diff options
-rw-r--r-- | Documentation/virt/kvm/api.txt | 55 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_arm.h | 1 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_emulate.h | 5 | ||||
-rw-r--r-- | arch/arm/include/asm/kvm_host.h | 8 | ||||
-rw-r--r-- | arch/arm/include/uapi/asm/kvm.h | 3 | ||||
-rw-r--r-- | arch/arm/kvm/guest.c | 10 | ||||
-rw-r--r-- | arch/arm64/include/asm/kvm_emulate.h | 5 | ||||
-rw-r--r-- | arch/arm64/include/asm/kvm_host.h | 8 | ||||
-rw-r--r-- | arch/arm64/include/uapi/asm/kvm.h | 3 | ||||
-rw-r--r-- | arch/arm64/kvm/guest.c | 10 | ||||
-rw-r--r-- | arch/arm64/kvm/inject_fault.c | 4 | ||||
-rw-r--r-- | include/uapi/linux/kvm.h | 8 | ||||
-rw-r--r-- | virt/kvm/arm/arm.c | 22 | ||||
-rw-r--r-- | virt/kvm/arm/mmio.c | 9 |
14 files changed, 145 insertions, 6 deletions
diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt index 4833904d32a5..bd29d44af32b 100644 --- a/Documentation/virt/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -1002,12 +1002,18 @@ Specifying exception.has_esr on a system that does not support it will return -EINVAL. Setting anything other than the lower 24bits of exception.serror_esr will return -EINVAL. +It is not possible to read back a pending external abort (injected via +KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered +directly to the virtual CPU). + + struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; @@ -1051,9 +1057,23 @@ contain a valid state and shall be written into the VCPU. ARM/ARM64: +User space may need to inject several types of events to the guest. + Set the pending SError exception state for this VCPU. It is not possible to 'cancel' an Serror that has been made pending. +If the guest performed an access to I/O memory which could not be handled by +userspace, for example because of missing instruction syndrome decode +information or because there is no device mapped at the accessed IPA, then +userspace can ask the kernel to inject an external abort using the address +from the exiting fault on the VCPU. It is a programming error to set +ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or +KVM_EXIT_ARM_NISV. This feature is only available if the system supports +KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in +how userspace reports accesses for the above cases to guests, across different +userspace implementations. Nevertheless, userspace can still emulate all Arm +exceptions by manipulating individual registers using the KVM_SET_ONE_REG API. + See KVM_GET_VCPU_EVENTS for the data structure. @@ -4468,6 +4488,39 @@ Hyper-V SynIC state change. Notification is used to remap SynIC event/message pages and to enable/disable SynIC messages/events processing in userspace. + /* KVM_EXIT_ARM_NISV */ + struct { + __u64 esr_iss; + __u64 fault_ipa; + } arm_nisv; + +Used on arm and arm64 systems. If a guest accesses memory not in a memslot, +KVM will typically return to userspace and ask it to do MMIO emulation on its +behalf. However, for certain classes of instructions, no instruction decode +(direction, length of memory access) is provided, and fetching and decoding +the instruction from the VM is overly complicated to live in the kernel. + +Historically, when this situation occurred, KVM would print a warning and kill +the VM. KVM assumed that if the guest accessed non-memslot memory, it was +trying to do I/O, which just couldn't be emulated, and the warning message was +phrased accordingly. However, what happened more often was that a guest bug +caused access outside the guest memory areas which should lead to a more +meaningful warning message and an external abort in the guest, if the access +did not fall within an I/O window. + +Userspace implementations can query for KVM_CAP_ARM_NISV_TO_USER, and enable +this capability at VM creation. Once this is done, these types of errors will +instead return to userspace with KVM_EXIT_ARM_NISV, with the valid bits from +the HSR (arm) and ESR_EL2 (arm64) in the esr_iss field, and the faulting IPA +in the fault_ipa field. Userspace can either fix up the access if it's +actually an I/O access by decoding the instruction from guest memory (if it's +very brave) and continue executing the guest, or it can decide to suspend, +dump, or restart the guest. + +Note that KVM does not skip the faulting instruction as it does for +KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state +if it decides to decode and emulate the instruction. + /* Fix the size of the union. */ char padding[256]; }; diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 0125aa059d5b..9c04bd810d07 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -162,6 +162,7 @@ #define HSR_ISV (_AC(1, UL) << HSR_ISV_SHIFT) #define HSR_SRT_SHIFT (16) #define HSR_SRT_MASK (0xf << HSR_SRT_SHIFT) +#define HSR_CM (1 << 8) #define HSR_FSC (0x3f) #define HSR_FSC_TYPE (0x3c) #define HSR_SSE (1 << 21) diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 40002416efec..e8ef349c04b4 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -167,6 +167,11 @@ static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_ISV; } +static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & (HSR_CM | HSR_WNR | HSR_FSC); +} + static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_WNR; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 5a077f85813f..556cd818eccf 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -78,6 +78,14 @@ struct kvm_arch { /* Mandated version of PSCI */ u32 psci_version; + + /* + * If we encounter a data abort without valid instruction syndrome + * information, report this to user space. User space can (and + * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is + * supported. + */ + bool return_nisv_io_abort_to_user; }; #define KVM_NR_MEM_OBJS 40 diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 2769360f195c..03cd7c19a683 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -131,8 +131,9 @@ struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 684cf64b4033..735f9b007e58 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -255,6 +255,12 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, { events->exception.serror_pending = !!(*vcpu_hcr(vcpu) & HCR_VA); + /* + * We never return a pending ext_dabt here because we deliver it to + * the virtual CPU directly when setting the event and it's no longer + * 'pending' at this point. + */ + return 0; } @@ -263,12 +269,16 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, { bool serror_pending = events->exception.serror_pending; bool has_esr = events->exception.serror_has_esr; + bool ext_dabt_pending = events->exception.ext_dabt_pending; if (serror_pending && has_esr) return -EINVAL; else if (serror_pending) kvm_inject_vabt(vcpu); + if (ext_dabt_pending) + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + return 0; } diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index d69c1efc63e7..a3c967988e1d 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -258,6 +258,11 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV); } +static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC); +} + static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index eb1f33af45aa..b36dae9ee5f9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -84,6 +84,14 @@ struct kvm_arch { /* Mandated version of PSCI */ u32 psci_version; + + /* + * If we encounter a data abort without valid instruction syndrome + * information, report this to user space. User space can (and + * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is + * supported. + */ + bool return_nisv_io_abort_to_user; }; #define KVM_NR_MEM_OBJS 40 diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index cff1ba12c768..820e5751ada7 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -164,8 +164,9 @@ struct kvm_vcpu_events { struct { __u8 serror_pending; __u8 serror_has_esr; + __u8 ext_dabt_pending; /* Align it to 8 bytes */ - __u8 pad[6]; + __u8 pad[5]; __u64 serror_esr; } exception; __u32 reserved[12]; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index d3ac9d2fd405..cd4429bfe5dc 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -712,6 +712,12 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, if (events->exception.serror_pending && events->exception.serror_has_esr) events->exception.serror_esr = vcpu_get_vsesr(vcpu); + /* + * We never return a pending ext_dabt here because we deliver it to + * the virtual CPU directly when setting the event and it's no longer + * 'pending' at this point. + */ + return 0; } @@ -720,6 +726,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, { bool serror_pending = events->exception.serror_pending; bool has_esr = events->exception.serror_has_esr; + bool ext_dabt_pending = events->exception.ext_dabt_pending; if (serror_pending && has_esr) { if (!cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) @@ -733,6 +740,9 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, kvm_inject_vabt(vcpu); } + if (ext_dabt_pending) + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + return 0; } diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index a9d25a305af5..ccdb6a051ab2 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -109,7 +109,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu) /** * kvm_inject_dabt - inject a data abort into the guest - * @vcpu: The VCPU to receive the undefined exception + * @vcpu: The VCPU to receive the data abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the @@ -125,7 +125,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr) /** * kvm_inject_pabt - inject a prefetch abort into the guest - * @vcpu: The VCPU to receive the undefined exception + * @vcpu: The VCPU to receive the prefetch abort * @addr: The address to report in the DFAR * * It is assumed that this code is called from the VCPU thread and that the diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a540c8357049..fb47c0fad6a6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -235,6 +235,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_S390_STSI 25 #define KVM_EXIT_IOAPIC_EOI 26 #define KVM_EXIT_HYPERV 27 +#define KVM_EXIT_ARM_NISV 28 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -394,6 +395,11 @@ struct kvm_run { } eoi; /* KVM_EXIT_HYPERV */ struct kvm_hyperv_exit hyperv; + /* KVM_EXIT_ARM_NISV */ + struct { + __u64 esr_iss; + __u64 fault_ipa; + } arm_nisv; /* Fix the size of the union. */ char padding[256]; }; @@ -1000,6 +1006,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PMU_EVENT_FILTER 173 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174 #define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175 +#define KVM_CAP_ARM_NISV_TO_USER 176 +#define KVM_CAP_ARM_INJECT_EXT_DABT 177 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 2aba375dfd13..c11d6613f4ee 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -102,6 +102,26 @@ int kvm_arch_check_processor_compat(void) return 0; } +int kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_ARM_NISV_TO_USER: + r = 0; + kvm->arch.return_nisv_io_abort_to_user = true; + break; + default: + r = -EINVAL; + break; + } + + return r; +} /** * kvm_arch_init_vm - initializes a VM data structure @@ -201,6 +221,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2: + case KVM_CAP_ARM_NISV_TO_USER: + case KVM_CAP_ARM_INJECT_EXT_DABT: r = 1; break; case KVM_CAP_ARM_SET_DEVICE_ADDR: diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c index 6af5c91337f2..70d3b449692c 100644 --- a/virt/kvm/arm/mmio.c +++ b/virt/kvm/arm/mmio.c @@ -167,7 +167,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, if (ret) return ret; } else { - kvm_err("load/store instruction decoding not implemented\n"); + if (vcpu->kvm->arch.return_nisv_io_abort_to_user) { + run->exit_reason = KVM_EXIT_ARM_NISV; + run->arm_nisv.esr_iss = kvm_vcpu_dabt_iss_nisv_sanitized(vcpu); + run->arm_nisv.fault_ipa = fault_ipa; + return 0; + } + + kvm_pr_unimpl("Data abort outside memslots with no valid syndrome info\n"); return -ENOSYS; } |