From c5edd753a0bd6243a597f5199c227a50457ee179 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:02 +0100 Subject: KVM: x86: Remove the KVM_GET_NR_MMU_PAGES ioctl The KVM_GET_NR_MMU_PAGES ioctl is quite questionable on 64-bit hosts since it fails to return the full 64 bits of the value that can be set with the corresponding KVM_SET_NR_MMU_PAGES call. Its "long" return value is truncated into an "int" in the kvm_arch_vm_ioctl() function. Since this ioctl also never has been used by userspace applications (QEMU, Google's internal VMM, kvmtool and CrosVM have been checked), it's likely the best if we remove this badly designed ioctl before anybody really tries to use it. Signed-off-by: Thomas Huth Reviewed-by: Sean Christopherson Message-Id: <20230208140105.655814-4-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d77aef872a0a..4003a166328c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1451,7 +1451,7 @@ struct kvm_vfio_spapr_tce { #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) -#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* deprecated */ #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ struct kvm_userspace_memory_region) #define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) -- cgit v1.2.3 From 30ec7997d175cd689fc61bfc4059f4d35b11858c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:47 +0100 Subject: KVM: arm64: timers: Allow userspace to set the global counter offset And this is the moment you have all been waiting for: setting the counter offset from userspace. We expose a brand new capability that reports the ability to set the offset for both the virtual and physical sides. In keeping with the architecture, the offset is expressed as a delta that is substracted from the physical counter value. Once this new API is used, there is no going back, and the counters cannot be written to to set the offsets implicitly (the writes are instead ignored). Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-8-maz@kernel.org --- arch/arm64/include/asm/kvm_host.h | 4 +++ arch/arm64/include/uapi/asm/kvm.h | 9 +++++++ arch/arm64/kvm/arch_timer.c | 54 +++++++++++++++++++++++++++++++++++---- arch/arm64/kvm/arm.c | 8 ++++++ include/uapi/linux/kvm.h | 3 +++ 5 files changed, 73 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 002a10cbade2..116233a390e9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -221,6 +221,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_EL1_32BIT 4 /* PSCI SYSTEM_SUSPEND enabled for the guest */ #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 + /* VM counter offset */ +#define KVM_ARCH_FLAG_VM_COUNTER_OFFSET 6 unsigned long flags; @@ -1010,6 +1012,8 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags); +int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, + struct kvm_arm_counter_offset *offset); /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..12fb0d8a760a 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index bb64a71ae193..771504c79711 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -851,9 +851,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) ptimer->vcpu = vcpu; ptimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.poffset; - /* Synchronize cntvoff across all vtimers of a VM. */ - timer_set_offset(vtimer, kvm_phys_timer_read()); - timer_set_offset(ptimer, 0); + /* Synchronize offsets across timers of a VM if not already provided */ + if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &vcpu->kvm->arch.flags)) { + timer_set_offset(vtimer, kvm_phys_timer_read()); + timer_set_offset(ptimer, 0); + } hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); timer->bg_timer.function = kvm_bg_timer_expire; @@ -897,8 +899,11 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; case KVM_REG_ARM_TIMER_CNT: - timer = vcpu_vtimer(vcpu); - timer_set_offset(timer, kvm_phys_timer_read() - value); + if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, + &vcpu->kvm->arch.flags)) { + timer = vcpu_vtimer(vcpu); + timer_set_offset(timer, kvm_phys_timer_read() - value); + } break; case KVM_REG_ARM_TIMER_CVAL: timer = vcpu_vtimer(vcpu); @@ -908,6 +913,13 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) timer = vcpu_ptimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; + case KVM_REG_ARM_PTIMER_CNT: + if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, + &vcpu->kvm->arch.flags)) { + timer = vcpu_ptimer(vcpu); + timer_set_offset(timer, kvm_phys_timer_read() - value); + } + break; case KVM_REG_ARM_PTIMER_CVAL: timer = vcpu_ptimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); @@ -1443,3 +1455,35 @@ int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -ENXIO; } + +int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, + struct kvm_arm_counter_offset *offset) +{ + int ret = 0; + + if (offset->reserved) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (lock_all_vcpus(kvm)) { + set_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &kvm->arch.flags); + + /* + * If userspace decides to set the offset using this + * API rather than merely restoring the counter + * values, the offset applies to both the virtual and + * physical views. + */ + kvm->arch.timer_data.voffset = offset->counter_offset; + kvm->arch.timer_data.poffset = offset->counter_offset; + + unlock_all_vcpus(kvm); + } else { + ret = -EBUSY; + } + + mutex_unlock(&kvm->lock); + + return ret; +} diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index ae5110cc3bad..1c8a4bbae684 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -220,6 +220,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: case KVM_CAP_ARM_SYSTEM_SUSPEND: + case KVM_CAP_COUNTER_OFFSET: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -1479,6 +1480,13 @@ long kvm_arch_vm_ioctl(struct file *filp, return -EFAULT; return kvm_vm_ioctl_mte_copy_tags(kvm, ©_tags); } + case KVM_ARM_SET_COUNTER_OFFSET: { + struct kvm_arm_counter_offset offset; + + if (copy_from_user(&offset, argp, sizeof(offset))) + return -EFAULT; + return kvm_vm_ioctl_set_counter_offset(kvm, &offset); + } default: return -EINVAL; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d77aef872a0a..6a7e1a0ecf04 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1184,6 +1184,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1544,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- cgit v1.2.3 From e65733b5c59a1ea20324a03494364958bef3fc68 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:38 +0000 Subject: KVM: x86: Redefine 'longmode' as a flag for KVM_EXIT_HYPERCALL The 'longmode' field is a bit annoying as it blows an entire __u32 to represent a boolean value. Since other architectures are looking to add support for KVM_EXIT_HYPERCALL, now is probably a good time to clean it up. Redefine the field (and the remaining padding) as a set of flags. Preserve the existing ABI by using bit 0 to indicate if the guest was in long mode and requiring that the remaining 31 bits must be zero. Cc: Paolo Bonzini Acked-by: Sean Christopherson Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-2-oliver.upton@linux.dev --- Documentation/virt/kvm/api.rst | 3 +-- arch/x86/include/asm/kvm_host.h | 7 +++++++ arch/x86/include/uapi/asm/kvm.h | 3 +++ arch/x86/kvm/x86.c | 6 +++++- include/uapi/linux/kvm.h | 9 +++++++-- 5 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 62de0768d6aa..9b01e3d0e757 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6218,8 +6218,7 @@ to the byte array. __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + __u64 flags; } hypercall; Unused. This was once used for 'hypercall to userspace'. To implement diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 808c292ad3f4..15bda40517ff 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2204,4 +2204,11 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) +/* + * KVM previously used a u32 field in kvm_run to indicate the hypercall was + * initiated from long mode. KVM now sets bit 0 to indicate long mode, but the + * remaining 31 lower bits must be 0 to preserve ABI. + */ +#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1) + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7713420abab0..27a1d5c1a018 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9803,7 +9803,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; - vcpu->run->hypercall.longmode = op_64_bit; + vcpu->run->hypercall.flags = 0; + if (op_64_bit) + vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE; + + WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); vcpu->arch.complete_userspace_io = complete_hypercall_exit; return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d77aef872a0a..dd42d7dfb86c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { -- cgit v1.2.3