diff mbox

[10/15] KVM: ARM: World-switch implementation

Message ID 20120915153533.21241.82489.stgit@ubuntu (mailing list archive)
State New, archived
Headers show

Commit Message

Christoffer Dall Sept. 15, 2012, 3:35 p.m. UTC
From: Christoffer Dall <cdall@cs.columbia.edu>

Provides complete world-switch implementation to switch to other guests
running in non-secure modes. Includes Hyp exception handlers that
capture necessary exception information and stores the information on
the VCPU and KVM structures.

The following Hyp-ABI is also documented in the code:

Hyp-ABI: Switching from host kernel to Hyp-mode:
   Switching to Hyp mode is done through a simple HVC #0 instruction. The
   exception vector code will check that the HVC comes from VMID==0 and if
   so will store the necessary state on the Hyp stack, which will look like
   this (growing downwards, see the hyp_hvc handler):
     ...
     stack_page + 4: spsr (Host-SVC cpsr)
     stack_page    : lr_usr
     --------------: stack bottom

Hyp-ABI: Switching from Hyp-mode to host kernel SVC mode:
   When returning from Hyp mode to SVC mode, another HVC instruction is
   executed from Hyp mode, which is taken in the hyp_svc handler. The
   bottom of the Hyp is derived from the Hyp stack pointer (only a single
   page aligned stack is used per CPU) and the initial SVC registers are
   used to restore the host state.

Hyp-ABI: Change the HVBAR:
   When removing the KVM module we want to reset our hold on Hyp mode.
   This is accomplished by calling HVC #0xff from the host kernel
   (VMID==0) with the desired new HVBAR in r0.

Otherwise, the world-switch is pretty straight-forward. All state that
can be modified by the guest is first backed up on the Hyp stack and the
VCPU values is loaded onto the hardware. State, which is not loaded, but
theoretically modifiable by the guest is protected through the
virtualiation features to generate a trap and cause software emulation.
Upon guest returns, all state is restored from hardware onto the VCPU
struct and the original state is restored from the Hyp-stack onto the
hardware.

SMP support using the VMPIDR calculated on the basis of the host MPIDR
and overriding the low bits with KVM vcpu_id contributed by Marc Zyngier.

Reuse of VMIDs has been implemented by Antonios Motakis and adapated from
a separate patch into the appropriate patches introducing the
functionality. Note that the VMIDs are stored per VM as required by the ARM
architecture reference manual.

To support VFP/NEON we trap those instructions using the HPCTR. When
we trap, we switch the FPU.  After a guest exit, the VFP state is
returned to the host.  When disabling access to floating point
instructions, we also mask FPEXC_EN in order to avoid the guest
receiving Undefined instruction exceptions before we have a chance to
switch back the floating point state.  We are reusing vfp_hard_struct,
so we depend on VFPv3 being enabled in the host kernel, if not, we still
trap cp10 and cp11 in order to inject an undefined instruction exception
whenever the guest tries to use VFP/NEON. VFP/NEON developed by
Antionios Motakis and Rusty Russell.

Signed-off-by: Rusty Russell <rusty.russell@linaro.org>
Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <c.dall@virtualopensystems.com>
---
 arch/arm/include/asm/kvm_arm.h  |   38 ++
 arch/arm/include/asm/kvm_host.h |    9 
 arch/arm/kernel/asm-offsets.c   |   44 ++
 arch/arm/kvm/arm.c              |  165 +++++++++
 arch/arm/kvm/interrupts.S       |  712 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 965 insertions(+), 3 deletions(-)

Comments

Will Deacon Sept. 25, 2012, 5 p.m. UTC | #1
On Sat, Sep 15, 2012 at 04:35:33PM +0100, Christoffer Dall wrote:
> diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
> index 1429d89..cd8fc86 100644
> --- a/arch/arm/kernel/asm-offsets.c
> +++ b/arch/arm/kernel/asm-offsets.c
> @@ -13,6 +13,7 @@
>  #include <linux/sched.h>
>  #include <linux/mm.h>
>  #include <linux/dma-mapping.h>
> +#include <linux/kvm_host.h>
>  #include <asm/cacheflush.h>
>  #include <asm/glue-df.h>
>  #include <asm/glue-pf.h>
> @@ -144,5 +145,48 @@ int main(void)
>    DEFINE(DMA_BIDIRECTIONAL,    DMA_BIDIRECTIONAL);
>    DEFINE(DMA_TO_DEVICE,                DMA_TO_DEVICE);
>    DEFINE(DMA_FROM_DEVICE,      DMA_FROM_DEVICE);
> +#ifdef CONFIG_KVM_ARM_HOST
> +  DEFINE(VCPU_KVM,             offsetof(struct kvm_vcpu, kvm));
> +  DEFINE(VCPU_MIDR,            offsetof(struct kvm_vcpu, arch.midr));
> +  DEFINE(VCPU_MPIDR,           offsetof(struct kvm_vcpu, arch.cp15[c0_MPIDR]));
> +  DEFINE(VCPU_CSSELR,          offsetof(struct kvm_vcpu, arch.cp15[c0_CSSELR]));
> +  DEFINE(VCPU_SCTLR,           offsetof(struct kvm_vcpu, arch.cp15[c1_SCTLR]));
> +  DEFINE(VCPU_CPACR,           offsetof(struct kvm_vcpu, arch.cp15[c1_CPACR]));
> +  DEFINE(VCPU_TTBR0,           offsetof(struct kvm_vcpu, arch.cp15[c2_TTBR0]));
> +  DEFINE(VCPU_TTBR1,           offsetof(struct kvm_vcpu, arch.cp15[c2_TTBR1]));
> +  DEFINE(VCPU_TTBCR,           offsetof(struct kvm_vcpu, arch.cp15[c2_TTBCR]));
> +  DEFINE(VCPU_DACR,            offsetof(struct kvm_vcpu, arch.cp15[c3_DACR]));
> +  DEFINE(VCPU_DFSR,            offsetof(struct kvm_vcpu, arch.cp15[c5_DFSR]));
> +  DEFINE(VCPU_IFSR,            offsetof(struct kvm_vcpu, arch.cp15[c5_IFSR]));
> +  DEFINE(VCPU_ADFSR,           offsetof(struct kvm_vcpu, arch.cp15[c5_ADFSR]));
> +  DEFINE(VCPU_AIFSR,           offsetof(struct kvm_vcpu, arch.cp15[c5_AIFSR]));
> +  DEFINE(VCPU_DFAR,            offsetof(struct kvm_vcpu, arch.cp15[c6_DFAR]));
> +  DEFINE(VCPU_IFAR,            offsetof(struct kvm_vcpu, arch.cp15[c6_IFAR]));
> +  DEFINE(VCPU_PRRR,            offsetof(struct kvm_vcpu, arch.cp15[c10_PRRR]));
> +  DEFINE(VCPU_NMRR,            offsetof(struct kvm_vcpu, arch.cp15[c10_NMRR]));
> +  DEFINE(VCPU_VBAR,            offsetof(struct kvm_vcpu, arch.cp15[c12_VBAR]));
> +  DEFINE(VCPU_CID,             offsetof(struct kvm_vcpu, arch.cp15[c13_CID]));
> +  DEFINE(VCPU_TID_URW,         offsetof(struct kvm_vcpu, arch.cp15[c13_TID_URW]));
> +  DEFINE(VCPU_TID_URO,         offsetof(struct kvm_vcpu, arch.cp15[c13_TID_URO]));
> +  DEFINE(VCPU_TID_PRIV,                offsetof(struct kvm_vcpu, arch.cp15[c13_TID_PRIV]));

Could you instead define an offset for arch.cp15, then use scaled offsets
from that in the assembly code?

> diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
> index 8a87fc7..087f9d1 100644
> --- a/arch/arm/kvm/arm.c
> +++ b/arch/arm/kvm/arm.c
> @@ -41,6 +41,7 @@
>  #include <asm/kvm_arm.h>
>  #include <asm/kvm_asm.h>
>  #include <asm/kvm_mmu.h>
> +#include <asm/kvm_emulate.h>
> 
>  #ifdef REQUIRES_VIRT
>  __asm__(".arch_extension       virt");
> @@ -50,6 +51,10 @@ static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
>  static struct vfp_hard_struct __percpu *kvm_host_vfp_state;
>  static unsigned long hyp_default_vectors;
> 
> +/* The VMID used in the VTTBR */
> +static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
> +static u8 kvm_next_vmid;
> +static DEFINE_SPINLOCK(kvm_vmid_lock);
> 
>  int kvm_arch_hardware_enable(void *garbage)
>  {
> @@ -273,6 +278,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
>  void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>  {
>         vcpu->cpu = cpu;
> +       vcpu->arch.vfp_host = this_cpu_ptr(kvm_host_vfp_state);
>  }
> 
>  void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
> @@ -305,12 +311,169 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
> 
>  int kvm_arch_vcpu_in_guest_mode(struct kvm_vcpu *v)
>  {
> +       return v->mode == IN_GUEST_MODE;
> +}
> +
> +static void reset_vm_context(void *info)
> +{
> +       __kvm_flush_vm_context();
> +}
> +
> +/**
> + * need_new_vmid_gen - check that the VMID is still valid
> + * @kvm: The VM's VMID to checkt
> + *
> + * return true if there is a new generation of VMIDs being used
> + *
> + * The hardware supports only 256 values with the value zero reserved for the
> + * host, so we check if an assigned value belongs to a previous generation,
> + * which which requires us to assign a new value. If we're the first to use a
> + * VMID for the new generation, we must flush necessary caches and TLBs on all
> + * CPUs.
> + */
> +static bool need_new_vmid_gen(struct kvm *kvm)
> +{
> +       return unlikely(kvm->arch.vmid_gen != atomic64_read(&kvm_vmid_gen));
> +}
> +
> +/**
> + * update_vttbr - Update the VTTBR with a valid VMID before the guest runs
> + * @kvm        The guest that we are about to run
> + *
> + * Called from kvm_arch_vcpu_ioctl_run before entering the guest to ensure the
> + * VM has a valid VMID, otherwise assigns a new one and flushes corresponding
> + * caches and TLBs.
> + */
> +static void update_vttbr(struct kvm *kvm)
> +{
> +       phys_addr_t pgd_phys;
> +
> +       if (!need_new_vmid_gen(kvm))
> +               return;
> +
> +       spin_lock(&kvm_vmid_lock);
> +
> +       /* First user of a new VMID generation? */
> +       if (unlikely(kvm_next_vmid == 0)) {
> +               atomic64_inc(&kvm_vmid_gen);
> +               kvm_next_vmid = 1;
> +
> +               /*
> +                * On SMP we know no other CPUs can use this CPU's or
> +                * each other's VMID since the kvm_vmid_lock blocks
> +                * them from reentry to the guest.
> +                */
> +               on_each_cpu(reset_vm_context, NULL, 1);

Why on_each_cpu? The maintenance operations should be broadcast, right?

> +       }
> +
> +       kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
> +       kvm->arch.vmid = kvm_next_vmid;
> +       kvm_next_vmid++;
> +
> +       /* update vttbr to be used with the new vmid */
> +       pgd_phys = virt_to_phys(kvm->arch.pgd);
> +       kvm->arch.vttbr = pgd_phys & ((1LLU << 40) - 1)
> +                         & ~((2 << VTTBR_X) - 1);
> +       kvm->arch.vttbr |= (u64)(kvm->arch.vmid) << 48;
> +
> +       spin_unlock(&kvm_vmid_lock);
> +}

This smells like a watered-down version of the ASID allocator. Now, I can't
really see much code sharing going on here, but perhaps your case is
simpler... do you anticipate running more than 255 VMs in parallel? If not,
then you could just invalidate the relevant TLB entries on VM shutdown and
avoid the rollover case.

> diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
> index edf9ed5..cc9448b 100644
> --- a/arch/arm/kvm/interrupts.S
> +++ b/arch/arm/kvm/interrupts.S
> @@ -23,6 +23,12 @@
>  #include <asm/asm-offsets.h>
>  #include <asm/kvm_asm.h>
>  #include <asm/kvm_arm.h>
> +#include <asm/vfpmacros.h>
> +
> +#define VCPU_USR_REG(_reg_nr)  (VCPU_USR_REGS + (_reg_nr * 4))
> +#define VCPU_USR_SP            (VCPU_USR_REG(13))
> +#define VCPU_FIQ_REG(_reg_nr)  (VCPU_FIQ_REGS + (_reg_nr * 4))
> +#define VCPU_FIQ_SPSR          (VCPU_FIQ_REG(7))
> 
>         .text
>         .align  PAGE_SHIFT
> @@ -34,7 +40,33 @@ __kvm_hyp_code_start:
>  @  Flush per-VMID TLBs
>  @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@

This comment syntax crops up a few times in your .S files but doesn't match
anything currently under arch/arm/. Please can you follow what we do there
and use /* */ ?

>  ENTRY(__kvm_tlb_flush_vmid)
> +       hvc     #0                      @ Switch to Hyp mode
> +       push    {r2, r3}
> +
> +       add     r0, r0, #KVM_VTTBR
> +       ldrd    r2, r3, [r0]
> +       mcrr    p15, 6, r2, r3, c2      @ Write VTTBR
> +       isb
> +       mcr     p15, 0, r0, c8, c3, 0   @ TLBIALLIS (rt ignored)
> +       dsb
> +       isb
> +       mov     r2, #0
> +       mov     r3, #0
> +       mcrr    p15, 6, r2, r3, c2      @ Back to VMID #0
> +       isb

Do you need this isb, given that you're about to do an hvc?

> +       pop     {r2, r3}
> +       hvc     #0                      @ Back to SVC
>         bx      lr
>  ENDPROC(__kvm_tlb_flush_vmid)
> 
> @@ -42,26 +74,702 @@ ENDPROC(__kvm_tlb_flush_vmid)
>  @  Flush TLBs and instruction caches of current CPU for all VMIDs
>  @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
> 
> +/*
> + * void __kvm_flush_vm_context(void);
> + */
>  ENTRY(__kvm_flush_vm_context)
> +       hvc     #0                      @ switch to hyp-mode
> +
> +       mov     r0, #0                  @ rn parameter for c15 flushes is SBZ
> +       mcr     p15, 4, r0, c8, c7, 4   @ Invalidate Non-secure Non-Hyp TLB
> +       mcr     p15, 0, r0, c7, c5, 0   @ Invalidate instruction caches
> +       dsb
> +       isb

Likewise.

> +       hvc     #0                      @ switch back to svc-mode, see hyp_svc
>         bx      lr
>  ENDPROC(__kvm_flush_vm_context)
> 
> +/* These are simply for the macros to work - value don't have meaning */
> +.equ usr, 0
> +.equ svc, 1
> +.equ abt, 2
> +.equ und, 3
> +.equ irq, 4
> +.equ fiq, 5
> +
> +.macro store_mode_state base_reg, mode
> +       .if \mode == usr
> +       mrs     r2, SP_usr
> +       mov     r3, lr
> +       stmdb   \base_reg!, {r2, r3}
> +       .elseif \mode != fiq
> +       mrs     r2, SP_\mode
> +       mrs     r3, LR_\mode
> +       mrs     r4, SPSR_\mode
> +       stmdb   \base_reg!, {r2, r3, r4}
> +       .else
> +       mrs     r2, r8_fiq
> +       mrs     r3, r9_fiq
> +       mrs     r4, r10_fiq
> +       mrs     r5, r11_fiq
> +       mrs     r6, r12_fiq
> +       mrs     r7, SP_fiq
> +       mrs     r8, LR_fiq
> +       mrs     r9, SPSR_fiq
> +       stmdb   \base_reg!, {r2-r9}
> +       .endif
> +.endm

Perhaps you could stick the assembly macros into a separate file, like we do
in assembler.h, so the code is more readable and they can be reused if
need-be?

Will
Peter Maydell Sept. 25, 2012, 5:15 p.m. UTC | #2
On 25 September 2012 18:00, Will Deacon <will.deacon@arm.com> wrote:
> On Sat, Sep 15, 2012 at 04:35:33PM +0100, Christoffer Dall wrote:
>>  ENTRY(__kvm_tlb_flush_vmid)
>> +       hvc     #0                      @ Switch to Hyp mode
>> +       push    {r2, r3}
>> +
>> +       add     r0, r0, #KVM_VTTBR
>> +       ldrd    r2, r3, [r0]
>> +       mcrr    p15, 6, r2, r3, c2      @ Write VTTBR
>> +       isb
>> +       mcr     p15, 0, r0, c8, c3, 0   @ TLBIALLIS (rt ignored)
>> +       dsb
>> +       isb
>> +       mov     r2, #0
>> +       mov     r3, #0
>> +       mcrr    p15, 6, r2, r3, c2      @ Back to VMID #0
>> +       isb
>
> Do you need this isb, given that you're about to do an hvc?
>
>> +       pop     {r2, r3}
>> +       hvc     #0                      @ Back to SVC
>>         bx      lr

...you probably don't want to do the memory accesses involved
in the 'pop' under the wrong VMID ?

-- PMM
Marc Zyngier Sept. 25, 2012, 5:42 p.m. UTC | #3
On Tue, 25 Sep 2012 18:15:50 +0100, Peter Maydell
<peter.maydell@linaro.org> wrote:
> On 25 September 2012 18:00, Will Deacon <will.deacon@arm.com> wrote:
>> On Sat, Sep 15, 2012 at 04:35:33PM +0100, Christoffer Dall wrote:
>>>  ENTRY(__kvm_tlb_flush_vmid)
>>> +       hvc     #0                      @ Switch to Hyp mode
>>> +       push    {r2, r3}
>>> +
>>> +       add     r0, r0, #KVM_VTTBR
>>> +       ldrd    r2, r3, [r0]
>>> +       mcrr    p15, 6, r2, r3, c2      @ Write VTTBR
>>> +       isb
>>> +       mcr     p15, 0, r0, c8, c3, 0   @ TLBIALLIS (rt ignored)
>>> +       dsb
>>> +       isb
>>> +       mov     r2, #0
>>> +       mov     r3, #0
>>> +       mcrr    p15, 6, r2, r3, c2      @ Back to VMID #0
>>> +       isb
>>
>> Do you need this isb, given that you're about to do an hvc?
>>
>>> +       pop     {r2, r3}
>>> +       hvc     #0                      @ Back to SVC
>>>         bx      lr
> 
> ...you probably don't want to do the memory accesses involved
> in the 'pop' under the wrong VMID ?

Well, we're still in HYP mode when performing the pop, so the VMID is
pretty much irrelevant. Same for the initial push, actually. As long as
we're sure VTTBR has been updated when we do the exception return, I think
we're safe.

        M.
Christoffer Dall Sept. 30, 2012, 12:33 a.m. UTC | #4
On Tue, Sep 25, 2012 at 1:42 PM, Marc Zyngier <marc.zyngier@arm.com> wrote:
> On Tue, 25 Sep 2012 18:15:50 +0100, Peter Maydell
> <peter.maydell@linaro.org> wrote:
>> On 25 September 2012 18:00, Will Deacon <will.deacon@arm.com> wrote:
>>> On Sat, Sep 15, 2012 at 04:35:33PM +0100, Christoffer Dall wrote:
>>>>  ENTRY(__kvm_tlb_flush_vmid)
>>>> +       hvc     #0                      @ Switch to Hyp mode
>>>> +       push    {r2, r3}
>>>> +
>>>> +       add     r0, r0, #KVM_VTTBR
>>>> +       ldrd    r2, r3, [r0]
>>>> +       mcrr    p15, 6, r2, r3, c2      @ Write VTTBR
>>>> +       isb
>>>> +       mcr     p15, 0, r0, c8, c3, 0   @ TLBIALLIS (rt ignored)
>>>> +       dsb
>>>> +       isb
>>>> +       mov     r2, #0
>>>> +       mov     r3, #0
>>>> +       mcrr    p15, 6, r2, r3, c2      @ Back to VMID #0
>>>> +       isb
>>>
>>> Do you need this isb, given that you're about to do an hvc?
>>>
>>>> +       pop     {r2, r3}
>>>> +       hvc     #0                      @ Back to SVC
>>>>         bx      lr
>>
>> ...you probably don't want to do the memory accesses involved
>> in the 'pop' under the wrong VMID ?
>
> Well, we're still in HYP mode when performing the pop, so the VMID is
> pretty much irrelevant. Same for the initial push, actually. As long as
> we're sure VTTBR has been updated when we do the exception return, I think
> we're safe.
>
yeah we're safe, but I can't find anywhere that says the ISB is
implied from exception handling/hvc, even though I seem to recall
having read this, so I put this here not to worry other readers.

-Christoffer
Peter Maydell Sept. 30, 2012, 9:48 a.m. UTC | #5
On 30 September 2012 01:33, Christoffer Dall
<c.dall@virtualopensystems.com> wrote:
> On Tue, Sep 25, 2012 at 1:42 PM, Marc Zyngier <marc.zyngier@arm.com> wrote:
>> Well, we're still in HYP mode when performing the pop, so the VMID is
>> pretty much irrelevant. Same for the initial push, actually. As long as
>> we're sure VTTBR has been updated when we do the exception return, I think
>> we're safe.
>>
> yeah we're safe, but I can't find anywhere that says the ISB is
> implied from exception handling/hvc, even though I seem to recall
> having read this, so I put this here not to worry other readers.

"TLB maintenance operations and the memory order model" in section
B3.10.1 of the ARM ARM says that exception entry forces completion of
TLB maintenance ops. Section B5.6.3 ("Synchronization of changes to
system control registers") says that taking an exception synchronizes
context, so the VTTBR update is guaranteed to have happened.

-- PMM
Christoffer Dall Sept. 30, 2012, 2:31 p.m. UTC | #6
On Sun, Sep 30, 2012 at 5:48 AM, Peter Maydell <peter.maydell@linaro.org> wrote:
> On 30 September 2012 01:33, Christoffer Dall
> <c.dall@virtualopensystems.com> wrote:
>> On Tue, Sep 25, 2012 at 1:42 PM, Marc Zyngier <marc.zyngier@arm.com> wrote:
>>> Well, we're still in HYP mode when performing the pop, so the VMID is
>>> pretty much irrelevant. Same for the initial push, actually. As long as
>>> we're sure VTTBR has been updated when we do the exception return, I think
>>> we're safe.
>>>
>> yeah we're safe, but I can't find anywhere that says the ISB is
>> implied from exception handling/hvc, even though I seem to recall
>> having read this, so I put this here not to worry other readers.
>
> "TLB maintenance operations and the memory order model" in section
> B3.10.1 of the ARM ARM says that exception entry forces completion of
> TLB maintenance ops. Section B5.6.3 ("Synchronization of changes to
> system control registers") says that taking an exception synchronizes
> context, so the VTTBR update is guaranteed to have happened.
>
thanks - I was counting on your help here :)

-Christoffer
diff mbox

Patch

diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 0f641c1..ee345a6 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -104,6 +104,18 @@ 
 #define TTBCR_T0SZ	3
 #define HTCR_MASK	(TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0)
 
+/* Hyp System Trap Register */
+#define HSTR_T(x)	(1 << x)
+#define HSTR_TTEE	(1 << 16)
+#define HSTR_TJDBX	(1 << 17)
+
+/* Hyp Coprocessor Trap Register */
+#define HCPTR_TCP(x)	(1 << x)
+#define HCPTR_TCP_MASK	(0x3fff)
+#define HCPTR_TASE	(1 << 15)
+#define HCPTR_TTA	(1 << 20)
+#define HCPTR_TCPAC	(1 << 31)
+
 /* Hyp Debug Configuration Register bits */
 #define HDCR_TDRA	(1 << 11)
 #define HDCR_TDOSA	(1 << 10)
@@ -134,5 +146,31 @@ 
 #define VTTBR_X		(5 - VTCR_GUEST_T0SZ)
 #endif
 
+/* Hyp Syndrome Register (HSR) bits */
+#define HSR_EC_SHIFT	(26)
+#define HSR_EC		(0x3fU << HSR_EC_SHIFT)
+#define HSR_IL		(1U << 25)
+#define HSR_ISS		(HSR_IL - 1)
+#define HSR_ISV_SHIFT	(24)
+#define HSR_ISV		(1U << HSR_ISV_SHIFT)
+
+#define HSR_EC_UNKNOWN	(0x00)
+#define HSR_EC_WFI	(0x01)
+#define HSR_EC_CP15_32	(0x03)
+#define HSR_EC_CP15_64	(0x04)
+#define HSR_EC_CP14_MR	(0x05)
+#define HSR_EC_CP14_LS	(0x06)
+#define HSR_EC_CP_0_13	(0x07)
+#define HSR_EC_CP10_ID	(0x08)
+#define HSR_EC_JAZELLE	(0x09)
+#define HSR_EC_BXJ	(0x0A)
+#define HSR_EC_CP14_64	(0x0C)
+#define HSR_EC_SVC_HYP	(0x11)
+#define HSR_EC_HVC	(0x12)
+#define HSR_EC_SMC	(0x13)
+#define HSR_EC_IABT	(0x20)
+#define HSR_EC_IABT_HYP	(0x21)
+#define HSR_EC_DABT	(0x24)
+#define HSR_EC_DABT_HYP	(0x25)
 
 #endif /* __ARM_KVM_ARM_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index f0c72b9..ca4c079 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -20,6 +20,7 @@ 
 #define __ARM_KVM_HOST_H__
 
 #include <asm/kvm.h>
+#include <asm/fpstate.h>
 
 #define KVM_MAX_VCPUS 4
 #define KVM_MEMORY_SLOTS 32
@@ -137,6 +138,14 @@  struct kvm_vcpu_arch {
 	u32 hifar;		/* Hyp Inst. Fault Address Register */
 	u32 hpfar;		/* Hyp IPA Fault Address Register */
 
+	/* Floating point registers (VFP and Advanced SIMD/NEON) */
+	struct vfp_hard_struct vfp_guest;
+	struct vfp_hard_struct *vfp_host;
+
+	/*
+	 * Anything that is not used directly from assembly code goes
+	 * here.
+	 */
 	/* IO related fields */
 	struct {
 		bool sign_extend;	/* for byte/halfword loads */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 1429d89..cd8fc86 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -13,6 +13,7 @@ 
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
+#include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
@@ -144,5 +145,48 @@  int main(void)
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
+#ifdef CONFIG_KVM_ARM_HOST
+  DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
+  DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
+  DEFINE(VCPU_MPIDR,		offsetof(struct kvm_vcpu, arch.cp15[c0_MPIDR]));
+  DEFINE(VCPU_CSSELR,		offsetof(struct kvm_vcpu, arch.cp15[c0_CSSELR]));
+  DEFINE(VCPU_SCTLR,		offsetof(struct kvm_vcpu, arch.cp15[c1_SCTLR]));
+  DEFINE(VCPU_CPACR,		offsetof(struct kvm_vcpu, arch.cp15[c1_CPACR]));
+  DEFINE(VCPU_TTBR0,		offsetof(struct kvm_vcpu, arch.cp15[c2_TTBR0]));
+  DEFINE(VCPU_TTBR1,		offsetof(struct kvm_vcpu, arch.cp15[c2_TTBR1]));
+  DEFINE(VCPU_TTBCR,		offsetof(struct kvm_vcpu, arch.cp15[c2_TTBCR]));
+  DEFINE(VCPU_DACR,		offsetof(struct kvm_vcpu, arch.cp15[c3_DACR]));
+  DEFINE(VCPU_DFSR,		offsetof(struct kvm_vcpu, arch.cp15[c5_DFSR]));
+  DEFINE(VCPU_IFSR,		offsetof(struct kvm_vcpu, arch.cp15[c5_IFSR]));
+  DEFINE(VCPU_ADFSR,		offsetof(struct kvm_vcpu, arch.cp15[c5_ADFSR]));
+  DEFINE(VCPU_AIFSR,		offsetof(struct kvm_vcpu, arch.cp15[c5_AIFSR]));
+  DEFINE(VCPU_DFAR,		offsetof(struct kvm_vcpu, arch.cp15[c6_DFAR]));
+  DEFINE(VCPU_IFAR,		offsetof(struct kvm_vcpu, arch.cp15[c6_IFAR]));
+  DEFINE(VCPU_PRRR,		offsetof(struct kvm_vcpu, arch.cp15[c10_PRRR]));
+  DEFINE(VCPU_NMRR,		offsetof(struct kvm_vcpu, arch.cp15[c10_NMRR]));
+  DEFINE(VCPU_VBAR,		offsetof(struct kvm_vcpu, arch.cp15[c12_VBAR]));
+  DEFINE(VCPU_CID,		offsetof(struct kvm_vcpu, arch.cp15[c13_CID]));
+  DEFINE(VCPU_TID_URW,		offsetof(struct kvm_vcpu, arch.cp15[c13_TID_URW]));
+  DEFINE(VCPU_TID_URO,		offsetof(struct kvm_vcpu, arch.cp15[c13_TID_URO]));
+  DEFINE(VCPU_TID_PRIV,		offsetof(struct kvm_vcpu, arch.cp15[c13_TID_PRIV]));
+  DEFINE(VCPU_VFP_GUEST,	offsetof(struct kvm_vcpu, arch.vfp_guest));
+  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.vfp_host));
+  DEFINE(VCPU_REGS,		offsetof(struct kvm_vcpu, arch.regs));
+  DEFINE(VCPU_USR_REGS,		offsetof(struct kvm_vcpu, arch.regs.usr_regs));
+  DEFINE(VCPU_SVC_REGS,		offsetof(struct kvm_vcpu, arch.regs.svc_regs));
+  DEFINE(VCPU_ABT_REGS,		offsetof(struct kvm_vcpu, arch.regs.abt_regs));
+  DEFINE(VCPU_UND_REGS,		offsetof(struct kvm_vcpu, arch.regs.und_regs));
+  DEFINE(VCPU_IRQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.irq_regs));
+  DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
+  DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.pc));
+  DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.cpsr));
+  DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
+  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.hsr));
+  DEFINE(VCPU_HDFAR,		offsetof(struct kvm_vcpu, arch.hdfar));
+  DEFINE(VCPU_HIFAR,		offsetof(struct kvm_vcpu, arch.hifar));
+  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.hpfar));
+  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.hyp_pc));
+  DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
+#endif
   return 0; 
 }
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 8a87fc7..087f9d1 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -41,6 +41,7 @@ 
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_emulate.h>
 
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
@@ -50,6 +51,10 @@  static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
 static struct vfp_hard_struct __percpu *kvm_host_vfp_state;
 static unsigned long hyp_default_vectors;
 
+/* The VMID used in the VTTBR */
+static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
+static u8 kvm_next_vmid;
+static DEFINE_SPINLOCK(kvm_vmid_lock);
 
 int kvm_arch_hardware_enable(void *garbage)
 {
@@ -273,6 +278,7 @@  void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	vcpu->cpu = cpu;
+	vcpu->arch.vfp_host = this_cpu_ptr(kvm_host_vfp_state);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -305,12 +311,169 @@  int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 
 int kvm_arch_vcpu_in_guest_mode(struct kvm_vcpu *v)
 {
+	return v->mode == IN_GUEST_MODE;
+}
+
+static void reset_vm_context(void *info)
+{
+	__kvm_flush_vm_context();
+}
+
+/**
+ * need_new_vmid_gen - check that the VMID is still valid
+ * @kvm: The VM's VMID to checkt
+ *
+ * return true if there is a new generation of VMIDs being used
+ *
+ * The hardware supports only 256 values with the value zero reserved for the
+ * host, so we check if an assigned value belongs to a previous generation,
+ * which which requires us to assign a new value. If we're the first to use a
+ * VMID for the new generation, we must flush necessary caches and TLBs on all
+ * CPUs.
+ */
+static bool need_new_vmid_gen(struct kvm *kvm)
+{
+	return unlikely(kvm->arch.vmid_gen != atomic64_read(&kvm_vmid_gen));
+}
+
+/**
+ * update_vttbr - Update the VTTBR with a valid VMID before the guest runs
+ * @kvm	The guest that we are about to run
+ *
+ * Called from kvm_arch_vcpu_ioctl_run before entering the guest to ensure the
+ * VM has a valid VMID, otherwise assigns a new one and flushes corresponding
+ * caches and TLBs.
+ */
+static void update_vttbr(struct kvm *kvm)
+{
+	phys_addr_t pgd_phys;
+
+	if (!need_new_vmid_gen(kvm))
+		return;
+
+	spin_lock(&kvm_vmid_lock);
+
+	/* First user of a new VMID generation? */
+	if (unlikely(kvm_next_vmid == 0)) {
+		atomic64_inc(&kvm_vmid_gen);
+		kvm_next_vmid = 1;
+
+		/*
+		 * On SMP we know no other CPUs can use this CPU's or
+		 * each other's VMID since the kvm_vmid_lock blocks
+		 * them from reentry to the guest.
+		 */
+		on_each_cpu(reset_vm_context, NULL, 1);
+	}
+
+	kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
+	kvm->arch.vmid = kvm_next_vmid;
+	kvm_next_vmid++;
+
+	/* update vttbr to be used with the new vmid */
+	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	kvm->arch.vttbr = pgd_phys & ((1LLU << 40) - 1)
+			  & ~((2 << VTTBR_X) - 1);
+	kvm->arch.vttbr |= (u64)(kvm->arch.vmid) << 48;
+
+	spin_unlock(&kvm_vmid_lock);
+}
+
+/*
+ * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
+ * proper exit to QEMU.
+ */
+static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		       int exception_index)
+{
+	run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 	return 0;
 }
 
+/**
+ * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
+ * @vcpu:	The VCPU pointer
+ * @run:	The kvm_run structure pointer used for userspace state exchange
+ *
+ * This function is called through the VCPU_RUN ioctl called from user space. It
+ * will execute VM code in a loop until the time slice for the process is used
+ * or some emulation is needed from user space in which case the function will
+ * return with return value 0 and with the kvm_run structure filled in with the
+ * required data for the requested emulation.
+ */
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	return -EINVAL;
+	int ret;
+	sigset_t sigsaved;
+
+	/* Make sure they initialize the vcpu with KVM_ARM_VCPU_INIT */
+	if (unlikely(!vcpu->arch.target))
+		return -ENOEXEC;
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+	ret = 1;
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	while (ret > 0) {
+		/*
+		 * Check conditions before entering the guest
+		 */
+		cond_resched();
+
+		update_vttbr(vcpu->kvm);
+
+		local_irq_disable();
+
+		/*
+		 * Re-check atomic conditions
+		 */
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			run->exit_reason = KVM_EXIT_INTR;
+		}
+
+		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
+			local_irq_enable();
+			continue;
+		}
+
+		BUG_ON(__vcpu_mode(*vcpu_cpsr(vcpu)) == 0xf);
+
+		/**************************************************************
+		 * Enter the guest
+		 */
+		trace_kvm_entry(vcpu->arch.regs.pc);
+		kvm_guest_enter();
+		vcpu->mode = IN_GUEST_MODE;
+
+		ret = __kvm_vcpu_run(vcpu);
+
+		vcpu->mode = OUTSIDE_GUEST_MODE;
+		kvm_guest_exit();
+		trace_kvm_exit(vcpu->arch.regs.pc);
+		/*
+		 * We may have taken a host interrupt in HYP mode (ie
+		 * while executing the guest). This interrupt is still
+		 * pending, as we haven't serviced it yet!
+		 *
+		 * We're now back in SVC mode, with interrupts
+		 * disabled.  Enabling the interrupts now will have
+		 * the effect of taking the interrupt again, in SVC
+		 * mode this time.
+		 */
+		local_irq_enable();
+
+		/*
+		 * Back from guest
+		 *************************************************************/
+
+		ret = handle_exit(vcpu, run, ret);
+	}
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	return ret;
 }
 
 static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index edf9ed5..cc9448b 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -23,6 +23,12 @@ 
 #include <asm/asm-offsets.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_arm.h>
+#include <asm/vfpmacros.h>
+
+#define VCPU_USR_REG(_reg_nr)	(VCPU_USR_REGS + (_reg_nr * 4))
+#define VCPU_USR_SP		(VCPU_USR_REG(13))
+#define VCPU_FIQ_REG(_reg_nr)	(VCPU_FIQ_REGS + (_reg_nr * 4))
+#define VCPU_FIQ_SPSR		(VCPU_FIQ_REG(7))
 
 	.text
 	.align	PAGE_SHIFT
@@ -34,7 +40,33 @@  __kvm_hyp_code_start:
 @  Flush per-VMID TLBs
 @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
 
+/*
+ * void __kvm_tlb_flush_vmid(struct kvm *kvm);
+ *
+ * We rely on the hardware to broadcast the TLB invalidation to all CPUs
+ * inside the inner-shareable domain (which is the case for all v7
+ * implementations).  If we come across a non-IS SMP implementation, we'll
+ * have to use an IPI based mechanism. Until then, we stick to the simple
+ * hardware assisted version.
+ */
 ENTRY(__kvm_tlb_flush_vmid)
+	hvc	#0			@ Switch to Hyp mode
+	push	{r2, r3}
+
+	add	r0, r0, #KVM_VTTBR
+	ldrd	r2, r3, [r0]
+	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	isb
+	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
+	dsb
+	isb
+	mov	r2, #0
+	mov	r3, #0
+	mcrr	p15, 6, r2, r3, c2	@ Back to VMID #0
+	isb
+
+	pop	{r2, r3}
+	hvc	#0			@ Back to SVC
 	bx	lr
 ENDPROC(__kvm_tlb_flush_vmid)
 
@@ -42,26 +74,702 @@  ENDPROC(__kvm_tlb_flush_vmid)
 @  Flush TLBs and instruction caches of current CPU for all VMIDs
 @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
 
+/*
+ * void __kvm_flush_vm_context(void);
+ */
 ENTRY(__kvm_flush_vm_context)
+	hvc	#0			@ switch to hyp-mode
+
+	mov	r0, #0			@ rn parameter for c15 flushes is SBZ
+	mcr     p15, 4, r0, c8, c7, 4   @ Invalidate Non-secure Non-Hyp TLB
+	mcr     p15, 0, r0, c7, c5, 0   @ Invalidate instruction caches
+	dsb
+	isb
+
+	hvc	#0			@ switch back to svc-mode, see hyp_svc
 	bx	lr
 ENDPROC(__kvm_flush_vm_context)
 
+/* Clobbers {r2-r6} */
+.macro store_vfp_state vfp_base
+	@ The VFPFMRX and VFPFMXR macros are the VMRS and VMSR instructions
+	VFPFMRX	r2, FPEXC
+	@ Make sure VFP is enabled so we can touch the registers.
+	orr	r6, r2, #FPEXC_EN
+	VFPFMXR	FPEXC, r6
+
+	VFPFMRX	r3, FPSCR
+	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
+	beq	1f
+	@ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so
+	@ we only need to save them if FPEXC_EX is set.
+	VFPFMRX r4, FPINST
+	tst	r2, #FPEXC_FP2V
+	VFPFMRX r5, FPINST2, ne		@ vmrsne
+	bic	r6, r2, #FPEXC_EX	@ FPEXC_EX disable
+	VFPFMXR	FPEXC, r6
+1:
+	VFPFSTMIA \vfp_base, r6		@ Save VFP registers
+	stm	\vfp_base, {r2-r5}	@ Save FPEXC, FPSCR, FPINST, FPINST2
+.endm
+
+/* Assume FPEXC_EN is on and FPEXC_EX is off, clobbers {r2-r6} */
+.macro restore_vfp_state vfp_base
+	VFPFLDMIA \vfp_base, r6		@ Load VFP registers
+	ldm	\vfp_base, {r2-r5}	@ Load FPEXC, FPSCR, FPINST, FPINST2
+
+	VFPFMXR FPSCR, r3
+	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
+	beq	1f
+	VFPFMXR FPINST, r4
+	tst	r2, #FPEXC_FP2V
+	VFPFMXR FPINST2, r5, ne
+1:
+	VFPFMXR FPEXC, r2	@ FPEXC	(last, in case !EN)
+.endm
+
 @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
 @  Hypervisor world-switch code
 @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
 
+/* These are simply for the macros to work - value don't have meaning */
+.equ usr, 0
+.equ svc, 1
+.equ abt, 2
+.equ und, 3
+.equ irq, 4
+.equ fiq, 5
+
+.macro store_mode_state base_reg, mode
+	.if \mode == usr
+	mrs	r2, SP_usr
+	mov	r3, lr
+	stmdb	\base_reg!, {r2, r3}
+	.elseif \mode != fiq
+	mrs	r2, SP_\mode
+	mrs	r3, LR_\mode
+	mrs	r4, SPSR_\mode
+	stmdb	\base_reg!, {r2, r3, r4}
+	.else
+	mrs	r2, r8_fiq
+	mrs	r3, r9_fiq
+	mrs	r4, r10_fiq
+	mrs	r5, r11_fiq
+	mrs	r6, r12_fiq
+	mrs	r7, SP_fiq
+	mrs	r8, LR_fiq
+	mrs	r9, SPSR_fiq
+	stmdb	\base_reg!, {r2-r9}
+	.endif
+.endm
+
+.macro load_mode_state base_reg, mode
+	.if \mode == usr
+	ldmia	\base_reg!, {r2, r3}
+	msr	SP_usr, r2
+	mov	lr, r3
+	.elseif \mode != fiq
+	ldmia	\base_reg!, {r2, r3, r4}
+	msr	SP_\mode, r2
+	msr	LR_\mode, r3
+	msr	SPSR_\mode, r4
+	.else
+	ldmia	\base_reg!, {r2-r9}
+	msr	r8_fiq, r2
+	msr	r9_fiq, r3
+	msr	r10_fiq, r4
+	msr	r11_fiq, r5
+	msr	r12_fiq, r6
+	msr	SP_fiq, r7
+	msr	LR_fiq, r8
+	msr	SPSR_fiq, r9
+	.endif
+.endm
+
+/* Reads cp15 registers from hardware and stores them in memory
+ * @vcpu:   If 0, registers are written in-order to the stack,
+ * 	    otherwise to the VCPU struct pointed to by vcpup
+ * @vcpup:  Register pointing to VCPU struct
+ */
+.macro read_cp15_state vcpu=0, vcpup
+	mrc	p15, 0, r2, c1, c0, 0	@ SCTLR
+	mrc	p15, 0, r3, c1, c0, 2	@ CPACR
+	mrc	p15, 0, r4, c2, c0, 2	@ TTBCR
+	mrc	p15, 0, r5, c3, c0, 0	@ DACR
+	mrrc	p15, 0, r6, r7, c2	@ TTBR 0
+	mrrc	p15, 1, r8, r9, c2	@ TTBR 1
+	mrc	p15, 0, r10, c10, c2, 0	@ PRRR
+	mrc	p15, 0, r11, c10, c2, 1	@ NMRR
+	mrc	p15, 2, r12, c0, c0, 0	@ CSSELR
+
+	.if \vcpu == 0
+	push	{r2-r12}		@ Push CP15 registers
+	.else
+	str	r2, [\vcpup, #VCPU_SCTLR]
+	str	r3, [\vcpup, #VCPU_CPACR]
+	str	r4, [\vcpup, #VCPU_TTBCR]
+	str	r5, [\vcpup, #VCPU_DACR]
+	add	\vcpup, \vcpup, #VCPU_TTBR0
+	strd	r6, r7, [\vcpup]
+	add	\vcpup, \vcpup, #(VCPU_TTBR1 - VCPU_TTBR0)
+	strd	r8, r9, [\vcpup]
+	sub	\vcpup, \vcpup, #(VCPU_TTBR1)
+	str	r10, [\vcpup, #VCPU_PRRR]
+	str	r11, [\vcpup, #VCPU_NMRR]
+	str	r12, [\vcpup, #VCPU_CSSELR]
+	.endif
+
+	mrc	p15, 0, r2, c13, c0, 1	@ CID
+	mrc	p15, 0, r3, c13, c0, 2	@ TID_URW
+	mrc	p15, 0, r4, c13, c0, 3	@ TID_URO
+	mrc	p15, 0, r5, c13, c0, 4	@ TID_PRIV
+	mrc	p15, 0, r6, c5, c0, 0	@ DFSR
+	mrc	p15, 0, r7, c5, c0, 1	@ IFSR
+	mrc	p15, 0, r8, c5, c1, 0	@ ADFSR
+	mrc	p15, 0, r9, c5, c1, 1	@ AIFSR
+	mrc	p15, 0, r10, c6, c0, 0	@ DFAR
+	mrc	p15, 0, r11, c6, c0, 2	@ IFAR
+	mrc	p15, 0, r12, c12, c0, 0	@ VBAR
+
+	.if \vcpu == 0
+	push	{r2-r12}		@ Push CP15 registers
+	.else
+	str	r2, [\vcpup, #VCPU_CID]
+	str	r3, [\vcpup, #VCPU_TID_URW]
+	str	r4, [\vcpup, #VCPU_TID_URO]
+	str	r5, [\vcpup, #VCPU_TID_PRIV]
+	str	r6, [\vcpup, #VCPU_DFSR]
+	str	r7, [\vcpup, #VCPU_IFSR]
+	str	r8, [\vcpup, #VCPU_ADFSR]
+	str	r9, [\vcpup, #VCPU_AIFSR]
+	str	r10, [\vcpup, #VCPU_DFAR]
+	str	r11, [\vcpup, #VCPU_IFAR]
+	str	r12, [\vcpup, #VCPU_VBAR]
+	.endif
+.endm
+
+/* Reads cp15 registers from memory and writes them to hardware
+ * @vcpu:   If 0, registers are read in-order from the stack,
+ * 	    otherwise from the VCPU struct pointed to by vcpup
+ * @vcpup:  Register pointing to VCPU struct
+ */
+.macro write_cp15_state vcpu=0, vcpup
+	.if \vcpu == 0
+	pop	{r2-r12}
+	.else
+	ldr	r2, [\vcpup, #VCPU_CID]
+	ldr	r3, [\vcpup, #VCPU_TID_URW]
+	ldr	r4, [\vcpup, #VCPU_TID_URO]
+	ldr	r5, [\vcpup, #VCPU_TID_PRIV]
+	ldr	r6, [\vcpup, #VCPU_DFSR]
+	ldr	r7, [\vcpup, #VCPU_IFSR]
+	ldr	r8, [\vcpup, #VCPU_ADFSR]
+	ldr	r9, [\vcpup, #VCPU_AIFSR]
+	ldr	r10, [\vcpup, #VCPU_DFAR]
+	ldr	r11, [\vcpup, #VCPU_IFAR]
+	ldr	r12, [\vcpup, #VCPU_VBAR]
+	.endif
+
+	mcr	p15, 0, r2, c13, c0, 1	@ CID
+	mcr	p15, 0, r3, c13, c0, 2	@ TID_URW
+	mcr	p15, 0, r4, c13, c0, 3	@ TID_URO
+	mcr	p15, 0, r5, c13, c0, 4	@ TID_PRIV
+	mcr	p15, 0, r6, c5, c0, 0	@ DFSR
+	mcr	p15, 0, r7, c5, c0, 1	@ IFSR
+	mcr	p15, 0, r8, c5, c1, 0	@ ADFSR
+	mcr	p15, 0, r9, c5, c1, 1	@ AIFSR
+	mcr	p15, 0, r10, c6, c0, 0	@ DFAR
+	mcr	p15, 0, r11, c6, c0, 2	@ IFAR
+	mcr	p15, 0, r12, c12, c0, 0	@ VBAR
+
+	.if \vcpu == 0
+	pop	{r2-r12}
+	.else
+	ldr	r2, [\vcpup, #VCPU_SCTLR]
+	ldr	r3, [\vcpup, #VCPU_CPACR]
+	ldr	r4, [\vcpup, #VCPU_TTBCR]
+	ldr	r5, [\vcpup, #VCPU_DACR]
+	add	\vcpup, \vcpup, #VCPU_TTBR0
+	ldrd	r6, r7, [\vcpup]
+	add	\vcpup, \vcpup, #(VCPU_TTBR1 - VCPU_TTBR0)
+	ldrd	r8, r9, [\vcpup]
+	sub	\vcpup, \vcpup, #(VCPU_TTBR1)
+	ldr	r10, [\vcpup, #VCPU_PRRR]
+	ldr	r11, [\vcpup, #VCPU_NMRR]
+	ldr	r12, [\vcpup, #VCPU_CSSELR]
+	.endif
+
+	mcr	p15, 0, r2, c1, c0, 0	@ SCTLR
+	mcr	p15, 0, r3, c1, c0, 2	@ CPACR
+	mcr	p15, 0, r4, c2, c0, 2	@ TTBCR
+	mcr	p15, 0, r5, c3, c0, 0	@ DACR
+	mcrr	p15, 0, r6, r7, c2	@ TTBR 0
+	mcrr	p15, 1, r8, r9, c2	@ TTBR 1
+	mcr	p15, 0, r10, c10, c2, 0	@ PRRR
+	mcr	p15, 0, r11, c10, c2, 1	@ NMRR
+	mcr	p15, 2, r12, c0, c0, 0	@ CSSELR
+.endm
+
+/* Configures the HSTR (Hyp System Trap Register) on entry/return
+ * (hardware reset value is 0) */
+.macro set_hstr entry
+	mrc	p15, 4, r2, c1, c1, 3
+	ldr	r3, =HSTR_T(15)
+	.if \entry == 1
+	orr	r2, r2, r3		@ Trap CR{15}
+	.else
+	bic	r2, r2, r3		@ Don't trap any CRx accesses
+	.endif
+	mcr	p15, 4, r2, c1, c1, 3
+.endm
+
+/* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
+ * (hardware reset value is 0). Keep previous value in r2. */
+.macro set_hcptr entry, mask
+	mrc	p15, 4, r2, c1, c1, 2
+	ldr	r3, =\mask
+	.if \entry == 1
+	orr	r3, r2, r3		@ Trap coproc-accesses defined in mask
+	.else
+	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
+	.endif
+	mcr	p15, 4, r3, c1, c1, 2
+.endm
+
+/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
+ * (hardware reset value is 0) */
+.macro set_hdcr entry
+	mrc	p15, 4, r2, c1, c1, 1
+	ldr	r3, =(HDCR_TPM|HDCR_TPMCR)
+	.if \entry == 1
+	orr	r2, r2, r3		@ Trap some perfmon accesses
+	.else
+	bic	r2, r2, r3		@ Don't trap any perfmon accesses
+	.endif
+	mcr	p15, 4, r2, c1, c1, 1
+.endm
+
+/* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
+.macro configure_hyp_role entry, vcpu_ptr
+	mrc	p15, 4, r2, c1, c1, 0	@ HCR
+	bic	r2, r2, #HCR_VIRT_EXCP_MASK
+	ldr	r3, =HCR_GUEST_MASK
+	.if \entry == 1
+	orr	r2, r2, r3
+	ldr	r3, [\vcpu_ptr, #VCPU_IRQ_LINES]
+	orr	r2, r2, r3
+	.else
+	bic	r2, r2, r3
+	.endif
+	mcr	p15, 4, r2, c1, c1, 0
+.endm
+
+.macro load_vcpu reg
+	mrc	p15, 4, \reg, c13, c0, 2	@ HTPIDR
+.endm
+
+@ Arguments:
+@  r0: pointer to vcpu struct
 ENTRY(__kvm_vcpu_run)
-	bx	lr
+	hvc	#0			@ switch to hyp-mode
+
+	@ Save the vcpu pointer
+	mcr	p15, 4, r0, c13, c0, 2	@ HTPIDR
+
+	@ Now we're in Hyp-mode and lr_usr, spsr_hyp are on the stack
+	mrs	r2, sp_usr
+	push	{r2}			@ Push r13_usr
+	push	{r4-r12}		@ Push r4-r12
+
+	store_mode_state sp, svc
+	store_mode_state sp, abt
+	store_mode_state sp, und
+	store_mode_state sp, irq
+	store_mode_state sp, fiq
+
+	@ Store hardware CP15 state and load guest state
+	read_cp15_state
+	write_cp15_state 1, r0
+
+	@ If the host kernel has not been configured with VFPv3 support,
+	@ then it is safer if we deny guests from using it as well.
+#ifdef CONFIG_VFPv3
+	@ Set FPEXC_EN so the guest doesn't trap floating point instructions
+	VFPFMRX r2, FPEXC		@ VMRS
+	push	{r2}
+	orr	r2, r2, #FPEXC_EN
+	VFPFMXR FPEXC, r2		@ VMSR
+#endif
+
+	@ Configure Hyp-role
+	configure_hyp_role 1, r0
+
+	@ Trap coprocessor CRx accesses
+	set_hstr 1
+	set_hcptr 1, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hdcr 1
+
+	@ Write configured ID register into MIDR alias
+	ldr	r1, [r0, #VCPU_MIDR]
+	mcr	p15, 4, r1, c0, c0, 0
+
+	@ Write guest view of MPIDR into VMPIDR
+	ldr	r1, [r0, #VCPU_MPIDR]
+	mcr	p15, 4, r1, c0, c0, 5
+
+	@ Load guest registers
+	add	r0, r0, #(VCPU_USR_SP)
+	load_mode_state r0, usr
+	load_mode_state r0, svc
+	load_mode_state r0, abt
+	load_mode_state r0, und
+	load_mode_state r0, irq
+	load_mode_state r0, fiq
+
+	@ Load return state (r0 now points to vcpu->arch.regs.pc)
+	ldmia	r0, {r2, r3}
+	msr	ELR_hyp, r2
+	msr	SPSR_cxsf, r3
+
+	@ Set up guest memory translation
+	sub	r1, r0, #(VCPU_PC - VCPU_KVM)	@ r1 points to kvm struct
+	ldr	r1, [r1]
+	add	r1, r1, #KVM_VTTBR
+	ldrd	r2, r3, [r1]
+	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+
+	@ Load remaining registers and do the switch
+	sub	r0, r0, #(VCPU_PC - VCPU_USR_REGS)
+	ldmia	r0, {r0-r12}
+	clrex				@ Clear exclusive monitor
+	eret
+
+__kvm_vcpu_return:
+	@ Set VMID == 0
+	mov	r2, #0
+	mov	r3, #0
+	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+
+	@ Store return state
+	mrs	r2, ELR_hyp
+	mrs	r3, spsr
+	str	r2, [r1, #VCPU_PC]
+	str	r3, [r1, #VCPU_CPSR]
+
+	@ Store guest registers
+	add	r1, r1, #(VCPU_FIQ_SPSR + 4)
+	store_mode_state r1, fiq
+	store_mode_state r1, irq
+	store_mode_state r1, und
+	store_mode_state r1, abt
+	store_mode_state r1, svc
+	store_mode_state r1, usr
+	sub	r1, r1, #(VCPU_USR_REG(13))
+
+	@ Don't trap coprocessor accesses for host kernel
+	set_hstr 0
+	set_hdcr 0
+	set_hcptr 0, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+
+#ifdef CONFIG_VFPv3
+	@ Save floating point registers we if let guest use them.
+	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	bne	after_vfp_restore
 
+	@ Switch VFP/NEON hardware state to the host's
+	add	r7, r1, #VCPU_VFP_GUEST
+	store_vfp_state r7
+	add	r7, r1, #VCPU_VFP_HOST
+	ldr	r7, [r7]
+	restore_vfp_state r7
+
+after_vfp_restore:
+	@ Restore FPEXC_EN which we clobbered on entry
+	pop	{r2}
+	VFPFMXR FPEXC, r2
+#endif
+
+	@ Reset Hyp-role
+	configure_hyp_role 0, r1
+
+	@ Let host read hardware MIDR
+	mrc	p15, 0, r2, c0, c0, 0
+	mcr	p15, 4, r2, c0, c0, 0
+
+	@ Back to hardware MPIDR
+	mrc	p15, 0, r2, c0, c0, 5
+	mcr	p15, 4, r2, c0, c0, 5
+
+	@ Store guest CP15 state and restore host state
+	read_cp15_state 1, r1
+	write_cp15_state
+
+	load_mode_state sp, fiq
+	load_mode_state sp, irq
+	load_mode_state sp, und
+	load_mode_state sp, abt
+	load_mode_state sp, svc
+
+	pop	{r4-r12}		@ Pop r4-r12
+	pop	{r2}			@ Pop r13_usr
+	msr	sp_usr, r2
+
+	hvc	#0			@ switch back to svc-mode, see hyp_svc
+
+	clrex				@ Clear exclusive monitor
+	bx	lr			@ return to IOCTL
 
 @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
 @  Hypervisor exception vector and handlers
 @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
 
+/*
+ * The KVM/ARM Hypervisor ABI is defined as follows:
+ *
+ * Entry to Hyp mode from the host kernel will happen _only_ when an HVC
+ * instruction is issued since all traps are disabled when running the host
+ * kernel as per the Hyp-mode initialization at boot time.
+ *
+ * HVC instructions cause a trap to the vector page + offset 0x18 (see hyp_hvc
+ * below) when the HVC instruction is called from SVC mode (i.e. a guest or the
+ * host kernel) and they cause a trap to the vector page + offset 0xc when HVC
+ * instructions are called from within Hyp-mode.
+ *
+ * Hyp-ABI: Switching from host kernel to Hyp-mode:
+ *    Switching to Hyp mode is done through a simple HVC #0 instruction. The
+ *    exception vector code will check that the HVC comes from VMID==0 and if
+ *    so will store the necessary state on the Hyp stack, which will look like
+ *    this (growing downwards, see the hyp_hvc handler):
+ *      ...
+ *      stack_page + 4: spsr (Host-SVC cpsr)
+ *      stack_page    : lr_usr
+ *      --------------: stack bottom
+ *
+ * Hyp-ABI: Switching from Hyp-mode to host kernel SVC mode:
+ *    When returning from Hyp mode to SVC mode, another HVC instruction is
+ *    executed from Hyp mode, which is taken in the hyp_svc handler. The
+ *    bottom of the Hyp is derived from the Hyp stack pointer (only a single
+ *    page aligned stack is used per CPU) and the initial SVC registers are
+ *    used to restore the host state.
+ *
+ * Hyp-ABI: Change the HVBAR:
+ *    When removing the KVM module we want to reset our hold on Hyp mode.
+ *    This is accomplished by calling HVC #0xff from the host kernel
+ *    (VMID==0) with the desired new HVBAR in r0.
+ *
+ * Note that the above is used to execute code in Hyp-mode from a host-kernel
+ * point of view, and is a different concept from performing a world-switch and
+ * executing guest code SVC mode (with a VMID != 0).
+ */
+
+@ Handle undef, svc, pabt, or dabt by crashing with a user notice
+.macro bad_exception exception_code, panic_str
+	mrrc	p15, 6, r2, r3, c2	@ Read VTTBR
+	lsr	r3, r3, #16
+	ands	r3, r3, #0xff
+
+	@ COND:neq means we're probably in the guest and we can try fetching
+	@ the vcpu pointer and stuff off the stack and keep our fingers crossed
+	beq	99f
+	mov	r0, #\exception_code
+	load_vcpu	r1		@ Load VCPU pointer
+	.if \exception_code == ARM_EXCEPTION_DATA_ABORT
+	mrc	p15, 4, r2, c5, c2, 0	@ HSR
+	mrc	p15, 4, r3, c6, c0, 0	@ HDFAR
+	str	r2, [r1, #VCPU_HSR]
+	str	r3, [r1, #VCPU_HDFAR]
+	.endif
+	.if \exception_code == ARM_EXCEPTION_PREF_ABORT
+	mrc	p15, 4, r2, c5, c2, 0	@ HSR
+	mrc	p15, 4, r3, c6, c0, 2	@ HIFAR
+	str	r2, [r1, #VCPU_HSR]
+	str	r3, [r1, #VCPU_HIFAR]
+	.endif
+	mrs	r2, ELR_hyp
+	str	r2, [r1, #VCPU_HYP_PC]
+	b	__kvm_vcpu_return
+
+	@ We were in the host already
+99:	hvc	#0	@ switch to SVC mode
+	ldr	r0, \panic_str
+	mrs	r1, ELR_hyp
+	b	panic
+
+.endm
+
+	.text
+
 	.align 5
 __kvm_hyp_vector:
 	.globl __kvm_hyp_vector
-	nop
+
+	@ Hyp-mode exception vector
+	W(b)	hyp_reset
+	W(b)	hyp_undef
+	W(b)	hyp_svc
+	W(b)	hyp_pabt
+	W(b)	hyp_dabt
+	W(b)	hyp_hvc
+	W(b)	hyp_irq
+	W(b)	hyp_fiq
+
+	.align
+hyp_reset:
+	b	hyp_reset
+
+	.align
+hyp_undef:
+	bad_exception ARM_EXCEPTION_UNDEFINED, und_die_str
+
+	.align
+hyp_svc:
+	@ Can only get here if HVC or SVC is called from Hyp, mode which means
+	@ we want to change mode back to SVC mode.
+	push	{r12}
+	mov	r12, sp
+	bic	r12, r12, #0x0ff
+	bic	r12, r12, #0xf00
+	ldr	lr, [r12, #4]
+	msr	SPSR_csxf, lr
+	ldr	lr, [r12]
+	pop	{r12}
+	eret
+
+	.align
+hyp_pabt:
+	bad_exception ARM_EXCEPTION_PREF_ABORT, pabt_die_str
+
+	.align
+hyp_dabt:
+	bad_exception ARM_EXCEPTION_DATA_ABORT, dabt_die_str
+
+	.align
+hyp_hvc:
+	@ Getting here is either becuase of a trap from a guest or from calling
+	@ HVC from the host kernel, which means "switch to Hyp mode".
+	push	{r0, r1, r2}
+
+	@ Check syndrome register
+	mrc	p15, 4, r0, c5, c2, 0	@ HSR
+	lsr	r1, r0, #HSR_EC_SHIFT
+#ifdef CONFIG_VFPv3
+	cmp	r1, #HSR_EC_CP_0_13
+	beq	switch_to_guest_vfp
+#endif
+	cmp	r1, #HSR_EC_HVC
+	bne	guest_trap		@ Not HVC instr.
+
+	@ Let's check if the HVC came from VMID 0 and allow simple
+	@ switch to Hyp mode
+	mrrc    p15, 6, r1, r2, c2
+	lsr     r2, r2, #16
+	and     r2, r2, #0xff
+	cmp     r2, #0
+	bne	guest_trap		@ Guest called HVC
+
+	@ HVC came from host. Check if this is a request to
+	@ switch HVBAR to another set of vectors (kvm_exit).
+	lsl	r0, r0, #16
+	lsr	r0, r0, #16
+	cmp	r0, #0xff
+	bne	host_switch_to_hyp	@ Not HVC #0xff
+
+	@ We're switching away from this hypervisor, let's blow the TLBs.
+	pop	{r0, r1, r2}
+	mcr	p15, 4, r0, c12, c0, 0  @ HVBAR
+	mcr	p15, 4, r0, c8, c7, 0   @ Flush Hyp TLB, r0 ignored
+	eret
+
+host_switch_to_hyp:
+	@ Store lr_usr,spsr (svc cpsr) on bottom of stack
+	mov	r1, sp
+	bic	r1, r1, #0x0ff
+	bic	r1, r1, #0xf00
+	str	lr, [r1]
+	mrs	lr, spsr
+	str	lr, [r1, #4]
+
+	pop	{r0, r1, r2}
+
+	@ Return to caller in Hyp mode
+	mrs	lr, ELR_hyp
+	mov	pc, lr
+
+guest_trap:
+	load_vcpu	r1		@ Load VCPU pointer
+	str	r0, [r1, #VCPU_HSR]
+	add	r1, r1, #VCPU_USR_REG(3)
+	stmia	r1, {r3-r12}
+	sub	r1, r1, #(VCPU_USR_REG(3) - VCPU_USR_REG(0))
+	pop	{r3, r4, r5}
+	stmia	r1, {r3, r4, r5}
+	sub	r1, r1, #VCPU_USR_REG(0)
+
+	@ Check if we need the fault information
+	lsr	r2, r0, #HSR_EC_SHIFT
+	cmp	r2, #HSR_EC_IABT
+	beq	2f
+	cmpne	r2, #HSR_EC_DABT
+	bne	1f
+
+2:	mrc	p15, 4, r2, c6, c0, 0	@ HDFAR
+	mrc	p15, 4, r3, c6, c0, 2	@ HIFAR
+	mrc	p15, 4, r4, c6, c0, 4	@ HPFAR
+	add	r5, r1, #VCPU_HDFAR
+	stmia	r5, {r2, r3, r4}
+
+1:	mov	r0, #ARM_EXCEPTION_HVC
+	b	__kvm_vcpu_return
+
+@ If VFPv3 support is not available, then we will not switch the VFP
+@ registers; however cp10 and cp11 accesses will still trap and fallback
+@ to the regular coprocessor emulation code, which currently will
+@ inject an undefined exception to the guest.
+#ifdef CONFIG_VFPv3
+switch_to_guest_vfp:
+	load_vcpu	r0		@ Load VCPU pointer
+	push	{r3-r7}
+
+	@ NEON/VFP used.  Turn on VFP access.
+	set_hcptr 0, (HCPTR_TCP(10) | HCPTR_TCP(11))
+
+	@ Switch VFP/NEON hardware state to the guest's
+	add	r7, r0, #VCPU_VFP_HOST
+	ldr	r7, [r7]
+	store_vfp_state r7
+	add	r7, r0, #VCPU_VFP_GUEST
+	restore_vfp_state r7
+
+	pop	{r3-r7}
+	pop	{r0-r2}
+	eret
+#endif
+
+	.align
+hyp_irq:
+	push	{r0}
+	load_vcpu	r0		@ Load VCPU pointer
+	add	r0, r0, #(VCPU_USR_REG(1))
+	stmia	r0, {r1-r12}
+	pop	{r0}
+	load_vcpu	r1		@ Load VCPU pointer again
+	str	r0, [r1, #VCPU_USR_REG(0)]
+
+	mov	r0, #ARM_EXCEPTION_IRQ
+	b	__kvm_vcpu_return
+
+	.align
+hyp_fiq:
+	b	hyp_fiq
+
+	.ltorg
+
+und_die_str:
+	.ascii	"unexpected undefined exception in Hyp mode at: %#08x"
+pabt_die_str:
+	.ascii	"unexpected prefetch abort in Hyp mode at: %#08x"
+dabt_die_str:
+	.ascii	"unexpected data abort in Hyp mode at: %#08x"
 
 /*
  * The below lines makes sure the HYP mode code fits in a single page (the