diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 998b2a3f615a..144a757e937f 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -50,7 +50,6 @@
 	 * effectively VHE-only or not.
 	 */
 	msr_hcr_el2 x0		// Setup HCR_EL2 as nVHE
-	isb
 	mov	x1, #1		// Write something to FAR_EL1
 	msr	far_el1, x1
 	isb
@@ -64,7 +63,6 @@
 .LnE2H0_\@:
 	orr	x0, x0, #HCR_E2H
 	msr_hcr_el2 x0
-	isb
 .LnVHE_\@:
 .endm
 
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 724319298e71..93371b6138d1 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -301,7 +301,8 @@ asmlinkage void __noreturn hyp_panic_bad_stack(void);
 asmlinkage void kvm_unexpected_el2_exception(void);
 struct kvm_cpu_context;
 void handle_trap(struct kvm_cpu_context *host_ctxt);
-asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on);
+asmlinkage void __noreturn __kvm_host_psci_cpu_on_entry(void);
+asmlinkage void __noreturn __kvm_host_psci_cpu_resume_entry(void);
 void __noreturn __pkvm_init_finalise(void);
 void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc);
 void kvm_patch_vector_branch(struct alt_instr *alt,
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 938cdb248f83..736561480f36 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1121,11 +1121,9 @@
 	.macro	msr_hcr_el2, reg
 #if IS_ENABLED(CONFIG_AMPERE_ERRATUM_AC04_CPU_23)
 	dsb	nsh
-	msr	hcr_el2, \reg
-	isb
-#else
-	msr	hcr_el2, \reg
 #endif
+	msr	hcr_el2, \reg
+	isb			// Required by AMPERE_ERRATUM_AC04_CPU_23
 	.endm
 #else
 
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 085bc9972f6b..634ddc904244 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -103,7 +103,6 @@ SYM_CODE_START_LOCAL(__finalise_el2)
 	// Engage the VHE magic!
 	mov_q	x0, HCR_HOST_VHE_FLAGS
 	msr_hcr_el2 x0
-	isb
 
 	// Use the EL1 allocated stack, per-cpu offset
 	mrs	x0, sp_el1
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 3092befcd97c..f337770ec459 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -125,7 +125,6 @@ SYM_FUNC_START(__hyp_do_panic)
 	mrs	x0, hcr_el2
 	bic	x0, x0, #HCR_VM
 	msr_hcr_el2 x0
-	isb
 	tlbi	vmalls12e1
 	dsb	nsh
 #endif
@@ -291,13 +290,3 @@ SYM_CODE_START(__kvm_hyp_host_forward_smc)
 
 	ret
 SYM_CODE_END(__kvm_hyp_host_forward_smc)
-
-/*
- * kvm_host_psci_cpu_entry is called through br instruction, which requires
- * bti j instruction as compilers (gcc and llvm) doesn't insert bti j for external
- * functions, but bti c instead.
- */
-SYM_CODE_START(kvm_host_psci_cpu_entry)
-       bti j
-       b __kvm_host_psci_cpu_entry
-SYM_CODE_END(kvm_host_psci_cpu_entry)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 0d42eedc7167..64296b31da73 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -173,9 +173,8 @@ SYM_CODE_END(___kvm_hyp_init)
  * x0: struct kvm_nvhe_init_params PA
  */
 SYM_CODE_START(kvm_hyp_cpu_entry)
-	mov	x1, #1				// is_cpu_on = true
+	ldr	x29, =__kvm_host_psci_cpu_on_entry
 	b	__kvm_hyp_init_cpu
-SYM_CODE_END(kvm_hyp_cpu_entry)
 
 /*
  * PSCI CPU_SUSPEND / SYSTEM_SUSPEND entry point
@@ -183,32 +182,17 @@ SYM_CODE_END(kvm_hyp_cpu_entry)
  * x0: struct kvm_nvhe_init_params PA
  */
 SYM_CODE_START(kvm_hyp_cpu_resume)
-	mov	x1, #0				// is_cpu_on = false
-	b	__kvm_hyp_init_cpu
-SYM_CODE_END(kvm_hyp_cpu_resume)
+	ldr	x29, =__kvm_host_psci_cpu_resume_entry
 
-/*
- * Common code for CPU entry points. Initializes EL2 state and
- * installs the hypervisor before handing over to a C handler.
- *
- * x0: struct kvm_nvhe_init_params PA
- * x1: bool is_cpu_on
- */
-SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
+SYM_INNER_LABEL(__kvm_hyp_init_cpu, SYM_L_LOCAL)
 	mov	x28, x0				// Stash arguments
-	mov	x29, x1
 
 	/* Check that the core was booted in EL2. */
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
-	b.eq	2f
+	b.ne	1f
 
-	/* The core booted in EL1. KVM cannot be initialized on it. */
-1:	wfe
-	wfi
-	b	1b
-
-2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
+	msr	SPsel, #1			// We want to use SP_EL2
 
 	init_el2_hcr	0
 
@@ -218,11 +202,16 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 	mov	x0, x28
 	bl	___kvm_hyp_init			// Clobbers x0..x2
 
-	/* Leave idmap. */
-	mov	x0, x29
-	ldr	x1, =kvm_host_psci_cpu_entry
-	br	x1
-SYM_CODE_END(__kvm_hyp_init_cpu)
+	/* Leave idmap -- using BLR is OK, LR is restored from host context */
+	blr	x29
+
+	// The core booted in EL1, or the C code unexpectedly returned.
+	// Either way, KVM cannot be initialized on it.
+1:	wfe
+	wfi
+	b	1b
+SYM_CODE_END(kvm_hyp_cpu_resume)
+SYM_CODE_END(kvm_hyp_cpu_entry)
 
 SYM_CODE_START(__kvm_handle_stub_hvc)
 	/*
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index ab4c7bddb163..e20db999e328 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -201,24 +201,14 @@ static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
 			 __hyp_pa(init_params), 0);
 }
 
-asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
+static void __noreturn __kvm_host_psci_cpu_entry(unsigned long pc, unsigned long r0)
 {
-	struct psci_boot_args *boot_args;
-	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *host_ctxt = host_data_ptr(host_ctxt);
 
-	host_ctxt = host_data_ptr(host_ctxt);
 	trace_hyp_enter(host_ctxt, HYP_REASON_PSCI);
 
-	if (is_cpu_on)
-		boot_args = this_cpu_ptr(&cpu_on_args);
-	else
-		boot_args = this_cpu_ptr(&suspend_args);
-
-	cpu_reg(host_ctxt, 0) = boot_args->r0;
-	write_sysreg_el2(boot_args->pc, SYS_ELR);
-
-	if (is_cpu_on)
-		release_boot_args(boot_args);
+	cpu_reg(host_ctxt, 0) = r0;
+	write_sysreg_el2(pc, SYS_ELR);
 
 	write_sysreg_el1(INIT_SCTLR_EL1_MMU_OFF, SYS_SCTLR);
 	write_sysreg(INIT_PSTATE_EL1, SPSR_EL2);
@@ -227,6 +217,26 @@ asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 	__host_enter(host_ctxt);
 }
 
+asmlinkage void __noreturn __kvm_host_psci_cpu_on_entry(void)
+{
+	struct psci_boot_args *boot_args = this_cpu_ptr(&cpu_on_args);
+	unsigned long pc, r0;
+
+	pc = READ_ONCE(boot_args->pc);
+	r0 = READ_ONCE(boot_args->r0);
+
+	release_boot_args(boot_args);
+
+	__kvm_host_psci_cpu_entry(pc, r0);
+}
+
+asmlinkage void __noreturn __kvm_host_psci_cpu_resume_entry(void)
+{
+	struct psci_boot_args *boot_args = this_cpu_ptr(&suspend_args);
+
+	__kvm_host_psci_cpu_entry(boot_args->pc, boot_args->r0);
+}
+
 static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
 {
 	if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id))