Merge tag 'kvmarm-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 5.16

- More progress on the protected VM front, now with the full
  fixed feature set as well as the limitation of some hypercalls
  after initialisation.

- Cleanup of the RAZ/WI sysreg handling, which was pointlessly
  complicated

- Fixes for the vgic placement in the IPA space, together with a
  bunch of selftests

- More memcg accounting of the memory allocated on behalf of a guest

- Timer and vgic selftests

- Workarounds for the Apple M1 broken vgic implementation

- KConfig cleanups

- New kvmarm.mode=none option, for those who really dislike us

8 files changed, 832 insertions, 29 deletions

diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 8d741f71377f..c3c11974fa3b 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -14,7 +14,7 @@ lib-objs := $(addprefix ../../../lib/, $(lib-objs))
 
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
 	 hyp-main.o hyp-smp.o psci-relay.o early_alloc.o stub.o page_alloc.o \
-	 cache.o setup.o mm.o mem_protect.o
+	 cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 	 ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o
 obj-y += $(lib-objs)
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 4b652ffb591d..0c6116d34e18 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -110,17 +110,14 @@ SYM_FUNC_START(__hyp_do_panic)
 	b	__host_enter_for_panic
 SYM_FUNC_END(__hyp_do_panic)
 
-.macro host_el1_sync_vect
-	.align 7
-.L__vect_start\@:
-	stp	x0, x1, [sp, #-16]!
-	mrs	x0, esr_el2
-	lsr	x0, x0, #ESR_ELx_EC_SHIFT
-	cmp	x0, #ESR_ELx_EC_HVC64
-	b.ne	__host_exit
-
+SYM_FUNC_START(__host_hvc)
 	ldp	x0, x1, [sp]		// Don't fixup the stack yet
 
+	/* No stub for you, sonny Jim */
+alternative_if ARM64_KVM_PROTECTED_MODE
+	b	__host_exit
+alternative_else_nop_endif
+
 	/* Check for a stub HVC call */
 	cmp	x0, #HVC_STUB_HCALL_NR
 	b.hs	__host_exit
@@ -137,6 +134,17 @@ SYM_FUNC_END(__hyp_do_panic)
 	ldr	x5, =__kvm_handle_stub_hvc
 	hyp_pa	x5, x6
 	br	x5
+SYM_FUNC_END(__host_hvc)
+
+.macro host_el1_sync_vect
+	.align 7
+.L__vect_start\@:
+	stp	x0, x1, [sp, #-16]!
+	mrs	x0, esr_el2
+	lsr	x0, x0, #ESR_ELx_EC_SHIFT
+	cmp	x0, #ESR_ELx_EC_HVC64
+	b.eq	__host_hvc
+	b	__host_exit
 .L__vect_end\@:
 .if ((.L__vect_end\@ - .L__vect_start\@) > 0x80)
 	.error "host_el1_sync_vect larger than vector entry"
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 2da6aa8da868..b096bf009144 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -4,7 +4,7 @@
  * Author: Andrew Scull <ascull@google.com>
  */
 
-#include <hyp/switch.h>
+#include <hyp/adjust_pc.h>
 
 #include <asm/pgtable-types.h>
 #include <asm/kvm_asm.h>
@@ -160,41 +160,65 @@ static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt)
 {
 	cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize();
 }
+
+static void handle___pkvm_vcpu_init_traps(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
+
+	__pkvm_vcpu_init_traps(kern_hyp_va(vcpu));
+}
+
 typedef void (*hcall_t)(struct kvm_cpu_context *);
 
 #define HANDLE_FUNC(x)	[__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x
 
 static const hcall_t host_hcall[] = {
-	HANDLE_FUNC(__kvm_vcpu_run),
+	/* ___kvm_hyp_init */
+	HANDLE_FUNC(__kvm_get_mdcr_el2),
+	HANDLE_FUNC(__pkvm_init),
+	HANDLE_FUNC(__pkvm_create_private_mapping),
+	HANDLE_FUNC(__pkvm_cpu_set_vector),
+	HANDLE_FUNC(__kvm_enable_ssbs),
+	HANDLE_FUNC(__vgic_v3_init_lrs),
+	HANDLE_FUNC(__vgic_v3_get_gic_config),
+	HANDLE_FUNC(__pkvm_prot_finalize),
+
+	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__kvm_adjust_pc),
+	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
 	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
-	HANDLE_FUNC(__kvm_enable_ssbs),
-	HANDLE_FUNC(__vgic_v3_get_gic_config),
 	HANDLE_FUNC(__vgic_v3_read_vmcr),
 	HANDLE_FUNC(__vgic_v3_write_vmcr),
-	HANDLE_FUNC(__vgic_v3_init_lrs),
-	HANDLE_FUNC(__kvm_get_mdcr_el2),
 	HANDLE_FUNC(__vgic_v3_save_aprs),
 	HANDLE_FUNC(__vgic_v3_restore_aprs),
-	HANDLE_FUNC(__pkvm_init),
-	HANDLE_FUNC(__pkvm_cpu_set_vector),
-	HANDLE_FUNC(__pkvm_host_share_hyp),
-	HANDLE_FUNC(__pkvm_create_private_mapping),
-	HANDLE_FUNC(__pkvm_prot_finalize),
+	HANDLE_FUNC(__pkvm_vcpu_init_traps),
 };
 
 static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(unsigned long, id, host_ctxt, 0);
+	unsigned long hcall_min = 0;
 	hcall_t hfn;
 
+	/*
+	 * If pKVM has been initialised then reject any calls to the
+	 * early "privileged" hypercalls. Note that we cannot reject
+	 * calls to __pkvm_prot_finalize for two reasons: (1) The static
+	 * key used to determine initialisation must be toggled prior to
+	 * finalisation and (2) finalisation is performed on a per-CPU
+	 * basis. This is all fine, however, since __pkvm_prot_finalize
+	 * returns -EPERM after the first call for a given CPU.
+	 */
+	if (static_branch_unlikely(&kvm_protected_mode_initialized))
+		hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize;
+
 	id -= KVM_HOST_SMCCC_ID(0);
 
-	if (unlikely(id >= ARRAY_SIZE(host_hcall)))
+	if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall)))
 		goto inval;
 
 	hfn = host_hcall[id];
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 34eeb524b686..c1a90dd022b8 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -11,7 +11,7 @@
 #include <asm/kvm_pgtable.h>
 #include <asm/stage2_pgtable.h>
 
-#include <hyp/switch.h>
+#include <hyp/fault.h>
 
 #include <nvhe/gfp.h>
 #include <nvhe/memory.h>
@@ -25,12 +25,6 @@ struct host_kvm host_kvm;
 
 static struct hyp_pool host_s2_pool;
 
-/*
- * Copies of the host's CPU features registers holding sanitized values.
- */
-u64 id_aa64mmfr0_el1_sys_val;
-u64 id_aa64mmfr1_el1_sys_val;
-
 const u8 pkvm_hyp_id = 1;
 
 static void *host_s2_zalloc_pages_exact(size_t size)
@@ -134,6 +128,9 @@ int __pkvm_prot_finalize(void)
 	struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu;
 	struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params);
 
+	if (params->hcr_el2 & HCR_VM)
+		return -EPERM;
+
 	params->vttbr = kvm_get_vttbr(mmu);
 	params->vtcr = host_kvm.arch.vtcr;
 	params->hcr_el2 |= HCR_VM;
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
new file mode 100644
index 000000000000..99c8d8b73e70
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/mm.h>
+#include <nvhe/fixed_config.h>
+#include <nvhe/trap_handler.h>
+
+/*
+ * Set trap register values based on features in ID_AA64PFR0.
+ */
+static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR0_EL1);
+	u64 hcr_set = HCR_RW;
+	u64 hcr_clear = 0;
+	u64 cptr_set = 0;
+
+	/* Protected KVM does not support AArch32 guests. */
+	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0),
+		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY);
+	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1),
+		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY);
+
+	/*
+	 * Linux guests assume support for floating-point and Advanced SIMD. Do
+	 * not change the trapping behavior for these from the KVM default.
+	 */
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP),
+				PVM_ID_AA64PFR0_ALLOW));
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD),
+				PVM_ID_AA64PFR0_ALLOW));
+
+	/* Trap RAS unless all current versions are supported */
+	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_RAS), feature_ids) <
+	    ID_AA64PFR0_RAS_V1P1) {
+		hcr_set |= HCR_TERR | HCR_TEA;
+		hcr_clear |= HCR_FIEN;
+	}
+
+	/* Trap AMU */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_AMU), feature_ids)) {
+		hcr_clear |= HCR_AMVOFFEN;
+		cptr_set |= CPTR_EL2_TAM;
+	}
+
+	/* Trap SVE */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_SVE), feature_ids))
+		cptr_set |= CPTR_EL2_TZ;
+
+	vcpu->arch.hcr_el2 |= hcr_set;
+	vcpu->arch.hcr_el2 &= ~hcr_clear;
+	vcpu->arch.cptr_el2 |= cptr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64PFR1.
+ */
+static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR1_EL1);
+	u64 hcr_set = 0;
+	u64 hcr_clear = 0;
+
+	/* Memory Tagging: Trap and Treat as Untagged if not supported. */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), feature_ids)) {
+		hcr_set |= HCR_TID5;
+		hcr_clear |= HCR_DCT | HCR_ATA;
+	}
+
+	vcpu->arch.hcr_el2 |= hcr_set;
+	vcpu->arch.hcr_el2 &= ~hcr_clear;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64DFR0.
+ */
+static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64DFR0_EL1);
+	u64 mdcr_set = 0;
+	u64 mdcr_clear = 0;
+	u64 cptr_set = 0;
+
+	/* Trap/constrain PMU */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMUVER), feature_ids)) {
+		mdcr_set |= MDCR_EL2_TPM | MDCR_EL2_TPMCR;
+		mdcr_clear |= MDCR_EL2_HPME | MDCR_EL2_MTPME |
+			      MDCR_EL2_HPMN_MASK;
+	}
+
+	/* Trap Debug */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER), feature_ids))
+		mdcr_set |= MDCR_EL2_TDRA | MDCR_EL2_TDA | MDCR_EL2_TDE;
+
+	/* Trap OS Double Lock */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DOUBLELOCK), feature_ids))
+		mdcr_set |= MDCR_EL2_TDOSA;
+
+	/* Trap SPE */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMSVER), feature_ids)) {
+		mdcr_set |= MDCR_EL2_TPMS;
+		mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+	}
+
+	/* Trap Trace Filter */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACE_FILT), feature_ids))
+		mdcr_set |= MDCR_EL2_TTRF;
+
+	/* Trap Trace */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACEVER), feature_ids))
+		cptr_set |= CPTR_EL2_TTA;
+
+	vcpu->arch.mdcr_el2 |= mdcr_set;
+	vcpu->arch.mdcr_el2 &= ~mdcr_clear;
+	vcpu->arch.cptr_el2 |= cptr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64MMFR0.
+ */
+static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR0_EL1);
+	u64 mdcr_set = 0;
+
+	/* Trap Debug Communications Channel registers */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_FGT), feature_ids))
+		mdcr_set |= MDCR_EL2_TDCC;
+
+	vcpu->arch.mdcr_el2 |= mdcr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64MMFR1.
+ */
+static void pvm_init_traps_aa64mmfr1(struct kvm_vcpu *vcpu)
+{
+	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR1_EL1);
+	u64 hcr_set = 0;
+
+	/* Trap LOR */
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_LOR), feature_ids))
+		hcr_set |= HCR_TLOR;
+
+	vcpu->arch.hcr_el2 |= hcr_set;
+}
+
+/*
+ * Set baseline trap register values.
+ */
+static void pvm_init_trap_regs(struct kvm_vcpu *vcpu)
+{
+	const u64 hcr_trap_feat_regs = HCR_TID3;
+	const u64 hcr_trap_impdef = HCR_TACR | HCR_TIDCP | HCR_TID1;
+
+	/*
+	 * Always trap:
+	 * - Feature id registers: to control features exposed to guests
+	 * - Implementation-defined features
+	 */
+	vcpu->arch.hcr_el2 |= hcr_trap_feat_regs | hcr_trap_impdef;
+
+	/* Clear res0 and set res1 bits to trap potential new features. */
+	vcpu->arch.hcr_el2 &= ~(HCR_RES0);
+	vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0);
+	vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1;
+	vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0);
+}
+
+/*
+ * Initialize trap register values for protected VMs.
+ */
+void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu)
+{
+	pvm_init_trap_regs(vcpu);
+	pvm_init_traps_aa64pfr0(vcpu);
+	pvm_init_traps_aa64pfr1(vcpu);
+	pvm_init_traps_aa64dfr0(vcpu);
+	pvm_init_traps_aa64mmfr0(vcpu);
+	pvm_init_traps_aa64mmfr1(vcpu);
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 57c27846320f..862c7b514e20 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -10,6 +10,7 @@
 #include <asm/kvm_pgtable.h>
 
 #include <nvhe/early_alloc.h>
+#include <nvhe/fixed_config.h>
 #include <nvhe/gfp.h>
 #include <nvhe/memory.h>
 #include <nvhe/mem_protect.h>
@@ -260,6 +261,8 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 	void (*fn)(phys_addr_t params_pa, void *finalize_fn_va);
 	int ret;
 
+	BUG_ON(kvm_check_pvm_sysreg_table());
+
 	if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
 		return -EINVAL;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index a34b01cc8ab9..c0e3fed26d93 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -27,6 +27,7 @@
 #include <asm/processor.h>
 #include <asm/thread_info.h>
 
+#include <nvhe/fixed_config.h>
 #include <nvhe/mem_protect.h>
 
 /* Non-VHE specific context */
@@ -158,6 +159,101 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
 		write_sysreg(pmu->events_host, pmcntenset_el0);
 }
 
+/**
+ * Handler for protected VM MSR, MRS or System instruction execution in AArch64.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't.
+ */
+static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	/*
+	 * Make sure we handle the exit for workarounds and ptrauth
+	 * before the pKVM handling, as the latter could decide to
+	 * UNDEF.
+	 */
+	return (kvm_hyp_handle_sysreg(vcpu, exit_code) ||
+		kvm_handle_pvm_sysreg(vcpu, exit_code));
+}
+
+/**
+ * Handler for protected floating-point and Advanced SIMD accesses.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't.
+ */
+static bool kvm_handle_pvm_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	/* Linux guests assume support for floating-point and Advanced SIMD. */
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP),
+				PVM_ID_AA64PFR0_ALLOW));
+	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD),
+				PVM_ID_AA64PFR0_ALLOW));
+
+	return kvm_hyp_handle_fpsimd(vcpu, exit_code);
+}
+
+static const exit_handler_fn hyp_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]		= NULL,
+	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
+	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg,
+	[ESR_ELx_EC_SVE]		= kvm_hyp_handle_fpsimd,
+	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
+	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
+	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+};
+
+static const exit_handler_fn pvm_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]		= NULL,
+	[ESR_ELx_EC_SYS64]		= kvm_handle_pvm_sys64,
+	[ESR_ELx_EC_SVE]		= kvm_handle_pvm_restricted,
+	[ESR_ELx_EC_FP_ASIMD]		= kvm_handle_pvm_fpsimd,
+	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
+	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
+	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+};
+
+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))))
+		return pvm_exit_handlers;
+
+	return hyp_exit_handlers;
+}
+
+/*
+ * Some guests (e.g., protected VMs) are not be allowed to run in AArch32.
+ * The ARMv8 architecture does not give the hypervisor a mechanism to prevent a
+ * guest from dropping to AArch32 EL0 if implemented by the CPU. If the
+ * hypervisor spots a guest in such a state ensure it is handled, and don't
+ * trust the host to spot or fix it.  The check below is based on the one in
+ * kvm_arch_vcpu_ioctl_run().
+ *
+ * Returns false if the guest ran in AArch32 when it shouldn't have, and
+ * thus should exit to the host, or true if a the guest run loop can continue.
+ */
+static bool handle_aarch32_guest(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)) {
+		/*
+		 * As we have caught the guest red-handed, decide that it isn't
+		 * fit for purpose anymore by making the vcpu invalid. The VMM
+		 * can try and fix it by re-initializing the vcpu with
+		 * KVM_ARM_VCPU_INIT, however, this is likely not possible for
+		 * protected VMs.
+		 */
+		vcpu->arch.target = -1;
+		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
+		*exit_code |= ARM_EXCEPTION_IL;
+		return false;
+	}
+
+	return true;
+}
+
 /* Switch to the guest for legacy non-VHE systems */
 int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 {
@@ -220,6 +316,9 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
 
+		if (unlikely(!handle_aarch32_guest(vcpu, &exit_code)))
+			break;
+
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 
diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
new file mode 100644
index 000000000000..3787ee6fb1a2
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+#include <hyp/adjust_pc.h>
+
+#include <nvhe/fixed_config.h>
+
+#include "../../sys_regs.h"
+
+/*
+ * Copies of the host's CPU features registers holding sanitized values at hyp.
+ */
+u64 id_aa64pfr0_el1_sys_val;
+u64 id_aa64pfr1_el1_sys_val;
+u64 id_aa64isar0_el1_sys_val;
+u64 id_aa64isar1_el1_sys_val;
+u64 id_aa64mmfr0_el1_sys_val;
+u64 id_aa64mmfr1_el1_sys_val;
+u64 id_aa64mmfr2_el1_sys_val;
+
+/*
+ * Inject an unknown/undefined exception to an AArch64 guest while most of its
+ * sysregs are live.
+ */
+static void inject_undef64(struct kvm_vcpu *vcpu)
+{
+	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
+
+	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
+	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
+
+	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 |
+			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC |
+			     KVM_ARM64_PENDING_EXCEPTION);
+
+	__kvm_adjust_pc(vcpu);
+
+	write_sysreg_el1(esr, SYS_ESR);
+	write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR);
+	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
+	write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
+}
+
+/*
+ * Returns the restricted features values of the feature register based on the
+ * limitations in restrict_fields.
+ * A feature id field value of 0b0000 does not impose any restrictions.
+ * Note: Use only for unsigned feature field values.
+ */
+static u64 get_restricted_features_unsigned(u64 sys_reg_val,
+					    u64 restrict_fields)
+{
+	u64 value = 0UL;
+	u64 mask = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+
+	/*
+	 * According to the Arm Architecture Reference Manual, feature fields
+	 * use increasing values to indicate increases in functionality.
+	 * Iterate over the restricted feature fields and calculate the minimum
+	 * unsigned value between the one supported by the system, and what the
+	 * value is being restricted to.
+	 */
+	while (sys_reg_val && restrict_fields) {
+		value |= min(sys_reg_val & mask, restrict_fields & mask);
+		sys_reg_val &= ~mask;
+		restrict_fields &= ~mask;
+		mask <<= ARM64_FEATURE_FIELD_BITS;
+	}
+
+	return value;
+}
+
+/*
+ * Functions that return the value of feature id registers for protected VMs
+ * based on allowed features, system features, and KVM support.
+ */
+
+static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu)
+{
+	const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm);
+	u64 set_mask = 0;
+	u64 allow_mask = PVM_ID_AA64PFR0_ALLOW;
+
+	if (!vcpu_has_sve(vcpu))
+		allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_SVE);
+
+	set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val,
+		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED);
+
+	/* Spectre and Meltdown mitigation in KVM */
+	set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2),
+			       (u64)kvm->arch.pfr0_csv2);
+	set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3),
+			       (u64)kvm->arch.pfr0_csv3);
+
+	return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask;
+}
+
+static u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu)
+{
+	const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm);
+	u64 allow_mask = PVM_ID_AA64PFR1_ALLOW;
+
+	if (!kvm_has_mte(kvm))
+		allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
+
+	return id_aa64pfr1_el1_sys_val & allow_mask;
+}
+
+static u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for Scalable Vectors, therefore, hyp has no sanitized
+	 * copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64ZFR0_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for debug, including breakpoints, and watchpoints,
+	 * therefore, pKVM has no sanitized copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64DFR0_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for debug, therefore, hyp has no sanitized copy of the
+	 * feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64DFR1_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for implementation defined features, therefore, hyp has no
+	 * sanitized copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64AFR0_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu)
+{
+	/*
+	 * No support for implementation defined features, therefore, hyp has no
+	 * sanitized copy of the feature id register.
+	 */
+	BUILD_BUG_ON(PVM_ID_AA64AFR1_ALLOW != 0ULL);
+	return 0;
+}
+
+static u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu)
+{
+	return id_aa64isar0_el1_sys_val & PVM_ID_AA64ISAR0_ALLOW;
+}
+
+static u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu)
+{
+	u64 allow_mask = PVM_ID_AA64ISAR1_ALLOW;
+
+	if (!vcpu_has_ptrauth(vcpu))
+		allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) |
+				ARM64_FEATURE_MASK(ID_AA64ISAR1_API) |
+				ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) |
+				ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI));
+
+	return id_aa64isar1_el1_sys_val & allow_mask;
+}
+
+static u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu)
+{
+	u64 set_mask;
+
+	set_mask = get_restricted_features_unsigned(id_aa64mmfr0_el1_sys_val,
+		PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED);
+
+	return (id_aa64mmfr0_el1_sys_val & PVM_ID_AA64MMFR0_ALLOW) | set_mask;
+}
+
+static u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu)
+{
+	return id_aa64mmfr1_el1_sys_val & PVM_ID_AA64MMFR1_ALLOW;
+}
+
+static u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu)
+{
+	return id_aa64mmfr2_el1_sys_val & PVM_ID_AA64MMFR2_ALLOW;
+}
+
+/* Read a sanitized cpufeature ID register by its encoding */
+u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id)
+{
+	switch (id) {
+	case SYS_ID_AA64PFR0_EL1:
+		return get_pvm_id_aa64pfr0(vcpu);
+	case SYS_ID_AA64PFR1_EL1:
+		return get_pvm_id_aa64pfr1(vcpu);
+	case SYS_ID_AA64ZFR0_EL1:
+		return get_pvm_id_aa64zfr0(vcpu);
+	case SYS_ID_AA64DFR0_EL1:
+		return get_pvm_id_aa64dfr0(vcpu);
+	case SYS_ID_AA64DFR1_EL1:
+		return get_pvm_id_aa64dfr1(vcpu);
+	case SYS_ID_AA64AFR0_EL1:
+		return get_pvm_id_aa64afr0(vcpu);
+	case SYS_ID_AA64AFR1_EL1:
+		return get_pvm_id_aa64afr1(vcpu);
+	case SYS_ID_AA64ISAR0_EL1:
+		return get_pvm_id_aa64isar0(vcpu);
+	case SYS_ID_AA64ISAR1_EL1:
+		return get_pvm_id_aa64isar1(vcpu);
+	case SYS_ID_AA64MMFR0_EL1:
+		return get_pvm_id_aa64mmfr0(vcpu);
+	case SYS_ID_AA64MMFR1_EL1:
+		return get_pvm_id_aa64mmfr1(vcpu);
+	case SYS_ID_AA64MMFR2_EL1:
+		return get_pvm_id_aa64mmfr2(vcpu);
+	default:
+		/*
+		 * Should never happen because all cases are covered in
+		 * pvm_sys_reg_descs[].
+		 */
+		WARN_ON(1);
+		break;
+	}
+
+	return 0;
+}
+
+static u64 read_id_reg(const struct kvm_vcpu *vcpu,
+		       struct sys_reg_desc const *r)
+{
+	return pvm_read_id_reg(vcpu, reg_to_encoding(r));
+}
+
+/* Handler to RAZ/WI sysregs */
+static bool pvm_access_raz_wi(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	if (!p->is_write)
+		p->regval = 0;
+
+	return true;
+}
+
+/*
+ * Accessor for AArch32 feature id registers.
+ *
+ * The value of these registers is "unknown" according to the spec if AArch32
+ * isn't supported.
+ */
+static bool pvm_access_id_aarch32(struct kvm_vcpu *vcpu,
+				  struct sys_reg_params *p,
+				  const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		inject_undef64(vcpu);
+		return false;
+	}
+
+	/*
+	 * No support for AArch32 guests, therefore, pKVM has no sanitized copy
+	 * of AArch32 feature id registers.
+	 */
+	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1),
+		     PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) > ID_AA64PFR0_ELx_64BIT_ONLY);
+
+	return pvm_access_raz_wi(vcpu, p, r);
+}
+
+/*
+ * Accessor for AArch64 feature id registers.
+ *
+ * If access is allowed, set the regval to the protected VM's view of the
+ * register and return true.
+ * Otherwise, inject an undefined exception and return false.
+ */
+static bool pvm_access_id_aarch64(struct kvm_vcpu *vcpu,
+				  struct sys_reg_params *p,
+				  const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		inject_undef64(vcpu);
+		return false;
+	}
+
+	p->regval = read_id_reg(vcpu, r);
+	return true;
+}
+
+static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu,
+			     struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	/* pVMs only support GICv3. 'nuf said. */
+	if (!p->is_write)
+		p->regval = ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE;
+
+	return true;
+}
+
+/* Mark the specified system register as an AArch32 feature id register. */
+#define AARCH32(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch32 }
+
+/* Mark the specified system register as an AArch64 feature id register. */
+#define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 }
+
+/* Mark the specified system register as Read-As-Zero/Write-Ignored */
+#define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi }
+
+/* Mark the specified system register as not being handled in hyp. */
+#define HOST_HANDLED(REG) { SYS_DESC(REG), .access = NULL }
+
+/*
+ * Architected system registers.
+ * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * NOTE: Anything not explicitly listed here is *restricted by default*, i.e.,
+ * it will lead to injecting an exception into the guest.
+ */
+static const struct sys_reg_desc pvm_sys_reg_descs[] = {
+	/* Cache maintenance by set/way operations are restricted. */
+
+	/* Debug and Trace Registers are restricted. */
+
+	/* AArch64 mappings of the AArch32 ID registers */
+	/* CRm=1 */
+	AARCH32(SYS_ID_PFR0_EL1),
+	AARCH32(SYS_ID_PFR1_EL1),
+	AARCH32(SYS_ID_DFR0_EL1),
+	AARCH32(SYS_ID_AFR0_EL1),
+	AARCH32(SYS_ID_MMFR0_EL1),
+	AARCH32(SYS_ID_MMFR1_EL1),
+	AARCH32(SYS_ID_MMFR2_EL1),
+	AARCH32(SYS_ID_MMFR3_EL1),
+
+	/* CRm=2 */
+	AARCH32(SYS_ID_ISAR0_EL1),
+	AARCH32(SYS_ID_ISAR1_EL1),
+	AARCH32(SYS_ID_ISAR2_EL1),
+	AARCH32(SYS_ID_ISAR3_EL1),
+	AARCH32(SYS_ID_ISAR4_EL1),
+	AARCH32(SYS_ID_ISAR5_EL1),
+	AARCH32(SYS_ID_MMFR4_EL1),
+	AARCH32(SYS_ID_ISAR6_EL1),
+
+	/* CRm=3 */
+	AARCH32(SYS_MVFR0_EL1),
+	AARCH32(SYS_MVFR1_EL1),
+	AARCH32(SYS_MVFR2_EL1),
+	AARCH32(SYS_ID_PFR2_EL1),
+	AARCH32(SYS_ID_DFR1_EL1),
+	AARCH32(SYS_ID_MMFR5_EL1),
+
+	/* AArch64 ID registers */
+	/* CRm=4 */
+	AARCH64(SYS_ID_AA64PFR0_EL1),
+	AARCH64(SYS_ID_AA64PFR1_EL1),
+	AARCH64(SYS_ID_AA64ZFR0_EL1),
+	AARCH64(SYS_ID_AA64DFR0_EL1),
+	AARCH64(SYS_ID_AA64DFR1_EL1),
+	AARCH64(SYS_ID_AA64AFR0_EL1),
+	AARCH64(SYS_ID_AA64AFR1_EL1),
+	AARCH64(SYS_ID_AA64ISAR0_EL1),
+	AARCH64(SYS_ID_AA64ISAR1_EL1),
+	AARCH64(SYS_ID_AA64MMFR0_EL1),
+	AARCH64(SYS_ID_AA64MMFR1_EL1),
+	AARCH64(SYS_ID_AA64MMFR2_EL1),
+
+	/* Scalable Vector Registers are restricted. */
+
+	RAZ_WI(SYS_ERRIDR_EL1),
+	RAZ_WI(SYS_ERRSELR_EL1),
+	RAZ_WI(SYS_ERXFR_EL1),
+	RAZ_WI(SYS_ERXCTLR_EL1),
+	RAZ_WI(SYS_ERXSTATUS_EL1),
+	RAZ_WI(SYS_ERXADDR_EL1),
+	RAZ_WI(SYS_ERXMISC0_EL1),
+	RAZ_WI(SYS_ERXMISC1_EL1),
+
+	/* Performance Monitoring Registers are restricted. */
+
+	/* Limited Ordering Regions Registers are restricted. */
+
+	HOST_HANDLED(SYS_ICC_SGI1R_EL1),
+	HOST_HANDLED(SYS_ICC_ASGI1R_EL1),
+	HOST_HANDLED(SYS_ICC_SGI0R_EL1),
+	{ SYS_DESC(SYS_ICC_SRE_EL1), .access = pvm_gic_read_sre, },
+
+	HOST_HANDLED(SYS_CCSIDR_EL1),
+	HOST_HANDLED(SYS_CLIDR_EL1),
+	HOST_HANDLED(SYS_CSSELR_EL1),
+	HOST_HANDLED(SYS_CTR_EL0),
+
+	/* Performance Monitoring Registers are restricted. */
+
+	/* Activity Monitoring Registers are restricted. */
+
+	HOST_HANDLED(SYS_CNTP_TVAL_EL0),
+	HOST_HANDLED(SYS_CNTP_CTL_EL0),
+	HOST_HANDLED(SYS_CNTP_CVAL_EL0),
+
+	/* Performance Monitoring Registers are restricted. */
+};
+
+/*
+ * Checks that the sysreg table is unique and in-order.
+ *
+ * Returns 0 if the table is consistent, or 1 otherwise.
+ */
+int kvm_check_pvm_sysreg_table(void)
+{
+	unsigned int i;
+
+	for (i = 1; i < ARRAY_SIZE(pvm_sys_reg_descs); i++) {
+		if (cmp_sys_reg(&pvm_sys_reg_descs[i-1], &pvm_sys_reg_descs[i]) >= 0)
+			return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Handler for protected VM MSR, MRS or System instruction execution.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't, to be handled by the host.
+ */
+bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	const struct sys_reg_desc *r;
+	struct sys_reg_params params;
+	unsigned long esr = kvm_vcpu_get_esr(vcpu);
+	int Rt = kvm_vcpu_sys_get_rt(vcpu);
+
+	params = esr_sys64_to_params(esr);
+	params.regval = vcpu_get_reg(vcpu, Rt);
+
+	r = find_reg(&params, pvm_sys_reg_descs, ARRAY_SIZE(pvm_sys_reg_descs));
+
+	/* Undefined (RESTRICTED). */
+	if (r == NULL) {
+		inject_undef64(vcpu);
+		return true;
+	}
+
+	/* Handled by the host (HOST_HANDLED) */
+	if (r->access == NULL)
+		return false;
+
+	/* Handled by hyp: skip instruction if instructed to do so. */
+	if (r->access(vcpu, &params, r))
+		__kvm_skip_instr(vcpu);
+
+	if (!params.is_write)
+		vcpu_set_reg(vcpu, Rt, params.regval);
+
+	return true;
+}
+
+/**
+ * Handler for protected VM restricted exceptions.
+ *
+ * Inject an undefined exception into the guest and return true to indicate that
+ * the hypervisor has handled the exit, and control should go back to the guest.
+ */
+bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	inject_undef64(vcpu);
+	return true;
+}