ARM: KVM: Remove the old world switch

As we now have a full reimplementation of the world switch, it is
time to kiss the old stuff goodbye. I'm not sure we'll miss it.

Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

2 files changed, 1 insertions, 1128 deletions

diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 01eb169f38f6..b1bd316f14c0 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -17,198 +17,8 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/const.h>
-#include <asm/unified.h>
-#include <asm/page.h>
-#include <asm/ptrace.h>
-#include <asm/asm-offsets.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_arm.h>
-#include <asm/vfpmacros.h>
-#include "interrupts_head.S"
 
 	.text
-	.pushsection	.hyp.text, "ax"
-
-/********************************************************************
- * Flush per-VMID TLBs
- *
- * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
- *
- * 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.
- *
- * As v7 does not support flushing per IPA, just nuke the whole TLB
- * instead, ignoring the ipa value.
- */
-ENTRY(__kvm_tlb_flush_vmid_ipa)
-	push	{r2, r3}
-
-	dsb	ishst
-	add	r0, r0, #KVM_VTTBR
-	ldrd	r2, r3, [r0]
-	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
-	isb
-	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
-	dsb	ish
-	isb
-	mov	r2, #0
-	mov	r3, #0
-	mcrr	p15, 6, r2, r3, c2	@ Back to VMID #0
-	isb				@ Not necessary if followed by eret
-
-	pop	{r2, r3}
-	bx	lr
-ENDPROC(__kvm_tlb_flush_vmid_ipa)
-
-/**
- * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
- *
- * Reuses __kvm_tlb_flush_vmid_ipa() for ARMv7, without passing address
- * parameter
- */
-
-ENTRY(__kvm_tlb_flush_vmid)
-	b	__kvm_tlb_flush_vmid_ipa
-ENDPROC(__kvm_tlb_flush_vmid)
-
-/********************************************************************
- * Flush TLBs and instruction caches of all CPUs inside the inner-shareable
- * domain, for all VMIDs
- *
- * void __kvm_flush_vm_context(void);
- */
-ENTRY(__kvm_flush_vm_context)
-	mov	r0, #0			@ rn parameter for c15 flushes is SBZ
-
-	/* Invalidate NS Non-Hyp TLB Inner Shareable (TLBIALLNSNHIS) */
-	mcr     p15, 4, r0, c8, c3, 4
-	/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
-	mcr     p15, 0, r0, c7, c1, 0
-	dsb	ish
-	isb				@ Not necessary if followed by eret
-
-	bx	lr
-ENDPROC(__kvm_flush_vm_context)
-
-
-/********************************************************************
- *  Hypervisor world-switch code
- *
- *
- * int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
- */
-ENTRY(__kvm_vcpu_run)
-	@ Save the vcpu pointer
-	mcr	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
-
-	save_host_regs
-
-	restore_vgic_state
-	restore_timer_state
-
-	@ Store hardware CP15 state and load guest state
-	read_cp15_state store_to_vcpu = 0
-	write_cp15_state read_from_vcpu = 1
-
-	@ 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 vmentry
-
-	@ Trap coprocessor CRx accesses
-	set_hstr vmentry
-	set_hcptr vmentry, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
-	set_hdcr vmentry
-
-	@ Write configured ID register into MIDR alias
-	ldr	r1, [vcpu, #VCPU_MIDR]
-	mcr	p15, 4, r1, c0, c0, 0
-
-	@ Write guest view of MPIDR into VMPIDR
-	ldr	r1, [vcpu, #CP15_OFFSET(c0_MPIDR)]
-	mcr	p15, 4, r1, c0, c0, 5
-
-	@ Set up guest memory translation
-	ldr	r1, [vcpu, #VCPU_KVM]
-	add	r1, r1, #KVM_VTTBR
-	ldrd	r2, r3, [r1]
-	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
-
-	@ We're all done, just restore the GPRs and go to the guest
-	restore_guest_regs
-	clrex				@ Clear exclusive monitor
-	eret
-
-__kvm_vcpu_return:
-	/*
-	 * return convention:
-	 * guest r0, r1, r2 saved on the stack
-	 * r0: vcpu pointer
-	 * r1: exception code
-	 */
-	save_guest_regs
-
-	@ Set VMID == 0
-	mov	r2, #0
-	mov	r3, #0
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
-
-	@ Don't trap coprocessor accesses for host kernel
-	set_hstr vmexit
-	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
-
-#ifdef CONFIG_VFPv3
-	@ Switch VFP/NEON hardware state to the host's
-	add	r7, vcpu, #(VCPU_GUEST_CTXT + CPU_CTXT_VFP)
-	store_vfp_state r7
-	add	r7, vcpu, #VCPU_HOST_CTXT
-	ldr	r7, [r7]
-	add	r7, r7, #CPU_CTXT_VFP
-	restore_vfp_state r7
-
-after_vfp_restore:
-	@ Restore FPEXC_EN which we clobbered on entry
-	pop	{r2}
-	VFPFMXR FPEXC, r2
-#else
-after_vfp_restore:
-#endif
-
-	@ Reset Hyp-role
-	configure_hyp_role vmexit
-
-	@ 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 store_to_vcpu = 1
-	write_cp15_state read_from_vcpu = 0
-
-	save_timer_state
-	save_vgic_state
-
-	restore_host_regs
-	clrex				@ Clear exclusive monitor
-	mov	r0, r1			@ Return the return code
-	bx	lr			@ return to IOCTL
 
 /********************************************************************
  *  Call function in Hyp mode
@@ -239,281 +49,4 @@ after_vfp_restore:
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	bx	lr
-
-/********************************************************************
- * 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 0x14 (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 0x8 when HVC
- * instructions are called from within Hyp-mode.
- *
- * Hyp-ABI: Calling HYP-mode functions from host (in SVC 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 push the necessary state (SPSR, lr_usr) on the Hyp stack.
- *    - r0 contains a pointer to a HYP function
- *    - r1, r2, and r3 contain arguments to the above function.
- *    - The HYP function will be called with its arguments in r0, r1 and r2.
- *    On HYP function return, we return directly to SVC.
- *
- * 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
-	push	{r0-r2}
-	mrrc	p15, 6, r0, r1, c2	@ Read VTTBR
-	lsr	r1, r1, #16
-	ands	r1, r1, #0xff
-	beq	99f
-
-	load_vcpu			@ Load VCPU pointer
-	.if \exception_code == ARM_EXCEPTION_DATA_ABORT
-	mrc	p15, 4, r2, c5, c2, 0	@ HSR
-	mrc	p15, 4, r1, c6, c0, 0	@ HDFAR
-	str	r2, [vcpu, #VCPU_HSR]
-	str	r1, [vcpu, #VCPU_HxFAR]
-	.endif
-	.if \exception_code == ARM_EXCEPTION_PREF_ABORT
-	mrc	p15, 4, r2, c5, c2, 0	@ HSR
-	mrc	p15, 4, r1, c6, c0, 2	@ HIFAR
-	str	r2, [vcpu, #VCPU_HSR]
-	str	r1, [vcpu, #VCPU_HxFAR]
-	.endif
-	mov	r1, #\exception_code
-	b	__kvm_vcpu_return
-
-	@ We were in the host already. Let's craft a panic-ing return to SVC.
-99:	mrs	r2, cpsr
-	bic	r2, r2, #MODE_MASK
-	orr	r2, r2, #SVC_MODE
-THUMB(	orr	r2, r2, #PSR_T_BIT	)
-	msr	spsr_cxsf, r2
-	mrs	r1, ELR_hyp
-	ldr	r2, =panic
-	msr	ELR_hyp, r2
-	ldr	r0, =\panic_str
-	clrex				@ Clear exclusive monitor
-	eret
-.endm
-
-	.align 5
-__kvm_hyp_vector:
-	.globl __kvm_hyp_vector
-
-	@ 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:
-	bad_exception ARM_EXCEPTION_HVC, svc_die_str
-
-	.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, r1, c5, c2, 0	@ HSR
-	lsr	r0, r1, #HSR_EC_SHIFT
-	cmp	r0, #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, r0, r2, c2
-	lsr     r2, r2, #16
-	and     r2, r2, #0xff
-	cmp     r2, #0
-	bne	guest_trap		@ Guest called HVC
-
-	/*
-	 * Getting here means host called HVC, we shift parameters and branch
-	 * to Hyp function.
-	 */
-	pop	{r0, r1, r2}
-
-	/* Check for __hyp_get_vectors */
-	cmp	r0, #-1
-	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
-	beq	1f
-
-	push	{lr}
-	mrs	lr, SPSR
-	push	{lr}
-
-	mov	lr, r0
-	mov	r0, r1
-	mov	r1, r2
-	mov	r2, r3
-
-THUMB(	orr	lr, #1)
-	blx	lr			@ Call the HYP function
-
-	pop	{lr}
-	msr	SPSR_csxf, lr
-	pop	{lr}
-1:	eret
-
-guest_trap:
-	load_vcpu			@ Load VCPU pointer to r0
-	str	r1, [vcpu, #VCPU_HSR]
-
-	@ Check if we need the fault information
-	lsr	r1, r1, #HSR_EC_SHIFT
-#ifdef CONFIG_VFPv3
-	cmp	r1, #HSR_EC_CP_0_13
-	beq	switch_to_guest_vfp
-#endif
-	cmp	r1, #HSR_EC_IABT
-	mrceq	p15, 4, r2, c6, c0, 2	@ HIFAR
-	beq	2f
-	cmp	r1, #HSR_EC_DABT
-	bne	1f
-	mrc	p15, 4, r2, c6, c0, 0	@ HDFAR
-
-2:	str	r2, [vcpu, #VCPU_HxFAR]
-
-	/*
-	 * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode:
-	 *
-	 * Abort on the stage 2 translation for a memory access from a
-	 * Non-secure PL1 or PL0 mode:
-	 *
-	 * For any Access flag fault or Translation fault, and also for any
-	 * Permission fault on the stage 2 translation of a memory access
-	 * made as part of a translation table walk for a stage 1 translation,
-	 * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR
-	 * is UNKNOWN.
-	 */
-
-	/* Check for permission fault, and S1PTW */
-	mrc	p15, 4, r1, c5, c2, 0	@ HSR
-	and	r0, r1, #HSR_FSC_TYPE
-	cmp	r0, #FSC_PERM
-	tsteq	r1, #(1 << 7)		@ S1PTW
-	mrcne	p15, 4, r2, c6, c0, 4	@ HPFAR
-	bne	3f
-
-	/* Preserve PAR */
-	mrrc	p15, 0, r0, r1, c7	@ PAR
-	push	{r0, r1}
-
-	/* Resolve IPA using the xFAR */
-	mcr	p15, 0, r2, c7, c8, 0	@ ATS1CPR
-	isb
-	mrrc	p15, 0, r0, r1, c7	@ PAR
-	tst	r0, #1
-	bne	4f			@ Failed translation
-	ubfx	r2, r0, #12, #20
-	lsl	r2, r2, #4
-	orr	r2, r2, r1, lsl #24
-
-	/* Restore PAR */
-	pop	{r0, r1}
-	mcrr	p15, 0, r0, r1, c7	@ PAR
-
-3:	load_vcpu			@ Load VCPU pointer to r0
-	str	r2, [r0, #VCPU_HPFAR]
-
-1:	mov	r1, #ARM_EXCEPTION_HVC
-	b	__kvm_vcpu_return
-
-4:	pop	{r0, r1}		@ Failed translation, return to guest
-	mcrr	p15, 0, r0, r1, c7	@ PAR
-	clrex
-	pop	{r0, r1, r2}
-	eret
-
-/*
- * 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:
-	push	{r3-r7}
-
-	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
-
-	@ Switch VFP/NEON hardware state to the guest's
-	add	r7, r0, #VCPU_HOST_CTXT
-	ldr	r7, [r7]
-	add	r7, r7, #CPU_CTXT_VFP
-	store_vfp_state r7
-	add	r7, r0, #(VCPU_GUEST_CTXT + CPU_CTXT_VFP)
-	restore_vfp_state r7
-
-	pop	{r3-r7}
-	pop	{r0-r2}
-	clrex
-	eret
-#endif
-
-	.align
-hyp_irq:
-	push	{r0, r1, r2}
-	mov	r1, #ARM_EXCEPTION_IRQ
-	load_vcpu			@ Load VCPU pointer to r0
-	b	__kvm_vcpu_return
-
-	.align
-hyp_fiq:
-	b	hyp_fiq
-
-	.ltorg
-
-	.popsection
-
-	.pushsection ".rodata"
-
-und_die_str:
-	.ascii	"unexpected undefined exception in Hyp mode at: %#08x\n"
-pabt_die_str:
-	.ascii	"unexpected prefetch abort in Hyp mode at: %#08x\n"
-dabt_die_str:
-	.ascii	"unexpected data abort in Hyp mode at: %#08x\n"
-svc_die_str:
-	.ascii	"unexpected HVC/SVC trap in Hyp mode at: %#08x\n"
-
-	.popsection
+ENDPROC(kvm_call_hyp)
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
deleted file mode 100644
index e0943cb80ab3..000000000000
--- a/arch/arm/kvm/interrupts_head.S
+++ /dev/null
@@ -1,660 +0,0 @@
-#include <linux/irqchip/arm-gic.h>
-#include <asm/assembler.h>
-
-/* Compat macro, until we get rid of this file entierely */
-#define VCPU_GP_REGS		(VCPU_GUEST_CTXT + CPU_CTXT_GP_REGS)
-#define VCPU_USR_REGS		(VCPU_GP_REGS + GP_REGS_USR)
-#define VCPU_SVC_REGS		(VCPU_GP_REGS + GP_REGS_SVC)
-#define VCPU_ABT_REGS		(VCPU_GP_REGS + GP_REGS_ABT)
-#define VCPU_UND_REGS		(VCPU_GP_REGS + GP_REGS_UND)
-#define VCPU_IRQ_REGS		(VCPU_GP_REGS + GP_REGS_IRQ)
-#define VCPU_FIQ_REGS		(VCPU_GP_REGS + GP_REGS_FIQ)
-#define VCPU_PC			(VCPU_GP_REGS + GP_REGS_PC)
-#define VCPU_CPSR		(VCPU_GP_REGS + GP_REGS_CPSR)
-
-#define VCPU_USR_REG(_reg_nr)	(VCPU_USR_REGS + (_reg_nr * 4))
-#define VCPU_USR_SP		(VCPU_USR_REG(13))
-#define VCPU_USR_LR		(VCPU_USR_REG(14))
-#define VCPU_CP15_BASE		(VCPU_GUEST_CTXT + CPU_CTXT_CP15)
-#define CP15_OFFSET(_cp15_reg_idx) (VCPU_CP15_BASE + (_cp15_reg_idx * 4))
-
-/*
- * Many of these macros need to access the VCPU structure, which is always
- * held in r0. These macros should never clobber r1, as it is used to hold the
- * exception code on the return path (except of course the macro that switches
- * all the registers before the final jump to the VM).
- */
-vcpu	.req	r0		@ vcpu pointer always in r0
-
-/* 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
-
-/* 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 push_host_regs_mode mode
-	mrs	r2, SP_\mode
-	mrs	r3, LR_\mode
-	mrs	r4, SPSR_\mode
-	push	{r2, r3, r4}
-.endm
-
-/*
- * Store all host persistent registers on the stack.
- * Clobbers all registers, in all modes, except r0 and r1.
- */
-.macro save_host_regs
-	/* Hyp regs. Only ELR_hyp (SPSR_hyp already saved) */
-	mrs	r2, ELR_hyp
-	push	{r2}
-
-	/* usr regs */
-	push	{r4-r12}	@ r0-r3 are always clobbered
-	mrs	r2, SP_usr
-	mov	r3, lr
-	push	{r2, r3}
-
-	push_host_regs_mode svc
-	push_host_regs_mode abt
-	push_host_regs_mode und
-	push_host_regs_mode irq
-
-	/* fiq regs */
-	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
-	push	{r2-r9}
-.endm
-
-.macro pop_host_regs_mode mode
-	pop	{r2, r3, r4}
-	msr	SP_\mode, r2
-	msr	LR_\mode, r3
-	msr	SPSR_\mode, r4
-.endm
-
-/*
- * Restore all host registers from the stack.
- * Clobbers all registers, in all modes, except r0 and r1.
- */
-.macro restore_host_regs
-	pop	{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
-
-	pop_host_regs_mode irq
-	pop_host_regs_mode und
-	pop_host_regs_mode abt
-	pop_host_regs_mode svc
-
-	pop	{r2, r3}
-	msr	SP_usr, r2
-	mov	lr, r3
-	pop	{r4-r12}
-
-	pop	{r2}
-	msr	ELR_hyp, r2
-.endm
-
-/*
- * Restore SP, LR and SPSR for a given mode. offset is the offset of
- * this mode's registers from the VCPU base.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r1, r2, r3, r4.
- */
-.macro restore_guest_regs_mode mode, offset
-	add	r1, vcpu, \offset
-	ldm	r1, {r2, r3, r4}
-	msr	SP_\mode, r2
-	msr	LR_\mode, r3
-	msr	SPSR_\mode, r4
-.endm
-
-/*
- * Restore all guest registers from the vcpu struct.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers *all* registers.
- */
-.macro restore_guest_regs
-	restore_guest_regs_mode svc, #VCPU_SVC_REGS
-	restore_guest_regs_mode abt, #VCPU_ABT_REGS
-	restore_guest_regs_mode und, #VCPU_UND_REGS
-	restore_guest_regs_mode irq, #VCPU_IRQ_REGS
-
-	add	r1, vcpu, #VCPU_FIQ_REGS
-	ldm	r1, {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
-
-	@ Load return state
-	ldr	r2, [vcpu, #VCPU_PC]
-	ldr	r3, [vcpu, #VCPU_CPSR]
-	msr	ELR_hyp, r2
-	msr	SPSR_cxsf, r3
-
-	@ Load user registers
-	ldr	r2, [vcpu, #VCPU_USR_SP]
-	ldr	r3, [vcpu, #VCPU_USR_LR]
-	msr	SP_usr, r2
-	mov	lr, r3
-	add	vcpu, vcpu, #(VCPU_USR_REGS)
-	ldm	vcpu, {r0-r12}
-.endm
-
-/*
- * Save SP, LR and SPSR for a given mode. offset is the offset of
- * this mode's registers from the VCPU base.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2, r3, r4, r5.
- */
-.macro save_guest_regs_mode mode, offset
-	add	r2, vcpu, \offset
-	mrs	r3, SP_\mode
-	mrs	r4, LR_\mode
-	mrs	r5, SPSR_\mode
-	stm	r2, {r3, r4, r5}
-.endm
-
-/*
- * Save all guest registers to the vcpu struct
- * Expects guest's r0, r1, r2 on the stack.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2, r3, r4, r5.
- */
-.macro save_guest_regs
-	@ Store usr registers
-	add	r2, vcpu, #VCPU_USR_REG(3)
-	stm	r2, {r3-r12}
-	add	r2, vcpu, #VCPU_USR_REG(0)
-	pop	{r3, r4, r5}		@ r0, r1, r2
-	stm	r2, {r3, r4, r5}
-	mrs	r2, SP_usr
-	mov	r3, lr
-	str	r2, [vcpu, #VCPU_USR_SP]
-	str	r3, [vcpu, #VCPU_USR_LR]
-
-	@ Store return state
-	mrs	r2, ELR_hyp
-	mrs	r3, spsr
-	str	r2, [vcpu, #VCPU_PC]
-	str	r3, [vcpu, #VCPU_CPSR]
-
-	@ Store other guest registers
-	save_guest_regs_mode svc, #VCPU_SVC_REGS
-	save_guest_regs_mode abt, #VCPU_ABT_REGS
-	save_guest_regs_mode und, #VCPU_UND_REGS
-	save_guest_regs_mode irq, #VCPU_IRQ_REGS
-.endm
-
-/* Reads cp15 registers from hardware and stores them in memory
- * @store_to_vcpu: If 0, registers are written in-order to the stack,
- * 		   otherwise to the VCPU struct pointed to by vcpup
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2 - r12
- */
-.macro read_cp15_state store_to_vcpu
-	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 \store_to_vcpu == 0
-	push	{r2-r12}		@ Push CP15 registers
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
-	str	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
-	str	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
-	str	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
-	add	r2, vcpu, #CP15_OFFSET(c2_TTBR0)
-	strd	r6, r7, [r2]
-	add	r2, vcpu, #CP15_OFFSET(c2_TTBR1)
-	strd	r8, r9, [r2]
-	str	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
-	str	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
-	str	r12, [vcpu, #CP15_OFFSET(c0_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 \store_to_vcpu == 0
-	push	{r2-r12}		@ Push CP15 registers
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c13_CID)]
-	str	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
-	str	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
-	str	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
-	str	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
-	str	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
-	str	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
-	str	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
-	str	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
-	str	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
-	str	r12, [vcpu, #CP15_OFFSET(c12_VBAR)]
-	.endif
-
-	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
-	mrrc	p15, 0, r4, r5, c7	@ PAR
-	mrc	p15, 0, r6, c10, c3, 0	@ AMAIR0
-	mrc	p15, 0, r7, c10, c3, 1	@ AMAIR1
-
-	.if \store_to_vcpu == 0
-	push	{r2,r4-r7}
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
-	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
-	strd	r4, r5, [r12]
-	str	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
-	str	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
-	.endif
-.endm
-
-/*
- * Reads cp15 registers from memory and writes them to hardware
- * @read_from_vcpu: If 0, registers are read in-order from the stack,
- *		    otherwise from the VCPU struct pointed to by vcpup
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro write_cp15_state read_from_vcpu
-	.if \read_from_vcpu == 0
-	pop	{r2,r4-r7}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
-	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
-	ldrd	r4, r5, [r12]
-	ldr	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
-	ldr	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
-	.endif
-
-	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
-	mcrr	p15, 0, r4, r5, c7	@ PAR
-	mcr	p15, 0, r6, c10, c3, 0	@ AMAIR0
-	mcr	p15, 0, r7, c10, c3, 1	@ AMAIR1
-
-	.if \read_from_vcpu == 0
-	pop	{r2-r12}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c13_CID)]
-	ldr	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
-	ldr	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
-	ldr	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
-	ldr	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
-	ldr	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
-	ldr	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
-	ldr	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
-	ldr	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
-	ldr	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
-	ldr	r12, [vcpu, #CP15_OFFSET(c12_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 \read_from_vcpu == 0
-	pop	{r2-r12}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
-	ldr	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
-	ldr	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
-	ldr	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
-	add	r12, vcpu, #CP15_OFFSET(c2_TTBR0)
-	ldrd	r6, r7, [r12]
-	add	r12, vcpu, #CP15_OFFSET(c2_TTBR1)
-	ldrd	r8, r9, [r12]
-	ldr	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
-	ldr	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
-	ldr	r12, [vcpu, #CP15_OFFSET(c0_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
-
-/*
- * Save the VGIC CPU state into memory
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro save_vgic_state
-	/* Get VGIC VCTRL base into r2 */
-	ldr	r2, [vcpu, #VCPU_KVM]
-	ldr	r2, [r2, #KVM_VGIC_VCTRL]
-	cmp	r2, #0
-	beq	2f
-
-	/* Compute the address of struct vgic_cpu */
-	add	r11, vcpu, #VCPU_VGIC_CPU
-
-	/* Save all interesting registers */
-	ldr	r4, [r2, #GICH_VMCR]
-	ldr	r5, [r2, #GICH_MISR]
-	ldr	r6, [r2, #GICH_EISR0]
-	ldr	r7, [r2, #GICH_EISR1]
-	ldr	r8, [r2, #GICH_ELRSR0]
-	ldr	r9, [r2, #GICH_ELRSR1]
-	ldr	r10, [r2, #GICH_APR]
-ARM_BE8(rev	r4, r4	)
-ARM_BE8(rev	r5, r5	)
-ARM_BE8(rev	r6, r6	)
-ARM_BE8(rev	r7, r7	)
-ARM_BE8(rev	r8, r8	)
-ARM_BE8(rev	r9, r9	)
-ARM_BE8(rev	r10, r10	)
-
-	str	r4, [r11, #VGIC_V2_CPU_VMCR]
-	str	r5, [r11, #VGIC_V2_CPU_MISR]
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	str	r6, [r11, #(VGIC_V2_CPU_EISR + 4)]
-	str	r7, [r11, #VGIC_V2_CPU_EISR]
-	str	r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
-	str	r9, [r11, #VGIC_V2_CPU_ELRSR]
-#else
-	str	r6, [r11, #VGIC_V2_CPU_EISR]
-	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
-	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
-	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
-#endif
-	str	r10, [r11, #VGIC_V2_CPU_APR]
-
-	/* Clear GICH_HCR */
-	mov	r5, #0
-	str	r5, [r2, #GICH_HCR]
-
-	/* Save list registers */
-	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_V2_CPU_LR
-	ldr	r4, [r11, #VGIC_CPU_NR_LR]
-1:	ldr	r6, [r2], #4
-ARM_BE8(rev	r6, r6	)
-	str	r6, [r3], #4
-	subs	r4, r4, #1
-	bne	1b
-2:
-.endm
-
-/*
- * Restore the VGIC CPU state from memory
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro restore_vgic_state
-	/* Get VGIC VCTRL base into r2 */
-	ldr	r2, [vcpu, #VCPU_KVM]
-	ldr	r2, [r2, #KVM_VGIC_VCTRL]
-	cmp	r2, #0
-	beq	2f
-
-	/* Compute the address of struct vgic_cpu */
-	add	r11, vcpu, #VCPU_VGIC_CPU
-
-	/* We only restore a minimal set of registers */
-	ldr	r3, [r11, #VGIC_V2_CPU_HCR]
-	ldr	r4, [r11, #VGIC_V2_CPU_VMCR]
-	ldr	r8, [r11, #VGIC_V2_CPU_APR]
-ARM_BE8(rev	r3, r3	)
-ARM_BE8(rev	r4, r4	)
-ARM_BE8(rev	r8, r8	)
-
-	str	r3, [r2, #GICH_HCR]
-	str	r4, [r2, #GICH_VMCR]
-	str	r8, [r2, #GICH_APR]
-
-	/* Restore list registers */
-	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_V2_CPU_LR
-	ldr	r4, [r11, #VGIC_CPU_NR_LR]
-1:	ldr	r6, [r3], #4
-ARM_BE8(rev	r6, r6  )
-	str	r6, [r2], #4
-	subs	r4, r4, #1
-	bne	1b
-2:
-.endm
-
-#define CNTHCTL_PL1PCTEN	(1 << 0)
-#define CNTHCTL_PL1PCEN		(1 << 1)
-
-/*
- * Save the timer state onto the VCPU and allow physical timer/counter access
- * for the host.
- *
- * Assumes vcpu pointer in vcpu reg
- * Clobbers r2-r5
- */
-.macro save_timer_state
-	ldr	r4, [vcpu, #VCPU_KVM]
-	ldr	r2, [r4, #KVM_TIMER_ENABLED]
-	cmp	r2, #0
-	beq	1f
-
-	mrc	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-	str	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-
-	isb
-
-	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
-	ldr	r4, =VCPU_TIMER_CNTV_CVAL
-	add	r5, vcpu, r4
-	strd	r2, r3, [r5]
-
-	@ Ensure host CNTVCT == CNTPCT
-	mov	r2, #0
-	mcrr	p15, 4, r2, r2, c14	@ CNTVOFF
-
-1:
-	mov	r2, #0			@ Clear ENABLE
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-
-	@ Allow physical timer/counter access for the host
-	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-	orr	r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN)
-	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-.endm
-
-/*
- * Load the timer state from the VCPU and deny physical timer/counter access
- * for the host.
- *
- * Assumes vcpu pointer in vcpu reg
- * Clobbers r2-r5
- */
-.macro restore_timer_state
-	@ Disallow physical timer access for the guest
-	@ Physical counter access is allowed
-	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-	orr	r2, r2, #CNTHCTL_PL1PCTEN
-	bic	r2, r2, #CNTHCTL_PL1PCEN
-	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-
-	ldr	r4, [vcpu, #VCPU_KVM]
-	ldr	r2, [r4, #KVM_TIMER_ENABLED]
-	cmp	r2, #0
-	beq	1f
-
-	ldr	r2, [r4, #KVM_TIMER_CNTVOFF]
-	ldr	r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
-	mcrr	p15, 4, rr_lo_hi(r2, r3), c14	@ CNTVOFF
-
-	ldr	r4, =VCPU_TIMER_CNTV_CVAL
-	add	r5, vcpu, r4
-	ldrd	r2, r3, [r5]
-	mcrr	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
-	isb
-
-	ldr	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-	and	r2, r2, #3
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-1:
-.endm
-
-.equ vmentry,	0
-.equ vmexit,	1
-
-/* Configures the HSTR (Hyp System Trap Register) on entry/return
- * (hardware reset value is 0) */
-.macro set_hstr operation
-	mrc	p15, 4, r2, c1, c1, 3
-	ldr	r3, =HSTR_T(15)
-	.if \operation == vmentry
-	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.
- * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
- * VFP wasn't already enabled (always executed on vmtrap).
- * If a label is specified with vmexit, it is branched to if VFP wasn't
- * enabled.
- */
-.macro set_hcptr operation, mask, label = none
-	mrc	p15, 4, r2, c1, c1, 2
-	ldr	r3, =\mask
-	.if \operation == vmentry
-	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
-	.if \operation != vmentry
-	.if \operation == vmexit
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	beq	1f
-	.endif
-	isb
-	.if \label != none
-	b	\label
-	.endif
-1:
-	.endif
-.endm
-
-/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
- * (hardware reset value is 0) */
-.macro set_hdcr operation
-	mrc	p15, 4, r2, c1, c1, 1
-	ldr	r3, =(HDCR_TPM|HDCR_TPMCR)
-	.if \operation == vmentry
-	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 operation
-	.if \operation == vmentry
-	ldr	r2, [vcpu, #VCPU_HCR]
-	ldr	r3, [vcpu, #VCPU_IRQ_LINES]
-	orr	r2, r2, r3
-	.else
-	mov	r2, #0
-	.endif
-	mcr	p15, 4, r2, c1, c1, 0	@ HCR
-.endm
-
-.macro load_vcpu
-	mrc	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
-.endm