From 24cab82c34aa6f3ede3de1d8621624cb5ef33feb Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 18 Mar 2019 10:13:01 +0000 Subject: KVM: arm/arm64: vgic: Add LPI translation cache definition Add the basic data structure that expresses an MSI to LPI translation as well as the allocation/release hooks. The size of the cache is arbitrarily defined as 16*nr_vcpus. Tested-by: Andre Przywara Reviewed-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 7a30524a80ee..ded50a30e2d5 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -249,6 +249,9 @@ struct vgic_dist { struct list_head lpi_list_head; int lpi_list_count; + /* LPI translation cache */ + struct list_head lpi_translation_cache; + /* used by vgic-debug */ struct vgic_state_iter *iter; -- cgit v1.2.3 From 3109741a8d773b91eec4a1f7764c97a1176ec32d Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 23 Aug 2019 19:33:30 +0200 Subject: KVM: arm/arm64: vgic: Use a single IO device per redistributor At the moment we use 2 IO devices per GICv3 redistributor: one one for the RD_base frame and one for the SGI_base frame. Instead we can use a single IO device per redistributor (the 2 frames are contiguous). This saves slots on the KVM_MMIO_BUS which is currently limited to NR_IOBUS_DEVS (1000). This change allows to instantiate up to 512 redistributors and may speed the guest boot with a large number of VCPUs. Signed-off-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 1 - virt/kvm/arm/vgic/vgic-init.c | 1 - virt/kvm/arm/vgic/vgic-mmio-v3.c | 81 ++++++++++++---------------------------- 3 files changed, 24 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index ded50a30e2d5..af4f09c02bf1 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -314,7 +314,6 @@ struct vgic_cpu { * parts of the redistributor. */ struct vgic_io_device rd_iodev; - struct vgic_io_device sgi_iodev; struct vgic_redist_region *rdreg; /* Contains the attributes and gpa of the LPI pending tables. */ diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 9175bfd83263..958e2f0d2207 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -193,7 +193,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) int i; vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; - vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&vgic_cpu->ap_list_head); raw_spin_lock_init(&vgic_cpu->ap_list_lock); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index fdcfb7ae4491..7dfd15dbb308 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -517,7 +517,8 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { VGIC_ACCESS_32bit), }; -static const struct vgic_register_region vgic_v3_rdbase_registers[] = { +static const struct vgic_register_region vgic_v3_rd_registers[] = { + /* RD_base registers */ REGISTER_DESC_WITH_LENGTH(GICR_CTLR, vgic_mmio_read_v3r_ctlr, vgic_mmio_write_v3r_ctlr, 4, VGIC_ACCESS_32bit), @@ -542,44 +543,42 @@ static const struct vgic_register_region vgic_v3_rdbase_registers[] = { REGISTER_DESC_WITH_LENGTH(GICR_IDREGS, vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, VGIC_ACCESS_32bit), -}; - -static const struct vgic_register_region vgic_v3_sgibase_registers[] = { - REGISTER_DESC_WITH_LENGTH(GICR_IGROUPR0, + /* SGI_base registers */ + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, vgic_mmio_read_group, vgic_mmio_write_group, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_ISENABLER0, + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ISENABLER0, vgic_mmio_read_enable, vgic_mmio_write_senable, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_ICENABLER0, + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICENABLER0, vgic_mmio_read_enable, vgic_mmio_write_cenable, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ISPENDR0, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, vgic_mmio_read_pending, vgic_mmio_write_spending, vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ICPENDR0, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0, vgic_mmio_read_pending, vgic_mmio_write_cpending, vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ISACTIVER0, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, vgic_mmio_read_active, vgic_mmio_write_sactive, NULL, vgic_mmio_uaccess_write_sactive, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_ICACTIVER0, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, vgic_mmio_read_active, vgic_mmio_write_cactive, NULL, vgic_mmio_uaccess_write_cactive, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_IPRIORITYR0, + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, vgic_mmio_read_priority, vgic_mmio_write_priority, 32, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), - REGISTER_DESC_WITH_LENGTH(GICR_ICFGR0, + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICFGR0, vgic_mmio_read_config, vgic_mmio_write_config, 8, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_IGRPMODR0, + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGRPMODR0, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_NSACR, + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_NSACR, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, VGIC_ACCESS_32bit), }; @@ -609,9 +608,8 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) struct vgic_dist *vgic = &kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; - struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev; struct vgic_redist_region *rdreg; - gpa_t rd_base, sgi_base; + gpa_t rd_base; int ret; if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) @@ -633,52 +631,31 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) vgic_cpu->rdreg = rdreg; rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; - sgi_base = rd_base + SZ_64K; kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops); rd_dev->base_addr = rd_base; rd_dev->iodev_type = IODEV_REDIST; - rd_dev->regions = vgic_v3_rdbase_registers; - rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers); + rd_dev->regions = vgic_v3_rd_registers; + rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); rd_dev->redist_vcpu = vcpu; mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base, - SZ_64K, &rd_dev->dev); + 2 * SZ_64K, &rd_dev->dev); mutex_unlock(&kvm->slots_lock); if (ret) return ret; - kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops); - sgi_dev->base_addr = sgi_base; - sgi_dev->iodev_type = IODEV_REDIST; - sgi_dev->regions = vgic_v3_sgibase_registers; - sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers); - sgi_dev->redist_vcpu = vcpu; - - mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base, - SZ_64K, &sgi_dev->dev); - if (ret) { - kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, - &rd_dev->dev); - goto out; - } - rdreg->free_index++; -out: - mutex_unlock(&kvm->slots_lock); - return ret; + return 0; } static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) { struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; - struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev; kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev); - kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &sgi_dev->dev); } static int vgic_register_all_redist_iodevs(struct kvm *kvm) @@ -828,8 +805,8 @@ int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) iodev.base_addr = 0; break; case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:{ - iodev.regions = vgic_v3_rdbase_registers; - iodev.nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers); + iodev.regions = vgic_v3_rd_registers; + iodev.nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); iodev.base_addr = 0; break; } @@ -987,21 +964,11 @@ int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val) { struct vgic_io_device rd_dev = { - .regions = vgic_v3_rdbase_registers, - .nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers), + .regions = vgic_v3_rd_registers, + .nr_regions = ARRAY_SIZE(vgic_v3_rd_registers), }; - struct vgic_io_device sgi_dev = { - .regions = vgic_v3_sgibase_registers, - .nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers), - }; - - /* SGI_base is the next 64K frame after RD_base */ - if (offset >= SZ_64K) - return vgic_uaccess(vcpu, &sgi_dev, is_write, offset - SZ_64K, - val); - else - return vgic_uaccess(vcpu, &rd_dev, is_write, offset, val); + return vgic_uaccess(vcpu, &rd_dev, is_write, offset, val); } int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write, -- cgit v1.2.3 From 92f35b751c71d14250a401246f2c792e3aa5b386 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 18 Aug 2019 14:09:47 +0100 Subject: KVM: arm/arm64: vgic: Allow more than 256 vcpus for KVM_IRQ_LINE While parts of the VGIC support a large number of vcpus (we bravely allow up to 512), other parts are more limited. One of these limits is visible in the KVM_IRQ_LINE ioctl, which only allows 256 vcpus to be signalled when using the CPU or PPI types. Unfortunately, we've cornered ourselves badly by allocating all the bits in the irq field. Since the irq_type subfield (8 bit wide) is currently only taking the values 0, 1 and 2 (and we have been careful not to allow anything else), let's reduce this field to only 4 bits, and allocate the remaining 4 bits to a vcpu2_index, which acts as a multiplier: vcpu_id = 256 * vcpu2_index + vcpu_index With that, and a new capability (KVM_CAP_ARM_IRQ_LINE_LAYOUT_2) allowing this to be discovered, it becomes possible to inject PPIs to up to 4096 vcpus. But please just don't. Whilst we're there, add a clarification about the use of KVM_IRQ_LINE on arm, which is not completely conditionned by KVM_CAP_IRQCHIP. Reported-by: Zenghui Yu Reviewed-by: Eric Auger Reviewed-by: Zenghui Yu Signed-off-by: Marc Zyngier --- Documentation/virt/kvm/api.txt | 12 ++++++++++-- arch/arm/include/uapi/asm/kvm.h | 4 +++- arch/arm64/include/uapi/asm/kvm.h | 4 +++- include/uapi/linux/kvm.h | 1 + virt/kvm/arm/arm.c | 2 ++ 5 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt index 2d067767b617..25931ca1cb38 100644 --- a/Documentation/virt/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -753,8 +753,8 @@ in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to use PPIs designated for specific cpus. The irq field is interpreted like this: -  bits: | 31 ... 24 | 23 ... 16 | 15 ... 0 | - field: | irq_type | vcpu_index | irq_id | +  bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 | + field: | vcpu2_index | irq_type | vcpu_index | irq_id | The irq_type field has the following values: - irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ @@ -766,6 +766,14 @@ The irq_type field has the following values: In both cases, level is used to assert/deassert the line. +When KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 is supported, the target vcpu is +identified as (256 * vcpu2_index + vcpu_index). Otherwise, vcpu2_index +must be zero. + +Note that on arm/arm64, the KVM_CAP_IRQCHIP capability only conditions +injection of interrupts for the in-kernel irqchip. KVM_IRQ_LINE can always +be used for a userspace interrupt controller. + struct kvm_irq_level { union { __u32 irq; /* GSI */ diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index a4217c1a5d01..2769360f195c 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -266,8 +266,10 @@ struct kvm_vcpu_events { #define KVM_DEV_ARM_ITS_CTRL_RESET 4 /* KVM_IRQ_LINE irq field index values */ +#define KVM_ARM_IRQ_VCPU2_SHIFT 28 +#define KVM_ARM_IRQ_VCPU2_MASK 0xf #define KVM_ARM_IRQ_TYPE_SHIFT 24 -#define KVM_ARM_IRQ_TYPE_MASK 0xff +#define KVM_ARM_IRQ_TYPE_MASK 0xf #define KVM_ARM_IRQ_VCPU_SHIFT 16 #define KVM_ARM_IRQ_VCPU_MASK 0xff #define KVM_ARM_IRQ_NUM_SHIFT 0 diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 9a507716ae2f..67c21f9bdbad 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -325,8 +325,10 @@ struct kvm_vcpu_events { #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 /* KVM_IRQ_LINE irq field index values */ +#define KVM_ARM_IRQ_VCPU2_SHIFT 28 +#define KVM_ARM_IRQ_VCPU2_MASK 0xf #define KVM_ARM_IRQ_TYPE_SHIFT 24 -#define KVM_ARM_IRQ_TYPE_MASK 0xff +#define KVM_ARM_IRQ_TYPE_MASK 0xf #define KVM_ARM_IRQ_VCPU_SHIFT 16 #define KVM_ARM_IRQ_VCPU_MASK 0xff #define KVM_ARM_IRQ_NUM_SHIFT 0 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5e3f12d5359e..5414b6588fbb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -996,6 +996,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172 #define KVM_CAP_PMU_EVENT_FILTER 173 +#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 35a069815baf..86c6aa1cb58e 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -196,6 +196,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_MP_STATE: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_VCPU_EVENTS: + case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2: r = 1; break; case KVM_CAP_ARM_SET_DEVICE_ADDR: @@ -888,6 +889,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; + vcpu_idx += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1); irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK; trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level); -- cgit v1.2.3 From 7396d337cfadc7c0b32dfd46581e9daff6666e84 Mon Sep 17 00:00:00 2001 From: Liran Alon Date: Mon, 26 Aug 2019 13:16:43 +0300 Subject: KVM: x86: Return to userspace with internal error on unexpected exit reason Receiving an unexpected exit reason from hardware should be considered as a severe bug in KVM. Therefore, instead of just injecting #UD to guest and ignore it, exit to userspace on internal error so that it could handle it properly (probably by terminating guest). In addition, prefer to use vcpu_unimpl() instead of WARN_ONCE() as handling unexpected exit reason should be a rare unexpected event (that was expected to never happen) and we prefer to print a message on it every time it occurs to guest. Furthermore, dump VMCS/VMCB to dmesg to assist diagnosing such cases. Reviewed-by: Mihai Carabas Reviewed-by: Nikita Leshenko Reviewed-by: Joao Martins Signed-off-by: Liran Alon Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm.c | 11 ++++++++--- arch/x86/kvm/vmx/vmx.c | 9 +++++++-- include/uapi/linux/kvm.h | 2 ++ 3 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 890b1bffcf7c..fdeaf8f44949 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4981,9 +4981,14 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code); - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; + vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code); + dump_vmcb(vcpu); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 1; + vcpu->run->internal.data[0] = exit_code; + return 0; } return svm_exit_handlers[exit_code](svm); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 024cb9bf5ad3..d95c2f3c027c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5870,8 +5870,13 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) else { vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason); - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; + dump_vmcs(); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 1; + vcpu->run->internal.data[0] = exit_reason; + return 0; } } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5414b6588fbb..233efbb1c81c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -243,6 +243,8 @@ struct kvm_hyperv_exit { #define KVM_INTERNAL_ERROR_SIMUL_EX 2 /* Encounter unexpected vm-exit due to delivery event. */ #define KVM_INTERNAL_ERROR_DELIVERY_EV 3 +/* Encounter unexpected vm-exit reason */ +#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { -- cgit v1.2.3