1 files changed, 780 insertions, 5 deletions

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index d23618af8291..1d44318744e0 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -4,10 +4,13 @@
  * Author: Jintack Lim <jintack.lim@linaro.org>
  */
 
+#include <linux/bitfield.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kvm_arm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
 #include <asm/kvm_nested.h>
 #include <asm/sysreg.h>
 
@@ -17,6 +20,779 @@
 #define NV_FTR(r, f)		ID_AA64##r##_EL1_##f
 
 /*
+ * Ratio of live shadow S2 MMU per vcpu. This is a trade-off between
+ * memory usage and potential number of different sets of S2 PTs in
+ * the guests. Running out of S2 MMUs only affects performance (we
+ * will invalidate them more often).
+ */
+#define S2_MMU_PER_VCPU		2
+
+void kvm_init_nested(struct kvm *kvm)
+{
+	kvm->arch.nested_mmus = NULL;
+	kvm->arch.nested_mmus_size = 0;
+}
+
+static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
+{
+	/*
+	 * We only initialise the IPA range on the canonical MMU, which
+	 * defines the contract between KVM and userspace on where the
+	 * "hardware" is in the IPA space. This affects the validity of MMIO
+	 * exits forwarded to userspace, for example.
+	 *
+	 * For nested S2s, we use the PARange as exposed to the guest, as it
+	 * is allowed to use it at will to expose whatever memory map it
+	 * wants to its own guests as it would be on real HW.
+	 */
+	return kvm_init_stage2_mmu(kvm, mmu, kvm_get_pa_bits(kvm));
+}
+
+int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_s2_mmu *tmp;
+	int num_mmus, ret = 0;
+
+	/*
+	 * Let's treat memory allocation failures as benign: If we fail to
+	 * allocate anything, return an error and keep the allocated array
+	 * alive. Userspace may try to recover by intializing the vcpu
+	 * again, and there is no reason to affect the whole VM for this.
+	 */
+	num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU;
+	tmp = kvrealloc(kvm->arch.nested_mmus,
+			size_mul(sizeof(*kvm->arch.nested_mmus), kvm->arch.nested_mmus_size),
+			size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus),
+			GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!tmp)
+		return -ENOMEM;
+
+	/*
+	 * If we went through a realocation, adjust the MMU back-pointers in
+	 * the previously initialised kvm_pgtable structures.
+	 */
+	if (kvm->arch.nested_mmus != tmp)
+		for (int i = 0; i < kvm->arch.nested_mmus_size; i++)
+			tmp[i].pgt->mmu = &tmp[i];
+
+	for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++)
+		ret = init_nested_s2_mmu(kvm, &tmp[i]);
+
+	if (ret) {
+		for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
+			kvm_free_stage2_pgd(&tmp[i]);
+
+		return ret;
+	}
+
+	kvm->arch.nested_mmus_size = num_mmus;
+	kvm->arch.nested_mmus = tmp;
+
+	return 0;
+}
+
+struct s2_walk_info {
+	int	     (*read_desc)(phys_addr_t pa, u64 *desc, void *data);
+	void	     *data;
+	u64	     baddr;
+	unsigned int max_oa_bits;
+	unsigned int pgshift;
+	unsigned int sl;
+	unsigned int t0sz;
+	bool	     be;
+};
+
+static unsigned int ps_to_output_size(unsigned int ps)
+{
+	switch (ps) {
+	case 0: return 32;
+	case 1: return 36;
+	case 2: return 40;
+	case 3: return 42;
+	case 4: return 44;
+	case 5:
+	default:
+		return 48;
+	}
+}
+
+static u32 compute_fsc(int level, u32 fsc)
+{
+	return fsc | (level & 0x3);
+}
+
+static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc)
+{
+	u32 esr;
+
+	esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC;
+	esr |= compute_fsc(level, fsc);
+	return esr;
+}
+
+static int get_ia_size(struct s2_walk_info *wi)
+{
+	return 64 - wi->t0sz;
+}
+
+static int check_base_s2_limits(struct s2_walk_info *wi,
+				int level, int input_size, int stride)
+{
+	int start_size, ia_size;
+
+	ia_size = get_ia_size(wi);
+
+	/* Check translation limits */
+	switch (BIT(wi->pgshift)) {
+	case SZ_64K:
+		if (level == 0 || (level == 1 && ia_size <= 42))
+			return -EFAULT;
+		break;
+	case SZ_16K:
+		if (level == 0 || (level == 1 && ia_size <= 40))
+			return -EFAULT;
+		break;
+	case SZ_4K:
+		if (level < 0 || (level == 0 && ia_size <= 42))
+			return -EFAULT;
+		break;
+	}
+
+	/* Check input size limits */
+	if (input_size > ia_size)
+		return -EFAULT;
+
+	/* Check number of entries in starting level table */
+	start_size = input_size - ((3 - level) * stride + wi->pgshift);
+	if (start_size < 1 || start_size > stride + 4)
+		return -EFAULT;
+
+	return 0;
+}
+
+/* Check if output is within boundaries */
+static int check_output_size(struct s2_walk_info *wi, phys_addr_t output)
+{
+	unsigned int output_size = wi->max_oa_bits;
+
+	if (output_size != 48 && (output & GENMASK_ULL(47, output_size)))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * This is essentially a C-version of the pseudo code from the ARM ARM
+ * AArch64.TranslationTableWalk  function.  I strongly recommend looking at
+ * that pseudocode in trying to understand this.
+ *
+ * Must be called with the kvm->srcu read lock held
+ */
+static int walk_nested_s2_pgd(phys_addr_t ipa,
+			      struct s2_walk_info *wi, struct kvm_s2_trans *out)
+{
+	int first_block_level, level, stride, input_size, base_lower_bound;
+	phys_addr_t base_addr;
+	unsigned int addr_top, addr_bottom;
+	u64 desc;  /* page table entry */
+	int ret;
+	phys_addr_t paddr;
+
+	switch (BIT(wi->pgshift)) {
+	default:
+	case SZ_64K:
+	case SZ_16K:
+		level = 3 - wi->sl;
+		first_block_level = 2;
+		break;
+	case SZ_4K:
+		level = 2 - wi->sl;
+		first_block_level = 1;
+		break;
+	}
+
+	stride = wi->pgshift - 3;
+	input_size = get_ia_size(wi);
+	if (input_size > 48 || input_size < 25)
+		return -EFAULT;
+
+	ret = check_base_s2_limits(wi, level, input_size, stride);
+	if (WARN_ON(ret))
+		return ret;
+
+	base_lower_bound = 3 + input_size - ((3 - level) * stride +
+			   wi->pgshift);
+	base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound);
+
+	if (check_output_size(wi, base_addr)) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		return 1;
+	}
+
+	addr_top = input_size - 1;
+
+	while (1) {
+		phys_addr_t index;
+
+		addr_bottom = (3 - level) * stride + wi->pgshift;
+		index = (ipa & GENMASK_ULL(addr_top, addr_bottom))
+			>> (addr_bottom - 3);
+
+		paddr = base_addr | index;
+		ret = wi->read_desc(paddr, &desc, wi->data);
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * Handle reversedescriptors if endianness differs between the
+		 * host and the guest hypervisor.
+		 */
+		if (wi->be)
+			desc = be64_to_cpu((__force __be64)desc);
+		else
+			desc = le64_to_cpu((__force __le64)desc);
+
+		/* Check for valid descriptor at this point */
+		if (!(desc & 1) || ((desc & 3) == 1 && level == 3)) {
+			out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
+			out->upper_attr = desc;
+			return 1;
+		}
+
+		/* We're at the final level or block translation level */
+		if ((desc & 3) == 1 || level == 3)
+			break;
+
+		if (check_output_size(wi, desc)) {
+			out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+			out->upper_attr = desc;
+			return 1;
+		}
+
+		base_addr = desc & GENMASK_ULL(47, wi->pgshift);
+
+		level += 1;
+		addr_top = addr_bottom - 1;
+	}
+
+	if (level < first_block_level) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	/*
+	 * We don't use the contiguous bit in the stage-2 ptes, so skip check
+	 * for misprogramming of the contiguous bit.
+	 */
+
+	if (check_output_size(wi, desc)) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	if (!(desc & BIT(10))) {
+		out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS);
+		out->upper_attr = desc;
+		return 1;
+	}
+
+	/* Calculate and return the result */
+	paddr = (desc & GENMASK_ULL(47, addr_bottom)) |
+		(ipa & GENMASK_ULL(addr_bottom - 1, 0));
+	out->output = paddr;
+	out->block_size = 1UL << ((3 - level) * stride + wi->pgshift);
+	out->readable = desc & (0b01 << 6);
+	out->writable = desc & (0b10 << 6);
+	out->level = level;
+	out->upper_attr = desc & GENMASK_ULL(63, 52);
+	return 0;
+}
+
+static int read_guest_s2_desc(phys_addr_t pa, u64 *desc, void *data)
+{
+	struct kvm_vcpu *vcpu = data;
+
+	return kvm_read_guest(vcpu->kvm, pa, desc, sizeof(*desc));
+}
+
+static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi)
+{
+	wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK;
+
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		wi->pgshift = 12;	 break;
+	case VTCR_EL2_TG0_16K:
+		wi->pgshift = 14;	 break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		wi->pgshift = 16;	 break;
+	}
+
+	wi->sl = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
+	/* Global limit for now, should eventually be per-VM */
+	wi->max_oa_bits = min(get_kvm_ipa_limit(),
+			      ps_to_output_size(FIELD_GET(VTCR_EL2_PS_MASK, vtcr)));
+}
+
+int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
+		       struct kvm_s2_trans *result)
+{
+	u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	struct s2_walk_info wi;
+	int ret;
+
+	result->esr = 0;
+
+	if (!vcpu_has_nv(vcpu))
+		return 0;
+
+	wi.read_desc = read_guest_s2_desc;
+	wi.data = vcpu;
+	wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+
+	vtcr_to_walk_info(vtcr, &wi);
+
+	wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_EE;
+
+	ret = walk_nested_s2_pgd(gipa, &wi, result);
+	if (ret)
+		result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC);
+
+	return ret;
+}
+
+static unsigned int ttl_to_size(u8 ttl)
+{
+	int level = ttl & 3;
+	int gran = (ttl >> 2) & 3;
+	unsigned int max_size = 0;
+
+	switch (gran) {
+	case TLBI_TTL_TG_4K:
+		switch (level) {
+		case 0:
+			break;
+		case 1:
+			max_size = SZ_1G;
+			break;
+		case 2:
+			max_size = SZ_2M;
+			break;
+		case 3:
+			max_size = SZ_4K;
+			break;
+		}
+		break;
+	case TLBI_TTL_TG_16K:
+		switch (level) {
+		case 0:
+		case 1:
+			break;
+		case 2:
+			max_size = SZ_32M;
+			break;
+		case 3:
+			max_size = SZ_16K;
+			break;
+		}
+		break;
+	case TLBI_TTL_TG_64K:
+		switch (level) {
+		case 0:
+		case 1:
+			/* No 52bit IPA support */
+			break;
+		case 2:
+			max_size = SZ_512M;
+			break;
+		case 3:
+			max_size = SZ_64K;
+			break;
+		}
+		break;
+	default:			/* No size information */
+		break;
+	}
+
+	return max_size;
+}
+
+/*
+ * Compute the equivalent of the TTL field by parsing the shadow PT.  The
+ * granule size is extracted from the cached VTCR_EL2.TG0 while the level is
+ * retrieved from first entry carrying the level as a tag.
+ */
+static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr)
+{
+	u64 tmp, sz = 0, vtcr = mmu->tlb_vtcr;
+	kvm_pte_t pte;
+	u8 ttl, level;
+
+	lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(mmu)->mmu_lock);
+
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		ttl = (TLBI_TTL_TG_4K << 2);
+		break;
+	case VTCR_EL2_TG0_16K:
+		ttl = (TLBI_TTL_TG_16K << 2);
+		break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		ttl = (TLBI_TTL_TG_64K << 2);
+		break;
+	}
+
+	tmp = addr;
+
+again:
+	/* Iteratively compute the block sizes for a particular granule size */
+	switch (vtcr & VTCR_EL2_TG0_MASK) {
+	case VTCR_EL2_TG0_4K:
+		if	(sz < SZ_4K)	sz = SZ_4K;
+		else if (sz < SZ_2M)	sz = SZ_2M;
+		else if (sz < SZ_1G)	sz = SZ_1G;
+		else			sz = 0;
+		break;
+	case VTCR_EL2_TG0_16K:
+		if	(sz < SZ_16K)	sz = SZ_16K;
+		else if (sz < SZ_32M)	sz = SZ_32M;
+		else			sz = 0;
+		break;
+	case VTCR_EL2_TG0_64K:
+	default:	    /* IMPDEF: treat any other value as 64k */
+		if	(sz < SZ_64K)	sz = SZ_64K;
+		else if (sz < SZ_512M)	sz = SZ_512M;
+		else			sz = 0;
+		break;
+	}
+
+	if (sz == 0)
+		return 0;
+
+	tmp &= ~(sz - 1);
+	if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL))
+		goto again;
+	if (!(pte & PTE_VALID))
+		goto again;
+	level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, pte);
+	if (!level)
+		goto again;
+
+	ttl |= level;
+
+	/*
+	 * We now have found some level information in the shadow S2. Check
+	 * that the resulting range is actually including the original IPA.
+	 */
+	sz = ttl_to_size(ttl);
+	if (addr < (tmp + sz))
+		return ttl;
+
+	return 0;
+}
+
+unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
+	unsigned long max_size;
+	u8 ttl;
+
+	ttl = FIELD_GET(TLBI_TTL_MASK, val);
+
+	if (!ttl || !kvm_has_feat(kvm, ID_AA64MMFR2_EL1, TTL, IMP)) {
+		/* No TTL, check the shadow S2 for a hint */
+		u64 addr = (val & GENMASK_ULL(35, 0)) << 12;
+		ttl = get_guest_mapping_ttl(mmu, addr);
+	}
+
+	max_size = ttl_to_size(ttl);
+
+	if (!max_size) {
+		/* Compute the maximum extent of the invalidation */
+		switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) {
+		case VTCR_EL2_TG0_4K:
+			max_size = SZ_1G;
+			break;
+		case VTCR_EL2_TG0_16K:
+			max_size = SZ_32M;
+			break;
+		case VTCR_EL2_TG0_64K:
+		default:    /* IMPDEF: treat any other value as 64k */
+			/*
+			 * No, we do not support 52bit IPA in nested yet. Once
+			 * we do, this should be 4TB.
+			 */
+			max_size = SZ_512M;
+			break;
+		}
+	}
+
+	WARN_ON(!max_size);
+	return max_size;
+}
+
+/*
+ * We can have multiple *different* MMU contexts with the same VMID:
+ *
+ * - S2 being enabled or not, hence differing by the HCR_EL2.VM bit
+ *
+ * - Multiple vcpus using private S2s (huh huh...), hence differing by the
+ *   VBBTR_EL2.BADDR address
+ *
+ * - A combination of the above...
+ *
+ * We can always identify which MMU context to pick at run-time.  However,
+ * TLB invalidation involving a VMID must take action on all the TLBs using
+ * this particular VMID. This translates into applying the same invalidation
+ * operation to all the contexts that are using this VMID. Moar phun!
+ */
+void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
+				const union tlbi_info *info,
+				void (*tlbi_callback)(struct kvm_s2_mmu *,
+						      const union tlbi_info *))
+{
+	write_lock(&kvm->mmu_lock);
+
+	for (int i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!kvm_s2_mmu_valid(mmu))
+			continue;
+
+		if (vmid == get_vmid(mmu->tlb_vttbr))
+			tlbi_callback(mmu, info);
+	}
+
+	write_unlock(&kvm->mmu_lock);
+}
+
+struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	bool nested_stage2_enabled;
+	u64 vttbr, vtcr, hcr;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
+	vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	hcr = vcpu_read_sys_reg(vcpu, HCR_EL2);
+
+	nested_stage2_enabled = hcr & HCR_VM;
+
+	/* Don't consider the CnP bit for the vttbr match */
+	vttbr &= ~VTTBR_CNP_BIT;
+
+	/*
+	 * Two possibilities when looking up a S2 MMU context:
+	 *
+	 * - either S2 is enabled in the guest, and we need a context that is
+	 *   S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR,
+	 *   which makes it safe from a TLB conflict perspective (a broken
+	 *   guest won't be able to generate them),
+	 *
+	 * - or S2 is disabled, and we need a context that is S2-disabled
+	 *   and matches the VMID only, as all TLBs are tagged by VMID even
+	 *   if S2 translation is disabled.
+	 */
+	for (int i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!kvm_s2_mmu_valid(mmu))
+			continue;
+
+		if (nested_stage2_enabled &&
+		    mmu->nested_stage2_enabled &&
+		    vttbr == mmu->tlb_vttbr &&
+		    vtcr == mmu->tlb_vtcr)
+			return mmu;
+
+		if (!nested_stage2_enabled &&
+		    !mmu->nested_stage2_enabled &&
+		    get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr))
+			return mmu;
+	}
+	return NULL;
+}
+
+static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_s2_mmu *s2_mmu;
+	int i;
+
+	lockdep_assert_held_write(&vcpu->kvm->mmu_lock);
+
+	s2_mmu = lookup_s2_mmu(vcpu);
+	if (s2_mmu)
+		goto out;
+
+	/*
+	 * Make sure we don't always search from the same point, or we
+	 * will always reuse a potentially active context, leaving
+	 * free contexts unused.
+	 */
+	for (i = kvm->arch.nested_mmus_next;
+	     i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next);
+	     i++) {
+		s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size];
+
+		if (atomic_read(&s2_mmu->refcnt) == 0)
+			break;
+	}
+	BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */
+
+	/* Set the scene for the next search */
+	kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
+
+	/* Clear the old state */
+	if (kvm_s2_mmu_valid(s2_mmu))
+		kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+
+	/*
+	 * The virtual VMID (modulo CnP) will be used as a key when matching
+	 * an existing kvm_s2_mmu.
+	 *
+	 * We cache VTCR at allocation time, once and for all. It'd be great
+	 * if the guest didn't screw that one up, as this is not very
+	 * forgiving...
+	 */
+	s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT;
+	s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+	s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM;
+
+out:
+	atomic_inc(&s2_mmu->refcnt);
+	return s2_mmu;
+}
+
+void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
+{
+	/* CnP being set denotes an invalid entry */
+	mmu->tlb_vttbr = VTTBR_CNP_BIT;
+	mmu->nested_stage2_enabled = false;
+	atomic_set(&mmu->refcnt, 0);
+}
+
+void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
+{
+	if (is_hyp_ctxt(vcpu)) {
+		vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
+	} else {
+		write_lock(&vcpu->kvm->mmu_lock);
+		vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
+		write_unlock(&vcpu->kvm->mmu_lock);
+	}
+}
+
+void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
+{
+	if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) {
+		atomic_dec(&vcpu->arch.hw_mmu->refcnt);
+		vcpu->arch.hw_mmu = NULL;
+	}
+}
+
+/*
+ * Returns non-zero if permission fault is handled by injecting it to the next
+ * level hypervisor.
+ */
+int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans)
+{
+	bool forward_fault = false;
+
+	trans->esr = 0;
+
+	if (!kvm_vcpu_trap_is_permission_fault(vcpu))
+		return 0;
+
+	if (kvm_vcpu_trap_is_iabt(vcpu)) {
+		forward_fault = !kvm_s2_trans_executable(trans);
+	} else {
+		bool write_fault = kvm_is_write_fault(vcpu);
+
+		forward_fault = ((write_fault && !trans->writable) ||
+				 (!write_fault && !trans->readable));
+	}
+
+	if (forward_fault)
+		trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM);
+
+	return forward_fault;
+}
+
+int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
+{
+	vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2);
+	vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2);
+
+	return kvm_inject_nested_sync(vcpu, esr_el2);
+}
+
+void kvm_nested_s2_wp(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu));
+	}
+}
+
+void kvm_nested_s2_unmap(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu));
+	}
+}
+
+void kvm_nested_s2_flush(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (kvm_s2_mmu_valid(mmu))
+			kvm_stage2_flush_range(mmu, 0, kvm_phys_size(mmu));
+	}
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+	int i;
+
+	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
+		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
+
+		if (!WARN_ON(atomic_read(&mmu->refcnt)))
+			kvm_free_stage2_pgd(mmu);
+	}
+	kfree(kvm->arch.nested_mmus);
+	kvm->arch.nested_mmus = NULL;
+	kvm->arch.nested_mmus_size = 0;
+	kvm_uninit_stage2_mmu(kvm);
+}
+
+/*
  * Our emulated CPU doesn't support all the possible features. For the
  * sake of simplicity (and probably mental sanity), wipe out a number
  * of feature bits we don't intend to support for the time being.
@@ -29,14 +805,13 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
 
 	switch (id) {
 	case SYS_ID_AA64ISAR0_EL1:
-		/* Support everything but TME, O.S. and Range TLBIs */
-		val &= ~(NV_FTR(ISAR0, TLB)		|
-			 NV_FTR(ISAR0, TME));
+		/* Support everything but TME */
+		val &= ~NV_FTR(ISAR0, TME);
 		break;
 
 	case SYS_ID_AA64ISAR1_EL1:
-		/* Support everything but Spec Invalidation */
-		val &= ~(GENMASK_ULL(63, 56)	|
+		/* Support everything but Spec Invalidation and LS64 */
+		val &= ~(NV_FTR(ISAR1, LS64)	|
 			 NV_FTR(ISAR1, SPECRES));
 		break;