20 files changed, 463 insertions, 225 deletions

diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index a38dea6186..d61e44642f 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -3,7 +3,7 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-incdir := $(srctree)/$(src)/include
+incdir := $(src)/include
 subdir-asflags-y := -I$(incdir)
 subdir-ccflags-y := -I$(incdir)
 
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 61e6f3ba7b..e950875e31 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -25,3 +25,9 @@ SYM_FUNC_START(__sve_restore_state)
 	sve_load 0, x1, x2, 3
 	ret
 SYM_FUNC_END(__sve_restore_state)
+
+SYM_FUNC_START(__sve_save_state)
+	mov	x2, #1
+	sve_save 0, x1, x2, 3
+	ret
+SYM_FUNC_END(__sve_save_state)
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 961bbef104..d00093699a 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -135,9 +135,9 @@ static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 	if (!vcpu_get_flag(vcpu, DEBUG_DIRTY))
 		return;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
-	host_dbg = &vcpu->arch.host_debug_state.regs;
+	host_dbg = host_data_ptr(host_debug_state.regs);
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
 	__debug_save_state(host_dbg, host_ctxt);
@@ -154,9 +154,9 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 	if (!vcpu_get_flag(vcpu, DEBUG_DIRTY))
 		return;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
-	host_dbg = &vcpu->arch.host_debug_state.regs;
+	host_dbg = host_data_ptr(host_debug_state.regs);
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
 	__debug_save_state(guest_dbg, guest_ctxt);
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index e3fcf8c4d5..0c4de44534 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -27,6 +27,7 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_nested.h>
+#include <asm/kvm_ptrauth.h>
 #include <asm/fpsimd.h>
 #include <asm/debug-monitors.h>
 #include <asm/processor.h>
@@ -39,12 +40,6 @@ struct kvm_exception_table_entry {
 extern struct kvm_exception_table_entry __start___kvm_ex_table;
 extern struct kvm_exception_table_entry __stop___kvm_ex_table;
 
-/* Check whether the FP regs are owned by the guest */
-static inline bool guest_owns_fp_regs(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.fp_state == FP_STATE_GUEST_OWNED;
-}
-
 /* Save the 32-bit only FPSIMD system register state */
 static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 {
@@ -155,7 +150,7 @@ static inline bool cpu_has_amu(void)
 
 static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
 	CHECK_FGT_MASKS(HFGRTR_EL2);
@@ -191,7 +186,7 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 
 static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
 	if (!cpus_have_final_cap(ARM64_HAS_FGT))
@@ -226,13 +221,13 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 
 		write_sysreg(0, pmselr_el0);
 
-		hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+		hctxt = host_data_ptr(host_ctxt);
 		ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0);
 		write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
 		vcpu_set_flag(vcpu, PMUSERENR_ON_CPU);
 	}
 
-	vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
+	*host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
 	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
@@ -254,13 +249,13 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 
 static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 {
-	write_sysreg(vcpu->arch.mdcr_el2_host, mdcr_el2);
+	write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2);
 
 	write_sysreg(0, hstr_el2);
 	if (kvm_arm_support_pmu_v3()) {
 		struct kvm_cpu_context *hctxt;
 
-		hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+		hctxt = host_data_ptr(host_ctxt);
 		write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0);
 		vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU);
 	}
@@ -271,10 +266,8 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 	__deactivate_traps_hfgxtr(vcpu);
 }
 
-static inline void ___activate_traps(struct kvm_vcpu *vcpu)
+static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr)
 {
-	u64 hcr = vcpu->arch.hcr_el2;
-
 	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
 		hcr |= HCR_TVM;
 
@@ -323,10 +316,24 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
 	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
 	__sve_restore_state(vcpu_sve_pffr(vcpu),
-			    &vcpu->arch.ctxt.fp_regs.fpsr);
+			    &vcpu->arch.ctxt.fp_regs.fpsr,
+			    true);
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }
 
+static inline void __hyp_sve_save_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			 &sve_state->fpsr,
+			 true);
+}
+
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
+
 /*
  * We trap the first access to the FP/SIMD to save the host context and
  * restore the guest context lazily.
@@ -337,7 +344,6 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	bool sve_guest;
 	u8 esr_ec;
-	u64 reg;
 
 	if (!system_supports_fpsimd())
 		return false;
@@ -360,24 +366,15 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Valid trap.  Switch the context: */
 
 	/* First disable enough traps to allow us to update the registers */
-	if (has_vhe() || has_hvhe()) {
-		reg = CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN;
-		if (sve_guest)
-			reg |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
-
-		sysreg_clear_set(cpacr_el1, 0, reg);
-	} else {
-		reg = CPTR_EL2_TFP;
-		if (sve_guest)
-			reg |= CPTR_EL2_TZ;
-
-		sysreg_clear_set(cptr_el2, reg, 0);
-	}
+	if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
+		cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
+	else
+		cpacr_clear_set(0, CPACR_ELx_FPEN);
 	isb();
 
 	/* Write out the host state if it's in the registers */
-	if (vcpu->arch.fp_state == FP_STATE_HOST_OWNED)
-		__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
+	if (host_owns_fp_regs())
+		kvm_hyp_save_fpsimd_host(vcpu);
 
 	/* Restore the guest state */
 	if (sve_guest)
@@ -389,7 +386,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (!(read_sysreg(hcr_el2) & HCR_RW))
 		write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);
 
-	vcpu->arch.fp_state = FP_STATE_GUEST_OWNED;
+	*host_data_ptr(fp_owner) = FP_STATE_GUEST_OWNED;
 
 	return true;
 }
@@ -449,60 +446,6 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static inline bool esr_is_ptrauth_trap(u64 esr)
-{
-	switch (esr_sys64_to_sysreg(esr)) {
-	case SYS_APIAKEYLO_EL1:
-	case SYS_APIAKEYHI_EL1:
-	case SYS_APIBKEYLO_EL1:
-	case SYS_APIBKEYHI_EL1:
-	case SYS_APDAKEYLO_EL1:
-	case SYS_APDAKEYHI_EL1:
-	case SYS_APDBKEYLO_EL1:
-	case SYS_APDBKEYHI_EL1:
-	case SYS_APGAKEYLO_EL1:
-	case SYS_APGAKEYHI_EL1:
-		return true;
-	}
-
-	return false;
-}
-
-#define __ptrauth_save_key(ctxt, key)					\
-	do {								\
-	u64 __val;                                                      \
-	__val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);                \
-	ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val;                   \
-	__val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);                \
-	ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val;                   \
-} while(0)
-
-DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
-
-static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code)
-{
-	struct kvm_cpu_context *ctxt;
-	u64 val;
-
-	if (!vcpu_has_ptrauth(vcpu))
-		return false;
-
-	ctxt = this_cpu_ptr(&kvm_hyp_ctxt);
-	__ptrauth_save_key(ctxt, APIA);
-	__ptrauth_save_key(ctxt, APIB);
-	__ptrauth_save_key(ctxt, APDA);
-	__ptrauth_save_key(ctxt, APDB);
-	__ptrauth_save_key(ctxt, APGA);
-
-	vcpu_ptrauth_enable(vcpu);
-
-	val = read_sysreg(hcr_el2);
-	val |= (HCR_API | HCR_APK);
-	write_sysreg(val, hcr_el2);
-
-	return true;
-}
-
 static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_context *ctxt;
@@ -590,9 +533,6 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
 	    __vgic_v3_perform_cpuif_access(vcpu) == 1)
 		return true;
 
-	if (esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
-		return kvm_hyp_handle_ptrauth(vcpu, exit_code);
-
 	if (kvm_hyp_handle_cntpct(vcpu))
 		return true;
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index 82b3d62538..24a9a8330d 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -53,6 +53,11 @@ pkvm_hyp_vcpu_to_hyp_vm(struct pkvm_hyp_vcpu *hyp_vcpu)
 	return container_of(hyp_vcpu->vcpu.kvm, struct pkvm_hyp_vm, kvm);
 }
 
+static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	return vcpu_is_protected(&hyp_vcpu->vcpu);
+}
+
 void pkvm_hyp_vm_table_init(void *tbl);
 
 int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 2250253a64..50fa0ffb6b 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -97,16 +97,3 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI)
 # causes a build failure. Remove profile optimization flags.
 KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS))
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
-
-# KVM nVHE code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-KCSAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n
-
-# Skip objtool checking for this directory because nVHE code is compiled with
-# non-standard build rules.
-OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 7746ea507b..53efda0235 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -83,10 +83,10 @@ void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE))
-		__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+		__debug_save_spe(host_data_ptr(host_debug_state.pmscr_el1));
 	/* Disable and flush Self-Hosted Trace generation */
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE))
-		__debug_save_trace(&vcpu->arch.host_debug_state.trfcr_el1);
+		__debug_save_trace(host_data_ptr(host_debug_state.trfcr_el1));
 }
 
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
@@ -97,9 +97,9 @@ void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE))
-		__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+		__debug_restore_spe(*host_data_ptr(host_debug_state.pmscr_el1));
 	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE))
-		__debug_restore_trace(vcpu->arch.host_debug_state.trfcr_el1);
+		__debug_restore_trace(*host_data_ptr(host_debug_state.trfcr_el1));
 }
 
 void __debug_switch_to_host(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index 320f2eaa14..efb053af33 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -177,6 +177,14 @@ static void ffa_retrieve_req(struct arm_smccc_res *res, u32 len)
 			  res);
 }
 
+static void ffa_rx_release(struct arm_smccc_res *res)
+{
+	arm_smccc_1_1_smc(FFA_RX_RELEASE,
+			  0, 0,
+			  0, 0, 0, 0, 0,
+			  res);
+}
+
 static void do_ffa_rxtx_map(struct arm_smccc_res *res,
 			    struct kvm_cpu_context *ctxt)
 {
@@ -543,16 +551,19 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res,
 	if (WARN_ON(offset > len ||
 		    fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)) {
 		ret = FFA_RET_ABORTED;
+		ffa_rx_release(res);
 		goto out_unlock;
 	}
 
 	if (len > ffa_desc_buf.len) {
 		ret = FFA_RET_NO_MEMORY;
+		ffa_rx_release(res);
 		goto out_unlock;
 	}
 
 	buf = ffa_desc_buf.buf;
 	memcpy(buf, hyp_buffers.rx, fraglen);
+	ffa_rx_release(res);
 
 	for (fragoff = fraglen; fragoff < len; fragoff += fraglen) {
 		ffa_mem_frag_rx(res, handle_lo, handle_hi, fragoff);
@@ -563,6 +574,7 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res,
 
 		fraglen = res->a3;
 		memcpy((void *)buf + fragoff, hyp_buffers.rx, fraglen);
+		ffa_rx_release(res);
 	}
 
 	ffa_mem_reclaim(res, handle_lo, handle_hi, flags);
@@ -600,7 +612,6 @@ static bool ffa_call_supported(u64 func_id)
 	case FFA_MSG_POLL:
 	case FFA_MSG_WAIT:
 	/* 32-bit variants of 64-bit calls */
-	case FFA_MSG_SEND_DIRECT_REQ:
 	case FFA_MSG_SEND_DIRECT_RESP:
 	case FFA_RXTX_MAP:
 	case FFA_MEM_DONATE:
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 2385fd03ed..f43d845f3c 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -23,26 +23,84 @@ DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
 
+static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
+{
+	__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+	/*
+	 * On saving/restoring guest sve state, always use the maximum VL for
+	 * the guest. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) guest VL.
+	 */
+	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
+	__sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+}
+
+static void __hyp_sve_restore_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	/*
+	 * On saving/restoring host sve state, always use the maximum VL for
+	 * the host. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) host VL.
+	 *
+	 * Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length
+	 * supported by the system (or limited at EL3).
+	 */
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			    &sve_state->fpsr,
+			    true);
+	write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR);
+}
+
+static void fpsimd_sve_flush(void)
+{
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
+static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
+{
+	if (!guest_owns_fp_regs())
+		return;
+
+	cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
+	isb();
+
+	if (vcpu_has_sve(vcpu))
+		__hyp_sve_save_guest(vcpu);
+	else
+		__fpsimd_save_state(&vcpu->arch.ctxt.fp_regs);
+
+	if (system_supports_sve())
+		__hyp_sve_restore_host();
+	else
+		__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
+
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
 static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
 
+	fpsimd_sve_flush();
+
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
 
 	hyp_vcpu->vcpu.arch.sve_state	= kern_hyp_va(host_vcpu->arch.sve_state);
-	hyp_vcpu->vcpu.arch.sve_max_vl	= host_vcpu->arch.sve_max_vl;
+	/* Limit guest vector length to the maximum supported by the host.  */
+	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
 
 	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;
 
 	hyp_vcpu->vcpu.arch.hcr_el2	= host_vcpu->arch.hcr_el2;
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
-	hyp_vcpu->vcpu.arch.cptr_el2	= host_vcpu->arch.cptr_el2;
 
 	hyp_vcpu->vcpu.arch.iflags	= host_vcpu->arch.iflags;
-	hyp_vcpu->vcpu.arch.fp_state	= host_vcpu->arch.fp_state;
 
 	hyp_vcpu->vcpu.arch.debug_ptr	= kern_hyp_va(host_vcpu->arch.debug_ptr);
-	hyp_vcpu->vcpu.arch.host_fpsimd_state = host_vcpu->arch.host_fpsimd_state;
 
 	hyp_vcpu->vcpu.arch.vsesr_el2	= host_vcpu->arch.vsesr_el2;
 
@@ -56,15 +114,15 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
 	unsigned int i;
 
+	fpsimd_sve_sync(&hyp_vcpu->vcpu);
+
 	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;
 
 	host_vcpu->arch.hcr_el2		= hyp_vcpu->vcpu.arch.hcr_el2;
-	host_vcpu->arch.cptr_el2	= hyp_vcpu->vcpu.arch.cptr_el2;
 
 	host_vcpu->arch.fault		= hyp_vcpu->vcpu.arch.fault;
 
 	host_vcpu->arch.iflags		= hyp_vcpu->vcpu.arch.iflags;
-	host_vcpu->arch.fp_state	= hyp_vcpu->vcpu.arch.fp_state;
 
 	host_cpu_if->vgic_hcr		= hyp_cpu_if->vgic_hcr;
 	for (i = 0; i < hyp_cpu_if->used_lrs; ++i)
@@ -82,6 +140,17 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 		struct pkvm_hyp_vcpu *hyp_vcpu;
 		struct kvm *host_kvm;
 
+		/*
+		 * KVM (and pKVM) doesn't support SME guests for now, and
+		 * ensures that SME features aren't enabled in pstate when
+		 * loading a vcpu. Therefore, if SME features enabled the host
+		 * is misbehaving.
+		 */
+		if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
 		host_kvm = kern_hyp_va(host_vcpu->kvm);
 		hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
 					      host_vcpu->vcpu_idx);
@@ -178,16 +247,6 @@ static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
 }
 
-static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
-{
-	cpu_reg(host_ctxt, 1) = __vgic_v3_read_vmcr();
-}
-
-static void handle___vgic_v3_write_vmcr(struct kvm_cpu_context *host_ctxt)
-{
-	__vgic_v3_write_vmcr(cpu_reg(host_ctxt, 1));
-}
-
 static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt)
 {
 	__vgic_v3_init_lrs();
@@ -198,18 +257,18 @@ static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2();
 }
 
-static void handle___vgic_v3_save_aprs(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_save_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
 
-	__vgic_v3_save_aprs(kern_hyp_va(cpu_if));
+	__vgic_v3_save_vmcr_aprs(kern_hyp_va(cpu_if));
 }
 
-static void handle___vgic_v3_restore_aprs(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_restore_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
 
-	__vgic_v3_restore_aprs(kern_hyp_va(cpu_if));
+	__vgic_v3_restore_vmcr_aprs(kern_hyp_va(cpu_if));
 }
 
 static void handle___pkvm_init(struct kvm_cpu_context *host_ctxt)
@@ -340,10 +399,8 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_range),
 	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
-	HANDLE_FUNC(__vgic_v3_read_vmcr),
-	HANDLE_FUNC(__vgic_v3_write_vmcr),
-	HANDLE_FUNC(__vgic_v3_save_aprs),
-	HANDLE_FUNC(__vgic_v3_restore_aprs),
+	HANDLE_FUNC(__vgic_v3_save_vmcr_aprs),
+	HANDLE_FUNC(__vgic_v3_restore_vmcr_aprs),
 	HANDLE_FUNC(__pkvm_vcpu_init_traps),
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
@@ -420,11 +477,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
 		handle_host_smc(host_ctxt);
 		break;
 	case ESR_ELx_EC_SVE:
-		if (has_hvhe())
-			sysreg_clear_set(cpacr_el1, 0, (CPACR_EL1_ZEN_EL1EN |
-							CPACR_EL1_ZEN_EL0EN));
-		else
-			sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
+		cpacr_clear_set(0, CPACR_ELx_ZEN);
 		isb();
 		sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
 		break;
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 861c76021a..caba3e4bd0 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -533,7 +533,13 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 	int ret = 0;
 
 	esr = read_sysreg_el2(SYS_ESR);
-	BUG_ON(!__get_fault_info(esr, &fault));
+	if (!__get_fault_info(esr, &fault)) {
+		/*
+		 * We've presumably raced with a page-table change which caused
+		 * AT to fail, try again.
+		 */
+		return;
+	}
 
 	addr = (fault.hpfar_el2 & HPFAR_MASK) << 8;
 	ret = host_stage2_idmap(addr);
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 26dd9a20ad..95cf185742 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -18,6 +18,8 @@ unsigned long __icache_flags;
 /* Used by kvm_get_vttbr(). */
 unsigned int kvm_arm_vmid_bits;
 
+unsigned int kvm_host_sve_max_vl;
+
 /*
  * Set trap register values based on features in ID_AA64PFR0.
  */
@@ -63,7 +65,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
 	/* Trap SVE */
 	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) {
 		if (has_hvhe())
-			cptr_clear |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			cptr_clear |= CPACR_ELx_ZEN;
 		else
 			cptr_set |= CPTR_EL2_TZ;
 	}
@@ -200,7 +202,7 @@ static void pvm_init_trap_regs(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Initialize trap register values for protected VMs.
+ * Initialize trap register values in protected mode.
  */
 void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu)
 {
@@ -430,6 +432,7 @@ static void *map_donated_memory(unsigned long host_va, size_t size)
 
 static void __unmap_donated_memory(void *va, size_t size)
 {
+	kvm_flush_dcache_to_poc(va, size);
 	WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(va),
 				       PAGE_ALIGN(size) >> PAGE_SHIFT));
 }
@@ -574,6 +577,8 @@ unlock:
 	if (ret)
 		unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));
 
+	hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu);
+
 	return ret;
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index d57bcb6ab9..dfe8fe0f7e 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -205,7 +205,7 @@ asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 	struct psci_boot_args *boot_args;
 	struct kvm_cpu_context *host_ctxt;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 
 	if (is_cpu_on)
 		boot_args = this_cpu_ptr(&cpu_on_args);
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index bc58d1b515..f4350ba07b 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -67,6 +67,28 @@ static int divide_memory_pool(void *virt, unsigned long size)
 	return 0;
 }
 
+static int pkvm_create_host_sve_mappings(void)
+{
+	void *start, *end;
+	int ret, i;
+
+	if (!system_supports_sve())
+		return 0;
+
+	for (i = 0; i < hyp_nr_cpus; i++) {
+		struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
+		struct cpu_sve_state *sve_state = host_data->sve_state;
+
+		start = kern_hyp_va(sve_state);
+		end = start + PAGE_ALIGN(pkvm_host_sve_state_size());
+		ret = pkvm_create_mappings(start, end, PAGE_HYP);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 				 unsigned long *per_cpu_base,
 				 u32 hyp_va_bits)
@@ -125,6 +147,8 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 			return ret;
 	}
 
+	pkvm_create_host_sve_mappings();
+
 	/*
 	 * Map the host sections RO in the hypervisor, but transfer the
 	 * ownership from the host to the hypervisor itself to make sure they
@@ -257,8 +281,7 @@ static int fix_hyp_pgtable_refcnt(void)
 
 void __noreturn __pkvm_init_finalise(void)
 {
-	struct kvm_host_data *host_data = this_cpu_ptr(&kvm_host_data);
-	struct kvm_cpu_context *host_ctxt = &host_data->host_ctxt;
+	struct kvm_cpu_context *host_ctxt = host_data_ptr(host_ctxt);
 	unsigned long nr_pages, reserved_pages, pfn;
 	int ret;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index c50f8459e4..6af179c635 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -40,7 +40,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
-	___activate_traps(vcpu);
+	___activate_traps(vcpu, vcpu->arch.hcr_el2);
 	__activate_traps_common(vcpu);
 
 	val = vcpu->arch.cptr_el2;
@@ -48,15 +48,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA;
 	if (cpus_have_final_cap(ARM64_SME)) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN);
+			val &= ~CPACR_ELx_SMEN;
 		else
 			val |= CPTR_EL2_TSM;
 	}
 
-	if (!guest_owns_fp_regs(vcpu)) {
+	if (!guest_owns_fp_regs()) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
-				 CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
+			val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN);
 		else
 			val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
 
@@ -182,6 +181,25 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
 		kvm_handle_pvm_sysreg(vcpu, exit_code));
 }
 
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Non-protected kvm relies on the host restoring its sve state.
+	 * Protected kvm restores the host's sve state as not to reveal that
+	 * fpsimd was used by a guest nor leak upper sve bits.
+	 */
+	if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) {
+		__hyp_sve_save_host();
+
+		/* Re-enable SVE traps if not supported for the guest vcpu. */
+		if (!vcpu_has_sve(vcpu))
+			cpacr_clear_set(CPACR_ELx_ZEN, 0);
+
+	} else {
+		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+	}
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
@@ -191,7 +209,6 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
-	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
 	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
 };
 
@@ -203,13 +220,12 @@ static const exit_handler_fn pvm_exit_handlers[] = {
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
-	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
 	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
 };
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 {
-	if (unlikely(kvm_vm_is_protected(kern_hyp_va(vcpu->kvm))))
+	if (unlikely(vcpu_is_protected(vcpu)))
 		return pvm_exit_handlers;
 
 	return hyp_exit_handlers;
@@ -228,9 +244,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
  */
 static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-
-	if (kvm_vm_is_protected(kvm) && vcpu_mode_is_32bit(vcpu)) {
+	if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) {
 		/*
 		 * As we have caught the guest red-handed, decide that it isn't
 		 * fit for purpose anymore by making the vcpu invalid. The VMM
@@ -264,7 +278,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		pmr_sync();
 	}
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	host_ctxt->__hyp_running_vcpu = vcpu;
 	guest_ctxt = &vcpu->arch.ctxt;
 
@@ -337,7 +351,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	__sysreg_restore_state_nvhe(host_ctxt);
 
-	if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)
+	if (guest_owns_fp_regs())
 		__fpsimd_save_fpexc32(vcpu);
 
 	__debug_switch_to_host(vcpu);
@@ -367,7 +381,7 @@ asmlinkage void __noreturn hyp_panic(void)
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	vcpu = host_ctxt->__hyp_running_vcpu;
 
 	if (vcpu) {
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 2fc68da403..ca3c09df8d 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -11,13 +11,23 @@
 #include <nvhe/mem_protect.h>
 
 struct tlb_inv_context {
-	u64		tcr;
+	struct kvm_s2_mmu	*mmu;
+	u64			tcr;
+	u64			sctlr;
 };
 
-static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
-				  struct tlb_inv_context *cxt,
-				  bool nsh)
+static void enter_vmid_context(struct kvm_s2_mmu *mmu,
+			       struct tlb_inv_context *cxt,
+			       bool nsh)
 {
+	struct kvm_s2_mmu *host_s2_mmu = &host_mmu.arch.mmu;
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_vcpu *vcpu;
+
+	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	vcpu = host_ctxt->__hyp_running_vcpu;
+	cxt->mmu = NULL;
+
 	/*
 	 * We have two requirements:
 	 *
@@ -40,20 +50,55 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 	else
 		dsb(ish);
 
+	/*
+	 * If we're already in the desired context, then there's nothing to do.
+	 */
+	if (vcpu) {
+		/*
+		 * We're in guest context. However, for this to work, this needs
+		 * to be called from within __kvm_vcpu_run(), which ensures that
+		 * __hyp_running_vcpu is set to the current guest vcpu.
+		 */
+		if (mmu == vcpu->arch.hw_mmu || WARN_ON(mmu != host_s2_mmu))
+			return;
+
+		cxt->mmu = vcpu->arch.hw_mmu;
+	} else {
+		/* We're in host context. */
+		if (mmu == host_s2_mmu)
+			return;
+
+		cxt->mmu = host_s2_mmu;
+	}
+
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		u64 val;
 
 		/*
 		 * For CPUs that are affected by ARM 1319367, we need to
-		 * avoid a host Stage-1 walk while we have the guest's
-		 * VMID set in the VTTBR in order to invalidate TLBs.
-		 * We're guaranteed that the S1 MMU is enabled, so we can
-		 * simply set the EPD bits to avoid any further TLB fill.
+		 * avoid a Stage-1 walk with the old VMID while we have
+		 * the new VMID set in the VTTBR in order to invalidate TLBs.
+		 * We're guaranteed that the host S1 MMU is enabled, so
+		 * we can simply set the EPD bits to avoid any further
+		 * TLB fill. For guests, we ensure that the S1 MMU is
+		 * temporarily enabled in the next context.
 		 */
 		val = cxt->tcr = read_sysreg_el1(SYS_TCR);
 		val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
 		write_sysreg_el1(val, SYS_TCR);
 		isb();
+
+		if (vcpu) {
+			val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
+			if (!(val & SCTLR_ELx_M)) {
+				val |= SCTLR_ELx_M;
+				write_sysreg_el1(val, SYS_SCTLR);
+				isb();
+			}
+		} else {
+			/* The host S1 MMU is always enabled. */
+			cxt->sctlr = SCTLR_ELx_M;
+		}
 	}
 
 	/*
@@ -62,18 +107,40 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 	 * ensuring that we always have an ISB, but not two ISBs back
 	 * to back.
 	 */
-	__load_stage2(mmu, kern_hyp_va(mmu->arch));
+	if (vcpu)
+		__load_host_stage2();
+	else
+		__load_stage2(mmu, kern_hyp_va(mmu->arch));
+
 	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
-static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
+static void exit_vmid_context(struct tlb_inv_context *cxt)
 {
-	__load_host_stage2();
+	struct kvm_s2_mmu *mmu = cxt->mmu;
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_vcpu *vcpu;
+
+	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	vcpu = host_ctxt->__hyp_running_vcpu;
+
+	if (!mmu)
+		return;
+
+	if (vcpu)
+		__load_stage2(mmu, kern_hyp_va(mmu->arch));
+	else
+		__load_host_stage2();
 
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
-		/* Ensure write of the host VMID */
+		/* Ensure write of the old VMID */
 		isb();
-		/* Restore the host's TCR_EL1 */
+
+		if (!(cxt->sctlr & SCTLR_ELx_M)) {
+			write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
+			isb();
+		}
+
 		write_sysreg_el1(cxt->tcr, SYS_TCR);
 	}
 }
@@ -84,7 +151,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt, false);
+	enter_vmid_context(mmu, &cxt, false);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -105,7 +172,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
@@ -114,7 +181,7 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt, true);
+	enter_vmid_context(mmu, &cxt, true);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -135,7 +202,7 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
@@ -152,7 +219,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	start = round_down(start, stride);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt, false);
+	enter_vmid_context(mmu, &cxt, false);
 
 	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
 				TLBI_TTL_UNKNOWN);
@@ -162,7 +229,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
@@ -170,13 +237,13 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt, false);
+	enter_vmid_context(mmu, &cxt, false);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
@@ -184,19 +251,19 @@ void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt, false);
+	enter_vmid_context(mmu, &cxt, false);
 
 	__tlbi(vmalle1);
 	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_flush_vm_context(void)
 {
-	/* Same remark as in __tlb_switch_to_guest() */
+	/* Same remark as in enter_vmid_context() */
 	dsb(ish);
 	__tlbi(alle1is);
 	dsb(ish);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 5a59ef88b6..9e2bbee774 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -914,12 +914,12 @@ static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx,
 static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte)
 {
 	u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR;
-	return memattr == KVM_S2_MEMATTR(pgt, NORMAL);
+	return kvm_pte_valid(pte) && memattr == KVM_S2_MEMATTR(pgt, NORMAL);
 }
 
 static bool stage2_pte_executable(kvm_pte_t pte)
 {
-	return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
+	return kvm_pte_valid(pte) && !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
 }
 
 static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx,
@@ -979,6 +979,21 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!stage2_pte_needs_update(ctx->old, new))
 		return -EAGAIN;
 
+	/* If we're only changing software bits, then store them and go! */
+	if (!kvm_pgtable_walk_shared(ctx) &&
+	    !((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) {
+		bool old_is_counted = stage2_pte_is_counted(ctx->old);
+
+		if (old_is_counted != stage2_pte_is_counted(new)) {
+			if (old_is_counted)
+				mm_ops->put_page(ctx->ptep);
+			else
+				mm_ops->get_page(ctx->ptep);
+		}
+		WARN_ON_ONCE(!stage2_try_set_pte(ctx, new));
+		return 0;
+	}
+
 	if (!stage2_try_break_pte(ctx, data->mmu))
 		return -EAGAIN;
 
@@ -1370,7 +1385,7 @@ static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	struct kvm_pgtable *pgt = ctx->arg;
 	struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
 
-	if (!kvm_pte_valid(ctx->old) || !stage2_pte_cacheable(pgt, ctx->old))
+	if (!stage2_pte_cacheable(pgt, ctx->old))
 		return 0;
 
 	if (mm_ops->dcache_clean_inval_poc)
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 6cb638b184..7b397fad26 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -330,7 +330,7 @@ void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
 		write_gicreg(0, ICH_HCR_EL2);
 }
 
-void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
+static void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -363,7 +363,7 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 	}
 }
 
-void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
+static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 {
 	u64 val;
 	u32 nr_pre_bits;
@@ -455,16 +455,35 @@ u64 __vgic_v3_get_gic_config(void)
 	return val;
 }
 
-u64 __vgic_v3_read_vmcr(void)
+static u64 __vgic_v3_read_vmcr(void)
 {
 	return read_gicreg(ICH_VMCR_EL2);
 }
 
-void __vgic_v3_write_vmcr(u32 vmcr)
+static void __vgic_v3_write_vmcr(u32 vmcr)
 {
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
+void __vgic_v3_save_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
+{
+	__vgic_v3_save_aprs(cpu_if);
+	if (cpu_if->vgic_sre)
+		cpu_if->vgic_vmcr = __vgic_v3_read_vmcr();
+}
+
+void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
+{
+	/*
+	 * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen
+	 * is dependent on ICC_SRE_EL1.SRE, and we have to perform the
+	 * VMCR_EL2 save/restore in the world switch.
+	 */
+	if (cpu_if->vgic_sre)
+		__vgic_v3_write_vmcr(cpu_if->vgic_vmcr);
+	__vgic_v3_restore_aprs(cpu_if);
+}
+
 static int __vgic_v3_bpr_min(void)
 {
 	/* See Pseudocode for VPriorityGroup */
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 1581df6aec..8fbb6a2e05 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -33,11 +33,43 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data);
 DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
 
+/*
+ * HCR_EL2 bits that the NV guest can freely change (no RES0/RES1
+ * semantics, irrespective of the configuration), but that cannot be
+ * applied to the actual HW as things would otherwise break badly.
+ *
+ * - TGE: we want the guest to use EL1, which is incompatible with
+ *   this bit being set
+ *
+ * - API/APK: they are already accounted for by vcpu_load(), and can
+ *   only take effect across a load/put cycle (such as ERET)
+ */
+#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK)
+
+static u64 __compute_hcr(struct kvm_vcpu *vcpu)
+{
+	u64 hcr = vcpu->arch.hcr_el2;
+
+	if (!vcpu_has_nv(vcpu))
+		return hcr;
+
+	if (is_hyp_ctxt(vcpu)) {
+		hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB;
+
+		if (!vcpu_el2_e2h_is_set(vcpu))
+			hcr |= HCR_NV1;
+
+		write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2);
+	}
+
+	return hcr | (__vcpu_sys_reg(vcpu, HCR_EL2) & ~NV_HCR_GUEST_EXCLUDE);
+}
+
 static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
 
-	___activate_traps(vcpu);
+	___activate_traps(vcpu, __compute_hcr(vcpu));
 
 	if (has_cntpoff()) {
 		struct timer_map map;
@@ -61,8 +93,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_ELx_TTA;
-	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
-		 CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
+	val &= ~(CPACR_ELx_ZEN | CPACR_ELx_SMEN);
 
 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
@@ -75,11 +106,11 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	val |= CPTR_EL2_TAM;
 
-	if (guest_owns_fp_regs(vcpu)) {
+	if (guest_owns_fp_regs()) {
 		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			val |= CPACR_ELx_ZEN;
 	} else {
-		val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+		val &= ~CPACR_ELx_FPEN;
 		__activate_traps_fpsimd32(vcpu);
 	}
 
@@ -162,6 +193,8 @@ static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu)
 
 void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
 {
+	host_data_ptr(host_ctxt)->__hyp_running_vcpu = vcpu;
+
 	__vcpu_load_switch_sysregs(vcpu);
 	__vcpu_load_activate_traps(vcpu);
 	__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
@@ -171,6 +204,66 @@ void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
 {
 	__vcpu_put_deactivate_traps(vcpu);
 	__vcpu_put_switch_sysregs(vcpu);
+
+	host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL;
+}
+
+static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	u64 spsr, elr, mode;
+
+	/*
+	 * Going through the whole put/load motions is a waste of time
+	 * if this is a VHE guest hypervisor returning to its own
+	 * userspace, or the hypervisor performing a local exception
+	 * return. No need to save/restore registers, no need to
+	 * switch S2 MMU. Just do the canonical ERET.
+	 *
+	 * Unless the trap has to be forwarded further down the line,
+	 * of course...
+	 */
+	if ((__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) ||
+	    (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_ERET))
+		return false;
+
+	spsr = read_sysreg_el1(SYS_SPSR);
+	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	switch (mode) {
+	case PSR_MODE_EL0t:
+		if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
+			return false;
+		break;
+	case PSR_MODE_EL2t:
+		mode = PSR_MODE_EL1t;
+		break;
+	case PSR_MODE_EL2h:
+		mode = PSR_MODE_EL1h;
+		break;
+	default:
+		return false;
+	}
+
+	/* If ERETAx fails, take the slow path */
+	if (esr_iss_is_eretax(esr)) {
+		if (!(vcpu_has_ptrauth(vcpu) && kvm_auth_eretax(vcpu, &elr)))
+			return false;
+	} else {
+		elr = read_sysreg_el1(SYS_ELR);
+	}
+
+	spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+
+	write_sysreg_el2(spsr, SYS_SPSR);
+	write_sysreg_el2(elr, SYS_ELR);
+
+	return true;
+}
+
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
 }
 
 static const exit_handler_fn hyp_exit_handlers[] = {
@@ -182,7 +275,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
-	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+	[ESR_ELx_EC_ERET]		= kvm_hyp_handle_eret,
 	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
 };
 
@@ -197,7 +290,7 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 	 * If we were in HYP context on entry, adjust the PSTATE view
 	 * so that the usual helpers work correctly.
 	 */
-	if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) {
+	if (vcpu_has_nv(vcpu) && (read_sysreg(hcr_el2) & HCR_NV)) {
 		u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
 
 		switch (mode) {
@@ -221,8 +314,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	struct kvm_cpu_context *guest_ctxt;
 	u64 exit_code;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
-	host_ctxt->__hyp_running_vcpu = vcpu;
+	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
 
 	sysreg_save_host_state_vhe(host_ctxt);
@@ -240,11 +332,6 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
-	if (is_hyp_ctxt(vcpu))
-		vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT);
-	else
-		vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT);
-
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
@@ -258,7 +345,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	sysreg_restore_host_state_vhe(host_ctxt);
 
-	if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)
+	if (guest_owns_fp_regs())
 		__fpsimd_save_fpexc32(vcpu);
 
 	__debug_switch_to_host(vcpu);
@@ -306,7 +393,7 @@ static void __hyp_call_panic(u64 spsr, u64 elr, u64 par)
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	vcpu = host_ctxt->__hyp_running_vcpu;
 
 	__deactivate_traps(vcpu);
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index a8b9ea4967..e12bd7d6d2 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -67,7 +67,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	__sysreg_save_user_state(host_ctxt);
 
 	/*
@@ -110,7 +110,7 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 
 	__sysreg_save_el1_state(guest_ctxt);
 	__sysreg_save_user_state(guest_ctxt);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 1a60b95381..5fa0359f3a 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -17,8 +17,8 @@ struct tlb_inv_context {
 	u64			sctlr;
 };
 
-static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
-				  struct tlb_inv_context *cxt)
+static void enter_vmid_context(struct kvm_s2_mmu *mmu,
+			       struct tlb_inv_context *cxt)
 {
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 	u64 val;
@@ -67,7 +67,7 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 	isb();
 }
 
-static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
+static void exit_vmid_context(struct tlb_inv_context *cxt)
 {
 	/*
 	 * We're done with the TLB operation, let's restore the host's
@@ -97,7 +97,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -118,7 +118,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
@@ -129,7 +129,7 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	dsb(nshst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -150,7 +150,7 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
@@ -169,7 +169,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
 				TLBI_TTL_UNKNOWN);
@@ -179,7 +179,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
@@ -189,13 +189,13 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
@@ -203,14 +203,14 @@ void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_flush_vm_context(void)