Merge tag 'kvmarm-fixes-5.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for Linux 5.8, take #1

* 32bit VM fixes:
  - Fix embarassing mapping issue between AArch32 CSSELR and AArch64
    ACTLR
  - Add ACTLR2 support for AArch32
  - Get rid of the useless ACTLR_EL1 save/restore
  - Fix CP14/15 accesses for AArch32 guests on BE hosts
  - Ensure that we don't loose any state when injecting a 32bit
    exception when running on a VHE host

* 64bit VM fixes:
  - Fix PtrAuth host saving happening in preemptible contexts
  - Optimize PtrAuth lazy enable
  - Drop vcpu to cpu context pointer
  - Fix sparse warnings for HYP per-CPU accesses
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 0c9b5fc..352aaeb 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -81,12 +81,39 @@
 
 extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
 
-/* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
+/*
+ * Obtain the PC-relative address of a kernel symbol
+ * s: symbol
+ *
+ * The goal of this macro is to return a symbol's address based on a
+ * PC-relative computation, as opposed to a loading the VA from a
+ * constant pool or something similar. This works well for HYP, as an
+ * absolute VA is guaranteed to be wrong. Only use this if trying to
+ * obtain the address of a symbol (i.e. not something you obtained by
+ * following a pointer).
+ */
+#define hyp_symbol_addr(s)						\
+	({								\
+		typeof(s) *addr;					\
+		asm("adrp	%0, %1\n"				\
+		    "add	%0, %0, :lo12:%1\n"			\
+		    : "=r" (addr) : "S" (&s));				\
+		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 = hyp_symbol_addr(sym);			\
+		void *__ptr;						\
+		__verify_pcpu_ptr(&sym);				\
+		__ptr = hyp_symbol_addr(sym);				\
 		__ptr += read_sysreg(tpidr_el2);			\
-		(typeof(&sym))__ptr;					\
+		(typeof(sym) __kernel __force *)__ptr;			\
 	 })
 
 #define __hyp_this_cpu_read(sym)					\
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 6ea53e6..4d0f8ea 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -112,12 +112,6 @@
 	vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK);
 }
 
-static inline void vcpu_ptrauth_setup_lazy(struct kvm_vcpu *vcpu)
-{
-	if (vcpu_has_ptrauth(vcpu))
-		vcpu_ptrauth_disable(vcpu);
-}
-
 static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.vsesr_el2;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index abbdf97..c3e6fcc6 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -284,9 +284,6 @@
 	struct kvm_guest_debug_arch vcpu_debug_state;
 	struct kvm_guest_debug_arch external_debug_state;
 
-	/* Pointer to host CPU context */
-	struct kvm_cpu_context *host_cpu_context;
-
 	struct thread_info *host_thread_info;	/* hyp VA */
 	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */
 
@@ -404,8 +401,10 @@
  * CP14 and CP15 live in the same array, as they are backed by the
  * same system registers.
  */
-#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
-#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
+#define CPx_BIAS		IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
+
+#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
+#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
 
 struct kvm_vm_stat {
 	ulong remote_tlb_flush;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 324c848..0027d34 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -108,26 +108,6 @@
 #define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
 
 /*
- * Obtain the PC-relative address of a kernel symbol
- * s: symbol
- *
- * The goal of this macro is to return a symbol's address based on a
- * PC-relative computation, as opposed to a loading the VA from a
- * constant pool or something similar. This works well for HYP, as an
- * absolute VA is guaranteed to be wrong. Only use this if trying to
- * obtain the address of a symbol (i.e. not something you obtained by
- * following a pointer).
- */
-#define hyp_symbol_addr(s)						\
-	({								\
-		typeof(s) *addr;					\
-		asm("adrp	%0, %1\n"				\
-		    "add	%0, %0, :lo12:%1\n"			\
-		    : "=r" (addr) : "S" (&s));				\
-		addr;							\
-	})
-
-/*
  * We currently support using a VM-specified IPA size. For backward
  * compatibility, the default IPA size is fixed to 40bits.
  */
diff --git a/arch/arm64/kvm/aarch32.c b/arch/arm64/kvm/aarch32.c
index 0a356aa..40a62a9 100644
--- a/arch/arm64/kvm/aarch32.c
+++ b/arch/arm64/kvm/aarch32.c
@@ -33,6 +33,26 @@
 	[7] = { 4, 4 },		/* FIQ, unused */
 };
 
+static bool pre_fault_synchronize(struct kvm_vcpu *vcpu)
+{
+	preempt_disable();
+	if (vcpu->arch.sysregs_loaded_on_cpu) {
+		kvm_arch_vcpu_put(vcpu);
+		return true;
+	}
+
+	preempt_enable();
+	return false;
+}
+
+static void post_fault_synchronize(struct kvm_vcpu *vcpu, bool loaded)
+{
+	if (loaded) {
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+		preempt_enable();
+	}
+}
+
 /*
  * When an exception is taken, most CPSR fields are left unchanged in the
  * handler. However, some are explicitly overridden (e.g. M[4:0]).
@@ -155,7 +175,10 @@
 
 void kvm_inject_undef32(struct kvm_vcpu *vcpu)
 {
+	bool loaded = pre_fault_synchronize(vcpu);
+
 	prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4);
+	post_fault_synchronize(vcpu, loaded);
 }
 
 /*
@@ -168,6 +191,9 @@
 	u32 vect_offset;
 	u32 *far, *fsr;
 	bool is_lpae;
+	bool loaded;
+
+	loaded = pre_fault_synchronize(vcpu);
 
 	if (is_pabt) {
 		vect_offset = 12;
@@ -191,6 +217,8 @@
 		/* no need to shuffle FS[4] into DFSR[10] as its 0 */
 		*fsr = DFSR_FSC_EXTABT_nLPAE;
 	}
+
+	post_fault_synchronize(vcpu, loaded);
 }
 
 void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 45276ed..90cb905 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -335,10 +335,8 @@
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	int *last_ran;
-	kvm_host_data_t *cpu_data;
 
 	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
-	cpu_data = this_cpu_ptr(&kvm_host_data);
 
 	/*
 	 * We might get preempted before the vCPU actually runs, but
@@ -350,7 +348,6 @@
 	}
 
 	vcpu->cpu = cpu;
-	vcpu->arch.host_cpu_context = &cpu_data->host_ctxt;
 
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
@@ -365,7 +362,8 @@
 	else
 		vcpu_set_wfx_traps(vcpu);
 
-	vcpu_ptrauth_setup_lazy(vcpu);
+	if (vcpu_has_ptrauth(vcpu))
+		vcpu_ptrauth_disable(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -985,11 +983,17 @@
 	 * Ensure a rebooted VM will fault in RAM pages and detect if the
 	 * guest MMU is turned off and flush the caches as needed.
 	 *
-	 * S2FWB enforces all memory accesses to RAM being cacheable, we
-	 * ensure that the cache is always coherent.
+	 * S2FWB enforces all memory accesses to RAM being cacheable,
+	 * ensuring that the data side is always coherent. We still
+	 * need to invalidate the I-cache though, as FWB does *not*
+	 * imply CTR_EL0.DIC.
 	 */
-	if (vcpu->arch.has_run_once && !cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
-		stage2_unmap_vm(vcpu->kvm);
+	if (vcpu->arch.has_run_once) {
+		if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
+			stage2_unmap_vm(vcpu->kvm);
+		else
+			__flush_icache_all();
+	}
 
 	vcpu_reset_hcr(vcpu);
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index eb19469..5a02d4c 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -162,40 +162,14 @@
 	return 1;
 }
 
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
-
-/*
- * Handle the guest trying to use a ptrauth instruction, or trying to access a
- * ptrauth register.
- */
-void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpu_context *ctxt;
-
-	if (vcpu_has_ptrauth(vcpu)) {
-		vcpu_ptrauth_enable(vcpu);
-		ctxt = vcpu->arch.host_cpu_context;
-		__ptrauth_save_key(ctxt->sys_regs, APIA);
-		__ptrauth_save_key(ctxt->sys_regs, APIB);
-		__ptrauth_save_key(ctxt->sys_regs, APDA);
-		__ptrauth_save_key(ctxt->sys_regs, APDB);
-		__ptrauth_save_key(ctxt->sys_regs, APGA);
-	} else {
-		kvm_inject_undefined(vcpu);
-	}
-}
-
 /*
  * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into
- * a NOP).
+ * a NOP). If we get here, it is that we didn't fixup ptrauth on exit, and all
+ * that we can do is give the guest an UNDEF.
  */
 static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_arm_vcpu_ptrauth_trap(vcpu);
+	kvm_inject_undefined(vcpu);
 	return 1;
 }
 
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index 0fc9872..e95af20 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -185,7 +185,7 @@
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
-	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 	guest_ctxt = &vcpu->arch.ctxt;
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
@@ -207,7 +207,7 @@
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
-	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 	guest_ctxt = &vcpu->arch.ctxt;
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 676b658..db1c448 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -490,6 +490,64 @@
 	return true;
 }
 
+static bool __hyp_text esr_is_ptrauth_trap(u32 esr)
+{
+	u32 ec = ESR_ELx_EC(esr);
+
+	if (ec == ESR_ELx_EC_PAC)
+		return true;
+
+	if (ec != ESR_ELx_EC_SYS64)
+		return false;
+
+	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(regs, key)						\
+({										\
+	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
+	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
+})
+
+static bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *ctxt;
+	u64 val;
+
+	if (!vcpu_has_ptrauth(vcpu) ||
+	    !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
+		return false;
+
+	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	__ptrauth_save_key(ctxt->sys_regs, APIA);
+	__ptrauth_save_key(ctxt->sys_regs, APIB);
+	__ptrauth_save_key(ctxt->sys_regs, APDA);
+	__ptrauth_save_key(ctxt->sys_regs, APDB);
+	__ptrauth_save_key(ctxt->sys_regs, APGA);
+
+	vcpu_ptrauth_enable(vcpu);
+
+	val = read_sysreg(hcr_el2);
+	val |= (HCR_API | HCR_APK);
+	write_sysreg(val, hcr_el2);
+
+	return true;
+}
+
 /*
  * Return true when we were able to fixup the guest exit and should return to
  * the guest, false when we should restore the host state and return to the
@@ -524,6 +582,9 @@
 	if (__hyp_handle_fpsimd(vcpu))
 		return true;
 
+	if (__hyp_handle_ptrauth(vcpu))
+		return true;
+
 	if (!__populate_fault_info(vcpu))
 		return true;
 
@@ -642,7 +703,7 @@
 	struct kvm_cpu_context *guest_ctxt;
 	u64 exit_code;
 
-	host_ctxt = vcpu->arch.host_cpu_context;
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 	host_ctxt->__hyp_running_vcpu = vcpu;
 	guest_ctxt = &vcpu->arch.ctxt;
 
@@ -747,7 +808,7 @@
 
 	vcpu = kern_hyp_va(vcpu);
 
-	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 	host_ctxt->__hyp_running_vcpu = vcpu;
 	guest_ctxt = &vcpu->arch.ctxt;
 
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index ea5d22f..cc7e957 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -39,7 +39,6 @@
 {
 	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
 	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(SYS_SCTLR);
-	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
 	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(SYS_CPACR);
 	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(SYS_TTBR0);
 	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(SYS_TTBR1);
@@ -123,7 +122,6 @@
 		isb();
 	}
 
-	write_sysreg(ctxt->sys_regs[ACTLR_EL1],		actlr_el1);
 	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	SYS_CPACR);
 	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	SYS_TTBR0);
 	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	SYS_TTBR1);
@@ -267,12 +265,13 @@
  */
 void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *host_ctxt = vcpu->arch.host_cpu_context;
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
 
 	if (!has_vhe())
 		return;
 
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 	__sysreg_save_user_state(host_ctxt);
 
 	/*
@@ -303,12 +302,13 @@
  */
 void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *host_ctxt = vcpu->arch.host_cpu_context;
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+	struct kvm_cpu_context *host_ctxt;
 
 	if (!has_vhe())
 		return;
 
+	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 	deactivate_traps_vhe_put();
 
 	__sysreg_save_el1_state(guest_ctxt);
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index e71d00b..b5ae3a5 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -163,15 +163,13 @@
  */
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *host_ctxt;
 	struct kvm_host_data *host;
 	u32 events_guest, events_host;
 
 	if (!has_vhe())
 		return;
 
-	host_ctxt = vcpu->arch.host_cpu_context;
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	host = this_cpu_ptr(&kvm_host_data);
 	events_guest = host->pmu_events.events_guest;
 	events_host = host->pmu_events.events_host;
 
@@ -184,15 +182,13 @@
  */
 void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *host_ctxt;
 	struct kvm_host_data *host;
 	u32 events_guest, events_host;
 
 	if (!has_vhe())
 		return;
 
-	host_ctxt = vcpu->arch.host_cpu_context;
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	host = this_cpu_ptr(&kvm_host_data);
 	events_guest = host->pmu_events.events_guest;
 	events_host = host->pmu_events.events_host;
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 8098543..baf5ce9 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -78,7 +78,6 @@
 	switch (reg) {
 	case CSSELR_EL1:	*val = read_sysreg_s(SYS_CSSELR_EL1);	break;
 	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
-	case ACTLR_EL1:		*val = read_sysreg_s(SYS_ACTLR_EL1);	break;
 	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
 	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
 	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
@@ -118,7 +117,6 @@
 	switch (reg) {
 	case CSSELR_EL1:	write_sysreg_s(val, SYS_CSSELR_EL1);	break;
 	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
-	case ACTLR_EL1:		write_sysreg_s(val, SYS_ACTLR_EL1);	break;
 	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
 	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
 	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
@@ -1034,16 +1032,13 @@
 			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *rd)
 {
-	kvm_arm_vcpu_ptrauth_trap(vcpu);
-
 	/*
-	 * Return false for both cases as we never skip the trapped
-	 * instruction:
-	 *
-	 * - Either we re-execute the same key register access instruction
-	 *   after enabling ptrauth.
-	 * - Or an UNDEF is injected as ptrauth is not supported/enabled.
+	 * If we land here, that is because we didn't fixup the access on exit
+	 * by allowing the PtrAuth sysregs. The only way this happens is when
+	 * the guest does not have PtrAuth support enabled.
 	 */
+	kvm_inject_undefined(vcpu);
+
 	return false;
 }
 
@@ -1319,10 +1314,16 @@
 static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
+	int reg = r->reg;
+
+	/* See the 32bit mapping in kvm_host.h */
+	if (p->is_aarch32)
+		reg = r->reg / 2;
+
 	if (p->is_write)
-		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
+		vcpu_write_sys_reg(vcpu, p->regval, reg);
 	else
-		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
+		p->regval = vcpu_read_sys_reg(vcpu, reg);
 	return true;
 }
 
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 9cb6b4c..aa9d356 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -27,6 +27,14 @@
 		return ignore_write(vcpu, p);
 
 	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
+
+	if (p->is_aarch32) {
+		if (r->Op2 & 2)
+			p->regval = upper_32_bits(p->regval);
+		else
+			p->regval = lower_32_bits(p->regval);
+	}
+
 	return true;
 }
 
@@ -47,6 +55,8 @@
 	/* ACTLR */
 	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
 	  access_actlr },
+	{ Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b011),
+	  access_actlr },
 };
 
 static struct kvm_sys_reg_target_table genericv8_target_table = {