diff options
| author | Marc Zyngier <maz@kernel.org> | 2026-04-08 12:22:35 +0100 |
|---|---|---|
| committer | Marc Zyngier <maz@kernel.org> | 2026-04-08 12:22:35 +0100 |
| commit | f8078d51ee232c8d4fa552d30e06c641b944e2c2 (patch) | |
| tree | b7c6c8c3c8a568b0ce98fa9b31a4118ed15bc3d5 /arch | |
| parent | 2de32a25a3f721052c9aaf753a65b96f63c2c7d9 (diff) | |
| parent | ce29261ec6482de54320c03398eb30e9615aee40 (diff) | |
| download | lwn-f8078d51ee232c8d4fa552d30e06c641b944e2c2.tar.gz lwn-f8078d51ee232c8d4fa552d30e06c641b944e2c2.zip | |
Merge branch kvm-arm64/vgic-v5-ppi into kvmarm-master/next
* kvm-arm64/vgic-v5-ppi: (40 commits)
: .
: Add initial GICv5 support for KVM guests, only adding PPI support
: for the time being. Patches courtesy of Sascha Bischoff.
:
: From the cover letter:
:
: "This is v7 of the patch series to add the virtual GICv5 [1] device
: (vgic_v5). Only PPIs are supported by this initial series, and the
: vgic_v5 implementation is restricted to the CPU interface,
: only. Further patch series are to follow in due course, and will add
: support for SPIs, LPIs, the GICv5 IRS, and the GICv5 ITS."
: .
KVM: arm64: selftests: Add no-vgic-v5 selftest
KVM: arm64: selftests: Introduce a minimal GICv5 PPI selftest
KVM: arm64: gic-v5: Communicate userspace-driveable PPIs via a UAPI
Documentation: KVM: Introduce documentation for VGICv5
KVM: arm64: gic-v5: Probe for GICv5 device
KVM: arm64: gic-v5: Set ICH_VCTLR_EL2.En on boot
KVM: arm64: gic-v5: Introduce kvm_arm_vgic_v5_ops and register them
KVM: arm64: gic-v5: Hide FEAT_GCIE from NV GICv5 guests
KVM: arm64: gic: Hide GICv5 for protected guests
KVM: arm64: gic-v5: Mandate architected PPI for PMU emulation on GICv5
KVM: arm64: gic-v5: Enlighten arch timer for GICv5
irqchip/gic-v5: Introduce minimal irq_set_type() for PPIs
KVM: arm64: gic-v5: Initialise ID and priority bits when resetting vcpu
KVM: arm64: gic-v5: Create and initialise vgic_v5
KVM: arm64: gic-v5: Support GICv5 interrupts with KVM_IRQ_LINE
KVM: arm64: gic-v5: Implement direct injection of PPIs
KVM: arm64: Introduce set_direct_injection irq_op
KVM: arm64: gic-v5: Trap and mask guest ICC_PPI_ENABLERx_EL1 writes
KVM: arm64: gic-v5: Check for pending PPIs
KVM: arm64: gic-v5: Clear TWI if single task running
...
Signed-off-by: Marc Zyngier <maz@kernel.org>
Diffstat (limited to 'arch')
29 files changed, 2219 insertions, 192 deletions
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_sys_val) = get_hyp_id_aa64pfr0_el1(); kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); + kvm_nvhe_sym(id_aa64pfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR2_EL1); kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); kvm_nvhe_sym(id_aa64isar2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); @@ -2537,6 +2570,9 @@ static void kvm_hyp_init_symbols(void) kvm_nvhe_sym(hfgitr2_masks) = hfgitr2_masks; kvm_nvhe_sym(hdfgrtr2_masks)= hdfgrtr2_masks; kvm_nvhe_sym(hdfgwtr2_masks)= hdfgwtr2_masks; + kvm_nvhe_sym(ich_hfgrtr_masks) = ich_hfgrtr_masks; + kvm_nvhe_sym(ich_hfgwtr_masks) = ich_hfgwtr_masks; + kvm_nvhe_sym(ich_hfgitr_masks) = ich_hfgitr_masks; /* * Flush entire BSS since part of its data containing init symbols is read diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c index d9f553cbf9df..e14685343191 100644 --- a/arch/arm64/kvm/config.c +++ b/arch/arm64/kvm/config.c @@ -225,6 +225,7 @@ struct reg_feat_map_desc { #define FEAT_MTPMU ID_AA64DFR0_EL1, MTPMU, IMP #define FEAT_HCX ID_AA64MMFR1_EL1, HCX, IMP #define FEAT_S2PIE ID_AA64MMFR3_EL1, S2PIE, IMP +#define FEAT_GCIE ID_AA64PFR2_EL1, GCIE, IMP static bool not_feat_aa64el3(struct kvm *kvm) { @@ -1277,6 +1278,58 @@ static const struct reg_bits_to_feat_map vtcr_el2_feat_map[] = { static const DECLARE_FEAT_MAP(vtcr_el2_desc, VTCR_EL2, vtcr_el2_feat_map, FEAT_AA64EL2); +static const struct reg_bits_to_feat_map ich_hfgrtr_feat_map[] = { + NEEDS_FEAT(ICH_HFGRTR_EL2_ICC_APR_EL1 | + ICH_HFGRTR_EL2_ICC_IDRn_EL1 | + ICH_HFGRTR_EL2_ICC_CR0_EL1 | + ICH_HFGRTR_EL2_ICC_HPPIR_EL1 | + ICH_HFGRTR_EL2_ICC_PCR_EL1 | + ICH_HFGRTR_EL2_ICC_ICSR_EL1 | + ICH_HFGRTR_EL2_ICC_IAFFIDR_EL1 | + ICH_HFGRTR_EL2_ICC_PPI_HMRn_EL1 | + ICH_HFGRTR_EL2_ICC_PPI_ENABLERn_EL1 | + ICH_HFGRTR_EL2_ICC_PPI_PENDRn_EL1 | + ICH_HFGRTR_EL2_ICC_PPI_PRIORITYRn_EL1 | + ICH_HFGRTR_EL2_ICC_PPI_ACTIVERn_EL1, + FEAT_GCIE), +}; + +static const DECLARE_FEAT_MAP_FGT(ich_hfgrtr_desc, ich_hfgrtr_masks, + ich_hfgrtr_feat_map, FEAT_GCIE); + +static const struct reg_bits_to_feat_map ich_hfgwtr_feat_map[] = { + NEEDS_FEAT(ICH_HFGWTR_EL2_ICC_APR_EL1 | + ICH_HFGWTR_EL2_ICC_CR0_EL1 | + ICH_HFGWTR_EL2_ICC_PCR_EL1 | + ICH_HFGWTR_EL2_ICC_ICSR_EL1 | + ICH_HFGWTR_EL2_ICC_PPI_ENABLERn_EL1 | + ICH_HFGWTR_EL2_ICC_PPI_PENDRn_EL1 | + ICH_HFGWTR_EL2_ICC_PPI_PRIORITYRn_EL1 | + ICH_HFGWTR_EL2_ICC_PPI_ACTIVERn_EL1, + FEAT_GCIE), +}; + +static const DECLARE_FEAT_MAP_FGT(ich_hfgwtr_desc, ich_hfgwtr_masks, + ich_hfgwtr_feat_map, FEAT_GCIE); + +static const struct reg_bits_to_feat_map ich_hfgitr_feat_map[] = { + NEEDS_FEAT(ICH_HFGITR_EL2_GICCDEN | + ICH_HFGITR_EL2_GICCDDIS | + ICH_HFGITR_EL2_GICCDPRI | + ICH_HFGITR_EL2_GICCDAFF | + ICH_HFGITR_EL2_GICCDPEND | + ICH_HFGITR_EL2_GICCDRCFG | + ICH_HFGITR_EL2_GICCDHM | + ICH_HFGITR_EL2_GICCDEOI | + ICH_HFGITR_EL2_GICCDDI | + ICH_HFGITR_EL2_GICRCDIA | + ICH_HFGITR_EL2_GICRCDNMIA, + FEAT_GCIE), +}; + +static const DECLARE_FEAT_MAP_FGT(ich_hfgitr_desc, ich_hfgitr_masks, + ich_hfgitr_feat_map, FEAT_GCIE); + static void __init check_feat_map(const struct reg_bits_to_feat_map *map, int map_size, u64 resx, const char *str) { @@ -1328,6 +1381,9 @@ void __init check_feature_map(void) check_reg_desc(&sctlr_el2_desc); check_reg_desc(&mdcr_el2_desc); check_reg_desc(&vtcr_el2_desc); + check_reg_desc(&ich_hfgrtr_desc); + check_reg_desc(&ich_hfgwtr_desc); + check_reg_desc(&ich_hfgitr_desc); } static bool idreg_feat_match(struct kvm *kvm, const struct reg_bits_to_feat_map *map) @@ -1460,6 +1516,13 @@ void compute_fgu(struct kvm *kvm, enum fgt_group_id fgt) val |= compute_fgu_bits(kvm, &hdfgrtr2_desc); val |= compute_fgu_bits(kvm, &hdfgwtr2_desc); break; + case ICH_HFGRTR_GROUP: + val |= compute_fgu_bits(kvm, &ich_hfgrtr_desc); + val |= compute_fgu_bits(kvm, &ich_hfgwtr_desc); + break; + case ICH_HFGITR_GROUP: + val |= compute_fgu_bits(kvm, &ich_hfgitr_desc); + break; default: BUG(); } @@ -1531,6 +1594,15 @@ struct resx get_reg_fixed_bits(struct kvm *kvm, enum vcpu_sysreg reg) case VTCR_EL2: resx = compute_reg_resx_bits(kvm, &vtcr_el2_desc, 0, 0); break; + case ICH_HFGRTR_EL2: + resx = compute_reg_resx_bits(kvm, &ich_hfgrtr_desc, 0, 0); + break; + case ICH_HFGWTR_EL2: + resx = compute_reg_resx_bits(kvm, &ich_hfgwtr_desc, 0, 0); + break; + case ICH_HFGITR_EL2: + resx = compute_reg_resx_bits(kvm, &ich_hfgitr_desc, 0, 0); + break; default: WARN_ON_ONCE(1); resx = (typeof(resx)){}; @@ -1565,6 +1637,12 @@ static __always_inline struct fgt_masks *__fgt_reg_to_masks(enum vcpu_sysreg reg return &hdfgrtr2_masks; case HDFGWTR2_EL2: return &hdfgwtr2_masks; + case ICH_HFGRTR_EL2: + return &ich_hfgrtr_masks; + case ICH_HFGWTR_EL2: + return &ich_hfgwtr_masks; + case ICH_HFGITR_EL2: + return &ich_hfgitr_masks; default: BUILD_BUG_ON(1); } @@ -1606,6 +1684,32 @@ static void __compute_hdfgwtr(struct kvm_vcpu *vcpu) *vcpu_fgt(vcpu, HDFGWTR_EL2) |= HDFGWTR_EL2_MDSCR_EL1; } +static void __compute_ich_hfgrtr(struct kvm_vcpu *vcpu) +{ + __compute_fgt(vcpu, ICH_HFGRTR_EL2); + + /* + * ICC_IAFFIDR_EL1 *always* needs to be trapped when running a guest. + * + * We also trap accesses to ICC_IDR0_EL1 to allow us to completely hide + * FEAT_GCIE_LEGACY from the guest, and to (potentially) present fewer + * ID bits than the host supports. + */ + *vcpu_fgt(vcpu, ICH_HFGRTR_EL2) &= ~(ICH_HFGRTR_EL2_ICC_IAFFIDR_EL1 | + ICH_HFGRTR_EL2_ICC_IDRn_EL1); +} + +static void __compute_ich_hfgwtr(struct kvm_vcpu *vcpu) +{ + __compute_fgt(vcpu, ICH_HFGWTR_EL2); + + /* + * We present a different subset of PPIs the guest from what + * exist in real hardware. We only trap writes, not reads. + */ + *vcpu_fgt(vcpu, ICH_HFGWTR_EL2) &= ~(ICH_HFGWTR_EL2_ICC_PPI_ENABLERn_EL1); +} + void kvm_vcpu_load_fgt(struct kvm_vcpu *vcpu) { if (!cpus_have_final_cap(ARM64_HAS_FGT)) @@ -1618,12 +1722,17 @@ void kvm_vcpu_load_fgt(struct kvm_vcpu *vcpu) __compute_hdfgwtr(vcpu); __compute_fgt(vcpu, HAFGRTR_EL2); - if (!cpus_have_final_cap(ARM64_HAS_FGT2)) - return; + if (cpus_have_final_cap(ARM64_HAS_FGT2)) { + __compute_fgt(vcpu, HFGRTR2_EL2); + __compute_fgt(vcpu, HFGWTR2_EL2); + __compute_fgt(vcpu, HFGITR2_EL2); + __compute_fgt(vcpu, HDFGRTR2_EL2); + __compute_fgt(vcpu, HDFGWTR2_EL2); + } - __compute_fgt(vcpu, HFGRTR2_EL2); - __compute_fgt(vcpu, HFGWTR2_EL2); - __compute_fgt(vcpu, HFGITR2_EL2); - __compute_fgt(vcpu, HDFGRTR2_EL2); - __compute_fgt(vcpu, HDFGWTR2_EL2); + if (cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) { + __compute_ich_hfgrtr(vcpu); + __compute_ich_hfgwtr(vcpu); + __compute_fgt(vcpu, ICH_HFGITR_EL2); + } } diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 22d497554c94..dba7ced74ca5 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -2053,6 +2053,60 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { SR_FGT(SYS_AMEVCNTR0_EL0(2), HAFGRTR, AMEVCNTR02_EL0, 1), SR_FGT(SYS_AMEVCNTR0_EL0(1), HAFGRTR, AMEVCNTR01_EL0, 1), SR_FGT(SYS_AMEVCNTR0_EL0(0), HAFGRTR, AMEVCNTR00_EL0, 1), + + /* + * ICH_HFGRTR_EL2 & ICH_HFGWTR_EL2 + */ + SR_FGT(SYS_ICC_APR_EL1, ICH_HFGRTR, ICC_APR_EL1, 0), + SR_FGT(SYS_ICC_IDR0_EL1, ICH_HFGRTR, ICC_IDRn_EL1, 0), + SR_FGT(SYS_ICC_CR0_EL1, ICH_HFGRTR, ICC_CR0_EL1, 0), + SR_FGT(SYS_ICC_HPPIR_EL1, ICH_HFGRTR, ICC_HPPIR_EL1, 0), + SR_FGT(SYS_ICC_PCR_EL1, ICH_HFGRTR, ICC_PCR_EL1, 0), + SR_FGT(SYS_ICC_ICSR_EL1, ICH_HFGRTR, ICC_ICSR_EL1, 0), + SR_FGT(SYS_ICC_IAFFIDR_EL1, ICH_HFGRTR, ICC_IAFFIDR_EL1, 0), + SR_FGT(SYS_ICC_PPI_HMR0_EL1, ICH_HFGRTR, ICC_PPI_HMRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_HMR1_EL1, ICH_HFGRTR, ICC_PPI_HMRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_ENABLER0_EL1, ICH_HFGRTR, ICC_PPI_ENABLERn_EL1, 0), + SR_FGT(SYS_ICC_PPI_ENABLER1_EL1, ICH_HFGRTR, ICC_PPI_ENABLERn_EL1, 0), + SR_FGT(SYS_ICC_PPI_CPENDR0_EL1, ICH_HFGRTR, ICC_PPI_PENDRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_CPENDR1_EL1, ICH_HFGRTR, ICC_PPI_PENDRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_SPENDR0_EL1, ICH_HFGRTR, ICC_PPI_PENDRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_SPENDR1_EL1, ICH_HFGRTR, ICC_PPI_PENDRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR0_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR1_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR2_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR3_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR4_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR5_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR6_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR7_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR8_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR9_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR10_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR11_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR12_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR13_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR14_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_PRIORITYR15_EL1, ICH_HFGRTR, ICC_PPI_PRIORITYRn_EL1, 0), + SR_FGT(SYS_ICC_PPI_CACTIVER0_EL1, ICH_HFGRTR, ICC_PPI_ACTIVERn_EL1, 0), + SR_FGT(SYS_ICC_PPI_CACTIVER1_EL1, ICH_HFGRTR, ICC_PPI_ACTIVERn_EL1, 0), + SR_FGT(SYS_ICC_PPI_SACTIVER0_EL1, ICH_HFGRTR, ICC_PPI_ACTIVERn_EL1, 0), + SR_FGT(SYS_ICC_PPI_SACTIVER1_EL1, ICH_HFGRTR, ICC_PPI_ACTIVERn_EL1, 0), + + /* + * ICH_HFGITR_EL2 + */ + SR_FGT(GICV5_OP_GIC_CDEN, ICH_HFGITR, GICCDEN, 0), + SR_FGT(GICV5_OP_GIC_CDDIS, ICH_HFGITR, GICCDDIS, 0), + SR_FGT(GICV5_OP_GIC_CDPRI, ICH_HFGITR, GICCDPRI, 0), + SR_FGT(GICV5_OP_GIC_CDAFF, ICH_HFGITR, GICCDAFF, 0), + SR_FGT(GICV5_OP_GIC_CDPEND, ICH_HFGITR, GICCDPEND, 0), + SR_FGT(GICV5_OP_GIC_CDRCFG, ICH_HFGITR, GICCDRCFG, 0), + SR_FGT(GICV5_OP_GIC_CDHM, ICH_HFGITR, GICCDHM, 0), + SR_FGT(GICV5_OP_GIC_CDEOI, ICH_HFGITR, GICCDEOI, 0), + SR_FGT(GICV5_OP_GIC_CDDI, ICH_HFGITR, GICCDDI, 0), + SR_FGT(GICV5_OP_GICR_CDIA, ICH_HFGITR, GICRCDIA, 0), + SR_FGT(GICV5_OP_GICR_CDNMIA, ICH_HFGITR, GICRCDNMIA, 0), }; /* @@ -2127,6 +2181,9 @@ FGT_MASKS(hfgwtr2_masks, HFGWTR2_EL2); FGT_MASKS(hfgitr2_masks, HFGITR2_EL2); FGT_MASKS(hdfgrtr2_masks, HDFGRTR2_EL2); FGT_MASKS(hdfgwtr2_masks, HDFGWTR2_EL2); +FGT_MASKS(ich_hfgrtr_masks, ICH_HFGRTR_EL2); +FGT_MASKS(ich_hfgwtr_masks, ICH_HFGWTR_EL2); +FGT_MASKS(ich_hfgitr_masks, ICH_HFGITR_EL2); static __init bool aggregate_fgt(union trap_config tc) { @@ -2162,6 +2219,14 @@ static __init bool aggregate_fgt(union trap_config tc) rmasks = &hfgitr2_masks; wmasks = NULL; break; + case ICH_HFGRTR_GROUP: + rmasks = &ich_hfgrtr_masks; + wmasks = &ich_hfgwtr_masks; + break; + case ICH_HFGITR_GROUP: + rmasks = &ich_hfgitr_masks; + wmasks = NULL; + break; } rresx = rmasks->res0 | rmasks->res1; @@ -2232,6 +2297,9 @@ static __init int check_all_fgt_masks(int ret) &hfgitr2_masks, &hdfgrtr2_masks, &hdfgwtr2_masks, + &ich_hfgrtr_masks, + &ich_hfgwtr_masks, + &ich_hfgitr_masks, }; int err = 0; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 2597e8bda867..ae04fd680d1e 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -233,6 +233,18 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu) __activate_fgt(hctxt, vcpu, HDFGWTR2_EL2); } +static inline void __activate_traps_ich_hfgxtr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) + return; + + __activate_fgt(hctxt, vcpu, ICH_HFGRTR_EL2); + __activate_fgt(hctxt, vcpu, ICH_HFGWTR_EL2); + __activate_fgt(hctxt, vcpu, ICH_HFGITR_EL2); +} + #define __deactivate_fgt(htcxt, vcpu, reg) \ do { \ write_sysreg_s(ctxt_sys_reg(hctxt, reg), \ @@ -265,6 +277,19 @@ static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu) __deactivate_fgt(hctxt, vcpu, HDFGWTR2_EL2); } +static inline void __deactivate_traps_ich_hfgxtr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) + return; + + __deactivate_fgt(hctxt, vcpu, ICH_HFGRTR_EL2); + __deactivate_fgt(hctxt, vcpu, ICH_HFGWTR_EL2); + __deactivate_fgt(hctxt, vcpu, ICH_HFGITR_EL2); + +} + static inline void __activate_traps_mpam(struct kvm_vcpu *vcpu) { u64 r = MPAM2_EL2_TRAPMPAM0EL1 | MPAM2_EL2_TRAPMPAM1EL1; @@ -328,6 +353,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) } __activate_traps_hfgxtr(vcpu); + __activate_traps_ich_hfgxtr(vcpu); __activate_traps_mpam(vcpu); } @@ -345,6 +371,7 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2); __deactivate_traps_hfgxtr(vcpu); + __deactivate_traps_ich_hfgxtr(vcpu); __deactivate_traps_mpam(); } diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 3d33fbefdfc1..62cdfbff7562 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -26,7 +26,7 @@ hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \ cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o hyp-obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ - ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o + ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o ../vgic-v5-sr.o hyp-obj-y += ../../../kernel/smccc-call.o hyp-obj-$(CONFIG_LIST_HARDENED) += list_debug.o hyp-obj-$(CONFIG_NVHE_EL2_TRACING) += clock.o trace.o events.o diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index eff9cb208627..31f080307d95 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -650,6 +650,20 @@ static void handle___tracing_write_event(struct kvm_cpu_context *host_ctxt) trace_selftest(id); } +static void handle___vgic_v5_save_apr(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct vgic_v5_cpu_if *, cpu_if, host_ctxt, 1); + + __vgic_v5_save_apr(kern_hyp_va(cpu_if)); +} + +static void handle___vgic_v5_restore_vmcr_apr(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct vgic_v5_cpu_if *, cpu_if, host_ctxt, 1); + + __vgic_v5_restore_vmcr_apr(kern_hyp_va(cpu_if)); +} + typedef void (*hcall_t)(struct kvm_cpu_context *); #define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x @@ -683,6 +697,8 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_timer_set_cntvoff), HANDLE_FUNC(__vgic_v3_save_aprs), HANDLE_FUNC(__vgic_v3_restore_vmcr_aprs), + HANDLE_FUNC(__vgic_v5_save_apr), + HANDLE_FUNC(__vgic_v5_restore_vmcr_apr), HANDLE_FUNC(__pkvm_reserve_vm), HANDLE_FUNC(__pkvm_unreserve_vm), HANDLE_FUNC(__pkvm_init_vm), diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index ca60721501d1..ed8830c707b0 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -44,6 +44,9 @@ struct fgt_masks hfgwtr2_masks; struct fgt_masks hfgitr2_masks; struct fgt_masks hdfgrtr2_masks; struct fgt_masks hdfgwtr2_masks; +struct fgt_masks ich_hfgrtr_masks; +struct fgt_masks ich_hfgwtr_masks; +struct fgt_masks ich_hfgitr_masks; extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); @@ -110,6 +113,12 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) /* Save VGICv3 state on non-VHE systems */ static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu) { + if (vgic_is_v5(kern_hyp_va(vcpu->kvm))) { + __vgic_v5_save_state(&vcpu->arch.vgic_cpu.vgic_v5); + __vgic_v5_save_ppi_state(&vcpu->arch.vgic_cpu.vgic_v5); + return; + } + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); @@ -119,6 +128,12 @@ static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu) /* Restore VGICv3 state on non-VHE systems */ static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) { + if (vgic_is_v5(kern_hyp_va(vcpu->kvm))) { + __vgic_v5_restore_state(&vcpu->arch.vgic_cpu.vgic_v5); + __vgic_v5_restore_ppi_state(&vcpu->arch.vgic_cpu.vgic_v5); + return; + } + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 06d28621722e..b40fd01ebf32 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -20,6 +20,7 @@ */ u64 id_aa64pfr0_el1_sys_val; u64 id_aa64pfr1_el1_sys_val; +u64 id_aa64pfr2_el1_sys_val; u64 id_aa64isar0_el1_sys_val; u64 id_aa64isar1_el1_sys_val; u64 id_aa64isar2_el1_sys_val; @@ -108,6 +109,11 @@ static const struct pvm_ftr_bits pvmid_aa64pfr1[] = { FEAT_END }; +static const struct pvm_ftr_bits pvmid_aa64pfr2[] = { + MAX_FEAT(ID_AA64PFR2_EL1, GCIE, NI), + FEAT_END +}; + static const struct pvm_ftr_bits pvmid_aa64mmfr0[] = { MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, PARANGE, 40), MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, ASIDBITS, 16), @@ -221,6 +227,8 @@ static u64 pvm_calc_id_reg(const struct kvm_vcpu *vcpu, u32 id) return get_restricted_features(vcpu, id_aa64pfr0_el1_sys_val, pvmid_aa64pfr0); case SYS_ID_AA64PFR1_EL1: return get_restricted_features(vcpu, id_aa64pfr1_el1_sys_val, pvmid_aa64pfr1); + case SYS_ID_AA64PFR2_EL1: + return get_restricted_features(vcpu, id_aa64pfr2_el1_sys_val, pvmid_aa64pfr2); case SYS_ID_AA64ISAR0_EL1: return id_aa64isar0_el1_sys_val; case SYS_ID_AA64ISAR1_EL1: diff --git a/arch/arm64/kvm/hyp/vgic-v5-sr.c b/arch/arm64/kvm/hyp/vgic-v5-sr.c new file mode 100644 index 000000000000..2c4304ffa9f3 --- /dev/null +++ b/arch/arm64/kvm/hyp/vgic-v5-sr.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025, 2026 - Arm Ltd + */ + +#include <linux/irqchip/arm-gic-v5.h> + +#include <asm/kvm_hyp.h> + +void __vgic_v5_save_apr(struct vgic_v5_cpu_if *cpu_if) +{ + cpu_if->vgic_apr = read_sysreg_s(SYS_ICH_APR_EL2); +} + +static void __vgic_v5_compat_mode_disable(void) +{ + sysreg_clear_set_s(SYS_ICH_VCTLR_EL2, ICH_VCTLR_EL2_V3, 0); + isb(); +} + +void __vgic_v5_restore_vmcr_apr(struct vgic_v5_cpu_if *cpu_if) +{ + __vgic_v5_compat_mode_disable(); + + write_sysreg_s(cpu_if->vgic_vmcr, SYS_ICH_VMCR_EL2); + write_sysreg_s(cpu_if->vgic_apr, SYS_ICH_APR_EL2); +} + +void __vgic_v5_save_ppi_state(struct vgic_v5_cpu_if *cpu_if) +{ + /* + * The following code assumes that the bitmap storage that we have for + * PPIs is either 64 (architected PPIs, only) or 128 bits (architected & + * impdef PPIs). + */ + BUILD_BUG_ON(VGIC_V5_NR_PRIVATE_IRQS % 64); + + bitmap_write(host_data_ptr(vgic_v5_ppi_state)->activer_exit, + read_sysreg_s(SYS_ICH_PPI_ACTIVER0_EL2), 0, 64); + bitmap_write(host_data_ptr(vgic_v5_ppi_state)->pendr_exit, + read_sysreg_s(SYS_ICH_PPI_PENDR0_EL2), 0, 64); + + cpu_if->vgic_ppi_priorityr[0] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR0_EL2); + cpu_if->vgic_ppi_priorityr[1] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR1_EL2); + cpu_if->vgic_ppi_priorityr[2] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR2_EL2); + cpu_if->vgic_ppi_priorityr[3] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR3_EL2); + cpu_if->vgic_ppi_priorityr[4] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR4_EL2); + cpu_if->vgic_ppi_priorityr[5] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR5_EL2); + cpu_if->vgic_ppi_priorityr[6] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR6_EL2); + cpu_if->vgic_ppi_priorityr[7] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR7_EL2); + + if (VGIC_V5_NR_PRIVATE_IRQS == 128) { + bitmap_write(host_data_ptr(vgic_v5_ppi_state)->activer_exit, + read_sysreg_s(SYS_ICH_PPI_ACTIVER1_EL2), 64, 64); + bitmap_write(host_data_ptr(vgic_v5_ppi_state)->pendr_exit, + read_sysreg_s(SYS_ICH_PPI_PENDR1_EL2), 64, 64); + + cpu_if->vgic_ppi_priorityr[8] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR8_EL2); + cpu_if->vgic_ppi_priorityr[9] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR9_EL2); + cpu_if->vgic_ppi_priorityr[10] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR10_EL2); + cpu_if->vgic_ppi_priorityr[11] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR11_EL2); + cpu_if->vgic_ppi_priorityr[12] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR12_EL2); + cpu_if->vgic_ppi_priorityr[13] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR13_EL2); + cpu_if->vgic_ppi_priorityr[14] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR14_EL2); + cpu_if->vgic_ppi_priorityr[15] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR15_EL2); + } + + /* Now that we are done, disable DVI */ + write_sysreg_s(0, SYS_ICH_PPI_DVIR0_EL2); + write_sysreg_s(0, SYS_ICH_PPI_DVIR1_EL2); +} + +void __vgic_v5_restore_ppi_state(struct vgic_v5_cpu_if *cpu_if) +{ + DECLARE_BITMAP(pendr, VGIC_V5_NR_PRIVATE_IRQS); + + /* We assume 64 or 128 PPIs - see above comment */ + BUILD_BUG_ON(VGIC_V5_NR_PRIVATE_IRQS % 64); + + /* Enable DVI so that the guest's interrupt config takes over */ + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_dvir, 0, 64), + SYS_ICH_PPI_DVIR0_EL2); + + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_activer, 0, 64), + SYS_ICH_PPI_ACTIVER0_EL2); + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_enabler, 0, 64), + SYS_ICH_PPI_ENABLER0_EL2); + + /* Update the pending state of the NON-DVI'd PPIs, only */ + bitmap_andnot(pendr, host_data_ptr(vgic_v5_ppi_state)->pendr_entry, + cpu_if->vgic_ppi_dvir, VGIC_V5_NR_PRIVATE_IRQS); + write_sysreg_s(bitmap_read(pendr, 0, 64), SYS_ICH_PPI_PENDR0_EL2); + + write_sysreg_s(cpu_if->vgic_ppi_priorityr[0], + SYS_ICH_PPI_PRIORITYR0_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[1], + SYS_ICH_PPI_PRIORITYR1_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[2], + SYS_ICH_PPI_PRIORITYR2_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[3], + SYS_ICH_PPI_PRIORITYR3_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[4], + SYS_ICH_PPI_PRIORITYR4_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[5], + SYS_ICH_PPI_PRIORITYR5_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[6], + SYS_ICH_PPI_PRIORITYR6_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[7], + SYS_ICH_PPI_PRIORITYR7_EL2); + + if (VGIC_V5_NR_PRIVATE_IRQS == 128) { + /* Enable DVI so that the guest's interrupt config takes over */ + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_dvir, 64, 64), + SYS_ICH_PPI_DVIR1_EL2); + + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_activer, 64, 64), + SYS_ICH_PPI_ACTIVER1_EL2); + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_enabler, 64, 64), + SYS_ICH_PPI_ENABLER1_EL2); + write_sysreg_s(bitmap_read(pendr, 64, 64), + SYS_ICH_PPI_PENDR1_EL2); + + write_sysreg_s(cpu_if->vgic_ppi_priorityr[8], + SYS_ICH_PPI_PRIORITYR8_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[9], + SYS_ICH_PPI_PRIORITYR9_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[10], + SYS_ICH_PPI_PRIORITYR10_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[11], + SYS_ICH_PPI_PRIORITYR11_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[12], + SYS_ICH_PPI_PRIORITYR12_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[13], + SYS_ICH_PPI_PRIORITYR13_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[14], + SYS_ICH_PPI_PRIORITYR14_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[15], + SYS_ICH_PPI_PRIORITYR15_EL2); + } else { + write_sysreg_s(0, SYS_ICH_PPI_DVIR1_EL2); + + write_sysreg_s(0, SYS_ICH_PPI_ACTIVER1_EL2); + write_sysreg_s(0, SYS_ICH_PPI_ENABLER1_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PENDR1_EL2); + + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR8_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR9_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR10_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR11_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR12_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR13_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR14_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR15_EL2); + } +} + +void __vgic_v5_save_state(struct vgic_v5_cpu_if *cpu_if) +{ + cpu_if->vgic_vmcr = read_sysreg_s(SYS_ICH_VMCR_EL2); + cpu_if->vgic_icsr = read_sysreg_s(SYS_ICC_ICSR_EL1); +} + +void __vgic_v5_restore_state(struct vgic_v5_cpu_if *cpu_if) +{ + write_sysreg_s(cpu_if->vgic_icsr, SYS_ICC_ICSR_EL1); +} diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile index afc4aed9231a..9695328bbd96 100644 --- a/arch/arm64/kvm/hyp/vhe/Makefile +++ b/arch/arm64/kvm/hyp/vhe/Makefile @@ -10,4 +10,4 @@ CFLAGS_switch.o += -Wno-override-init obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ - ../fpsimd.o ../hyp-entry.o ../exception.o + ../fpsimd.o ../hyp-entry.o ../exception.o ../vgic-v5-sr.o diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 2c43097248b2..efd5d21c7ac7 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -1558,6 +1558,11 @@ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val) ID_AA64PFR1_EL1_MTE); break; + case SYS_ID_AA64PFR2_EL1: + /* GICv5 is not yet supported for NV */ + val &= ~ID_AA64PFR2_EL1_GCIE; + break; + case SYS_ID_AA64MMFR0_EL1: /* Hide ExS, Secure Memory */ val &= ~(ID_AA64MMFR0_EL1_EXS | diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 93cc9bbb5cec..e1860acae641 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -939,7 +939,8 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) * number against the dimensions of the vgic and make sure * it's valid. */ - if (!irq_is_ppi(irq) && !vgic_valid_spi(vcpu->kvm, irq)) + if (!irq_is_ppi(vcpu->kvm, irq) && + !vgic_valid_spi(vcpu->kvm, irq)) return -EINVAL; } else if (kvm_arm_pmu_irq_initialized(vcpu)) { return -EINVAL; @@ -961,8 +962,13 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) if (!vgic_initialized(vcpu->kvm)) return -ENODEV; - if (!kvm_arm_pmu_irq_initialized(vcpu)) - return -ENXIO; + if (!kvm_arm_pmu_irq_initialized(vcpu)) { + if (!vgic_is_v5(vcpu->kvm)) + return -ENXIO; + + /* Use the architected irq number for GICv5. */ + vcpu->arch.pmu.irq_num = KVM_ARMV8_PMU_GICV5_IRQ; + } ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num, &vcpu->arch.pmu); @@ -987,11 +993,15 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) unsigned long i; struct kvm_vcpu *vcpu; + /* On GICv5, the PMUIRQ is architecturally mandated to be PPI 23 */ + if (vgic_is_v5(kvm) && irq != KVM_ARMV8_PMU_GICV5_IRQ) + return false; + kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_arm_pmu_irq_initialized(vcpu)) continue; - if (irq_is_ppi(irq)) { + if (irq_is_ppi(vcpu->kvm, irq)) { if (vcpu->arch.pmu.irq_num != irq) return false; } else { @@ -1142,7 +1152,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -EFAULT; /* The PMU overflow interrupt can be a PPI or a valid SPI. */ - if (!(irq_is_ppi(irq) || irq_is_spi(irq))) + if (!(irq_is_ppi(vcpu->kvm, irq) || irq_is_spi(vcpu->kvm, irq))) return -EINVAL; if (!pmu_irq_is_valid(kvm, irq)) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 1b4cacb6e918..e1001544d4f4 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -681,6 +681,91 @@ static bool access_gic_dir(struct kvm_vcpu *vcpu, return true; } +static bool access_gicv5_idr0(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return undef_access(vcpu, p, r); + + /* + * Expose KVM's priority- and ID-bits to the guest, but not GCIE_LEGACY. + * + * Note: for GICv5 the mimic the way that the num_pri_bits and + * num_id_bits fields are used with GICv3: + * - num_pri_bits stores the actual number of priority bits, whereas the + * register field stores num_pri_bits - 1. + * - num_id_bits stores the raw field value, which is 0b0000 for 16 bits + * and 0b0001 for 24 bits. + */ + p->regval = FIELD_PREP(ICC_IDR0_EL1_PRI_BITS, vcpu->arch.vgic_cpu.num_pri_bits - 1) | + FIELD_PREP(ICC_IDR0_EL1_ID_BITS, vcpu->arch.vgic_cpu.num_id_bits); + + return true; +} + +static bool access_gicv5_iaffid(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return undef_access(vcpu, p, r); + + /* + * For GICv5 VMs, the IAFFID value is the same as the VPE ID. The VPE ID + * is the same as the VCPU's ID. + */ + p->regval = FIELD_PREP(ICC_IAFFIDR_EL1_IAFFID, vcpu->vcpu_id); + + return true; +} + +static bool access_gicv5_ppi_enabler(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + unsigned long *mask = vcpu->kvm->arch.vgic.gicv5_vm.vgic_ppi_mask; + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + int i; + + /* We never expect to get here with a read! */ + if (WARN_ON_ONCE(!p->is_write)) + return undef_access(vcpu, p, r); + + /* + * If we're only handling architected PPIs and the guest writes to the + * enable for the non-architected PPIs, we just return as there's + * nothing to do at all. We don't even allocate the storage for them in + * this case. + */ + if (VGIC_V5_NR_PRIVATE_IRQS == 64 && p->Op2 % 2) + return true; + + /* + * Merge the raw guest write into out bitmap at an offset of either 0 or + * 64, then and it with our PPI mask. + */ + bitmap_write(cpu_if->vgic_ppi_enabler, p->regval, 64 * (p->Op2 % 2), 64); + bitmap_and(cpu_if->vgic_ppi_enabler, cpu_if->vgic_ppi_enabler, mask, + VGIC_V5_NR_PRIVATE_IRQS); + + /* + * Sync the change in enable states to the vgic_irqs. We consider all + * PPIs as we don't expose many to the guest. + */ + for_each_set_bit(i, mask, VGIC_V5_NR_PRIVATE_IRQS) { + u32 intid = vgic_v5_make_ppi(i); + struct vgic_irq *irq; + + irq = vgic_get_vcpu_irq(vcpu, intid); + + scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) + irq->enabled = test_bit(i, cpu_if->vgic_ppi_enabler); + + vgic_put_irq(vcpu->kvm, irq); + } + + return true; +} + static bool trap_raz_wi(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) @@ -1758,6 +1843,7 @@ static u8 pmuver_to_perfmon(u8 pmuver) static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val); static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val); +static u64 sanitise_id_aa64pfr2_el1(const struct kvm_vcpu *vcpu, u64 val); static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val); /* Read a sanitised cpufeature ID register by sys_reg_desc */ @@ -1783,10 +1869,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, val = sanitise_id_aa64pfr1_el1(vcpu, val); break; case SYS_ID_AA64PFR2_EL1: - val &= ID_AA64PFR2_EL1_FPMR | - (kvm_has_mte(vcpu->kvm) ? - ID_AA64PFR2_EL1_MTEFAR | ID_AA64PFR2_EL1_MTESTOREONLY : - 0); + val = sanitise_id_aa64pfr2_el1(vcpu, val); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) @@ -1985,7 +2068,7 @@ static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val) val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, CSV3, IMP); } - if (vgic_is_v3(vcpu->kvm)) { + if (vgic_host_has_gicv3()) { val &= ~ID_AA64PFR0_EL1_GIC_MASK; val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); } @@ -2027,6 +2110,23 @@ static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val) return val; } +static u64 sanitise_id_aa64pfr2_el1(const struct kvm_vcpu *vcpu, u64 val) +{ + val &= ID_AA64PFR2_EL1_FPMR | + ID_AA64PFR2_EL1_MTEFAR | + ID_AA64PFR2_EL1_MTESTOREONLY; + + if (!kvm_has_mte(vcpu->kvm)) { + val &= ~ID_AA64PFR2_EL1_MTEFAR; + val &= ~ID_AA64PFR2_EL1_MTESTOREONLY; + } + + if (vgic_host_has_gicv5()) + val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR2_EL1, GCIE, IMP); + + return 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); @@ -2177,14 +2277,6 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val))) return -EINVAL; - /* - * If we are running on a GICv5 host and support FEAT_GCIE_LEGACY, then - * we support GICv3. Fail attempts to do anything but set that to IMP. - */ - if (vgic_is_v3_compat(vcpu->kvm) && - FIELD_GET(ID_AA64PFR0_EL1_GIC_MASK, user_val) != ID_AA64PFR0_EL1_GIC_IMP) - return -EINVAL; - return set_id_reg(vcpu, rd, user_val); } @@ -2224,6 +2316,12 @@ static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu, return set_id_reg(vcpu, rd, user_val); } +static int set_id_aa64pfr2_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, u64 user_val) +{ + return set_id_reg(vcpu, rd, user_val); +} + /* * Allow userspace to de-feature a stage-2 translation granule but prevent it * from claiming the impossible. @@ -3205,10 +3303,11 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64PFR1_EL1_RES0 | ID_AA64PFR1_EL1_MPAM_frac | ID_AA64PFR1_EL1_MTE)), - ID_WRITABLE(ID_AA64PFR2_EL1, - ID_AA64PFR2_EL1_FPMR | - ID_AA64PFR2_EL1_MTEFAR | - ID_AA64PFR2_EL1_MTESTOREONLY), + ID_FILTERED(ID_AA64PFR2_EL1, id_aa64pfr2_el1, + ~(ID_AA64PFR2_EL1_FPMR | + ID_AA64PFR2_EL1_MTEFAR | + ID_AA64PFR2_EL1_MTESTOREONLY | + ID_AA64PFR2_EL1_GCIE)), ID_UNALLOCATED(4,3), ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0), ID_HIDDEN(ID_AA64SMFR0_EL1), @@ -3391,6 +3490,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ICC_AP1R1_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP1R2_EL1), undef_access }, { SYS_DESC(SYS_ICC_AP1R3_EL1), undef_access }, + { SYS_DESC(SYS_ICC_IDR0_EL1), access_gicv5_idr0 }, + { SYS_DESC(SYS_ICC_IAFFIDR_EL1), access_gicv5_iaffid }, + { SYS_DESC(SYS_ICC_PPI_ENABLER0_EL1), access_gicv5_ppi_enabler }, + { SYS_DESC(SYS_ICC_PPI_ENABLER1_EL1), access_gicv5_ppi_enabler }, { SYS_DESC(SYS_ICC_DIR_EL1), access_gic_dir }, { SYS_DESC(SYS_ICC_RPR_EL1), undef_access }, { SYS_DESC(SYS_ICC_SGI1R_EL1), access_gic_sgi }, @@ -5647,6 +5750,8 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu) compute_fgu(kvm, HFGRTR2_GROUP); compute_fgu(kvm, HFGITR2_GROUP); compute_fgu(kvm, HDFGRTR2_GROUP); + compute_fgu(kvm, ICH_HFGRTR_GROUP); + compute_fgu(kvm, ICH_HFGITR_GROUP); set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags); out: @@ -5667,17 +5772,52 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) guard(mutex)(&kvm->arch.config_lock); + if (kvm_vm_has_ran_once(kvm)) + return 0; + /* * This hacks into the ID registers, so only perform it when the * first vcpu runs, or the kvm_set_vm_id_reg() helper will scream. */ - if (!irqchip_in_kernel(kvm) && !kvm_vm_has_ran_once(kvm)) { + if (!irqchip_in_kernel(kvm)) { u64 val; val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val); + val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR2_EL1) & ~ID_AA64PFR2_EL1_GCIE; + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR2_EL1, val); val = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, val); + } else { + /* + * Certain userspace software - QEMU - samples the system + * register state without creating an irqchip, then blindly + * restores the state prior to running the final guest. This + * means that it restores the virtualization & emulation + * capabilities of the host system, rather than something that + * reflects the final guest state. Moreover, it checks that the + * state was "correctly" restored (i.e., verbatim), bailing if + * it isn't, so masking off invalid state isn't an option. + * + * On GICv5 hardware that supports FEAT_GCIE_LEGACY we can run + * both GICv3- and GICv5-based guests. Therefore, we initially + * present both ID_AA64PFR0.GIC and ID_AA64PFR2.GCIE as IMP to + * reflect that userspace can create EITHER a vGICv3 or a + * vGICv5. This is an architecturally invalid combination, of + * course. Once an in-kernel GIC is created, the sysreg state is + * updated to reflect the actual, valid configuration. + * + * Setting both the GIC and GCIE features to IMP unsurprisingly + * results in guests falling over, and hence we need to fix up + * this mess in KVM. Before running for the first time we yet + * again ensure that the GIC and GCIE fields accurately reflect + * the actual hardware the guest should see. + * + * This hack allows legacy QEMU-based GICv3 guests to run + * unmodified on compatible GICv5 hosts, and avoids the inverse + * problem for GICv5-based guests in the future. + */ + kvm_vgic_finalize_idregs(kvm); } if (vcpu_has_nv(vcpu)) { diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index e9b8b5fc480c..47169604100f 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -66,12 +66,11 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); * or through the generic KVM_CREATE_DEVICE API ioctl. * irqchip_in_kernel() tells you if this function succeeded or not. * @kvm: kvm struct pointer - * @type: KVM_DEV_TYPE_ARM_VGIC_V[23] + * @type: KVM_DEV_TYPE_ARM_VGIC_V[235] */ int kvm_vgic_create(struct kvm *kvm, u32 type) { struct kvm_vcpu *vcpu; - u64 aa64pfr0, pfr1; unsigned long i; int ret; @@ -132,8 +131,11 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) if (type == KVM_DEV_TYPE_ARM_VGIC_V2) kvm->max_vcpus = VGIC_V2_MAX_CPUS; - else + else if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->max_vcpus = VGIC_V3_MAX_CPUS; + else if (type == KVM_DEV_TYPE_ARM_VGIC_V5) + kvm->max_vcpus = min(VGIC_V5_MAX_CPUS, + kvm_vgic_global_state.max_gic_vcpus); if (atomic_read(&kvm->online_vcpus) > kvm->max_vcpus) { ret = -E2BIG; @@ -145,19 +147,11 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST; kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; - pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; - - if (type == KVM_DEV_TYPE_ARM_VGIC_V2) { - kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - } else { - INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); - aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); - pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); - } - - kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); - kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); + /* + * We've now created the GIC. Update the system register state + * to accurately reflect what we've created. + */ + kvm_vgic_finalize_idregs(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { ret = vgic_allocate_private_irqs_locked(vcpu, type); @@ -179,6 +173,15 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->arch.vgic.nassgicap = system_supports_direct_sgis(); + /* + * We now know that we have a GICv5. The Arch Timer PPI interrupts may + * have been initialised at this stage, but will have done so assuming + * that we have an older GIC, meaning that the IntIDs won't be + * correct. We init them again, and this time they will be correct. + */ + if (type == KVM_DEV_TYPE_ARM_VGIC_V5) + kvm_timer_init_vm(kvm); + out_unlock: mutex_unlock(&kvm->arch.config_lock); kvm_unlock_all_vcpus(kvm); @@ -259,9 +262,65 @@ int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu) return ret; } +static void vgic_allocate_private_irq(struct kvm_vcpu *vcpu, int i, u32 type) +{ + struct vgic_irq *irq = &vcpu->arch.vgic_cpu.private_irqs[i]; + + INIT_LIST_HEAD(&irq->ap_list); + raw_spin_lock_init(&irq->irq_lock); + irq->vcpu = NULL; + irq->target_vcpu = vcpu; + refcount_set(&irq->refcount, 0); + + irq->intid = i; + if (vgic_irq_is_sgi(i)) { + /* SGIs */ + irq->enabled = 1; + irq->config = VGIC_CONFIG_EDGE; + } else { + /* PPIs */ + irq->config = VGIC_CONFIG_LEVEL; + } + + switch (type) { + case KVM_DEV_TYPE_ARM_VGIC_V3: + irq->group = 1; + irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + irq->group = 0; + irq->targets = BIT(vcpu->vcpu_id); + break; + } +} + +static void vgic_v5_allocate_private_irq(struct kvm_vcpu *vcpu, int i, u32 type) +{ + struct vgic_irq *irq = &vcpu->arch.vgic_cpu.private_irqs[i]; + u32 intid = vgic_v5_make_ppi(i); + + INIT_LIST_HEAD(&irq->ap_list); + raw_spin_lock_init(&irq->irq_lock); + irq->vcpu = NULL; + irq->target_vcpu = vcpu; + refcount_set(&irq->refcount, 0); + + irq->intid = intid; + + /* The only Edge architected PPI is the SW_PPI */ + if (i == GICV5_ARCH_PPI_SW_PPI) + irq->config = VGIC_CONFIG_EDGE; + else + irq->config = VGIC_CONFIG_LEVEL; + + /* Register the GICv5-specific PPI ops */ + vgic_v5_set_ppi_ops(vcpu, intid); +} + static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + u32 num_private_irqs; int i; lockdep_assert_held(&vcpu->kvm->arch.config_lock); @@ -269,8 +328,13 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) if (vgic_cpu->private_irqs) return 0; + if (vgic_is_v5(vcpu->kvm)) + num_private_irqs = VGIC_V5_NR_PRIVATE_IRQS; + else + num_private_irqs = VGIC_NR_PRIVATE_IRQS; + vgic_cpu->private_irqs = kzalloc_objs(struct vgic_irq, - VGIC_NR_PRIVATE_IRQS, + num_private_irqs, GFP_KERNEL_ACCOUNT); if (!vgic_cpu->private_irqs) @@ -280,34 +344,11 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) * Enable and configure all SGIs to be edge-triggered and * configure all PPIs as level-triggered. */ - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; - - INIT_LIST_HEAD(&irq->ap_list); - raw_spin_lock_init(&irq->irq_lock); - irq->intid = i; - irq->vcpu = NULL; - irq->target_vcpu = vcpu; - refcount_set(&irq->refcount, 0); - if (vgic_irq_is_sgi(i)) { - /* SGIs */ - irq->enabled = 1; - irq->config = VGIC_CONFIG_EDGE; - } else { - /* PPIs */ - irq->config = VGIC_CONFIG_LEVEL; - } - - switch (type) { - case KVM_DEV_TYPE_ARM_VGIC_V3: - irq->group = 1; - irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); - break; - case KVM_DEV_TYPE_ARM_VGIC_V2: - irq->group = 0; - irq->targets = BIT(vcpu->vcpu_id); - break; - } + for (i = 0; i < num_private_irqs; i++) { + if (vgic_is_v5(vcpu->kvm)) + vgic_v5_allocate_private_irq(vcpu, i, type); + else + vgic_allocate_private_irq(vcpu, i, type); } return 0; @@ -366,7 +407,11 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) static void kvm_vgic_vcpu_reset(struct kvm_vcpu *vcpu) { - if (kvm_vgic_global_state.type == VGIC_V2) + const struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V5) + vgic_v5_reset(vcpu); + else if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_reset(vcpu); else vgic_v3_reset(vcpu); @@ -397,22 +442,28 @@ int vgic_init(struct kvm *kvm) if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) return -EBUSY; - /* freeze the number of spis */ - if (!dist->nr_spis) - dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS; + if (!vgic_is_v5(kvm)) { + /* freeze the number of spis */ + if (!dist->nr_spis) + dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS; - ret = kvm_vgic_dist_init(kvm, dist->nr_spis); - if (ret) - goto out; + ret = kvm_vgic_dist_init(kvm, dist->nr_spis); + if (ret) + return ret; - /* - * Ensure vPEs are allocated if direct IRQ injection (e.g. vSGIs, - * vLPIs) is supported. - */ - if (vgic_supports_direct_irqs(kvm)) { - ret = vgic_v4_init(kvm); + /* + * Ensure vPEs are allocated if direct IRQ injection (e.g. vSGIs, + * vLPIs) is supported. + */ + if (vgic_supports_direct_irqs(kvm)) { + ret = vgic_v4_init(kvm); + if (ret) + return ret; + } + } else { + ret = vgic_v5_init(kvm); if (ret) - goto out; + return ret; } kvm_for_each_vcpu(idx, vcpu, kvm) @@ -420,12 +471,12 @@ int vgic_init(struct kvm *kvm) ret = kvm_vgic_setup_default_irq_routing(kvm); if (ret) - goto out; + return ret; vgic_debug_init(kvm); dist->initialized = true; -out: - return ret; + + return 0; } static void kvm_vgic_dist_destroy(struct kvm *kvm) @@ -569,6 +620,7 @@ int vgic_lazy_init(struct kvm *kvm) int kvm_vgic_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + bool needs_dist = true; enum vgic_type type; gpa_t dist_base; int ret = 0; @@ -587,12 +639,16 @@ int kvm_vgic_map_resources(struct kvm *kvm) if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) { ret = vgic_v2_map_resources(kvm); type = VGIC_V2; - } else { + } else if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { ret = vgic_v3_map_resources(kvm); type = VGIC_V3; + } else { + ret = vgic_v5_map_resources(kvm); + type = VGIC_V5; + needs_dist = false; } - if (ret) + if (ret || !needs_dist) goto out; dist_base = dist->vgic_dist_base; @@ -617,6 +673,36 @@ out_slots: return ret; } +void kvm_vgic_finalize_idregs(struct kvm *kvm) +{ + u32 type = kvm->arch.vgic.vgic_model; + u64 aa64pfr0, aa64pfr2, pfr1; + + aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; + aa64pfr2 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR2_EL1) & ~ID_AA64PFR2_EL1_GCIE; + pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC; + + switch (type) { + case KVM_DEV_TYPE_ARM_VGIC_V2: + kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + break; + case KVM_DEV_TYPE_ARM_VGIC_V3: + INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); + aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP); + pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3); + break; + case KVM_DEV_TYPE_ARM_VGIC_V5: + aa64pfr2 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR2_EL1, GCIE, IMP); + break; + default: + WARN_ONCE(1, "Unknown VGIC type!!!\n"); + } + + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0); + kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR2_EL1, aa64pfr2); + kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1); +} + /* GENERIC PROBE */ void kvm_vgic_cpu_up(void) diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 3d1a776b716d..a96c77dccf35 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -336,6 +336,10 @@ int kvm_register_vgic_device(unsigned long type) break; ret = kvm_vgic_register_its_device(); break; + case KVM_DEV_TYPE_ARM_VGIC_V5: + ret = kvm_register_device_ops(&kvm_arm_vgic_v5_ops, + KVM_DEV_TYPE_ARM_VGIC_V5); + break; } return ret; @@ -639,7 +643,7 @@ static int vgic_v3_set_attr(struct kvm_device *dev, if (vgic_initialized(dev->kvm)) return -EBUSY; - if (!irq_is_ppi(val)) + if (!irq_is_ppi(dev->kvm, val)) return -EINVAL; dev->kvm->arch.vgic.mi_intid = val; @@ -715,3 +719,104 @@ struct kvm_device_ops kvm_arm_vgic_v3_ops = { .get_attr = vgic_v3_get_attr, .has_attr = vgic_v3_has_attr, }; + +static int vgic_v5_get_userspace_ppis(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + struct vgic_v5_vm *gicv5_vm = &dev->kvm->arch.vgic.gicv5_vm; + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + int ret; + + guard(mutex)(&dev->kvm->arch.config_lock); + + /* + * We either support 64 or 128 PPIs. In the former case, we need to + * return 0s for the second 64 bits as we have no storage backing those. + */ + ret = put_user(bitmap_read(gicv5_vm->userspace_ppis, 0, 64), uaddr); + if (ret) + return ret; + uaddr++; + + if (VGIC_V5_NR_PRIVATE_IRQS == 128) + ret = put_user(bitmap_read(gicv5_vm->userspace_ppis, 64, 128), uaddr); + else + ret = put_user(0, uaddr); + + return ret; +} + +static int vgic_v5_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + return -ENXIO; + case KVM_DEV_ARM_VGIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + return vgic_set_common_attr(dev, attr); + case KVM_DEV_ARM_VGIC_USERSPACE_PPIS: + default: + return -ENXIO; + } + default: + return -ENXIO; + } + +} + +static int vgic_v5_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + return -ENXIO; + case KVM_DEV_ARM_VGIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + return vgic_get_common_attr(dev, attr); + case KVM_DEV_ARM_VGIC_USERSPACE_PPIS: + return vgic_v5_get_userspace_ppis(dev, attr); + default: + return -ENXIO; + } + default: + return -ENXIO; + } +} + +static int vgic_v5_has_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + return -ENXIO; + case KVM_DEV_ARM_VGIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + return 0; + case KVM_DEV_ARM_VGIC_USERSPACE_PPIS: + return 0; + default: + return -ENXIO; + } + default: + return -ENXIO; + } +} + +struct kvm_device_ops kvm_arm_vgic_v5_ops = { + .name = "kvm-arm-vgic-v5", + .create = vgic_create, + .destroy = vgic_destroy, + .set_attr = vgic_v5_set_attr, + .get_attr = vgic_v5_get_attr, + .has_attr = vgic_v5_has_attr, +}; diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index a573b1f0c6cb..74d76dec9730 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -842,18 +842,46 @@ vgic_find_mmio_region(const struct vgic_register_region *regions, void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_set_vmcr(vcpu, vmcr); - else + const struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + switch (dist->vgic_model) { + case KVM_DEV_TYPE_ARM_VGIC_V5: + vgic_v5_set_vmcr(vcpu, vmcr); + break; + case KVM_DEV_TYPE_ARM_VGIC_V3: vgic_v3_set_vmcr(vcpu, vmcr); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + vgic_v3_set_vmcr(vcpu, vmcr); + else + vgic_v2_set_vmcr(vcpu, vmcr); + break; + default: + BUG(); + } } void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_get_vmcr(vcpu, vmcr); - else + const struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + switch (dist->vgic_model) { + case KVM_DEV_TYPE_ARM_VGIC_V5: + vgic_v5_get_vmcr(vcpu, vmcr); + break; + case KVM_DEV_TYPE_ARM_VGIC_V3: vgic_v3_get_vmcr(vcpu, vmcr); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + vgic_v3_get_vmcr(vcpu, vmcr); + else + vgic_v2_get_vmcr(vcpu, vmcr); + break; + default: + BUG(); + } } /* diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 6a355eca1934..9e841e7afd4a 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -499,7 +499,7 @@ void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; - if (!vgic_is_v3(vcpu->kvm)) + if (!vgic_host_has_gicv3()) return; /* Hide GICv3 sysreg if necessary */ diff --git a/arch/arm64/kvm/vgic/vgic-v5.c b/arch/arm64/kvm/vgic/vgic-v5.c index 331651087e2c..2b6cd5c3f9c2 100644 --- a/arch/arm64/kvm/vgic/vgic-v5.c +++ b/arch/arm64/kvm/vgic/vgic-v5.c @@ -1,28 +1,52 @@ // SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025, 2026 Arm Ltd. + */ #include <kvm/arm_vgic.h> + +#include <linux/bitops.h> #include <linux/irqchip/arm-vgic-info.h> #include "vgic.h" +static struct vgic_v5_ppi_caps ppi_caps; + +/* + * Not all PPIs are guaranteed to be implemented for GICv5. Deterermine which + * ones are, and generate a mask. + */ +static void vgic_v5_get_implemented_ppis(void) +{ + if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) + return; + + /* + * If we have KVM, we have EL2, which means that we have support for the + * EL1 and EL2 Physical & Virtual timers. + */ + __assign_bit(GICV5_ARCH_PPI_CNTHP, ppi_caps.impl_ppi_mask, 1); + __assign_bit(GICV5_ARCH_PPI_CNTV, ppi_caps.impl_ppi_mask, 1); + __assign_bit(GICV5_ARCH_PPI_CNTHV, ppi_caps.impl_ppi_mask, 1); + __assign_bit(GICV5_ARCH_PPI_CNTP, ppi_caps.impl_ppi_mask, 1); + + /* The SW_PPI should be available */ + __assign_bit(GICV5_ARCH_PPI_SW_PPI, ppi_caps.impl_ppi_mask, 1); + + /* The PMUIRQ is available if we have the PMU */ + __assign_bit(GICV5_ARCH_PPI_PMUIRQ, ppi_caps.impl_ppi_mask, system_supports_pmuv3()); +} + /* * Probe for a vGICv5 compatible interrupt controller, returning 0 on success. - * Currently only supports GICv3-based VMs on a GICv5 host, and hence only - * registers a VGIC_V3 device. */ int vgic_v5_probe(const struct gic_kvm_info *info) { + bool v5_registered = false; u64 ich_vtr_el2; int ret; - if (!cpus_have_final_cap(ARM64_HAS_GICV5_LEGACY)) - return -ENODEV; - kvm_vgic_global_state.type = VGIC_V5; - kvm_vgic_global_state.has_gcie_v3_compat = true; - - /* We only support v3 compat mode - use vGICv3 limits */ - kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS; kvm_vgic_global_state.vcpu_base = 0; kvm_vgic_global_state.vctrl_base = NULL; @@ -30,6 +54,38 @@ int vgic_v5_probe(const struct gic_kvm_info *info) kvm_vgic_global_state.has_gicv4 = false; kvm_vgic_global_state.has_gicv4_1 = false; + /* + * GICv5 is currently not supported in Protected mode. Skip the + * registration of GICv5 completely to make sure no guests can create a + * GICv5-based guest. + */ + if (is_protected_kvm_enabled()) { + kvm_info("GICv5-based guests are not supported with pKVM\n"); + goto skip_v5; + } + + kvm_vgic_global_state.max_gic_vcpus = VGIC_V5_MAX_CPUS; + + vgic_v5_get_implemented_ppis(); + + ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V5); + if (ret) { + kvm_err("Cannot register GICv5 KVM device.\n"); + goto skip_v5; + } + + v5_registered = true; + kvm_info("GCIE system register CPU interface\n"); + +skip_v5: + /* If we don't support the GICv3 compat mode we're done. */ + if (!cpus_have_final_cap(ARM64_HAS_GICV5_LEGACY)) { + if (!v5_registered) + return -ENODEV; + return 0; + } + + kvm_vgic_global_state.has_gcie_v3_compat = true; ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config); kvm_vgic_global_state.ich_vtr_el2 = (u32)ich_vtr_el2; @@ -45,6 +101,10 @@ int vgic_v5_probe(const struct gic_kvm_info *info) return ret; } + /* We potentially limit the max VCPUs further than we need to here */ + kvm_vgic_global_state.max_gic_vcpus = min(VGIC_V3_MAX_CPUS, + VGIC_V5_MAX_CPUS); + static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif); kvm_info("GCIE legacy system register CPU interface\n"); @@ -52,3 +112,428 @@ int vgic_v5_probe(const struct gic_kvm_info *info) return 0; } + +void vgic_v5_reset(struct kvm_vcpu *vcpu) +{ + /* + * We always present 16-bits of ID space to the guest, irrespective of + * the host allowing more. + */ + vcpu->arch.vgic_cpu.num_id_bits = ICC_IDR0_EL1_ID_BITS_16BITS; + + /* + * The GICv5 architeture only supports 5-bits of priority in the + * CPUIF (but potentially fewer in the IRS). + */ + vcpu->arch.vgic_cpu.num_pri_bits = 5; +} + +int vgic_v5_init(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long idx; + + if (vgic_initialized(kvm)) + return 0; + + kvm_for_each_vcpu(idx, vcpu, kvm) { + if (vcpu_has_nv(vcpu)) { + kvm_err("Nested GICv5 VMs are currently unsupported\n"); + return -EINVAL; + } + } + + /* We only allow userspace to drive the SW_PPI, if it is implemented. */ + bitmap_zero(kvm->arch.vgic.gicv5_vm.userspace_ppis, + VGIC_V5_NR_PRIVATE_IRQS); + __assign_bit(GICV5_ARCH_PPI_SW_PPI, + kvm->arch.vgic.gicv5_vm.userspace_ppis, + VGIC_V5_NR_PRIVATE_IRQS); + bitmap_and(kvm->arch.vgic.gicv5_vm.userspace_ppis, + kvm->arch.vgic.gicv5_vm.userspace_ppis, + ppi_caps.impl_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS); + + return 0; +} + +int vgic_v5_map_resources(struct kvm *kvm) +{ + if (!vgic_initialized(kvm)) + return -EBUSY; + + return 0; +} + +int vgic_v5_finalize_ppi_state(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu0; + int i; + + if (!vgic_is_v5(kvm)) + return 0; + + /* The PPI state for all VCPUs should be the same. Pick the first. */ + vcpu0 = kvm_get_vcpu(kvm, 0); + + bitmap_zero(kvm->arch.vgic.gicv5_vm.vgic_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS); + bitmap_zero(kvm->arch.vgic.gicv5_vm.vgic_ppi_hmr, VGIC_V5_NR_PRIVATE_IRQS); + + for_each_set_bit(i, ppi_caps.impl_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS) { + const u32 intid = vgic_v5_make_ppi(i); + struct vgic_irq *irq; + + irq = vgic_get_vcpu_irq(vcpu0, intid); + + /* Expose PPIs with an owner or the SW_PPI, only */ + scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) { + if (irq->owner || i == GICV5_ARCH_PPI_SW_PPI) { + __assign_bit(i, kvm->arch.vgic.gicv5_vm.vgic_ppi_mask, 1); + __assign_bit(i, kvm->arch.vgic.gicv5_vm.vgic_ppi_hmr, + irq->config == VGIC_CONFIG_LEVEL); + } + } + + vgic_put_irq(vcpu0->kvm, irq); + } + + return 0; +} + +static u32 vgic_v5_get_effective_priority_mask(struct kvm_vcpu *vcpu) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + u32 highest_ap, priority_mask; + + /* + * If the guest's CPU has not opted to receive interrupts, then the + * effective running priority is the highest priority. Just return 0 + * (the highest priority). + */ + if (!FIELD_GET(FEAT_GCIE_ICH_VMCR_EL2_EN, cpu_if->vgic_vmcr)) + return 0; + + /* + * Counting the number of trailing zeros gives the current active + * priority. Explicitly use the 32-bit version here as we have 32 + * priorities. 32 then means that there are no active priorities. + */ + highest_ap = cpu_if->vgic_apr ? __builtin_ctz(cpu_if->vgic_apr) : 32; + + /* + * An interrupt is of sufficient priority if it is equal to or + * greater than the priority mask. Add 1 to the priority mask + * (i.e., lower priority) to match the APR logic before taking + * the min. This gives us the lowest priority that is masked. + */ + priority_mask = FIELD_GET(FEAT_GCIE_ICH_VMCR_EL2_VPMR, cpu_if->vgic_vmcr); + + return min(highest_ap, priority_mask + 1); +} + +/* + * For GICv5, the PPIs are mostly directly managed by the hardware. We (the + * hypervisor) handle the pending, active, enable state save/restore, but don't + * need the PPIs to be queued on a per-VCPU AP list. Therefore, sanity check the + * state, unlock, and return. + */ +bool vgic_v5_ppi_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, + unsigned long flags) + __releases(&irq->irq_lock) +{ + struct kvm_vcpu *vcpu; + + lockdep_assert_held(&irq->irq_lock); + + if (WARN_ON_ONCE(!__irq_is_ppi(KVM_DEV_TYPE_ARM_VGIC_V5, irq->intid))) + goto out_unlock_fail; + + vcpu = irq->target_vcpu; + if (WARN_ON_ONCE(!vcpu)) + goto out_unlock_fail; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + /* Directly kick the target VCPU to make sure it sees the IRQ */ + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); + kvm_vcpu_kick(vcpu); + + return true; + +out_unlock_fail: + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + return false; +} + +/* + * Sets/clears the corresponding bit in the ICH_PPI_DVIR register. + */ +void vgic_v5_set_ppi_dvi(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool dvi) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + u32 ppi; + + lockdep_assert_held(&irq->irq_lock); + + ppi = vgic_v5_get_hwirq_id(irq->intid); + __assign_bit(ppi, cpu_if->vgic_ppi_dvir, dvi); +} + +static struct irq_ops vgic_v5_ppi_irq_ops = { + .queue_irq_unlock = vgic_v5_ppi_queue_irq_unlock, + .set_direct_injection = vgic_v5_set_ppi_dvi, +}; + +void vgic_v5_set_ppi_ops(struct kvm_vcpu *vcpu, u32 vintid) +{ + kvm_vgic_set_irq_ops(vcpu, vintid, &vgic_v5_ppi_irq_ops); +} + +/* + * Sync back the PPI priorities to the vgic_irq shadow state for any interrupts + * exposed to the guest (skipping all others). + */ +static void vgic_v5_sync_ppi_priorities(struct kvm_vcpu *vcpu) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + u64 priorityr; + int i; + + /* + * We have up to 16 PPI Priority regs, but only have a few interrupts + * that the guest is allowed to use. Limit our sync of PPI priorities to + * those actually exposed to the guest by first iterating over the mask + * of exposed PPIs. + */ + for_each_set_bit(i, vcpu->kvm->arch.vgic.gicv5_vm.vgic_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS) { + u32 intid = vgic_v5_make_ppi(i); + struct vgic_irq *irq; + int pri_idx, pri_reg, pri_bit; + u8 priority; + + /* + * Determine which priority register and the field within it to + * extract. + */ + pri_reg = i / 8; + pri_idx = i % 8; + pri_bit = pri_idx * 8; + + priorityr = cpu_if->vgic_ppi_priorityr[pri_reg]; + priority = field_get(GENMASK(pri_bit + 4, pri_bit), priorityr); + + irq = vgic_get_vcpu_irq(vcpu, intid); + + scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) + irq->priority = priority; + + vgic_put_irq(vcpu->kvm, irq); + } +} + +bool vgic_v5_has_pending_ppi(struct kvm_vcpu *vcpu) +{ + unsigned int priority_mask; + int i; + + priority_mask = vgic_v5_get_effective_priority_mask(vcpu); + + /* + * If the combined priority mask is 0, nothing can be signalled! In the + * case where the guest has disabled interrupt delivery for the vcpu + * (via ICV_CR0_EL1.EN->ICH_VMCR_EL2.EN), we calculate the priority mask + * as 0 too (the highest possible priority). + */ + if (!priority_mask) + return false; + + for_each_set_bit(i, vcpu->kvm->arch.vgic.gicv5_vm.vgic_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS) { + u32 intid = vgic_v5_make_ppi(i); + bool has_pending = false; + struct vgic_irq *irq; + + irq = vgic_get_vcpu_irq(vcpu, intid); + + scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) + has_pending = (irq->enabled && irq_is_pending(irq) && + irq->priority <= priority_mask); + + vgic_put_irq(vcpu->kvm, irq); + + if (has_pending) + return true; + } + + return false; +} + +/* + * Detect any PPIs state changes, and propagate the state with KVM's + * shadow structures. + */ +void vgic_v5_fold_ppi_state(struct kvm_vcpu *vcpu) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + DECLARE_BITMAP(changed_active, VGIC_V5_NR_PRIVATE_IRQS); + DECLARE_BITMAP(changed_pending, VGIC_V5_NR_PRIVATE_IRQS); + DECLARE_BITMAP(changed_bits, VGIC_V5_NR_PRIVATE_IRQS); + unsigned long *activer, *pendr_entry, *pendr; + int i; + + activer = host_data_ptr(vgic_v5_ppi_state)->activer_exit; + pendr_entry = host_data_ptr(vgic_v5_ppi_state)->pendr_entry; + pendr = host_data_ptr(vgic_v5_ppi_state)->pendr_exit; + + bitmap_xor(changed_active, cpu_if->vgic_ppi_activer, activer, + VGIC_V5_NR_PRIVATE_IRQS); + bitmap_xor(changed_pending, pendr_entry, pendr, + VGIC_V5_NR_PRIVATE_IRQS); + bitmap_or(changed_bits, changed_active, changed_pending, + VGIC_V5_NR_PRIVATE_IRQS); + + for_each_set_bit(i, changed_bits, VGIC_V5_NR_PRIVATE_IRQS) { + u32 intid = vgic_v5_make_ppi(i); + struct vgic_irq *irq; + + irq = vgic_get_vcpu_irq(vcpu, intid); + + scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) { + irq->active = test_bit(i, activer); + + /* This is an OR to avoid losing incoming edges! */ + if (irq->config == VGIC_CONFIG_EDGE) + irq->pending_latch |= test_bit(i, pendr); + } + + vgic_put_irq(vcpu->kvm, irq); + } + + /* + * Re-inject the exit state as entry state next time! + * + * Note that the write of the Enable state is trapped, and hence there + * is nothing to explcitly sync back here as we already have the latest + * copy by definition. + */ + bitmap_copy(cpu_if->vgic_ppi_activer, activer, VGIC_V5_NR_PRIVATE_IRQS); +} + +void vgic_v5_flush_ppi_state(struct kvm_vcpu *vcpu) +{ + DECLARE_BITMAP(pendr, VGIC_V5_NR_PRIVATE_IRQS); + int i; + + /* + * Time to enter the guest - we first need to build the guest's + * ICC_PPI_PENDRx_EL1, however. + */ + bitmap_zero(pendr, VGIC_V5_NR_PRIVATE_IRQS); + for_each_set_bit(i, vcpu->kvm->arch.vgic.gicv5_vm.vgic_ppi_mask, + VGIC_V5_NR_PRIVATE_IRQS) { + u32 intid = vgic_v5_make_ppi(i); + struct vgic_irq *irq; + + irq = vgic_get_vcpu_irq(vcpu, intid); + + scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) + __assign_bit(i, pendr, irq_is_pending(irq)); + + vgic_put_irq(vcpu->kvm, irq); + } + + /* + * Copy the shadow state to the pending reg that will be written to the + * ICH_PPI_PENDRx_EL2 regs. While the guest is running we track any + * incoming changes to the pending state in the vgic_irq structures. The + * incoming changes are merged with the outgoing changes on the return + * path. + */ + bitmap_copy(host_data_ptr(vgic_v5_ppi_state)->pendr_entry, pendr, + VGIC_V5_NR_PRIVATE_IRQS); + + /* + * Make sure that we can correctly detect "edges" in the PPI + * state. There's a path where we never actually enter the guest, and + * failure to do this risks losing pending state + */ + bitmap_copy(host_data_ptr(vgic_v5_ppi_state)->pendr_exit, pendr, + VGIC_V5_NR_PRIVATE_IRQS); +} + +void vgic_v5_load(struct kvm_vcpu *vcpu) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + + /* + * On the WFI path, vgic_load is called a second time. The first is when + * scheduling in the vcpu thread again, and the second is when leaving + * WFI. Skip the second instance as it serves no purpose and just + * restores the same state again. + */ + if (cpu_if->gicv5_vpe.resident) + return; + + kvm_call_hyp(__vgic_v5_restore_vmcr_apr, cpu_if); + + cpu_if->gicv5_vpe.resident = true; +} + +void vgic_v5_put(struct kvm_vcpu *vcpu) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + + /* + * Do nothing if we're not resident. This can happen in the WFI path + * where we do a vgic_put in the WFI path and again later when + * descheduling the thread. We risk losing VMCR state if we sync it + * twice, so instead return early in this case. + */ + if (!cpu_if->gicv5_vpe.resident) + return; + + kvm_call_hyp(__vgic_v5_save_apr, cpu_if); + + cpu_if->gicv5_vpe.resident = false; + + /* The shadow priority is only updated on entering WFI */ + if (vcpu_get_flag(vcpu, IN_WFI)) + vgic_v5_sync_ppi_priorities(vcpu); +} + +void vgic_v5_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + u64 vmcr = cpu_if->vgic_vmcr; + + vmcrp->en = FIELD_GET(FEAT_GCIE_ICH_VMCR_EL2_EN, vmcr); + vmcrp->pmr = FIELD_GET(FEAT_GCIE_ICH_VMCR_EL2_VPMR, vmcr); +} + +void vgic_v5_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + u64 vmcr; + + vmcr = FIELD_PREP(FEAT_GCIE_ICH_VMCR_EL2_VPMR, vmcrp->pmr) | + FIELD_PREP(FEAT_GCIE_ICH_VMCR_EL2_EN, vmcrp->en); + + cpu_if->vgic_vmcr = vmcr; +} + +void vgic_v5_restore_state(struct kvm_vcpu *vcpu) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + + __vgic_v5_restore_state(cpu_if); + __vgic_v5_restore_ppi_state(cpu_if); + dsb(sy); +} + +void vgic_v5_save_state(struct kvm_vcpu *vcpu) +{ + struct vgic_v5_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v5; + + __vgic_v5_save_state(cpu_if); + __vgic_v5_save_ppi_state(cpu_if); + dsb(sy); +} diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index e22b79cfff96..1e9fe8764584 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -86,6 +86,10 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) */ struct vgic_irq *vgic_get_irq(struct kvm *kvm, u32 intid) { + /* Non-private IRQs are not yet implemented for GICv5 */ + if (vgic_is_v5(kvm)) + return NULL; + /* SPIs */ if (intid >= VGIC_NR_PRIVATE_IRQS && intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) { @@ -94,7 +98,7 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, u32 intid) } /* LPIs */ - if (intid >= VGIC_MIN_LPI) + if (irq_is_lpi(kvm, intid)) return vgic_get_lpi(kvm, intid); return NULL; @@ -105,6 +109,18 @@ struct vgic_irq *vgic_get_vcpu_irq(struct kvm_vcpu *vcpu, u32 intid) if (WARN_ON(!vcpu)) return NULL; + if (vgic_is_v5(vcpu->kvm)) { + u32 int_num, hwirq_id; + + if (!__irq_is_ppi(KVM_DEV_TYPE_ARM_VGIC_V5, intid)) + return NULL; + + hwirq_id = FIELD_GET(GICV5_HWIRQ_ID, intid); + int_num = array_index_nospec(hwirq_id, VGIC_V5_NR_PRIVATE_IRQS); + + return &vcpu->arch.vgic_cpu.private_irqs[int_num]; + } + /* SGIs and PPIs */ if (intid < VGIC_NR_PRIVATE_IRQS) { intid = array_index_nospec(intid, VGIC_NR_PRIVATE_IRQS); @@ -123,7 +139,7 @@ static void vgic_release_lpi_locked(struct vgic_dist *dist, struct vgic_irq *irq static __must_check bool __vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { - if (irq->intid < VGIC_MIN_LPI) + if (!irq_is_lpi(kvm, irq->intid)) return false; return refcount_dec_and_test(&irq->refcount); @@ -148,7 +164,7 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) * Acquire/release it early on lockdep kernels to make locking issues * in rare release paths a bit more obvious. */ - if (IS_ENABLED(CONFIG_LOCKDEP) && irq->intid >= VGIC_MIN_LPI) { + if (IS_ENABLED(CONFIG_LOCKDEP) && irq_is_lpi(kvm, irq->intid)) { guard(spinlock_irqsave)(&dist->lpi_xa.xa_lock); } @@ -186,7 +202,7 @@ void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { - if (irq->intid >= VGIC_MIN_LPI) { + if (irq_is_lpi(vcpu->kvm, irq->intid)) { raw_spin_lock(&irq->irq_lock); list_del(&irq->ap_list); irq->vcpu = NULL; @@ -404,6 +420,9 @@ bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, lockdep_assert_held(&irq->irq_lock); + if (irq->ops && irq->ops->queue_irq_unlock) + return irq->ops->queue_irq_unlock(kvm, irq, flags); + retry: vcpu = vgic_target_oracle(irq); if (irq->vcpu || !vcpu) { @@ -521,12 +540,12 @@ int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, if (ret) return ret; - if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS) + if (!vcpu && irq_is_private(kvm, intid)) return -EINVAL; trace_vgic_update_irq_pending(vcpu ? vcpu->vcpu_idx : 0, intid, level); - if (intid < VGIC_NR_PRIVATE_IRQS) + if (irq_is_private(kvm, intid)) irq = vgic_get_vcpu_irq(vcpu, intid); else irq = vgic_get_irq(kvm, intid); @@ -553,10 +572,27 @@ int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, return 0; } +void kvm_vgic_set_irq_ops(struct kvm_vcpu *vcpu, u32 vintid, + struct irq_ops *ops) +{ + struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid); + + BUG_ON(!irq); + + scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) + irq->ops = ops; + + vgic_put_irq(vcpu->kvm, irq); +} + +void kvm_vgic_clear_irq_ops(struct kvm_vcpu *vcpu, u32 vintid) +{ + kvm_vgic_set_irq_ops(vcpu, vintid, NULL); +} + /* @irq->irq_lock must be held */ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - unsigned int host_irq, - struct irq_ops *ops) + unsigned int host_irq) { struct irq_desc *desc; struct irq_data *data; @@ -576,20 +612,25 @@ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, irq->hw = true; irq->host_irq = host_irq; irq->hwintid = data->hwirq; - irq->ops = ops; + + if (irq->ops && irq->ops->set_direct_injection) + irq->ops->set_direct_injection(vcpu, irq, true); + return 0; } /* @irq->irq_lock must be held */ static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq) { + if (irq->ops && irq->ops->set_direct_injection) + irq->ops->set_direct_injection(irq->target_vcpu, irq, false); + irq->hw = false; irq->hwintid = 0; - irq->ops = NULL; } int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, - u32 vintid, struct irq_ops *ops) + u32 vintid) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid); unsigned long flags; @@ -598,7 +639,7 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, BUG_ON(!irq); raw_spin_lock_irqsave(&irq->irq_lock, flags); - ret = kvm_vgic_map_irq(vcpu, irq, host_irq, ops); + ret = kvm_vgic_map_irq(vcpu, irq, host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); @@ -685,7 +726,7 @@ int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner) return -EAGAIN; /* SGIs and LPIs cannot be wired up to any device */ - if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid)) + if (!irq_is_ppi(vcpu->kvm, intid) && !vgic_valid_spi(vcpu->kvm, intid)) return -EINVAL; irq = vgic_get_vcpu_irq(vcpu, intid); @@ -812,8 +853,13 @@ retry: vgic_release_deleted_lpis(vcpu->kvm); } -static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) +static void vgic_fold_state(struct kvm_vcpu *vcpu) { + if (vgic_is_v5(vcpu->kvm)) { + vgic_v5_fold_ppi_state(vcpu); + return; + } + if (!*host_data_ptr(last_lr_irq)) return; @@ -1002,7 +1048,10 @@ static inline bool can_access_vgic_from_kernel(void) static inline void vgic_save_state(struct kvm_vcpu *vcpu) { - if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + /* No switch statement here. See comment in vgic_restore_state() */ + if (vgic_is_v5(vcpu->kvm)) + vgic_v5_save_state(vcpu); + else if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) vgic_v2_save_state(vcpu); else __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); @@ -1011,20 +1060,24 @@ static inline void vgic_save_state(struct kvm_vcpu *vcpu) /* Sync back the hardware VGIC state into our emulation after a guest's run. */ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { - /* If nesting, emulate the HW effect from L0 to L1 */ - if (vgic_state_is_nested(vcpu)) { - vgic_v3_sync_nested(vcpu); - return; - } + if (vgic_is_v3(vcpu->kvm)) { + /* 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); + if (vcpu_has_nv(vcpu)) + vgic_v3_nested_update_mi(vcpu); + } if (can_access_vgic_from_kernel()) vgic_save_state(vcpu); - vgic_fold_lr_state(vcpu); - vgic_prune_ap_list(vcpu); + vgic_fold_state(vcpu); + + if (!vgic_is_v5(vcpu->kvm)) + vgic_prune_ap_list(vcpu); } /* Sync interrupts that were deactivated through a DIR trap */ @@ -1040,12 +1093,34 @@ void kvm_vgic_process_async_update(struct kvm_vcpu *vcpu) static inline void vgic_restore_state(struct kvm_vcpu *vcpu) { - if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + /* + * As nice as it would be to restructure this code into a switch + * statement as can be found elsewhere, the logic quickly gets ugly. + * + * __vgic_v3_restore_state() is doing a lot of heavy lifting here. It is + * required for GICv3-on-GICv3, GICv2-on-GICv3, GICv3-on-GICv5, and the + * no-in-kernel-irqchip case on GICv3 hardware. Hence, adding a switch + * here results in much more complex code. + */ + if (vgic_is_v5(vcpu->kvm)) + vgic_v5_restore_state(vcpu); + else if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) vgic_v2_restore_state(vcpu); else __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); } +static void vgic_flush_state(struct kvm_vcpu *vcpu) +{ + if (vgic_is_v5(vcpu->kvm)) { + vgic_v5_flush_ppi_state(vcpu); + return; + } + + scoped_guard(raw_spinlock, &vcpu->arch.vgic_cpu.ap_list_lock) + vgic_flush_lr_state(vcpu); +} + /* Flush our emulation state into the GIC hardware before entering the guest. */ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) { @@ -1082,42 +1157,69 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - scoped_guard(raw_spinlock, &vcpu->arch.vgic_cpu.ap_list_lock) - vgic_flush_lr_state(vcpu); + vgic_flush_state(vcpu); if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); - if (vgic_supports_direct_irqs(vcpu->kvm)) + if (vgic_supports_direct_irqs(vcpu->kvm) && kvm_vgic_global_state.has_gicv4) vgic_v4_commit(vcpu); } void kvm_vgic_load(struct kvm_vcpu *vcpu) { + const struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); return; } - if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) - vgic_v2_load(vcpu); - else + switch (dist->vgic_model) { + case KVM_DEV_TYPE_ARM_VGIC_V5: + vgic_v5_load(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V3: vgic_v3_load(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + vgic_v3_load(vcpu); + else + vgic_v2_load(vcpu); + break; + default: + BUG(); + } } void kvm_vgic_put(struct kvm_vcpu *vcpu) { + const struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); return; } - if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) - vgic_v2_put(vcpu); - else + switch (dist->vgic_model) { + case KVM_DEV_TYPE_ARM_VGIC_V5: + vgic_v5_put(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V3: vgic_v3_put(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + vgic_v3_put(vcpu); + else + vgic_v2_put(vcpu); + break; + default: + BUG(); + } } int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) @@ -1128,6 +1230,9 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) unsigned long flags; struct vgic_vmcr vmcr; + if (vgic_is_v5(vcpu->kvm)) + return vgic_v5_has_pending_ppi(vcpu); + if (!vcpu->kvm->arch.vgic.enabled) return false; diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index c9b3bb07e483..9d941241c8a2 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -187,6 +187,7 @@ static inline u64 vgic_ich_hcr_trap_bits(void) * registers regardless of the hardware backed GIC used. */ struct vgic_vmcr { + u32 en; /* GICv5-specific */ u32 grpen0; u32 grpen1; @@ -363,6 +364,19 @@ void vgic_debug_init(struct kvm *kvm); void vgic_debug_destroy(struct kvm *kvm); int vgic_v5_probe(const struct gic_kvm_info *info); +void vgic_v5_reset(struct kvm_vcpu *vcpu); +int vgic_v5_init(struct kvm *kvm); +int vgic_v5_map_resources(struct kvm *kvm); +void vgic_v5_set_ppi_ops(struct kvm_vcpu *vcpu, u32 vintid); +bool vgic_v5_has_pending_ppi(struct kvm_vcpu *vcpu); +void vgic_v5_flush_ppi_state(struct kvm_vcpu *vcpu); +void vgic_v5_fold_ppi_state(struct kvm_vcpu *vcpu); +void vgic_v5_load(struct kvm_vcpu *vcpu); +void vgic_v5_put(struct kvm_vcpu *vcpu); +void vgic_v5_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +void vgic_v5_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +void vgic_v5_restore_state(struct kvm_vcpu *vcpu); +void vgic_v5_save_state(struct kvm_vcpu *vcpu); static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu) { @@ -425,15 +439,6 @@ void vgic_its_invalidate_all_caches(struct kvm *kvm); int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq); int vgic_its_invall(struct kvm_vcpu *vcpu); -bool system_supports_direct_sgis(void); -bool vgic_supports_direct_msis(struct kvm *kvm); -bool vgic_supports_direct_sgis(struct kvm *kvm); - -static inline bool vgic_supports_direct_irqs(struct kvm *kvm) -{ - return vgic_supports_direct_msis(kvm) || vgic_supports_direct_sgis(kvm); -} - int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); void vgic_v4_configure_vsgis(struct kvm *kvm); @@ -447,6 +452,11 @@ static inline bool kvm_has_gicv3(struct kvm *kvm) return kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP); } +static inline bool kvm_has_gicv5(struct kvm *kvm) +{ + return kvm_has_feat(kvm, ID_AA64PFR2_EL1, GCIE, IMP); +} + void vgic_v3_flush_nested(struct kvm_vcpu *vcpu); void vgic_v3_sync_nested(struct kvm_vcpu *vcpu); void vgic_v3_load_nested(struct kvm_vcpu *vcpu); @@ -454,15 +464,32 @@ 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); -static inline bool vgic_is_v3_compat(struct kvm *kvm) +static inline bool vgic_host_has_gicv3(void) { - return cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF) && + /* + * Either the host is a native GICv3, or it is GICv5 with + * FEAT_GCIE_LEGACY. + */ + return kvm_vgic_global_state.type == VGIC_V3 || kvm_vgic_global_state.has_gcie_v3_compat; } -static inline bool vgic_is_v3(struct kvm *kvm) +static inline bool vgic_host_has_gicv5(void) +{ + return kvm_vgic_global_state.type == VGIC_V5; +} + +bool system_supports_direct_sgis(void); +bool vgic_supports_direct_msis(struct kvm *kvm); +bool vgic_supports_direct_sgis(struct kvm *kvm); + +static inline bool vgic_supports_direct_irqs(struct kvm *kvm) { - return kvm_vgic_global_state.type == VGIC_V3 || vgic_is_v3_compat(kvm); + /* GICv5 always supports direct IRQs */ + if (vgic_is_v5(kvm)) + return true; + + return vgic_supports_direct_msis(kvm) || vgic_supports_direct_sgis(kvm); } int vgic_its_debug_init(struct kvm_device *dev); diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 9d1c21108057..51dcca5b2fa6 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -3243,6 +3243,14 @@ UnsignedEnum 3:0 ID_BITS EndEnum EndSysreg +Sysreg ICC_HPPIR_EL1 3 0 12 10 3 +Res0 63:33 +Field 32 HPPIV +Field 31:29 TYPE +Res0 28:24 +Field 23:0 ID +EndSysreg + Sysreg ICC_ICSR_EL1 3 0 12 10 4 Res0 63:48 Field 47:32 IAFFID @@ -3257,6 +3265,11 @@ Field 1 Enabled Field 0 F EndSysreg +Sysreg ICC_IAFFIDR_EL1 3 0 12 10 5 +Res0 63:16 +Field 15:0 IAFFID +EndSysreg + SysregFields ICC_PPI_ENABLERx_EL1 Field 63 EN63 Field 62 EN62 @@ -3663,6 +3676,42 @@ Res0 14:12 Field 11:0 AFFINITY EndSysreg +Sysreg ICC_APR_EL1 3 1 12 0 0 +Res0 63:32 +Field 31 P31 +Field 30 P30 +Field 29 P29 +Field 28 P28 +Field 27 P27 +Field 26 P26 +Field 25 P25 +Field 24 P24 +Field 23 P23 +Field 22 P22 +Field 21 P21 +Field 20 P20 +Field 19 P19 +Field 18 P18 +Field 17 P17 +Field 16 P16 +Field 15 P15 +Field 14 P14 +Field 13 P13 +Field 12 P12 +Field 11 P11 +Field 10 P10 +Field 9 P9 +Field 8 P8 +Field 7 P7 +Field 6 P6 +Field 5 P5 +Field 4 P4 +Field 3 P3 +Field 2 P2 +Field 1 P1 +Field 0 P0 +EndSysreg + Sysreg ICC_CR0_EL1 3 1 12 0 1 Res0 63:39 Field 38 PID @@ -4687,6 +4736,42 @@ Field 31:16 PhyPARTID29 Field 15:0 PhyPARTID28 EndSysreg +Sysreg ICH_APR_EL2 3 4 12 8 4 +Res0 63:32 +Field 31 P31 +Field 30 P30 +Field 29 P29 +Field 28 P28 +Field 27 P27 +Field 26 P26 +Field 25 P25 +Field 24 P24 +Field 23 P23 +Field 22 P22 +Field 21 P21 +Field 20 P20 +Field 19 P19 +Field 18 P18 +Field 17 P17 +Field 16 P16 +Field 15 P15 +Field 14 P14 +Field 13 P13 +Field 12 P12 +Field 11 P11 +Field 10 P10 +Field 9 P9 +Field 8 P8 +Field 7 P7 +Field 6 P6 +Field 5 P5 +Field 4 P4 +Field 3 P3 +Field 2 P2 +Field 1 P1 +Field 0 P0 +EndSysreg + Sysreg ICH_HFGRTR_EL2 3 4 12 9 4 Res0 63:21 Field 20 ICC_PPI_ACTIVERn_EL1 @@ -4735,6 +4820,306 @@ Field 1 GICCDDIS Field 0 GICCDEN EndSysreg +SysregFields ICH_PPI_DVIRx_EL2 +Field 63 DVI63 +Field 62 DVI62 +Field 61 DVI61 +Field 60 DVI60 +Field 59 DVI59 +Field 58 DVI58 +Field 57 DVI57 +Field 56 DVI56 +Field 55 DVI55 +Field 54 DVI54 +Field 53 DVI53 +Field 52 DVI52 +Field 51 DVI51 +Field 50 DVI50 +Field 49 DVI49 +Field 48 DVI48 +Field 47 DVI47 +Field 46 DVI46 +Field 45 DVI45 +Field 44 DVI44 +Field 43 DVI43 +Field 42 DVI42 +Field 41 DVI41 +Field 40 DVI40 +Field 39 DVI39 +Field 38 DVI38 +Field 37 DVI37 +Field 36 DVI36 +Field 35 DVI35 +Field 34 DVI34 +Field 33 DVI33 +Field 32 DVI32 +Field 31 DVI31 +Field 30 DVI30 +Field 29 DVI29 +Field 28 DVI28 +Field 27 DVI27 +Field 26 DVI26 +Field 25 DVI25 +Field 24 DVI24 +Field 23 DVI23 +Field 22 DVI22 +Field 21 DVI21 +Field 20 DVI20 +Field 19 DVI19 +Field 18 DVI18 +Field 17 DVI17 +Field 16 DVI16 +Field 15 DVI15 +Field 14 DVI14 +Field 13 DVI13 +Field 12 DVI12 +Field 11 DVI11 +Field 10 DVI10 +Field 9 DVI9 +Field 8 DVI8 +Field 7 DVI7 +Field 6 DVI6 +Field 5 DVI5 +Field 4 DVI4 +Field 3 DVI3 +Field 2 DVI2 +Field 1 DVI1 +Field 0 DVI0 +EndSysregFields + +Sysreg ICH_PPI_DVIR0_EL2 3 4 12 10 0 +Fields ICH_PPI_DVIx_EL2 +EndSysreg + +Sysreg ICH_PPI_DVIR1_EL2 3 4 12 10 1 +Fields ICH_PPI_DVIx_EL2 +EndSysreg + +SysregFields ICH_PPI_ENABLERx_EL2 +Field 63 EN63 +Field 62 EN62 +Field 61 EN61 +Field 60 EN60 +Field 59 EN59 +Field 58 EN58 +Field 57 EN57 +Field 56 EN56 +Field 55 EN55 +Field 54 EN54 +Field 53 EN53 +Field 52 EN52 +Field 51 EN51 +Field 50 EN50 +Field 49 EN49 +Field 48 EN48 +Field 47 EN47 +Field 46 EN46 +Field 45 EN45 +Field 44 EN44 +Field 43 EN43 +Field 42 EN42 +Field 41 EN41 +Field 40 EN40 +Field 39 EN39 +Field 38 EN38 +Field 37 EN37 +Field 36 EN36 +Field 35 EN35 +Field 34 EN34 +Field 33 EN33 +Field 32 EN32 +Field 31 EN31 +Field 30 EN30 +Field 29 EN29 +Field 28 EN28 +Field 27 EN27 +Field 26 EN26 +Field 25 EN25 +Field 24 EN24 +Field 23 EN23 +Field 22 EN22 +Field 21 EN21 +Field 20 EN20 +Field 19 EN19 +Field 18 EN18 +Field 17 EN17 +Field 16 EN16 +Field 15 EN15 +Field 14 EN14 +Field 13 EN13 +Field 12 EN12 +Field 11 EN11 +Field 10 EN10 +Field 9 EN9 +Field 8 EN8 +Field 7 EN7 +Field 6 EN6 +Field 5 EN5 +Field 4 EN4 +Field 3 EN3 +Field 2 EN2 +Field 1 EN1 +Field 0 EN0 +EndSysregFields + +Sysreg ICH_PPI_ENABLER0_EL2 3 4 12 10 2 +Fields ICH_PPI_ENABLERx_EL2 +EndSysreg + +Sysreg ICH_PPI_ENABLER1_EL2 3 4 12 10 3 +Fields ICH_PPI_ENABLERx_EL2 +EndSysreg + +SysregFields ICH_PPI_PENDRx_EL2 +Field 63 PEND63 +Field 62 PEND62 +Field 61 PEND61 +Field 60 PEND60 +Field 59 PEND59 +Field 58 PEND58 +Field 57 PEND57 +Field 56 PEND56 +Field 55 PEND55 +Field 54 PEND54 +Field 53 PEND53 +Field 52 PEND52 +Field 51 PEND51 +Field 50 PEND50 +Field 49 PEND49 +Field 48 PEND48 +Field 47 PEND47 +Field 46 PEND46 +Field 45 PEND45 +Field 44 PEND44 +Field 43 PEND43 +Field 42 PEND42 +Field 41 PEND41 +Field 40 PEND40 +Field 39 PEND39 +Field 38 PEND38 +Field 37 PEND37 +Field 36 PEND36 +Field 35 PEND35 +Field 34 PEND34 +Field 33 PEND33 +Field 32 PEND32 +Field 31 PEND31 +Field 30 PEND30 +Field 29 PEND29 +Field 28 PEND28 +Field 27 PEND27 +Field 26 PEND26 +Field 25 PEND25 +Field 24 PEND24 +Field 23 PEND23 +Field 22 PEND22 +Field 21 PEND21 +Field 20 PEND20 +Field 19 PEND19 +Field 18 PEND18 +Field 17 PEND17 +Field 16 PEND16 +Field 15 PEND15 +Field 14 PEND14 +Field 13 PEND13 +Field 12 PEND12 +Field 11 PEND11 +Field 10 PEND10 +Field 9 PEND9 +Field 8 PEND8 +Field 7 PEND7 +Field 6 PEND6 +Field 5 PEND5 +Field 4 PEND4 +Field 3 PEND3 +Field 2 PEND2 +Field 1 PEND1 +Field 0 PEND0 +EndSysregFields + +Sysreg ICH_PPI_PENDR0_EL2 3 4 12 10 4 +Fields ICH_PPI_PENDRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PENDR1_EL2 3 4 12 10 5 +Fields ICH_PPI_PENDRx_EL2 +EndSysreg + +SysregFields ICH_PPI_ACTIVERx_EL2 +Field 63 ACTIVE63 +Field 62 ACTIVE62 +Field 61 ACTIVE61 +Field 60 ACTIVE60 +Field 59 ACTIVE59 +Field 58 ACTIVE58 +Field 57 ACTIVE57 +Field 56 ACTIVE56 +Field 55 ACTIVE55 +Field 54 ACTIVE54 +Field 53 ACTIVE53 +Field 52 ACTIVE52 +Field 51 ACTIVE51 +Field 50 ACTIVE50 +Field 49 ACTIVE49 +Field 48 ACTIVE48 +Field 47 ACTIVE47 +Field 46 ACTIVE46 +Field 45 ACTIVE45 +Field 44 ACTIVE44 +Field 43 ACTIVE43 +Field 42 ACTIVE42 +Field 41 ACTIVE41 +Field 40 ACTIVE40 +Field 39 ACTIVE39 +Field 38 ACTIVE38 +Field 37 ACTIVE37 +Field 36 ACTIVE36 +Field 35 ACTIVE35 +Field 34 ACTIVE34 +Field 33 ACTIVE33 +Field 32 ACTIVE32 +Field 31 ACTIVE31 +Field 30 ACTIVE30 +Field 29 ACTIVE29 +Field 28 ACTIVE28 +Field 27 ACTIVE27 +Field 26 ACTIVE26 +Field 25 ACTIVE25 +Field 24 ACTIVE24 +Field 23 ACTIVE23 +Field 22 ACTIVE22 +Field 21 ACTIVE21 +Field 20 ACTIVE20 +Field 19 ACTIVE19 +Field 18 ACTIVE18 +Field 17 ACTIVE17 +Field 16 ACTIVE16 +Field 15 ACTIVE15 +Field 14 ACTIVE14 +Field 13 ACTIVE13 +Field 12 ACTIVE12 +Field 11 ACTIVE11 +Field 10 ACTIVE10 +Field 9 ACTIVE9 +Field 8 ACTIVE8 +Field 7 ACTIVE7 +Field 6 ACTIVE6 +Field 5 ACTIVE5 +Field 4 ACTIVE4 +Field 3 ACTIVE3 +Field 2 ACTIVE2 +Field 1 ACTIVE1 +Field 0 ACTIVE0 +EndSysregFields + +Sysreg ICH_PPI_ACTIVER0_EL2 3 4 12 10 6 +Fields ICH_PPI_ACTIVERx_EL2 +EndSysreg + +Sysreg ICH_PPI_ACTIVER1_EL2 3 4 12 10 7 +Fields ICH_PPI_ACTIVERx_EL2 +EndSysreg + Sysreg ICH_HCR_EL2 3 4 12 11 0 Res0 63:32 Field 31:27 EOIcount @@ -4789,6 +5174,18 @@ Field 1 V3 Field 0 En EndSysreg +Sysreg ICH_CONTEXTR_EL2 3 4 12 11 6 +Field 63 V +Field 62 F +Field 61 IRICHPPIDIS +Field 60 DB +Field 59:55 DBPM +Res0 54:48 +Field 47:32 VPE +Res0 31:16 +Field 15:0 VM +EndSysreg + Sysreg ICH_VMCR_EL2 3 4 12 11 7 Prefix FEAT_GCIE Res0 63:32 @@ -4810,6 +5207,89 @@ Field 1 VENG1 Field 0 VENG0 EndSysreg +SysregFields ICH_PPI_PRIORITYRx_EL2 +Res0 63:61 +Field 60:56 Priority7 +Res0 55:53 +Field 52:48 Priority6 +Res0 47:45 +Field 44:40 Priority5 +Res0 39:37 +Field 36:32 Priority4 +Res0 31:29 +Field 28:24 Priority3 +Res0 23:21 +Field 20:16 Priority2 +Res0 15:13 +Field 12:8 Priority1 +Res0 7:5 +Field 4:0 Priority0 +EndSysregFields + +Sysreg ICH_PPI_PRIORITYR0_EL2 3 4 12 14 0 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR1_EL2 3 4 12 14 1 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR2_EL2 3 4 12 14 2 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR3_EL2 3 4 12 14 3 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR4_EL2 3 4 12 14 4 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR5_EL2 3 4 12 14 5 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR6_EL2 3 4 12 14 6 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR7_EL2 3 4 12 14 7 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR8_EL2 3 4 12 15 0 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR9_EL2 3 4 12 15 1 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR10_EL2 3 4 12 15 2 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR11_EL2 3 4 12 15 3 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR12_EL2 3 4 12 15 4 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR13_EL2 3 4 12 15 5 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR14_EL2 3 4 12 15 6 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + +Sysreg ICH_PPI_PRIORITYR15_EL2 3 4 12 15 7 +Fields ICH_PPI_PRIORITYRx_EL2 +EndSysreg + Sysreg CONTEXTIDR_EL2 3 4 13 0 1 Fields CONTEXTIDR_ELx EndSysreg |
