diff options
Diffstat (limited to 'arch/arm64/kvm/nested.c')
| -rw-r--r-- | arch/arm64/kvm/nested.c | 846 |
1 files changed, 642 insertions, 204 deletions
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 4a3fc11f7ecf..291dbe38eb5c 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -8,6 +8,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <asm/fixmap.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> @@ -16,6 +17,24 @@ #include "sys_regs.h" +struct vncr_tlb { + /* The guest's VNCR_EL2 */ + u64 gva; + struct s1_walk_info wi; + struct s1_walk_result wr; + + u64 hpa; + + /* -1 when not mapped on a CPU */ + int cpu; + + /* + * true if the TLB is valid. Can only be changed with the + * mmu_lock held. + */ + bool valid; +}; + /* * 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 @@ -28,6 +47,7 @@ void kvm_init_nested(struct kvm *kvm) { kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; + atomic_set(&kvm->arch.vncr_map_count, 0); } static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) @@ -55,6 +75,13 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) !cpus_have_final_cap(ARM64_HAS_HCR_NV1)) return -EINVAL; + if (!vcpu->arch.ctxt.vncr_array) + vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL_ACCOUNT | + __GFP_ZERO); + + if (!vcpu->arch.ctxt.vncr_array) + return -ENOMEM; + /* * Let's treat memory allocation failures as benign: If we fail to * allocate anything, return an error and keep the allocated array @@ -85,6 +112,9 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++) kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]); + free_page((unsigned long)vcpu->arch.ctxt.vncr_array); + vcpu->arch.ctxt.vncr_array = NULL; + return ret; } @@ -405,6 +435,30 @@ static unsigned int ttl_to_size(u8 ttl) return max_size; } +static u8 pgshift_level_to_ttl(u16 shift, u8 level) +{ + u8 ttl; + + switch(shift) { + case 12: + ttl = TLBI_TTL_TG_4K; + break; + case 14: + ttl = TLBI_TTL_TG_16K; + break; + case 16: + ttl = TLBI_TTL_TG_64K; + break; + default: + BUG(); + } + + ttl <<= 2; + ttl |= level & 3; + + return ttl; +} + /* * 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 @@ -676,23 +730,36 @@ void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu) void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu) { /* - * The vCPU kept its reference on the MMU after the last put, keep - * rolling with it. + * If the vCPU kept its reference on the MMU after the last put, + * keep rolling with it. */ - if (vcpu->arch.hw_mmu) - return; - if (is_hyp_ctxt(vcpu)) { - vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; + if (!vcpu->arch.hw_mmu) + 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); + if (!vcpu->arch.hw_mmu) { + scoped_guard(write_lock, &vcpu->kvm->mmu_lock) + vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu); + } + + if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) + kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu); } } void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu) { + /* Unconditionally drop the VNCR mapping if we have one */ + if (host_data_test_flag(L1_VNCR_MAPPED)) { + BUG_ON(vcpu->arch.vncr_tlb->cpu != smp_processor_id()); + BUG_ON(is_hyp_ctxt(vcpu)); + + clear_fixmap(vncr_fixmap(vcpu->arch.vncr_tlb->cpu)); + vcpu->arch.vncr_tlb->cpu = -1; + host_data_clear_flag(L1_VNCR_MAPPED); + atomic_dec(&vcpu->kvm->arch.vncr_map_count); + } + /* * Keep a reference on the associated stage-2 MMU if the vCPU is * scheduling out and not in WFI emulation, suggesting it is likely to @@ -743,6 +810,245 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2) return kvm_inject_nested_sync(vcpu, esr_el2); } +static void invalidate_vncr(struct vncr_tlb *vt) +{ + vt->valid = false; + if (vt->cpu != -1) + clear_fixmap(vncr_fixmap(vt->cpu)); +} + +static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + + lockdep_assert_held_write(&kvm->mmu_lock); + + if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) + return; + + kvm_for_each_vcpu(i, vcpu, kvm) { + struct vncr_tlb *vt = vcpu->arch.vncr_tlb; + u64 ipa_start, ipa_end, ipa_size; + + /* + * Careful here: We end-up here from an MMU notifier, + * and this can race against a vcpu not being onlined + * yet, without the pseudo-TLB being allocated. + * + * Skip those, as they obviously don't participate in + * the invalidation at this stage. + */ + if (!vt) + continue; + + if (!vt->valid) + continue; + + ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, + vt->wr.level)); + ipa_start = vt->wr.pa & (ipa_size - 1); + ipa_end = ipa_start + ipa_size; + + if (ipa_end <= start || ipa_start >= end) + continue; + + invalidate_vncr(vt); + } +} + +struct s1e2_tlbi_scope { + enum { + TLBI_ALL, + TLBI_VA, + TLBI_VAA, + TLBI_ASID, + } type; + + u16 asid; + u64 va; + u64 size; +}; + +static void invalidate_vncr_va(struct kvm *kvm, + struct s1e2_tlbi_scope *scope) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + + lockdep_assert_held_write(&kvm->mmu_lock); + + kvm_for_each_vcpu(i, vcpu, kvm) { + struct vncr_tlb *vt = vcpu->arch.vncr_tlb; + u64 va_start, va_end, va_size; + + if (!vt->valid) + continue; + + va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, + vt->wr.level)); + va_start = vt->gva & (va_size - 1); + va_end = va_start + va_size; + + switch (scope->type) { + case TLBI_ALL: + break; + + case TLBI_VA: + if (va_end <= scope->va || + va_start >= (scope->va + scope->size)) + continue; + if (vt->wr.nG && vt->wr.asid != scope->asid) + continue; + break; + + case TLBI_VAA: + if (va_end <= scope->va || + va_start >= (scope->va + scope->size)) + continue; + break; + + case TLBI_ASID: + if (!vt->wr.nG || vt->wr.asid != scope->asid) + continue; + break; + } + + invalidate_vncr(vt); + } +} + +static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val, + struct s1e2_tlbi_scope *scope) +{ + switch (inst) { + case OP_TLBI_ALLE2: + case OP_TLBI_ALLE2IS: + case OP_TLBI_ALLE2OS: + case OP_TLBI_VMALLE1: + case OP_TLBI_VMALLE1IS: + case OP_TLBI_VMALLE1OS: + case OP_TLBI_ALLE2NXS: + case OP_TLBI_ALLE2ISNXS: + case OP_TLBI_ALLE2OSNXS: + case OP_TLBI_VMALLE1NXS: + case OP_TLBI_VMALLE1ISNXS: + case OP_TLBI_VMALLE1OSNXS: + scope->type = TLBI_ALL; + break; + case OP_TLBI_VAE2: + case OP_TLBI_VAE2IS: + case OP_TLBI_VAE2OS: + case OP_TLBI_VAE1: + case OP_TLBI_VAE1IS: + case OP_TLBI_VAE1OS: + case OP_TLBI_VAE2NXS: + case OP_TLBI_VAE2ISNXS: + case OP_TLBI_VAE2OSNXS: + case OP_TLBI_VAE1NXS: + case OP_TLBI_VAE1ISNXS: + case OP_TLBI_VAE1OSNXS: + case OP_TLBI_VALE2: + case OP_TLBI_VALE2IS: + case OP_TLBI_VALE2OS: + case OP_TLBI_VALE1: + case OP_TLBI_VALE1IS: + case OP_TLBI_VALE1OS: + case OP_TLBI_VALE2NXS: + case OP_TLBI_VALE2ISNXS: + case OP_TLBI_VALE2OSNXS: + case OP_TLBI_VALE1NXS: + case OP_TLBI_VALE1ISNXS: + case OP_TLBI_VALE1OSNXS: + scope->type = TLBI_VA; + scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val)); + if (!scope->size) + scope->size = SZ_1G; + scope->va = (val << 12) & ~(scope->size - 1); + scope->asid = FIELD_GET(TLBIR_ASID_MASK, val); + break; + case OP_TLBI_ASIDE1: + case OP_TLBI_ASIDE1IS: + case OP_TLBI_ASIDE1OS: + case OP_TLBI_ASIDE1NXS: + case OP_TLBI_ASIDE1ISNXS: + case OP_TLBI_ASIDE1OSNXS: + scope->type = TLBI_ASID; + scope->asid = FIELD_GET(TLBIR_ASID_MASK, val); + break; + case OP_TLBI_VAAE1: + case OP_TLBI_VAAE1IS: + case OP_TLBI_VAAE1OS: + case OP_TLBI_VAAE1NXS: + case OP_TLBI_VAAE1ISNXS: + case OP_TLBI_VAAE1OSNXS: + case OP_TLBI_VAALE1: + case OP_TLBI_VAALE1IS: + case OP_TLBI_VAALE1OS: + case OP_TLBI_VAALE1NXS: + case OP_TLBI_VAALE1ISNXS: + case OP_TLBI_VAALE1OSNXS: + scope->type = TLBI_VAA; + scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val)); + if (!scope->size) + scope->size = SZ_1G; + scope->va = (val << 12) & ~(scope->size - 1); + break; + case OP_TLBI_RVAE2: + case OP_TLBI_RVAE2IS: + case OP_TLBI_RVAE2OS: + case OP_TLBI_RVAE1: + case OP_TLBI_RVAE1IS: + case OP_TLBI_RVAE1OS: + case OP_TLBI_RVAE2NXS: + case OP_TLBI_RVAE2ISNXS: + case OP_TLBI_RVAE2OSNXS: + case OP_TLBI_RVAE1NXS: + case OP_TLBI_RVAE1ISNXS: + case OP_TLBI_RVAE1OSNXS: + case OP_TLBI_RVALE2: + case OP_TLBI_RVALE2IS: + case OP_TLBI_RVALE2OS: + case OP_TLBI_RVALE1: + case OP_TLBI_RVALE1IS: + case OP_TLBI_RVALE1OS: + case OP_TLBI_RVALE2NXS: + case OP_TLBI_RVALE2ISNXS: + case OP_TLBI_RVALE2OSNXS: + case OP_TLBI_RVALE1NXS: + case OP_TLBI_RVALE1ISNXS: + case OP_TLBI_RVALE1OSNXS: + scope->type = TLBI_VA; + scope->va = decode_range_tlbi(val, &scope->size, &scope->asid); + break; + case OP_TLBI_RVAAE1: + case OP_TLBI_RVAAE1IS: + case OP_TLBI_RVAAE1OS: + case OP_TLBI_RVAAE1NXS: + case OP_TLBI_RVAAE1ISNXS: + case OP_TLBI_RVAAE1OSNXS: + case OP_TLBI_RVAALE1: + case OP_TLBI_RVAALE1IS: + case OP_TLBI_RVAALE1OS: + case OP_TLBI_RVAALE1NXS: + case OP_TLBI_RVAALE1ISNXS: + case OP_TLBI_RVAALE1OSNXS: + scope->type = TLBI_VAA; + scope->va = decode_range_tlbi(val, &scope->size, NULL); + break; + } +} + +void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val) +{ + struct s1e2_tlbi_scope scope = {}; + + compute_s1_tlbi_range(vcpu, inst, val, &scope); + + guard(write_lock)(&vcpu->kvm->mmu_lock); + invalidate_vncr_va(vcpu->kvm, &scope); +} + void kvm_nested_s2_wp(struct kvm *kvm) { int i; @@ -755,6 +1061,8 @@ void kvm_nested_s2_wp(struct kvm *kvm) if (kvm_s2_mmu_valid(mmu)) kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu)); } + + kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits)); } void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block) @@ -769,6 +1077,8 @@ void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block) if (kvm_s2_mmu_valid(mmu)) kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block); } + + kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits)); } void kvm_nested_s2_flush(struct kvm *kvm) @@ -802,6 +1112,295 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) } /* + * Dealing with VNCR_EL2 exposed by the *guest* is a complicated matter: + * + * - We introduce an internal representation of a vcpu-private TLB, + * representing the mapping between the guest VA contained in VNCR_EL2, + * the IPA the guest's EL2 PTs point to, and the actual PA this lives at. + * + * - On translation fault from a nested VNCR access, we create such a TLB. + * If there is no mapping to describe, the guest inherits the fault. + * Crucially, no actual mapping is done at this stage. + * + * - On vcpu_load() in a non-HYP context with HCR_EL2.NV==1, if the above + * TLB exists, we map it in the fixmap for this CPU, and run with it. We + * have to respect the permissions dictated by the guest, but not the + * memory type (FWB is a must). + * + * - Note that we usually don't do a vcpu_load() on the back of a fault + * (unless we are preempted), so the resolution of a translation fault + * must go via a request that will map the VNCR page in the fixmap. + * vcpu_load() might as well use the same mechanism. + * + * - On vcpu_put() in a non-HYP context with HCR_EL2.NV==1, if the TLB was + * mapped, we unmap it. Yes it is that simple. The TLB still exists + * though, and may be reused at a later load. + * + * - On permission fault, we simply forward the fault to the guest's EL2. + * Get out of my way. + * + * - On any TLBI for the EL2&0 translation regime, we must find any TLB that + * intersects with the TLBI request, invalidate it, and unmap the page + * from the fixmap. Because we need to look at all the vcpu-private TLBs, + * this requires some wide-ranging locking to ensure that nothing races + * against it. This may require some refcounting to avoid the search when + * no such TLB is present. + * + * - On MMU notifiers, we must invalidate our TLB in a similar way, but + * looking at the IPA instead. The funny part is that there may not be a + * stage-2 mapping for this page if L1 hasn't accessed it using LD/ST + * instructions. + */ + +int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu) +{ + if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) + return 0; + + vcpu->arch.vncr_tlb = kzalloc(sizeof(*vcpu->arch.vncr_tlb), + GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.vncr_tlb) + return -ENOMEM; + + return 0; +} + +static u64 read_vncr_el2(struct kvm_vcpu *vcpu) +{ + return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48); +} + +static int kvm_translate_vncr(struct kvm_vcpu *vcpu) +{ + bool write_fault, writable; + unsigned long mmu_seq; + struct vncr_tlb *vt; + struct page *page; + u64 va, pfn, gfn; + int ret; + + vt = vcpu->arch.vncr_tlb; + + /* + * If we're about to walk the EL2 S1 PTs, we must invalidate the + * current TLB, as it could be sampled from another vcpu doing a + * TLBI *IS. A real CPU wouldn't do that, but we only keep a single + * translation, so not much of a choice. + * + * We also prepare the next walk wilst we're at it. + */ + scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { + invalidate_vncr(vt); + + vt->wi = (struct s1_walk_info) { + .regime = TR_EL20, + .as_el0 = false, + .pan = false, + }; + vt->wr = (struct s1_walk_result){}; + } + + guard(srcu)(&vcpu->kvm->srcu); + + va = read_vncr_el2(vcpu); + + ret = __kvm_translate_va(vcpu, &vt->wi, &vt->wr, va); + if (ret) + return ret; + + write_fault = kvm_is_write_fault(vcpu); + + mmu_seq = vcpu->kvm->mmu_invalidate_seq; + smp_rmb(); + + gfn = vt->wr.pa >> PAGE_SHIFT; + pfn = kvm_faultin_pfn(vcpu, gfn, write_fault, &writable, &page); + if (is_error_noslot_pfn(pfn) || (write_fault && !writable)) + return -EFAULT; + + scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { + if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) + return -EAGAIN; + + vt->gva = va; + vt->hpa = pfn << PAGE_SHIFT; + vt->valid = true; + vt->cpu = -1; + + kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu); + kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw); + } + + if (vt->wr.pw) + mark_page_dirty(vcpu->kvm, gfn); + + return 0; +} + +static void inject_vncr_perm(struct kvm_vcpu *vcpu) +{ + struct vncr_tlb *vt = vcpu->arch.vncr_tlb; + u64 esr = kvm_vcpu_get_esr(vcpu); + + /* Adjust the fault level to reflect that of the guest's */ + esr &= ~ESR_ELx_FSC; + esr |= FIELD_PREP(ESR_ELx_FSC, + ESR_ELx_FSC_PERM_L(vt->wr.level)); + + kvm_inject_nested_sync(vcpu, esr); +} + +static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) +{ + struct vncr_tlb *vt = vcpu->arch.vncr_tlb; + + lockdep_assert_held_read(&vcpu->kvm->mmu_lock); + + if (!vt->valid) + return false; + + if (read_vncr_el2(vcpu) != vt->gva) + return false; + + if (vt->wr.nG) { + u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); + u64 ttbr = ((tcr & TCR_A1) ? + vcpu_read_sys_reg(vcpu, TTBR1_EL2) : + vcpu_read_sys_reg(vcpu, TTBR0_EL2)); + u16 asid; + + asid = FIELD_GET(TTBR_ASID_MASK, ttbr); + if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || + !(tcr & TCR_ASID16)) + asid &= GENMASK(7, 0); + + return asid != vt->wr.asid; + } + + return true; +} + +int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu) +{ + struct vncr_tlb *vt = vcpu->arch.vncr_tlb; + u64 esr = kvm_vcpu_get_esr(vcpu); + + BUG_ON(!(esr & ESR_ELx_VNCR_SHIFT)); + + if (esr_fsc_is_permission_fault(esr)) { + inject_vncr_perm(vcpu); + } else if (esr_fsc_is_translation_fault(esr)) { + bool valid; + int ret; + + scoped_guard(read_lock, &vcpu->kvm->mmu_lock) + valid = kvm_vncr_tlb_lookup(vcpu); + + if (!valid) + ret = kvm_translate_vncr(vcpu); + else + ret = -EPERM; + + switch (ret) { + case -EAGAIN: + case -ENOMEM: + /* Let's try again... */ + break; + case -EFAULT: + case -EINVAL: + case -ENOENT: + case -EACCES: + /* + * Translation failed, inject the corresponding + * exception back to EL2. + */ + BUG_ON(!vt->wr.failed); + + esr &= ~ESR_ELx_FSC; + esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst); + + kvm_inject_nested_sync(vcpu, esr); + break; + case -EPERM: + /* Hack to deal with POE until we get kernel support */ + inject_vncr_perm(vcpu); + break; + case 0: + break; + } + } else { + WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr); + } + + return 1; +} + +static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) +{ + struct vncr_tlb *vt = vcpu->arch.vncr_tlb; + pgprot_t prot; + + guard(preempt)(); + guard(read_lock)(&vcpu->kvm->mmu_lock); + + /* + * The request to map VNCR may have raced against some other + * event, such as an interrupt, and may not be valid anymore. + */ + if (is_hyp_ctxt(vcpu)) + return; + + /* + * Check that the pseudo-TLB is valid and that VNCR_EL2 still + * contains the expected value. If it doesn't, we simply bail out + * without a mapping -- a transformed MSR/MRS will generate the + * fault and allows us to populate the pseudo-TLB. + */ + if (!vt->valid) + return; + + if (read_vncr_el2(vcpu) != vt->gva) + return; + + if (vt->wr.nG) { + u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); + u64 ttbr = ((tcr & TCR_A1) ? + vcpu_read_sys_reg(vcpu, TTBR1_EL2) : + vcpu_read_sys_reg(vcpu, TTBR0_EL2)); + u16 asid; + + asid = FIELD_GET(TTBR_ASID_MASK, ttbr); + if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || + !(tcr & TCR_ASID16)) + asid &= GENMASK(7, 0); + + if (asid != vt->wr.asid) + return; + } + + vt->cpu = smp_processor_id(); + + if (vt->wr.pw && vt->wr.pr) + prot = PAGE_KERNEL; + else if (vt->wr.pr) + prot = PAGE_KERNEL_RO; + else + prot = PAGE_NONE; + + /* + * We can't map write-only (or no permission at all) in the kernel, + * but the guest can do it if using POE, so we'll have to turn a + * translation fault into a permission fault at runtime. + * FIXME: WO doesn't work at all, need POE support in the kernel. + */ + if (pgprot_val(prot) != pgprot_val(PAGE_NONE)) { + __set_fixmap(vncr_fixmap(vt->cpu), vt->hpa, prot); + host_data_set_flag(L1_VNCR_MAPPED); + atomic_inc(&vcpu->kvm->arch.vncr_map_count); + } +} + +/* * 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. @@ -1018,216 +1617,49 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) set_sysreg_masks(kvm, VMPIDR_EL2, res0, res1); /* HCR_EL2 */ - res0 = BIT(48); - res1 = HCR_RW; - if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, TWED, IMP)) - res0 |= GENMASK(63, 59); - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, MTE, MTE2)) - res0 |= (HCR_TID5 | HCR_DCT | HCR_ATA); - if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, TTLBxS)) - res0 |= (HCR_TTLBIS | HCR_TTLBOS); - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) && - !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2)) - res0 |= HCR_ENSCXT; - if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, IMP)) - res0 |= (HCR_TOCU | HCR_TICAB | HCR_TID4); - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1)) - res0 |= HCR_AMVOFFEN; - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1)) - res0 |= HCR_FIEN; - if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, FWB, IMP)) - res0 |= HCR_FWB; - /* Implementation choice: NV2 is the only supported config */ - if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) - res0 |= (HCR_NV2 | HCR_NV | HCR_AT); - if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, NI)) - res0 |= HCR_NV1; - if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && - kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC))) - res0 |= (HCR_API | HCR_APK); - if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TME, IMP)) - res0 |= BIT(39); - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) - res0 |= (HCR_TEA | HCR_TERR); - if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP)) - res0 |= HCR_TLOR; - if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP)) - res0 |= HCR_E2H; - if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, IMP)) - res1 |= HCR_E2H; + get_reg_fixed_bits(kvm, HCR_EL2, &res0, &res1); set_sysreg_masks(kvm, HCR_EL2, res0, res1); /* HCRX_EL2 */ - res0 = HCRX_EL2_RES0; - res1 = HCRX_EL2_RES1; - if (!kvm_has_feat(kvm, ID_AA64ISAR3_EL1, PACM, TRIVIAL_IMP)) - res0 |= HCRX_EL2_PACMEn; - if (!kvm_has_feat(kvm, ID_AA64PFR2_EL1, FPMR, IMP)) - res0 |= HCRX_EL2_EnFPM; - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP)) - res0 |= HCRX_EL2_GCSEn; - if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, SYSREG_128, IMP)) - res0 |= HCRX_EL2_EnIDCP128; - if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, DEV_ASYNC)) - res0 |= (HCRX_EL2_EnSDERR | HCRX_EL2_EnSNERR); - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, DF2, IMP)) - res0 |= HCRX_EL2_TMEA; - if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP)) - res0 |= HCRX_EL2_D128En; - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP)) - res0 |= HCRX_EL2_PTTWI; - if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SCTLRX, IMP)) - res0 |= HCRX_EL2_SCTLR2En; - if (!kvm_has_tcr2(kvm)) - res0 |= HCRX_EL2_TCR2En; - if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP)) - res0 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2); - if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, CMOW, IMP)) - res0 |= HCRX_EL2_CMOW; - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, NMI, IMP)) - res0 |= (HCRX_EL2_VFNMI | HCRX_EL2_VINMI | HCRX_EL2_TALLINT); - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP) || - !(read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS)) - res0 |= HCRX_EL2_SMPME; - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)) - res0 |= (HCRX_EL2_FGTnXS | HCRX_EL2_FnXS); - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V)) - res0 |= HCRX_EL2_EnASR; - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64)) - res0 |= HCRX_EL2_EnALS; - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA)) - res0 |= HCRX_EL2_EnAS0; + get_reg_fixed_bits(kvm, HCRX_EL2, &res0, &res1); set_sysreg_masks(kvm, HCRX_EL2, res0, res1); /* HFG[RW]TR_EL2 */ - res0 = res1 = 0; - if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && - kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC))) - res0 |= (HFGxTR_EL2_APDAKey | HFGxTR_EL2_APDBKey | - HFGxTR_EL2_APGAKey | HFGxTR_EL2_APIAKey | - HFGxTR_EL2_APIBKey); - if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP)) - res0 |= (HFGxTR_EL2_LORC_EL1 | HFGxTR_EL2_LOREA_EL1 | - HFGxTR_EL2_LORID_EL1 | HFGxTR_EL2_LORN_EL1 | - HFGxTR_EL2_LORSA_EL1); - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) && - !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2)) - res0 |= (HFGxTR_EL2_SCXTNUM_EL1 | HFGxTR_EL2_SCXTNUM_EL0); - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP)) - res0 |= HFGxTR_EL2_ICC_IGRPENn_EL1; - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) - res0 |= (HFGxTR_EL2_ERRIDR_EL1 | HFGxTR_EL2_ERRSELR_EL1 | - HFGxTR_EL2_ERXFR_EL1 | HFGxTR_EL2_ERXCTLR_EL1 | - HFGxTR_EL2_ERXSTATUS_EL1 | HFGxTR_EL2_ERXMISCn_EL1 | - HFGxTR_EL2_ERXPFGF_EL1 | HFGxTR_EL2_ERXPFGCTL_EL1 | - HFGxTR_EL2_ERXPFGCDN_EL1 | HFGxTR_EL2_ERXADDR_EL1); - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA)) - res0 |= HFGxTR_EL2_nACCDATA_EL1; - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP)) - res0 |= (HFGxTR_EL2_nGCS_EL0 | HFGxTR_EL2_nGCS_EL1); - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP)) - res0 |= (HFGxTR_EL2_nSMPRI_EL1 | HFGxTR_EL2_nTPIDR2_EL0); - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP)) - res0 |= HFGxTR_EL2_nRCWMASK_EL1; - if (!kvm_has_s1pie(kvm)) - res0 |= (HFGxTR_EL2_nPIRE0_EL1 | HFGxTR_EL2_nPIR_EL1); - if (!kvm_has_s1poe(kvm)) - res0 |= (HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nPOR_EL1); - if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S2POE, IMP)) - res0 |= HFGxTR_EL2_nS2POR_EL1; - if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP)) - res0 |= (HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nAMAIR2_EL1); - set_sysreg_masks(kvm, HFGRTR_EL2, res0 | __HFGRTR_EL2_RES0, res1); - set_sysreg_masks(kvm, HFGWTR_EL2, res0 | __HFGWTR_EL2_RES0, res1); + get_reg_fixed_bits(kvm, HFGRTR_EL2, &res0, &res1); + set_sysreg_masks(kvm, HFGRTR_EL2, res0, res1); + get_reg_fixed_bits(kvm, HFGWTR_EL2, &res0, &res1); + set_sysreg_masks(kvm, HFGWTR_EL2, res0, res1); /* HDFG[RW]TR_EL2 */ - res0 = res1 = 0; - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP)) - res0 |= HDFGRTR_EL2_OSDLR_EL1; - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) - res0 |= (HDFGRTR_EL2_PMEVCNTRn_EL0 | HDFGRTR_EL2_PMEVTYPERn_EL0 | - HDFGRTR_EL2_PMCCFILTR_EL0 | HDFGRTR_EL2_PMCCNTR_EL0 | - HDFGRTR_EL2_PMCNTEN | HDFGRTR_EL2_PMINTEN | - HDFGRTR_EL2_PMOVS | HDFGRTR_EL2_PMSELR_EL0 | - HDFGRTR_EL2_PMMIR_EL1 | HDFGRTR_EL2_PMUSERENR_EL0 | - HDFGRTR_EL2_PMCEIDn_EL0); - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP)) - res0 |= (HDFGRTR_EL2_PMBLIMITR_EL1 | HDFGRTR_EL2_PMBPTR_EL1 | - HDFGRTR_EL2_PMBSR_EL1 | HDFGRTR_EL2_PMSCR_EL1 | - HDFGRTR_EL2_PMSEVFR_EL1 | HDFGRTR_EL2_PMSFCR_EL1 | - HDFGRTR_EL2_PMSICR_EL1 | HDFGRTR_EL2_PMSIDR_EL1 | - HDFGRTR_EL2_PMSIRR_EL1 | HDFGRTR_EL2_PMSLATFR_EL1 | - HDFGRTR_EL2_PMBIDR_EL1); - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP)) - res0 |= (HDFGRTR_EL2_TRC | HDFGRTR_EL2_TRCAUTHSTATUS | - HDFGRTR_EL2_TRCAUXCTLR | HDFGRTR_EL2_TRCCLAIM | - HDFGRTR_EL2_TRCCNTVRn | HDFGRTR_EL2_TRCID | - HDFGRTR_EL2_TRCIMSPECn | HDFGRTR_EL2_TRCOSLSR | - HDFGRTR_EL2_TRCPRGCTLR | HDFGRTR_EL2_TRCSEQSTR | - HDFGRTR_EL2_TRCSSCSRn | HDFGRTR_EL2_TRCSTATR | - HDFGRTR_EL2_TRCVICTLR); - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP)) - res0 |= (HDFGRTR_EL2_TRBBASER_EL1 | HDFGRTR_EL2_TRBIDR_EL1 | - HDFGRTR_EL2_TRBLIMITR_EL1 | HDFGRTR_EL2_TRBMAR_EL1 | - HDFGRTR_EL2_TRBPTR_EL1 | HDFGRTR_EL2_TRBSR_EL1 | - HDFGRTR_EL2_TRBTRG_EL1); - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) - res0 |= (HDFGRTR_EL2_nBRBIDR | HDFGRTR_EL2_nBRBCTL | - HDFGRTR_EL2_nBRBDATA); - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2)) - res0 |= HDFGRTR_EL2_nPMSNEVFR_EL1; - set_sysreg_masks(kvm, HDFGRTR_EL2, res0 | HDFGRTR_EL2_RES0, res1); - - /* Reuse the bits from the read-side and add the write-specific stuff */ - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) - res0 |= (HDFGWTR_EL2_PMCR_EL0 | HDFGWTR_EL2_PMSWINC_EL0); - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP)) - res0 |= HDFGWTR_EL2_TRCOSLAR; - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP)) - res0 |= HDFGWTR_EL2_TRFCR_EL1; - set_sysreg_masks(kvm, HFGWTR_EL2, res0 | HDFGWTR_EL2_RES0, res1); + get_reg_fixed_bits(kvm, HDFGRTR_EL2, &res0, &res1); + set_sysreg_masks(kvm, HDFGRTR_EL2, res0, res1); + get_reg_fixed_bits(kvm, HDFGWTR_EL2, &res0, &res1); + set_sysreg_masks(kvm, HDFGWTR_EL2, res0, res1); /* HFGITR_EL2 */ - res0 = HFGITR_EL2_RES0; - res1 = HFGITR_EL2_RES1; - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, DPB, DPB2)) - res0 |= HFGITR_EL2_DCCVADP; - if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2)) - res0 |= (HFGITR_EL2_ATS1E1RP | HFGITR_EL2_ATS1E1WP); - if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) - res0 |= (HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS | - HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS | - HFGITR_EL2_TLBIVAALE1OS | HFGITR_EL2_TLBIVALE1OS | - HFGITR_EL2_TLBIVAAE1OS | HFGITR_EL2_TLBIASIDE1OS | - HFGITR_EL2_TLBIVAE1OS | HFGITR_EL2_TLBIVMALLE1OS); - if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) - res0 |= (HFGITR_EL2_TLBIRVAALE1 | HFGITR_EL2_TLBIRVALE1 | - HFGITR_EL2_TLBIRVAAE1 | HFGITR_EL2_TLBIRVAE1 | - HFGITR_EL2_TLBIRVAALE1IS | HFGITR_EL2_TLBIRVALE1IS | - HFGITR_EL2_TLBIRVAAE1IS | HFGITR_EL2_TLBIRVAE1IS | - HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS | - HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS); - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, IMP)) - res0 |= (HFGITR_EL2_CFPRCTX | HFGITR_EL2_DVPRCTX | - HFGITR_EL2_CPPRCTX); - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) - res0 |= (HFGITR_EL2_nBRBINJ | HFGITR_EL2_nBRBIALL); - if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP)) - res0 |= (HFGITR_EL2_nGCSPUSHM_EL1 | HFGITR_EL2_nGCSSTR_EL1 | - HFGITR_EL2_nGCSEPP); - if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX)) - res0 |= HFGITR_EL2_COSPRCTX; - if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, ATS1A, IMP)) - res0 |= HFGITR_EL2_ATS1E1A; + get_reg_fixed_bits(kvm, HFGITR_EL2, &res0, &res1); set_sysreg_masks(kvm, HFGITR_EL2, res0, res1); /* HAFGRTR_EL2 - not a lot to see here */ - res0 = HAFGRTR_EL2_RES0; - res1 = HAFGRTR_EL2_RES1; - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1)) - res0 |= ~(res0 | res1); + get_reg_fixed_bits(kvm, HAFGRTR_EL2, &res0, &res1); set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1); + /* HFG[RW]TR2_EL2 */ + get_reg_fixed_bits(kvm, HFGRTR2_EL2, &res0, &res1); + set_sysreg_masks(kvm, HFGRTR2_EL2, res0, res1); + get_reg_fixed_bits(kvm, HFGWTR2_EL2, &res0, &res1); + set_sysreg_masks(kvm, HFGWTR2_EL2, res0, res1); + + /* HDFG[RW]TR2_EL2 */ + get_reg_fixed_bits(kvm, HDFGRTR2_EL2, &res0, &res1); + set_sysreg_masks(kvm, HDFGRTR2_EL2, res0, res1); + get_reg_fixed_bits(kvm, HDFGWTR2_EL2, &res0, &res1); + set_sysreg_masks(kvm, HDFGWTR2_EL2, res0, res1); + + /* HFGITR2_EL2 */ + get_reg_fixed_bits(kvm, HFGITR2_EL2, &res0, &res1); + set_sysreg_masks(kvm, HFGITR2_EL2, res0, res1); + /* TCR2_EL2 */ res0 = TCR2_EL2_RES0; res1 = TCR2_EL2_RES1; @@ -1318,6 +1750,9 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount; set_sysreg_masks(kvm, ICH_HCR_EL2, res0, res1); + /* VNCR_EL2 */ + set_sysreg_masks(kvm, VNCR_EL2, VNCR_EL2_RES0, VNCR_EL2_RES1); + out: for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++) (void)__vcpu_sys_reg(vcpu, sr); @@ -1338,6 +1773,9 @@ void check_nested_vcpu_requests(struct kvm_vcpu *vcpu) write_unlock(&vcpu->kvm->mmu_lock); } + if (kvm_check_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu)) + kvm_map_l1_vncr(vcpu); + /* Must be last, as may switch context! */ if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu)) kvm_inject_nested_irq(vcpu); |