Merge tag 'kvmarm-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 5.10

- New page table code for both hypervisor and guest stage-2
- Introduction of a new EL2-private host context
- Allow EL2 to have its own private per-CPU variables
- Support of PMU event filtering
- Complete rework of the Spectre mitigation

18 files changed, 618 insertions, 794 deletions

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 54d181177656..ddbe6bf00e33 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -219,6 +219,23 @@ lr	.req	x30		// link register
 	.endm
 
 	/*
+	 * @dst: destination register
+	 */
+#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__)
+	.macro	this_cpu_offset, dst
+	mrs	\dst, tpidr_el2
+	.endm
+#else
+	.macro	this_cpu_offset, dst
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+	mrs	\dst, tpidr_el1
+alternative_else
+	mrs	\dst, tpidr_el2
+alternative_endif
+	.endm
+#endif
+
+	/*
 	 * @dst: Result of per_cpu(sym, smp_processor_id()) (can be SP)
 	 * @sym: The name of the per-cpu variable
 	 * @tmp: scratch register
@@ -226,11 +243,7 @@ lr	.req	x30		// link register
 	.macro adr_this_cpu, dst, sym, tmp
 	adrp	\tmp, \sym
 	add	\dst, \tmp, #:lo12:\sym
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	\tmp, tpidr_el1
-alternative_else
-	mrs	\tmp, tpidr_el2
-alternative_endif
+	this_cpu_offset \tmp
 	add	\dst, \dst, \tmp
 	.endm
 
@@ -241,11 +254,7 @@ alternative_endif
 	 */
 	.macro ldr_this_cpu dst, sym, tmp
 	adr_l	\dst, \sym
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	\tmp, tpidr_el1
-alternative_else
-	mrs	\tmp, tpidr_el2
-alternative_endif
+	this_cpu_offset \tmp
 	ldr	\dst, [\dst, \tmp]
 	.endm
 
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 07b643a70710..c4ac9a13ad5f 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -31,13 +31,13 @@
 #define ARM64_HAS_DCPOP				21
 #define ARM64_SVE				22
 #define ARM64_UNMAP_KERNEL_AT_EL0		23
-#define ARM64_HARDEN_BRANCH_PREDICTOR		24
+#define ARM64_SPECTRE_V2			24
 #define ARM64_HAS_RAS_EXTN			25
 #define ARM64_WORKAROUND_843419			26
 #define ARM64_HAS_CACHE_IDC			27
 #define ARM64_HAS_CACHE_DIC			28
 #define ARM64_HW_DBM				29
-#define ARM64_SSBD				30
+#define ARM64_SPECTRE_V4			30
 #define ARM64_MISMATCHED_CACHE_TYPE		31
 #define ARM64_HAS_STAGE2_FWB			32
 #define ARM64_HAS_CRC32				33
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 89b4f0142c28..fba6700b457b 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -698,30 +698,6 @@ static inline bool system_supports_tlb_range(void)
 		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
 }
 
-#define ARM64_BP_HARDEN_UNKNOWN		-1
-#define ARM64_BP_HARDEN_WA_NEEDED	0
-#define ARM64_BP_HARDEN_NOT_REQUIRED	1
-
-int get_spectre_v2_workaround_state(void);
-
-#define ARM64_SSBD_UNKNOWN		-1
-#define ARM64_SSBD_FORCE_DISABLE	0
-#define ARM64_SSBD_KERNEL		1
-#define ARM64_SSBD_FORCE_ENABLE		2
-#define ARM64_SSBD_MITIGATED		3
-
-static inline int arm64_get_ssbd_state(void)
-{
-#ifdef CONFIG_ARM64_SSBD
-	extern int ssbd_state;
-	return ssbd_state;
-#else
-	return ARM64_SSBD_UNKNOWN;
-#endif
-}
-
-void arm64_set_ssbd_mitigation(bool state);
-
 extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 
 static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
diff --git a/arch/arm64/include/asm/hyp_image.h b/arch/arm64/include/asm/hyp_image.h
new file mode 100644
index 000000000000..daa1a1da539e
--- /dev/null
+++ b/arch/arm64/include/asm/hyp_image.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Google LLC.
+ * Written by David Brazdil <dbrazdil@google.com>
+ */
+
+#ifndef __ARM64_HYP_IMAGE_H__
+#define __ARM64_HYP_IMAGE_H__
+
+/*
+ * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_,
+ * to separate it from the kernel proper.
+ */
+#define kvm_nvhe_sym(sym)	__kvm_nvhe_##sym
+
+#ifdef LINKER_SCRIPT
+
+/*
+ * KVM nVHE ELF section names are prefixed with .hyp, to separate them
+ * from the kernel proper.
+ */
+#define HYP_SECTION_NAME(NAME)	.hyp##NAME
+
+/* Defines an ELF hyp section from input section @NAME and its subsections. */
+#define HYP_SECTION(NAME) \
+	HYP_SECTION_NAME(NAME) : { *(NAME NAME##.*) }
+
+/*
+ * Defines a linker script alias of a kernel-proper symbol referenced by
+ * KVM nVHE hyp code.
+ */
+#define KVM_NVHE_ALIAS(sym)	kvm_nvhe_sym(sym) = sym;
+
+#endif /* LINKER_SCRIPT */
+
+#endif /* __ARM64_HYP_IMAGE_H__ */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 6f98fbd0ac81..54387ccd1ab2 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -7,11 +7,9 @@
 #ifndef __ARM_KVM_ASM_H__
 #define __ARM_KVM_ASM_H__
 
+#include <asm/hyp_image.h>
 #include <asm/virt.h>
 
-#define	VCPU_WORKAROUND_2_FLAG_SHIFT	0
-#define	VCPU_WORKAROUND_2_FLAG		(_AC(1, UL) << VCPU_WORKAROUND_2_FLAG_SHIFT)
-
 #define ARM_EXIT_WITH_SERROR_BIT  31
 #define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
 #define ARM_EXCEPTION_IS_TRAP(x)  (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP)
@@ -38,17 +36,34 @@
 
 #define __SMCCC_WORKAROUND_1_SMC_SZ 36
 
+#define KVM_HOST_SMCCC_ID(id)						\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   (id))
+
+#define KVM_HOST_SMCCC_FUNC(name) KVM_HOST_SMCCC_ID(__KVM_HOST_SMCCC_FUNC_##name)
+
+#define __KVM_HOST_SMCCC_FUNC___kvm_hyp_init			0
+#define __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run			1
+#define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context		2
+#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa		3
+#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid		4
+#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid	5
+#define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff		6
+#define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs			7
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_ich_vtr_el2		8
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr		9
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr		10
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs		11
+#define __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2		12
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs		13
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs		14
+
 #ifndef __ASSEMBLY__
 
 #include <linux/mm.h>
 
-/*
- * Translate name of a symbol defined in nVHE hyp to the name seen
- * by kernel proper. All nVHE symbols are prefixed by the build system
- * to avoid clashes with the VHE variants.
- */
-#define kvm_nvhe_sym(sym)	__kvm_nvhe_##sym
-
 #define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
 #define DECLARE_KVM_NVHE_SYM(sym)	extern char kvm_nvhe_sym(sym)[]
 
@@ -60,10 +75,53 @@
 	DECLARE_KVM_VHE_SYM(sym);		\
 	DECLARE_KVM_NVHE_SYM(sym)
 
+#define DECLARE_KVM_VHE_PER_CPU(type, sym)	\
+	DECLARE_PER_CPU(type, sym)
+#define DECLARE_KVM_NVHE_PER_CPU(type, sym)	\
+	DECLARE_PER_CPU(type, kvm_nvhe_sym(sym))
+
+#define DECLARE_KVM_HYP_PER_CPU(type, sym)	\
+	DECLARE_KVM_VHE_PER_CPU(type, sym);	\
+	DECLARE_KVM_NVHE_PER_CPU(type, sym)
+
+/*
+ * Compute pointer to a symbol defined in nVHE percpu region.
+ * Returns NULL if percpu memory has not been allocated yet.
+ */
+#define this_cpu_ptr_nvhe_sym(sym)	per_cpu_ptr_nvhe_sym(sym, smp_processor_id())
+#define per_cpu_ptr_nvhe_sym(sym, cpu)						\
+	({									\
+		unsigned long base, off;					\
+		base = kvm_arm_hyp_percpu_base[cpu];				\
+		off = (unsigned long)&CHOOSE_NVHE_SYM(sym) -			\
+		      (unsigned long)&CHOOSE_NVHE_SYM(__per_cpu_start);		\
+		base ? (typeof(CHOOSE_NVHE_SYM(sym))*)(base + off) : NULL;	\
+	})
+
+#if defined(__KVM_NVHE_HYPERVISOR__)
+
+#define CHOOSE_NVHE_SYM(sym)	sym
+#define CHOOSE_HYP_SYM(sym)	CHOOSE_NVHE_SYM(sym)
+
+/* The nVHE hypervisor shouldn't even try to access VHE symbols */
+extern void *__nvhe_undefined_symbol;
+#define CHOOSE_VHE_SYM(sym)		__nvhe_undefined_symbol
+#define this_cpu_ptr_hyp_sym(sym)	(&__nvhe_undefined_symbol)
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(&__nvhe_undefined_symbol)
+
+#elif defined(__KVM_VHE_HYPERVISOR__)
+
 #define CHOOSE_VHE_SYM(sym)	sym
-#define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
+#define CHOOSE_HYP_SYM(sym)	CHOOSE_VHE_SYM(sym)
+
+/* The VHE hypervisor shouldn't even try to access nVHE symbols */
+extern void *__vhe_undefined_symbol;
+#define CHOOSE_NVHE_SYM(sym)		__vhe_undefined_symbol
+#define this_cpu_ptr_hyp_sym(sym)	(&__vhe_undefined_symbol)
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(&__vhe_undefined_symbol)
+
+#else
 
-#ifndef __KVM_NVHE_HYPERVISOR__
 /*
  * BIG FAT WARNINGS:
  *
@@ -75,12 +133,21 @@
  * - Don't let the nVHE hypervisor have access to this, as it will
  *   pick the *wrong* symbol (yes, it runs at EL2...).
  */
-#define CHOOSE_HYP_SYM(sym)	(is_kernel_in_hyp_mode() ? CHOOSE_VHE_SYM(sym) \
+#define CHOOSE_HYP_SYM(sym)		(is_kernel_in_hyp_mode()	\
+					   ? CHOOSE_VHE_SYM(sym)	\
 					   : CHOOSE_NVHE_SYM(sym))
-#else
-/* The nVHE hypervisor shouldn't even try to access anything */
-extern void *__nvhe_undefined_symbol;
-#define CHOOSE_HYP_SYM(sym)	__nvhe_undefined_symbol
+
+#define this_cpu_ptr_hyp_sym(sym)	(is_kernel_in_hyp_mode()	\
+					   ? this_cpu_ptr(&sym)		\
+					   : this_cpu_ptr_nvhe_sym(sym))
+
+#define per_cpu_ptr_hyp_sym(sym, cpu)	(is_kernel_in_hyp_mode()	\
+					   ? per_cpu_ptr(&sym, cpu)	\
+					   : per_cpu_ptr_nvhe_sym(sym, cpu))
+
+#define CHOOSE_VHE_SYM(sym)	sym
+#define CHOOSE_NVHE_SYM(sym)	kvm_nvhe_sym(sym)
+
 #endif
 
 /* Translate a kernel address @ptr into its equivalent linear mapping */
@@ -98,15 +165,19 @@ struct kvm_vcpu;
 struct kvm_s2_mmu;
 
 DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
+DECLARE_KVM_NVHE_SYM(__kvm_hyp_host_vector);
 DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
 #define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
+#define __kvm_hyp_host_vector	CHOOSE_NVHE_SYM(__kvm_hyp_host_vector)
 #define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
 
-#ifdef CONFIG_KVM_INDIRECT_VECTORS
+extern unsigned long kvm_arm_hyp_percpu_base[NR_CPUS];
+DECLARE_KVM_NVHE_SYM(__per_cpu_start);
+DECLARE_KVM_NVHE_SYM(__per_cpu_end);
+
 extern atomic_t arm64_el2_vector_last_slot;
 DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
-#endif
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
@@ -149,26 +220,6 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 		addr;							\
 	})
 
-/*
- * Home-grown __this_cpu_{ptr,read} variants that always work at HYP,
- * provided that sym is really a *symbol* and not a pointer obtained from
- * a data structure. As for SHIFT_PERCPU_PTR(), the creative casting keeps
- * sparse quiet.
- */
-#define __hyp_this_cpu_ptr(sym)						\
-	({								\
-		void *__ptr;						\
-		__verify_pcpu_ptr(&sym);				\
-		__ptr = hyp_symbol_addr(sym);				\
-		__ptr += read_sysreg(tpidr_el2);			\
-		(typeof(sym) __kernel __force *)__ptr;			\
-	 })
-
-#define __hyp_this_cpu_read(sym)					\
-	({								\
-		*__hyp_this_cpu_ptr(sym);				\
-	 })
-
 #define __KVM_EXTABLE(from, to)						\
 	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
 	"	.align		3\n"					\
@@ -199,20 +250,8 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 
 #else /* __ASSEMBLY__ */
 
-.macro hyp_adr_this_cpu reg, sym, tmp
-	adr_l	\reg, \sym
-	mrs	\tmp, tpidr_el2
-	add	\reg, \reg, \tmp
-.endm
-
-.macro hyp_ldr_this_cpu reg, sym, tmp
-	adr_l	\reg, \sym
-	mrs	\tmp, tpidr_el2
-	ldr	\reg,  [\reg, \tmp]
-.endm
-
 .macro get_host_ctxt reg, tmp
-	hyp_adr_this_cpu \reg, kvm_host_data, \tmp
+	adr_this_cpu \reg, kvm_host_data, \tmp
 	add	\reg, \reg, #HOST_DATA_CONTEXT
 .endm
 
@@ -221,6 +260,16 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
 .endm
 
+.macro get_loaded_vcpu vcpu, ctxt
+	adr_this_cpu \ctxt, kvm_hyp_ctxt, \vcpu
+	ldr	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
+.macro set_loaded_vcpu vcpu, ctxt, tmp
+	adr_this_cpu \ctxt, kvm_hyp_ctxt, \tmp
+	str	\vcpu, [\ctxt, #HOST_CONTEXT_VCPU]
+.endm
+
 /*
  * KVM extable for unexpected exceptions.
  * In the same format _asm_extable, but output to a different section so that
@@ -236,6 +285,45 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 	.popsection
 .endm
 
+#define CPU_XREG_OFFSET(x)	(CPU_USER_PT_REGS + 8*x)
+#define CPU_LR_OFFSET		CPU_XREG_OFFSET(30)
+#define CPU_SP_EL0_OFFSET	(CPU_LR_OFFSET + 8)
+
+/*
+ * We treat x18 as callee-saved as the host may use it as a platform
+ * register (e.g. for shadow call stack).
+ */
+.macro save_callee_saved_regs ctxt
+	str	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
+	stp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	stp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	stp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	stp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	stp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	stp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+.macro restore_callee_saved_regs ctxt
+	// We require \ctxt is not x18-x28
+	ldr	x18,      [\ctxt, #CPU_XREG_OFFSET(18)]
+	ldp	x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)]
+	ldp	x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)]
+	ldp	x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)]
+	ldp	x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)]
+	ldp	x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)]
+	ldp	x29, lr,  [\ctxt, #CPU_XREG_OFFSET(29)]
+.endm
+
+.macro save_sp_el0 ctxt, tmp
+	mrs	\tmp,	sp_el0
+	str	\tmp,	[\ctxt, #CPU_SP_EL0_OFFSET]
+.endm
+
+.macro restore_sp_el0 ctxt, tmp
+	ldr	\tmp,	  [\ctxt, #CPU_SP_EL0_OFFSET]
+	msr	sp_el0, \tmp
+.endm
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 1cc5f5f72d0b..5ef2669ccd6c 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -391,20 +391,6 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
-static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG;
-}
-
-static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu,
-						      bool flag)
-{
-	if (flag)
-		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
-	else
-		vcpu->arch.workaround_flags &= ~VCPU_WORKAROUND_2_FLAG;
-}
-
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu)) {
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 905c2b87e05a..0aecbab6a7fb 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -11,6 +11,7 @@
 #ifndef __ARM64_KVM_HOST_H__
 #define __ARM64_KVM_HOST_H__
 
+#include <linux/arm-smccc.h>
 #include <linux/bitmap.h>
 #include <linux/types.h>
 #include <linux/jump_label.h>
@@ -79,8 +80,8 @@ struct kvm_s2_mmu {
 	 * for vEL1/EL0 with vHCR_EL2.VM == 0.  In that case, we use the
 	 * canonical stage-2 page tables.
 	 */
-	pgd_t		*pgd;
 	phys_addr_t	pgd_phys;
+	struct kvm_pgtable *pgt;
 
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
@@ -110,6 +111,13 @@ struct kvm_arch {
 	 * supported.
 	 */
 	bool return_nisv_io_abort_to_user;
+
+	/*
+	 * VM-wide PMU filter, implemented as a bitmap and big enough for
+	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).
+	 */
+	unsigned long *pmu_filter;
+	unsigned int pmuver;
 };
 
 struct kvm_vcpu_fault_info {
@@ -262,8 +270,6 @@ struct kvm_host_data {
 	struct kvm_pmu_events pmu_events;
 };
 
-typedef struct kvm_host_data kvm_host_data_t;
-
 struct vcpu_reset_state {
 	unsigned long	pc;
 	unsigned long	r0;
@@ -480,18 +486,15 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
-u64 __kvm_call_hyp(void *hypfn, ...);
-
-#define kvm_call_hyp_nvhe(f, ...)					\
-	do {								\
-		DECLARE_KVM_NVHE_SYM(f);				\
-		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
-	} while(0)
-
-#define kvm_call_hyp_nvhe_ret(f, ...)					\
+#define kvm_call_hyp_nvhe(f, ...)						\
 	({								\
-		DECLARE_KVM_NVHE_SYM(f);				\
-		__kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__);	\
+		struct arm_smccc_res res;				\
+									\
+		arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(f),		\
+				  ##__VA_ARGS__, &res);			\
+		WARN_ON(res.a0 != SMCCC_RET_SUCCESS);			\
+									\
+		res.a1;							\
 	})
 
 /*
@@ -517,7 +520,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 			ret = f(__VA_ARGS__);				\
 			isb();						\
 		} else {						\
-			ret = kvm_call_hyp_nvhe_ret(f, ##__VA_ARGS__);	\
+			ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__);	\
 		}							\
 									\
 		ret;							\
@@ -565,7 +568,7 @@ void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
-DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data);
+DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);
 
 static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 {
@@ -631,46 +634,6 @@ static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {}
 static inline void kvm_clr_pmu_events(u32 clr) {}
 #endif
 
-#define KVM_BP_HARDEN_UNKNOWN		-1
-#define KVM_BP_HARDEN_WA_NEEDED		0
-#define KVM_BP_HARDEN_NOT_REQUIRED	1
-
-static inline int kvm_arm_harden_branch_predictor(void)
-{
-	switch (get_spectre_v2_workaround_state()) {
-	case ARM64_BP_HARDEN_WA_NEEDED:
-		return KVM_BP_HARDEN_WA_NEEDED;
-	case ARM64_BP_HARDEN_NOT_REQUIRED:
-		return KVM_BP_HARDEN_NOT_REQUIRED;
-	case ARM64_BP_HARDEN_UNKNOWN:
-	default:
-		return KVM_BP_HARDEN_UNKNOWN;
-	}
-}
-
-#define KVM_SSBD_UNKNOWN		-1
-#define KVM_SSBD_FORCE_DISABLE		0
-#define KVM_SSBD_KERNEL		1
-#define KVM_SSBD_FORCE_ENABLE		2
-#define KVM_SSBD_MITIGATED		3
-
-static inline int kvm_arm_have_ssbd(void)
-{
-	switch (arm64_get_ssbd_state()) {
-	case ARM64_SSBD_FORCE_DISABLE:
-		return KVM_SSBD_FORCE_DISABLE;
-	case ARM64_SSBD_KERNEL:
-		return KVM_SSBD_KERNEL;
-	case ARM64_SSBD_FORCE_ENABLE:
-		return KVM_SSBD_FORCE_ENABLE;
-	case ARM64_SSBD_MITIGATED:
-		return KVM_SSBD_MITIGATED;
-	case ARM64_SSBD_UNKNOWN:
-	default:
-		return KVM_SSBD_UNKNOWN;
-	}
-}
-
 void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
 void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 46689e7db46c..6b664de5ec1f 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -12,6 +12,9 @@
 #include <asm/alternative.h>
 #include <asm/sysreg.h>
 
+DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
+DECLARE_PER_CPU(unsigned long, kvm_hyp_vector);
+
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
 		u64 reg;						\
@@ -87,11 +90,11 @@ void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
 void deactivate_traps_vhe_put(void);
 #endif
 
-u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+u64 __guest_enter(struct kvm_vcpu *vcpu);
 
-void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt);
+void __noreturn hyp_panic(void);
 #ifdef __KVM_NVHE_HYPERVISOR__
-void __noreturn __hyp_do_panic(unsigned long, ...);
+void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
 #endif
 
 #endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 189839c3706a..331394306cce 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -9,6 +9,7 @@
 
 #include <asm/page.h>
 #include <asm/memory.h>
+#include <asm/mmu.h>
 #include <asm/cpufeature.h>
 
 /*
@@ -43,16 +44,6 @@
  *	HYP_VA_MIN = 1 << (VA_BITS - 1)
  * HYP_VA_MAX = HYP_VA_MIN + (1 << (VA_BITS - 1)) - 1
  *
- * This of course assumes that the trampoline page exists within the
- * VA_BITS range. If it doesn't, then it means we're in the odd case
- * where the kernel idmap (as well as HYP) uses more levels than the
- * kernel runtime page tables (as seen when the kernel is configured
- * for 4k pages, 39bits VA, and yet memory lives just above that
- * limit, forcing the idmap to use 4 levels of page tables while the
- * kernel itself only uses 3). In this particular case, it doesn't
- * matter which side of VA_BITS we use, as we're guaranteed not to
- * conflict with anything.
- *
  * When using VHE, there are no separate hyp mappings and all KVM
  * functionality is already mapped as part of the main kernel
  * mappings, and none of this applies in that case.
@@ -117,15 +108,10 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 #define kvm_phys_size(kvm)		(_AC(1, ULL) << kvm_phys_shift(kvm))
 #define kvm_phys_mask(kvm)		(kvm_phys_size(kvm) - _AC(1, ULL))
 
-static inline bool kvm_page_empty(void *ptr)
-{
-	struct page *ptr_page = virt_to_page(ptr);
-	return page_count(ptr_page) == 1;
-}
-
+#include <asm/kvm_pgtable.h>
 #include <asm/stage2_pgtable.h>
 
-int create_hyp_mappings(void *from, void *to, pgprot_t prot);
+int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
 int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **kaddr,
 			   void __iomem **haddr);
@@ -141,149 +127,9 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
-void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
-
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 int kvm_mmu_init(void);
-void kvm_clear_hyp_idmap(void);
-
-#define kvm_mk_pmd(ptep)					\
-	__pmd(__phys_to_pmd_val(__pa(ptep)) | PMD_TYPE_TABLE)
-#define kvm_mk_pud(pmdp)					\
-	__pud(__phys_to_pud_val(__pa(pmdp)) | PMD_TYPE_TABLE)
-#define kvm_mk_p4d(pmdp)					\
-	__p4d(__phys_to_p4d_val(__pa(pmdp)) | PUD_TYPE_TABLE)
-
-#define kvm_set_pud(pudp, pud)		set_pud(pudp, pud)
-
-#define kvm_pfn_pte(pfn, prot)		pfn_pte(pfn, prot)
-#define kvm_pfn_pmd(pfn, prot)		pfn_pmd(pfn, prot)
-#define kvm_pfn_pud(pfn, prot)		pfn_pud(pfn, prot)
-
-#define kvm_pud_pfn(pud)		pud_pfn(pud)
-
-#define kvm_pmd_mkhuge(pmd)		pmd_mkhuge(pmd)
-#define kvm_pud_mkhuge(pud)		pud_mkhuge(pud)
-
-static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
-{
-	pte_val(pte) |= PTE_S2_RDWR;
-	return pte;
-}
-
-static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
-{
-	pmd_val(pmd) |= PMD_S2_RDWR;
-	return pmd;
-}
-
-static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
-{
-	pud_val(pud) |= PUD_S2_RDWR;
-	return pud;
-}
-
-static inline pte_t kvm_s2pte_mkexec(pte_t pte)
-{
-	pte_val(pte) &= ~PTE_S2_XN;
-	return pte;
-}
-
-static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
-{
-	pmd_val(pmd) &= ~PMD_S2_XN;
-	return pmd;
-}
-
-static inline pud_t kvm_s2pud_mkexec(pud_t pud)
-{
-	pud_val(pud) &= ~PUD_S2_XN;
-	return pud;
-}
-
-static inline void kvm_set_s2pte_readonly(pte_t *ptep)
-{
-	pteval_t old_pteval, pteval;
-
-	pteval = READ_ONCE(pte_val(*ptep));
-	do {
-		old_pteval = pteval;
-		pteval &= ~PTE_S2_RDWR;
-		pteval |= PTE_S2_RDONLY;
-		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
-	} while (pteval != old_pteval);
-}
-
-static inline bool kvm_s2pte_readonly(pte_t *ptep)
-{
-	return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY;
-}
-
-static inline bool kvm_s2pte_exec(pte_t *ptep)
-{
-	return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN);
-}
-
-static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp)
-{
-	kvm_set_s2pte_readonly((pte_t *)pmdp);
-}
-
-static inline bool kvm_s2pmd_readonly(pmd_t *pmdp)
-{
-	return kvm_s2pte_readonly((pte_t *)pmdp);
-}
-
-static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
-{
-	return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
-}
-
-static inline void kvm_set_s2pud_readonly(pud_t *pudp)
-{
-	kvm_set_s2pte_readonly((pte_t *)pudp);
-}
-
-static inline bool kvm_s2pud_readonly(pud_t *pudp)
-{
-	return kvm_s2pte_readonly((pte_t *)pudp);
-}
-
-static inline bool kvm_s2pud_exec(pud_t *pudp)
-{
-	return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
-}
-
-static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
-{
-	return pud_mkyoung(pud);
-}
-
-static inline bool kvm_s2pud_young(pud_t pud)
-{
-	return pud_young(pud);
-}
-
-#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
-
-#ifdef __PAGETABLE_PMD_FOLDED
-#define hyp_pmd_table_empty(pmdp) (0)
-#else
-#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
-#endif
-
-#ifdef __PAGETABLE_PUD_FOLDED
-#define hyp_pud_table_empty(pudp) (0)
-#else
-#define hyp_pud_table_empty(pudp) kvm_page_empty(pudp)
-#endif
-
-#ifdef __PAGETABLE_P4D_FOLDED
-#define hyp_p4d_table_empty(p4dp) (0)
-#else
-#define hyp_p4d_table_empty(p4dp) kvm_page_empty(p4dp)
-#endif
 
 struct kvm;
 
@@ -325,77 +171,9 @@ static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
 	}
 }
 
-static inline void __kvm_flush_dcache_pte(pte_t pte)
-{
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
-		struct page *page = pte_page(pte);
-		kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
-	}
-}
-
-static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
-{
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
-		struct page *page = pmd_page(pmd);
-		kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
-	}
-}
-
-static inline void __kvm_flush_dcache_pud(pud_t pud)
-{
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
-		struct page *page = pud_page(pud);
-		kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
-	}
-}
-
 void kvm_set_way_flush(struct kvm_vcpu *vcpu);
 void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 
-static inline bool __kvm_cpu_uses_extended_idmap(void)
-{
-	return __cpu_uses_extended_idmap_level();
-}
-
-static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
-{
-	return idmap_ptrs_per_pgd;
-}
-
-/*
- * Can't use pgd_populate here, because the extended idmap adds an extra level
- * above CONFIG_PGTABLE_LEVELS (which is 2 or 3 if we're using the extended
- * idmap), and pgd_populate is only available if CONFIG_PGTABLE_LEVELS = 4.
- */
-static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
-				       pgd_t *hyp_pgd,
-				       pgd_t *merged_hyp_pgd,
-				       unsigned long hyp_idmap_start)
-{
-	int idmap_idx;
-	u64 pgd_addr;
-
-	/*
-	 * Use the first entry to access the HYP mappings. It is
-	 * guaranteed to be free, otherwise we wouldn't use an
-	 * extended idmap.
-	 */
-	VM_BUG_ON(pgd_val(merged_hyp_pgd[0]));
-	pgd_addr = __phys_to_pgd_val(__pa(hyp_pgd));
-	merged_hyp_pgd[0] = __pgd(pgd_addr | PMD_TYPE_TABLE);
-
-	/*
-	 * Create another extended level entry that points to the boot HYP map,
-	 * which contains an ID mapping of the HYP init code. We essentially
-	 * merge the boot and runtime HYP maps by doing so, but they don't
-	 * overlap anyway, so this is fine.
-	 */
-	idmap_idx = hyp_idmap_start >> VA_BITS;
-	VM_BUG_ON(pgd_val(merged_hyp_pgd[idmap_idx]));
-	pgd_addr = __phys_to_pgd_val(__pa(boot_hyp_pgd));
-	merged_hyp_pgd[idmap_idx] = __pgd(pgd_addr | PMD_TYPE_TABLE);
-}
-
 static inline unsigned int kvm_get_vmid_bits(void)
 {
 	int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
@@ -430,19 +208,17 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
 	return ret;
 }
 
-#ifdef CONFIG_KVM_INDIRECT_VECTORS
 /*
  * EL2 vectors can be mapped and rerouted in a number of ways,
  * depending on the kernel configuration and CPU present:
  *
- * - If the CPU has the ARM64_HARDEN_BRANCH_PREDICTOR cap, the
- *   hardening sequence is placed in one of the vector slots, which is
- *   executed before jumping to the real vectors.
+ * - If the CPU is affected by Spectre-v2, the hardening sequence is
+ *   placed in one of the vector slots, which is executed before jumping
+ *   to the real vectors.
  *
- * - If the CPU has both the ARM64_HARDEN_EL2_VECTORS cap and the
- *   ARM64_HARDEN_BRANCH_PREDICTOR cap, the slot containing the
- *   hardening sequence is mapped next to the idmap page, and executed
- *   before jumping to the real vectors.
+ * - If the CPU also has the ARM64_HARDEN_EL2_VECTORS cap, the slot
+ *   containing the hardening sequence is mapped next to the idmap page,
+ *   and executed before jumping to the real vectors.
  *
  * - If the CPU only has the ARM64_HARDEN_EL2_VECTORS cap, then an
  *   empty slot is selected, mapped next to the idmap page, and
@@ -452,19 +228,16 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
  * VHE, as we don't have hypervisor-specific mappings. If the system
  * is VHE and yet selects this capability, it will be ignored.
  */
-#include <asm/mmu.h>
-
 extern void *__kvm_bp_vect_base;
 extern int __kvm_harden_el2_vector_slot;
 
-/*  This is called on both VHE and !VHE systems */
 static inline void *kvm_get_hyp_vector(void)
 {
 	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
 	void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
 	int slot = -1;
 
-	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
+	if (cpus_have_const_cap(ARM64_SPECTRE_V2) && data->f