diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 8dee8f68fe15..9b847f06cb19 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3110,9 +3110,9 @@ [X86,PV_OPS] Disable paravirtualized VMware scheduler clock and use the default one. - no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting. - steal time is computed, but won't influence scheduler - behaviour + no-steal-acc [X86,KVM,ARM64] Disable paravirtualized steal time + accounting. steal time is computed, but won't + influence scheduler behaviour nolapic [X86-32,APIC] Do not enable or use the local APIC. 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/Documentation/virt/kvm/arm/pvtime.rst b/Documentation/virt/kvm/arm/pvtime.rst new file mode 100644 index 000000000000..2357dd2d8655 --- /dev/null +++ b/Documentation/virt/kvm/arm/pvtime.rst @@ -0,0 +1,80 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Paravirtualized time support for arm64 +====================================== + +Arm specification DEN0057/A defines a standard for paravirtualised time +support for AArch64 guests: + +https://developer.arm.com/docs/den0057/a + +KVM/arm64 implements the stolen time part of this specification by providing +some hypervisor service calls to support a paravirtualized guest obtaining a +view of the amount of time stolen from its execution. + +Two new SMCCC compatible hypercalls are defined: + +* PV_TIME_FEATURES: 0xC5000020 +* PV_TIME_ST: 0xC5000021 + +These are only available in the SMC64/HVC64 calling convention as +paravirtualized time is not available to 32 bit Arm guests. The existence of +the PV_FEATURES hypercall should be probed using the SMCCC 1.1 ARCH_FEATURES +mechanism before calling it. + +PV_TIME_FEATURES + ============= ======== ========== + Function ID: (uint32) 0xC5000020 + PV_call_id: (uint32) The function to query for support. + Currently only PV_TIME_ST is supported. + Return value: (int64) NOT_SUPPORTED (-1) or SUCCESS (0) if the relevant + PV-time feature is supported by the hypervisor. + ============= ======== ========== + +PV_TIME_ST + ============= ======== ========== + Function ID: (uint32) 0xC5000021 + Return value: (int64) IPA of the stolen time data structure for this + VCPU. On failure: + NOT_SUPPORTED (-1) + ============= ======== ========== + +The IPA returned by PV_TIME_ST should be mapped by the guest as normal memory +with inner and outer write back caching attributes, in the inner shareable +domain. A total of 16 bytes from the IPA returned are guaranteed to be +meaningfully filled by the hypervisor (see structure below). + +PV_TIME_ST returns the structure for the calling VCPU. + +Stolen Time +----------- + +The structure pointed to by the PV_TIME_ST hypercall is as follows: + ++-------------+-------------+-------------+----------------------------+ +| Field | Byte Length | Byte Offset | Description | ++=============+=============+=============+============================+ +| Revision | 4 | 0 | Must be 0 for version 1.0 | ++-------------+-------------+-------------+----------------------------+ +| Attributes | 4 | 4 | Must be 0 | ++-------------+-------------+-------------+----------------------------+ +| Stolen time | 8 | 8 | Stolen time in unsigned | +| | | | nanoseconds indicating how | +| | | | much time this VCPU thread | +| | | | was involuntarily not | +| | | | running on a physical CPU. | ++-------------+-------------+-------------+----------------------------+ + +All values in the structure are stored little-endian. + +The structure will be updated by the hypervisor prior to scheduling a VCPU. It +will be present within a reserved region of the normal memory given to the +guest. The guest should not attempt to write into this memory. There is a +structure per VCPU of the guest. + +It is advisable that one or more 64k pages are set aside for the purpose of +these structures and not used for other purposes, this enables the guest to map +the region using 64k pages and avoids conflicting attributes with other memory. + +For the user space interface see Documentation/virt/kvm/devices/vcpu.txt +section "3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL". diff --git a/Documentation/virt/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt index 2b5dab16c4f2..6f3bd64a05b0 100644 --- a/Documentation/virt/kvm/devices/vcpu.txt +++ b/Documentation/virt/kvm/devices/vcpu.txt @@ -60,3 +60,17 @@ time to use the number provided for a given timer, overwriting any previously configured values on other VCPUs. Userspace should configure the interrupt numbers on at least one VCPU after creating all VCPUs and before running any VCPUs. + +3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL +Architectures: ARM64 + +3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA +Parameters: 64-bit base address +Returns: -ENXIO: Stolen time not implemented + -EEXIST: Base address already set for this VCPU + -EINVAL: Base address not 64 byte aligned + +Specifies the base address of the stolen time structure for this VCPU. The +base address must be 64 byte aligned and exist within a valid guest memory +region. See Documentation/virt/kvm/arm/pvtime.txt for more information +including the layout of the stolen time structure. 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..9b118516d2db 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -95,12 +95,12 @@ static inline unsigned long *vcpu_hcr(const struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr; } -static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr &= ~HCR_TWE; } -static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr |= HCR_TWE; } @@ -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 8a37c8e89777..556cd818eccf 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 @@ -38,6 +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); @@ -76,6 +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 @@ -323,6 +333,29 @@ 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; +} + +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/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/Makefile b/arch/arm/kvm/Makefile index b76b75bd9e00..e442d82821df 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -24,7 +24,7 @@ obj-y += kvm-arm.o init.o interrupts.o obj-y += handle_exit.o guest.o emulate.o reset.o obj-y += coproc.o coproc_a15.o coproc_a7.o vgic-v3-coproc.o obj-y += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o -obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o +obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o $(KVM)/arm/hypercalls.o obj-y += $(KVM)/arm/aarch32.o obj-y += $(KVM)/arm/vgic/vgic.o diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 684cf64b4033..0e6f23504c26 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -21,6 +21,10 @@ #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } struct kvm_stats_debugfs_item debugfs_entries[] = { + VCPU_STAT(halt_successful_poll), + VCPU_STAT(halt_attempted_poll), + VCPU_STAT(halt_poll_invalid), + VCPU_STAT(halt_wakeup), VCPU_STAT(hvc_exit_stat), VCPU_STAT(wfe_exit_stat), VCPU_STAT(wfi_exit_stat), @@ -255,6 +259,12 @@ 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 +273,16 @@ 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/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 2a6a1394d26e..e58a89d2f13f 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include "trace.h" diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 9a07916af8dd..7c90b4c615a5 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include #include -#include #include #include @@ -75,26 +74,20 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A72: { struct arm_smccc_res res; - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - break; + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + if ((int)res.a0 != 0) + return; - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: - arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if ((int)res.a0 != 0) - break; + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: per_cpu(harden_branch_predictor_fn, cpu) = call_hvc_arch_workaround_1; cpu_do_switch_mm = cpu_v7_hvc_switch_mm; spectre_v2_method = "hypervisor"; break; - case PSCI_CONDUIT_SMC: - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if ((int)res.a0 != 0) - break; + case SMCCC_CONDUIT_SMC: per_cpu(harden_branch_predictor_fn, cpu) = call_smc_arch_workaround_1; cpu_do_switch_mm = cpu_v7_smc_switch_mm; diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index ddf9d762ac62..6e5d839f42b5 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -61,7 +61,6 @@ * RW: 64bit by default, can be overridden for 32bit VMs * TAC: Trap ACTLR * TSC: Trap SMC - * TVM: Trap VM ops (until M+C set in SCTLR_EL1) * TSW: Trap cache operations by set/way * TWE: Trap WFE * TWI: Trap WFI @@ -74,7 +73,7 @@ * SWIO: Turn set/way invalidates into set/way clean+invalidate */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ - HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ + HCR_BSU_IS | HCR_FB | HCR_TAC | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ HCR_FMO | HCR_IMO) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index d69c1efc63e7..5efe5ca8fecf 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -53,8 +53,18 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) /* trap error record accesses */ vcpu->arch.hcr_el2 |= HCR_TERR; } - if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) + + if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) { vcpu->arch.hcr_el2 |= HCR_FWB; + } else { + /* + * For non-FWB CPUs, we trap VM ops (HCR_EL2.TVM) until M+C + * get set in SCTLR_EL1 such that we can detect when the guest + * MMU gets turned on and do the necessary cache maintenance + * then. + */ + vcpu->arch.hcr_el2 |= HCR_TVM; + } if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) vcpu->arch.hcr_el2 &= ~HCR_RW; @@ -77,14 +87,19 @@ static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu->arch.hcr_el2; } -static inline void vcpu_clear_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_clear_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 &= ~HCR_TWE; + if (atomic_read(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count)) + vcpu->arch.hcr_el2 &= ~HCR_TWI; + else + vcpu->arch.hcr_el2 |= HCR_TWI; } -static inline void vcpu_set_wfe_traps(struct kvm_vcpu *vcpu) +static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 |= HCR_TWE; + vcpu->arch.hcr_el2 |= HCR_TWI; } static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu) @@ -258,6 +273,11 @@ 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 f656169db8c3..b36dae9ee5f9 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); @@ -83,6 +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 @@ -338,6 +347,13 @@ 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() */ @@ -478,6 +494,27 @@ 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); +gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); +void kvm_update_stolen_time(struct kvm_vcpu *vcpu); + +int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr); +int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr); +int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr); + +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); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h index 799d9dd6f7cc..cf3a0fd7c1a7 100644 --- a/arch/arm64/include/asm/paravirt.h +++ b/arch/arm64/include/asm/paravirt.h @@ -21,6 +21,13 @@ static inline u64 paravirt_steal_clock(int cpu) { return pv_ops.time.steal_clock(cpu); } -#endif + +int __init pv_time_init(void); + +#else + +#define pv_time_init() do {} while (0) + +#endif // CONFIG_PARAVIRT #endif 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/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 67c21f9bdbad..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]; @@ -323,6 +324,8 @@ struct kvm_vcpu_events { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_PVTIME_CTRL 2 +#define KVM_ARM_VCPU_PVTIME_IPA 0 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_VCPU2_SHIFT 28 diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 93f34b4eca25..90e8aa63af25 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -6,7 +6,6 @@ */ #include -#include #include #include #include @@ -167,9 +166,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, } #endif /* CONFIG_KVM_INDIRECT_VECTORS */ -#include #include -#include static void call_smc_arch_workaround_1(void) { @@ -213,43 +210,31 @@ static int detect_harden_bp_fw(void) struct arm_smccc_res res; u32 midr = read_cpuid_id(); - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - return -1; + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: - arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - switch ((int)res.a0) { - case 1: - /* Firmware says we're just fine */ - return 0; - case 0: - cb = call_hvc_arch_workaround_1; - /* This is a guest, no need to patch KVM vectors */ - smccc_start = NULL; - smccc_end = NULL; - break; - default: - return -1; - } + switch ((int)res.a0) { + case 1: + /* Firmware says we're just fine */ + return 0; + case 0: + break; + default: + return -1; + } + + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: + cb = call_hvc_arch_workaround_1; + /* This is a guest, no need to patch KVM vectors */ + smccc_start = NULL; + smccc_end = NULL; break; - case PSCI_CONDUIT_SMC: - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - switch ((int)res.a0) { - case 1: - /* Firmware says we're just fine */ - return 0; - case 0: - cb = call_smc_arch_workaround_1; - smccc_start = __smccc_workaround_1_smc_start; - smccc_end = __smccc_workaround_1_smc_end; - break; - default: - return -1; - } + case SMCCC_CONDUIT_SMC: + cb = call_smc_arch_workaround_1; + smccc_start = __smccc_workaround_1_smc_start; + smccc_end = __smccc_workaround_1_smc_end; break; default: @@ -309,11 +294,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt, BUG_ON(nr_inst != 1); - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: insn = aarch64_insn_get_hvc_value(); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: insn = aarch64_insn_get_smc_value(); break; default: @@ -339,6 +324,8 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt, void arm64_set_ssbd_mitigation(bool state) { + int conduit; + if (!IS_ENABLED(CONFIG_ARM64_SSBD)) { pr_info_once("SSBD disabled by kernel configuration\n"); return; @@ -352,19 +339,10 @@ void arm64_set_ssbd_mitigation(bool state) return; } - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: - arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); - break; + conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_WORKAROUND_2, state, + NULL); - case PSCI_CONDUIT_SMC: - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); - break; - - default: - WARN_ON_ONCE(1); - break; - } + WARN_ON_ONCE(conduit == SMCCC_CONDUIT_NONE); } static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, @@ -374,6 +352,7 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, bool required = true; s32 val; bool this_cpu_safe = false; + int conduit; WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); @@ -391,25 +370,10 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, goto out_printmsg; } - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { - ssbd_state = ARM64_SSBD_UNKNOWN; - if (!this_cpu_safe) - __ssb_safe = false; - return false; - } + conduit = arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_2, &res); - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: - arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_2, &res); - break; - - case PSCI_CONDUIT_SMC: - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_2, &res); - break; - - default: + if (conduit == SMCCC_CONDUIT_NONE) { ssbd_state = ARM64_SSBD_UNKNOWN; if (!this_cpu_safe) __ssb_safe = false; diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 4cfed91fe256..1ef702b0be2d 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -6,13 +6,153 @@ * Author: Stefano Stabellini */ +#define pr_fmt(fmt) "arm-pv: " fmt + +#include +#include #include +#include #include +#include +#include +#include +#include #include + #include +#include +#include struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; struct paravirt_patch_template pv_ops; EXPORT_SYMBOL_GPL(pv_ops); + +struct pv_time_stolen_time_region { + struct pvclock_vcpu_stolen_time *kaddr; +}; + +static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region); + +static bool steal_acc = true; +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} + +early_param("no-steal-acc", parse_no_stealacc); + +/* return stolen time in ns by asking the hypervisor */ +static u64 pv_steal_clock(int cpu) +{ + struct pv_time_stolen_time_region *reg; + + reg = per_cpu_ptr(&stolen_time_region, cpu); + if (!reg->kaddr) { + pr_warn_once("stolen time enabled but not configured for cpu %d\n", + cpu); + return 0; + } + + return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); +} + +static int stolen_time_dying_cpu(unsigned int cpu) +{ + struct pv_time_stolen_time_region *reg; + + reg = this_cpu_ptr(&stolen_time_region); + if (!reg->kaddr) + return 0; + + memunmap(reg->kaddr); + memset(reg, 0, sizeof(*reg)); + + return 0; +} + +static int init_stolen_time_cpu(unsigned int cpu) +{ + struct pv_time_stolen_time_region *reg; + struct arm_smccc_res res; + + reg = this_cpu_ptr(&stolen_time_region); + + arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_ST, &res); + + if (res.a0 == SMCCC_RET_NOT_SUPPORTED) + return -EINVAL; + + reg->kaddr = memremap(res.a0, + sizeof(struct pvclock_vcpu_stolen_time), + MEMREMAP_WB); + + if (!reg->kaddr) { + pr_warn("Failed to map stolen time data structure\n"); + return -ENOMEM; + } + + if (le32_to_cpu(reg->kaddr->revision) != 0 || + le32_to_cpu(reg->kaddr->attributes) != 0) { + pr_warn_once("Unexpected revision or attributes in stolen time data\n"); + return -ENXIO; + } + + return 0; +} + +static int pv_time_init_stolen_time(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING, + "hypervisor/arm/pvtime:starting", + init_stolen_time_cpu, stolen_time_dying_cpu); + if (ret < 0) + return ret; + return 0; +} + +static bool has_pv_steal_clock(void) +{ + struct arm_smccc_res res; + + /* To detect the presence of PV time support we require SMCCC 1.1+ */ + if (psci_ops.smccc_version < SMCCC_VERSION_1_1) + return false; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_HV_PV_TIME_FEATURES, &res); + + if (res.a0 != SMCCC_RET_SUCCESS) + return false; + + arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_FEATURES, + ARM_SMCCC_HV_PV_TIME_ST, &res); + + return (res.a0 == SMCCC_RET_SUCCESS); +} + +int __init pv_time_init(void) +{ + int ret; + + if (!has_pv_steal_clock()) + return 0; + + ret = pv_time_init_stolen_time(); + if (ret) + return ret; + + pv_ops.time.steal_clock = pv_steal_clock; + + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + + pr_info("using stolen time PV\n"); + + return 0; +} diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index ea94cf8f9dc6..d6259dac62b6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -2,6 +2,7 @@ // Copyright (C) 2017 Arm Ltd. #define pr_fmt(fmt) "sdei: " fmt +#include #include #include #include @@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit) return 0; } - sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; + sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 if (arm64_kernel_unmapped_at_el0()) { diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 0b2946414dc9..73f06d4b3aae 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -30,6 +30,7 @@ #include #include +#include unsigned long profile_pc(struct pt_regs *regs) { @@ -65,4 +66,6 @@ void __init time_init(void) /* Calibrate the delay loop directly */ lpj_fine = arch_timer_rate / HZ; + + pv_time_init(); } diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index a67121d419a2..a475c68cbfec 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,6 +21,8 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" depends on OF + # for TASKSTATS/TASK_DELAY_ACCT: + depends on NET && MULTIUSER select MMU_NOTIFIER select PREEMPT_NOTIFIERS select HAVE_KVM_CPU_RELAX_INTERCEPT @@ -39,6 +41,8 @@ config KVM select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE + select TASKSTATS + select TASK_DELAY_ACCT ---help--- Support hosting virtualized guest machines. We don't support KVM with 16K page tables yet, due to the multiple diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 3ac1a64d2fb9..5ffbdc39e780 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -13,6 +13,8 @@ obj-$(CONFIG_KVM_ARM_HOST) += hyp/ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o kvm-$(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/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index dfd626447482..2fff06114a8f 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -34,6 +34,10 @@ #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } struct kvm_stats_debugfs_item debugfs_entries[] = { + VCPU_STAT(halt_successful_poll), + VCPU_STAT(halt_attempted_poll), + VCPU_STAT(halt_poll_invalid), + VCPU_STAT(halt_wakeup), VCPU_STAT(hvc_exit_stat), VCPU_STAT(wfe_exit_stat), VCPU_STAT(wfi_exit_stat), @@ -712,6 +716,12 @@ 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 +730,7 @@ 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 +744,9 @@ 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; } @@ -858,6 +872,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_set_attr(vcpu, attr); break; + case KVM_ARM_VCPU_PVTIME_CTRL: + ret = kvm_arm_pvtime_set_attr(vcpu, attr); + break; default: ret = -ENXIO; break; @@ -878,6 +895,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_get_attr(vcpu, attr); break; + case KVM_ARM_VCPU_PVTIME_CTRL: + ret = kvm_arm_pvtime_get_attr(vcpu, attr); + break; default: ret = -ENXIO; break; @@ -898,6 +918,9 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_has_attr(vcpu, attr); break; + case KVM_ARM_VCPU_PVTIME_CTRL: + ret = kvm_arm_pvtime_has_attr(vcpu, attr); + break; default: ret = -ENXIO; break; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 706cca23f0d2..aacfc55de44c 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -11,8 +11,6 @@ #include #include -#include - #include #include #include @@ -22,6 +20,8 @@ #include #include +#include + #define CREATE_TRACE_POINTS #include "trace.h" 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/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 46822afc57e0..9f2165937f7d 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2098,9 +2098,9 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu, WARN_ON(1); } - kvm_err("Unsupported guest CP%d access at: %08lx [%08lx]\n", - cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); - print_sys_reg_instr(params); + print_sys_reg_msg(params, + "Unsupported guest CP%d access at: %08lx [%08lx]\n", + cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); } @@ -2233,6 +2233,12 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run) NULL, 0); } +static bool is_imp_def_sys_reg(struct sys_reg_params *params) +{ + // See ARM DDI 0487E.a, section D12.3.2 + return params->Op0 == 3 && (params->CRn & 0b1011) == 0b1011; +} + static int emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { @@ -2248,10 +2254,12 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, if (likely(r)) { perform_access(vcpu, params, r); + } else if (is_imp_def_sys_reg(params)) { + kvm_inject_undefined(vcpu); } else { - kvm_err("Unsupported guest sys_reg access at: %lx [%08lx]\n", - *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); - print_sys_reg_instr(params); + print_sys_reg_msg(params, + "Unsupported guest sys_reg access at: %lx [%08lx]\n", + *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); } return 1; @@ -2360,8 +2368,11 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG) return NULL; + if (!index_to_params(id, ¶ms)) + return NULL; + table = get_target_table(vcpu->arch.target, true, &num); - r = find_reg_by_id(id, ¶ms, table, num); + r = find_reg(¶ms, table, num); if (!r) r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 9bca0312d798..5a6fc30f5989 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -62,11 +62,24 @@ struct sys_reg_desc { #define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */ #define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */ +static __printf(2, 3) +inline void print_sys_reg_msg(const struct sys_reg_params *p, + char *fmt, ...) +{ + va_list va; + + va_start(va, fmt); + /* Look, we even formatted it for you to paste into the table! */ + kvm_pr_unimpl("%pV { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", + &(struct va_format){ fmt, &va }, + p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read"); + va_end(va); +} + static inline void print_sys_reg_instr(const struct sys_reg_params *p) { - /* Look, we even formatted it for you to paste into the table! */ - kvm_pr_unimpl(" { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", - p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read"); + /* GCC warns on an empty format string */ + print_sys_reg_msg(p, "%s", ""); } static inline bool ignore_write(struct kvm_vcpu *vcpu, diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index 9cd70d1a5622..a479023fa036 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -967,29 +967,29 @@ static int sdei_get_conduit(struct platform_device *pdev) if (np) { if (of_property_read_string(np, "method", &method)) { pr_warn("missing \"method\" property\n"); - return CONDUIT_INVALID; + return SMCCC_CONDUIT_NONE; } if (!strcmp("hvc", method)) { sdei_firmware_call = &sdei_smccc_hvc; - return CONDUIT_HVC; + return SMCCC_CONDUIT_HVC; } else if (!strcmp("smc", method)) { sdei_firmware_call = &sdei_smccc_smc; - return CONDUIT_SMC; + return SMCCC_CONDUIT_SMC; } pr_warn("invalid \"method\" property: %s\n", method); } else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) { if (acpi_psci_use_hvc()) { sdei_firmware_call = &sdei_smccc_hvc; - return CONDUIT_HVC; + return SMCCC_CONDUIT_HVC; } else { sdei_firmware_call = &sdei_smccc_smc; - return CONDUIT_SMC; + return SMCCC_CONDUIT_SMC; } } - return CONDUIT_INVALID; + return SMCCC_CONDUIT_NONE; } static int sdei_probe(struct platform_device *pdev) diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index 84f4ff351c62..b3b6c15e7b36 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -53,10 +53,18 @@ bool psci_tos_resident_on(int cpu) } struct psci_operations psci_ops = { - .conduit = PSCI_CONDUIT_NONE, + .conduit = SMCCC_CONDUIT_NONE, .smccc_version = SMCCC_VERSION_1_0, }; +enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void) +{ + if (psci_ops.smccc_version < SMCCC_VERSION_1_1) + return SMCCC_CONDUIT_NONE; + + return psci_ops.conduit; +} + typedef unsigned long (psci_fn)(unsigned long, unsigned long, unsigned long, unsigned long); static psci_fn *invoke_psci_fn; @@ -212,13 +220,13 @@ static unsigned long psci_migrate_info_up_cpu(void) 0, 0, 0); } -static void set_conduit(enum psci_conduit conduit) +static void set_conduit(enum arm_smccc_conduit conduit) { switch (conduit) { - case PSCI_CONDUIT_HVC: + case SMCCC_CONDUIT_HVC: invoke_psci_fn = __invoke_psci_fn_hvc; break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: invoke_psci_fn = __invoke_psci_fn_smc; break; default: @@ -240,9 +248,9 @@ static int get_set_conduit_method(struct device_node *np) } if (!strcmp("hvc", method)) { - set_conduit(PSCI_CONDUIT_HVC); + set_conduit(SMCCC_CONDUIT_HVC); } else if (!strcmp("smc", method)) { - set_conduit(PSCI_CONDUIT_SMC); + set_conduit(SMCCC_CONDUIT_SMC); } else { pr_warn("invalid \"method\" property: %s\n", method); return -EINVAL; @@ -583,9 +591,9 @@ int __init psci_acpi_init(void) pr_info("probing for conduit method from ACPI.\n"); if (acpi_psci_use_hvc()) - set_conduit(PSCI_CONDUIT_HVC); + set_conduit(SMCCC_CONDUIT_HVC); else - set_conduit(PSCI_CONDUIT_SMC); + set_conduit(SMCCC_CONDUIT_SMC); return psci_probe(); } diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c index 563e87ed0766..45969927cc81 100644 --- a/drivers/irqchip/irq-gic-v4.c +++ b/drivers/irqchip/irq-gic-v4.c @@ -141,12 +141,17 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info) int its_schedule_vpe(struct its_vpe *vpe, bool on) { struct its_cmd_info info; + int ret; WARN_ON(preemptible()); info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE; - return its_send_vpe_cmd(vpe, &info); + ret = its_send_vpe_cmd(vpe, &info); + if (!ret) + vpe->resident = on; + + return ret; } int its_invall_vpe(struct its_vpe *vpe) diff --git a/include/Kbuild b/include/Kbuild index ffba79483cc5..e8154f8bcac5 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -67,6 +67,8 @@ header-test- += keys/big_key-type.h header-test- += keys/request_key_auth-type.h header-test- += keys/trusted.h header-test- += kvm/arm_arch_timer.h +header-test-$(CONFIG_ARM) += kvm/arm_hypercalls.h +header-test-$(CONFIG_ARM64) += kvm/arm_hypercalls.h header-test- += kvm/arm_pmu.h header-test-$(CONFIG_ARM) += kvm/arm_psci.h header-test-$(CONFIG_ARM64) += kvm/arm_psci.h diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h new file mode 100644 index 000000000000..0e2509d27910 --- /dev/null +++ b/include/kvm/arm_hypercalls.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 Arm Ltd. */ + +#ifndef __KVM_ARM_HYPERCALLS_H +#define __KVM_ARM_HYPERCALLS_H + +#include + +int kvm_hvc_call_handler(struct kvm_vcpu *vcpu); + +static inline u32 smccc_get_function(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 0); +} + +static inline unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 1); +} + +static inline unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 2); +} + +static inline unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 3); +} + +static inline void smccc_set_retval(struct kvm_vcpu *vcpu, + unsigned long a0, + unsigned long a1, + unsigned long a2, + unsigned long a3) +{ + vcpu_set_reg(vcpu, 0, a0); + vcpu_set_reg(vcpu, 1, a1); + vcpu_set_reg(vcpu, 2, a2); + vcpu_set_reg(vcpu, 3, a3); +} + +#endif diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 632e78bdef4d..5b58bd2fe088 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -40,7 +40,7 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm) } -int kvm_hvc_call_handler(struct kvm_vcpu *vcpu); +int kvm_psci_call(struct kvm_vcpu *vcpu); struct kvm_one_reg; diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index af4f09c02bf1..9d53f545a3d5 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -240,7 +240,7 @@ struct vgic_dist { * Contains the attributes and gpa of the LPI configuration table. * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share * one address across all redistributors. - * GICv3 spec: 6.1.2 "LPI Configuration tables" + * GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables" */ u64 propbaser; @@ -378,8 +378,6 @@ static inline int kvm_vgic_get_max_vcpus(void) return kvm_vgic_global_state.max_gic_vcpus; } -int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); - /** * kvm_vgic_setup_default_irq_routing: * Setup a default flat gsi routing table mapping all SPIs @@ -396,7 +394,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq, int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); -void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu); -void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu); +int vgic_v4_load(struct kvm_vcpu *vcpu); +int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db); #endif /* __KVM_ARM_VGIC_H */ diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 080012a6f025..59494df0f55b 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 @@ -80,6 +81,22 @@ #include #include + +enum arm_smccc_conduit { + SMCCC_CONDUIT_NONE, + SMCCC_CONDUIT_SMC, + SMCCC_CONDUIT_HVC, +}; + +/** + * arm_smccc_1_1_get_conduit() + * + * Returns the conduit to be used for SMCCCv1.1 or later. + * + * When SMCCCv1.1 is not present, returns SMCCC_CONDUIT_NONE. + */ +enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 @@ -302,5 +319,63 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define SMCCC_RET_NOT_SUPPORTED -1 #define SMCCC_RET_NOT_REQUIRED -2 +/* + * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED. + * Used when the SMCCC conduit is not defined. The empty asm statement + * avoids compiler warnings about unused variables. + */ +#define __fail_smccc_1_1(...) \ + do { \ + __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ + asm ("" __constraints(__count_args(__VA_ARGS__))); \ + if (___res) \ + ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ + } while (0) + +/* + * arm_smccc_1_1_invoke() - make an SMCCC v1.1 compliant call + * + * This is a variadic macro taking one to eight source arguments, and + * an optional return structure. + * + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This macro will make either an HVC call or an SMC call depending on the + * current SMCCC conduit. If no valid conduit is available then -1 + * (SMCCC_RET_NOT_SUPPORTED) is returned in @res.a0 (if supplied). + * + * The return value also provides the conduit that was used. + */ +#define arm_smccc_1_1_invoke(...) ({ \ + int method = arm_smccc_1_1_get_conduit(); \ + switch (method) { \ + case SMCCC_CONDUIT_HVC: \ + arm_smccc_1_1_hvc(__VA_ARGS__); \ + break; \ + case SMCCC_CONDUIT_SMC: \ + arm_smccc_1_1_smc(__VA_ARGS__); \ + break; \ + default: \ + __fail_smccc_1_1(__VA_ARGS__); \ + method = SMCCC_CONDUIT_NONE; \ + break; \ + } \ + method; \ + }) + +/* 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/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 3305ea7f9dc7..0a241c5c911d 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -5,12 +5,6 @@ #include -enum sdei_conduit_types { - CONDUIT_INVALID = 0, - CONDUIT_SMC, - CONDUIT_HVC, -}; - #include #ifdef CONFIG_ARM_SDE_INTERFACE diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 068793a619ca..89d75edb5750 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -136,6 +136,7 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, + CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index e6b155713b47..5dbcfc65f21e 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -32,9 +32,13 @@ struct its_vm { struct its_vpe { struct page *vpt_page; struct its_vm *its_vm; + /* per-vPE VLPI tracking */ + atomic_t vlpi_count; /* Doorbell interrupt */ int irq; irq_hw_number_t vpe_db_lpi; + /* VPE resident */ + bool resident; /* VPE proxy mapping */ int vpe_proxy_event; /* diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d41c521a39da..a0f4c0f9cf3b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -746,6 +746,28 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); + +#define __kvm_put_guest(kvm, gfn, offset, value, type) \ +({ \ + unsigned long __addr = gfn_to_hva(kvm, gfn); \ + type __user *__uaddr = (type __user *)(__addr + offset); \ + int __ret = -EFAULT; \ + \ + if (!kvm_is_error_hva(__addr)) \ + __ret = put_user(value, __uaddr); \ + if (!__ret) \ + mark_page_dirty(kvm, gfn); \ + __ret; \ +}) + +#define kvm_put_guest(kvm, gpa, value, type) \ +({ \ + gpa_t __gpa = gpa; \ + struct kvm *__kvm = kvm; \ + __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ + offset_in_page(__gpa), (value), type); \ +}) + int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); @@ -1241,7 +1263,7 @@ extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { - struct kvm_device_ops *ops; + const struct kvm_device_ops *ops; struct kvm *kvm; void *private; struct list_head vm_node; @@ -1294,7 +1316,7 @@ struct kvm_device_ops { void kvm_device_get(struct kvm_device *dev); void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); -int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type); +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; 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/include/linux/psci.h b/include/linux/psci.h index e2bacc6fd2f2..ebe0a881d13d 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -7,6 +7,7 @@ #ifndef __LINUX_PSCI_H #define __LINUX_PSCI_H +#include #include #include @@ -18,12 +19,6 @@ bool psci_tos_resident_on(int cpu); int psci_cpu_suspend_enter(u32 state); bool psci_power_state_is_valid(u32 state); -enum psci_conduit { - PSCI_CONDUIT_NONE, - PSCI_CONDUIT_SMC, - PSCI_CONDUIT_HVC, -}; - enum smccc_version { SMCCC_VERSION_1_0, SMCCC_VERSION_1_1, @@ -38,7 +33,7 @@ struct psci_operations { int (*affinity_info)(unsigned long target_affinity, unsigned long lowest_affinity_level); int (*migrate_info_type)(void); - enum psci_conduit conduit; + enum arm_smccc_conduit conduit; enum smccc_version smccc_version; }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 52641d8ca9e8..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 @@ -1227,6 +1235,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_XIVE, #define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE + KVM_DEV_TYPE_ARM_PV_TIME, +#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_MAX, }; diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index e2bb5bd60227..f182b2380345 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -80,7 +80,7 @@ static inline bool userspace_irqchip(struct kvm *kvm) static void soft_timer_start(struct hrtimer *hrt, u64 ns) { hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns), - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_HARD); } static void soft_timer_cancel(struct hrtimer *hrt) @@ -697,11 +697,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) update_vtimer_cntvoff(vcpu, kvm_phys_timer_read()); ptimer->cntvoff = 0; - hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); timer->bg_timer.function = kvm_bg_timer_expire; - hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); vtimer->hrtimer.function = kvm_hrtimer_expire; ptimer->hrtimer.function = kvm_hrtimer_expire; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 86c6aa1cb58e..8de4daf25097 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 @@ -98,6 +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 @@ -197,6 +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: @@ -322,20 +348,24 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) /* * If we're about to block (most likely because we've just hit a * WFI), we need to sync back the state of the GIC CPU interface - * so that we have the lastest PMR and group enables. This ensures + * so that we have the latest PMR and group enables. This ensures * that kvm_arch_vcpu_runnable has up-to-date data to decide * whether we have pending interrupts. + * + * For the same reason, we want to tell GICv4 that we need + * doorbells to be signalled, should an interrupt become pending. */ preempt_disable(); kvm_vgic_vmcr_sync(vcpu); + vgic_v4_put(vcpu, true); preempt_enable(); - - kvm_vgic_v4_enable_doorbell(vcpu); } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - kvm_vgic_v4_disable_doorbell(vcpu); + preempt_disable(); + vgic_v4_load(vcpu); + preempt_enable(); } int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) @@ -351,6 +381,8 @@ 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); } @@ -380,11 +412,13 @@ 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); + vcpu_clear_wfx_traps(vcpu); else - vcpu_set_wfe_traps(vcpu); + vcpu_set_wfx_traps(vcpu); vcpu_ptrauth_setup_lazy(vcpu); } @@ -645,6 +679,9 @@ 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); } } @@ -1315,7 +1352,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } } -static void cpu_init_hyp_mode(void *dummy) +static void cpu_init_hyp_mode(void) { phys_addr_t pgd_ptr; unsigned long hyp_stack_ptr; @@ -1349,7 +1386,7 @@ static void cpu_hyp_reinit(void) if (is_kernel_in_hyp_mode()) kvm_timer_init_vhe(); else - cpu_init_hyp_mode(NULL); + cpu_init_hyp_mode(); kvm_arm_init_debug(); diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c new file mode 100644 index 000000000000..550dfa3e53cd --- /dev/null +++ b/virt/kvm/arm/hypercalls.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Arm Ltd. + +#include +#include + +#include + +#include +#include + +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: + val = ARM_SMCCC_VERSION_1_1; + break; + case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: + feature = smccc_get_arg1(vcpu); + switch (feature) { + case ARM_SMCCC_ARCH_WORKAROUND_1: + switch (kvm_arm_harden_branch_predictor()) { + case KVM_BP_HARDEN_UNKNOWN: + break; + case KVM_BP_HARDEN_WA_NEEDED: + val = SMCCC_RET_SUCCESS; + break; + case KVM_BP_HARDEN_NOT_REQUIRED: + val = SMCCC_RET_NOT_REQUIRED; + break; + } + break; + case ARM_SMCCC_ARCH_WORKAROUND_2: + switch (kvm_arm_have_ssbd()) { + case KVM_SSBD_FORCE_DISABLE: + case KVM_SSBD_UNKNOWN: + break; + case KVM_SSBD_KERNEL: + val = SMCCC_RET_SUCCESS; + break; + case KVM_SSBD_FORCE_ENABLE: + case KVM_SSBD_MITIGATED: + val = SMCCC_RET_NOT_REQUIRED; + 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; + 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); + } + + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; +} 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; } diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 38b4c910b6c3..0b32a904a1bb 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -38,6 +38,11 @@ static unsigned long io_map_base; #define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0) #define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1) +static bool is_iomap(unsigned long flags) +{ + return flags & KVM_S2PTE_FLAG_IS_IOMAP; +} + static bool memslot_is_logging(struct kvm_memory_slot *memslot) { return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); @@ -1698,6 +1703,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = vma_kernel_pagesize(vma); if (logging_active || + (vma->vm_flags & VM_PFNMAP) || !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) { force_pte = true; vma_pagesize = PAGE_SIZE; @@ -1760,6 +1766,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, writable = false; } + if (exec_fault && is_iomap(flags)) + return -ENOEXEC; + spin_lock(&kvm->mmu_lock); if (mmu_notifier_retry(kvm, mmu_seq)) goto out_unlock; @@ -1781,7 +1790,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (writable) kvm_set_pfn_dirty(pfn); - if (fault_status != FSC_PERM) + if (fault_status != FSC_PERM && !is_iomap(flags)) clean_dcache_guest_page(pfn, vma_pagesize); if (exec_fault) @@ -1948,9 +1957,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) if (kvm_is_error_hva(hva) || (write_fault && !writable)) { if (is_iabt) { /* Prefetch Abort on I/O address */ - kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - ret = 1; - goto out_unlock; + ret = -ENOEXEC; + goto out; } /* @@ -1992,6 +2000,11 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); if (ret == 0) ret = 1; +out: + if (ret == -ENOEXEC) { + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + ret = 1; + } out_unlock: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; @@ -2301,15 +2314,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (!vma || vma->vm_start >= reg_end) break; - /* - * Mapping a read-only VMA is only allowed if the - * memory region is configured as read-only. - */ - if (writable && !(vma->vm_flags & VM_WRITE)) { - ret = -EPERM; - break; - } - /* * Take the intersection of this VMA with the memory region */ diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 87927f7e1ee7..17e2bdd4b76f 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -15,6 +15,7 @@ #include #include +#include /* * This is an implementation of the Power State Coordination Interface @@ -23,38 +24,6 @@ #define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1) -static u32 smccc_get_function(struct kvm_vcpu *vcpu) -{ - return vcpu_get_reg(vcpu, 0); -} - -static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu) -{ - return vcpu_get_reg(vcpu, 1); -} - -static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu) -{ - return vcpu_get_reg(vcpu, 2); -} - -static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu) -{ - return vcpu_get_reg(vcpu, 3); -} - -static void smccc_set_retval(struct kvm_vcpu *vcpu, - unsigned long a0, - unsigned long a1, - unsigned long a2, - unsigned long a3) -{ - vcpu_set_reg(vcpu, 0, a0); - vcpu_set_reg(vcpu, 1, a1); - vcpu_set_reg(vcpu, 2, a2); - vcpu_set_reg(vcpu, 3, a3); -} - static unsigned long psci_affinity_mask(unsigned long affinity_level) { if (affinity_level <= 3) @@ -373,7 +342,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) * Errors: * -EINVAL: Unrecognized PSCI function */ -static int kvm_psci_call(struct kvm_vcpu *vcpu) +int kvm_psci_call(struct kvm_vcpu *vcpu) { switch (kvm_psci_version(vcpu, vcpu->kvm)) { case KVM_ARM_PSCI_1_0: @@ -387,55 +356,6 @@ static int kvm_psci_call(struct kvm_vcpu *vcpu) }; } -int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) -{ - u32 func_id = smccc_get_function(vcpu); - u32 val = SMCCC_RET_NOT_SUPPORTED; - u32 feature; - - switch (func_id) { - case ARM_SMCCC_VERSION_FUNC_ID: - val = ARM_SMCCC_VERSION_1_1; - break; - case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: - feature = smccc_get_arg1(vcpu); - switch(feature) { - case ARM_SMCCC_ARCH_WORKAROUND_1: - switch (kvm_arm_harden_branch_predictor()) { - case KVM_BP_HARDEN_UNKNOWN: - break; - case KVM_BP_HARDEN_WA_NEEDED: - val = SMCCC_RET_SUCCESS; - break; - case KVM_BP_HARDEN_NOT_REQUIRED: - val = SMCCC_RET_NOT_REQUIRED; - break; - } - break; - case ARM_SMCCC_ARCH_WORKAROUND_2: - switch (kvm_arm_have_ssbd()) { - case KVM_SSBD_FORCE_DISABLE: - case KVM_SSBD_UNKNOWN: - break; - case KVM_SSBD_KERNEL: - val = SMCCC_RET_SUCCESS; - break; - case KVM_SSBD_FORCE_ENABLE: - case KVM_SSBD_MITIGATED: - val = SMCCC_RET_NOT_REQUIRED; - break; - } - break; - } - break; - default: - return kvm_psci_call(vcpu); - } - - smccc_set_retval(vcpu, val, 0, 0, 0); - return 1; -} - int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) { return 3; /* PSCI version and two workaround registers */ diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c new file mode 100644 index 000000000000..1e0f4c284888 --- /dev/null +++ b/virt/kvm/arm/pvtime.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Arm Ltd. + +#include +#include + +#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); + long val = SMCCC_RET_NOT_SUPPORTED; + + 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; +} + +int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *user = (u64 __user *)attr->addr; + struct kvm *kvm = vcpu->kvm; + u64 ipa; + int ret = 0; + int idx; + + if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + return -ENXIO; + + if (get_user(ipa, user)) + return -EFAULT; + if (!IS_ALIGNED(ipa, 64)) + return -EINVAL; + if (vcpu->arch.steal.base != GPA_INVALID) + return -EEXIST; + + /* Check the address is in a valid memslot */ + idx = srcu_read_lock(&kvm->srcu); + if (kvm_is_error_hva(gfn_to_hva(kvm, ipa >> PAGE_SHIFT))) + ret = -EINVAL; + srcu_read_unlock(&kvm->srcu, idx); + + if (!ret) + vcpu->arch.steal.base = ipa; + + return ret; +} + +int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *user = (u64 __user *)attr->addr; + u64 ipa; + + if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + return -ENXIO; + + ipa = vcpu->arch.steal.base; + + if (put_user(ipa, user)) + return -EFAULT; + return 0; +} + +int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_ARM_VCPU_PVTIME_IPA: + return 0; + } + return -ENXIO; +} diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 6f50c429196d..a963b9d766b7 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -70,7 +70,7 @@ void kvm_vgic_early_init(struct kvm *kvm) */ int kvm_vgic_create(struct kvm *kvm, u32 type) { - int i, vcpu_lock_idx = -1, ret; + int i, ret; struct kvm_vcpu *vcpu; if (irqchip_in_kernel(kvm)) @@ -86,17 +86,9 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) !kvm_vgic_global_state.can_emulate_gicv2) return -ENODEV; - /* - * Any time a vcpu is run, vcpu_load is called which tries to grab the - * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure - * that no other VCPUs are run while we create the vgic. - */ ret = -EBUSY; - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!mutex_trylock(&vcpu->mutex)) - goto out_unlock; - vcpu_lock_idx = i; - } + if (!lock_all_vcpus(kvm)) + return ret; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.has_run_once) @@ -125,10 +117,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); out_unlock: - for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { - vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); - mutex_unlock(&vcpu->mutex); - } + unlock_all_vcpus(kvm); return ret; } @@ -177,6 +166,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) break; default: kfree(dist->spis); + dist->spis = NULL; return -EINVAL; } } @@ -203,6 +193,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) INIT_LIST_HEAD(&vgic_cpu->ap_list_head); raw_spin_lock_init(&vgic_cpu->ap_list_lock); + atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0); /* * Enable and configure all SGIs to be edge-triggered and diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 2be6b66b3856..98c7360d9fb7 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -360,7 +360,10 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) if (ret) return ret; + if (map.vpe) + atomic_dec(&map.vpe->vlpi_count); map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + atomic_inc(&map.vpe->vlpi_count); ret = its_map_vlpi(irq->host_irq, &map); } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 8d69f007dd0c..f45635a6f0ec 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -357,14 +357,14 @@ retry: } /** - * vgic_its_save_pending_tables - Save the pending tables into guest RAM + * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ int vgic_v3_save_pending_tables(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - int last_byte_offset = -1; struct vgic_irq *irq; + gpa_t last_ptr = ~(gpa_t)0; int ret; u8 val; @@ -384,11 +384,11 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; - if (byte_offset != last_byte_offset) { + if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; - last_byte_offset = byte_offset; + last_ptr = ptr; } stored = val & (1U << bit_nr); @@ -664,6 +664,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu) if (has_vhe()) __vgic_v3_activate_traps(vcpu); + + WARN_ON(vgic_v4_load(vcpu)); } void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) @@ -676,6 +678,8 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) void vgic_v3_put(struct kvm_vcpu *vcpu) { + WARN_ON(vgic_v4_put(vcpu, false)); + vgic_v3_vmcr_sync(vcpu); kvm_call_hyp(__vgic_v3_save_aprs, vcpu); diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c index 477af6aebb97..46f875589c47 100644 --- a/virt/kvm/arm/vgic/vgic-v4.c +++ b/virt/kvm/arm/vgic/vgic-v4.c @@ -85,6 +85,10 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) { struct kvm_vcpu *vcpu = info; + /* We got the message, no need to fire again */ + if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) + disable_irq_nosync(irq); + vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); @@ -192,20 +196,30 @@ void vgic_v4_teardown(struct kvm *kvm) its_vm->vpes = NULL; } -int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu) +int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db) { - if (!vgic_supports_direct_msis(vcpu->kvm)) + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + struct irq_desc *desc = irq_to_desc(vpe->irq); + + if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; - return its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, false); + /* + * If blocking, a doorbell is required. Undo the nested + * disable_irq() calls... + */ + while (need_db && irqd_irq_disabled(&desc->irq_data)) + enable_irq(vpe->irq); + + return its_schedule_vpe(vpe, false); } -int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) +int vgic_v4_load(struct kvm_vcpu *vcpu) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int err; - if (!vgic_supports_direct_msis(vcpu->kvm)) + if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) return 0; /* @@ -214,11 +228,14 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) * doc in drivers/irqchip/irq-gic-v4.c to understand how this * turns into a VMOVP command at the ITS level. */ - err = irq_set_affinity(irq, cpumask_of(smp_processor_id())); + err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id())); if (err) return err; - err = its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, true); + /* Disabled the doorbell, as we're about to enter the guest */ + disable_irq_nosync(vpe->irq); + + err = its_schedule_vpe(vpe, true); if (err) return err; @@ -226,9 +243,7 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) * Now that the VPE is resident, let's get rid of a potential * doorbell interrupt that would still be pending. */ - err = irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, false); - - return err; + return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false); } static struct vgic_its *vgic_get_its(struct kvm *kvm, @@ -266,7 +281,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, mutex_lock(&its->its_lock); - /* Perform then actual DevID/EventID -> LPI translation. */ + /* Perform the actual DevID/EventID -> LPI translation. */ ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, irq_entry->msi.data, &irq); if (ret) @@ -294,6 +309,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, irq->hw = true; irq->host_irq = virq; + atomic_inc(&map.vpe->vlpi_count); out: mutex_unlock(&its->its_lock); @@ -327,6 +343,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, WARN_ON(!(irq->hw && irq->host_irq == virq)); if (irq->hw) { + atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); irq->hw = false; ret = its_unmap_vlpi(virq); } @@ -335,21 +352,3 @@ out: mutex_unlock(&its->its_lock); return ret; } - -void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu) -{ - if (vgic_supports_direct_msis(vcpu->kvm)) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; - if (irq) - enable_irq(irq); - } -} - -void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu) -{ - if (vgic_supports_direct_msis(vcpu->kvm)) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; - if (irq) - disable_irq(irq); - } -} diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 45a870cb63f5..99b02ca730a8 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -857,8 +857,6 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - WARN_ON(vgic_v4_sync_hwstate(vcpu)); - /* An empty ap_list_head implies used_lrs == 0 */ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) return; @@ -882,8 +880,6 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu) /* Flush our emulation state into the GIC hardware before entering the guest. */ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) { - WARN_ON(vgic_v4_flush_hwstate(vcpu)); - /* * If there are no virtual interrupts active or pending for this * VCPU, then there is no work to do and we can bail out without diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 83066a81b16a..c7fefd6b1c80 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -316,7 +316,5 @@ void vgic_its_invalidate_cache(struct kvm *kvm); bool vgic_supports_direct_msis(struct kvm *kvm); int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); -int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu); -int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu); #endif diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 13efc291b1c7..fef50464d56a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3115,14 +3115,14 @@ struct kvm_device *kvm_device_from_filp(struct file *filp) return filp->private_data; } -static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { +static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { #ifdef CONFIG_KVM_MPIC [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, #endif }; -int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type) +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type) { if (type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENOSPC; @@ -3143,7 +3143,7 @@ void kvm_unregister_device_ops(u32 type) static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { - struct kvm_device_ops *ops = NULL; + const struct kvm_device_ops *ops = NULL; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int type;