diff options
Diffstat (limited to 'arch/arm64/kvm')
53 files changed, 5222 insertions, 1612 deletions
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index ead632ad01b4..713248f240e0 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -19,7 +19,6 @@ if VIRTUALIZATION menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" - depends on AS_HAS_ARMV8_4 select KVM_COMMON select KVM_GENERIC_HARDWARE_ENABLING select KVM_GENERIC_MMU_NOTIFIER @@ -71,8 +70,8 @@ config PTDUMP_STAGE2_DEBUGFS depends on KVM depends on DEBUG_KERNEL depends on DEBUG_FS - depends on GENERIC_PTDUMP - select PTDUMP_CORE + depends on ARCH_HAS_PTDUMP + select PTDUMP default n help Say Y here if you want to show the stage-2 kernel pagetables diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 3cf7adb2b503..7c329e01c557 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -14,7 +14,7 @@ CFLAGS_sys_regs.o += -Wno-override-init CFLAGS_handle_exit.o += -Wno-override-init kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ - inject_fault.o va_layout.o handle_exit.o \ + inject_fault.o va_layout.o handle_exit.o config.o \ guest.o debug.o reset.o sys_regs.o stacktrace.o \ vgic-sys-reg-v3.o fpsimd.o pkvm.o \ arch_timer.o trng.o vmid.o emulate-nested.o nested.o at.o \ @@ -23,7 +23,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ vgic/vgic-v3.o vgic/vgic-v4.o \ vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \ vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \ - vgic/vgic-its.o vgic/vgic-debug.o + vgic/vgic-its.o vgic/vgic-debug.o vgic/vgic-v3-nested.o kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o pmu.o kvm-$(CONFIG_ARM64_PTR_AUTH) += pauth.o diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 70802e4c91cf..5133dcbfe9f7 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -1070,8 +1070,7 @@ static void timer_context_init(struct kvm_vcpu *vcpu, int timerid) else ctxt->offset.vm_offset = &kvm->arch.timer_data.poffset; - hrtimer_init(&ctxt->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - ctxt->hrtimer.function = kvm_hrtimer_expire; + hrtimer_setup(&ctxt->hrtimer, kvm_hrtimer_expire, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); switch (timerid) { case TIMER_PTIMER: @@ -1098,8 +1097,8 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) timer_set_offset(vcpu_ptimer(vcpu), 0); } - hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - timer->bg_timer.function = kvm_bg_timer_expire; + hrtimer_setup(&timer->bg_timer, kvm_bg_timer_expire, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_HARD); } void kvm_timer_init_vm(struct kvm *kvm) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 0160b4924351..36cfcffb40d8 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -125,6 +125,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, } mutex_unlock(&kvm->slots_lock); break; + case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS: + mutex_lock(&kvm->lock); + if (!kvm->created_vcpus) { + r = 0; + set_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags); + } + mutex_unlock(&kvm->lock); + break; default: break; } @@ -313,6 +321,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_SYSTEM_SUSPEND: case KVM_CAP_IRQFD_RESAMPLE: case KVM_CAP_COUNTER_OFFSET: + case KVM_CAP_ARM_WRITABLE_IMP_ID_REGS: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -359,6 +368,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_EL1_32BIT: r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1); break; + case KVM_CAP_ARM_EL2: + r = cpus_have_final_cap(ARM64_HAS_NESTED_VIRT); + break; + case KVM_CAP_ARM_EL2_E2H0: + r = cpus_have_final_cap(ARM64_HAS_HCR_NV1); + break; case KVM_CAP_GUEST_DEBUG_HW_BPS: r = get_num_brps(); break; @@ -366,7 +381,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = get_num_wrps(); break; case KVM_CAP_ARM_PMU_V3: - r = kvm_arm_support_pmu_v3(); + r = kvm_supports_guest_pmuv3(); break; case KVM_CAP_ARM_INJECT_SERROR_ESR: r = cpus_have_final_cap(ARM64_HAS_RAS_EXTN); @@ -466,7 +481,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) return err; - return kvm_share_hyp(vcpu, vcpu + 1); + err = kvm_share_hyp(vcpu, vcpu + 1); + if (err) + kvm_vgic_vcpu_destroy(vcpu); + + return err; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -586,8 +605,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) nommu: vcpu->cpu = cpu; - kvm_vgic_load(vcpu); + /* + * The timer must be loaded before the vgic to correctly set up physical + * interrupt deactivation in nested state (e.g. timer interrupt). + */ kvm_timer_vcpu_load(vcpu); + kvm_vgic_load(vcpu); kvm_vcpu_load_debug(vcpu); if (has_vhe()) kvm_vcpu_load_vhe(vcpu); @@ -825,6 +848,16 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) if (ret) return ret; + if (vcpu_has_nv(vcpu)) { + ret = kvm_vcpu_allocate_vncr_tlb(vcpu); + if (ret) + return ret; + + ret = kvm_vgic_vcpu_nv_init(vcpu); + if (ret) + return ret; + } + /* * This needs to happen after any restriction has been applied * to the feature set. @@ -835,14 +868,20 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) if (ret) return ret; - ret = kvm_arm_pmu_v3_enable(vcpu); - if (ret) - return ret; + if (kvm_vcpu_has_pmu(vcpu)) { + ret = kvm_arm_pmu_v3_enable(vcpu); + if (ret) + return ret; + } if (is_protected_kvm_enabled()) { ret = pkvm_create_hyp_vm(kvm); if (ret) return ret; + + ret = pkvm_create_hyp_vcpu(vcpu); + if (ret) + return ret; } mutex_lock(&kvm->arch.config_lock); @@ -1148,7 +1187,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ preempt_disable(); - kvm_pmu_flush_hwstate(vcpu); + if (kvm_vcpu_has_pmu(vcpu)) + kvm_pmu_flush_hwstate(vcpu); local_irq_disable(); @@ -1167,7 +1207,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) { vcpu->mode = OUTSIDE_GUEST_MODE; isb(); /* Ensure work in x_flush_hwstate is committed */ - kvm_pmu_sync_hwstate(vcpu); + if (kvm_vcpu_has_pmu(vcpu)) + kvm_pmu_sync_hwstate(vcpu); if (unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_timer_sync_user(vcpu); kvm_vgic_sync_hwstate(vcpu); @@ -1197,7 +1238,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * that the vgic can properly sample the updated state of the * interrupt line. */ - kvm_pmu_sync_hwstate(vcpu); + if (kvm_vcpu_has_pmu(vcpu)) + kvm_pmu_sync_hwstate(vcpu); /* * Sync the vgic state before syncing the timer state because @@ -1386,7 +1428,7 @@ static unsigned long system_supported_vcpu_features(void) if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1)) clear_bit(KVM_ARM_VCPU_EL1_32BIT, &features); - if (!kvm_arm_support_pmu_v3()) + if (!kvm_supports_guest_pmuv3()) clear_bit(KVM_ARM_VCPU_PMU_V3, &features); if (!system_supports_sve()) @@ -2307,6 +2349,13 @@ static int __init init_subsystems(void) goto out; } + if (kvm_mode == KVM_MODE_NV && + !(vgic_present && kvm_vgic_global_state.type == VGIC_V3)) { + kvm_err("NV support requires GICv3, giving up\n"); + err = -EINVAL; + goto out; + } + /* * Init HYP architected timer support */ @@ -2411,6 +2460,19 @@ static void kvm_hyp_init_symbols(void) kvm_nvhe_sym(__icache_flags) = __icache_flags; kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; + /* Propagate the FGT state to the the nVHE side */ + kvm_nvhe_sym(hfgrtr_masks) = hfgrtr_masks; + kvm_nvhe_sym(hfgwtr_masks) = hfgwtr_masks; + kvm_nvhe_sym(hfgitr_masks) = hfgitr_masks; + kvm_nvhe_sym(hdfgrtr_masks) = hdfgrtr_masks; + kvm_nvhe_sym(hdfgwtr_masks) = hdfgwtr_masks; + kvm_nvhe_sym(hafgrtr_masks) = hafgrtr_masks; + kvm_nvhe_sym(hfgrtr2_masks) = hfgrtr2_masks; + kvm_nvhe_sym(hfgwtr2_masks) = hfgwtr2_masks; + kvm_nvhe_sym(hfgitr2_masks) = hfgitr2_masks; + kvm_nvhe_sym(hdfgrtr2_masks)= hdfgrtr2_masks; + kvm_nvhe_sym(hdfgwtr2_masks)= hdfgwtr2_masks; + /* * Flush entire BSS since part of its data containing init symbols is read * while the MMU is off. @@ -2565,6 +2627,13 @@ static int __init init_hyp_mode(void) goto out_err; } + err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_start), + kvm_ksym_ref(__hyp_data_end), PAGE_HYP); + if (err) { + kvm_err("Cannot map .hyp.data section\n"); + goto out_err; + } + err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start), kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO); if (err) { @@ -2704,16 +2773,19 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) return irqchip_in_kernel(kvm); } -bool kvm_arch_has_irq_bypass(void) -{ - return true; -} - int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm_kernel_irq_routing_entry *irq_entry = &irqfd->irq_entry; + + /* + * The only thing we have a chance of directly-injecting is LPIs. Maybe + * one day... + */ + if (irq_entry->type != KVM_IRQ_ROUTING_MSI) + return 0; return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq, &irqfd->irq_entry); @@ -2723,6 +2795,10 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm_kernel_irq_routing_entry *irq_entry = &irqfd->irq_entry; + + if (irq_entry->type != KVM_IRQ_ROUTING_MSI) + return; kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq, &irqfd->irq_entry); @@ -2803,11 +2879,12 @@ static __init int kvm_arm_init(void) if (err) goto out_hyp; - kvm_info("%s%sVHE mode initialized successfully\n", + kvm_info("%s%sVHE%s mode initialized successfully\n", in_hyp_mode ? "" : (is_protected_kvm_enabled() ? "Protected " : "Hyp "), in_hyp_mode ? "" : (cpus_have_final_cap(ARM64_KVM_HVHE) ? - "h" : "n")); + "h" : "n"), + cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) ? "+NV2": ""); /* * FIXME: Do something reasonable if kvm_init() fails after pKVM diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 3a96c96816e9..a25be111cd8f 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -10,61 +10,11 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> -enum trans_regime { - TR_EL10, - TR_EL20, - TR_EL2, -}; - -struct s1_walk_info { - u64 baddr; - enum trans_regime regime; - unsigned int max_oa_bits; - unsigned int pgshift; - unsigned int txsz; - int sl; - bool hpd; - bool e0poe; - bool poe; - bool pan; - bool be; - bool s2; -}; - -struct s1_walk_result { - union { - struct { - u64 desc; - u64 pa; - s8 level; - u8 APTable; - bool UXNTable; - bool PXNTable; - bool uwxn; - bool uov; - bool ur; - bool uw; - bool ux; - bool pwxn; - bool pov; - bool pr; - bool pw; - bool px; - }; - struct { - u8 fst; - bool ptw; - bool s2; - }; - }; - bool failed; -}; - -static void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool ptw, bool s2) +static void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw) { wr->fst = fst; - wr->ptw = ptw; - wr->s2 = s2; + wr->ptw = s1ptw; + wr->s2 = s1ptw; wr->failed = true; } @@ -145,20 +95,15 @@ static void compute_s1poe(struct kvm_vcpu *vcpu, struct s1_walk_info *wi) } } -static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi, +static int setup_s1_walk(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, struct s1_walk_result *wr, u64 va) { u64 hcr, sctlr, tcr, tg, ps, ia_bits, ttbr; unsigned int stride, x; - bool va55, tbi, lva, as_el0; + bool va55, tbi, lva; hcr = __vcpu_sys_reg(vcpu, HCR_EL2); - wi->regime = compute_translation_regime(vcpu, op); - as_el0 = (op == OP_AT_S1E0R || op == OP_AT_S1E0W); - wi->pan = (op == OP_AT_S1E1RP || op == OP_AT_S1E1WP) && - (*vcpu_cpsr(vcpu) & PSR_PAN_BIT); - va55 = va & BIT(55); if (wi->regime == TR_EL2 && va55) @@ -319,7 +264,7 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi, /* R_BNDVG and following statements */ if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR2_EL1, E0PD, IMP) && - as_el0 && (tcr & (va55 ? TCR_E0PD1 : TCR_E0PD0))) + wi->as_el0 && (tcr & (va55 ? TCR_E0PD1 : TCR_E0PD0))) goto transfault_l0; /* AArch64.S1StartLevel() */ @@ -345,11 +290,11 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi, return 0; addrsz: /* Address Size Fault level 0 */ - fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(0), false, false); + fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(0), false); return -EFAULT; transfault_l0: /* Translation Fault level 0 */ - fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(0), false, false); + fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(0), false); return -EFAULT; } @@ -380,13 +325,13 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, if (ret) { fail_s1_walk(wr, (s2_trans.esr & ~ESR_ELx_FSC_LEVEL) | level, - true, true); + true); return ret; } if (!kvm_s2_trans_readable(&s2_trans)) { fail_s1_walk(wr, ESR_ELx_FSC_PERM_L(level), - true, true); + true); return -EPERM; } @@ -396,8 +341,7 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, ret = kvm_read_guest(vcpu->kvm, ipa, &desc, sizeof(desc)); if (ret) { - fail_s1_walk(wr, ESR_ELx_FSC_SEA_TTW(level), - true, false); + fail_s1_walk(wr, ESR_ELx_FSC_SEA_TTW(level), false); return ret; } @@ -457,6 +401,11 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, if (check_output_size(desc & GENMASK(47, va_bottom), wi)) goto addrsz; + if (!(desc & PTE_AF)) { + fail_s1_walk(wr, ESR_ELx_FSC_ACCESS_L(level), false); + return -EACCES; + } + va_bottom += contiguous_bit_shift(desc, wi, level); wr->failed = false; @@ -465,13 +414,40 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, wr->pa = desc & GENMASK(47, va_bottom); wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0); + wr->nG = (wi->regime != TR_EL2) && (desc & PTE_NG); + if (wr->nG) { + u64 asid_ttbr, tcr; + + switch (wi->regime) { + case TR_EL10: + tcr = vcpu_read_sys_reg(vcpu, TCR_EL1); + asid_ttbr = ((tcr & TCR_A1) ? + vcpu_read_sys_reg(vcpu, TTBR1_EL1) : + vcpu_read_sys_reg(vcpu, TTBR0_EL1)); + break; + case TR_EL20: + tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); + asid_ttbr = ((tcr & TCR_A1) ? + vcpu_read_sys_reg(vcpu, TTBR1_EL2) : + vcpu_read_sys_reg(vcpu, TTBR0_EL2)); + break; + default: + BUG(); + } + + wr->asid = FIELD_GET(TTBR_ASID_MASK, asid_ttbr); + if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || + !(tcr & TCR_ASID16)) + wr->asid &= GENMASK(7, 0); + } + return 0; addrsz: - fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(level), true, false); + fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(level), false); return -EINVAL; transfault: - fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(level), true, false); + fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(level), false); return -ENOENT; } @@ -488,7 +464,6 @@ struct mmu_config { u64 sctlr; u64 vttbr; u64 vtcr; - u64 hcr; }; static void __mmu_config_save(struct mmu_config *config) @@ -511,13 +486,10 @@ static void __mmu_config_save(struct mmu_config *config) config->sctlr = read_sysreg_el1(SYS_SCTLR); config->vttbr = read_sysreg(vttbr_el2); config->vtcr = read_sysreg(vtcr_el2); - config->hcr = read_sysreg(hcr_el2); } static void __mmu_config_restore(struct mmu_config *config) { - write_sysreg(config->hcr, hcr_el2); - /* * ARM errata 1165522 and 1530923 require TGE to be 1 before * we update the guest state. @@ -1090,22 +1062,22 @@ static void compute_s1_overlay_permissions(struct kvm_vcpu *vcpu, break; } - if (pov_perms & ~POE_RXW) + if (pov_perms & ~POE_RWX) pov_perms = POE_NONE; if (wi->poe && wr->pov) { wr->pr &= pov_perms & POE_R; - wr->px &= pov_perms & POE_X; wr->pw &= pov_perms & POE_W; + wr->px &= pov_perms & POE_X; } - if (uov_perms & ~POE_RXW) + if (uov_perms & ~POE_RWX) uov_perms = POE_NONE; if (wi->e0poe && wr->uov) { wr->ur &= uov_perms & POE_R; - wr->ux &= uov_perms & POE_X; wr->uw &= uov_perms & POE_W; + wr->ux &= uov_perms & POE_X; } } @@ -1155,7 +1127,12 @@ static u64 handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) bool perm_fail = false; int ret, idx; - ret = setup_s1_walk(vcpu, op, &wi, &wr, vaddr); + wi.regime = compute_translation_regime(vcpu, op); + wi.as_el0 = (op == OP_AT_S1E0R || op == OP_AT_S1E0W); + wi.pan = (op == OP_AT_S1E1RP || op == OP_AT_S1E1WP) && + (*vcpu_cpsr(vcpu) & PSR_PAN_BIT); + + ret = setup_s1_walk(vcpu, &wi, &wr, vaddr); if (ret) goto compute_par; @@ -1198,7 +1175,7 @@ static u64 handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) } if (perm_fail) - fail_s1_walk(&wr, ESR_ELx_FSC_PERM_L(wr.level), false, false); + fail_s1_walk(&wr, ESR_ELx_FSC_PERM_L(wr.level), false); compute_par: return compute_par_s1(vcpu, &wr, wi.regime); @@ -1210,7 +1187,8 @@ compute_par: * If the translation is unsuccessful, the value may only contain * PAR_EL1.F, and cannot be taken at face value. It isn't an * indication of the translation having failed, only that the fast - * path did not succeed, *unless* it indicates a S1 permission fault. + * path did not succeed, *unless* it indicates a S1 permission or + * access fault. */ static u64 __kvm_at_s1e01_fast(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) { @@ -1266,8 +1244,8 @@ static u64 __kvm_at_s1e01_fast(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) __load_stage2(mmu, mmu->arch); skip_mmu_switch: - /* Clear TGE, enable S2 translation, we're rolling */ - write_sysreg((config.hcr & ~HCR_TGE) | HCR_VM, hcr_el2); + /* Temporarily switch back to guest context */ + write_sysreg_hcr(vcpu->arch.hcr_el2); isb(); switch (op) { @@ -1299,6 +1277,8 @@ skip_mmu_switch: if (!fail) par = read_sysreg_par(); + write_sysreg_hcr(HCR_HOST_VHE_FLAGS); + if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu))) __mmu_config_restore(&config); @@ -1313,19 +1293,29 @@ static bool par_check_s1_perm_fault(u64 par) !(par & SYS_PAR_EL1_S)); } +static bool par_check_s1_access_fault(u64 par) +{ + u8 fst = FIELD_GET(SYS_PAR_EL1_FST, par); + + return ((fst & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS && + !(par & SYS_PAR_EL1_S)); +} + void __kvm_at_s1e01(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) { u64 par = __kvm_at_s1e01_fast(vcpu, op, vaddr); /* - * If PAR_EL1 reports that AT failed on a S1 permission fault, we - * know for sure that the PTW was able to walk the S1 tables and - * there's nothing else to do. + * If PAR_EL1 reports that AT failed on a S1 permission or access + * fault, we know for sure that the PTW was able to walk the S1 + * tables and there's nothing else to do. * * If AT failed for any other reason, then we must walk the guest S1 * to emulate the instruction. */ - if ((par & SYS_PAR_EL1_F) && !par_check_s1_perm_fault(par)) + if ((par & SYS_PAR_EL1_F) && + !par_check_s1_perm_fault(par) && + !par_check_s1_access_fault(par)) par = handle_at_slow(vcpu, op, vaddr); vcpu_write_sys_reg(vcpu, par, PAR_EL1); @@ -1350,7 +1340,7 @@ void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) if (!vcpu_el2_e2h_is_set(vcpu)) val |= HCR_NV | HCR_NV1; - write_sysreg(val, hcr_el2); + write_sysreg_hcr(val); isb(); par = SYS_PAR_EL1_F; @@ -1375,7 +1365,7 @@ void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) if (!fail) par = read_sysreg_par(); - write_sysreg(hcr, hcr_el2); + write_sysreg_hcr(hcr); isb(); } @@ -1444,3 +1434,31 @@ void __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) par = compute_par_s12(vcpu, par, &out); vcpu_write_sys_reg(vcpu, par, PAR_EL1); } + +/* + * Translate a VA for a given EL in a given translation regime, with + * or without PAN. This requires wi->{regime, as_el0, pan} to be + * set. The rest of the wi and wr should be 0-initialised. + */ +int __kvm_translate_va(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, + struct s1_walk_result *wr, u64 va) +{ + int ret; + + ret = setup_s1_walk(vcpu, wi, wr, va); + if (ret) + return ret; + + if (wr->level == S1_MMU_DISABLED) { + wr->ur = wr->uw = wr->ux = true; + wr->pr = wr->pw = wr->px = true; + } else { + ret = walk_s1(vcpu, wi, wr, va); + if (ret) + return ret; + + compute_s1_permissions(vcpu, wi, wr); + } + + return 0; +} diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c new file mode 100644 index 000000000000..54911a93b001 --- /dev/null +++ b/arch/arm64/kvm/config.c @@ -0,0 +1,1085 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 Google LLC + * Author: Marc Zyngier <maz@kernel.org> + */ + +#include <linux/kvm_host.h> +#include <asm/sysreg.h> + +struct reg_bits_to_feat_map { + u64 bits; + +#define NEVER_FGU BIT(0) /* Can trap, but never UNDEF */ +#define CALL_FUNC BIT(1) /* Needs to evaluate tons of crap */ +#define FIXED_VALUE BIT(2) /* RAZ/WI or RAO/WI in KVM */ + unsigned long flags; + + union { + struct { + u8 regidx; + u8 shift; + u8 width; + bool sign; + s8 lo_lim; + }; + bool (*match)(struct kvm *); + bool (*fval)(struct kvm *, u64 *); + }; +}; + +#define __NEEDS_FEAT_3(m, f, id, fld, lim) \ + { \ + .bits = (m), \ + .flags = (f), \ + .regidx = IDREG_IDX(SYS_ ## id), \ + .shift = id ##_## fld ## _SHIFT, \ + .width = id ##_## fld ## _WIDTH, \ + .sign = id ##_## fld ## _SIGNED, \ + .lo_lim = id ##_## fld ##_## lim \ + } + +#define __NEEDS_FEAT_2(m, f, fun, dummy) \ + { \ + .bits = (m), \ + .flags = (f) | CALL_FUNC, \ + .fval = (fun), \ + } + +#define __NEEDS_FEAT_1(m, f, fun) \ + { \ + .bits = (m), \ + .flags = (f) | CALL_FUNC, \ + .match = (fun), \ + } + +#define NEEDS_FEAT_FLAG(m, f, ...) \ + CONCATENATE(__NEEDS_FEAT_, COUNT_ARGS(__VA_ARGS__))(m, f, __VA_ARGS__) + +#define NEEDS_FEAT_FIXED(m, ...) \ + NEEDS_FEAT_FLAG(m, FIXED_VALUE, __VA_ARGS__, 0) + +#define NEEDS_FEAT(m, ...) NEEDS_FEAT_FLAG(m, 0, __VA_ARGS__) + +#define FEAT_SPE ID_AA64DFR0_EL1, PMSVer, IMP +#define FEAT_SPE_FnE ID_AA64DFR0_EL1, PMSVer, V1P2 +#define FEAT_BRBE ID_AA64DFR0_EL1, BRBE, IMP +#define FEAT_TRC_SR ID_AA64DFR0_EL1, TraceVer, IMP +#define FEAT_PMUv3 ID_AA64DFR0_EL1, PMUVer, IMP +#define FEAT_PMUv3p9 ID_AA64DFR0_EL1, PMUVer, V3P9 +#define FEAT_TRBE ID_AA64DFR0_EL1, TraceBuffer, IMP +#define FEAT_TRBEv1p1 ID_AA64DFR0_EL1, TraceBuffer, TRBE_V1P1 +#define FEAT_DoubleLock ID_AA64DFR0_EL1, DoubleLock, IMP +#define FEAT_TRF ID_AA64DFR0_EL1, TraceFilt, IMP +#define FEAT_AA32EL0 ID_AA64PFR0_EL1, EL0, AARCH32 +#define FEAT_AA32EL1 ID_AA64PFR0_EL1, EL1, AARCH32 +#define FEAT_AA64EL1 ID_AA64PFR0_EL1, EL1, IMP +#define FEAT_AA64EL3 ID_AA64PFR0_EL1, EL3, IMP +#define FEAT_AIE ID_AA64MMFR3_EL1, AIE, IMP +#define FEAT_S2POE ID_AA64MMFR3_EL1, S2POE, IMP +#define FEAT_S1POE ID_AA64MMFR3_EL1, S1POE, IMP +#define FEAT_S1PIE ID_AA64MMFR3_EL1, S1PIE, IMP +#define FEAT_THE ID_AA64PFR1_EL1, THE, IMP +#define FEAT_SME ID_AA64PFR1_EL1, SME, IMP +#define FEAT_GCS ID_AA64PFR1_EL1, GCS, IMP +#define FEAT_LS64 ID_AA64ISAR1_EL1, LS64, LS64 +#define FEAT_LS64_V ID_AA64ISAR1_EL1, LS64, LS64_V +#define FEAT_LS64_ACCDATA ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA +#define FEAT_RAS ID_AA64PFR0_EL1, RAS, IMP +#define FEAT_RASv2 ID_AA64PFR0_EL1, RAS, V2 +#define FEAT_GICv3 ID_AA64PFR0_EL1, GIC, IMP +#define FEAT_LOR ID_AA64MMFR1_EL1, LO, IMP +#define FEAT_SPEv1p4 ID_AA64DFR0_EL1, PMSVer, V1P4 +#define FEAT_SPEv1p5 ID_AA64DFR0_EL1, PMSVer, V1P5 +#define FEAT_ATS1A ID_AA64ISAR2_EL1, ATS1A, IMP +#define FEAT_SPECRES2 ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX +#define FEAT_SPECRES ID_AA64ISAR1_EL1, SPECRES, IMP +#define FEAT_TLBIRANGE ID_AA64ISAR0_EL1, TLB, RANGE +#define FEAT_TLBIOS ID_AA64ISAR0_EL1, TLB, OS +#define FEAT_PAN2 ID_AA64MMFR1_EL1, PAN, PAN2 +#define FEAT_DPB2 ID_AA64ISAR1_EL1, DPB, DPB2 +#define FEAT_AMUv1 ID_AA64PFR0_EL1, AMU, IMP +#define FEAT_AMUv1p1 ID_AA64PFR0_EL1, AMU, V1P1 +#define FEAT_CMOW ID_AA64MMFR1_EL1, CMOW, IMP +#define FEAT_D128 ID_AA64MMFR3_EL1, D128, IMP +#define FEAT_DoubleFault2 ID_AA64PFR1_EL1, DF2, IMP +#define FEAT_FPMR ID_AA64PFR2_EL1, FPMR, IMP +#define FEAT_MOPS ID_AA64ISAR2_EL1, MOPS, IMP +#define FEAT_NMI ID_AA64PFR1_EL1, NMI, IMP +#define FEAT_SCTLR2 ID_AA64MMFR3_EL1, SCTLRX, IMP +#define FEAT_SYSREG128 ID_AA64ISAR2_EL1, SYSREG_128, IMP +#define FEAT_TCR2 ID_AA64MMFR3_EL1, TCRX, IMP +#define FEAT_XS ID_AA64ISAR1_EL1, XS, IMP +#define FEAT_EVT ID_AA64MMFR2_EL1, EVT, IMP +#define FEAT_EVT_TTLBxS ID_AA64MMFR2_EL1, EVT, TTLBxS +#define FEAT_MTE2 ID_AA64PFR1_EL1, MTE, MTE2 +#define FEAT_RME ID_AA64PFR0_EL1, RME, IMP +#define FEAT_MPAM ID_AA64PFR0_EL1, MPAM, 1 +#define FEAT_S2FWB ID_AA64MMFR2_EL1, FWB, IMP +#define FEAT_TME ID_AA64ISAR0_EL1, TME, IMP +#define FEAT_TWED ID_AA64MMFR1_EL1, TWED, IMP +#define FEAT_E2H0 ID_AA64MMFR4_EL1, E2H0, IMP +#define FEAT_SRMASK ID_AA64MMFR4_EL1, SRMASK, IMP +#define FEAT_PoPS ID_AA64MMFR4_EL1, PoPS, IMP +#define FEAT_PFAR ID_AA64PFR1_EL1, PFAR, IMP +#define FEAT_Debugv8p9 ID_AA64DFR0_EL1, PMUVer, V3P9 +#define FEAT_PMUv3_SS ID_AA64DFR0_EL1, PMSS, IMP +#define FEAT_SEBEP ID_AA64DFR0_EL1, SEBEP, IMP +#define FEAT_EBEP ID_AA64DFR1_EL1, EBEP, IMP +#define FEAT_ITE ID_AA64DFR1_EL1, ITE, IMP +#define FEAT_PMUv3_ICNTR ID_AA64DFR1_EL1, PMICNTR, IMP +#define FEAT_SPMU ID_AA64DFR1_EL1, SPMU, IMP +#define FEAT_SPE_nVM ID_AA64DFR2_EL1, SPE_nVM, IMP +#define FEAT_STEP2 ID_AA64DFR2_EL1, STEP, IMP + +static bool not_feat_aa64el3(struct kvm *kvm) +{ + return !kvm_has_feat(kvm, FEAT_AA64EL3); +} + +static bool feat_nv2(struct kvm *kvm) +{ + return ((kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY) && + kvm_has_feat_enum(kvm, ID_AA64MMFR2_EL1, NV, NI)) || + kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, NV2)); +} + +static bool feat_nv2_e2h0_ni(struct kvm *kvm) +{ + return feat_nv2(kvm) && !kvm_has_feat(kvm, FEAT_E2H0); +} + +static bool feat_rasv1p1(struct kvm *kvm) +{ + return (kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1) || + (kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, RAS, IMP) && + kvm_has_feat(kvm, ID_AA64PFR1_EL1, RAS_frac, RASv1p1))); +} + +static bool feat_csv2_2_csv2_1p2(struct kvm *kvm) +{ + return (kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) || + (kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2) && + kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, CSV2, IMP))); +} + +static bool feat_pauth(struct kvm *kvm) +{ + return kvm_has_pauth(kvm, PAuth); +} + +static bool feat_pauth_lr(struct kvm *kvm) +{ + return kvm_has_pauth(kvm, PAuth_LR); +} + +static bool feat_aderr(struct kvm *kvm) +{ + return (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, FEAT_ADERR) && + kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SDERR, FEAT_ADERR)); +} + +static bool feat_anerr(struct kvm *kvm) +{ + return (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ANERR, FEAT_ANERR) && + kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SNERR, FEAT_ANERR)); +} + +static bool feat_sme_smps(struct kvm *kvm) +{ + /* + * Revists this if KVM ever supports SME -- this really should + * look at the guest's view of SMIDR_EL1. Funnily enough, this + * is not captured in the JSON file, but only as a note in the + * ARM ARM. + */ + return (kvm_has_feat(kvm, FEAT_SME) && + (read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS)); +} + +static bool feat_spe_fds(struct kvm *kvm) +{ + /* + * Revists this if KVM ever supports SPE -- this really should + * look at the guest's view of PMSIDR_EL1. + */ + return (kvm_has_feat(kvm, FEAT_SPEv1p4) && + (read_sysreg_s(SYS_PMSIDR_EL1) & PMSIDR_EL1_FDS)); +} + +static bool feat_trbe_mpam(struct kvm *kvm) +{ + /* + * Revists this if KVM ever supports both MPAM and TRBE -- + * this really should look at the guest's view of TRBIDR_EL1. + */ + return (kvm_has_feat(kvm, FEAT_TRBE) && + kvm_has_feat(kvm, FEAT_MPAM) && + (read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_MPAM)); +} + +static bool feat_ebep_pmuv3_ss(struct kvm *kvm) +{ + return kvm_has_feat(kvm, FEAT_EBEP) || kvm_has_feat(kvm, FEAT_PMUv3_SS); +} + +static bool compute_hcr_rw(struct kvm *kvm, u64 *bits) +{ + /* This is purely academic: AArch32 and NV are mutually exclusive */ + if (bits) { + if (kvm_has_feat(kvm, FEAT_AA32EL1)) + *bits &= ~HCR_EL2_RW; + else + *bits |= HCR_EL2_RW; + } + + return true; +} + +static bool compute_hcr_e2h(struct kvm *kvm, u64 *bits) +{ + if (bits) { + if (kvm_has_feat(kvm, FEAT_E2H0)) + *bits &= ~HCR_EL2_E2H; + else + *bits |= HCR_EL2_E2H; + } + + return true; +} + +static const struct reg_bits_to_feat_map hfgrtr_feat_map[] = { + NEEDS_FEAT(HFGRTR_EL2_nAMAIR2_EL1 | + HFGRTR_EL2_nMAIR2_EL1, + FEAT_AIE), + NEEDS_FEAT(HFGRTR_EL2_nS2POR_EL1, FEAT_S2POE), + NEEDS_FEAT(HFGRTR_EL2_nPOR_EL1 | + HFGRTR_EL2_nPOR_EL0, + FEAT_S1POE), + NEEDS_FEAT(HFGRTR_EL2_nPIR_EL1 | + HFGRTR_EL2_nPIRE0_EL1, + FEAT_S1PIE), + NEEDS_FEAT(HFGRTR_EL2_nRCWMASK_EL1, FEAT_THE), + NEEDS_FEAT(HFGRTR_EL2_nTPIDR2_EL0 | + HFGRTR_EL2_nSMPRI_EL1, + FEAT_SME), + NEEDS_FEAT(HFGRTR_EL2_nGCS_EL1 | + HFGRTR_EL2_nGCS_EL0, + FEAT_GCS), + NEEDS_FEAT(HFGRTR_EL2_nACCDATA_EL1, FEAT_LS64_ACCDATA), + NEEDS_FEAT(HFGRTR_EL2_ERXADDR_EL1 | + HFGRTR_EL2_ERXMISCn_EL1 | + HFGRTR_EL2_ERXSTATUS_EL1 | + HFGRTR_EL2_ERXCTLR_EL1 | + HFGRTR_EL2_ERXFR_EL1 | + HFGRTR_EL2_ERRSELR_EL1 | + HFGRTR_EL2_ERRIDR_EL1, + FEAT_RAS), + NEEDS_FEAT(HFGRTR_EL2_ERXPFGCDN_EL1 | + HFGRTR_EL2_ERXPFGCTL_EL1 | + HFGRTR_EL2_ERXPFGF_EL1, + feat_rasv1p1), + NEEDS_FEAT(HFGRTR_EL2_ICC_IGRPENn_EL1, FEAT_GICv3), + NEEDS_FEAT(HFGRTR_EL2_SCXTNUM_EL0 | + HFGRTR_EL2_SCXTNUM_EL1, + feat_csv2_2_csv2_1p2), + NEEDS_FEAT(HFGRTR_EL2_LORSA_EL1 | + HFGRTR_EL2_LORN_EL1 | + HFGRTR_EL2_LORID_EL1 | + HFGRTR_EL2_LOREA_EL1 | + HFGRTR_EL2_LORC_EL1, + FEAT_LOR), + NEEDS_FEAT(HFGRTR_EL2_APIBKey | + HFGRTR_EL2_APIAKey | + HFGRTR_EL2_APGAKey | + HFGRTR_EL2_APDBKey | + HFGRTR_EL2_APDAKey, + feat_pauth), + NEEDS_FEAT_FLAG(HFGRTR_EL2_VBAR_EL1 | + HFGRTR_EL2_TTBR1_EL1 | + HFGRTR_EL2_TTBR0_EL1 | + HFGRTR_EL2_TPIDR_EL0 | + HFGRTR_EL2_TPIDRRO_EL0 | + HFGRTR_EL2_TPIDR_EL1 | + HFGRTR_EL2_TCR_EL1 | + HFGRTR_EL2_SCTLR_EL1 | + HFGRTR_EL2_REVIDR_EL1 | + HFGRTR_EL2_PAR_EL1 | + HFGRTR_EL2_MPIDR_EL1 | + HFGRTR_EL2_MIDR_EL1 | + HFGRTR_EL2_MAIR_EL1 | + HFGRTR_EL2_ISR_EL1 | + HFGRTR_EL2_FAR_EL1 | + HFGRTR_EL2_ESR_EL1 | + HFGRTR_EL2_DCZID_EL0 | + HFGRTR_EL2_CTR_EL0 | + HFGRTR_EL2_CSSELR_EL1 | + HFGRTR_EL2_CPACR_EL1 | + HFGRTR_EL2_CONTEXTIDR_EL1| + HFGRTR_EL2_CLIDR_EL1 | + HFGRTR_EL2_CCSIDR_EL1 | + HFGRTR_EL2_AMAIR_EL1 | + HFGRTR_EL2_AIDR_EL1 | + HFGRTR_EL2_AFSR1_EL1 | + HFGRTR_EL2_AFSR0_EL1, + NEVER_FGU, FEAT_AA64EL1), +}; + +static const struct reg_bits_to_feat_map hfgwtr_feat_map[] = { + NEEDS_FEAT(HFGWTR_EL2_nAMAIR2_EL1 | + HFGWTR_EL2_nMAIR2_EL1, + FEAT_AIE), + NEEDS_FEAT(HFGWTR_EL2_nS2POR_EL1, FEAT_S2POE), + NEEDS_FEAT(HFGWTR_EL2_nPOR_EL1 | + HFGWTR_EL2_nPOR_EL0, + FEAT_S1POE), + NEEDS_FEAT(HFGWTR_EL2_nPIR_EL1 | + HFGWTR_EL2_nPIRE0_EL1, + FEAT_S1PIE), + NEEDS_FEAT(HFGWTR_EL2_nRCWMASK_EL1, FEAT_THE), + NEEDS_FEAT(HFGWTR_EL2_nTPIDR2_EL0 | + HFGWTR_EL2_nSMPRI_EL1, + FEAT_SME), + NEEDS_FEAT(HFGWTR_EL2_nGCS_EL1 | + HFGWTR_EL2_nGCS_EL0, + FEAT_GCS), + NEEDS_FEAT(HFGWTR_EL2_nACCDATA_EL1, FEAT_LS64_ACCDATA), + NEEDS_FEAT(HFGWTR_EL2_ERXADDR_EL1 | + HFGWTR_EL2_ERXMISCn_EL1 | + HFGWTR_EL2_ERXSTATUS_EL1 | + HFGWTR_EL2_ERXCTLR_EL1 | + HFGWTR_EL2_ERRSELR_EL1, + FEAT_RAS), + NEEDS_FEAT(HFGWTR_EL2_ERXPFGCDN_EL1 | + HFGWTR_EL2_ERXPFGCTL_EL1, + feat_rasv1p1), + NEEDS_FEAT(HFGWTR_EL2_ICC_IGRPENn_EL1, FEAT_GICv3), + NEEDS_FEAT(HFGWTR_EL2_SCXTNUM_EL0 | + HFGWTR_EL2_SCXTNUM_EL1, + feat_csv2_2_csv2_1p2), + NEEDS_FEAT(HFGWTR_EL2_LORSA_EL1 | + HFGWTR_EL2_LORN_EL1 | + HFGWTR_EL2_LOREA_EL1 | + HFGWTR_EL2_LORC_EL1, + FEAT_LOR), + NEEDS_FEAT(HFGWTR_EL2_APIBKey | + HFGWTR_EL2_APIAKey | + HFGWTR_EL2_APGAKey | + HFGWTR_EL2_APDBKey | + HFGWTR_EL2_APDAKey, + feat_pauth), + NEEDS_FEAT_FLAG(HFGWTR_EL2_VBAR_EL1 | + HFGWTR_EL2_TTBR1_EL1 | + HFGWTR_EL2_TTBR0_EL1 | + HFGWTR_EL2_TPIDR_EL0 | + HFGWTR_EL2_TPIDRRO_EL0 | + HFGWTR_EL2_TPIDR_EL1 | + HFGWTR_EL2_TCR_EL1 | + HFGWTR_EL2_SCTLR_EL1 | + HFGWTR_EL2_PAR_EL1 | + HFGWTR_EL2_MAIR_EL1 | + HFGWTR_EL2_FAR_EL1 | + HFGWTR_EL2_ESR_EL1 | + HFGWTR_EL2_CSSELR_EL1 | + HFGWTR_EL2_CPACR_EL1 | + HFGWTR_EL2_CONTEXTIDR_EL1| + HFGWTR_EL2_AMAIR_EL1 | + HFGWTR_EL2_AFSR1_EL1 | + HFGWTR_EL2_AFSR0_EL1, + NEVER_FGU, FEAT_AA64EL1), +}; + +static const struct reg_bits_to_feat_map hdfgrtr_feat_map[] = { + NEEDS_FEAT(HDFGRTR_EL2_PMBIDR_EL1 | + HDFGRTR_EL2_PMSLATFR_EL1 | + HDFGRTR_EL2_PMSIRR_EL1 | + HDFGRTR_EL2_PMSIDR_EL1 | + HDFGRTR_EL2_PMSICR_EL1 | + HDFGRTR_EL2_PMSFCR_EL1 | + HDFGRTR_EL2_PMSEVFR_EL1 | + HDFGRTR_EL2_PMSCR_EL1 | + HDFGRTR_EL2_PMBSR_EL1 | + HDFGRTR_EL2_PMBPTR_EL1 | + HDFGRTR_EL2_PMBLIMITR_EL1, + FEAT_SPE), + NEEDS_FEAT(HDFGRTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE), + NEEDS_FEAT(HDFGRTR_EL2_nBRBDATA | + HDFGRTR_EL2_nBRBCTL | + HDFGRTR_EL2_nBRBIDR, + FEAT_BRBE), + NEEDS_FEAT(HDFGRTR_EL2_TRCVICTLR | + HDFGRTR_EL2_TRCSTATR | + HDFGRTR_EL2_TRCSSCSRn | + HDFGRTR_EL2_TRCSEQSTR | + HDFGRTR_EL2_TRCPRGCTLR | + HDFGRTR_EL2_TRCOSLSR | + HDFGRTR_EL2_TRCIMSPECn | + HDFGRTR_EL2_TRCID | + HDFGRTR_EL2_TRCCNTVRn | + HDFGRTR_EL2_TRCCLAIM | + HDFGRTR_EL2_TRCAUXCTLR | + HDFGRTR_EL2_TRCAUTHSTATUS | + HDFGRTR_EL2_TRC, + FEAT_TRC_SR), + NEEDS_FEAT(HDFGRTR_EL2_PMCEIDn_EL0 | + HDFGRTR_EL2_PMUSERENR_EL0 | + HDFGRTR_EL2_PMMIR_EL1 | + HDFGRTR_EL2_PMSELR_EL0 | + HDFGRTR_EL2_PMOVS | + HDFGRTR_EL2_PMINTEN | + HDFGRTR_EL2_PMCNTEN | + HDFGRTR_EL2_PMCCNTR_EL0 | + HDFGRTR_EL2_PMCCFILTR_EL0 | + HDFGRTR_EL2_PMEVTYPERn_EL0 | + HDFGRTR_EL2_PMEVCNTRn_EL0, + FEAT_PMUv3), + NEEDS_FEAT(HDFGRTR_EL2_TRBTRG_EL1 | + HDFGRTR_EL2_TRBSR_EL1 | + HDFGRTR_EL2_TRBPTR_EL1 | + HDFGRTR_EL2_TRBMAR_EL1 | + HDFGRTR_EL2_TRBLIMITR_EL1 | + HDFGRTR_EL2_TRBIDR_EL1 | + HDFGRTR_EL2_TRBBASER_EL1, + FEAT_TRBE), + NEEDS_FEAT_FLAG(HDFGRTR_EL2_OSDLR_EL1, NEVER_FGU, + FEAT_DoubleLock), + NEEDS_FEAT_FLAG(HDFGRTR_EL2_OSECCR_EL1 | + HDFGRTR_EL2_OSLSR_EL1 | + HDFGRTR_EL2_DBGPRCR_EL1 | + HDFGRTR_EL2_DBGAUTHSTATUS_EL1| + HDFGRTR_EL2_DBGCLAIM | + HDFGRTR_EL2_MDSCR_EL1 | + HDFGRTR_EL2_DBGWVRn_EL1 | + HDFGRTR_EL2_DBGWCRn_EL1 | + HDFGRTR_EL2_DBGBVRn_EL1 | + HDFGRTR_EL2_DBGBCRn_EL1, + NEVER_FGU, FEAT_AA64EL1) +}; + +static const struct reg_bits_to_feat_map hdfgwtr_feat_map[] = { + NEEDS_FEAT(HDFGWTR_EL2_PMSLATFR_EL1 | + HDFGWTR_EL2_PMSIRR_EL1 | + HDFGWTR_EL2_PMSICR_EL1 | + HDFGWTR_EL2_PMSFCR_EL1 | + HDFGWTR_EL2_PMSEVFR_EL1 | + HDFGWTR_EL2_PMSCR_EL1 | + HDFGWTR_EL2_PMBSR_EL1 | + HDFGWTR_EL2_PMBPTR_EL1 | + HDFGWTR_EL2_PMBLIMITR_EL1, + FEAT_SPE), + NEEDS_FEAT(HDFGWTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE), + NEEDS_FEAT(HDFGWTR_EL2_nBRBDATA | + HDFGWTR_EL2_nBRBCTL, + FEAT_BRBE), + NEEDS_FEAT(HDFGWTR_EL2_TRCVICTLR | + HDFGWTR_EL2_TRCSSCSRn | + HDFGWTR_EL2_TRCSEQSTR | + HDFGWTR_EL2_TRCPRGCTLR | + HDFGWTR_EL2_TRCOSLAR | + HDFGWTR_EL2_TRCIMSPECn | + HDFGWTR_EL2_TRCCNTVRn | + HDFGWTR_EL2_TRCCLAIM | + HDFGWTR_EL2_TRCAUXCTLR | + HDFGWTR_EL2_TRC, + FEAT_TRC_SR), + NEEDS_FEAT(HDFGWTR_EL2_PMUSERENR_EL0 | + HDFGWTR_EL2_PMCR_EL0 | + HDFGWTR_EL2_PMSWINC_EL0 | + HDFGWTR_EL2_PMSELR_EL0 | + HDFGWTR_EL2_PMOVS | + HDFGWTR_EL2_PMINTEN | + HDFGWTR_EL2_PMCNTEN | + HDFGWTR_EL2_PMCCNTR_EL0 | + HDFGWTR_EL2_PMCCFILTR_EL0 | + HDFGWTR_EL2_PMEVTYPERn_EL0 | + HDFGWTR_EL2_PMEVCNTRn_EL0, + FEAT_PMUv3), + NEEDS_FEAT(HDFGWTR_EL2_TRBTRG_EL1 | + HDFGWTR_EL2_TRBSR_EL1 | + HDFGWTR_EL2_TRBPTR_EL1 | + HDFGWTR_EL2_TRBMAR_EL1 | + HDFGWTR_EL2_TRBLIMITR_EL1 | + HDFGWTR_EL2_TRBBASER_EL1, + FEAT_TRBE), + NEEDS_FEAT_FLAG(HDFGWTR_EL2_OSDLR_EL1, + NEVER_FGU, FEAT_DoubleLock), + NEEDS_FEAT_FLAG(HDFGWTR_EL2_OSECCR_EL1 | + HDFGWTR_EL2_OSLAR_EL1 | + HDFGWTR_EL2_DBGPRCR_EL1 | + HDFGWTR_EL2_DBGCLAIM | + HDFGWTR_EL2_MDSCR_EL1 | + HDFGWTR_EL2_DBGWVRn_EL1 | + HDFGWTR_EL2_DBGWCRn_EL1 | + HDFGWTR_EL2_DBGBVRn_EL1 | + HDFGWTR_EL2_DBGBCRn_EL1, + NEVER_FGU, FEAT_AA64EL1), + NEEDS_FEAT(HDFGWTR_EL2_TRFCR_EL1, FEAT_TRF), +}; + + +static const struct reg_bits_to_feat_map hfgitr_feat_map[] = { + NEEDS_FEAT(HFGITR_EL2_PSBCSYNC, FEAT_SPEv1p5), + NEEDS_FEAT(HFGITR_EL2_ATS1E1A, FEAT_ATS1A), + NEEDS_FEAT(HFGITR_EL2_COSPRCTX, FEAT_SPECRES2), + NEEDS_FEAT(HFGITR_EL2_nGCSEPP | + HFGITR_EL2_nGCSSTR_EL1 | + HFGITR_EL2_nGCSPUSHM_EL1, + FEAT_GCS), + NEEDS_FEAT(HFGITR_EL2_nBRBIALL | + HFGITR_EL2_nBRBINJ, + FEAT_BRBE), + NEEDS_FEAT(HFGITR_EL2_CPPRCTX | + HFGITR_EL2_DVPRCTX | + HFGITR_EL2_CFPRCTX, + FEAT_SPECRES), + NEEDS_FEAT(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, + FEAT_TLBIRANGE), + NEEDS_FEAT(HFGITR_EL2_TLBIVAALE1OS | + HFGITR_EL2_TLBIVALE1OS | + HFGITR_EL2_TLBIVAAE1OS | + HFGITR_EL2_TLBIASIDE1OS | + HFGITR_EL2_TLBIVAE1OS | + HFGITR_EL2_TLBIVMALLE1OS, + FEAT_TLBIOS), + NEEDS_FEAT(HFGITR_EL2_ATS1E1WP | + HFGITR_EL2_ATS1E1RP, + FEAT_PAN2), + NEEDS_FEAT(HFGITR_EL2_DCCVADP, FEAT_DPB2), + NEEDS_FEAT_FLAG(HFGITR_EL2_DCCVAC | + HFGITR_EL2_SVC_EL1 | + HFGITR_EL2_SVC_EL0 | + HFGITR_EL2_ERET | + HFGITR_EL2_TLBIVAALE1 | + HFGITR_EL2_TLBIVALE1 | + HFGITR_EL2_TLBIVAAE1 | + HFGITR_EL2_TLBIASIDE1 | + HFGITR_EL2_TLBIVAE1 | + HFGITR_EL2_TLBIVMALLE1 | + HFGITR_EL2_TLBIVAALE1IS | + HFGITR_EL2_TLBIVALE1IS | + HFGITR_EL2_TLBIVAAE1IS | + HFGITR_EL2_TLBIASIDE1IS | + HFGITR_EL2_TLBIVAE1IS | + HFGITR_EL2_TLBIVMALLE1IS| + HFGITR_EL2_ATS1E0W | + HFGITR_EL2_ATS1E0R | + HFGITR_EL2_ATS1E1W | + HFGITR_EL2_ATS1E1R | + HFGITR_EL2_DCZVA | + HFGITR_EL2_DCCIVAC | + HFGITR_EL2_DCCVAP | + HFGITR_EL2_DCCVAU | + HFGITR_EL2_DCCISW | + HFGITR_EL2_DCCSW | + HFGITR_EL2_DCISW | + HFGITR_EL2_DCIVAC | + HFGITR_EL2_ICIVAU | + HFGITR_EL2_ICIALLU | + HFGITR_EL2_ICIALLUIS, + NEVER_FGU, FEAT_AA64EL1), +}; + +static const struct reg_bits_to_feat_map hafgrtr_feat_map[] = { + NEEDS_FEAT(HAFGRTR_EL2_AMEVTYPER115_EL0 | + HAFGRTR_EL2_AMEVTYPER114_EL0 | + HAFGRTR_EL2_AMEVTYPER113_EL0 | + HAFGRTR_EL2_AMEVTYPER112_EL0 | + HAFGRTR_EL2_AMEVTYPER111_EL0 | + HAFGRTR_EL2_AMEVTYPER110_EL0 | + HAFGRTR_EL2_AMEVTYPER19_EL0 | + HAFGRTR_EL2_AMEVTYPER18_EL0 | + HAFGRTR_EL2_AMEVTYPER17_EL0 | + HAFGRTR_EL2_AMEVTYPER16_EL0 | + HAFGRTR_EL2_AMEVTYPER15_EL0 | + HAFGRTR_EL2_AMEVTYPER14_EL0 | + HAFGRTR_EL2_AMEVTYPER13_EL0 | + HAFGRTR_EL2_AMEVTYPER12_EL0 | + HAFGRTR_EL2_AMEVTYPER11_EL0 | + HAFGRTR_EL2_AMEVTYPER10_EL0 | + HAFGRTR_EL2_AMEVCNTR115_EL0 | + HAFGRTR_EL2_AMEVCNTR114_EL0 | + HAFGRTR_EL2_AMEVCNTR113_EL0 | + HAFGRTR_EL2_AMEVCNTR112_EL0 | + HAFGRTR_EL2_AMEVCNTR111_EL0 | + HAFGRTR_EL2_AMEVCNTR110_EL0 | + HAFGRTR_EL2_AMEVCNTR19_EL0 | + HAFGRTR_EL2_AMEVCNTR18_EL0 | + HAFGRTR_EL2_AMEVCNTR17_EL0 | + HAFGRTR_EL2_AMEVCNTR16_EL0 | + HAFGRTR_EL2_AMEVCNTR15_EL0 | + HAFGRTR_EL2_AMEVCNTR14_EL0 | + HAFGRTR_EL2_AMEVCNTR13_EL0 | + HAFGRTR_EL2_AMEVCNTR12_EL0 | + HAFGRTR_EL2_AMEVCNTR11_EL0 | + HAFGRTR_EL2_AMEVCNTR10_EL0 | + HAFGRTR_EL2_AMCNTEN1 | + HAFGRTR_EL2_AMCNTEN0 | + HAFGRTR_EL2_AMEVCNTR03_EL0 | + HAFGRTR_EL2_AMEVCNTR02_EL0 | + HAFGRTR_EL2_AMEVCNTR01_EL0 | + HAFGRTR_EL2_AMEVCNTR00_EL0, + FEAT_AMUv1), +}; + +static const struct reg_bits_to_feat_map hfgitr2_feat_map[] = { + NEEDS_FEAT(HFGITR2_EL2_nDCCIVAPS, FEAT_PoPS), + NEEDS_FEAT(HFGITR2_EL2_TSBCSYNC, FEAT_TRBEv1p1) +}; + +static const struct reg_bits_to_feat_map hfgrtr2_feat_map[] = { + NEEDS_FEAT(HFGRTR2_EL2_nPFAR_EL1, FEAT_PFAR), + NEEDS_FEAT(HFGRTR2_EL2_nERXGSR_EL1, FEAT_RASv2), + NEEDS_FEAT(HFGRTR2_EL2_nACTLRALIAS_EL1 | + HFGRTR2_EL2_nACTLRMASK_EL1 | + HFGRTR2_EL2_nCPACRALIAS_EL1 | + HFGRTR2_EL2_nCPACRMASK_EL1 | + HFGRTR2_EL2_nSCTLR2MASK_EL1 | + HFGRTR2_EL2_nSCTLRALIAS2_EL1 | + HFGRTR2_EL2_nSCTLRALIAS_EL1 | + HFGRTR2_EL2_nSCTLRMASK_EL1 | + HFGRTR2_EL2_nTCR2ALIAS_EL1 | + HFGRTR2_EL2_nTCR2MASK_EL1 | + HFGRTR2_EL2_nTCRALIAS_EL1 | + HFGRTR2_EL2_nTCRMASK_EL1, + FEAT_SRMASK), + NEEDS_FEAT(HFGRTR2_EL2_nRCWSMASK_EL1, FEAT_THE), +}; + +static const struct reg_bits_to_feat_map hfgwtr2_feat_map[] = { + NEEDS_FEAT(HFGWTR2_EL2_nPFAR_EL1, FEAT_PFAR), + NEEDS_FEAT(HFGWTR2_EL2_nACTLRALIAS_EL1 | + HFGWTR2_EL2_nACTLRMASK_EL1 | + HFGWTR2_EL2_nCPACRALIAS_EL1 | + HFGWTR2_EL2_nCPACRMASK_EL1 | + HFGWTR2_EL2_nSCTLR2MASK_EL1 | + HFGWTR2_EL2_nSCTLRALIAS2_EL1 | + HFGWTR2_EL2_nSCTLRALIAS_EL1 | + HFGWTR2_EL2_nSCTLRMASK_EL1 | + HFGWTR2_EL2_nTCR2ALIAS_EL1 | + HFGWTR2_EL2_nTCR2MASK_EL1 | + HFGWTR2_EL2_nTCRALIAS_EL1 | + HFGWTR2_EL2_nTCRMASK_EL1, + FEAT_SRMASK), + NEEDS_FEAT(HFGWTR2_EL2_nRCWSMASK_EL1, FEAT_THE), +}; + +static const struct reg_bits_to_feat_map hdfgrtr2_feat_map[] = { + NEEDS_FEAT(HDFGRTR2_EL2_nMDSELR_EL1, FEAT_Debugv8p9), + NEEDS_FEAT(HDFGRTR2_EL2_nPMECR_EL1, feat_ebep_pmuv3_ss), + NEEDS_FEAT(HDFGRTR2_EL2_nTRCITECR_EL1, FEAT_ITE), + NEEDS_FEAT(HDFGRTR2_EL2_nPMICFILTR_EL0 | + HDFGRTR2_EL2_nPMICNTR_EL0, + FEAT_PMUv3_ICNTR), + NEEDS_FEAT(HDFGRTR2_EL2_nPMUACR_EL1, FEAT_PMUv3p9), + NEEDS_FEAT(HDFGRTR2_EL2_nPMSSCR_EL1 | + HDFGRTR2_EL2_nPMSSDATA, + FEAT_PMUv3_SS), + NEEDS_FEAT(HDFGRTR2_EL2_nPMIAR_EL1, FEAT_SEBEP), + NEEDS_FEAT(HDFGRTR2_EL2_nPMSDSFR_EL1, feat_spe_fds), + NEEDS_FEAT(HDFGRTR2_EL2_nPMBMAR_EL1, FEAT_SPE_nVM), + NEEDS_FEAT(HDFGRTR2_EL2_nSPMACCESSR_EL1 | + HDFGRTR2_EL2_nSPMCNTEN | + HDFGRTR2_EL2_nSPMCR_EL0 | + HDFGRTR2_EL2_nSPMDEVAFF_EL1 | + HDFGRTR2_EL2_nSPMEVCNTRn_EL0 | + HDFGRTR2_EL2_nSPMEVTYPERn_EL0| + HDFGRTR2_EL2_nSPMID | + HDFGRTR2_EL2_nSPMINTEN | + HDFGRTR2_EL2_nSPMOVS | + HDFGRTR2_EL2_nSPMSCR_EL1 | + HDFGRTR2_EL2_nSPMSELR_EL0, + FEAT_SPMU), + NEEDS_FEAT(HDFGRTR2_EL2_nMDSTEPOP_EL1, FEAT_STEP2), + NEEDS_FEAT(HDFGRTR2_EL2_nTRBMPAM_EL1, feat_trbe_mpam), +}; + +static const struct reg_bits_to_feat_map hdfgwtr2_feat_map[] = { + NEEDS_FEAT(HDFGWTR2_EL2_nMDSELR_EL1, FEAT_Debugv8p9), + NEEDS_FEAT(HDFGWTR2_EL2_nPMECR_EL1, feat_ebep_pmuv3_ss), + NEEDS_FEAT(HDFGWTR2_EL2_nTRCITECR_EL1, FEAT_ITE), + NEEDS_FEAT(HDFGWTR2_EL2_nPMICFILTR_EL0 | + HDFGWTR2_EL2_nPMICNTR_EL0, + FEAT_PMUv3_ICNTR), + NEEDS_FEAT(HDFGWTR2_EL2_nPMUACR_EL1 | + HDFGWTR2_EL2_nPMZR_EL0, + FEAT_PMUv3p9), + NEEDS_FEAT(HDFGWTR2_EL2_nPMSSCR_EL1, FEAT_PMUv3_SS), + NEEDS_FEAT(HDFGWTR2_EL2_nPMIAR_EL1, FEAT_SEBEP), + NEEDS_FEAT(HDFGWTR2_EL2_nPMSDSFR_EL1, feat_spe_fds), + NEEDS_FEAT(HDFGWTR2_EL2_nPMBMAR_EL1, FEAT_SPE_nVM), + NEEDS_FEAT(HDFGWTR2_EL2_nSPMACCESSR_EL1 | + HDFGWTR2_EL2_nSPMCNTEN | + HDFGWTR2_EL2_nSPMCR_EL0 | + HDFGWTR2_EL2_nSPMEVCNTRn_EL0 | + HDFGWTR2_EL2_nSPMEVTYPERn_EL0| + HDFGWTR2_EL2_nSPMINTEN | + HDFGWTR2_EL2_nSPMOVS | + HDFGWTR2_EL2_nSPMSCR_EL1 | + HDFGWTR2_EL2_nSPMSELR_EL0, + FEAT_SPMU), + NEEDS_FEAT(HDFGWTR2_EL2_nMDSTEPOP_EL1, FEAT_STEP2), + NEEDS_FEAT(HDFGWTR2_EL2_nTRBMPAM_EL1, feat_trbe_mpam), +}; + +static const struct reg_bits_to_feat_map hcrx_feat_map[] = { + NEEDS_FEAT(HCRX_EL2_PACMEn, feat_pauth_lr), + NEEDS_FEAT(HCRX_EL2_EnFPM, FEAT_FPMR), + NEEDS_FEAT(HCRX_EL2_GCSEn, FEAT_GCS), + NEEDS_FEAT(HCRX_EL2_EnIDCP128, FEAT_SYSREG128), + NEEDS_FEAT(HCRX_EL2_EnSDERR, feat_aderr), + NEEDS_FEAT(HCRX_EL2_TMEA, FEAT_DoubleFault2), + NEEDS_FEAT(HCRX_EL2_EnSNERR, feat_anerr), + NEEDS_FEAT(HCRX_EL2_D128En, FEAT_D128), + NEEDS_FEAT(HCRX_EL2_PTTWI, FEAT_THE), + NEEDS_FEAT(HCRX_EL2_SCTLR2En, FEAT_SCTLR2), + NEEDS_FEAT(HCRX_EL2_TCR2En, FEAT_TCR2), + NEEDS_FEAT(HCRX_EL2_MSCEn | + HCRX_EL2_MCE2, + FEAT_MOPS), + NEEDS_FEAT(HCRX_EL2_CMOW, FEAT_CMOW), + NEEDS_FEAT(HCRX_EL2_VFNMI | + HCRX_EL2_VINMI | + HCRX_EL2_TALLINT, + FEAT_NMI), + NEEDS_FEAT(HCRX_EL2_SMPME, feat_sme_smps), + NEEDS_FEAT(HCRX_EL2_FGTnXS | + HCRX_EL2_FnXS, + FEAT_XS), + NEEDS_FEAT(HCRX_EL2_EnASR, FEAT_LS64_V), + NEEDS_FEAT(HCRX_EL2_EnALS, FEAT_LS64), + NEEDS_FEAT(HCRX_EL2_EnAS0, FEAT_LS64_ACCDATA), +}; + +static const struct reg_bits_to_feat_map hcr_feat_map[] = { + NEEDS_FEAT(HCR_EL2_TID0, FEAT_AA32EL0), + NEEDS_FEAT_FIXED(HCR_EL2_RW, compute_hcr_rw), + NEEDS_FEAT(HCR_EL2_HCD, not_feat_aa64el3), + NEEDS_FEAT(HCR_EL2_AMO | + HCR_EL2_BSU | + HCR_EL2_CD | + HCR_EL2_DC | + HCR_EL2_FB | + HCR_EL2_FMO | + HCR_EL2_ID | + HCR_EL2_IMO | + HCR_EL2_MIOCNCE | + HCR_EL2_PTW | + HCR_EL2_SWIO | + HCR_EL2_TACR | + HCR_EL2_TDZ | + HCR_EL2_TGE | + HCR_EL2_TID1 | + HCR_EL2_TID2 | + HCR_EL2_TID3 | + HCR_EL2_TIDCP | + HCR_EL2_TPCP | + HCR_EL2_TPU | + HCR_EL2_TRVM | + HCR_EL2_TSC | + HCR_EL2_TSW | + HCR_EL2_TTLB | + HCR_EL2_TVM | + HCR_EL2_TWE | + HCR_EL2_TWI | + HCR_EL2_VF | + HCR_EL2_VI | + HCR_EL2_VM | + HCR_EL2_VSE, + FEAT_AA64EL1), + NEEDS_FEAT(HCR_EL2_AMVOFFEN, FEAT_AMUv1p1), + NEEDS_FEAT(HCR_EL2_EnSCXT, feat_csv2_2_csv2_1p2), + NEEDS_FEAT(HCR_EL2_TICAB | + HCR_EL2_TID4 | + HCR_EL2_TOCU, + FEAT_EVT), + NEEDS_FEAT(HCR_EL2_TTLBIS | + HCR_EL2_TTLBOS, + FEAT_EVT_TTLBxS), + NEEDS_FEAT(HCR_EL2_TLOR, FEAT_LOR), + NEEDS_FEAT(HCR_EL2_ATA | + HCR_EL2_DCT | + HCR_EL2_TID5, + FEAT_MTE2), + NEEDS_FEAT(HCR_EL2_AT | /* Ignore the original FEAT_NV */ + HCR_EL2_NV2 | + HCR_EL2_NV, + feat_nv2), + NEEDS_FEAT(HCR_EL2_NV1, feat_nv2_e2h0_ni), /* Missing from JSON */ + NEEDS_FEAT(HCR_EL2_API | + HCR_EL2_APK, + feat_pauth), + NEEDS_FEAT(HCR_EL2_TEA | + HCR_EL2_TERR, + FEAT_RAS), + NEEDS_FEAT(HCR_EL2_FIEN, feat_rasv1p1), + NEEDS_FEAT(HCR_EL2_GPF, FEAT_RME), + NEEDS_FEAT(HCR_EL2_FWB, FEAT_S2FWB), + NEEDS_FEAT(HCR_EL2_TME, FEAT_TME), + NEEDS_FEAT(HCR_EL2_TWEDEL | + HCR_EL2_TWEDEn, + FEAT_TWED), + NEEDS_FEAT_FIXED(HCR_EL2_E2H, compute_hcr_e2h), +}; + +static void __init check_feat_map(const struct reg_bits_to_feat_map *map, + int map_size, u64 res0, const char *str) +{ + u64 mask = 0; + + for (int i = 0; i < map_size; i++) + mask |= map[i].bits; + + if (mask != ~res0) + kvm_err("Undefined %s behaviour, bits %016llx\n", + str, mask ^ ~res0); +} + +void __init check_feature_map(void) +{ + check_feat_map(hfgrtr_feat_map, ARRAY_SIZE(hfgrtr_feat_map), + hfgrtr_masks.res0, hfgrtr_masks.str); + check_feat_map(hfgwtr_feat_map, ARRAY_SIZE(hfgwtr_feat_map), + hfgwtr_masks.res0, hfgwtr_masks.str); + check_feat_map(hfgitr_feat_map, ARRAY_SIZE(hfgitr_feat_map), + hfgitr_masks.res0, hfgitr_masks.str); + check_feat_map(hdfgrtr_feat_map, ARRAY_SIZE(hdfgrtr_feat_map), + hdfgrtr_masks.res0, hdfgrtr_masks.str); + check_feat_map(hdfgwtr_feat_map, ARRAY_SIZE(hdfgwtr_feat_map), + hdfgwtr_masks.res0, hdfgwtr_masks.str); + check_feat_map(hafgrtr_feat_map, ARRAY_SIZE(hafgrtr_feat_map), + hafgrtr_masks.res0, hafgrtr_masks.str); + check_feat_map(hcrx_feat_map, ARRAY_SIZE(hcrx_feat_map), + __HCRX_EL2_RES0, "HCRX_EL2"); + check_feat_map(hcr_feat_map, ARRAY_SIZE(hcr_feat_map), + HCR_EL2_RES0, "HCR_EL2"); +} + +static bool idreg_feat_match(struct kvm *kvm, const struct reg_bits_to_feat_map *map) +{ + u64 regval = kvm->arch.id_regs[map->regidx]; + u64 regfld = (regval >> map->shift) & GENMASK(map->width - 1, 0); + + if (map->sign) { + s64 sfld = sign_extend64(regfld, map->width - 1); + s64 slim = sign_extend64(map->lo_lim, map->width - 1); + return sfld >= slim; + } else { + return regfld >= map->lo_lim; + } +} + +static u64 __compute_fixed_bits(struct kvm *kvm, + const struct reg_bits_to_feat_map *map, + int map_size, + u64 *fixed_bits, + unsigned long require, + unsigned long exclude) +{ + u64 val = 0; + + for (int i = 0; i < map_size; i++) { + bool match; + + if ((map[i].flags & require) != require) + continue; + + if (map[i].flags & exclude) + continue; + + if (map[i].flags & CALL_FUNC) + match = (map[i].flags & FIXED_VALUE) ? + map[i].fval(kvm, fixed_bits) : + map[i].match(kvm); + else + match = idreg_feat_match(kvm, &map[i]); + + if (!match || (map[i].flags & FIXED_VALUE)) + val |= map[i].bits; + } + + return val; +} + +static u64 compute_res0_bits(struct kvm *kvm, + const struct reg_bits_to_feat_map *map, + int map_size, + unsigned long require, + unsigned long exclude) +{ + return __compute_fixed_bits(kvm, map, map_size, NULL, + require, exclude | FIXED_VALUE); +} + +static u64 compute_fixed_bits(struct kvm *kvm, + const struct reg_bits_to_feat_map *map, + int map_size, + u64 *fixed_bits, + unsigned long require, + unsigned long exclude) +{ + return __compute_fixed_bits(kvm, map, map_size, fixed_bits, + require | FIXED_VALUE, exclude); +} + +void compute_fgu(struct kvm *kvm, enum fgt_group_id fgt) +{ + u64 val = 0; + + switch (fgt) { + case HFGRTR_GROUP: + val |= compute_res0_bits(kvm, hfgrtr_feat_map, + ARRAY_SIZE(hfgrtr_feat_map), + 0, NEVER_FGU); + val |= compute_res0_bits(kvm, hfgwtr_feat_map, + ARRAY_SIZE(hfgwtr_feat_map), + 0, NEVER_FGU); + break; + case HFGITR_GROUP: + val |= compute_res0_bits(kvm, hfgitr_feat_map, + ARRAY_SIZE(hfgitr_feat_map), + 0, NEVER_FGU); + break; + case HDFGRTR_GROUP: + val |= compute_res0_bits(kvm, hdfgrtr_feat_map, + ARRAY_SIZE(hdfgrtr_feat_map), + 0, NEVER_FGU); + val |= compute_res0_bits(kvm, hdfgwtr_feat_map, + ARRAY_SIZE(hdfgwtr_feat_map), + 0, NEVER_FGU); + break; + case HAFGRTR_GROUP: + val |= compute_res0_bits(kvm, hafgrtr_feat_map, + ARRAY_SIZE(hafgrtr_feat_map), + 0, NEVER_FGU); + break; + case HFGRTR2_GROUP: + val |= compute_res0_bits(kvm, hfgrtr2_feat_map, + ARRAY_SIZE(hfgrtr2_feat_map), + 0, NEVER_FGU); + val |= compute_res0_bits(kvm, hfgwtr2_feat_map, + ARRAY_SIZE(hfgwtr2_feat_map), + 0, NEVER_FGU); + break; + case HFGITR2_GROUP: + val |= compute_res0_bits(kvm, hfgitr2_feat_map, + ARRAY_SIZE(hfgitr2_feat_map), + 0, NEVER_FGU); + break; + case HDFGRTR2_GROUP: + val |= compute_res0_bits(kvm, hdfgrtr2_feat_map, + ARRAY_SIZE(hdfgrtr2_feat_map), + 0, NEVER_FGU); + val |= compute_res0_bits(kvm, hdfgwtr2_feat_map, + ARRAY_SIZE(hdfgwtr2_feat_map), + 0, NEVER_FGU); + break; + default: + BUG(); + } + + kvm->arch.fgu[fgt] = val; +} + +void get_reg_fixed_bits(struct kvm *kvm, enum vcpu_sysreg reg, u64 *res0, u64 *res1) +{ + u64 fixed = 0, mask; + + switch (reg) { + case HFGRTR_EL2: + *res0 = compute_res0_bits(kvm, hfgrtr_feat_map, + ARRAY_SIZE(hfgrtr_feat_map), 0, 0); + *res0 |= hfgrtr_masks.res0; + *res1 = HFGRTR_EL2_RES1; + break; + case HFGWTR_EL2: + *res0 = compute_res0_bits(kvm, hfgwtr_feat_map, + ARRAY_SIZE(hfgwtr_feat_map), 0, 0); + *res0 |= hfgwtr_masks.res0; + *res1 = HFGWTR_EL2_RES1; + break; + case HFGITR_EL2: + *res0 = compute_res0_bits(kvm, hfgitr_feat_map, + ARRAY_SIZE(hfgitr_feat_map), 0, 0); + *res0 |= hfgitr_masks.res0; + *res1 = HFGITR_EL2_RES1; + break; + case HDFGRTR_EL2: + *res0 = compute_res0_bits(kvm, hdfgrtr_feat_map, + ARRAY_SIZE(hdfgrtr_feat_map), 0, 0); + *res0 |= hdfgrtr_masks.res0; + *res1 = HDFGRTR_EL2_RES1; + break; + case HDFGWTR_EL2: + *res0 = compute_res0_bits(kvm, hdfgwtr_feat_map, + ARRAY_SIZE(hdfgwtr_feat_map), 0, 0); + *res0 |= hdfgwtr_masks.res0; + *res1 = HDFGWTR_EL2_RES1; + break; + case HAFGRTR_EL2: + *res0 = compute_res0_bits(kvm, hafgrtr_feat_map, + ARRAY_SIZE(hafgrtr_feat_map), 0, 0); + *res0 |= hafgrtr_masks.res0; + *res1 = HAFGRTR_EL2_RES1; + break; + case HFGRTR2_EL2: + *res0 = compute_res0_bits(kvm, hfgrtr2_feat_map, + ARRAY_SIZE(hfgrtr2_feat_map), 0, 0); + *res0 |= hfgrtr2_masks.res0; + *res1 = HFGRTR2_EL2_RES1; + break; + case HFGWTR2_EL2: + *res0 = compute_res0_bits(kvm, hfgwtr2_feat_map, + ARRAY_SIZE(hfgwtr2_feat_map), 0, 0); + *res0 |= hfgwtr2_masks.res0; + *res1 = HFGWTR2_EL2_RES1; + break; + case HFGITR2_EL2: + *res0 = compute_res0_bits(kvm, hfgitr2_feat_map, + ARRAY_SIZE(hfgitr2_feat_map), 0, 0); + *res0 |= hfgitr2_masks.res0; + *res1 = HFGITR2_EL2_RES1; + break; + case HDFGRTR2_EL2: + *res0 = compute_res0_bits(kvm, hdfgrtr2_feat_map, + ARRAY_SIZE(hdfgrtr2_feat_map), 0, 0); + *res0 |= hdfgrtr2_masks.res0; + *res1 = HDFGRTR2_EL2_RES1; + break; + case HDFGWTR2_EL2: + *res0 = compute_res0_bits(kvm, hdfgwtr2_feat_map, + ARRAY_SIZE(hdfgwtr2_feat_map), 0, 0); + *res0 |= hdfgwtr2_masks.res0; + *res1 = HDFGWTR2_EL2_RES1; + break; + case HCRX_EL2: + *res0 = compute_res0_bits(kvm, hcrx_feat_map, + ARRAY_SIZE(hcrx_feat_map), 0, 0); + *res0 |= __HCRX_EL2_RES0; + *res1 = __HCRX_EL2_RES1; + break; + case HCR_EL2: + mask = compute_fixed_bits(kvm, hcr_feat_map, + ARRAY_SIZE(hcr_feat_map), &fixed, + 0, 0); + *res0 = compute_res0_bits(kvm, hcr_feat_map, + ARRAY_SIZE(hcr_feat_map), 0, 0); + *res0 |= HCR_EL2_RES0 | (mask & ~fixed); + *res1 = HCR_EL2_RES1 | (mask & fixed); + break; + default: + WARN_ON_ONCE(1); + *res0 = *res1 = 0; + break; + } +} diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 607d37bab70b..3a384e9660b8 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -412,26 +412,26 @@ static const struct trap_bits coarse_trap_bits[] = { }, [CGT_ICH_HCR_TC] = { .index = ICH_HCR_EL2, - .value = ICH_HCR_TC, - .mask = ICH_HCR_TC, + .value = ICH_HCR_EL2_TC, + .mask = ICH_HCR_EL2_TC, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TALL0] = { .index = ICH_HCR_EL2, - .value = ICH_HCR_TALL0, - .mask = ICH_HCR_TALL0, + .value = ICH_HCR_EL2_TALL0, + .mask = ICH_HCR_EL2_TALL0, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TALL1] = { .index = ICH_HCR_EL2, - .value = ICH_HCR_TALL1, - .mask = ICH_HCR_TALL1, + .value = ICH_HCR_EL2_TALL1, + .mask = ICH_HCR_EL2_TALL1, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TDIR] = { .index = ICH_HCR_EL2, - .value = ICH_HCR_TDIR, - .mask = ICH_HCR_TDIR, + .value = ICH_HCR_EL2_TDIR, + .mask = ICH_HCR_EL2_TDIR, .behaviour = BEHAVE_FORWARD_RW, }, }; @@ -622,6 +622,11 @@ struct encoding_to_trap_config { const unsigned int line; }; +/* + * WARNING: using ranges is a treacherous endeavour, as sysregs that + * are part of an architectural range are not necessarily contiguous + * in the [Op0,Op1,CRn,CRm,Ops] space. Tread carefully. + */ #define SR_RANGE_TRAP(sr_start, sr_end, trap_id) \ { \ .encoding = sr_start, \ @@ -1279,98 +1284,128 @@ enum fg_filter_id { __NR_FG_FILTER_IDS__ }; -#define SR_FGF(sr, g, b, p, f) \ - { \ - .encoding = sr, \ - .end = sr, \ - .tc = { \ +#define __FGT(g, b, p, f) \ + { \ .fgt = g ## _GROUP, \ .bit = g ## _EL2_ ## b ## _SHIFT, \ .pol = p, \ .fgf = f, \ - }, \ + } + +#define FGT(g, b, p) __FGT(g, b, p, __NO_FGF__) + +/* + * See the warning next to SR_RANGE_TRAP(), and apply the same + * level of caution. + */ +#define SR_FGF_RANGE(sr, e, g, b, p, f) \ + { \ + .encoding = sr, \ + .end = e, \ + .tc = __FGT(g, b, p, f), \ .line = __LINE__, \ } -#define SR_FGT(sr, g, b, p) SR_FGF(sr, g, b, p, __NO_FGF__) +#define SR_FGF(sr, g, b, p, f) SR_FGF_RANGE(sr, sr, g, b, p, f) +#define SR_FGT(sr, g, b, p) SR_FGF_RANGE(sr, sr, g, b, p, __NO_FGF__) +#define SR_FGT_RANGE(sr, end, g, b, p) \ + SR_FGF_RANGE(sr, end, g, b, p, __NO_FGF__) 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), - SR_FGT(SYS_ERXPFGCTL_EL1, HFGxTR, ERXPFGCTL_EL1, 1), - SR_FGT(SYS_ERXPFGF_EL1, HFGxTR, ERXPFGF_EL1, 1), - SR_FGT(SYS_ERXMISC0_EL1, HFGxTR, ERXMISCn_EL1, 1), - SR_FGT(SYS_ERXMISC1_EL1, HFGxTR, ERXMISCn_EL1, 1), - SR_FGT(SYS_ERXMISC2_EL1, HFGxTR, ERXMISCn_EL1, 1), - SR_FGT(SYS_ERXMISC3_EL1, HFGxTR, ERXMISCn_EL1, 1), - SR_FGT(SYS_ERXSTATUS_EL1, HFGxTR, ERXSTATUS_EL1, 1), - SR_FGT(SYS_ERXCTLR_EL1, HFGxTR, ERXCTLR_EL1, 1), - SR_FGT(SYS_ERXFR_EL1, HFGxTR, ERXFR_EL1, 1), - SR_FGT(SYS_ERRSELR_EL1, HFGxTR, ERRSELR_EL1, 1), - SR_FGT(SYS_ERRIDR_EL1, HFGxTR, ERRIDR_EL1, 1), - SR_FGT(SYS_ICC_IGRPEN0_EL1, HFGxTR, ICC_IGRPENn_EL1, 1), - SR_FGT(SYS_ICC_IGRPEN1_EL1, HFGxTR, ICC_IGRPENn_EL1, 1), - SR_FGT(SYS_VBAR_EL1, HFGxTR, VBAR_EL1, 1), - SR_FGT(SYS_TTBR1_EL1, HFGxTR, TTBR1_EL1, 1), - SR_FGT(SYS_TTBR0_EL1, HFGxTR, TTBR0_EL1, 1), - SR_FGT(SYS_TPIDR_EL0, HFGxTR, TPIDR_EL0, 1), - SR_FGT(SYS_TPIDRRO_EL0, HFGxTR, TPIDRRO_EL0, 1), - SR_FGT(SYS_TPIDR_EL1, HFGxTR, TPIDR_EL1, 1), - SR_FGT(SYS_TCR_EL1, HFGxTR, TCR_EL1, 1), - SR_FGT(SYS_TCR2_EL1, HFGxTR, TCR_EL1, 1), - SR_FGT(SYS_SCXTNUM_EL0, HFGxTR, SCXTNUM_EL0, 1), - SR_FGT(SYS_SCXTNUM_EL1, HFGxTR, SCXTNUM_EL1, 1), - SR_FGT(SYS_SCTLR_EL1, HFGxTR, SCTLR_EL1, 1), - SR_FGT(SYS_REVIDR_EL1, HFGxTR, REVIDR_EL1, 1), - SR_FGT(SYS_PAR_EL1, HFGxTR, PAR_EL1, 1), - SR_FGT(SYS_MPIDR_EL1, HFGxTR, MPIDR_EL1, 1), - SR_FGT(SYS_MIDR_EL1, HFGxTR, MIDR_EL1, 1), - SR_FGT(SYS_MAIR_EL1, HFGxTR, MAIR_EL1, 1), - SR_FGT(SYS_LORSA_EL1, HFGxTR, LORSA_EL1, 1), - SR_FGT(SYS_LORN_EL1, HFGxTR, LORN_EL1, 1), - SR_FGT(SYS_LORID_EL1, HFGxTR, LORID_EL1, 1), - SR_FGT(SYS_LOREA_EL1, HFGxTR, LOREA_EL1, 1), - SR_FGT(SYS_LORC_EL1, HFGxTR, LORC_EL1, 1), - SR_FGT(SYS_ISR_EL1, HFGxTR, ISR_EL1, 1), - SR_FGT(SYS_FAR_EL1, HFGxTR, FAR_EL1, 1), - SR_FGT(SYS_ESR_EL1, HFGxTR, ESR_EL1, 1), - SR_FGT(SYS_DCZID_EL0, HFGxTR, DCZID_EL0, 1), - SR_FGT(SYS_CTR_EL0, HFGxTR, CTR_EL0, 1), - SR_FGT(SYS_CSSELR_EL1, HFGxTR, CSSELR_EL1, 1), - SR_FGT(SYS_CPACR_EL1, HFGxTR, CPACR_EL1, 1), - SR_FGT(SYS_CONTEXTIDR_EL1, HFGxTR, CONTEXTIDR_EL1, 1), - SR_FGT(SYS_CLIDR_EL1, HFGxTR, CLIDR_EL1, 1), - SR_FGT(SYS_CCSIDR_EL1, HFGxTR, CCSIDR_EL1, 1), - SR_FGT(SYS_APIBKEYLO_EL1, HFGxTR, APIBKey, 1), - SR_FGT(SYS_APIBKEYHI_EL1, HFGxTR, APIBKey, 1), - SR_FGT(SYS_APIAKEYLO_EL1, HFGxTR, APIAKey, 1), - SR_FGT(SYS_APIAKEYHI_EL1, HFGxTR, APIAKey, 1), - SR_FGT(SYS_APGAKEYLO_EL1, HFGxTR, APGAKey, 1), - SR_FGT(SYS_APGAKEYHI_EL1, HFGxTR, APGAKey, 1), - SR_FGT(SYS_APDBKEYLO_EL1, HFGxTR, APDBKey, 1), - SR_FGT(SYS_APDBKEYHI_EL1, HFGxTR, APDBKey, 1), - SR_FGT(SYS_APDAKEYLO_EL1, HFGxTR, APDAKey, 1), - SR_FGT(SYS_APDAKEYHI_EL1, HFGxTR, APDAKey, 1), - SR_FGT(SYS_AMAIR_EL1, HFGxTR, AMAIR_EL1, 1), - SR_FGT(SYS_AIDR_EL1, HFGxTR, AIDR_EL1, 1), - SR_FGT(SYS_AFSR1_EL1, HFGxTR, AFSR1_EL1, 1), - SR_FGT(SYS_AFSR0_EL1, HFGxTR, AFSR0_EL1, 1), + SR_FGT(SYS_AMAIR2_EL1, HFGRTR, nAMAIR2_EL1, 0), + SR_FGT(SYS_MAIR2_EL1, HFGRTR, nMAIR2_EL1, 0), + SR_FGT(SYS_S2POR_EL1, HFGRTR, nS2POR_EL1, 0), + SR_FGT(SYS_POR_EL1, HFGRTR, nPOR_EL1, 0), + SR_FGT(SYS_POR_EL0, HFGRTR, nPOR_EL0, 0), + SR_FGT(SYS_PIR_EL1, HFGRTR, nPIR_EL1, 0), + SR_FGT(SYS_PIRE0_EL1, HFGRTR, nPIRE0_EL1, 0), + SR_FGT(SYS_RCWMASK_EL1, HFGRTR, nRCWMASK_EL1, 0), + SR_FGT(SYS_TPIDR2_EL0, HFGRTR, nTPIDR2_EL0, 0), + SR_FGT(SYS_SMPRI_EL1, HFGRTR, nSMPRI_EL1, 0), + SR_FGT(SYS_GCSCR_EL1, HFGRTR, nGCS_EL1, 0), + SR_FGT(SYS_GCSPR_EL1, HFGRTR, nGCS_EL1, 0), + SR_FGT(SYS_GCSCRE0_EL1, HFGRTR, nGCS_EL0, 0), + SR_FGT(SYS_GCSPR_EL0, HFGRTR, nGCS_EL0, 0), + SR_FGT(SYS_ACCDATA_EL1, HFGRTR, nACCDATA_EL1, 0), + SR_FGT(SYS_ERXADDR_EL1, HFGRTR, ERXADDR_EL1, 1), + SR_FGT(SYS_ERXPFGCDN_EL1, HFGRTR, ERXPFGCDN_EL1, 1), + SR_FGT(SYS_ERXPFGCTL_EL1, HFGRTR, ERXPFGCTL_EL1, 1), + SR_FGT(SYS_ERXPFGF_EL1, HFGRTR, ERXPFGF_EL1, 1), + SR_FGT(SYS_ERXMISC0_EL1, HFGRTR, ERXMISCn_EL1, 1), + SR_FGT(SYS_ERXMISC1_EL1, HFGRTR, ERXMISCn_EL1, 1), + SR_FGT(SYS_ERXMISC2_EL1, HFGRTR, ERXMISCn_EL1, 1), + SR_FGT(SYS_ERXMISC3_EL1, HFGRTR, ERXMISCn_EL1, 1), + SR_FGT(SYS_ERXSTATUS_EL1, HFGRTR, ERXSTATUS_EL1, 1), + SR_FGT(SYS_ERXCTLR_EL1, HFGRTR, ERXCTLR_EL1, 1), + SR_FGT(SYS_ERXFR_EL1, HFGRTR, ERXFR_EL1, 1), + SR_FGT(SYS_ERRSELR_EL1, HFGRTR, ERRSELR_EL1, 1), + SR_FGT(SYS_ERRIDR_EL1, HFGRTR, ERRIDR_EL1, 1), + SR_FGT(SYS_ICC_IGRPEN0_EL1, HFGRTR, ICC_IGRPENn_EL1, 1), + SR_FGT(SYS_ICC_IGRPEN1_EL1, HFGRTR, ICC_IGRPENn_EL1, 1), + SR_FGT(SYS_VBAR_EL1, HFGRTR, VBAR_EL1, 1), + SR_FGT(SYS_TTBR1_EL1, HFGRTR, TTBR1_EL1, 1), + SR_FGT(SYS_TTBR0_EL1, HFGRTR, TTBR0_EL1, 1), + SR_FGT(SYS_TPIDR_EL0, HFGRTR, TPIDR_EL0, 1), + SR_FGT(SYS_TPIDRRO_EL0, HFGRTR, TPIDRRO_EL0, 1), + SR_FGT(SYS_TPIDR_EL1, HFGRTR, TPIDR_EL1, 1), + SR_FGT(SYS_TCR_EL1, HFGRTR, TCR_EL1, 1), + SR_FGT(SYS_TCR2_EL1, HFGRTR, TCR_EL1, 1), + SR_FGT(SYS_SCXTNUM_EL0, HFGRTR, SCXTNUM_EL0, 1), + SR_FGT(SYS_SCXTNUM_EL1, HFGRTR, SCXTNUM_EL1, 1), + SR_FGT(SYS_SCTLR_EL1, HFGRTR, SCTLR_EL1, 1), + SR_FGT(SYS_REVIDR_EL1, HFGRTR, REVIDR_EL1, 1), + SR_FGT(SYS_PAR_EL1, HFGRTR, PAR_EL1, 1), + SR_FGT(SYS_MPIDR_EL1, HFGRTR, MPIDR_EL1, 1), + SR_FGT(SYS_MIDR_EL1, HFGRTR, MIDR_EL1, 1), + SR_FGT(SYS_MAIR_EL1, HFGRTR, MAIR_EL1, 1), + SR_FGT(SYS_LORSA_EL1, HFGRTR, LORSA_EL1, 1), + SR_FGT(SYS_LORN_EL1, HFGRTR, LORN_EL1, 1), + SR_FGT(SYS_LORID_EL1, HFGRTR, LORID_EL1, 1), + SR_FGT(SYS_LOREA_EL1, HFGRTR, LOREA_EL1, 1), + SR_FGT(SYS_LORC_EL1, HFGRTR, LORC_EL1, 1), + SR_FGT(SYS_ISR_EL1, HFGRTR, ISR_EL1, 1), + SR_FGT(SYS_FAR_EL1, HFGRTR, FAR_EL1, 1), + SR_FGT(SYS_ESR_EL1, HFGRTR, ESR_EL1, 1), + SR_FGT(SYS_DCZID_EL0, HFGRTR, DCZID_EL0, 1), + SR_FGT(SYS_CTR_EL0, HFGRTR, CTR_EL0, 1), + SR_FGT(SYS_CSSELR_EL1, HFGRTR, CSSELR_EL1, 1), + SR_FGT(SYS_CPACR_EL1, HFGRTR, CPACR_EL1, 1), + SR_FGT(SYS_CONTEXTIDR_EL1, HFGRTR, CONTEXTIDR_EL1, 1), + SR_FGT(SYS_CLIDR_EL1, HFGRTR, CLIDR_EL1, 1), + SR_FGT(SYS_CCSIDR_EL1, HFGRTR, CCSIDR_EL1, 1), + SR_FGT(SYS_APIBKEYLO_EL1, HFGRTR, APIBKey, 1), + SR_FGT(SYS_APIBKEYHI_EL1, HFGRTR, APIBKey, 1), + SR_FGT(SYS_APIAKEYLO_EL1, HFGRTR, APIAKey, 1), + SR_FGT(SYS_APIAKEYHI_EL1, HFGRTR, APIAKey, 1), + SR_FGT(SYS_APGAKEYLO_EL1, HFGRTR, APGAKey, 1), + SR_FGT(SYS_APGAKEYHI_EL1, HFGRTR, APGAKey, 1), + SR_FGT(SYS_APDBKEYLO_EL1, HFGRTR, APDBKey, 1), + SR_FGT(SYS_APDBKEYHI_EL1, HFGRTR, APDBKey, 1), + SR_FGT(SYS_APDAKEYLO_EL1, HFGRTR, APDAKey, 1), + SR_FGT(SYS_APDAKEYHI_EL1, HFGRTR, APDAKey, 1), + SR_FGT(SYS_AMAIR_EL1, HFGRTR, AMAIR_EL1, 1), + SR_FGT(SYS_AIDR_EL1, HFGRTR, AIDR_EL1, 1), + SR_FGT(SYS_AFSR1_EL1, HFGRTR, AFSR1_EL1, 1), + SR_FGT(SYS_AFSR0_EL1, HFGRTR, AFSR0_EL1, 1), + + /* HFGRTR2_EL2, HFGWTR2_EL2 */ + SR_FGT(SYS_ACTLRALIAS_EL1, HFGRTR2, nACTLRALIAS_EL1, 0), + SR_FGT(SYS_ACTLRMASK_EL1, HFGRTR2, nACTLRMASK_EL1, 0), + SR_FGT(SYS_CPACRALIAS_EL1, HFGRTR2, nCPACRALIAS_EL1, 0), + SR_FGT(SYS_CPACRMASK_EL1, HFGRTR2, nCPACRMASK_EL1, 0), + SR_FGT(SYS_PFAR_EL1, HFGRTR2, nPFAR_EL1, 0), + SR_FGT(SYS_RCWSMASK_EL1, HFGRTR2, nRCWSMASK_EL1, 0), + SR_FGT(SYS_SCTLR2ALIAS_EL1, HFGRTR2, nSCTLRALIAS2_EL1, 0), + SR_FGT(SYS_SCTLR2MASK_EL1, HFGRTR2, nSCTLR2MASK_EL1, 0), + SR_FGT(SYS_SCTLRALIAS_EL1, HFGRTR2, nSCTLRALIAS_EL1, 0), + SR_FGT(SYS_SCTLRMASK_EL1, HFGRTR2, nSCTLRMASK_EL1, 0), + SR_FGT(SYS_TCR2ALIAS_EL1, HFGRTR2, nTCR2ALIAS_EL1, 0), + SR_FGT(SYS_TCR2MASK_EL1, HFGRTR2, nTCR2MASK_EL1, 0), + SR_FGT(SYS_TCRALIAS_EL1, HFGRTR2, nTCRALIAS_EL1, 0), + SR_FGT(SYS_TCRMASK_EL1, HFGRTR2, nTCRMASK_EL1, 0), + SR_FGT(SYS_ERXGSR_EL1, HFGRTR2, nERXGSR_EL1, 0), + /* HFGITR_EL2 */ SR_FGT(OP_AT_S1E1A, HFGITR, ATS1E1A, 1), SR_FGT(OP_COSP_RCTX, HFGITR, COSPRCTX, 1), @@ -1480,6 +1515,11 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { SR_FGT(SYS_IC_IVAU, HFGITR, ICIVAU, 1), SR_FGT(SYS_IC_IALLU, HFGITR, ICIALLU, 1), SR_FGT(SYS_IC_IALLUIS, HFGITR, ICIALLUIS, 1), + + /* HFGITR2_EL2 */ + SR_FGT(SYS_DC_CIGDVAPS, HFGITR2, nDCCIVAPS, 0), + SR_FGT(SYS_DC_CIVAPS, HFGITR2, nDCCIVAPS, 0), + /* HDFGRTR_EL2 */ SR_FGT(SYS_PMBIDR_EL1, HDFGRTR, PMBIDR_EL1, 1), SR_FGT(SYS_PMSNEVFR_EL1, HDFGRTR, nPMSNEVFR_EL1, 0), @@ -1789,68 +1829,12 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { SR_FGT(SYS_PMCNTENSET_EL0, HDFGRTR, PMCNTEN, 1), SR_FGT(SYS_PMCCNTR_EL0, HDFGRTR, PMCCNTR_EL0, 1), SR_FGT(SYS_PMCCFILTR_EL0, HDFGRTR, PMCCFILTR_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(0), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(1), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(2), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(3), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(4), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(5), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(6), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(7), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(8), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(9), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(10), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(11), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(12), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(13), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(14), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(15), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(16), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(17), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(18), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(19), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(20), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(21), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(22), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(23), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(24), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(25), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(26), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(27), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(28), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(29), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVTYPERn_EL0(30), HDFGRTR, PMEVTYPERn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(0), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(1), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(2), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(3), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(4), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(5), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(6), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(7), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(8), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(9), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(10), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(11), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(12), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(13), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(14), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(15), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(16), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(17), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(18), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(19), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(20), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(21), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(22), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(23), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(24), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(25), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(26), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(27), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(28), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(29), HDFGRTR, PMEVCNTRn_EL0, 1), - SR_FGT(SYS_PMEVCNTRn_EL0(30), HDFGRTR, PMEVCNTRn_EL0, 1), + SR_FGT_RANGE(SYS_PMEVTYPERn_EL0(0), + SYS_PMEVTYPERn_EL0(30), + HDFGRTR, PMEVTYPERn_EL0, 1), + SR_FGT_RANGE(SYS_PMEVCNTRn_EL0(0), + SYS_PMEVCNTRn_EL0(30), + HDFGRTR, PMEVCNTRn_EL0, 1), SR_FGT(SYS_OSDLR_EL1, HDFGRTR, OSDLR_EL1, 1), SR_FGT(SYS_OSECCR_EL1, HDFGRTR, OSECCR_EL1, 1), SR_FGT(SYS_OSLSR_EL1, HDFGRTR, OSLSR_EL1, 1), @@ -1928,6 +1912,59 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { SR_FGT(SYS_DBGBCRn_EL1(13), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(14), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(15), HDFGRTR, DBGBCRn_EL1, 1), + + /* HDFGRTR2_EL2 */ + SR_FGT(SYS_MDSELR_EL1, HDFGRTR2, nMDSELR_EL1, 0), + SR_FGT(SYS_MDSTEPOP_EL1, HDFGRTR2, nMDSTEPOP_EL1, 0), + SR_FGT(SYS_PMCCNTSVR_EL1, HDFGRTR2, nPMSSDATA, 0), + SR_FGT_RANGE(SYS_PMEVCNTSVRn_EL1(0), + SYS_PMEVCNTSVRn_EL1(30), + HDFGRTR2, nPMSSDATA, 0), + SR_FGT(SYS_PMICNTSVR_EL1, HDFGRTR2, nPMSSDATA, 0), + SR_FGT(SYS_PMECR_EL1, HDFGRTR2, nPMECR_EL1, 0), + SR_FGT(SYS_PMIAR_EL1, HDFGRTR2, nPMIAR_EL1, 0), + SR_FGT(SYS_PMICFILTR_EL0, HDFGRTR2, nPMICFILTR_EL0, 0), + SR_FGT(SYS_PMICNTR_EL0, HDFGRTR2, nPMICNTR_EL0, 0), + SR_FGT(SYS_PMSSCR_EL1, HDFGRTR2, nPMSSCR_EL1, 0), + SR_FGT(SYS_PMUACR_EL1, HDFGRTR2, nPMUACR_EL1, 0), + SR_FGT(SYS_SPMACCESSR_EL1, HDFGRTR2, nSPMACCESSR_EL1, 0), + SR_FGT(SYS_SPMCFGR_EL1, HDFGRTR2, nSPMID, 0), + SR_FGT(SYS_SPMDEVARCH_EL1, HDFGRTR2, nSPMID, 0), + SR_FGT(SYS_SPMCGCRn_EL1(0), HDFGRTR2, nSPMID, 0), + SR_FGT(SYS_SPMCGCRn_EL1(1), HDFGRTR2, nSPMID, 0), + SR_FGT(SYS_SPMIIDR_EL1, HDFGRTR2, nSPMID, 0), + SR_FGT(SYS_SPMCNTENCLR_EL0, HDFGRTR2, nSPMCNTEN, 0), + SR_FGT(SYS_SPMCNTENSET_EL0, HDFGRTR2, nSPMCNTEN, 0), + SR_FGT(SYS_SPMCR_EL0, HDFGRTR2, nSPMCR_EL0, 0), + SR_FGT(SYS_SPMDEVAFF_EL1, HDFGRTR2, nSPMDEVAFF_EL1, 0), + /* + * We have up to 64 of these registers in ranges of 16, banked via + * SPMSELR_EL0.BANK. We're only concerned with the accessors here, + * not the architectural registers. + */ + SR_FGT_RANGE(SYS_SPMEVCNTRn_EL0(0), + SYS_SPMEVCNTRn_EL0(15), + HDFGRTR2, nSPMEVCNTRn_EL0, 0), + SR_FGT_RANGE(SYS_SPMEVFILT2Rn_EL0(0), + SYS_SPMEVFILT2Rn_EL0(15), + HDFGRTR2, nSPMEVTYPERn_EL0, 0), + SR_FGT_RANGE(SYS_SPMEVFILTRn_EL0(0), + SYS_SPMEVFILTRn_EL0(15), + HDFGRTR2, nSPMEVTYPERn_EL0, 0), + SR_FGT_RANGE(SYS_SPMEVTYPERn_EL0(0), + SYS_SPMEVTYPERn_EL0(15), + HDFGRTR2, nSPMEVTYPERn_EL0, 0), + SR_FGT(SYS_SPMINTENCLR_EL1, HDFGRTR2, nSPMINTEN, 0), + SR_FGT(SYS_SPMINTENSET_EL1, HDFGRTR2, nSPMINTEN, 0), + SR_FGT(SYS_SPMOVSCLR_EL0, HDFGRTR2, nSPMOVS, 0), + SR_FGT(SYS_SPMOVSSET_EL0, HDFGRTR2, nSPMOVS, 0), + SR_FGT(SYS_SPMSCR_EL1, HDFGRTR2, nSPMSCR_EL1, 0), + SR_FGT(SYS_SPMSELR_EL0, HDFGRTR2, nSPMSELR_EL0, 0), + SR_FGT(SYS_TRCITECR_EL1, HDFGRTR2, nTRCITECR_EL1, 0), + SR_FGT(SYS_PMBMAR_EL1, HDFGRTR2, nPMBMAR_EL1, 0), + SR_FGT(SYS_PMSDSFR_EL1, HDFGRTR2, nPMSDSFR_EL1, 0), + SR_FGT(SYS_TRBMPAM_EL1, HDFGRTR2, nTRBMPAM_EL1, 0), + /* * HDFGWTR_EL2 * @@ -1938,12 +1975,19 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { * read-side mappings, and only the write-side mappings that * differ from the read side, and the trap handler will pick * the correct shadow register based on the access type. + * + * Same model applies to the FEAT_FGT2 registers. */ SR_FGT(SYS_TRFCR_EL1, HDFGWTR, TRFCR_EL1, 1), SR_FGT(SYS_TRCOSLAR, HDFGWTR, TRCOSLAR, 1), 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), + + /* HDFGWTR2_EL2 */ + SR_FGT(SYS_PMZR_EL0, HDFGWTR2, nPMZR_EL0, 0), + SR_FGT(SYS_SPMZR_EL0, HDFGWTR2, nSPMEVCNTRn_EL0, 0), + /* * HAFGRTR_EL2 */ @@ -1989,6 +2033,20 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { SR_FGT(SYS_AMEVCNTR0_EL0(0), HAFGRTR, AMEVCNTR00_EL0, 1), }; +/* + * Additional FGTs that do not fire with ESR_EL2.EC==0x18. This table + * isn't used for exception routing, but only as a promise that the + * trap is handled somewhere else. + */ +static const union trap_config non_0x18_fgt[] __initconst = { + FGT(HFGITR, PSBCSYNC, 1), + FGT(HFGITR, nGCSSTR_EL1, 0), + FGT(HFGITR, SVC_EL1, 1), + FGT(HFGITR, SVC_EL0, 1), + FGT(HFGITR, ERET, 1), + FGT(HFGITR2, TSBCSYNC, 1), +}; + static union trap_config get_trap_config(u32 sysreg) { return (union trap_config) { @@ -2033,6 +2091,130 @@ static u32 encoding_next(u32 encoding) return sys_reg(op0 + 1, 0, 0, 0, 0); } +#define FGT_MASKS(__n, __m) \ + struct fgt_masks __n = { .str = #__m, .res0 = __m, } + +FGT_MASKS(hfgrtr_masks, HFGRTR_EL2_RES0); +FGT_MASKS(hfgwtr_masks, HFGWTR_EL2_RES0); +FGT_MASKS(hfgitr_masks, HFGITR_EL2_RES0); +FGT_MASKS(hdfgrtr_masks, HDFGRTR_EL2_RES0); +FGT_MASKS(hdfgwtr_masks, HDFGWTR_EL2_RES0); +FGT_MASKS(hafgrtr_masks, HAFGRTR_EL2_RES0); +FGT_MASKS(hfgrtr2_masks, HFGRTR2_EL2_RES0); +FGT_MASKS(hfgwtr2_masks, HFGWTR2_EL2_RES0); +FGT_MASKS(hfgitr2_masks, HFGITR2_EL2_RES0); +FGT_MASKS(hdfgrtr2_masks, HDFGRTR2_EL2_RES0); +FGT_MASKS(hdfgwtr2_masks, HDFGWTR2_EL2_RES0); + +static __init bool aggregate_fgt(union trap_config tc) +{ + struct fgt_masks *rmasks, *wmasks; + + switch (tc.fgt) { + case HFGRTR_GROUP: + rmasks = &hfgrtr_masks; + wmasks = &hfgwtr_masks; + break; + case HDFGRTR_GROUP: + rmasks = &hdfgrtr_masks; + wmasks = &hdfgwtr_masks; + break; + case HAFGRTR_GROUP: + rmasks = &hafgrtr_masks; + wmasks = NULL; + break; + case HFGITR_GROUP: + rmasks = &hfgitr_masks; + wmasks = NULL; + break; + case HFGRTR2_GROUP: + rmasks = &hfgrtr2_masks; + wmasks = &hfgwtr2_masks; + break; + case HDFGRTR2_GROUP: + rmasks = &hdfgrtr2_masks; + wmasks = &hdfgwtr2_masks; + break; + case HFGITR2_GROUP: + rmasks = &hfgitr2_masks; + wmasks = NULL; + break; + } + + /* + * A bit can be reserved in either the R or W register, but + * not both. + */ + if ((BIT(tc.bit) & rmasks->res0) && + (!wmasks || (BIT(tc.bit) & wmasks->res0))) + return false; + + if (tc.pol) + rmasks->mask |= BIT(tc.bit) & ~rmasks->res0; + else + rmasks->nmask |= BIT(tc.bit) & ~rmasks->res0; + + if (wmasks) { + if (tc.pol) + wmasks->mask |= BIT(tc.bit) & ~wmasks->res0; + else + wmasks->nmask |= BIT(tc.bit) & ~wmasks->res0; + } + + return true; +} + +static __init int check_fgt_masks(struct fgt_masks *masks) +{ + unsigned long duplicate = masks->mask & masks->nmask; + u64 res0 = masks->res0; + int ret = 0; + + if (duplicate) { + int i; + + for_each_set_bit(i, &duplicate, 64) { + kvm_err("%s[%d] bit has both polarities\n", + masks->str, i); + } + + ret = -EINVAL; + } + + masks->res0 = ~(masks->mask | masks->nmask); + if (masks->res0 != res0) + kvm_info("Implicit %s = %016llx, expecting %016llx\n", + masks->str, masks->res0, res0); + + return ret; +} + +static __init int check_all_fgt_masks(int ret) +{ + static struct fgt_masks * const masks[] __initconst = { + &hfgrtr_masks, + &hfgwtr_masks, + &hfgitr_masks, + &hdfgrtr_masks, + &hdfgwtr_masks, + &hafgrtr_masks, + &hfgrtr2_masks, + &hfgwtr2_masks, + &hfgitr2_masks, + &hdfgrtr2_masks, + &hdfgwtr2_masks, + }; + int err = 0; + + for (int i = 0; i < ARRAY_SIZE(masks); i++) + err |= check_fgt_masks(masks[i]); + + return ret ?: err; +} + +#define for_each_encoding_in(__x, __s, __e) \ + for (u32 __x = __s; __x <= __e; __x = encoding_next(__x)) + int __init populate_nv_trap_config(void) { int ret = 0; @@ -2041,6 +2223,7 @@ int __init populate_nv_trap_config(void) BUILD_BUG_ON(__NR_CGT_GROUP_IDS__ > BIT(TC_CGT_BITS)); BUILD_BUG_ON(__NR_FGT_GROUP_IDS__ > BIT(TC_FGT_BITS)); BUILD_BUG_ON(__NR_FG_FILTER_IDS__ > BIT(TC_FGF_BITS)); + BUILD_BUG_ON(__HCRX_EL2_MASK & __HCRX_EL2_nMASK); for (int i = 0; i < ARRAY_SIZE(encoding_to_cgt); i++) { const struct encoding_to_trap_config *cgt = &encoding_to_cgt[i]; @@ -2051,7 +2234,7 @@ int __init populate_nv_trap_config(void) ret = -EINVAL; } - for (u32 enc = cgt->encoding; enc <= cgt->end; enc = encoding_next(enc)) { + for_each_encoding_in(enc, cgt->encoding, cgt->end) { prev = xa_store(&sr_forward_xa, enc, xa_mk_value(cgt->tc.val), GFP_KERNEL); if (prev && !xa_is_err(prev)) { @@ -2066,6 +2249,10 @@ int __init populate_nv_trap_config(void) } } + if (__HCRX_EL2_RES0 != HCRX_EL2_RES0) + kvm_info("Sanitised HCR_EL2_RES0 = %016llx, expecting %016llx\n", + __HCRX_EL2_RES0, HCRX_EL2_RES0); + kvm_info("nv: %ld coarse grained trap handlers\n", ARRAY_SIZE(encoding_to_cgt)); @@ -2082,23 +2269,39 @@ int __init populate_nv_trap_config(void) print_nv_trap_error(fgt, "Invalid FGT", ret); } - tc = get_trap_config(fgt->encoding); + for_each_encoding_in(enc, fgt->encoding, fgt->end) { + tc = get_trap_config(enc); - if (tc.fgt) { - ret = -EINVAL; - print_nv_trap_error(fgt, "Duplicate FGT", ret); - } + if (tc.fgt) { + ret = -EINVAL; + print_nv_trap_error(fgt, "Duplicate FGT", ret); + } + + tc.val |= fgt->tc.val; + prev = xa_store(&sr_forward_xa, enc, + xa_mk_value(tc.val), GFP_KERNEL); + + if (xa_is_err(prev)) { + ret = xa_err(prev); + print_nv_trap_error(fgt, "Failed FGT insertion", ret); + } - tc.val |= fgt->tc.val; - prev = xa_store(&sr_forward_xa, fgt->encoding, - xa_mk_value(tc.val), GFP_KERNEL); + if (!aggregate_fgt(tc)) { + ret = -EINVAL; + print_nv_trap_error(fgt, "FGT bit is reserved", ret); + } + } + } - if (xa_is_err(prev)) { - ret = xa_err(prev); - print_nv_trap_error(fgt, "Failed FGT insertion", ret); + for (int i = 0; i < ARRAY_SIZE(non_0x18_fgt); i++) { + if (!aggregate_fgt(non_0x18_fgt[i])) { + ret = -EINVAL; + kvm_err("non_0x18_fgt[%d] is reserved\n", i); } } + ret = check_all_fgt_masks(ret); + kvm_info("nv: %ld fine grained trap handlers\n", ARRAY_SIZE(encoding_to_fgt)); @@ -2215,11 +2418,11 @@ static u64 kvm_get_sysreg_res0(struct kvm *kvm, enum vcpu_sysreg sr) return masks->mask[sr - __VNCR_START__].res0; } -static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read, - u64 val, const union trap_config tc) +static bool check_fgt_bit(struct kvm_vcpu *vcpu, enum vcpu_sysreg sr, + const union trap_config tc) { struct kvm *kvm = vcpu->kvm; - enum vcpu_sysreg sr; + u64 val; /* * KVM doesn't know about any FGTs that apply to the host, and hopefully @@ -2228,6 +2431,8 @@ static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read, if (is_hyp_ctxt(vcpu)) return false; + val = __vcpu_sys_reg(vcpu, sr); + if (tc.pol) return (val & BIT(tc.bit)); @@ -2242,38 +2447,17 @@ static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read, if (val & BIT(tc.bit)) return false; - switch ((enum fgt_group_id)tc.fgt) { - case HFGxTR_GROUP: - sr = is_read ? HFGRTR_EL2 : HFGWTR_EL2; - break; - - case HDFGRTR_GROUP: - sr = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2; - break; - - case HAFGRTR_GROUP: - sr = HAFGRTR_EL2; - break; - - case HFGITR_GROUP: - sr = HFGITR_EL2; - break; - - default: - WARN_ONCE(1, "Unhandled FGT group"); - return false; - } - return !(kvm_get_sysreg_res0(kvm, sr) & BIT(tc.bit)); } bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index) { + enum vcpu_sysreg fgtreg; union trap_config tc; enum trap_behaviour b; bool is_read; u32 sysreg; - u64 esr, val; + u64 esr; esr = kvm_vcpu_get_esr(vcpu); sysreg = esr_sys64_to_sysreg(esr); @@ -2319,26 +2503,20 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index) case __NO_FGT_GROUP__: break; - case HFGxTR_GROUP: - if (is_read) - val = __vcpu_sys_reg(vcpu, HFGRTR_EL2); - else - val = __vcpu_sys_reg(vcpu, HFGWTR_EL2); + case HFGRTR_GROUP: + fgtreg = is_read ? HFGRTR_EL2 : HFGWTR_EL2; break; case HDFGRTR_GROUP: - if (is_read) - val = __vcpu_sys_reg(vcpu, HDFGRTR_EL2); - else - val = __vcpu_sys_reg(vcpu, HDFGWTR_EL2); + fgtreg = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2; break; case HAFGRTR_GROUP: - val = __vcpu_sys_reg(vcpu, HAFGRTR_EL2); + fgtreg = HAFGRTR_EL2; break; case HFGITR_GROUP: - val = __vcpu_sys_reg(vcpu, HFGITR_EL2); + fgtreg = HFGITR_EL2; switch (tc.fgf) { u64 tmp; @@ -2352,13 +2530,26 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index) } break; - case __NR_FGT_GROUP_IDS__: + case HFGRTR2_GROUP: + fgtreg = is_read ? HFGRTR2_EL2 : HFGWTR2_EL2; + break; + + case HDFGRTR2_GROUP: + fgtreg = is_read ? HDFGRTR2_EL2 : HDFGWTR2_EL2; + break; + + case HFGITR2_GROUP: + fgtreg = HFGITR2_EL2; + break; + + default: /* Something is really wrong, bail out */ - WARN_ONCE(1, "__NR_FGT_GROUP_IDS__"); + WARN_ONCE(1, "Bad FGT group (encoding %08x, config %016llx)\n", + sysreg, tc.val); goto local; } - if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, is_read, val, tc)) + if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, fgtreg, tc)) goto inject; b = compute_trap_behaviour(vcpu, tc); @@ -2471,13 +2662,6 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) { u64 spsr, elr, esr; - /* - * Forward this trap to the virtual EL2 if the virtual - * HCR_EL2.NV bit is set and this is coming from !EL2. - */ - if (forward_hcr_traps(vcpu, HCR_NV)) - return; - spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2); spsr = kvm_check_illegal_exception_return(vcpu, spsr); @@ -2503,6 +2687,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) } preempt_disable(); + vcpu_set_flag(vcpu, IN_NESTED_ERET); kvm_arch_vcpu_put(vcpu); if (!esr_iss_is_eretax(esr)) @@ -2514,9 +2699,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) *vcpu_cpsr(vcpu) = spsr; kvm_arch_vcpu_load(vcpu, smp_processor_id()); + vcpu_clear_flag(vcpu, IN_NESTED_ERET); preempt_enable(); - kvm_pmu_nested_transition(vcpu); + if (kvm_vcpu_has_pmu(vcpu)) + kvm_pmu_nested_transition(vcpu); } static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2, @@ -2599,7 +2786,8 @@ static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2, kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); - kvm_pmu_nested_transition(vcpu); + if (kvm_vcpu_has_pmu(vcpu)) + kvm_pmu_nested_transition(vcpu); return 1; } diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 512d152233ff..453266c96481 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -10,6 +10,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <linux/ubsan.h> #include <asm/esr.h> #include <asm/exception.h> @@ -129,8 +130,12 @@ static int kvm_handle_fpasimd(struct kvm_vcpu *vcpu) static int kvm_handle_wfx(struct kvm_vcpu *vcpu) { u64 esr = kvm_vcpu_get_esr(vcpu); + bool is_wfe = !!(esr & ESR_ELx_WFx_ISS_WFE); - if (esr & ESR_ELx_WFx_ISS_WFE) { + if (guest_hyp_wfx_traps_enabled(vcpu)) + return kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); + + if (is_wfe) { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true); vcpu->stat.wfe_exit_stat++; } else { @@ -294,6 +299,81 @@ static int handle_svc(struct kvm_vcpu *vcpu) return 1; } +static int kvm_handle_gcs(struct kvm_vcpu *vcpu) +{ + /* We don't expect GCS, so treat it with contempt */ + if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, GCS, IMP)) + WARN_ON_ONCE(1); + + kvm_inject_undefined(vcpu); + return 1; +} + +static int handle_other(struct kvm_vcpu *vcpu) +{ + bool is_l2 = vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu); + u64 hcrx = __vcpu_sys_reg(vcpu, HCRX_EL2); + u64 esr = kvm_vcpu_get_esr(vcpu); + u64 iss = ESR_ELx_ISS(esr); + struct kvm *kvm = vcpu->kvm; + bool allowed, fwd = false; + + /* + * We only trap for two reasons: + * + * - the feature is disabled, and the only outcome is to + * generate an UNDEF. + * + * - the feature is enabled, but a NV guest wants to trap the + * feature used by its L2 guest. We forward the exception in + * this case. + * + * What we don't expect is to end-up here if the guest is + * expected be be able to directly use the feature, hence the + * WARN_ON below. + */ + switch (iss) { + case ESR_ELx_ISS_OTHER_ST64BV: + allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V); + if (is_l2) + fwd = !(hcrx & HCRX_EL2_EnASR); + break; + case ESR_ELx_ISS_OTHER_ST64BV0: + allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA); + if (is_l2) + fwd = !(hcrx & HCRX_EL2_EnAS0); + break; + case ESR_ELx_ISS_OTHER_LDST64B: + allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64); + if (is_l2) + fwd = !(hcrx & HCRX_EL2_EnALS); + break; + case ESR_ELx_ISS_OTHER_TSBCSYNC: + allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, TRBE_V1P1); + if (is_l2) + fwd = (__vcpu_sys_reg(vcpu, HFGITR2_EL2) & HFGITR2_EL2_TSBCSYNC); + break; + case ESR_ELx_ISS_OTHER_PSBCSYNC: + allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P5); + if (is_l2) + fwd = (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_PSBCSYNC); + break; + default: + /* Clearly, we're missing something. */ + WARN_ON_ONCE(1); + allowed = false; + } + + WARN_ON_ONCE(allowed && !fwd); + + if (allowed && fwd) + kvm_inject_nested_sync(vcpu, esr); + else + kvm_inject_undefined(vcpu); + + return 1; +} + static exit_handle_fn arm_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec, [ESR_ELx_EC_WFx] = kvm_handle_wfx, @@ -303,6 +383,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_CP14_LS] = kvm_handle_cp14_load_store, [ESR_ELx_EC_CP10_ID] = kvm_handle_cp10_id, [ESR_ELx_EC_CP14_64] = kvm_handle_cp14_64, + [ESR_ELx_EC_OTHER] = handle_other, [ESR_ELx_EC_HVC32] = handle_hvc, [ESR_ELx_EC_SMC32] = handle_smc, [ESR_ELx_EC_HVC64] = handle_hvc, @@ -313,6 +394,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_ERET] = kvm_handle_eret, [ESR_ELx_EC_IABT_LOW] = kvm_handle_guest_abort, [ESR_ELx_EC_DABT_LOW] = kvm_handle_guest_abort, + [ESR_ELx_EC_DABT_CUR] = kvm_handle_vncr_abort, [ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug, [ESR_ELx_EC_WATCHPT_LOW]= kvm_handle_guest_debug, [ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug, @@ -320,6 +402,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_BRK64] = kvm_handle_guest_debug, [ESR_ELx_EC_FP_ASIMD] = kvm_handle_fpasimd, [ESR_ELx_EC_PAC] = kvm_handle_ptrauth, + [ESR_ELx_EC_GCS] = kvm_handle_gcs, }; static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) @@ -470,6 +553,11 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, print_nvhe_hyp_panic("BUG", panic_addr); } else if (IS_ENABLED(CONFIG_CFI_CLANG) && esr_is_cfi_brk(esr)) { kvm_nvhe_report_cfi_failure(panic_addr); + } else if (IS_ENABLED(CONFIG_UBSAN_KVM_EL2) && + ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 && + esr_is_ubsan_brk(esr)) { + print_nvhe_hyp_panic(report_ubsan_failure(esr & UBSAN_BRK_MASK), + panic_addr); } else { print_nvhe_hyp_panic("panic", panic_addr); } diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h index 17df94570f03..fc573fc767b0 100644 --- a/arch/arm64/kvm/hyp/include/hyp/fault.h +++ b/arch/arm64/kvm/hyp/include/hyp/fault.h @@ -12,6 +12,16 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> +static inline bool __fault_safe_to_translate(u64 esr) +{ + u64 fsc = esr & ESR_ELx_FSC; + + if (esr_fsc_is_sea_ttw(esr) || esr_fsc_is_secc_ttw(esr)) + return false; + + return !(fsc == ESR_ELx_FSC_EXTABT && (esr & ESR_ELx_FnV)); +} + static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) { int ret; @@ -44,34 +54,50 @@ static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) return true; } -static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) +/* + * Checks for the conditions when HPFAR_EL2 is written, per ARM ARM R_FKLWR. + */ +static inline bool __hpfar_valid(u64 esr) { - u64 hpfar, far; - - far = read_sysreg_el2(SYS_FAR); - /* - * The HPFAR can be invalid if the stage 2 fault did not - * happen during a stage 1 page table walk (the ESR_EL2.S1PTW - * bit is clear) and one of the two following cases are true: - * 1. The fault was due to a permission fault - * 2. The processor carries errata 834220 + * CPUs affected by ARM erratum #834220 may incorrectly report a + * stage-2 translation fault when a stage-1 permission fault occurs. * - * Therefore, for all non S1PTW faults where we either have a - * permission fault or the errata workaround is enabled, we - * resolve the IPA using the AT instruction. + * Re-walk the page tables to determine if a stage-1 fault actually + * occurred. */ - if (!(esr & ESR_ELx_S1PTW) && - (cpus_have_final_cap(ARM64_WORKAROUND_834220) || - esr_fsc_is_permission_fault(esr))) { - if (!__translate_far_to_hpfar(far, &hpfar)) - return false; - } else { + if (cpus_have_final_cap(ARM64_WORKAROUND_834220) && + esr_fsc_is_translation_fault(esr)) + return false; + + if (esr_fsc_is_translation_fault(esr) || esr_fsc_is_access_flag_fault(esr)) + return true; + + if ((esr & ESR_ELx_S1PTW) && esr_fsc_is_permission_fault(esr)) + return true; + + return esr_fsc_is_addr_sz_fault(esr); +} + +static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) +{ + u64 hpfar; + + fault->far_el2 = read_sysreg_el2(SYS_FAR); + fault->hpfar_el2 = 0; + + if (__hpfar_valid(esr)) hpfar = read_sysreg(hpfar_el2); - } + else if (unlikely(!__fault_safe_to_translate(esr))) + return true; + else if (!__translate_far_to_hpfar(fault->far_el2, &hpfar)) + return false; - fault->far_el2 = far; - fault->hpfar_el2 = hpfar; + /* + * Hijack HPFAR_EL2.NS (RES0 in Non-secure) to indicate a valid + * HPFAR value. + */ + fault->hpfar_el2 = hpfar | HPFAR_EL2_NS; return true; } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 23bbe28eaaf9..bb9f2eecfb67 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -65,12 +65,56 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) } } +#define reg_to_fgt_masks(reg) \ + ({ \ + struct fgt_masks *m; \ + switch(reg) { \ + case HFGRTR_EL2: \ + m = &hfgrtr_masks; \ + break; \ + case HFGWTR_EL2: \ + m = &hfgwtr_masks; \ + break; \ + case HFGITR_EL2: \ + m = &hfgitr_masks; \ + break; \ + case HDFGRTR_EL2: \ + m = &hdfgrtr_masks; \ + break; \ + case HDFGWTR_EL2: \ + m = &hdfgwtr_masks; \ + break; \ + case HAFGRTR_EL2: \ + m = &hafgrtr_masks; \ + break; \ + case HFGRTR2_EL2: \ + m = &hfgrtr2_masks; \ + break; \ + case HFGWTR2_EL2: \ + m = &hfgwtr2_masks; \ + break; \ + case HFGITR2_EL2: \ + m = &hfgitr2_masks; \ + break; \ + case HDFGRTR2_EL2: \ + m = &hdfgrtr2_masks; \ + break; \ + case HDFGWTR2_EL2: \ + m = &hdfgwtr2_masks; \ + break; \ + default: \ + BUILD_BUG_ON(1); \ + } \ + \ + m; \ + }) + #define compute_clr_set(vcpu, reg, clr, set) \ do { \ - u64 hfg; \ - hfg = __vcpu_sys_reg(vcpu, reg) & ~__ ## reg ## _RES0; \ - set |= hfg & __ ## reg ## _MASK; \ - clr |= ~hfg & __ ## reg ## _nMASK; \ + u64 hfg = __vcpu_sys_reg(vcpu, reg); \ + struct fgt_masks *m = reg_to_fgt_masks(reg); \ + set |= hfg & m->mask; \ + clr |= ~hfg & m->nmask; \ } while(0) #define reg_to_fgt_group_id(reg) \ @@ -79,7 +123,7 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) switch(reg) { \ case HFGRTR_EL2: \ case HFGWTR_EL2: \ - id = HFGxTR_GROUP; \ + id = HFGRTR_GROUP; \ break; \ case HFGITR_EL2: \ id = HFGITR_GROUP; \ @@ -91,6 +135,17 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) case HAFGRTR_EL2: \ id = HAFGRTR_GROUP; \ break; \ + case HFGRTR2_EL2: \ + case HFGWTR2_EL2: \ + id = HFGRTR2_GROUP; \ + break; \ + case HFGITR2_EL2: \ + id = HFGITR2_GROUP; \ + break; \ + case HDFGRTR2_EL2: \ + case HDFGWTR2_EL2: \ + id = HDFGRTR2_GROUP; \ + break; \ default: \ BUILD_BUG_ON(1); \ } \ @@ -101,13 +156,16 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) #define compute_undef_clr_set(vcpu, kvm, reg, clr, set) \ do { \ u64 hfg = kvm->arch.fgu[reg_to_fgt_group_id(reg)]; \ - set |= hfg & __ ## reg ## _MASK; \ - clr |= hfg & __ ## reg ## _nMASK; \ + struct fgt_masks *m = reg_to_fgt_masks(reg); \ + set |= hfg & m->mask; \ + clr |= hfg & m->nmask; \ } while(0) #define update_fgt_traps_cs(hctxt, vcpu, kvm, reg, clr, set) \ do { \ - u64 c = 0, s = 0; \ + struct fgt_masks *m = reg_to_fgt_masks(reg); \ + u64 c = clr, s = set; \ + u64 val; \ \ ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg); \ if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) \ @@ -115,30 +173,15 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) \ compute_undef_clr_set(vcpu, kvm, reg, c, s); \ \ - s |= set; \ - c |= clr; \ - if (c || s) { \ - u64 val = __ ## reg ## _nMASK; \ - val |= s; \ - val &= ~c; \ - write_sysreg_s(val, SYS_ ## reg); \ - } \ + val = m->nmask; \ + val |= s; \ + val &= ~c; \ + write_sysreg_s(val, SYS_ ## reg); \ } while(0) #define update_fgt_traps(hctxt, vcpu, kvm, reg) \ update_fgt_traps_cs(hctxt, vcpu, kvm, 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); @@ -152,56 +195,60 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu) struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); struct kvm *kvm = kern_hyp_va(vcpu->kvm); - 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; update_fgt_traps(hctxt, vcpu, kvm, HFGRTR_EL2); update_fgt_traps_cs(hctxt, vcpu, kvm, HFGWTR_EL2, 0, cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38) ? - HFGxTR_EL2_TCR_EL1_MASK : 0); + HFGWTR_EL2_TCR_EL1_MASK : 0); update_fgt_traps(hctxt, vcpu, kvm, HFGITR_EL2); update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR_EL2); update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR_EL2); if (cpu_has_amu()) update_fgt_traps(hctxt, vcpu, kvm, HAFGRTR_EL2); + + if (!cpus_have_final_cap(ARM64_HAS_FGT2)) + return; + + update_fgt_traps(hctxt, vcpu, kvm, HFGRTR2_EL2); + update_fgt_traps(hctxt, vcpu, kvm, HFGWTR2_EL2); + update_fgt_traps(hctxt, vcpu, kvm, HFGITR2_EL2); + update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR2_EL2); + update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR2_EL2); } -#define __deactivate_fgt(htcxt, vcpu, kvm, reg) \ +#define __deactivate_fgt(htcxt, vcpu, reg) \ do { \ - if ((vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) || \ - kvm->arch.fgu[reg_to_fgt_group_id(reg)]) \ - write_sysreg_s(ctxt_sys_reg(hctxt, reg), \ - SYS_ ## reg); \ + write_sysreg_s(ctxt_sys_reg(hctxt, reg), \ + SYS_ ## reg); \ } while(0) static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); - struct kvm *kvm = kern_hyp_va(vcpu->kvm); if (!cpus_have_final_cap(ARM64_HAS_FGT)) return; - __deactivate_fgt(hctxt, vcpu, kvm, HFGRTR_EL2); - if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38)) - write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2); - else - __deactivate_fgt(hctxt, vcpu, kvm, HFGWTR_EL2); - __deactivate_fgt(hctxt, vcpu, kvm, HFGITR_EL2); - __deactivate_fgt(hctxt, vcpu, kvm, HDFGRTR_EL2); - __deactivate_fgt(hctxt, vcpu, kvm, HDFGWTR_EL2); + __deactivate_fgt(hctxt, vcpu, HFGRTR_EL2); + __deactivate_fgt(hctxt, vcpu, HFGWTR_EL2); + __deactivate_fgt(hctxt, vcpu, HFGITR_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGRTR_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGWTR_EL2); if (cpu_has_amu()) - __deactivate_fgt(hctxt, vcpu, kvm, HAFGRTR_EL2); + __deactivate_fgt(hctxt, vcpu, HAFGRTR_EL2); + + if (!cpus_have_final_cap(ARM64_HAS_FGT2)) + return; + + __deactivate_fgt(hctxt, vcpu, HFGRTR2_EL2); + __deactivate_fgt(hctxt, vcpu, HFGWTR2_EL2); + __deactivate_fgt(hctxt, vcpu, HFGITR2_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGRTR2_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGWTR2_EL2); } static inline void __activate_traps_mpam(struct kvm_vcpu *vcpu) @@ -235,6 +282,8 @@ static inline void __deactivate_traps_mpam(void) static inline void __activate_traps_common(struct kvm_vcpu *vcpu) { + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */ write_sysreg(1 << 15, hstr_el2); @@ -244,12 +293,9 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) * counter, which could make a PMXEVCNTR_EL0 access UNDEF at * EL1 instead of being trapped to EL2. */ - if (kvm_arm_support_pmu_v3()) { - struct kvm_cpu_context *hctxt; - + if (system_supports_pmuv3()) { write_sysreg(0, pmselr_el0); - hctxt = host_data_ptr(host_ctxt); ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0); write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); vcpu_set_flag(vcpu, PMUSERENR_ON_CPU); @@ -261,14 +307,12 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) if (cpus_have_final_cap(ARM64_HAS_HCX)) { u64 hcrx = vcpu->arch.hcrx_el2; if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { - u64 clr = 0, set = 0; - - compute_clr_set(vcpu, HCRX_EL2, clr, set); - - hcrx |= set; - hcrx &= ~clr; + u64 val = __vcpu_sys_reg(vcpu, HCRX_EL2); + hcrx |= val & __HCRX_EL2_MASK; + hcrx &= ~(~val & __HCRX_EL2_nMASK); } + ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2); write_sysreg_s(hcrx, SYS_HCRX_EL2); } @@ -278,19 +322,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) { + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); write_sysreg(0, hstr_el2); - if (kvm_arm_support_pmu_v3()) { - struct kvm_cpu_context *hctxt; - - hctxt = host_data_ptr(host_ctxt); + if (system_supports_pmuv3()) { write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU); } if (cpus_have_final_cap(ARM64_HAS_HCX)) - write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2); + write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2); __deactivate_traps_hfgxtr(vcpu); __deactivate_traps_mpam(); @@ -301,7 +344,7 @@ static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr) if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) hcr |= HCR_TVM; - write_sysreg(hcr, hcr_el2); + write_sysreg_hcr(hcr); if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index 76ff095c6b6e..b9cff893bbe0 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -43,6 +43,17 @@ static inline u64 *ctxt_mdscr_el1(struct kvm_cpu_context *ctxt) return &ctxt_sys_reg(ctxt, MDSCR_EL1); } +static inline u64 ctxt_midr_el1(struct kvm_cpu_context *ctxt) +{ + struct kvm *kvm = kern_hyp_va(ctxt_to_vcpu(ctxt)->kvm); + + if (!(ctxt_is_guest(ctxt) && + test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags))) + return read_cpuid_id(); + + return kvm_read_vm_id_reg(kvm, SYS_MIDR_EL1); +} + static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { *ctxt_mdscr_el1(ctxt) = read_sysreg(mdscr_el1); @@ -168,8 +179,9 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) } static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt, - u64 mpidr) + u64 midr, u64 mpidr) { + write_sysreg(midr, vpidr_el2); write_sysreg(mpidr, vmpidr_el2); if (has_vhe() || diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h index 978f38c386ee..5f9d56754e39 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h @@ -39,12 +39,12 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages); int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages); int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages); int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages); -int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, +int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot); -int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm); +int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm); int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot); -int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm); -int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm); +int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm); +int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm); int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu); bool addr_is_memory(phys_addr_t phys); @@ -56,7 +56,7 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt); int hyp_pin_shared_mem(void *from, void *to); void hyp_unpin_shared_mem(void *from, void *to); -void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc); +void reclaim_pgtable_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc); int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, struct kvm_hyp_memcache *host_mc); @@ -67,4 +67,10 @@ static __always_inline void __load_host_stage2(void) else write_sysreg(0, vttbr_el2); } + +#ifdef CONFIG_NVHE_EL2_DEBUG +void pkvm_ownership_selftest(void *base); +#else +static inline void pkvm_ownership_selftest(void *base) { } +#endif #endif /* __KVM_NVHE_MEM_PROTECT__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h index 34233d586060..dee1a406b0c2 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h @@ -8,23 +8,30 @@ #include <linux/types.h> /* - * Bits 0-1 are reserved to track the memory ownership state of each page: - * 00: The page is owned exclusively by the page-table owner. - * 01: The page is owned by the page-table owner, but is shared - * with another entity. - * 10: The page is shared with, but not owned by the page-table owner. - * 11: Reserved for future use (lending). + * Bits 0-1 are used to encode the memory ownership state of each page from the + * point of view of a pKVM "component" (host, hyp, guest, ... see enum + * pkvm_component_id): + * 00: The page is owned and exclusively accessible by the component; + * 01: The page is owned and accessible by the component, but is also + * accessible by another component; + * 10: The page is accessible but not owned by the component; + * The storage of this state depends on the component: either in the + * hyp_vmemmap for the host and hyp states or in PTE software bits for guests. */ enum pkvm_page_state { PKVM_PAGE_OWNED = 0ULL, PKVM_PAGE_SHARED_OWNED = BIT(0), PKVM_PAGE_SHARED_BORROWED = BIT(1), - __PKVM_PAGE_RESERVED = BIT(0) | BIT(1), - /* Meta-states which aren't encoded directly in the PTE's SW bits */ - PKVM_NOPAGE = BIT(2), + /* + * 'Meta-states' are not stored directly in PTE SW bits for guest + * states, but inferred from the context (e.g. invalid PTE entries). + * For the host and hyp, meta-states are stored directly in the + * struct hyp_page. + */ + PKVM_NOPAGE = BIT(0) | BIT(1), }; -#define PKVM_PAGE_META_STATES_MASK (~__PKVM_PAGE_RESERVED) +#define PKVM_PAGE_STATE_MASK (BIT(0) | BIT(1)) #define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1) static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot, @@ -44,8 +51,15 @@ struct hyp_page { u16 refcount; u8 order; - /* Host (non-meta) state. Guarded by the host stage-2 lock. */ - enum pkvm_page_state host_state : 8; + /* Host state. Guarded by the host stage-2 lock. */ + unsigned __host_state : 4; + + /* + * Complement of the hyp state. Guarded by the hyp stage-1 lock. We use + * the complement so that the initial 0 in __hyp_state_comp (due to the + * entire vmemmap starting off zeroed) encodes PKVM_NOPAGE. + */ + unsigned __hyp_state_comp : 4; u32 host_share_guest_count; }; @@ -82,6 +96,26 @@ static inline struct hyp_page *hyp_phys_to_page(phys_addr_t phys) #define hyp_page_to_virt(page) __hyp_va(hyp_page_to_phys(page)) #define hyp_page_to_pool(page) (((struct hyp_page *)page)->pool) +static inline enum pkvm_page_state get_host_state(struct hyp_page *p) +{ + return p->__host_state; +} + +static inline void set_host_state(struct hyp_page *p, enum pkvm_page_state state) +{ + p->__host_state = state; +} + +static inline enum pkvm_page_state get_hyp_state(struct hyp_page *p) +{ + return p->__hyp_state_comp ^ PKVM_PAGE_STATE_MASK; +} + +static inline void set_hyp_state(struct hyp_page *p, enum pkvm_page_state state) +{ + p->__hyp_state_comp = state ^ PKVM_PAGE_STATE_MASK; +} + /* * Refcounting for 'struct hyp_page'. * hyp_pool::lock must be held if atomic access to the refcount is required. diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h index 230e4f2527de..6e83ce35c2f2 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h @@ -13,9 +13,11 @@ extern struct kvm_pgtable pkvm_pgtable; extern hyp_spinlock_t pkvm_pgd_lock; -int hyp_create_pcpu_fixmap(void); +int hyp_create_fixmap(void); void *hyp_fixmap_map(phys_addr_t phys); void hyp_fixmap_unmap(void); +void *hyp_fixblock_map(phys_addr_t phys, size_t *size); +void hyp_fixblock_unmap(void); int hyp_create_idmap(u32 hyp_va_bits); int hyp_map_vectors(void); diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h index e42bf68c8848..ce31d3b73603 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h @@ -43,12 +43,6 @@ struct pkvm_hyp_vm { struct hyp_pool pool; hyp_spinlock_t lock; - /* - * The number of vcpus initialized and ready to run. - * Modifying this is protected by 'vm_table_lock'. - */ - unsigned int nr_vcpus; - /* Array of the hyp vCPU structures for this VM. */ struct pkvm_hyp_vcpu *vcpus[]; }; diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index b43426a493df..a76522d63c3e 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -99,3 +99,9 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAG # causes a build failure. Remove profile optimization flags. KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS)) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + +ifeq ($(CONFIG_UBSAN_KVM_EL2),y) +UBSAN_SANITIZE := y +# Always use brk and not hooks +ccflags-y += $(CFLAGS_UBSAN_TRAP) +endif diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index e433dfab882a..3369dd0c4009 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -730,10 +730,10 @@ static void do_ffa_version(struct arm_smccc_res *res, hyp_ffa_version = ffa_req_version; } - if (hyp_ffa_post_init()) + if (hyp_ffa_post_init()) { res->a0 = FFA_RET_NOT_SUPPORTED; - else { - has_version_negotiated = true; + } else { + smp_store_release(&has_version_negotiated, true); res->a0 = hyp_ffa_version; } unlock: @@ -809,7 +809,8 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) if (!is_ffa_call(func_id)) return false; - if (!has_version_negotiated && func_id != FFA_VERSION) { + if (func_id != FFA_VERSION && + !smp_load_acquire(&has_version_negotiated)) { ffa_to_smccc_error(&res, FFA_RET_INVALID_PARAMETERS); goto out_handled; } diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 58f0cb2298cc..eef15b374abb 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -124,7 +124,7 @@ SYM_FUNC_START(__hyp_do_panic) /* Ensure host stage-2 is disabled */ mrs x0, hcr_el2 bic x0, x0, #HCR_VM - msr hcr_el2, x0 + msr_hcr_el2 x0 isb tlbi vmalls12e1 dsb nsh diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index f8af11189572..aada42522e7b 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -100,7 +100,7 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init) msr mair_el2, x1 ldr x1, [x0, #NVHE_INIT_HCR_EL2] - msr hcr_el2, x1 + msr_hcr_el2 x1 mov x2, #HCR_E2H and x2, x1, x2 @@ -262,7 +262,7 @@ reset: alternative_if ARM64_KVM_PROTECTED_MODE mov_q x5, HCR_HOST_NVHE_FLAGS - msr hcr_el2, x5 + msr_hcr_el2 x5 alternative_else_nop_endif /* Install stub vectors */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 2c37680d954c..8e8848de4d47 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -123,10 +123,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt; - hyp_vcpu->vcpu.arch.sve_state = kern_hyp_va(host_vcpu->arch.sve_state); - /* Limit guest vector length to the maximum supported by the host. */ - hyp_vcpu->vcpu.arch.sve_max_vl = min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl); - hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2; hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE); hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) & @@ -249,7 +245,8 @@ static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(u64, pfn, host_ctxt, 1); DECLARE_REG(u64, gfn, host_ctxt, 2); - DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); + DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4); struct pkvm_hyp_vcpu *hyp_vcpu; int ret = -EINVAL; @@ -264,7 +261,7 @@ static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt) if (ret) goto out; - ret = __pkvm_host_share_guest(pfn, gfn, hyp_vcpu, prot); + ret = __pkvm_host_share_guest(pfn, gfn, nr_pages, hyp_vcpu, prot); out: cpu_reg(host_ctxt, 1) = ret; } @@ -273,6 +270,7 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); struct pkvm_hyp_vm *hyp_vm; int ret = -EINVAL; @@ -283,7 +281,7 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt) if (!hyp_vm) goto out; - ret = __pkvm_host_unshare_guest(gfn, hyp_vm); + ret = __pkvm_host_unshare_guest(gfn, nr_pages, hyp_vm); put_pkvm_hyp_vm(hyp_vm); out: cpu_reg(host_ctxt, 1) = ret; @@ -312,6 +310,7 @@ static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt { DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); struct pkvm_hyp_vm *hyp_vm; int ret = -EINVAL; @@ -322,7 +321,7 @@ static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt if (!hyp_vm) goto out; - ret = __pkvm_host_wrprotect_guest(gfn, hyp_vm); + ret = __pkvm_host_wrprotect_guest(gfn, nr_pages, hyp_vm); put_pkvm_hyp_vm(hyp_vm); out: cpu_reg(host_ctxt, 1) = ret; @@ -332,7 +331,8 @@ static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *ho { DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); DECLARE_REG(u64, gfn, host_ctxt, 2); - DECLARE_REG(bool, mkold, host_ctxt, 3); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); + DECLARE_REG(bool, mkold, host_ctxt, 4); struct pkvm_hyp_vm *hyp_vm; int ret = -EINVAL; @@ -343,7 +343,7 @@ static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *ho if (!hyp_vm) goto out; - ret = __pkvm_host_test_clear_young_guest(gfn, mkold, hyp_vm); + ret = __pkvm_host_test_clear_young_guest(gfn, nr_pages, mkold, hyp_vm); put_pkvm_hyp_vm(hyp_vm); out: cpu_reg(host_ctxt, 1) = ret; diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S index f4562f417d3f..d724f6d69302 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -25,5 +25,7 @@ SECTIONS { BEGIN_HYP_SECTION(.data..percpu) PERCPU_INPUT(L1_CACHE_BYTES) END_HYP_SECTION + HYP_SECTION(.bss) + HYP_SECTION(.data) } diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 19c3c631708c..95d7534c9679 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -60,6 +60,11 @@ static void hyp_unlock_component(void) hyp_spin_unlock(&pkvm_pgd_lock); } +#define for_each_hyp_page(__p, __st, __sz) \ + for (struct hyp_page *__p = hyp_phys_to_page(__st), \ + *__e = __p + ((__sz) >> PAGE_SHIFT); \ + __p < __e; __p++) + static void *host_s2_zalloc_pages_exact(size_t size) { void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size)); @@ -161,12 +166,6 @@ int kvm_host_prepare_stage2(void *pgt_pool_base) return 0; } -static bool guest_stage2_force_pte_cb(u64 addr, u64 end, - enum kvm_pgtable_prot prot) -{ - return true; -} - static void *guest_s2_zalloc_pages_exact(size_t size) { void *addr = hyp_alloc_pages(¤t_vm->pool, get_order(size)); @@ -217,16 +216,42 @@ static void guest_s2_put_page(void *addr) hyp_put_page(¤t_vm->pool, addr); } +static void __apply_guest_page(void *va, size_t size, + void (*func)(void *addr, size_t size)) +{ + size += va - PTR_ALIGN_DOWN(va, PAGE_SIZE); + va = PTR_ALIGN_DOWN(va, PAGE_SIZE); + size = PAGE_ALIGN(size); + + while (size) { + size_t map_size = PAGE_SIZE; + void *map; + + if (IS_ALIGNED((unsigned long)va, PMD_SIZE) && size >= PMD_SIZE) + map = hyp_fixblock_map(__hyp_pa(va), &map_size); + else + map = hyp_fixmap_map(__hyp_pa(va)); + + func(map, map_size); + + if (map_size == PMD_SIZE) + hyp_fixblock_unmap(); + else + hyp_fixmap_unmap(); + + size -= map_size; + va += map_size; + } +} + static void clean_dcache_guest_page(void *va, size_t size) { - __clean_dcache_guest_page(hyp_fixmap_map(__hyp_pa(va)), size); - hyp_fixmap_unmap(); + __apply_guest_page(va, size, __clean_dcache_guest_page); } static void invalidate_icache_guest_page(void *va, size_t size) { - __invalidate_icache_guest_page(hyp_fixmap_map(__hyp_pa(va)), size); - hyp_fixmap_unmap(); + __apply_guest_page(va, size, __invalidate_icache_guest_page); } int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd) @@ -255,8 +280,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd) }; guest_lock_component(vm); - ret = __kvm_pgtable_stage2_init(mmu->pgt, mmu, &vm->mm_ops, 0, - guest_stage2_force_pte_cb); + ret = __kvm_pgtable_stage2_init(mmu->pgt, mmu, &vm->mm_ops, 0, NULL); guest_unlock_component(vm); if (ret) return ret; @@ -266,7 +290,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd) return 0; } -void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc) +void reclaim_pgtable_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc) { struct hyp_page *page; void *addr; @@ -309,7 +333,7 @@ int __pkvm_prot_finalize(void) */ kvm_flush_dcache_to_poc(params, sizeof(*params)); - write_sysreg(params->hcr_el2, hcr_el2); + write_sysreg_hcr(params->hcr_el2); __load_stage2(&host_mmu.arch.mmu, &host_mmu.arch); /* @@ -467,7 +491,8 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) return -EAGAIN; if (pte) { - WARN_ON(addr_is_memory(addr) && hyp_phys_to_page(addr)->host_state != PKVM_NOPAGE); + WARN_ON(addr_is_memory(addr) && + get_host_state(hyp_phys_to_page(addr)) != PKVM_NOPAGE); return -EPERM; } @@ -493,17 +518,15 @@ int host_stage2_idmap_locked(phys_addr_t addr, u64 size, static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state) { - phys_addr_t end = addr + size; - - for (; addr < end; addr += PAGE_SIZE) - hyp_phys_to_page(addr)->host_state = state; + for_each_hyp_page(page, addr, size) + set_host_state(page, state); } int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) { int ret; - if (!addr_is_memory(addr)) + if (!range_is_memory(addr, addr + size)) return -EPERM; ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt, @@ -578,7 +601,14 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt) return; } - addr = (fault.hpfar_el2 & HPFAR_MASK) << 8; + + /* + * Yikes, we couldn't resolve the fault IPA. This should reinject an + * abort into the host when we figure out how to do that. + */ + BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS)); + addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12; + ret = host_stage2_idmap(addr); BUG_ON(ret && ret != -EAGAIN); } @@ -611,16 +641,16 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, static int __host_check_page_state_range(u64 addr, u64 size, enum pkvm_page_state state) { - u64 end = addr + size; int ret; - ret = check_range_allowed_memory(addr, end); + ret = check_range_allowed_memory(addr, addr + size); if (ret) return ret; hyp_assert_lock_held(&host_mmu.lock); - for (; addr < end; addr += PAGE_SIZE) { - if (hyp_phys_to_page(addr)->host_state != state) + + for_each_hyp_page(page, addr, size) { + if (get_host_state(page) != state) return -EPERM; } @@ -630,7 +660,7 @@ static int __host_check_page_state_range(u64 addr, u64 size, static int __host_set_page_state_range(u64 addr, u64 size, enum pkvm_page_state state) { - if (hyp_phys_to_page(addr)->host_state == PKVM_NOPAGE) { + if (get_host_state(hyp_phys_to_page(addr)) == PKVM_NOPAGE) { int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT); if (ret) @@ -642,24 +672,20 @@ static int __host_set_page_state_range(u64 addr, u64 size, return 0; } -static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte, u64 addr) +static void __hyp_set_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state) { - if (!kvm_pte_valid(pte)) - return PKVM_NOPAGE; - - return pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte)); + for_each_hyp_page(page, phys, size) + set_hyp_state(page, state); } -static int __hyp_check_page_state_range(u64 addr, u64 size, - enum pkvm_page_state state) +static int __hyp_check_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state) { - struct check_walk_data d = { - .desired = state, - .get_page_state = hyp_get_page_state, - }; + for_each_hyp_page(page, phys, size) { + if (get_hyp_state(page) != state) + return -EPERM; + } - hyp_assert_lock_held(&pkvm_pgd_lock); - return check_page_state_range(&pkvm_pgtable, addr, size, &d); + return 0; } static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr) @@ -670,10 +696,9 @@ static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr) return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); } -static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr, +static int __guest_check_page_state_range(struct pkvm_hyp_vm *vm, u64 addr, u64 size, enum pkvm_page_state state) { - struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); struct check_walk_data d = { .desired = state, .get_page_state = guest_get_page_state, @@ -686,8 +711,6 @@ static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr, int __pkvm_host_share_hyp(u64 pfn) { u64 phys = hyp_pfn_to_phys(pfn); - void *virt = __hyp_va(phys); - enum kvm_pgtable_prot prot; u64 size = PAGE_SIZE; int ret; @@ -697,14 +720,11 @@ int __pkvm_host_share_hyp(u64 pfn) ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); if (ret) goto unlock; - if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) { - ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE); - if (ret) - goto unlock; - } + ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE); + if (ret) + goto unlock; - prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED); - WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot)); + __hyp_set_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED); WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED)); unlock: @@ -727,7 +747,7 @@ int __pkvm_host_unshare_hyp(u64 pfn) ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); if (ret) goto unlock; - ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_SHARED_BORROWED); + ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED); if (ret) goto unlock; if (hyp_page_count((void *)virt)) { @@ -735,7 +755,7 @@ int __pkvm_host_unshare_hyp(u64 pfn) goto unlock; } - WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size); + __hyp_set_page_state_range(phys, size, PKVM_NOPAGE); WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_OWNED)); unlock: @@ -750,7 +770,6 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) u64 phys = hyp_pfn_to_phys(pfn); u64 size = PAGE_SIZE * nr_pages; void *virt = __hyp_va(phys); - enum kvm_pgtable_prot prot; int ret; host_lock_component(); @@ -759,14 +778,12 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); if (ret) goto unlock; - if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) { - ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE); - if (ret) - goto unlock; - } + ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE); + if (ret) + goto unlock; - prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED); - WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot)); + __hyp_set_page_state_range(phys, size, PKVM_PAGE_OWNED); + WARN_ON(pkvm_create_mappings_locked(virt, virt + size, PAGE_HYP)); WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HYP)); unlock: @@ -786,15 +803,14 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages) host_lock_component(); hyp_lock_component(); - ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_OWNED); + ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE); if (ret) goto unlock; - if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) { - ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE); - if (ret) - goto unlock; - } + __hyp_set_page_state_range(phys, size, PKVM_NOPAGE); WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size); WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HOST)); @@ -809,24 +825,30 @@ int hyp_pin_shared_mem(void *from, void *to) { u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE); u64 end = PAGE_ALIGN((u64)to); + u64 phys = __hyp_pa(start); u64 size = end - start; + struct hyp_page *p; int ret; host_lock_component(); hyp_lock_component(); - ret = __host_check_page_state_range(__hyp_pa(start), size, - PKVM_PAGE_SHARED_OWNED); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); if (ret) goto unlock; - ret = __hyp_check_page_state_range(start, size, - PKVM_PAGE_SHARED_BORROWED); + ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED); if (ret) goto unlock; - for (cur = start; cur < end; cur += PAGE_SIZE) - hyp_page_ref_inc(hyp_virt_to_page(cur)); + for (cur = start; cur < end; cur += PAGE_SIZE) { + p = hyp_virt_to_page(cur); + hyp_page_ref_inc(p); + if (p->refcount == 1) + WARN_ON(pkvm_create_mappings_locked((void *)cur, + (void *)cur + PAGE_SIZE, + PAGE_HYP)); + } unlock: hyp_unlock_component(); @@ -839,12 +861,17 @@ void hyp_unpin_shared_mem(void *from, void *to) { u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE); u64 end = PAGE_ALIGN((u64)to); + struct hyp_page *p; host_lock_component(); hyp_lock_component(); - for (cur = start; cur < end; cur += PAGE_SIZE) - hyp_page_ref_dec(hyp_virt_to_page(cur)); + for (cur = start; cur < end; cur += PAGE_SIZE) { + p = hyp_virt_to_page(cur); + if (p->refcount == 1) + WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, cur, PAGE_SIZE) != PAGE_SIZE); + hyp_page_ref_dec(p); + } hyp_unlock_component(); host_unlock_component(); @@ -880,49 +907,84 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages) return ret; } -int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, +static int __guest_check_transition_size(u64 phys, u64 ipa, u64 nr_pages, u64 *size) +{ + size_t block_size; + + if (nr_pages == 1) { + *size = PAGE_SIZE; + return 0; + } + + /* We solely support second to last level huge mapping */ + block_size = kvm_granule_size(KVM_PGTABLE_LAST_LEVEL - 1); + + if (nr_pages != block_size >> PAGE_SHIFT) + return -EINVAL; + + if (!IS_ALIGNED(phys | ipa, block_size)) + return -EINVAL; + + *size = block_size; + return 0; +} + +int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) { struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); u64 phys = hyp_pfn_to_phys(pfn); u64 ipa = hyp_pfn_to_phys(gfn); - struct hyp_page *page; + u64 size; int ret; if (prot & ~KVM_PGTABLE_PROT_RWX) return -EINVAL; - ret = check_range_allowed_memory(phys, phys + PAGE_SIZE); + ret = __guest_check_transition_size(phys, ipa, nr_pages, &size); + if (ret) + return ret; + + ret = check_range_allowed_memory(phys, phys + size); if (ret) return ret; host_lock_component(); guest_lock_component(vm); - ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE); + ret = __guest_check_page_state_range(vm, ipa, size, PKVM_NOPAGE); if (ret) goto unlock; - page = hyp_phys_to_page(phys); - switch (page->host_state) { - case PKVM_PAGE_OWNED: - WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED)); - break; - case PKVM_PAGE_SHARED_OWNED: - if (page->host_share_guest_count) - break; - /* Only host to np-guest multi-sharing is tolerated */ - WARN_ON(1); - fallthrough; - default: - ret = -EPERM; - goto unlock; + for_each_hyp_page(page, phys, size) { + switch (get_host_state(page)) { + case PKVM_PAGE_OWNED: + continue; + case PKVM_PAGE_SHARED_OWNED: + if (page->host_share_guest_count == U32_MAX) { + ret = -EBUSY; + goto unlock; + } + + /* Only host to np-guest multi-sharing is tolerated */ + if (page->host_share_guest_count) + continue; + + fallthrough; + default: + ret = -EPERM; + goto unlock; + } + } + + for_each_hyp_page(page, phys, size) { + set_host_state(page, PKVM_PAGE_SHARED_OWNED); + page->host_share_guest_count++; } - WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys, + WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, size, phys, pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED), &vcpu->vcpu.arch.pkvm_memcache, 0)); - page->host_share_guest_count++; unlock: guest_unlock_component(vm); @@ -931,10 +993,9 @@ unlock: return ret; } -static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa) +static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa, u64 size) { enum pkvm_page_state state; - struct hyp_page *page; kvm_pte_t pte; u64 phys; s8 level; @@ -945,7 +1006,7 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip return ret; if (!kvm_pte_valid(pte)) return -ENOENT; - if (level != KVM_PGTABLE_LAST_LEVEL) + if (kvm_granule_size(level) != size) return -E2BIG; state = guest_get_page_state(pte, ipa); @@ -953,43 +1014,49 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip return -EPERM; phys = kvm_pte_to_phys(pte); - ret = check_range_allowed_memory(phys, phys + PAGE_SIZE); + ret = check_range_allowed_memory(phys, phys + size); if (WARN_ON(ret)) return ret; - page = hyp_phys_to_page(phys); - if (page->host_state != PKVM_PAGE_SHARED_OWNED) - return -EPERM; - if (WARN_ON(!page->host_share_guest_count)) - return -EINVAL; + for_each_hyp_page(page, phys, size) { + if (get_host_state(page) != PKVM_PAGE_SHARED_OWNED) + return -EPERM; + if (WARN_ON(!page->host_share_guest_count)) + return -EINVAL; + } *__phys = phys; return 0; } -int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm) +int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm) { u64 ipa = hyp_pfn_to_phys(gfn); - struct hyp_page *page; - u64 phys; + u64 size, phys; int ret; + ret = __guest_check_transition_size(0, ipa, nr_pages, &size); + if (ret) + return ret; + host_lock_component(); guest_lock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); + ret = __check_host_shared_guest(vm, &phys, ipa, size); if (ret) goto unlock; - ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE); + ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, size); if (ret) goto unlock; - page = hyp_phys_to_page(phys); - page->host_share_guest_count--; - if (!page->host_share_guest_count) - WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED)); + for_each_hyp_page(page, phys, size) { + /* __check_host_shared_guest() protects against underflow */ + page->host_share_guest_count--; + if (!page->host_share_guest_count) + set_host_state(page, PKVM_PAGE_OWNED); + } unlock: guest_unlock_component(vm); @@ -998,7 +1065,7 @@ unlock: return ret; } -static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa) +static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa, u64 size) { u64 phys; int ret; @@ -1009,7 +1076,7 @@ static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa) host_lock_component(); guest_lock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); + ret = __check_host_shared_guest(vm, &phys, ipa, size); guest_unlock_component(vm); host_unlock_component(); @@ -1029,7 +1096,7 @@ int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_ if (prot & ~KVM_PGTABLE_PROT_RWX) return -EINVAL; - assert_host_shared_guest(vm, ipa); + assert_host_shared_guest(vm, ipa, PAGE_SIZE); guest_lock_component(vm); ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); guest_unlock_component(vm); @@ -1037,33 +1104,41 @@ int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_ return ret; } -int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) +int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm) { - u64 ipa = hyp_pfn_to_phys(gfn); + u64 size, ipa = hyp_pfn_to_phys(gfn); int ret; if (pkvm_hyp_vm_is_protected(vm)) return -EPERM; - assert_host_shared_guest(vm, ipa); + ret = __guest_check_transition_size(0, ipa, nr_pages, &size); + if (ret) + return ret; + + assert_host_shared_guest(vm, ipa, size); guest_lock_component(vm); - ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, size); guest_unlock_component(vm); return ret; } -int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm) { - u64 ipa = hyp_pfn_to_phys(gfn); + u64 size, ipa = hyp_pfn_to_phys(gfn); int ret; if (pkvm_hyp_vm_is_protected(vm)) return -EPERM; - assert_host_shared_guest(vm, ipa); + ret = __guest_check_transition_size(0, ipa, nr_pages, &size); + if (ret) + return ret; + + assert_host_shared_guest(vm, ipa, size); guest_lock_component(vm); - ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); + ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, size, mkold); guest_unlock_component(vm); return ret; @@ -1077,10 +1152,210 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu) if (pkvm_hyp_vm_is_protected(vm)) return -EPERM; - assert_host_shared_guest(vm, ipa); + assert_host_shared_guest(vm, ipa, PAGE_SIZE); guest_lock_component(vm); kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); guest_unlock_component(vm); return 0; } + +#ifdef CONFIG_NVHE_EL2_DEBUG +struct pkvm_expected_state { + enum pkvm_page_state host; + enum pkvm_page_state hyp; + enum pkvm_page_state guest[2]; /* [ gfn, gfn + 1 ] */ +}; + +static struct pkvm_expected_state selftest_state; +static struct hyp_page *selftest_page; + +static struct pkvm_hyp_vm selftest_vm = { + .kvm = { + .arch = { + .mmu = { + .arch = &selftest_vm.kvm.arch, + .pgt = &selftest_vm.pgt, + }, + }, + }, +}; + +static struct pkvm_hyp_vcpu selftest_vcpu = { + .vcpu = { + .arch = { + .hw_mmu = &selftest_vm.kvm.arch.mmu, + }, + .kvm = &selftest_vm.kvm, + }, +}; + +static void init_selftest_vm(void *virt) +{ + struct hyp_page *p = hyp_virt_to_page(virt); + int i; + + selftest_vm.kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr; + WARN_ON(kvm_guest_prepare_stage2(&selftest_vm, virt)); + + for (i = 0; i < pkvm_selftest_pages(); i++) { + if (p[i].refcount) + continue; + p[i].refcount = 1; + hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i])); + } +} + +static u64 selftest_ipa(void) +{ + return BIT(selftest_vm.pgt.ia_bits - 1); +} + +static void assert_page_state(void) +{ + void *virt = hyp_page_to_virt(selftest_page); + u64 size = PAGE_SIZE << selftest_page->order; + struct pkvm_hyp_vcpu *vcpu = &selftest_vcpu; + u64 phys = hyp_virt_to_phys(virt); + u64 ipa[2] = { selftest_ipa(), selftest_ipa() + PAGE_SIZE }; + struct pkvm_hyp_vm *vm; + + vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + + host_lock_component(); + WARN_ON(__host_check_page_state_range(phys, size, selftest_state.host)); + host_unlock_component(); + + hyp_lock_component(); + WARN_ON(__hyp_check_page_state_range(phys, size, selftest_state.hyp)); + hyp_unlock_component(); + + guest_lock_component(&selftest_vm); + WARN_ON(__guest_check_page_state_range(vm, ipa[0], size, selftest_state.guest[0])); + WARN_ON(__guest_check_page_state_range(vm, ipa[1], size, selftest_state.guest[1])); + guest_unlock_component(&selftest_vm); +} + +#define assert_transition_res(res, fn, ...) \ + do { \ + WARN_ON(fn(__VA_ARGS__) != res); \ + assert_page_state(); \ + } while (0) + +void pkvm_ownership_selftest(void *base) +{ + enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_RWX; + void *virt = hyp_alloc_pages(&host_s2_pool, 0); + struct pkvm_hyp_vcpu *vcpu = &selftest_vcpu; + struct pkvm_hyp_vm *vm = &selftest_vm; + u64 phys, size, pfn, gfn; + + WARN_ON(!virt); + selftest_page = hyp_virt_to_page(virt); + selftest_page->refcount = 0; + init_selftest_vm(base); + + size = PAGE_SIZE << selftest_page->order; + phys = hyp_virt_to_phys(virt); + pfn = hyp_phys_to_pfn(phys); + gfn = hyp_phys_to_pfn(selftest_ipa()); + + selftest_state.host = PKVM_NOPAGE; + selftest_state.hyp = PKVM_PAGE_OWNED; + selftest_state.guest[0] = selftest_state.guest[1] = PKVM_NOPAGE; + assert_page_state(); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + + selftest_state.host = PKVM_PAGE_SHARED_OWNED; + selftest_state.hyp = PKVM_PAGE_SHARED_BORROWED; + assert_transition_res(0, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + + assert_transition_res(0, hyp_pin_shared_mem, virt, virt + size); + assert_transition_res(0, hyp_pin_shared_mem, virt, virt + size); + hyp_unpin_shared_mem(virt, virt + size); + WARN_ON(hyp_page_count(virt) != 1); + assert_transition_res(-EBUSY, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + + hyp_unpin_shared_mem(virt, virt + size); + assert_page_state(); + WARN_ON(hyp_page_count(virt)); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_unshare_hyp, pfn); + + selftest_state.host = PKVM_PAGE_SHARED_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_unshare_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1); + + selftest_state.host = PKVM_PAGE_SHARED_OWNED; + selftest_state.guest[0] = PKVM_PAGE_SHARED_BORROWED; + assert_transition_res(0, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + + selftest_state.guest[1] = PKVM_PAGE_SHARED_BORROWED; + assert_transition_res(0, __pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot); + WARN_ON(hyp_virt_to_page(virt)->host_share_guest_count != 2); + + selftest_state.guest[0] = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_unshare_guest, gfn, 1, vm); + + selftest_state.guest[1] = PKVM_NOPAGE; + selftest_state.host = PKVM_PAGE_OWNED; + assert_transition_res(0, __pkvm_host_unshare_guest, gfn + 1, 1, vm); + + selftest_state.host = PKVM_NOPAGE; + selftest_state.hyp = PKVM_PAGE_OWNED; + assert_transition_res(0, __pkvm_host_donate_hyp, pfn, 1); + + selftest_page->refcount = 1; + hyp_put_page(&host_s2_pool, virt); +} +#endif diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index f41c7440b34b..ae8391baebc3 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -229,9 +229,8 @@ int hyp_map_vectors(void) return 0; } -void *hyp_fixmap_map(phys_addr_t phys) +static void *fixmap_map_slot(struct hyp_fixmap_slot *slot, phys_addr_t phys) { - struct hyp_fixmap_slot *slot = this_cpu_ptr(&fixmap_slots); kvm_pte_t pte, *ptep = slot->ptep; pte = *ptep; @@ -243,10 +242,21 @@ void *hyp_fixmap_map(phys_addr_t phys) return (void *)slot->addr; } +void *hyp_fixmap_map(phys_addr_t phys) +{ + return fixmap_map_slot(this_cpu_ptr(&fixmap_slots), phys); +} + static void fixmap_clear_slot(struct hyp_fixmap_slot *slot) { kvm_pte_t *ptep = slot->ptep; u64 addr = slot->addr; + u32 level; + + if (FIELD_GET(KVM_PTE_TYPE, *ptep) == KVM_PTE_TYPE_PAGE) + level = KVM_PGTABLE_LAST_LEVEL; + else + level = KVM_PGTABLE_LAST_LEVEL - 1; /* create_fixblock() guarantees PMD level */ WRITE_ONCE(*ptep, *ptep & ~KVM_PTE_VALID); @@ -260,7 +270,7 @@ 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_LAST_LEVEL); + __tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level); dsb(ish); isb(); } @@ -273,9 +283,9 @@ void hyp_fixmap_unmap(void) static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { - struct hyp_fixmap_slot *slot = per_cpu_ptr(&fixmap_slots, (u64)ctx->arg); + struct hyp_fixmap_slot *slot = (struct hyp_fixmap_slot *)ctx->arg; - if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_LAST_LEVEL) + if (!kvm_pte_valid(ctx->old) || (ctx->end - ctx->start) != kvm_granule_size(ctx->level)) return -EINVAL; slot->addr = ctx->addr; @@ -296,13 +306,84 @@ static int create_fixmap_slot(u64 addr, u64 cpu) struct kvm_pgtable_walker walker = { .cb = __create_fixmap_slot_cb, .flags = KVM_PGTABLE_WALK_LEAF, - .arg = (void *)cpu, + .arg = per_cpu_ptr(&fixmap_slots, cpu), }; return kvm_pgtable_walk(&pkvm_pgtable, addr, PAGE_SIZE, &walker); } -int hyp_create_pcpu_fixmap(void) +#if PAGE_SHIFT < 16 +#define HAS_FIXBLOCK +static struct hyp_fixmap_slot hyp_fixblock_slot; +static DEFINE_HYP_SPINLOCK(hyp_fixblock_lock); +#endif + +static int create_fixblock(void) +{ +#ifdef HAS_FIXBLOCK + struct kvm_pgtable_walker walker = { + .cb = __create_fixmap_slot_cb, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = &hyp_fixblock_slot, + }; + unsigned long addr; + phys_addr_t phys; + int ret, i; + + /* Find a RAM phys address, PMD aligned */ + for (i = 0; i < hyp_memblock_nr; i++) { + phys = ALIGN(hyp_memory[i].base, PMD_SIZE); + if (phys + PMD_SIZE < (hyp_memory[i].base + hyp_memory[i].size)) + break; + } + + if (i >= hyp_memblock_nr) + return -EINVAL; + + hyp_spin_lock(&pkvm_pgd_lock); + addr = ALIGN(__io_map_base, PMD_SIZE); + ret = __pkvm_alloc_private_va_range(addr, PMD_SIZE); + if (ret) + goto unlock; + + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, PMD_SIZE, phys, PAGE_HYP); + if (ret) + goto unlock; + + ret = kvm_pgtable_walk(&pkvm_pgtable, addr, PMD_SIZE, &walker); + +unlock: + hyp_spin_unlock(&pkvm_pgd_lock); + + return ret; +#else + return 0; +#endif +} + +void *hyp_fixblock_map(phys_addr_t phys, size_t *size) +{ +#ifdef HAS_FIXBLOCK + *size = PMD_SIZE; + hyp_spin_lock(&hyp_fixblock_lock); + return fixmap_map_slot(&hyp_fixblock_slot, phys); +#else + *size = PAGE_SIZE; + return hyp_fixmap_map(phys); +#endif +} + +void hyp_fixblock_unmap(void) +{ +#ifdef HAS_FIXBLOCK + fixmap_clear_slot(&hyp_fixblock_slot); + hyp_spin_unlock(&hyp_fixblock_lock); +#else + hyp_fixmap_unmap(); +#endif +} + +int hyp_create_fixmap(void) { unsigned long addr, i; int ret; @@ -322,7 +403,7 @@ int hyp_create_pcpu_fixmap(void) return ret; } - return 0; + return create_fixblock(); } int hyp_create_idmap(u32 hyp_va_bits) diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 3927fe52a3dd..338505cb0171 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -46,7 +46,8 @@ static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_FWB; if (cpus_have_final_cap(ARM64_HAS_EVT) && - !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE)) + !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE) && + kvm_read_vm_id_reg(vcpu->kvm, SYS_CTR_EL0) == read_cpuid(CTR_EL0)) vcpu->arch.hcr_el2 |= HCR_TID4; else vcpu->arch.hcr_el2 |= HCR_TID2; @@ -166,8 +167,13 @@ static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu) pkvm_vcpu_reset_hcr(vcpu); - if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu))) + if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu))) { + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + /* Trust the host for non-protected vcpu features. */ + vcpu->arch.hcrx_el2 = host_vcpu->arch.hcrx_el2; return 0; + } ret = pkvm_check_pvm_cpu_features(vcpu); if (ret) @@ -175,6 +181,7 @@ static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu) pvm_init_traps_hcr(vcpu); pvm_init_traps_mdcr(vcpu); + vcpu_set_hcrx(vcpu); return 0; } @@ -239,10 +246,12 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, hyp_spin_lock(&vm_table_lock); hyp_vm = get_vm_by_handle(handle); - if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx) + if (!hyp_vm || hyp_vm->kvm.created_vcpus <= vcpu_idx) goto unlock; hyp_vcpu = hyp_vm->vcpus[vcpu_idx]; + if (!hyp_vcpu) + goto unlock; /* Ensure vcpu isn't loaded on more than one cpu simultaneously. */ if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) { @@ -315,6 +324,9 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc unsigned long host_arch_flags = READ_ONCE(host_kvm->arch.flags); DECLARE_BITMAP(allowed_features, KVM_VCPU_MAX_FEATURES); + /* CTR_EL0 is always under host control, even for protected VMs. */ + hyp_vm->kvm.arch.ctr_el0 = host_kvm->arch.ctr_el0; + if (test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &host_kvm->arch.flags)) set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags); @@ -325,6 +337,10 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc bitmap_copy(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features, KVM_VCPU_MAX_FEATURES); + + if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &host_arch_flags)) + hyp_vm->kvm.arch.midr_el1 = host_kvm->arch.midr_el1; + return; } @@ -356,13 +372,32 @@ static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu) hyp_unpin_shared_mem(host_vcpu, host_vcpu + 1); } +static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + void *sve_state; + + if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE)) + return; + + sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state); + hyp_unpin_shared_mem(sve_state, + sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu)); +} + static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[], unsigned int nr_vcpus) { int i; - for (i = 0; i < nr_vcpus; i++) - unpin_host_vcpu(hyp_vcpus[i]->host_vcpu); + for (i = 0; i < nr_vcpus; i++) { + struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vcpus[i]; + + if (!hyp_vcpu) + continue; + + unpin_host_vcpu(hyp_vcpu->host_vcpu); + unpin_host_sve_state(hyp_vcpu); + } } static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm, @@ -376,34 +411,56 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm, pkvm_init_features_from_host(hyp_vm, host_kvm); } -static void pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu) +static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu) { struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu; + unsigned int sve_max_vl; + size_t sve_state_size; + void *sve_state; + int ret = 0; - if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) + if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED); + return 0; + } + + /* Limit guest vector length to the maximum supported by the host. */ + sve_max_vl = min(READ_ONCE(host_vcpu->arch.sve_max_vl), kvm_host_sve_max_vl); + sve_state_size = sve_state_size_from_vl(sve_max_vl); + sve_state = kern_hyp_va(READ_ONCE(host_vcpu->arch.sve_state)); + + if (!sve_state || !sve_state_size) { + ret = -EINVAL; + goto err; + } + + ret = hyp_pin_shared_mem(sve_state, sve_state + sve_state_size); + if (ret) + goto err; + + vcpu->arch.sve_state = sve_state; + vcpu->arch.sve_max_vl = sve_max_vl; + + return 0; +err: + clear_bit(KVM_ARM_VCPU_SVE, vcpu->kvm->arch.vcpu_features); + return ret; } static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, struct pkvm_hyp_vm *hyp_vm, - struct kvm_vcpu *host_vcpu, - unsigned int vcpu_idx) + struct kvm_vcpu *host_vcpu) { int ret = 0; if (hyp_pin_shared_mem(host_vcpu, host_vcpu + 1)) return -EBUSY; - if (host_vcpu->vcpu_idx != vcpu_idx) { - ret = -EINVAL; - goto done; - } - hyp_vcpu->host_vcpu = host_vcpu; hyp_vcpu->vcpu.kvm = &hyp_vm->kvm; hyp_vcpu->vcpu.vcpu_id = READ_ONCE(host_vcpu->vcpu_id); - hyp_vcpu->vcpu.vcpu_idx = vcpu_idx; + hyp_vcpu->vcpu.vcpu_idx = READ_ONCE(host_vcpu->vcpu_idx); hyp_vcpu->vcpu.arch.hw_mmu = &hyp_vm->kvm.arch.mmu; hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags); @@ -416,7 +473,7 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, if (ret) goto done; - pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu); + ret = pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu); done: if (ret) unpin_host_vcpu(host_vcpu); @@ -641,27 +698,28 @@ int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, goto unlock; } - idx = hyp_vm->nr_vcpus; + ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu); + if (ret) + goto unlock; + + idx = hyp_vcpu->vcpu.vcpu_idx; if (idx >= hyp_vm->kvm.created_vcpus) { ret = -EINVAL; goto unlock; } - ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu, idx); - if (ret) + if (hyp_vm->vcpus[idx]) { + ret = -EINVAL; goto unlock; + } hyp_vm->vcpus[idx] = hyp_vcpu; - hyp_vm->nr_vcpus++; unlock: hyp_spin_unlock(&vm_table_lock); - if (ret) { + if (ret) unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu)); - return ret; - } - - return 0; + return ret; } static void @@ -678,7 +736,7 @@ teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size) int __pkvm_teardown_vm(pkvm_handle_t handle) { - struct kvm_hyp_memcache *mc; + struct kvm_hyp_memcache *mc, *stage2_mc; struct pkvm_hyp_vm *hyp_vm; struct kvm *host_kvm; unsigned int idx; @@ -706,18 +764,24 @@ int __pkvm_teardown_vm(pkvm_handle_t handle) /* Reclaim guest pages (including page-table pages) */ mc = &host_kvm->arch.pkvm.teardown_mc; - reclaim_guest_pages(hyp_vm, mc); - unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->nr_vcpus); + stage2_mc = &host_kvm->arch.pkvm.stage2_teardown_mc; + reclaim_pgtable_pages(hyp_vm, stage2_mc); + unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->kvm.created_vcpus); /* Push the metadata pages to the teardown memcache */ - for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) { + for (idx = 0; idx < hyp_vm->kvm.created_vcpus; ++idx) { struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx]; - struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache; + struct kvm_hyp_memcache *vcpu_mc; + + if (!hyp_vcpu) + continue; + + vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache; while (vcpu_mc->nr_pages) { void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt); - push_hyp_memcache(mc, addr, hyp_virt_to_phys); + push_hyp_memcache(stage2_mc, addr, hyp_virt_to_phys); unmap_donated_memory_noclear(addr, PAGE_SIZE); } diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index d62bcb5634a2..a48d3f5a5afb 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -28,6 +28,7 @@ static void *vmemmap_base; static void *vm_table_base; static void *hyp_pgt_base; static void *host_s2_pgt_base; +static void *selftest_base; static void *ffa_proxy_pages; static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; static struct hyp_pool hpool; @@ -38,6 +39,11 @@ static int divide_memory_pool(void *virt, unsigned long size) hyp_early_alloc_init(virt, size); + nr_pages = pkvm_selftest_pages(); + selftest_base = hyp_early_alloc_contig(nr_pages); + if (nr_pages && !selftest_base) + return -ENOMEM; + nr_pages = hyp_vmemmap_pages(sizeof(struct hyp_page)); vmemmap_base = hyp_early_alloc_contig(nr_pages); if (!vmemmap_base) @@ -119,6 +125,10 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, if (ret) return ret; + ret = pkvm_create_mappings(__hyp_data_start, __hyp_data_end, PAGE_HYP); + if (ret) + return ret; + ret = pkvm_create_mappings(__hyp_rodata_start, __hyp_rodata_end, PAGE_HYP_RO); if (ret) return ret; @@ -180,6 +190,7 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { enum pkvm_page_state state; + struct hyp_page *page; phys_addr_t phys; if (!kvm_pte_valid(ctx->old)) @@ -192,19 +203,25 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx, if (!addr_is_memory(phys)) return -EINVAL; + page = hyp_phys_to_page(phys); + /* * Adjust the host stage-2 mappings to match the ownership attributes - * configured in the hypervisor stage-1. + * configured in the hypervisor stage-1, and make sure to propagate them + * to the hyp_vmemmap state. */ state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(ctx->old)); switch (state) { case PKVM_PAGE_OWNED: + set_hyp_state(page, PKVM_PAGE_OWNED); return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP); case PKVM_PAGE_SHARED_OWNED: - hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_BORROWED; + set_hyp_state(page, PKVM_PAGE_SHARED_OWNED); + set_host_state(page, PKVM_PAGE_SHARED_BORROWED); break; case PKVM_PAGE_SHARED_BORROWED: - hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_OWNED; + set_hyp_state(page, PKVM_PAGE_SHARED_BORROWED); + set_host_state(page, PKVM_PAGE_SHARED_OWNED); break; default: return -EINVAL; @@ -295,7 +312,7 @@ void __noreturn __pkvm_init_finalise(void) if (ret) goto out; - ret = hyp_create_pcpu_fixmap(); + ret = hyp_create_fixmap(); if (ret) goto out; @@ -304,6 +321,8 @@ void __noreturn __pkvm_init_finalise(void) goto out; pkvm_hyp_vm_table_init(vm_table_base); + + pkvm_ownership_selftest(selftest_base); out: /* * We tail-called to here from handle___pkvm_init() and will not return, diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 7d2ba6ef0261..73affe1333a4 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -33,6 +33,18 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); +struct fgt_masks hfgrtr_masks; +struct fgt_masks hfgwtr_masks; +struct fgt_masks hfgitr_masks; +struct fgt_masks hdfgrtr_masks; +struct fgt_masks hdfgwtr_masks; +struct fgt_masks hafgrtr_masks; +struct fgt_masks hfgrtr2_masks; +struct fgt_masks hfgwtr2_masks; +struct fgt_masks hfgitr2_masks; +struct fgt_masks hdfgrtr2_masks; +struct fgt_masks hdfgwtr2_masks; + extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); static void __activate_cptr_traps(struct kvm_vcpu *vcpu) @@ -142,7 +154,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) __deactivate_traps_common(vcpu); - write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); + write_sysreg_hcr(this_cpu_ptr(&kvm_init_params)->hcr_el2); __deactivate_cptr_traps(vcpu); write_sysreg(__kvm_hyp_host_vector, vbar_el2); diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c index dba101565de3..3cc613cce5f5 100644 --- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c @@ -28,7 +28,9 @@ void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt) void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt) { - __sysreg_restore_el1_state(ctxt, ctxt_sys_reg(ctxt, MPIDR_EL1)); + u64 midr = ctxt_midr_el1(ctxt); + + __sysreg_restore_el1_state(ctxt, midr, ctxt_sys_reg(ctxt, MPIDR_EL1)); __sysreg_restore_common_state(ctxt); __sysreg_restore_user_state(ctxt); __sysreg_restore_el2_return_state(ctxt); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index df5cc74a7dd0..c351b4abd5db 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -11,12 +11,6 @@ #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> - -#define KVM_PTE_TYPE BIT(1) -#define KVM_PTE_TYPE_BLOCK 0 -#define KVM_PTE_TYPE_PAGE 1 -#define KVM_PTE_TYPE_TABLE 1 - struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 3f9741e51d41..f162b0df5cae 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -18,7 +18,7 @@ #define vtr_to_nr_pre_bits(v) ((((u32)(v) >> 26) & 7) + 1) #define vtr_to_nr_apr_regs(v) (1 << (vtr_to_nr_pre_bits(v) - 5)) -static u64 __gic_v3_get_lr(unsigned int lr) +u64 __gic_v3_get_lr(unsigned int lr) { switch (lr & 0xf) { case 0: @@ -218,7 +218,7 @@ void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) elrsr = read_gicreg(ICH_ELRSR_EL2); - write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EN, ICH_HCR_EL2); + write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EL2_En, ICH_HCR_EL2); for (i = 0; i < used_lrs; i++) { if (elrsr & (1 << i)) @@ -274,7 +274,7 @@ void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) * system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1 * so that the trap bits can take effect. Yes, we *loves* the GIC. */ - if (!(cpu_if->vgic_hcr & ICH_HCR_EN)) { + if (!(cpu_if->vgic_hcr & ICH_HCR_EL2_En)) { write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1); isb(); } else if (!cpu_if->vgic_sre) { @@ -429,23 +429,27 @@ u64 __vgic_v3_get_gic_config(void) /* * To check whether we have a MMIO-based (GICv2 compatible) * CPU interface, we need to disable the system register - * view. To do that safely, we have to prevent any interrupt - * from firing (which would be deadly). + * view. * - * Note that this only makes sense on VHE, as interrupts are - * already masked for nVHE as part of the exception entry to - * EL2. - */ - if (has_vhe()) - flags = local_daif_save(); - - /* * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates * that to be able to set ICC_SRE_EL1.SRE to 0, all the * interrupt overrides must be set. You've got to love this. + * + * As we always run VHE with HCR_xMO set, no extra xMO + * manipulation is required in that case. + * + * To safely disable SRE, we have to prevent any interrupt + * from firing (which would be deadly). This only makes sense + * on VHE, as interrupts are already masked for nVHE as part + * of the exception entry to EL2. */ - sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); - isb(); + if (has_vhe()) { + flags = local_daif_save(); + } else { + sysreg_clear_set_hcr(0, HCR_AMO | HCR_FMO | HCR_IMO); + isb(); + } + write_gicreg(0, ICC_SRE_EL1); isb(); @@ -453,11 +457,13 @@ u64 __vgic_v3_get_gic_config(void) write_gicreg(sre, ICC_SRE_EL1); isb(); - sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); - isb(); - if (has_vhe()) + if (has_vhe()) { local_daif_restore(flags); + } else { + sysreg_clear_set_hcr(HCR_AMO | HCR_FMO | HCR_IMO, 0); + isb(); + } val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63); val |= read_gicreg(ICH_VTR_EL2); @@ -752,7 +758,7 @@ static void __vgic_v3_bump_eoicount(void) u32 hcr; hcr = read_gicreg(ICH_HCR_EL2); - hcr += 1 << ICH_HCR_EOIcount_SHIFT; + hcr += 1 << ICH_HCR_EL2_EOIcount_SHIFT; write_gicreg(hcr, ICH_HCR_EL2); } @@ -1052,11 +1058,11 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu, switch (sysreg) { case SYS_ICC_IGRPEN0_EL1: if (is_read && - (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1)) + (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1)) return true; if (!is_read && - (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1)) + (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1)) return true; fallthrough; @@ -1069,15 +1075,15 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu, case SYS_ICC_EOIR0_EL1: case SYS_ICC_HPPIR0_EL1: case SYS_ICC_IAR0_EL1: - return ich_hcr & ICH_HCR_TALL0; + return ich_hcr & ICH_HCR_EL2_TALL0; case SYS_ICC_IGRPEN1_EL1: if (is_read && - (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1)) + (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1)) return true; if (!is_read && - (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1)) + (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1)) return true; fallthrough; @@ -1090,10 +1096,10 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu, case SYS_ICC_EOIR1_EL1: case SYS_ICC_HPPIR1_EL1: case SYS_ICC_IAR1_EL1: - return ich_hcr & ICH_HCR_TALL1; + return ich_hcr & ICH_HCR_EL2_TALL1; case SYS_ICC_DIR_EL1: - if (ich_hcr & ICH_HCR_TDIR) + if (ich_hcr & ICH_HCR_EL2_TDIR) return true; fallthrough; @@ -1101,7 +1107,7 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu, case SYS_ICC_RPR_EL1: case SYS_ICC_CTLR_EL1: case SYS_ICC_PMR_EL1: - return ich_hcr & ICH_HCR_TC; + return ich_hcr & ICH_HCR_EL2_TC; default: return false; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 647737d6e8d0..c9b330dc2066 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -48,21 +48,46 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); static u64 __compute_hcr(struct kvm_vcpu *vcpu) { + u64 guest_hcr = __vcpu_sys_reg(vcpu, HCR_EL2); u64 hcr = vcpu->arch.hcr_el2; if (!vcpu_has_nv(vcpu)) return hcr; + /* + * We rely on the invariant that a vcpu entered from HYP + * context must also exit in the same context, as only an ERET + * instruction can kick us out of it, and we obviously trap + * that sucker. PSTATE.M will get fixed-up on exit. + */ if (is_hyp_ctxt(vcpu)) { + host_data_set_flag(VCPU_IN_HYP_CONTEXT); + hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB; if (!vcpu_el2_e2h_is_set(vcpu)) hcr |= HCR_NV1; write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2); + } else { + host_data_clear_flag(VCPU_IN_HYP_CONTEXT); + + if (guest_hcr & HCR_NV) { + u64 va = __fix_to_virt(vncr_fixmap(smp_processor_id())); + + /* Inherit the low bits from the actual register */ + va |= __vcpu_sys_reg(vcpu, VNCR_EL2) & GENMASK(PAGE_SHIFT - 1, 0); + write_sysreg_s(va, SYS_VNCR_EL2); + + /* Force NV2 in case the guest is forgetful... */ + guest_hcr |= HCR_NV2; + } } - return hcr | (__vcpu_sys_reg(vcpu, HCR_EL2) & ~NV_HCR_GUEST_EXCLUDE); + BUG_ON(host_data_test_flag(VCPU_IN_HYP_CONTEXT) && + host_data_test_flag(L1_VNCR_MAPPED)); + + return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE); } static void __activate_cptr_traps(struct kvm_vcpu *vcpu) @@ -184,7 +209,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) ___deactivate_traps(vcpu); - write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + write_sysreg_hcr(HCR_HOST_VHE_FLAGS); if (has_cntpoff()) { struct timer_map map; @@ -459,6 +484,14 @@ static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code) if (ret) return false; + /* + * If we have to check for any VNCR mapping being invalidated, + * go back to the slow path for further processing. + */ + if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu) && + atomic_read(&vcpu->kvm->arch.vncr_map_count)) + return false; + __kvm_skip_instr(vcpu); return true; @@ -527,6 +560,25 @@ static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code) return kvm_hyp_handle_sysreg(vcpu, exit_code); } +static bool kvm_hyp_handle_impdef(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 iss; + + if (!cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS)) + return false; + + /* + * Compute a synthetic ESR for a sysreg trap. Conveniently, AFSR1_EL2 + * is populated with a correct ISS for a sysreg trap. These fruity + * parts are 64bit only, so unconditionally set IL. + */ + iss = ESR_ELx_ISS(read_sysreg_s(SYS_AFSR1_EL2)); + vcpu->arch.fault.esr_el2 = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SYS64) | + FIELD_PREP(ESR_ELx_ISS_MASK, iss) | + ESR_ELx_IL; + return false; +} + static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, @@ -538,6 +590,9 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, [ESR_ELx_EC_ERET] = kvm_hyp_handle_eret, [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, + + /* Apple shenanigans */ + [0x3F] = kvm_hyp_handle_impdef, }; static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) @@ -546,9 +601,12 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) /* * If we were in HYP context on entry, adjust the PSTATE view - * so that the usual helpers work correctly. + * so that the usual helpers work correctly. This enforces our + * invariant that the guest's HYP context status is preserved + * across a run. */ - if (vcpu_has_nv(vcpu) && (read_sysreg(hcr_el2) & HCR_NV)) { + if (vcpu_has_nv(vcpu) && + unlikely(host_data_test_flag(VCPU_IN_HYP_CONTEXT))) { u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); switch (mode) { @@ -564,6 +622,10 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) *vcpu_cpsr(vcpu) |= mode; } + /* Apply extreme paranoia! */ + BUG_ON(vcpu_has_nv(vcpu) && + !!host_data_test_flag(VCPU_IN_HYP_CONTEXT) != is_hyp_ctxt(vcpu)); + return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers); } diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c index 90b018e06f2c..3814b0b2c937 100644 --- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -87,11 +87,12 @@ static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu) write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1), par_el1); write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1), tpidr_el1); - write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2); - write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR); - write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR); - write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR); - write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR); + write_sysreg(ctxt_midr_el1(&vcpu->arch.ctxt), vpidr_el2); + write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2); + write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR); if (vcpu_el2_e2h_is_set(vcpu)) { /* @@ -191,7 +192,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; - u64 mpidr; + u64 midr, mpidr; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_user_state(host_ctxt); @@ -221,22 +222,17 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) } else { if (vcpu_has_nv(vcpu)) { /* - * Use the guest hypervisor's VPIDR_EL2 when in a - * nested state. The hardware value of MIDR_EL1 gets - * restored on put. - */ - write_sysreg(ctxt_sys_reg(guest_ctxt, VPIDR_EL2), vpidr_el2); - - /* * As we're restoring a nested guest, set the value * provided by the guest hypervisor. */ + midr = ctxt_sys_reg(guest_ctxt, VPIDR_EL2); mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2); } else { + midr = ctxt_midr_el1(guest_ctxt); mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1); } - __sysreg_restore_el1_state(guest_ctxt, mpidr); + __sysreg_restore_el1_state(guest_ctxt, midr, mpidr); } vcpu_set_flag(vcpu, SYSREGS_ON_CPU); @@ -271,9 +267,5 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) /* Restore host user state */ __sysreg_restore_user_state(host_ctxt); - /* If leaving a nesting guest, restore MIDR_EL1 default view */ - if (vcpu_has_nv(vcpu)) - write_sysreg(read_cpuid_id(), vpidr_el2); - vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); } diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c index 3d50a1bd2bdb..ec2569818629 100644 --- a/arch/arm64/kvm/hyp/vhe/tlb.c +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -63,7 +63,7 @@ static void enter_vmid_context(struct kvm_s2_mmu *mmu, __load_stage2(mmu, mmu->arch); val = read_sysreg(hcr_el2); val &= ~HCR_TGE; - write_sysreg(val, hcr_el2); + write_sysreg_hcr(val); isb(); } @@ -73,7 +73,7 @@ static void exit_vmid_context(struct tlb_inv_context *cxt) * We're done with the TLB operation, let's restore the host's * view of HCR_EL2. */ - write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + write_sysreg_hcr(HCR_HOST_VHE_FLAGS); isb(); /* ... and the stage-2 MMU context that we switched away from */ diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 27ce4cb44904..569941eeb3fe 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -15,6 +15,8 @@ GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES \ GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0) +#define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2 \ + GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_2_BIT_COUNT - 1, 0) static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) { @@ -360,6 +362,8 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) break; case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: val[0] = smccc_feat->vendor_hyp_bmap; + /* Function numbers 2-63 are reserved for pKVM for now */ + val[2] = smccc_feat->vendor_hyp_bmap_2; break; case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: kvm_ptp_get_time(vcpu, val); @@ -387,6 +391,7 @@ static const u64 kvm_arm_fw_reg_ids[] = { KVM_REG_ARM_STD_BMAP, KVM_REG_ARM_STD_HYP_BMAP, KVM_REG_ARM_VENDOR_HYP_BMAP, + KVM_REG_ARM_VENDOR_HYP_BMAP_2, }; void kvm_arm_init_hypercalls(struct kvm *kvm) @@ -497,6 +502,9 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) case KVM_REG_ARM_VENDOR_HYP_BMAP: val = READ_ONCE(smccc_feat->vendor_hyp_bmap); break; + case KVM_REG_ARM_VENDOR_HYP_BMAP_2: + val = READ_ONCE(smccc_feat->vendor_hyp_bmap_2); + break; default: return -ENOENT; } @@ -527,6 +535,10 @@ static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) fw_reg_bmap = &smccc_feat->vendor_hyp_bmap; fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; break; + case KVM_REG_ARM_VENDOR_HYP_BMAP_2: + fw_reg_bmap = &smccc_feat->vendor_hyp_bmap_2; + fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2; + break; default: return -ENOENT; } @@ -633,6 +645,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) case KVM_REG_ARM_STD_BMAP: case KVM_REG_ARM_STD_HYP_BMAP: case KVM_REG_ARM_VENDOR_HYP_BMAP: + case KVM_REG_ARM_VENDOR_HYP_BMAP_2: return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val); default: return -ENOENT; diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 1f55b0c7b11d..2942ec92c5a4 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1086,14 +1086,26 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) } } -static void hyp_mc_free_fn(void *addr, void *unused) +static void hyp_mc_free_fn(void *addr, void *mc) { + struct kvm_hyp_memcache *memcache = mc; + + if (memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2) + kvm_account_pgtable_pages(addr, -1); + free_page((unsigned long)addr); } -static void *hyp_mc_alloc_fn(void *unused) +static void *hyp_mc_alloc_fn(void *mc) { - return (void *)__get_free_page(GFP_KERNEL_ACCOUNT); + struct kvm_hyp_memcache *memcache = mc; + void *addr; + + addr = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); + if (addr && memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2) + kvm_account_pgtable_pages(addr, 1); + + return addr; } void free_hyp_memcache(struct kvm_hyp_memcache *mc) @@ -1102,7 +1114,7 @@ void free_hyp_memcache(struct kvm_hyp_memcache *mc) return; kfree(mc->mapping); - __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL); + __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, mc); } int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) @@ -1117,7 +1129,7 @@ int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) } return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn, - kvm_host_pa, NULL); + kvm_host_pa, mc); } /** @@ -1292,6 +1304,10 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, if (map_size == PAGE_SIZE) return true; + /* pKVM only supports PMD_SIZE huge-mappings */ + if (is_protected_kvm_enabled() && map_size != PMD_SIZE) + return false; + size = memslot->npages * PAGE_SIZE; gpa_start = memslot->base_gfn << PAGE_SHIFT; @@ -1489,6 +1505,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } + if (!is_protected_kvm_enabled()) + memcache = &vcpu->arch.mmu_page_cache; + else + memcache = &vcpu->arch.pkvm_memcache; + /* * Permission faults just need to update the existing leaf entry, * and so normally don't require allocations from the memcache. The @@ -1498,13 +1519,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!fault_is_perm || (logging_active && write_fault)) { int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu); - if (!is_protected_kvm_enabled()) { - memcache = &vcpu->arch.mmu_page_cache; + if (!is_protected_kvm_enabled()) ret = kvm_mmu_topup_memory_cache(memcache, min_pages); - } else { - memcache = &vcpu->arch.pkvm_memcache; + else ret = topup_hyp_memcache(memcache, min_pages); - } + if (ret) return ret; } @@ -1525,7 +1544,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * logging_active is guaranteed to never be true for VM_PFNMAP * memslots. */ - if (logging_active || is_protected_kvm_enabled()) { + if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; } else { @@ -1782,9 +1801,28 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) gfn_t gfn; int ret, idx; + /* Synchronous External Abort? */ + if (kvm_vcpu_abt_issea(vcpu)) { + /* + * For RAS the host kernel may handle this abort. + * There is no need to pass the error into the guest. + */ + if (kvm_handle_guest_sea()) + kvm_inject_vabt(vcpu); + + return 1; + } + esr = kvm_vcpu_get_esr(vcpu); + /* + * The fault IPA should be reliable at this point as we're not dealing + * with an SEA. + */ ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); + if (KVM_BUG_ON(ipa == INVALID_GPA, vcpu->kvm)) + return -EFAULT; + is_iabt = kvm_vcpu_trap_is_iabt(vcpu); if (esr_fsc_is_translation_fault(esr)) { @@ -1806,18 +1844,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) } } - /* Synchronous External Abort? */ - if (kvm_vcpu_abt_issea(vcpu)) { - /* - * For RAS the host kernel may handle this abort. - * There is no need to pass the error into the guest. - */ - if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu))) - kvm_inject_vabt(vcpu); - - return 1; - } - trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu), kvm_vcpu_get_hfar(vcpu), fault_ipa); diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 0c9387d2f507..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> @@ -16,8 +17,23 @@ #include "sys_regs.h" -/* Protection against the sysreg repainting madness... */ -#define NV_FTR(r, f) ID_AA64##r##_EL1_##f +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 @@ -31,6 +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) @@ -54,6 +71,17 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) struct kvm_s2_mmu *tmp; int num_mmus, ret = 0; + if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features) && + !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 @@ -84,6 +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; } @@ -404,6 +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 @@ -675,23 +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 @@ -742,6 +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; @@ -754,6 +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) @@ -768,6 +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) @@ -801,140 +1112,446 @@ 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. * This list should get updated as new features get added to the NV * support, and new extension to the architecture. */ -static void limit_nv_id_regs(struct kvm *kvm) +u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val) { - u64 val, tmp; - - /* Support everything but TME */ - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1); - val &= ~NV_FTR(ISAR0, TME); - kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1, val); - - /* Support everything but Spec Invalidation and LS64 */ - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1); - val &= ~(NV_FTR(ISAR1, LS64) | - NV_FTR(ISAR1, SPECRES)); - kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1, val); - - /* No AMU, MPAM, S-EL2, or RAS */ - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1); - val &= ~(GENMASK_ULL(55, 52) | - NV_FTR(PFR0, AMU) | - NV_FTR(PFR0, MPAM) | - NV_FTR(PFR0, SEL2) | - NV_FTR(PFR0, RAS) | - NV_FTR(PFR0, EL3) | - NV_FTR(PFR0, EL2) | - NV_FTR(PFR0, EL1) | - NV_FTR(PFR0, EL0)); - /* 64bit only at any EL */ - val |= FIELD_PREP(NV_FTR(PFR0, EL0), 0b0001); - val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001); - val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001); - val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001); - kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val); - - /* Only support BTI, SSBS, CSV2_frac */ - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1); - val &= (NV_FTR(PFR1, BT) | - NV_FTR(PFR1, SSBS) | - NV_FTR(PFR1, CSV2_frac)); - kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1, val); - - /* Hide ECV, ExS, Secure Memory */ - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1); - val &= ~(NV_FTR(MMFR0, ECV) | - NV_FTR(MMFR0, EXS) | - NV_FTR(MMFR0, TGRAN4_2) | - NV_FTR(MMFR0, TGRAN16_2) | - NV_FTR(MMFR0, TGRAN64_2) | - NV_FTR(MMFR0, SNSMEM)); - - /* Disallow unsupported S2 page sizes */ - switch (PAGE_SIZE) { - case SZ_64K: - val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0001); - fallthrough; - case SZ_16K: - val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0001); - fallthrough; - case SZ_4K: - /* Support everything */ + switch (reg) { + case SYS_ID_AA64ISAR0_EL1: + /* Support everything but TME */ + val &= ~ID_AA64ISAR0_EL1_TME; break; - } - /* - * Since we can't support a guest S2 page size smaller than - * the host's own page size (due to KVM only populating its - * own S2 using the kernel's page size), advertise the - * limitation using FEAT_GTG. - */ - switch (PAGE_SIZE) { - case SZ_4K: - val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0010); - fallthrough; - case SZ_16K: - val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0010); - fallthrough; - case SZ_64K: - val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN64_2), 0b0010); + + case SYS_ID_AA64ISAR1_EL1: + /* Support everything but LS64 and Spec Invalidation */ + val &= ~(ID_AA64ISAR1_EL1_LS64 | + ID_AA64ISAR1_EL1_SPECRES); + break; + + case SYS_ID_AA64PFR0_EL1: + /* No RME, AMU, MPAM, S-EL2, or RAS */ + val &= ~(ID_AA64PFR0_EL1_RME | + ID_AA64PFR0_EL1_AMU | + ID_AA64PFR0_EL1_MPAM | + ID_AA64PFR0_EL1_SEL2 | + ID_AA64PFR0_EL1_RAS | + ID_AA64PFR0_EL1_EL3 | + ID_AA64PFR0_EL1_EL2 | + ID_AA64PFR0_EL1_EL1 | + ID_AA64PFR0_EL1_EL0); + /* 64bit only at any EL */ + val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL0, IMP); + val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL1, IMP); + val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL2, IMP); + val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL3, IMP); + break; + + case SYS_ID_AA64PFR1_EL1: + /* Only support BTI, SSBS, CSV2_frac */ + val &= (ID_AA64PFR1_EL1_BT | + ID_AA64PFR1_EL1_SSBS | + ID_AA64PFR1_EL1_CSV2_frac); + break; + + case SYS_ID_AA64MMFR0_EL1: + /* Hide ExS, Secure Memory */ + val &= ~(ID_AA64MMFR0_EL1_EXS | + ID_AA64MMFR0_EL1_TGRAN4_2 | + ID_AA64MMFR0_EL1_TGRAN16_2 | + ID_AA64MMFR0_EL1_TGRAN64_2 | + ID_AA64MMFR0_EL1_SNSMEM); + + /* Hide CNTPOFF if present */ + val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, ECV, IMP); + + /* Disallow unsupported S2 page sizes */ + switch (PAGE_SIZE) { + case SZ_64K: + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, NI); + fallthrough; + case SZ_16K: + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, NI); + fallthrough; + case SZ_4K: + /* Support everything */ + break; + } + + /* + * Since we can't support a guest S2 page size smaller + * than the host's own page size (due to KVM only + * populating its own S2 using the kernel's page + * size), advertise the limitation using FEAT_GTG. + */ + switch (PAGE_SIZE) { + case SZ_4K: + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP); + fallthrough; + case SZ_16K: + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP); + fallthrough; + case SZ_64K: + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP); + break; + } + + /* Cap PARange to 48bits */ + val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, PARANGE, 48); + break; + + case SYS_ID_AA64MMFR1_EL1: + val &= (ID_AA64MMFR1_EL1_HCX | + ID_AA64MMFR1_EL1_PAN | + ID_AA64MMFR1_EL1_LO | + ID_AA64MMFR1_EL1_HPDS | + ID_AA64MMFR1_EL1_VH | + ID_AA64MMFR1_EL1_VMIDBits); + /* FEAT_E2H0 implies no VHE */ + if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) + val &= ~ID_AA64MMFR1_EL1_VH; + break; + + case SYS_ID_AA64MMFR2_EL1: + val &= ~(ID_AA64MMFR2_EL1_BBM | + ID_AA64MMFR2_EL1_TTL | + GENMASK_ULL(47, 44) | + ID_AA64MMFR2_EL1_ST | + ID_AA64MMFR2_EL1_CCIDX | + ID_AA64MMFR2_EL1_VARange); + + /* Force TTL support */ + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR2_EL1, TTL, IMP); + break; + + case SYS_ID_AA64MMFR4_EL1: + /* + * You get EITHER + * + * - FEAT_VHE without FEAT_E2H0 + * - FEAT_NV limited to FEAT_NV2 + * - HCR_EL2.NV1 being RES0 + * + * OR + * + * - FEAT_E2H0 without FEAT_VHE nor FEAT_NV + * + * Life is too short for anything else. + */ + if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) { + val = 0; + } else { + val = SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY); + val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI_NV1); + } + break; + + case SYS_ID_AA64DFR0_EL1: + /* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */ + val &= (ID_AA64DFR0_EL1_PMUVer | + ID_AA64DFR0_EL1_WRPs | + ID_AA64DFR0_EL1_BRPs | + ID_AA64DFR0_EL1_DebugVer| + ID_AA64DFR0_EL1_HPMN0); + + /* Cap Debug to ARMv8.1 */ + val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, VHE); break; } - /* Cap PARange to 48bits */ - tmp = FIELD_GET(NV_FTR(MMFR0, PARANGE), val); - if (tmp > 0b0101) { - val &= ~NV_FTR(MMFR0, PARANGE); - val |= FIELD_PREP(NV_FTR(MMFR0, PARANGE), 0b0101); - } - kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1, val); - - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1); - val &= (NV_FTR(MMFR1, HCX) | - NV_FTR(MMFR1, PAN) | - NV_FTR(MMFR1, LO) | - NV_FTR(MMFR1, HPDS) | - NV_FTR(MMFR1, VH) | - NV_FTR(MMFR1, VMIDBits)); - kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1, val); - - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1); - val &= ~(NV_FTR(MMFR2, BBM) | - NV_FTR(MMFR2, TTL) | - GENMASK_ULL(47, 44) | - NV_FTR(MMFR2, ST) | - NV_FTR(MMFR2, CCIDX) | - NV_FTR(MMFR2, VARange)); - - /* Force TTL support */ - val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001); - kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1, val); - - val = 0; - if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1)) - val |= FIELD_PREP(NV_FTR(MMFR4, E2H0), - ID_AA64MMFR4_EL1_E2H0_NI_NV1); - kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR4_EL1, val); - - /* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */ - val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1); - val &= (NV_FTR(DFR0, PMUVer) | - NV_FTR(DFR0, WRPs) | - NV_FTR(DFR0, BRPs) | - NV_FTR(DFR0, DebugVer) | - NV_FTR(DFR0, HPMN0)); - - /* Cap Debug to ARMv8.1 */ - tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val); - if (tmp > 0b0111) { - val &= ~NV_FTR(DFR0, DebugVer); - val |= FIELD_PREP(NV_FTR(DFR0, DebugVer), 0b0111); - } - kvm_set_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1, val); + + return val; } u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu, @@ -981,8 +1598,6 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) if (!kvm->arch.sysreg_masks) return -ENOMEM; - limit_nv_id_regs(kvm); - /* VTTBR_EL2 */ res0 = res1 = 0; if (!kvm_has_feat_enum(kvm, ID_AA64MMFR1_EL1, VMIDBits, 16)) @@ -1002,213 +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; - if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, NV2)) - res0 |= HCR_NV2; - if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, IMP)) - res0 |= (HCR_AT | HCR_NV1 | HCR_NV); - 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_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; @@ -1290,6 +1741,18 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) res0 |= GENMASK(11, 8); set_sysreg_masks(kvm, CNTHCTL_EL2, res0, res1); + /* ICH_HCR_EL2 */ + res0 = ICH_HCR_EL2_RES0; + res1 = ICH_HCR_EL2_RES1; + if (!(kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_TDS)) + res0 |= ICH_HCR_EL2_TDIR; + /* No GICv4 is presented to the guest */ + 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); @@ -1309,4 +1772,11 @@ 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); } diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 930b677eb9b0..fcd70bfe44fb 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -5,12 +5,12 @@ */ #include <linux/init.h> +#include <linux/interval_tree_generic.h> #include <linux/kmemleak.h> #include <linux/kvm_host.h> #include <asm/kvm_mmu.h> #include <linux/memblock.h> #include <linux/mutex.h> -#include <linux/sort.h> #include <asm/kvm_pkvm.h> @@ -24,23 +24,6 @@ static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr); phys_addr_t hyp_mem_base; phys_addr_t hyp_mem_size; -static int cmp_hyp_memblock(const void *p1, const void *p2) -{ - const struct memblock_region *r1 = p1; - const struct memblock_region *r2 = p2; - - return r1->base < r2->base ? -1 : (r1->base > r2->base); -} - -static void __init sort_memblock_regions(void) -{ - sort(hyp_memory, - *hyp_memblock_nr_ptr, - sizeof(struct memblock_region), - cmp_hyp_memblock, - NULL); -} - static int __init register_memblock_regions(void) { struct memblock_region *reg; @@ -52,7 +35,6 @@ static int __init register_memblock_regions(void) hyp_memory[*hyp_memblock_nr_ptr] = *reg; (*hyp_memblock_nr_ptr)++; } - sort_memblock_regions(); return 0; } @@ -79,6 +61,7 @@ void __init kvm_hyp_reserve(void) hyp_mem_pages += host_s2_pgtable_pages(); hyp_mem_pages += hyp_vm_table_pages(); hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE); + hyp_mem_pages += pkvm_selftest_pages(); hyp_mem_pages += hyp_ffa_proxy_pages(); /* @@ -111,6 +94,29 @@ static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm) host_kvm->arch.pkvm.handle = 0; free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); + free_hyp_memcache(&host_kvm->arch.pkvm.stage2_teardown_mc); +} + +static int __pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu) +{ + size_t hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE); + pkvm_handle_t handle = vcpu->kvm->arch.pkvm.handle; + void *hyp_vcpu; + int ret; + + vcpu->arch.pkvm_memcache.flags |= HYP_MEMCACHE_ACCOUNT_STAGE2; + + hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT); + if (!hyp_vcpu) + return -ENOMEM; + + ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, vcpu, hyp_vcpu); + if (!ret) + vcpu_set_flag(vcpu, VCPU_PKVM_FINALIZED); + else + free_pages_exact(hyp_vcpu, hyp_vcpu_sz); + + return ret; } /* @@ -125,11 +131,8 @@ static void __pkvm_destroy_hyp_vm(struct kvm *host_kvm) */ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) { - size_t pgd_sz, hyp_vm_sz, hyp_vcpu_sz; - struct kvm_vcpu *host_vcpu; - pkvm_handle_t handle; + size_t pgd_sz, hyp_vm_sz; void *pgd, *hyp_vm; - unsigned long idx; int ret; if (host_kvm->created_vcpus < 1) @@ -161,40 +164,11 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) if (ret < 0) goto free_vm; - handle = ret; - - host_kvm->arch.pkvm.handle = handle; - - /* Donate memory for the vcpus at hyp and initialize it. */ - hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE); - kvm_for_each_vcpu(idx, host_vcpu, host_kvm) { - void *hyp_vcpu; - - /* Indexing of the vcpus to be sequential starting at 0. */ - if (WARN_ON(host_vcpu->vcpu_idx != idx)) { - ret = -EINVAL; - goto destroy_vm; - } - - hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT); - if (!hyp_vcpu) { - ret = -ENOMEM; - goto destroy_vm; - } - - ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, host_vcpu, - hyp_vcpu); - if (ret) { - free_pages_exact(hyp_vcpu, hyp_vcpu_sz); - goto destroy_vm; - } - } + host_kvm->arch.pkvm.handle = ret; + host_kvm->arch.pkvm.stage2_teardown_mc.flags |= HYP_MEMCACHE_ACCOUNT_STAGE2; + kvm_account_pgtable_pages(pgd, pgd_sz / PAGE_SIZE); return 0; - -destroy_vm: - __pkvm_destroy_hyp_vm(host_kvm); - return ret; free_vm: free_pages_exact(hyp_vm, hyp_vm_sz); free_pgd: @@ -214,6 +188,18 @@ int pkvm_create_hyp_vm(struct kvm *host_kvm) return ret; } +int pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu) +{ + int ret = 0; + + mutex_lock(&vcpu->kvm->arch.config_lock); + if (!vcpu_get_flag(vcpu, VCPU_PKVM_FINALIZED)) + ret = __pkvm_create_hyp_vcpu(vcpu); + mutex_unlock(&vcpu->kvm->arch.config_lock); + + return ret; +} + void pkvm_destroy_hyp_vm(struct kvm *host_kvm) { mutex_lock(&host_kvm->arch.config_lock); @@ -259,6 +245,7 @@ static int __init finalize_pkvm(void) * at, which would end badly once inaccessible. */ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); + kmemleak_free_part(__hyp_data_start, __hyp_data_end - __hyp_data_start); kmemleak_free_part(__hyp_rodata_start, __hyp_rodata_end - __hyp_rodata_start); kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size); @@ -270,80 +257,68 @@ static int __init finalize_pkvm(void) } device_initcall_sync(finalize_pkvm); -static int cmp_mappings(struct rb_node *node, const struct rb_node *parent) +static u64 __pkvm_mapping_start(struct pkvm_mapping *m) { - struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node); - struct pkvm_mapping *b = rb_entry(parent, struct pkvm_mapping, node); - - if (a->gfn < b->gfn) - return -1; - if (a->gfn > b->gfn) - return 1; - return 0; + return m->gfn * PAGE_SIZE; } -static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn) +static u64 __pkvm_mapping_end(struct pkvm_mapping *m) { - struct rb_node *node = root->rb_node, *prev = NULL; - struct pkvm_mapping *mapping; - - while (node) { - mapping = rb_entry(node, struct pkvm_mapping, node); - if (mapping->gfn == gfn) - return node; - prev = node; - node = (gfn < mapping->gfn) ? node->rb_left : node->rb_right; - } - - return prev; + return (m->gfn + m->nr_pages) * PAGE_SIZE - 1; } +INTERVAL_TREE_DEFINE(struct pkvm_mapping, node, u64, __subtree_last, + __pkvm_mapping_start, __pkvm_mapping_end, static, + pkvm_mapping); + /* - * __tmp is updated to rb_next(__tmp) *before* entering the body of the loop to allow freeing - * of __map inline. + * __tmp is updated to iter_first(pkvm_mappings) *before* entering the body of the loop to allow + * freeing of __map inline. */ #define for_each_mapping_in_range_safe(__pgt, __start, __end, __map) \ - for (struct rb_node *__tmp = find_first_mapping_node(&(__pgt)->pkvm_mappings, \ - ((__start) >> PAGE_SHIFT)); \ + for (struct pkvm_mapping *__tmp = pkvm_mapping_iter_first(&(__pgt)->pkvm_mappings, \ + __start, __end - 1); \ __tmp && ({ \ - __map = rb_entry(__tmp, struct pkvm_mapping, node); \ - __tmp = rb_next(__tmp); \ + __map = __tmp; \ + __tmp = pkvm_mapping_iter_next(__map, __start, __end - 1); \ true; \ }); \ - ) \ - if (__map->gfn < ((__start) >> PAGE_SHIFT)) \ - continue; \ - else if (__map->gfn >= ((__end) >> PAGE_SHIFT)) \ - break; \ - else + ) int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops) { - pgt->pkvm_mappings = RB_ROOT; + pgt->pkvm_mappings = RB_ROOT_CACHED; pgt->mmu = mmu; return 0; } -void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) +static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 end) { struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); pkvm_handle_t handle = kvm->arch.pkvm.handle; struct pkvm_mapping *mapping; - struct rb_node *node; + int ret; if (!handle) - return; + return 0; - node = rb_first(&pgt->pkvm_mappings); - while (node) { - mapping = rb_entry(node, struct pkvm_mapping, node); - kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn); - node = rb_next(node); - rb_erase(&mapping->node, &pgt->pkvm_mappings); + for_each_mapping_in_range_safe(pgt, start, end, mapping) { + ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn, + mapping->nr_pages); + if (WARN_ON(ret)) + return ret; + pkvm_mapping_remove(mapping, &pgt->pkvm_mappings); kfree(mapping); } + + return 0; +} + +void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) +{ + __pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL)); } int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, @@ -357,42 +332,46 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 pfn = phys >> PAGE_SHIFT; int ret; - if (size != PAGE_SIZE) + if (size != PAGE_SIZE && size != PMD_SIZE) return -EINVAL; lockdep_assert_held_write(&kvm->mmu_lock); - ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot); - if (ret) { - /* Is the gfn already mapped due to a racing vCPU? */ - if (ret == -EPERM) + + /* + * Calling stage2_map() on top of existing mappings is either happening because of a race + * with another vCPU, or because we're changing between page and block mappings. As per + * user_mem_abort(), same-size permission faults are handled in the relax_perms() path. + */ + mapping = pkvm_mapping_iter_first(&pgt->pkvm_mappings, addr, addr + size - 1); + if (mapping) { + if (size == (mapping->nr_pages * PAGE_SIZE)) return -EAGAIN; + + /* Remove _any_ pkvm_mapping overlapping with the range, bigger or smaller. */ + ret = __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size); + if (ret) + return ret; + mapping = NULL; } + ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, size / PAGE_SIZE, prot); + if (WARN_ON(ret)) + return ret; + swap(mapping, cache->mapping); mapping->gfn = gfn; mapping->pfn = pfn; - WARN_ON(rb_find_add(&mapping->node, &pgt->pkvm_mappings, cmp_mappings)); + mapping->nr_pages = size / PAGE_SIZE; + pkvm_mapping_insert(mapping, &pgt->pkvm_mappings); return ret; } int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { - struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu); - pkvm_handle_t handle = kvm->arch.pkvm.handle; - struct pkvm_mapping *mapping; - int ret = 0; + lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(pgt->mmu)->mmu_lock); - lockdep_assert_held_write(&kvm->mmu_lock); - for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) { - ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn); - if (WARN_ON(ret)) - break; - rb_erase(&mapping->node, &pgt->pkvm_mappings); - kfree(mapping); - } - - return ret; + return __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size); } int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) @@ -404,7 +383,8 @@ int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) lockdep_assert_held(&kvm->mmu_lock); for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) { - ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn); + ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn, + mapping->nr_pages); if (WARN_ON(ret)) break; } @@ -419,7 +399,8 @@ int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) lockdep_assert_held(&kvm->mmu_lock); for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) - __clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE); + __clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), + PAGE_SIZE * mapping->nr_pages); return 0; } @@ -434,7 +415,7 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 lockdep_assert_held(&kvm->mmu_lock); for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn, - mkold); + mapping->nr_pages, mkold); return young; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 6c5950b9ceac..25c29107f13f 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -17,8 +17,6 @@ #define PERF_ATTR_CFG1_COUNTER_64BIT BIT(0) -DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available); - static LIST_HEAD(arm_pmus); static DEFINE_MUTEX(arm_pmus_lock); @@ -26,6 +24,12 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc); +bool kvm_supports_guest_pmuv3(void) +{ + guard(mutex)(&arm_pmus_lock); + return !list_empty(&arm_pmus); +} + static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]); @@ -150,9 +154,6 @@ static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc) */ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) { - if (!kvm_vcpu_has_pmu(vcpu)) - return 0; - return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); } @@ -191,13 +192,23 @@ static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force) */ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { - if (!kvm_vcpu_has_pmu(vcpu)) - return; - kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false); } /** + * kvm_pmu_set_counter_value_user - set PMU counter value from user + * @vcpu: The vcpu pointer + * @select_idx: The counter index + * @val: The counter value + */ +void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) +{ + kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); + __vcpu_sys_reg(vcpu, counter_index_to_reg(select_idx)) = val; + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); +} + +/** * kvm_pmu_release_perf_event - remove the perf event * @pmc: The PMU counter pointer */ @@ -248,20 +259,6 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) } /** - * kvm_pmu_vcpu_reset - reset pmu state for cpu - * @vcpu: The vcpu pointer - * - */ -void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) -{ - unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu); - int i; - - for_each_set_bit(i, &mask, 32) - kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i)); -} - -/** * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu * @vcpu: The vcpu pointer * @@ -283,7 +280,7 @@ static u64 kvm_pmu_hyp_counter_mask(struct kvm_vcpu *vcpu) return 0; hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2)); - n = vcpu->kvm->arch.pmcr_n; + n = vcpu->kvm->arch.nr_pmu_counters; /* * Programming HPMN to a value greater than PMCR_EL0.N is @@ -350,7 +347,7 @@ void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; - if (!kvm_vcpu_has_pmu(vcpu) || !val) + if (!val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { @@ -401,9 +398,6 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = &vcpu->arch.pmu; bool overflow; - if (!kvm_vcpu_has_pmu(vcpu)) - return; - overflow = kvm_pmu_overflow_status(vcpu); if (pmu->irq_level == overflow) return; @@ -599,9 +593,6 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; - if (!kvm_vcpu_has_pmu(vcpu)) - return; - /* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */ if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; @@ -617,14 +608,12 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { - /* - * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply - * to the 'guest' range of counters and never the 'hyp' range. - */ unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & - ~kvm_pmu_hyp_counter_mask(vcpu) & ~BIT(ARMV8_PMU_CYCLE_IDX); + if (!vcpu_is_el2(vcpu)) + mask &= ~kvm_pmu_hyp_counter_mask(vcpu); + for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } @@ -673,6 +662,20 @@ static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc) return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2; } +static int kvm_map_pmu_event(struct kvm *kvm, unsigned int eventsel) +{ + struct arm_pmu *pmu = kvm->arch.arm_pmu; + + /* + * The CPU PMU likely isn't PMUv3; let the driver provide a mapping + * for the guest's PMUv3 event ID. + */ + if (unlikely(pmu->map_pmuv3_event)) + return pmu->map_pmuv3_event(eventsel); + + return eventsel; +} + /** * kvm_pmu_create_perf_event - create a perf event for a counter * @pmc: Counter context @@ -683,7 +686,8 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu; struct perf_event *event; struct perf_event_attr attr; - u64 eventsel, evtreg; + int eventsel; + u64 evtreg; evtreg = kvm_pmc_read_evtreg(pmc); @@ -709,6 +713,14 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) !test_bit(eventsel, vcpu->kvm->arch.pmu_filter)) return; + /* + * Don't create an event if we're running on hardware that requires + * PMUv3 event translation and we couldn't find a valid mapping. + */ + eventsel = kvm_map_pmu_event(vcpu->kvm, eventsel); + if (eventsel < 0) + return; + memset(&attr, 0, sizeof(struct perf_event_attr)); attr.type = arm_pmu->pmu.type; attr.size = sizeof(attr); @@ -766,9 +778,6 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx); u64 reg; - if (!kvm_vcpu_has_pmu(vcpu)) - return; - reg = counter_index_to_evtreg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm); @@ -786,29 +795,23 @@ void kvm_host_pmu_init(struct arm_pmu *pmu) if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit())) return; - mutex_lock(&arm_pmus_lock); + guard(mutex)(&arm_pmus_lock); entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) - goto out_unlock; + return; entry->arm_pmu = pmu; list_add_tail(&entry->entry, &arm_pmus); - - if (list_is_singular(&arm_pmus)) - static_branch_enable(&kvm_arm_pmu_available); - -out_unlock: - mutex_unlock(&arm_pmus_lock); } static struct arm_pmu *kvm_pmu_probe_armpmu(void) { - struct arm_pmu *tmp, *pmu = NULL; struct arm_pmu_entry *entry; + struct arm_pmu *pmu; int cpu; - mutex_lock(&arm_pmus_lock); + guard(mutex)(&arm_pmus_lock); /* * It is safe to use a stale cpu to iterate the list of PMUs so long as @@ -829,42 +832,62 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void) */ cpu = raw_smp_processor_id(); list_for_each_entry(entry, &arm_pmus, entry) { - tmp = entry->arm_pmu; + pmu = entry->arm_pmu; - if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) { - pmu = tmp; - break; - } + if (cpumask_test_cpu(cpu, &pmu->supported_cpus)) + return pmu; } - mutex_unlock(&arm_pmus_lock); + return NULL; +} + +static u64 __compute_pmceid(struct arm_pmu *pmu, bool pmceid1) +{ + u32 hi[2], lo[2]; + + bitmap_to_arr32(lo, pmu->pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); + bitmap_to_arr32(hi, pmu->pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); + + return ((u64)hi[pmceid1] << 32) | lo[pmceid1]; +} + +static u64 compute_pmceid0(struct arm_pmu *pmu) +{ + u64 val = __compute_pmceid(pmu, 0); - return pmu; + /* always support SW_INCR */ + val |= BIT(ARMV8_PMUV3_PERFCTR_SW_INCR); + /* always support CHAIN */ + val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN); + return val; +} + +static u64 compute_pmceid1(struct arm_pmu *pmu) +{ + u64 val = __compute_pmceid(pmu, 1); + + /* + * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled + * as RAZ + */ + val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) | + BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) | + BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32)); + return val; } u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { + struct arm_pmu *cpu_pmu = vcpu->kvm->arch.arm_pmu; unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; int base, i, nr_events; - if (!kvm_vcpu_has_pmu(vcpu)) - return 0; - if (!pmceid1) { - val = read_sysreg(pmceid0_el0); - /* always support CHAIN */ - val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN); + val = compute_pmceid0(cpu_pmu); base = 0; } else { - val = read_sysreg(pmceid1_el0); - /* - * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled - * as RAZ - */ - val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) | - BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) | - BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32)); + val = compute_pmceid1(cpu_pmu); base = 32; } @@ -900,9 +923,6 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { - if (!kvm_vcpu_has_pmu(vcpu)) - return 0; - if (!vcpu->arch.pmu.created) return -EINVAL; @@ -925,9 +945,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) return -EINVAL; } - /* One-off reload of the PMU on first run */ - kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); - return 0; } @@ -995,18 +1012,43 @@ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm) struct arm_pmu *arm_pmu = kvm->arch.arm_pmu; /* + * PMUv3 requires that all event counters are capable of counting any + * event, though the same may not be true of non-PMUv3 hardware. + */ + if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS)) + return 1; + + /* * The arm_pmu->cntr_mask considers the fixed counter(s) as well. * Ignore those and return only the general-purpose counters. */ return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS); } +static void kvm_arm_set_nr_counters(struct kvm *kvm, unsigned int nr) +{ + kvm->arch.nr_pmu_counters = nr; + + /* Reset MDCR_EL2.HPMN behind the vcpus' back... */ + if (test_bit(KVM_ARM_VCPU_HAS_EL2, kvm->arch.vcpu_features)) { + struct kvm_vcpu *vcpu; + unsigned long i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2); + val &= ~MDCR_EL2_HPMN; + val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters); + __vcpu_sys_reg(vcpu, MDCR_EL2) = val; + } + } +} + static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu) { lockdep_assert_held(&kvm->arch.config_lock); kvm->arch.arm_pmu = arm_pmu; - kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm); + kvm_arm_set_nr_counters(kvm, kvm_arm_pmu_get_max_counters(kvm)); } /** @@ -1062,6 +1104,20 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) return ret; } +static int kvm_arm_pmu_v3_set_nr_counters(struct kvm_vcpu *vcpu, unsigned int n) +{ + struct kvm *kvm = vcpu->kvm; + + if (!kvm->arch.arm_pmu) + return -EINVAL; + + if (n > kvm_arm_pmu_get_max_counters(kvm)) + return -EINVAL; + + kvm_arm_set_nr_counters(kvm, n); + return 0; +} + int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { struct kvm *kvm = vcpu->kvm; @@ -1158,6 +1214,15 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id); } + case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS: { + unsigned int __user *uaddr = (unsigned int __user *)(long)attr->addr; + unsigned int n; + + if (get_user(n, uaddr)) + return -EFAULT; + + return kvm_arm_pmu_v3_set_nr_counters(vcpu, n); + } case KVM_ARM_VCPU_PMU_V3_INIT: return kvm_arm_pmu_v3_init(vcpu); } @@ -1196,6 +1261,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) case KVM_ARM_VCPU_PMU_V3_INIT: case KVM_ARM_VCPU_PMU_V3_FILTER: case KVM_ARM_VCPU_PMU_V3_SET_PMU: + case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS: if (kvm_vcpu_has_pmu(vcpu)) return 0; } @@ -1205,13 +1271,26 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) u8 kvm_arm_pmu_get_pmuver_limit(void) { - u64 tmp; + unsigned int pmuver; + + pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, + read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1)); - tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); - tmp = cpuid_feature_cap_perfmon_field(tmp, - ID_AA64DFR0_EL1_PMUVer_SHIFT, - ID_AA64DFR0_EL1_PMUVer_V3P5); - return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); + /* + * Spoof a barebones PMUv3 implementation if the system supports IMPDEF + * traps of the PMUv3 sysregs + */ + if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS)) + return ID_AA64DFR0_EL1_PMUVer_IMP; + + /* + * Otherwise, treat IMPLEMENTATION DEFINED functionality as + * unimplemented + */ + if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) + return 0; + + return min(pmuver, ID_AA64DFR0_EL1_PMUVer_V3P5); } /** @@ -1221,8 +1300,12 @@ 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); + u64 n = vcpu->kvm->arch.nr_pmu_counters; + + if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu)) + n = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2)); - return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N); + return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N); } void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu) @@ -1231,9 +1314,6 @@ void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu) unsigned long mask; int i; - if (!kvm_vcpu_has_pmu(vcpu)) - return; - mask = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); for_each_set_bit(i, &mask, 32) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 0b3adf3e17b4..6b48a3d16d0d 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -41,7 +41,7 @@ void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr)) + if (!system_supports_pmuv3() || !kvm_pmu_switch_needed(attr)) return; if (!attr->exclude_host) @@ -57,7 +57,7 @@ void kvm_clr_pmu_events(u64 clr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3()) + if (!system_supports_pmuv3()) return; pmu->events_host &= ~clr; @@ -133,7 +133,7 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) struct kvm_pmu_events *pmu; u64 events_guest, events_host; - if (!kvm_arm_support_pmu_v3() || !has_vhe()) + if (!system_supports_pmuv3() || !has_vhe()) return; preempt_disable(); @@ -154,7 +154,7 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) struct kvm_pmu_events *pmu; u64 events_guest, events_host; - if (!kvm_arm_support_pmu_v3() || !has_vhe()) + if (!system_supports_pmuv3() || !has_vhe()) return; pmu = kvm_get_pmu_events(); @@ -180,7 +180,7 @@ bool kvm_set_pmuserenr(u64 val) struct kvm_cpu_context *hctxt; struct kvm_vcpu *vcpu; - if (!kvm_arm_support_pmu_v3() || !has_vhe()) + if (!system_supports_pmuv3() || !has_vhe()) return false; vcpu = kvm_get_running_vcpu(); diff --git a/arch/arm64/kvm/ptdump.c b/arch/arm64/kvm/ptdump.c index e4a342e903e2..098416d7e5c2 100644 --- a/arch/arm64/kvm/ptdump.c +++ b/arch/arm64/kvm/ptdump.c @@ -52,8 +52,8 @@ static const struct ptdump_prot_bits stage2_pte_bits[] = { .set = "AF", .clear = " ", }, { - .mask = PTE_TABLE_BIT | PTE_VALID, - .val = PTE_VALID, + .mask = PMD_TYPE_MASK, + .val = PMD_TYPE_SECT, .set = "BLK", .clear = " ", }, diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 803e11b0dc8f..959532422d3a 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -158,6 +158,8 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) if (sve_state) kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); kfree(sve_state); + free_page((unsigned long)vcpu->arch.ctxt.vncr_array); + kfree(vcpu->arch.vncr_tlb); kfree(vcpu->arch.ccsidr); } @@ -196,9 +198,6 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.reset_state.reset = false; spin_unlock(&vcpu->arch.mp_state_lock); - /* Reset PMU outside of the non-preemptible section */ - kvm_pmu_vcpu_reset(vcpu); - preempt_disable(); loaded = (vcpu->cpu != -1); if (loaded) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 82430c1e1dd0..a6cf2888d150 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -17,6 +17,7 @@ #include <linux/mm.h> #include <linux/printk.h> #include <linux/uaccess.h> +#include <linux/irqchip/arm-gic-v3.h> #include <asm/arm_pmuv3.h> #include <asm/cacheflush.h> @@ -531,7 +532,13 @@ static bool access_gic_sre(struct kvm_vcpu *vcpu, if (p->is_write) return ignore_write(vcpu, p); - p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre; + if (p->Op1 == 4) { /* ICC_SRE_EL2 */ + p->regval = (ICC_SRE_EL2_ENABLE | ICC_SRE_EL2_SRE | + ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB); + } else { /* ICC_SRE_EL1 */ + p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre; + } + return true; } @@ -778,7 +785,7 @@ static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 mask = BIT(ARMV8_PMU_CYCLE_IDX); - u8 n = vcpu->kvm->arch.pmcr_n; + u8 n = vcpu->kvm->arch.nr_pmu_counters; if (n) mask |= GENMASK(n - 1, 0); @@ -960,6 +967,22 @@ static int get_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, return 0; } +static int set_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, + u64 val) +{ + u64 idx; + + if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 0) + /* PMCCNTR_EL0 */ + idx = ARMV8_PMU_CYCLE_IDX; + else + /* PMEVCNTRn_EL0 */ + idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); + + kvm_pmu_set_counter_value_user(vcpu, idx, val); + return 0; +} + static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) @@ -1051,25 +1074,10 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { - bool set; - - val &= kvm_pmu_accessible_counter_mask(vcpu); - - switch (r->reg) { - case PMOVSSET_EL0: - /* CRm[1] being set indicates a SET register, and CLR otherwise */ - set = r->CRm & 2; - break; - default: - /* Op2[0] being set indicates a SET register, and CLR otherwise */ - set = r->Op2 & 1; - break; - } + u64 mask = kvm_pmu_accessible_counter_mask(vcpu); - if (set) - __vcpu_sys_reg(vcpu, r->reg) |= val; - else - __vcpu_sys_reg(vcpu, r->reg) &= ~val; + __vcpu_sys_reg(vcpu, r->reg) = val & mask; + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return 0; } @@ -1208,8 +1216,9 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, * with the existing KVM behavior. */ if (!kvm_vm_has_ran_once(kvm) && + !vcpu_has_nv(vcpu) && new_n <= kvm_arm_pmu_get_max_counters(kvm)) - kvm->arch.pmcr_n = new_n; + kvm->arch.nr_pmu_counters = new_n; mutex_unlock(&kvm->arch.config_lock); @@ -1229,6 +1238,8 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, val |= ARMV8_PMU_PMCR_LC; __vcpu_sys_reg(vcpu, r->reg) = val; + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + return 0; } @@ -1255,6 +1266,7 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, #define PMU_PMEVCNTR_EL0(n) \ { PMU_SYS_REG(PMEVCNTRn_EL0(n)), \ .reset = reset_pmevcntr, .get_user = get_pmu_evcntr, \ + .set_user = set_pmu_evcntr, \ .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), } /* Macro to expand the PMEVTYPERn_EL0 register */ @@ -1589,13 +1601,14 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, val = sanitise_id_aa64pfr0_el1(vcpu, val); break; case SYS_ID_AA64PFR1_EL1: - if (!kvm_has_mte(vcpu->kvm)) + if (!kvm_has_mte(vcpu->kvm)) { val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE); + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac); + } val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI); - val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX); @@ -1627,6 +1640,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, break; case SYS_ID_AA64MMFR2_EL1: val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; + val &= ~ID_AA64MMFR2_EL1_NV; break; case SYS_ID_AA64MMFR3_EL1: val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE | @@ -1637,6 +1651,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, break; } + if (vcpu_has_nv(vcpu)) + val = limit_nv_id_reg(vcpu->kvm, id, val); + return val; } @@ -1663,15 +1680,24 @@ static bool is_feature_id_reg(u32 encoding) * Return true if the register's (Op0, Op1, CRn, CRm, Op2) is * (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8, which is the range of ID * registers KVM maintains on a per-VM basis. + * + * Additionally, the implementation ID registers and CTR_EL0 are handled as + * per-VM registers. */ static inline bool is_vm_ftr_id_reg(u32 id) { - if (id == SYS_CTR_EL0) + switch (id) { + case SYS_CTR_EL0: + case SYS_MIDR_EL1: + case SYS_REVIDR_EL1: + case SYS_AIDR_EL1: return true; + default: + return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 && + sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 && + sys_reg_CRm(id) < 8); - return (sys_reg_Op0(id) == 3 && sys_reg_Op1(id) == 0 && - sys_reg_CRn(id) == 0 && sys_reg_CRm(id) >= 1 && - sys_reg_CRm(id) < 8); + } } static inline bool is_vcpu_ftr_id_reg(u32 id) @@ -1802,16 +1828,6 @@ static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val) return val; } -#define ID_REG_LIMIT_FIELD_ENUM(val, reg, field, limit) \ -({ \ - u64 __f_val = FIELD_GET(reg##_##field##_MASK, val); \ - (val) &= ~reg##_##field##_MASK; \ - (val) |= FIELD_PREP(reg##_##field##_MASK, \ - min(__f_val, \ - (u64)SYS_FIELD_VALUE(reg, field, limit))); \ - (val); \ -}) - static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val) { val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8); @@ -1870,12 +1886,14 @@ static int set_id_aa64dfr0_el1(struct kvm_vcpu *vcpu, static u64 read_sanitised_id_dfr0_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - u8 perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit()); + u8 perfmon; u64 val = read_sanitised_ftr_reg(SYS_ID_DFR0_EL1); val &= ~ID_DFR0_EL1_PerfMon_MASK; - if (kvm_vcpu_has_pmu(vcpu)) + if (kvm_vcpu_has_pmu(vcpu)) { + perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit()); val |= SYS_FIELD_PREP(ID_DFR0_EL1, PerfMon, perfmon); + } val = ID_REG_LIMIT_FIELD_ENUM(val, ID_DFR0_EL1, CopDbg, Debugv8p8); @@ -1929,6 +1947,12 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, if ((hw_val & mpam_mask) == (user_val & mpam_mask)) user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK; + /* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */ + if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) || + !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) || + (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val))) + return -EINVAL; + return set_id_reg(vcpu, rd, user_val); } @@ -1937,11 +1961,65 @@ static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu, { u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); u64 mpam_mask = ID_AA64PFR1_EL1_MPAM_frac_MASK; + u8 mte = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE, hw_val); + u8 user_mte_frac = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE_frac, user_val); + u8 hw_mte_frac = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE_frac, hw_val); /* See set_id_aa64pfr0_el1 for comment about MPAM */ if ((hw_val & mpam_mask) == (user_val & mpam_mask)) user_val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK; + /* + * Previously MTE_frac was hidden from guest. However, if the + * hardware supports MTE2 but not MTE_ASYM_FAULT then a value + * of 0 for this field indicates that the hardware supports + * MTE_ASYNC. Whereas, 0xf indicates MTE_ASYNC is not supported. + * + * As KVM must accept values from KVM provided by user-space, + * when ID_AA64PFR1_EL1.MTE is 2 allow user-space to set + * ID_AA64PFR1_EL1.MTE_frac to 0. However, ignore it to avoid + * incorrectly claiming hardware support for MTE_ASYNC in the + * guest. + */ + + if (mte == ID_AA64PFR1_EL1_MTE_MTE2 && + hw_mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI && + user_mte_frac == ID_AA64PFR1_EL1_MTE_frac_ASYNC) { + user_val &= ~ID_AA64PFR1_EL1_MTE_frac_MASK; + user_val |= hw_val & ID_AA64PFR1_EL1_MTE_frac_MASK; + } + + return set_id_reg(vcpu, rd, user_val); +} + +static int set_id_aa64mmfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, u64 user_val) +{ + u64 sanitized_val = kvm_read_sanitised_id_reg(vcpu, rd); + u64 tgran2_mask = ID_AA64MMFR0_EL1_TGRAN4_2_MASK | + ID_AA64MMFR0_EL1_TGRAN16_2_MASK | + ID_AA64MMFR0_EL1_TGRAN64_2_MASK; + + if (vcpu_has_nv(vcpu) && + ((sanitized_val & tgran2_mask) != (user_val & tgran2_mask))) + return -EINVAL; + + return set_id_reg(vcpu, rd, user_val); +} + +static int set_id_aa64mmfr2_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, u64 user_val) +{ + u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); + u64 nv_mask = ID_AA64MMFR2_EL1_NV_MASK; + + /* + * We made the mistake to expose the now deprecated NV field, + * so allow userspace to write it, but silently ignore it. + */ + if ((hw_val & nv_mask) == (user_val & nv_mask)) + user_val &= ~nv_mask; + return set_id_reg(vcpu, rd, user_val); } @@ -2234,15 +2312,6 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, "trap of EL2 register redirected to EL1"); } -#define EL2_REG(name, acc, rst, v) { \ - SYS_DESC(SYS_##name), \ - .access = acc, \ - .reset = rst, \ - .reg = name, \ - .visibility = el2_visibility, \ - .val = v, \ -} - #define EL2_REG_FILTERED(name, acc, rst, v, filter) { \ SYS_DESC(SYS_##name), \ .access = acc, \ @@ -2252,6 +2321,9 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, .val = v, \ } +#define EL2_REG(name, acc, rst, v) \ + EL2_REG_FILTERED(name, acc, rst, v, el2_visibility) + #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) @@ -2266,35 +2338,33 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, * from userspace. */ +#define ID_DESC_DEFAULT_CALLBACKS \ + .access = access_id_reg, \ + .get_user = get_id_reg, \ + .set_user = set_id_reg, \ + .visibility = id_visibility, \ + .reset = kvm_read_sanitised_id_reg + #define ID_DESC(name) \ SYS_DESC(SYS_##name), \ - .access = access_id_reg, \ - .get_user = get_id_reg \ + ID_DESC_DEFAULT_CALLBACKS /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ ID_DESC(name), \ - .set_user = set_id_reg, \ - .visibility = id_visibility, \ - .reset = kvm_read_sanitised_id_reg, \ .val = 0, \ } /* sys_reg_desc initialiser for known cpufeature ID registers */ #define AA32_ID_SANITISED(name) { \ ID_DESC(name), \ - .set_user = set_id_reg, \ .visibility = aa32_id_visibility, \ - .reset = kvm_read_sanitised_id_reg, \ .val = 0, \ } /* sys_reg_desc initialiser for writable ID registers */ #define ID_WRITABLE(name, mask) { \ ID_DESC(name), \ - .set_user = set_id_reg, \ - .visibility = id_visibility, \ - .reset = kvm_read_sanitised_id_reg, \ .val = mask, \ } @@ -2302,8 +2372,6 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, #define ID_FILTERED(sysreg, name, mask) { \ ID_DESC(sysreg), \ .set_user = set_##name, \ - .visibility = id_visibility, \ - .reset = kvm_read_sanitised_id_reg, \ .val = (mask), \ } @@ -2313,12 +2381,10 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, * (1 <= crm < 8, 0 <= Op2 < 8). */ #define ID_UNALLOCATED(crm, op2) { \ + .name = "S3_0_0_" #crm "_" #op2, \ Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2), \ - .access = access_id_reg, \ - .get_user = get_id_reg, \ - .set_user = set_id_reg, \ + ID_DESC_DEFAULT_CALLBACKS, \ .visibility = raz_visibility, \ - .reset = kvm_read_sanitised_id_reg, \ .val = 0, \ } @@ -2329,9 +2395,7 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu, */ #define ID_HIDDEN(name) { \ ID_DESC(name), \ - .set_user = set_id_reg, \ .visibility = raz_visibility, \ - .reset = kvm_read_sanitised_id_reg, \ .val = 0, \ } @@ -2407,6 +2471,16 @@ static unsigned int sve_el2_visibility(const struct kvm_vcpu *vcpu, return __el2_visibility(vcpu, rd, sve_visibility); } +static unsigned int vncr_el2_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + if (el2_visibility(vcpu, rd) == 0 && + kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) + return 0; + + return REG_HIDDEN; +} + static bool access_zcr_el2(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) @@ -2426,6 +2500,59 @@ static bool access_zcr_el2(struct kvm_vcpu *vcpu, vq = SYS_FIELD_GET(ZCR_ELx, LEN, p->regval) + 1; vq = min(vq, vcpu_sve_max_vq(vcpu)); vcpu_write_sys_reg(vcpu, vq - 1, ZCR_EL2); + + return true; +} + +static bool access_gic_vtr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + p->regval = kvm_vgic_global_state.ich_vtr_el2; + p->regval &= ~(ICH_VTR_EL2_DVIM | + ICH_VTR_EL2_A3V | + ICH_VTR_EL2_IDbits); + p->regval |= ICH_VTR_EL2_nV4; + + return true; +} + +static bool access_gic_misr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + p->regval = vgic_v3_get_misr(vcpu); + + return true; +} + +static bool access_gic_eisr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + p->regval = vgic_v3_get_eisr(vcpu); + + return true; +} + +static bool access_gic_elrsr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + p->regval = vgic_v3_get_elrsr(vcpu); + return true; } @@ -2478,21 +2605,158 @@ static bool access_mdcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - u64 old = __vcpu_sys_reg(vcpu, MDCR_EL2); + u64 hpmn, val, old = __vcpu_sys_reg(vcpu, MDCR_EL2); - if (!access_rw(vcpu, p, r)) - return false; + if (!p->is_write) { + p->regval = old; + return true; + } + + val = p->regval; + hpmn = FIELD_GET(MDCR_EL2_HPMN, val); /* - * Request a reload of the PMU to enable/disable the counters affected - * by HPME. + * If HPMN is out of bounds, limit it to what we actually + * support. This matches the UNKNOWN definition of the field + * in that case, and keeps the emulation simple. Sort of. */ - if ((old ^ __vcpu_sys_reg(vcpu, MDCR_EL2)) & MDCR_EL2_HPME) + if (hpmn > vcpu->kvm->arch.nr_pmu_counters) { + hpmn = vcpu->kvm->arch.nr_pmu_counters; + u64_replace_bits(val, hpmn, MDCR_EL2_HPMN); + } + + __vcpu_sys_reg(vcpu, MDCR_EL2) = val; + + /* + * Request a reload of the PMU to enable/disable the counters + * affected by HPME. + */ + if ((old ^ val) & MDCR_EL2_HPME) kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); return true; } +/* + * For historical (ahem ABI) reasons, KVM treated MIDR_EL1, REVIDR_EL1, and + * AIDR_EL1 as "invariant" registers, meaning userspace cannot change them. + * The values made visible to userspace were the register values of the boot + * CPU. + * + * At the same time, reads from these registers at EL1 previously were not + * trapped, allowing the guest to read the actual hardware value. On big-little + * machines, this means the VM can see different values depending on where a + * given vCPU got scheduled. + * + * These registers are now trapped as collateral damage from SME, and what + * follows attempts to give a user / guest view consistent with the existing + * ABI. + */ +static bool access_imp_id_reg(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return write_to_read_only(vcpu, p, r); + + /* + * Return the VM-scoped implementation ID register values if userspace + * has made them writable. + */ + if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &vcpu->kvm->arch.flags)) + return access_id_reg(vcpu, p, r); + + /* + * Otherwise, fall back to the old behavior of returning the value of + * the current CPU. + */ + switch (reg_to_encoding(r)) { + case SYS_REVIDR_EL1: + p->regval = read_sysreg(revidr_el1); + break; + case SYS_AIDR_EL1: + p->regval = read_sysreg(aidr_el1); + break; + default: + WARN_ON_ONCE(1); + } + + return true; +} + +static u64 __ro_after_init boot_cpu_midr_val; +static u64 __ro_after_init boot_cpu_revidr_val; +static u64 __ro_after_init boot_cpu_aidr_val; + +static void init_imp_id_regs(void) +{ + boot_cpu_midr_val = read_sysreg(midr_el1); + boot_cpu_revidr_val = read_sysreg(revidr_el1); + boot_cpu_aidr_val = read_sysreg(aidr_el1); +} + +static u64 reset_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + switch (reg_to_encoding(r)) { + case SYS_MIDR_EL1: + return boot_cpu_midr_val; + case SYS_REVIDR_EL1: + return boot_cpu_revidr_val; + case SYS_AIDR_EL1: + return boot_cpu_aidr_val; + default: + KVM_BUG_ON(1, vcpu->kvm); + return 0; + } +} + +static int set_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, + u64 val) +{ + struct kvm *kvm = vcpu->kvm; + u64 expected; + + guard(mutex)(&kvm->arch.config_lock); + + expected = read_id_reg(vcpu, r); + if (expected == val) + return 0; + + if (!test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags)) + return -EINVAL; + + /* + * Once the VM has started the ID registers are immutable. Reject the + * write if userspace tries to change it. + */ + if (kvm_vm_has_ran_once(kvm)) + return -EBUSY; + + /* + * Any value is allowed for the implementation ID registers so long as + * it is within the writable mask. + */ + if ((val & r->val) != val) + return -EINVAL; + + kvm_set_vm_id_reg(kvm, reg_to_encoding(r), val); + return 0; +} + +#define IMPLEMENTATION_ID(reg, mask) { \ + SYS_DESC(SYS_##reg), \ + .access = access_imp_id_reg, \ + .get_user = get_id_reg, \ + .set_user = set_imp_id_reg, \ + .reset = reset_imp_id_reg, \ + .val = mask, \ + } + +static u64 reset_mdcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + __vcpu_sys_reg(vcpu, r->reg) = vcpu->kvm->arch.nr_pmu_counters; + return vcpu->kvm->arch.nr_pmu_counters; +} /* * Architected system registers. @@ -2542,7 +2806,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_DBGVCR32_EL2), undef_access, reset_val, DBGVCR32_EL2, 0 }, + IMPLEMENTATION_ID(MIDR_EL1, GENMASK_ULL(31, 0)), { SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 }, + IMPLEMENTATION_ID(REVIDR_EL1, GENMASK_ULL(63, 0)), /* * ID regs: all ID_SANITISED() entries here must have corresponding @@ -2660,10 +2926,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_UNALLOCATED(6,7), /* CRm=7 */ - ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 | - ID_AA64MMFR0_EL1_TGRAN4_2 | - ID_AA64MMFR0_EL1_TGRAN64_2 | - ID_AA64MMFR0_EL1_TGRAN16_2 | + ID_FILTERED(ID_AA64MMFR0_EL1, id_aa64mmfr0_el1, + ~(ID_AA64MMFR0_EL1_RES0 | ID_AA64MMFR0_EL1_ASIDBITS)), ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 | ID_AA64MMFR1_EL1_HCX | @@ -2671,7 +2935,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64MMFR1_EL1_XNX | ID_AA64MMFR1_EL1_VH | ID_AA64MMFR1_EL1_VMIDBits)), - ID_WRITABLE(ID_AA64MMFR2_EL1, ~(ID_AA64MMFR2_EL1_RES0 | + ID_FILTERED(ID_AA64MMFR2_EL1, + id_aa64mmfr2_el1, ~(ID_AA64MMFR2_EL1_RES0 | ID_AA64MMFR2_EL1_EVT | ID_AA64MMFR2_EL1_FWB | ID_AA64MMFR2_EL1_IDS | @@ -2680,7 +2945,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1PIE | ID_AA64MMFR3_EL1_S1POE)), - ID_SANITISED(ID_AA64MMFR4_EL1), + ID_WRITABLE(ID_AA64MMFR4_EL1, ID_AA64MMFR4_EL1_NV_frac), ID_UNALLOCATED(7,5), ID_UNALLOCATED(7,6), ID_UNALLOCATED(7,7), @@ -2814,6 +3079,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { .set_user = set_clidr, .val = ~CLIDR_EL1_RES0 }, { SYS_DESC(SYS_CCSIDR2_EL1), undef_access }, { SYS_DESC(SYS_SMIDR_EL1), undef_access }, + IMPLEMENTATION_ID(AIDR_EL1, GENMASK_ULL(63, 0)), { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, ID_FILTERED(CTR_EL0, ctr_el0, CTR_EL0_DIC_MASK | @@ -2850,7 +3116,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { .access = access_pmceid, .reset = NULL }, { PMU_SYS_REG(PMCCNTR_EL0), .access = access_pmu_evcntr, .reset = reset_unknown, - .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr}, + .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr, + .set_user = set_pmu_evcntr }, { PMU_SYS_REG(PMXEVTYPER_EL0), .access = access_pmu_evtyper, .reset = NULL }, { PMU_SYS_REG(PMXEVCNTR_EL0), @@ -3034,7 +3301,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), EL2_REG_VNCR(HCR_EL2, reset_hcr, 0), - EL2_REG(MDCR_EL2, access_mdcr, reset_val, 0), + EL2_REG(MDCR_EL2, access_mdcr, reset_mdcr, 0), EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1), EL2_REG_VNCR(HSTR_EL2, reset_val, 0), EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0), @@ -3054,6 +3321,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { tcr2_el2_visibility), EL2_REG_VNCR(VTTBR_EL2, reset_val, 0), EL2_REG_VNCR(VTCR_EL2, reset_val, 0), + EL2_REG_FILTERED(VNCR_EL2, bad_vncr_trap, reset_val, 0, + vncr_el2_visibility), { SYS_DESC(SYS_DACR32_EL2), undef_access, reset_unknown, DACR32_EL2 }, EL2_REG_VNCR(HDFGRTR_EL2, reset_val, 0), @@ -3102,7 +3371,40 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(RVBAR_EL2, access_rw, reset_val, 0), { SYS_DESC(SYS_RMR_EL2), undef_access }, + EL2_REG_VNCR(ICH_AP0R0_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_AP0R1_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_AP0R2_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_AP0R3_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_AP1R0_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_AP1R1_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_AP1R2_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_AP1R3_EL2, reset_val, 0), + + { SYS_DESC(SYS_ICC_SRE_EL2), access_gic_sre }, + EL2_REG_VNCR(ICH_HCR_EL2, reset_val, 0), + { SYS_DESC(SYS_ICH_VTR_EL2), access_gic_vtr }, + { SYS_DESC(SYS_ICH_MISR_EL2), access_gic_misr }, + { SYS_DESC(SYS_ICH_EISR_EL2), access_gic_eisr }, + { SYS_DESC(SYS_ICH_ELRSR_EL2), access_gic_elrsr }, + EL2_REG_VNCR(ICH_VMCR_EL2, reset_val, 0), + + EL2_REG_VNCR(ICH_LR0_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR1_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR2_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR3_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR4_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR5_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR6_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR7_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR8_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR9_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR10_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR11_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR12_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR13_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR14_EL2, reset_val, 0), + EL2_REG_VNCR(ICH_LR15_EL2, reset_val, 0), EL2_REG(CONTEXTIDR_EL2, access_rw, reset_val, 0), EL2_REG(TPIDR_EL2, access_rw, reset_val, 0), @@ -3304,8 +3606,7 @@ static bool handle_ripas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); - u64 base, range, tg, num, scale; - int shift; + u64 base, range; if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); @@ -3315,26 +3616,7 @@ static bool handle_ripas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * of the guest's S2 (different base granule size, for example), we * decide to ignore TTL and only use the described range. */ - tg = FIELD_GET(GENMASK(47, 46), p->regval); - scale = FIELD_GET(GENMASK(45, 44), p->regval); - num = FIELD_GET(GENMASK(43, 39), p->regval); - base = p->regval & GENMASK(36, 0); - - switch(tg) { - case 1: - shift = 12; - break; - case 2: - shift = 14; - break; - case 3: - default: /* IMPDEF: handle tg==0 as 64k */ - shift = 16; - break; - } - - base <<= shift; - range = __TLBI_RANGE_PAGES(num, scale) << shift; + base = decode_range_tlbi(p->regval, &range, NULL); kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr), &(union tlbi_info) { @@ -3400,11 +3682,22 @@ static void s2_mmu_tlbi_s1e1(struct kvm_s2_mmu *mmu, WARN_ON(__kvm_tlbi_s1e2(mmu, info->va.addr, info->va.encoding)); } +static bool handle_tlbi_el2(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); + + if (!kvm_supported_tlbi_s1e2_op(vcpu, sys_encoding)) + return undef_access(vcpu, p, r); + + kvm_handle_s1e2_tlbi(vcpu, sys_encoding, p->regval); + return true; +} + static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2); - u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); /* * If we're here, this is because we've trapped on a EL1 TLBI @@ -3415,6 +3708,13 @@ static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * - HCR_EL2.E2H == 0 : a non-VHE guest * - HCR_EL2.{E2H,TGE} == { 1, 0 } : a VHE guest in guest mode * + * Another possibility is that we are invalidating the EL2 context + * using EL1 instructions, but that we landed here because we need + * additional invalidation for structures that are not held in the + * CPU TLBs (such as the VNCR pseudo-TLB and its EL2 mapping). In + * that case, we are guaranteed that HCR_EL2.{E2H,TGE} == { 1, 1 } + * as we don't allow an NV-capable L1 in a nVHE configuration. + * * We don't expect these helpers to ever be called when running * in a vEL1 context. */ @@ -3424,7 +3724,13 @@ static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p, if (!kvm_supported_tlbi_s1e1_op(vcpu, sys_encoding)) return undef_access(vcpu, p, r); - kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr), + if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) { + kvm_handle_s1e2_tlbi(vcpu, sys_encoding, p->regval); + return true; + } + + kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, + get_vmid(__vcpu_sys_reg(vcpu, VTTBR_EL2)), &(union tlbi_info) { .va = { .addr = p->regval, @@ -3546,16 +3852,21 @@ static struct sys_reg_desc sys_insn_descs[] = { SYS_INSN(TLBI_IPAS2LE1IS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1IS, handle_ripas2e1is), - SYS_INSN(TLBI_ALLE2OS, undef_access), - SYS_INSN(TLBI_VAE2OS, undef_access), + SYS_INSN(TLBI_ALLE2OS, handle_tlbi_el2), + SYS_INSN(TLBI_VAE2OS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1OS, handle_alle1is), - SYS_INSN(TLBI_VALE2OS, undef_access), + SYS_INSN(TLBI_VALE2OS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1OS, handle_vmalls12e1is), - SYS_INSN(TLBI_RVAE2IS, undef_access), - SYS_INSN(TLBI_RVALE2IS, undef_access), + SYS_INSN(TLBI_RVAE2IS, handle_tlbi_el2), + SYS_INSN(TLBI_RVALE2IS, handle_tlbi_el2), + SYS_INSN(TLBI_ALLE2IS, handle_tlbi_el2), + SYS_INSN(TLBI_VAE2IS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1IS, handle_alle1is), + + SYS_INSN(TLBI_VALE2IS, handle_tlbi_el2), + SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is), SYS_INSN(TLBI_IPAS2E1OS, handle_ipas2e1is), SYS_INSN(TLBI_IPAS2E1, handle_ipas2e1is), @@ -3565,11 +3876,17 @@ static struct sys_reg_desc sys_insn_descs[] = { SYS_INSN(TLBI_IPAS2LE1, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1, handle_ripas2e1is), SYS_INSN(TLBI_RIPAS2LE1OS, handle_ripas2e1is), - SYS_INSN(TLBI_RVAE2OS, undef_access), - SYS_INSN(TLBI_RVALE2OS, undef_access), - SYS_INSN(TLBI_RVAE2, undef_access), - SYS_INSN(TLBI_RVALE2, undef_access), + SYS_INSN(TLBI_RVAE2OS, handle_tlbi_el2), + SYS_INSN(TLBI_RVALE2OS, handle_tlbi_el2), + SYS_INSN(TLBI_RVAE2, handle_tlbi_el2), + SYS_INSN(TLBI_RVALE2, handle_tlbi_el2), + SYS_INSN(TLBI_ALLE2, handle_tlbi_el2), + SYS_INSN(TLBI_VAE2, handle_tlbi_el2), + SYS_INSN(TLBI_ALLE1, handle_alle1is), + + SYS_INSN(TLBI_VALE2, handle_tlbi_el2), + SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is), SYS_INSN(TLBI_IPAS2E1ISNXS, handle_ipas2e1is), @@ -3577,19 +3894,19 @@ static struct sys_reg_desc sys_insn_descs[] = { SYS_INSN(TLBI_IPAS2LE1ISNXS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1ISNXS, handle_ripas2e1is), - SYS_INSN(TLBI_ALLE2OSNXS, undef_access), - SYS_INSN(TLBI_VAE2OSNXS, undef_access), + SYS_INSN(TLBI_ALLE2OSNXS, handle_tlbi_el2), + SYS_INSN(TLBI_VAE2OSNXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1OSNXS, handle_alle1is), - SYS_INSN(TLBI_VALE2OSNXS, undef_access), + SYS_INSN(TLBI_VALE2OSNXS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1OSNXS, handle_vmalls12e1is), - SYS_INSN(TLBI_RVAE2ISNXS, undef_access), - SYS_INSN(TLBI_RVALE2ISNXS, undef_access), - SYS_INSN(TLBI_ALLE2ISNXS, undef_access), - SYS_INSN(TLBI_VAE2ISNXS, undef_access), + SYS_INSN(TLBI_RVAE2ISNXS, handle_tlbi_el2), + SYS_INSN(TLBI_RVALE2ISNXS, handle_tlbi_el2), + SYS_INSN(TLBI_ALLE2ISNXS, handle_tlbi_el2), + SYS_INSN(TLBI_VAE2ISNXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1ISNXS, handle_alle1is), - SYS_INSN(TLBI_VALE2ISNXS, undef_access), + SYS_INSN(TLBI_VALE2ISNXS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1ISNXS, handle_vmalls12e1is), SYS_INSN(TLBI_IPAS2E1OSNXS, handle_ipas2e1is), SYS_INSN(TLBI_IPAS2E1NXS, handle_ipas2e1is), @@ -3599,14 +3916,14 @@ static struct sys_reg_desc sys_insn_descs[] = { SYS_INSN(TLBI_IPAS2LE1NXS, handle_ipas2e1is), SYS_INSN(TLBI_RIPAS2LE1NXS, handle_ripas2e1is), SYS_INSN(TLBI_RIPAS2LE1OSNXS, handle_ripas2e1is), - SYS_INSN(TLBI_RVAE2OSNXS, undef_access), - SYS_INSN(TLBI_RVALE2OSNXS, undef_access), - SYS_INSN(TLBI_RVAE2NXS, undef_access), - SYS_INSN(TLBI_RVALE2NXS, undef_access), - SYS_INSN(TLBI_ALLE2NXS, undef_access), - SYS_INSN(TLBI_VAE2NXS, undef_access), + SYS_INSN(TLBI_RVAE2OSNXS, handle_tlbi_el2), + SYS_INSN(TLBI_RVALE2OSNXS, handle_tlbi_el2), + SYS_INSN(TLBI_RVAE2NXS, handle_tlbi_el2), + SYS_INSN(TLBI_RVALE2NXS, handle_tlbi_el2), + SYS_INSN(TLBI_ALLE2NXS, handle_tlbi_el2), + SYS_INSN(TLBI_VAE2NXS, handle_tlbi_el2), SYS_INSN(TLBI_ALLE1NXS, handle_alle1is), - SYS_INSN(TLBI_VALE2NXS, undef_access), + SYS_INSN(TLBI_VALE2NXS, handle_tlbi_el2), SYS_INSN(TLBI_VMALLS12E1NXS, handle_vmalls12e1is), }; @@ -4272,9 +4589,13 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu) * Certain AArch32 ID registers are handled by rerouting to the AArch64 * system register table. Registers in the ID range where CRm=0 are * excluded from this scheme as they do not trivially map into AArch64 - * system register encodings. + * system register encodings, except for AIDR/REVIDR. */ - if (params.Op1 == 0 && params.CRn == 0 && params.CRm) + if (params.Op1 == 0 && params.CRn == 0 && + (params.CRm || params.Op2 == 6 /* REVIDR */)) + return kvm_emulate_cp15_id_reg(vcpu, ¶ms); + if (params.Op1 == 1 && params.CRn == 0 && + params.CRm == 0 && params.Op2 == 7 /* AIDR */) return kvm_emulate_cp15_id_reg(vcpu, ¶ms); return kvm_handle_cp_32(vcpu, ¶ms, cp15_regs, ARRAY_SIZE(cp15_regs)); @@ -4473,6 +4794,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) } set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags); + + if (kvm_vcpu_has_pmu(vcpu)) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); } /** @@ -4578,65 +4902,6 @@ id_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id, return r; } -/* - * These are the invariant sys_reg registers: we let the guest see the - * host versions of these, so they're part of the guest state. - * - * A future CPU may provide a mechanism to present different values to - * the guest, or a future kvm may trap them. - */ - -#define FUNCTION_INVARIANT(reg) \ - static u64 reset_##reg(struct kvm_vcpu *v, \ - const struct sys_reg_desc *r) \ - { \ - ((struct sys_reg_desc *)r)->val = read_sysreg(reg); \ - return ((struct sys_reg_desc *)r)->val; \ - } - -FUNCTION_INVARIANT(midr_el1) -FUNCTION_INVARIANT(revidr_el1) -FUNCTION_INVARIANT(aidr_el1) - -/* ->val is filled in by kvm_sys_reg_table_init() */ -static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = { - { SYS_DESC(SYS_MIDR_EL1), NULL, reset_midr_el1 }, - { SYS_DESC(SYS_REVIDR_EL1), NULL, reset_revidr_el1 }, - { SYS_DESC(SYS_AIDR_EL1), NULL, reset_aidr_el1 }, -}; - -static int get_invariant_sys_reg(u64 id, u64 __user *uaddr) -{ - const struct sys_reg_desc *r; - - r = get_reg_by_id(id, invariant_sys_regs, - ARRAY_SIZE(invariant_sys_regs)); - if (!r) - return -ENOENT; - - return put_user(r->val, uaddr); -} - -static int set_invariant_sys_reg(u64 id, u64 __user *uaddr) -{ - const struct sys_reg_desc *r; - u64 val; - - r = get_reg_by_id(id, invariant_sys_regs, - ARRAY_SIZE(invariant_sys_regs)); - if (!r) - return -ENOENT; - - if (get_user(val, uaddr)) - return -EFAULT; - - /* This is what we mean by invariant: you can't change it. */ - if (r->val != val) - return -EINVAL; - - return 0; -} - static int demux_c15_get(struct kvm_vcpu *vcpu, u64 id, void __user *uaddr) { u32 val; @@ -4718,15 +4983,10 @@ int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(unsigned long)reg->addr; - int err; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) return demux_c15_get(vcpu, reg->id, uaddr); - err = get_invariant_sys_reg(reg->id, uaddr); - if (err != -ENOENT) - return err; - return kvm_sys_reg_get_user(vcpu, reg, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); } @@ -4762,15 +5022,10 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(unsigned long)reg->addr; - int err; if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) return demux_c15_set(vcpu, reg->id, uaddr); - err = set_invariant_sys_reg(reg->id, uaddr); - if (err != -ENOENT) - return err; - return kvm_sys_reg_set_user(vcpu, reg, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); } @@ -4859,23 +5114,14 @@ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind) unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu) { - return ARRAY_SIZE(invariant_sys_regs) - + num_demux_regs() + return num_demux_regs() + walk_sys_regs(vcpu, (u64 __user *)NULL); } int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { - unsigned int i; int err; - /* Then give them all the invariant registers' indices. */ - for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) { - if (put_user(sys_reg_to_index(&invariant_sys_regs[i]), uindices)) - return -EFAULT; - uindices++; - } - err = walk_sys_regs(vcpu, uindices); if (err < 0) return err; @@ -4971,88 +5217,18 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu) mutex_lock(&kvm->arch.config_lock); vcpu_set_hcr(vcpu); vcpu_set_ich_hcr(vcpu); - - if (cpus_have_final_cap(ARM64_HAS_HCX)) { - /* - * In general, all HCRX_EL2 bits are gated by a feature. - * The only reason we can set SMPME without checking any - * feature is that its effects are not directly observable - * from the guest. - */ - vcpu->arch.hcrx_el2 = HCRX_EL2_SMPME; - - if (kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP)) - vcpu->arch.hcrx_el2 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2); - - if (kvm_has_tcr2(kvm)) - vcpu->arch.hcrx_el2 |= HCRX_EL2_TCR2En; - - if (kvm_has_fpmr(kvm)) - vcpu->arch.hcrx_el2 |= HCRX_EL2_EnFPM; - } + vcpu_set_hcrx(vcpu); if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags)) goto out; - kvm->arch.fgu[HFGxTR_GROUP] = (HFGxTR_EL2_nAMAIR2_EL1 | - HFGxTR_EL2_nMAIR2_EL1 | - HFGxTR_EL2_nS2POR_EL1 | - HFGxTR_EL2_nACCDATA_EL1 | - HFGxTR_EL2_nSMPRI_EL1_MASK | - HFGxTR_EL2_nTPIDR2_EL0_MASK); - - if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) - kvm->arch.fgu[HFGITR_GROUP] |= (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)) - kvm->arch.fgu[HFGITR_GROUP] |= (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_AA64ISAR2_EL1, ATS1A, IMP)) - kvm->arch.fgu[HFGITR_GROUP] |= HFGITR_EL2_ATS1E1A; - - if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2)) - kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_ATS1E1RP | - HFGITR_EL2_ATS1E1WP); - - if (!kvm_has_s1pie(kvm)) - kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPIRE0_EL1 | - HFGxTR_EL2_nPIR_EL1); - - if (!kvm_has_s1poe(kvm)) - kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPOR_EL1 | - HFGxTR_EL2_nPOR_EL0); - - if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP)) - kvm->arch.fgu[HAFGRTR_GROUP] |= ~(HAFGRTR_EL2_RES0 | - HAFGRTR_EL2_RES1); - - if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) { - kvm->arch.fgu[HDFGRTR_GROUP] |= (HDFGRTR_EL2_nBRBDATA | - HDFGRTR_EL2_nBRBCTL | - HDFGRTR_EL2_nBRBIDR); - kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_nBRBINJ | - HFGITR_EL2_nBRBIALL); - } + compute_fgu(kvm, HFGRTR_GROUP); + compute_fgu(kvm, HFGITR_GROUP); + compute_fgu(kvm, HDFGRTR_GROUP); + compute_fgu(kvm, HAFGRTR_GROUP); + compute_fgu(kvm, HFGRTR2_GROUP); + compute_fgu(kvm, HFGITR2_GROUP); + compute_fgu(kvm, HDFGRTR2_GROUP); set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags); out: @@ -5101,18 +5277,17 @@ int __init kvm_sys_reg_table_init(void) valid &= check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs), true); valid &= check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true); valid &= check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true); - valid &= check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false); valid &= check_sysreg_table(sys_insn_descs, ARRAY_SIZE(sys_insn_descs), false); if (!valid) return -EINVAL; - /* We abuse the reset function to overwrite the table itself. */ - for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) - invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]); + init_imp_id_regs(); ret = populate_nv_trap_config(); + check_feature_map(); + for (i = 0; !ret && i < ARRAY_SIZE(sys_reg_descs); i++) ret = populate_sysreg_config(sys_reg_descs + i, i); diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 1d94ed6efad2..cc6338d38766 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -247,4 +247,14 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu); CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \ Op2(sys_reg_Op2(reg)) +#define ID_REG_LIMIT_FIELD_ENUM(val, reg, field, limit) \ +({ \ + u64 __f_val = FIELD_GET(reg##_##field##_MASK, val); \ + (val) &= ~reg##_##field##_MASK; \ + (val) |= FIELD_PREP(reg##_##field##_MASK, \ + min(__f_val, \ + (u64)SYS_FIELD_VALUE(reg, field, limit))); \ + (val); \ +}) + #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */ diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h index c18c1a95831e..9c60f6465c78 100644 --- a/arch/arm64/kvm/trace_arm.h +++ b/arch/arm64/kvm/trace_arm.h @@ -176,7 +176,7 @@ TRACE_EVENT(kvm_set_way_flush, ), TP_printk("S/W flush at 0x%016lx (cache %s)", - __entry->vcpu_pc, __entry->cache ? "on" : "off") + __entry->vcpu_pc, str_on_off(__entry->cache)) ); TRACE_EVENT(kvm_toggle_cache, @@ -196,8 +196,8 @@ TRACE_EVENT(kvm_toggle_cache, ), TP_printk("VM op at 0x%016lx (cache was %s, now %s)", - __entry->vcpu_pc, __entry->was ? "on" : "off", - __entry->now ? "on" : "off") + __entry->vcpu_pc, str_on_off(__entry->was), + str_on_off(__entry->now)) ); /* diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c index 9e7c486b48c2..5eacb4b3250a 100644 --- a/arch/arm64/kvm/vgic-sys-reg-v3.c +++ b/arch/arm64/kvm/vgic-sys-reg-v3.c @@ -35,12 +35,12 @@ static int set_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, vgic_v3_cpu->num_id_bits = host_id_bits; - host_seis = FIELD_GET(ICH_VTR_SEIS_MASK, kvm_vgic_global_state.ich_vtr_el2); + host_seis = FIELD_GET(ICH_VTR_EL2_SEIS, kvm_vgic_global_state.ich_vtr_el2); seis = FIELD_GET(ICC_CTLR_EL1_SEIS_MASK, val); if (host_seis != seis) return -EINVAL; - host_a3v = FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2); + host_a3v = FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2); a3v = FIELD_GET(ICC_CTLR_EL1_A3V_MASK, val); if (host_a3v != a3v) return -EINVAL; @@ -68,10 +68,10 @@ static int get_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, val |= FIELD_PREP(ICC_CTLR_EL1_PRI_BITS_MASK, vgic_v3_cpu->num_pri_bits - 1); val |= FIELD_PREP(ICC_CTLR_EL1_ID_BITS_MASK, vgic_v3_cpu->num_id_bits); val |= FIELD_PREP(ICC_CTLR_EL1_SEIS_MASK, - FIELD_GET(ICH_VTR_SEIS_MASK, + FIELD_GET(ICH_VTR_EL2_SEIS, kvm_vgic_global_state.ich_vtr_el2)); val |= FIELD_PREP(ICC_CTLR_EL1_A3V_MASK, - FIELD_GET(ICH_VTR_A3V_MASK, kvm_vgic_global_state.ich_vtr_el2)); + FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2)); /* * The VMCR.CTLR value is in ICC_CTLR_EL1 layout. * Extract it directly using ICC_CTLR_EL1 reg definitions. diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index afb018528bc3..f8425f381de9 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -320,3 +320,227 @@ void vgic_debug_init(struct kvm *kvm) void vgic_debug_destroy(struct kvm *kvm) { } + +/** + * struct vgic_its_iter - Iterator for traversing VGIC ITS device tables. + * @dev: Pointer to the current its_device being processed. + * @ite: Pointer to the current its_ite within the device being processed. + * + * This structure is used to maintain the current position during iteration + * over the ITS device tables. It holds pointers to both the current device + * and the current ITE within that device. + */ +struct vgic_its_iter { + struct its_device *dev; + struct its_ite *ite; +}; + +/** + * end_of_iter - Checks if the iterator has reached the end. + * @iter: The iterator to check. + * + * When the iterator completed processing the final ITE in the last device + * table, it was marked to indicate the end of iteration by setting its + * device and ITE pointers to NULL. + * This function checks whether the iterator was marked as end. + * + * Return: True if the iterator is marked as end, false otherwise. + */ +static inline bool end_of_iter(struct vgic_its_iter *iter) +{ + return !iter->dev && !iter->ite; +} + +/** + * vgic_its_iter_next - Advances the iterator to the next entry in the ITS tables. + * @its: The VGIC ITS structure. + * @iter: The iterator to advance. + * + * This function moves the iterator to the next ITE within the current device, + * or to the first ITE of the next device if the current ITE is the last in + * the device. If the current device is the last device, the iterator is set + * to indicate the end of iteration. + */ +static void vgic_its_iter_next(struct vgic_its *its, struct vgic_its_iter *iter) +{ + struct its_device *dev = iter->dev; + struct its_ite *ite = iter->ite; + + if (!ite || list_is_last(&ite->ite_list, &dev->itt_head)) { + if (list_is_last(&dev->dev_list, &its->device_list)) { + dev = NULL; + ite = NULL; + } else { + dev = list_next_entry(dev, dev_list); + ite = list_first_entry_or_null(&dev->itt_head, + struct its_ite, + ite_list); + } + } else { + ite = list_next_entry(ite, ite_list); + } + + iter->dev = dev; + iter->ite = ite; +} + +/** + * vgic_its_debug_start - Start function for the seq_file interface. + * @s: The seq_file structure. + * @pos: The starting position (offset). + * + * This function initializes the iterator to the beginning of the ITS tables + * and advances it to the specified position. It acquires the its_lock mutex + * to protect shared data. + * + * Return: An iterator pointer on success, NULL if no devices are found or + * the end of the list is reached, or ERR_PTR(-ENOMEM) on memory + * allocation failure. + */ +static void *vgic_its_debug_start(struct seq_file *s, loff_t *pos) +{ + struct vgic_its *its = s->private; + struct vgic_its_iter *iter; + struct its_device *dev; + loff_t offset = *pos; + + mutex_lock(&its->its_lock); + + dev = list_first_entry_or_null(&its->device_list, + struct its_device, dev_list); + if (!dev) + return NULL; + + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return ERR_PTR(-ENOMEM); + + iter->dev = dev; + iter->ite = list_first_entry_or_null(&dev->itt_head, + struct its_ite, ite_list); + + while (!end_of_iter(iter) && offset--) + vgic_its_iter_next(its, iter); + + if (end_of_iter(iter)) { + kfree(iter); + return NULL; + } + + return iter; +} + +/** + * vgic_its_debug_next - Next function for the seq_file interface. + * @s: The seq_file structure. + * @v: The current iterator. + * @pos: The current position (offset). + * + * This function advances the iterator to the next entry and increments the + * position. + * + * Return: An iterator pointer on success, or NULL if the end of the list is + * reached. + */ +static void *vgic_its_debug_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct vgic_its *its = s->private; + struct vgic_its_iter *iter = v; + + ++*pos; + vgic_its_iter_next(its, iter); + + if (end_of_iter(iter)) { + kfree(iter); + return NULL; + } + return iter; +} + +/** + * vgic_its_debug_stop - Stop function for the seq_file interface. + * @s: The seq_file structure. + * @v: The current iterator. + * + * This function frees the iterator and releases the its_lock mutex. + */ +static void vgic_its_debug_stop(struct seq_file *s, void *v) +{ + struct vgic_its *its = s->private; + struct vgic_its_iter *iter = v; + + if (!IS_ERR_OR_NULL(iter)) + kfree(iter); + mutex_unlock(&its->its_lock); +} + +/** + * vgic_its_debug_show - Show function for the seq_file interface. + * @s: The seq_file structure. + * @v: The current iterator. + * + * This function formats and prints the ITS table entry information to the + * seq_file output. + * + * Return: 0 on success. + */ +static int vgic_its_debug_show(struct seq_file *s, void *v) +{ + struct vgic_its_iter *iter = v; + struct its_device *dev = iter->dev; + struct its_ite *ite = iter->ite; + + if (list_is_first(&ite->ite_list, &dev->itt_head)) { + seq_printf(s, "\n"); + seq_printf(s, "Device ID: 0x%x, Event ID Range: [0 - %llu]\n", + dev->device_id, BIT_ULL(dev->num_eventid_bits) - 1); + seq_printf(s, "EVENT_ID INTID HWINTID TARGET COL_ID HW\n"); + seq_printf(s, "-----------------------------------------------\n"); + } + + if (ite && ite->irq && ite->collection) { + seq_printf(s, "%8u %8u %8u %8u %8u %2d\n", + ite->event_id, ite->irq->intid, ite->irq->hwintid, + ite->collection->target_addr, + ite->collection->collection_id, ite->irq->hw); + } + + return 0; +} + +static const struct seq_operations vgic_its_debug_sops = { + .start = vgic_its_debug_start, + .next = vgic_its_debug_next, + .stop = vgic_its_debug_stop, + .show = vgic_its_debug_show +}; + +DEFINE_SEQ_ATTRIBUTE(vgic_its_debug); + +/** + * vgic_its_debug_init - Initializes the debugfs interface for VGIC ITS. + * @dev: The KVM device structure. + * + * This function creates a debugfs file named "vgic-its-state@%its_base" + * to expose the ITS table information. + * + * Return: 0 on success. + */ +int vgic_its_debug_init(struct kvm_device *dev) +{ + struct vgic_its *its = dev->private; + char *name; + + name = kasprintf(GFP_KERNEL, "vgic-its-state@%llx", (u64)its->vgic_its_base); + if (!name) + return -ENOMEM; + + debugfs_create_file(name, 0444, dev->kvm->debugfs_dentry, its, &vgic_its_debug_fops); + + kfree(name); + return 0; +} + +void vgic_its_debug_destroy(struct kvm_device *dev) +{ +} diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 775461cf2d2d..1f33e71c2a73 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -198,6 +198,27 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) return 0; } +/* Default GICv3 Maintenance Interrupt INTID, as per SBSA */ +#define DEFAULT_MI_INTID 25 + +int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu) +{ + int ret; + + guard(mutex)(&vcpu->kvm->arch.config_lock); + + /* + * Matching the tradition established with the timers, provide + * a default PPI for the maintenance interrupt. It makes + * things easier to reason about. + */ + if (vcpu->kvm->arch.vgic.mi_intid == 0) + vcpu->kvm->arch.vgic.mi_intid = DEFAULT_MI_INTID; + ret = kvm_vgic_set_owner(vcpu, vcpu->kvm->arch.vgic.mi_intid, vcpu); + + return ret; +} + static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; @@ -588,12 +609,20 @@ void kvm_vgic_cpu_down(void) static irqreturn_t vgic_maintenance_handler(int irq, void *data) { + struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)data; + /* * We cannot rely on the vgic maintenance interrupt to be * delivered synchronously. This means we can only use it to * exit the VM, and we perform the handling of EOIed * interrupts on the exit path (see vgic_fold_lr_state). + * + * Of course, NV throws a wrench in this plan, and needs + * something special. */ + if (vcpu && vgic_state_is_nested(vcpu)) + vgic_v3_handle_nested_maint_irq(vcpu); + return IRQ_HANDLED; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index fb96802799c6..569f9da9049f 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -154,36 +154,6 @@ out_unlock: return irq; } -struct its_device { - struct list_head dev_list; - - /* the head for the list of ITTEs */ - struct list_head itt_head; - u32 num_eventid_bits; - gpa_t itt_addr; - u32 device_id; -}; - -#define COLLECTION_NOT_MAPPED ((u32)~0) - -struct its_collection { - struct list_head coll_list; - - u32 collection_id; - u32 target_addr; -}; - -#define its_is_collection_mapped(coll) ((coll) && \ - ((coll)->target_addr != COLLECTION_NOT_MAPPED)) - -struct its_ite { - struct list_head ite_list; - - struct vgic_irq *irq; - struct its_collection *collection; - u32 event_id; -}; - /** * struct vgic_its_abi - ITS abi ops and settings * @cte_esz: collection table entry size @@ -1938,6 +1908,8 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev) mutex_lock(&its->its_lock); + vgic_its_debug_destroy(kvm_dev); + vgic_its_free_device_list(kvm, its); vgic_its_free_collection_list(kvm, its); vgic_its_invalidate_cache(its); @@ -2771,7 +2743,12 @@ static int vgic_its_set_attr(struct kvm_device *dev, if (ret) return ret; - return vgic_register_its_iodev(dev->kvm, its, addr); + ret = vgic_register_its_iodev(dev->kvm, its, addr); + if (ret) + return ret; + + return vgic_its_debug_init(dev); + } case KVM_DEV_ARM_VGIC_GRP_CTRL: return vgic_its_ctrl(dev->kvm, its, attr->attr); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 5f4f57aaa23e..359094f68c23 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -303,6 +303,12 @@ static int vgic_get_common_attr(struct kvm_device *dev, VGIC_NR_PRIVATE_IRQS, uaddr); break; } + case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + + r = put_user(dev->kvm->arch.vgic.mi_intid, uaddr); + break; + } } return r; @@ -517,7 +523,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; - bool uaccess; + bool uaccess, post_init = true; u32 val; int ret; @@ -533,6 +539,9 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, /* Sysregs uaccess is performed by the sysreg handling code */ uaccess = false; break; + case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: + post_init = false; + fallthrough; default: uaccess = true; } @@ -552,7 +561,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, mutex_lock(&dev->kvm->arch.config_lock); - if (unlikely(!vgic_initialized(dev->kvm))) { + if (post_init != vgic_initialized(dev->kvm)) { ret = -EBUSY; goto out; } @@ -582,6 +591,19 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, } break; } + case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: + if (!is_write) { + val = dev->kvm->arch.vgic.mi_intid; + ret = 0; + break; + } + + ret = -EINVAL; + if ((val < VGIC_NR_PRIVATE_IRQS) && (val >= VGIC_NR_SGIS)) { + dev->kvm->arch.vgic.mi_intid = val; + ret = 0; + } + break; default: ret = -EINVAL; break; @@ -608,6 +630,7 @@ static int vgic_v3_set_attr(struct kvm_device *dev, case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: + case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: return vgic_v3_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); @@ -622,6 +645,7 @@ static int vgic_v3_get_attr(struct kvm_device *dev, case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: + case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: return vgic_v3_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); @@ -645,6 +669,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev, case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: return vgic_v3_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + case KVM_DEV_ARM_VGIC_GRP_MAINT_IRQ: return 0; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c new file mode 100644 index 000000000000..4f6954c30674 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/cpu.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/uaccess.h> + +#include <kvm/arm_vgic.h> + +#include <asm/kvm_arm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_nested.h> + +#include "vgic.h" + +#define ICH_LRN(n) (ICH_LR0_EL2 + (n)) +#define ICH_AP0RN(n) (ICH_AP0R0_EL2 + (n)) +#define ICH_AP1RN(n) (ICH_AP1R0_EL2 + (n)) + +struct mi_state { + u16 eisr; + u16 elrsr; + bool pend; +}; + +/* + * The shadow registers loaded to the hardware when running a L2 guest + * with the virtual IMO/FMO bits set. + */ +struct shadow_if { + struct vgic_v3_cpu_if cpuif; + unsigned long lr_map; +}; + +static DEFINE_PER_CPU(struct shadow_if, shadow_if); + +/* + * Nesting GICv3 support + * + * On a non-nesting VM (only running at EL0/EL1), the host hypervisor + * completely controls the interrupts injected via the list registers. + * Consequently, most of the state that is modified by the guest (by ACK-ing + * and EOI-ing interrupts) is synced by KVM on each entry/exit, so that we + * keep a semi-consistent view of the interrupts. + * + * This still applies for a NV guest, but only while "InHost" (either + * running at EL2, or at EL0 with HCR_EL2.{E2H.TGE}=={1,1}. + * + * When running a L2 guest ("not InHost"), things are radically different, + * as the L1 guest is in charge of provisioning the interrupts via its own + * view of the ICH_LR*_EL2 registers, which conveniently live in the VNCR + * page. This means that the flow described above does work (there is no + * state to rebuild in the L0 hypervisor), and that most things happed on L2 + * load/put: + * + * - on L2 load: move the in-memory L1 vGIC configuration into a shadow, + * per-CPU data structure that is used to populate the actual LRs. This is + * an extra copy that we could avoid, but life is short. In the process, + * we remap any interrupt that has the HW bit set to the mapped interrupt + * on the host, should the host consider it a HW one. This allows the HW + * deactivation to take its course, such as for the timer. + * + * - on L2 put: perform the inverse transformation, so that the result of L2 + * running becomes visible to L1 in the VNCR-accessible registers. + * + * - there is nothing to do on L2 entry, as everything will have happened + * on load. However, this is the point where we detect that an interrupt + * targeting L1 and prepare the grand switcheroo. + * + * - on L2 exit: emulate the HW bit, and deactivate corresponding the L1 + * interrupt. The L0 active state will be cleared by the HW if the L1 + * interrupt was itself backed by a HW interrupt. + * + * Maintenance Interrupt (MI) management: + * + * Since the L2 guest runs the vgic in its full glory, MIs get delivered and + * used as a handover point between L2 and L1. + * + * - on delivery of a MI to L0 while L2 is running: make the L1 MI pending, + * and let it rip. This will initiate a vcpu_put() on L2, and allow L1 to + * run and process the MI. + * + * - L1 MI is a fully virtual interrupt, not linked to the host's MI. Its + * state must be computed at each entry/exit of the guest, much like we do + * it for the PMU interrupt. + * + * - because most of the ICH_*_EL2 registers live in the VNCR page, the + * quality of emulation is poor: L1 can setup the vgic so that an MI would + * immediately fire, and not observe anything until the next exit. Trying + * to read ICH_MISR_EL2 would do the trick, for example. + * + * System register emulation: + * + * We get two classes of registers: + * + * - those backed by memory (LRs, APRs, HCR, VMCR): L1 can freely access + * them, and L0 doesn't see a thing. + * + * - those that always trap (ELRSR, EISR, MISR): these are status registers + * that are built on the fly based on the in-memory state. + * + * Only L1 can access the ICH_*_EL2 registers. A non-NV L2 obviously cannot, + * and a NV L2 would either access the VNCR page provided by L1 (memory + * based registers), or see the access redirected to L1 (registers that + * trap) thanks to NV being set by L1. + */ + +bool vgic_state_is_nested(struct kvm_vcpu *vcpu) +{ + u64 xmo; + + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { + xmo = __vcpu_sys_reg(vcpu, HCR_EL2) & (HCR_IMO | HCR_FMO); + WARN_ONCE(xmo && xmo != (HCR_IMO | HCR_FMO), + "Separate virtual IRQ/FIQ settings not supported\n"); + + return !!xmo; + } + + return false; +} + +static struct shadow_if *get_shadow_if(void) +{ + return this_cpu_ptr(&shadow_if); +} + +static bool lr_triggers_eoi(u64 lr) +{ + return !(lr & (ICH_LR_STATE | ICH_LR_HW)) && (lr & ICH_LR_EOI); +} + +static void vgic_compute_mi_state(struct kvm_vcpu *vcpu, struct mi_state *mi_state) +{ + u16 eisr = 0, elrsr = 0; + bool pend = false; + + for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) { + u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i)); + + if (lr_triggers_eoi(lr)) + eisr |= BIT(i); + if (!(lr & ICH_LR_STATE)) + elrsr |= BIT(i); + pend |= (lr & ICH_LR_PENDING_BIT); + } + + mi_state->eisr = eisr; + mi_state->elrsr = elrsr; + mi_state->pend = pend; +} + +u16 vgic_v3_get_eisr(struct kvm_vcpu *vcpu) +{ + struct mi_state mi_state; + + vgic_compute_mi_state(vcpu, &mi_state); + return mi_state.eisr; +} + +u16 vgic_v3_get_elrsr(struct kvm_vcpu *vcpu) +{ + struct mi_state mi_state; + + vgic_compute_mi_state(vcpu, &mi_state); + return mi_state.elrsr; +} + +u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu) +{ + struct mi_state mi_state; + u64 reg = 0, hcr, vmcr; + + hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2); + vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2); + + vgic_compute_mi_state(vcpu, &mi_state); + + if (mi_state.eisr) + reg |= ICH_MISR_EL2_EOI; + + if (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_UIE) { + int used_lrs = kvm_vgic_global_state.nr_lr; + + used_lrs -= hweight16(mi_state.elrsr); + reg |= (used_lrs <= 1) ? ICH_MISR_EL2_U : 0; + } + + if ((hcr & ICH_HCR_EL2_LRENPIE) && FIELD_GET(ICH_HCR_EL2_EOIcount_MASK, hcr)) + reg |= ICH_MISR_EL2_LRENP; + + if ((hcr & ICH_HCR_EL2_NPIE) && !mi_state.pend) + reg |= ICH_MISR_EL2_NP; + + if ((hcr & ICH_HCR_EL2_VGrp0EIE) && (vmcr & ICH_VMCR_ENG0_MASK)) + reg |= ICH_MISR_EL2_VGrp0E; + + if ((hcr & ICH_HCR_EL2_VGrp0DIE) && !(vmcr & ICH_VMCR_ENG0_MASK)) + reg |= ICH_MISR_EL2_VGrp0D; + + if ((hcr & ICH_HCR_EL2_VGrp1EIE) && (vmcr & ICH_VMCR_ENG1_MASK)) + reg |= ICH_MISR_EL2_VGrp1E; + + if ((hcr & ICH_HCR_EL2_VGrp1DIE) && !(vmcr & ICH_VMCR_ENG1_MASK)) + reg |= ICH_MISR_EL2_VGrp1D; + + return reg; +} + +/* + * For LRs which have HW bit set such as timer interrupts, we modify them to + * have the host hardware interrupt number instead of the virtual one programmed + * by the guest hypervisor. + */ +static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu, + struct vgic_v3_cpu_if *s_cpu_if) +{ + unsigned long lr_map = 0; + int index = 0; + + for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) { + u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i)); + struct vgic_irq *irq; + + if (!(lr & ICH_LR_STATE)) + lr = 0; + + if (!(lr & ICH_LR_HW)) + goto next; + + /* We have the HW bit set, check for validity of pINTID */ + irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr)); + if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI ) { + /* There was no real mapping, so nuke the HW bit */ + lr &= ~ICH_LR_HW; + if (irq) + vgic_put_irq(vcpu->kvm, irq); + goto next; + } + + /* Translate the virtual mapping to the real one */ + lr &= ~ICH_LR_PHYS_ID_MASK; + lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid); + + vgic_put_irq(vcpu->kvm, irq); + +next: + s_cpu_if->vgic_lr[index] = lr; + if (lr) { + lr_map |= BIT(i); + index++; + } + } + + container_of(s_cpu_if, struct shadow_if, cpuif)->lr_map = lr_map; + s_cpu_if->used_lrs = index; +} + +void vgic_v3_sync_nested(struct kvm_vcpu *vcpu) +{ + struct shadow_if *shadow_if = get_shadow_if(); + int i, index = 0; + + for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) { + u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i)); + struct vgic_irq *irq; + + if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE)) + goto next; + + /* + * If we had a HW lr programmed by the guest hypervisor, we + * need to emulate the HW effect between the guest hypervisor + * and the nested guest. + */ + irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr)); + if (WARN_ON(!irq)) /* Shouldn't happen as we check on load */ + goto next; + + lr = __gic_v3_get_lr(index); + if (!(lr & ICH_LR_STATE)) + irq->active = false; + + vgic_put_irq(vcpu->kvm, irq); + next: + index++; + } +} + +static void vgic_v3_create_shadow_state(struct kvm_vcpu *vcpu, + struct vgic_v3_cpu_if *s_cpu_if) +{ + struct vgic_v3_cpu_if *host_if = &vcpu->arch.vgic_cpu.vgic_v3; + u64 val = 0; + int i; + + /* + * If we're on a system with a broken vgic that requires + * trapping, propagate the trapping requirements. + * + * Ah, the smell of rotten fruits... + */ + if (static_branch_unlikely(&vgic_v3_cpuif_trap)) + val = host_if->vgic_hcr & (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 | + ICH_HCR_EL2_TC | ICH_HCR_EL2_TDIR); + s_cpu_if->vgic_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) | val; + s_cpu_if->vgic_vmcr = __vcpu_sys_reg(vcpu, ICH_VMCR_EL2); + s_cpu_if->vgic_sre = host_if->vgic_sre; + + for (i = 0; i < 4; i++) { + s_cpu_if->vgic_ap0r[i] = __vcpu_sys_reg(vcpu, ICH_AP0RN(i)); + s_cpu_if->vgic_ap1r[i] = __vcpu_sys_reg(vcpu, ICH_AP1RN(i)); + } + + vgic_v3_create_shadow_lr(vcpu, s_cpu_if); +} + +void vgic_v3_load_nested(struct kvm_vcpu *vcpu) +{ + struct shadow_if *shadow_if = get_shadow_if(); + struct vgic_v3_cpu_if *cpu_if = &shadow_if->cpuif; + + BUG_ON(!vgic_state_is_nested(vcpu)); + + vgic_v3_create_shadow_state(vcpu, cpu_if); + + __vgic_v3_restore_vmcr_aprs(cpu_if); + __vgic_v3_activate_traps(cpu_if); + + __vgic_v3_restore_state(cpu_if); + + /* + * Propagate the number of used LRs for the benefit of the HYP + * GICv3 emulation code. Yes, this is a pretty sorry hack. + */ + vcpu->arch.vgic_cpu.vgic_v3.used_lrs = cpu_if->used_lrs; +} + +void vgic_v3_put_nested(struct kvm_vcpu *vcpu) +{ + struct shadow_if *shadow_if = get_shadow_if(); + struct vgic_v3_cpu_if *s_cpu_if = &shadow_if->cpuif; + u64 val; + int i; + + __vgic_v3_save_vmcr_aprs(s_cpu_if); + __vgic_v3_deactivate_traps(s_cpu_if); + __vgic_v3_save_state(s_cpu_if); + + /* + * Translate the shadow state HW fields back to the virtual ones + * before copying the shadow struct back to the nested one. + */ + val = __vcpu_sys_reg(vcpu, ICH_HCR_EL2); + val &= ~ICH_HCR_EL2_EOIcount_MASK; + val |= (s_cpu_if->vgic_hcr & ICH_HCR_EL2_EOIcount_MASK); + __vcpu_sys_reg(vcpu, ICH_HCR_EL2) = val; + __vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr; + + for (i = 0; i < 4; i++) { + __vcpu_sys_reg(vcpu, ICH_AP0RN(i)) = s_cpu_if->vgic_ap0r[i]; + __vcpu_sys_reg(vcpu, ICH_AP1RN(i)) = s_cpu_if->vgic_ap1r[i]; + } + + for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) { + val = __vcpu_sys_reg(vcpu, ICH_LRN(i)); + + val &= ~ICH_LR_STATE; + val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE; + + __vcpu_sys_reg(vcpu, ICH_LRN(i)) = val; + s_cpu_if->vgic_lr[i] = 0; + } + + shadow_if->lr_map = 0; + vcpu->arch.vgic_cpu.vgic_v3.used_lrs = 0; +} + +/* + * If we exit a L2 VM with a pending maintenance interrupt from the GIC, + * then we need to forward this to L1 so that it can re-sync the appropriate + * LRs and sample level triggered interrupts again. + */ +void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu) +{ + bool state = read_sysreg_s(SYS_ICH_MISR_EL2); + + /* This will force a switch back to L1 if the level is high */ + kvm_vgic_inject_irq(vcpu->kvm, vcpu, + vcpu->kvm->arch.vgic.mi_intid, state, vcpu); + + sysreg_clear_set_s(SYS_ICH_HCR_EL2, ICH_HCR_EL2_En, 0); +} + +void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu) +{ + bool level; + + level = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En; + if (level) + level &= vgic_v3_get_misr(vcpu); + kvm_vgic_inject_irq(vcpu->kvm, vcpu, + vcpu->kvm->arch.vgic.mi_intid, level, vcpu); +} diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index d7233ab982d0..b9ad7c42c5b0 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -24,7 +24,7 @@ void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; - cpuif->vgic_hcr |= ICH_HCR_UIE; + cpuif->vgic_hcr |= ICH_HCR_EL2_UIE; } static bool lr_signals_eoi_mi(u64 lr_val) @@ -42,7 +42,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - cpuif->vgic_hcr &= ~ICH_HCR_UIE; + cpuif->vgic_hcr &= ~ICH_HCR_EL2_UIE; for (lr = 0; lr < cpuif->used_lrs; lr++) { u64 val = cpuif->vgic_lr[lr]; @@ -284,15 +284,13 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu) vgic_v3->vgic_sre = 0; } - vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 & - ICH_VTR_ID_BITS_MASK) >> - ICH_VTR_ID_BITS_SHIFT; - vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 & - ICH_VTR_PRI_BITS_MASK) >> - ICH_VTR_PRI_BITS_SHIFT) + 1; + vcpu->arch.vgic_cpu.num_id_bits = FIELD_GET(ICH_VTR_EL2_IDbits, + kvm_vgic_global_state.ich_vtr_el2); + vcpu->arch.vgic_cpu.num_pri_bits = FIELD_GET(ICH_VTR_EL2_PRIbits, + kvm_vgic_global_state.ich_vtr_el2) + 1; /* Get the show on the road... */ - vgic_v3->vgic_hcr = ICH_HCR_EN; + vgic_v3->vgic_hcr = ICH_HCR_EL2_En; } void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu) @@ -301,18 +299,19 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu) /* Hide GICv3 sysreg if necessary */ if (!kvm_has_gicv3(vcpu->kvm)) { - vgic_v3->vgic_hcr |= ICH_HCR_TALL0 | ICH_HCR_TALL1 | ICH_HCR_TC; + vgic_v3->vgic_hcr |= (ICH_HCR_EL2_TALL0 | ICH_HCR_EL2_TALL1 | + ICH_HCR_EL2_TC); return; } if (group0_trap) - vgic_v3->vgic_hcr |= ICH_HCR_TALL0; + vgic_v3->vgic_hcr |= ICH_HCR_EL2_TALL0; if (group1_trap) - vgic_v3->vgic_hcr |= ICH_HCR_TALL1; + vgic_v3->vgic_hcr |= ICH_HCR_EL2_TALL1; if (common_trap) - vgic_v3->vgic_hcr |= ICH_HCR_TC; + vgic_v3->vgic_hcr |= ICH_HCR_EL2_TC; if (dir_trap) - vgic_v3->vgic_hcr |= ICH_HCR_TDIR; + vgic_v3->vgic_hcr |= ICH_HCR_EL2_TDIR; } int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) @@ -632,8 +631,8 @@ static const struct midr_range broken_seis[] = { static bool vgic_v3_broken_seis(void) { - return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) && - is_midr_in_range_list(read_cpuid_id(), broken_seis)); + return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_SEIS) && + is_midr_in_range_list(broken_seis)); } /** @@ -706,10 +705,10 @@ int vgic_v3_probe(const struct gic_kvm_info *info) if (vgic_v3_broken_seis()) { kvm_info("GICv3 with broken locally generated SEI\n"); - kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK; + kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_EL2_SEIS; group0_trap = true; group1_trap = true; - if (ich_vtr_el2 & ICH_VTR_TDS_MASK) + if (ich_vtr_el2 & ICH_VTR_EL2_TDS) dir_trap = true; else common_trap = true; @@ -735,6 +734,12 @@ void vgic_v3_load(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + /* If the vgic is nested, perform the full state loading */ + if (vgic_state_is_nested(vcpu)) { + vgic_v3_load_nested(vcpu); + return; + } + if (likely(!is_protected_kvm_enabled())) kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if); @@ -748,6 +753,11 @@ void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + if (vgic_state_is_nested(vcpu)) { + vgic_v3_put_nested(vcpu); + return; + } + if (likely(!is_protected_kvm_enabled())) kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if); WARN_ON(vgic_v4_put(vcpu)); diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index eedecbbbcf31..c7de6154627c 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -336,6 +336,22 @@ void vgic_v4_teardown(struct kvm *kvm) its_vm->vpes = NULL; } +static inline bool vgic_v4_want_doorbell(struct kvm_vcpu *vcpu) +{ + if (vcpu_get_flag(vcpu, IN_WFI)) + return true; + + if (likely(!vcpu_has_nv(vcpu))) + return false; + + /* + * GICv4 hardware is only ever used for the L1. Mark the vPE (i.e. the + * L1 context) nonresident and request a doorbell to kick us out of the + * L2 when an IRQ becomes pending. + */ + return vcpu_get_flag(vcpu, IN_NESTED_ERET); +} + int vgic_v4_put(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; @@ -343,7 +359,7 @@ int vgic_v4_put(struct kvm_vcpu *vcpu) if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; - return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI)); + return its_make_vpe_non_resident(vpe, vgic_v4_want_doorbell(vcpu)); } int vgic_v4_load(struct kvm_vcpu *vcpu) @@ -415,7 +431,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, struct vgic_irq *irq; struct its_vlpi_map map; unsigned long flags; - int ret; + int ret = 0; if (!vgic_supports_direct_msis(kvm)) return 0; @@ -430,10 +446,15 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, mutex_lock(&its->its_lock); - /* Perform the actual DevID/EventID -> LPI translation. */ - ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, - irq_entry->msi.data, &irq); - if (ret) + /* + * Perform the actual DevID/EventID -> LPI translation. + * + * Silently exit if translation fails as the guest (or userspace!) has + * managed to do something stupid. Emulated LPI injection will still + * work if the guest figures itself out at a later time. + */ + if (vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, + irq_entry->msi.data, &irq)) goto out; /* Silently exit if the vLPI is already mapped */ @@ -512,7 +533,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, if (ret) goto out; - WARN_ON(!(irq->hw && irq->host_irq == virq)); + WARN_ON(irq->hw && irq->host_irq != virq); if (irq->hw) { atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); irq->hw = false; diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index cc8c6b9b5dd8..8f8096d48925 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -872,6 +872,15 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { int used_lrs; + /* If nesting, emulate the HW effect from L0 to L1 */ + if (vgic_state_is_nested(vcpu)) { + vgic_v3_sync_nested(vcpu); + return; + } + + if (vcpu_has_nv(vcpu)) + vgic_v3_nested_update_mi(vcpu); + /* An empty ap_list_head implies used_lrs == 0 */ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) return; @@ -901,6 +910,35 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu) void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) { /* + * If in a nested state, we must return early. Two possibilities: + * + * - If we have any pending IRQ for the guest and the guest + * expects IRQs to be handled in its virtual EL2 mode (the + * virtual IMO bit is set) and it is not already running in + * virtual EL2 mode, then we have to emulate an IRQ + * exception to virtual EL2. + * + * We do that by placing a request to ourselves which will + * abort the entry procedure and inject the exception at the + * beginning of the run loop. + * + * - Otherwise, do exactly *NOTHING*. The guest state is + * already loaded, and we can carry on with running it. + * + * If we have NV, but are not in a nested state, compute the + * maintenance interrupt state, as it may fire. + */ + if (vgic_state_is_nested(vcpu)) { + if (kvm_vgic_vcpu_pending_irq(vcpu)) + kvm_make_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu); + + return; + } + + if (vcpu_has_nv(vcpu)) + vgic_v3_nested_update_mi(vcpu); + + /* * If there are no virtual interrupts active or pending for this * VCPU, then there is no work to do and we can bail out without * taking any lock. There is a potential race with someone injecting diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 122d95b4e284..4349084cb9a6 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -172,6 +172,36 @@ struct vgic_reg_attr { gpa_t addr; }; +struct its_device { + struct list_head dev_list; + + /* the head for the list of ITTEs */ + struct list_head itt_head; + u32 num_eventid_bits; + gpa_t itt_addr; + u32 device_id; +}; + +#define COLLECTION_NOT_MAPPED ((u32)~0) + +struct its_collection { + struct list_head coll_list; + + u32 collection_id; + u32 target_addr; +}; + +#define its_is_collection_mapped(coll) ((coll) && \ + ((coll)->target_addr != COLLECTION_NOT_MAPPED)) + +struct its_ite { + struct list_head ite_list; + + struct vgic_irq *irq; + struct its_collection *collection; + u32 event_id; +}; + int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr); int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, @@ -353,4 +383,13 @@ static inline bool kvm_has_gicv3(struct kvm *kvm) return kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP); } +void vgic_v3_sync_nested(struct kvm_vcpu *vcpu); +void vgic_v3_load_nested(struct kvm_vcpu *vcpu); +void vgic_v3_put_nested(struct kvm_vcpu *vcpu); +void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu); +void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu); + +int vgic_its_debug_init(struct kvm_device *dev); +void vgic_its_debug_destroy(struct kvm_device *dev); + #endif |