From b88d05a893cb7c8a48d03ff93d4aca95a6165377 Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Thu, 19 Mar 2026 15:56:43 +0000 Subject: KVM: arm64: gic-v5: Support GICv5 interrupts with KVM_IRQ_LINE Interrupts under GICv5 look quite different to those from older Arm GICs. Specifically, the type is encoded in the top bits of the interrupt ID. Extend KVM_IRQ_LINE to cope with GICv5 PPIs and SPIs. The requires subtly changing the KVM_IRQ_LINE API for GICv5 guests. For older Arm GICs, PPIs had to be in the range of 16-31, and SPIs had to be 32-1019, but this no longer holds true for GICv5. Instead, for a GICv5 guest support PPIs in the range of 0-127, and SPIs in the range 0-65535. The documentation is updated accordingly. The SPI range doesn't cover the full SPI range that a GICv5 system can potentially cope with (GICv5 provides up to 24-bits of SPI ID space, and we only have 16 bits to work with in KVM_IRQ_LINE). However, 65k SPIs is more than would be reasonably expected on systems for years to come. In order to use vgic_is_v5(), the kvm/arm_vgic.h header is added to kvm/arm.c. Note: As the GICv5 KVM implementation currently doesn't support injecting SPIs attempts to do so will fail. This restriction will by lifted as the GICv5 KVM support evolves. Co-authored-by: Timothy Hayes Signed-off-by: Timothy Hayes Signed-off-by: Sascha Bischoff Reviewed-by: Jonathan Cameron Link: https://patch.msgid.link/20260319154937.3619520-28-sascha.bischoff@arm.com Signed-off-by: Marc Zyngier --- Documentation/virt/kvm/api.rst | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 032516783e96..03d87d9b97d9 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -907,10 +907,12 @@ The irq_type field has the following values: - KVM_ARM_IRQ_TYPE_CPU: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ - KVM_ARM_IRQ_TYPE_SPI: - in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.) + in-kernel GICv2/GICv3: SPI, irq_id between 32 and 1019 (incl.) (the vcpu_index field is ignored) + in-kernel GICv5: SPI, irq_id between 0 and 65535 (incl.) - KVM_ARM_IRQ_TYPE_PPI: - in-kernel GIC: PPI, irq_id between 16 and 31 (incl.) + in-kernel GICv2/GICv3: PPI, irq_id between 16 and 31 (incl.) + in-kernel GICv5: PPI, irq_id between 0 and 127 (incl.) (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs) -- cgit v1.2.3 From 7c31c06e2d2d75859d773ba940e56d1db2bd1fcd Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Thu, 19 Mar 2026 15:58:01 +0000 Subject: KVM: arm64: gic-v5: Mandate architected PPI for PMU emulation on GICv5 Make it mandatory to use the architected PPI when running a GICv5 guest. Attempts to set anything other than the architected PPI (23) are rejected. Additionally, KVM_ARM_VCPU_PMU_V3_INIT is relaxed to no longer require KVM_ARM_VCPU_PMU_V3_IRQ to be called for GICv5-based guests. In this case, the architectued PPI is automatically used. Documentation is bumped accordingly. Signed-off-by: Sascha Bischoff Reviewed-by: Jonathan Cameron Reviewed-by: Joey Gouly Link: https://patch.msgid.link/20260319154937.3619520-33-sascha.bischoff@arm.com Signed-off-by: Marc Zyngier --- Documentation/virt/kvm/devices/vcpu.rst | 5 +++-- arch/arm64/kvm/pmu-emul.c | 13 +++++++++++-- include/kvm/arm_pmu.h | 5 ++++- 3 files changed, 18 insertions(+), 5 deletions(-) (limited to 'Documentation') diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst index 60bf205cb373..5e3805820010 100644 --- a/Documentation/virt/kvm/devices/vcpu.rst +++ b/Documentation/virt/kvm/devices/vcpu.rst @@ -37,7 +37,8 @@ Returns: A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt type must be same for each vcpu. As a PPI, the interrupt number is the same for -all vcpus, while as an SPI it must be a separate number per vcpu. +all vcpus, while as an SPI it must be a separate number per vcpu. For +GICv5-based guests, the architected PPI (23) must be used. 1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT --------------------------------------- @@ -50,7 +51,7 @@ Returns: -EEXIST Interrupt number already used -ENODEV PMUv3 not supported or GIC not initialized -ENXIO PMUv3 not supported, missing VCPU feature or interrupt - number not set + number not set (non-GICv5 guests, only) -EBUSY PMUv3 already initialized ======= ====================================================== diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 41a3c5dc2bca..e1860acae641 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -962,8 +962,13 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) if (!vgic_initialized(vcpu->kvm)) return -ENODEV; - if (!kvm_arm_pmu_irq_initialized(vcpu)) - return -ENXIO; + if (!kvm_arm_pmu_irq_initialized(vcpu)) { + if (!vgic_is_v5(vcpu->kvm)) + return -ENXIO; + + /* Use the architected irq number for GICv5. */ + vcpu->arch.pmu.irq_num = KVM_ARMV8_PMU_GICV5_IRQ; + } ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num, &vcpu->arch.pmu); @@ -988,6 +993,10 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) unsigned long i; struct kvm_vcpu *vcpu; + /* On GICv5, the PMUIRQ is architecturally mandated to be PPI 23 */ + if (vgic_is_v5(kvm) && irq != KVM_ARMV8_PMU_GICV5_IRQ) + return false; + kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_arm_pmu_irq_initialized(vcpu)) continue; diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 96754b51b411..0a36a3d5c894 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -12,6 +12,9 @@ #define KVM_ARMV8_PMU_MAX_COUNTERS 32 +/* PPI #23 - architecturally specified for GICv5 */ +#define KVM_ARMV8_PMU_GICV5_IRQ 0x20000017 + #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM) struct kvm_pmc { u8 idx; /* index into the pmu->pmc array */ @@ -38,7 +41,7 @@ struct arm_pmu_entry { }; bool kvm_supports_guest_pmuv3(void); -#define kvm_arm_pmu_irq_initialized(v) ((v)->arch.pmu.irq_num >= VGIC_NR_SGIS) +#define kvm_arm_pmu_irq_initialized(v) ((v)->arch.pmu.irq_num != 0) u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx); void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val); void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val); -- cgit v1.2.3 From eb3c4d2c9a4d76b775a9dbd5ac056d1abf0083a1 Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Thu, 19 Mar 2026 15:59:35 +0000 Subject: Documentation: KVM: Introduce documentation for VGICv5 Now that it is possible to create a VGICv5 device, provide initial documentation for it. At this stage, there is little to document. Signed-off-by: Sascha Bischoff Reviewed-by: Jonathan Cameron Link: https://patch.msgid.link/20260319154937.3619520-39-sascha.bischoff@arm.com Signed-off-by: Marc Zyngier --- Documentation/virt/kvm/devices/arm-vgic-v5.rst | 37 ++++++++++++++++++++++++++ Documentation/virt/kvm/devices/index.rst | 1 + 2 files changed, 38 insertions(+) create mode 100644 Documentation/virt/kvm/devices/arm-vgic-v5.rst (limited to 'Documentation') diff --git a/Documentation/virt/kvm/devices/arm-vgic-v5.rst b/Documentation/virt/kvm/devices/arm-vgic-v5.rst new file mode 100644 index 000000000000..9904cb888277 --- /dev/null +++ b/Documentation/virt/kvm/devices/arm-vgic-v5.rst @@ -0,0 +1,37 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================================================== +ARM Virtual Generic Interrupt Controller v5 (VGICv5) +==================================================== + + +Device types supported: + - KVM_DEV_TYPE_ARM_VGIC_V5 ARM Generic Interrupt Controller v5.0 + +Only one VGIC instance may be instantiated through this API. The created VGIC +will act as the VM interrupt controller, requiring emulated user-space devices +to inject interrupts to the VGIC instead of directly to CPUs. + +Creating a guest GICv5 device requires a host GICv5 host. The current VGICv5 +device only supports PPI interrupts. These can either be injected from emulated +in-kernel devices (such as the Arch Timer, or PMU), or via the KVM_IRQ_LINE +ioctl. + +Groups: + KVM_DEV_ARM_VGIC_GRP_CTRL + Attributes: + + KVM_DEV_ARM_VGIC_CTRL_INIT + request the initialization of the VGIC, no additional parameter in + kvm_device_attr.addr. Must be called after all VCPUs have been created. + + Errors: + + ======= ======================================================== + -ENXIO VGIC not properly configured as required prior to calling + this attribute + -ENODEV no online VCPU + -ENOMEM memory shortage when allocating vgic internal data + -EFAULT Invalid guest ram access + -EBUSY One or more VCPUS are running + ======= ======================================================== diff --git a/Documentation/virt/kvm/devices/index.rst b/Documentation/virt/kvm/devices/index.rst index 192cda7405c8..70845aba38f4 100644 --- a/Documentation/virt/kvm/devices/index.rst +++ b/Documentation/virt/kvm/devices/index.rst @@ -10,6 +10,7 @@ Devices arm-vgic-its arm-vgic arm-vgic-v3 + arm-vgic-v5 mpic s390_flic vcpu -- cgit v1.2.3 From d51c978b7d3e143381f871d28d8a0437d446b51b Mon Sep 17 00:00:00 2001 From: Sascha Bischoff Date: Thu, 19 Mar 2026 15:59:50 +0000 Subject: KVM: arm64: gic-v5: Communicate userspace-driveable PPIs via a UAPI GICv5 systems will likely not support the full set of PPIs. The presence of any virtual PPI is tied to the presence of the physical PPI. Therefore, the available PPIs will be limited by the physical host. Userspace cannot drive any PPIs that are not implemented. Moreover, it is not desirable to expose all PPIs to the guest in the first place, even if they are supported in hardware. Some devices, such as the arch timer, are implemented in KVM, and hence those PPIs shouldn't be driven by userspace, either. Provided a new UAPI: KVM_DEV_ARM_VGIC_GRP_CTRL => KVM_DEV_ARM_VGIC_USERPSPACE_PPIs This allows userspace to query which PPIs it is able to drive via KVM_IRQ_LINE. Additionally, introduce a check in kvm_vm_ioctl_irq_line() to reject any PPIs not in the userspace mask. Signed-off-by: Sascha Bischoff Reviewed-by: Jonathan Cameron Link: https://patch.msgid.link/20260319154937.3619520-40-sascha.bischoff@arm.com Signed-off-by: Marc Zyngier --- Documentation/virt/kvm/devices/arm-vgic-v5.rst | 13 +++++++++++ arch/arm64/include/uapi/asm/kvm.h | 1 + arch/arm64/kvm/arm.c | 11 ++++++++- arch/arm64/kvm/vgic/vgic-kvm-device.c | 31 ++++++++++++++++++++++++++ arch/arm64/kvm/vgic/vgic-v5.c | 10 +++++++++ include/kvm/arm_vgic.h | 3 +++ tools/arch/arm64/include/uapi/asm/kvm.h | 1 + 7 files changed, 69 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/virt/kvm/devices/arm-vgic-v5.rst b/Documentation/virt/kvm/devices/arm-vgic-v5.rst index 9904cb888277..29335ea823fc 100644 --- a/Documentation/virt/kvm/devices/arm-vgic-v5.rst +++ b/Documentation/virt/kvm/devices/arm-vgic-v5.rst @@ -25,6 +25,19 @@ Groups: request the initialization of the VGIC, no additional parameter in kvm_device_attr.addr. Must be called after all VCPUs have been created. + KVM_DEV_ARM_VGIC_USERPSPACE_PPIs + request the mask of userspace-drivable PPIs. Only a subset of the PPIs can + be directly driven from userspace with GICv5, and the returned mask + informs userspace of which it is allowed to drive via KVM_IRQ_LINE. + + Userspace must allocate and point to __u64[2] of data in + kvm_device_attr.addr. When this call returns, the provided memory will be + populated with the userspace PPI mask. The lower __u64 contains the mask + for the lower 64 PPIS, with the remaining 64 being in the second __u64. + + This is a read-only attribute, and cannot be set. Attempts to set it are + rejected. + Errors: ======= ======================================================== diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index a792a599b9d6..1c13bfa2d38a 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -428,6 +428,7 @@ enum { #define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 #define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 #define KVM_DEV_ARM_ITS_CTRL_RESET 4 +#define KVM_DEV_ARM_VGIC_USERSPACE_PPIS 5 /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index cb22bed9c85d..36410f7cd2ad 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1449,10 +1449,11 @@ static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level) int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status) { - u32 irq = irq_level->irq; unsigned int irq_type, vcpu_id, irq_num; struct kvm_vcpu *vcpu = NULL; bool level = irq_level->level; + u32 irq = irq_level->irq; + unsigned long *mask; irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; vcpu_id = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; @@ -1486,6 +1487,14 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, if (irq_num >= VGIC_V5_NR_PRIVATE_IRQS) return -EINVAL; + /* + * Only allow PPIs that are explicitly exposed to + * usespace to be driven via KVM_IRQ_LINE + */ + mask = kvm->arch.vgic.gicv5_vm.userspace_ppis; + if (!test_bit(irq_num, mask)) + return -EINVAL; + /* Build a GICv5-style IntID here */ irq_num = vgic_v5_make_ppi(irq_num); } else if (irq_num < VGIC_NR_SGIS || diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 772da54c1518..a96c77dccf35 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -720,6 +720,32 @@ struct kvm_device_ops kvm_arm_vgic_v3_ops = { .has_attr = vgic_v3_has_attr, }; +static int vgic_v5_get_userspace_ppis(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + struct vgic_v5_vm *gicv5_vm = &dev->kvm->arch.vgic.gicv5_vm; + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + int ret; + + guard(mutex)(&dev->kvm->arch.config_lock); + + /* + * We either support 64 or 128 PPIs. In the former case, we need to + * return 0s for the second 64 bits as we have no storage backing those. + */ + ret = put_user(bitmap_read(gicv5_vm->userspace_ppis, 0, 64), uaddr); + if (ret) + return ret; + uaddr++; + + if (VGIC_V5_NR_PRIVATE_IRQS == 128) + ret = put_user(bitmap_read(gicv5_vm->userspace_ppis, 64, 128), uaddr); + else + ret = put_user(0, uaddr); + + return ret; +} + static int vgic_v5_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { @@ -732,6 +758,7 @@ static int vgic_v5_set_attr(struct kvm_device *dev, switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return vgic_set_common_attr(dev, attr); + case KVM_DEV_ARM_VGIC_USERSPACE_PPIS: default: return -ENXIO; } @@ -753,6 +780,8 @@ static int vgic_v5_get_attr(struct kvm_device *dev, switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return vgic_get_common_attr(dev, attr); + case KVM_DEV_ARM_VGIC_USERSPACE_PPIS: + return vgic_v5_get_userspace_ppis(dev, attr); default: return -ENXIO; } @@ -773,6 +802,8 @@ static int vgic_v5_has_attr(struct kvm_device *dev, switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; + case KVM_DEV_ARM_VGIC_USERSPACE_PPIS: + return 0; default: return -ENXIO; } diff --git a/arch/arm64/kvm/vgic/vgic-v5.c b/arch/arm64/kvm/vgic/vgic-v5.c index f7a24ea6ad78..2b6cd5c3f9c2 100644 --- a/arch/arm64/kvm/vgic/vgic-v5.c +++ b/arch/arm64/kvm/vgic/vgic-v5.c @@ -143,6 +143,16 @@ int vgic_v5_init(struct kvm *kvm) } } + /* We only allow userspace to drive the SW_PPI, if it is implemented. */ + bitmap_zero(kvm->arch.vgic.gicv5_vm.userspace_ppis, + VGIC_V5_NR_PRIVATE_IRQS); + __assign_bit(GICV5_ARCH_PPI_SW_PPI, + kvm->arch.vgic.gicv5_vm.userspace_ppis, + VGIC_V5_NR_PRIVATE_IRQS); + bitmap_and(kvm->arch.vgic.gicv5_vm.userspace_ppis, + kvm->arch.vgic.gicv5_vm.userspace_ppis, + ppi_caps.impl_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS); + return 0; } diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 8cc3a7b4d815..1388dc6028a9 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -350,6 +350,9 @@ struct vgic_v5_vm { */ DECLARE_BITMAP(vgic_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS); + /* A mask of the PPIs that are exposed for userspace to drive. */ + DECLARE_BITMAP(userspace_ppis, VGIC_V5_NR_PRIVATE_IRQS); + /* * The HMR itself is handled by the hardware, but we still need to have * a mask that we can use when merging in pending state (only the state diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index a792a599b9d6..1c13bfa2d38a 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -428,6 +428,7 @@ enum { #define KVM_DEV_ARM_ITS_RESTORE_TABLES 2 #define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3 #define KVM_DEV_ARM_ITS_CTRL_RESET 4 +#define KVM_DEV_ARM_VGIC_USERSPACE_PPIS 5 /* Device Control API on vcpu fd */ #define KVM_ARM_VCPU_PMU_V3_CTRL 0 -- cgit v1.2.3