Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

24 files changed, 526 insertions, 352 deletions

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 83c1e09be4..27ca89b628 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -3,7 +3,6 @@
 # KVM configuration
 #
 
-source "virt/lib/Kconfig"
 source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
@@ -21,16 +20,14 @@ if VIRTUALIZATION
 menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
+	select KVM_COMMON
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select MMU_NOTIFIER
-	select PREEMPT_NOTIFIERS
+	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_VFIO
-	select HAVE_KVM_EVENTFD
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select NEED_KVM_DIRTY_RING_WITH_BITMAP
 	select HAVE_KVM_MSI
@@ -41,7 +38,6 @@ menuconfig KVM
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
-	select INTERVAL_TREE
 	select XARRAY_MULTI
 	help
 	  Support hosting virtualized guest machines.
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 13ba691b84..9dec8c419b 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -295,8 +295,7 @@ static u64 wfit_delay_ns(struct kvm_vcpu *vcpu)
 	u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
 	struct arch_timer_context *ctx;
 
-	ctx = (vcpu_has_nv(vcpu) && is_hyp_ctxt(vcpu)) ? vcpu_hvtimer(vcpu)
-						       : vcpu_vtimer(vcpu);
+	ctx = is_hyp_ctxt(vcpu) ? vcpu_hvtimer(vcpu) : vcpu_vtimer(vcpu);
 
 	return kvm_counter_compute_delta(ctx, val);
 }
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 4796104c44..a25265aca4 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -221,7 +221,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = vgic_present;
 		break;
 	case KVM_CAP_IOEVENTFD:
-	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
@@ -669,6 +668,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
+	if (vcpu_has_nv(vcpu)) {
+		ret = kvm_init_nv_sysregs(vcpu->kvm);
+		if (ret)
+			return ret;
+	}
+
 	ret = kvm_timer_enable(vcpu);
 	if (ret)
 		return ret;
@@ -1837,6 +1842,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
+	u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	unsigned long tcr;
 
 	/*
@@ -1859,6 +1865,10 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	}
 	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
+	tcr &= ~TCR_EL2_PS_MASK;
+	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0));
+	if (kvm_lpa2_is_enabled())
+		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 06185216a2..431fd42993 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -1012,6 +1012,7 @@ enum fgt_group_id {
 	HDFGRTR_GROUP,
 	HDFGWTR_GROUP,
 	HFGITR_GROUP,
+	HAFGRTR_GROUP,
 
 	/* Must be last */
 	__NR_FGT_GROUP_IDS__
@@ -1042,10 +1043,20 @@ enum fg_filter_id {
 
 static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	/* HFGRTR_EL2, HFGWTR_EL2 */
+	SR_FGT(SYS_AMAIR2_EL1,		HFGxTR, nAMAIR2_EL1, 0),
+	SR_FGT(SYS_MAIR2_EL1,		HFGxTR, nMAIR2_EL1, 0),
+	SR_FGT(SYS_S2POR_EL1,		HFGxTR, nS2POR_EL1, 0),
+	SR_FGT(SYS_POR_EL1,		HFGxTR, nPOR_EL1, 0),
+	SR_FGT(SYS_POR_EL0,		HFGxTR, nPOR_EL0, 0),
 	SR_FGT(SYS_PIR_EL1,		HFGxTR, nPIR_EL1, 0),
 	SR_FGT(SYS_PIRE0_EL1,		HFGxTR, nPIRE0_EL1, 0),
+	SR_FGT(SYS_RCWMASK_EL1,		HFGxTR, nRCWMASK_EL1, 0),
 	SR_FGT(SYS_TPIDR2_EL0,		HFGxTR, nTPIDR2_EL0, 0),
 	SR_FGT(SYS_SMPRI_EL1,		HFGxTR, nSMPRI_EL1, 0),
+	SR_FGT(SYS_GCSCR_EL1,		HFGxTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSPR_EL1,		HFGxTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSCRE0_EL1,		HFGxTR, nGCS_EL0, 0),
+	SR_FGT(SYS_GCSPR_EL0,		HFGxTR, nGCS_EL0, 0),
 	SR_FGT(SYS_ACCDATA_EL1,		HFGxTR, nACCDATA_EL1, 0),
 	SR_FGT(SYS_ERXADDR_EL1,		HFGxTR, ERXADDR_EL1, 1),
 	SR_FGT(SYS_ERXPFGCDN_EL1,	HFGxTR, ERXPFGCDN_EL1, 1),
@@ -1107,6 +1118,11 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_AFSR1_EL1, 		HFGxTR, AFSR1_EL1, 1),
 	SR_FGT(SYS_AFSR0_EL1, 		HFGxTR, AFSR0_EL1, 1),
 	/* HFGITR_EL2 */
+	SR_FGT(OP_AT_S1E1A, 		HFGITR, ATS1E1A, 1),
+	SR_FGT(OP_COSP_RCTX, 		HFGITR, COSPRCTX, 1),
+	SR_FGT(OP_GCSPUSHX, 		HFGITR, nGCSEPP, 0),
+	SR_FGT(OP_GCSPOPX, 		HFGITR, nGCSEPP, 0),
+	SR_FGT(OP_GCSPUSHM, 		HFGITR, nGCSPUSHM_EL1, 0),
 	SR_FGT(OP_BRB_IALL, 		HFGITR, nBRBIALL, 0),
 	SR_FGT(OP_BRB_INJ, 		HFGITR, nBRBINJ, 0),
 	SR_FGT(SYS_DC_CVAC, 		HFGITR, DCCVAC, 1),
@@ -1674,6 +1690,49 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_PMCR_EL0,		HDFGWTR, PMCR_EL0, 1),
 	SR_FGT(SYS_PMSWINC_EL0,		HDFGWTR, PMSWINC_EL0, 1),
 	SR_FGT(SYS_OSLAR_EL1,		HDFGWTR, OSLAR_EL1, 1),
+	/*
+	 * HAFGRTR_EL2
+	 */
+	SR_FGT(SYS_AMEVTYPER1_EL0(15),	HAFGRTR, AMEVTYPER115_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(14),	HAFGRTR, AMEVTYPER114_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(13),	HAFGRTR, AMEVTYPER113_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(12),	HAFGRTR, AMEVTYPER112_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(11),	HAFGRTR, AMEVTYPER111_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(10),	HAFGRTR, AMEVTYPER110_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(9),	HAFGRTR, AMEVTYPER19_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(8),	HAFGRTR, AMEVTYPER18_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(7),	HAFGRTR, AMEVTYPER17_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(6),	HAFGRTR, AMEVTYPER16_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(5),	HAFGRTR, AMEVTYPER15_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(4),	HAFGRTR, AMEVTYPER14_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(3),	HAFGRTR, AMEVTYPER13_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(2),	HAFGRTR, AMEVTYPER12_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(1),	HAFGRTR, AMEVTYPER11_EL0, 1),
+	SR_FGT(SYS_AMEVTYPER1_EL0(0),	HAFGRTR, AMEVTYPER10_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(15),	HAFGRTR, AMEVCNTR115_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(14),	HAFGRTR, AMEVCNTR114_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(13),	HAFGRTR, AMEVCNTR113_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(12),	HAFGRTR, AMEVCNTR112_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(11),	HAFGRTR, AMEVCNTR111_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(10),	HAFGRTR, AMEVCNTR110_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(9),	HAFGRTR, AMEVCNTR19_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(8),	HAFGRTR, AMEVCNTR18_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(7),	HAFGRTR, AMEVCNTR17_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(6),	HAFGRTR, AMEVCNTR16_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(5),	HAFGRTR, AMEVCNTR15_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(4),	HAFGRTR, AMEVCNTR14_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(3),	HAFGRTR, AMEVCNTR13_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(2),	HAFGRTR, AMEVCNTR12_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(1),	HAFGRTR, AMEVCNTR11_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR1_EL0(0),	HAFGRTR, AMEVCNTR10_EL0, 1),
+	SR_FGT(SYS_AMCNTENCLR1_EL0,	HAFGRTR, AMCNTEN1, 1),
+	SR_FGT(SYS_AMCNTENSET1_EL0,	HAFGRTR, AMCNTEN1, 1),
+	SR_FGT(SYS_AMCNTENCLR0_EL0,	HAFGRTR, AMCNTEN0, 1),
+	SR_FGT(SYS_AMCNTENSET0_EL0,	HAFGRTR, AMCNTEN0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(3),	HAFGRTR, AMEVCNTR03_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(2),	HAFGRTR, AMEVCNTR02_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(1),	HAFGRTR, AMEVCNTR01_EL0, 1),
+	SR_FGT(SYS_AMEVCNTR0_EL0(0),	HAFGRTR, AMEVCNTR00_EL0, 1),
 };
 
 static union trap_config get_trap_config(u32 sysreg)
@@ -1894,6 +1953,10 @@ bool __check_nv_sr_forward(struct kvm_vcpu *vcpu)
 			val = sanitised_sys_reg(vcpu, HDFGWTR_EL2);
 		break;
 
+	case HAFGRTR_GROUP:
+		val = sanitised_sys_reg(vcpu, HAFGRTR_EL2);
+		break;
+
 	case HFGITR_GROUP:
 		val = sanitised_sys_reg(vcpu, HFGITR_EL2);
 		switch (tc.fgf) {
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 9ddcfe2c3e..9e13c1bc2a 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
 	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
+	     esr_fsc_is_permission_fault(esr))) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index f99d8af0b9..a038320cdb 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -79,6 +79,45 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 		clr |= ~hfg & __ ## reg ## _nMASK; 			\
 	} while(0)
 
+#define update_fgt_traps_cs(vcpu, reg, clr, set)			\
+	do {								\
+		struct kvm_cpu_context *hctxt =				\
+			&this_cpu_ptr(&kvm_host_data)->host_ctxt;	\
+		u64 c = 0, s = 0;					\
+									\
+		ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg);	\
+		compute_clr_set(vcpu, reg, c, s);			\
+		s |= set;						\
+		c |= clr;						\
+		if (c || s) {						\
+			u64 val = __ ## reg ## _nMASK;			\
+			val |= s;					\
+			val &= ~c;					\
+			write_sysreg_s(val, SYS_ ## reg);		\
+		}							\
+	} while(0)
+
+#define update_fgt_traps(vcpu, reg)		\
+	update_fgt_traps_cs(vcpu, reg, 0, 0)
+
+/*
+ * Validate the fine grain trap masks.
+ * Check that the masks do not overlap and that all bits are accounted for.
+ */
+#define CHECK_FGT_MASKS(reg)							\
+	do {									\
+		BUILD_BUG_ON((__ ## reg ## _MASK) & (__ ## reg ## _nMASK));	\
+		BUILD_BUG_ON(~((__ ## reg ## _RES0) ^ (__ ## reg ## _MASK) ^	\
+			       (__ ## reg ## _nMASK)));				\
+	} while(0)
+
+static inline bool cpu_has_amu(void)
+{
+       u64 pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
+
+       return cpuid_feature_extract_unsigned_field(pfr0,
+               ID_AA64PFR0_EL1_AMU_SHIFT);
+}
 
 static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
@@ -86,6 +125,14 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	u64 r_clr = 0, w_clr = 0, r_set = 0, w_set = 0, tmp;
 	u64 r_val, w_val;
 
+	CHECK_FGT_MASKS(HFGRTR_EL2);
+	CHECK_FGT_MASKS(HFGWTR_EL2);
+	CHECK_FGT_MASKS(HFGITR_EL2);
+	CHECK_FGT_MASKS(HDFGRTR_EL2);
+	CHECK_FGT_MASKS(HDFGWTR_EL2);
+	CHECK_FGT_MASKS(HAFGRTR_EL2);
+	CHECK_FGT_MASKS(HCRX_EL2);
+
 	if (!cpus_have_final_cap(ARM64_HAS_FGT))
 		return;
 
@@ -110,12 +157,15 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 		compute_clr_set(vcpu, HFGWTR_EL2, w_clr, w_set);
 	}
 
-	/* The default is not to trap anything but ACCDATA_EL1 */
-	r_val = __HFGRTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	/* The default to trap everything not handled or supported in KVM. */
+	tmp = HFGxTR_EL2_nAMAIR2_EL1 | HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nS2POR_EL1 |
+	      HFGxTR_EL2_nPOR_EL1 | HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nACCDATA_EL1;
+
+	r_val = __HFGRTR_EL2_nMASK & ~tmp;
 	r_val |= r_set;
 	r_val &= ~r_clr;
 
-	w_val = __HFGWTR_EL2_nMASK & ~HFGxTR_EL2_nACCDATA_EL1;
+	w_val = __HFGWTR_EL2_nMASK & ~tmp;
 	w_val |= w_set;
 	w_val &= ~w_clr;
 
@@ -125,34 +175,12 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
 		return;
 
-	ctxt_sys_reg(hctxt, HFGITR_EL2) = read_sysreg_s(SYS_HFGITR_EL2);
+	update_fgt_traps(vcpu, HFGITR_EL2);
+	update_fgt_traps(vcpu, HDFGRTR_EL2);
+	update_fgt_traps(vcpu, HDFGWTR_EL2);
 
-	r_set = r_clr = 0;
-	compute_clr_set(vcpu, HFGITR_EL2, r_clr, r_set);
-	r_val = __HFGITR_EL2_nMASK;
-	r_val |= r_set;
-	r_val &= ~r_clr;
-
-	write_sysreg_s(r_val, SYS_HFGITR_EL2);
-
-	ctxt_sys_reg(hctxt, HDFGRTR_EL2) = read_sysreg_s(SYS_HDFGRTR_EL2);
-	ctxt_sys_reg(hctxt, HDFGWTR_EL2) = read_sysreg_s(SYS_HDFGWTR_EL2);
-
-	r_clr = r_set = w_clr = w_set = 0;
-
-	compute_clr_set(vcpu, HDFGRTR_EL2, r_clr, r_set);
-	compute_clr_set(vcpu, HDFGWTR_EL2, w_clr, w_set);
-
-	r_val = __HDFGRTR_EL2_nMASK;
-	r_val |= r_set;
-	r_val &= ~r_clr;
-
-	w_val = __HDFGWTR_EL2_nMASK;
-	w_val |= w_set;
-	w_val &= ~w_clr;
-
-	write_sysreg_s(r_val, SYS_HDFGRTR_EL2);
-	write_sysreg_s(w_val, SYS_HDFGWTR_EL2);
+	if (cpu_has_amu())
+		update_fgt_traps(vcpu, HAFGRTR_EL2);
 }
 
 static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
@@ -171,6 +199,9 @@ static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	write_sysreg_s(ctxt_sys_reg(hctxt, HFGITR_EL2), SYS_HFGITR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGRTR_EL2), SYS_HDFGRTR_EL2);
 	write_sysreg_s(ctxt_sys_reg(hctxt, HDFGWTR_EL2), SYS_HDFGWTR_EL2);
+
+	if (cpu_has_amu())
+		write_sysreg_s(ctxt_sys_reg(hctxt, HAFGRTR_EL2), SYS_HAFGRTR_EL2);
 }
 
 static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
@@ -591,7 +622,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
 		bool valid;
 
-		valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
+		valid = kvm_vcpu_trap_is_translation_fault(vcpu) &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_abt_iss1tw(vcpu);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
index e91922daa8..51f0436491 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
@@ -69,6 +69,8 @@
 	ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SSBS) \
 	)
 
+#define PVM_ID_AA64PFR2_ALLOW 0ULL
+
 /*
  * Allow for protected VMs:
  * - Mixed-endian
@@ -101,6 +103,7 @@
  * - Privileged Access Never
  * - SError interrupt exceptions from speculative reads
  * - Enhanced Translation Synchronization
+ * - Control for cache maintenance permission
  */
 #define PVM_ID_AA64MMFR1_ALLOW (\
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS) | \
@@ -108,7 +111,8 @@
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HPDS) | \
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_PAN) | \
 	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_SpecSEI) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) | \
+	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_CMOW) \
 	)
 
 /*
@@ -133,6 +137,8 @@
 	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_E0PD) \
 	)
 
+#define PVM_ID_AA64MMFR3_ALLOW (0ULL)
+
 /*
  * No support for Scalable Vectors for protected VMs:
  *	Requires additional support from KVM, e.g., context-switching and
@@ -178,10 +184,18 @@
 	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RNDR) \
 	)
 
+/* Restrict pointer authentication to the basic version. */
+#define PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), ID_AA64ISAR1_EL1_APA_PAuth) | \
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), ID_AA64ISAR1_EL1_API_PAuth) \
+	)
+
+#define PVM_ID_AA64ISAR2_RESTRICT_UNSIGNED (\
+	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3), ID_AA64ISAR2_EL1_APA3_PAuth) \
+	)
+
 #define PVM_ID_AA64ISAR1_ALLOW (\
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_DPB) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_JSCVT) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_FCMA) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_LRCPC) | \
@@ -196,8 +210,8 @@
 	)
 
 #define PVM_ID_AA64ISAR2_ALLOW (\
+	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_ATS1A)| \
 	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) | \
 	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_MOPS) \
 	)
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fe5472a184..97c527ef53 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -16,7 +16,7 @@ struct hyp_pool {
 	 * API at EL2.
 	 */
 	hyp_spinlock_t lock;
-	struct list_head free_area[MAX_ORDER + 1];
+	struct list_head free_area[NR_PAGE_ORDERS];
 	phys_addr_t range_start;
 	phys_addr_t range_end;
 	unsigned short max_order;
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 1cc06e6797..2994878d68 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -122,11 +122,7 @@ alternative_if ARM64_HAS_CNP
 alternative_else_nop_endif
 	msr	ttbr0_el2, x2
 
-	/*
-	 * Set the PS bits in TCR_EL2.
-	 */
 	ldr	x0, [x0, #NVHE_INIT_TCR_EL2]
-	tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2
 	msr	tcr_el2, x0
 
 	isb
@@ -292,6 +288,8 @@ alternative_else_nop_endif
 	mov	sp, x0
 
 	/* And turn the MMU back on! */
+	dsb	nsh
+	isb
 	set_sctlr_el2	x2
 	ret	x1
 SYM_FUNC_END(__pkvm_init_switch_pgd)
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 8d0a5834e8..861c76021a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -91,7 +91,7 @@ static void host_s2_put_page(void *addr)
 	hyp_put_page(&host_s2_pool, addr);
 }
 
-static void host_s2_free_unlinked_table(void *addr, u32 level)
+static void host_s2_free_unlinked_table(void *addr, s8 level)
 {
 	kvm_pgtable_stage2_free_unlinked(&host_mmu.mm_ops, addr, level);
 }
@@ -443,7 +443,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 {
 	struct kvm_mem_range cur;
 	kvm_pte_t pte;
-	u32 level;
+	s8 level;
 	int ret;
 
 	hyp_assert_lock_held(&host_mmu.lock);
@@ -462,7 +462,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
 		level++;
-	} while ((level < KVM_PGTABLE_MAX_LEVELS) &&
+	} while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
 			!(kvm_level_supports_block_mapping(level) &&
 			  range_included(&cur, range)));
 
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 65a7a186d7..b01a3d1078 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -260,7 +260,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
 	 * https://lore.kernel.org/kvm/20221017115209.2099-1-will@kernel.org/T/#mf10dfbaf1eaef9274c581b81c53758918c1d0f03
 	 */
 	dsb(ishst);
-	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), (KVM_PGTABLE_MAX_LEVELS - 1));
+	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), KVM_PGTABLE_LAST_LEVEL);
 	dsb(ish);
 	isb();
 }
@@ -275,7 +275,7 @@ static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	struct hyp_fixmap_slot *slot = per_cpu_ptr(&fixmap_slots, (u64)ctx->arg);
 
-	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_MAX_LEVELS - 1)
+	if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	slot->addr = ctx->addr;
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index b1e392186a..e691290d37 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -228,7 +228,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,
 	int i;
 
 	hyp_spin_lock_init(&pool->lock);
-	pool->max_order = min(MAX_ORDER, get_order(nr_pages << PAGE_SHIFT));
+	pool->max_order = min(MAX_PAGE_ORDER,
+			      get_order(nr_pages << PAGE_SHIFT));
 	for (i = 0; i <= pool->max_order; i++)
 		INIT_LIST_HEAD(&pool->free_area[i]);
 	pool->range_start = phys;
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 9d23a51d7f..26dd9a20ad 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -12,7 +12,7 @@
 #include <nvhe/pkvm.h>
 #include <nvhe/trap_handler.h>
 
-/* Used by icache_is_vpipt(). */
+/* Used by icache_is_aliasing(). */
 unsigned long __icache_flags;
 
 /* Used by kvm_get_vttbr(). */
@@ -136,6 +136,10 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
 			cptr_set |= CPTR_EL2_TTA;
 	}
 
+	/* Trap External Trace */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids))
+		mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT;
+
 	vcpu->arch.mdcr_el2 |= mdcr_set;
 	vcpu->arch.mdcr_el2 &= ~mdcr_clear;
 	vcpu->arch.cptr_el2 |= cptr_set;
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 0d5e0a89dd..bc58d1b515 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -181,7 +181,7 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!kvm_pte_valid(ctx->old))
 		return 0;
 
-	if (ctx->level != (KVM_PGTABLE_MAX_LEVELS - 1))
+	if (ctx->level != KVM_PGTABLE_LAST_LEVEL)
 		return -EINVAL;
 
 	phys = kvm_pte_to_phys(ctx->old);
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 1b265713d6..2fc68da403 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -105,28 +105,6 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	/*
-	 * If the host is running at EL1 and we have a VPIPT I-cache,
-	 * then we must perform I-cache maintenance at EL2 in order for
-	 * it to have an effect on the guest. Since the guest cannot hit
-	 * I-cache lines allocated with a different VMID, we don't need
-	 * to worry about junk out of guest reset (we nuke the I-cache on
-	 * VMID rollover), but we do need to be careful when remapping
-	 * executable pages for the same guest. This can happen when KSM
-	 * takes a CoW fault on an executable page, copies the page into
-	 * a page that was previously mapped in the guest and then needs
-	 * to invalidate the guest view of the I-cache for that page
-	 * from EL1. To solve this, we invalidate the entire I-cache when
-	 * unmapping a page from a guest if we have a VPIPT I-cache but
-	 * the host is running at EL1. As above, we could do better if
-	 * we had the VA.
-	 *
-	 * The moral of this story is: if you have a VPIPT I-cache, then
-	 * you should be running with VHE enabled.
-	 */
-	if (icache_is_vpipt())
-		icache_inval_all_pou();
-
 	__tlb_switch_to_host(&cxt);
 }
 
@@ -157,28 +135,6 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	dsb(nsh);
 	isb();
 
-	/*
-	 * If the host is running at EL1 and we have a VPIPT I-cache,
-	 * then we must perform I-cache maintenance at EL2 in order for
-	 * it to have an effect on the guest. Since the guest cannot hit
-	 * I-cache lines allocated with a different VMID, we don't need
-	 * to worry about junk out of guest reset (we nuke the I-cache on
-	 * VMID rollover), but we do need to be careful when remapping
-	 * executable pages for the same guest. This can happen when KSM
-	 * takes a CoW fault on an executable page, copies the page into
-	 * a page that was previously mapped in the guest and then needs
-	 * to invalidate the guest view of the I-cache for that page
-	 * from EL1. To solve this, we invalidate the entire I-cache when
-	 * unmapping a page from a guest if we have a VPIPT I-cache but
-	 * the host is running at EL1. As above, we could do better if
-	 * we had the VA.
-	 *
-	 * The moral of this story is: if you have a VPIPT I-cache, then
-	 * you should be running with VHE enabled.
-	 */
-	if (icache_is_vpipt())
-		icache_inval_all_pou();
-
 	__tlb_switch_to_host(&cxt);
 }
 
@@ -198,17 +154,14 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	/* Switch to requested VMID */
 	__tlb_switch_to_guest(mmu, &cxt, false);
 
-	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+				TLBI_TTL_UNKNOWN);
 
 	dsb(ish);
 	__tlbi(vmalle1is);
 	dsb(ish);
 	isb();
 
-	/* See the comment in __kvm_tlb_flush_vmid_ipa() */
-	if (icache_is_vpipt())
-		icache_inval_all_pou();
-
 	__tlb_switch_to_host(&cxt);
 }
 
@@ -246,18 +199,5 @@ void __kvm_flush_vm_context(void)
 	/* Same remark as in __tlb_switch_to_guest() */
 	dsb(ish);
 	__tlbi(alle1is);
-
-	/*
-	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
-	 * is necessary across a VMID rollover.
-	 *
-	 * VPIPT caches constrain lookup and maintenance to the active VMID,
-	 * so we need to invalidate lines with a stale VMID to avoid an ABA
-	 * race after multiple rollovers.
-	 *
-	 */
-	if (icache_is_vpipt())
-		asm volatile("ic ialluis");
-
 	dsb(ish);
 }
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 1966fdee74..ce5cef7d73 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -79,7 +79,10 @@ static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
 
 static bool kvm_phys_is_valid(u64 phys)
 {
-	return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX));
+	u64 parange_max = kvm_get_parange_max();
+	u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max);
+
+	return phys < BIT(shift);
 }
 
 static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys)
@@ -98,7 +101,7 @@ static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx,
 	return IS_ALIGNED(ctx->addr, granule);
 }
 
-static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level)
+static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level)
 {
 	u64 shift = kvm_granule_shift(level);
 	u64 mask = BIT(PAGE_SHIFT - 3) - 1;
@@ -114,7 +117,7 @@ static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
 	return (addr & mask) >> shift;
 }
 
-static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
+static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level)
 {
 	struct kvm_pgtable pgt = {
 		.ia_bits	= ia_bits,
@@ -124,9 +127,9 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
 	return kvm_pgd_page_idx(&pgt, -1ULL) + 1;
 }
 
-static bool kvm_pte_table(kvm_pte_t pte, u32 level)
+static bool kvm_pte_table(kvm_pte_t pte, s8 level)
 {
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	if (!kvm_pte_valid(pte))
@@ -154,11 +157,11 @@ static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops
 	return pte;
 }
 
-static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
+static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level)
 {
 	kvm_pte_t pte = kvm_phys_to_pte(pa);
-	u64 type = (level == KVM_PGTABLE_MAX_LEVELS - 1) ? KVM_PTE_TYPE_PAGE :
-							   KVM_PTE_TYPE_BLOCK;
+	u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE :
+						       KVM_PTE_TYPE_BLOCK;
 
 	pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI);
 	pte |= FIELD_PREP(KVM_PTE_TYPE, type);
@@ -203,11 +206,11 @@ static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker,
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level);
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level);
 
 static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 				      struct kvm_pgtable_mm_ops *mm_ops,
-				      kvm_pteref_t pteref, u32 level)
+				      kvm_pteref_t pteref, s8 level)
 {
 	enum kvm_pgtable_walk_flags flags = data->walker->flags;
 	kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref);
@@ -272,12 +275,13 @@ out:
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level)
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level)
 {
 	u32 idx;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(level >= KVM_PGTABLE_MAX_LEVELS))
+	if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL ||
+			 level > KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) {
@@ -340,7 +344,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 
 struct leaf_walk_data {
 	kvm_pte_t	pte;
-	u32		level;
+	s8		level;
 };
 
 static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
@@ -355,7 +359,7 @@ static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
 }
 
 int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
-			 kvm_pte_t *ptep, u32 *level)
+			 kvm_pte_t *ptep, s8 *level)
 {
 	struct leaf_walk_data data;
 	struct kvm_pgtable_walker walker = {
@@ -408,7 +412,8 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
 	}
 
 	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap);
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
 	attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
@@ -467,7 +472,7 @@ static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	if (hyp_map_walker_try_leaf(ctx, data))
 		return 0;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL);
@@ -563,14 +568,19 @@ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
 			 struct kvm_pgtable_mm_ops *mm_ops)
 {
-	u64 levels = ARM64_HW_PGTABLE_LEVELS(va_bits);
+	s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 -
+			 ARM64_HW_PGTABLE_LEVELS(va_bits);
+
+	if (start_level < KVM_PGTABLE_FIRST_LEVEL ||
+	    start_level > KVM_PGTABLE_LAST_LEVEL)
+		return -EINVAL;
 
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL);
 	if (!pgt->pgd)
 		return -ENOMEM;
 
 	pgt->ia_bits		= va_bits;
-	pgt->start_level	= KVM_PGTABLE_MAX_LEVELS - levels;
+	pgt->start_level	= start_level;
 	pgt->mm_ops		= mm_ops;
 	pgt->mmu		= NULL;
 	pgt->force_pte_cb	= NULL;
@@ -624,7 +634,7 @@ struct stage2_map_data {
 u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 {
 	u64 vtcr = VTCR_EL2_FLAGS;
-	u8 lvls;
+	s8 lvls;
 
 	vtcr |= kvm_get_parange(mmfr0) << VTCR_EL2_PS_SHIFT;
 	vtcr |= VTCR_EL2_T0SZ(phys_shift);
@@ -635,6 +645,15 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 	lvls = stage2_pgtable_levels(phys_shift);
 	if (lvls < 2)
 		lvls = 2;
+
+	/*
+	 * When LPA2 is enabled, the HW supports an extra level of translation
+	 * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2
+	 * to as an addition to SL0 to enable encoding this extra start level.
+	 * However, since we always use concatenated pages for the first level
+	 * lookup, we will never need this extra level and therefore do not need
+	 * to touch SL2.
+	 */
 	vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
 
 #ifdef CONFIG_ARM64_HW_AFDBM
@@ -654,6 +673,9 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
 		vtcr |= VTCR_EL2_HA;
 #endif /* CONFIG_ARM64_HW_AFDBM */
 
+	if (kvm_lpa2_is_enabled())
+		vtcr |= VTCR_EL2_DS;
+
 	/* Set the vmid bits */
 	vtcr |= (get_vmid_bits(mmfr1) == 16) ?
 		VTCR_EL2_VS_16BIT :
@@ -711,7 +733,9 @@ static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot p
 	if (prot & KVM_PGTABLE_PROT_W)
 		attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;
 
-	attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+	if (!kvm_lpa2_is_enabled())
+		attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
+
 	attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
 	attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
 	*ptep = attr;
@@ -805,12 +829,15 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 		 * Perform the appropriate TLB invalidation based on the
 		 * evicted pte value (if any).
 		 */
-		if (kvm_pte_table(ctx->old, ctx->level))
-			kvm_tlb_flush_vmid_range(mmu, ctx->addr,
-						kvm_granule_size(ctx->level));
-		else if (kvm_pte_valid(ctx->old))
+		if (kvm_pte_table(ctx->old, ctx->level)) {
+			u64 size = kvm_granule_size(ctx->level);
+			u64 addr = ALIGN_DOWN(ctx->addr, size);
+
+			kvm_tlb_flush_vmid_range(mmu, addr, size);
+		} else if (kvm_pte_valid(ctx->old)) {
 			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
 				     ctx->addr, ctx->level);
+		}
 	}
 
 	if (stage2_pte_is_counted(ctx->old))
@@ -902,7 +929,7 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 {
 	u64 phys = stage2_map_walker_phys_addr(ctx, data);
 
-	if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1)))
+	if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL)
 		return false;
 
 	return kvm_block_mapping_supported(ctx, phys);
@@ -981,7 +1008,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 	if (ret != -E2BIG)
 		return ret;
 
-	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL))
 		return -EINVAL;
 
 	if (!data->memcache)
@@ -1151,7 +1178,7 @@ struct stage2_attr_data {
 	kvm_pte_t			attr_set;
 	kvm_pte_t			attr_clr;
 	kvm_pte_t			pte;
-	u32				level;
+	s8				level;
 };
 
 static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
@@ -1194,7 +1221,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
 static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 				    u64 size, kvm_pte_t attr_set,
 				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
-				    u32 *level, enum kvm_pgtable_walk_flags flags)
+				    s8 *level, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
@@ -1296,7 +1323,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				   enum kvm_pgtable_prot prot)
 {
 	int ret;
-	u32 level;
+	s8 level;
 	kvm_pte_t set = 0, clr = 0;
 
 	if (prot & KVM_PTE_LEAF_ATTR_HI_SW)
@@ -1349,7 +1376,7 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 }
 
 kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
-					      u64 phys, u32 level,
+					      u64 phys, s8 level,
 					      enum kvm_pgtable_prot prot,
 					      void *mc, bool force_pte)
 {
@@ -1395,7 +1422,6 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
 				 level + 1);
 	if (ret) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level);
-		mm_ops->put_page(pgtable);
 		return ERR_PTR(ret);
 	}
 
@@ -1407,7 +1433,7 @@ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
  * fully populated tree up to the PTE entries. Note that @level is
  * interpreted as in "level @level entry".
  */
-static int stage2_block_get_nr_page_tables(u32 level)
+static int stage2_block_get_nr_page_tables(s8 level)
 {
 	switch (level) {
 	case 1:
@@ -1418,7 +1444,7 @@ static int stage2_block_get_nr_page_tables(u32 level)
 		return 0;
 	default:
 		WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL ||
-			     level >= KVM_PGTABLE_MAX_LEVELS);
+			     level > KVM_PGTABLE_LAST_LEVEL);
 		return -EINVAL;
 	};
 }
@@ -1431,13 +1457,13 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	struct kvm_s2_mmu *mmu;
 	kvm_pte_t pte = ctx->old, new, *childp;
 	enum kvm_pgtable_prot prot;
-	u32 level = ctx->level;
+	s8 level = ctx->level;
 	bool force_pte;
 	int nr_pages;
 	u64 phys;
 
 	/* No huge-pages exist at the last level */
-	if (level == KVM_PGTABLE_MAX_LEVELS - 1)
+	if (level == KVM_PGTABLE_LAST_LEVEL)
 		return 0;
 
 	/* We only split valid block mappings */
@@ -1478,7 +1504,6 @@ static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx,
 
 	if (!stage2_try_break_pte(ctx, mmu)) {
 		kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level);
-		mm_ops->put_page(childp);
 		return -EAGAIN;
 	}
 
@@ -1514,7 +1539,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	u64 vtcr = mmu->vtcr;
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz);
@@ -1537,7 +1562,7 @@ size_t kvm_pgtable_stage2_pgd_size(u64 vtcr)
 {
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
-	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+	s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
 }
@@ -1573,7 +1598,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 	pgt->pgd = NULL;
 }
 
-void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
 	struct kvm_pgtable_walker walker = {
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index b636b4111d..1a60b95381 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -171,7 +171,8 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	/* Switch to requested VMID */
 	__tlb_switch_to_guest(mmu, &cxt);
 
-	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, 0);
+	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
+				TLBI_TTL_UNKNOWN);
 
 	dsb(ish);
 	__tlbi(vmalle1is);
@@ -216,18 +217,5 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-
-	/*
-	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
-	 * is necessary across a VMID rollover.
-	 *
-	 * VPIPT caches constrain lookup and maintenance to the active VMID,
-	 * so we need to invalidate lines with a stale VMID to avoid an ABA
-	 * race after multiple rollovers.
-	 *
-	 */
-	if (icache_is_vpipt())
-		asm volatile("ic ialluis");
-
 	dsb(ish);
 }
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index d87c8fcc4c..92270acfc0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -223,12 +223,12 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 {
 	struct page *page = container_of(head, struct page, rcu_head);
 	void *pgtable = page_to_virt(page);
-	u32 level = page_private(page);
+	s8 level = page_private(page);
 
 	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
 }
 
-static void stage2_free_unlinked_table(void *addr, u32 level)
+static void stage2_free_unlinked_table(void *addr, s8 level)
 {
 	struct page *page = virt_to_page(addr);
 
@@ -804,13 +804,13 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 	struct kvm_pgtable pgt = {
 		.pgd		= (kvm_pteref_t)kvm->mm->pgd,
 		.ia_bits	= vabits_actual,
-		.start_level	= (KVM_PGTABLE_MAX_LEVELS -
-				   CONFIG_PGTABLE_LEVELS),
+		.start_level	= (KVM_PGTABLE_LAST_LEVEL -
+				   CONFIG_PGTABLE_LEVELS + 1),
 		.mm_ops		= &kvm_user_mm_ops,
 	};
 	unsigned long flags;
 	kvm_pte_t pte = 0;	/* Keep GCC quiet... */
-	u32 level = ~0;
+	s8 level = S8_MAX;
 	int ret;
 
 	/*
@@ -829,7 +829,9 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 	 * Not seeing an error, but not updating level? Something went
 	 * deeply wrong...
 	 */
-	if (WARN_ON(level >= KVM_PGTABLE_MAX_LEVELS))
+	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
+		return -EFAULT;
+	if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL))
 		return -EFAULT;
 
 	/* Oops, the userspace PTs are gone... Replay the fault */
@@ -1374,7 +1376,7 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
 
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
-			  unsigned long fault_status)
+			  bool fault_is_perm)
 {
 	int ret = 0;
 	bool write_fault, writable, force_pte = false;
@@ -1388,17 +1390,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
-	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 
-	fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level);
+	if (fault_is_perm)
+		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
-	if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
+	if (fault_is_perm && !write_fault && !exec_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
 	}
@@ -1409,8 +1411,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * only exception to this is when dirty logging is enabled at runtime
 	 * and a write fault needs to collapse a block entry into a table.
 	 */
-	if (fault_status != ESR_ELx_FSC_PERM ||
-	    (logging_active && write_fault)) {
+	if (!fault_is_perm || (logging_active && write_fault)) {
 		ret = kvm_mmu_topup_memory_cache(memcache,
 						 kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
 		if (ret)
@@ -1527,8 +1528,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * backed by a THP and thus use block mapping if possible.
 	 */
 	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
-		if (fault_status ==  ESR_ELx_FSC_PERM &&
-		    fault_granule > PAGE_SIZE)
+		if (fault_is_perm && fault_granule > PAGE_SIZE)
 			vma_pagesize = fault_granule;
 		else
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@@ -1541,7 +1541,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		}
 	}
 
-	if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
+	if (!fault_is_perm && !device && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new disallowed VMA */
 		if (mte_allowed) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1567,7 +1567,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
+	if (fault_is_perm && vma_pagesize == fault_granule)
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	else
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
@@ -1618,7 +1618,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
  */
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 {
-	unsigned long fault_status;
+	unsigned long esr;
 	phys_addr_t fault_ipa;
 	struct kvm_memory_slot *memslot;
 	unsigned long hva;
@@ -1626,12 +1626,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
-	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
+	esr = kvm_vcpu_get_esr(vcpu);
 
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
 
-	if (fault_status == ESR_ELx_FSC_FAULT) {
+	if (esr_fsc_is_translation_fault(esr)) {
 		/* Beyond sanitised PARange (which is the IPA limit) */
 		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
 			kvm_inject_size_fault(vcpu);
@@ -1666,9 +1666,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	if (fault_status != ESR_ELx_FSC_FAULT &&
-	    fault_status != ESR_ELx_FSC_PERM &&
-	    fault_status != ESR_ELx_FSC_ACCESS) {
+	if (!esr_fsc_is_translation_fault(esr) &&
+	    !esr_fsc_is_permission_fault(esr) &&
+	    !esr_fsc_is_access_flag_fault(esr)) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1730,13 +1730,14 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	/* Userspace should not be able to register out-of-bounds IPAs */
 	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->arch.hw_mmu));
 
-	if (fault_status == ESR_ELx_FSC_ACCESS) {
+	if (esr_fsc_is_access_flag_fault(esr)) {
 		handle_access_fault(vcpu, fault_ipa);
 		ret = 1;
 		goto out_unlock;
 	}
 
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva,
+			     esr_fsc_is_permission_fault(esr));
 	if (ret == 0)
 		ret = 1;
 out:
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 042695a210..ba95d044bc 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -23,13 +23,9 @@
  * This list should get updated as new features get added to the NV
  * support, and new extension to the architecture.
  */
-void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
-			  const struct sys_reg_desc *r)
+static u64 limit_nv_id_reg(u32 id, u64 val)
 {
-	u32 id = reg_to_encoding(r);
-	u64 val, tmp;
-
-	val = p->regval;
+	u64 tmp;
 
 	switch (id) {
 	case SYS_ID_AA64ISAR0_EL1:
@@ -158,5 +154,17 @@ void access_nested_id_reg(struct kvm_vcpu *v, struct sys_reg_params *p,
 		break;
 	}
 
-	p->regval = val;
+	return val;
+}
+int kvm_init_nv_sysregs(struct kvm *kvm)
+{
+	mutex_lock(&kvm->arch.config_lock);
+
+	for (int i = 0; i < KVM_ARM_ID_REG_NUM; i++)
+		kvm->arch.id_regs[i] = limit_nv_id_reg(IDX_IDREG(i),
+						       kvm->arch.id_regs[i]);
+
+	mutex_unlock(&kvm->arch.config_lock);
+
+	return 0;
 }
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index fe99b3dab6..3d9467ff73 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -267,9 +267,8 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 {
-	u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT;
+	u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu));
 
-	val &= ARMV8_PMU_PMCR_N_MASK;
 	if (val == 0)
 		return BIT(ARMV8_PMU_CYCLE_IDX);
 	else
@@ -1136,8 +1135,7 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
  */
 u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
 {
-	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) &
-			~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
 
-	return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+	return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N);
 }
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 5bb4de162c..68d1d05672 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -280,12 +280,11 @@ int __init kvm_set_ipa_limit(void)
 	parange = cpuid_feature_extract_unsigned_field(mmfr0,
 				ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 	/*
-	 * IPA size beyond 48 bits could not be supported
-	 * on either 4K or 16K page size. Hence let's cap
-	 * it to 48 bits, in case it's reported as larger
-	 * on the system.
+	 * IPA size beyond 48 bits for 4K and 16K page size is only supported
+	 * when LPA2 is available. So if we have LPA2, enable it, else cap to 48
+	 * bits, in case it's reported as larger on the system.
 	 */
-	if (PAGE_SIZE != SZ_64K)
+	if (!kvm_lpa2_is_enabled() && PAGE_SIZE != SZ_64K)
 		parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48);
 
 	/*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4735e1b37f..30253bd199 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -45,44 +45,170 @@ static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
 static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      u64 val);
 
-static bool read_from_write_only(struct kvm_vcpu *vcpu,
-				 struct sys_reg_params *params,
-				 const struct sys_reg_desc *r)
+static bool bad_trap(struct kvm_vcpu *vcpu,
+		     struct sys_reg_params *params,
+		     const struct sys_reg_desc *r,
+		     const char *msg)
 {
-	WARN_ONCE(1, "Unexpected sys_reg read to write-only register\n");
+	WARN_ONCE(1, "Unexpected %s\n", msg);
 	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 	return false;
 }
 
+static bool read_from_write_only(struct kvm_vcpu *vcpu,
+				 struct sys_reg_params *params,
+				 const struct sys_reg_desc *r)
+{
+	return bad_trap(vcpu, params, r,
+			"sys_reg read to write-only register");
+}
+
 static bool write_to_read_only(struct kvm_vcpu *vcpu,
 			       struct sys_reg_params *params,
 			       const struct sys_reg_desc *r)
 {
-	WARN_ONCE(1, "Unexpected sys_reg write to read-only register\n");
-	print_sys_reg_instr(params);
-	kvm_inject_undefined(vcpu);
-	return false;
+	return bad_trap(vcpu, params, r,
+			"sys_reg write to read-only register");
+}
+
+#define PURE_EL2_SYSREG(el2)						\
+	case el2: {							\
+		*el1r = el2;						\
+		return true;						\
+	}
+
+#define MAPPED_EL2_SYSREG(el2, el1, fn)					\
+	case el2: {							\
+		*xlate = fn;						\
+		*el1r = el1;						\
+		return true;						\
+	}
+
+static bool get_el2_to_el1_mapping(unsigned int reg,
+				   unsigned int *el1r, u64 (**xlate)(u64))
+{
+	switch (reg) {
+		PURE_EL2_SYSREG(  VPIDR_EL2	);
+		PURE_EL2_SYSREG(  VMPIDR_EL2	);
+		PURE_EL2_SYSREG(  ACTLR_EL2	);
+		PURE_EL2_SYSREG(  HCR_EL2	);
+		PURE_EL2_SYSREG(  MDCR_EL2	);
+		PURE_EL2_SYSREG(  HSTR_EL2	);
+		PURE_EL2_SYSREG(  HACR_EL2	);
+		PURE_EL2_SYSREG(  VTTBR_EL2	);
+		PURE_EL2_SYSREG(  VTCR_EL2	);
+		PURE_EL2_SYSREG(  RVBAR_EL2	);
+		PURE_EL2_SYSREG(  TPIDR_EL2	);
+		PURE_EL2_SYSREG(  HPFAR_EL2	);
+		PURE_EL2_SYSREG(  CNTHCTL_EL2	);
+		MAPPED_EL2_SYSREG(SCTLR_EL2,   SCTLR_EL1,
+				  translate_sctlr_el2_to_sctlr_el1	     );
+		MAPPED_EL2_SYSREG(CPTR_EL2,    CPACR_EL1,
+				  translate_cptr_el2_to_cpacr_el1	     );
+		MAPPED_EL2_SYSREG(TTBR0_EL2,   TTBR0_EL1,
+				  translate_ttbr0_el2_to_ttbr0_el1	     );
+		MAPPED_EL2_SYSREG(TTBR1_EL2,   TTBR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(TCR_EL2,     TCR_EL1,
+				  translate_tcr_el2_to_tcr_el1		     );
+		MAPPED_EL2_SYSREG(VBAR_EL2,    VBAR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AFSR0_EL2,   AFSR0_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(AFSR1_EL2,   AFSR1_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(ESR_EL2,     ESR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(FAR_EL2,     FAR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(MAIR_EL2,    MAIR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(AMAIR_EL2,   AMAIR_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(ELR_EL2,     ELR_EL1,	    NULL	     );
+		MAPPED_EL2_SYSREG(SPSR_EL2,    SPSR_EL1,    NULL	     );
+	default:
+		return false;
+	}
 }
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	u64 val = 0x8badf00d8badf00d;
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
+		goto memory_read;
 
-	if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-	    __vcpu_read_sys_reg_from_cpu(reg, &val))
+	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_read;
+
+		/*
+		 * If this register does not have an EL1 counterpart,
+		 * then read the stored EL2 version.
+		 */
+		if (reg == el1r)
+			goto memory_read;
+
+		/*
+		 * If we have a non-VHE guest and that the sysreg
+		 * requires translation to be used at EL1, use the
+		 * in-memory copy instead.
+		 */
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			goto memory_read;
+
+		/* Get the current version of the EL1 counterpart. */
+		WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
 		return val;
+	}
 
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_read;
+
+	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
+		return val;
+
+memory_read:
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-	    __vcpu_write_sys_reg_to_cpu(val, reg))
+	u64 (*xlate)(u64) = NULL;
+	unsigned int el1r;
+
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
+		goto memory_write;
+
+	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
+		if (!is_hyp_ctxt(vcpu))
+			goto memory_write;
+
+		/*
+		 * Always store a copy of the write to memory to avoid having
+		 * to reverse-translate virtual EL2 system registers for a
+		 * non-VHE guest hypervisor.
+		 */
+		__vcpu_sys_reg(vcpu, reg) = val;
+
+		/* No EL1 counterpart? We're done here.? */
+		if (reg == el1r)
+			return;
+
+		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
+			val = xlate(val);
+
+		/* Redirect this to the EL1 version of the register. */
+		WARN_ON(!__vcpu_write_sys_reg_to_cpu(val, el1r));
+		return;
+	}
+
+	/* EL1 register can't be on the CPU if the guest is in vEL2. */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		goto memory_write;
+
+	if (__vcpu_write_sys_reg_to_cpu(val, reg))
 		return;
 
-	__vcpu_sys_reg(vcpu, reg) = val;
+memory_write:
+	 __vcpu_sys_reg(vcpu, reg) = val;
 }
 
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
@@ -877,7 +1003,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 	u64 pmcr, val;
 
 	pmcr = kvm_vcpu_read_pmcr(vcpu);
-	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr);
 	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
 		kvm_inject_undefined(vcpu);
 		return false;
@@ -1143,7 +1269,7 @@ static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 		    u64 val)
 {
-	u8 new_n = (val >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	u8 new_n = FIELD_GET(ARMV8_PMU_PMCR_N, val);
 	struct kvm *kvm = vcpu->kvm;
 
 	mutex_lock(&kvm->arch.config_lock);
@@ -1505,8 +1631,6 @@ static bool access_id_reg(struct kvm_vcpu *vcpu,
 		return write_to_read_only(vcpu, p, r);
 
 	p->regval = read_id_reg(vcpu, r);
-	if (vcpu_has_nv(vcpu))
-		access_nested_id_reg(vcpu, p, r);
 
 	return true;
 }
@@ -1885,6 +2009,32 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
 	return REG_HIDDEN;
 }
 
+static bool bad_vncr_trap(struct kvm_vcpu *vcpu,
+			  struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	/*
+	 * We really shouldn't be here, and this is likely the result
+	 * of a misconfigured trap, as this register should target the
+	 * VNCR page, and nothing else.
+	 */
+	return bad_trap(vcpu, p, r,
+			"trap of VNCR-backed register");
+}
+
+static bool bad_redir_trap(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	/*
+	 * We really shouldn't be here, and this is likely the result
+	 * of a misconfigured trap, as this register should target the
+	 * corresponding EL1, and nothing else.
+	 */
+	return bad_trap(vcpu, p, r,
+			"trap of EL2 register redirected to EL1");
+}
+
 #define EL2_REG(name, acc, rst, v) {		\
 	SYS_DESC(SYS_##name),			\
 	.access = acc,				\
@@ -1894,6 +2044,9 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu,
 	.val = v,				\
 }
 
+#define EL2_REG_VNCR(name, rst, v)	EL2_REG(name, bad_vncr_trap, rst, v)
+#define EL2_REG_REDIR(name, rst, v)	EL2_REG(name, bad_redir_trap, rst, v)
+
 /*
  * EL{0,1}2 registers are the EL2 view on an EL0 or EL1 register when
  * HCR_EL2.E2H==1, and only in the sysreg table for convenience of
@@ -2508,32 +2661,33 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ PMU_SYS_REG(PMCCFILTR_EL0), .access = access_pmu_evtyper,
 	  .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 },
 
-	EL2_REG(VPIDR_EL2, access_rw, reset_unknown, 0),
-	EL2_REG(VMPIDR_EL2, access_rw, reset_unknown, 0),
+	EL2_REG_VNCR(VPIDR_EL2, reset_unknown, 0),
+	EL2_REG_VNCR(VMPIDR_EL2, reset_unknown, 0),
 	EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1),
 	EL2_REG(ACTLR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HCR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HCR_EL2, reset_val, 0),
 	EL2_REG(MDCR_EL2, access_rw, reset_val, 0),
 	EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
-	EL2_REG(HSTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGRTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGWTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HFGITR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HACR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HSTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGWTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HFGITR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HACR_EL2, reset_val, 0),
 
-	EL2_REG(HCRX_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HCRX_EL2, reset_val, 0),
 
 	EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(TTBR1_EL2, access_rw, reset_val, 0),
 	EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1),
-	EL2_REG(VTTBR_EL2, access_rw, reset_val, 0),
-	EL2_REG(VTCR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(VTTBR_EL2, reset_val, 0),
+	EL2_REG_VNCR(VTCR_EL2, reset_val, 0),
 
 	{ SYS_DESC(SYS_DACR32_EL2), trap_undef, reset_unknown, DACR32_EL2 },
-	EL2_REG(HDFGRTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(HDFGWTR_EL2, access_rw, reset_val, 0),
-	EL2_REG(SPSR_EL2, access_rw, reset_val, 0),
-	EL2_REG(ELR_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(HDFGRTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HDFGWTR_EL2, reset_val, 0),
+	EL2_REG_VNCR(HAFGRTR_EL2, reset_val, 0),
+	EL2_REG_REDIR(SPSR_EL2, reset_val, 0),
+	EL2_REG_REDIR(ELR_EL2, reset_val, 0),
 	{ SYS_DESC(SYS_SP_EL1), access_sp_el1},
 
 	/* AArch32 SPSR_* are RES0 if trapped from a NV guest */
@@ -2549,10 +2703,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_IFSR32_EL2), trap_undef, reset_unknown, IFSR32_EL2 },
 	EL2_REG(AFSR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(AFSR1_EL2, access_rw, reset_val, 0),
-	EL2_REG(ESR_EL2, access_rw, reset_val, 0),
+	EL2_REG_REDIR(ESR_EL2, reset_val, 0),
 	{ SYS_DESC(SYS_FPEXC32_EL2), trap_undef, reset_val, FPEXC32_EL2, 0x700 },
 
-	EL2_REG(FAR_EL2, access_rw, reset_val, 0),
+	EL2_REG_REDIR(FAR_EL2, reset_val, 0),
 	EL2_REG(HPFAR_EL2, access_rw, reset_val, 0),
 
 	EL2_REG(MAIR_EL2, access_rw, reset_val, 0),
@@ -2565,24 +2719,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0),
 	EL2_REG(TPIDR_EL2, access_rw, reset_val, 0),
 
-	EL2_REG(CNTVOFF_EL2, access_rw, reset_val, 0),
+	EL2_REG_VNCR(CNTVOFF_EL2, reset_val, 0),
 	EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
 
-	EL12_REG(SCTLR, access_vm_reg, reset_val, 0x00C50078),
-	EL12_REG(CPACR, access_rw, reset_val, 0),
-	EL12_REG(TTBR0, access_vm_reg, reset_unknown, 0),
-	EL12_REG(TTBR1, access_vm_reg, reset_unknown, 0),
-	EL12_REG(TCR, access_vm_reg, reset_val, 0),
-	{ SYS_DESC(SYS_SPSR_EL12), access_spsr},
-	{ SYS_DESC(SYS_ELR_EL12), access_elr},
-	EL12_REG(AFSR0, access_vm_reg, reset_unknown, 0),
-	EL12_REG(AFSR1, access_vm_reg, reset_unknown, 0),
-	EL12_REG(ESR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(FAR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(MAIR, access_vm_reg, reset_unknown, 0),
-	EL12_REG(AMAIR, access_vm_reg, reset_amair_el1, 0),
-	EL12_REG(VBAR, access_rw, reset_val, 0),
-	EL12_REG(CONTEXTIDR, access_vm_reg, reset_val, 0),
 	EL12_REG(CNTKCTL, access_rw, reset_val, 0),
 
 	EL2_REG(SP_EL2, NULL, reset_unknown, 0),
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index 2533f264b9..c15ee1df03 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -357,38 +357,13 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
 					 gpa_t addr, unsigned int len,
 					 unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for (i = 0; i < len * 8; i++) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-
-		/*
-		 * pending_latch is set irrespective of irq type
-		 * (level or edge) to avoid dependency that VM should
-		 * restore irq config before pending info.
-		 */
-		irq->pending_latch = test_bit(i, &val);
-
-		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
-			irq_set_irqchip_state(irq->host_irq,
-					      IRQCHIP_STATE_PENDING,
-					      irq->pending_latch);
-			irq->pending_latch = false;
-		}
-
-		if (irq->pending_latch)
-			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
-		else
-			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+	int ret;
 
-		vgic_put_irq(vcpu->kvm, irq);
-	}
+	ret = vgic_uaccess_write_spending(vcpu, addr, len, val);
+	if (ret)
+		return ret;
 
-	return 0;
+	return vgic_uaccess_write_cpending(vcpu, addr, len, ~val);
 }
 
 /* We want to avoid outer shareable. */
diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c
index ff558c05e9..cf76523a21 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@@ -301,9 +301,8 @@ static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 		vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2);
 }
 
-void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
-			      gpa_t addr, unsigned int len,
-			      unsigned long val)
+static void __set_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len,
+			  unsigned long val, bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
@@ -312,14 +311,22 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		/* GICD_ISPENDR0 SGI bits are WI */
-		if (is_vgic_v2_sgi(vcpu, irq)) {
+		/* GICD_ISPENDR0 SGI bits are WI when written from the guest. */
+		if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
 			vgic_put_irq(vcpu->kvm, irq);
 			continue;
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
+		/*
+		 * GICv2 SGIs are terribly broken. We can't restore
+		 * the source of the interrupt, so just pick the vcpu
+		 * itself as the source...
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source |= BIT(vcpu->vcpu_id);
+
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			/* HW SGI? Ask the GIC to inject it */
 			int err;
@@ -335,7 +342,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 		}
 
 		irq->pending_latch = true;
-		if (irq->hw)
+		if (irq->hw && !is_user)
 			vgic_irq_set_phys_active(irq, true);
 
 		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
@@ -343,33 +350,18 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 	}
 }
 
+void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
+			      gpa_t addr, unsigned int len,
+			      unsigned long val)
+{
+	__set_pending(vcpu, addr, len, val, false);
+}
+
 int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
 				gpa_t addr, unsigned int len,
 				unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for_each_set_bit(i, &val, len * 8) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		irq->pending_latch = true;
-
-		/*
-		 * GICv2 SGIs are terribly broken. We can't restore
-		 * the source of the interrupt, so just pick the vcpu
-		 * itself as the source...
-		 */
-		if (is_vgic_v2_sgi(vcpu, irq))
-			irq->source |= BIT(vcpu->vcpu_id);
-
-		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
+	__set_pending(vcpu, addr, len, val, true);
 	return 0;
 }
 
@@ -394,9 +386,9 @@ static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
 		vgic_irq_set_phys_active(irq, false);
 }
 
-void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
-			      gpa_t addr, unsigned int len,
-			      unsigned long val)
+static void __clear_pending(struct kvm_vcpu *vcpu,
+			    gpa_t addr, unsigned int len,
+			    unsigned long val, bool is_user)
 {
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
@@ -405,14 +397,22 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	for_each_set_bit(i, &val, len * 8) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
 
-		/* GICD_ICPENDR0 SGI bits are WI */
-		if (is_vgic_v2_sgi(vcpu, irq)) {
+		/* GICD_ICPENDR0 SGI bits are WI when written from the guest. */
+		if (is_vgic_v2_sgi(vcpu, irq) && !is_user) {
 			vgic_put_irq(vcpu->kvm, irq);
 			continue;
 		}
 
 		raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
+		/*
+		 * More fun with GICv2 SGIs! If we're clearing one of them
+		 * from userspace, which source vcpu to clear? Let's not
+		 * even think of it, and blow the whole set.
+		 */
+		if (is_vgic_v2_sgi(vcpu, irq))
+			irq->source = 0;
+
 		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
 			/* HW SGI? Ask the GIC to clear its pending bit */
 			int err;
@@ -427,7 +427,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			continue;
 		}
 
-		if (irq->hw)
+		if (irq->hw && !is_user)
 			vgic_hw_irq_cpending(vcpu, irq);
 		else
 			irq->pending_latch = false;
@@ -437,33 +437,18 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 	}
 }
 
+void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
+			      gpa_t addr, unsigned int len,
+			      unsigned long val)
+{
+	__clear_pending(vcpu, addr, len, val, false);
+}
+
 int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
 				gpa_t addr, unsigned int len,
 				unsigned long val)
 {
-	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
-	int i;
-	unsigned long flags;
-
-	for_each_set_bit(i, &val, len * 8) {
-		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
-
-		raw_spin_lock_irqsave(&irq->irq_lock, flags);
-		/*
-		 * More fun with GICv2 SGIs! If we're clearing one of them
-		 * from userspace, which source vcpu to clear? Let's not
-		 * even think of it, and blow the whole set.
-		 */
-		if (is_vgic_v2_sgi(vcpu, irq))
-			irq->source = 0;
-
-		irq->pending_latch = false;
-
-		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
-
-		vgic_put_irq(vcpu->kvm, irq);
-	}
-
+	__clear_pending(vcpu, addr, len, val, true);
 	return 0;
 }