diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 0555f14cc8beea975cea08506a158ad04809784a..c815477b4303ea52f487fd0737fb22cb187b4388 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -10,6 +10,7 @@ #ifndef __ASSEMBLY__ #include +#include #include #include #include @@ -325,15 +326,16 @@ static inline u64 __gic_readq_nonatomic(const volatile void __iomem *addr) #define gits_write_cwriter(v, c) __gic_writeq_nonatomic(v, c) /* - * GITS_VPROPBASER - hi and lo bits may be accessed independently. + * GICR_VPROPBASER - hi and lo bits may be accessed independently. */ -#define gits_write_vpropbaser(v, c) __gic_writeq_nonatomic(v, c) +#define gicr_read_vpropbaser(c) __gic_readq_nonatomic(c) +#define gicr_write_vpropbaser(v, c) __gic_writeq_nonatomic(v, c) /* - * GITS_VPENDBASER - the Valid bit must be cleared before changing + * GICR_VPENDBASER - the Valid bit must be cleared before changing * anything else. */ -static inline void gits_write_vpendbaser(u64 val, void * __iomem addr) +static inline void gicr_write_vpendbaser(u64 val, void __iomem *addr) { u32 tmp; @@ -350,7 +352,7 @@ static inline void gits_write_vpendbaser(u64 val, void * __iomem addr) __gic_writeq_nonatomic(val, addr); } -#define gits_read_vpendbaser(c) __gic_readq_nonatomic(c) +#define gicr_read_vpendbaser(c) __gic_readq_nonatomic(c) static inline bool gic_prio_masking_enabled(void) { diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index c1747fcb86d36921353161500ff2612678d53286..a0f122bffce7fbf24408526ae3c22a6358a1a271 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -112,12 +112,12 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr; } -static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr &= ~HCR_TWE; } -static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr |= HCR_TWE; } diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index d8ac89879327df65c732f916204692d25bfed4e9..c3c3321676c91a186ee27e4fb087f4c37f3a707e 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -39,6 +39,7 @@ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) +#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 8e1444c477695d9e3eacfd323a603c5a1fa4e274..2a267eb1e7a1cb8c3fadc2e91f9157b262091196 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -769,6 +769,19 @@ config HISILICON_ERRATUM_162102203 If unsure, say N. +config HISILICON_ERRATUM_162100602 + bool "Hisilicon erratum 162100602" + depends on ARM_SMMU_V3 + default y + help + On Hisilicon LINXICORE9100 cores, SMMU pagetable prefetch features may + prefetch and use a invalid PTE even the PTE is valid at that time. This + will cause the device trigger fake pagefaults. If the SMMU works in + terminate mode, transactions which occur fake pagefaults will be aborted, + and could result in unexpected errors. + + If unsure, say Y. + config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" default y diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index ee9bdaa40532dd43e59cfd0fb888e551145a9ed8..89f11411c923c48a96f633b7fed4bd62ebc9ac9e 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -140,10 +140,11 @@ static inline u32 gic_read_rpr(void) #define gicr_write_pendbaser(v, c) writeq_relaxed(v, c) #define gicr_read_pendbaser(c) readq_relaxed(c) -#define gits_write_vpropbaser(v, c) writeq_relaxed(v, c) +#define gicr_write_vpropbaser(v, c) writeq_relaxed(v, c) +#define gicr_read_vpropbaser(c) readq_relaxed(c) -#define gits_write_vpendbaser(v, c) writeq_relaxed(v, c) -#define gits_read_vpendbaser(c) readq_relaxed(c) +#define gicr_write_vpendbaser(v, c) writeq_relaxed(v, c) +#define gicr_read_vpendbaser(c) readq_relaxed(c) static inline bool gic_prio_masking_enabled(void) { diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index c400ea284f7ffa48b7b2e6c415a845d00d106f9a..163a38107d3d6b1a2ed6a5d6e334ff03ca51f1d3 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -61,6 +61,9 @@ #define ARM64_HAS_TLB_RANGE 51 #define ARM64_WORKAROUND_AMPERE_AC03_XXXXXX 52 #define ARM64_HAS_ECV 53 +#define ARM64_WORKAROUND_HISILICON_1980005 54 +#define ARM64_WORKAROUND_HISILICON_ERRATUM_162100125 55 +#define ARM64_WORKAROUND_HISILICON_ERRATUM_162100602 56 #define ARM64_NCAPS 80 diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 9b368906191d0cad2bb4879ee8c9b84e8f82a312..3226929c8816e513ae6ebc378da000cd5dcf1415 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -107,6 +107,8 @@ #define FUJITSU_CPU_PART_A64FX 0x001 #define HISI_CPU_PART_TSV110 0xD01 +#define HISI_CPU_PART_TSV200 0xD02 +#define HISI_CPU_PART_LINXICORE9100 0xD02 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -145,6 +147,9 @@ #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX) #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) +#define MIDR_HISI_TSV200 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV200) +#define MIDR_HISI_LINXICORE9100 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_LINXICORE9100) + #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 9be64c0ad31f6a9e72ff715e5d9ed54aa36a7fb3..c847d76ef56975cfe6b23ec8e99d806c970cd46e 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -61,7 +61,6 @@ * RW: 64bit by default, can be overridden for 32bit VMs * TAC: Trap ACTLR * TSC: Trap SMC - * TVM: Trap VM ops (until M+C set in SCTLR_EL1) * TSW: Trap cache operations by set/way * TWE: Trap WFE * TWI: Trap WFI @@ -75,7 +74,7 @@ * PTW: Take a stage2 fault if a stage1 walk steps in device memory */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ - HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ + HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ HCR_FMO | HCR_IMO | HCR_PTW ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 4a4c20a1bf26557ebfdac2af798e2ffd08e6091c..1d4ceb096fa6bd31138a9769ac58551eb9a86abc 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -53,8 +53,18 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) /* trap error record accesses */ vcpu->arch.hcr_el2 |= HCR_TERR; } - if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) + + if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) { vcpu->arch.hcr_el2 |= HCR_FWB; + } else { + /* + * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C + * get set in SCTLR_EL1 such that we can detect when the guest + * MMU gets turned on and do the necessary cache maintenance + * then. + */ + vcpu->arch.hcr_el2 |= HCR_TVM; + } if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) vcpu->arch.hcr_el2 &= ~HCR_RW; @@ -77,14 +87,20 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr_el2; } -static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 &= ~HCR_TWE; + if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count) || + vcpu->kvm->arch.vgic.nassgireq) + vcpu->arch.hcr_el2 &= ~HCR_TWI; + else + vcpu->arch.hcr_el2 |= HCR_TWI; } -static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 |= HCR_TWE; + vcpu->arch.hcr_el2 |= HCR_TWI; } static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index a639c7fee3a8c59f8b1ed7cd3d1254c53a6436b7..01886b83d1206afac90f61bb89b96cc719ecc1f4 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -44,6 +44,7 @@ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) +#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ab8ebfa19ddc5ca9b9a2ca8971094cff4cc58af4..6706d8ad8cd4a8ff2afa8f5e53f31b813b8f7d05 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -56,6 +56,31 @@ is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope) return model == entry->midr_range.model; } +#ifdef CONFIG_HISILICON_ERRATUM_1980005 +static bool +hisilicon_1980005_match(const struct arm64_cpu_capabilities *entry, + int scope) +{ + static const struct midr_range idc_support_list[] = { + MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_REV(MIDR_HISI_TSV200, 1, 0), + MIDR_REV(MIDR_HISI_TSV200, 1, 2), + + { /* sentinel */ } + }; + + return is_midr_in_range_list(read_cpuid_id(), idc_support_list); +} + +static void +hisilicon_1980005_enable(const struct arm64_cpu_capabilities *__unused) +{ + cpus_set_cap(ARM64_HAS_CACHE_IDC); + arm64_ftr_reg_ctrel0.sys_val |= BIT(CTR_IDC_SHIFT); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); +} +#endif + static bool has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, int scope) @@ -752,6 +777,20 @@ static const struct midr_range cavium_erratum_30115_cpus[] = { }; #endif +#ifdef CONFIG_HISILICON_ERRATUM_162100125 +static const struct midr_range hisilicon_erratum_162100125_cpus[] = { + MIDR_REV(MIDR_HISI_LINXICORE9100, 0, 0), + {}, +}; +#endif + +#ifdef CONFIG_HISILICON_ERRATUM_162100602 +static const struct midr_range hisilicon_erratum_162100602_cpus[] = { + MIDR_REV(MIDR_HISI_LINXICORE9100, 0, 0), + {}, +}; +#endif + #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 static const struct arm64_cpu_capabilities qcom_erratum_1003_list[] = { { @@ -831,6 +870,15 @@ static struct midr_range broken_aarch32_aes[] = { #endif const struct arm64_cpu_capabilities arm64_errata[] = { +#ifdef CONFIG_HISILICON_ERRATUM_1980005 + { + .desc = "Taishan IDC coherence workaround", + .capability = ARM64_WORKAROUND_HISILICON_1980005, + .matches = hisilicon_1980005_match, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .cpu_enable = hisilicon_1980005_enable, + }, +#endif #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { .desc = "ARM errata 826319, 827319, 824069, 819472", @@ -904,6 +952,20 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .cpu_enable = cpu_enable_trap_ctr_access, }, +#ifdef CONFIG_HISILICON_ERRATUM_162100125 + { + .desc = "Hisilicon erratum 162100125", + .capability = ARM64_WORKAROUND_HISILICON_ERRATUM_162100125, + ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100125_cpus), + }, +#endif +#ifdef CONFIG_HISILICON_ERRATUM_162100602 + { + .desc = "Hisilicon erratum 162100602", + .capability = ARM64_WORKAROUND_HISILICON_ERRATUM_162100602, + ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100602_cpus), + }, +#endif #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f394047685df5a3dce83cd8ee6ecc15b96d8ee06..6c0cdac84fb604d541409dcd360c3d694be66729 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -977,6 +977,9 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) if (is_kdump_kernel()) return false; + if (cpus_have_const_cap(ARM64_WORKAROUND_HISILICON_ERRATUM_162100125)) + return false; + return has_cpuid_feature(entry, scope); } diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 62b431831f2e004cea8c152fde4137d91a01e634..cfbf5393e2558ea77af5aeaff6f3c6abd119e09b 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2549,6 +2549,23 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, gather->pgsize, true, smmu_domain); } +#ifdef CONFIG_HISILICON_ERRATUM_162100602 +static void arm_smmu_iotlb_sync_map(struct iommu_domain *domain) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + + if (!cpus_have_const_cap(ARM64_WORKAROUND_HISILICON_ERRATUM_162100602)) + return; + + if(smmu_domain->smmu) + arm_smmu_tlb_inv_context(smmu_domain); + //granule_size = 1 << __ffs(smmu_domain->domain.pgsize_bitmap); + + /* Add a SYNC command to sync io-pgtale to avoid errors in pgtable prefetch*/ + //arm_smmu_tlb_inv_range_domain(iova, granule_size, granule_size, true, smmu_domain); +} +#endif + static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { @@ -2843,6 +2860,9 @@ static struct iommu_ops arm_smmu_ops = { .unmap = arm_smmu_unmap, .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, +#ifdef CONFIG_HISILICON_ERRATUM_162100602 + .iotlb_sync_map = arm_smmu_iotlb_sync_map, +#endif .iova_to_phys = arm_smmu_iova_to_phys, .add_device = arm_smmu_add_device, .remove_device = arm_smmu_remove_device, diff --git a/drivers/irqchip/irq-gic-phytium-2500-its.c b/drivers/irqchip/irq-gic-phytium-2500-its.c index 7a77d9787f2ee0c8a3da6108c0e62c02d0cbf3c0..1ff4895741bf2de80920e1ae20581bfeb8f45a48 100644 --- a/drivers/irqchip/irq-gic-phytium-2500-its.c +++ b/drivers/irqchip/irq-gic-phytium-2500-its.c @@ -2162,12 +2162,12 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base) bool clean; u64 val; - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); val &= ~GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); do { - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); clean = !(val & GICR_VPENDBASER_Dirty); if (!clean) { count--; @@ -2277,7 +2277,7 @@ static void its_cpu_init_lpis(void) val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n", smp_processor_id(), val); - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); /* * Also clear Valid bit of GICR_VPENDBASER, in case some @@ -2947,7 +2947,7 @@ static void its_vpe_schedule(struct its_vpe *vpe) val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; val |= GICR_VPROPBASER_RaWb; val |= GICR_VPROPBASER_InnerShareable; - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); val = virt_to_phys(page_address(vpe->vpt_page)) & GENMASK_ULL(51, 16); @@ -2965,7 +2965,7 @@ static void its_vpe_schedule(struct its_vpe *vpe) val |= GICR_VPENDBASER_PendingLast; val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0; val |= GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); } static void its_vpe_deschedule(struct its_vpe *vpe) @@ -4124,7 +4124,7 @@ int __init phytium_its_init(struct fwnode_handle *handle, struct rdists *rdists, if (has_v4 & rdists->has_vlpis) { if (its_init_vpe_domain() || - its_init_v4(parent_domain, &its_vpe_domain_ops)) { + its_init_v4(parent_domain, &its_vpe_domain_ops, NULL)) { rdists->has_vlpis = false; pr_err("ITS: Disabling GICv4 support\n"); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 151eaa84e075abb835dbfb334725eac9046279cc..e444266592e224338c1c7c8f526b4daec6506921 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include @@ -13,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -44,6 +46,7 @@ #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING (1ULL << 0) #define ITS_FLAGS_WORKAROUND_CAVIUM_22375 (1ULL << 1) #define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2) +#define ITS_FLAGS_WORKAROUND_HISILICON_162100801 (1ULL << 3) #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0) #define RDIST_FLAGS_RD_TABLES_PREALLOCATED (1 << 1) @@ -98,6 +101,7 @@ struct its_node { struct mutex dev_alloc_lock; struct list_head entry; void __iomem *base; + void __iomem *sgir_base; phys_addr_t phys_base; struct its_cmd_block *cmd_base; struct its_cmd_block *cmd_write; @@ -105,24 +109,36 @@ struct its_node { struct its_collection *collections; struct fwnode_handle *fwnode_handle; u64 (*get_msi_base)(struct its_device *its_dev); + u64 typer; u64 cbaser_save; u32 ctlr_save; + u32 mpidr; struct list_head its_device_list; u64 flags; unsigned long list_nr; - u32 ite_size; - u32 device_ids; int numa_node; unsigned int msi_domain_flags; u32 pre_its_base; /* for Socionext Synquacer */ - bool is_v4; int vlpi_redist_offset; }; +#define is_v4(its) (!!((its)->typer & GITS_TYPER_VLPIS)) +#define is_v4_1(its) (!!((its)->typer & GITS_TYPER_VMAPP)) +#define device_ids(its) (FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1) + #define ITS_ITT_ALIGN SZ_256 /* The maximum number of VPEID bits supported by VLPI commands */ -#define ITS_MAX_VPEID_BITS (16) +#define ITS_MAX_VPEID_BITS \ + ({ \ + int nvpeid = 16; \ + if (gic_rdists->has_rvpeid && \ + gic_rdists->gicd_typer2 & GICD_TYPER2_VIL) \ + nvpeid = 1 + (gic_rdists->gicd_typer2 & \ + GICD_TYPER2_VID); \ + \ + nvpeid; \ + }) #define ITS_MAX_VPEID (1 << (ITS_MAX_VPEID_BITS)) /* Convert page order to size in bytes */ @@ -133,7 +149,7 @@ struct event_lpi_map { u16 *col_map; irq_hw_number_t lpi_base; int nr_lpis; - struct mutex vlpi_lock; + raw_spinlock_t vlpi_lock; struct its_vm *vm; struct its_vlpi_map *vlpi_maps; int nr_vlpis; @@ -185,22 +201,37 @@ static DEFINE_IDA(its_vpeid_ida); #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K) +/* + * Skip ITSs that have no vLPIs mapped, unless we're on GICv4.1, as we + * always have vSGIs mapped. + */ +static bool require_its_list_vmovp(struct its_vm *vm, struct its_node *its) +{ + return (gic_rdists->has_rvpeid || vm->vlpi_count[its->list_nr]); +} + static u16 get_its_list(struct its_vm *vm) { struct its_node *its; unsigned long its_list = 0; list_for_each_entry(its, &its_nodes, entry) { - if (!its->is_v4) + if (!is_v4(its)) continue; - if (vm->vlpi_count[its->list_nr]) + if (require_its_list_vmovp(vm, its)) __set_bit(its->list_nr, &its_list); } return (u16)its_list; } +static inline u32 its_get_event_id(struct irq_data *d) +{ + struct its_device *its_dev = irq_data_get_irq_chip_data(d); + return d->hwirq - its_dev->event_map.lpi_base; +} + static struct its_collection *dev_event_to_col(struct its_device *its_dev, u32 event) { @@ -209,6 +240,82 @@ static struct its_collection *dev_event_to_col(struct its_device *its_dev, return its->collections + its_dev->event_map.col_map[event]; } +static struct its_vlpi_map *dev_event_to_vlpi_map(struct its_device *its_dev, + u32 event) +{ + if (WARN_ON_ONCE(event >= its_dev->event_map.nr_lpis)) + return NULL; + + return &its_dev->event_map.vlpi_maps[event]; +} + +static struct its_vlpi_map *get_vlpi_map(struct irq_data *d) +{ + if (irqd_is_forwarded_to_vcpu(d)) { + struct its_device *its_dev = irq_data_get_irq_chip_data(d); + u32 event = its_get_event_id(d); + + return dev_event_to_vlpi_map(its_dev, event); + } + + return NULL; +} + +static int vpe_to_cpuid_lock(struct its_vpe *vpe, unsigned long *flags) +{ + raw_spin_lock_irqsave(&vpe->vpe_lock, *flags); + return vpe->col_idx; +} + +static void vpe_to_cpuid_unlock(struct its_vpe *vpe, unsigned long flags) +{ + raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags); +} + +static struct irq_chip its_vpe_irq_chip; + +static int irq_to_cpuid_lock(struct irq_data *d, unsigned long *flags) +{ + struct its_vpe *vpe = NULL; + int cpu; + + if (d->chip == &its_vpe_irq_chip) { + vpe = irq_data_get_irq_chip_data(d); + } else { + struct its_vlpi_map *map = get_vlpi_map(d); + if (map) + vpe = map->vpe; + } + + if (vpe) { + cpu = vpe_to_cpuid_lock(vpe, flags); + } else { + /* Physical LPIs are already locked via the irq_desc lock */ + struct its_device *its_dev = irq_data_get_irq_chip_data(d); + cpu = its_dev->event_map.col_map[its_get_event_id(d)]; + /* Keep GCC quiet... */ + *flags = 0; + } + + return cpu; +} + +static void irq_to_cpuid_unlock(struct irq_data *d, unsigned long flags) +{ + struct its_vpe *vpe = NULL; + + if (d->chip == &its_vpe_irq_chip) { + vpe = irq_data_get_irq_chip_data(d); + } else { + struct its_vlpi_map *map = get_vlpi_map(d); + if (map) + vpe = map->vpe; + } + + if (vpe) + vpe_to_cpuid_unlock(vpe, flags); +} + static struct its_collection *valid_col(struct its_collection *col) { if (WARN_ON_ONCE(col->target_address & GENMASK_ULL(15, 0))) @@ -308,6 +415,19 @@ struct its_cmd_desc { u16 seq_num; u16 its_list; } its_vmovp_cmd; + + struct { + struct its_vpe *vpe; + } its_invdb_cmd; + + struct { + struct its_vpe *vpe; + u8 sgi; + u8 priority; + bool enable; + bool group; + bool clear; + } its_vsgi_cmd; }; }; @@ -421,6 +541,63 @@ static void its_encode_vpt_size(struct its_cmd_block *cmd, u8 vpt_size) its_mask_encode(&cmd->raw_cmd[3], vpt_size, 4, 0); } +static void its_encode_vconf_addr(struct its_cmd_block *cmd, u64 vconf_pa) +{ + its_mask_encode(&cmd->raw_cmd[0], vconf_pa >> 16, 51, 16); +} + +static void its_encode_alloc(struct its_cmd_block *cmd, bool alloc) +{ + its_mask_encode(&cmd->raw_cmd[0], alloc, 8, 8); +} + +static void its_encode_ptz(struct its_cmd_block *cmd, bool ptz) +{ + its_mask_encode(&cmd->raw_cmd[0], ptz, 9, 9); +} + +static void its_encode_vmapp_default_db(struct its_cmd_block *cmd, + u32 vpe_db_lpi) +{ + its_mask_encode(&cmd->raw_cmd[1], vpe_db_lpi, 31, 0); +} + +static void its_encode_vmovp_default_db(struct its_cmd_block *cmd, + u32 vpe_db_lpi) +{ + its_mask_encode(&cmd->raw_cmd[3], vpe_db_lpi, 31, 0); +} + +static void its_encode_db(struct its_cmd_block *cmd, bool db) +{ + its_mask_encode(&cmd->raw_cmd[2], db, 63, 63); +} + +static void its_encode_sgi_intid(struct its_cmd_block *cmd, u8 sgi) +{ + its_mask_encode(&cmd->raw_cmd[0], sgi, 35, 32); +} + +static void its_encode_sgi_priority(struct its_cmd_block *cmd, u8 prio) +{ + its_mask_encode(&cmd->raw_cmd[0], prio >> 4, 23, 20); +} + +static void its_encode_sgi_group(struct its_cmd_block *cmd, bool grp) +{ + its_mask_encode(&cmd->raw_cmd[0], grp, 10, 10); +} + +static void its_encode_sgi_clear(struct its_cmd_block *cmd, bool clr) +{ + its_mask_encode(&cmd->raw_cmd[0], clr, 9, 9); +} + +static void its_encode_sgi_enable(struct its_cmd_block *cmd, bool en) +{ + its_mask_encode(&cmd->raw_cmd[0], en, 8, 8); +} + static inline void its_fixup_cmd(struct its_cmd_block *cmd) { /* Let's fixup BE commands */ @@ -604,19 +781,45 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, struct its_cmd_block *cmd, struct its_cmd_desc *desc) { - unsigned long vpt_addr; + unsigned long vpt_addr, vconf_addr; u64 target; - - vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page)); - target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset; + bool alloc; its_encode_cmd(cmd, GITS_CMD_VMAPP); its_encode_vpeid(cmd, desc->its_vmapp_cmd.vpe->vpe_id); its_encode_valid(cmd, desc->its_vmapp_cmd.valid); + + if (!desc->its_vmapp_cmd.valid) { + if (is_v4_1(its)) { + alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count); + its_encode_alloc(cmd, alloc); + } + + goto out; + } + + vpt_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->vpt_page)); + target = desc->its_vmapp_cmd.col->target_address + its->vlpi_redist_offset; + its_encode_target(cmd, target); its_encode_vpt_addr(cmd, vpt_addr); its_encode_vpt_size(cmd, LPI_NRBITS - 1); + if (!is_v4_1(its)) + goto out; + + vconf_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->its_vm->vprop_page)); + + alloc = !atomic_fetch_inc(&desc->its_vmapp_cmd.vpe->vmapp_count); + + its_encode_alloc(cmd, alloc); + + /* We can only signal PTZ when alloc==1. Why do we have two bits? */ + its_encode_ptz(cmd, alloc); + its_encode_vconf_addr(cmd, vconf_addr); + its_encode_vmapp_default_db(cmd, desc->its_vmapp_cmd.vpe->vpe_db_lpi); + +out: its_fixup_cmd(cmd); return valid_vpe(its, desc->its_vmapp_cmd.vpe); @@ -628,7 +831,7 @@ static struct its_vpe *its_build_vmapti_cmd(struct its_node *its, { u32 db; - if (desc->its_vmapti_cmd.db_enabled) + if (!is_v4_1(its) && desc->its_vmapti_cmd.db_enabled) db = desc->its_vmapti_cmd.vpe->vpe_db_lpi; else db = 1023; @@ -651,7 +854,7 @@ static struct its_vpe *its_build_vmovi_cmd(struct its_node *its, { u32 db; - if (desc->its_vmovi_cmd.db_enabled) + if (!is_v4_1(its) && desc->its_vmovi_cmd.db_enabled) db = desc->its_vmovi_cmd.vpe->vpe_db_lpi; else db = 1023; @@ -681,11 +884,105 @@ static struct its_vpe *its_build_vmovp_cmd(struct its_node *its, its_encode_vpeid(cmd, desc->its_vmovp_cmd.vpe->vpe_id); its_encode_target(cmd, target); + if (is_v4_1(its)) { + its_encode_db(cmd, true); + its_encode_vmovp_default_db(cmd, desc->its_vmovp_cmd.vpe->vpe_db_lpi); + } + its_fixup_cmd(cmd); return valid_vpe(its, desc->its_vmovp_cmd.vpe); } +static struct its_vpe *its_build_vinv_cmd(struct its_node *its, + struct its_cmd_block *cmd, + struct its_cmd_desc *desc) +{ + struct its_vlpi_map *map; + + map = dev_event_to_vlpi_map(desc->its_inv_cmd.dev, + desc->its_inv_cmd.event_id); + + its_encode_cmd(cmd, GITS_CMD_INV); + its_encode_devid(cmd, desc->its_inv_cmd.dev->device_id); + its_encode_event_id(cmd, desc->its_inv_cmd.event_id); + + its_fixup_cmd(cmd); + + return valid_vpe(its, map->vpe); +} + +static struct its_vpe *its_build_vint_cmd(struct its_node *its, + struct its_cmd_block *cmd, + struct its_cmd_desc *desc) +{ + struct its_vlpi_map *map; + + map = dev_event_to_vlpi_map(desc->its_int_cmd.dev, + desc->its_int_cmd.event_id); + + its_encode_cmd(cmd, GITS_CMD_INT); + its_encode_devid(cmd, desc->its_int_cmd.dev->device_id); + its_encode_event_id(cmd, desc->its_int_cmd.event_id); + + its_fixup_cmd(cmd); + + return valid_vpe(its, map->vpe); +} + +static struct its_vpe *its_build_vclear_cmd(struct its_node *its, + struct its_cmd_block *cmd, + struct its_cmd_desc *desc) +{ + struct its_vlpi_map *map; + + map = dev_event_to_vlpi_map(desc->its_clear_cmd.dev, + desc->its_clear_cmd.event_id); + + its_encode_cmd(cmd, GITS_CMD_CLEAR); + its_encode_devid(cmd, desc->its_clear_cmd.dev->device_id); + its_encode_event_id(cmd, desc->its_clear_cmd.event_id); + + its_fixup_cmd(cmd); + + return valid_vpe(its, map->vpe); +} + +static struct its_vpe *its_build_invdb_cmd(struct its_node *its, + struct its_cmd_block *cmd, + struct its_cmd_desc *desc) +{ + if (WARN_ON(!is_v4_1(its))) + return NULL; + + its_encode_cmd(cmd, GITS_CMD_INVDB); + its_encode_vpeid(cmd, desc->its_invdb_cmd.vpe->vpe_id); + + its_fixup_cmd(cmd); + + return valid_vpe(its, desc->its_invdb_cmd.vpe); +} + +static struct its_vpe *its_build_vsgi_cmd(struct its_node *its, + struct its_cmd_block *cmd, + struct its_cmd_desc *desc) +{ + if (WARN_ON(!is_v4_1(its))) + return NULL; + + its_encode_cmd(cmd, GITS_CMD_VSGI); + its_encode_vpeid(cmd, desc->its_vsgi_cmd.vpe->vpe_id); + its_encode_sgi_intid(cmd, desc->its_vsgi_cmd.sgi); + its_encode_sgi_priority(cmd, desc->its_vsgi_cmd.priority); + its_encode_sgi_group(cmd, desc->its_vsgi_cmd.group); + its_encode_sgi_clear(cmd, desc->its_vsgi_cmd.clear); + its_encode_sgi_enable(cmd, desc->its_vsgi_cmd.enable); + + its_fixup_cmd(cmd); + + return valid_vpe(its, desc->its_vsgi_cmd.vpe); +} + static u64 its_cmd_ptr_to_offset(struct its_node *its, struct its_cmd_block *ptr) { @@ -963,7 +1260,7 @@ static void its_send_invall(struct its_node *its, struct its_collection *col) static void its_send_vmapti(struct its_device *dev, u32 id) { - struct its_vlpi_map *map = &dev->event_map.vlpi_maps[id]; + struct its_vlpi_map *map = dev_event_to_vlpi_map(dev, id); struct its_cmd_desc desc; desc.its_vmapti_cmd.vpe = map->vpe; @@ -977,7 +1274,7 @@ static void its_send_vmapti(struct its_device *dev, u32 id) static void its_send_vmovi(struct its_device *dev, u32 id) { - struct its_vlpi_map *map = &dev->event_map.vlpi_maps[id]; + struct its_vlpi_map *map = dev_event_to_vlpi_map(dev, id); struct its_cmd_desc desc; desc.its_vmovi_cmd.vpe = map->vpe; @@ -1000,6 +1297,14 @@ static void its_send_vmapp(struct its_node *its, its_send_single_vcommand(its, its_build_vmapp_cmd, &desc); } +static void its_send_vinvall(struct its_node *its, struct its_vpe *vpe) +{ + struct its_cmd_desc desc; + + desc.its_vinvall_cmd.vpe = vpe; + its_send_single_vcommand(its, its_build_vinvall_cmd, &desc); +} + static void its_send_vmovp(struct its_vpe *vpe) { struct its_cmd_desc desc = {}; @@ -1031,50 +1336,84 @@ static void its_send_vmovp(struct its_vpe *vpe) /* Emit VMOVPs */ list_for_each_entry(its, &its_nodes, entry) { - if (!its->is_v4) + if (!is_v4(its)) continue; - if (!vpe->its_vm->vlpi_count[its->list_nr]) + if (!require_its_list_vmovp(vpe->its_vm, its)) continue; desc.its_vmovp_cmd.col = &its->collections[col_id]; its_send_single_vcommand(its, its_build_vmovp_cmd, &desc); + if (is_v4_1(its) && (its->flags & + ITS_FLAGS_WORKAROUND_HISILICON_162100801)) + its_send_vinvall(its, vpe); } raw_spin_unlock_irqrestore(&vmovp_lock, flags); } -static void its_send_vinvall(struct its_node *its, struct its_vpe *vpe) +static void its_send_vinv(struct its_device *dev, u32 event_id) { struct its_cmd_desc desc; - desc.its_vinvall_cmd.vpe = vpe; - its_send_single_vcommand(its, its_build_vinvall_cmd, &desc); + /* + * There is no real VINV command. This is just a normal INV, + * with a VSYNC instead of a SYNC. + */ + desc.its_inv_cmd.dev = dev; + desc.its_inv_cmd.event_id = event_id; + + its_send_single_vcommand(dev->its, its_build_vinv_cmd, &desc); } -/* - * irqchip functions - assumes MSI, mostly. - */ +static void its_send_vint(struct its_device *dev, u32 event_id) +{ + struct its_cmd_desc desc; -static inline u32 its_get_event_id(struct irq_data *d) + /* + * There is no real VINT command. This is just a normal INT, + * with a VSYNC instead of a SYNC. + */ + desc.its_int_cmd.dev = dev; + desc.its_int_cmd.event_id = event_id; + + its_send_single_vcommand(dev->its, its_build_vint_cmd, &desc); +} + +static void its_send_vclear(struct its_device *dev, u32 event_id) { - struct its_device *its_dev = irq_data_get_irq_chip_data(d); - return d->hwirq - its_dev->event_map.lpi_base; + struct its_cmd_desc desc; + + /* + * There is no real VCLEAR command. This is just a normal CLEAR, + * with a VSYNC instead of a SYNC. + */ + desc.its_clear_cmd.dev = dev; + desc.its_clear_cmd.event_id = event_id; + + its_send_single_vcommand(dev->its, its_build_vclear_cmd, &desc); } +static void its_send_invdb(struct its_node *its, struct its_vpe *vpe) +{ + struct its_cmd_desc desc; + + desc.its_invdb_cmd.vpe = vpe; + its_send_single_vcommand(its, its_build_invdb_cmd, &desc); +} + +/* + * irqchip functions - assumes MSI, mostly. + */ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set) { + struct its_vlpi_map *map = get_vlpi_map(d); irq_hw_number_t hwirq; void *va; u8 *cfg; - if (irqd_is_forwarded_to_vcpu(d)) { - struct its_device *its_dev = irq_data_get_irq_chip_data(d); - u32 event = its_get_event_id(d); - struct its_vlpi_map *map; - - va = page_address(its_dev->event_map.vm->vprop_page); - map = &its_dev->event_map.vlpi_maps[event]; + if (map) { + va = page_address(map->vm->vprop_page); hwirq = map->vintid; /* Remember the updated property */ @@ -1100,23 +1439,83 @@ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set) dsb(ishst); } +static void wait_for_syncr(void __iomem *rdbase) +{ + while (readl_relaxed(rdbase + GICR_SYNCR) & 1) + cpu_relax(); +} + +static void __direct_lpi_inv(struct irq_data *d, u64 val) +{ + void __iomem *rdbase; + unsigned long flags; + int cpu; + + /* Target the redistributor this LPI is currently routed to */ + cpu = irq_to_cpuid_lock(d, &flags); + raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock); + + rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base; + gic_write_lpir(val, rdbase + GICR_INVLPIR); + wait_for_syncr(rdbase); + + raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock); + irq_to_cpuid_unlock(d, flags); +} + +static void direct_lpi_inv(struct irq_data *d) +{ + struct its_vlpi_map *map = get_vlpi_map(d); + u64 val; + + if (map) { + struct its_device *its_dev = irq_data_get_irq_chip_data(d); + + WARN_ON(!is_v4_1(its_dev->its)); + + val = GICR_INVLPIR_V; + val |= FIELD_PREP(GICR_INVLPIR_VPEID, map->vpe->vpe_id); + val |= FIELD_PREP(GICR_INVLPIR_INTID, map->vintid); + } else { + val = d->hwirq; + } + + __direct_lpi_inv(d, val); +} + static void lpi_update_config(struct irq_data *d, u8 clr, u8 set) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); lpi_write_config(d, clr, set); - its_send_inv(its_dev, its_get_event_id(d)); + if (gic_rdists->has_direct_lpi && + (is_v4_1(its_dev->its) || !irqd_is_forwarded_to_vcpu(d))) + direct_lpi_inv(d); + else if (!irqd_is_forwarded_to_vcpu(d)) + its_send_inv(its_dev, its_get_event_id(d)); + else + its_send_vinv(its_dev, its_get_event_id(d)); } static void its_vlpi_set_doorbell(struct irq_data *d, bool enable) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); + struct its_vlpi_map *map; + + /* + * GICv4.1 does away with the per-LPI nonsense, nothing to do + * here. + */ + if (is_v4_1(its_dev->its)) + return; - if (its_dev->event_map.vlpi_maps[event].db_enabled == enable) + map = dev_event_to_vlpi_map(its_dev, event); + + if (map->db_enabled == enable) return; - its_dev->event_map.vlpi_maps[event].db_enabled = enable; + map->db_enabled = enable; /* * More fun with the architecture: @@ -1340,20 +1739,46 @@ static int its_irq_set_irqchip_state(struct irq_data *d, if (which != IRQCHIP_STATE_PENDING) return -EINVAL; - if (state) - its_send_int(its_dev, event); - else - its_send_clear(its_dev, event); - - return 0; -} - -static void its_map_vm(struct its_node *its, struct its_vm *vm) -{ + if (irqd_is_forwarded_to_vcpu(d)) { + if (state) + its_send_vint(its_dev, event); + else + its_send_vclear(its_dev, event); + } else { + if (state) + its_send_int(its_dev, event); + else + its_send_clear(its_dev, event); + } + + return 0; +} + +/* + * Two favourable cases: + * + * (a) Either we have a GICv4.1, and all vPEs have to be mapped at all times + * for vSGI delivery + * + * (b) Or the ITSs do not use a list map, meaning that VMOVP is cheap enough + * and we're better off mapping all VPEs always + * + * If neither (a) nor (b) is true, then we map vPEs on demand. + * + */ +static bool gic_requires_eager_mapping(void) +{ + if (!its_list_map || gic_rdists->has_rvpeid) + return true; + + return false; +} + +static void its_map_vm(struct its_node *its, struct its_vm *vm) +{ unsigned long flags; - /* Not using the ITS list? Everything is always mapped. */ - if (!its_list_map) + if (gic_requires_eager_mapping()) return; raw_spin_lock_irqsave(&vmovp_lock, flags); @@ -1387,7 +1812,7 @@ static void its_unmap_vm(struct its_node *its, struct its_vm *vm) unsigned long flags; /* Not using the ITS list? Everything is always mapped. */ - if (!its_list_map) + if (gic_requires_eager_mapping()) return; raw_spin_lock_irqsave(&vmovp_lock, flags); @@ -1411,13 +1836,13 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) if (!info->map) return -EINVAL; - mutex_lock(&its_dev->event_map.vlpi_lock); + raw_spin_lock(&its_dev->event_map.vlpi_lock); if (!its_dev->event_map.vm) { struct its_vlpi_map *maps; maps = kcalloc(its_dev->event_map.nr_lpis, sizeof(*maps), - GFP_KERNEL); + GFP_ATOMIC); if (!maps) { ret = -ENOMEM; goto out; @@ -1460,29 +1885,30 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info) } out: - mutex_unlock(&its_dev->event_map.vlpi_lock); + raw_spin_unlock(&its_dev->event_map.vlpi_lock); return ret; } static int its_vlpi_get(struct irq_data *d, struct its_cmd_info *info) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); - u32 event = its_get_event_id(d); + struct its_vlpi_map *map; int ret = 0; - mutex_lock(&its_dev->event_map.vlpi_lock); + raw_spin_lock(&its_dev->event_map.vlpi_lock); - if (!its_dev->event_map.vm || - !its_dev->event_map.vlpi_maps[event].vm) { + map = get_vlpi_map(d); + + if (!its_dev->event_map.vm || !map) { ret = -EINVAL; goto out; } /* Copy our mapping information to the incoming request */ - *info->map = its_dev->event_map.vlpi_maps[event]; + *info->map = *map; out: - mutex_unlock(&its_dev->event_map.vlpi_lock); + raw_spin_unlock(&its_dev->event_map.vlpi_lock); return ret; } @@ -1492,7 +1918,7 @@ static int its_vlpi_unmap(struct irq_data *d) u32 event = its_get_event_id(d); int ret = 0; - mutex_lock(&its_dev->event_map.vlpi_lock); + raw_spin_lock(&its_dev->event_map.vlpi_lock); if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) { ret = -EINVAL; @@ -1522,7 +1948,7 @@ static int its_vlpi_unmap(struct irq_data *d) } out: - mutex_unlock(&its_dev->event_map.vlpi_lock); + raw_spin_unlock(&its_dev->event_map.vlpi_lock); return ret; } @@ -1548,7 +1974,7 @@ static int its_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) struct its_cmd_info *info = vcpu_info; /* Need a v4 ITS */ - if (!its_dev->its->is_v4) + if (!is_v4(its_dev->its)) return -EINVAL; /* Unmap request? */ @@ -1884,18 +2310,17 @@ static void its_write_baser(struct its_node *its, struct its_baser *baser, } static int its_setup_baser(struct its_node *its, struct its_baser *baser, - u64 cache, u64 shr, u32 psz, u32 order, - bool indirect) + u64 cache, u64 shr, u32 order, bool indirect) { u64 val = its_read_baser(its, baser); u64 esz = GITS_BASER_ENTRY_SIZE(val); u64 type = GITS_BASER_TYPE(val); u64 baser_phys, tmp; - u32 alloc_pages; + u32 alloc_pages, psz; struct page *page; void *base; -retry_alloc_baser: + psz = baser->psz; alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); if (alloc_pages > GITS_BASER_PAGES_MAX) { pr_warn("ITS@%pa: %s too large, reduce ITS pages %u->%u\n", @@ -1968,25 +2393,6 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, goto retry_baser; } - if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) { - /* - * Page size didn't stick. Let's try a smaller - * size and retry. If we reach 4K, then - * something is horribly wrong... - */ - free_pages((unsigned long)base, order); - baser->base = NULL; - - switch (psz) { - case SZ_16K: - psz = SZ_4K; - goto retry_alloc_baser; - case SZ_64K: - psz = SZ_16K; - goto retry_alloc_baser; - } - } - if (val != tmp) { pr_err("ITS@%pa: %s doesn't stick: %llx %llx\n", &its->phys_base, its_base_type_string[type], @@ -2012,13 +2418,14 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, static bool its_parse_indirect_baser(struct its_node *its, struct its_baser *baser, - u32 psz, u32 *order, u32 ids) + u32 *order, u32 ids) { u64 tmp = its_read_baser(its, baser); u64 type = GITS_BASER_TYPE(tmp); u64 esz = GITS_BASER_ENTRY_SIZE(tmp); u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb; u32 new_order = *order; + u32 psz = baser->psz; bool indirect = false; /* No need to enable Indirection if memory requirement < (psz*2)bytes */ @@ -2054,9 +2461,9 @@ static bool its_parse_indirect_baser(struct its_node *its, if (new_order >= MAX_ORDER) { new_order = MAX_ORDER - 1; ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz); - pr_warn("ITS@%pa: %s Table too large, reduce ids %u->%u\n", + pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n", &its->phys_base, its_base_type_string[type], - its->device_ids, ids); + device_ids(its), ids); } *order = new_order; @@ -2064,6 +2471,65 @@ static bool its_parse_indirect_baser(struct its_node *its, return indirect; } +static u32 compute_common_aff(u64 val) +{ + u32 aff, clpiaff; + + aff = FIELD_GET(GICR_TYPER_AFFINITY, val); + clpiaff = FIELD_GET(GICR_TYPER_COMMON_LPI_AFF, val); + + return aff & ~(GENMASK(31, 0) >> (clpiaff * 8)); +} + +static u32 compute_its_aff(struct its_node *its) +{ + u64 val; + u32 svpet; + + /* + * Reencode the ITS SVPET and MPIDR as a GICR_TYPER, and compute + * the resulting affinity. We then use that to see if this match + * our own affinity. + */ + svpet = FIELD_GET(GITS_TYPER_SVPET, its->typer); + val = FIELD_PREP(GICR_TYPER_COMMON_LPI_AFF, svpet); + val |= FIELD_PREP(GICR_TYPER_AFFINITY, its->mpidr); + return compute_common_aff(val); +} + +static struct its_node *find_sibling_its(struct its_node *cur_its) +{ + struct its_node *its; + u32 aff; + + if (!FIELD_GET(GITS_TYPER_SVPET, cur_its->typer)) + return NULL; + + aff = compute_its_aff(cur_its); + + list_for_each_entry(its, &its_nodes, entry) { + u64 baser; + + if (!is_v4_1(its) || its == cur_its) + continue; + + if (!FIELD_GET(GITS_TYPER_SVPET, its->typer)) + continue; + + if (aff != compute_its_aff(its)) + continue; + + /* GICv4.1 guarantees that the vPE table is GITS_BASER2 */ + baser = its->tables[2].val; + if (!(baser & GITS_BASER_VALID)) + continue; + + return its; + } + + return NULL; +} + static void its_free_tables(struct its_node *its) { int i; @@ -2077,11 +2543,58 @@ static void its_free_tables(struct its_node *its) } } +static int its_probe_baser_psz(struct its_node *its, struct its_baser *baser) +{ + u64 psz = SZ_64K; + + while (psz) { + u64 val, gpsz; + + val = its_read_baser(its, baser); + val &= ~GITS_BASER_PAGE_SIZE_MASK; + + switch (psz) { + case SZ_64K: + gpsz = GITS_BASER_PAGE_SIZE_64K; + break; + case SZ_16K: + gpsz = GITS_BASER_PAGE_SIZE_16K; + break; + case SZ_4K: + default: + gpsz = GITS_BASER_PAGE_SIZE_4K; + break; + } + + gpsz >>= GITS_BASER_PAGE_SIZE_SHIFT; + + val |= FIELD_PREP(GITS_BASER_PAGE_SIZE_MASK, gpsz); + its_write_baser(its, baser, val); + + if (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser->val) == gpsz) + break; + + switch (psz) { + case SZ_64K: + psz = SZ_16K; + break; + case SZ_16K: + psz = SZ_4K; + break; + case SZ_4K: + default: + return -1; + } + } + + baser->psz = psz; + return 0; +} + static int its_alloc_tables(struct its_node *its) { u64 shr = GITS_BASER_InnerShareable; u64 cache = GITS_BASER_RaWaWb; - u32 psz = SZ_64K; int err, i; if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) @@ -2092,39 +2605,53 @@ static int its_alloc_tables(struct its_node *its) struct its_baser *baser = its->tables + i; u64 val = its_read_baser(its, baser); u64 type = GITS_BASER_TYPE(val); - u32 order = get_order(psz); bool indirect = false; + u32 order; - switch (type) { - case GITS_BASER_TYPE_NONE: + if (type == GITS_BASER_TYPE_NONE) continue; + if (its_probe_baser_psz(its, baser)) { + its_free_tables(its); + return -ENXIO; + } + + order = get_order(baser->psz); + + switch (type) { case GITS_BASER_TYPE_DEVICE: - indirect = its_parse_indirect_baser(its, baser, - psz, &order, - its->device_ids); + indirect = its_parse_indirect_baser(its, baser, &order, + device_ids(its)); break; case GITS_BASER_TYPE_VCPU: - indirect = its_parse_indirect_baser(its, baser, - psz, &order, + if (is_v4_1(its)) { + struct its_node *sibling; + + WARN_ON(i != 2); + if ((sibling = find_sibling_its(its))) { + *baser = sibling->tables[2]; + its_write_baser(its, baser, baser->val); + continue; + } + } + + indirect = its_parse_indirect_baser(its, baser, &order, ITS_MAX_VPEID_BITS); break; case GITS_BASER_TYPE_COLLECTION: - indirect = its_parse_indirect_baser(its, baser, - psz, &order, + indirect = its_parse_indirect_baser(its, baser, &order, order_base_2(num_possible_cpus())); break; } - err = its_setup_baser(its, baser, cache, shr, psz, order, indirect); + err = its_setup_baser(its, baser, cache, shr, order, indirect); if (err < 0) { its_free_tables(its); return err; } /* Update settings which will be used for next BASERn */ - psz = baser->psz; cache = baser->val & GITS_BASER_CACHEABILITY_MASK; shr = baser->val & GITS_BASER_SHAREABILITY_MASK; } @@ -2132,6 +2659,291 @@ static int its_alloc_tables(struct its_node *its) return 0; } +static u64 inherit_vpe_l1_table_from_its(void) +{ + struct its_node *its; + u64 val; + u32 aff; + + val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER); + aff = compute_common_aff(val); + + list_for_each_entry(its, &its_nodes, entry) { + u64 baser, addr; + + if (!is_v4_1(its)) + continue; + + if (!FIELD_GET(GITS_TYPER_SVPET, its->typer)) + continue; + + if (aff != compute_its_aff(its)) + continue; + + /* GICv4.1 guarantees that the vPE table is GITS_BASER2 */ + baser = its->tables[2].val; + if (!(baser & GITS_BASER_VALID)) + continue; + + /* We have a winner! */ + gic_data_rdist()->vpe_l1_base = its->tables[2].base; + + val = GICR_VPROPBASER_4_1_VALID; + if (baser & GITS_BASER_INDIRECT) + val |= GICR_VPROPBASER_4_1_INDIRECT; + val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, + FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser)); + switch (FIELD_GET(GITS_BASER_PAGE_SIZE_MASK, baser)) { + case GIC_PAGE_SIZE_64K: + addr = GITS_BASER_ADDR_48_to_52(baser); + break; + default: + addr = baser & GENMASK_ULL(47, 12); + break; + } + val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, addr >> 12); + val |= FIELD_PREP(GICR_VPROPBASER_SHAREABILITY_MASK, + FIELD_GET(GITS_BASER_SHAREABILITY_MASK, baser)); + val |= FIELD_PREP(GICR_VPROPBASER_INNER_CACHEABILITY_MASK, + FIELD_GET(GITS_BASER_INNER_CACHEABILITY_MASK, baser)); + val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1); + + return val; + } + + return 0; +} + +static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask) +{ + u32 aff; + u64 val; + int cpu; + + val = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER); + aff = compute_common_aff(val); + + for_each_possible_cpu(cpu) { + void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base; + + if (!base || cpu == smp_processor_id()) + continue; + + val = gic_read_typer(base + GICR_TYPER); + if (aff != compute_common_aff(val)) + continue; + + /* + * At this point, we have a victim. This particular CPU + * has already booted, and has an affinity that matches + * ours wrt CommonLPIAff. Let's use its own VPROPBASER. + * Make sure we don't write the Z bit in that case. + */ + val = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER); + val &= ~GICR_VPROPBASER_4_1_Z; + + gic_data_rdist()->vpe_l1_base = gic_data_rdist_cpu(cpu)->vpe_l1_base; + *mask = gic_data_rdist_cpu(cpu)->vpe_table_mask; + + return val; + } + + return 0; +} + +static bool allocate_vpe_l2_table(int cpu, u32 id) +{ + void __iomem *base = gic_data_rdist_cpu(cpu)->rd_base; + unsigned int psz, esz, idx, npg, gpsz; + u64 val; + struct page *page; + __le64 *table; + + if (!gic_rdists->has_rvpeid) + return true; + + /* Skip non-present CPUs */ + if (!base) + return true; + + val = gicr_read_vpropbaser(base + SZ_128K + GICR_VPROPBASER); + + esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val) + 1; + gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val); + npg = FIELD_GET(GICR_VPROPBASER_4_1_SIZE, val) + 1; + + switch (gpsz) { + default: + WARN_ON(1); + /* fall through */ + case GIC_PAGE_SIZE_4K: + psz = SZ_4K; + break; + case GIC_PAGE_SIZE_16K: + psz = SZ_16K; + break; + case GIC_PAGE_SIZE_64K: + psz = SZ_64K; + break; + } + + /* Don't allow vpe_id that exceeds single, flat table limit */ + if (!(val & GICR_VPROPBASER_4_1_INDIRECT)) + return (id < (npg * psz / (esz * SZ_8))); + + /* Compute 1st level table index & check if that exceeds table limit */ + idx = id >> ilog2(psz / (esz * SZ_8)); + if (idx >= (npg * psz / GITS_LVL1_ENTRY_SIZE)) + return false; + + table = gic_data_rdist_cpu(cpu)->vpe_l1_base; + + /* Allocate memory for 2nd level table */ + if (!table[idx]) { + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz)); + if (!page) + return false; + + /* Flush Lvl2 table to PoC if hw doesn't support coherency */ + if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK)) + gic_flush_dcache_to_poc(page_address(page), psz); + + table[idx] = cpu_to_le64(page_to_phys(page) | GITS_BASER_VALID); + + /* Flush Lvl1 entry to PoC if hw doesn't support coherency */ + if (!(val & GICR_VPROPBASER_SHAREABILITY_MASK)) + gic_flush_dcache_to_poc(table + idx, GITS_LVL1_ENTRY_SIZE); + + /* Ensure updated table contents are visible to RD hardware */ + dsb(sy); + } + + return true; +} + +static int allocate_vpe_l1_table(void) +{ + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + u64 val, gpsz, npg, pa; + unsigned int psz = SZ_64K; + unsigned int np, epp, esz; + struct page *page; + + if (!gic_rdists->has_rvpeid) + return 0; + + /* + * if VPENDBASER.Valid is set, disable any previously programmed + * VPE by setting PendingLast while clearing Valid. This has the + * effect of making sure no doorbell will be generated and we can + * then safely clear VPROPBASER.Valid. + */ + if (gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER) & GICR_VPENDBASER_Valid) + gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast, + vlpi_base + GICR_VPENDBASER); + + /* + * If we can inherit the configuration from another RD, let's do + * so. Otherwise, we have to go through the allocation process. We + * assume that all RDs have the exact same requirements, as + * nothing will work otherwise. + */ + val = inherit_vpe_l1_table_from_rd(&gic_data_rdist()->vpe_table_mask); + if (val & GICR_VPROPBASER_4_1_VALID) + goto out; + + gic_data_rdist()->vpe_table_mask = kzalloc(sizeof(cpumask_t), GFP_ATOMIC); + if (!gic_data_rdist()->vpe_table_mask) + return -ENOMEM; + + val = inherit_vpe_l1_table_from_its(); + if (val & GICR_VPROPBASER_4_1_VALID) + goto out; + + /* First probe the page size */ + val = FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, GIC_PAGE_SIZE_64K); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + val = gicr_read_vpropbaser(vlpi_base + GICR_VPROPBASER); + gpsz = FIELD_GET(GICR_VPROPBASER_4_1_PAGE_SIZE, val); + esz = FIELD_GET(GICR_VPROPBASER_4_1_ENTRY_SIZE, val); + + switch (gpsz) { + default: + gpsz = GIC_PAGE_SIZE_4K; + /* fall through */ + case GIC_PAGE_SIZE_4K: + psz = SZ_4K; + break; + case GIC_PAGE_SIZE_16K: + psz = SZ_16K; + break; + case GIC_PAGE_SIZE_64K: + psz = SZ_64K; + break; + } + + /* + * Start populating the register from scratch, including RO fields + * (which we want to print in debug cases...) + */ + val = 0; + val |= FIELD_PREP(GICR_VPROPBASER_4_1_PAGE_SIZE, gpsz); + val |= FIELD_PREP(GICR_VPROPBASER_4_1_ENTRY_SIZE, esz); + + /* How many entries per GIC page? */ + esz++; + epp = psz / (esz * SZ_8); + + /* + * If we need more than just a single L1 page, flag the table + * as indirect and compute the number of required L1 pages. + */ + if (epp < ITS_MAX_VPEID) { + int nl2; + + val |= GICR_VPROPBASER_4_1_INDIRECT; + + /* Number of L2 pages required to cover the VPEID space */ + nl2 = DIV_ROUND_UP(ITS_MAX_VPEID, epp); + + /* Number of L1 pages to point to the L2 pages */ + npg = DIV_ROUND_UP(nl2 * SZ_8, psz); + } else { + npg = 1; + } + + val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, npg - 1); + + /* Right, that's the number of CPU pages we need for L1 */ + np = DIV_ROUND_UP(npg * psz, PAGE_SIZE); + + pr_debug("np = %d, npg = %lld, psz = %d, epp = %d, esz = %d\n", + np, npg, psz, epp, esz); + page = alloc_pages(GFP_ATOMIC | __GFP_ZERO, get_order(np * PAGE_SIZE)); + if (!page) + return -ENOMEM; + + gic_data_rdist()->vpe_l1_base = page_address(page); + pa = virt_to_phys(page_address(page)); + WARN_ON(!IS_ALIGNED(pa, psz)); + + val |= FIELD_PREP(GICR_VPROPBASER_4_1_ADDR, pa >> 12); + val |= GICR_VPROPBASER_RaWb; + val |= GICR_VPROPBASER_InnerShareable; + val |= GICR_VPROPBASER_4_1_Z; + val |= GICR_VPROPBASER_4_1_VALID; + +out: + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + cpumask_set_cpu(smp_processor_id(), gic_data_rdist()->vpe_table_mask); + + pr_debug("CPU%d: VPROPBASER = %llx %*pbl\n", + smp_processor_id(), val, + cpumask_pr_args(gic_data_rdist()->vpe_table_mask)); + + return 0; +} + static int its_alloc_collections(struct its_node *its) { int i; @@ -2223,18 +3035,14 @@ static int __init allocate_lpi_tables(void) return 0; } -static u64 its_clear_vpend_valid(void __iomem *vlpi_base) +static u64 read_vpend_dirty_clear(void __iomem *vlpi_base) { u32 count = 1000000; /* 1s! */ bool clean; u64 val; - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); - do { - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); clean = !(val & GICR_VPENDBASER_Dirty); if (!clean) { count--; @@ -2243,6 +3051,27 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base) } } while (!clean && count); + if (unlikely(!clean)) + pr_err_ratelimited("ITS virtual pending table not cleaning\n"); + + return val; +} + +static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +{ + u64 val; + + /* Make sure we wait until the RD is done with the initial scan */ + val = read_vpend_dirty_clear(vlpi_base); + val &= ~GICR_VPENDBASER_Valid; + val &= ~clr; + val |= set; + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + val = read_vpend_dirty_clear(vlpi_base); + if (unlikely(val & GICR_VPENDBASER_Dirty)) + val |= GICR_VPENDBASER_PendingLast; + return val; } @@ -2331,7 +3160,7 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); - if (gic_rdists->has_vlpis) { + if (gic_rdists->has_vlpis && !gic_rdists->has_rvpeid) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); /* @@ -2344,15 +3173,24 @@ static void its_cpu_init_lpis(void) val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n", smp_processor_id(), val); - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); /* * Also clear Valid bit of GICR_VPENDBASER, in case some * ancient programming gets left in and has possibility of * corrupting memory. */ - val = its_clear_vpend_valid(vlpi_base); - WARN_ON(val & GICR_VPENDBASER_Dirty); + val = its_clear_vpend_valid(vlpi_base, 0, 0); + } + + if (allocate_vpe_l1_table()) { + /* + * If the allocation has failed, we're in massive trouble. + * Disable direct injection, and pray that no VM was + * already running... + */ + gic_rdists->has_rvpeid = false; + gic_rdists->has_vlpis = false; } /* Make sure the GIC has seen the above */ @@ -2498,7 +3336,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id) /* Don't allow device id that exceeds ITS hardware limit */ if (!baser) - return (ilog2(dev_id) < its->device_ids); + return (ilog2(dev_id) < device_ids(its)); return its_alloc_table_entry(its, baser, dev_id); } @@ -2506,6 +3344,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id) static bool its_alloc_vpe_table(u32 vpe_id) { struct its_node *its; + int cpu; /* * Make sure the L2 tables are allocated on *all* v4 ITSs. We @@ -2517,7 +3356,7 @@ static bool its_alloc_vpe_table(u32 vpe_id) list_for_each_entry(its, &its_nodes, entry) { struct its_baser *baser; - if (!its->is_v4) + if (!is_v4(its)) continue; baser = its_get_baser(its, GITS_BASER_TYPE_VCPU); @@ -2528,6 +3367,19 @@ static bool its_alloc_vpe_table(u32 vpe_id) return false; } + /* Non v4.1? No need to iterate RDs and go back early. */ + if (!gic_rdists->has_rvpeid) + return true; + + /* + * Make sure the L2 tables are allocated for all copies of + * the L1 table on *all* v4.1 RDs. + */ + for_each_possible_cpu(cpu) { + if (!allocate_vpe_l2_table(cpu, vpe_id)) + return false; + } + return true; } @@ -2556,7 +3408,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, * sized as a power of two (and you need at least one bit...). */ nr_ites = max(2, nvecs); - sz = nr_ites * its->ite_size; + sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1); sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1; itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node); if (alloc_lpis) { @@ -2587,7 +3439,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, dev->event_map.col_map = col_map; dev->event_map.lpi_base = lpi_base; dev->event_map.nr_lpis = nr_lpis; - mutex_init(&dev->event_map.vlpi_lock); + raw_spin_lock_init(&dev->event_map.vlpi_lock); dev->device_id = dev_id; INIT_LIST_HEAD(&dev->entry); @@ -2608,6 +3460,7 @@ static void its_free_device(struct its_device *its_dev) raw_spin_lock_irqsave(&its_dev->its->lock, flags); list_del(&its_dev->entry); raw_spin_unlock_irqrestore(&its_dev->its->lock, flags); + kfree(its_dev->event_map.col_map); kfree(its_dev->itt); kfree(its_dev); } @@ -2811,7 +3664,6 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, its_lpi_free(its_dev->event_map.lpi_map, its_dev->event_map.lpi_base, its_dev->event_map.nr_lpis); - kfree(its_dev->event_map.col_map); /* Unmap device/itt */ its_send_mapd(its_dev, 0); @@ -2833,7 +3685,7 @@ static const struct irq_domain_ops its_domain_ops = { /* * This is insane. * - * If a GICv4 doesn't implement Direct LPIs (which is extremely + * If a GICv4.0 doesn't implement Direct LPIs (which is extremely * likely), the only way to perform an invalidate is to use a fake * device to issue an INV command, implying that the LPI has first * been mapped to some event on that device. Since this is not exactly @@ -2841,9 +3693,20 @@ static const struct irq_domain_ops its_domain_ops = { * only issue an UNMAP if we're short on available slots. * * Broken by design(tm). + * + * GICv4.1, on the other hand, mandates that we're able to invalidate + * by writing to a MMIO register. It doesn't implement the whole of + * DirectLPI, but that's good enough. And most of the time, we don't + * even have to invalidate anything, as the redistributor can be told + * whether to generate a doorbell or not (we thus leave it enabled, + * always). */ static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe) { + /* GICv4.1 doesn't use a proxy, so nothing to do here */ + if (gic_rdists->has_rvpeid) + return; + /* Already unmapped? */ if (vpe->vpe_proxy_event == -1) return; @@ -2866,6 +3729,10 @@ static void its_vpe_db_proxy_unmap_locked(struct its_vpe *vpe) static void its_vpe_db_proxy_unmap(struct its_vpe *vpe) { + /* GICv4.1 doesn't use a proxy, so nothing to do here */ + if (gic_rdists->has_rvpeid) + return; + if (!gic_rdists->has_direct_lpi) { unsigned long flags; @@ -2877,6 +3744,10 @@ static void its_vpe_db_proxy_unmap(struct its_vpe *vpe) static void its_vpe_db_proxy_map_locked(struct its_vpe *vpe) { + /* GICv4.1 doesn't use a proxy, so nothing to do here */ + if (gic_rdists->has_rvpeid) + return; + /* Already mapped? */ if (vpe->vpe_proxy_event != -1) return; @@ -2899,13 +3770,16 @@ static void its_vpe_db_proxy_move(struct its_vpe *vpe, int from, int to) unsigned long flags; struct its_collection *target_col; + /* GICv4.1 doesn't use a proxy, so nothing to do here */ + if (gic_rdists->has_rvpeid) + return; + if (gic_rdists->has_direct_lpi) { void __iomem *rdbase; rdbase = per_cpu_ptr(gic_rdists->rdist, from)->rd_base; gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR); - while (gic_read_lpir(rdbase + GICR_SYNCR) & 1) - cpu_relax(); + wait_for_syncr(rdbase); return; } @@ -2926,25 +3800,62 @@ static int its_vpe_set_affinity(struct irq_data *d, bool force) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); - int cpu = cpumask_first(mask_val); + struct cpumask common, *table_mask; + unsigned long flags; + int from, cpu; /* * Changing affinity is mega expensive, so let's be as lazy as * we can and only do it if we really have to. Also, if mapped * into the proxy device, we need to move the doorbell * interrupt to its new location. + * + * Another thing is that changing the affinity of a vPE affects + * *other interrupts* such as all the vLPIs that are routed to + * this vPE. This means that the irq_desc lock is not enough to + * protect us, and that we must ensure nobody samples vpe->col_idx + * during the update, hence the lock below which must also be + * taken on any vLPI handling path that evaluates vpe->col_idx. */ - if (vpe->col_idx != cpu) { - int from = vpe->col_idx; + from = vpe_to_cpuid_lock(vpe, &flags); + table_mask = gic_data_rdist_cpu(from)->vpe_table_mask; - vpe->col_idx = cpu; - its_send_vmovp(vpe); - its_vpe_db_proxy_move(vpe, from, cpu); - } + /* + * If we are offered another CPU in the same GICv4.1 ITS + * affinity, pick this one. Otherwise, any CPU will do. + */ + if (table_mask && cpumask_and(&common, mask_val, table_mask)) + cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common); + else + cpu = cpumask_first(mask_val); + + if (from == cpu) + goto out; + + vpe->col_idx = cpu; + + its_send_vmovp(vpe); + its_vpe_db_proxy_move(vpe, from, cpu); + +out: + irq_data_update_effective_affinity(d, cpumask_of(cpu)); + vpe_to_cpuid_unlock(vpe, flags); + + return IRQ_SET_MASK_OK_DONE; +} + +static void its_wait_vpt_parse_complete(void) +{ + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + u64 val; - irq_data_update_effective_affinity(d, cpumask_of(cpu)); + if (!gic_rdists->has_vpend_valid_dirty) + return; - return IRQ_SET_MASK_OK_DONE; + WARN_ON_ONCE(readq_relaxed_poll_timeout_atomic(vlpi_base + GICR_VPENDBASER, + val, + !(val & GICR_VPENDBASER_Dirty), + 10, 500)); } static void its_vpe_schedule(struct its_vpe *vpe) @@ -2958,12 +3869,12 @@ static void its_vpe_schedule(struct its_vpe *vpe) val |= (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; val |= GICR_VPROPBASER_RaWb; val |= GICR_VPROPBASER_InnerShareable; - gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + gicr_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); val = virt_to_phys(page_address(vpe->vpt_page)) & GENMASK_ULL(51, 16); val |= GICR_VPENDBASER_RaWaWb; - val |= GICR_VPENDBASER_NonShareable; + val |= GICR_VPENDBASER_InnerShareable; /* * There is no good way of finding out if the pending table is * empty as we can race against the doorbell interrupt very @@ -2976,7 +3887,7 @@ static void its_vpe_schedule(struct its_vpe *vpe) val |= GICR_VPENDBASER_PendingLast; val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0; val |= GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); } static void its_vpe_deschedule(struct its_vpe *vpe) @@ -2984,16 +3895,10 @@ static void its_vpe_deschedule(struct its_vpe *vpe) void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); u64 val; - val = its_clear_vpend_valid(vlpi_base); + val = its_clear_vpend_valid(vlpi_base, 0, 0); - if (unlikely(val & GICR_VPENDBASER_Dirty)) { - pr_err_ratelimited("ITS virtual pending table not cleaning\n"); - vpe->idai = false; - vpe->pending_last = true; - } else { - vpe->idai = !!(val & GICR_VPENDBASER_IDAI); - vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast); - } + vpe->idai = !!(val & GICR_VPENDBASER_IDAI); + vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast); } static void its_vpe_invall(struct its_vpe *vpe) @@ -3001,7 +3906,7 @@ static void its_vpe_invall(struct its_vpe *vpe) struct its_node *its; list_for_each_entry(its, &its_nodes, entry) { - if (!its->is_v4) + if (!is_v4(its)) continue; if (its_list_map && !vpe->its_vm->vlpi_count[its->list_nr]) @@ -3030,6 +3935,10 @@ static int its_vpe_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) its_vpe_deschedule(vpe); return 0; + case COMMIT_VPE: + its_wait_vpt_parse_complete(); + return 0; + case INVALL_VPE: its_vpe_invall(vpe); return 0; @@ -3056,16 +3965,10 @@ static void its_vpe_send_inv(struct irq_data *d) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); - if (gic_rdists->has_direct_lpi) { - void __iomem *rdbase; - - rdbase = per_cpu_ptr(gic_rdists->rdist, vpe->col_idx)->rd_base; - gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_INVLPIR); - while (gic_read_lpir(rdbase + GICR_SYNCR) & 1) - cpu_relax(); - } else { + if (gic_rdists->has_direct_lpi) + __direct_lpi_inv(d, d->parent_data->hwirq); + else its_vpe_send_cmd(vpe, its_send_inv); - } } static void its_vpe_mask_irq(struct irq_data *d) @@ -3104,8 +4007,7 @@ static int its_vpe_set_irqchip_state(struct irq_data *d, gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_SETLPIR); } else { gic_write_lpir(vpe->vpe_db_lpi, rdbase + GICR_CLRLPIR); - while (gic_read_lpir(rdbase + GICR_SYNCR) & 1) - cpu_relax(); + wait_for_syncr(rdbase); } } else { if (state) @@ -3133,6 +4035,375 @@ static struct irq_chip its_vpe_irq_chip = { .irq_set_vcpu_affinity = its_vpe_set_vcpu_affinity, }; +static struct its_node *find_4_1_its(void) +{ + static struct its_node *its = NULL; + + if (!its) { + list_for_each_entry(its, &its_nodes, entry) { + if (is_v4_1(its)) + return its; + } + + /* Oops? */ + its = NULL; + } + + return its; +} + +static void its_vpe_4_1_send_inv(struct irq_data *d) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + struct its_node *its; + + /* + * GICv4.1 wants doorbells to be invalidated using the + * INVDB command in order to be broadcast to all RDs. Send + * it to the first valid ITS, and let the HW do its magic. + */ + its = find_4_1_its(); + if (its) + its_send_invdb(its, vpe); +} + +static void its_vpe_4_1_mask_irq(struct irq_data *d) +{ + lpi_write_config(d->parent_data, LPI_PROP_ENABLED, 0); + its_vpe_4_1_send_inv(d); +} + +static void its_vpe_4_1_unmask_irq(struct irq_data *d) +{ + lpi_write_config(d->parent_data, 0, LPI_PROP_ENABLED); + its_vpe_4_1_send_inv(d); +} + +static void its_vpe_4_1_schedule(struct its_vpe *vpe, + struct its_cmd_info *info) +{ + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + u64 val = 0; + + /* Schedule the VPE */ + val |= GICR_VPENDBASER_Valid; + val |= info->g0en ? GICR_VPENDBASER_4_1_VGRP0EN : 0; + val |= info->g1en ? GICR_VPENDBASER_4_1_VGRP1EN : 0; + val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id); + + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); +} + +static void its_vpe_4_1_deschedule(struct its_vpe *vpe, + struct its_cmd_info *info) +{ + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + u64 val; + + if (info->req_db) { + unsigned long flags; + + /* + * vPE is going to block: make the vPE non-resident with + * PendingLast clear and DB set. The GIC guarantees that if + * we read-back PendingLast clear, then a doorbell will be + * delivered when an interrupt comes. + * + * Note the locking to deal with the concurrent update of + * pending_last from the doorbell interrupt handler that can + * run concurrently. + */ + raw_spin_lock_irqsave(&vpe->vpe_lock, flags); + val = its_clear_vpend_valid(vlpi_base, + GICR_VPENDBASER_PendingLast, + GICR_VPENDBASER_4_1_DB); + vpe->pending_last = !!(val & GICR_VPENDBASER_PendingLast); + raw_spin_unlock_irqrestore(&vpe->vpe_lock, flags); + } else { + /* + * We're not blocking, so just make the vPE non-resident + * with PendingLast set, indicating that we'll be back. + */ + val = its_clear_vpend_valid(vlpi_base, + 0, + GICR_VPENDBASER_PendingLast); + vpe->pending_last = true; + } +} + +static void its_vpe_4_1_invall(struct its_vpe *vpe) +{ + void __iomem *rdbase; + unsigned long flags; + u64 val; + int cpu; + + val = GICR_INVALLR_V; + val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id); + + /* Target the redistributor this vPE is currently known on */ + cpu = vpe_to_cpuid_lock(vpe, &flags); + raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock); + rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base; + gic_write_lpir(val, rdbase + GICR_INVALLR); + + wait_for_syncr(rdbase); + raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock); + vpe_to_cpuid_unlock(vpe, flags); +} + +static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + struct its_cmd_info *info = vcpu_info; + + switch (info->cmd_type) { + case SCHEDULE_VPE: + its_vpe_4_1_schedule(vpe, info); + return 0; + + case DESCHEDULE_VPE: + its_vpe_4_1_deschedule(vpe, info); + return 0; + + case COMMIT_VPE: + its_wait_vpt_parse_complete(); + return 0; + + case INVALL_VPE: + its_vpe_4_1_invall(vpe); + return 0; + + default: + return -EINVAL; + } +} + +static struct irq_chip its_vpe_4_1_irq_chip = { + .name = "GICv4.1-vpe", + .irq_mask = its_vpe_4_1_mask_irq, + .irq_unmask = its_vpe_4_1_unmask_irq, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = its_vpe_set_affinity, + .irq_set_vcpu_affinity = its_vpe_4_1_set_vcpu_affinity, +}; + +static void its_configure_sgi(struct irq_data *d, bool clear) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + struct its_cmd_desc desc; + + desc.its_vsgi_cmd.vpe = vpe; + desc.its_vsgi_cmd.sgi = d->hwirq; + desc.its_vsgi_cmd.priority = vpe->sgi_config[d->hwirq].priority; + desc.its_vsgi_cmd.enable = vpe->sgi_config[d->hwirq].enabled; + desc.its_vsgi_cmd.group = vpe->sgi_config[d->hwirq].group; + desc.its_vsgi_cmd.clear = clear; + + /* + * GICv4.1 allows us to send VSGI commands to any ITS as long as the + * destination VPE is mapped there. Since we map them eagerly at + * activation time, we're pretty sure the first GICv4.1 ITS will do. + */ + its_send_single_vcommand(find_4_1_its(), its_build_vsgi_cmd, &desc); +} + +static void its_sgi_mask_irq(struct irq_data *d) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + + vpe->sgi_config[d->hwirq].enabled = false; + its_configure_sgi(d, false); +} + +static void its_sgi_unmask_irq(struct irq_data *d) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + + vpe->sgi_config[d->hwirq].enabled = true; + its_configure_sgi(d, false); +} + +static int its_sgi_set_affinity(struct irq_data *d, + const struct cpumask *mask_val, + bool force) +{ + /* + * There is no notion of affinity for virtual SGIs, at least + * not on the host (since they can only be targetting a vPE). + * Tell the kernel we've done whatever it asked for. + */ + irq_data_update_effective_affinity(d, mask_val); + return IRQ_SET_MASK_OK; +} + +static int its_sgi_set_irqchip_state(struct irq_data *d, + enum irqchip_irq_state which, + bool state) +{ + if (which != IRQCHIP_STATE_PENDING) + return -EINVAL; + + if (state) { + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + struct its_node *its = find_4_1_its(); + u64 val; + + val = FIELD_PREP(GITS_SGIR_VPEID, vpe->vpe_id); + val |= FIELD_PREP(GITS_SGIR_VINTID, d->hwirq); + writeq_relaxed(val, its->sgir_base + GITS_SGIR - SZ_128K); + } else { + its_configure_sgi(d, true); + } + + return 0; +} + +static int its_sgi_get_irqchip_state(struct irq_data *d, + enum irqchip_irq_state which, bool *val) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + void __iomem *base; + unsigned long flags; + u32 count = 1000000; /* 1s! */ + u32 status; + int cpu; + + if (which != IRQCHIP_STATE_PENDING) + return -EINVAL; + + /* + * Locking galore! We can race against two different events: + * + * - Concurent vPE affinity change: we must make sure it cannot + * happen, or we'll talk to the wrong redistributor. This is + * identical to what happens with vLPIs. + * + * - Concurrent VSGIPENDR access: As it involves accessing two + * MMIO registers, this must be made atomic one way or another. + */ + cpu = vpe_to_cpuid_lock(vpe, &flags); + raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock); + base = gic_data_rdist_cpu(cpu)->rd_base + SZ_128K; + writel_relaxed(vpe->vpe_id, base + GICR_VSGIR); + do { + status = readl_relaxed(base + GICR_VSGIPENDR); + if (!(status & GICR_VSGIPENDR_BUSY)) + goto out; + + count--; + if (!count) { + pr_err_ratelimited("Unable to get SGI status\n"); + goto out; + } + cpu_relax(); + udelay(1); + } while (count); + +out: + raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock); + vpe_to_cpuid_unlock(vpe, flags); + + if (!count) + return -ENXIO; + + *val = !!(status & (1 << d->hwirq)); + + return 0; +} + +static int its_sgi_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + struct its_cmd_info *info = vcpu_info; + + switch (info->cmd_type) { + case PROP_UPDATE_VSGI: + vpe->sgi_config[d->hwirq].priority = info->priority; + vpe->sgi_config[d->hwirq].group = info->group; + its_configure_sgi(d, false); + return 0; + + default: + return -EINVAL; + } +} + +static struct irq_chip its_sgi_irq_chip = { + .name = "GICv4.1-sgi", + .irq_mask = its_sgi_mask_irq, + .irq_unmask = its_sgi_unmask_irq, + .irq_set_affinity = its_sgi_set_affinity, + .irq_set_irqchip_state = its_sgi_set_irqchip_state, + .irq_get_irqchip_state = its_sgi_get_irqchip_state, + .irq_set_vcpu_affinity = its_sgi_set_vcpu_affinity, +}; + +static int its_sgi_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct its_vpe *vpe = args; + int i; + + /* Yes, we do want 16 SGIs */ + WARN_ON(nr_irqs != 16); + + for (i = 0; i < 16; i++) { + vpe->sgi_config[i].priority = 0; + vpe->sgi_config[i].enabled = false; + vpe->sgi_config[i].group = false; + + irq_domain_set_hwirq_and_chip(domain, virq + i, i, + &its_sgi_irq_chip, vpe); + irq_set_status_flags(virq + i, IRQ_DISABLE_UNLAZY); + } + + return 0; +} + +static void its_sgi_irq_domain_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs) +{ + /* Nothing to do */ +} + +static int its_sgi_irq_domain_activate(struct irq_domain *domain, + struct irq_data *d, bool reserve) +{ + /* Write out the initial SGI configuration */ + its_configure_sgi(d, false); + return 0; +} + +static void its_sgi_irq_domain_deactivate(struct irq_domain *domain, + struct irq_data *d) +{ + struct its_vpe *vpe = irq_data_get_irq_chip_data(d); + + /* + * The VSGI command is awkward: + * + * - To change the configuration, CLEAR must be set to false, + * leaving the pending bit unchanged. + * - To clear the pending bit, CLEAR must be set to true, leaving + * the configuration unchanged. + * + * You just can't do both at once, hence the two commands below. + */ + vpe->sgi_config[d->hwirq].enabled = false; + its_configure_sgi(d, false); + its_configure_sgi(d, true); +} + +static const struct irq_domain_ops its_sgi_domain_ops = { + .alloc = its_sgi_irq_domain_alloc, + .free = its_sgi_irq_domain_free, + .activate = its_sgi_irq_domain_activate, + .deactivate = its_sgi_irq_domain_deactivate, +}; + static int its_vpe_id_alloc(void) { return ida_simple_get(&its_vpeid_ida, 0, ITS_MAX_VPEID, GFP_KERNEL); @@ -3166,9 +4437,13 @@ static int its_vpe_init(struct its_vpe *vpe) return -ENOMEM; } + raw_spin_lock_init(&vpe->vpe_lock); vpe->vpe_id = vpe_id; vpe->vpt_page = vpt_page; - vpe->vpe_proxy_event = -1; + if (gic_rdists->has_rvpeid) + atomic_set(&vpe->vmapp_count, 0); + else + vpe->vpe_proxy_event = -1; return 0; } @@ -3210,6 +4485,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain, static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *args) { + struct irq_chip *irqchip = &its_vpe_irq_chip; struct its_vm *vm = args; unsigned long *bitmap; struct page *vprop_page; @@ -3237,6 +4513,9 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq vm->nr_db_lpis = nr_ids; vm->vprop_page = vprop_page; + if (gic_rdists->has_rvpeid) + irqchip = &its_vpe_4_1_irq_chip; + for (i = 0; i < nr_irqs; i++) { vm->vpes[i]->vpe_db_lpi = base + i; err = its_vpe_init(vm->vpes[i]); @@ -3247,7 +4526,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq if (err) break; irq_domain_set_hwirq_and_chip(domain, virq + i, i, - &its_vpe_irq_chip, vm->vpes[i]); + irqchip, vm->vpes[i]); set_bit(i, bitmap); } @@ -3263,15 +4542,19 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain, struct its_vpe *vpe = irq_data_get_irq_chip_data(d); struct its_node *its; - /* If we use the list map, we issue VMAPP on demand... */ - if (its_list_map) + /* + * If we use the list map, we issue VMAPP on demand... Unless + * we're on a GICv4.1 and we eagerly map the VPE on all ITSs + * so that VSGIs can work. + */ + if (!gic_requires_eager_mapping()) return 0; /* Map the VPE to the first possible CPU */ vpe->col_idx = cpumask_first(cpu_online_mask); list_for_each_entry(its, &its_nodes, entry) { - if (!its->is_v4) + if (!is_v4(its)) continue; its_send_vmapp(its, vpe, true); @@ -3290,14 +4573,14 @@ static void its_vpe_irq_domain_deactivate(struct irq_domain *domain, struct its_node *its; /* - * If we use the list map, we unmap the VPE once no VLPIs are - * associated with the VM. + * If we use the list map on GICv4.0, we unmap the VPE once no + * VLPIs are associated with the VM. */ - if (its_list_map) + if (!gic_requires_eager_mapping()) return; list_for_each_entry(its, &its_nodes, entry) { - if (!its->is_v4) + if (!is_v4(its)) continue; its_send_vmapp(its, vpe, false); @@ -3348,8 +4631,9 @@ static bool __maybe_unused its_enable_quirk_cavium_22375(void *data) { struct its_node *its = data; - /* erratum 22375: only alloc 8MB table size */ - its->device_ids = 0x14; /* 20 bits, 8MB */ + /* erratum 22375: only alloc 8MB table size (20 bits) */ + its->typer &= ~GITS_TYPER_DEVBITS; + its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, 20 - 1); its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375; return true; @@ -3369,7 +4653,8 @@ static bool __maybe_unused its_enable_quirk_qdf2400_e0065(void *data) struct its_node *its = data; /* On QDF2400, the size of the ITE is 16Bytes */ - its->ite_size = 16; + its->typer &= ~GITS_TYPER_ITT_ENTRY_SIZE; + its->typer |= FIELD_PREP(GITS_TYPER_ITT_ENTRY_SIZE, 16 - 1); return true; } @@ -3403,8 +4688,10 @@ static bool __maybe_unused its_enable_quirk_socionext_synquacer(void *data) its->get_msi_base = its_irq_get_msi_base_pre_its; ids = ilog2(pre_its_window[1]) - 2; - if (its->device_ids > ids) - its->device_ids = ids; + if (device_ids(its) > ids) { + its->typer &= ~GITS_TYPER_DEVBITS; + its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, ids - 1); + } /* the pre-ITS breaks isolation, so disable MSI remapping */ its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP; @@ -3425,6 +4712,14 @@ static bool __maybe_unused its_enable_quirk_hip07_161600802(void *data) return true; } +static bool __maybe_unused its_enable_quirk_hip09_162100801(void *data) +{ + struct its_node *its = data; + + its->flags |= ITS_FLAGS_WORKAROUND_HISILICON_162100801; + return true; +} + static const struct gic_quirk its_quirks[] = { #ifdef CONFIG_CAVIUM_ERRATUM_22375 { @@ -3470,6 +4765,14 @@ static const struct gic_quirk its_quirks[] = { .mask = 0xffffffff, .init = its_enable_quirk_hip07_161600802, }, +#endif +#ifdef CONFIG_HISILICON_ERRATUM_162100801 + { + .desc = "ITS: Hip09 erratum 162100801", + .iidr = 0x00051736, + .mask = 0xffffffff, + .init = its_enable_quirk_hip09_162100801, + }, #endif { } @@ -3631,7 +4934,7 @@ static int its_init_vpe_domain(void) } /* Use the last possible DevID */ - devid = GENMASK(its->device_ids - 1, 0); + devid = GENMASK(device_ids(its) - 1, 0); vpe_proxy.dev = its_create_device(its, devid, entries, false); if (!vpe_proxy.dev) { kfree(vpe_proxy.vpes); @@ -3697,7 +5000,7 @@ static int __init its_probe_one(struct resource *res, struct page *page; int err; - its_base = ioremap(res->start, resource_size(res)); + its_base = ioremap(res->start, SZ_64K); if (!its_base) { pr_warn("ITS@%pa: Unable to map ITS registers\n", &res->start); return -ENOMEM; @@ -3729,12 +5032,10 @@ static int __init its_probe_one(struct resource *res, INIT_LIST_HEAD(&its->entry); INIT_LIST_HEAD(&its->its_device_list); typer = gic_read_typer(its_base + GITS_TYPER); + its->typer = typer; its->base = its_base; its->phys_base = res->start; - its->ite_size = GITS_TYPER_ITT_ENTRY_SIZE(typer); - its->device_ids = GITS_TYPER_DEVBITS(typer); - its->is_v4 = !!(typer & GITS_TYPER_VLPIS); - if (its->is_v4) { + if (is_v4(its)) { if (!(typer & GITS_TYPER_VMOVP)) { err = its_compute_its_list_map(res, its_base); if (err < 0) @@ -3747,6 +5048,21 @@ static int __init its_probe_one(struct resource *res, } else { pr_info("ITS@%pa: Single VMOVP capable\n", &res->start); } + + if (is_v4_1(its)) { + u32 svpet = FIELD_GET(GITS_TYPER_SVPET, typer); + + its->sgir_base = ioremap(res->start + SZ_128K, SZ_64K); + if (!its->sgir_base) { + err = -ENOMEM; + goto out_free_its; + } + + its->mpidr = readl_relaxed(its_base + GITS_MPIDR); + + pr_info("ITS@%pa: Using GICv4.1 mode %08x %08x\n", + &res->start, its->mpidr, svpet); + } } its->numa_node = numa_node; @@ -3755,7 +5071,7 @@ static int __init its_probe_one(struct resource *res, get_order(ITS_CMD_QUEUE_SZ)); if (!page) { err = -ENOMEM; - goto out_free_its; + goto out_unmap_sgir; } its->cmd_base = (void *)page_address(page); its->cmd_write = its->cmd_base; @@ -3801,7 +5117,7 @@ static int __init its_probe_one(struct resource *res, gits_write_cwriter(0, its->base + GITS_CWRITER); ctlr = readl_relaxed(its->base + GITS_CTLR); ctlr |= GITS_CTLR_ENABLE; - if (its->is_v4) + if (is_v4(its)) ctlr |= GITS_CTLR_ImDe; writel_relaxed(ctlr, its->base + GITS_CTLR); @@ -3819,6 +5135,9 @@ static int __init its_probe_one(struct resource *res, its_free_tables(its); out_free_cmd: free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ)); +out_unmap_sgir: + if (its->sgir_base) + iounmap(its->sgir_base); out_free_its: kfree(its); out_unmap: @@ -4102,8 +5421,11 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists, struct device_node *of_node; struct its_node *its; bool has_v4 = false; + bool has_v4_1 = false; int err; + gic_rdists = rdists; + its_parent = parent_domain; of_node = to_of_node(handle); if (of_node) @@ -4116,18 +5438,29 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists, return -ENXIO; } - gic_rdists = rdists; - err = allocate_lpi_tables(); if (err) return err; - list_for_each_entry(its, &its_nodes, entry) - has_v4 |= its->is_v4; + list_for_each_entry(its, &its_nodes, entry) { + has_v4 |= is_v4(its); + has_v4_1 |= is_v4_1(its); + } + + /* Don't bother with inconsistent systems */ + if (WARN_ON(!has_v4_1 && rdists->has_rvpeid)) + rdists->has_rvpeid = false; if (has_v4 & rdists->has_vlpis) { + const struct irq_domain_ops *sgi_ops; + + if (has_v4_1) + sgi_ops = &its_sgi_domain_ops; + else + sgi_ops = NULL; + if (its_init_vpe_domain() || - its_init_v4(parent_domain, &its_vpe_domain_ops)) { + its_init_v4(parent_domain, &its_vpe_domain_ops, sgi_ops)) { rdists->has_vlpis = false; pr_err("ITS: Disabling GICv4 support\n"); } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 77a130c03223808774801ab39dae5838bb2e1337..f7dcb6332f68e9a9047a06130f1fcc59c95a48c6 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -714,6 +714,7 @@ static void __init gic_dist_init(void) unsigned int i; u64 affinity; void __iomem *base = gic_data.dist_base; + u32 val; /* Disable the distributor */ writel_relaxed(0, base + GICD_CTLR); @@ -746,9 +747,14 @@ static void __init gic_dist_init(void) /* Now do the common stuff, and wait for the distributor to drain */ gic_dist_config(base, GIC_LINE_NR, gic_dist_wait_for_rwp); + val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1; + if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) { + pr_info("Enabling SGIs without active state\n"); + val |= GICD_CTLR_nASSGIreq; + } + /* Enable distributor with ARE, Group1 */ - writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1, - base + GICD_CTLR); + writel_relaxed(val, base + GICD_CTLR); /* * Set all global interrupts to the boot CPU only. ARE must be @@ -819,6 +825,7 @@ static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr) typer = gic_read_typer(ptr + GICR_TYPER); if ((typer >> 32) == aff) { u64 offset = ptr - region->redist_base; + raw_spin_lock_init(&gic_data_rdist()->rd_lock); gic_data_rdist_rd_base() = ptr; gic_data_rdist()->phys_base = region->phys_base + offset; @@ -849,8 +856,38 @@ static int __gic_update_rdist_properties(struct redist_region *region, void __iomem *ptr) { u64 typer = gic_read_typer(ptr + GICR_TYPER); + + /* Boot-time cleanip */ + if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) { + u64 val; + + /* Deactivate any present vPE */ + val = gicr_read_vpendbaser(ptr + SZ_128K + GICR_VPENDBASER); + if (val & GICR_VPENDBASER_Valid) + gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast, + ptr + SZ_128K + GICR_VPENDBASER); + + /* Mark the VPE table as invalid */ + val = gicr_read_vpropbaser(ptr + SZ_128K + GICR_VPROPBASER); + val &= ~GICR_VPROPBASER_4_1_VALID; + gicr_write_vpropbaser(val, ptr + SZ_128K + GICR_VPROPBASER); + } + gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS); - gic_data.rdists.has_direct_lpi &= !!(typer & GICR_TYPER_DirectLPIS); + + /* RVPEID implies some form of DirectLPI, no matter what the doc says... :-/ */ + gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID); + gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) | + gic_data.rdists.has_rvpeid); + gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY); + + /* Detect non-sensical configurations */ + if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) { + gic_data.rdists.has_direct_lpi = false; + gic_data.rdists.has_vlpis = false; + gic_data.rdists.has_rvpeid = false; + } + gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr); return 1; @@ -863,9 +900,11 @@ static void gic_update_rdist_properties(void) if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; pr_info("%d PPIs implemented\n", gic_data.ppi_nr); - pr_info("%sVLPI support, %sdirect LPI support\n", - !gic_data.rdists.has_vlpis ? "no " : "", - !gic_data.rdists.has_direct_lpi ? "no " : ""); + if (gic_data.rdists.has_vlpis) + pr_info("GICv4 features: %s%s%s\n", + gic_data.rdists.has_direct_lpi ? "DirectLPI " : "", + gic_data.rdists.has_rvpeid ? "RVPEID " : "", + gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : ""); } /* Check whether it's single security state view */ @@ -1542,18 +1581,24 @@ static int __init gic_init_bases(void __iomem *dist_base, pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32); pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR); + + gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); + gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, &gic_data); - irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist)); + gic_data.rdists.has_rvpeid = true; gic_data.rdists.has_vlpis = true; gic_data.rdists.has_direct_lpi = true; + gic_data.rdists.has_vpend_valid_dirty = true; if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { err = -ENOMEM; goto out_free; } + irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); + gic_data.has_rss = !!(typer & GICD_TYPER_RSS); pr_info("Distributor has %sRange Selector support\n", gic_data.has_rss ? "" : "no "); @@ -1722,6 +1767,7 @@ static void __init gic_of_setup_kvm_info(struct device_node *node) gic_v3_kvm_info.vcpu = r; gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; + gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; gic_set_kvm_info(&gic_v3_kvm_info); } @@ -2037,6 +2083,7 @@ static void __init gic_acpi_setup_kvm_info(void) } gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; + gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; gic_set_kvm_info(&gic_v3_kvm_info); } diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c index 563e87ed07668067276d039cbb9b1060eddf22d6..4ea71b28f9f5f21ec0c8979bd91f07bf215c75cf 100644 --- a/drivers/irqchip/irq-gic-v4.c +++ b/drivers/irqchip/irq-gic-v4.c @@ -85,6 +85,76 @@ static struct irq_domain *gic_domain; static const struct irq_domain_ops *vpe_domain_ops; +static const struct irq_domain_ops *sgi_domain_ops; + +#ifdef CONFIG_ARM64 +#include + +bool gic_cpuif_has_vsgi(void) +{ + unsigned long fld, reg = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + + fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64PFR0_GIC_SHIFT); + + return fld >= 0x3; +} +#else +bool gic_cpuif_has_vsgi(void) +{ + return false; +} +#endif + +static bool has_v4_1(void) +{ + return !!sgi_domain_ops; +} + +static bool has_v4_1_sgi(void) +{ + return has_v4_1() && gic_cpuif_has_vsgi(); +} + +static int its_alloc_vcpu_sgis(struct its_vpe *vpe, int idx) +{ + char *name; + int sgi_base; + + if (!has_v4_1_sgi()) + return 0; + + name = kasprintf(GFP_KERNEL, "GICv4-sgi-%d", task_pid_nr(current)); + if (!name) + goto err; + + vpe->fwnode = irq_domain_alloc_named_id_fwnode(name, idx); + if (!vpe->fwnode) + goto err; + + kfree(name); + name = NULL; + + vpe->sgi_domain = irq_domain_create_linear(vpe->fwnode, 16, + sgi_domain_ops, vpe); + if (!vpe->sgi_domain) + goto err; + + sgi_base = __irq_domain_alloc_irqs(vpe->sgi_domain, -1, 16, + NUMA_NO_NODE, vpe, + false, NULL); + if (sgi_base <= 0) + goto err; + + return 0; + +err: + if (vpe->sgi_domain) + irq_domain_remove(vpe->sgi_domain); + if (vpe->fwnode) + irq_domain_free_fwnode(vpe->fwnode); + kfree(name); + return -ENOMEM; +} int its_alloc_vcpu_irqs(struct its_vm *vm) { @@ -112,8 +182,13 @@ int its_alloc_vcpu_irqs(struct its_vm *vm) if (vpe_base_irq <= 0) goto err; - for (i = 0; i < vm->nr_vpes; i++) + for (i = 0; i < vm->nr_vpes; i++) { + int ret; vm->vpes[i]->irq = vpe_base_irq + i; + ret = its_alloc_vcpu_sgis(vm->vpes[i], i); + if (ret) + goto err; + } return 0; @@ -126,8 +201,28 @@ int its_alloc_vcpu_irqs(struct its_vm *vm) return -ENOMEM; } +static void its_free_sgi_irqs(struct its_vm *vm) +{ + int i; + + if (!has_v4_1_sgi()) + return; + + for (i = 0; i < vm->nr_vpes; i++) { + unsigned int irq = irq_find_mapping(vm->vpes[i]->sgi_domain, 0); + + if (WARN_ON(!irq)) + continue; + + irq_domain_free_irqs(irq, 16); + irq_domain_remove(vm->vpes[i]->sgi_domain); + irq_domain_free_fwnode(vm->vpes[i]->fwnode); + } +} + void its_free_vcpu_irqs(struct its_vm *vm) { + its_free_sgi_irqs(vm); irq_domain_free_irqs(vm->vpes[0]->irq, vm->nr_vpes); irq_domain_remove(vm->domain); irq_domain_free_fwnode(vm->fwnode); @@ -138,17 +233,73 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info) return irq_set_vcpu_affinity(vpe->irq, info); } -int its_schedule_vpe(struct its_vpe *vpe, bool on) +int its_make_vpe_non_resident(struct its_vpe *vpe, bool db) { - struct its_cmd_info info; + struct irq_desc *desc = irq_to_desc(vpe->irq); + struct its_cmd_info info = { }; + int ret; WARN_ON(preemptible()); - info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE; + info.cmd_type = DESCHEDULE_VPE; + if (has_v4_1()) { + /* GICv4.1 can directly deal with doorbells */ + info.req_db = db; + } else { + /* Undo the nested disable_irq() calls... */ + while (db && irqd_irq_disabled(&desc->irq_data)) + enable_irq(vpe->irq); + } - return its_send_vpe_cmd(vpe, &info); + ret = its_send_vpe_cmd(vpe, &info); + if (!ret) + vpe->resident = false; + + vpe->ready = false; + + return ret; } +int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en) +{ + struct its_cmd_info info = { }; + int ret; + + WARN_ON(preemptible()); + + info.cmd_type = SCHEDULE_VPE; + if (has_v4_1()) { + info.g0en = g0en; + info.g1en = g1en; + } else { + /* Disabled the doorbell, as we're about to enter the guest */ + disable_irq_nosync(vpe->irq); + } + + ret = its_send_vpe_cmd(vpe, &info); + if (!ret) + vpe->resident = true; + + return ret; +} + +int its_commit_vpe(struct its_vpe *vpe) +{ + struct its_cmd_info info = { + .cmd_type = COMMIT_VPE, + }; + int ret; + + WARN_ON(preemptible()); + + ret = its_send_vpe_cmd(vpe, &info); + if (!ret) + vpe->ready = true; + + return ret; +} + + int its_invall_vpe(struct its_vpe *vpe) { struct its_cmd_info info = { @@ -211,12 +362,28 @@ int its_prop_update_vlpi(int irq, u8 config, bool inv) return irq_set_vcpu_affinity(irq, &info); } -int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops) +int its_prop_update_vsgi(int irq, u8 priority, bool group) +{ + struct its_cmd_info info = { + .cmd_type = PROP_UPDATE_VSGI, + { + .priority = priority, + .group = group, + }, + }; + + return irq_set_vcpu_affinity(irq, &info); +} + +int its_init_v4(struct irq_domain *domain, + const struct irq_domain_ops *vpe_ops, + const struct irq_domain_ops *sgi_ops) { if (domain) { pr_info("ITS: Enabling GICv4 support\n"); gic_domain = domain; - vpe_domain_ops = ops; + vpe_domain_ops = vpe_ops; + sgi_domain_ops = sgi_ops; return 0; } diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index af4f09c02bf1c6e9936f5ca52537c13c1cd8c934..39d3d849d9264ac21690c390b3436d07b0ca0df0 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -70,6 +70,7 @@ struct vgic_global { /* Hardware has GICv4? */ bool has_gicv4; + bool has_gicv4_1; /* GIC system register CPU interface */ struct static_key_false gicv3_cpuif; @@ -230,6 +231,9 @@ struct vgic_dist { /* distributor enabled */ bool enabled; + /* Wants SGIs without active state */ + bool nassgireq; + struct vgic_irq *spis; struct vgic_io_device dist_iodev; @@ -240,7 +244,7 @@ struct vgic_dist { * Contains the attributes and gpa of the LPI configuration table. * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share * one address across all redistributors. - * GICv3 spec: 6.1.2 "LPI Configuration tables" + * GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables" */ u64 propbaser; @@ -396,7 +400,8 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq, int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); -void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu); -void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu); +int vgic_v4_load(struct kvm_vcpu *vcpu); +void vgic_v4_commit(struct kvm_vcpu *vcpu); +int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db); #endif /* __KVM_ARM_VGIC_H */ diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index b9850f5f1906a2539df8c4c49737dba12248eecf..fa8c0455c3523316e00a6eaaaed4bf4347ccdb42 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -32,6 +32,8 @@ struct gic_kvm_info { struct resource vctrl; /* vlpi support */ bool has_v4; + /* rvpeid support */ + bool has_v4_1; }; const struct gic_kvm_info *gic_get_kvm_info(void); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 5cc10cf7cb3e6f74fe73bf6d0497ef4ca9ce4ad5..58050837b1109398765f9f40aa4ce8c985677dad 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -13,6 +13,7 @@ #define GICD_CTLR 0x0000 #define GICD_TYPER 0x0004 #define GICD_IIDR 0x0008 +#define GICD_TYPER2 0x000C #define GICD_STATUSR 0x0010 #define GICD_SETSPI_NSR 0x0040 #define GICD_CLRSPI_NSR 0x0048 @@ -56,6 +57,7 @@ #define GICD_SPENDSGIR 0x0F20 #define GICD_CTLR_RWP (1U << 31) +#define GICD_CTLR_nASSGIreq (1U << 8) #define GICD_CTLR_DS (1U << 6) #define GICD_CTLR_ARE_NS (1U << 4) #define GICD_CTLR_ENABLE_G1A (1U << 1) @@ -89,6 +91,10 @@ #define GICD_TYPER_ESPIS(typer) \ (((typer) & GICD_TYPER_ESPI) ? GICD_TYPER_SPIS((typer) >> 27) : 0) +#define GICD_TYPER2_nASSGIcap (1U << 8) +#define GICD_TYPER2_VIL (1U << 7) +#define GICD_TYPER2_VID GENMASK(4, 0) + #define GICD_IROUTER_SPI_MODE_ONE (0U << 31) #define GICD_IROUTER_SPI_MODE_ANY (1U << 31) @@ -98,6 +104,11 @@ #define GIC_V3_DIST_SIZE 0x10000 +#define GIC_PAGE_SIZE_4K 0ULL +#define GIC_PAGE_SIZE_16K 1ULL +#define GIC_PAGE_SIZE_64K 2ULL +#define GIC_PAGE_SIZE_MASK 3ULL + /* * Re-Distributor registers, offsets from RD_base */ @@ -232,8 +243,19 @@ #define GICR_TYPER_PLPIS (1U << 0) #define GICR_TYPER_VLPIS (1U << 1) +#define GICR_TYPER_DIRTY (1U << 2) #define GICR_TYPER_DirectLPIS (1U << 3) #define GICR_TYPER_LAST (1U << 4) +#define GICR_TYPER_RVPEID (1U << 7) +#define GICR_TYPER_COMMON_LPI_AFF GENMASK_ULL(25, 24) +#define GICR_TYPER_AFFINITY GENMASK_ULL(63, 32) + +#define GICR_INVLPIR_INTID GENMASK_ULL(31, 0) +#define GICR_INVLPIR_VPEID GENMASK_ULL(47, 32) +#define GICR_INVLPIR_V GENMASK_ULL(63, 63) + +#define GICR_INVALLR_VPEID GICR_INVLPIR_VPEID +#define GICR_INVALLR_V GICR_INVLPIR_V #define GIC_V3_REDIST_SIZE 0x20000 @@ -272,6 +294,18 @@ #define GICR_VPROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt) #define GICR_VPROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb) +/* + * GICv4.1 VPROPBASER reinvention. A subtle mix between the old + * VPROPBASER and ITS_BASER. Just not quite any of the two. + */ +#define GICR_VPROPBASER_4_1_VALID (1ULL << 63) +#define GICR_VPROPBASER_4_1_ENTRY_SIZE GENMASK_ULL(61, 59) +#define GICR_VPROPBASER_4_1_INDIRECT (1ULL << 55) +#define GICR_VPROPBASER_4_1_PAGE_SIZE GENMASK_ULL(54, 53) +#define GICR_VPROPBASER_4_1_Z (1ULL << 52) +#define GICR_VPROPBASER_4_1_ADDR GENMASK_ULL(51, 12) +#define GICR_VPROPBASER_4_1_SIZE GENMASK_ULL(6, 0) + #define GICR_VPENDBASER 0x0078 #define GICR_VPENDBASER_SHAREABILITY_SHIFT (10) @@ -289,6 +323,9 @@ #define GICR_VPENDBASER_NonShareable \ GIC_BASER_SHAREABILITY(GICR_VPENDBASER, NonShareable) +#define GICR_VPENDBASER_InnerShareable \ + GIC_BASER_SHAREABILITY(GICR_VPENDBASER, InnerShareable) + #define GICR_VPENDBASER_nCnB GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nCnB) #define GICR_VPENDBASER_nC GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nC) #define GICR_VPENDBASER_RaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt) @@ -303,12 +340,31 @@ #define GICR_VPENDBASER_IDAI (1ULL << 62) #define GICR_VPENDBASER_Valid (1ULL << 63) +/* + * GICv4.1 VPENDBASER, used for VPE residency. On top of these fields, + * also use the above Valid, PendingLast and Dirty. + */ +#define GICR_VPENDBASER_4_1_DB (1ULL << 62) +#define GICR_VPENDBASER_4_1_VGRP0EN (1ULL << 59) +#define GICR_VPENDBASER_4_1_VGRP1EN (1ULL << 58) +#define GICR_VPENDBASER_4_1_VPEID GENMASK_ULL(15, 0) + +#define GICR_VSGIR 0x0080 + +#define GICR_VSGIR_VPEID GENMASK(15, 0) + +#define GICR_VSGIPENDR 0x0088 + +#define GICR_VSGIPENDR_BUSY (1U << 31) +#define GICR_VSGIPENDR_PENDING GENMASK(15, 0) + /* * ITS registers, offsets from ITS_base */ #define GITS_CTLR 0x0000 #define GITS_IIDR 0x0004 #define GITS_TYPER 0x0008 +#define GITS_MPIDR 0x0018 #define GITS_CBASER 0x0080 #define GITS_CWRITER 0x0088 #define GITS_CREADR 0x0090 @@ -325,6 +381,11 @@ #define GITS_TRANSLATER 0x10040 +#define GITS_SGIR 0x20020 + +#define GITS_SGIR_VPEID GENMASK_ULL(47, 32) +#define GITS_SGIR_VINTID GENMASK_ULL(3, 0) + #define GITS_CTLR_ENABLE (1U << 0) #define GITS_CTLR_ImDe (1U << 1) #define GITS_CTLR_ITS_NUMBER_SHIFT 4 @@ -334,14 +395,16 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 -#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_DEVBITS GENMASK_ULL(17, 13) #define GITS_TYPER_PTA (1UL << 19) #define GITS_TYPER_HCC_SHIFT 24 #define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & 0xff) #define GITS_TYPER_VMOVP (1ULL << 37) +#define GITS_TYPER_VMAPP (1ULL << 40) +#define GITS_TYPER_SVPET GENMASK_ULL(42, 41) #define GITS_IIDR_REV_SHIFT 12 #define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT) @@ -412,10 +475,11 @@ #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) #define GITS_BASER_PAGE_SIZE_SHIFT (8) -#define GITS_BASER_PAGE_SIZE_4K (0ULL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_16K (1ULL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_64K (2ULL << GITS_BASER_PAGE_SIZE_SHIFT) -#define GITS_BASER_PAGE_SIZE_MASK (3ULL << GITS_BASER_PAGE_SIZE_SHIFT) +#define __GITS_BASER_PSZ(sz) (GIC_PAGE_SIZE_ ## sz << GITS_BASER_PAGE_SIZE_SHIFT) +#define GITS_BASER_PAGE_SIZE_4K __GITS_BASER_PSZ(4K) +#define GITS_BASER_PAGE_SIZE_16K __GITS_BASER_PSZ(16K) +#define GITS_BASER_PAGE_SIZE_64K __GITS_BASER_PSZ(64K) +#define GITS_BASER_PAGE_SIZE_MASK __GITS_BASER_PSZ(MASK) #define GITS_BASER_PAGES_MAX 256 #define GITS_BASER_PAGES_SHIFT (0) #define GITS_BASER_NR_PAGES(r) (((r) & 0xff) + 1) @@ -456,8 +520,10 @@ #define GITS_CMD_VMAPTI GITS_CMD_GICv4(GITS_CMD_MAPTI) #define GITS_CMD_VMOVI GITS_CMD_GICv4(GITS_CMD_MOVI) #define GITS_CMD_VSYNC GITS_CMD_GICv4(GITS_CMD_SYNC) -/* VMOVP is the odd one, as it doesn't have a physical counterpart */ +/* VMOVP, VSGI and INVDB are the odd ones, as they dont have a physical counterpart */ #define GITS_CMD_VMOVP GITS_CMD_GICv4(2) +#define GITS_CMD_VSGI GITS_CMD_GICv4(3) +#define GITS_CMD_INVDB GITS_CMD_GICv4(0xe) /* * ITS error numbers @@ -603,17 +669,23 @@ struct rdists { struct { + raw_spinlock_t rd_lock; void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; bool lpi_enabled; + cpumask_t *vpe_table_mask; + void *vpe_l1_base; } __percpu *rdist; phys_addr_t prop_table_pa; void *prop_table_va; u64 flags; u32 gicd_typer; + u32 gicd_typer2; bool has_vlpis; + bool has_rvpeid; bool has_direct_lpi; + bool has_vpend_valid_dirty; }; struct irq_domain; diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index e6b155713b47e1df911db04a2394efe5b1b7b1b7..2c63375bbd43f41d3c5019ab4f4f3583196b522f 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -32,11 +32,41 @@ struct its_vm { struct its_vpe { struct page *vpt_page; struct its_vm *its_vm; + /* per-vPE VLPI tracking */ + atomic_t vlpi_count; /* Doorbell interrupt */ int irq; irq_hw_number_t vpe_db_lpi; - /* VPE proxy mapping */ - int vpe_proxy_event; + /* VPE resident */ + bool resident; + /* VPT parse complete */ + bool ready; + union { + /* GICv4.0 implementations */ + struct { + /* VPE proxy mapping */ + int vpe_proxy_event; + /* Implementation Defined Area Invalid */ + bool idai; + }; + /* GICv4.1 implementations */ + struct { + struct fwnode_handle *fwnode; + struct irq_domain *sgi_domain; + struct { + u8 priority; + bool enabled; + bool group; + } sgi_config[16]; + atomic_t vmapp_count; + }; + }; + + /* + * Ensures mutual exclusion between affinity setting of the + * vPE and vLPI operations using vpe->col_idx. + */ + raw_spinlock_t vpe_lock; /* * This collection ID is used to indirect the target * redistributor for this VPE. The ID itself isn't involved in @@ -45,8 +75,6 @@ struct its_vpe { u16 col_idx; /* Unique (system-wide) VPE identifier */ u16 vpe_id; - /* Implementation Defined Area Invalid */ - bool idai; /* Pending VLPIs on schedule out? */ bool pending_last; }; @@ -78,7 +106,9 @@ enum its_vcpu_info_cmd_type { PROP_UPDATE_AND_INV_VLPI, SCHEDULE_VPE, DESCHEDULE_VPE, + COMMIT_VPE, INVALL_VPE, + PROP_UPDATE_VSGI, }; struct its_cmd_info { @@ -86,19 +116,35 @@ struct its_cmd_info { union { struct its_vlpi_map *map; u8 config; + bool req_db; + struct { + bool g0en; + bool g1en; + }; + struct { + u8 priority; + bool group; + }; }; }; int its_alloc_vcpu_irqs(struct its_vm *vm); void its_free_vcpu_irqs(struct its_vm *vm); -int its_schedule_vpe(struct its_vpe *vpe, bool on); +int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en); +int its_make_vpe_non_resident(struct its_vpe *vpe, bool db); +int its_commit_vpe(struct its_vpe *vpe); int its_invall_vpe(struct its_vpe *vpe); int its_map_vlpi(int irq, struct its_vlpi_map *map); int its_get_vlpi(int irq, struct its_vlpi_map *map); int its_unmap_vlpi(int irq); int its_prop_update_vlpi(int irq, u8 config, bool inv); +int its_prop_update_vsgi(int irq, u8 priority, bool group); struct irq_domain_ops; -int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops); +int its_init_v4(struct irq_domain *domain, + const struct irq_domain_ops *vpe_ops, + const struct irq_domain_ops *sgi_ops); + +bool gic_cpuif_has_vsgi(void); #endif diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index f7150fbeeb55e32e3cddbec102518d47089f195a..6ddc7a6aa679e601d4fa179ae73c20637b8f833d 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -322,20 +322,24 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) /* * If we're about to block (most likely because we've just hit a * WFI), we need to sync back the state of the GIC CPU interface - * so that we have the lastest PMR and group enables. This ensures + * so that we have the latest PMR and group enables. This ensures * that kvm_arch_vcpu_runnable has up-to-date data to decide * whether we have pending interrupts. + * + * For the same reason, we want to tell GICv4 that we need + * doorbells to be signalled, should an interrupt become pending. */ preempt_disable(); kvm_vgic_vmcr_sync(vcpu); + vgic_v4_put(vcpu, true); preempt_enable(); - - kvm_vgic_v4_enable_doorbell(vcpu); } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - kvm_vgic_v4_disable_doorbell(vcpu); + preempt_disable(); + vgic_v4_load(vcpu); + preempt_enable(); } int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) @@ -398,9 +402,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vcpu_pmu_restore_guest(vcpu); if (single_task_running()) - vcpu_clear_wfe_traps(vcpu); + vcpu_clear_wfx_traps(vcpu); else - vcpu_set_wfe_traps(vcpu); + vcpu_set_wfx_traps(vcpu); if (vcpu_has_ptrauth(vcpu)) { struct kvm_cpu_context __maybe_unused *ctxt = vcpu->arch.host_cpu_context; @@ -673,6 +677,14 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu) * that a VCPU sees new virtual interrupts. */ kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu); + + if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { + /* The distributor enable bits were changed */ + preempt_disable(); + vgic_v4_put(vcpu, false); + vgic_v4_load(vcpu); + preempt_enable(); + } } } diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index cc12fe9b2df3fbe0f38f5fe080b9678717a2116b..b13a9e3f99ddc13efd1947da8effcd8259c5fef7 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -178,6 +178,8 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { char *type; + bool pending; + if (irq->intid < VGIC_NR_SGIS) type = "SGI"; else if (irq->intid < VGIC_NR_PRIVATE_IRQS) @@ -190,6 +192,16 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS) print_header(s, irq, vcpu); + pending = irq->pending_latch; + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &pending); + WARN_ON_ONCE(err); + } + seq_printf(s, " %s %4d " " %2d " "%d%d%d%d%d%d%d " @@ -201,7 +213,7 @@ static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, "\n", type, irq->intid, (irq->target_vcpu) ? irq->target_vcpu->vcpu_id : -1, - irq->pending_latch, + pending, irq->line_level, irq->active, irq->enabled, diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 68991015388906abbb612bed972b6c9c44feb31a..9127bf4332533b6431e069afe8d396a8d0636c88 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -204,6 +204,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) INIT_LIST_HEAD(&vgic_cpu->ap_list_head); raw_spin_lock_init(&vgic_cpu->ap_list_lock); + atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0); /* * Enable and configure all SGIs to be edge-triggered and diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index e06bb8ed7688a7141dfd96ed0567daad40a05523..a72f584254d088f8843dad7bbdbc11934b456de7 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -367,7 +367,10 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) if (ret) return ret; + if (map.vpe) + atomic_dec(&map.vpe->vlpi_count); map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + atomic_inc(&map.vpe->vlpi_count); ret = its_map_vlpi(irq->host_irq, &map); } @@ -843,9 +846,8 @@ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its, u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; - ite = find_ite(its, device_id, event_id); - if (ite && ite->collection) { + if (ite && its_is_collection_mapped(ite->collection)) { /* * Though the spec talks about removing the pending state, we * don't bother here since we clear the ITTE anyway and the diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index b1e639ea22e9a8e6e15a17940b199bdbdb3243ac..d64a63682aef231bc5ed5d9bb28aebcb72b7ba7c 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -3,9 +3,11 @@ * VGICv3 MMIO handling functions */ +#include #include #include #include +#include #include #include @@ -69,6 +71,8 @@ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu, if (vgic->enabled) value |= GICD_CTLR_ENABLE_SS_G1; value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS; + if (vgic->nassgireq) + value |= GICD_CTLR_nASSGIreq; break; case GICD_TYPER: value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS; @@ -80,6 +84,10 @@ static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu, value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19; } break; + case GICD_TYPER2: + if (kvm_vgic_global_state.has_gicv4_1 && gic_cpuif_has_vsgi()) + value = GICD_TYPER2_nASSGIcap; + break; case GICD_IIDR: value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) | (vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) | @@ -97,17 +105,46 @@ static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - bool was_enabled = dist->enabled; switch (addr & 0x0c) { - case GICD_CTLR: + case GICD_CTLR: { + bool was_enabled, is_hwsgi; + + mutex_lock(&vcpu->kvm->lock); + + was_enabled = dist->enabled; + is_hwsgi = dist->nassgireq; + dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; - if (!was_enabled && dist->enabled) + /* Not a GICv4.1? No HW SGIs */ + if (!kvm_vgic_global_state.has_gicv4_1 || !gic_cpuif_has_vsgi()) + val &= ~GICD_CTLR_nASSGIreq; + + /* Dist stays enabled? nASSGIreq is RO */ + if (was_enabled && dist->enabled) { + val &= ~GICD_CTLR_nASSGIreq; + val |= FIELD_PREP(GICD_CTLR_nASSGIreq, is_hwsgi); + } + + /* Switching HW SGIs? */ + dist->nassgireq = val & GICD_CTLR_nASSGIreq; + if (is_hwsgi != dist->nassgireq) + vgic_v4_configure_vsgis(vcpu->kvm); + + if (kvm_vgic_global_state.has_gicv4_1 && + was_enabled != dist->enabled) + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_RELOAD_GICv4); + else if (!was_enabled && dist->enabled) vgic_kick_vcpus(vcpu->kvm); + + mutex_unlock(&vcpu->kvm->lock); break; + } case GICD_TYPER: + case GICD_TYPER2: case GICD_IIDR: + /* This is at best for documentation purposes... */ return; } } @@ -116,10 +153,22 @@ static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + switch (addr & 0x0c) { + case GICD_TYPER2: case GICD_IIDR: if (val != vgic_mmio_read_v3_misc(vcpu, addr, len)) return -EINVAL; + return 0; + case GICD_CTLR: + /* Not a GICv4.1? No HW SGIs */ + if (!kvm_vgic_global_state.has_gicv4_1) + val &= ~GICD_CTLR_nASSGIreq; + + dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; + dist->nassgireq = val & GICD_CTLR_nASSGIreq; + return 0; } vgic_mmio_write_v3_misc(vcpu, addr, len, val); @@ -274,8 +323,18 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + bool state = irq->pending_latch; - if (irq->pending_latch) + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &state); + WARN_ON(err); + } + + if (state) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); @@ -957,8 +1016,18 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) * generate interrupts of either group. */ if (!irq->group || allow_group1) { - irq->pending_latch = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + if (!irq->hw) { + irq->pending_latch = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } else { + /* HW SGI? Ask the GIC to inject it */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + true); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } } else { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index fb1dcd397b93a629b40bcf6db27bd7fe42b41643..b384d46cbc7c91f99b3e49b158f9b44b28e8ff5c 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -5,6 +5,8 @@ #include #include +#include +#include #include #include #include @@ -59,6 +61,11 @@ unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, return value; } +static void vgic_update_vsgi(struct vgic_irq *irq) +{ + WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group)); +} + void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { @@ -71,7 +78,12 @@ void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->group = !!(val & BIT(i)); - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + vgic_update_vsgi(irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } else { + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } vgic_put_irq(vcpu->kvm, irq); } @@ -113,7 +125,21 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (vgic_irq_is_mapped_level(irq)) { + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + if (!irq->enabled) { + struct irq_data *data; + + irq->enabled = true; + data = &irq_to_desc(irq->host_irq)->irq_data; + while (irqd_irq_disabled(data)) + enable_irq(irq->host_irq); + } + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } else if (vgic_irq_is_mapped_level(irq)) { bool was_high = irq->line_level; /* @@ -148,6 +174,8 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) + disable_irq_nosync(irq->host_irq); irq->enabled = false; @@ -167,10 +195,22 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); unsigned long flags; + bool val; raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq_is_pending(irq)) - value |= (1U << i); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + val = false; + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &val); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + } else { + val = irq_is_pending(irq); + } + + value |= ((u32)val << i); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); @@ -236,6 +276,21 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, } raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* HW SGI? Ask the GIC to inject it */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + true); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } + if (irq->hw) vgic_hw_irq_spending(vcpu, irq, is_uaccess); else @@ -290,6 +345,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* HW SGI? Ask the GIC to clear its pending bit */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + false); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } + if (irq->hw) vgic_hw_irq_cpending(vcpu, irq, is_uaccess); else @@ -397,8 +466,15 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq->hw) { + if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); + } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* + * GICv4.1 VSGI feature doesn't track an active state, + * so let's not kid ourselves, there is nothing we can + * do here. + */ + irq->active = false; } else { u32 model = vcpu->kvm->arch.vgic.vgic_model; u8 active_source; @@ -542,6 +618,8 @@ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, raw_spin_lock_irqsave(&irq->irq_lock, flags); /* Narrow the priority range to what we actually support */ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) + vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index b3a97dcaa30d912ede0be1c628de5f61fe3f181c..1ec64640b7dff401fb44c80810a639504117c411 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include +#include #include #include #include @@ -356,8 +358,31 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) return 0; } +/* + * The deactivation of the doorbell interrupt will trigger the + * unmapping of the associated vPE. + */ +static void unmap_all_vpes(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int i; + + for (i = 0; i < dist->its_vm.nr_vpes; i++) + free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i)); +} + +static void map_all_vpes(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int i; + + for (i = 0; i < dist->its_vm.nr_vpes; i++) + WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i), + dist->its_vm.vpes[i]->irq)); +} + /** - * vgic_its_save_pending_tables - Save the pending tables into guest RAM + * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ int vgic_v3_save_pending_tables(struct kvm *kvm) @@ -365,13 +390,28 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; gpa_t last_ptr = ~(gpa_t)0; - int ret; + bool vlpi_avail = false; + int ret = 0; u8 val; + if (unlikely(!vgic_initialized(kvm))) + return -ENXIO; + + /* + * A preparation for getting any VLPI states. + * The above vgic initialized check also ensures that the allocation + * and enabling of the doorbells have already been done. + */ + if (kvm_vgic_global_state.has_gicv4_1) { + unmap_all_vpes(kvm); + vlpi_avail = true; + } + list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { int byte_offset, bit_nr; struct kvm_vcpu *vcpu; gpa_t pendbase, ptr; + bool is_pending; bool stored; vcpu = irq->target_vcpu; @@ -387,24 +427,35 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) - return ret; + goto out; last_ptr = ptr; } stored = val & (1U << bit_nr); - if (stored == irq->pending_latch) + + is_pending = irq->pending_latch; + + if (irq->hw && vlpi_avail) + vgic_v4_get_vlpi_state(irq, &is_pending); + + if (stored == is_pending) continue; - if (irq->pending_latch) + if (is_pending) val |= 1 << bit_nr; else val &= ~(1 << bit_nr); ret = kvm_write_guest_lock(kvm, ptr, &val, 1); if (ret) - return ret; + goto out; } - return 0; + +out: + if (vlpi_avail) + map_all_vpes(kvm); + + return ret; } /** @@ -540,6 +591,8 @@ int vgic_v3_map_resources(struct kvm *kvm) goto out; } + if (kvm_vgic_global_state.has_gicv4_1) + vgic_v4_configure_vsgis(kvm); dist->ready = true; out: @@ -595,7 +648,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info) /* GICv4 support? */ if (info->has_v4) { kvm_vgic_global_state.has_gicv4 = gicv4_enable; - kvm_info("GICv4 support %sabled\n", + kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; + kvm_info("GICv4%s support %sabled\n", + kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", gicv4_enable ? "en" : "dis"); } @@ -664,6 +719,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu) if (has_vhe()) __vgic_v3_activate_traps(vcpu); + + WARN_ON(vgic_v4_load(vcpu)); } void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) @@ -676,6 +733,8 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) void vgic_v3_put(struct kvm_vcpu *vcpu) { + WARN_ON(vgic_v4_put(vcpu, false)); + vgic_v3_vmcr_sync(vcpu); kvm_call_hyp(__vgic_v3_save_aprs, vcpu); diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c index 477af6aebb970ebf0bbfa35066da4aab78c43618..f507e3fcffce377201570fc65a972fa61d68c0c8 100644 --- a/virt/kvm/arm/vgic/vgic-v4.c +++ b/virt/kvm/arm/vgic/vgic-v4.c @@ -67,10 +67,10 @@ * it. And if we've migrated our vcpu from one CPU to another, we must * tell the ITS (so that the messages reach the right redistributor). * This is done in two steps: first issue a irq_set_affinity() on the - * irq corresponding to the vcpu, then call its_schedule_vpe(). You - * must be in a non-preemptible context. On exit, another call to - * its_schedule_vpe() tells the redistributor that we're done with the - * vcpu. + * irq corresponding to the vcpu, then call its_make_vpe_resident(). + * You must be in a non-preemptible context. On exit, a call to + * its_make_vpe_non_resident() tells the redistributor that we're done + * with the vcpu. * * Finally, the doorbell handling: Each vcpu is allocated an interrupt * which will fire each time a VLPI is made pending whilst the vcpu is @@ -85,13 +85,148 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) { struct kvm_vcpu *vcpu = info; + /* We got the message, no need to fire again */ + if (!kvm_vgic_global_state.has_gicv4_1 && + !irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) + disable_irq_nosync(irq); + + /* + * The v4.1 doorbell can fire concurrently with the vPE being + * made non-resident. Ensure we only update pending_last + * *after* the non-residency sequence has completed. + */ + raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; + raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); return IRQ_HANDLED; } +static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq) +{ + vpe->sgi_config[irq->intid].enabled = irq->enabled; + vpe->sgi_config[irq->intid].group = irq->group; + vpe->sgi_config[irq->intid].priority = irq->priority; +} + +static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu) +{ + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + int i; + + /* + * With GICv4.1, every virtual SGI can be directly injected. So + * let's pretend that they are HW interrupts, tied to a host + * IRQ. The SGI code will do its magic. + */ + for (i = 0; i < VGIC_NR_SGIS; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); + struct irq_desc *desc; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw) + goto unlock; + + irq->hw = true; + irq->host_irq = irq_find_mapping(vpe->sgi_domain, i); + + /* Transfer the full irq state to the vPE */ + vgic_v4_sync_sgi_config(vpe, irq); + desc = irq_to_desc(irq->host_irq); + ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc), + false); + if (!WARN_ON(ret)) { + /* Transfer pending state */ + ret = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + irq->pending_latch); + WARN_ON(ret); + irq->pending_latch = false; + } + unlock: + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) +{ + int i; + + for (i = 0; i < VGIC_NR_SGIS; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); + struct irq_desc *desc; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (!irq->hw) + goto unlock; + + irq->hw = false; + ret = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &irq->pending_latch); + WARN_ON(ret); + + desc = irq_to_desc(irq->host_irq); + irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); + unlock: + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +/* Must be called with the kvm lock held */ +void vgic_v4_configure_vsgis(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int i; + + kvm_arm_halt_guest(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (dist->nassgireq) + vgic_v4_enable_vsgis(vcpu); + else + vgic_v4_disable_vsgis(vcpu); + } + + kvm_arm_resume_guest(kvm); +} + +/* + * Must be called with GICv4.1 and the vPE unmapped, which + * indicates the invalidation of any VPT caches associated + * with the vPE, thus we can get the VLPI state by peeking + * at the VPT. + */ +void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val) +{ + struct its_vpe *vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + int mask = BIT(irq->intid % BITS_PER_BYTE); + void *va; + u8 *ptr; + + va = page_address(vpe->vpt_page); + ptr = va + irq->intid / BITS_PER_BYTE; + + *val = !!(*ptr & mask); +} + +int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq) +{ + return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu); +} + /** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized @@ -136,6 +271,7 @@ int vgic_v4_init(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { int irq = dist->its_vm.vpes[i]->irq; + unsigned long irq_flags = DB_IRQ_FLAGS; /* * Don't automatically enable the doorbell, as we're @@ -143,10 +279,15 @@ int vgic_v4_init(struct kvm *kvm) * blocked. Also disable the lazy disabling, as the * doorbell could kick us out of the guest too * early... + * + * On GICv4.1, the doorbell is managed in HW and must + * be left enabled. */ - irq_set_status_flags(irq, DB_IRQ_FLAGS); - ret = request_irq(irq, vgic_v4_doorbell_handler, - 0, "vcpu", vcpu); + if (kvm_vgic_global_state.has_gicv4_1) + irq_flags &= ~IRQ_NOAUTOEN; + irq_set_status_flags(irq, irq_flags); + + ret = vgic_v4_request_vpe_irq(vcpu, irq); if (ret) { kvm_err("failed to allocate vcpu IRQ%d\n", irq); /* @@ -192,20 +333,22 @@ void vgic_v4_teardown(struct kvm *kvm) its_vm->vpes = NULL; } -int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu) +int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db) { - if (!vgic_supports_direct_msis(vcpu->kvm)) + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + + if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; - return its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, false); + return its_make_vpe_non_resident(vpe, need_db); } -int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) +int vgic_v4_load(struct kvm_vcpu *vcpu) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int err; - if (!vgic_supports_direct_msis(vcpu->kvm)) + if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) return 0; /* @@ -214,23 +357,37 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) * doc in drivers/irqchip/irq-gic-v4.c to understand how this * turns into a VMOVP command at the ITS level. */ - err = irq_set_affinity(irq, cpumask_of(smp_processor_id())); + err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id())); if (err) return err; - err = its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, true); + err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled); if (err) return err; /* * Now that the VPE is resident, let's get rid of a potential - * doorbell interrupt that would still be pending. + * doorbell interrupt that would still be pending. This is a + * GICv4.0 only "feature"... */ - err = irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, false); + if (!kvm_vgic_global_state.has_gicv4_1) + err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false); return err; } +void vgic_v4_commit(struct kvm_vcpu *vcpu) +{ + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + + /* + * No need to wait for the vPE to be ready across a shallow guest + * exit, as only a vcpu_put will invalidate it. + */ + if (!vpe->ready) + its_commit_vpe(vpe); +} + static struct vgic_its *vgic_get_its(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *irq_entry) { @@ -251,6 +408,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, struct vgic_its *its; struct vgic_irq *irq; struct its_vlpi_map map; + unsigned long flags; int ret; if (!vgic_supports_direct_msis(kvm)) @@ -266,7 +424,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, mutex_lock(&its->its_lock); - /* Perform then actual DevID/EventID -> LPI translation. */ + /* Perform the actual DevID/EventID -> LPI translation. */ ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, irq_entry->msi.data, &irq); if (ret) @@ -294,6 +452,25 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, irq->hw = true; irq->host_irq = virq; + atomic_inc(&map.vpe->vlpi_count); + + /* Transfer pending state */ + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->pending_latch) { + ret = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + irq->pending_latch); + WARN_RATELIMIT(ret, "IRQ %d", irq->host_irq); + + /* + * Clear pending_latch and communicate this state + * change via vgic_queue_irq_unlock. + */ + irq->pending_latch = false; + vgic_queue_irq_unlock(kvm, irq, flags); + } else { + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } out: mutex_unlock(&its->its_lock); @@ -327,6 +504,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, WARN_ON(!(irq->hw && irq->host_irq == virq)); if (irq->hw) { + atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); irq->hw = false; ret = its_unmap_vlpi(virq); } @@ -335,21 +513,3 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, mutex_unlock(&its->its_lock); return ret; } - -void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu) -{ - if (vgic_supports_direct_msis(vcpu->kvm)) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; - if (irq) - enable_irq(irq); - } -} - -void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu) -{ - if (vgic_supports_direct_msis(vcpu->kvm)) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; - if (irq) - disable_irq(irq); - } -} diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 45a870cb63f584ae3de99504d60ab1a1b4c35926..2726523a1de9c2e484a01f390bfef7e8a4241a2e 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -857,8 +857,6 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - WARN_ON(vgic_v4_sync_hwstate(vcpu)); - /* An empty ap_list_head implies used_lrs == 0 */ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) return; @@ -882,8 +880,6 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu) /* Flush our emulation state into the GIC hardware before entering the guest. */ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) { - WARN_ON(vgic_v4_flush_hwstate(vcpu)); - /* * If there are no virtual interrupts active or pending for this * VCPU, then there is no work to do and we can bail out without @@ -910,6 +906,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); + + if (vgic_supports_direct_msis(vcpu->kvm)) + vgic_v4_commit(vcpu); } void kvm_vgic_load(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 83066a81b16a2ad032766591530e04c0a93ed988..14a0d7310c13699cc50458b69e844302e38bc364 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -316,7 +316,8 @@ void vgic_its_invalidate_cache(struct kvm *kvm); bool vgic_supports_direct_msis(struct kvm *kvm); int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); -int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu); -int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu); +void vgic_v4_configure_vsgis(struct kvm *kvm); +void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); +int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq); #endif diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f654f8855d05a4434c273754808c30099940de2e..ac74b31efb811f23135cf8941b84d22e8b5c5609 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1053,7 +1053,7 @@ int __kvm_set_memory_region(struct kvm *kvm, unsigned long npages; struct kvm_memory_slot *slot; struct kvm_memory_slot old, new; - struct kvm_memslots *slots = NULL, *old_memslots; + struct kvm_memslots *slots; int as_id, id; enum kvm_mr_change change; @@ -1162,7 +1162,13 @@ int __kvm_set_memory_region(struct kvm *kvm, slot = id_to_memslot(slots, id); slot->flags |= KVM_MEMSLOT_INVALID; - old_memslots = install_new_memslots(kvm, as_id, slots); + /* + * We can re-use the old memslots, the only difference from the + * newly installed memslots is the invalid flag, which will get + * dropped by update_memslots anyway. We'll also revert to the + * old memslots if preparing the new memory region fails. + */ + slots = install_new_memslots(kvm, as_id, slots); /* From this point no new shadow pages pointing to a deleted, * or moved, memslot will be created. @@ -1172,13 +1178,6 @@ int __kvm_set_memory_region(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_roots) */ kvm_arch_flush_shadow_memslot(kvm, slot); - - /* - * We can re-use the old_memslots from above, the only difference - * from the currently installed memslots is the invalid flag. This - * will get overwritten by update_memslots anyway. - */ - slots = old_memslots; } r = kvm_arch_prepare_memory_region(kvm, &new, mem, change); @@ -1192,15 +1191,17 @@ int __kvm_set_memory_region(struct kvm *kvm, } update_memslots(slots, &new, change); - old_memslots = install_new_memslots(kvm, as_id, slots); + slots = install_new_memslots(kvm, as_id, slots); kvm_arch_commit_memory_region(kvm, mem, &old, &new, change); kvm_free_memslot(kvm, &old, &new); - kvfree(old_memslots); + kvfree(slots); return 0; out_slots: + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + slots = install_new_memslots(kvm, as_id, slots); kvfree(slots); out_free: kvm_free_memslot(kvm, &new, &old);