
 	default:
 		printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn);
@@ -301,6 +429,12 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	int emulated = EMULATE_DONE;
 
 	switch (sprn) {
+	case SPRN_IBAT0U ... SPRN_IBAT3L:
+	case SPRN_IBAT4U ... SPRN_IBAT7L:
+	case SPRN_DBAT0U ... SPRN_DBAT3L:
+	case SPRN_DBAT4U ... SPRN_DBAT7L:
+		kvmppc_set_gpr(vcpu, rt, kvmppc_read_bat(vcpu, sprn));
+		break;
 	case SPRN_SDR1:
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
 		break;
@@ -320,19 +454,40 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]);
 		break;
 	case SPRN_HID2:
+	case SPRN_HID2_GEKKO:
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]);
 		break;
 	case SPRN_HID4:
+	case SPRN_HID4_GEKKO:
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]);
 		break;
 	case SPRN_HID5:
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]);
 		break;
+	case SPRN_GQR0:
+	case SPRN_GQR1:
+	case SPRN_GQR2:
+	case SPRN_GQR3:
+	case SPRN_GQR4:
+	case SPRN_GQR5:
+	case SPRN_GQR6:
+	case SPRN_GQR7:
+		kvmppc_set_gpr(vcpu, rt,
+			       to_book3s(vcpu)->gqr[sprn - SPRN_GQR0]);
+		break;
 	case SPRN_THRM1:
 	case SPRN_THRM2:
 	case SPRN_THRM3:
 	case SPRN_CTRLF:
 	case SPRN_CTRLT:
+	case SPRN_L2CR:
+	case SPRN_MMCR0_GEKKO:
+	case SPRN_MMCR1_GEKKO:
+	case SPRN_PMC1_GEKKO:
+	case SPRN_PMC2_GEKKO:
+	case SPRN_PMC3_GEKKO:
+	case SPRN_PMC4_GEKKO:
+	case SPRN_WPAR_GEKKO:
 		kvmppc_set_gpr(vcpu, rt, 0);
 		break;
 	default:
@@ -346,3 +501,73 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	return emulated;
 }
 
+u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst)
+{
+	u32 dsisr = 0;
+
+	/*
+	 * This is what the spec says about DSISR bits (not mentioned = 0):
+	 *
+	 * 12:13		[DS]	Set to bits 30:31
+	 * 15:16		[X]	Set to bits 29:30
+	 * 17			[X]	Set to bit 25
+	 *			[D/DS]	Set to bit 5
+	 * 18:21		[X]	Set to bits 21:24
+	 *			[D/DS]	Set to bits 1:4
+	 * 22:26			Set to bits 6:10 (RT/RS/FRT/FRS)
+	 * 27:31			Set to bits 11:15 (RA)
+	 */
+
+	switch (get_op(inst)) {
+	/* D-form */
+	case OP_LFS:
+	case OP_LFD:
+	case OP_STFD:
+	case OP_STFS:
+		dsisr |= (inst >> 12) & 0x4000;	/* bit 17 */
+		dsisr |= (inst >> 17) & 0x3c00; /* bits 18:21 */
+		break;
+	/* X-form */
+	case 31:
+		dsisr |= (inst << 14) & 0x18000; /* bits 15:16 */
+		dsisr |= (inst << 8)  & 0x04000; /* bit 17 */
+		dsisr |= (inst << 3)  & 0x03c00; /* bits 18:21 */
+		break;
+	default:
+		printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst);
+		break;
+	}
+
+	dsisr |= (inst >> 16) & 0x03ff; /* bits 22:31 */
+
+	return dsisr;
+}
+
+ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst)
+{
+	ulong dar = 0;
+	ulong ra;
+
+	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));
+		break;
+	default:
+		printk(KERN_INFO "KVM: Unaligned instruction 0x%x\n", inst);
+		break;
+	}
+
+	return dar;
+}

arch/powerpc/kvm/book3s_64_interrupts.S → arch/powerpc/kvm/book3s_interrupts.S

@@ -24,36 +24,56 @@
 #include <asm/asm-offsets.h>
 #include <asm/exception-64s.h>
 
-#define KVMPPC_HANDLE_EXIT .kvmppc_handle_exit
-#define ULONG_SIZE 8
-#define VCPU_GPR(n)     (VCPU_GPRS + (n * ULONG_SIZE))
+#if defined(CONFIG_PPC_BOOK3S_64)
 
-.macro DISABLE_INTERRUPTS
-       mfmsr   r0
-       rldicl  r0,r0,48,1
-       rotldi  r0,r0,16
-       mtmsrd  r0,1
-.endm
+#define ULONG_SIZE 		8
+#define FUNC(name) 		GLUE(.,name)
 
+#define GET_SHADOW_VCPU(reg)    \
+        addi    reg, r13, PACA_KVM_SVCPU
+
+#define DISABLE_INTERRUPTS	\
+	mfmsr   r0;		\
+	rldicl  r0,r0,48,1;	\
+	rotldi  r0,r0,16;	\
+	mtmsrd  r0,1;		\
+
+#elif defined(CONFIG_PPC_BOOK3S_32)
+
+#define ULONG_SIZE              4
+#define FUNC(name)		name
+
+#define GET_SHADOW_VCPU(reg)    \
+        lwz     reg, (THREAD + THREAD_KVM_SVCPU)(r2)
+
+#define DISABLE_INTERRUPTS	\
+	mfmsr   r0;		\
+	rlwinm  r0,r0,0,17,15;	\
+	mtmsr   r0;		\
+
+#endif /* CONFIG_PPC_BOOK3S_XX */
+
+
+#define VCPU_GPR(n)		(VCPU_GPRS + (n * ULONG_SIZE))
 #define VCPU_LOAD_NVGPRS(vcpu) \
-	ld	r14, VCPU_GPR(r14)(vcpu); \
-	ld	r15, VCPU_GPR(r15)(vcpu); \
-	ld	r16, VCPU_GPR(r16)(vcpu); \
-	ld	r17, VCPU_GPR(r17)(vcpu); \
-	ld	r18, VCPU_GPR(r18)(vcpu); \
-	ld	r19, VCPU_GPR(r19)(vcpu); \
-	ld	r20, VCPU_GPR(r20)(vcpu); \
-	ld	r21, VCPU_GPR(r21)(vcpu); \
-	ld	r22, VCPU_GPR(r22)(vcpu); \
-	ld	r23, VCPU_GPR(r23)(vcpu); \
-	ld	r24, VCPU_GPR(r24)(vcpu); \
-	ld	r25, VCPU_GPR(r25)(vcpu); \
-	ld	r26, VCPU_GPR(r26)(vcpu); \
-	ld	r27, VCPU_GPR(r27)(vcpu); \
-	ld	r28, VCPU_GPR(r28)(vcpu); \
-	ld	r29, VCPU_GPR(r29)(vcpu); \
-	ld	r30, VCPU_GPR(r30)(vcpu); \
-	ld	r31, VCPU_GPR(r31)(vcpu); \
+	PPC_LL	r14, VCPU_GPR(r14)(vcpu); \
+	PPC_LL	r15, VCPU_GPR(r15)(vcpu); \
+	PPC_LL	r16, VCPU_GPR(r16)(vcpu); \
+	PPC_LL	r17, VCPU_GPR(r17)(vcpu); \
+	PPC_LL	r18, VCPU_GPR(r18)(vcpu); \
+	PPC_LL	r19, VCPU_GPR(r19)(vcpu); \
+	PPC_LL	r20, VCPU_GPR(r20)(vcpu); \
+	PPC_LL	r21, VCPU_GPR(r21)(vcpu); \
+	PPC_LL	r22, VCPU_GPR(r22)(vcpu); \
+	PPC_LL	r23, VCPU_GPR(r23)(vcpu); \
+	PPC_LL	r24, VCPU_GPR(r24)(vcpu); \
+	PPC_LL	r25, VCPU_GPR(r25)(vcpu); \
+	PPC_LL	r26, VCPU_GPR(r26)(vcpu); \
+	PPC_LL	r27, VCPU_GPR(r27)(vcpu); \
+	PPC_LL	r28, VCPU_GPR(r28)(vcpu); \
+	PPC_LL	r29, VCPU_GPR(r29)(vcpu); \
+	PPC_LL	r30, VCPU_GPR(r30)(vcpu); \
+	PPC_LL	r31, VCPU_GPR(r31)(vcpu); \
 
 /*****************************************************************************
  *                                                                           *
@@ -69,11 +89,11 @@ _GLOBAL(__kvmppc_vcpu_entry)
 
 kvm_start_entry:
 	/* Write correct stack frame */
-	mflr    r0
-	std     r0,16(r1)
+	mflr	r0
+	PPC_STL	r0,PPC_LR_STKOFF(r1)
 
 	/* Save host state to the stack */
-	stdu	r1, -SWITCH_FRAME_SIZE(r1)
+	PPC_STLU r1, -SWITCH_FRAME_SIZE(r1)
 
 	/* Save r3 (kvm_run) and r4 (vcpu) */
 	SAVE_2GPRS(3, r1)
@@ -82,33 +102,28 @@ kvm_start_entry:
 	SAVE_NVGPRS(r1)
 
 	/* Save LR */
-	std	r0, _LINK(r1)
+	PPC_STL	r0, _LINK(r1)
 
 	/* Load non-volatile guest state from the vcpu */
 	VCPU_LOAD_NVGPRS(r4)
 
+	GET_SHADOW_VCPU(r5)
+
 	/* Save R1/R2 in the PACA */
-	std	r1, PACA_KVM_HOST_R1(r13)
-	std	r2, PACA_KVM_HOST_R2(r13)
+	PPC_STL	r1, SVCPU_HOST_R1(r5)
+	PPC_STL	r2, SVCPU_HOST_R2(r5)
 
 	/* XXX swap in/out on load? */
-	ld	r3, VCPU_HIGHMEM_HANDLER(r4)
-	std	r3, PACA_KVM_VMHANDLER(r13)
+	PPC_LL	r3, VCPU_HIGHMEM_HANDLER(r4)
+	PPC_STL	r3, SVCPU_VMHANDLER(r5)
 
 kvm_start_lightweight:
 
-	ld	r9, VCPU_PC(r4)			/* r9 = vcpu->arch.pc */
-	ld	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
-
-	/* Load some guest state in the respective registers */
-	ld	r5, VCPU_CTR(r4)	/* r5 = vcpu->arch.ctr */
-					/* will be swapped in by rmcall */
-
-	ld	r3, VCPU_LR(r4)		/* r3 = vcpu->arch.lr */
-	mtlr	r3			/* LR = r3 */
+	PPC_LL	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
 
 	DISABLE_INTERRUPTS
 
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* Some guests may need to have dcbz set to 32 byte length.
 	 *
 	 * Usually we ensure that by patching the guest's instructions
@@ -118,7 +133,7 @@ kvm_start_lightweight:
 	 * because that's a lot faster.
 	 */
 
-	ld	r3, VCPU_HFLAGS(r4)
+	PPC_LL	r3, VCPU_HFLAGS(r4)
 	rldicl.	r3, r3, 0, 63		/* CR = ((r3 & 1) == 0) */
 	beq	no_dcbz32_on
 
@@ -128,13 +143,15 @@ kvm_start_lightweight:
 
 no_dcbz32_on:
 
-	ld	r6, VCPU_RMCALL(r4)
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+	PPC_LL	r6, VCPU_RMCALL(r4)
 	mtctr	r6
 
-	ld	r3, VCPU_TRAMPOLINE_ENTER(r4)
+	PPC_LL	r3, VCPU_TRAMPOLINE_ENTER(r4)
 	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR))
 
-	/* Jump to SLB patching handlder and into our guest */
+	/* Jump to segment patching handler and into our guest */
 	bctr
 
 /*
@@ -149,31 +166,20 @@ kvmppc_handler_highmem:
 	/*
 	 * Register usage at this point:
 	 *
-	 * R0         = guest last inst
-	 * R1         = host R1
-	 * R2         = host R2
-	 * R3         = guest PC
-	 * R4         = guest MSR
-	 * R5         = guest DAR
-	 * R6         = guest DSISR
-	 * R13        = PACA
-	 * PACA.KVM.* = guest *
+	 * R1       = host R1
+	 * R2       = host R2
+	 * R12      = exit handler id
+	 * R13      = PACA
+	 * SVCPU.*  = guest *
 	 *
 	 */
 
 	/* R7 = vcpu */
-	ld	r7, GPR4(r1)
+	PPC_LL	r7, GPR4(r1)
 
-	/* Now save the guest state */
+#ifdef CONFIG_PPC_BOOK3S_64
 
-	stw	r0, VCPU_LAST_INST(r7)
-
-	std	r3, VCPU_PC(r7)
-	std	r4, VCPU_SHADOW_SRR1(r7)
-	std	r5, VCPU_FAULT_DEAR(r7)
-	std	r6, VCPU_FAULT_DSISR(r7)
-
-	ld	r5, VCPU_HFLAGS(r7)
+	PPC_LL	r5, VCPU_HFLAGS(r7)
 	rldicl.	r5, r5, 0, 63		/* CR = ((r5 & 1) == 0) */
 	beq	no_dcbz32_off
 
@@ -184,35 +190,29 @@ kvmppc_handler_highmem:
 
 no_dcbz32_off:
 
-	std	r14, VCPU_GPR(r14)(r7)
-	std	r15, VCPU_GPR(r15)(r7)
-	std	r16, VCPU_GPR(r16)(r7)
-	std	r17, VCPU_GPR(r17)(r7)
-	std	r18, VCPU_GPR(r18)(r7)
-	std	r19, VCPU_GPR(r19)(r7)
-	std	r20, VCPU_GPR(r20)(r7)
-	std	r21, VCPU_GPR(r21)(r7)
-	std	r22, VCPU_GPR(r22)(r7)
-	std	r23, VCPU_GPR(r23)(r7)
-	std	r24, VCPU_GPR(r24)(r7)
-	std	r25, VCPU_GPR(r25)(r7)
-	std	r26, VCPU_GPR(r26)(r7)
-	std	r27, VCPU_GPR(r27)(r7)
-	std	r28, VCPU_GPR(r28)(r7)
-	std	r29, VCPU_GPR(r29)(r7)
-	std	r30, VCPU_GPR(r30)(r7)
-	std	r31, VCPU_GPR(r31)(r7)
-
-	/* Save guest CTR */
-	mfctr	r5
-	std	r5, VCPU_CTR(r7)
-
-	/* Save guest LR */
-	mflr	r5
-	std	r5, VCPU_LR(r7)
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+	PPC_STL	r14, VCPU_GPR(r14)(r7)
+	PPC_STL	r15, VCPU_GPR(r15)(r7)
+	PPC_STL	r16, VCPU_GPR(r16)(r7)
+	PPC_STL	r17, VCPU_GPR(r17)(r7)
+	PPC_STL	r18, VCPU_GPR(r18)(r7)
+	PPC_STL	r19, VCPU_GPR(r19)(r7)
+	PPC_STL	r20, VCPU_GPR(r20)(r7)
+	PPC_STL	r21, VCPU_GPR(r21)(r7)
+	PPC_STL	r22, VCPU_GPR(r22)(r7)
+	PPC_STL	r23, VCPU_GPR(r23)(r7)
+	PPC_STL	r24, VCPU_GPR(r24)(r7)
+	PPC_STL	r25, VCPU_GPR(r25)(r7)
+	PPC_STL	r26, VCPU_GPR(r26)(r7)
+	PPC_STL	r27, VCPU_GPR(r27)(r7)
+	PPC_STL	r28, VCPU_GPR(r28)(r7)
+	PPC_STL	r29, VCPU_GPR(r29)(r7)
+	PPC_STL	r30, VCPU_GPR(r30)(r7)
+	PPC_STL	r31, VCPU_GPR(r31)(r7)
 
 	/* Restore host msr -> SRR1 */
-	ld	r6, VCPU_HOST_MSR(r7)
+	PPC_LL	r6, VCPU_HOST_MSR(r7)
 
 	/*
 	 * For some interrupts, we need to call the real Linux
@@ -228,9 +228,12 @@ no_dcbz32_off:
 	beq	call_linux_handler
 	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
 	beq	call_linux_handler
+	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
+	beq	call_linux_handler
 
 	/* Back to EE=1 */
 	mtmsr	r6
+	sync
 	b	kvm_return_point
 
 call_linux_handler:
@@ -249,14 +252,14 @@ call_linux_handler:
 	 */
 
 	/* Restore host IP -> SRR0 */
-	ld	r5, VCPU_HOST_RETIP(r7)
+	PPC_LL	r5, VCPU_HOST_RETIP(r7)
 
 	/* XXX Better move to a safe function?
 	 *     What if we get an HTAB flush in between mtsrr0 and mtsrr1? */
 
 	mtlr	r12
 
-	ld	r4, VCPU_TRAMPOLINE_LOWMEM(r7)
+	PPC_LL	r4, VCPU_TRAMPOLINE_LOWMEM(r7)
 	mtsrr0	r4
 	LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR))
 	mtsrr1	r3
@@ -274,7 +277,7 @@ kvm_return_point:
 
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)
-	bl	KVMPPC_HANDLE_EXIT
+	bl	FUNC(kvmppc_handle_exit)
 
 	/* If RESUME_GUEST, get back in the loop */
 	cmpwi	r3, RESUME_GUEST
@@ -285,7 +288,7 @@ kvm_return_point:
 
 kvm_exit_loop:
 
-	ld	r4, _LINK(r1)
+	PPC_LL	r4, _LINK(r1)
 	mtlr	r4
 
 	/* Restore non-volatile host registers (r14 - r31) */
@@ -296,8 +299,8 @@ kvm_exit_loop:
 
 kvm_loop_heavyweight:
 
-	ld	r4, _LINK(r1)
-	std     r4, (16 + SWITCH_FRAME_SIZE)(r1)
+	PPC_LL	r4, _LINK(r1)
+	PPC_STL r4, (PPC_LR_STKOFF + SWITCH_FRAME_SIZE)(r1)
 
 	/* Load vcpu and cpu_run */
 	REST_2GPRS(3, r1)
@@ -315,4 +318,3 @@ kvm_loop_lightweight:
 
 	/* Jump back into the beginning of this function */
 	b	kvm_start_lightweight
-

arch/powerpc/kvm/book3s_paired_singles.c

@@ -0,0 +1,1289 @@
+/*
+ * 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 Novell Inc 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/kvm.h>
+#include <asm/kvm_ppc.h>
+#include <asm/disassemble.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_fpu.h>
+#include <asm/reg.h>
+#include <asm/cacheflush.h>
+#include <linux/vmalloc.h>
+
+/* #define DEBUG */
+
+#ifdef DEBUG
+#define dprintk printk
+#else
+#define dprintk(...) do { } while(0);
+#endif
+
+#define OP_LFS			48
+#define OP_LFSU			49
+#define OP_LFD			50
+#define OP_LFDU			51
+#define OP_STFS			52
+#define OP_STFSU		53
+#define OP_STFD			54
+#define OP_STFDU		55
+#define OP_PSQ_L		56
+#define OP_PSQ_LU		57
+#define OP_PSQ_ST		60
+#define OP_PSQ_STU		61
+
+#define OP_31_LFSX		535
+#define OP_31_LFSUX		567
+#define OP_31_LFDX		599
+#define OP_31_LFDUX		631
+#define OP_31_STFSX		663
+#define OP_31_STFSUX		695
+#define OP_31_STFX		727
+#define OP_31_STFUX		759
+#define OP_31_LWIZX		887
+#define OP_31_STFIWX		983
+
+#define OP_59_FADDS		21
+#define OP_59_FSUBS		20
+#define OP_59_FSQRTS		22
+#define OP_59_FDIVS		18
+#define OP_59_FRES		24
+#define OP_59_FMULS		25
+#define OP_59_FRSQRTES		26
+#define OP_59_FMSUBS		28
+#define OP_59_FMADDS		29
+#define OP_59_FNMSUBS		30
+#define OP_59_FNMADDS		31
+
+#define OP_63_FCMPU		0
+#define OP_63_FCPSGN		8
+#define OP_63_FRSP		12
+#define OP_63_FCTIW		14
+#define OP_63_FCTIWZ		15
+#define OP_63_FDIV		18
+#define OP_63_FADD		21
+#define OP_63_FSQRT		22
+#define OP_63_FSEL		23
+#define OP_63_FRE		24
+#define OP_63_FMUL		25
+#define OP_63_FRSQRTE		26
+#define OP_63_FMSUB		28
+#define OP_63_FMADD		29
+#define OP_63_FNMSUB		30
+#define OP_63_FNMADD		31
+#define OP_63_FCMPO		32
+#define OP_63_MTFSB1		38 // XXX
+#define OP_63_FSUB		20
+#define OP_63_FNEG		40
+#define OP_63_MCRFS		64
+#define OP_63_MTFSB0		70
+#define OP_63_FMR		72
+#define OP_63_MTFSFI		134
+#define OP_63_FABS		264
+#define OP_63_MFFS		583
+#define OP_63_MTFSF		711
+
+#define OP_4X_PS_CMPU0		0
+#define OP_4X_PSQ_LX		6
+#define OP_4XW_PSQ_STX		7
+#define OP_4A_PS_SUM0		10
+#define OP_4A_PS_SUM1		11
+#define OP_4A_PS_MULS0		12
+#define OP_4A_PS_MULS1		13
+#define OP_4A_PS_MADDS0		14
+#define OP_4A_PS_MADDS1		15
+#define OP_4A_PS_DIV		18
+#define OP_4A_PS_SUB		20
+#define OP_4A_PS_ADD		21
+#define OP_4A_PS_SEL		23
+#define OP_4A_PS_RES		24
+#define OP_4A_PS_MUL		25
+#define OP_4A_PS_RSQRTE		26
+#define OP_4A_PS_MSUB		28
+#define OP_4A_PS_MADD		29
+#define OP_4A_PS_NMSUB		30
+#define OP_4A_PS_NMADD		31
+#define OP_4X_PS_CMPO0		32
+#define OP_4X_PSQ_LUX		38
+#define OP_4XW_PSQ_STUX		39
+#define OP_4X_PS_NEG		40
+#define OP_4X_PS_CMPU1		64
+#define OP_4X_PS_MR		72
+#define OP_4X_PS_CMPO1		96
+#define OP_4X_PS_NABS		136
+#define OP_4X_PS_ABS		264
+#define OP_4X_PS_MERGE00	528
+#define OP_4X_PS_MERGE01	560
+#define OP_4X_PS_MERGE10	592
+#define OP_4X_PS_MERGE11	624
+
+#define SCALAR_NONE		0
+#define SCALAR_HIGH		(1 << 0)
+#define SCALAR_LOW		(1 << 1)
+#define SCALAR_NO_PS0		(1 << 2)
+#define SCALAR_NO_PS1		(1 << 3)
+
+#define GQR_ST_TYPE_MASK	0x00000007
+#define GQR_ST_TYPE_SHIFT	0
+#define GQR_ST_SCALE_MASK	0x00003f00
+#define GQR_ST_SCALE_SHIFT	8
+#define GQR_LD_TYPE_MASK	0x00070000
+#define GQR_LD_TYPE_SHIFT	16
+#define GQR_LD_SCALE_MASK	0x3f000000
+#define GQR_LD_SCALE_SHIFT	24
+
+#define GQR_QUANTIZE_FLOAT	0
+#define GQR_QUANTIZE_U8		4
+#define GQR_QUANTIZE_U16	5
+#define GQR_QUANTIZE_S8		6
+#define GQR_QUANTIZE_S16	7
+
+#define FPU_LS_SINGLE		0
+#define FPU_LS_DOUBLE		1
+#define FPU_LS_SINGLE_LOW	2
+
+static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt)
+{
+	struct thread_struct t;
+
+	t.fpscr.val = vcpu->arch.fpscr;
+	cvt_df((double*)&vcpu->arch.fpr[rt], (float*)&vcpu->arch.qpr[rt], &t);
+}
+
+static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
+{
+	u64 dsisr;
+
+	vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 36, 0);
+	vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0);
+	vcpu->arch.dear = eaddr;
+	/* Page Fault */
+	dsisr = kvmppc_set_field(0, 33, 33, 1);
+	if (is_store)
+		to_book3s(vcpu)->dsisr = kvmppc_set_field(dsisr, 38, 38, 1);
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE);
+}
+
+static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				   int rs, ulong addr, int ls_type)
+{
+	int emulated = EMULATE_FAIL;
+	struct thread_struct t;
+	int r;
+	char tmp[8];
+	int len = sizeof(u32);
+
+	if (ls_type == FPU_LS_DOUBLE)
+		len = sizeof(u64);
+
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	/* read from memory */
+	r = kvmppc_ld(vcpu, &addr, len, tmp, true);
+	vcpu->arch.paddr_accessed = addr;
+
+	if (r < 0) {
+		kvmppc_inject_pf(vcpu, addr, false);
+		goto done_load;
+	} else if (r == EMULATE_DO_MMIO) {
+		emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, len, 1);
+		goto done_load;
+	}
+
+	emulated = EMULATE_DONE;
+
+	/* put in registers */
+	switch (ls_type) {
+	case FPU_LS_SINGLE:
+		cvt_fd((float*)tmp, (double*)&vcpu->arch.fpr[rs], &t);
+		vcpu->arch.qpr[rs] = *((u32*)tmp);
+		break;
+	case FPU_LS_DOUBLE:
+		vcpu->arch.fpr[rs] = *((u64*)tmp);
+		break;
+	}
+
+	dprintk(KERN_INFO "KVM: FPR_LD [0x%llx] at 0x%lx (%d)\n", *(u64*)tmp,
+			  addr, len);
+
+done_load:
+	return emulated;
+}
+
+static int kvmppc_emulate_fpr_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				    int rs, ulong addr, int ls_type)
+{
+	int emulated = EMULATE_FAIL;
+	struct thread_struct t;
+	int r;
+	char tmp[8];
+	u64 val;
+	int len;
+
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	switch (ls_type) {
+	case FPU_LS_SINGLE:
+		cvt_df((double*)&vcpu->arch.fpr[rs], (float*)tmp, &t);
+		val = *((u32*)tmp);
+		len = sizeof(u32);
+		break;
+	case FPU_LS_SINGLE_LOW:
+		*((u32*)tmp) = vcpu->arch.fpr[rs];
+		val = vcpu->arch.fpr[rs] & 0xffffffff;
+		len = sizeof(u32);
+		break;
+	case FPU_LS_DOUBLE:
+		*((u64*)tmp) = vcpu->arch.fpr[rs];
+		val = vcpu->arch.fpr[rs];
+		len = sizeof(u64);
+		break;
+	default:
+		val = 0;
+		len = 0;
+	}
+
+	r = kvmppc_st(vcpu, &addr, len, tmp, true);
+	vcpu->arch.paddr_accessed = addr;
+	if (r < 0) {
+		kvmppc_inject_pf(vcpu, addr, true);
+	} else if (r == EMULATE_DO_MMIO) {
+		emulated = kvmppc_handle_store(run, vcpu, val, len, 1);
+	} else {
+		emulated = EMULATE_DONE;
+	}
+
+	dprintk(KERN_INFO "KVM: FPR_ST [0x%llx] at 0x%lx (%d)\n",
+			  val, addr, len);
+
+	return emulated;
+}
+
+static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				   int rs, ulong addr, bool w, int i)
+{
+	int emulated = EMULATE_FAIL;
+	struct thread_struct t;
+	int r;
+	float one = 1.0;
+	u32 tmp[2];
+
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	/* read from memory */
+	if (w) {
+		r = kvmppc_ld(vcpu, &addr, sizeof(u32), tmp, true);
+		memcpy(&tmp[1], &one, sizeof(u32));
+	} else {
+		r = kvmppc_ld(vcpu, &addr, sizeof(u32) * 2, tmp, true);
+	}
+	vcpu->arch.paddr_accessed = addr;
+	if (r < 0) {
+		kvmppc_inject_pf(vcpu, addr, false);
+		goto done_load;
+	} else if ((r == EMULATE_DO_MMIO) && w) {
+		emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, 4, 1);
+		vcpu->arch.qpr[rs] = tmp[1];
+		goto done_load;
+	} else if (r == EMULATE_DO_MMIO) {
+		emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FQPR | rs, 8, 1);
+		goto done_load;
+	}
+
+	emulated = EMULATE_DONE;
+
+	/* put in registers */
+	cvt_fd((float*)&tmp[0], (double*)&vcpu->arch.fpr[rs], &t);
+	vcpu->arch.qpr[rs] = tmp[1];
+
+	dprintk(KERN_INFO "KVM: PSQ_LD [0x%x, 0x%x] at 0x%lx (%d)\n", tmp[0],
+			  tmp[1], addr, w ? 4 : 8);
+
+done_load:
+	return emulated;
+}
+
+static int kvmppc_emulate_psq_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				    int rs, ulong addr, bool w, int i)
+{
+	int emulated = EMULATE_FAIL;
+	struct thread_struct t;
+	int r;
+	u32 tmp[2];
+	int len = w ? sizeof(u32) : sizeof(u64);
+
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	cvt_df((double*)&vcpu->arch.fpr[rs], (float*)&tmp[0], &t);
+	tmp[1] = vcpu->arch.qpr[rs];
+
+	r = kvmppc_st(vcpu, &addr, len, tmp, true);
+	vcpu->arch.paddr_accessed = addr;
+	if (r < 0) {
+		kvmppc_inject_pf(vcpu, addr, true);
+	} else if ((r == EMULATE_DO_MMIO) && w) {
+		emulated = kvmppc_handle_store(run, vcpu, tmp[0], 4, 1);
+	} else if (r == EMULATE_DO_MMIO) {
+		u64 val = ((u64)tmp[0] << 32) | tmp[1];
+		emulated = kvmppc_handle_store(run, vcpu, val, 8, 1);
+	} else {
+		emulated = EMULATE_DONE;
+	}
+
+	dprintk(KERN_INFO "KVM: PSQ_ST [0x%x, 0x%x] at 0x%lx (%d)\n",
+			  tmp[0], tmp[1], addr, len);
+
+	return emulated;
+}
+
+/*
+ * Cuts out inst bits with ordering according to spec.
+ * That means the leftmost bit is zero. All given bits are included.
+ */
+static inline u32 inst_get_field(u32 inst, int msb, int lsb)
+{
+	return kvmppc_get_field(inst, msb + 32, lsb + 32);
+}
+
+/*
+ * Replaces inst bits with ordering according to spec.
+ */
+static inline u32 inst_set_field(u32 inst, int msb, int lsb, int value)
+{
+	return kvmppc_set_field(inst, msb + 32, lsb + 32, value);
+}
+
+bool kvmppc_inst_is_paired_single(struct kvm_vcpu *vcpu, u32 inst)
+{
+	if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE))
+		return false;
+
+	switch (get_op(inst)) {
+	case OP_PSQ_L:
+	case OP_PSQ_LU:
+	case OP_PSQ_ST:
+	case OP_PSQ_STU:
+	case OP_LFS:
+	case OP_LFSU:
+	case OP_LFD:
+	case OP_LFDU:
+	case OP_STFS:
+	case OP_STFSU:
+	case OP_STFD:
+	case OP_STFDU:
+		return true;
+	case 4:
+		/* X form */
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_4X_PS_CMPU0:
+		case OP_4X_PSQ_LX:
+		case OP_4X_PS_CMPO0:
+		case OP_4X_PSQ_LUX:
+		case OP_4X_PS_NEG:
+		case OP_4X_PS_CMPU1:
+		case OP_4X_PS_MR:
+		case OP_4X_PS_CMPO1:
+		case OP_4X_PS_NABS:
+		case OP_4X_PS_ABS:
+		case OP_4X_PS_MERGE00:
+		case OP_4X_PS_MERGE01:
+		case OP_4X_PS_MERGE10:
+		case OP_4X_PS_MERGE11:
+			return true;
+		}
+		/* XW form */
+		switch (inst_get_field(inst, 25, 30)) {
+		case OP_4XW_PSQ_STX:
+		case OP_4XW_PSQ_STUX:
+			return true;
+		}
+		/* A form */
+		switch (inst_get_field(inst, 26, 30)) {
+		case OP_4A_PS_SUM1:
+		case OP_4A_PS_SUM0:
+		case OP_4A_PS_MULS0:
+		case OP_4A_PS_MULS1:
+		case OP_4A_PS_MADDS0:
+		case OP_4A_PS_MADDS1:
+		case OP_4A_PS_DIV:
+		case OP_4A_PS_SUB:
+		case OP_4A_PS_ADD:
+		case OP_4A_PS_SEL:
+		case OP_4A_PS_RES:
+		case OP_4A_PS_MUL:
+		case OP_4A_PS_RSQRTE:
+		case OP_4A_PS_MSUB:
+		case OP_4A_PS_MADD:
+		case OP_4A_PS_NMSUB:
+		case OP_4A_PS_NMADD:
+			return true;
+		}
+		break;
+	case 59:
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_59_FADDS:
+		case OP_59_FSUBS:
+		case OP_59_FDIVS:
+		case OP_59_FRES:
+		case OP_59_FRSQRTES:
+			return true;
+		}
+		switch (inst_get_field(inst, 26, 30)) {
+		case OP_59_FMULS:
+		case OP_59_FMSUBS:
+		case OP_59_FMADDS:
+		case OP_59_FNMSUBS:
+		case OP_59_FNMADDS:
+			return true;
+		}
+		break;
+	case 63:
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_63_MTFSB0:
+		case OP_63_MTFSB1:
+		case OP_63_MTFSF:
+		case OP_63_MTFSFI:
+		case OP_63_MCRFS:
+		case OP_63_MFFS:
+		case OP_63_FCMPU:
+		case OP_63_FCMPO:
+		case OP_63_FNEG:
+		case OP_63_FMR:
+		case OP_63_FABS:
+		case OP_63_FRSP:
+		case OP_63_FDIV:
+		case OP_63_FADD:
+		case OP_63_FSUB:
+		case OP_63_FCTIW:
+		case OP_63_FCTIWZ:
+		case OP_63_FRSQRTE:
+		case OP_63_FCPSGN:
+			return true;
+		}
+		switch (inst_get_field(inst, 26, 30)) {
+		case OP_63_FMUL:
+		case OP_63_FSEL:
+		case OP_63_FMSUB:
+		case OP_63_FMADD:
+		case OP_63_FNMSUB:
+		case OP_63_FNMADD:
+			return true;
+		}
+		break;
+	case 31:
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_31_LFSX:
+		case OP_31_LFSUX:
+		case OP_31_LFDX:
+		case OP_31_LFDUX:
+		case OP_31_STFSX:
+		case OP_31_STFSUX:
+		case OP_31_STFX:
+		case OP_31_STFUX:
+		case OP_31_STFIWX:
+			return true;
+		}
+		break;
+	}
+
+	return false;
+}
+
+static int get_d_signext(u32 inst)
+{
+	int d = inst & 0x8ff;
+
+	if (d & 0x800)
+		return -(d & 0x7ff);
+
+	return (d & 0x7ff);
+}
+
+static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc,
+				      int reg_out, int reg_in1, int reg_in2,
+				      int reg_in3, int scalar,
+				      void (*func)(struct thread_struct *t,
+						 u32 *dst, u32 *src1,
+						 u32 *src2, u32 *src3))
+{
+	u32 *qpr = vcpu->arch.qpr;
+	u64 *fpr = vcpu->arch.fpr;
+	u32 ps0_out;
+	u32 ps0_in1, ps0_in2, ps0_in3;
+	u32 ps1_in1, ps1_in2, ps1_in3;
+	struct thread_struct t;
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	/* RC */
+	WARN_ON(rc);
+
+	/* PS0 */
+	cvt_df((double*)&fpr[reg_in1], (float*)&ps0_in1, &t);
+	cvt_df((double*)&fpr[reg_in2], (float*)&ps0_in2, &t);
+	cvt_df((double*)&fpr[reg_in3], (float*)&ps0_in3, &t);
+
+	if (scalar & SCALAR_LOW)
+		ps0_in2 = qpr[reg_in2];
+
+	func(&t, &ps0_out, &ps0_in1, &ps0_in2, &ps0_in3);
+
+	dprintk(KERN_INFO "PS3 ps0 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n",
+			  ps0_in1, ps0_in2, ps0_in3, ps0_out);
+
+	if (!(scalar & SCALAR_NO_PS0))
+		cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t);
+
+	/* PS1 */
+	ps1_in1 = qpr[reg_in1];
+	ps1_in2 = qpr[reg_in2];
+	ps1_in3 = qpr[reg_in3];
+
+	if (scalar & SCALAR_HIGH)
+		ps1_in2 = ps0_in2;
+
+	if (!(scalar & SCALAR_NO_PS1))
+		func(&t, &qpr[reg_out], &ps1_in1, &ps1_in2, &ps1_in3);
+
+	dprintk(KERN_INFO "PS3 ps1 -> f(0x%x, 0x%x, 0x%x) = 0x%x\n",
+			  ps1_in1, ps1_in2, ps1_in3, qpr[reg_out]);
+
+	return EMULATE_DONE;
+}
+
+static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc,
+				    int reg_out, int reg_in1, int reg_in2,
+				    int scalar,
+				    void (*func)(struct thread_struct *t,
+						 u32 *dst, u32 *src1,
+						 u32 *src2))
+{
+	u32 *qpr = vcpu->arch.qpr;
+	u64 *fpr = vcpu->arch.fpr;
+	u32 ps0_out;
+	u32 ps0_in1, ps0_in2;
+	u32 ps1_out;
+	u32 ps1_in1, ps1_in2;
+	struct thread_struct t;
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	/* RC */
+	WARN_ON(rc);
+
+	/* PS0 */
+	cvt_df((double*)&fpr[reg_in1], (float*)&ps0_in1, &t);
+
+	if (scalar & SCALAR_LOW)
+		ps0_in2 = qpr[reg_in2];
+	else
+		cvt_df((double*)&fpr[reg_in2], (float*)&ps0_in2, &t);
+
+	func(&t, &ps0_out, &ps0_in1, &ps0_in2);
+
+	if (!(scalar & SCALAR_NO_PS0)) {
+		dprintk(KERN_INFO "PS2 ps0 -> f(0x%x, 0x%x) = 0x%x\n",
+				  ps0_in1, ps0_in2, ps0_out);
+
+		cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t);
+	}
+
+	/* PS1 */
+	ps1_in1 = qpr[reg_in1];
+	ps1_in2 = qpr[reg_in2];
+
+	if (scalar & SCALAR_HIGH)
+		ps1_in2 = ps0_in2;
+
+	func(&t, &ps1_out, &ps1_in1, &ps1_in2);
+
+	if (!(scalar & SCALAR_NO_PS1)) {
+		qpr[reg_out] = ps1_out;
+
+		dprintk(KERN_INFO "PS2 ps1 -> f(0x%x, 0x%x) = 0x%x\n",
+				  ps1_in1, ps1_in2, qpr[reg_out]);
+	}
+
+	return EMULATE_DONE;
+}
+
+static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc,
+				    int reg_out, int reg_in,
+				    void (*func)(struct thread_struct *t,
+						 u32 *dst, u32 *src1))
+{
+	u32 *qpr = vcpu->arch.qpr;
+	u64 *fpr = vcpu->arch.fpr;
+	u32 ps0_out, ps0_in;
+	u32 ps1_in;
+	struct thread_struct t;
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	/* RC */
+	WARN_ON(rc);
+
+	/* PS0 */
+	cvt_df((double*)&fpr[reg_in], (float*)&ps0_in, &t);
+	func(&t, &ps0_out, &ps0_in);
+
+	dprintk(KERN_INFO "PS1 ps0 -> f(0x%x) = 0x%x\n",
+			  ps0_in, ps0_out);
+
+	cvt_fd((float*)&ps0_out, (double*)&fpr[reg_out], &t);
+
+	/* PS1 */
+	ps1_in = qpr[reg_in];
+	func(&t, &qpr[reg_out], &ps1_in);
+
+	dprintk(KERN_INFO "PS1 ps1 -> f(0x%x) = 0x%x\n",
+			  ps1_in, qpr[reg_out]);
+
+	return EMULATE_DONE;
+}
+
+int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	u32 inst = kvmppc_get_last_inst(vcpu);
+	enum emulation_result emulated = EMULATE_DONE;
+
+	int ax_rd = inst_get_field(inst, 6, 10);
+	int ax_ra = inst_get_field(inst, 11, 15);
+	int ax_rb = inst_get_field(inst, 16, 20);
+	int ax_rc = inst_get_field(inst, 21, 25);
+	short full_d = inst_get_field(inst, 16, 31);
+
+	u64 *fpr_d = &vcpu->arch.fpr[ax_rd];
+	u64 *fpr_a = &vcpu->arch.fpr[ax_ra];
+	u64 *fpr_b = &vcpu->arch.fpr[ax_rb];
+	u64 *fpr_c = &vcpu->arch.fpr[ax_rc];
+
+	bool rcomp = (inst & 1) ? true : false;
+	u32 cr = kvmppc_get_cr(vcpu);
+	struct thread_struct t;
+#ifdef DEBUG
+	int i;
+#endif
+
+	t.fpscr.val = vcpu->arch.fpscr;
+
+	if (!kvmppc_inst_is_paired_single(vcpu, inst))
+		return EMULATE_FAIL;
+
+	if (!(vcpu->arch.msr & MSR_FP)) {
+		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL);
+		return EMULATE_AGAIN;
+	}
+
+	kvmppc_giveup_ext(vcpu, MSR_FP);
+	preempt_disable();
+	enable_kernel_fp();
+	/* Do we need to clear FE0 / FE1 here? Don't think so. */
+
+#ifdef DEBUG
+	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
+		u32 f;
+		cvt_df((double*)&vcpu->arch.fpr[i], (float*)&f, &t);
+		dprintk(KERN_INFO "FPR[%d] = 0x%x / 0x%llx    QPR[%d] = 0x%x\n",
+			i, f, vcpu->arch.fpr[i], i, vcpu->arch.qpr[i]);
+	}
+#endif
+
+	switch (get_op(inst)) {
+	case OP_PSQ_L:
+	{
+		ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0;
+		bool w = inst_get_field(inst, 16, 16) ? true : false;
+		int i = inst_get_field(inst, 17, 19);
+
+		addr += get_d_signext(inst);
+		emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i);
+		break;
+	}
+	case OP_PSQ_LU:
+	{
+		ulong addr = kvmppc_get_gpr(vcpu, ax_ra);
+		bool w = inst_get_field(inst, 16, 16) ? true : false;
+		int i = inst_get_field(inst, 17, 19);
+
+		addr += get_d_signext(inst);
+		emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i);
+
+		if (emulated == EMULATE_DONE)
+			kvmppc_set_gpr(vcpu, ax_ra, addr);
+		break;
+	}
+	case OP_PSQ_ST:
+	{
+		ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0;
+		bool w = inst_get_field(inst, 16, 16) ? true : false;
+		int i = inst_get_field(inst, 17, 19);
+
+		addr += get_d_signext(inst);
+		emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i);
+		break;
+	}
+	case OP_PSQ_STU:
+	{
+		ulong addr = kvmppc_get_gpr(vcpu, ax_ra);
+		bool w = inst_get_field(inst, 16, 16) ? true : false;
+		int i = inst_get_field(inst, 17, 19);
+
+		addr += get_d_signext(inst);
+		emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i);
+
+		if (emulated == EMULATE_DONE)
+			kvmppc_set_gpr(vcpu, ax_ra, addr);
+		break;
+	}
+	case 4:
+		/* X form */
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_4X_PS_CMPU0:
+			/* XXX */
+			emulated = EMULATE_FAIL;
+			break;
+		case OP_4X_PSQ_LX:
+		{
+			ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0;
+			bool w = inst_get_field(inst, 21, 21) ? true : false;
+			int i = inst_get_field(inst, 22, 24);
+
+			addr += kvmppc_get_gpr(vcpu, ax_rb);
+			emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i);
+			break;
+		}
+		case OP_4X_PS_CMPO0:
+			/* XXX */
+			emulated = EMULATE_FAIL;
+			break;
+		case OP_4X_PSQ_LUX:
+		{
+			ulong addr = kvmppc_get_gpr(vcpu, ax_ra);
+			bool w = inst_get_field(inst, 21, 21) ? true : false;
+			int i = inst_get_field(inst, 22, 24);
+
+			addr += kvmppc_get_gpr(vcpu, ax_rb);
+			emulated = kvmppc_emulate_psq_load(run, vcpu, ax_rd, addr, w, i);
+
+			if (emulated == EMULATE_DONE)
+				kvmppc_set_gpr(vcpu, ax_ra, addr);
+			break;
+		}
+		case OP_4X_PS_NEG:
+			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
+			vcpu->arch.fpr[ax_rd] ^= 0x8000000000000000ULL;
+			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
+			vcpu->arch.qpr[ax_rd] ^= 0x80000000;
+			break;
+		case OP_4X_PS_CMPU1:
+			/* XXX */
+			emulated = EMULATE_FAIL;
+			break;
+		case OP_4X_PS_MR:
+			WARN_ON(rcomp);
+			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
+			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
+			break;
+		case OP_4X_PS_CMPO1:
+			/* XXX */
+			emulated = EMULATE_FAIL;
+			break;
+		case OP_4X_PS_NABS:
+			WARN_ON(rcomp);
+			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
+			vcpu->arch.fpr[ax_rd] |= 0x8000000000000000ULL;
+			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
+			vcpu->arch.qpr[ax_rd] |= 0x80000000;
+			break;
+		case OP_4X_PS_ABS:
+			WARN_ON(rcomp);
+			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rb];
+			vcpu->arch.fpr[ax_rd] &= ~0x8000000000000000ULL;
+			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
+			vcpu->arch.qpr[ax_rd] &= ~0x80000000;
+			break;
+		case OP_4X_PS_MERGE00:
+			WARN_ON(rcomp);
+			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra];
+			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
+			cvt_df((double*)&vcpu->arch.fpr[ax_rb],
+			       (float*)&vcpu->arch.qpr[ax_rd], &t);
+			break;
+		case OP_4X_PS_MERGE01:
+			WARN_ON(rcomp);
+			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra];
+			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
+			break;
+		case OP_4X_PS_MERGE10:
+			WARN_ON(rcomp);
+			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
+			cvt_fd((float*)&vcpu->arch.qpr[ax_ra],
+			       (double*)&vcpu->arch.fpr[ax_rd], &t);
+			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
+			cvt_df((double*)&vcpu->arch.fpr[ax_rb],
+			       (float*)&vcpu->arch.qpr[ax_rd], &t);
+			break;
+		case OP_4X_PS_MERGE11:
+			WARN_ON(rcomp);
+			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
+			cvt_fd((float*)&vcpu->arch.qpr[ax_ra],
+			       (double*)&vcpu->arch.fpr[ax_rd], &t);
+			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
+			break;
+		}
+		/* XW form */
+		switch (inst_get_field(inst, 25, 30)) {
+		case OP_4XW_PSQ_STX:
+		{
+			ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0;
+			bool w = inst_get_field(inst, 21, 21) ? true : false;
+			int i = inst_get_field(inst, 22, 24);
+
+			addr += kvmppc_get_gpr(vcpu, ax_rb);
+			emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i);
+			break;
+		}
+		case OP_4XW_PSQ_STUX:
+		{
+			ulong addr = kvmppc_get_gpr(vcpu, ax_ra);
+			bool w = inst_get_field(inst, 21, 21) ? true : false;
+			int i = inst_get_field(inst, 22, 24);
+
+			addr += kvmppc_get_gpr(vcpu, ax_rb);
+			emulated = kvmppc_emulate_psq_store(run, vcpu, ax_rd, addr, w, i);
+
+			if (emulated == EMULATE_DONE)
+				kvmppc_set_gpr(vcpu, ax_ra, addr);
+			break;
+		}
+		}
+		/* A form */
+		switch (inst_get_field(inst, 26, 30)) {
+		case OP_4A_PS_SUM1:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_rb, ax_ra, SCALAR_NO_PS0 | SCALAR_HIGH, fps_fadds);
+			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_rc];
+			break;
+		case OP_4A_PS_SUM0:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rb, SCALAR_NO_PS1 | SCALAR_LOW, fps_fadds);
+			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rc];
+			break;
+		case OP_4A_PS_MULS0:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, SCALAR_HIGH, fps_fmuls);
+			break;
+		case OP_4A_PS_MULS1:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, SCALAR_LOW, fps_fmuls);
+			break;
+		case OP_4A_PS_MADDS0:
+			emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, ax_rb, SCALAR_HIGH, fps_fmadds);
+			break;
+		case OP_4A_PS_MADDS1:
+			emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, ax_rb, SCALAR_LOW, fps_fmadds);
+			break;
+		case OP_4A_PS_DIV:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rb, SCALAR_NONE, fps_fdivs);
+			break;
+		case OP_4A_PS_SUB:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rb, SCALAR_NONE, fps_fsubs);
+			break;
+		case OP_4A_PS_ADD:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rb, SCALAR_NONE, fps_fadds);
+			break;
+		case OP_4A_PS_SEL:
+			emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fsel);
+			break;
+		case OP_4A_PS_RES:
+			emulated = kvmppc_ps_one_in(vcpu, rcomp, ax_rd,
+					ax_rb, fps_fres);
+			break;
+		case OP_4A_PS_MUL:
+			emulated = kvmppc_ps_two_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, SCALAR_NONE, fps_fmuls);
+			break;
+		case OP_4A_PS_RSQRTE:
+			emulated = kvmppc_ps_one_in(vcpu, rcomp, ax_rd,
+					ax_rb, fps_frsqrte);
+			break;
+		case OP_4A_PS_MSUB:
+			emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fmsubs);
+			break;
+		case OP_4A_PS_MADD:
+			emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fmadds);
+			break;
+		case OP_4A_PS_NMSUB:
+			emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fnmsubs);
+			break;
+		case OP_4A_PS_NMADD:
+			emulated = kvmppc_ps_three_in(vcpu, rcomp, ax_rd,
+					ax_ra, ax_rc, ax_rb, SCALAR_NONE, fps_fnmadds);
+			break;
+		}
+		break;
+
+	/* Real FPU operations */
+
+	case OP_LFS:
+	{
+		ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d;
+
+		emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr,
+						   FPU_LS_SINGLE);
+		break;
+	}
+	case OP_LFSU:
+	{
+		ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d;
+
+		emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr,
+						   FPU_LS_SINGLE);
+
+		if (emulated == EMULATE_DONE)
+			kvmppc_set_gpr(vcpu, ax_ra, addr);
+		break;
+	}
+	case OP_LFD:
+	{
+		ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d;
+
+		emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr,
+						   FPU_LS_DOUBLE);
+		break;
+	}
+	case OP_LFDU:
+	{
+		ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d;
+
+		emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd, addr,
+						   FPU_LS_DOUBLE);
+
+		if (emulated == EMULATE_DONE)
+			kvmppc_set_gpr(vcpu, ax_ra, addr);
+		break;
+	}
+	case OP_STFS:
+	{
+		ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d;
+
+		emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr,
+						    FPU_LS_SINGLE);
+		break;
+	}
+	case OP_STFSU:
+	{
+		ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d;
+
+		emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr,
+						    FPU_LS_SINGLE);
+
+		if (emulated == EMULATE_DONE)
+			kvmppc_set_gpr(vcpu, ax_ra, addr);
+		break;
+	}
+	case OP_STFD:
+	{
+		ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) + full_d;
+
+		emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr,
+						    FPU_LS_DOUBLE);
+		break;
+	}
+	case OP_STFDU:
+	{
+		ulong addr = kvmppc_get_gpr(vcpu, ax_ra) + full_d;
+
+		emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd, addr,
+						    FPU_LS_DOUBLE);
+
+		if (emulated == EMULATE_DONE)
+			kvmppc_set_gpr(vcpu, ax_ra, addr);
+		break;
+	}
+	case 31:
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_31_LFSX:
+		{
+			ulong addr = ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0;
+
+			addr += kvmppc_get_gpr(vcpu, ax_rb);
+			emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd,
+							   addr, FPU_LS_SINGLE);
+			break;
+		}
+		case OP_31_LFSUX:
+		{
+			ulong addr = kvmppc_get_gpr(vcpu, ax_ra) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd,
+							   addr, FPU_LS_SINGLE);
+
+			if (emulated == EMULATE_DONE)
+				kvmppc_set_gpr(vcpu, ax_ra, addr);
+			break;
+		}
+		case OP_31_LFDX:
+		{
+			ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd,
+							   addr, FPU_LS_DOUBLE);
+			break;
+		}
+		case OP_31_LFDUX:
+		{
+			ulong addr = kvmppc_get_gpr(vcpu, ax_ra) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_load(run, vcpu, ax_rd,
+							   addr, FPU_LS_DOUBLE);
+
+			if (emulated == EMULATE_DONE)
+				kvmppc_set_gpr(vcpu, ax_ra, addr);
+			break;
+		}
+		case OP_31_STFSX:
+		{
+			ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd,
+							    addr, FPU_LS_SINGLE);
+			break;
+		}
+		case OP_31_STFSUX:
+		{
+			ulong addr = kvmppc_get_gpr(vcpu, ax_ra) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd,
+							    addr, FPU_LS_SINGLE);
+
+			if (emulated == EMULATE_DONE)
+				kvmppc_set_gpr(vcpu, ax_ra, addr);
+			break;
+		}
+		case OP_31_STFX:
+		{
+			ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd,
+							    addr, FPU_LS_DOUBLE);
+			break;
+		}
+		case OP_31_STFUX:
+		{
+			ulong addr = kvmppc_get_gpr(vcpu, ax_ra) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd,
+							    addr, FPU_LS_DOUBLE);
+
+			if (emulated == EMULATE_DONE)
+				kvmppc_set_gpr(vcpu, ax_ra, addr);
+			break;
+		}
+		case OP_31_STFIWX:
+		{
+			ulong addr = (ax_ra ? kvmppc_get_gpr(vcpu, ax_ra) : 0) +
+				     kvmppc_get_gpr(vcpu, ax_rb);
+
+			emulated = kvmppc_emulate_fpr_store(run, vcpu, ax_rd,
+							    addr,
+							    FPU_LS_SINGLE_LOW);
+			break;
+		}
+			break;
+		}
+		break;
+	case 59:
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_59_FADDS:
+			fpd_fadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FSUBS:
+			fpd_fsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FDIVS:
+			fpd_fdivs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FRES:
+			fpd_fres(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FRSQRTES:
+			fpd_frsqrtes(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		}
+		switch (inst_get_field(inst, 26, 30)) {
+		case OP_59_FMULS:
+			fpd_fmuls(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FMSUBS:
+			fpd_fmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FMADDS:
+			fpd_fmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FNMSUBS:
+			fpd_fnmsubs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_59_FNMADDS:
+			fpd_fnmadds(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		}
+		break;
+	case 63:
+		switch (inst_get_field(inst, 21, 30)) {
+		case OP_63_MTFSB0:
+		case OP_63_MTFSB1:
+		case OP_63_MCRFS:
+		case OP_63_MTFSFI:
+			/* XXX need to implement */
+			break;
+		case OP_63_MFFS:
+			/* XXX missing CR */
+			*fpr_d = vcpu->arch.fpscr;
+			break;
+		case OP_63_MTFSF:
+			/* XXX missing fm bits */
+			/* XXX missing CR */
+			vcpu->arch.fpscr = *fpr_b;
+			break;
+		case OP_63_FCMPU:
+		{
+			u32 tmp_cr;
+			u32 cr0_mask = 0xf0000000;
+			u32 cr_shift = inst_get_field(inst, 6, 8) * 4;
+
+			fpd_fcmpu(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b);
+			cr &= ~(cr0_mask >> cr_shift);
+			cr |= (cr & cr0_mask) >> cr_shift;
+			break;
+		}
+		case OP_63_FCMPO:
+		{
+			u32 tmp_cr;
+			u32 cr0_mask = 0xf0000000;
+			u32 cr_shift = inst_get_field(inst, 6, 8) * 4;
+
+			fpd_fcmpo(&vcpu->arch.fpscr, &tmp_cr, fpr_a, fpr_b);
+			cr &= ~(cr0_mask >> cr_shift);
+			cr |= (cr & cr0_mask) >> cr_shift;
+			break;
+		}
+		case OP_63_FNEG:
+			fpd_fneg(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			break;
+		case OP_63_FMR:
+			*fpr_d = *fpr_b;
+			break;
+		case OP_63_FABS:
+			fpd_fabs(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			break;
+		case OP_63_FCPSGN:
+			fpd_fcpsgn(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			break;
+		case OP_63_FDIV:
+			fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			break;
+		case OP_63_FADD:
+			fpd_fadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			break;
+		case OP_63_FSUB:
+			fpd_fsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_b);
+			break;
+		case OP_63_FCTIW:
+			fpd_fctiw(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			break;
+		case OP_63_FCTIWZ:
+			fpd_fctiwz(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			break;
+		case OP_63_FRSP:
+			fpd_frsp(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			kvmppc_sync_qpr(vcpu, ax_rd);
+			break;
+		case OP_63_FRSQRTE:
+		{
+			double one = 1.0f;
+
+			/* fD = sqrt(fB) */
+			fpd_fsqrt(&vcpu->arch.fpscr, &cr, fpr_d, fpr_b);
+			/* fD = 1.0f / fD */
+			fpd_fdiv(&vcpu->arch.fpscr, &cr, fpr_d, (u64*)&one, fpr_d);
+			break;
+		}
+		}
+		switch (inst_get_field(inst, 26, 30)) {
+		case OP_63_FMUL:
+			fpd_fmul(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c);
+			break;
+		case OP_63_FSEL:
+			fpd_fsel(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			break;
+		case OP_63_FMSUB:
+			fpd_fmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			break;
+		case OP_63_FMADD:
+			fpd_fmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			break;
+		case OP_63_FNMSUB:
+			fpd_fnmsub(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			break;
+		case OP_63_FNMADD:
+			fpd_fnmadd(&vcpu->arch.fpscr, &cr, fpr_d, fpr_a, fpr_c, fpr_b);
+			break;
+		}
+		break;
+	}
+
+#ifdef DEBUG
+	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
+		u32 f;
+		cvt_df((double*)&vcpu->arch.fpr[i], (float*)&f, &t);
+		dprintk(KERN_INFO "FPR[%d] = 0x%x\n", i, f);
+	}
+#endif
+
+	if (rcomp)
+		kvmppc_set_cr(vcpu, cr);
+
+	preempt_enable();
+
+	return emulated;
+}

arch/powerpc/kvm/book3s_64_rmhandlers.S → arch/powerpc/kvm/book3s_rmhandlers.S

@@ -22,7 +22,10 @@
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/asm-offsets.h>
+
+#ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/exception-64s.h>
+#endif
 
 /*****************************************************************************
  *                                                                           *
@@ -30,6 +33,39 @@
  *                                                                           *
  ****************************************************************************/
 
+#if defined(CONFIG_PPC_BOOK3S_64)
+
+#define LOAD_SHADOW_VCPU(reg)				\
+	mfspr	reg, SPRN_SPRG_PACA
+
+#define SHADOW_VCPU_OFF		PACA_KVM_SVCPU
+#define MSR_NOIRQ		MSR_KERNEL & ~(MSR_IR | MSR_DR)
+#define FUNC(name) 		GLUE(.,name)
+
+#elif defined(CONFIG_PPC_BOOK3S_32)
+
+#define LOAD_SHADOW_VCPU(reg)						\
+	mfspr	reg, SPRN_SPRG_THREAD;					\
+	lwz	reg, THREAD_KVM_SVCPU(reg);				\
+	/* PPC32 can have a NULL pointer - let's check for that */	\
+	mtspr   SPRN_SPRG_SCRATCH1, r12;	/* Save r12 */		\
+	mfcr	r12;							\
+	cmpwi	reg, 0;							\
+	bne	1f;							\
+	mfspr	reg, SPRN_SPRG_SCRATCH0;				\
+	mtcr	r12;							\
+	mfspr	r12, SPRN_SPRG_SCRATCH1;				\
+	b	kvmppc_resume_\intno;					\
+1:;									\
+	mtcr	r12;							\
+	mfspr	r12, SPRN_SPRG_SCRATCH1;				\
+	tophys(reg, reg)
+
+#define SHADOW_VCPU_OFF		0
+#define MSR_NOIRQ		MSR_KERNEL
+#define FUNC(name)		name
+
+#endif
 
 .macro INTERRUPT_TRAMPOLINE intno
 
@@ -42,19 +78,19 @@ kvmppc_trampoline_\intno:
 	 * First thing to do is to find out if we're coming
 	 * from a KVM guest or a Linux process.
 	 *
-	 * To distinguish, we check a magic byte in the PACA
+	 * To distinguish, we check a magic byte in the PACA/current
 	 */
-	mfspr	r13, SPRN_SPRG_PACA		/* r13 = PACA */
-	std	r12, PACA_KVM_SCRATCH0(r13)
+	LOAD_SHADOW_VCPU(r13)
+	PPC_STL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
 	mfcr	r12
-	stw	r12, PACA_KVM_SCRATCH1(r13)
-	lbz	r12, PACA_KVM_IN_GUEST(r13)
+	stw	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
+	lbz	r12, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13)
 	cmpwi	r12, KVM_GUEST_MODE_NONE
 	bne	..kvmppc_handler_hasmagic_\intno
 	/* No KVM guest? Then jump back to the Linux handler! */
-	lwz	r12, PACA_KVM_SCRATCH1(r13)
+	lwz	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
 	mtcr	r12
-	ld	r12, PACA_KVM_SCRATCH0(r13)
+	PPC_LL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
 	mfspr	r13, SPRN_SPRG_SCRATCH0		/* r13 = original r13 */
 	b	kvmppc_resume_\intno		/* Get back original handler */
 
@@ -76,9 +112,7 @@ kvmppc_trampoline_\intno:
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_SYSTEM_RESET
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_MACHINE_CHECK
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_STORAGE
-INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_SEGMENT
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_STORAGE
-INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_SEGMENT
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALIGNMENT
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PROGRAM
@@ -88,7 +122,14 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_SYSCALL
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_TRACE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PERFMON
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALTIVEC
+
+/* Those are only available on 64 bit machines */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_SEGMENT
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_SEGMENT
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_VSX
+#endif
 
 /*
  * Bring us back to the faulting code, but skip the
@@ -99,11 +140,11 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_VSX
  *
  * Input Registers:
  *
- * R12               = free
- * R13               = PACA
- * PACA.KVM.SCRATCH0 = guest R12
- * PACA.KVM.SCRATCH1 = guest CR
- * SPRG_SCRATCH0     = guest R13
+ * R12            = free
+ * R13            = Shadow VCPU (PACA)
+ * SVCPU.SCRATCH0 = guest R12
+ * SVCPU.SCRATCH1 = guest CR
+ * SPRG_SCRATCH0  = guest R13
  *
  */
 kvmppc_handler_skip_ins:
@@ -114,9 +155,9 @@ kvmppc_handler_skip_ins:
 	mtsrr0	r12
 
 	/* Clean up all state */
-	lwz	r12, PACA_KVM_SCRATCH1(r13)
+	lwz	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
 	mtcr	r12
-	ld	r12, PACA_KVM_SCRATCH0(r13)
+	PPC_LL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
 	mfspr	r13, SPRN_SPRG_SCRATCH0
 
 	/* And get back into the code */
@@ -147,41 +188,48 @@ kvmppc_handler_lowmem_trampoline_end:
  *
  * R3 = function
  * R4 = MSR
- * R5 = CTR
+ * R5 = scratch register
  *
  */
 _GLOBAL(kvmppc_rmcall)
-	mtmsr	r4		/* Disable relocation, so mtsrr
+	LOAD_REG_IMMEDIATE(r5, MSR_NOIRQ)
+	mtmsr	r5		/* Disable relocation and interrupts, so mtsrr
 				   doesn't get interrupted */
-	mtctr	r5
+	sync
 	mtsrr0	r3
 	mtsrr1	r4
 	RFI
 
+#if defined(CONFIG_PPC_BOOK3S_32)
+#define STACK_LR	INT_FRAME_SIZE+4
+#elif defined(CONFIG_PPC_BOOK3S_64)
+#define STACK_LR	_LINK
+#endif
+
 /*
  * Activate current's external feature (FPU/Altivec/VSX)
  */
-#define define_load_up(what) 				\
-							\
-_GLOBAL(kvmppc_load_up_ ## what);			\
-	subi	r1, r1, INT_FRAME_SIZE;			\
-	mflr	r3;					\
-	std	r3, _LINK(r1);				\
-	mfmsr	r4;					\
-	std	r31, GPR3(r1);				\
-	mr	r31, r4;				\
-	li	r5, MSR_DR;				\
-	oris	r5, r5, MSR_EE@h;			\
-	andc	r4, r4, r5;				\
-	mtmsr	r4;					\
-							\
-	bl	.load_up_ ## what;			\
-							\
-	mtmsr	r31;					\
-	ld	r3, _LINK(r1);				\
-	ld	r31, GPR3(r1);				\
-	addi	r1, r1, INT_FRAME_SIZE;			\
-	mtlr	r3;					\
+#define define_load_up(what) 					\
+								\
+_GLOBAL(kvmppc_load_up_ ## what);				\
+	PPC_STLU r1, -INT_FRAME_SIZE(r1);			\
+	mflr	r3;						\
+	PPC_STL	r3, STACK_LR(r1);				\
+	PPC_STL	r20, _NIP(r1);					\
+	mfmsr	r20;						\
+	LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE);			\
+	andc	r3,r20,r3;		/* Disable DR,EE */	\
+	mtmsr	r3;						\
+	sync;							\
+								\
+	bl	FUNC(load_up_ ## what);				\
+								\
+	mtmsr	r20;			/* Enable DR,EE */	\
+	sync;							\
+	PPC_LL	r3, STACK_LR(r1);				\
+	PPC_LL	r20, _NIP(r1);					\
+	mtlr	r3;						\
+	addi	r1, r1, INT_FRAME_SIZE;				\
 	blr
 
 define_load_up(fpu)
@@ -194,11 +242,10 @@ define_load_up(vsx)
 
 .global kvmppc_trampoline_lowmem
 kvmppc_trampoline_lowmem:
-	.long kvmppc_handler_lowmem_trampoline - _stext
+	.long kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START
 
 .global kvmppc_trampoline_enter
 kvmppc_trampoline_enter:
-	.long kvmppc_handler_trampoline_enter - _stext
-
-#include "book3s_64_slb.S"
+	.long kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START
 
+#include "book3s_segment.S"

arch/powerpc/kvm/book3s_segment.S

@@ -0,0 +1,259 @@
+/*
+ * 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 SUSE Linux Products GmbH 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+/* Real mode helpers */
+
+#if defined(CONFIG_PPC_BOOK3S_64)
+
+#define GET_SHADOW_VCPU(reg)    \
+	addi    reg, r13, PACA_KVM_SVCPU
+
+#elif defined(CONFIG_PPC_BOOK3S_32)
+
+#define GET_SHADOW_VCPU(reg)    			\
+	tophys(reg, r2);       			\
+	lwz     reg, (THREAD + THREAD_KVM_SVCPU)(reg);	\
+	tophys(reg, reg)
+
+#endif
+
+/* Disable for nested KVM */
+#define USE_QUICK_LAST_INST
+
+
+/* Get helper functions for subarch specific functionality */
+
+#if defined(CONFIG_PPC_BOOK3S_64)
+#include "book3s_64_slb.S"
+#elif defined(CONFIG_PPC_BOOK3S_32)
+#include "book3s_32_sr.S"
+#endif
+
+/******************************************************************************
+ *                                                                            *
+ *                               Entry code                                   *
+ *                                                                            *
+ *****************************************************************************/
+
+.global kvmppc_handler_trampoline_enter
+kvmppc_handler_trampoline_enter:
+
+	/* Required state:
+	 *
+	 * MSR = ~IR|DR
+	 * R13 = PACA
+	 * R1 = host R1
+	 * R2 = host R2
+	 * R10 = guest MSR
+	 * all other volatile GPRS = free
+	 * SVCPU[CR] = guest CR
+	 * SVCPU[XER] = guest XER
+	 * SVCPU[CTR] = guest CTR
+	 * SVCPU[LR] = guest LR
+	 */
+
+	/* r3 = shadow vcpu */
+	GET_SHADOW_VCPU(r3)
+
+	/* Move SRR0 and SRR1 into the respective regs */
+	PPC_LL  r9, SVCPU_PC(r3)
+	mtsrr0	r9
+	mtsrr1	r10
+
+	/* Activate guest mode, so faults get handled by KVM */
+	li	r11, KVM_GUEST_MODE_GUEST
+	stb	r11, SVCPU_IN_GUEST(r3)
+
+	/* Switch to guest segment. This is subarch specific. */
+	LOAD_GUEST_SEGMENTS
+
+	/* Enter guest */
+
+	PPC_LL	r4, (SVCPU_CTR)(r3)
+	PPC_LL	r5, (SVCPU_LR)(r3)
+	lwz	r6, (SVCPU_CR)(r3)
+	lwz	r7, (SVCPU_XER)(r3)
+
+	mtctr	r4
+	mtlr	r5
+	mtcr	r6
+	mtxer	r7
+
+	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)
+
+	PPC_LL	r3, (SVCPU_R3)(r3)
+
+	RFI
+kvmppc_handler_trampoline_enter_end:
+
+
+
+/******************************************************************************
+ *                                                                            *
+ *                               Exit code                                    *
+ *                                                                            *
+ *****************************************************************************/
+
+.global kvmppc_handler_trampoline_exit
+kvmppc_handler_trampoline_exit:
+
+	/* Register usage at this point:
+	 *
+	 * SPRG_SCRATCH0  = guest R13
+	 * R12            = exit handler id
+	 * R13            = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64]
+	 * SVCPU.SCRATCH0 = guest R12
+	 * SVCPU.SCRATCH1 = guest CR
+	 *
+	 */
+
+	/* Save registers */
+
+	PPC_STL	r0, (SHADOW_VCPU_OFF + SVCPU_R0)(r13)
+	PPC_STL	r1, (SHADOW_VCPU_OFF + SVCPU_R1)(r13)
+	PPC_STL	r2, (SHADOW_VCPU_OFF + SVCPU_R2)(r13)
+	PPC_STL	r3, (SHADOW_VCPU_OFF + SVCPU_R3)(r13)
+	PPC_STL	r4, (SHADOW_VCPU_OFF + SVCPU_R4)(r13)
+	PPC_STL	r5, (SHADOW_VCPU_OFF + SVCPU_R5)(r13)
+	PPC_STL	r6, (SHADOW_VCPU_OFF + SVCPU_R6)(r13)
+	PPC_STL	r7, (SHADOW_VCPU_OFF + SVCPU_R7)(r13)
+	PPC_STL	r8, (SHADOW_VCPU_OFF + SVCPU_R8)(r13)
+	PPC_STL	r9, (SHADOW_VCPU_OFF + SVCPU_R9)(r13)
+	PPC_STL	r10, (SHADOW_VCPU_OFF + SVCPU_R10)(r13)
+	PPC_STL	r11, (SHADOW_VCPU_OFF + SVCPU_R11)(r13)
+
+	/* Restore R1/R2 so we can handle faults */
+	PPC_LL	r1, (SHADOW_VCPU_OFF + SVCPU_HOST_R1)(r13)
+	PPC_LL	r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13)
+
+	/* Save guest PC and MSR */
+	mfsrr0	r3
+	mfsrr1	r4
+
+	PPC_STL	r3, (SHADOW_VCPU_OFF + SVCPU_PC)(r13)
+	PPC_STL	r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13)
+
+	/* Get scratch'ed off registers */
+	mfspr	r9, SPRN_SPRG_SCRATCH0
+	PPC_LL	r8, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
+	lwz	r7, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
+
+	PPC_STL	r9, (SHADOW_VCPU_OFF + SVCPU_R13)(r13)
+	PPC_STL	r8, (SHADOW_VCPU_OFF + SVCPU_R12)(r13)
+	stw	r7, (SHADOW_VCPU_OFF + SVCPU_CR)(r13)
+
+	/* Save more register state  */
+
+	mfxer	r5
+	mfdar	r6
+	mfdsisr	r7
+	mfctr	r8
+	mflr	r9
+
+	stw	r5, (SHADOW_VCPU_OFF + SVCPU_XER)(r13)
+	PPC_STL	r6, (SHADOW_VCPU_OFF + SVCPU_FAULT_DAR)(r13)
+	stw	r7, (SHADOW_VCPU_OFF + SVCPU_FAULT_DSISR)(r13)
+	PPC_STL	r8, (SHADOW_VCPU_OFF + SVCPU_CTR)(r13)
+	PPC_STL	r9, (SHADOW_VCPU_OFF + SVCPU_LR)(r13)
+
+	/*
+	 * In order for us to easily get the last instruction,
+	 * we got the #vmexit at, we exploit the fact that the
+	 * virtual layout is still the same here, so we can just
+	 * ld from the guest's PC address
+	 */
+
+	/* We only load the last instruction when it's safe */
+	cmpwi	r12, BOOK3S_INTERRUPT_DATA_STORAGE
+	beq	ld_last_inst
+	cmpwi	r12, BOOK3S_INTERRUPT_PROGRAM
+	beq	ld_last_inst
+	cmpwi	r12, BOOK3S_INTERRUPT_ALIGNMENT
+	beq-	ld_last_inst
+
+	b	no_ld_last_inst
+
+ld_last_inst:
+	/* Save off the guest instruction we're at */
+
+	/* In case lwz faults */
+	li	r0, KVM_INST_FETCH_FAILED
+
+#ifdef USE_QUICK_LAST_INST
+
+	/* Set guest mode to 'jump over instruction' so if lwz faults
+	 * we'll just continue at the next IP. */
+	li	r9, KVM_GUEST_MODE_SKIP
+	stb	r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13)
+
+	/*    1) enable paging for data */
+	mfmsr	r9
+	ori	r11, r9, MSR_DR			/* Enable paging for data */
+	mtmsr	r11
+	sync
+	/*    2) fetch the instruction */
+	lwz	r0, 0(r3)
+	/*    3) disable paging again */
+	mtmsr	r9
+	sync
+
+#endif
+	stw	r0, (SHADOW_VCPU_OFF + SVCPU_LAST_INST)(r13)
+
+no_ld_last_inst:
+
+	/* Unset guest mode */
+	li	r9, KVM_GUEST_MODE_NONE
+	stb	r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13)
+
+	/* Switch back to host MMU */
+	LOAD_HOST_SEGMENTS
+
+	/* Register usage at this point:
+	 *
+	 * R1       = host R1
+	 * R2       = host R2
+	 * R12      = exit handler id
+	 * R13      = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64]
+	 * SVCPU.*  = guest *
+	 *
+	 */
+
+	/* RFI into the highmem handler */
+	mfmsr	r7
+	ori	r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME	/* Enable paging */
+	mtsrr1	r7
+	/* Load highmem handler address */
+	PPC_LL	r8, (SHADOW_VCPU_OFF + SVCPU_VMHANDLER)(r13)
+	mtsrr0	r8
+
+	RFI
+kvmppc_handler_trampoline_exit_end:

arch/powerpc/kvm/booke.c

@@ -133,6 +133,12 @@ void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_EXTERNAL);
 }
 
+void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
+                                  struct kvm_interrupt *irq)
+{
+	clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
+}
+
 /* Deliver the interrupt of the corresponding priority, if possible. */
 static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                                         unsigned int priority)
@@ -479,6 +485,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
+	vcpu_load(vcpu);
+
 	regs->pc = vcpu->arch.pc;
 	regs->cr = kvmppc_get_cr(vcpu);
 	regs->ctr = vcpu->arch.ctr;
@@ -499,6 +507,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
 
+	vcpu_put(vcpu);
+
 	return 0;
 }
 
@@ -506,6 +516,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
+	vcpu_load(vcpu);
+
 	vcpu->arch.pc = regs->pc;
 	kvmppc_set_cr(vcpu, regs->cr);
 	vcpu->arch.ctr = regs->ctr;
@@ -525,6 +537,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
 
+	vcpu_put(vcpu);
+
 	return 0;
 }
 
@@ -553,7 +567,12 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
                                   struct kvm_translation *tr)
 {
-	return kvmppc_core_vcpu_translate(vcpu, tr);
+	int r;
+
+	vcpu_load(vcpu);
+	r = kvmppc_core_vcpu_translate(vcpu, tr);
+	vcpu_put(vcpu);
+	return r;
 }
 
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)

arch/powerpc/kvm/e500.c

@@ -161,7 +161,7 @@ static int __init kvmppc_e500_init(void)
 	flush_icache_range(kvmppc_booke_handlers,
 			kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
 
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
+	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
 }
 
 static void __init kvmppc_e500_exit(void)

arch/powerpc/kvm/emulate.c

@@ -38,10 +38,12 @@
 #define OP_31_XOP_LBZX      87
 #define OP_31_XOP_STWX      151
 #define OP_31_XOP_STBX      215
+#define OP_31_XOP_LBZUX     119
 #define OP_31_XOP_STBUX     247
 #define OP_31_XOP_LHZX      279
 #define OP_31_XOP_LHZUX     311
 #define OP_31_XOP_MFSPR     339
+#define OP_31_XOP_LHAX      343
 #define OP_31_XOP_STHX      407
 #define OP_31_XOP_STHUX     439
 #define OP_31_XOP_MTSPR     467
@@ -62,10 +64,12 @@
 #define OP_STBU 39
 #define OP_LHZ  40
 #define OP_LHZU 41
+#define OP_LHA  42
+#define OP_LHAU 43
 #define OP_STH  44
 #define OP_STHU 45
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
 static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
 {
 	return 1;
@@ -82,7 +86,7 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 	unsigned long dec_nsec;
 
 	pr_debug("mtDEC: %x\n", vcpu->arch.dec);
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
 	/* mtdec lowers the interrupt line when positive. */
 	kvmppc_core_dequeue_dec(vcpu);
 
@@ -128,7 +132,7 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
  * from opcode tables in the future. */
 int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
-	u32 inst = vcpu->arch.last_inst;
+	u32 inst = kvmppc_get_last_inst(vcpu);
 	u32 ea;
 	int ra;
 	int rb;
@@ -143,13 +147,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	pr_debug(KERN_INFO "Emulating opcode %d / %d\n", get_op(inst), get_xop(inst));
 
-	/* Try again next time */
-	if (inst == KVM_INST_FETCH_FAILED)
-		return EMULATE_DONE;
-
 	switch (get_op(inst)) {
 	case OP_TRAP:
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
 	case OP_TRAP_64:
 		kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP);
 #else
@@ -171,6 +171,19 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			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);
+			break;
+
 		case OP_31_XOP_STWX:
 			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
@@ -200,6 +213,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			kvmppc_set_gpr(vcpu, rs, ea);
 			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);
@@ -450,6 +468,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_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);
+		break;
+
 	case OP_STH:
 		rs = get_rs(inst);
 		emulated = kvmppc_handle_store(run, vcpu,
@@ -472,7 +502,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	if (emulated == EMULATE_FAIL) {
 		emulated = kvmppc_core_emulate_op(run, vcpu, inst, &advance);
-		if (emulated == EMULATE_FAIL) {
+		if (emulated == EMULATE_AGAIN) {
+			advance = 0;
+		} else if (emulated == EMULATE_FAIL) {
 			advance = 0;
 			printk(KERN_ERR "Couldn't emulate instruction 0x%08x "
 			       "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst));
@@ -480,10 +512,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	}
 
-	trace_kvm_ppc_instr(inst, vcpu->arch.pc, emulated);
+	trace_kvm_ppc_instr(inst, kvmppc_get_pc(vcpu), emulated);
 
+	/* Advance past emulated instruction. */
 	if (advance)
-		vcpu->arch.pc += 4; /* Advance past emulated instruction. */
+		kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4);
 
 	return emulated;
 }

arch/powerpc/kvm/fpu.S

@@ -0,0 +1,273 @@
+/*
+ *  FPU helper code to use FPU operations from inside the kernel
+ *
+ *    Copyright (C) 2010 Alexander Graf (agraf@suse.de)
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/* Instructions operating on single parameters */
+
+/*
+ * Single operation with one input operand
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (short*)&result
+ * R5 = (short*)&param1
+ */
+#define FPS_ONE_IN(name) 					\
+_GLOBAL(fps_ ## name);							\
+	lfd	0,0(r3);		/* load up fpscr value */	\
+	MTFSF_L(0);							\
+	lfs	0,0(r5);						\
+									\
+	name	0,0;							\
+									\
+	stfs	0,0(r4);						\
+	mffs	0;							\
+	stfd	0,0(r3);	/* save new fpscr value */	\
+	blr
+
+/*
+ * Single operation with two input operands
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (short*)&result
+ * R5 = (short*)&param1
+ * R6 = (short*)&param2
+ */
+#define FPS_TWO_IN(name) 					\
+_GLOBAL(fps_ ## name);							\
+	lfd	0,0(r3);		/* load up fpscr value */	\
+	MTFSF_L(0);							\
+	lfs	0,0(r5);						\
+	lfs	1,0(r6);						\
+									\
+	name	0,0,1;							\
+									\
+	stfs	0,0(r4);						\
+	mffs	0;							\
+	stfd	0,0(r3);		/* save new fpscr value */	\
+	blr
+
+/*
+ * Single operation with three input operands
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (short*)&result
+ * R5 = (short*)&param1
+ * R6 = (short*)&param2
+ * R7 = (short*)&param3
+ */
+#define FPS_THREE_IN(name) 					\
+_GLOBAL(fps_ ## name);							\
+	lfd	0,0(r3);		/* load up fpscr value */	\
+	MTFSF_L(0);							\
+	lfs	0,0(r5);						\
+	lfs	1,0(r6);						\
+	lfs	2,0(r7);						\
+									\
+	name	0,0,1,2;						\
+									\
+	stfs	0,0(r4);						\
+	mffs	0;							\
+	stfd	0,0(r3);		/* save new fpscr value */	\
+	blr
+
+FPS_ONE_IN(fres)
+FPS_ONE_IN(frsqrte)
+FPS_ONE_IN(fsqrts)
+FPS_TWO_IN(fadds)
+FPS_TWO_IN(fdivs)
+FPS_TWO_IN(fmuls)
+FPS_TWO_IN(fsubs)
+FPS_THREE_IN(fmadds)
+FPS_THREE_IN(fmsubs)
+FPS_THREE_IN(fnmadds)
+FPS_THREE_IN(fnmsubs)
+FPS_THREE_IN(fsel)
+
+
+/* Instructions operating on double parameters */
+
+/*
+ * Beginning of double instruction processing
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (u32*)&cr
+ * R5 = (double*)&result
+ * R6 = (double*)&param1
+ * R7 = (double*)&param2 [load_two]
+ * R8 = (double*)&param3 [load_three]
+ * LR = instruction call function
+ */
+fpd_load_three:
+	lfd	2,0(r8)			/* load param3 */
+fpd_load_two:
+	lfd	1,0(r7)			/* load param2 */
+fpd_load_one:
+	lfd	0,0(r6)			/* load param1 */
+fpd_load_none:
+	lfd	3,0(r3)			/* load up fpscr value */
+	MTFSF_L(3)
+	lwz	r6, 0(r4)		/* load cr */
+	mtcr	r6
+	blr
+
+/*
+ * End of double instruction processing
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (u32*)&cr
+ * R5 = (double*)&result
+ * LR = caller of instruction call function
+ */
+fpd_return:
+	mfcr	r6
+	stfd	0,0(r5)			/* save result */
+	mffs	0
+	stfd	0,0(r3)			/* save new fpscr value */
+	stw	r6,0(r4)		/* save new cr value */
+	blr
+
+/*
+ * Double operation with no input operand
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (u32*)&cr
+ * R5 = (double*)&result
+ */
+#define FPD_NONE_IN(name) 						\
+_GLOBAL(fpd_ ## name);							\
+	mflr	r12;							\
+	bl	fpd_load_none;						\
+	mtlr	r12;							\
+									\
+	name.	0;			/* call instruction */		\
+	b	fpd_return
+
+/*
+ * Double operation with one input operand
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (u32*)&cr
+ * R5 = (double*)&result
+ * R6 = (double*)&param1
+ */
+#define FPD_ONE_IN(name) 						\
+_GLOBAL(fpd_ ## name);							\
+	mflr	r12;							\
+	bl	fpd_load_one;						\
+	mtlr	r12;							\
+									\
+	name.	0,0;			/* call instruction */		\
+	b	fpd_return
+
+/*
+ * Double operation with two input operands
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (u32*)&cr
+ * R5 = (double*)&result
+ * R6 = (double*)&param1
+ * R7 = (double*)&param2
+ * R8 = (double*)&param3
+ */
+#define FPD_TWO_IN(name) 						\
+_GLOBAL(fpd_ ## name);							\
+	mflr	r12;							\
+	bl	fpd_load_two;						\
+	mtlr	r12;							\
+									\
+	name.	0,0,1;			/* call instruction */		\
+	b	fpd_return
+
+/*
+ * CR Double operation with two input operands
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (u32*)&cr
+ * R5 = (double*)&param1
+ * R6 = (double*)&param2
+ * R7 = (double*)&param3
+ */
+#define FPD_TWO_IN_CR(name)						\
+_GLOBAL(fpd_ ## name);							\
+	lfd	1,0(r6);		/* load param2 */		\
+	lfd	0,0(r5);		/* load param1 */		\
+	lfd	3,0(r3);		/* load up fpscr value */	\
+	MTFSF_L(3);							\
+	lwz	r6, 0(r4);		/* load cr */			\
+	mtcr	r6;							\
+									\
+	name	0,0,1;			/* call instruction */		\
+	mfcr	r6;							\
+	mffs	0;							\
+	stfd	0,0(r3);		/* save new fpscr value */	\
+	stw	r6,0(r4);		/* save new cr value */		\
+	blr
+
+/*
+ * Double operation with three input operands
+ *
+ * R3 = (double*)&fpscr
+ * R4 = (u32*)&cr
+ * R5 = (double*)&result
+ * R6 = (double*)&param1
+ * R7 = (double*)&param2
+ * R8 = (double*)&param3
+ */
+#define FPD_THREE_IN(name) 						\
+_GLOBAL(fpd_ ## name);							\
+	mflr	r12;							\
+	bl	fpd_load_three;						\
+	mtlr	r12;							\
+									\
+	name.	0,0,1,2;		/* call instruction */		\
+	b	fpd_return
+
+FPD_ONE_IN(fsqrts)
+FPD_ONE_IN(frsqrtes)
+FPD_ONE_IN(fres)
+FPD_ONE_IN(frsp)
+FPD_ONE_IN(fctiw)
+FPD_ONE_IN(fctiwz)
+FPD_ONE_IN(fsqrt)
+FPD_ONE_IN(fre)
+FPD_ONE_IN(frsqrte)
+FPD_ONE_IN(fneg)
+FPD_ONE_IN(fabs)
+FPD_TWO_IN(fadds)
+FPD_TWO_IN(fsubs)
+FPD_TWO_IN(fdivs)
+FPD_TWO_IN(fmuls)
+FPD_TWO_IN_CR(fcmpu)
+FPD_TWO_IN(fcpsgn)
+FPD_TWO_IN(fdiv)
+FPD_TWO_IN(fadd)
+FPD_TWO_IN(fmul)
+FPD_TWO_IN_CR(fcmpo)
+FPD_TWO_IN(fsub)
+FPD_THREE_IN(fmsubs)
+FPD_THREE_IN(fmadds)
+FPD_THREE_IN(fnmsubs)
+FPD_THREE_IN(fnmadds)
+FPD_THREE_IN(fsel)
+FPD_THREE_IN(fmsub)
+FPD_THREE_IN(fmadd)
+FPD_THREE_IN(fnmsub)
+FPD_THREE_IN(fnmadd)

arch/powerpc/kvm/powerpc.c

@@ -70,7 +70,7 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	case EMULATE_FAIL:
 		/* XXX Deliver Program interrupt to guest. */
 		printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__,
-		       vcpu->arch.last_inst);
+		       kvmppc_get_last_inst(vcpu));
 		r = RESUME_HOST;
 		break;
 	default:
@@ -148,6 +148,10 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 	switch (ext) {
 	case KVM_CAP_PPC_SEGSTATE:
+	case KVM_CAP_PPC_PAIRED_SINGLES:
+	case KVM_CAP_PPC_UNSET_IRQ:
+	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_PPC_OSI:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -193,12 +197,17 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
 	vcpu = kvmppc_core_vcpu_create(kvm, id);
-	kvmppc_create_vcpu_debugfs(vcpu, id);
+	if (!IS_ERR(vcpu))
+		kvmppc_create_vcpu_debugfs(vcpu, id);
 	return vcpu;
 }
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	/* Make sure we're not using the vcpu anymore */
+	hrtimer_cancel(&vcpu->arch.dec_timer);
+	tasklet_kill(&vcpu->arch.tasklet);
+
 	kvmppc_remove_vcpu_debugfs(vcpu);
 	kvmppc_core_vcpu_free(vcpu);
 }
@@ -278,7 +287,7 @@ static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu,
 static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
                                       struct kvm_run *run)
 {
-	ulong gpr;
+	u64 gpr;
 
 	if (run->mmio.len > sizeof(gpr)) {
 		printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len);
@@ -287,6 +296,7 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 
 	if (vcpu->arch.mmio_is_bigendian) {
 		switch (run->mmio.len) {
+		case 8: gpr = *(u64 *)run->mmio.data; break;
 		case 4: gpr = *(u32 *)run->mmio.data; break;
 		case 2: gpr = *(u16 *)run->mmio.data; break;
 		case 1: gpr = *(u8 *)run->mmio.data; break;
@@ -300,7 +310,43 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 		}
 	}
 
+	if (vcpu->arch.mmio_sign_extend) {
+		switch (run->mmio.len) {
+#ifdef CONFIG_PPC64
+		case 4:
+			gpr = (s64)(s32)gpr;
+			break;
+#endif
+		case 2:
+			gpr = (s64)(s16)gpr;
+			break;
+		case 1:
+			gpr = (s64)(s8)gpr;
+			break;
+		}
+	}
+
 	kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
+
+	switch (vcpu->arch.io_gpr & KVM_REG_EXT_MASK) {
+	case KVM_REG_GPR:
+		kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
+		break;
+	case KVM_REG_FPR:
+		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+		break;
+#ifdef CONFIG_PPC_BOOK3S
+	case KVM_REG_QPR:
+		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+		break;
+	case KVM_REG_FQPR:
+		vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+		vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+		break;
+#endif
+	default:
+		BUG();
+	}
 }
 
 int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
@@ -319,12 +365,25 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	vcpu->arch.mmio_is_bigendian = is_bigendian;
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_is_write = 0;
+	vcpu->arch.mmio_sign_extend = 0;
 
 	return EMULATE_DO_MMIO;
 }
 
+/* Same as above, but sign extends */
+int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                        unsigned int rt, unsigned int bytes, int is_bigendian)
+{
+	int r;
+
+	r = kvmppc_handle_load(run, vcpu, rt, bytes, is_bigendian);
+	vcpu->arch.mmio_sign_extend = 1;
+
+	return r;
+}
+
 int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                        u32 val, unsigned int bytes, int is_bigendian)
+                        u64 val, unsigned int bytes, int is_bigendian)
 {
 	void *data = run->mmio.data;
 
@@ -342,6 +401,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* Store the value at the lowest bytes in 'data'. */
 	if (is_bigendian) {
 		switch (bytes) {
+		case 8: *(u64 *)data = val; break;
 		case 4: *(u32 *)data = val; break;
 		case 2: *(u16 *)data = val; break;
 		case 1: *(u8  *)data = val; break;
@@ -376,6 +436,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (!vcpu->arch.dcr_is_write)
 			kvmppc_complete_dcr_load(vcpu, run);
 		vcpu->arch.dcr_needed = 0;
+	} else if (vcpu->arch.osi_needed) {
+		u64 *gprs = run->osi.gprs;
+		int i;
+
+		for (i = 0; i < 32; i++)
+			kvmppc_set_gpr(vcpu, i, gprs[i]);
+		vcpu->arch.osi_needed = 0;
 	}
 
 	kvmppc_core_deliver_interrupts(vcpu);
@@ -396,7 +463,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 {
-	kvmppc_core_queue_external(vcpu, irq);
+	if (irq->irq == KVM_INTERRUPT_UNSET)
+		kvmppc_core_dequeue_external(vcpu, irq);
+	else
+		kvmppc_core_queue_external(vcpu, irq);
 
 	if (waitqueue_active(&vcpu->wq)) {
 		wake_up_interruptible(&vcpu->wq);
@@ -406,6 +476,27 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+				     struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_PPC_OSI:
+		r = 0;
+		vcpu->arch.osi_enabled = true;
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+
+	return r;
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
                                     struct kvm_mp_state *mp_state)
 {
@@ -434,6 +525,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
 		break;
 	}
+	case KVM_ENABLE_CAP:
+	{
+		struct kvm_enable_cap cap;
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			goto out;
+		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}

arch/powerpc/mm/mmu_context_hash32.c

@@ -60,11 +60,7 @@
 static unsigned long next_mmu_context;
 static unsigned long context_map[LAST_CONTEXT / BITS_PER_LONG + 1];
 
-
-/*
- * Set up the context for a new address space.
- */
-int init_new_context(struct task_struct *t, struct mm_struct *mm)
+unsigned long __init_new_context(void)
 {
 	unsigned long ctx = next_mmu_context;
 
@@ -74,11 +70,30 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
 			ctx = 0;
 	}
 	next_mmu_context = (ctx + 1) & LAST_CONTEXT;
-	mm->context.id = ctx;
+
+	return ctx;
+}
+EXPORT_SYMBOL_GPL(__init_new_context);
+
+/*
+ * Set up the context for a new address space.
+ */
+int init_new_context(struct task_struct *t, struct mm_struct *mm)
+{
+	mm->context.id = __init_new_context();
 
 	return 0;
 }
 
+/*
+ * Free a context ID. Make sure to call this with preempt disabled!
+ */
+void __destroy_context(unsigned long ctx)
+{
+	clear_bit(ctx, context_map);
+}
+EXPORT_SYMBOL_GPL(__destroy_context);
+
 /*
  * We're finished using the context for an address space.
  */
@@ -86,7 +101,7 @@ void destroy_context(struct mm_struct *mm)
 {
 	preempt_disable();
 	if (mm->context.id != NO_CONTEXT) {
-		clear_bit(mm->context.id, context_map);
+		__destroy_context(mm->context.id);
 		mm->context.id = NO_CONTEXT;
 	}
 	preempt_enable();

arch/s390/kvm/kvm-s390.c

@@ -341,11 +341,13 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
-		goto out_free_cpu;
+		goto out_free_sie_block;
 	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
 		 vcpu->arch.sie_block);
 
 	return vcpu;
+out_free_sie_block:
+	free_page((unsigned long)(vcpu->arch.sie_block));
 out_free_cpu:
 	kfree(vcpu);
 out_nomem:
@@ -750,7 +752,7 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 static int __init kvm_s390_init(void)
 {
 	int ret;
-	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
+	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 	if (ret)
 		return ret;
 

arch/s390/kvm/kvm-s390.h

@@ -72,7 +72,7 @@ static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
 	struct kvm_memslots *memslots;
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	memslots = rcu_dereference(vcpu->kvm->memslots);
+	memslots = kvm_memslots(vcpu->kvm);
 
 	mem = &memslots->memslots[0];
 

arch/x86/include/asm/kvm.h

@@ -21,6 +21,7 @@
 #define __KVM_HAVE_PIT_STATE2
 #define __KVM_HAVE_XEN_HVM
 #define __KVM_HAVE_VCPU_EVENTS
+#define __KVM_HAVE_DEBUGREGS
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -257,6 +258,11 @@ struct kvm_reinject_control {
 /* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
 #define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
+#define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
+
+/* Interrupt shadow states */
+#define KVM_X86_SHADOW_INT_MOV_SS	0x01
+#define KVM_X86_SHADOW_INT_STI		0x02
 
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
@@ -271,7 +277,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 soft;
-		__u8 pad;
+		__u8 shadow;
 	} interrupt;
 	struct {
 		__u8 injected;
@@ -284,4 +290,13 @@ struct kvm_vcpu_events {
 	__u32 reserved[10];
 };
 
+/* for KVM_GET/SET_DEBUGREGS */
+struct kvm_debugregs {
+	__u64 db[4];
+	__u64 dr6;
+	__u64 dr7;
+	__u64 flags;
+	__u64 reserved[9];
+};
+
 #endif /* _ASM_X86_KVM_H */

arch/x86/include/asm/kvm_emulate.h

@@ -11,6 +11,8 @@
 #ifndef _ASM_X86_KVM_X86_EMULATE_H
 #define _ASM_X86_KVM_X86_EMULATE_H
 
+#include <asm/desc_defs.h>
+
 struct x86_emulate_ctxt;
 
 /*
@@ -62,6 +64,15 @@ struct x86_emulate_ops {
 	int (*read_std)(unsigned long addr, void *val,
 			unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
 
+	/*
+	 * write_std: Write bytes of standard (non-emulated/special) memory.
+	 *            Used for descriptor writing.
+	 *  @addr:  [IN ] Linear address to which to write.
+	 *  @val:   [OUT] Value write to memory, zero-extended to 'u_long'.
+	 *  @bytes: [IN ] Number of bytes to write to memory.
+	 */
+	int (*write_std)(unsigned long addr, void *val,
+			 unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
 	/*
 	 * fetch: Read bytes of standard (non-emulated/special) memory.
 	 *        Used for instruction fetch.
@@ -109,6 +120,23 @@ struct x86_emulate_ops {
 				unsigned int bytes,
 				struct kvm_vcpu *vcpu);
 
+	int (*pio_in_emulated)(int size, unsigned short port, void *val,
+			       unsigned int count, struct kvm_vcpu *vcpu);
+
+	int (*pio_out_emulated)(int size, unsigned short port, const void *val,
+				unsigned int count, struct kvm_vcpu *vcpu);
+
+	bool (*get_cached_descriptor)(struct desc_struct *desc,
+				      int seg, struct kvm_vcpu *vcpu);
+	void (*set_cached_descriptor)(struct desc_struct *desc,
+				      int seg, struct kvm_vcpu *vcpu);
+	u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu);
+	void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu);
+	void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu);
+	ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
+	void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
+	int (*cpl)(struct kvm_vcpu *vcpu);
+	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
@@ -124,6 +152,12 @@ struct fetch_cache {
 	unsigned long end;
 };
 
+struct read_cache {
+	u8 data[1024];
+	unsigned long pos;
+	unsigned long end;
+};
+
 struct decode_cache {
 	u8 twobyte;
 	u8 b;
@@ -139,7 +173,7 @@ struct decode_cache {
 	u8 seg_override;
 	unsigned int d;
 	unsigned long regs[NR_VCPU_REGS];
-	unsigned long eip, eip_orig;
+	unsigned long eip;
 	/* modrm */
 	u8 modrm;
 	u8 modrm_mod;
@@ -151,16 +185,15 @@ struct decode_cache {
 	void *modrm_ptr;
 	unsigned long modrm_val;
 	struct fetch_cache fetch;
+	struct read_cache io_read;
 };
 
-#define X86_SHADOW_INT_MOV_SS  1
-#define X86_SHADOW_INT_STI     2
-
 struct x86_emulate_ctxt {
 	/* Register state before/after emulation. */
 	struct kvm_vcpu *vcpu;
 
 	unsigned long eflags;
+	unsigned long eip; /* eip before instruction emulation */
 	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
 	int mode;
 	u32 cs_base;
@@ -168,6 +201,7 @@ struct x86_emulate_ctxt {
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
 
+	bool restart; /* restart string instruction after writeback */
 	/* decode cache */
 	struct decode_cache decode;
 };
@@ -194,5 +228,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
 		    struct x86_emulate_ops *ops);
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
 		     struct x86_emulate_ops *ops);
+int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
+			 struct x86_emulate_ops *ops,
+			 u16 tss_selector, int reason,
+			 bool has_error_code, u32 error_code);
 
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */

arch/x86/include/asm/kvm_host.h

@@ -171,15 +171,15 @@ struct kvm_pte_chain {
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
-		unsigned glevels:4;
 		unsigned level:4;
+		unsigned cr4_pae:1;
 		unsigned quadrant:2;
 		unsigned pad_for_nice_hex_output:6;
 		unsigned direct:1;
 		unsigned access:3;
 		unsigned invalid:1;
-		unsigned cr4_pge:1;
 		unsigned nxe:1;
+		unsigned cr0_wp:1;
 	};
 };
 
@@ -187,8 +187,6 @@ struct kvm_mmu_page {
 	struct list_head link;
 	struct hlist_node hash_link;
 
-	struct list_head oos_link;
-
 	/*
 	 * The following two entries are used to key the shadow page in the
 	 * hash table.
@@ -204,9 +202,9 @@ struct kvm_mmu_page {
 	 * in this shadow page.
 	 */
 	DECLARE_BITMAP(slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
-	int multimapped;         /* More than one parent_pte? */
-	int root_count;          /* Currently serving as active root */
+	bool multimapped;         /* More than one parent_pte? */
 	bool unsync;
+	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
 	union {
 		u64 *parent_pte;               /* !multimapped */
@@ -224,14 +222,9 @@ struct kvm_pv_mmu_op_buffer {
 
 struct kvm_pio_request {
 	unsigned long count;
-	int cur_count;
-	gva_t guest_gva;
 	int in;
 	int port;
 	int size;
-	int string;
-	int down;
-	int rep;
 };
 
 /*
@@ -320,6 +313,7 @@ struct kvm_vcpu_arch {
 	struct kvm_queued_exception {
 		bool pending;
 		bool has_error_code;
+		bool reinject;
 		u8 nr;
 		u32 error_code;
 	} exception;
@@ -362,8 +356,8 @@ struct kvm_vcpu_arch {
 	u64 *mce_banks;
 
 	/* used for guest single stepping over the given code position */
-	u16 singlestep_cs;
 	unsigned long singlestep_rip;
+
 	/* fields used by HYPER-V emulation */
 	u64 hv_vapic;
 };
@@ -389,6 +383,7 @@ struct kvm_arch {
 	unsigned int n_free_mmu_pages;
 	unsigned int n_requested_mmu_pages;
 	unsigned int n_alloc_mmu_pages;
+	atomic_t invlpg_counter;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
 	 * Hash table of struct kvm_mmu_page.
@@ -461,11 +456,6 @@ struct kvm_vcpu_stat {
 	u32 nmi_injections;
 };
 
-struct descriptor_table {
-	u16 limit;
-	unsigned long base;
-} __attribute__((packed));
-
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
@@ -503,12 +493,11 @@ struct kvm_x86_ops {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 	void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
 	void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
-	void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	int (*get_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long *dest);
-	int (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value);
+	void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+	void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
@@ -527,7 +516,8 @@ struct kvm_x86_ops {
 	void (*set_irq)(struct kvm_vcpu *vcpu);
 	void (*set_nmi)(struct kvm_vcpu *vcpu);
 	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
-				bool has_error_code, u32 error_code);
+				bool has_error_code, u32 error_code,
+				bool reinject);
 	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
 	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
 	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
@@ -541,6 +531,8 @@ struct kvm_x86_ops {
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
 
+	void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry);
+
 	const struct trace_print_flags *exit_reasons_str;
 };
 
@@ -587,23 +579,14 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
-void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
-		   unsigned long *rflags);
 
-unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
-void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
-		     unsigned long *rflags);
 void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 
 struct x86_emulate_ctxt;
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in,
-		     int size, unsigned port);
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
-			   int size, unsigned long count, int down,
-			    gva_t address, int rep, unsigned port);
+int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
@@ -616,12 +599,15 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
+		    bool has_error_code, u32 error_code);
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
 void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
+int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
+int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
 unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
@@ -634,6 +620,8 @@ void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
+void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
+void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
 			   u32 error_code);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
@@ -649,8 +637,6 @@ int emulator_write_emulated(unsigned long addr,
 			    unsigned int bytes,
 			    struct kvm_vcpu *vcpu);
 
-unsigned long segment_base(u16 selector);
-
 void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes,
@@ -675,7 +661,6 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_enable_tdp(void);
 void kvm_disable_tdp(void);
 
-int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
 int complete_pio(struct kvm_vcpu *vcpu);
 bool kvm_check_iopl(struct kvm_vcpu *vcpu);
 
@@ -724,23 +709,6 @@ static inline void kvm_load_ldt(u16 sel)
 	asm("lldt %0" : : "rm"(sel));
 }
 
-static inline void kvm_get_idt(struct descriptor_table *table)
-{
-	asm("sidt %0" : "=m"(*table));
-}
-
-static inline void kvm_get_gdt(struct descriptor_table *table)
-{
-	asm("sgdt %0" : "=m"(*table));
-}
-
-static inline unsigned long kvm_read_tr_base(void)
-{
-	u16 tr;
-	asm("str %0" : "=g"(tr));
-	return segment_base(tr);
-}
-
 #ifdef CONFIG_X86_64
 static inline unsigned long read_msr(unsigned long msr)
 {
@@ -826,4 +794,6 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_define_shared_msr(unsigned index, u32 msr);
 void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
+bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
+
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/include/asm/kvm_para.h

@@ -16,10 +16,23 @@
 #define KVM_FEATURE_CLOCKSOURCE		0
 #define KVM_FEATURE_NOP_IO_DELAY	1
 #define KVM_FEATURE_MMU_OP		2
+/* This indicates that the new set of kvmclock msrs
+ * are available. The use of 0x11 and 0x12 is deprecated
+ */
+#define KVM_FEATURE_CLOCKSOURCE2        3
+
+/* The last 8 bits are used to indicate how to interpret the flags field
+ * in pvclock structure. If no bits are set, all flags are ignored.
+ */
+#define KVM_FEATURE_CLOCKSOURCE_STABLE_BIT	24
 
 #define MSR_KVM_WALL_CLOCK  0x11
 #define MSR_KVM_SYSTEM_TIME 0x12
 
+/* Custom MSRs falls in the range 0x4b564d00-0x4b564dff */
+#define MSR_KVM_WALL_CLOCK_NEW  0x4b564d00
+#define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
+
 #define KVM_MAX_MMU_OP_BATCH           32
 
 /* Operations for KVM_HC_MMU_OP */

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

@@ -202,8 +202,9 @@
 #define MSR_IA32_EBL_CR_POWERON		0x0000002a
 #define MSR_IA32_FEATURE_CONTROL        0x0000003a
 
-#define FEATURE_CONTROL_LOCKED		(1<<0)
-#define FEATURE_CONTROL_VMXON_ENABLED	(1<<2)
+#define FEATURE_CONTROL_LOCKED				(1<<0)
+#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
+#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
 
 #define MSR_IA32_APICBASE		0x0000001b
 #define MSR_IA32_APICBASE_BSP		(1<<8)

arch/x86/include/asm/pvclock-abi.h

@@ -29,7 +29,8 @@ struct pvclock_vcpu_time_info {
 	u64   system_time;
 	u32   tsc_to_system_mul;
 	s8    tsc_shift;
-	u8    pad[3];
+	u8    flags;
+	u8    pad[2];
 } __attribute__((__packed__)); /* 32 bytes */
 
 struct pvclock_wall_clock {
@@ -38,5 +39,6 @@ struct pvclock_wall_clock {
 	u32   nsec;
 } __attribute__((__packed__));
 
+#define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */

arch/x86/include/asm/pvclock.h

@@ -6,6 +6,7 @@
 
 /* some helper functions for xen and kvm pv clock sources */
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+void pvclock_set_flags(u8 flags);
 unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
 			    struct pvclock_vcpu_time_info *vcpu,

arch/x86/include/asm/svm.h

@@ -81,7 +81,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 event_inj_err;
 	u64 nested_cr3;
 	u64 lbr_ctl;
-	u8 reserved_5[832];
+	u64 reserved_5;
+	u64 next_rip;
+	u8 reserved_6[816];
 };
 
 
@@ -115,6 +117,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
 #define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
 
+#define SVM_VM_CR_VALID_MASK	0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK  0x0010ULL
+
 struct __attribute__ ((__packed__)) vmcb_seg {
 	u16 selector;
 	u16 attrib;
@@ -238,6 +244,7 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
 #define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
 
 #define	SVM_EXIT_READ_CR0 	0x000
 #define	SVM_EXIT_READ_CR3 	0x003

arch/x86/include/asm/vmx.h

@@ -25,6 +25,8 @@
  *
  */
 
+#include <linux/types.h>
+
 /*
  * Definitions of Primary Processor-Based VM-Execution Controls.
  */
@@ -120,6 +122,8 @@ enum vmcs_field {
 	GUEST_IA32_DEBUGCTL_HIGH        = 0x00002803,
 	GUEST_IA32_PAT			= 0x00002804,
 	GUEST_IA32_PAT_HIGH		= 0x00002805,
+	GUEST_IA32_EFER			= 0x00002806,
+	GUEST_IA32_EFER_HIGH		= 0x00002807,
 	GUEST_PDPTR0                    = 0x0000280a,
 	GUEST_PDPTR0_HIGH               = 0x0000280b,
 	GUEST_PDPTR1                    = 0x0000280c,
@@ -130,6 +134,8 @@ enum vmcs_field {
 	GUEST_PDPTR3_HIGH               = 0x00002811,
 	HOST_IA32_PAT			= 0x00002c00,
 	HOST_IA32_PAT_HIGH		= 0x00002c01,
+	HOST_IA32_EFER			= 0x00002c02,
+	HOST_IA32_EFER_HIGH		= 0x00002c03,
 	PIN_BASED_VM_EXEC_CONTROL       = 0x00004000,
 	CPU_BASED_VM_EXEC_CONTROL       = 0x00004002,
 	EXCEPTION_BITMAP                = 0x00004004,
@@ -394,6 +400,10 @@ enum vmcs_field {
 #define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
 #define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
 
-
+struct vmx_msr_entry {
+	u32 index;
+	u32 reserved;
+	u64 value;
+} __aligned(16);
 
 #endif

arch/x86/kernel/kvmclock.c

@@ -29,6 +29,8 @@
 #define KVM_SCALE 22
 
 static int kvmclock = 1;
+static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -54,7 +56,8 @@ static unsigned long kvm_get_wallclock(void)
 
 	low = (int)__pa_symbol(&wall_clock);
 	high = ((u64)__pa_symbol(&wall_clock) >> 32);
-	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
+
+	native_write_msr(msr_kvm_wall_clock, low, high);
 
 	vcpu_time = &get_cpu_var(hv_clock);
 	pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
@@ -130,7 +133,8 @@ static int kvm_register_clock(char *txt)
 	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
 	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
 	       cpu, high, low, txt);
-	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
+
+	return native_write_msr_safe(msr_kvm_system_time, low, high);
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -165,14 +169,14 @@ static void __init kvm_smp_prepare_boot_cpu(void)
 #ifdef CONFIG_KEXEC
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
-	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_write_msr(msr_kvm_system_time, 0, 0);
 	native_machine_crash_shutdown(regs);
 }
 #endif
 
 static void kvm_shutdown(void)
 {
-	native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+	native_write_msr(msr_kvm_system_time, 0, 0);
 	native_machine_shutdown();
 }
 
@@ -181,27 +185,37 @@ void __init kvmclock_init(void)
 	if (!kvm_para_available())
 		return;
 
-	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-		if (kvm_register_clock("boot clock"))
-			return;
-		pv_time_ops.sched_clock = kvm_clock_read;
-		x86_platform.calibrate_tsc = kvm_get_tsc_khz;
-		x86_platform.get_wallclock = kvm_get_wallclock;
-		x86_platform.set_wallclock = kvm_set_wallclock;
+	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
+		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
+	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
+		return;
+
+	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+		msr_kvm_system_time, msr_kvm_wall_clock);
+
+	if (kvm_register_clock("boot clock"))
+		return;
+	pv_time_ops.sched_clock = kvm_clock_read;
+	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+	x86_platform.get_wallclock = kvm_get_wallclock;
+	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-		x86_cpuinit.setup_percpu_clockev =
-			kvm_setup_secondary_clock;
+	x86_cpuinit.setup_percpu_clockev =
+		kvm_setup_secondary_clock;
 #endif
 #ifdef CONFIG_SMP
-		smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
-		machine_ops.shutdown  = kvm_shutdown;
+	machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
-		machine_ops.crash_shutdown  = kvm_crash_shutdown;
+	machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
-		kvm_get_preset_lpj();
-		clocksource_register(&kvm_clock);
-		pv_info.paravirt_enabled = 1;
-		pv_info.name = "KVM";
-	}
+	kvm_get_preset_lpj();
+	clocksource_register(&kvm_clock);
+	pv_info.paravirt_enabled = 1;
+	pv_info.name = "KVM";
+
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 }

arch/x86/kernel/pvclock.c

@@ -31,8 +31,16 @@ struct pvclock_shadow_time {
 	u32 tsc_to_nsec_mul;
 	int tsc_shift;
 	u32 version;
+	u8  flags;
 };
 
+static u8 valid_flags __read_mostly = 0;
+
+void pvclock_set_flags(u8 flags)
+{
+	valid_flags = flags;
+}
+
 /*
  * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
  * yielding a 64-bit result.
@@ -91,6 +99,7 @@ static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
 		dst->system_timestamp  = src->system_time;
 		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
 		dst->tsc_shift         = src->tsc_shift;
+		dst->flags             = src->flags;
 		rmb();		/* test version after fetching data */
 	} while ((src->version & 1) || (dst->version != src->version));
 
@@ -109,11 +118,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
 	return pv_tsc_khz;
 }
 
+static atomic64_t last_value = ATOMIC64_INIT(0);
+
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 {
 	struct pvclock_shadow_time shadow;
 	unsigned version;
 	cycle_t ret, offset;
+	u64 last;
 
 	do {
 		version = pvclock_get_time_values(&shadow, src);
@@ -123,6 +135,31 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 		barrier();
 	} while (version != src->version);
 
+	if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
+		(shadow.flags & PVCLOCK_TSC_STABLE_BIT))
+		return ret;
+
+	/*
+	 * Assumption here is that last_value, a global accumulator, always goes
+	 * forward. If we are less than that, we should not be much smaller.
+	 * We assume there is an error marging we're inside, and then the correction
+	 * does not sacrifice accuracy.
+	 *
+	 * For reads: global may have changed between test and return,
+	 * but this means someone else updated poked the clock at a later time.
+	 * We just need to make sure we are not seeing a backwards event.
+	 *
+	 * For updates: last_value = ret is not enough, since two vcpus could be
+	 * updating at the same time, and one of them could be slightly behind,
+	 * making the assumption that last_value always go forward fail to hold.
+	 */
+	last = atomic64_read(&last_value);
+	do {
+		if (ret < last)
+			return last;
+		last = atomic64_cmpxchg(&last_value, last, ret);
+	} while (unlikely(last != ret));
+
 	return ret;
 }
 

arch/x86/kernel/tboot.c

@@ -46,6 +46,7 @@
 
 /* Global pointer to shared data; NULL means no measured launch. */
 struct tboot *tboot __read_mostly;
+EXPORT_SYMBOL(tboot);
 
 /* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */
 #define AP_WAIT_TIMEOUT		1

arch/x86/kvm/emulate.c

@@ -33,6 +33,7 @@
 #include <asm/kvm_emulate.h>
 
 #include "x86.h"
+#include "tss.h"
 
 /*
  * Opcode effective-address decode tables.
@@ -50,6 +51,8 @@
 #define DstReg      (2<<1)	/* Register operand. */
 #define DstMem      (3<<1)	/* Memory operand. */
 #define DstAcc      (4<<1)      /* Destination Accumulator */
+#define DstDI       (5<<1)	/* Destination is in ES:(E)DI */
+#define DstMem64    (6<<1)	/* 64bit memory operand */
 #define DstMask     (7<<1)
 /* Source operand type. */
 #define SrcNone     (0<<4)	/* No source operand. */
@@ -63,6 +66,7 @@
 #define SrcOne      (7<<4)	/* Implied '1' */
 #define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
 #define SrcImmU     (9<<4)      /* Immediate operand, unsigned */
+#define SrcSI       (0xa<<4)	/* Source is in the DS:RSI */
 #define SrcMask     (0xf<<4)
 /* Generic ModRM decode. */
 #define ModRM       (1<<8)
@@ -85,6 +89,9 @@
 #define Src2ImmByte (2<<29)
 #define Src2One     (3<<29)
 #define Src2Imm16   (4<<29)
+#define Src2Mem16   (5<<29) /* Used for Ep encoding. First argument has to be
+			       in memory and second argument is located
+			       immediately after the first one in memory. */
 #define Src2Mask    (7<<29)
 
 enum {
@@ -147,8 +154,8 @@ static u32 opcode_table[256] = {
 	0, 0, 0, 0,
 	/* 0x68 - 0x6F */
 	SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0,
-	SrcNone  | ByteOp  | ImplicitOps, SrcNone  | ImplicitOps, /* insb, insw/insd */
-	SrcNone  | ByteOp  | ImplicitOps, SrcNone  | ImplicitOps, /* outsb, outsw/outsd */
+	DstDI | ByteOp | Mov | String, DstDI | Mov | String, /* insb, insw/insd */
+	SrcSI | ByteOp | ImplicitOps | String, SrcSI | ImplicitOps | String, /* outsb, outsw/outsd */
 	/* 0x70 - 0x77 */
 	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
 	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
@@ -173,12 +180,12 @@ static u32 opcode_table[256] = {
 	/* 0xA0 - 0xA7 */
 	ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs,
 	ByteOp | DstMem | SrcReg | Mov | MemAbs, DstMem | SrcReg | Mov | MemAbs,
-	ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String,
-	ByteOp | ImplicitOps | String, ImplicitOps | String,
+	ByteOp | SrcSI | DstDI | Mov | String, SrcSI | DstDI | Mov | String,
+	ByteOp | SrcSI | DstDI | String, SrcSI | DstDI | String,
 	/* 0xA8 - 0xAF */
-	0, 0, ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String,
-	ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String,
-	ByteOp | ImplicitOps | String, ImplicitOps | String,
+	0, 0, ByteOp | DstDI | Mov | String, DstDI | Mov | String,
+	ByteOp | SrcSI | DstAcc | Mov | String, SrcSI | DstAcc | Mov | String,
+	ByteOp | DstDI | String, DstDI | String,
 	/* 0xB0 - 0xB7 */
 	ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov,
 	ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov,
@@ -204,13 +211,13 @@ static u32 opcode_table[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xE0 - 0xE7 */
 	0, 0, 0, 0,
-	ByteOp | SrcImmUByte, SrcImmUByte,
-	ByteOp | SrcImmUByte, SrcImmUByte,
+	ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc,
+	ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc,
 	/* 0xE8 - 0xEF */
 	SrcImm | Stack, SrcImm | ImplicitOps,
 	SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
+	SrcNone | ByteOp | DstAcc, SrcNone | DstAcc,
+	SrcNone | ByteOp | DstAcc, SrcNone | DstAcc,
 	/* 0xF0 - 0xF7 */
 	0, 0, 0, 0,
 	ImplicitOps | Priv, ImplicitOps, Group | Group3_Byte, Group | Group3,
@@ -343,7 +350,8 @@ static u32 group_table[] = {
 	[Group5*8] =
 	DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM,
 	SrcMem | ModRM | Stack, 0,
-	SrcMem | ModRM | Stack, 0, SrcMem | ModRM | Stack, 0,
+	SrcMem | ModRM | Stack, SrcMem | ModRM | Src2Mem16 | ImplicitOps,
+	SrcMem | ModRM | Stack, 0,
 	[Group7*8] =
 	0, 0, ModRM | SrcMem | Priv, ModRM | SrcMem | Priv,
 	SrcNone | ModRM | DstMem | Mov, 0,
@@ -353,14 +361,14 @@ static u32 group_table[] = {
 	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM | Lock,
 	DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock,
 	[Group9*8] =
-	0, ImplicitOps | ModRM | Lock, 0, 0, 0, 0, 0, 0,
+	0, DstMem64 | ModRM | Lock, 0, 0, 0, 0, 0, 0,
 };
 
 static u32 group2_table[] = {
 	[Group7*8] =
-	SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM,
+	SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM | Priv,
 	SrcNone | ModRM | DstMem | Mov, 0,
-	SrcMem16 | ModRM | Mov, 0,
+	SrcMem16 | ModRM | Mov | Priv, 0,
 	[Group9*8] =
 	0, 0, 0, 0, 0, 0, 0, 0,
 };
@@ -562,7 +570,7 @@ static u32 group2_table[] = {
 #define insn_fetch(_type, _size, _eip)                                  \
 ({	unsigned long _x;						\
 	rc = do_insn_fetch(ctxt, ops, (_eip), &_x, (_size));		\
-	if (rc != 0)							\
+	if (rc != X86EMUL_CONTINUE)					\
 		goto done;						\
 	(_eip) += (_size);						\
 	(_type)_x;							\
@@ -638,40 +646,40 @@ static unsigned long ss_base(struct x86_emulate_ctxt *ctxt)
 
 static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt,
 			      struct x86_emulate_ops *ops,
-			      unsigned long linear, u8 *dest)
+			      unsigned long eip, u8 *dest)
 {
 	struct fetch_cache *fc = &ctxt->decode.fetch;
 	int rc;
-	int size;
+	int size, cur_size;
 
-	if (linear < fc->start || linear >= fc->end) {
-		size = min(15UL, PAGE_SIZE - offset_in_page(linear));
-		rc = ops->fetch(linear, fc->data, size, ctxt->vcpu, NULL);
-		if (rc)
+	if (eip == fc->end) {
+		cur_size = fc->end - fc->start;
+		size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip));
+		rc = ops->fetch(ctxt->cs_base + eip, fc->data + cur_size,
+				size, ctxt->vcpu, NULL);
+		if (rc != X86EMUL_CONTINUE)
 			return rc;
-		fc->start = linear;
-		fc->end = linear + size;
+		fc->end += size;
 	}
-	*dest = fc->data[linear - fc->start];
-	return 0;
+	*dest = fc->data[eip - fc->start];
+	return X86EMUL_CONTINUE;
 }
 
 static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
 			 struct x86_emulate_ops *ops,
 			 unsigned long eip, void *dest, unsigned size)
 {
-	int rc = 0;
+	int rc;
 
 	/* x86 instructions are limited to 15 bytes. */
-	if (eip + size - ctxt->decode.eip_orig > 15)
+	if (eip + size - ctxt->eip > 15)
 		return X86EMUL_UNHANDLEABLE;
-	eip += ctxt->cs_base;
 	while (size--) {
 		rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++);
-		if (rc)
+		if (rc != X86EMUL_CONTINUE)
 			return rc;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 /*
@@ -702,7 +710,7 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt,
 	*address = 0;
 	rc = ops->read_std((unsigned long)ptr, (unsigned long *)size, 2,
 			   ctxt->vcpu, NULL);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rc = ops->read_std((unsigned long)ptr + 2, address, op_bytes,
 			   ctxt->vcpu, NULL);
@@ -782,7 +790,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	struct decode_cache *c = &ctxt->decode;
 	u8 sib;
 	int index_reg = 0, base_reg = 0, scale;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 
 	if (c->rex_prefix) {
 		c->modrm_reg = (c->rex_prefix & 4) << 1;	/* REX.R */
@@ -895,7 +903,7 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt,
 		      struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 
 	switch (c->ad_bytes) {
 	case 2:
@@ -916,14 +924,18 @@ int
 x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 	int mode = ctxt->mode;
 	int def_op_bytes, def_ad_bytes, group;
 
-	/* Shadow copy of register state. Committed on successful emulation. */
 
+	/* we cannot decode insn before we complete previous rep insn */
+	WARN_ON(ctxt->restart);
+
+	/* Shadow copy of register state. Committed on successful emulation. */
 	memset(c, 0, sizeof(struct decode_cache));
-	c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu);
+	c->eip = ctxt->eip;
+	c->fetch.start = c->fetch.end = c->eip;
 	ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
 
@@ -1015,11 +1027,6 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		}
 	}
 
-	if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) {
-		kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction");
-		return -1;
-	}
-
 	if (c->d & Group) {
 		group = c->d & GroupMask;
 		c->modrm = insn_fetch(u8, 1, c->eip);
@@ -1046,7 +1053,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		rc = decode_modrm(ctxt, ops);
 	else if (c->d & MemAbs)
 		rc = decode_abs(ctxt, ops);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
 	if (!c->has_seg_override)
@@ -1057,6 +1064,10 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 
 	if (c->ad_bytes != 8)
 		c->modrm_ea = (u32)c->modrm_ea;
+
+	if (c->rip_relative)
+		c->modrm_ea += c->eip;
+
 	/*
 	 * Decode and fetch the source operand: register, memory
 	 * or immediate.
@@ -1091,6 +1102,8 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			break;
 		}
 		c->src.type = OP_MEM;
+		c->src.ptr = (unsigned long *)c->modrm_ea;
+		c->src.val = 0;
 		break;
 	case SrcImm:
 	case SrcImmU:
@@ -1139,6 +1152,14 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->src.bytes = 1;
 		c->src.val = 1;
 		break;
+	case SrcSI:
+		c->src.type = OP_MEM;
+		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
+		c->src.ptr = (unsigned long *)
+			register_address(c,  seg_override_base(ctxt, c),
+					 c->regs[VCPU_REGS_RSI]);
+		c->src.val = 0;
+		break;
 	}
 
 	/*
@@ -1168,6 +1189,12 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->src2.bytes = 1;
 		c->src2.val = 1;
 		break;
+	case Src2Mem16:
+		c->src2.type = OP_MEM;
+		c->src2.bytes = 2;
+		c->src2.ptr = (unsigned long *)(c->modrm_ea + c->src.bytes);
+		c->src2.val = 0;
+		break;
 	}
 
 	/* Decode and fetch the destination operand: register or memory. */
@@ -1180,6 +1207,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			 c->twobyte && (c->b == 0xb6 || c->b == 0xb7));
 		break;
 	case DstMem:
+	case DstMem64:
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
 			c->dst.type = OP_REG;
@@ -1188,12 +1216,24 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			break;
 		}
 		c->dst.type = OP_MEM;
+		c->dst.ptr = (unsigned long *)c->modrm_ea;
+		if ((c->d & DstMask) == DstMem64)
+			c->dst.bytes = 8;
+		else
+			c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
+		c->dst.val = 0;
+		if (c->d & BitOp) {
+			unsigned long mask = ~(c->dst.bytes * 8 - 1);
+
+			c->dst.ptr = (void *)c->dst.ptr +
+						   (c->src.val & mask) / 8;
+		}
 		break;
 	case DstAcc:
 		c->dst.type = OP_REG;
-		c->dst.bytes = c->op_bytes;
+		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
 		c->dst.ptr = &c->regs[VCPU_REGS_RAX];
-		switch (c->op_bytes) {
+		switch (c->dst.bytes) {
 			case 1:
 				c->dst.val = *(u8 *)c->dst.ptr;
 				break;
@@ -1203,18 +1243,248 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			case 4:
 				c->dst.val = *(u32 *)c->dst.ptr;
 				break;
+			case 8:
+				c->dst.val = *(u64 *)c->dst.ptr;
+				break;
 		}
 		c->dst.orig_val = c->dst.val;
 		break;
+	case DstDI:
+		c->dst.type = OP_MEM;
+		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
+		c->dst.ptr = (unsigned long *)
+			register_address(c, es_base(ctxt),
+					 c->regs[VCPU_REGS_RDI]);
+		c->dst.val = 0;
+		break;
 	}
 
-	if (c->rip_relative)
-		c->modrm_ea += c->eip;
-
 done:
 	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
 }
 
+static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
+			   struct x86_emulate_ops *ops,
+			   unsigned int size, unsigned short port,
+			   void *dest)
+{
+	struct read_cache *rc = &ctxt->decode.io_read;
+
+	if (rc->pos == rc->end) { /* refill pio read ahead */
+		struct decode_cache *c = &ctxt->decode;
+		unsigned int in_page, n;
+		unsigned int count = c->rep_prefix ?
+			address_mask(c, c->regs[VCPU_REGS_RCX]) : 1;
+		in_page = (ctxt->eflags & EFLG_DF) ?
+			offset_in_page(c->regs[VCPU_REGS_RDI]) :
+			PAGE_SIZE - offset_in_page(c->regs[VCPU_REGS_RDI]);
+		n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size,
+			count);
+		if (n == 0)
+			n = 1;
+		rc->pos = rc->end = 0;
+		if (!ops->pio_in_emulated(size, port, rc->data, n, ctxt->vcpu))
+			return 0;
+		rc->end = n * size;
+	}
+
+	memcpy(dest, rc->data + rc->pos, size);
+	rc->pos += size;
+	return 1;
+}
+
+static u32 desc_limit_scaled(struct desc_struct *desc)
+{
+	u32 limit = get_desc_limit(desc);
+
+	return desc->g ? (limit << 12) | 0xfff : limit;
+}
+
+static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
+				     struct x86_emulate_ops *ops,
+				     u16 selector, struct desc_ptr *dt)
+{
+	if (selector & 1 << 2) {
+		struct desc_struct desc;
+		memset (dt, 0, sizeof *dt);
+		if (!ops->get_cached_descriptor(&desc, VCPU_SREG_LDTR, ctxt->vcpu))
+			return;
+
+		dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */
+		dt->address = get_desc_base(&desc);
+	} else
+		ops->get_gdt(dt, ctxt->vcpu);
+}
+
+/* allowed just for 8 bytes segments */
+static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				   struct x86_emulate_ops *ops,
+				   u16 selector, struct desc_struct *desc)
+{
+	struct desc_ptr dt;
+	u16 index = selector >> 3;
+	int ret;
+	u32 err;
+	ulong addr;
+
+	get_descriptor_table_ptr(ctxt, ops, selector, &dt);
+
+	if (dt.size < index * 8 + 7) {
+		kvm_inject_gp(ctxt->vcpu, selector & 0xfffc);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+	addr = dt.address + index * 8;
+	ret = ops->read_std(addr, desc, sizeof *desc, ctxt->vcpu,  &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT)
+		kvm_inject_page_fault(ctxt->vcpu, addr, err);
+
+       return ret;
+}
+
+/* allowed just for 8 bytes segments */
+static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				    struct x86_emulate_ops *ops,
+				    u16 selector, struct desc_struct *desc)
+{
+	struct desc_ptr dt;
+	u16 index = selector >> 3;
+	u32 err;
+	ulong addr;
+	int ret;
+
+	get_descriptor_table_ptr(ctxt, ops, selector, &dt);
+
+	if (dt.size < index * 8 + 7) {
+		kvm_inject_gp(ctxt->vcpu, selector & 0xfffc);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+
+	addr = dt.address + index * 8;
+	ret = ops->write_std(addr, desc, sizeof *desc, ctxt->vcpu, &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT)
+		kvm_inject_page_fault(ctxt->vcpu, addr, err);
+
+	return ret;
+}
+
+static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				   struct x86_emulate_ops *ops,
+				   u16 selector, int seg)
+{
+	struct desc_struct seg_desc;
+	u8 dpl, rpl, cpl;
+	unsigned err_vec = GP_VECTOR;
+	u32 err_code = 0;
+	bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
+	int ret;
+
+	memset(&seg_desc, 0, sizeof seg_desc);
+
+	if ((seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86)
+	    || ctxt->mode == X86EMUL_MODE_REAL) {
+		/* set real mode segment descriptor */
+		set_desc_base(&seg_desc, selector << 4);
+		set_desc_limit(&seg_desc, 0xffff);
+		seg_desc.type = 3;
+		seg_desc.p = 1;
+		seg_desc.s = 1;
+		goto load;
+	}
+
+	/* NULL selector is not valid for TR, CS and SS */
+	if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR)
+	    && null_selector)
+		goto exception;
+
+	/* TR should be in GDT only */
+	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
+		goto exception;
+
+	if (null_selector) /* for NULL selector skip all following checks */
+		goto load;
+
+	ret = read_segment_descriptor(ctxt, ops, selector, &seg_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	err_code = selector & 0xfffc;
+	err_vec = GP_VECTOR;
+
+	/* can't load system descriptor into segment selecor */
+	if (seg <= VCPU_SREG_GS && !seg_desc.s)
+		goto exception;
+
+	if (!seg_desc.p) {
+		err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
+		goto exception;
+	}
+
+	rpl = selector & 3;
+	dpl = seg_desc.dpl;
+	cpl = ops->cpl(ctxt->vcpu);
+
+	switch (seg) {
+	case VCPU_SREG_SS:
+		/*
+		 * segment is not a writable data segment or segment
+		 * selector's RPL != CPL or segment selector's RPL != CPL
+		 */
+		if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl)
+			goto exception;
+		break;
+	case VCPU_SREG_CS:
+		if (!(seg_desc.type & 8))
+			goto exception;
+
+		if (seg_desc.type & 4) {
+			/* conforming */
+			if (dpl > cpl)
+				goto exception;
+		} else {
+			/* nonconforming */
+			if (rpl > cpl || dpl != cpl)
+				goto exception;
+		}
+		/* CS(RPL) <- CPL */
+		selector = (selector & 0xfffc) | cpl;
+		break;
+	case VCPU_SREG_TR:
+		if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9))
+			goto exception;
+		break;
+	case VCPU_SREG_LDTR:
+		if (seg_desc.s || seg_desc.type != 2)
+			goto exception;
+		break;
+	default: /*  DS, ES, FS, or GS */
+		/*
+		 * segment is not a data or readable code segment or
+		 * ((segment is a data or nonconforming code segment)
+		 * and (both RPL and CPL > DPL))
+		 */
+		if ((seg_desc.type & 0xa) == 0x8 ||
+		    (((seg_desc.type & 0xc) != 0xc) &&
+		     (rpl > dpl && cpl > dpl)))
+			goto exception;
+		break;
+	}
+
+	if (seg_desc.s) {
+		/* mark segment as accessed */
+		seg_desc.type |= 1;
+		ret = write_segment_descriptor(ctxt, ops, selector, &seg_desc);
+		if (ret != X86EMUL_CONTINUE)
+			return ret;
+	}
+load:
+	ops->set_segment_selector(selector, seg, ctxt->vcpu);
+	ops->set_cached_descriptor(&seg_desc, seg, ctxt->vcpu);
+	return X86EMUL_CONTINUE;
+exception:
+	kvm_queue_exception_e(ctxt->vcpu, err_vec, err_code);
+	return X86EMUL_PROPAGATE_FAULT;
+}
+
 static inline void emulate_push(struct x86_emulate_ctxt *ctxt)
 {
 	struct decode_cache *c = &ctxt->decode;
@@ -1251,7 +1521,7 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt,
 	int rc;
 	unsigned long val, change_mask;
 	int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
-	int cpl = kvm_x86_ops->get_cpl(ctxt->vcpu);
+	int cpl = ops->cpl(ctxt->vcpu);
 
 	rc = emulate_pop(ctxt, ops, &val, len);
 	if (rc != X86EMUL_CONTINUE)
@@ -1306,10 +1576,10 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt,
 	int rc;
 
 	rc = emulate_pop(ctxt, ops, &selector, c->op_bytes);
-	if (rc != 0)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, seg);
+	rc = load_segment_descriptor(ctxt, ops, (u16)selector, seg);
 	return rc;
 }
 
@@ -1332,7 +1602,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt,
 			struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 	int reg = VCPU_REGS_RDI;
 
 	while (reg >= VCPU_REGS_RAX) {
@@ -1343,7 +1613,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt,
 		}
 
 		rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			break;
 		--reg;
 	}
@@ -1354,12 +1624,8 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
 				struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc;
 
-	rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes);
-	if (rc != 0)
-		return rc;
-	return 0;
+	return emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes);
 }
 
 static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt)
@@ -1395,7 +1661,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
 			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
 
 	switch (c->modrm_reg) {
 	case 0 ... 1:	/* test */
@@ -1408,11 +1673,9 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
 		emulate_1op("neg", c->dst, ctxt->eflags);
 		break;
 	default:
-		DPRINTF("Cannot emulate %02x\n", c->b);
-		rc = X86EMUL_UNHANDLEABLE;
-		break;
+		return 0;
 	}
-	return rc;
+	return 1;
 }
 
 static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
@@ -1442,20 +1705,14 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
 		emulate_push(ctxt);
 		break;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
-			       struct x86_emulate_ops *ops,
-			       unsigned long memop)
+			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	u64 old, new;
-	int rc;
-
-	rc = ops->read_emulated(memop, &old, 8, ctxt->vcpu);
-	if (rc != X86EMUL_CONTINUE)
-		return rc;
+	u64 old = c->dst.orig_val;
 
 	if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) ||
 	    ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) {
@@ -1463,17 +1720,13 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 		c->regs[VCPU_REGS_RAX] = (u32) (old >> 0);
 		c->regs[VCPU_REGS_RDX] = (u32) (old >> 32);
 		ctxt->eflags &= ~EFLG_ZF;
-
 	} else {
-		new = ((u64)c->regs[VCPU_REGS_RCX] << 32) |
+		c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) |
 		       (u32) c->regs[VCPU_REGS_RBX];
 
-		rc = ops->cmpxchg_emulated(memop, &old, &new, 8, ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			return rc;
 		ctxt->eflags |= EFLG_ZF;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static int emulate_ret_far(struct x86_emulate_ctxt *ctxt,
@@ -1484,14 +1737,14 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt,
 	unsigned long cs;
 
 	rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	if (c->op_bytes == 4)
 		c->eip = (u32)c->eip;
 	rc = emulate_pop(ctxt, ops, &cs, c->op_bytes);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, VCPU_SREG_CS);
+	rc = load_segment_descriptor(ctxt, ops, (u16)cs, VCPU_SREG_CS);
 	return rc;
 }
 
@@ -1544,7 +1797,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt,
 	default:
 		break;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
@@ -1598,8 +1851,11 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt)
 	u64 msr_data;
 
 	/* syscall is not available in real mode */
-	if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86)
-		return X86EMUL_UNHANDLEABLE;
+	if (ctxt->mode == X86EMUL_MODE_REAL ||
+	    ctxt->mode == X86EMUL_MODE_VM86) {
+		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
 
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
@@ -1649,14 +1905,16 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt)
 	/* inject #GP if in real mode */
 	if (ctxt->mode == X86EMUL_MODE_REAL) {
 		kvm_inject_gp(ctxt->vcpu, 0);
-		return X86EMUL_UNHANDLEABLE;
+		return X86EMUL_PROPAGATE_FAULT;
 	}
 
 	/* XXX sysenter/sysexit have not been tested in 64bit mode.
 	* Therefore, we inject an #UD.
 	*/
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		return X86EMUL_UNHANDLEABLE;
+	if (ctxt->mode == X86EMUL_MODE_PROT64) {
+		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
 
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
@@ -1711,7 +1969,7 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_REAL ||
 	    ctxt->mode == X86EMUL_MODE_VM86) {
 		kvm_inject_gp(ctxt->vcpu, 0);
-		return X86EMUL_UNHANDLEABLE;
+		return X86EMUL_PROPAGATE_FAULT;
 	}
 
 	setup_syscalls_segments(ctxt, &cs, &ss);
@@ -1756,7 +2014,8 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
+static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt,
+			      struct x86_emulate_ops *ops)
 {
 	int iopl;
 	if (ctxt->mode == X86EMUL_MODE_REAL)
@@ -1764,7 +2023,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_VM86)
 		return true;
 	iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
-	return kvm_x86_ops->get_cpl(ctxt->vcpu) > iopl;
+	return ops->cpl(ctxt->vcpu) > iopl;
 }
 
 static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt,
@@ -1801,22 +2060,419 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt,
 				 struct x86_emulate_ops *ops,
 				 u16 port, u16 len)
 {
-	if (emulator_bad_iopl(ctxt))
+	if (emulator_bad_iopl(ctxt, ops))
 		if (!emulator_io_port_access_allowed(ctxt, ops, port, len))
 			return false;
 	return true;
 }
 
+static u32 get_cached_descriptor_base(struct x86_emulate_ctxt *ctxt,
+				      struct x86_emulate_ops *ops,
+				      int seg)
+{
+	struct desc_struct desc;
+	if (ops->get_cached_descriptor(&desc, seg, ctxt->vcpu))
+		return get_desc_base(&desc);
+	else
+		return ~0;
+}
+
+static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt,
+				struct x86_emulate_ops *ops,
+				struct tss_segment_16 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+
+	tss->ip = c->eip;
+	tss->flag = ctxt->eflags;
+	tss->ax = c->regs[VCPU_REGS_RAX];
+	tss->cx = c->regs[VCPU_REGS_RCX];
+	tss->dx = c->regs[VCPU_REGS_RDX];
+	tss->bx = c->regs[VCPU_REGS_RBX];
+	tss->sp = c->regs[VCPU_REGS_RSP];
+	tss->bp = c->regs[VCPU_REGS_RBP];
+	tss->si = c->regs[VCPU_REGS_RSI];
+	tss->di = c->regs[VCPU_REGS_RDI];
+
+	tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu);
+	tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu);
+	tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu);
+	tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu);
+	tss->ldt = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu);
+}
+
+static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
+				 struct x86_emulate_ops *ops,
+				 struct tss_segment_16 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int ret;
+
+	c->eip = tss->ip;
+	ctxt->eflags = tss->flag | 2;
+	c->regs[VCPU_REGS_RAX] = tss->ax;
+	c->regs[VCPU_REGS_RCX] = tss->cx;
+	c->regs[VCPU_REGS_RDX] = tss->dx;
+	c->regs[VCPU_REGS_RBX] = tss->bx;
+	c->regs[VCPU_REGS_RSP] = tss->sp;
+	c->regs[VCPU_REGS_RBP] = tss->bp;
+	c->regs[VCPU_REGS_RSI] = tss->si;
+	c->regs[VCPU_REGS_RDI] = tss->di;
+
+	/*
+	 * SDM says that segment selectors are loaded before segment
+	 * descriptors
+	 */
+	ops->set_segment_selector(tss->ldt, VCPU_SREG_LDTR, ctxt->vcpu);
+	ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu);
+	ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu);
+
+	/*
+	 * Now load segment descriptors. If fault happenes at this stage
+	 * it is handled in a context of new task
+	 */
+	ret = load_segment_descriptor(ctxt, ops, tss->ldt, VCPU_SREG_LDTR);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	return X86EMUL_CONTINUE;
+}
+
+static int task_switch_16(struct x86_emulate_ctxt *ctxt,
+			  struct x86_emulate_ops *ops,
+			  u16 tss_selector, u16 old_tss_sel,
+			  ulong old_tss_base, struct desc_struct *new_desc)
+{
+	struct tss_segment_16 tss_seg;
+	int ret;
+	u32 err, new_tss_base = get_desc_base(new_desc);
+
+	ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	save_state_to_tss16(ctxt, ops, &tss_seg);
+
+	ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			     &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+		return ret;
+	}
+
+	if (old_tss_sel != 0xffff) {
+		tss_seg.prev_task_link = old_tss_sel;
+
+		ret = ops->write_std(new_tss_base,
+				     &tss_seg.prev_task_link,
+				     sizeof tss_seg.prev_task_link,
+				     ctxt->vcpu, &err);
+		if (ret == X86EMUL_PROPAGATE_FAULT) {
+			/* FIXME: need to provide precise fault address */
+			kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+			return ret;
+		}
+	}
+
+	return load_state_from_tss16(ctxt, ops, &tss_seg);
+}
+
+static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
+				struct x86_emulate_ops *ops,
+				struct tss_segment_32 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+
+	tss->cr3 = ops->get_cr(3, ctxt->vcpu);
+	tss->eip = c->eip;
+	tss->eflags = ctxt->eflags;
+	tss->eax = c->regs[VCPU_REGS_RAX];
+	tss->ecx = c->regs[VCPU_REGS_RCX];
+	tss->edx = c->regs[VCPU_REGS_RDX];
+	tss->ebx = c->regs[VCPU_REGS_RBX];
+	tss->esp = c->regs[VCPU_REGS_RSP];
+	tss->ebp = c->regs[VCPU_REGS_RBP];
+	tss->esi = c->regs[VCPU_REGS_RSI];
+	tss->edi = c->regs[VCPU_REGS_RDI];
+
+	tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu);
+	tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu);
+	tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu);
+	tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu);
+	tss->fs = ops->get_segment_selector(VCPU_SREG_FS, ctxt->vcpu);
+	tss->gs = ops->get_segment_selector(VCPU_SREG_GS, ctxt->vcpu);
+	tss->ldt_selector = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu);
+}
+
+static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
+				 struct x86_emulate_ops *ops,
+				 struct tss_segment_32 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int ret;
+
+	ops->set_cr(3, tss->cr3, ctxt->vcpu);
+	c->eip = tss->eip;
+	ctxt->eflags = tss->eflags | 2;
+	c->regs[VCPU_REGS_RAX] = tss->eax;
+	c->regs[VCPU_REGS_RCX] = tss->ecx;
+	c->regs[VCPU_REGS_RDX] = tss->edx;
+	c->regs[VCPU_REGS_RBX] = tss->ebx;
+	c->regs[VCPU_REGS_RSP] = tss->esp;
+	c->regs[VCPU_REGS_RBP] = tss->ebp;
+	c->regs[VCPU_REGS_RSI] = tss->esi;
+	c->regs[VCPU_REGS_RDI] = tss->edi;
+
+	/*
+	 * SDM says that segment selectors are loaded before segment
+	 * descriptors
+	 */
+	ops->set_segment_selector(tss->ldt_selector, VCPU_SREG_LDTR, ctxt->vcpu);
+	ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu);
+	ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu);
+	ops->set_segment_selector(tss->fs, VCPU_SREG_FS, ctxt->vcpu);
+	ops->set_segment_selector(tss->gs, VCPU_SREG_GS, ctxt->vcpu);
+
+	/*
+	 * Now load segment descriptors. If fault happenes at this stage
+	 * it is handled in a context of new task
+	 */
+	ret = load_segment_descriptor(ctxt, ops, tss->ldt_selector, VCPU_SREG_LDTR);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->fs, VCPU_SREG_FS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->gs, VCPU_SREG_GS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	return X86EMUL_CONTINUE;
+}
+
+static int task_switch_32(struct x86_emulate_ctxt *ctxt,
+			  struct x86_emulate_ops *ops,
+			  u16 tss_selector, u16 old_tss_sel,
+			  ulong old_tss_base, struct desc_struct *new_desc)
+{
+	struct tss_segment_32 tss_seg;
+	int ret;
+	u32 err, new_tss_base = get_desc_base(new_desc);
+
+	ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	save_state_to_tss32(ctxt, ops, &tss_seg);
+
+	ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			     &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+		return ret;
+	}
+
+	if (old_tss_sel != 0xffff) {
+		tss_seg.prev_task_link = old_tss_sel;
+
+		ret = ops->write_std(new_tss_base,
+				     &tss_seg.prev_task_link,
+				     sizeof tss_seg.prev_task_link,
+				     ctxt->vcpu, &err);
+		if (ret == X86EMUL_PROPAGATE_FAULT) {
+			/* FIXME: need to provide precise fault address */
+			kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+			return ret;
+		}
+	}
+
+	return load_state_from_tss32(ctxt, ops, &tss_seg);
+}
+
+static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
+				   struct x86_emulate_ops *ops,
+				   u16 tss_selector, int reason,
+				   bool has_error_code, u32 error_code)
+{
+	struct desc_struct curr_tss_desc, next_tss_desc;
+	int ret;
+	u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu);
+	ulong old_tss_base =
+		get_cached_descriptor_base(ctxt, ops, VCPU_SREG_TR);
+	u32 desc_limit;
+
+	/* FIXME: old_tss_base == ~0 ? */
+
+	ret = read_segment_descriptor(ctxt, ops, tss_selector, &next_tss_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = read_segment_descriptor(ctxt, ops, old_tss_sel, &curr_tss_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	/* FIXME: check that next_tss_desc is tss */
+
+	if (reason != TASK_SWITCH_IRET) {
+		if ((tss_selector & 3) > next_tss_desc.dpl ||
+		    ops->cpl(ctxt->vcpu) > next_tss_desc.dpl) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return X86EMUL_PROPAGATE_FAULT;
+		}
+	}
+
+	desc_limit = desc_limit_scaled(&next_tss_desc);
+	if (!next_tss_desc.p ||
+	    ((desc_limit < 0x67 && (next_tss_desc.type & 8)) ||
+	     desc_limit < 0x2b)) {
+		kvm_queue_exception_e(ctxt->vcpu, TS_VECTOR,
+				      tss_selector & 0xfffc);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+
+	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
+		curr_tss_desc.type &= ~(1 << 1); /* clear busy flag */
+		write_segment_descriptor(ctxt, ops, old_tss_sel,
+					 &curr_tss_desc);
+	}
+
+	if (reason == TASK_SWITCH_IRET)
+		ctxt->eflags = ctxt->eflags & ~X86_EFLAGS_NT;
+
+	/* set back link to prev task only if NT bit is set in eflags
+	   note that old_tss_sel is not used afetr this point */
+	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
+		old_tss_sel = 0xffff;
+
+	if (next_tss_desc.type & 8)
+		ret = task_switch_32(ctxt, ops, tss_selector, old_tss_sel,
+				     old_tss_base, &next_tss_desc);
+	else
+		ret = task_switch_16(ctxt, ops, tss_selector, old_tss_sel,
+				     old_tss_base, &next_tss_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE)
+		ctxt->eflags = ctxt->eflags | X86_EFLAGS_NT;
+
+	if (reason != TASK_SWITCH_IRET) {
+		next_tss_desc.type |= (1 << 1); /* set busy flag */
+		write_segment_descriptor(ctxt, ops, tss_selector,
+					 &next_tss_desc);
+	}
+
+	ops->set_cr(0,  ops->get_cr(0, ctxt->vcpu) | X86_CR0_TS, ctxt->vcpu);
+	ops->set_cached_descriptor(&next_tss_desc, VCPU_SREG_TR, ctxt->vcpu);
+	ops->set_segment_selector(tss_selector, VCPU_SREG_TR, ctxt->vcpu);
+
+	if (has_error_code) {
+		struct decode_cache *c = &ctxt->decode;
+
+		c->op_bytes = c->ad_bytes = (next_tss_desc.type & 8) ? 4 : 2;
+		c->lock_prefix = 0;
+		c->src.val = (unsigned long) error_code;
+		emulate_push(ctxt);
+	}
+
+	return ret;
+}
+
+int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
+			 struct x86_emulate_ops *ops,
+			 u16 tss_selector, int reason,
+			 bool has_error_code, u32 error_code)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int rc;
+
+	memset(c, 0, sizeof(struct decode_cache));
+	c->eip = ctxt->eip;
+	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
+	c->dst.type = OP_NONE;
+
+	rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason,
+				     has_error_code, error_code);
+
+	if (rc == X86EMUL_CONTINUE) {
+		memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
+		kvm_rip_write(ctxt->vcpu, c->eip);
+		rc = writeback(ctxt, ops);
+	}
+
+	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
+}
+
+static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned long base,
+			    int reg, struct operand *op)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int df = (ctxt->eflags & EFLG_DF) ? -1 : 1;
+
+	register_address_increment(c, &c->regs[reg], df * op->bytes);
+	op->ptr = (unsigned long *)register_address(c,  base, c->regs[reg]);
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
-	unsigned long memop = 0;
 	u64 msr_data;
-	unsigned long saved_eip = 0;
 	struct decode_cache *c = &ctxt->decode;
-	unsigned int port;
-	int io_dir_in;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
+	int saved_dst_type = c->dst.type;
 
 	ctxt->interruptibility = 0;
 
@@ -1826,26 +2482,30 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	 */
 
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
-	saved_eip = c->eip;
+
+	if (ctxt->mode == X86EMUL_MODE_PROT64 && (c->d & No64)) {
+		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+		goto done;
+	}
 
 	/* LOCK prefix is allowed only with some instructions */
-	if (c->lock_prefix && !(c->d & Lock)) {
+	if (c->lock_prefix && (!(c->d & Lock) || c->dst.type != OP_MEM)) {
 		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
 		goto done;
 	}
 
 	/* Privileged instruction can be executed only in CPL=0 */
-	if ((c->d & Priv) && kvm_x86_ops->get_cpl(ctxt->vcpu)) {
+	if ((c->d & Priv) && ops->cpl(ctxt->vcpu)) {
 		kvm_inject_gp(ctxt->vcpu, 0);
 		goto done;
 	}
 
-	if (((c->d & ModRM) && (c->modrm_mod != 3)) || (c->d & MemAbs))
-		memop = c->modrm_ea;
-
 	if (c->rep_prefix && (c->d & String)) {
+		ctxt->restart = true;
 		/* All REP prefixes have the same first termination condition */
-		if (c->regs[VCPU_REGS_RCX] == 0) {
+		if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) {
+		string_done:
+			ctxt->restart = false;
 			kvm_rip_write(ctxt->vcpu, c->eip);
 			goto done;
 		}
@@ -1857,25 +2517,18 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		 * 	- if REPNE/REPNZ and ZF = 1 then done
 		 */
 		if ((c->b == 0xa6) || (c->b == 0xa7) ||
-				(c->b == 0xae) || (c->b == 0xaf)) {
+		    (c->b == 0xae) || (c->b == 0xaf)) {
 			if ((c->rep_prefix == REPE_PREFIX) &&
-				((ctxt->eflags & EFLG_ZF) == 0)) {
-					kvm_rip_write(ctxt->vcpu, c->eip);
-					goto done;
-			}
+			    ((ctxt->eflags & EFLG_ZF) == 0))
+				goto string_done;
 			if ((c->rep_prefix == REPNE_PREFIX) &&
-				((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) {
-				kvm_rip_write(ctxt->vcpu, c->eip);
-				goto done;
-			}
+			    ((ctxt->eflags & EFLG_ZF) == EFLG_ZF))
+				goto string_done;
 		}
-		c->regs[VCPU_REGS_RCX]--;
-		c->eip = kvm_rip_read(ctxt->vcpu);
+		c->eip = ctxt->eip;
 	}
 
 	if (c->src.type == OP_MEM) {
-		c->src.ptr = (unsigned long *)memop;
-		c->src.val = 0;
 		rc = ops->read_emulated((unsigned long)c->src.ptr,
 					&c->src.val,
 					c->src.bytes,
@@ -1885,29 +2538,25 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->src.orig_val = c->src.val;
 	}
 
+	if (c->src2.type == OP_MEM) {
+		rc = ops->read_emulated((unsigned long)c->src2.ptr,
+					&c->src2.val,
+					c->src2.bytes,
+					ctxt->vcpu);
+		if (rc != X86EMUL_CONTINUE)
+			goto done;
+	}
+
 	if ((c->d & DstMask) == ImplicitOps)
 		goto special_insn;
 
 
-	if (c->dst.type == OP_MEM) {
-		c->dst.ptr = (unsigned long *)memop;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.val = 0;
-		if (c->d & BitOp) {
-			unsigned long mask = ~(c->dst.bytes * 8 - 1);
-
-			c->dst.ptr = (void *)c->dst.ptr +
-						   (c->src.val & mask) / 8;
-		}
-		if (!(c->d & Mov)) {
-			/* optimisation - avoid slow emulated read */
-			rc = ops->read_emulated((unsigned long)c->dst.ptr,
-						&c->dst.val,
-						c->dst.bytes,
-						ctxt->vcpu);
-			if (rc != X86EMUL_CONTINUE)
-				goto done;
-		}
+	if ((c->dst.type == OP_MEM) && !(c->d & Mov)) {
+		/* optimisation - avoid slow emulated read if Mov */
+		rc = ops->read_emulated((unsigned long)c->dst.ptr, &c->dst.val,
+					c->dst.bytes, ctxt->vcpu);
+		if (rc != X86EMUL_CONTINUE)
+			goto done;
 	}
 	c->dst.orig_val = c->dst.val;
 
@@ -1926,7 +2575,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0x07:		/* pop es */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x08 ... 0x0d:
@@ -1945,7 +2594,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0x17:		/* pop ss */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x18 ... 0x1d:
@@ -1957,7 +2606,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0x1f:		/* pop ds */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x20 ... 0x25:
@@ -1988,7 +2637,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	case 0x58 ... 0x5f: /* pop reg */
 	pop_instruction:
 		rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x60:	/* pusha */
@@ -1996,7 +2645,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0x61:	/* popa */
 		rc = emulate_popa(ctxt, ops);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x63:		/* movsxd */
@@ -2010,47 +2659,29 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0x6c:		/* insb */
 	case 0x6d:		/* insw/insd */
+		c->dst.bytes = min(c->dst.bytes, 4u);
 		if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX],
-					  (c->d & ByteOp) ? 1 : c->op_bytes)) {
+					  c->dst.bytes)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (kvm_emulate_pio_string(ctxt->vcpu,
-				1,
-				(c->d & ByteOp) ? 1 : c->op_bytes,
-				c->rep_prefix ?
-				address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
-				(ctxt->eflags & EFLG_DF),
-				register_address(c, es_base(ctxt),
-						 c->regs[VCPU_REGS_RDI]),
-				c->rep_prefix,
-				c->regs[VCPU_REGS_RDX]) == 0) {
-			c->eip = saved_eip;
-			return -1;
-		}
-		return 0;
+		if (!pio_in_emulated(ctxt, ops, c->dst.bytes,
+				     c->regs[VCPU_REGS_RDX], &c->dst.val))
+			goto done; /* IO is needed, skip writeback */
+		break;
 	case 0x6e:		/* outsb */
 	case 0x6f:		/* outsw/outsd */
+		c->src.bytes = min(c->src.bytes, 4u);
 		if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX],
-					  (c->d & ByteOp) ? 1 : c->op_bytes)) {
+					  c->src.bytes)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (kvm_emulate_pio_string(ctxt->vcpu,
-				0,
-				(c->d & ByteOp) ? 1 : c->op_bytes,
-				c->rep_prefix ?
-				address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
-				(ctxt->eflags & EFLG_DF),
-					 register_address(c,
-					  seg_override_base(ctxt, c),
-						 c->regs[VCPU_REGS_RSI]),
-				c->rep_prefix,
-				c->regs[VCPU_REGS_RDX]) == 0) {
-			c->eip = saved_eip;
-			return -1;
-		}
-		return 0;
+		ops->pio_out_emulated(c->src.bytes, c->regs[VCPU_REGS_RDX],
+				      &c->src.val, 1, ctxt->vcpu);
+
+		c->dst.type = OP_NONE; /* nothing to writeback */
+		break;
 	case 0x70 ... 0x7f: /* jcc (short) */
 		if (test_cc(c->b, ctxt->eflags))
 			jmp_rel(c, c->src.val);
@@ -2107,12 +2738,11 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	case 0x8c: { /* mov r/m, sreg */
 		struct kvm_segment segreg;
 
-		if (c->modrm_reg <= 5)
+		if (c->modrm_reg <= VCPU_SREG_GS)
 			kvm_get_segment(ctxt->vcpu, &segreg, c->modrm_reg);
 		else {
-			printk(KERN_INFO "0x8c: Invalid segreg in modrm byte 0x%02x\n",
-			       c->modrm);
-			goto cannot_emulate;
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
 		}
 		c->dst.val = segreg.selector;
 		break;
@@ -2132,16 +2762,16 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		}
 
 		if (c->modrm_reg == VCPU_SREG_SS)
-			toggle_interruptibility(ctxt, X86_SHADOW_INT_MOV_SS);
+			toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_MOV_SS);
 
-		rc = kvm_load_segment_descriptor(ctxt->vcpu, sel, c->modrm_reg);
+		rc = load_segment_descriptor(ctxt, ops, sel, c->modrm_reg);
 
 		c->dst.type = OP_NONE;  /* Disable writeback. */
 		break;
 	}
 	case 0x8f:		/* pop (sole member of Grp1a) */
 		rc = emulate_grp1a(ctxt, ops);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x90: /* nop / xchg r8,rax */
@@ -2175,89 +2805,16 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->dst.val = (unsigned long)c->regs[VCPU_REGS_RAX];
 		break;
 	case 0xa4 ... 0xa5:	/* movs */
-		c->dst.type = OP_MEM;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(c,
-						   es_base(ctxt),
-						   c->regs[VCPU_REGS_RDI]);
-		rc = ops->read_emulated(register_address(c,
-						seg_override_base(ctxt, c),
-						c->regs[VCPU_REGS_RSI]),
-					&c->dst.val,
-					c->dst.bytes, ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
-		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
-		break;
+		goto mov;
 	case 0xa6 ... 0xa7:	/* cmps */
-		c->src.type = OP_NONE; /* Disable writeback. */
-		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->src.ptr = (unsigned long *)register_address(c,
-				       seg_override_base(ctxt, c),
-						   c->regs[VCPU_REGS_RSI]);
-		rc = ops->read_emulated((unsigned long)c->src.ptr,
-					&c->src.val,
-					c->src.bytes,
-					ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-
 		c->dst.type = OP_NONE; /* Disable writeback. */
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(c,
-						   es_base(ctxt),
-						   c->regs[VCPU_REGS_RDI]);
-		rc = ops->read_emulated((unsigned long)c->dst.ptr,
-					&c->dst.val,
-					c->dst.bytes,
-					ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-
 		DPRINTF("cmps: mem1=0x%p mem2=0x%p\n", c->src.ptr, c->dst.ptr);
-
-		emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags);
-
-		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
-				       (ctxt->eflags & EFLG_DF) ? -c->src.bytes
-								  : c->src.bytes);
-		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-								  : c->dst.bytes);
-
-		break;
+		goto cmp;
 	case 0xaa ... 0xab:	/* stos */
-		c->dst.type = OP_MEM;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(c,
-						   es_base(ctxt),
-						   c->regs[VCPU_REGS_RDI]);
 		c->dst.val = c->regs[VCPU_REGS_RAX];
-		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
 		break;
 	case 0xac ... 0xad:	/* lods */
-		c->dst.type = OP_REG;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX];
-		rc = ops->read_emulated(register_address(c,
-						seg_override_base(ctxt, c),
-						c->regs[VCPU_REGS_RSI]),
-					&c->dst.val,
-					c->dst.bytes,
-					ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
-		break;
+		goto mov;
 	case 0xae ... 0xaf:	/* scas */
 		DPRINTF("Urk! I don't handle SCAS.\n");
 		goto cannot_emulate;
@@ -2277,7 +2834,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0xcb:		/* ret far */
 		rc = emulate_ret_far(ctxt, ops);
-		if (rc)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0xd0 ... 0xd1:	/* Grp2 */
@@ -2290,14 +2847,10 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0xe4: 	/* inb */
 	case 0xe5: 	/* in */
-		port = c->src.val;
-		io_dir_in = 1;
-		goto do_io;
+		goto do_io_in;
 	case 0xe6: /* outb */
 	case 0xe7: /* out */
-		port = c->src.val;
-		io_dir_in = 0;
-		goto do_io;
+		goto do_io_out;
 	case 0xe8: /* call (near) */ {
 		long int rel = c->src.val;
 		c->src.val = (unsigned long) c->eip;
@@ -2308,8 +2861,9 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	case 0xe9: /* jmp rel */
 		goto jmp;
 	case 0xea: /* jmp far */
-		if (kvm_load_segment_descriptor(ctxt->vcpu, c->src2.val,
-						VCPU_SREG_CS))
+	jump_far:
+		if (load_segment_descriptor(ctxt, ops, c->src2.val,
+					    VCPU_SREG_CS))
 			goto done;
 
 		c->eip = c->src.val;
@@ -2321,25 +2875,29 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0xec: /* in al,dx */
 	case 0xed: /* in (e/r)ax,dx */
-		port = c->regs[VCPU_REGS_RDX];
-		io_dir_in = 1;
-		goto do_io;
+		c->src.val = c->regs[VCPU_REGS_RDX];
+	do_io_in:
+		c->dst.bytes = min(c->dst.bytes, 4u);
+		if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			goto done;
+		}
+		if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val,
+				     &c->dst.val))
+			goto done; /* IO is needed */
+		break;
 	case 0xee: /* out al,dx */
 	case 0xef: /* out (e/r)ax,dx */
-		port = c->regs[VCPU_REGS_RDX];
-		io_dir_in = 0;
-	do_io:
-		if (!emulator_io_permited(ctxt, ops, port,
-					  (c->d & ByteOp) ? 1 : c->op_bytes)) {
+		c->src.val = c->regs[VCPU_REGS_RDX];
+	do_io_out:
+		c->dst.bytes = min(c->dst.bytes, 4u);
+		if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (kvm_emulate_pio(ctxt->vcpu, io_dir_in,
-				   (c->d & ByteOp) ? 1 : c->op_bytes,
-				   port) != 0) {
-			c->eip = saved_eip;
-			goto cannot_emulate;
-		}
+		ops->pio_out_emulated(c->dst.bytes, c->src.val, &c->dst.val, 1,
+				      ctxt->vcpu);
+		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xf4:              /* hlt */
 		ctxt->vcpu->arch.halt_request = 1;
@@ -2350,16 +2908,15 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xf6 ... 0xf7:	/* Grp3 */
-		rc = emulate_grp3(ctxt, ops);
-		if (rc != 0)
-			goto done;
+		if (!emulate_grp3(ctxt, ops))
+			goto cannot_emulate;
 		break;
 	case 0xf8: /* clc */
 		ctxt->eflags &= ~EFLG_CF;
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xfa: /* cli */
-		if (emulator_bad_iopl(ctxt))
+		if (emulator_bad_iopl(ctxt, ops))
 			kvm_inject_gp(ctxt->vcpu, 0);
 		else {
 			ctxt->eflags &= ~X86_EFLAGS_IF;
@@ -2367,10 +2924,10 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		}
 		break;
 	case 0xfb: /* sti */
-		if (emulator_bad_iopl(ctxt))
+		if (emulator_bad_iopl(ctxt, ops))
 			kvm_inject_gp(ctxt->vcpu, 0);
 		else {
-			toggle_interruptibility(ctxt, X86_SHADOW_INT_STI);
+			toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_STI);
 			ctxt->eflags |= X86_EFLAGS_IF;
 			c->dst.type = OP_NONE;	/* Disable writeback. */
 		}
@@ -2383,28 +2940,55 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		ctxt->eflags |= EFLG_DF;
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
-	case 0xfe ... 0xff:	/* Grp4/Grp5 */
+	case 0xfe: /* Grp4 */
+	grp45:
 		rc = emulate_grp45(ctxt, ops);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
+	case 0xff: /* Grp5 */
+		if (c->modrm_reg == 5)
+			goto jump_far;
+		goto grp45;
 	}
 
 writeback:
 	rc = writeback(ctxt, ops);
-	if (rc != 0)
+	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
+	/*
+	 * restore dst type in case the decoding will be reused
+	 * (happens for string instruction )
+	 */
+	c->dst.type = saved_dst_type;
+
+	if ((c->d & SrcMask) == SrcSI)
+		string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI,
+				&c->src);
+
+	if ((c->d & DstMask) == DstDI)
+		string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst);
+
+	if (c->rep_prefix && (c->d & String)) {
+		struct read_cache *rc = &ctxt->decode.io_read;
+		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
+		/*
+		 * Re-enter guest when pio read ahead buffer is empty or,
+		 * if it is not used, after each 1024 iteration.
+		 */
+		if ((rc->end == 0 && !(c->regs[VCPU_REGS_RCX] & 0x3ff)) ||
+		    (rc->end != 0 && rc->end == rc->pos))
+			ctxt->restart = false;
+	}
+
 	/* Commit shadow register state. */
 	memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
 	kvm_rip_write(ctxt->vcpu, c->eip);
+	ops->set_rflags(ctxt->vcpu, ctxt->eflags);
 
 done:
-	if (rc == X86EMUL_UNHANDLEABLE) {
-		c->eip = saved_eip;
-		return -1;
-	}
-	return 0;
+	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
 
 twobyte_insn:
 	switch (c->b) {
@@ -2418,18 +3002,18 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				goto cannot_emulate;
 
 			rc = kvm_fix_hypercall(ctxt->vcpu);
-			if (rc)
+			if (rc != X86EMUL_CONTINUE)
 				goto done;
 
 			/* Let the processor re-execute the fixed hypercall */
-			c->eip = kvm_rip_read(ctxt->vcpu);
+			c->eip = ctxt->eip;
 			/* Disable writeback. */
 			c->dst.type = OP_NONE;
 			break;
 		case 2: /* lgdt */
 			rc = read_descriptor(ctxt, ops, c->src.ptr,
 					     &size, &address, c->op_bytes);
-			if (rc)
+			if (rc != X86EMUL_CONTINUE)
 				goto done;
 			realmode_lgdt(ctxt->vcpu, size, address);
 			/* Disable writeback. */
@@ -2440,7 +3024,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				switch (c->modrm_rm) {
 				case 1:
 					rc = kvm_fix_hypercall(ctxt->vcpu);
-					if (rc)
+					if (rc != X86EMUL_CONTINUE)
 						goto done;
 					break;
 				default:
@@ -2450,7 +3034,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				rc = read_descriptor(ctxt, ops, c->src.ptr,
 						     &size, &address,
 						     c->op_bytes);
-				if (rc)
+				if (rc != X86EMUL_CONTINUE)
 					goto done;
 				realmode_lidt(ctxt->vcpu, size, address);
 			}
@@ -2459,15 +3043,18 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			break;
 		case 4: /* smsw */
 			c->dst.bytes = 2;
-			c->dst.val = realmode_get_cr(ctxt->vcpu, 0);
+			c->dst.val = ops->get_cr(0, ctxt->vcpu);
 			break;
 		case 6: /* lmsw */
-			realmode_lmsw(ctxt->vcpu, (u16)c->src.val,
-				      &ctxt->eflags);
+			ops->set_cr(0, (ops->get_cr(0, ctxt->vcpu) & ~0x0ful) |
+				    (c->src.val & 0x0f), ctxt->vcpu);
 			c->dst.type = OP_NONE;
 			break;
+		case 5: /* not defined */
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
 		case 7: /* invlpg*/
-			emulate_invlpg(ctxt->vcpu, memop);
+			emulate_invlpg(ctxt->vcpu, c->modrm_ea);
 			/* Disable writeback. */
 			c->dst.type = OP_NONE;
 			break;
@@ -2493,54 +3080,54 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->dst.type = OP_NONE;
 		break;
 	case 0x20: /* mov cr, reg */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
-		c->regs[c->modrm_rm] =
-				realmode_get_cr(ctxt->vcpu, c->modrm_reg);
+		switch (c->modrm_reg) {
+		case 1:
+		case 5 ... 7:
+		case 9 ... 15:
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
+		}
+		c->regs[c->modrm_rm] = ops->get_cr(c->modrm_reg, ctxt->vcpu);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x21: /* mov from dr to reg */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
-		rc = emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]);
-		if (rc)
-			goto cannot_emulate;
+		if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) &&
+		    (c->modrm_reg == 4 || c->modrm_reg == 5)) {
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
+		}
+		emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x22: /* mov reg, cr */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
-		realmode_set_cr(ctxt->vcpu,
-				c->modrm_reg, c->modrm_val, &ctxt->eflags);
+		ops->set_cr(c->modrm_reg, c->modrm_val, ctxt->vcpu);
 		c->dst.type = OP_NONE;
 		break;
 	case 0x23: /* mov from reg to dr */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
-		rc = emulator_set_dr(ctxt, c->modrm_reg,
-				     c->regs[c->modrm_rm]);
-		if (rc)
-			goto cannot_emulate;
+		if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) &&
+		    (c->modrm_reg == 4 || c->modrm_reg == 5)) {
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
+		}
+		emulator_set_dr(ctxt, c->modrm_reg, c->regs[c->modrm_rm]);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x30:
 		/* wrmsr */
 		msr_data = (u32)c->regs[VCPU_REGS_RAX]
 			| ((u64)c->regs[VCPU_REGS_RDX] << 32);
-		rc = kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data);
-		if (rc) {
+		if (kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
-			c->eip = kvm_rip_read(ctxt->vcpu);
+			goto done;
 		}
 		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;
 		break;
 	case 0x32:
 		/* rdmsr */
-		rc = kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data);
-		if (rc) {
+		if (kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
-			c->eip = kvm_rip_read(ctxt->vcpu);
+			goto done;
 		} else {
 			c->regs[VCPU_REGS_RAX] = (u32)msr_data;
 			c->regs[VCPU_REGS_RDX] = msr_data >> 32;
@@ -2577,7 +3164,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0xa1:	 /* pop fs */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0xa3:
@@ -2596,7 +3183,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0xa9:	/* pop gs */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0xab:
@@ -2668,16 +3255,14 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 							(u64) c->src.val;
 		break;
 	case 0xc7:		/* Grp9 (cmpxchg8b) */
-		rc = emulate_grp9(ctxt, ops, memop);
-		if (rc != 0)
+		rc = emulate_grp9(ctxt, ops);
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
-		c->dst.type = OP_NONE;
 		break;
 	}
 	goto writeback;
 
 cannot_emulate:
 	DPRINTF("Cannot emulate %02x\n", c->b);
-	c->eip = saved_eip;
 	return -1;
 }

arch/x86/kvm/i8259.c

@@ -33,6 +33,29 @@
 #include <linux/kvm_host.h>
 #include "trace.h"
 
+static void pic_lock(struct kvm_pic *s)
+	__acquires(&s->lock)
+{
+	raw_spin_lock(&s->lock);
+}
+
+static void pic_unlock(struct kvm_pic *s)
+	__releases(&s->lock)
+{
+	bool wakeup = s->wakeup_needed;
+	struct kvm_vcpu *vcpu;
+
+	s->wakeup_needed = false;
+
+	raw_spin_unlock(&s->lock);
+
+	if (wakeup) {
+		vcpu = s->kvm->bsp_vcpu;
+		if (vcpu)
+			kvm_vcpu_kick(vcpu);
+	}
+}
+
 static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
 {
 	s->isr &= ~(1 << irq);
@@ -45,19 +68,19 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
 	 * Other interrupt may be delivered to PIC while lock is dropped but
 	 * it should be safe since PIC state is already updated at this stage.
 	 */
-	raw_spin_unlock(&s->pics_state->lock);
+	pic_unlock(s->pics_state);
 	kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq);
-	raw_spin_lock(&s->pics_state->lock);
+	pic_lock(s->pics_state);
 }
 
 void kvm_pic_clear_isr_ack(struct kvm *kvm)
 {
 	struct kvm_pic *s = pic_irqchip(kvm);
 
-	raw_spin_lock(&s->lock);
+	pic_lock(s);
 	s->pics[0].isr_ack = 0xff;
 	s->pics[1].isr_ack = 0xff;
-	raw_spin_unlock(&s->lock);
+	pic_unlock(s);
 }
 
 /*
@@ -158,9 +181,9 @@ static void pic_update_irq(struct kvm_pic *s)
 
 void kvm_pic_update_irq(struct kvm_pic *s)
 {
-	raw_spin_lock(&s->lock);
+	pic_lock(s);
 	pic_update_irq(s);
-	raw_spin_unlock(&s->lock);
+	pic_unlock(s);
 }
 
 int kvm_pic_set_irq(void *opaque, int irq, int level)
@@ -168,14 +191,14 @@ int kvm_pic_set_irq(void *opaque, int irq, int level)
 	struct kvm_pic *s = opaque;
 	int ret = -1;
 
-	raw_spin_lock(&s->lock);
+	pic_lock(s);
 	if (irq >= 0 && irq < PIC_NUM_PINS) {
 		ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
 		pic_update_irq(s);
 		trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
 				      s->pics[irq >> 3].imr, ret == 0);
 	}
-	raw_spin_unlock(&s->lock);
+	pic_unlock(s);
 
 	return ret;
 }
@@ -205,7 +228,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 	int irq, irq2, intno;
 	struct kvm_pic *s = pic_irqchip(kvm);
 
-	raw_spin_lock(&s->lock);
+	pic_lock(s);
 	irq = pic_get_irq(&s->pics[0]);
 	if (irq >= 0) {
 		pic_intack(&s->pics[0], irq);
@@ -230,7 +253,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
 		intno = s->pics[0].irq_base + irq;
 	}
 	pic_update_irq(s);
-	raw_spin_unlock(&s->lock);
+	pic_unlock(s);
 
 	return intno;
 }
@@ -444,7 +467,7 @@ static int picdev_write(struct kvm_io_device *this,
 			printk(KERN_ERR "PIC: non byte write\n");
 		return 0;
 	}
-	raw_spin_lock(&s->lock);
+	pic_lock(s);
 	switch (addr) {
 	case 0x20:
 	case 0x21:
@@ -457,7 +480,7 @@ static int picdev_write(struct kvm_io_device *this,
 		elcr_ioport_write(&s->pics[addr & 1], addr, data);
 		break;
 	}
-	raw_spin_unlock(&s->lock);
+	pic_unlock(s);
 	return 0;
 }
 
@@ -474,7 +497,7 @@ static int picdev_read(struct kvm_io_device *this,
 			printk(KERN_ERR "PIC: non byte read\n");
 		return 0;
 	}
-	raw_spin_lock(&s->lock);
+	pic_lock(s);
 	switch (addr) {
 	case 0x20:
 	case 0x21:
@@ -488,7 +511,7 @@ static int picdev_read(struct kvm_io_device *this,
 		break;
 	}
 	*(unsigned char *)val = data;
-	raw_spin_unlock(&s->lock);
+	pic_unlock(s);
 	return 0;
 }
 
@@ -505,7 +528,7 @@ static void pic_irq_request(void *opaque, int level)
 	s->output = level;
 	if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) {
 		s->pics[0].isr_ack &= ~(1 << irq);
-		kvm_vcpu_kick(vcpu);
+		s->wakeup_needed = true;
 	}
 }
 

arch/x86/kvm/irq.h

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

arch/x86/kvm/kvm_timer.h

@@ -10,9 +10,7 @@ struct kvm_timer {
 };
 
 struct kvm_timer_ops {
-        bool (*is_periodic)(struct kvm_timer *);
+	bool (*is_periodic)(struct kvm_timer *);
 };
 
-
 enum hrtimer_restart kvm_timer_fn(struct hrtimer *data);
-

arch/x86/kvm/mmu.c

@@ -148,7 +148,6 @@ module_param(oos_shadow, bool, 0644);
 
 #include <trace/events/kvm.h>
 
-#undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
 #include "mmutrace.h"
 
@@ -174,12 +173,7 @@ struct kvm_shadow_walk_iterator {
 	     shadow_walk_okay(&(_walker));			\
 	     shadow_walk_next(&(_walker)))
 
-
-struct kvm_unsync_walk {
-	int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk);
-};
-
-typedef int (*mmu_parent_walk_fn) (struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp);
+typedef int (*mmu_parent_walk_fn) (struct kvm_mmu_page *sp);
 
 static struct kmem_cache *pte_chain_cache;
 static struct kmem_cache *rmap_desc_cache;
@@ -223,7 +217,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
-static int is_write_protection(struct kvm_vcpu *vcpu)
+static bool is_write_protection(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
 }
@@ -327,7 +321,6 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
 		page = alloc_page(GFP_KERNEL);
 		if (!page)
 			return -ENOMEM;
-		set_page_private(page, 0);
 		cache->objects[cache->nobjs++] = page_address(page);
 	}
 	return 0;
@@ -438,9 +431,9 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
 	int i;
 
 	gfn = unalias_gfn(kvm, gfn);
+	slot = gfn_to_memslot_unaliased(kvm, gfn);
 	for (i = PT_DIRECTORY_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
-		slot          = gfn_to_memslot_unaliased(kvm, gfn);
 		write_count   = slot_largepage_idx(gfn, slot, i);
 		*write_count -= 1;
 		WARN_ON(*write_count < 0);
@@ -654,7 +647,6 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
 {
 	struct kvm_rmap_desc *desc;
-	struct kvm_rmap_desc *prev_desc;
 	u64 *prev_spte;
 	int i;
 
@@ -666,7 +658,6 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
 		return NULL;
 	}
 	desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
-	prev_desc = NULL;
 	prev_spte = NULL;
 	while (desc) {
 		for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) {
@@ -794,7 +785,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 	int retval = 0;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; i++) {
 		struct kvm_memory_slot *memslot = &slots->memslots[i];
@@ -925,7 +916,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 	sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
-	INIT_LIST_HEAD(&sp->oos_link);
 	bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
 	sp->multimapped = 0;
 	sp->parent_pte = parent_pte;
@@ -1009,8 +999,7 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
 }
 
 
-static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			    mmu_parent_walk_fn fn)
+static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn)
 {
 	struct kvm_pte_chain *pte_chain;
 	struct hlist_node *node;
@@ -1019,8 +1008,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 
 	if (!sp->multimapped && sp->parent_pte) {
 		parent_sp = page_header(__pa(sp->parent_pte));
-		fn(vcpu, parent_sp);
-		mmu_parent_walk(vcpu, parent_sp, fn);
+		fn(parent_sp);
+		mmu_parent_walk(parent_sp, fn);
 		return;
 	}
 	hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
@@ -1028,8 +1017,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			if (!pte_chain->parent_ptes[i])
 				break;
 			parent_sp = page_header(__pa(pte_chain->parent_ptes[i]));
-			fn(vcpu, parent_sp);
-			mmu_parent_walk(vcpu, parent_sp, fn);
+			fn(parent_sp);
+			mmu_parent_walk(parent_sp, fn);
 		}
 }
 
@@ -1066,16 +1055,15 @@ static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp)
 		}
 }
 
-static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+static int unsync_walk_fn(struct kvm_mmu_page *sp)
 {
 	kvm_mmu_update_parents_unsync(sp);
 	return 1;
 }
 
-static void kvm_mmu_mark_parents_unsync(struct kvm_vcpu *vcpu,
-					struct kvm_mmu_page *sp)
+static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
 {
-	mmu_parent_walk(vcpu, sp, unsync_walk_fn);
+	mmu_parent_walk(sp, unsync_walk_fn);
 	kvm_mmu_update_parents_unsync(sp);
 }
 
@@ -1201,6 +1189,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	WARN_ON(!sp->unsync);
+	trace_kvm_mmu_sync_page(sp);
 	sp->unsync = 0;
 	--kvm->stat.mmu_unsync;
 }
@@ -1209,12 +1198,11 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp);
 
 static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
-	if (sp->role.glevels != vcpu->arch.mmu.root_level) {
+	if (sp->role.cr4_pae != !!is_pae(vcpu)) {
 		kvm_mmu_zap_page(vcpu->kvm, sp);
 		return 1;
 	}
 
-	trace_kvm_mmu_sync_page(sp);
 	if (rmap_write_protect(vcpu->kvm, sp->gfn))
 		kvm_flush_remote_tlbs(vcpu->kvm);
 	kvm_unlink_unsync_page(vcpu->kvm, sp);
@@ -1331,6 +1319,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	role = vcpu->arch.mmu.base_role;
 	role.level = level;
 	role.direct = direct;
+	if (role.direct)
+		role.cr4_pae = 0;
 	role.access = access;
 	if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
 		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
@@ -1351,7 +1341,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			mmu_page_add_parent_pte(vcpu, sp, parent_pte);
 			if (sp->unsync_children) {
 				set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
-				kvm_mmu_mark_parents_unsync(vcpu, sp);
+				kvm_mmu_mark_parents_unsync(sp);
 			}
 			trace_kvm_mmu_get_page(sp, false);
 			return sp;
@@ -1573,13 +1563,14 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	r = 0;
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
+restart:
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
 		if (sp->gfn == gfn && !sp->role.direct) {
 			pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
 				 sp->role.word);
 			r = 1;
 			if (kvm_mmu_zap_page(kvm, sp))
-				n = bucket->first;
+				goto restart;
 		}
 	return r;
 }
@@ -1593,13 +1584,14 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &kvm->arch.mmu_page_hash[index];
+restart:
 	hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) {
 		if (sp->gfn == gfn && !sp->role.direct
 		    && !sp->role.invalid) {
 			pgprintk("%s: zap %lx %x\n",
 				 __func__, gfn, sp->role.word);
 			if (kvm_mmu_zap_page(kvm, sp))
-				nn = bucket->first;
+				goto restart;
 		}
 	}
 }
@@ -1626,20 +1618,6 @@ static void mmu_convert_notrap(struct kvm_mmu_page *sp)
 	}
 }
 
-struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
-{
-	struct page *page;
-
-	gpa_t gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
-
-	if (gpa == UNMAPPED_GVA)
-		return NULL;
-
-	page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-
-	return page;
-}
-
 /*
  * The function is based on mtrr_type_lookup() in
  * arch/x86/kernel/cpu/mtrr/generic.c
@@ -1752,7 +1730,6 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 	struct kvm_mmu_page *s;
 	struct hlist_node *node, *n;
 
-	trace_kvm_mmu_unsync_page(sp);
 	index = kvm_page_table_hashfn(sp->gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
 	/* don't unsync if pagetable is shadowed with multiple roles */
@@ -1762,10 +1739,11 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		if (s->role.word != sp->role.word)
 			return 1;
 	}
+	trace_kvm_mmu_unsync_page(sp);
 	++vcpu->kvm->stat.mmu_unsync;
 	sp->unsync = 1;
 
-	kvm_mmu_mark_parents_unsync(vcpu, sp);
+	kvm_mmu_mark_parents_unsync(sp);
 
 	mmu_convert_notrap(sp);
 	return 0;
@@ -2081,21 +2059,23 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
 		ASSERT(!VALID_PAGE(root));
-		if (tdp_enabled)
-			direct = 1;
 		if (mmu_check_root(vcpu, root_gfn))
 			return 1;
+		if (tdp_enabled) {
+			direct = 1;
+			root_gfn = 0;
+		}
+		spin_lock(&vcpu->kvm->mmu_lock);
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
 				      PT64_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
+		spin_unlock(&vcpu->kvm->mmu_lock);
 		vcpu->arch.mmu.root_hpa = root;
 		return 0;
 	}
 	direct = !is_paging(vcpu);
-	if (tdp_enabled)
-		direct = 1;
 	for (i = 0; i < 4; ++i) {
 		hpa_t root = vcpu->arch.mmu.pae_root[i];
 
@@ -2111,11 +2091,18 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 			root_gfn = 0;
 		if (mmu_check_root(vcpu, root_gfn))
 			return 1;
+		if (tdp_enabled) {
+			direct = 1;
+			root_gfn = i << 30;
+		}
+		spin_lock(&vcpu->kvm->mmu_lock);
 		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
 				      PT32_ROOT_LEVEL, direct,
 				      ACC_ALL, NULL);
 		root = __pa(sp->spt);
 		++sp->root_count;
+		spin_unlock(&vcpu->kvm->mmu_lock);
+
 		vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
 	}
 	vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
@@ -2299,13 +2286,19 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
 		/* no rsvd bits for 2 level 4K page table entries */
 		context->rsvd_bits_mask[0][1] = 0;
 		context->rsvd_bits_mask[0][0] = 0;
+		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+
+		if (!is_pse(vcpu)) {
+			context->rsvd_bits_mask[1][1] = 0;
+			break;
+		}
+
 		if (is_cpuid_PSE36())
 			/* 36bits PSE 4MB page */
 			context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
 		else
 			/* 32 bits PSE 4MB page */
 			context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
 		break;
 	case PT32E_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][2] =
@@ -2318,7 +2311,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
 		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
+		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
 		break;
 	case PT64_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
@@ -2336,7 +2329,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
 		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
+		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
 		break;
 	}
 }
@@ -2438,7 +2431,8 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
 	else
 		r = paging32_init_context(vcpu);
 
-	vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level;
+	vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
+	vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu);
 
 	return r;
 }
@@ -2478,7 +2472,9 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 		goto out;
 	spin_lock(&vcpu->kvm->mmu_lock);
 	kvm_mmu_free_some_pages(vcpu);
+	spin_unlock(&vcpu->kvm->mmu_lock);
 	r = mmu_alloc_roots(vcpu);
+	spin_lock(&vcpu->kvm->mmu_lock);
 	mmu_sync_roots(vcpu);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	if (r)
@@ -2527,7 +2523,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
         }
 
 	++vcpu->kvm->stat.mmu_pte_updated;
-	if (sp->role.glevels == PT32_ROOT_LEVEL)
+	if (!sp->role.cr4_pae)
 		paging32_update_pte(vcpu, sp, spte, new);
 	else
 		paging64_update_pte(vcpu, sp, spte, new);
@@ -2562,36 +2558,11 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
 }
 
 static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-					  const u8 *new, int bytes)
+					  u64 gpte)
 {
 	gfn_t gfn;
-	int r;
-	u64 gpte = 0;
 	pfn_t pfn;
 
-	if (bytes != 4 && bytes != 8)
-		return;
-
-	/*
-	 * Assume that the pte write on a page table of the same type
-	 * as the current vcpu paging mode.  This is nearly always true
-	 * (might be false while changing modes).  Note it is verified later
-	 * by update_pte().
-	 */
-	if (is_pae(vcpu)) {
-		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
-		if ((bytes == 4) && (gpa % 4 == 0)) {
-			r = kvm_read_guest(vcpu->kvm, gpa & ~(u64)7, &gpte, 8);
-			if (r)
-				return;
-			memcpy((void *)&gpte + (gpa % 8), new, 4);
-		} else if ((bytes == 8) && (gpa % 8 == 0)) {
-			memcpy((void *)&gpte, new, 8);
-		}
-	} else {
-		if ((bytes == 4) && (gpa % 4 == 0))
-			memcpy((void *)&gpte, new, 4);
-	}
 	if (!is_present_gpte(gpte))
 		return;
 	gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
@@ -2640,10 +2611,46 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	int flooded = 0;
 	int npte;
 	int r;
+	int invlpg_counter;
 
 	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
-	mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
+
+	invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter);
+
+	/*
+	 * Assume that the pte write on a page table of the same type
+	 * as the current vcpu paging mode.  This is nearly always true
+	 * (might be false while changing modes).  Note it is verified later
+	 * by update_pte().
+	 */
+	if ((is_pae(vcpu) && bytes == 4) || !new) {
+		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
+		if (is_pae(vcpu)) {
+			gpa &= ~(gpa_t)7;
+			bytes = 8;
+		}
+		r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8));
+		if (r)
+			gentry = 0;
+		new = (const u8 *)&gentry;
+	}
+
+	switch (bytes) {
+	case 4:
+		gentry = *(const u32 *)new;
+		break;
+	case 8:
+		gentry = *(const u64 *)new;
+		break;
+	default:
+		gentry = 0;
+		break;
+	}
+
+	mmu_guess_page_from_pte_write(vcpu, gpa, gentry);
 	spin_lock(&vcpu->kvm->mmu_lock);
+	if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter)
+		gentry = 0;
 	kvm_mmu_access_page(vcpu, gfn);
 	kvm_mmu_free_some_pages(vcpu);
 	++vcpu->kvm->stat.mmu_pte_write;
@@ -2662,10 +2669,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	}
 	index = kvm_page_table_hashfn(gfn);
 	bucket = &vcpu->kvm->arch.mmu_page_hash[index];
+
+restart:
 	hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
 		if (sp->gfn != gfn || sp->role.direct || sp->role.invalid)
 			continue;
-		pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
+		pte_size = sp->role.cr4_pae ? 8 : 4;
 		misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
 		misaligned |= bytes < 4;
 		if (misaligned || flooded) {
@@ -2682,14 +2691,14 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			pgprintk("misaligned: gpa %llx bytes %d role %x\n",
 				 gpa, bytes, sp->role.word);
 			if (kvm_mmu_zap_page(vcpu->kvm, sp))
-				n = bucket->first;
+				goto restart;
 			++vcpu->kvm->stat.mmu_flooded;
 			continue;
 		}
 		page_offset = offset;
 		level = sp->role.level;
 		npte = 1;
-		if (sp->role.glevels == PT32_ROOT_LEVEL) {
+		if (!sp->role.cr4_pae) {
 			page_offset <<= 1;	/* 32->64 */
 			/*
 			 * A 32-bit pde maps 4MB while the shadow pdes map
@@ -2707,20 +2716,11 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 				continue;
 		}
 		spte = &sp->spt[page_offset / sizeof(*spte)];
-		if ((gpa & (pte_size - 1)) || (bytes < pte_size)) {
-			gentry = 0;
-			r = kvm_read_guest_atomic(vcpu->kvm,
-						  gpa & ~(u64)(pte_size - 1),
-						  &gentry, pte_size);
-			new = (const void *)&gentry;
-			if (r < 0)
-				new = NULL;
-		}
 		while (npte--) {
 			entry = *spte;
 			mmu_pte_write_zap_pte(vcpu, sp, spte);
-			if (new)
-				mmu_pte_write_new_pte(vcpu, sp, spte, new);
+			if (gentry)
+				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
 			mmu_pte_write_flush_tlb(vcpu, entry, *spte);
 			++spte;
 		}
@@ -2900,22 +2900,23 @@ void kvm_mmu_zap_all(struct kvm *kvm)
 	struct kvm_mmu_page *sp, *node;
 
 	spin_lock(&kvm->mmu_lock);
+restart:
 	list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link)
 		if (kvm_mmu_zap_page(kvm, sp))
-			node = container_of(kvm->arch.active_mmu_pages.next,
-					    struct kvm_mmu_page, link);
+			goto restart;
+
 	spin_unlock(&kvm->mmu_lock);
 
 	kvm_flush_remote_tlbs(kvm);
 }
 
-static void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm)
 {
 	struct kvm_mmu_page *page;
 
 	page = container_of(kvm->arch.active_mmu_pages.prev,
 			    struct kvm_mmu_page, link);
-	kvm_mmu_zap_page(kvm, page);
+	return kvm_mmu_zap_page(kvm, page) + 1;
 }
 
 static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
@@ -2927,7 +2928,7 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
 	spin_lock(&kvm_lock);
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		int npages, idx;
+		int npages, idx, freed_pages;
 
 		idx = srcu_read_lock(&kvm->srcu);
 		spin_lock(&kvm->mmu_lock);
@@ -2935,8 +2936,8 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
 			 kvm->arch.n_free_mmu_pages;
 		cache_count += npages;
 		if (!kvm_freed && nr_to_scan > 0 && npages > 0) {
-			kvm_mmu_remove_one_alloc_mmu_page(kvm);
-			cache_count--;
+			freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm);
+			cache_count -= freed_pages;
 			kvm_freed = kvm;
 		}
 		nr_to_scan--;
@@ -3011,7 +3012,8 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	unsigned int  nr_pages = 0;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
+
 	for (i = 0; i < slots->nmemslots; i++)
 		nr_pages += slots->memslots[i].npages;
 
@@ -3174,8 +3176,7 @@ static gva_t canonicalize(gva_t gva)
 }
 
 
-typedef void (*inspect_spte_fn) (struct kvm *kvm, struct kvm_mmu_page *sp,
-				 u64 *sptep);
+typedef void (*inspect_spte_fn) (struct kvm *kvm, u64 *sptep);
 
 static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp,
 			    inspect_spte_fn fn)
@@ -3191,7 +3192,7 @@ static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp,
 				child = page_header(ent & PT64_BASE_ADDR_MASK);
 				__mmu_spte_walk(kvm, child, fn);
 			} else
-				fn(kvm, sp, &sp->spt[i]);
+				fn(kvm, &sp->spt[i]);
 		}
 	}
 }
@@ -3282,11 +3283,13 @@ static void audit_mappings(struct kvm_vcpu *vcpu)
 
 static int count_rmaps(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memslots *slots;
 	int nmaps = 0;
 	int i, j, k, idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
 		struct kvm_memory_slot *m = &slots->memslots[i];
 		struct kvm_rmap_desc *d;
@@ -3315,7 +3318,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu)
 	return nmaps;
 }
 
-void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep)
+void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 {
 	unsigned long *rmapp;
 	struct kvm_mmu_page *rev_sp;
@@ -3331,14 +3334,14 @@ void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep)
 			printk(KERN_ERR "%s: no memslot for gfn %ld\n",
 					 audit_msg, gfn);
 			printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n",
-					audit_msg, sptep - rev_sp->spt,
+			       audit_msg, (long int)(sptep - rev_sp->spt),
 					rev_sp->gfn);
 			dump_stack();
 			return;
 		}
 
 		rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt],
-				    is_large_pte(*sptep));
+				    rev_sp->role.level);
 		if (!*rmapp) {
 			if (!printk_ratelimit())
 				return;
@@ -3373,7 +3376,7 @@ static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu)
 				continue;
 			if (!(ent & PT_WRITABLE_MASK))
 				continue;
-			inspect_spte_has_rmap(vcpu->kvm, sp, &pt[i]);
+			inspect_spte_has_rmap(vcpu->kvm, &pt[i]);
 		}
 	}
 	return;

arch/x86/kvm/mmutrace.h

@@ -6,14 +6,12 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvmmmu
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE mmutrace
 
 #define KVM_MMU_PAGE_FIELDS \
 	__field(__u64, gfn) \
 	__field(__u32, role) \
 	__field(__u32, root_count) \
-	__field(__u32, unsync)
+	__field(bool, unsync)
 
 #define KVM_MMU_PAGE_ASSIGN(sp)			     \
 	__entry->gfn = sp->gfn;			     \
@@ -30,14 +28,14 @@
 								        \
 	role.word = __entry->role;					\
 									\
-	trace_seq_printf(p, "sp gfn %llx %u/%u q%u%s %s%s %spge"	\
+	trace_seq_printf(p, "sp gfn %llx %u%s q%u%s %s%s"		\
 			 " %snxe root %u %s%c",				\
-			 __entry->gfn, role.level, role.glevels,	\
+			 __entry->gfn, role.level,			\
+			 role.cr4_pae ? " pae" : "",			\
 			 role.quadrant,					\
 			 role.direct ? " direct" : "",			\
 			 access_str[role.access],			\
 			 role.invalid ? " invalid" : "",		\
-			 role.cr4_pge ? "" : "!",			\
 			 role.nxe ? "" : "!",				\
 			 __entry->root_count,				\
 			 __entry->unsync ? "unsync" : "sync", 0);	\
@@ -94,15 +92,15 @@ TRACE_EVENT(
 	TP_printk("pte %llx level %u", __entry->pte, __entry->level)
 );
 
-/* We set a pte accessed bit */
-TRACE_EVENT(
-	kvm_mmu_set_accessed_bit,
+DECLARE_EVENT_CLASS(kvm_mmu_set_bit_class,
+
 	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+
 	TP_ARGS(table_gfn, index, size),
 
 	TP_STRUCT__entry(
 		__field(__u64, gpa)
-		),
+	),
 
 	TP_fast_assign(
 		__entry->gpa = ((u64)table_gfn << PAGE_SHIFT)
@@ -112,22 +110,20 @@ TRACE_EVENT(
 	TP_printk("gpa %llx", __entry->gpa)
 );
 
-/* We set a pte dirty bit */
-TRACE_EVENT(
-	kvm_mmu_set_dirty_bit,
+/* We set a pte accessed bit */
+DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_accessed_bit,
+
 	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
-	TP_ARGS(table_gfn, index, size),
 
-	TP_STRUCT__entry(
-		__field(__u64, gpa)
-		),
+	TP_ARGS(table_gfn, index, size)
+);
 
-	TP_fast_assign(
-		__entry->gpa = ((u64)table_gfn << PAGE_SHIFT)
-				+ index * size;
-		),
+/* We set a pte dirty bit */
+DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_dirty_bit,
 
-	TP_printk("gpa %llx", __entry->gpa)
+	TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+
+	TP_ARGS(table_gfn, index, size)
 );
 
 TRACE_EVENT(
@@ -166,55 +162,45 @@ TRACE_EVENT(
 		  __entry->created ? "new" : "existing")
 );
 
-TRACE_EVENT(
-	kvm_mmu_sync_page,
+DECLARE_EVENT_CLASS(kvm_mmu_page_class,
+
 	TP_PROTO(struct kvm_mmu_page *sp),
 	TP_ARGS(sp),
 
 	TP_STRUCT__entry(
 		KVM_MMU_PAGE_FIELDS
-		),
+	),
 
 	TP_fast_assign(
 		KVM_MMU_PAGE_ASSIGN(sp)
-		),
+	),
 
 	TP_printk("%s", KVM_MMU_PAGE_PRINTK())
 );
 
-TRACE_EVENT(
-	kvm_mmu_unsync_page,
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_sync_page,
 	TP_PROTO(struct kvm_mmu_page *sp),
-	TP_ARGS(sp),
-
-	TP_STRUCT__entry(
-		KVM_MMU_PAGE_FIELDS
-		),
 
-	TP_fast_assign(
-		KVM_MMU_PAGE_ASSIGN(sp)
-		),
-
-	TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+	TP_ARGS(sp)
 );
 
-TRACE_EVENT(
-	kvm_mmu_zap_page,
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_unsync_page,
 	TP_PROTO(struct kvm_mmu_page *sp),
-	TP_ARGS(sp),
 
-	TP_STRUCT__entry(
-		KVM_MMU_PAGE_FIELDS
-		),
+	TP_ARGS(sp)
+);
 
-	TP_fast_assign(
-		KVM_MMU_PAGE_ASSIGN(sp)
-		),
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_zap_page,
+	TP_PROTO(struct kvm_mmu_page *sp),
 
-	TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+	TP_ARGS(sp)
 );
-
 #endif /* _TRACE_KVMMMU_H */
 
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mmutrace
+
 /* This part must be outside protection */
 #include <trace/define_trace.h>

arch/x86/kvm/paging_tmpl.h

@@ -170,7 +170,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 			goto access_error;
 
 #if PTTYPE == 64
-		if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK))
+		if (fetch_fault && (pte & PT64_NX_MASK))
 			goto access_error;
 #endif
 
@@ -190,10 +190,10 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 
 		if ((walker->level == PT_PAGE_TABLE_LEVEL) ||
 		    ((walker->level == PT_DIRECTORY_LEVEL) &&
-				(pte & PT_PAGE_SIZE_MASK)  &&
+				is_large_pte(pte) &&
 				(PTTYPE == 64 || is_pse(vcpu))) ||
 		    ((walker->level == PT_PDPE_LEVEL) &&
-				(pte & PT_PAGE_SIZE_MASK)  &&
+				is_large_pte(pte) &&
 				is_long_mode(vcpu))) {
 			int lvl = walker->level;
 
@@ -258,11 +258,17 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
 	pt_element_t gpte;
 	unsigned pte_access;
 	pfn_t pfn;
+	u64 new_spte;
 
 	gpte = *(const pt_element_t *)pte;
 	if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
-		if (!is_present_gpte(gpte))
-			__set_spte(spte, shadow_notrap_nonpresent_pte);
+		if (!is_present_gpte(gpte)) {
+			if (page->unsync)
+				new_spte = shadow_trap_nonpresent_pte;
+			else
+				new_spte = shadow_notrap_nonpresent_pte;
+			__set_spte(spte, new_spte);
+		}
 		return;
 	}
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
@@ -457,6 +463,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 {
 	struct kvm_shadow_walk_iterator iterator;
+	gpa_t pte_gpa = -1;
 	int level;
 	u64 *sptep;
 	int need_flush = 0;
@@ -467,9 +474,16 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 		level = iterator.level;
 		sptep = iterator.sptep;
 
-		if (level == PT_PAGE_TABLE_LEVEL  ||
-		    ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
-		    ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {
+		if (is_last_spte(*sptep, level)) {
+			struct kvm_mmu_page *sp = page_header(__pa(sptep));
+			int offset, shift;
+
+			shift = PAGE_SHIFT -
+				  (PT_LEVEL_BITS - PT64_LEVEL_BITS) * level;
+			offset = sp->role.quadrant << shift;
+
+			pte_gpa = (sp->gfn << PAGE_SHIFT) + offset;
+			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
 
 			if (is_shadow_present_pte(*sptep)) {
 				rmap_remove(vcpu->kvm, sptep);
@@ -487,7 +501,17 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 
 	if (need_flush)
 		kvm_flush_remote_tlbs(vcpu->kvm);
+
+	atomic_inc(&vcpu->kvm->arch.invlpg_counter);
+
 	spin_unlock(&vcpu->kvm->mmu_lock);
+
+	if (pte_gpa == -1)
+		return;
+
+	if (mmu_topup_memory_caches(vcpu))
+		return;
+	kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0);
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
@@ -551,12 +575,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
 	int i, offset, nr_present;
 	bool reset_host_protection;
+	gpa_t first_pte_gpa;
 
 	offset = nr_present = 0;
 
 	if (PTTYPE == 32)
 		offset = sp->role.quadrant << PT64_LEVEL_BITS;
 
+	first_pte_gpa = gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t);
+
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
 		unsigned pte_access;
 		pt_element_t gpte;
@@ -566,8 +593,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		if (!is_shadow_present_pte(sp->spt[i]))
 			continue;
 
-		pte_gpa = gfn_to_gpa(sp->gfn);
-		pte_gpa += (i+offset) * sizeof(pt_element_t);
+		pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
 
 		if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
 					  sizeof(pt_element_t)))

arch/x86/kvm/svm.c

@@ -44,10 +44,11 @@ MODULE_LICENSE("GPL");
 #define SEG_TYPE_LDT 2
 #define SEG_TYPE_BUSY_TSS16 3
 
-#define SVM_FEATURE_NPT  (1 << 0)
-#define SVM_FEATURE_LBRV (1 << 1)
-#define SVM_FEATURE_SVML (1 << 2)
-#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
+#define SVM_FEATURE_NPT            (1 <<  0)
+#define SVM_FEATURE_LBRV           (1 <<  1)
+#define SVM_FEATURE_SVML           (1 <<  2)
+#define SVM_FEATURE_NRIP           (1 <<  3)
+#define SVM_FEATURE_PAUSE_FILTER   (1 << 10)
 
 #define NESTED_EXIT_HOST	0	/* Exit handled on host level */
 #define NESTED_EXIT_DONE	1	/* Exit caused nested vmexit  */
@@ -70,6 +71,7 @@ struct kvm_vcpu;
 struct nested_state {
 	struct vmcb *hsave;
 	u64 hsave_msr;
+	u64 vm_cr_msr;
 	u64 vmcb;
 
 	/* These are the merged vectors */
@@ -77,6 +79,7 @@ struct nested_state {
 
 	/* gpa pointers to the real vectors */
 	u64 vmcb_msrpm;
+	u64 vmcb_iopm;
 
 	/* A VMEXIT is required but not yet emulated */
 	bool exit_required;
@@ -91,6 +94,9 @@ struct nested_state {
 
 };
 
+#define MSRPM_OFFSETS	16
+static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
+
 struct vcpu_svm {
 	struct kvm_vcpu vcpu;
 	struct vmcb *vmcb;
@@ -110,13 +116,39 @@ struct vcpu_svm {
 	struct nested_state nested;
 
 	bool nmi_singlestep;
+
+	unsigned int3_injected;
+	unsigned long int3_rip;
+};
+
+#define MSR_INVALID			0xffffffffU
+
+static struct svm_direct_access_msrs {
+	u32 index;   /* Index of the MSR */
+	bool always; /* True if intercept is always on */
+} direct_access_msrs[] = {
+	{ .index = MSR_K6_STAR,				.always = true  },
+	{ .index = MSR_IA32_SYSENTER_CS,		.always = true  },
+#ifdef CONFIG_X86_64
+	{ .index = MSR_GS_BASE,				.always = true  },
+	{ .index = MSR_FS_BASE,				.always = true  },
+	{ .index = MSR_KERNEL_GS_BASE,			.always = true  },
+	{ .index = MSR_LSTAR,				.always = true  },
+	{ .index = MSR_CSTAR,				.always = true  },
+	{ .index = MSR_SYSCALL_MASK,			.always = true  },
+#endif
+	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
+	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
+	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
+	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
+	{ .index = MSR_INVALID,				.always = false },
 };
 
 /* enable NPT for AMD64 and X86 with PAE */
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 static bool npt_enabled = true;
 #else
-static bool npt_enabled = false;
+static bool npt_enabled;
 #endif
 static int npt = 1;
 
@@ -129,6 +161,7 @@ static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
 
 static int nested_svm_exit_handled(struct vcpu_svm *svm);
+static int nested_svm_intercept(struct vcpu_svm *svm);
 static int nested_svm_vmexit(struct vcpu_svm *svm);
 static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 				      bool has_error_code, u32 error_code);
@@ -163,8 +196,8 @@ static unsigned long iopm_base;
 struct kvm_ldttss_desc {
 	u16 limit0;
 	u16 base0;
-	unsigned base1 : 8, type : 5, dpl : 2, p : 1;
-	unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
+	unsigned base1:8, type:5, dpl:2, p:1;
+	unsigned limit1:4, zero0:3, g:1, base2:8;
 	u32 base3;
 	u32 zero1;
 } __attribute__((packed));
@@ -194,6 +227,27 @@ static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
 #define MSRS_RANGE_SIZE 2048
 #define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
 
+static u32 svm_msrpm_offset(u32 msr)
+{
+	u32 offset;
+	int i;
+
+	for (i = 0; i < NUM_MSR_MAPS; i++) {
+		if (msr < msrpm_ranges[i] ||
+		    msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
+			continue;
+
+		offset  = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
+		offset += (i * MSRS_RANGE_SIZE);       /* add range offset */
+
+		/* Now we have the u8 offset - but need the u32 offset */
+		return offset / 4;
+	}
+
+	/* MSR not in any range */
+	return MSR_INVALID;
+}
+
 #define MAX_INST_SIZE 15
 
 static inline u32 svm_has(u32 feat)
@@ -213,7 +267,7 @@ static inline void stgi(void)
 
 static inline void invlpga(unsigned long addr, u32 asid)
 {
-	asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid));
+	asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
 }
 
 static inline void force_new_asid(struct kvm_vcpu *vcpu)
@@ -235,23 +289,6 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	vcpu->arch.efer = efer;
 }
 
-static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
-				bool has_error_code, u32 error_code)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	/* If we are within a nested VM we'd better #VMEXIT and let the
-	   guest handle the exception */
-	if (nested_svm_check_exception(svm, nr, has_error_code, error_code))
-		return;
-
-	svm->vmcb->control.event_inj = nr
-		| SVM_EVTINJ_VALID
-		| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
-		| SVM_EVTINJ_TYPE_EXEPT;
-	svm->vmcb->control.event_inj_err = error_code;
-}
-
 static int is_external_interrupt(u32 info)
 {
 	info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
@@ -264,7 +301,7 @@ static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 	u32 ret = 0;
 
 	if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
-		ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
+		ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
 	return ret & mask;
 }
 
@@ -283,6 +320,9 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (svm->vmcb->control.next_rip != 0)
+		svm->next_rip = svm->vmcb->control.next_rip;
+
 	if (!svm->next_rip) {
 		if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
 				EMULATE_DONE)
@@ -297,6 +337,43 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	svm_set_interrupt_shadow(vcpu, 0);
 }
 
+static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
+				bool has_error_code, u32 error_code,
+				bool reinject)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/*
+	 * If we are within a nested VM we'd better #VMEXIT and let the guest
+	 * handle the exception
+	 */
+	if (!reinject &&
+	    nested_svm_check_exception(svm, nr, has_error_code, error_code))
+		return;
+
+	if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) {
+		unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
+
+		/*
+		 * For guest debugging where we have to reinject #BP if some
+		 * INT3 is guest-owned:
+		 * Emulate nRIP by moving RIP forward. Will fail if injection
+		 * raises a fault that is not intercepted. Still better than
+		 * failing in all cases.
+		 */
+		skip_emulated_instruction(&svm->vcpu);
+		rip = kvm_rip_read(&svm->vcpu);
+		svm->int3_rip = rip + svm->vmcb->save.cs.base;
+		svm->int3_injected = rip - old_rip;
+	}
+
+	svm->vmcb->control.event_inj = nr
+		| SVM_EVTINJ_VALID
+		| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
+		| SVM_EVTINJ_TYPE_EXEPT;
+	svm->vmcb->control.event_inj_err = error_code;
+}
+
 static int has_svm(void)
 {
 	const char *msg;
@@ -319,7 +396,7 @@ static int svm_hardware_enable(void *garbage)
 
 	struct svm_cpu_data *sd;
 	uint64_t efer;
-	struct descriptor_table gdt_descr;
+	struct desc_ptr gdt_descr;
 	struct desc_struct *gdt;
 	int me = raw_smp_processor_id();
 
@@ -344,8 +421,8 @@ static int svm_hardware_enable(void *garbage)
 	sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
 	sd->next_asid = sd->max_asid + 1;
 
-	kvm_get_gdt(&gdt_descr);
-	gdt = (struct desc_struct *)gdt_descr.base;
+	native_store_gdt(&gdt_descr);
+	gdt = (struct desc_struct *)gdt_descr.address;
 	sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
 
 	wrmsrl(MSR_EFER, efer | EFER_SVME);
@@ -391,42 +468,98 @@ static int svm_cpu_init(int cpu)
 
 }
 
+static bool valid_msr_intercept(u32 index)
+{
+	int i;
+
+	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
+		if (direct_access_msrs[i].index == index)
+			return true;
+
+	return false;
+}
+
 static void set_msr_interception(u32 *msrpm, unsigned msr,
 				 int read, int write)
+{
+	u8 bit_read, bit_write;
+	unsigned long tmp;
+	u32 offset;
+
+	/*
+	 * If this warning triggers extend the direct_access_msrs list at the
+	 * beginning of the file
+	 */
+	WARN_ON(!valid_msr_intercept(msr));
+
+	offset    = svm_msrpm_offset(msr);
+	bit_read  = 2 * (msr & 0x0f);
+	bit_write = 2 * (msr & 0x0f) + 1;
+	tmp       = msrpm[offset];
+
+	BUG_ON(offset == MSR_INVALID);
+
+	read  ? clear_bit(bit_read,  &tmp) : set_bit(bit_read,  &tmp);
+	write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
+
+	msrpm[offset] = tmp;
+}
+
+static void svm_vcpu_init_msrpm(u32 *msrpm)
 {
 	int i;
 
-	for (i = 0; i < NUM_MSR_MAPS; i++) {
-		if (msr >= msrpm_ranges[i] &&
-		    msr < msrpm_ranges[i] + MSRS_IN_RANGE) {
-			u32 msr_offset = (i * MSRS_IN_RANGE + msr -
-					  msrpm_ranges[i]) * 2;
-
-			u32 *base = msrpm + (msr_offset / 32);
-			u32 msr_shift = msr_offset % 32;
-			u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1);
-			*base = (*base & ~(0x3 << msr_shift)) |
-				(mask << msr_shift);
+	memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+
+	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+		if (!direct_access_msrs[i].always)
+			continue;
+
+		set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
+	}
+}
+
+static void add_msr_offset(u32 offset)
+{
+	int i;
+
+	for (i = 0; i < MSRPM_OFFSETS; ++i) {
+
+		/* Offset already in list? */
+		if (msrpm_offsets[i] == offset)
 			return;
-		}
+
+		/* Slot used by another offset? */
+		if (msrpm_offsets[i] != MSR_INVALID)
+			continue;
+
+		/* Add offset to list */
+		msrpm_offsets[i] = offset;
+
+		return;
 	}
+
+	/*
+	 * If this BUG triggers the msrpm_offsets table has an overflow. Just
+	 * increase MSRPM_OFFSETS in this case.
+	 */
 	BUG();
 }
 
-static void svm_vcpu_init_msrpm(u32 *msrpm)
+static void init_msrpm_offsets(void)
 {
-	memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+	int i;
 
-#ifdef CONFIG_X86_64
-	set_msr_interception(msrpm, MSR_GS_BASE, 1, 1);
-	set_msr_interception(msrpm, MSR_FS_BASE, 1, 1);
-	set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1);
-	set_msr_interception(msrpm, MSR_LSTAR, 1, 1);
-	set_msr_interception(msrpm, MSR_CSTAR, 1, 1);
-	set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1);
-#endif
-	set_msr_interception(msrpm, MSR_K6_STAR, 1, 1);
-	set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1);
+	memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
+
+	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+		u32 offset;
+
+		offset = svm_msrpm_offset(direct_access_msrs[i].index);
+		BUG_ON(offset == MSR_INVALID);
+
+		add_msr_offset(offset);
+	}
 }
 
 static void svm_enable_lbrv(struct vcpu_svm *svm)
@@ -467,6 +600,8 @@ static __init int svm_hardware_setup(void)
 	memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
 	iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
 
+	init_msrpm_offsets();
+
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
 
@@ -523,7 +658,7 @@ static void init_seg(struct vmcb_seg *seg)
 {
 	seg->selector = 0;
 	seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK |
-		SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
+		      SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
 	seg->limit = 0xffff;
 	seg->base = 0;
 }
@@ -543,16 +678,16 @@ static void init_vmcb(struct vcpu_svm *svm)
 
 	svm->vcpu.fpu_active = 1;
 
-	control->intercept_cr_read = 	INTERCEPT_CR0_MASK |
+	control->intercept_cr_read =	INTERCEPT_CR0_MASK |
 					INTERCEPT_CR3_MASK |
 					INTERCEPT_CR4_MASK;
 
-	control->intercept_cr_write = 	INTERCEPT_CR0_MASK |
+	control->intercept_cr_write =	INTERCEPT_CR0_MASK |
 					INTERCEPT_CR3_MASK |
 					INTERCEPT_CR4_MASK |
 					INTERCEPT_CR8_MASK;
 
-	control->intercept_dr_read = 	INTERCEPT_DR0_MASK |
+	control->intercept_dr_read =	INTERCEPT_DR0_MASK |
 					INTERCEPT_DR1_MASK |
 					INTERCEPT_DR2_MASK |
 					INTERCEPT_DR3_MASK |
@@ -561,7 +696,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 					INTERCEPT_DR6_MASK |
 					INTERCEPT_DR7_MASK;
 
-	control->intercept_dr_write = 	INTERCEPT_DR0_MASK |
+	control->intercept_dr_write =	INTERCEPT_DR0_MASK |
 					INTERCEPT_DR1_MASK |
 					INTERCEPT_DR2_MASK |
 					INTERCEPT_DR3_MASK |
@@ -575,7 +710,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 					(1 << MC_VECTOR);
 
 
-	control->intercept = 	(1ULL << INTERCEPT_INTR) |
+	control->intercept =	(1ULL << INTERCEPT_INTR) |
 				(1ULL << INTERCEPT_NMI) |
 				(1ULL << INTERCEPT_SMI) |
 				(1ULL << INTERCEPT_SELECTIVE_CR0) |
@@ -636,7 +771,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 	save->rip = 0x0000fff0;
 	svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
 
-	/* This is the guest-visible cr0 value.
+	/*
+	 * This is the guest-visible cr0 value.
 	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
 	 */
 	svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
@@ -729,6 +865,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	svm_vcpu_init_msrpm(svm->msrpm);
 
 	svm->nested.msrpm = page_address(nested_msrpm_pages);
+	svm_vcpu_init_msrpm(svm->nested.msrpm);
 
 	svm->vmcb = page_address(page);
 	clear_page(svm->vmcb);
@@ -882,7 +1019,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
 	var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
 
-	/* AMD's VMCB does not have an explicit unusable field, so emulate it
+	/*
+	 * AMD's VMCB does not have an explicit unusable field, so emulate it
 	 * for cross vendor migration purposes by "not present"
 	 */
 	var->unusable = !var->present || (var->type == 0);
@@ -918,7 +1056,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 			var->type |= 0x1;
 		break;
 	case VCPU_SREG_SS:
-		/* On AMD CPUs sometimes the DB bit in the segment
+		/*
+		 * On AMD CPUs sometimes the DB bit in the segment
 		 * descriptor is left as 1, although the whole segment has
 		 * been made unusable. Clear it here to pass an Intel VMX
 		 * entry check when cross vendor migrating.
@@ -936,36 +1075,36 @@ static int svm_get_cpl(struct kvm_vcpu *vcpu)
 	return save->cpl;
 }
 
-static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	dt->limit = svm->vmcb->save.idtr.limit;
-	dt->base = svm->vmcb->save.idtr.base;
+	dt->size = svm->vmcb->save.idtr.limit;
+	dt->address = svm->vmcb->save.idtr.base;
 }
 
-static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->save.idtr.limit = dt->limit;
-	svm->vmcb->save.idtr.base = dt->base ;
+	svm->vmcb->save.idtr.limit = dt->size;
+	svm->vmcb->save.idtr.base = dt->address ;
 }
 
-static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	dt->limit = svm->vmcb->save.gdtr.limit;
-	dt->base = svm->vmcb->save.gdtr.base;
+	dt->size = svm->vmcb->save.gdtr.limit;
+	dt->address = svm->vmcb->save.gdtr.base;
 }
 
-static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->save.gdtr.limit = dt->limit;
-	svm->vmcb->save.gdtr.base = dt->base ;
+	svm->vmcb->save.gdtr.limit = dt->size;
+	svm->vmcb->save.gdtr.base = dt->address ;
 }
 
 static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
@@ -978,6 +1117,7 @@ static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 
 static void update_cr0_intercept(struct vcpu_svm *svm)
 {
+	struct vmcb *vmcb = svm->vmcb;
 	ulong gcr0 = svm->vcpu.arch.cr0;
 	u64 *hcr0 = &svm->vmcb->save.cr0;
 
@@ -989,11 +1129,25 @@ static void update_cr0_intercept(struct vcpu_svm *svm)
 
 
 	if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
-		svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
-		svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+		vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+		vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+		if (is_nested(svm)) {
+			struct vmcb *hsave = svm->nested.hsave;
+
+			hsave->control.intercept_cr_read  &= ~INTERCEPT_CR0_MASK;
+			hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+			vmcb->control.intercept_cr_read  |= svm->nested.intercept_cr_read;
+			vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write;
+		}
 	} else {
 		svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
 		svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+		if (is_nested(svm)) {
+			struct vmcb *hsave = svm->nested.hsave;
+
+			hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
+			hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+		}
 	}
 }
 
@@ -1001,6 +1155,27 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (is_nested(svm)) {
+		/*
+		 * We are here because we run in nested mode, the host kvm
+		 * intercepts cr0 writes but the l1 hypervisor does not.
+		 * But the L1 hypervisor may intercept selective cr0 writes.
+		 * This needs to be checked here.
+		 */
+		unsigned long old, new;
+
+		/* Remove bits that would trigger a real cr0 write intercept */
+		old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK;
+		new = cr0 & SVM_CR0_SELECTIVE_MASK;
+
+		if (old == new) {
+			/* cr0 write with ts and mp unchanged */
+			svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+			if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE)
+				return;
+		}
+	}
+
 #ifdef CONFIG_X86_64
 	if (vcpu->arch.efer & EFER_LME) {
 		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
@@ -1134,70 +1309,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 	svm->vmcb->control.asid = sd->next_asid++;
 }
 
-static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest)
+static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	switch (dr) {
-	case 0 ... 3:
-		*dest = vcpu->arch.db[dr];
-		break;
-	case 4:
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
-			return EMULATE_FAIL; /* will re-inject UD */
-		/* fall through */
-	case 6:
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-			*dest = vcpu->arch.dr6;
-		else
-			*dest = svm->vmcb->save.dr6;
-		break;
-	case 5:
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
-			return EMULATE_FAIL; /* will re-inject UD */
-		/* fall through */
-	case 7:
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-			*dest = vcpu->arch.dr7;
-		else
-			*dest = svm->vmcb->save.dr7;
-		break;
-	}
-
-	return EMULATE_DONE;
-}
-
-static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	switch (dr) {
-	case 0 ... 3:
-		vcpu->arch.db[dr] = value;
-		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
-			vcpu->arch.eff_db[dr] = value;
-		break;
-	case 4:
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
-			return EMULATE_FAIL; /* will re-inject UD */
-		/* fall through */
-	case 6:
-		vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
-		break;
-	case 5:
-		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
-			return EMULATE_FAIL; /* will re-inject UD */
-		/* fall through */
-	case 7:
-		vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1;
-		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
-			svm->vmcb->save.dr7 = vcpu->arch.dr7;
-			vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK);
-		}
-		break;
-	}
-
-	return EMULATE_DONE;
+	svm->vmcb->save.dr7 = value;
 }
 
 static int pf_interception(struct vcpu_svm *svm)
@@ -1234,7 +1350,7 @@ static int db_interception(struct vcpu_svm *svm)
 	}
 
 	if (svm->vcpu.guest_debug &
-	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){
+	    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
 		kvm_run->debug.arch.pc =
 			svm->vmcb->save.cs.base + svm->vmcb->save.rip;
@@ -1268,7 +1384,22 @@ static int ud_interception(struct vcpu_svm *svm)
 static void svm_fpu_activate(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
+	u32 excp;
+
+	if (is_nested(svm)) {
+		u32 h_excp, n_excp;
+
+		h_excp  = svm->nested.hsave->control.intercept_exceptions;
+		n_excp  = svm->nested.intercept_exceptions;
+		h_excp &= ~(1 << NM_VECTOR);
+		excp    = h_excp | n_excp;
+	} else {
+		excp  = svm->vmcb->control.intercept_exceptions;
+		excp &= ~(1 << NM_VECTOR);
+	}
+
+	svm->vmcb->control.intercept_exceptions = excp;
+
 	svm->vcpu.fpu_active = 1;
 	update_cr0_intercept(svm);
 }
@@ -1309,29 +1440,23 @@ static int shutdown_interception(struct vcpu_svm *svm)
 
 static int io_interception(struct vcpu_svm *svm)
 {
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
 	int size, in, string;
 	unsigned port;
 
 	++svm->vcpu.stat.io_exits;
-
-	svm->next_rip = svm->vmcb->control.exit_info_2;
-
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
-
-	if (string) {
-		if (emulate_instruction(&svm->vcpu,
-					0, 0, 0) == EMULATE_DO_MMIO)
-			return 0;
-		return 1;
-	}
-
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
+	if (string || in)
+		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
-
+	svm->next_rip = svm->vmcb->control.exit_info_2;
 	skip_emulated_instruction(&svm->vcpu);
-	return kvm_emulate_pio(&svm->vcpu, in, size, port);
+
+	return kvm_fast_pio_out(vcpu, size, port);
 }
 
 static int nmi_interception(struct vcpu_svm *svm)
@@ -1384,6 +1509,8 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm)
 static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 				      bool has_error_code, u32 error_code)
 {
+	int vmexit;
+
 	if (!is_nested(svm))
 		return 0;
 
@@ -1392,21 +1519,28 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 	svm->vmcb->control.exit_info_1 = error_code;
 	svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
 
-	return nested_svm_exit_handled(svm);
+	vmexit = nested_svm_intercept(svm);
+	if (vmexit == NESTED_EXIT_DONE)
+		svm->nested.exit_required = true;
+
+	return vmexit;
 }
 
-static inline int nested_svm_intr(struct vcpu_svm *svm)
+/* This function returns true if it is save to enable the irq window */
+static inline bool nested_svm_intr(struct vcpu_svm *svm)
 {
 	if (!is_nested(svm))
-		return 0;
+		return true;
 
 	if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
-		return 0;
+		return true;
 
 	if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
-		return 0;
+		return false;
 
-	svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+	svm->vmcb->control.exit_code   = SVM_EXIT_INTR;
+	svm->vmcb->control.exit_info_1 = 0;
+	svm->vmcb->control.exit_info_2 = 0;
 
 	if (svm->nested.intercept & 1ULL) {
 		/*
@@ -1417,21 +1551,40 @@ static inline int nested_svm_intr(struct vcpu_svm *svm)
 		 */
 		svm->nested.exit_required = true;
 		trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
-		return 1;
+		return false;
 	}
 
-	return 0;
+	return true;
+}
+
+/* This function returns true if it is save to enable the nmi window */
+static inline bool nested_svm_nmi(struct vcpu_svm *svm)
+{
+	if (!is_nested(svm))
+		return true;
+
+	if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI)))
+		return true;
+
+	svm->vmcb->control.exit_code = SVM_EXIT_NMI;
+	svm->nested.exit_required = true;
+
+	return false;
 }
 
-static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx)
+static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
 {
 	struct page *page;
 
+	might_sleep();
+
 	page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
 	if (is_error_page(page))
 		goto error;
 
-	return kmap_atomic(page, idx);
+	*_page = page;
+
+	return kmap(page);
 
 error:
 	kvm_release_page_clean(page);
@@ -1440,61 +1593,55 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx)
 	return NULL;
 }
 
-static void nested_svm_unmap(void *addr, enum km_type idx)
+static void nested_svm_unmap(struct page *page)
 {
-	struct page *page;
+	kunmap(page);
+	kvm_release_page_dirty(page);
+}
 
-	if (!addr)
-		return;
+static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
+{
+	unsigned port;
+	u8 val, bit;
+	u64 gpa;
 
-	page = kmap_atomic_to_page(addr);
+	if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
+		return NESTED_EXIT_HOST;
 
-	kunmap_atomic(addr, idx);
-	kvm_release_page_dirty(page);
+	port = svm->vmcb->control.exit_info_1 >> 16;
+	gpa  = svm->nested.vmcb_iopm + (port / 8);
+	bit  = port % 8;
+	val  = 0;
+
+	if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1))
+		val &= (1 << bit);
+
+	return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
 }
 
-static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm)
+static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 {
-	u32 param = svm->vmcb->control.exit_info_1 & 1;
-	u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
-	bool ret = false;
-	u32 t0, t1;
-	u8 *msrpm;
+	u32 offset, msr, value;
+	int write, mask;
 
 	if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
-		return false;
+		return NESTED_EXIT_HOST;
 
-	msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
+	msr    = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+	offset = svm_msrpm_offset(msr);
+	write  = svm->vmcb->control.exit_info_1 & 1;
+	mask   = 1 << ((2 * (msr & 0xf)) + write);
 
-	if (!msrpm)
-		goto out;
+	if (offset == MSR_INVALID)
+		return NESTED_EXIT_DONE;
 
-	switch (msr) {
-	case 0 ... 0x1fff:
-		t0 = (msr * 2) % 8;
-		t1 = msr / 8;
-		break;
-	case 0xc0000000 ... 0xc0001fff:
-		t0 = (8192 + msr - 0xc0000000) * 2;
-		t1 = (t0 / 8);
-		t0 %= 8;
-		break;
-	case 0xc0010000 ... 0xc0011fff:
-		t0 = (16384 + msr - 0xc0010000) * 2;
-		t1 = (t0 / 8);
-		t0 %= 8;
-		break;
-	default:
-		ret = true;
-		goto out;
-	}
+	/* Offset is in 32 bit units but need in 8 bit units */
+	offset *= 4;
 
-	ret = msrpm[t1] & ((1 << param) << t0);
-
-out:
-	nested_svm_unmap(msrpm, KM_USER0);
+	if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4))
+		return NESTED_EXIT_DONE;
 
-	return ret;
+	return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
 }
 
 static int nested_svm_exit_special(struct vcpu_svm *svm)
@@ -1504,17 +1651,21 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
 	switch (exit_code) {
 	case SVM_EXIT_INTR:
 	case SVM_EXIT_NMI:
+	case SVM_EXIT_EXCP_BASE + MC_VECTOR:
 		return NESTED_EXIT_HOST;
-		/* For now we are always handling NPFs when using them */
 	case SVM_EXIT_NPF:
+		/* For now we are always handling NPFs when using them */
 		if (npt_enabled)
 			return NESTED_EXIT_HOST;
 		break;
-	/* When we're shadowing, trap PFs */
 	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+		/* When we're shadowing, trap PFs */
 		if (!npt_enabled)
 			return NESTED_EXIT_HOST;
 		break;
+	case SVM_EXIT_EXCP_BASE + NM_VECTOR:
+		nm_interception(svm);
+		break;
 	default:
 		break;
 	}
@@ -1525,7 +1676,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
 /*
  * If this function returns true, this #vmexit was already handled
  */
-static int nested_svm_exit_handled(struct vcpu_svm *svm)
+static int nested_svm_intercept(struct vcpu_svm *svm)
 {
 	u32 exit_code = svm->vmcb->control.exit_code;
 	int vmexit = NESTED_EXIT_HOST;
@@ -1534,6 +1685,9 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm)
 	case SVM_EXIT_MSR:
 		vmexit = nested_svm_exit_handled_msr(svm);
 		break;
+	case SVM_EXIT_IOIO:
+		vmexit = nested_svm_intercept_ioio(svm);
+		break;
 	case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
 		u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
 		if (svm->nested.intercept_cr_read & cr_bits)
@@ -1564,6 +1718,10 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm)
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
+	case SVM_EXIT_ERR: {
+		vmexit = NESTED_EXIT_DONE;
+		break;
+	}
 	default: {
 		u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
 		if (svm->nested.intercept & exit_bits)
@@ -1571,9 +1729,17 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm)
 	}
 	}
 
-	if (vmexit == NESTED_EXIT_DONE) {
+	return vmexit;
+}
+
+static int nested_svm_exit_handled(struct vcpu_svm *svm)
+{
+	int vmexit;
+
+	vmexit = nested_svm_intercept(svm);
+
+	if (vmexit == NESTED_EXIT_DONE)
 		nested_svm_vmexit(svm);
-	}
 
 	return vmexit;
 }
@@ -1615,6 +1781,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
+	struct page *page;
 
 	trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
 				       vmcb->control.exit_info_1,
@@ -1622,10 +1789,13 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 				       vmcb->control.exit_int_info,
 				       vmcb->control.exit_int_info_err);
 
-	nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0);
+	nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page);
 	if (!nested_vmcb)
 		return 1;
 
+	/* Exit nested SVM mode */
+	svm->nested.vmcb = 0;
+
 	/* Give the current vmcb to the guest */
 	disable_gif(svm);
 
@@ -1635,9 +1805,10 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	nested_vmcb->save.ds     = vmcb->save.ds;
 	nested_vmcb->save.gdtr   = vmcb->save.gdtr;
 	nested_vmcb->save.idtr   = vmcb->save.idtr;
-	if (npt_enabled)
-		nested_vmcb->save.cr3    = vmcb->save.cr3;
+	nested_vmcb->save.cr0    = kvm_read_cr0(&svm->vcpu);
+	nested_vmcb->save.cr3    = svm->vcpu.arch.cr3;
 	nested_vmcb->save.cr2    = vmcb->save.cr2;
+	nested_vmcb->save.cr4    = svm->vcpu.arch.cr4;
 	nested_vmcb->save.rflags = vmcb->save.rflags;
 	nested_vmcb->save.rip    = vmcb->save.rip;
 	nested_vmcb->save.rsp    = vmcb->save.rsp;
@@ -1709,10 +1880,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->vmcb->save.cpl = 0;
 	svm->vmcb->control.exit_int_info = 0;
 
-	/* Exit nested SVM mode */
-	svm->nested.vmcb = 0;
-
-	nested_svm_unmap(nested_vmcb, KM_USER0);
+	nested_svm_unmap(page);
 
 	kvm_mmu_reset_context(&svm->vcpu);
 	kvm_mmu_load(&svm->vcpu);
@@ -1722,19 +1890,33 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 
 static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 {
-	u32 *nested_msrpm;
+	/*
+	 * This function merges the msr permission bitmaps of kvm and the
+	 * nested vmcb. It is omptimized in that it only merges the parts where
+	 * the kvm msr permission bitmap may contain zero bits
+	 */
 	int i;
 
-	nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
-	if (!nested_msrpm)
-		return false;
+	if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+		return true;
 
-	for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
-		svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
+	for (i = 0; i < MSRPM_OFFSETS; i++) {
+		u32 value, p;
+		u64 offset;
 
-	svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
+		if (msrpm_offsets[i] == 0xffffffff)
+			break;
+
+		p      = msrpm_offsets[i];
+		offset = svm->nested.vmcb_msrpm + (p * 4);
+
+		if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4))
+			return false;
+
+		svm->nested.msrpm[p] = svm->msrpm[p] | value;
+	}
 
-	nested_svm_unmap(nested_msrpm, KM_USER0);
+	svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
 
 	return true;
 }
@@ -1744,26 +1926,34 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
+	struct page *page;
+	u64 vmcb_gpa;
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+	vmcb_gpa = svm->vmcb->save.rax;
+
+	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
 	if (!nested_vmcb)
 		return false;
 
-	/* nested_vmcb is our indicator if nested SVM is activated */
-	svm->nested.vmcb = svm->vmcb->save.rax;
-
-	trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+	trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, vmcb_gpa,
 			       nested_vmcb->save.rip,
 			       nested_vmcb->control.int_ctl,
 			       nested_vmcb->control.event_inj,
 			       nested_vmcb->control.nested_ctl);
 
+	trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read,
+				    nested_vmcb->control.intercept_cr_write,
+				    nested_vmcb->control.intercept_exceptions,
+				    nested_vmcb->control.intercept);
+
 	/* Clear internal status */
 	kvm_clear_exception_queue(&svm->vcpu);
 	kvm_clear_interrupt_queue(&svm->vcpu);
 
-	/* Save the old vmcb, so we don't need to pick what we save, but
-	   can restore everything when a VMEXIT occurs */
+	/*
+	 * Save the old vmcb, so we don't need to pick what we save, but can
+	 * restore everything when a VMEXIT occurs
+	 */
 	hsave->save.es     = vmcb->save.es;
 	hsave->save.cs     = vmcb->save.cs;
 	hsave->save.ss     = vmcb->save.ss;
@@ -1803,14 +1993,17 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	if (npt_enabled) {
 		svm->vmcb->save.cr3 = nested_vmcb->save.cr3;
 		svm->vcpu.arch.cr3 = nested_vmcb->save.cr3;
-	} else {
+	} else
 		kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
-		kvm_mmu_reset_context(&svm->vcpu);
-	}
+
+	/* Guest paging mode is active - reset mmu */
+	kvm_mmu_reset_context(&svm->vcpu);
+
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
 	kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
 	kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
 	kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+
 	/* In case we don't even reach vcpu_run, the fields are not updated */
 	svm->vmcb->save.rax = nested_vmcb->save.rax;
 	svm->vmcb->save.rsp = nested_vmcb->save.rsp;
@@ -1819,22 +2012,8 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
 	svm->vmcb->save.cpl = nested_vmcb->save.cpl;
 
-	/* We don't want a nested guest to be more powerful than the guest,
-	   so all intercepts are ORed */
-	svm->vmcb->control.intercept_cr_read |=
-		nested_vmcb->control.intercept_cr_read;
-	svm->vmcb->control.intercept_cr_write |=
-		nested_vmcb->control.intercept_cr_write;
-	svm->vmcb->control.intercept_dr_read |=
-		nested_vmcb->control.intercept_dr_read;
-	svm->vmcb->control.intercept_dr_write |=
-		nested_vmcb->control.intercept_dr_write;
-	svm->vmcb->control.intercept_exceptions |=
-		nested_vmcb->control.intercept_exceptions;
-
-	svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
-
-	svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
+	svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL;
+	svm->nested.vmcb_iopm  = nested_vmcb->control.iopm_base_pa  & ~0x0fffULL;
 
 	/* cache intercepts */
 	svm->nested.intercept_cr_read    = nested_vmcb->control.intercept_cr_read;
@@ -1851,13 +2030,43 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	else
 		svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
 
+	if (svm->vcpu.arch.hflags & HF_VINTR_MASK) {
+		/* We only want the cr8 intercept bits of the guest */
+		svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK;
+		svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
+	}
+
+	/* We don't want to see VMMCALLs from a nested guest */
+	svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VMMCALL);
+
+	/*
+	 * We don't want a nested guest to be more powerful than the guest, so
+	 * all intercepts are ORed
+	 */
+	svm->vmcb->control.intercept_cr_read |=
+		nested_vmcb->control.intercept_cr_read;
+	svm->vmcb->control.intercept_cr_write |=
+		nested_vmcb->control.intercept_cr_write;
+	svm->vmcb->control.intercept_dr_read |=
+		nested_vmcb->control.intercept_dr_read;
+	svm->vmcb->control.intercept_dr_write |=
+		nested_vmcb->control.intercept_dr_write;
+	svm->vmcb->control.intercept_exceptions |=
+		nested_vmcb->control.intercept_exceptions;
+
+	svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
+
+	svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl;
 	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
 	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
 	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
 	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
 	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
 
-	nested_svm_unmap(nested_vmcb, KM_USER0);
+	nested_svm_unmap(page);
+
+	/* nested_vmcb is our indicator if nested SVM is activated */
+	svm->nested.vmcb = vmcb_gpa;
 
 	enable_gif(svm);
 
@@ -1883,6 +2092,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
 static int vmload_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
+	struct page *page;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
@@ -1890,12 +2100,12 @@ static int vmload_interception(struct vcpu_svm *svm)
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
 	if (!nested_vmcb)
 		return 1;
 
 	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
-	nested_svm_unmap(nested_vmcb, KM_USER0);
+	nested_svm_unmap(page);
 
 	return 1;
 }
@@ -1903,6 +2113,7 @@ static int vmload_interception(struct vcpu_svm *svm)
 static int vmsave_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
+	struct page *page;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
@@ -1910,12 +2121,12 @@ static int vmsave_interception(struct vcpu_svm *svm)
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
 
-	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
 	if (!nested_vmcb)
 		return 1;
 
 	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
-	nested_svm_unmap(nested_vmcb, KM_USER0);
+	nested_svm_unmap(page);
 
 	return 1;
 }
@@ -2018,6 +2229,8 @@ static int task_switch_interception(struct vcpu_svm *svm)
 		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK;
 	uint32_t idt_v =
 		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID;
+	bool has_error_code = false;
+	u32 error_code = 0;
 
 	tss_selector = (u16)svm->vmcb->control.exit_info_1;
 
@@ -2038,6 +2251,12 @@ static int task_switch_interception(struct vcpu_svm *svm)
 			svm->vcpu.arch.nmi_injected = false;
 			break;
 		case SVM_EXITINTINFO_TYPE_EXEPT:
+			if (svm->vmcb->control.exit_info_2 &
+			    (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) {
+				has_error_code = true;
+				error_code =
+					(u32)svm->vmcb->control.exit_info_2;
+			}
 			kvm_clear_exception_queue(&svm->vcpu);
 			break;
 		case SVM_EXITINTINFO_TYPE_INTR:
@@ -2054,7 +2273,14 @@ static int task_switch_interception(struct vcpu_svm *svm)
 	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
 		skip_emulated_instruction(&svm->vcpu);
 
-	return kvm_task_switch(&svm->vcpu, tss_selector, reason);
+	if (kvm_task_switch(&svm->vcpu, tss_selector, reason,
+				has_error_code, error_code) == EMULATE_FAIL) {
+		svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		svm->vcpu.run->internal.ndata = 0;
+		return 0;
+	}
+	return 1;
 }
 
 static int cpuid_interception(struct vcpu_svm *svm)
@@ -2145,9 +2371,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 	case MSR_IA32_SYSENTER_ESP:
 		*data = svm->sysenter_esp;
 		break;
-	/* Nobody will change the following 5 values in the VMCB so
-	   we can safely return them on rdmsr. They will always be 0
-	   until LBRV is implemented. */
+	/*
+	 * Nobody will change the following 5 values in the VMCB so we can
+	 * safely return them on rdmsr. They will always be 0 until LBRV is
+	 * implemented.
+	 */
 	case MSR_IA32_DEBUGCTLMSR:
 		*data = svm->vmcb->save.dbgctl;
 		break;
@@ -2167,7 +2395,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 		*data = svm->nested.hsave_msr;
 		break;
 	case MSR_VM_CR:
-		*data = 0;
+		*data = svm->nested.vm_cr_msr;
 		break;
 	case MSR_IA32_UCODE_REV:
 		*data = 0x01000065;
@@ -2197,6 +2425,31 @@ static int rdmsr_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
+static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	int svm_dis, chg_mask;
+
+	if (data & ~SVM_VM_CR_VALID_MASK)
+		return 1;
+
+	chg_mask = SVM_VM_CR_VALID_MASK;
+
+	if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK)
+		chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK);
+
+	svm->nested.vm_cr_msr &= ~chg_mask;
+	svm->nested.vm_cr_msr |= (data & chg_mask);
+
+	svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK;
+
+	/* check for svm_disable while efer.svme is set */
+	if (svm_dis && (vcpu->arch.efer & EFER_SVME))
+		return 1;
+
+	return 0;
+}
+
 static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -2263,6 +2516,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 		svm->nested.hsave_msr = data;
 		break;
 	case MSR_VM_CR:
+		return svm_set_vm_cr(vcpu, data);
 	case MSR_VM_IGNNE:
 		pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
@@ -2326,16 +2580,16 @@ static int pause_interception(struct vcpu_svm *svm)
 }
 
 static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
-	[SVM_EXIT_READ_CR0]           		= emulate_on_interception,
-	[SVM_EXIT_READ_CR3]           		= emulate_on_interception,
-	[SVM_EXIT_READ_CR4]           		= emulate_on_interception,
-	[SVM_EXIT_READ_CR8]           		= emulate_on_interception,
+	[SVM_EXIT_READ_CR0]			= emulate_on_interception,
+	[SVM_EXIT_READ_CR3]			= emulate_on_interception,
+	[SVM_EXIT_READ_CR4]			= emulate_on_interception,
+	[SVM_EXIT_READ_CR8]			= emulate_on_interception,
 	[SVM_EXIT_CR0_SEL_WRITE]		= emulate_on_interception,
-	[SVM_EXIT_WRITE_CR0]          		= emulate_on_interception,
-	[SVM_EXIT_WRITE_CR3]          		= emulate_on_interception,
-	[SVM_EXIT_WRITE_CR4]          		= emulate_on_interception,
-	[SVM_EXIT_WRITE_CR8]          		= cr8_write_interception,
-	[SVM_EXIT_READ_DR0] 			= emulate_on_interception,
+	[SVM_EXIT_WRITE_CR0]			= emulate_on_interception,
+	[SVM_EXIT_WRITE_CR3]			= emulate_on_interception,
+	[SVM_EXIT_WRITE_CR4]			= emulate_on_interception,
+	[SVM_EXIT_WRITE_CR8]			= cr8_write_interception,
+	[SVM_EXIT_READ_DR0]			= emulate_on_interception,
 	[SVM_EXIT_READ_DR1]			= emulate_on_interception,
 	[SVM_EXIT_READ_DR2]			= emulate_on_interception,
 	[SVM_EXIT_READ_DR3]			= emulate_on_interception,
@@ -2354,15 +2608,14 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_EXCP_BASE + DB_VECTOR]	= db_interception,
 	[SVM_EXIT_EXCP_BASE + BP_VECTOR]	= bp_interception,
 	[SVM_EXIT_EXCP_BASE + UD_VECTOR]	= ud_interception,
-	[SVM_EXIT_EXCP_BASE + PF_VECTOR] 	= pf_interception,
-	[SVM_EXIT_EXCP_BASE + NM_VECTOR] 	= nm_interception,
-	[SVM_EXIT_EXCP_BASE + MC_VECTOR] 	= mc_interception,
-	[SVM_EXIT_INTR] 			= intr_interception,
+	[SVM_EXIT_EXCP_BASE + PF_VECTOR]	= pf_interception,
+	[SVM_EXIT_EXCP_BASE + NM_VECTOR]	= nm_interception,
+	[SVM_EXIT_EXCP_BASE + MC_VECTOR]	= mc_interception,
+	[SVM_EXIT_INTR]				= intr_interception,
 	[SVM_EXIT_NMI]				= nmi_interception,
 	[SVM_EXIT_SMI]				= nop_on_interception,
 	[SVM_EXIT_INIT]				= nop_on_interception,
 	[SVM_EXIT_VINTR]			= interrupt_window_interception,
-	/* [SVM_EXIT_CR0_SEL_WRITE]		= emulate_on_interception, */
 	[SVM_EXIT_CPUID]			= cpuid_interception,
 	[SVM_EXIT_IRET]                         = iret_interception,
 	[SVM_EXIT_INVD]                         = emulate_on_interception,
@@ -2370,7 +2623,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,
 	[SVM_EXIT_INVLPGA]			= invlpga_interception,
-	[SVM_EXIT_IOIO] 		  	= io_interception,
+	[SVM_EXIT_IOIO]				= io_interception,
 	[SVM_EXIT_MSR]				= msr_interception,
 	[SVM_EXIT_TASK_SWITCH]			= task_switch_interception,
 	[SVM_EXIT_SHUTDOWN]			= shutdown_interception,
@@ -2393,7 +2646,12 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 	u32 exit_code = svm->vmcb->control.exit_code;
 
-	trace_kvm_exit(exit_code, svm->vmcb->save.rip);
+	trace_kvm_exit(exit_code, vcpu);
+
+	if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
+		vcpu->arch.cr0 = svm->vmcb->save.cr0;
+	if (npt_enabled)
+		vcpu->arch.cr3 = svm->vmcb->save.cr3;
 
 	if (unlikely(svm->nested.exit_required)) {
 		nested_svm_vmexit(svm);
@@ -2422,11 +2680,6 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 
 	svm_complete_interrupts(svm);
 
-	if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
-		vcpu->arch.cr0 = svm->vmcb->save.cr0;
-	if (npt_enabled)
-		vcpu->arch.cr3 = svm->vmcb->save.cr3;
-
 	if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		kvm_run->fail_entry.hardware_entry_failure_reason
@@ -2511,6 +2764,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+		return;
+
 	if (irr == -1)
 		return;
 
@@ -2522,8 +2778,12 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
-	return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
-		!(svm->vcpu.arch.hflags & HF_NMI_MASK);
+	int ret;
+	ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+	      !(svm->vcpu.arch.hflags & HF_NMI_MASK);
+	ret = ret && gif_set(svm) && nested_svm_nmi(svm);
+
+	return ret;
 }
 
 static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
@@ -2568,13 +2828,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	nested_svm_intr(svm);
-
-	/* In case GIF=0 we can't rely on the CPU to tell us when
-	 * GIF becomes 1, because that's a separate STGI/VMRUN intercept.
-	 * The next time we get that intercept, this function will be
-	 * called again though and we'll get the vintr intercept. */
-	if (gif_set(svm)) {
+	/*
+	 * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
+	 * 1, because that's a separate STGI/VMRUN intercept.  The next time we
+	 * get that intercept, this function will be called again though and
+	 * we'll get the vintr intercept.
+	 */
+	if (gif_set(svm) && nested_svm_intr(svm)) {
 		svm_set_vintr(svm);
 		svm_inject_irq(svm, 0x0);
 	}
@@ -2588,9 +2848,10 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 	    == HF_NMI_MASK)
 		return; /* IRET will cause a vm exit */
 
-	/* Something prevents NMI from been injected. Single step over
-	   possible problem (IRET or exception injection or interrupt
-	   shadow) */
+	/*
+	 * Something prevents NMI from been injected. Single step over possible
+	 * problem (IRET or exception injection or interrupt shadow)
+	 */
 	svm->nmi_singlestep = true;
 	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
 	update_db_intercept(vcpu);
@@ -2614,6 +2875,9 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+		return;
+
 	if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
 		int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
 		kvm_set_cr8(vcpu, cr8);
@@ -2625,6 +2889,9 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 cr8;
 
+	if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+		return;
+
 	cr8 = kvm_get_cr8(vcpu);
 	svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
 	svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
@@ -2635,6 +2902,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 	u8 vector;
 	int type;
 	u32 exitintinfo = svm->vmcb->control.exit_int_info;
+	unsigned int3_injected = svm->int3_injected;
+
+	svm->int3_injected = 0;
 
 	if (svm->vcpu.arch.hflags & HF_IRET_MASK)
 		svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
@@ -2654,18 +2924,25 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 		svm->vcpu.arch.nmi_injected = true;
 		break;
 	case SVM_EXITINTINFO_TYPE_EXEPT:
-		/* In case of software exception do not reinject an exception
-		   vector, but re-execute and instruction instead */
-		if (is_nested(svm))
-			break;
-		if (kvm_exception_is_soft(vector))
+		/*
+		 * In case of software exceptions, do not reinject the vector,
+		 * but re-execute the instruction instead. Rewind RIP first
+		 * if we emulated INT3 before.
+		 */
+		if (kvm_exception_is_soft(vector)) {
+			if (vector == BP_VECTOR && int3_injected &&
+			    kvm_is_linear_rip(&svm->vcpu, svm->int3_rip))
+				kvm_rip_write(&svm->vcpu,
+					      kvm_rip_read(&svm->vcpu) -
+					      int3_injected);
 			break;
+		}
 		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
 			u32 err = svm->vmcb->control.exit_int_info_err;
-			kvm_queue_exception_e(&svm->vcpu, vector, err);
+			kvm_requeue_exception_e(&svm->vcpu, vector, err);
 
 		} else
-			kvm_queue_exception(&svm->vcpu, vector);
+			kvm_requeue_exception(&svm->vcpu, vector);
 		break;
 	case SVM_EXITINTINFO_TYPE_INTR:
 		kvm_queue_interrupt(&svm->vcpu, vector, false);
@@ -2688,6 +2965,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	u16 gs_selector;
 	u16 ldt_selector;
 
+	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+
 	/*
 	 * A vmexit emulation is required before the vcpu can be executed
 	 * again.
@@ -2695,10 +2976,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->nested.exit_required))
 		return;
 
-	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
-	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
-	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
-
 	pre_svm_run(svm);
 
 	sync_lapic_to_cr8(vcpu);
@@ -2879,25 +3156,39 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }
 
+static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+{
+	switch (func) {
+	case 0x8000000A:
+		entry->eax = 1; /* SVM revision 1 */
+		entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper
+				   ASID emulation to nested SVM */
+		entry->ecx = 0; /* Reserved */
+		entry->edx = 0; /* Do not support any additional features */
+
+		break;
+	}
+}
+
 static const struct trace_print_flags svm_exit_reasons_str[] = {
-	{ SVM_EXIT_READ_CR0,           		"read_cr0" },
-	{ SVM_EXIT_READ_CR3,	      		"read_cr3" },
-	{ SVM_EXIT_READ_CR4,	      		"read_cr4" },
-	{ SVM_EXIT_READ_CR8,  	      		"read_cr8" },
-	{ SVM_EXIT_WRITE_CR0,          		"write_cr0" },
-	{ SVM_EXIT_WRITE_CR3,	      		"write_cr3" },
-	{ SVM_EXIT_WRITE_CR4,          		"write_cr4" },
-	{ SVM_EXIT_WRITE_CR8, 	      		"write_cr8" },
-	{ SVM_EXIT_READ_DR0, 	      		"read_dr0" },
-	{ SVM_EXIT_READ_DR1,	      		"read_dr1" },
-	{ SVM_EXIT_READ_DR2,	      		"read_dr2" },
-	{ SVM_EXIT_READ_DR3,	      		"read_dr3" },
-	{ SVM_EXIT_WRITE_DR0,	      		"write_dr0" },
-	{ SVM_EXIT_WRITE_DR1,	      		"write_dr1" },
-	{ SVM_EXIT_WRITE_DR2,	      		"write_dr2" },
-	{ SVM_EXIT_WRITE_DR3,	      		"write_dr3" },
-	{ SVM_EXIT_WRITE_DR5,	      		"write_dr5" },
-	{ SVM_EXIT_WRITE_DR7,	      		"write_dr7" },
+	{ SVM_EXIT_READ_CR0,			"read_cr0" },
+	{ SVM_EXIT_READ_CR3,			"read_cr3" },
+	{ SVM_EXIT_READ_CR4,			"read_cr4" },
+	{ SVM_EXIT_READ_CR8,			"read_cr8" },
+	{ SVM_EXIT_WRITE_CR0,			"write_cr0" },
+	{ SVM_EXIT_WRITE_CR3,			"write_cr3" },
+	{ SVM_EXIT_WRITE_CR4,			"write_cr4" },
+	{ SVM_EXIT_WRITE_CR8,			"write_cr8" },
+	{ SVM_EXIT_READ_DR0,			"read_dr0" },
+	{ SVM_EXIT_READ_DR1,			"read_dr1" },
+	{ SVM_EXIT_READ_DR2,			"read_dr2" },
+	{ SVM_EXIT_READ_DR3,			"read_dr3" },
+	{ SVM_EXIT_WRITE_DR0,			"write_dr0" },
+	{ SVM_EXIT_WRITE_DR1,			"write_dr1" },
+	{ SVM_EXIT_WRITE_DR2,			"write_dr2" },
+	{ SVM_EXIT_WRITE_DR3,			"write_dr3" },
+	{ SVM_EXIT_WRITE_DR5,			"write_dr5" },
+	{ SVM_EXIT_WRITE_DR7,			"write_dr7" },
 	{ SVM_EXIT_EXCP_BASE + DB_VECTOR,	"DB excp" },
 	{ SVM_EXIT_EXCP_BASE + BP_VECTOR,	"BP excp" },
 	{ SVM_EXIT_EXCP_BASE + UD_VECTOR,	"UD excp" },
@@ -2946,8 +3237,10 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	update_cr0_intercept(svm);
 	svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR;
+	if (is_nested(svm))
+		svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR;
+	update_cr0_intercept(svm);
 }
 
 static struct kvm_x86_ops svm_x86_ops = {
@@ -2986,8 +3279,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.set_idt = svm_set_idt,
 	.get_gdt = svm_get_gdt,
 	.set_gdt = svm_set_gdt,
-	.get_dr = svm_get_dr,
-	.set_dr = svm_set_dr,
+	.set_dr7 = svm_set_dr7,
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
@@ -3023,12 +3315,14 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.cpuid_update = svm_cpuid_update,
 
 	.rdtscp_supported = svm_rdtscp_supported,
+
+	.set_supported_cpuid = svm_set_supported_cpuid,
 };
 
 static int __init svm_init(void)
 {
 	return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm),
-			      THIS_MODULE);
+			__alignof__(struct vcpu_svm), THIS_MODULE);
 }
 
 static void __exit svm_exit(void)

arch/x86/kvm/timer.c

@@ -12,7 +12,8 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
 	/*
 	 * There is a race window between reading and incrementing, but we do
 	 * not care about potentially loosing timer events in the !reinject
-	 * case anyway.
+	 * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
+	 * in vcpu_enter_guest.
 	 */
 	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
 		atomic_inc(&ktimer->pending);

arch/x86/kvm/trace.h

@@ -5,8 +5,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
-#define TRACE_INCLUDE_PATH arch/x86/kvm
-#define TRACE_INCLUDE_FILE trace
 
 /*
  * Tracepoint for guest mode entry.
@@ -184,8 +182,8 @@ TRACE_EVENT(kvm_apic,
  * Tracepoint for kvm guest exit:
  */
 TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned int exit_reason, unsigned long guest_rip),
-	TP_ARGS(exit_reason, guest_rip),
+	TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu),
+	TP_ARGS(exit_reason, vcpu),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int,	exit_reason	)
@@ -194,7 +192,7 @@ TRACE_EVENT(kvm_exit,
 
 	TP_fast_assign(
 		__entry->exit_reason	= exit_reason;
-		__entry->guest_rip	= guest_rip;
+		__entry->guest_rip	= kvm_rip_read(vcpu);
 	),
 
 	TP_printk("reason %s rip 0x%lx",
@@ -221,6 +219,38 @@ TRACE_EVENT(kvm_inj_virq,
 	TP_printk("irq %u", __entry->irq)
 );
 
+#define EXS(x) { x##_VECTOR, "#" #x }
+
+#define kvm_trace_sym_exc						\
+	EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM),	\
+	EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF),		\
+	EXS(MF), EXS(MC)
+
+/*
+ * Tracepoint for kvm interrupt injection:
+ */
+TRACE_EVENT(kvm_inj_exception,
+	TP_PROTO(unsigned exception, bool has_error, unsigned error_code),
+	TP_ARGS(exception, has_error, error_code),
+
+	TP_STRUCT__entry(
+		__field(	u8,	exception	)
+		__field(	u8,	has_error	)
+		__field(	u32,	error_code	)
+	),
+
+	TP_fast_assign(
+		__entry->exception	= exception;
+		__entry->has_error	= has_error;
+		__entry->error_code	= error_code;
+	),
+
+	TP_printk("%s (0x%x)",
+		  __print_symbolic(__entry->exception, kvm_trace_sym_exc),
+		  /* FIXME: don't print error_code if not present */
+		  __entry->has_error ? __entry->error_code : 0)
+);
+
 /*
  * Tracepoint for page fault.
  */
@@ -413,12 +443,34 @@ TRACE_EVENT(kvm_nested_vmrun,
 	),
 
 	TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x "
-		  "event_inj: 0x%08x npt: %s\n",
+		  "event_inj: 0x%08x npt: %s",
 		__entry->rip, __entry->vmcb, __entry->nested_rip,
 		__entry->int_ctl, __entry->event_inj,
 		__entry->npt ? "on" : "off")
 );
 
+TRACE_EVENT(kvm_nested_intercepts,
+	    TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept),
+	    TP_ARGS(cr_read, cr_write, exceptions, intercept),
+
+	TP_STRUCT__entry(
+		__field(	__u16,		cr_read		)
+		__field(	__u16,		cr_write	)
+		__field(	__u32,		exceptions	)
+		__field(	__u64,		intercept	)
+	),
+
+	TP_fast_assign(
+		__entry->cr_read	= cr_read;
+		__entry->cr_write	= cr_write;
+		__entry->exceptions	= exceptions;
+		__entry->intercept	= intercept;
+	),
+
+	TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx",
+		__entry->cr_read, __entry->cr_write, __entry->exceptions,
+		__entry->intercept)
+);
 /*
  * Tracepoint for #VMEXIT while nested
  */
@@ -447,7 +499,7 @@ TRACE_EVENT(kvm_nested_vmexit,
 		__entry->exit_int_info_err	= exit_int_info_err;
 	),
 	TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx "
-		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x",
 		  __entry->rip,
 		  ftrace_print_symbols_seq(p, __entry->exit_code,
 					   kvm_x86_ops->exit_reasons_str),
@@ -482,7 +534,7 @@ TRACE_EVENT(kvm_nested_vmexit_inject,
 	),
 
 	TP_printk("reason: %s ext_inf1: 0x%016llx "
-		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x",
 		  ftrace_print_symbols_seq(p, __entry->exit_code,
 					   kvm_x86_ops->exit_reasons_str),
 		__entry->exit_info1, __entry->exit_info2,
@@ -504,7 +556,7 @@ TRACE_EVENT(kvm_nested_intr_vmexit,
 		__entry->rip	=	rip
 	),
 
-	TP_printk("rip: 0x%016llx\n", __entry->rip)
+	TP_printk("rip: 0x%016llx", __entry->rip)
 );
 
 /*
@@ -526,7 +578,7 @@ TRACE_EVENT(kvm_invlpga,
 		__entry->address	=	address;
 	),
 
-	TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n",
+	TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx",
 		  __entry->rip, __entry->asid, __entry->address)
 );
 
@@ -547,11 +599,102 @@ TRACE_EVENT(kvm_skinit,
 		__entry->slb		=	slb;
 	),
 
-	TP_printk("rip: 0x%016llx slb: 0x%08x\n",
+	TP_printk("rip: 0x%016llx slb: 0x%08x",
 		  __entry->rip, __entry->slb)
 );
 
+#define __print_insn(insn, ilen) ({		                 \
+	int i;							 \
+	const char *ret = p->buffer + p->len;			 \
+								 \
+	for (i = 0; i < ilen; ++i)				 \
+		trace_seq_printf(p, " %02x", insn[i]);		 \
+	trace_seq_printf(p, "%c", 0);				 \
+	ret;							 \
+	})
+
+#define KVM_EMUL_INSN_F_CR0_PE (1 << 0)
+#define KVM_EMUL_INSN_F_EFL_VM (1 << 1)
+#define KVM_EMUL_INSN_F_CS_D   (1 << 2)
+#define KVM_EMUL_INSN_F_CS_L   (1 << 3)
+
+#define kvm_trace_symbol_emul_flags	                  \
+	{ 0,   			    "real" },		  \
+	{ KVM_EMUL_INSN_F_CR0_PE			  \
+	  | KVM_EMUL_INSN_F_EFL_VM, "vm16" },		  \
+	{ KVM_EMUL_INSN_F_CR0_PE,   "prot16" },		  \
+	{ KVM_EMUL_INSN_F_CR0_PE			  \
+	  | KVM_EMUL_INSN_F_CS_D,   "prot32" },		  \
+	{ KVM_EMUL_INSN_F_CR0_PE			  \
+	  | KVM_EMUL_INSN_F_CS_L,   "prot64" }
+
+#define kei_decode_mode(mode) ({			\
+	u8 flags = 0xff;				\
+	switch (mode) {					\
+	case X86EMUL_MODE_REAL:				\
+		flags = 0;				\
+		break;					\
+	case X86EMUL_MODE_VM86:				\
+		flags = KVM_EMUL_INSN_F_EFL_VM;		\
+		break;					\
+	case X86EMUL_MODE_PROT16:			\
+		flags = KVM_EMUL_INSN_F_CR0_PE;		\
+		break;					\
+	case X86EMUL_MODE_PROT32:			\
+		flags = KVM_EMUL_INSN_F_CR0_PE		\
+			| KVM_EMUL_INSN_F_CS_D;		\
+		break;					\
+	case X86EMUL_MODE_PROT64:			\
+		flags = KVM_EMUL_INSN_F_CR0_PE		\
+			| KVM_EMUL_INSN_F_CS_L;		\
+		break;					\
+	}						\
+	flags;						\
+	})
+
+TRACE_EVENT(kvm_emulate_insn,
+	TP_PROTO(struct kvm_vcpu *vcpu, __u8 failed),
+	TP_ARGS(vcpu, failed),
+
+	TP_STRUCT__entry(
+		__field(    __u64, rip                       )
+		__field(    __u32, csbase                    )
+		__field(    __u8,  len                       )
+		__array(    __u8,  insn,    15	             )
+		__field(    __u8,  flags       	   	     )
+		__field(    __u8,  failed                    )
+		),
+
+	TP_fast_assign(
+		__entry->rip = vcpu->arch.emulate_ctxt.decode.fetch.start;
+		__entry->csbase = kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS);
+		__entry->len = vcpu->arch.emulate_ctxt.decode.eip
+			       - vcpu->arch.emulate_ctxt.decode.fetch.start;
+		memcpy(__entry->insn,
+		       vcpu->arch.emulate_ctxt.decode.fetch.data,
+		       15);
+		__entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt.mode);
+		__entry->failed = failed;
+		),
+
+	TP_printk("%x:%llx:%s (%s)%s",
+		  __entry->csbase, __entry->rip,
+		  __print_insn(__entry->insn, __entry->len),
+		  __print_symbolic(__entry->flags,
+				   kvm_trace_symbol_emul_flags),
+		  __entry->failed ? " failed" : ""
+		)
+	);
+
+#define trace_kvm_emulate_insn_start(vcpu) trace_kvm_emulate_insn(vcpu, 0)
+#define trace_kvm_emulate_insn_failed(vcpu) trace_kvm_emulate_insn(vcpu, 1)
+
 #endif /* _TRACE_KVM_H */
 
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH arch/x86/kvm
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
 /* This part must be outside protection */
 #include <trace/define_trace.h>

arch/x86/kvm/vmx.c

@@ -27,6 +27,7 @@
 #include <linux/moduleparam.h>
 #include <linux/ftrace_event.h>
 #include <linux/slab.h>
+#include <linux/tboot.h>
 #include "kvm_cache_regs.h"
 #include "x86.h"
 
@@ -98,6 +99,8 @@ module_param(ple_gap, int, S_IRUGO);
 static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
 module_param(ple_window, int, S_IRUGO);
 
+#define NR_AUTOLOAD_MSRS 1
+
 struct vmcs {
 	u32 revision_id;
 	u32 abort;
@@ -125,6 +128,11 @@ struct vcpu_vmx {
 	u64 		      msr_guest_kernel_gs_base;
 #endif
 	struct vmcs          *vmcs;
+	struct msr_autoload {
+		unsigned nr;
+		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
+		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+	} msr_autoload;
 	struct {
 		int           loaded;
 		u16           fs_sel, gs_sel, ldt_sel;
@@ -234,56 +242,56 @@ static const u32 vmx_msr_index[] = {
 };
 #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
 
-static inline int is_page_fault(u32 intr_info)
+static inline bool is_page_fault(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
 		(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
 }
 
-static inline int is_no_device(u32 intr_info)
+static inline bool is_no_device(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
 		(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
 }
 
-static inline int is_invalid_opcode(u32 intr_info)
+static inline bool is_invalid_opcode(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
 		(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
 }
 
-static inline int is_external_interrupt(u32 intr_info)
+static inline bool is_external_interrupt(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
 		== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
 }
 
-static inline int is_machine_check(u32 intr_info)
+static inline bool is_machine_check(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
 		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
 }
 
-static inline int cpu_has_vmx_msr_bitmap(void)
+static inline bool cpu_has_vmx_msr_bitmap(void)
 {
 	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
 }
 
-static inline int cpu_has_vmx_tpr_shadow(void)
+static inline bool cpu_has_vmx_tpr_shadow(void)
 {
 	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
 }
 
-static inline int vm_need_tpr_shadow(struct kvm *kvm)
+static inline bool vm_need_tpr_shadow(struct kvm *kvm)
 {
 	return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
 }
 
-static inline int cpu_has_secondary_exec_ctrls(void)
+static inline bool cpu_has_secondary_exec_ctrls(void)
 {
 	return vmcs_config.cpu_based_exec_ctrl &
 		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
@@ -303,80 +311,80 @@ static inline bool cpu_has_vmx_flexpriority(void)
 
 static inline bool cpu_has_vmx_ept_execute_only(void)
 {
-	return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT);
+	return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
 }
 
 static inline bool cpu_has_vmx_eptp_uncacheable(void)
 {
-	return !!(vmx_capability.ept & VMX_EPTP_UC_BIT);
+	return vmx_capability.ept & VMX_EPTP_UC_BIT;
 }
 
 static inline bool cpu_has_vmx_eptp_writeback(void)
 {
-	return !!(vmx_capability.ept & VMX_EPTP_WB_BIT);
+	return vmx_capability.ept & VMX_EPTP_WB_BIT;
 }
 
 static inline bool cpu_has_vmx_ept_2m_page(void)
 {
-	return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
+	return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
 }
 
 static inline bool cpu_has_vmx_ept_1g_page(void)
 {
-	return !!(vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT);
+	return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
 }
 
-static inline int cpu_has_vmx_invept_individual_addr(void)
+static inline bool cpu_has_vmx_invept_individual_addr(void)
 {
-	return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
+	return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT;
 }
 
-static inline int cpu_has_vmx_invept_context(void)
+static inline bool cpu_has_vmx_invept_context(void)
 {
-	return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT);
+	return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
 }
 
-static inline int cpu_has_vmx_invept_global(void)
+static inline bool cpu_has_vmx_invept_global(void)
 {
-	return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT);
+	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
 }
 
-static inline int cpu_has_vmx_ept(void)
+static inline bool cpu_has_vmx_ept(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_ENABLE_EPT;
 }
 
-static inline int cpu_has_vmx_unrestricted_guest(void)
+static inline bool cpu_has_vmx_unrestricted_guest(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_UNRESTRICTED_GUEST;
 }
 
-static inline int cpu_has_vmx_ple(void)
+static inline bool cpu_has_vmx_ple(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
 }
 
-static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
+static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
 {
 	return flexpriority_enabled && irqchip_in_kernel(kvm);
 }
 
-static inline int cpu_has_vmx_vpid(void)
+static inline bool cpu_has_vmx_vpid(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_ENABLE_VPID;
 }
 
-static inline int cpu_has_vmx_rdtscp(void)
+static inline bool cpu_has_vmx_rdtscp(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_RDTSCP;
 }
 
-static inline int cpu_has_virtual_nmis(void)
+static inline bool cpu_has_virtual_nmis(void)
 {
 	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
 }
@@ -595,16 +603,56 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
 
+static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
+{
+	unsigned i;
+	struct msr_autoload *m = &vmx->msr_autoload;
+
+	for (i = 0; i < m->nr; ++i)
+		if (m->guest[i].index == msr)
+			break;
+
+	if (i == m->nr)
+		return;
+	--m->nr;
+	m->guest[i] = m->guest[m->nr];
+	m->host[i] = m->host[m->nr];
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+}
+
+static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
+				  u64 guest_val, u64 host_val)
+{
+	unsigned i;
+	struct msr_autoload *m = &vmx->msr_autoload;
+
+	for (i = 0; i < m->nr; ++i)
+		if (m->guest[i].index == msr)
+			break;
+
+	if (i == m->nr) {
+		++m->nr;
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+	}
+
+	m->guest[i].index = msr;
+	m->guest[i].value = guest_val;
+	m->host[i].index = msr;
+	m->host[i].value = host_val;
+}
+
 static void reload_tss(void)
 {
 	/*
 	 * VT restores TR but not its size.  Useless.
 	 */
-	struct descriptor_table gdt;
+	struct desc_ptr gdt;
 	struct desc_struct *descs;
 
-	kvm_get_gdt(&gdt);
-	descs = (void *)gdt.base;
+	native_store_gdt(&gdt);
+	descs = (void *)gdt.address;
 	descs[GDT_ENTRY_TSS].type = 9; /* available TSS */
 	load_TR_desc();
 }
@@ -631,9 +679,57 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	guest_efer |= host_efer & ignore_bits;
 	vmx->guest_msrs[efer_offset].data = guest_efer;
 	vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+	clear_atomic_switch_msr(vmx, MSR_EFER);
+	/* On ept, can't emulate nx, and must switch nx atomically */
+	if (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX)) {
+		guest_efer = vmx->vcpu.arch.efer;
+		if (!(guest_efer & EFER_LMA))
+			guest_efer &= ~EFER_LME;
+		add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer);
+		return false;
+	}
+
 	return true;
 }
 
+static unsigned long segment_base(u16 selector)
+{
+	struct desc_ptr gdt;
+	struct desc_struct *d;
+	unsigned long table_base;
+	unsigned long v;
+
+	if (!(selector & ~3))
+		return 0;
+
+	native_store_gdt(&gdt);
+	table_base = gdt.address;
+
+	if (selector & 4) {           /* from ldt */
+		u16 ldt_selector = kvm_read_ldt();
+
+		if (!(ldt_selector & ~3))
+			return 0;
+
+		table_base = segment_base(ldt_selector);
+	}
+	d = (struct desc_struct *)(table_base + (selector & ~7));
+	v = get_desc_base(d);
+#ifdef CONFIG_X86_64
+       if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+               v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
+#endif
+	return v;
+}
+
+static inline unsigned long kvm_read_tr_base(void)
+{
+	u16 tr;
+	asm("str %0" : "=g"(tr));
+	return segment_base(tr);
+}
+
 static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -758,7 +854,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	if (vcpu->cpu != cpu) {
-		struct descriptor_table dt;
+		struct desc_ptr dt;
 		unsigned long sysenter_esp;
 
 		vcpu->cpu = cpu;
@@ -767,8 +863,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 * processors.
 		 */
 		vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */
-		kvm_get_gdt(&dt);
-		vmcs_writel(HOST_GDTR_BASE, dt.base);   /* 22.2.4 */
+		native_store_gdt(&dt);
+		vmcs_writel(HOST_GDTR_BASE, dt.address);   /* 22.2.4 */
 
 		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
@@ -846,9 +942,9 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 	int ret = 0;
 
 	if (interruptibility & GUEST_INTR_STATE_STI)
-		ret |= X86_SHADOW_INT_STI;
+		ret |= KVM_X86_SHADOW_INT_STI;
 	if (interruptibility & GUEST_INTR_STATE_MOV_SS)
-		ret |= X86_SHADOW_INT_MOV_SS;
+		ret |= KVM_X86_SHADOW_INT_MOV_SS;
 
 	return ret & mask;
 }
@@ -860,9 +956,9 @@ static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 
 	interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
 
-	if (mask & X86_SHADOW_INT_MOV_SS)
+	if (mask & KVM_X86_SHADOW_INT_MOV_SS)
 		interruptibility |= GUEST_INTR_STATE_MOV_SS;
-	if (mask & X86_SHADOW_INT_STI)
+	else if (mask & KVM_X86_SHADOW_INT_STI)
 		interruptibility |= GUEST_INTR_STATE_STI;
 
 	if ((interruptibility != interruptibility_old))
@@ -882,7 +978,8 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 }
 
 static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
-				bool has_error_code, u32 error_code)
+				bool has_error_code, u32 error_code,
+				bool reinject)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
@@ -1176,9 +1273,16 @@ static __init int vmx_disabled_by_bios(void)
 	u64 msr;
 
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
-	return (msr & (FEATURE_CONTROL_LOCKED |
-		       FEATURE_CONTROL_VMXON_ENABLED))
-	    == FEATURE_CONTROL_LOCKED;
+	if (msr & FEATURE_CONTROL_LOCKED) {
+		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
+			&& tboot_enabled())
+			return 1;
+		if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
+			&& !tboot_enabled())
+			return 1;
+	}
+
+	return 0;
 	/* locked but not enabled */
 }
 
@@ -1186,21 +1290,23 @@ static int hardware_enable(void *garbage)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
-	u64 old;
+	u64 old, test_bits;
 
 	if (read_cr4() & X86_CR4_VMXE)
 		return -EBUSY;
 
 	INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu));
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
-	if ((old & (FEATURE_CONTROL_LOCKED |
-		    FEATURE_CONTROL_VMXON_ENABLED))
-	    != (FEATURE_CONTROL_LOCKED |
-		FEATURE_CONTROL_VMXON_ENABLED))
+
+	test_bits = FEATURE_CONTROL_LOCKED;
+	test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+	if (tboot_enabled())
+		test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;
+
+	if ((old & test_bits) != test_bits) {
 		/* enable and lock */
-		wrmsrl(MSR_IA32_FEATURE_CONTROL, old |
-		       FEATURE_CONTROL_LOCKED |
-		       FEATURE_CONTROL_VMXON_ENABLED);
+		wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
+	}
 	write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */
 	asm volatile (ASM_VMX_VMXON_RAX
 		      : : "a"(&phys_addr), "m"(phys_addr)
@@ -1521,7 +1627,7 @@ static gva_t rmode_tss_base(struct kvm *kvm)
 		struct kvm_memslots *slots;
 		gfn_t base_gfn;
 
-		slots = rcu_dereference(kvm->memslots);
+		slots = kvm_memslots(kvm);
 		base_gfn = kvm->memslots->memslots[0].base_gfn +
 				 kvm->memslots->memslots[0].npages - 3;
 		return base_gfn << PAGE_SHIFT;
@@ -1649,6 +1755,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
 	vmcs_write32(VM_ENTRY_CONTROLS,
 		     vmcs_read32(VM_ENTRY_CONTROLS)
 		     & ~VM_ENTRY_IA32E_MODE);
+	vmx_set_efer(vcpu, vcpu->arch.efer);
 }
 
 #endif
@@ -1934,28 +2041,28 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
 	*l = (ar >> 13) & 1;
 }
 
-static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
-	dt->limit = vmcs_read32(GUEST_IDTR_LIMIT);
-	dt->base = vmcs_readl(GUEST_IDTR_BASE);
+	dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
+	dt->address = vmcs_readl(GUEST_IDTR_BASE);
 }
 
-static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
-	vmcs_write32(GUEST_IDTR_LIMIT, dt->limit);
-	vmcs_writel(GUEST_IDTR_BASE, dt->base);
+	vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
+	vmcs_writel(GUEST_IDTR_BASE, dt->address);
 }
 
-static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
-	dt->limit = vmcs_read32(GUEST_GDTR_LIMIT);
-	dt->base = vmcs_readl(GUEST_GDTR_BASE);
+	dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
+	dt->address = vmcs_readl(GUEST_GDTR_BASE);
 }
 
-static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
-	vmcs_write32(GUEST_GDTR_LIMIT, dt->limit);
-	vmcs_writel(GUEST_GDTR_BASE, dt->base);
+	vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
+	vmcs_writel(GUEST_GDTR_BASE, dt->address);
 }
 
 static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
@@ -2296,6 +2403,16 @@ static void allocate_vpid(struct vcpu_vmx *vmx)
 	spin_unlock(&vmx_vpid_lock);
 }
 
+static void free_vpid(struct vcpu_vmx *vmx)
+{
+	if (!enable_vpid)
+		return;
+	spin_lock(&vmx_vpid_lock);
+	if (vmx->vpid != 0)
+		__clear_bit(vmx->vpid, vmx_vpid_bitmap);
+	spin_unlock(&vmx_vpid_lock);
+}
+
 static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
 {
 	int f = sizeof(unsigned long);
@@ -2334,7 +2451,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	u32 junk;
 	u64 host_pat, tsc_this, tsc_base;
 	unsigned long a;
-	struct descriptor_table dt;
+	struct desc_ptr dt;
 	int i;
 	unsigned long kvm_vmx_return;
 	u32 exec_control;
@@ -2415,14 +2532,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8);  /* 22.2.4 */
 
-	kvm_get_idt(&dt);
-	vmcs_writel(HOST_IDTR_BASE, dt.base);   /* 22.2.4 */
+	native_store_idt(&dt);
+	vmcs_writel(HOST_IDTR_BASE, dt.address);   /* 22.2.4 */
 
 	asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
 	vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
 
 	rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk);
 	vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs);
@@ -2947,22 +3066,20 @@ static int handle_io(struct kvm_vcpu *vcpu)
 	int size, in, string;
 	unsigned port;
 
-	++vcpu->stat.io_exits;
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	string = (exit_qualification & 16) != 0;
+	in = (exit_qualification & 8) != 0;
 
-	if (string) {
-		if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO)
-			return 0;
-		return 1;
-	}
+	++vcpu->stat.io_exits;
 
-	size = (exit_qualification & 7) + 1;
-	in = (exit_qualification & 8) != 0;
-	port = exit_qualification >> 16;
+	if (string || in)
+		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
 
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
 	skip_emulated_instruction(vcpu);
-	return kvm_emulate_pio(vcpu, in, size, port);
+
+	return kvm_fast_pio_out(vcpu, size, port);
 }
 
 static void
@@ -3053,19 +3170,9 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int check_dr_alias(struct kvm_vcpu *vcpu)
-{
-	if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
-		kvm_queue_exception(vcpu, UD_VECTOR);
-		return -1;
-	}
-	return 0;
-}
-
 static int handle_dr(struct kvm_vcpu *vcpu)
 {
 	unsigned long exit_qualification;
-	unsigned long val;
 	int dr, reg;
 
 	/* Do not handle if the CPL > 0, will trigger GP on re-entry */
@@ -3100,67 +3207,20 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 	dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
 	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
 	if (exit_qualification & TYPE_MOV_FROM_DR) {
-		switch (dr) {
-		case 0 ... 3:
-			val = vcpu->arch.db[dr];
-			break;
-		case 4:
-			if (check_dr_alias(vcpu) < 0)
-				return 1;
-			/* fall through */
-		case 6:
-			val = vcpu->arch.dr6;
-			break;
-		case 5:
-			if (check_dr_alias(vcpu) < 0)
-				return 1;
-			/* fall through */
-		default: /* 7 */
-			val = vcpu->arch.dr7;
-			break;
-		}
-		kvm_register_write(vcpu, reg, val);
-	} else {
-		val = vcpu->arch.regs[reg];
-		switch (dr) {
-		case 0 ... 3:
-			vcpu->arch.db[dr] = val;
-			if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
-				vcpu->arch.eff_db[dr] = val;
-			break;
-		case 4:
-			if (check_dr_alias(vcpu) < 0)
-				return 1;
-			/* fall through */
-		case 6:
-			if (val & 0xffffffff00000000ULL) {
-				kvm_inject_gp(vcpu, 0);
-				return 1;
-			}
-			vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
-			break;
-		case 5:
-			if (check_dr_alias(vcpu) < 0)
-				return 1;
-			/* fall through */
-		default: /* 7 */
-			if (val & 0xffffffff00000000ULL) {
-				kvm_inject_gp(vcpu, 0);
-				return 1;
-			}
-			vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
-			if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
-				vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
-				vcpu->arch.switch_db_regs =
-					(val & DR7_BP_EN_MASK);
-			}
-			break;
-		}
-	}
+		unsigned long val;
+		if (!kvm_get_dr(vcpu, dr, &val))
+			kvm_register_write(vcpu, reg, val);
+	} else
+		kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]);
 	skip_emulated_instruction(vcpu);
 	return 1;
 }
 
+static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	vmcs_writel(GUEST_DR7, val);
+}
+
 static int handle_cpuid(struct kvm_vcpu *vcpu)
 {
 	kvm_emulate_cpuid(vcpu);
@@ -3292,6 +3352,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qualification;
+	bool has_error_code = false;
+	u32 error_code = 0;
 	u16 tss_selector;
 	int reason, type, idt_v;
 
@@ -3314,6 +3376,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 			kvm_clear_interrupt_queue(vcpu);
 			break;
 		case INTR_TYPE_HARD_EXCEPTION:
+			if (vmx->idt_vectoring_info &
+			    VECTORING_INFO_DELIVER_CODE_MASK) {
+				has_error_code = true;
+				error_code =
+					vmcs_read32(IDT_VECTORING_ERROR_CODE);
+			}
+			/* fall through */
 		case INTR_TYPE_SOFT_EXCEPTION:
 			kvm_clear_exception_queue(vcpu);
 			break;
@@ -3328,8 +3397,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 		       type != INTR_TYPE_NMI_INTR))
 		skip_emulated_instruction(vcpu);
 
-	if (!kvm_task_switch(vcpu, tss_selector, reason))
+	if (kvm_task_switch(vcpu, tss_selector, reason,
+				has_error_code, error_code) == EMULATE_FAIL) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
 		return 0;
+	}
 
 	/* clear all local breakpoint enable flags */
 	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
@@ -3574,7 +3648,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	u32 exit_reason = vmx->exit_reason;
 	u32 vectoring_info = vmx->idt_vectoring_info;
 
-	trace_kvm_exit(exit_reason, kvm_rip_read(vcpu));
+	trace_kvm_exit(exit_reason, vcpu);
 
 	/* If guest state is invalid, start emulating */
 	if (vmx->emulation_required && emulate_invalid_guest_state)
@@ -3923,10 +3997,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	spin_lock(&vmx_vpid_lock);
-	if (vmx->vpid != 0)
-		__clear_bit(vmx->vpid, vmx_vpid_bitmap);
-	spin_unlock(&vmx_vpid_lock);
+	free_vpid(vmx);
 	vmx_free_vmcs(vcpu);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
@@ -3988,6 +4059,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 uninit_vcpu:
 	kvm_vcpu_uninit(&vmx->vcpu);
 free_vcpu:
+	free_vpid(vmx);
 	kmem_cache_free(kvm_vcpu_cache, vmx);
 	return ERR_PTR(err);
 }
@@ -4118,6 +4190,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+{
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
@@ -4154,6 +4230,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.set_idt = vmx_set_idt,
 	.get_gdt = vmx_get_gdt,
 	.set_gdt = vmx_set_gdt,
+	.set_dr7 = vmx_set_dr7,
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
@@ -4189,6 +4266,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.cpuid_update = vmx_cpuid_update,
 
 	.rdtscp_supported = vmx_rdtscp_supported,
+
+	.set_supported_cpuid = vmx_set_supported_cpuid,
 };
 
 static int __init vmx_init(void)
@@ -4236,7 +4315,8 @@ static int __init vmx_init(void)
 
 	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
 
-	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
+	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r)
 		goto out3;
 

arch/x86/kvm/x86.c

@@ -42,7 +42,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <trace/events/kvm.h>
-#undef TRACE_INCLUDE_FILE
+
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
@@ -224,34 +224,6 @@ static void drop_user_return_notifiers(void *ignore)
 		kvm_on_user_return(&smsr->urn);
 }
 
-unsigned long segment_base(u16 selector)
-{
-	struct descriptor_table gdt;
-	struct desc_struct *d;
-	unsigned long table_base;
-	unsigned long v;
-
-	if (selector == 0)
-		return 0;
-
-	kvm_get_gdt(&gdt);
-	table_base = gdt.base;
-
-	if (selector & 4) {           /* from ldt */
-		u16 ldt_selector = kvm_read_ldt();
-
-		table_base = segment_base(ldt_selector);
-	}
-	d = (struct desc_struct *)(table_base + (selector & ~7));
-	v = get_desc_base(d);
-#ifdef CONFIG_X86_64
-	if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
-		v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
-#endif
-	return v;
-}
-EXPORT_SYMBOL_GPL(segment_base);
-
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
 {
 	if (irqchip_in_kernel(vcpu->kvm))
@@ -293,7 +265,8 @@ static int exception_class(int vector)
 }
 
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
-		unsigned nr, bool has_error, u32 error_code)
+		unsigned nr, bool has_error, u32 error_code,
+		bool reinject)
 {
 	u32 prev_nr;
 	int class1, class2;
@@ -304,6 +277,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		vcpu->arch.exception.has_error_code = has_error;
 		vcpu->arch.exception.nr = nr;
 		vcpu->arch.exception.error_code = error_code;
+		vcpu->arch.exception.reinject = reinject;
 		return;
 	}
 
@@ -332,10 +306,16 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
 {
-	kvm_multiple_exception(vcpu, nr, false, 0);
+	kvm_multiple_exception(vcpu, nr, false, 0, false);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception);
 
+void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
+{
+	kvm_multiple_exception(vcpu, nr, false, 0, true);
+}
+EXPORT_SYMBOL_GPL(kvm_requeue_exception);
+
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
 			   u32 error_code)
 {
@@ -352,10 +332,16 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi);
 
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
 {
-	kvm_multiple_exception(vcpu, nr, true, error_code);
+	kvm_multiple_exception(vcpu, nr, true, error_code, false);
 }
 EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
 
+void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
+{
+	kvm_multiple_exception(vcpu, nr, true, error_code, true);
+}
+EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
+
 /*
  * Checks if cpl <= required_cpl; if true, return true.  Otherwise queue
  * a #GP and return false.
@@ -476,7 +462,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	}
 
 	kvm_x86_ops->set_cr0(vcpu, cr0);
-	vcpu->arch.cr0 = cr0;
 
 	kvm_mmu_reset_context(vcpu);
 	return;
@@ -485,7 +470,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0);
 
 void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 {
-	kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f));
+	kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
@@ -517,7 +502,6 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	}
 	kvm_x86_ops->set_cr4(vcpu, cr4);
 	vcpu->arch.cr4 = cr4;
-	vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled;
 	kvm_mmu_reset_context(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr4);
@@ -592,6 +576,80 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_cr8);
 
+int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
+{
+	switch (dr) {
+	case 0 ... 3:
+		vcpu->arch.db[dr] = val;
+		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+			vcpu->arch.eff_db[dr] = val;
+		break;
+	case 4:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+			kvm_queue_exception(vcpu, UD_VECTOR);
+			return 1;
+		}
+		/* fall through */
+	case 6:
+		if (val & 0xffffffff00000000ULL) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+		vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+		break;
+	case 5:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+			kvm_queue_exception(vcpu, UD_VECTOR);
+			return 1;
+		}
+		/* fall through */
+	default: /* 7 */
+		if (val & 0xffffffff00000000ULL) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+		vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
+		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+			kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7);
+			vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK);
+		}
+		break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_set_dr);
+
+int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
+{
+	switch (dr) {
+	case 0 ... 3:
+		*val = vcpu->arch.db[dr];
+		break;
+	case 4:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+			kvm_queue_exception(vcpu, UD_VECTOR);
+			return 1;
+		}
+		/* fall through */
+	case 6:
+		*val = vcpu->arch.dr6;
+		break;
+	case 5:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+			kvm_queue_exception(vcpu, UD_VECTOR);
+			return 1;
+		}
+		/* fall through */
+	default: /* 7 */
+		*val = vcpu->arch.dr7;
+		break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_get_dr);
+
 static inline u32 bit(int bitno)
 {
 	return 1 << (bitno & 31);
@@ -606,9 +664,10 @@ static inline u32 bit(int bitno)
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	5
+#define KVM_SAVE_MSRS_BEGIN	7
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
 	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
 	HV_X64_MSR_APIC_ASSIST_PAGE,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
@@ -625,48 +684,42 @@ static u32 emulated_msrs[] = {
 	MSR_IA32_MISC_ENABLE,
 };
 
-static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
-	if (efer & efer_reserved_bits) {
-		kvm_inject_gp(vcpu, 0);
-		return;
-	}
+	if (efer & efer_reserved_bits)
+		return 1;
 
 	if (is_paging(vcpu)
-	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
-		kvm_inject_gp(vcpu, 0);
-		return;
-	}
+	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+		return 1;
 
 	if (efer & EFER_FFXSR) {
 		struct kvm_cpuid_entry2 *feat;
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
-		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
-			kvm_inject_gp(vcpu, 0);
-			return;
-		}
+		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT)))
+			return 1;
 	}
 
 	if (efer & EFER_SVME) {
 		struct kvm_cpuid_entry2 *feat;
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
-		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
-			kvm_inject_gp(vcpu, 0);
-			return;
-		}
+		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM)))
+			return 1;
 	}
 
-	kvm_x86_ops->set_efer(vcpu, efer);
-
 	efer &= ~EFER_LMA;
 	efer |= vcpu->arch.efer & EFER_LMA;
 
+	kvm_x86_ops->set_efer(vcpu, efer);
+
 	vcpu->arch.efer = efer;
 
 	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
 	kvm_mmu_reset_context(vcpu);
+
+	return 0;
 }
 
 void kvm_enable_efer_bits(u64 mask)
@@ -696,14 +749,22 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 
 static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 {
-	static int version;
+	int version;
+	int r;
 	struct pvclock_wall_clock wc;
 	struct timespec boot;
 
 	if (!wall_clock)
 		return;
 
-	version++;
+	r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version));
+	if (r)
+		return;
+
+	if (version & 1)
+		++version;  /* first time write, random junk */
+
+	++version;
 
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 
@@ -796,6 +857,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	vcpu->hv_clock.system_time = ts.tv_nsec +
 				     (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
 
+	vcpu->hv_clock.flags = 0;
+
 	/*
 	 * The interface expects us to write an even number signaling that the
 	 * update is finished. Since the guest won't see the intermediate
@@ -1087,10 +1150,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
 	case MSR_EFER:
-		set_efer(vcpu, data);
-		break;
+		return set_efer(vcpu, data);
 	case MSR_K7_HWCR:
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
+		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
 		if (data != 0) {
 			pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
 				data);
@@ -1133,10 +1196,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_IA32_MISC_ENABLE:
 		vcpu->arch.ia32_misc_enable_msr = data;
 		break;
+	case MSR_KVM_WALL_CLOCK_NEW:
 	case MSR_KVM_WALL_CLOCK:
 		vcpu->kvm->arch.wall_clock = data;
 		kvm_write_wall_clock(vcpu->kvm, data);
 		break;
+	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
 		if (vcpu->arch.time_page) {
 			kvm_release_page_dirty(vcpu->arch.time_page);
@@ -1408,9 +1473,11 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		data = vcpu->arch.efer;
 		break;
 	case MSR_KVM_WALL_CLOCK:
+	case MSR_KVM_WALL_CLOCK_NEW:
 		data = vcpu->kvm->arch.wall_clock;
 		break;
 	case MSR_KVM_SYSTEM_TIME:
+	case MSR_KVM_SYSTEM_TIME_NEW:
 		data = vcpu->arch.time;
 		break;
 	case MSR_IA32_P5_MC_ADDR:
@@ -1549,6 +1616,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_HYPERV_VAPIC:
 	case KVM_CAP_HYPERV_SPIN:
 	case KVM_CAP_PCI_SEGMENT:
+	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
 		r = 1;
 		break;
@@ -1769,6 +1837,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
 {
 	int r;
 
+	vcpu_load(vcpu);
 	r = -E2BIG;
 	if (cpuid->nent < vcpu->arch.cpuid_nent)
 		goto out;
@@ -1780,6 +1849,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
 
 out:
 	cpuid->nent = vcpu->arch.cpuid_nent;
+	vcpu_put(vcpu);
 	return r;
 }
 
@@ -1910,6 +1980,24 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		}
 		break;
 	}
+	case KVM_CPUID_SIGNATURE: {
+		char signature[12] = "KVMKVMKVM\0\0";
+		u32 *sigptr = (u32 *)signature;
+		entry->eax = 0;
+		entry->ebx = sigptr[0];
+		entry->ecx = sigptr[1];
+		entry->edx = sigptr[2];
+		break;
+	}
+	case KVM_CPUID_FEATURES:
+		entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) |
+			     (1 << KVM_FEATURE_NOP_IO_DELAY) |
+			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
+			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+		entry->ebx = 0;
+		entry->ecx = 0;
+		entry->edx = 0;
+		break;
 	case 0x80000000:
 		entry->eax = min(entry->eax, 0x8000001a);
 		break;
@@ -1918,6 +2006,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		entry->ecx &= kvm_supported_word6_x86_features;
 		break;
 	}
+
+	kvm_x86_ops->set_supported_cpuid(function, entry);
+
 	put_cpu();
 }
 
@@ -1953,6 +2044,23 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 	for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
 		do_cpuid_ent(&cpuid_entries[nent], func, 0,
 			     &nent, cpuid->nent);
+
+
+
+	r = -E2BIG;
+	if (nent >= cpuid->nent)
+		goto out_free;
+
+	do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent,
+		     cpuid->nent);
+
+	r = -E2BIG;
+	if (nent >= cpuid->nent)
+		goto out_free;
+
+	do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent,
+		     cpuid->nent);
+
 	r = -E2BIG;
 	if (nent >= cpuid->nent)
 		goto out_free;
@@ -2032,6 +2140,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
 	int r;
 	unsigned bank_num = mcg_cap & 0xff, bank;
 
+	vcpu_load(vcpu);
 	r = -EINVAL;
 	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
 		goto out;
@@ -2046,6 +2155,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
 	for (bank = 0; bank < bank_num; bank++)
 		vcpu->arch.mce_banks[bank*4] = ~(u64)0;
 out:
+	vcpu_put(vcpu);
 	return r;
 }
 
@@ -2105,14 +2215,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 {
 	vcpu_load(vcpu);
 
-	events->exception.injected = vcpu->arch.exception.pending;
+	events->exception.injected =
+		vcpu->arch.exception.pending &&
+		!kvm_exception_is_soft(vcpu->arch.exception.nr);
 	events->exception.nr = vcpu->arch.exception.nr;
 	events->exception.has_error_code = vcpu->arch.exception.has_error_code;
 	events->exception.error_code = vcpu->arch.exception.error_code;
 
-	events->interrupt.injected = vcpu->arch.interrupt.pending;
+	events->interrupt.injected =
+		vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft;
 	events->interrupt.nr = vcpu->arch.interrupt.nr;
-	events->interrupt.soft = vcpu->arch.interrupt.soft;
+	events->interrupt.soft = 0;
+	events->interrupt.shadow =
+		kvm_x86_ops->get_interrupt_shadow(vcpu,
+			KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);
 
 	events->nmi.injected = vcpu->arch.nmi_injected;
 	events->nmi.pending = vcpu->arch.nmi_pending;
@@ -2121,7 +2237,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	events->sipi_vector = vcpu->arch.sipi_vector;
 
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
-			 | KVM_VCPUEVENT_VALID_SIPI_VECTOR);
+			 | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+			 | KVM_VCPUEVENT_VALID_SHADOW);
 
 	vcpu_put(vcpu);
 }
@@ -2130,7 +2247,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
 {
 	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
-			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR))
+			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+			      | KVM_VCPUEVENT_VALID_SHADOW))
 		return -EINVAL;
 
 	vcpu_load(vcpu);
@@ -2145,6 +2263,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	vcpu->arch.interrupt.soft = events->interrupt.soft;
 	if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
 		kvm_pic_clear_isr_ack(vcpu->kvm);
+	if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
+		kvm_x86_ops->set_interrupt_shadow(vcpu,
+						  events->interrupt.shadow);
 
 	vcpu->arch.nmi_injected = events->nmi.injected;
 	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
@@ -2159,6 +2280,36 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
+					     struct kvm_debugregs *dbgregs)
+{
+	vcpu_load(vcpu);
+
+	memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
+	dbgregs->dr6 = vcpu->arch.dr6;
+	dbgregs->dr7 = vcpu->arch.dr7;
+	dbgregs->flags = 0;
+
+	vcpu_put(vcpu);
+}
+
+static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
+					    struct kvm_debugregs *dbgregs)
+{
+	if (dbgregs->flags)
+		return -EINVAL;
+
+	vcpu_load(vcpu);
+
+	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
+	vcpu->arch.dr6 = dbgregs->dr6;
+	vcpu->arch.dr7 = dbgregs->dr7;
+
+	vcpu_put(vcpu);
+
+	return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -2313,7 +2464,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&mce, argp, sizeof mce))
 			goto out;
+		vcpu_load(vcpu);
 		r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
+		vcpu_put(vcpu);
 		break;
 	}
 	case KVM_GET_VCPU_EVENTS: {
@@ -2337,6 +2490,29 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
 		break;
 	}
+	case KVM_GET_DEBUGREGS: {
+		struct kvm_debugregs dbgregs;
+
+		kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);
+
+		r = -EFAULT;
+		if (copy_to_user(argp, &dbgregs,
+				 sizeof(struct kvm_debugregs)))
+			break;
+		r = 0;
+		break;
+	}
+	case KVM_SET_DEBUGREGS: {
+		struct kvm_debugregs dbgregs;
+
+		r = -EFAULT;
+		if (copy_from_user(&dbgregs, argp,
+				   sizeof(struct kvm_debugregs)))
+			break;
+
+		r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs);
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -2390,7 +2566,7 @@ gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn)
 	struct kvm_mem_alias *alias;
 	struct kvm_mem_aliases *aliases;
 
-	aliases = rcu_dereference(kvm->arch.aliases);
+	aliases = kvm_aliases(kvm);
 
 	for (i = 0; i < aliases->naliases; ++i) {
 		alias = &aliases->aliases[i];
@@ -2409,7 +2585,7 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 	struct kvm_mem_alias *alias;
 	struct kvm_mem_aliases *aliases;
 
-	aliases = rcu_dereference(kvm->arch.aliases);
+	aliases = kvm_aliases(kvm);
 
 	for (i = 0; i < aliases->naliases; ++i) {
 		alias = &aliases->aliases[i];
@@ -2804,11 +2980,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
+		r = -ENXIO;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 					irq_event.irq, irq_event.level);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
+				r = -EFAULT;
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,
 							sizeof irq_event))
@@ -3024,6 +3202,18 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
 	return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
 }
 
+static void kvm_set_segment(struct kvm_vcpu *vcpu,
+			struct kvm_segment *var, int seg)
+{
+	kvm_x86_ops->set_segment(vcpu, var, seg);
+}
+
+void kvm_get_segment(struct kvm_vcpu *vcpu,
+		     struct kvm_segment *var, int seg)
+{
+	kvm_x86_ops->get_segment(vcpu, var, seg);
+}
+
 gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
@@ -3104,14 +3294,17 @@ static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes,
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
 }
 
-static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
-				struct kvm_vcpu *vcpu, u32 *error)
+static int kvm_write_guest_virt_system(gva_t addr, void *val,
+				       unsigned int bytes,
+				       struct kvm_vcpu *vcpu,
+				       u32 *error)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
 	while (bytes) {
-		gpa_t gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error);
+		gpa_t gpa =  vcpu->arch.mmu.gva_to_gpa(vcpu, addr,
+						       PFERR_WRITE_MASK, error);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
 		int ret;
@@ -3134,7 +3327,6 @@ static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
 	return r;
 }
 
-
 static int emulator_read_emulated(unsigned long addr,
 				  void *val,
 				  unsigned int bytes,
@@ -3237,9 +3429,9 @@ static int emulator_write_emulated_onepage(unsigned long addr,
 }
 
 int emulator_write_emulated(unsigned long addr,
-				   const void *val,
-				   unsigned int bytes,
-				   struct kvm_vcpu *vcpu)
+			    const void *val,
+			    unsigned int bytes,
+			    struct kvm_vcpu *vcpu)
 {
 	/* Crossing a page boundary? */
 	if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
@@ -3257,45 +3449,150 @@ int emulator_write_emulated(unsigned long addr,
 }
 EXPORT_SYMBOL_GPL(emulator_write_emulated);
 
+#define CMPXCHG_TYPE(t, ptr, old, new) \
+	(cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old))
+
+#ifdef CONFIG_X86_64
+#  define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new)
+#else
+#  define CMPXCHG64(ptr, old, new) \
+	(cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old))
+#endif
+
 static int emulator_cmpxchg_emulated(unsigned long addr,
 				     const void *old,
 				     const void *new,
 				     unsigned int bytes,
 				     struct kvm_vcpu *vcpu)
 {
-	printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
-#ifndef CONFIG_X86_64
-	/* guests cmpxchg8b have to be emulated atomically */
-	if (bytes == 8) {
-		gpa_t gpa;
-		struct page *page;
-		char *kaddr;
-		u64 val;
+	gpa_t gpa;
+	struct page *page;
+	char *kaddr;
+	bool exchanged;
 
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);
+	/* guests cmpxchg8b have to be emulated atomically */
+	if (bytes > 8 || (bytes & (bytes - 1)))
+		goto emul_write;
 
-		if (gpa == UNMAPPED_GVA ||
-		   (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
-			goto emul_write;
+	gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);
 
-		if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
-			goto emul_write;
+	if (gpa == UNMAPPED_GVA ||
+	    (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
+		goto emul_write;
 
-		val = *(u64 *)new;
+	if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
+		goto emul_write;
 
-		page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+	page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
 
-		kaddr = kmap_atomic(page, KM_USER0);
-		set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
-		kunmap_atomic(kaddr, KM_USER0);
-		kvm_release_page_dirty(page);
+	kaddr = kmap_atomic(page, KM_USER0);
+	kaddr += offset_in_page(gpa);
+	switch (bytes) {
+	case 1:
+		exchanged = CMPXCHG_TYPE(u8, kaddr, old, new);
+		break;
+	case 2:
+		exchanged = CMPXCHG_TYPE(u16, kaddr, old, new);
+		break;
+	case 4:
+		exchanged = CMPXCHG_TYPE(u32, kaddr, old, new);
+		break;
+	case 8:
+		exchanged = CMPXCHG64(kaddr, old, new);
+		break;
+	default:
+		BUG();
 	}
+	kunmap_atomic(kaddr, KM_USER0);
+	kvm_release_page_dirty(page);
+
+	if (!exchanged)
+		return X86EMUL_CMPXCHG_FAILED;
+
+	kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1);
+
+	return X86EMUL_CONTINUE;
+
 emul_write:
-#endif
+	printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
 
 	return emulator_write_emulated(addr, new, bytes, vcpu);
 }
 
+static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
+{
+	/* TODO: String I/O for in kernel device */
+	int r;
+
+	if (vcpu->arch.pio.in)
+		r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
+				    vcpu->arch.pio.size, pd);
+	else
+		r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
+				     vcpu->arch.pio.port, vcpu->arch.pio.size,
+				     pd);
+	return r;
+}
+
+
+static int emulator_pio_in_emulated(int size, unsigned short port, void *val,
+			     unsigned int count, struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.pio.count)
+		goto data_avail;
+
+	trace_kvm_pio(1, port, size, 1);
+
+	vcpu->arch.pio.port = port;
+	vcpu->arch.pio.in = 1;
+	vcpu->arch.pio.count  = count;
+	vcpu->arch.pio.size = size;
+
+	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+	data_avail:
+		memcpy(val, vcpu->arch.pio_data, size * count);
+		vcpu->arch.pio.count = 0;
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_IO;
+	vcpu->run->io.direction = KVM_EXIT_IO_IN;
+	vcpu->run->io.size = size;
+	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+	vcpu->run->io.count = count;
+	vcpu->run->io.port = port;
+
+	return 0;
+}
+
+static int emulator_pio_out_emulated(int size, unsigned short port,
+			      const void *val, unsigned int count,
+			      struct kvm_vcpu *vcpu)
+{
+	trace_kvm_pio(0, port, size, 1);
+
+	vcpu->arch.pio.port = port;
+	vcpu->arch.pio.in = 0;
+	vcpu->arch.pio.count = count;
+	vcpu->arch.pio.size = size;
+
+	memcpy(vcpu->arch.pio_data, val, size * count);
+
+	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+		vcpu->arch.pio.count = 0;
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_IO;
+	vcpu->run->io.direction = KVM_EXIT_IO_OUT;
+	vcpu->run->io.size = size;
+	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+	vcpu->run->io.count = count;
+	vcpu->run->io.port = port;
+
+	return 0;
+}
+
 static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
 	return kvm_x86_ops->get_segment_base(vcpu, seg);
@@ -3316,14 +3613,14 @@ int emulate_clts(struct kvm_vcpu *vcpu)
 
 int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
 {
-	return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest);
+	return kvm_get_dr(ctxt->vcpu, dr, dest);
 }
 
 int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
 {
 	unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
 
-	return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask);
+	return kvm_set_dr(ctxt->vcpu, dr, value & mask);
 }
 
 void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
@@ -3344,50 +3641,205 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 }
 EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
 
-static struct x86_emulate_ops emulate_ops = {
-	.read_std            = kvm_read_guest_virt_system,
-	.fetch               = kvm_fetch_guest_virt,
-	.read_emulated       = emulator_read_emulated,
-	.write_emulated      = emulator_write_emulated,
-	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
-};
-
-static void cache_all_regs(struct kvm_vcpu *vcpu)
+static u64 mk_cr_64(u64 curr_cr, u32 new_val)
 {
-	kvm_register_read(vcpu, VCPU_REGS_RAX);
-	kvm_register_read(vcpu, VCPU_REGS_RSP);
-	kvm_register_read(vcpu, VCPU_REGS_RIP);
-	vcpu->arch.regs_dirty = ~0;
+	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
 }
 
-int emulate_instruction(struct kvm_vcpu *vcpu,
-			unsigned long cr2,
-			u16 error_code,
-			int emulation_type)
+static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu)
 {
-	int r, shadow_mask;
-	struct decode_cache *c;
-	struct kvm_run *run = vcpu->run;
-
-	kvm_clear_exception_queue(vcpu);
-	vcpu->arch.mmio_fault_cr2 = cr2;
-	/*
-	 * TODO: fix emulate.c to use guest_read/write_register
-	 * instead of direct ->regs accesses, can save hundred cycles
-	 * on Intel for instructions that don't read/change RSP, for
-	 * for example.
-	 */
-	cache_all_regs(vcpu);
-
-	vcpu->mmio_is_write = 0;
-	vcpu->arch.pio.string = 0;
+	unsigned long value;
+
+	switch (cr) {
+	case 0:
+		value = kvm_read_cr0(vcpu);
+		break;
+	case 2:
+		value = vcpu->arch.cr2;
+		break;
+	case 3:
+		value = vcpu->arch.cr3;
+		break;
+	case 4:
+		value = kvm_read_cr4(vcpu);
+		break;
+	case 8:
+		value = kvm_get_cr8(vcpu);
+		break;
+	default:
+		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
+		return 0;
+	}
+
+	return value;
+}
+
+static void emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu)
+{
+	switch (cr) {
+	case 0:
+		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
+		break;
+	case 2:
+		vcpu->arch.cr2 = val;
+		break;
+	case 3:
+		kvm_set_cr3(vcpu, val);
+		break;
+	case 4:
+		kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
+		break;
+	case 8:
+		kvm_set_cr8(vcpu, val & 0xfUL);
+		break;
+	default:
+		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
+	}
+}
+
+static int emulator_get_cpl(struct kvm_vcpu *vcpu)
+{
+	return kvm_x86_ops->get_cpl(vcpu);
+}
+
+static void emulator_get_gdt(struct desc_ptr *dt, struct kvm_vcpu *vcpu)
+{
+	kvm_x86_ops->get_gdt(vcpu, dt);
+}
+
+static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg,
+					   struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment var;
+
+	kvm_get_segment(vcpu, &var, seg);
+
+	if (var.unusable)
+		return false;
+
+	if (var.g)
+		var.limit >>= 12;
+	set_desc_limit(desc, var.limit);
+	set_desc_base(desc, (unsigned long)var.base);
+	desc->type = var.type;
+	desc->s = var.s;
+	desc->dpl = var.dpl;
+	desc->p = var.present;
+	desc->avl = var.avl;
+	desc->l = var.l;
+	desc->d = var.db;
+	desc->g = var.g;
+
+	return true;
+}
+
+static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg,
+					   struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment var;
+
+	/* needed to preserve selector */
+	kvm_get_segment(vcpu, &var, seg);
+
+	var.base = get_desc_base(desc);
+	var.limit = get_desc_limit(desc);
+	if (desc->g)
+		var.limit = (var.limit << 12) | 0xfff;
+	var.type = desc->type;
+	var.present = desc->p;
+	var.dpl = desc->dpl;
+	var.db = desc->d;
+	var.s = desc->s;
+	var.l = desc->l;
+	var.g = desc->g;
+	var.avl = desc->avl;
+	var.present = desc->p;
+	var.unusable = !var.present;
+	var.padding = 0;
+
+	kvm_set_segment(vcpu, &var, seg);
+	return;
+}
+
+static u16 emulator_get_segment_selector(int seg, struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment kvm_seg;
+
+	kvm_get_segment(vcpu, &kvm_seg, seg);
+	return kvm_seg.selector;
+}
+
+static void emulator_set_segment_selector(u16 sel, int seg,
+					  struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment kvm_seg;
+
+	kvm_get_segment(vcpu, &kvm_seg, seg);
+	kvm_seg.selector = sel;
+	kvm_set_segment(vcpu, &kvm_seg, seg);
+}
+
+static void emulator_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+	kvm_x86_ops->set_rflags(vcpu, rflags);
+}
+
+static struct x86_emulate_ops emulate_ops = {
+	.read_std            = kvm_read_guest_virt_system,
+	.write_std           = kvm_write_guest_virt_system,
+	.fetch               = kvm_fetch_guest_virt,
+	.read_emulated       = emulator_read_emulated,
+	.write_emulated      = emulator_write_emulated,
+	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
+	.pio_in_emulated     = emulator_pio_in_emulated,
+	.pio_out_emulated    = emulator_pio_out_emulated,
+	.get_cached_descriptor = emulator_get_cached_descriptor,
+	.set_cached_descriptor = emulator_set_cached_descriptor,
+	.get_segment_selector = emulator_get_segment_selector,
+	.set_segment_selector = emulator_set_segment_selector,
+	.get_gdt             = emulator_get_gdt,
+	.get_cr              = emulator_get_cr,
+	.set_cr              = emulator_set_cr,
+	.cpl                 = emulator_get_cpl,
+	.set_rflags          = emulator_set_rflags,
+};
+
+static void cache_all_regs(struct kvm_vcpu *vcpu)
+{
+	kvm_register_read(vcpu, VCPU_REGS_RAX);
+	kvm_register_read(vcpu, VCPU_REGS_RSP);
+	kvm_register_read(vcpu, VCPU_REGS_RIP);
+	vcpu->arch.regs_dirty = ~0;
+}
+
+int emulate_instruction(struct kvm_vcpu *vcpu,
+			unsigned long cr2,
+			u16 error_code,
+			int emulation_type)
+{
+	int r, shadow_mask;
+	struct decode_cache *c;
+	struct kvm_run *run = vcpu->run;
+
+	kvm_clear_exception_queue(vcpu);
+	vcpu->arch.mmio_fault_cr2 = cr2;
+	/*
+	 * TODO: fix emulate.c to use guest_read/write_register
+	 * instead of direct ->regs accesses, can save hundred cycles
+	 * on Intel for instructions that don't read/change RSP, for
+	 * for example.
+	 */
+	cache_all_regs(vcpu);
+
+	vcpu->mmio_is_write = 0;
 
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
 		int cs_db, cs_l;
 		kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
 		vcpu->arch.emulate_ctxt.vcpu = vcpu;
-		vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu);
+		vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+		vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu);
 		vcpu->arch.emulate_ctxt.mode =
 			(!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
 			(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
@@ -3396,6 +3848,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 			? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
 
 		r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
+		trace_kvm_emulate_insn_start(vcpu);
 
 		/* Only allow emulation of specific instructions on #UD
 		 * (namely VMMCALL, sysenter, sysexit, syscall)*/
@@ -3428,6 +3881,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		++vcpu->stat.insn_emulation;
 		if (r)  {
 			++vcpu->stat.insn_emulation_fail;
+			trace_kvm_emulate_insn_failed(vcpu);
 			if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
 				return EMULATE_DONE;
 			return EMULATE_FAIL;
@@ -3439,16 +3893,20 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		return EMULATE_DONE;
 	}
 
+restart:
 	r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
 	shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;
 
 	if (r == 0)
 		kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask);
 
-	if (vcpu->arch.pio.string)
+	if (vcpu->arch.pio.count) {
+		if (!vcpu->arch.pio.in)
+			vcpu->arch.pio.count = 0;
 		return EMULATE_DO_MMIO;
+	}
 
-	if ((r || vcpu->mmio_is_write) && run) {
+	if (r || vcpu->mmio_is_write) {
 		run->exit_reason = KVM_EXIT_MMIO;
 		run->mmio.phys_addr = vcpu->mmio_phys_addr;
 		memcpy(run->mmio.data, vcpu->mmio_data, 8);
@@ -3458,222 +3916,41 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 
 	if (r) {
 		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
-			return EMULATE_DONE;
+			goto done;
 		if (!vcpu->mmio_needed) {
+			++vcpu->stat.insn_emulation_fail;
+			trace_kvm_emulate_insn_failed(vcpu);
 			kvm_report_emulation_failure(vcpu, "mmio");
 			return EMULATE_FAIL;
 		}
 		return EMULATE_DO_MMIO;
 	}
 
-	kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
-
 	if (vcpu->mmio_is_write) {
 		vcpu->mmio_needed = 0;
 		return EMULATE_DO_MMIO;
 	}
 
-	return EMULATE_DONE;
-}
-EXPORT_SYMBOL_GPL(emulate_instruction);
-
-static int pio_copy_data(struct kvm_vcpu *vcpu)
-{
-	void *p = vcpu->arch.pio_data;
-	gva_t q = vcpu->arch.pio.guest_gva;
-	unsigned bytes;
-	int ret;
-	u32 error_code;
-
-	bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
-	if (vcpu->arch.pio.in)
-		ret = kvm_write_guest_virt(q, p, bytes, vcpu, &error_code);
-	else
-		ret = kvm_read_guest_virt(q, p, bytes, vcpu, &error_code);
-
-	if (ret == X86EMUL_PROPAGATE_FAULT)
-		kvm_inject_page_fault(vcpu, q, error_code);
-
-	return ret;
-}
-
-int complete_pio(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pio_request *io = &vcpu->arch.pio;
-	long delta;
-	int r;
-	unsigned long val;
-
-	if (!io->string) {
-		if (io->in) {
-			val = kvm_register_read(vcpu, VCPU_REGS_RAX);
-			memcpy(&val, vcpu->arch.pio_data, io->size);
-			kvm_register_write(vcpu, VCPU_REGS_RAX, val);
-		}
-	} else {
-		if (io->in) {
-			r = pio_copy_data(vcpu);
-			if (r)
-				goto out;
-		}
-
-		delta = 1;
-		if (io->rep) {
-			delta *= io->cur_count;
-			/*
-			 * The size of the register should really depend on
-			 * current address size.
-			 */
-			val = kvm_register_read(vcpu, VCPU_REGS_RCX);
-			val -= delta;
-			kvm_register_write(vcpu, VCPU_REGS_RCX, val);
-		}
-		if (io->down)
-			delta = -delta;
-		delta *= io->size;
-		if (io->in) {
-			val = kvm_register_read(vcpu, VCPU_REGS_RDI);
-			val += delta;
-			kvm_register_write(vcpu, VCPU_REGS_RDI, val);
-		} else {
-			val = kvm_register_read(vcpu, VCPU_REGS_RSI);
-			val += delta;
-			kvm_register_write(vcpu, VCPU_REGS_RSI, val);
-		}
-	}
-out:
-	io->count -= io->cur_count;
-	io->cur_count = 0;
-
-	return 0;
-}
-
-static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
-{
-	/* TODO: String I/O for in kernel device */
-	int r;
-
-	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
-				    vcpu->arch.pio.size, pd);
-	else
-		r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
-				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
-	return r;
-}
-
-static int pio_string_write(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pio_request *io = &vcpu->arch.pio;
-	void *pd = vcpu->arch.pio_data;
-	int i, r = 0;
-
-	for (i = 0; i < io->cur_count; i++) {
-		if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
-				     io->port, io->size, pd)) {
-			r = -EOPNOTSUPP;
-			break;
-		}
-		pd += io->size;
-	}
-	return r;
-}
-
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
-{
-	unsigned long val;
+done:
+	if (vcpu->arch.exception.pending)
+		vcpu->arch.emulate_ctxt.restart = false;
 
-	trace_kvm_pio(!in, port, size, 1);
+	if (vcpu->arch.emulate_ctxt.restart)
+		goto restart;
 
-	vcpu->run->exit_reason = KVM_EXIT_IO;
-	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
-	vcpu->run->io.size = vcpu->arch.pio.size = size;
-	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
-	vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1;
-	vcpu->run->io.port = vcpu->arch.pio.port = port;
-	vcpu->arch.pio.in = in;
-	vcpu->arch.pio.string = 0;
-	vcpu->arch.pio.down = 0;
-	vcpu->arch.pio.rep = 0;
-
-	if (!vcpu->arch.pio.in) {
-		val = kvm_register_read(vcpu, VCPU_REGS_RAX);
-		memcpy(vcpu->arch.pio_data, &val, 4);
-	}
-
-	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
-		complete_pio(vcpu);
-		return 1;
-	}
-	return 0;
+	return EMULATE_DONE;
 }
-EXPORT_SYMBOL_GPL(kvm_emulate_pio);
+EXPORT_SYMBOL_GPL(emulate_instruction);
 
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
-		  int size, unsigned long count, int down,
-		  gva_t address, int rep, unsigned port)
+int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
 {
-	unsigned now, in_page;
-	int ret = 0;
-
-	trace_kvm_pio(!in, port, size, count);
-
-	vcpu->run->exit_reason = KVM_EXIT_IO;
-	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
-	vcpu->run->io.size = vcpu->arch.pio.size = size;
-	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
-	vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
-	vcpu->run->io.port = vcpu->arch.pio.port = port;
-	vcpu->arch.pio.in = in;
-	vcpu->arch.pio.string = 1;
-	vcpu->arch.pio.down = down;
-	vcpu->arch.pio.rep = rep;
-
-	if (!count) {
-		kvm_x86_ops->skip_emulated_instruction(vcpu);
-		return 1;
-	}
-
-	if (!down)
-		in_page = PAGE_SIZE - offset_in_page(address);
-	else
-		in_page = offset_in_page(address) + size;
-	now = min(count, (unsigned long)in_page / size);
-	if (!now)
-		now = 1;
-	if (down) {
-		/*
-		 * String I/O in reverse.  Yuck.  Kill the guest, fix later.
-		 */
-		pr_unimpl(vcpu, "guest string pio down\n");
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-	vcpu->run->io.count = now;
-	vcpu->arch.pio.cur_count = now;
-
-	if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count)
-		kvm_x86_ops->skip_emulated_instruction(vcpu);
-
-	vcpu->arch.pio.guest_gva = address;
-
-	if (!vcpu->arch.pio.in) {
-		/* string PIO write */
-		ret = pio_copy_data(vcpu);
-		if (ret == X86EMUL_PROPAGATE_FAULT)
-			return 1;
-		if (ret == 0 && !pio_string_write(vcpu)) {
-			complete_pio(vcpu);
-			if (vcpu->arch.pio.count == 0)
-				ret = 1;
-		}
-	}
-	/* no string PIO read support yet */
-
+	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+	int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu);
+	/* do not return to emulator after return from userspace */
+	vcpu->arch.pio.count = 0;
 	return ret;
 }
-EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
+EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
 static void bounce_off(void *info)
 {
@@ -3996,85 +4273,20 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
 	return emulator_write_emulated(rip, instruction, 3, vcpu);
 }
 
-static u64 mk_cr_64(u64 curr_cr, u32 new_val)
-{
-	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
-}
-
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
 {
-	struct descriptor_table dt = { limit, base };
+	struct desc_ptr dt = { limit, base };
 
 	kvm_x86_ops->set_gdt(vcpu, &dt);
 }
 
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
 {
-	struct descriptor_table dt = { limit, base };
+	struct desc_ptr dt = { limit, base };
 
 	kvm_x86_ops->set_idt(vcpu, &dt);
 }
 
-void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
-		   unsigned long *rflags)
-{
-	kvm_lmsw(vcpu, msw);
-	*rflags = kvm_get_rflags(vcpu);
-}
-
-unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
-{
-	unsigned long value;
-
-	switch (cr) {
-	case 0:
-		value = kvm_read_cr0(vcpu);
-		break;
-	case 2:
-		value = vcpu->arch.cr2;
-		break;
-	case 3:
-		value = vcpu->arch.cr3;
-		break;
-	case 4:
-		value = kvm_read_cr4(vcpu);
-		break;
-	case 8:
-		value = kvm_get_cr8(vcpu);
-		break;
-	default:
-		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
-		return 0;
-	}
-
-	return value;
-}
-
-void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
-		     unsigned long *rflags)
-{
-	switch (cr) {
-	case 0:
-		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
-		*rflags = kvm_get_rflags(vcpu);
-		break;
-	case 2:
-		vcpu->arch.cr2 = val;
-		break;
-	case 3:
-		kvm_set_cr3(vcpu, val);
-		break;
-	case 4:
-		kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
-		break;
-	case 8:
-		kvm_set_cr8(vcpu, val & 0xfUL);
-		break;
-	default:
-		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
-	}
-}
-
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
@@ -4138,9 +4350,13 @@ int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
+	if (!best || best->eax < 0x80000008)
+		goto not_found;
 	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
 	if (best)
 		return best->eax & 0xff;
+not_found:
 	return 36;
 }
 
@@ -4254,9 +4470,13 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 {
 	/* try to reinject previous events if any */
 	if (vcpu->arch.exception.pending) {
+		trace_kvm_inj_exception(vcpu->arch.exception.nr,
+					vcpu->arch.exception.has_error_code,
+					vcpu->arch.exception.error_code);
 		kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
 					  vcpu->arch.exception.has_error_code,
-					  vcpu->arch.exception.error_code);
+					  vcpu->arch.exception.error_code,
+					  vcpu->arch.exception.reinject);
 		return;
 	}
 
@@ -4486,7 +4706,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
-	post_kvm_run_save(vcpu);
 
 	vapic_exit(vcpu);
 
@@ -4514,26 +4733,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		kvm_set_cr8(vcpu, kvm_run->cr8);
 
-	if (vcpu->arch.pio.cur_count) {
-		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = complete_pio(vcpu);
-		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-		if (r)
-			goto out;
-	}
-	if (vcpu->mmio_needed) {
-		memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
-		vcpu->mmio_read_completed = 1;
-		vcpu->mmio_needed = 0;
-
+	if (vcpu->arch.pio.count || vcpu->mmio_needed ||
+	    vcpu->arch.emulate_ctxt.restart) {
+		if (vcpu->mmio_needed) {
+			memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+			vcpu->mmio_read_completed = 1;
+			vcpu->mmio_needed = 0;
+		}
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0,
-					EMULTYPE_NO_DECODE);
+		r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
 		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (r == EMULATE_DO_MMIO) {
-			/*
-			 * Read-modify-write.  Back to userspace.
-			 */
 			r = 0;
 			goto out;
 		}
@@ -4545,6 +4755,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	r = __vcpu_run(vcpu);
 
 out:
+	post_kvm_run_save(vcpu);
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
@@ -4616,12 +4827,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return 0;
 }
 
-void kvm_get_segment(struct kvm_vcpu *vcpu,
-		     struct kvm_segment *var, int seg)
-{
-	kvm_x86_ops->get_segment(vcpu, var, seg);
-}
-
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
 {
 	struct kvm_segment cs;
@@ -4635,7 +4840,7 @@ EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits);
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	struct descriptor_table dt;
+	struct desc_ptr dt;
 
 	vcpu_load(vcpu);
 
@@ -4650,11 +4855,11 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);
 
 	kvm_x86_ops->get_idt(vcpu, &dt);
-	sregs->idt.limit = dt.limit;
-	sregs->idt.base = dt.base;
+	sregs->idt.limit = dt.size;
+	sregs->idt.base = dt.address;
 	kvm_x86_ops->get_gdt(vcpu, &dt);
-	sregs->gdt.limit = dt.limit;
-	sregs->gdt.base = dt.base;
+	sregs->gdt.limit = dt.size;
+	sregs->gdt.base = dt.address;
 
 	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
@@ -4693,563 +4898,33 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static void kvm_set_segment(struct kvm_vcpu *vcpu,
-			struct kvm_segment *var, int seg)
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
+		    bool has_error_code, u32 error_code)
 {
-	kvm_x86_ops->set_segment(vcpu, var, seg);
-}
-
-static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
-				   struct kvm_segment *kvm_desct)
-{
-	kvm_desct->base = get_desc_base(seg_desc);
-	kvm_desct->limit = get_desc_limit(seg_desc);
-	if (seg_desc->g) {
-		kvm_desct->limit <<= 12;
-		kvm_desct->limit |= 0xfff;
-	}
-	kvm_desct->selector = selector;
-	kvm_desct->type = seg_desc->type;
-	kvm_desct->present = seg_desc->p;
-	kvm_desct->dpl = seg_desc->dpl;
-	kvm_desct->db = seg_desc->d;
-	kvm_desct->s = seg_desc->s;
-	kvm_desct->l = seg_desc->l;
-	kvm_desct->g = seg_desc->g;
-	kvm_desct->avl = seg_desc->avl;
-	if (!selector)
-		kvm_desct->unusable = 1;
-	else
-		kvm_desct->unusable = 0;
-	kvm_desct->padding = 0;
-}
-
-static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu,
-					  u16 selector,
-					  struct descriptor_table *dtable)
-{
-	if (selector & 1 << 2) {
-		struct kvm_segment kvm_seg;
-
-		kvm_get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR);
-
-		if (kvm_seg.unusable)
-			dtable->limit = 0;
-		else
-			dtable->limit = kvm_seg.limit;
-		dtable->base = kvm_seg.base;
-	}
-	else
-		kvm_x86_ops->get_gdt(vcpu, dtable);
-}
-
-/* allowed just for 8 bytes segments */
-static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-					 struct desc_struct *seg_desc)
-{
-	struct descriptor_table dtable;
-	u16 index = selector >> 3;
-	int ret;
-	u32 err;
-	gva_t addr;
-
-	get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
-	if (dtable.limit < index * 8 + 7) {
-		kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
-		return X86EMUL_PROPAGATE_FAULT;
-	}
-	addr = dtable.base + index * 8;
-	ret = kvm_read_guest_virt_system(addr, seg_desc, sizeof(*seg_desc),
-					 vcpu,  &err);
-	if (ret == X86EMUL_PROPAGATE_FAULT)
-		kvm_inject_page_fault(vcpu, addr, err);
-
-       return ret;
-}
-
-/* allowed just for 8 bytes segments */
-static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-					 struct desc_struct *seg_desc)
-{
-	struct descriptor_table dtable;
-	u16 index = selector >> 3;
-
-	get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
-	if (dtable.limit < index * 8 + 7)
-		return 1;
-	return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu, NULL);
-}
-
-static gpa_t get_tss_base_addr_write(struct kvm_vcpu *vcpu,
-			       struct desc_struct *seg_desc)
-{
-	u32 base_addr = get_desc_base(seg_desc);
-
-	return kvm_mmu_gva_to_gpa_write(vcpu, base_addr, NULL);
-}
-
-static gpa_t get_tss_base_addr_read(struct kvm_vcpu *vcpu,
-			     struct desc_struct *seg_desc)
-{
-	u32 base_addr = get_desc_base(seg_desc);
-
-	return kvm_mmu_gva_to_gpa_read(vcpu, base_addr, NULL);
-}
-
-static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
-{
-	struct kvm_segment kvm_seg;
-
-	kvm_get_segment(vcpu, &kvm_seg, seg);
-	return kvm_seg.selector;
-}
-
-static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg)
-{
-	struct kvm_segment segvar = {
-		.base = selector << 4,
-		.limit = 0xffff,
-		.selector = selector,
-		.type = 3,
-		.present = 1,
-		.dpl = 3,
-		.db = 0,
-		.s = 1,
-		.l = 0,
-		.g = 0,
-		.avl = 0,
-		.unusable = 0,
-	};
-	kvm_x86_ops->set_segment(vcpu, &segvar, seg);
-	return X86EMUL_CONTINUE;
-}
-
-static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
-{
-	return (seg != VCPU_SREG_LDTR) &&
-		(seg != VCPU_SREG_TR) &&
-		(kvm_get_rflags(vcpu) & X86_EFLAGS_VM);
-}
-
-int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg)
-{
-	struct kvm_segment kvm_seg;
-	struct desc_struct seg_desc;
-	u8 dpl, rpl, cpl;
-	unsigned err_vec = GP_VECTOR;
-	u32 err_code = 0;
-	bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
-	int ret;
+	int cs_db, cs_l, ret;
+	cache_all_regs(vcpu);
 
-	if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu))
-		return kvm_load_realmode_segment(vcpu, selector, seg);
+	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
-	/* NULL selector is not valid for TR, CS and SS */
-	if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR)
-	    && null_selector)
-		goto exception;
+	vcpu->arch.emulate_ctxt.vcpu = vcpu;
+	vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+	vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu);
+	vcpu->arch.emulate_ctxt.mode =
+		(!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
+		(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
+		? X86EMUL_MODE_VM86 : cs_l
+		? X86EMUL_MODE_PROT64 :	cs_db
+		? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
 
-	/* TR should be in GDT only */
-	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
-		goto exception;
+	ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops,
+				   tss_selector, reason, has_error_code,
+				   error_code);
 
-	ret = load_guest_segment_descriptor(vcpu, selector, &seg_desc);
 	if (ret)
-		return ret;
-
-	seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg);
-
-	if (null_selector) { /* for NULL selector skip all following checks */
-		kvm_seg.unusable = 1;
-		goto load;
-	}
-
-	err_code = selector & 0xfffc;
-	err_vec = GP_VECTOR;
-
-	/* can't load system descriptor into segment selecor */
-	if (seg <= VCPU_SREG_GS && !kvm_seg.s)
-		goto exception;
-
-	if (!kvm_seg.present) {
-		err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
-		goto exception;
-	}
-
-	rpl = selector & 3;
-	dpl = kvm_seg.dpl;
-	cpl = kvm_x86_ops->get_cpl(vcpu);
-
-	switch (seg) {
-	case VCPU_SREG_SS:
-		/*
-		 * segment is not a writable data segment or segment
-		 * selector's RPL != CPL or segment selector's RPL != CPL
-		 */
-		if (rpl != cpl || (kvm_seg.type & 0xa) != 0x2 || dpl != cpl)
-			goto exception;
-		break;
-	case VCPU_SREG_CS:
-		if (!(kvm_seg.type & 8))
-			goto exception;
-
-		if (kvm_seg.type & 4) {
-			/* conforming */
-			if (dpl > cpl)
-				goto exception;
-		} else {
-			/* nonconforming */
-			if (rpl > cpl || dpl != cpl)
-				goto exception;
-		}
-		/* CS(RPL) <- CPL */
-		selector = (selector & 0xfffc) | cpl;
-            break;
-	case VCPU_SREG_TR:
-		if (kvm_seg.s || (kvm_seg.type != 1 && kvm_seg.type != 9))
-			goto exception;
-		break;
-	case VCPU_SREG_LDTR:
-		if (kvm_seg.s || kvm_seg.type != 2)
-			goto exception;
-		break;
-	default: /*  DS, ES, FS, or GS */
-		/*
-		 * segment is not a data or readable code segment or
-		 * ((segment is a data or nonconforming code segment)
-		 * and (both RPL and CPL > DPL))
-		 */
-		if ((kvm_seg.type & 0xa) == 0x8 ||
-		    (((kvm_seg.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl)))
-			goto exception;
-		break;
-	}
-
-	if (!kvm_seg.unusable && kvm_seg.s) {
-		/* mark segment as accessed */
-		kvm_seg.type |= 1;
-		seg_desc.type |= 1;
-		save_guest_segment_descriptor(vcpu, selector, &seg_desc);
-	}
-load:
-	kvm_set_segment(vcpu, &kvm_seg, seg);
-	return X86EMUL_CONTINUE;
-exception:
-	kvm_queue_exception_e(vcpu, err_vec, err_code);
-	return X86EMUL_PROPAGATE_FAULT;
-}
-
-static void save_state_to_tss32(struct kvm_vcpu *vcpu,
-				struct tss_segment_32 *tss)
-{
-	tss->cr3 = vcpu->arch.cr3;
-	tss->eip = kvm_rip_read(vcpu);
-	tss->eflags = kvm_get_rflags(vcpu);
-	tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	tss->ebx = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	tss->esp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-	tss->ebp = kvm_register_read(vcpu, VCPU_REGS_RBP);
-	tss->esi = kvm_register_read(vcpu, VCPU_REGS_RSI);
-	tss->edi = kvm_register_read(vcpu, VCPU_REGS_RDI);
-	tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
-	tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
-	tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
-	tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
-	tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS);
-	tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS);
-	tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-}
-
-static void kvm_load_segment_selector(struct kvm_vcpu *vcpu, u16 sel, int seg)
-{
-	struct kvm_segment kvm_seg;
-	kvm_get_segment(vcpu, &kvm_seg, seg);
-	kvm_seg.selector = sel;
-	kvm_set_segment(vcpu, &kvm_seg, seg);
-}
-
-static int load_state_from_tss32(struct kvm_vcpu *vcpu,
-				  struct tss_segment_32 *tss)
-{
-	kvm_set_cr3(vcpu, tss->cr3);
-
-	kvm_rip_write(vcpu, tss->eip);
-	kvm_set_rflags(vcpu, tss->eflags | 2);
-
-	kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, tss->edx);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, tss->ebx);
-	kvm_register_write(vcpu, VCPU_REGS_RSP, tss->esp);
-	kvm_register_write(vcpu, VCPU_REGS_RBP, tss->ebp);
-	kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi);
-	kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi);
-
-	/*
-	 * SDM says that segment selectors are loaded before segment
-	 * descriptors
-	 */
-	kvm_load_segment_selector(vcpu, tss->ldt_selector, VCPU_SREG_LDTR);
-	kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
-	kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
-	kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
-	kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
-	kvm_load_segment_selector(vcpu, tss->fs, VCPU_SREG_FS);
-	kvm_load_segment_selector(vcpu, tss->gs, VCPU_SREG_GS);
-
-	/*
-	 * Now load segment descriptors. If fault happenes at this stage
-	 * it is handled in a context of new task
-	 */
-	if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, VCPU_SREG_LDTR))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->fs, VCPU_SREG_FS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->gs, VCPU_SREG_GS))
-		return 1;
-	return 0;
-}
-
-static void save_state_to_tss16(struct kvm_vcpu *vcpu,
-				struct tss_segment_16 *tss)
-{
-	tss->ip = kvm_rip_read(vcpu);
-	tss->flag = kvm_get_rflags(vcpu);
-	tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	tss->bx = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	tss->sp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-	tss->bp = kvm_register_read(vcpu, VCPU_REGS_RBP);
-	tss->si = kvm_register_read(vcpu, VCPU_REGS_RSI);
-	tss->di = kvm_register_read(vcpu, VCPU_REGS_RDI);
-
-	tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
-	tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
-	tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
-	tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
-	tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-}
-
-static int load_state_from_tss16(struct kvm_vcpu *vcpu,
-				 struct tss_segment_16 *tss)
-{
-	kvm_rip_write(vcpu, tss->ip);
-	kvm_set_rflags(vcpu, tss->flag | 2);
-	kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, tss->bx);
-	kvm_register_write(vcpu, VCPU_REGS_RSP, tss->sp);
-	kvm_register_write(vcpu, VCPU_REGS_RBP, tss->bp);
-	kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si);
-	kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di);
-
-	/*
-	 * SDM says that segment selectors are loaded before segment
-	 * descriptors
-	 */
-	kvm_load_segment_selector(vcpu, tss->ldt, VCPU_SREG_LDTR);
-	kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
-	kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
-	kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
-	kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
-
-	/*
-	 * Now load segment descriptors. If fault happenes at this stage
-	 * it is handled in a context of new task
-	 */
-	if (kvm_load_segment_descriptor(vcpu, tss->ldt, VCPU_SREG_LDTR))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
-		return 1;
-	return 0;
-}
-
-static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
-			      u16 old_tss_sel, u32 old_tss_base,
-			      struct desc_struct *nseg_desc)
-{
-	struct tss_segment_16 tss_segment_16;
-	int ret = 0;
-
-	if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
-			   sizeof tss_segment_16))
-		goto out;
-
-	save_state_to_tss16(vcpu, &tss_segment_16);
-
-	if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
-			    sizeof tss_segment_16))
-		goto out;
-
-	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
-			   &tss_segment_16, sizeof tss_segment_16))
-		goto out;
-
-	if (old_tss_sel != 0xffff) {
-		tss_segment_16.prev_task_link = old_tss_sel;
-
-		if (kvm_write_guest(vcpu->kvm,
-				    get_tss_base_addr_write(vcpu, nseg_desc),
-				    &tss_segment_16.prev_task_link,
-				    sizeof tss_segment_16.prev_task_link))
-			goto out;
-	}
-
-	if (load_state_from_tss16(vcpu, &tss_segment_16))
-		goto out;
+		return EMULATE_FAIL;
 
-	ret = 1;
-out:
-	return ret;
-}
-
-static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       u16 old_tss_sel, u32 old_tss_base,
-		       struct desc_struct *nseg_desc)
-{
-	struct tss_segment_32 tss_segment_32;
-	int ret = 0;
-
-	if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
-			   sizeof tss_segment_32))
-		goto out;
-
-	save_state_to_tss32(vcpu, &tss_segment_32);
-
-	if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
-			    sizeof tss_segment_32))
-		goto out;
-
-	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
-			   &tss_segment_32, sizeof tss_segment_32))
-		goto out;
-
-	if (old_tss_sel != 0xffff) {
-		tss_segment_32.prev_task_link = old_tss_sel;
-
-		if (kvm_write_guest(vcpu->kvm,
-				    get_tss_base_addr_write(vcpu, nseg_desc),
-				    &tss_segment_32.prev_task_link,
-				    sizeof tss_segment_32.prev_task_link))
-			goto out;
-	}
-
-	if (load_state_from_tss32(vcpu, &tss_segment_32))
-		goto out;
-
-	ret = 1;
-out:
-	return ret;
-}
-
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
-{
-	struct kvm_segment tr_seg;
-	struct desc_struct cseg_desc;
-	struct desc_struct nseg_desc;
-	int ret = 0;
-	u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
-	u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
-	u32 desc_limit;
-
-	old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL);
-
-	/* FIXME: Handle errors. Failure to read either TSS or their
-	 * descriptors should generate a pagefault.
-	 */
-	if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc))
-		goto out;
-
-	if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc))
-		goto out;
-
-	if (reason != TASK_SWITCH_IRET) {
-		int cpl;
-
-		cpl = kvm_x86_ops->get_cpl(vcpu);
-		if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) {
-			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-			return 1;
-		}
-	}
-
-	desc_limit = get_desc_limit(&nseg_desc);
-	if (!nseg_desc.p ||
-	    ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
-	     desc_limit < 0x2b)) {
-		kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
-		return 1;
-	}
-
-	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
-		cseg_desc.type &= ~(1 << 1); //clear the B flag
-		save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc);
-	}
-
-	if (reason == TASK_SWITCH_IRET) {
-		u32 eflags = kvm_get_rflags(vcpu);
-		kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
-	}
-
-	/* set back link to prev task only if NT bit is set in eflags
-	   note that old_tss_sel is not used afetr this point */
-	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
-		old_tss_sel = 0xffff;
-
-	if (nseg_desc.type & 8)
-		ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel,
-					 old_tss_base, &nseg_desc);
-	else
-		ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel,
-					 old_tss_base, &nseg_desc);
-
-	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
-		u32 eflags = kvm_get_rflags(vcpu);
-		kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT);
-	}
-
-	if (reason != TASK_SWITCH_IRET) {
-		nseg_desc.type |= (1 << 1);
-		save_guest_segment_descriptor(vcpu, tss_selector,
-					      &nseg_desc);
-	}
-
-	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS);
-	seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
-	tr_seg.type = 11;
-	kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
-out:
-	return ret;
+	kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+	return EMULATE_DONE;
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
@@ -5258,15 +4933,15 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 {
 	int mmu_reset_needed = 0;
 	int pending_vec, max_bits;
-	struct descriptor_table dt;
+	struct desc_ptr dt;
 
 	vcpu_load(vcpu);
 
-	dt.limit = sregs->idt.limit;
-	dt.base = sregs->idt.base;
+	dt.size = sregs->idt.limit;
+	dt.address = sregs->idt.base;
 	kvm_x86_ops->set_idt(vcpu, &dt);
-	dt.limit = sregs->gdt.limit;
-	dt.base = sregs->gdt.base;
+	dt.size = sregs->gdt.limit;
+	dt.address = sregs->gdt.base;
 	kvm_x86_ops->set_gdt(vcpu, &dt);
 
 	vcpu->arch.cr2 = sregs->cr2;
@@ -5365,11 +5040,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 		vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
 	}
 
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-		vcpu->arch.singlestep_cs =
-			get_segment_selector(vcpu, VCPU_SREG_CS);
-		vcpu->arch.singlestep_rip = kvm_rip_read(vcpu);
-	}
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
+			get_segment_base(vcpu, VCPU_SREG_CS);
 
 	/*
 	 * Trigger an rflags update that will inject or remove the trace
@@ -5860,13 +5533,22 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip)
+{
+	unsigned long current_rip = kvm_rip_read(vcpu) +
+		get_segment_base(vcpu, VCPU_SREG_CS);
+
+	return current_rip == linear_rip;
+}
+EXPORT_SYMBOL_GPL(kvm_is_linear_rip);
+
 unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
 {
 	unsigned long rflags;
 
 	rflags = kvm_x86_ops->get_rflags(vcpu);
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF);
+		rflags &= ~X86_EFLAGS_TF;
 	return rflags;
 }
 EXPORT_SYMBOL_GPL(kvm_get_rflags);
@@ -5874,10 +5556,8 @@ EXPORT_SYMBOL_GPL(kvm_get_rflags);
 void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
-	    vcpu->arch.singlestep_cs ==
-			get_segment_selector(vcpu, VCPU_SREG_CS) &&
-	    vcpu->arch.singlestep_rip == kvm_rip_read(vcpu))
-		rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+	    kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
+		rflags |= X86_EFLAGS_TF;
 	kvm_x86_ops->set_rflags(vcpu, rflags);
 }
 EXPORT_SYMBOL_GPL(kvm_set_rflags);
@@ -5893,3 +5573,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);

arch/x86/kvm/x86.h

@@ -65,6 +65,13 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
+static inline struct kvm_mem_aliases *kvm_aliases(struct kvm *kvm)
+{
+	return rcu_dereference_check(kvm->arch.aliases,
+			srcu_read_lock_held(&kvm->srcu)
+			|| lockdep_is_held(&kvm->slots_lock));
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 

include/linux/kvm.h

@@ -160,6 +160,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_DCR              15
 #define KVM_EXIT_NMI              16
 #define KVM_EXIT_INTERNAL_ERROR   17
+#define KVM_EXIT_OSI              18
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -259,6 +260,10 @@ struct kvm_run {
 			__u32 ndata;
 			__u64 data[16];
 		} internal;
+		/* KVM_EXIT_OSI */
+		struct {
+			__u64 gprs[32];
+		} osi;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -400,6 +405,15 @@ struct kvm_ioeventfd {
 	__u8  pad[36];
 };
 
+/* for KVM_ENABLE_CAP */
+struct kvm_enable_cap {
+	/* in */
+	__u32 cap;
+	__u32 flags;
+	__u64 args[4];
+	__u8  pad[64];
+};
+
 #define KVMIO 0xAE
 
 /*
@@ -501,7 +515,15 @@ struct kvm_ioeventfd {
 #define KVM_CAP_HYPERV_VAPIC 45
 #define KVM_CAP_HYPERV_SPIN 46
 #define KVM_CAP_PCI_SEGMENT 47
+#define KVM_CAP_PPC_PAIRED_SINGLES 48
+#define KVM_CAP_INTR_SHADOW 49
+#ifdef __KVM_HAVE_DEBUGREGS
+#define KVM_CAP_DEBUGREGS 50
+#endif
 #define KVM_CAP_X86_ROBUST_SINGLESTEP 51
+#define KVM_CAP_PPC_OSI 52
+#define KVM_CAP_PPC_UNSET_IRQ 53
+#define KVM_CAP_ENABLE_CAP 54
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -688,6 +710,10 @@ struct kvm_clock_data {
 /* Available with KVM_CAP_VCPU_EVENTS */
 #define KVM_GET_VCPU_EVENTS       _IOR(KVMIO,  0x9f, struct kvm_vcpu_events)
 #define KVM_SET_VCPU_EVENTS       _IOW(KVMIO,  0xa0, struct kvm_vcpu_events)
+/* Available with KVM_CAP_DEBUGREGS */
+#define KVM_GET_DEBUGREGS         _IOR(KVMIO,  0xa1, struct kvm_debugregs)
+#define KVM_SET_DEBUGREGS         _IOW(KVMIO,  0xa2, struct kvm_debugregs)
+#define KVM_ENABLE_CAP            _IOW(KVMIO,  0xa3, struct kvm_enable_cap)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 

include/linux/kvm_host.h

@@ -105,6 +105,12 @@ struct kvm_vcpu {
 	struct kvm_vcpu_arch arch;
 };
 
+/*
+ * Some of the bitops functions do not support too long bitmaps.
+ * This number must be determined not to exceed such limits.
+ */
+#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
+
 struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
@@ -237,17 +243,23 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 void vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
-int kvm_init(void *opaque, unsigned int vcpu_size,
+int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		  struct module *module);
 void kvm_exit(void);
 
 void kvm_get_kvm(struct kvm *kvm);
 void kvm_put_kvm(struct kvm *kvm);
 
+static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
+{
+	return rcu_dereference_check(kvm->memslots,
+			srcu_read_lock_held(&kvm->srcu)
+			|| lockdep_is_held(&kvm->slots_lock));
+}
+
 #define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
 #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
 static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
-struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva);
 
 extern struct page *bad_page;
 extern pfn_t bad_pfn;

include/linux/tboot.h

@@ -150,6 +150,7 @@ extern int tboot_force_iommu(void);
 
 #else
 
+#define tboot_enabled()			0
 #define tboot_probe()			do { } while (0)
 #define tboot_shutdown(shutdown_type)	do { } while (0)
 #define tboot_sleep(sleep_state, pm1a_control, pm1b_control)	\

include/trace/events/kvm.h

@@ -5,7 +5,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
-#define TRACE_INCLUDE_FILE kvm
 
 #if defined(__KVM_HAVE_IOAPIC)
 TRACE_EVENT(kvm_set_irq,

virt/kvm/assigned-dev.c

@@ -316,12 +316,16 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 				kvm_assigned_dev_intr, 0,
 				"kvm_assigned_msix_device",
 				(void *)dev);
-		/* FIXME: free requested_irq's on failure */
 		if (r)
-			return r;
+			goto err;
 	}
 
 	return 0;
+err:
+	for (i -= 1; i >= 0; i--)
+		free_irq(dev->host_msix_entries[i].vector, (void *)dev);
+	pci_disable_msix(dev->dev);
+	return r;
 }
 
 #endif

virt/kvm/coalesced_mmio.c

@@ -120,8 +120,10 @@ int kvm_coalesced_mmio_init(struct kvm *kvm)
 	return ret;
 
 out_free_dev:
+	kvm->coalesced_mmio_dev = NULL;
 	kfree(dev);
 out_free_page:
+	kvm->coalesced_mmio_ring = NULL;
 	__free_page(page);
 out_err:
 	return ret;
@@ -139,7 +141,7 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	struct kvm_coalesced_mmio_dev *dev = kvm->coalesced_mmio_dev;
 
 	if (dev == NULL)
-		return -EINVAL;
+		return -ENXIO;
 
 	mutex_lock(&kvm->slots_lock);
 	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
@@ -162,7 +164,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 	struct kvm_coalesced_mmio_zone *z;
 
 	if (dev == NULL)
-		return -EINVAL;
+		return -ENXIO;
 
 	mutex_lock(&kvm->slots_lock);
 

virt/kvm/iommu.c

@@ -127,7 +127,7 @@ static int kvm_iommu_map_memslots(struct kvm *kvm)
 	int i, r = 0;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; i++) {
 		r = kvm_iommu_map_pages(kvm, &slots->memslots[i]);
@@ -286,7 +286,7 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm)
 	int i;
 	struct kvm_memslots *slots;
 
-	slots = rcu_dereference(kvm->memslots);
+	slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; i++) {
 		kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn,

virt/kvm/kvm_main.c

@@ -422,9 +422,6 @@ static struct kvm *kvm_create_vm(void)
 	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	spin_unlock(&kvm_lock);
-#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
-	kvm_coalesced_mmio_init(kvm);
-#endif
 out:
 	return kvm;
 
@@ -560,6 +557,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
+	r = -EINVAL;
+	if (npages > KVM_MEM_MAX_NR_PAGES)
+		goto out;
+
 	if (!npages)
 		mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
@@ -833,7 +834,7 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
-	struct kvm_memslots *slots = rcu_dereference(kvm->memslots);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 
 	for (i = 0; i < slots->nmemslots; ++i) {
 		struct kvm_memory_slot *memslot = &slots->memslots[i];
@@ -855,7 +856,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
-	struct kvm_memslots *slots = rcu_dereference(kvm->memslots);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 
 	gfn = unalias_gfn_instantiation(kvm, gfn);
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
@@ -899,7 +900,7 @@ unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)
 int memslot_id(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
-	struct kvm_memslots *slots = rcu_dereference(kvm->memslots);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
 	struct kvm_memory_slot *memslot = NULL;
 
 	gfn = unalias_gfn(kvm, gfn);
@@ -914,6 +915,11 @@ int memslot_id(struct kvm *kvm, gfn_t gfn)
 	return memslot - slots->memslots;
 }
 
+static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+}
+
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *slot;
@@ -922,7 +928,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 	slot = gfn_to_memslot_unaliased(kvm, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return bad_hva();
-	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
+	return gfn_to_hva_memslot(slot, gfn);
 }
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
@@ -972,11 +978,6 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn);
 
-static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
-{
-	return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE);
-}
-
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
 			 struct kvm_memory_slot *slot, gfn_t gfn)
 {
@@ -1190,13 +1191,8 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	memslot = gfn_to_memslot_unaliased(kvm, gfn);
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
-		unsigned long *p = memslot->dirty_bitmap +
-					rel_gfn / BITS_PER_LONG;
-		int offset = rel_gfn % BITS_PER_LONG;
 
-		/* avoid RMW */
-		if (!generic_test_le_bit(offset, p))
-			generic___set_le_bit(offset, p);
+		generic___set_le_bit(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 
@@ -1609,7 +1605,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&zone, argp, sizeof zone))
 			goto out;
-		r = -ENXIO;
 		r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone);
 		if (r)
 			goto out;
@@ -1621,7 +1616,6 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&zone, argp, sizeof zone))
 			goto out;
-		r = -ENXIO;
 		r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone);
 		if (r)
 			goto out;
@@ -1755,12 +1749,19 @@ static struct file_operations kvm_vm_fops = {
 
 static int kvm_dev_ioctl_create_vm(void)
 {
-	int fd;
+	int fd, r;
 	struct kvm *kvm;
 
 	kvm = kvm_create_vm();
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
+#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
+	r = kvm_coalesced_mmio_init(kvm);
+	if (r < 0) {
+		kvm_put_kvm(kvm);
+		return r;
+	}
+#endif
 	fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
 	if (fd < 0)
 		kvm_put_kvm(kvm);
@@ -1928,11 +1929,6 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 		       cpu);
 		hardware_disable(NULL);
 		break;
-	case CPU_UP_CANCELED:
-		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
-		       cpu);
-		smp_call_function_single(cpu, hardware_disable, NULL, 1);
-		break;
 	case CPU_ONLINE:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
@@ -1991,7 +1987,9 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		     int len, const void *val)
 {
 	int i;
-	struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]);
+	struct kvm_io_bus *bus;
+
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
 	for (i = 0; i < bus->dev_count; i++)
 		if (!kvm_iodevice_write(bus->devs[i], addr, len, val))
 			return 0;
@@ -2003,8 +2001,9 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		    int len, void *val)
 {
 	int i;
-	struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]);
+	struct kvm_io_bus *bus;
 
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
 	for (i = 0; i < bus->dev_count; i++)
 		if (!kvm_iodevice_read(bus->devs[i], addr, len, val))
 			return 0;
@@ -2179,7 +2178,7 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 	kvm_arch_vcpu_put(vcpu);
 }
 
-int kvm_init(void *opaque, unsigned int vcpu_size,
+int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		  struct module *module)
 {
 	int r;
@@ -2229,8 +2228,9 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		goto out_free_4;
 
 	/* A kmem cache lets us meet the alignment requirements of fx_save. */
-	kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size,
-					   __alignof__(struct kvm_vcpu),
+	if (!vcpu_align)
+		vcpu_align = __alignof__(struct kvm_vcpu);
+	kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align,
 					   0, NULL);
 	if (!kvm_vcpu_cache) {
 		r = -ENOMEM;
@@ -2279,7 +2279,6 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
-	tracepoint_synchronize_unregister();
 	kvm_exit_debug();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);