diff options
47 files changed, 3204 insertions, 382 deletions
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 032516783e96..03d87d9b97d9 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -907,10 +907,12 @@ The irq_type field has the following values: - KVM_ARM_IRQ_TYPE_CPU: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ - KVM_ARM_IRQ_TYPE_SPI: - in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.) + in-kernel GICv2/GICv3: SPI, irq_id between 32 and 1019 (incl.) (the vcpu_index field is ignored) + in-kernel GICv5: SPI, irq_id between 0 and 65535 (incl.) - KVM_ARM_IRQ_TYPE_PPI: - in-kernel GIC: PPI, irq_id between 16 and 31 (incl.) + in-kernel GICv2/GICv3: PPI, irq_id between 16 and 31 (incl.) + in-kernel GICv5: PPI, irq_id between 0 and 127 (incl.) (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs) diff --git a/Documentation/virt/kvm/devices/arm-vgic-v5.rst b/Documentation/virt/kvm/devices/arm-vgic-v5.rst new file mode 100644 index 000000000000..29335ea823fc --- /dev/null +++ b/Documentation/virt/kvm/devices/arm-vgic-v5.rst @@ -0,0 +1,50 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================================================== +ARM Virtual Generic Interrupt Controller v5 (VGICv5) +==================================================== + + +Device types supported: + - KVM_DEV_TYPE_ARM_VGIC_V5 ARM Generic Interrupt Controller v5.0 + +Only one VGIC instance may be instantiated through this API. The created VGIC +will act as the VM interrupt controller, requiring emulated user-space devices +to inject interrupts to the VGIC instead of directly to CPUs. + +Creating a guest GICv5 device requires a host GICv5 host. The current VGICv5 +device only supports PPI interrupts. These can either be injected from emulated +in-kernel devices (such as the Arch Timer, or PMU), or via the KVM_IRQ_LINE +ioctl. + +Groups: + KVM_DEV_ARM_VGIC_GRP_CTRL + Attributes: + + KVM_DEV_ARM_VGIC_CTRL_INIT + request the initialization of the VGIC, no additional parameter in + kvm_device_attr.addr. Must be called after all VCPUs have been created. + + KVM_DEV_ARM_VGIC_USERPSPACE_PPIs + request the mask of userspace-drivable PPIs. Only a subset of the PPIs can + be directly driven from userspace with GICv5, and the returned mask + informs userspace of which it is allowed to drive via KVM_IRQ_LINE. + + Userspace must allocate and point to __u64[2] of data in + kvm_device_attr.addr. When this call returns, the provided memory will be + populated with the userspace PPI mask. The lower __u64 contains the mask + for the lower 64 PPIS, with the remaining 64 being in the second __u64. + + This is a read-only attribute, and cannot be set. Attempts to set it are + rejected. + + Errors: + + ======= ======================================================== + -ENXIO VGIC not properly configured as required prior to calling + this attribute + -ENODEV no online VCPU + -ENOMEM memory shortage when allocating vgic internal data + -EFAULT Invalid guest ram access + -EBUSY One or more VCPUS are running + ======= ======================================================== diff --git a/Documentation/virt/kvm/devices/index.rst b/Documentation/virt/kvm/devices/index.rst index 192cda7405c8..70845aba38f4 100644 --- a/Documentation/virt/kvm/devices/index.rst +++ b/Documentation/virt/kvm/devices/index.rst @@ -10,6 +10,7 @@ Devices arm-vgic-its arm-vgic arm-vgic-v3 + arm-vgic-v5 mpic s390_flic vcpu diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst index 60bf205cb373..5e3805820010 100644 --- a/Documentation/virt/kvm/devices/vcpu.rst +++ b/Documentation/virt/kvm/devices/vcpu.rst @@ -37,7 +37,8 @@ Returns: A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt type must be same for each vcpu. As a PPI, the interrupt number is the same for -all vcpus, while as an SPI it must be a separate number per vcpu. +all vcpus, while as an SPI it must be a separate number per vcpu. For +GICv5-based guests, the architected PPI (23) must be used. 1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT --------------------------------------- @@ -50,7 +51,7 @@ Returns: -EEXIST Interrupt number already used -ENODEV PMUv3 not supported or GIC not initialized -ENXIO PMUv3 not supported, missing VCPU feature or interrupt - number not set + number not set (non-GICv5 guests, only) -EBUSY PMUv3 already initialized ======= ====================================================== diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 85f4c1615472..998b2a3f615a 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -248,6 +248,8 @@ ICH_HFGWTR_EL2_ICC_CR0_EL1 | \ ICH_HFGWTR_EL2_ICC_APR_EL1) msr_s SYS_ICH_HFGWTR_EL2, x0 // Disable reg write traps + mov x0, #(ICH_VCTLR_EL2_En) + msr_s SYS_ICH_VCTLR_EL2, x0 // Enable vHPPI selection .Lskip_gicv5_\@: .endm diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index c8eb992d3ac8..724319298e71 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -81,6 +81,8 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff, __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs, __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs, + __KVM_HOST_SMCCC_FUNC___vgic_v5_save_apr, + __KVM_HOST_SMCCC_FUNC___vgic_v5_restore_vmcr_apr, __KVM_HOST_SMCCC_FUNC___pkvm_reserve_vm, __KVM_HOST_SMCCC_FUNC___pkvm_unreserve_vm, __KVM_HOST_SMCCC_FUNC___pkvm_init_vm, diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7fff5bede09a..7298a68eaef9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -287,6 +287,9 @@ enum fgt_group_id { HDFGRTR2_GROUP, HDFGWTR2_GROUP = HDFGRTR2_GROUP, HFGITR2_GROUP, + ICH_HFGRTR_GROUP, + ICH_HFGWTR_GROUP = ICH_HFGRTR_GROUP, + ICH_HFGITR_GROUP, /* Must be last */ __NR_FGT_GROUP_IDS__ @@ -620,6 +623,10 @@ enum vcpu_sysreg { VNCR(ICH_HCR_EL2), VNCR(ICH_VMCR_EL2), + VNCR(ICH_HFGRTR_EL2), + VNCR(ICH_HFGWTR_EL2), + VNCR(ICH_HFGITR_EL2), + NR_SYS_REGS /* Nothing after this line! */ }; @@ -675,6 +682,9 @@ extern struct fgt_masks hfgwtr2_masks; extern struct fgt_masks hfgitr2_masks; extern struct fgt_masks hdfgrtr2_masks; extern struct fgt_masks hdfgwtr2_masks; +extern struct fgt_masks ich_hfgrtr_masks; +extern struct fgt_masks ich_hfgwtr_masks; +extern struct fgt_masks ich_hfgitr_masks; extern struct fgt_masks kvm_nvhe_sym(hfgrtr_masks); extern struct fgt_masks kvm_nvhe_sym(hfgwtr_masks); @@ -687,6 +697,9 @@ extern struct fgt_masks kvm_nvhe_sym(hfgwtr2_masks); extern struct fgt_masks kvm_nvhe_sym(hfgitr2_masks); extern struct fgt_masks kvm_nvhe_sym(hdfgrtr2_masks); extern struct fgt_masks kvm_nvhe_sym(hdfgwtr2_masks); +extern struct fgt_masks kvm_nvhe_sym(ich_hfgrtr_masks); +extern struct fgt_masks kvm_nvhe_sym(ich_hfgwtr_masks); +extern struct fgt_masks kvm_nvhe_sym(ich_hfgitr_masks); struct kvm_cpu_context { struct user_pt_regs regs; /* sp = sp_el0 */ @@ -787,6 +800,21 @@ struct kvm_host_data { /* Last vgic_irq part of the AP list recorded in an LR */ struct vgic_irq *last_lr_irq; + + /* PPI state tracking for GICv5-based guests */ + struct { + /* + * For tracking the PPI pending state, we need both the entry + * state and exit state to correctly detect edges as it is + * possible that an interrupt has been injected in software in + * the interim. + */ + DECLARE_BITMAP(pendr_entry, VGIC_V5_NR_PRIVATE_IRQS); + DECLARE_BITMAP(pendr_exit, VGIC_V5_NR_PRIVATE_IRQS); + + /* The saved state of the regs when leaving the guest */ + DECLARE_BITMAP(activer_exit, VGIC_V5_NR_PRIVATE_IRQS); + } vgic_v5_ppi_state; }; struct kvm_host_psci_config { @@ -1662,6 +1690,11 @@ static __always_inline enum fgt_group_id __fgt_reg_to_group_id(enum vcpu_sysreg case HDFGRTR2_EL2: case HDFGWTR2_EL2: return HDFGRTR2_GROUP; + case ICH_HFGRTR_EL2: + case ICH_HFGWTR_EL2: + return ICH_HFGRTR_GROUP; + case ICH_HFGITR_EL2: + return ICH_HFGITR_GROUP; default: BUILD_BUG_ON(1); } @@ -1676,6 +1709,7 @@ static __always_inline enum fgt_group_id __fgt_reg_to_group_id(enum vcpu_sysreg case HDFGWTR_EL2: \ case HFGWTR2_EL2: \ case HDFGWTR2_EL2: \ + case ICH_HFGWTR_EL2: \ p = &(vcpu)->arch.fgt[id].w; \ break; \ default: \ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 4bf63025061e..8d06b62e7188 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -87,6 +87,15 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if); void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if); int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu); +/* GICv5 */ +void __vgic_v5_save_apr(struct vgic_v5_cpu_if *cpu_if); +void __vgic_v5_restore_vmcr_apr(struct vgic_v5_cpu_if *cpu_if); +/* No hypercalls for the following */ +void __vgic_v5_save_ppi_state(struct vgic_v5_cpu_if *cpu_if); +void __vgic_v5_restore_ppi_state(struct vgic_v5_cpu_if *cpu_if); +void __vgic_v5_save_state(struct vgic_v5_cpu_if *cpu_if); +void __vgic_v5_restore_state(struct vgic_v5_cpu_if *cpu_if); + #ifdef __KVM_NVHE_HYPERVISOR__ void __timer_enable_traps(struct kvm_vcpu *vcpu); void __timer_disable_traps(struct kvm_vcpu *vcpu); @@ -135,6 +144,7 @@ void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); extern u64 kvm_nvhe_sym(id_aa64pfr0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64pfr1_el1_sys_val); +extern u64 kvm_nvhe_sym(id_aa64pfr2_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64isar0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64isar1_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64isar2_el1_sys_val); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index f4436ecc630c..938cdb248f83 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -1052,6 +1052,7 @@ #define GICV5_OP_GIC_CDPRI sys_insn(1, 0, 12, 1, 2) #define GICV5_OP_GIC_CDRCFG sys_insn(1, 0, 12, 1, 5) #define GICV5_OP_GICR_CDIA sys_insn(1, 0, 12, 3, 0) +#define GICV5_OP_GICR_CDNMIA sys_insn(1, 0, 12, 3, 1) /* Definitions for GIC CDAFF */ #define GICV5_GIC_CDAFF_IAFFID_MASK GENMASK_ULL(47, 32) @@ -1098,6 +1099,12 @@ #define GICV5_GIC_CDIA_TYPE_MASK GENMASK_ULL(31, 29) #define GICV5_GIC_CDIA_ID_MASK GENMASK_ULL(23, 0) +/* Definitions for GICR CDNMIA */ +#define GICV5_GICR_CDNMIA_VALID_MASK BIT_ULL(32) +#define GICV5_GICR_CDNMIA_VALID(r) FIELD_GET(GICV5_GICR_CDNMIA_VALID_MASK, r) +#define GICV5_GICR_CDNMIA_TYPE_MASK GENMASK_ULL(31, 29) +#define GICV5_GICR_CDNMIA_ID_MASK GENMASK_ULL(23, 0) + #define gicr_insn(insn) read_sysreg_s(GICV5_OP_GICR_##insn) #define gic_insn(v, insn) write_sysreg_s(v, GICV5_OP_GIC_##insn) diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h index c2485a862e69..14366d35ce82 100644 --- a/arch/arm64/include/asm/vncr_mapping.h +++ b/arch/arm64/include/asm/vncr_mapping.h @@ -108,5 +108,8 @@ #define VNCR_MPAMVPM5_EL2 0x968 #define VNCR_MPAMVPM6_EL2 0x970 #define VNCR_MPAMVPM7_EL2 0x978 +#define VNCR_ICH_HFGITR_EL2 0xB10 +#define VNCR_ICH_HFGRTR_EL2 0xB18 +#define VNCR_ICH_HFGWTR_EL2 0xB20 #endif /* __ARM64_VNCR_MAPPING_H__ */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index a792a599b9d6..1c13bfa2d38a 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -428,6 +428,7 @@ enum { #define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 #define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 #define KVM_DEV_ARM_ITS_CTRL_RESET 4 +#define KVM_DEV_ARM_VGIC_USERSPACE_PPIS 5 /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 600f250753b4..67b989671b41 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -56,6 +56,12 @@ static struct irq_ops arch_timer_irq_ops = { .get_input_level = kvm_arch_timer_get_input_level, }; +static struct irq_ops arch_timer_irq_ops_vgic_v5 = { + .get_input_level = kvm_arch_timer_get_input_level, + .queue_irq_unlock = vgic_v5_ppi_queue_irq_unlock, + .set_direct_injection = vgic_v5_set_ppi_dvi, +}; + static int nr_timers(struct kvm_vcpu *vcpu) { if (!vcpu_has_nv(vcpu)) @@ -177,6 +183,10 @@ void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) map->emul_ptimer = vcpu_ptimer(vcpu); } + map->direct_vtimer->direct = true; + if (map->direct_ptimer) + map->direct_ptimer->direct = true; + trace_kvm_get_timer_map(vcpu->vcpu_id, map); } @@ -396,7 +406,11 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return vcpu_has_wfit_active(vcpu) && wfit_delay_ns(vcpu) == 0; + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + + return kvm_timer_should_fire(vtimer) || kvm_timer_should_fire(ptimer) || + (vcpu_has_wfit_active(vcpu) && wfit_delay_ns(vcpu) == 0); } /* @@ -447,6 +461,10 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, if (userspace_irqchip(vcpu->kvm)) return; + /* Skip injecting on GICv5 for directly injected (DVI'd) timers */ + if (vgic_is_v5(vcpu->kvm) && timer_ctx->direct) + return; + kvm_vgic_inject_irq(vcpu->kvm, vcpu, timer_irq(timer_ctx), timer_ctx->irq.level, @@ -674,6 +692,7 @@ static void kvm_timer_vcpu_load_gic(struct arch_timer_context *ctx) phys_active = kvm_vgic_map_is_active(vcpu, timer_irq(ctx)); phys_active |= ctx->irq.level; + phys_active |= vgic_is_v5(vcpu->kvm); set_timer_irq_phys_active(ctx, phys_active); } @@ -740,13 +759,11 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu, ret = kvm_vgic_map_phys_irq(vcpu, map->direct_vtimer->host_timer_irq, - timer_irq(map->direct_vtimer), - &arch_timer_irq_ops); + timer_irq(map->direct_vtimer)); WARN_ON_ONCE(ret); ret = kvm_vgic_map_phys_irq(vcpu, map->direct_ptimer->host_timer_irq, - timer_irq(map->direct_ptimer), - &arch_timer_irq_ops); + timer_irq(map->direct_ptimer)); WARN_ON_ONCE(ret); } } @@ -864,7 +881,8 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) get_timer_map(vcpu, &map); if (static_branch_likely(&has_gic_active_state)) { - if (vcpu_has_nv(vcpu)) + /* We don't do NV on GICv5, yet */ + if (vcpu_has_nv(vcpu) && !vgic_is_v5(vcpu->kvm)) kvm_timer_vcpu_load_nested_switch(vcpu, &map); kvm_timer_vcpu_load_gic(map.direct_vtimer); @@ -934,6 +952,12 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); + + if (vgic_is_v5(vcpu->kvm)) { + set_timer_irq_phys_active(map.direct_vtimer, false); + if (map.direct_ptimer) + set_timer_irq_phys_active(map.direct_ptimer, false); + } } void kvm_timer_sync_nested(struct kvm_vcpu *vcpu) @@ -1097,10 +1121,19 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) HRTIMER_MODE_ABS_HARD); } +/* + * This is always called during kvm_arch_init_vm, but will also be + * called from kvm_vgic_create if we have a vGICv5. + */ void kvm_timer_init_vm(struct kvm *kvm) { + /* + * Set up the default PPIs - note that we adjust them based on + * the model of the GIC as GICv5 uses a different way to + * describing interrupts. + */ for (int i = 0; i < NR_KVM_TIMERS; i++) - kvm->arch.timer_data.ppi[i] = default_ppi[i]; + kvm->arch.timer_data.ppi[i] = get_vgic_ppi(kvm, default_ppi[i]); } void kvm_timer_cpu_up(void) @@ -1269,7 +1302,15 @@ static int timer_irq_set_irqchip_state(struct irq_data *d, static void timer_irq_eoi(struct irq_data *d) { - if (!irqd_is_forwarded_to_vcpu(d)) + /* + * On a GICv5 host, we still need to call EOI on the parent for + * PPIs. The host driver already handles irqs which are forwarded to + * vcpus, and skips the GIC CDDI while still doing the GIC CDEOI. This + * is required to emulate the EOIMode=1 on GICv5 hardware. Failure to + * call EOI unsurprisingly results in *BAD* lock-ups. + */ + if (!irqd_is_forwarded_to_vcpu(d) || + kvm_vgic_global_state.type == VGIC_V5) irq_chip_eoi_parent(d); } @@ -1333,7 +1374,8 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info) host_vtimer_irq = info->virtual_irq; kvm_irq_fixup_flags(host_vtimer_irq, &host_vtimer_irq_flags); - if (kvm_vgic_global_state.no_hw_deactivation) { + if (kvm_vgic_global_state.no_hw_deactivation || + kvm_vgic_global_state.type == VGIC_V5) { struct fwnode_handle *fwnode; struct irq_data *data; @@ -1351,7 +1393,8 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info) return -ENOMEM; } - arch_timer_irq_ops.flags |= VGIC_IRQ_SW_RESAMPLE; + if (kvm_vgic_global_state.no_hw_deactivation) + arch_timer_irq_ops.flags |= VGIC_IRQ_SW_RESAMPLE; WARN_ON(irq_domain_push_irq(domain, host_vtimer_irq, (void *)TIMER_VTIMER)); } @@ -1502,10 +1545,13 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) break; /* - * We know by construction that we only have PPIs, so - * all values are less than 32. + * We know by construction that we only have PPIs, so all values + * are less than 32 for non-GICv5 VGICs. On GICv5, they are + * architecturally defined to be under 32 too. However, we mask + * off most of the bits as we might be presented with a GICv5 + * style PPI where the type is encoded in the top-bits. */ - ppis |= BIT(irq); + ppis |= BIT(irq & 0x1f); } valid = hweight32(ppis) == nr_timers(vcpu); @@ -1543,6 +1589,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; + struct irq_ops *ops; int ret; if (timer->enabled) @@ -1563,20 +1610,22 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) get_timer_map(vcpu, &map); + ops = vgic_is_v5(vcpu->kvm) ? &arch_timer_irq_ops_vgic_v5 : + &arch_timer_irq_ops; + + for (int i = 0; i < nr_timers(vcpu); i++) + kvm_vgic_set_irq_ops(vcpu, timer_irq(vcpu_get_timer(vcpu, i)), ops); + ret = kvm_vgic_map_phys_irq(vcpu, map.direct_vtimer->host_timer_irq, - timer_irq(map.direct_vtimer), - &arch_timer_irq_ops); + timer_irq(map.direct_vtimer)); if (ret) return ret; - if (map.direct_ptimer) { + if (map.direct_ptimer) ret = kvm_vgic_map_phys_irq(vcpu, map.direct_ptimer->host_timer_irq, - timer_irq(map.direct_ptimer), - &arch_timer_irq_ops); - } - + timer_irq(map.direct_ptimer)); if (ret) return ret; @@ -1603,15 +1652,14 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) if (get_user(irq, uaddr)) return -EFAULT; - if (!(irq_is_ppi(irq))) + if (!(irq_is_ppi(vcpu->kvm, irq))) return -EINVAL; - mutex_lock(&vcpu->kvm->arch.config_lock); + guard(mutex)(&vcpu->kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE, &vcpu->kvm->arch.flags)) { - ret = -EBUSY; - goto out; + return -EBUSY; } switch (attr->attr) { @@ -1628,19 +1676,23 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) idx = TIMER_HPTIMER; break; default: - ret = -ENXIO; - goto out; + return -ENXIO; } /* + * The PPIs for the Arch Timers are architecturally defined for + * GICv5. Reject anything that changes them from the specified value. + */ + if (vgic_is_v5(vcpu->kvm) && vcpu->kvm->arch.timer_data.ppi[idx] != irq) + return -EINVAL; + + /* * We cannot validate the IRQ unicity before we run, so take it at * face value. The verdict will be given on first vcpu run, for each * vcpu. Yes this is late. Blame it on the stupid API. */ vcpu->kvm->arch.timer_data.ppi[idx] = irq; -out: - mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 04c43c9eb764..c4c810b01012 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -47,6 +47,9 @@ #include <kvm/arm_hypercalls.h> #include <kvm/arm_pmu.h> #include <kvm/arm_psci.h> +#include <kvm/arm_vgic.h> + +#include <linux/irqchip/arm-gic-v5.h> #include "sys_regs.h" @@ -615,6 +618,9 @@ static bool kvm_vcpu_should_clear_twi(struct kvm_vcpu *vcpu) if (unlikely(kvm_wfi_trap_policy != KVM_WFX_NOTRAP_SINGLE_TASK)) return kvm_wfi_trap_policy == KVM_WFX_NOTRAP; + if (vgic_is_v5(vcpu->kvm)) + return single_task_running(); + return single_task_running() && vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || @@ -938,6 +944,10 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) return ret; } + ret = vgic_v5_finalize_ppi_state(kvm); + if (ret) + return ret; + if (is_protected_kvm_enabled()) { ret = pkvm_create_hyp_vm(kvm); if (ret) @@ -1443,10 +1453,11 @@ static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level) int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status) { - u32 irq = irq_level->irq; unsigned int irq_type, vcpu_id, irq_num; struct kvm_vcpu *vcpu = NULL; bool level = irq_level->level; + u32 irq = irq_level->irq; + unsigned long *mask; irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; vcpu_id = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; @@ -1476,16 +1487,37 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, if (!vcpu) return -EINVAL; - if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS) + if (vgic_is_v5(kvm)) { + if (irq_num >= VGIC_V5_NR_PRIVATE_IRQS) + return -EINVAL; + + /* + * Only allow PPIs that are explicitly exposed to + * usespace to be driven via KVM_IRQ_LINE + */ + mask = kvm->arch.vgic.gicv5_vm.userspace_ppis; + if (!test_bit(irq_num, mask)) + return -EINVAL; + + /* Build a GICv5-style IntID here */ + irq_num = vgic_v5_make_ppi(irq_num); + } else if (irq_num < VGIC_NR_SGIS || + irq_num >= VGIC_NR_PRIVATE_IRQS) { return -EINVAL; + } return kvm_vgic_inject_irq(kvm, vcpu, irq_num, level, NULL); case KVM_ARM_IRQ_TYPE_SPI: if (!irqchip_in_kernel(kvm)) return -ENXIO; - if (irq_num < VGIC_NR_PRIVATE_IRQS) - return -EINVAL; + if (vgic_is_v5(kvm)) { + /* Build a GICv5-style IntID here */ + irq_num = vgic_v5_make_spi(irq_num); + } else { + if (irq_num < VGIC_NR_PRIVATE_IRQS) + return -EINVAL; + } return kvm_vgic_inject_irq(kvm, NULL, irq_num, level, NULL); } @@ -2515,6 +2547,7 @@ static void kvm_hyp_init_symbols(void) { kvm_nvhe_sym(id_aa64pfr0_el1 |