From c726200dd106d4c58a281eea7159b8ba28a4ab34 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Fri, 11 Oct 2019 13:07:05 +0200 Subject: KVM: arm/arm64: Allow reporting non-ISV data aborts to userspace For a long time, if a guest accessed memory outside of a memslot using any of the load/store instructions in the architecture which doesn't supply decoding information in the ESR_EL2 (the ISV bit is not set), the kernel would print the following message and terminate the VM as a result of returning -ENOSYS to userspace: load/store instruction decoding not implemented The reason behind this message is that KVM assumes that all accesses outside a memslot is an MMIO access which should be handled by userspace, and we originally expected to eventually implement some sort of decoding of load/store instructions where the ISV bit was not set. However, it turns out that many of the instructions which don't provide decoding information on abort are not safe to use for MMIO accesses, and the remaining few that would potentially make sense to use on MMIO accesses, such as those with register writeback, are not used in practice. It also turns out that fetching an instruction from guest memory can be a pretty horrible affair, involving stopping all CPUs on SMP systems, handling multiple corner cases of address translation in software, and more. It doesn't appear likely that we'll ever implement this in the kernel. What is much more common is that a user has misconfigured his/her guest and is actually not accessing an MMIO region, but just hitting some random hole in the IPA space. In this scenario, the error message above is almost misleading and has led to a great deal of confusion over the years. It is, nevertheless, ABI to userspace, and we therefore need to introduce a new capability that userspace explicitly enables to change behavior. This patch introduces KVM_CAP_ARM_NISV_TO_USER (NISV meaning Non-ISV) which does exactly that, and introduces a new exit reason to report the event to userspace. User space can then emulate an exception to the guest, restart the guest, suspend the guest, or take any other appropriate action as per the policy of the running system. Reported-by: Heinrich Schuchardt Signed-off-by: Christoffer Dall Reviewed-by: Alexander Graf Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/arm/include/asm/kvm_host.h') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 8a37c8e89777..19a92c49039c 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -76,6 +76,14 @@ 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 -- cgit v1.2.3-59-g8ed1b From b48c1a45a190898103cec28771efc399fd65a05a Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:16 +0100 Subject: KVM: arm64: Implement PV_TIME_FEATURES call This provides a mechanism for querying which paravirtualized time features are available in this hypervisor. Also add the header file which defines the ABI for the paravirtualized time features we're about to add. Signed-off-by: Steven Price Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 6 ++++++ arch/arm64/include/asm/kvm_host.h | 2 ++ arch/arm64/include/asm/pvclock-abi.h | 17 +++++++++++++++++ arch/arm64/kvm/Makefile | 1 + include/linux/arm-smccc.h | 14 ++++++++++++++ virt/kvm/arm/hypercalls.c | 8 +++++++- virt/kvm/arm/pvtime.c | 20 ++++++++++++++++++++ 7 files changed, 67 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/include/asm/pvclock-abi.h create mode 100644 virt/kvm/arm/pvtime.c (limited to 'arch/arm/include/asm/kvm_host.h') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 8a37c8e89777..5a0c3569ebde 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -7,6 +7,7 @@ #ifndef __ARM_KVM_HOST_H__ #define __ARM_KVM_HOST_H__ +#include #include #include #include @@ -323,6 +324,11 @@ static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) int kvm_perf_init(void); int kvm_perf_teardown(void); +static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) +{ + return SMCCC_RET_NOT_SUPPORTED; +} + void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f656169db8c3..93b46d9526d0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -478,6 +478,8 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run, int kvm_perf_init(void); int kvm_perf_teardown(void); +long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); + void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); diff --git a/arch/arm64/include/asm/pvclock-abi.h b/arch/arm64/include/asm/pvclock-abi.h new file mode 100644 index 000000000000..c4f1c0a0789c --- /dev/null +++ b/arch/arm64/include/asm/pvclock-abi.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 Arm Ltd. */ + +#ifndef __ASM_PVCLOCK_ABI_H +#define __ASM_PVCLOCK_ABI_H + +/* The below structure is defined in ARM DEN0057A */ + +struct pvclock_vcpu_stolen_time { + __le32 revision; + __le32 attributes; + __le64 stolen_time; + /* Structure must be 64 byte aligned, pad to that size */ + u8 padding[48]; +} __packed; + +#endif diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 73dce4d47d47..5ffbdc39e780 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -14,6 +14,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/e kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.o kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index df01a8579034..92e0046ce7a7 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -45,6 +45,7 @@ #define ARM_SMCCC_OWNER_SIP 2 #define ARM_SMCCC_OWNER_OEM 3 #define ARM_SMCCC_OWNER_STANDARD 4 +#define ARM_SMCCC_OWNER_STANDARD_HYP 5 #define ARM_SMCCC_OWNER_TRUSTED_APP 48 #define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 #define ARM_SMCCC_OWNER_TRUSTED_OS 50 @@ -318,5 +319,18 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define SMCCC_RET_NOT_SUPPORTED -1 #define SMCCC_RET_NOT_REQUIRED -2 +/* Paravirtualised time calls (defined by ARM DEN0057A) */ +#define ARM_SMCCC_HV_PV_TIME_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x20) + +#define ARM_SMCCC_HV_PV_TIME_ST \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x21) + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c index f875241bd030..97ea8b133e77 100644 --- a/virt/kvm/arm/hypercalls.c +++ b/virt/kvm/arm/hypercalls.c @@ -12,7 +12,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) { u32 func_id = smccc_get_function(vcpu); - u32 val = SMCCC_RET_NOT_SUPPORTED; + long val = SMCCC_RET_NOT_SUPPORTED; u32 feature; switch (func_id) { @@ -48,8 +48,14 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; } break; + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = SMCCC_RET_SUCCESS; + break; } break; + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = kvm_hypercall_pv_features(vcpu); + break; default: return kvm_psci_call(vcpu); } diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c new file mode 100644 index 000000000000..9fc69fc2d683 --- /dev/null +++ b/virt/kvm/arm/pvtime.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Arm Ltd. + +#include + +#include + +long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) +{ + u32 feature = smccc_get_arg1(vcpu); + long val = SMCCC_RET_NOT_SUPPORTED; + + switch (feature) { + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = SMCCC_RET_SUCCESS; + break; + } + + return val; +} -- cgit v1.2.3-59-g8ed1b From 8564d6372a7d8a6d440441b8ed8020f97f744450 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:18 +0100 Subject: KVM: arm64: Support stolen time reporting via shared structure Implement the service call for configuring a shared structure between a VCPU and the hypervisor in which the hypervisor can write the time stolen from the VCPU's execution time by other tasks on the host. User space allocates memory which is placed at an IPA also chosen by user space. The hypervisor then updates the shared structure using kvm_put_guest() to ensure single copy atomicity of the 64-bit value reporting the stolen time in nanoseconds. Whenever stolen time is enabled by the guest, the stolen time counter is reset. The stolen time itself is retrieved from the sched_info structure maintained by the Linux scheduler code. We enable SCHEDSTATS when selecting KVM Kconfig to ensure this value is meaningful. Signed-off-by: Steven Price Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 19 ++++++++++++++ arch/arm64/include/asm/kvm_host.h | 20 +++++++++++++++ arch/arm64/kvm/Kconfig | 1 + include/linux/kvm_types.h | 2 ++ virt/kvm/arm/arm.c | 11 +++++++++ virt/kvm/arm/hypercalls.c | 6 +++++ virt/kvm/arm/pvtime.c | 52 +++++++++++++++++++++++++++++++++++++++ 7 files changed, 111 insertions(+) (limited to 'arch/arm/include/asm/kvm_host.h') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 5a0c3569ebde..5a077f85813f 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_RECORD_STEAL KVM_ARCH_REQ(3) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -329,6 +330,24 @@ static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) return SMCCC_RET_NOT_SUPPORTED; } +static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) +{ + return GPA_INVALID; +} + +static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) +{ +} + +static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) +{ + return false; +} + void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 93b46d9526d0..75ef37f79633 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_RECORD_STEAL KVM_ARCH_REQ(3) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -338,6 +339,13 @@ struct kvm_vcpu_arch { /* True when deferrable sysregs are loaded on the physical CPU, * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ bool sysregs_loaded_on_cpu; + + /* Guest PV state */ + struct { + u64 steal; + u64 last_steal; + gpa_t base; + } steal; }; /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ @@ -479,6 +487,18 @@ int kvm_perf_init(void); int kvm_perf_teardown(void); long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); +gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); +void kvm_update_stolen_time(struct kvm_vcpu *vcpu); + +static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) +{ + vcpu_arch->steal.base = GPA_INVALID; +} + +static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) +{ + return (vcpu_arch->steal.base != GPA_INVALID); +} void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index a67121d419a2..d8b88e40d223 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ config KVM select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE + select SCHEDSTATS ---help--- Support hosting virtualized guest machines. We don't support KVM with 16K page tables yet, due to the multiple diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index bde5374ae021..1c88e69db3d9 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -35,6 +35,8 @@ typedef unsigned long gva_t; typedef u64 gpa_t; typedef u64 gfn_t; +#define GPA_INVALID (~(gpa_t)0) + typedef unsigned long hva_t; typedef u64 hpa_t; typedef u64 hfn_t; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 86c6aa1cb58e..2aba375dfd13 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -40,6 +40,10 @@ #include #include +#include +#include +#include + #ifdef REQUIRES_VIRT __asm__(".arch_extension virt"); #endif @@ -351,6 +355,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm_arm_reset_debug_ptr(vcpu); + kvm_arm_pvtime_vcpu_init(&vcpu->arch); + return kvm_vgic_vcpu_init(vcpu); } @@ -380,6 +386,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vcpu_load_sysregs(vcpu); kvm_arch_vcpu_load_fp(vcpu); kvm_vcpu_pmu_restore_guest(vcpu); + if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) + kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu); if (single_task_running()) vcpu_clear_wfe_traps(vcpu); @@ -645,6 +653,9 @@ 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_RECORD_STEAL, vcpu)) + kvm_update_stolen_time(vcpu); } } diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c index 97ea8b133e77..550dfa3e53cd 100644 --- a/virt/kvm/arm/hypercalls.c +++ b/virt/kvm/arm/hypercalls.c @@ -14,6 +14,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) u32 func_id = smccc_get_function(vcpu); long val = SMCCC_RET_NOT_SUPPORTED; u32 feature; + gpa_t gpa; switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: @@ -56,6 +57,11 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) case ARM_SMCCC_HV_PV_TIME_FEATURES: val = kvm_hypercall_pv_features(vcpu); break; + case ARM_SMCCC_HV_PV_TIME_ST: + gpa = kvm_init_stolen_time(vcpu); + if (gpa != GPA_INVALID) + val = gpa; + break; default: return kvm_psci_call(vcpu); } diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c index 9fc69fc2d683..b90b3a7bea85 100644 --- a/virt/kvm/arm/pvtime.c +++ b/virt/kvm/arm/pvtime.c @@ -3,8 +3,35 @@ #include +#include + #include +void kvm_update_stolen_time(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u64 steal; + __le64 steal_le; + u64 offset; + int idx; + u64 base = vcpu->arch.steal.base; + + if (base == GPA_INVALID) + return; + + /* Let's do the local bookkeeping */ + steal = vcpu->arch.steal.steal; + steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal; + vcpu->arch.steal.last_steal = current->sched_info.run_delay; + vcpu->arch.steal.steal = steal; + + steal_le = cpu_to_le64(steal); + idx = srcu_read_lock(&kvm->srcu); + offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time); + kvm_put_guest(kvm, base + offset, steal_le, u64); + srcu_read_unlock(&kvm->srcu, idx); +} + long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) { u32 feature = smccc_get_arg1(vcpu); @@ -12,9 +39,34 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: + case ARM_SMCCC_HV_PV_TIME_ST: val = SMCCC_RET_SUCCESS; break; } return val; } + +gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) +{ + struct pvclock_vcpu_stolen_time init_values = {}; + struct kvm *kvm = vcpu->kvm; + u64 base = vcpu->arch.steal.base; + int idx; + + if (base == GPA_INVALID) + return base; + + /* + * Start counting stolen time from the time the guest requests + * the feature enabled. + */ + vcpu->arch.steal.steal = 0; + vcpu->arch.steal.last_steal = current->sched_info.run_delay; + + idx = srcu_read_lock(&kvm->srcu); + kvm_write_guest(kvm, base, &init_values, sizeof(init_values)); + srcu_read_unlock(&kvm->srcu, idx); + + return base; +} -- cgit v1.2.3-59-g8ed1b