diff options
28 files changed, 290 insertions, 287 deletions
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 0dd5d8733dd5..deb494f759ed 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5343,9 +5343,9 @@ KVM_XEN_ATTR_TYPE_SHARED_INFO 32 vCPUs in the shared_info page, KVM does not automatically do so and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used explicitly even when the vcpu_info for a given vCPU resides at the - "default" location in the shared_info page. This is because KVM is - not aware of the Xen CPU id which is used as the index into the - vcpu_info[] array, so cannot know the correct default location. + "default" location in the shared_info page. This is because KVM may + not be aware of the Xen CPU id which is used as the index into the + vcpu_info[] array, so may know the correct default location. Note that the shared info page may be constantly written to by KVM; it contains the event channel bitmap used to deliver interrupts to @@ -5356,23 +5356,29 @@ KVM_XEN_ATTR_TYPE_SHARED_INFO any vCPU has been running or any event channel interrupts can be routed to the guest. + Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared info + page. + KVM_XEN_ATTR_TYPE_UPCALL_VECTOR Sets the exception vector used to deliver Xen event channel upcalls. This is the HVM-wide vector injected directly by the hypervisor (not through the local APIC), typically configured by a guest via - HVM_PARAM_CALLBACK_IRQ. + HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest + SHUTDOWN_soft_reset) by setting it to zero. KVM_XEN_ATTR_TYPE_EVTCHN This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures an outbound port number for interception of EVTCHNOP_send requests - from the guest. A given sending port number may be directed back - to a specified vCPU (by APIC ID) / port / priority on the guest, - or to trigger events on an eventfd. The vCPU and priority can be - changed by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, - but other fields cannot change for a given sending port. A port - mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags - field. + from the guest. A given sending port number may be directed back to + a specified vCPU (by APIC ID) / port / priority on the guest, or to + trigger events on an eventfd. The vCPU and priority can be changed + by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other + fields cannot change for a given sending port. A port mapping is + removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing + KVM_XEN_EVTCHN_RESET in the flags field removes all interception of + outbound event channels. The values of the flags field are mutually + exclusive and cannot be combined as a bitmask. KVM_XEN_ATTR_TYPE_XEN_VERSION This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates @@ -5388,7 +5394,7 @@ KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read other vCPUs' vcpu_runstate_info. Xen guests enable this feature via - the VM_ASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist + the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist hypercall. 4.127 KVM_XEN_HVM_GET_ATTR @@ -5446,15 +5452,18 @@ KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO As with the shared_info page for the VM, the corresponding page may be dirtied at any time if event channel interrupt delivery is enabled, so userspace should always assume that the page is dirty without relying - on dirty logging. + on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable + the vcpu_info. KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO Sets the guest physical address of an additional pvclock structure for a given vCPU. This is typically used for guest vsyscall support. + Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure. KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR Sets the guest physical address of the vcpu_runstate_info for a given vCPU. This is how a Xen guest tracks CPU state such as steal time. + Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area. KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of @@ -5487,7 +5496,8 @@ KVM_XEN_VCPU_ATTR_TYPE_TIMER This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the event channel port/priority for the VIRQ_TIMER of the vCPU, as well - as allowing a pending timer to be saved/restored. + as allowing a pending timer to be saved/restored. Setting the timer + port to zero disables kernel handling of the singleshot timer. KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates @@ -5495,7 +5505,8 @@ KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR per-vCPU local APIC upcall vector, configured by a Xen guest with the HVMOP_set_evtchn_upcall_vector hypercall. This is typically used by Windows guests, and is distinct from the HVM-wide upcall - vector configured with HVM_PARAM_CALLBACK_IRQ. + vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by + setting the vector to zero. 4.129 KVM_XEN_VCPU_GET_ATTR @@ -6577,11 +6588,6 @@ Please note that the kernel is allowed to use the kvm_run structure as the primary storage for certain register types. Therefore, the kernel may use the values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set. -:: - - }; - - 6. Capabilities that can be enabled on vCPUs ============================================ diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 845a561629f1..a3ca76f9be75 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -16,17 +16,26 @@ The acquisition orders for mutexes are as follows: - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring them together is quite rare. -- Unlike kvm->slots_lock, kvm->slots_arch_lock is released before - synchronize_srcu(&kvm->srcu). Therefore kvm->slots_arch_lock - can be taken inside a kvm->srcu read-side critical section, - while kvm->slots_lock cannot. - - kvm->mn_active_invalidate_count ensures that pairs of invalidate_range_start() and invalidate_range_end() callbacks use the same memslots array. kvm->slots_lock and kvm->slots_arch_lock are taken on the waiting side in install_new_memslots, so MMU notifiers must not take either kvm->slots_lock or kvm->slots_arch_lock. +For SRCU: + +- ``synchronize_srcu(&kvm->srcu)`` is called _inside_ + the kvm->slots_lock critical section, therefore kvm->slots_lock + cannot be taken inside a kvm->srcu read-side critical section. + Instead, kvm->slots_arch_lock is released before the call + to ``synchronize_srcu()`` and _can_ be taken inside a + kvm->srcu read-side critical section. + +- kvm->lock is taken inside kvm->srcu, therefore + ``synchronize_srcu(&kvm->srcu)`` cannot be called inside + a kvm->lock critical section. If you cannot delay the + call until after kvm->lock is released, use ``call_srcu``. + On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock diff --git a/MAINTAINERS b/MAINTAINERS index f61eb221415b..7ba3be035565 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11468,7 +11468,7 @@ F: arch/x86/kvm/hyperv.* F: arch/x86/kvm/kvm_onhyperv.* F: arch/x86/kvm/svm/hyperv.* F: arch/x86/kvm/svm/svm_onhyperv.* -F: arch/x86/kvm/vmx/evmcs.* +F: arch/x86/kvm/vmx/hyperv.* KVM X86 Xen (KVM/Xen) M: David Woodhouse <dwmw2@infradead.org> diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2c7f2a26421e..e8296942a868 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1769,6 +1769,7 @@ static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_ba } struct kvm_hv_hcall { + /* Hypercall input data */ u64 param; u64 ingpa; u64 outgpa; @@ -1779,12 +1780,21 @@ struct kvm_hv_hcall { bool fast; bool rep; sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; + + /* + * Current read offset when KVM reads hypercall input data gradually, + * either offset in bytes from 'ingpa' for regular hypercalls or the + * number of already consumed 'XMM halves' for 'fast' hypercalls. + */ + union { + gpa_t data_offset; + int consumed_xmm_halves; + }; }; static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, - u16 orig_cnt, u16 cnt_cap, u64 *data, - int consumed_xmm_halves, gpa_t offset) + u16 orig_cnt, u16 cnt_cap, u64 *data) { /* * Preserve the original count when ignoring entries via a "cap", KVM @@ -1799,11 +1809,11 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, * Each XMM holds two sparse banks, but do not count halves that * have already been consumed for hypercall parameters. */ - if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) + if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves) return HV_STATUS_INVALID_HYPERCALL_INPUT; for (i = 0; i < cnt; i++) { - j = i + consumed_xmm_halves; + j = i + hc->consumed_xmm_halves; if (j % 2) data[i] = sse128_hi(hc->xmm[j / 2]); else @@ -1812,27 +1822,24 @@ static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, return 0; } - return kvm_read_guest(kvm, hc->ingpa + offset, data, + return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data, cnt * sizeof(*data)); } static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, - u64 *sparse_banks, int consumed_xmm_halves, - gpa_t offset) + u64 *sparse_banks) { if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS) return -EINVAL; /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */ return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS, - sparse_banks, consumed_xmm_halves, offset); + sparse_banks); } -static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[], - int consumed_xmm_halves, gpa_t offset) +static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[]) { - return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, - entries, consumed_xmm_halves, offset); + return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries); } static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu, @@ -1926,8 +1933,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct kvm_vcpu *v; unsigned long i; bool all_cpus; - int consumed_xmm_halves = 0; - gpa_t data_offset; /* * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS @@ -1955,12 +1960,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush.address_space = hc->ingpa; flush.flags = hc->outgpa; flush.processor_mask = sse128_lo(hc->xmm[0]); - consumed_xmm_halves = 1; + hc->consumed_xmm_halves = 1; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush, sizeof(flush)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush); + hc->data_offset = sizeof(flush); } trace_kvm_hv_flush_tlb(flush.processor_mask, @@ -1985,12 +1990,12 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush_ex.flags = hc->outgpa; memcpy(&flush_ex.hv_vp_set, &hc->xmm[0], sizeof(hc->xmm[0])); - consumed_xmm_halves = 2; + hc->consumed_xmm_halves = 2; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, sizeof(flush_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; - data_offset = sizeof(flush_ex); + hc->data_offset = sizeof(flush_ex); } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, @@ -2009,8 +2014,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, - consumed_xmm_halves, data_offset)) + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } @@ -2021,8 +2025,10 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) * consumed_xmm_halves to make sure TLB flush entries are read * from the correct offset. */ - data_offset += hc->var_cnt * sizeof(sparse_banks[0]); - consumed_xmm_halves += hc->var_cnt; + if (hc->fast) + hc->consumed_xmm_halves += hc->var_cnt; + else + hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]); } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || @@ -2030,8 +2036,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) { tlb_flush_entries = NULL; } else { - if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries, - consumed_xmm_halves, data_offset)) + if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries)) return HV_STATUS_INVALID_HYPERCALL_INPUT; tlb_flush_entries = __tlb_flush_entries; } @@ -2180,9 +2185,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1, - offsetof(struct hv_send_ipi_ex, - vp_set.bank_contents))) + if (!hc->fast) + hc->data_offset = offsetof(struct hv_send_ipi_ex, + vp_set.bank_contents); + else + hc->consumed_xmm_halves = 1; + + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks)) return HV_STATUS_INVALID_HYPERCALL_INPUT; } diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 0687162c4f22..3742d9adacfc 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -426,8 +426,9 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); if (irq.trig_mode && - kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, - irq.dest_id, irq.dest_mode)) + (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, + irq.dest_id, irq.dest_mode) || + kvm_apic_pending_eoi(vcpu, irq.vector))) __set_bit(irq.vector, ioapic_handled_vectors); } } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 28e3769066e2..58c3242fcc7a 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -188,11 +188,11 @@ static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) extern struct static_key_false_deferred apic_hw_disabled; -static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic) +static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic) { if (static_branch_unlikely(&apic_hw_disabled.key)) return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; - return MSR_IA32_APICBASE_ENABLE; + return true; } extern struct static_key_false_deferred apic_sw_disabled; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 1f03701b943a..6f54dc9409c9 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -363,7 +363,7 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, * A shadow-present leaf SPTE may be non-writable for 4 possible reasons: * * 1. To intercept writes for dirty logging. KVM write-protects huge pages - * so that they can be split be split down into the dirty logging + * so that they can be split down into the dirty logging * granularity (4KiB) whenever the guest writes to them. KVM also * write-protects 4KiB pages so that writes can be recorded in the dirty log * (e.g. if not using PML). SPTEs are write-protected for dirty logging diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 771210ce5181..d6df38d371a0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1074,7 +1074,9 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int ret = RET_PF_FIXED; bool wrprot = false; - WARN_ON(sp->role.level != fault->goal_level); + if (WARN_ON_ONCE(sp->role.level != fault->goal_level)) + return RET_PF_RETRY; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else @@ -1173,9 +1175,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, iter.old_spte, iter.level); - if (iter.level == fault->goal_level) - break; - /* * If SPTE has been frozen by another thread, just give up and * retry, avoiding unnecessary page table allocation and free. @@ -1183,6 +1182,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (is_removed_spte(iter.old_spte)) goto retry; + if (iter.level == fault->goal_level) + goto map_target_level; + /* Step down into the lower level page table if it exists. */ if (is_shadow_present_pte(iter.old_spte) && !is_large_pte(iter.old_spte)) @@ -1203,8 +1205,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) r = tdp_mmu_link_sp(kvm, &iter, sp, true); /* - * Also force the guest to retry the access if the upper level SPTEs - * aren't in place. + * Force the guest to retry if installing an upper level SPTE + * failed, e.g. because a different task modified the SPTE. */ if (r) { tdp_mmu_free_sp(sp); @@ -1214,11 +1216,20 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->huge_page_disallowed && fault->req_level >= iter.level) { spin_lock(&kvm->arch.tdp_mmu_pages_lock); - track_possible_nx_huge_page(kvm, sp); + if (sp->nx_huge_page_disallowed) + track_possible_nx_huge_page(kvm, sp); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } } + /* + * The walk aborted before reaching the target level, e.g. because the + * iterator detected an upper level SPTE was frozen during traversal. + */ + WARN_ON_ONCE(iter.level == fault->goal_level); + goto retry; + +map_target_level: ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter); retry: diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 684393c22105..eb594620dd75 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -238,7 +238,8 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return false; /* recalibrate sample period and check if it's accepted by perf core */ - if (perf_event_period(pmc->perf_event, + if (is_sampling_event(pmc->perf_event) && + perf_event_period(pmc->perf_event, get_sample_period(pmc, pmc->counter))) return false; diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 85ff3c0588ba..cdb91009701d 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -140,7 +140,8 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) static inline void pmc_update_sample_period(struct kvm_pmc *pmc) { - if (!pmc->perf_event || pmc->is_paused) + if (!pmc->perf_event || pmc->is_paused || + !is_sampling_event(pmc->perf_event)) return; perf_event_period(pmc->perf_event, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b6f4411b613e..d93c715cda6a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5296,10 +5296,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); - kvm_vcpu_write_guest(vcpu, - vmptr + offsetof(struct vmcs12, - launch_state), - &zero, sizeof(zero)); + /* + * Silently ignore memory errors on VMCLEAR, Intel's pseudocode + * for VMCLEAR includes a "ensure that data for VMCS referenced + * by the operand is in memory" clause that guards writes to + * memory, i.e. doing nothing for I/O is architecturally valid. + * + * FIXME: Suppress failures if and only if no memslot is found, + * i.e. exit to userspace if __copy_to_user() fails. + */ + (void)kvm_vcpu_write_guest(vcpu, + vmptr + offsetof(struct vmcs12, + launch_state), + &zero, sizeof(zero)); } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { nested_release_evmcs(vcpu); } @@ -6873,7 +6882,8 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_TSC_SCALING; + SECONDARY_EXEC_TSC_SCALING | + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; /* * We can emulate "VMCS shadowing," even if the hardware diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index fe5615fd8295..fc9008dbed33 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4459,6 +4459,13 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * controls for features that are/aren't exposed to the guest. */ if (nested) { + /* + * All features that can be added or removed to VMX MSRs must + * be supported in the first place for nested virtualization. + */ + if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control))) + enabled = false; + if (enabled) vmx->nested.msrs.secondary_ctls_high |= control; else diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 312aea1854ae..da4bbd043a7b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13132,6 +13132,9 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e) { if (r == X86EMUL_PROPAGATE_FAULT) { + if (KVM_BUG_ON(!e, vcpu->kvm)) + return -EIO; + kvm_inject_emulated_page_fault(vcpu, e); return 1; } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index d7af40240248..2e29bdc2949c 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -41,7 +41,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int ret = 0; int idx = srcu_read_lock(&kvm->srcu); - if (gfn == GPA_INVALID) { + if (gfn == KVM_XEN_INVALID_GFN) { kvm_gpc_deactivate(gpc); goto out; } @@ -659,7 +659,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) if (kvm->arch.xen.shinfo_cache.active) data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); else - data->u.shared_info.gfn = GPA_INVALID; + data->u.shared_info.gfn = KVM_XEN_INVALID_GFN; r = 0; break; @@ -705,7 +705,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) BUILD_BUG_ON(offsetof(struct vcpu_info, time) != offsetof(struct compat_vcpu_info, time)); - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); r = 0; break; @@ -719,7 +719,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; @@ -739,7 +739,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) r = -EOPNOTSUPP; break; } - if (data->u.gpa == GPA_INVALID) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { r = 0; deactivate_out: kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache); @@ -937,7 +937,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) if (vcpu->arch.xen.vcpu_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -945,7 +945,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) if (vcpu->arch.xen.vcpu_time_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; else - data->u.gpa = GPA_INVALID; + data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; @@ -1069,6 +1069,7 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 : kvm->arch.xen_hvm_config.blob_size_32; u8 *page; + int ret; if (page_num >= blob_size) return 1; @@ -1079,10 +1080,10 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) if (IS_ERR(page)) return PTR_ERR(page); - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { - kfree(page); + ret = kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE); + kfree(page); + if (ret) return 1; - } } return 0; } @@ -1183,30 +1184,22 @@ static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, u64 param, u64 *r) { - int idx, i; struct sched_poll sched_poll; evtchn_port_t port, *ports; - gpa_t gpa; + struct x86_exception e; + int i; if (!lapic_in_kernel(vcpu) || !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND)) return false; - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - if (!gpa) { - *r = -EFAULT; - return true; - } - if (IS_ENABLED(CONFIG_64BIT) && !longmode) { struct compat_sched_poll sp32; /* Sanity check that the compat struct definition is correct */ BUILD_BUG_ON(sizeof(sp32) != 16); - if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) { + if (kvm_read_guest_virt(vcpu, param, &sp32, sizeof(sp32), &e)) { *r = -EFAULT; return true; } @@ -1220,8 +1213,8 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, sched_poll.nr_ports = sp32.nr_ports; sched_poll.timeout = sp32.timeout; } else { - if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll, - sizeof(sched_poll))) { + if (kvm_read_guest_virt(vcpu, param, &sched_poll, + sizeof(sched_poll), &e)) { *r = -EFAULT; return true; } @@ -1243,18 +1236,13 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, } else ports = &port; + if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, + sched_poll.nr_ports * sizeof(*ports), &e)) { + *r = -EFAULT; + return true; + } + for (i = 0; i < sched_poll.nr_ports; i++) { - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, - (gva_t)(sched_poll.ports + i), - NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, - &ports[i], sizeof(port))) { - *r = -EFAULT; - goto out; - } if (ports[i] >= max_evtchn_port(vcpu->kvm)) { *r = -EINVAL; goto out; @@ -1330,9 +1318,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, int vcpu_id, u64 param, u64 *r) { struct vcpu_set_singleshot_timer oneshot; + struct x86_exception e; s64 delta; - gpa_t gpa; - int idx; if (!kvm_xen_timer_enabled(vcpu)) return false; @@ -1343,9 +1330,6 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, *r = -EINVAL; return true; } - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); /* * The only difference for 32-bit compat is the 4 bytes of @@ -1363,9 +1347,8 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) != sizeof_field(struct vcpu_set_singleshot_timer, flags)); - if (!gpa || - kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) : - sizeof(struct compat_vcpu_set_singleshot_timer))) { + if (kvm_read_guest_virt(vcpu, param, &oneshot, longmode ? sizeof(oneshot) : + sizeof(struct compat_vcpu_set_singleshot_timer), &e)) { *r = -EFAULT; return true; } @@ -1825,20 +1808,20 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct evtchnfd *evtchnfd; + int ret; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - + /* Protect writes to evtchnfd as well as the idr lookup. */ mutex_lock(&kvm->lock); evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port); - mutex_unlock(&kvm->lock); + ret = -ENOENT; if (!evtchnfd) - return -ENOENT; + goto out_unlock; /* For an UPDATE, nothing may change except the priority/vcpu */ + ret = -EINVAL; if (evtchnfd->type != data->u.evtchn.type) - return -EINVAL; + goto out_unlock; /* * Port cannot change, and if it's zero that was an eventfd @@ -1846,20 +1829,21 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, */ if (!evtchnfd->deliver.port.port || evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port) - return -EINVAL; + goto out_unlock; /* We only support 2 level event channels for now */ if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) - return -EINVAL; + goto out_unlock; - mutex_lock(&kvm->lock); evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority; if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) { evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu; evtchnfd->deliver.port.vcpu_idx = -1; } + ret = 0; +out_unlock: mutex_unlock(&kvm->lock); - return 0; + return ret; } /* @@ -1871,12 +1855,9 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, { u32 port = data->u.evtchn.send_port; struct eventfd_ctx *eventfd = NULL; - struct evtchnfd *evtchnfd = NULL; + struct evtchnfd *evtchnfd; int ret = -EINVAL; - if (!port || port >= max_evtchn_port(kvm)) - return -EINVAL; - evtchnfd = kzalloc(sizeof(struct evtchnfd), GFP_KERNEL); if (!evtchnfd) return -ENOMEM; @@ -1952,8 +1933,7 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) if (!evtchnfd) return -ENOENT; - if (kvm) - synchronize_srcu(&kvm->srcu); + synchronize_srcu(&kvm->srcu); if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); @@ -1962,18 +1942,42 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) static int kvm_xen_eventfd_reset(struct kvm *kvm) { - struct evtchnfd *evtchnfd; + struct evtchnfd *evtchnfd, **all_evtchnfds; int i; + int n = 0; mutex_lock(&kvm->lock); + + /* + * Because synchronize_srcu() cannot be called inside the + * critical section, first collect all the evtchnfd objects + * in an array as they are removed from evtchn_ports. + */ + idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) + n++; + + all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL); + if (!all_evtchnfds) { + mutex_unlock(&kvm->lock); + return -ENOMEM; + } + + n = 0; idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { + all_evtchnfds[n++] = evtchnfd; idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port); - synchronize_srcu(&kvm->srcu); + } + mutex_unlock(&kvm->lock); + + synchronize_srcu(&kvm->srcu); + + while (n--) { + evtchnfd = all_evtchnfds[n]; if (!evtchnfd->deliver.port.port) eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx); kfree(evtchnfd); } - mutex_unlock(&kvm->lock); + kfree(all_evtchnfds); return 0; } @@ -2002,20 +2006,22 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) { struct evtchnfd *evtchnfd; struct evtchn_send send; - gpa_t gpa; - int idx; - - idx = srcu_read_lock(&vcpu->kvm->srcu); - gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + struct x86_exception e; - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) { + /* Sanity check: this structure is the same for 32-bit and 64-bit */ + BUILD_BUG_ON(sizeof(send) != 4); + if (kvm_read_guest_virt(vcpu, param, &send, sizeof(send), &e)) { *r = -EFAULT; return true; } - /* The evtchn_ports idr is protected by vcpu->kvm->srcu */ + /* + * evtchnfd is protected by kvm->srcu; the idr lookup instead + * is protected by RCU. + */ + rcu_read_lock(); evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port); + rcu_read_unlock(); if (!evtchnfd) return false; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 20522d4ba1e0..55155e262646 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1767,6 +1767,7 @@ struct kvm_xen_hvm_attr { __u8 runstate_update_flag; struct { __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) } shared_info; struct { __u32 send_port; @@ -1798,6 +1799,7 @@ struct kvm_xen_hvm_attr { } u; }; + /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 @@ -1823,6 +1825,7 @@ struct kvm_xen_vcpu_attr { __u16 pad[3]; union { __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) __u64 pad[8]; struct { __u64 state; diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 6ce8c488d62e..6d9381d60172 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,86 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only -/aarch64/aarch32_id_regs -/aarch64/arch_timer -/aarch64/debug-exceptions -/aarch64/get-reg-list -/aarch64/hypercalls -/aarch64/page_fault_test -/aarch64/psci_test -/aarch64/vcpu_width_config -/aarch64/vgic_init -/aarch64/vgic_irq -/s390x/memop -/s390x/resets -/s390x/sync_regs_test -/s390x/tprot -/x86_64/amx_test -/x86_64/cpuid_test -/x86_64/cr4_cpuid_sync_test -/x86_64/debug_regs -/x86_64/exit_on_emulation_failure_test -/x86_64/fix_hypercall_test -/x86_64/get_msr_index_features -/x86_64/kvm_clock_test -/x86_64/kvm_pv_test -/x86_64/hyperv_clock -/x86_64/hyperv_cpuid -/x86_64/hyperv_evmcs -/x86_64/hyperv_features -/x86_64/hyperv_ipi -/x86_64/hyperv_svm_test -/x86_64/hyperv_tlb_flush -/x86_64/max_vcpuid_cap_test -/x86_64/mmio_warning_test -/x86_64/monitor_mwait_test -/x86_64/nested_exceptions_test -/x86_64/nx_huge_pages_test -/x86_64/platform_info_test -/x86_64/pmu_event_filter_test -/x86_64/set_boot_cpu_id -/x86_64/set_sregs_test -/x86_64/sev_migrate_tests -/x86_64/smaller_maxphyaddr_emulation_test -/x86_64/smm_test -/x86_64/state_test -/x86_64/svm_vmcall_test -/x86_64/svm_int_ctl_test -/x86_64/svm_nested_soft_inject_test -/x86_64/svm_nested_shutdown_test -/x86_64/sync_regs_test -/x86_64/tsc_msrs_test -/x86_64/tsc_scaling_sync -/x86_64/ucna_injection_test -/x86_64/userspace_io_test -/x86_64/userspace_msr_exit_test -/x86_64/vmx_apic_access_test -/x86_64/vmx_close_while_nested_test -/x86_64/vmx_dirty_log_test -/x86_64/vmx_exception_with_invalid_guest_state -/x86_64/vmx_invalid_nested_guest_state -/x86_64/vmx_msrs_test -/x86_64/vmx_preemption_timer_test -/x86_64/vmx_set_nested_state_test -/x86_64/vmx_tsc_adjust_test -/x86_64/vmx_nested_tsc_scaling_test -/x86_64/xapic_ipi_test -/x86_64/xapic_state_test -/x86_64/xen_shinfo_test -/x86_64/xen_vmcall_test -/x86_64/xss_msr_test -/x86_64/vmx_pmu_caps_test -/x86_64/triple_fault_event_test -/access_tracking_perf_test -/demand_paging_test -/dirty_log_test -/dirty_log_perf_test -/hardware_disable_test -/kvm_create_max_vcpus -/kvm_page_table_test -/max_guest_memory_test -/memslot_modification_stress_test -/memslot_perf_test -/rseq_test -/set_memory_region_test -/steal_time -/kvm_binary_stats_test -/system_counter_offset_test +* +!/**/ +!*.c +!*.h +!*.S +!*.sh diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 947676983da1..1750f91dd936 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -7,35 +7,14 @@ top_srcdir = ../../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) -# For cross-builds to work, UNAME_M has to map to ARCH and arch specific -# directories and targets in this Makefile. "uname -m" doesn't map to -# arch specific sub-directory names. -# -# UNAME_M variable to used to run the compiles pointing to the right arch -# directories and build the right targets for these supported architectures. -# -# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable. -# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable. -# -# x86_64 targets are named to include x86_64 as a suffix and directories -# for includes are in x86_64 sub-directory. s390x and aarch64 follow the -# same convention. "uname -m" doesn't result in the correct mapping for -# s390x and aarch64. -# -# No change necessary for x86_64 -UNAME_M := $(shell uname -m) - -# Set UNAME_M for arm64 compile/install to work -ifeq ($(ARCH),arm64) - UNAME_M := aarch64 -endif -# Set UNAME_M s390x compile/install to work -ifeq ($(ARCH),s390) - UNAME_M := s390x -endif -# Set UNAME_M riscv compile/install to work -ifeq ($(ARCH),riscv) - UNAME_M := riscv +ifeq ($(ARCH),x86) + ARCH_DIR := x86_64 +else ifeq ($(ARCH),arm64) + ARCH_DIR := aarch64 +else ifeq ($(ARCH),s390) + ARCH_DIR := s390x +else + ARCH_DIR := $(ARCH) endif LIBKVM += lib/assert.c @@ -196,10 +175,15 @@ TEST_GEN_PROGS_riscv += kvm_page_table_test TEST_GEN_PROGS_riscv += set_memory_region_test TEST_GEN_PROGS_riscv += kvm_binary_stats_test -TEST_PROGS += $(TEST_PROGS_$(UNAME_M)) -TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) -TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(UNAME_M)) -LIBKVM += $(LIBKVM_$(UNAME_M)) +TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR)) +TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR)) +TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR)) +LIBKVM += $(LIBKVM_$(ARCH_DIR)) + +# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most +# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`, +# which causes the environment variable to override the makefile). +include ../lib.mk INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ @@ -210,25 +194,23 @@ else LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ + -Wno-gnu-variable-sized-type-not-at-end \ + -fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \ + -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ $(KHDR_INCLUDES) -no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ - $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) +no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ + $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) # On s390, build the testcases KVM-enabled -pgste-option = $(call try-run, echo 'int main() { return 0; }' | \ +pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \ $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) LDLIBS += -ldl LDFLAGS += -pthread $(no-pie-option) $(pgste-option) -# After inclusion, $(OUTPUT) is defined and -# $(TEST_GEN_PROGS) starts with $(OUTPUT)/ -include ../lib.mk - LIBKVM_C := $(filter %.c,$(LIBKVM)) LIBKVM_S := $(filter %.S,$(LIBKVM)) LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 95d22cfb7b41..beb944fa6fd4 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -117,7 +117,7 @@ static void guest_cas(void) GUEST_ASSERT(guest_check_lse()); asm volatile(".arch_extension lse\n" "casal %0, %1, [%2]\n" - :: "r" (0), "r" (TEST_DATA), "r" (guest_test_memory)); + :: "r" (0ul), "r" (TEST_DATA), "r" (guest_test_memory)); val = READ_ONCE(*guest_test_memory); GUEST_ASSERT_EQ(val, TEST_DATA); } diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index 562c16dfbb00..f212bd8ab93d 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -14,11 +14,13 @@ static vm_vaddr_t *ucall_exit_mmio_addr; void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { - virt_pg_map(vm, mmio_gpa, mmio_gpa); + vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR); + + virt_map(vm, mmio_gva, mmio_gpa, 1); vm->ucall_mmio_addr = mmio_gpa; - write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa); + write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva); } void ucall_arch_do_ucall(vm_vaddr_t uc) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index c88c3ace16d2..56d5ea949cbb 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -186,6 +186,15 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); +/* + * Initializes vm->vpages_valid to match the canonical VA space of the + * architecture. + * + * The default implementation is valid for architectures which split the + * range addressed by a single page table into a low and high region + * based on the MSB of the VA. On architectures with this behavior + * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1]. + */ __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm) { sparsebit_set_num(vm->vpages_valid, @@ -1416,10 +1425,10 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, while (npages--) { virt_pg_map(vm, vaddr, paddr); + sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); + vaddr += page_size; paddr += page_size; - - sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); } } diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index 0cc0971ce60e..2f0e2ea941cc 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -4,6 +4,8 @@ #include "linux/bitmap.h" #include "linux/atomic.h" +#define GUEST_UCALL_FAILED -1 + struct ucall_header { DECLARE_BITMAP(in_use, KVM_MAX_VCPUS); struct ucall ucalls[KVM_MAX_VCPUS]; @@ -41,7 +43,8 @@ static struct ucall *ucall_alloc(void) struct ucall *uc; int i; - GUEST_ASSERT(ucall_pool); + if (!ucall_pool) + goto ucall_failed; for (i = 0; i < KVM_MAX_VCPUS; ++i) { if (!test_and_set_bit(i, ucall_pool->in_use)) { @@ -51,7 +54,13 @@ static struct ucall *ucall_alloc(void) } } - GUEST_ASSERT(0); +ucall_failed: + /* + * If the vCPU cannot grab a ucall structure, make a bare ucall with a + * magic value to signal to get_ucall() that things went sideways. + * GUEST_ASSERT() depends on ucall_alloc() and so cannot be used here. + */ + ucall_arch_do_ucall(GUEST_UCALL_FAILED); return NULL; } @@ -93,6 +102,9 @@ uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) addr = ucall_arch_get_ucall(vcpu); if (addr) { + TEST_ASSERT(addr != (void *)GUEST_UCALL_FAILED, + "Guest failed to allocate ucall struct"); + memcpy(uc, addr, sizeof(*uc)); vcpu_run_complete_io(vcpu); } else { diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c4d368d56cfe..acfa1d01e7df 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1031,7 +1031,7 @@ bool is_amd_cpu(void) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) { - *pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32; + *pa_bits = kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32; *va_bits = 32; } else { *pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR); diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index e698306bf49d..e6587e193490 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -265,6 +265,9 @@ static uint64_t get_max_slots(struct vm_data *data, uint32_t host_page_size) slots = data->nslots; while (--slots > 1) { pages_per_slot = mempages / slots; + if (!pages_per_slot) + continue; + rempages = mempages % pages_per_slot; if (check_slot_pages(host_page_size, guest_page_size, pages_per_slot, rempages)) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c index 8b791eac7d5a..0cbb0e646ef8 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c @@ -193,8 +193,9 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) GUEST_SYNC(stage++); /* * 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL. - * Nothing to write anything to XMM regs. */ + ipi_ex->vp_set.valid_bank_mask = 0; + hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2); hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT, IPI_VECTOR, HV_GENERIC_SET_ALL); nop_loop(); diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c index e497ace629c1..b34980d45648 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -41,8 +41,17 @@ static void guest_int_handler(struct ex_regs *regs) static void l2_guest_code_int(void) { GUEST_ASSERT_1(int_fired == 1, int_fired); - vmmcall(); - ud2(); + + /* + * Same as the vmmcall() function, but with a ud2 sneaked after the + * vmmcall. The caller injects an exception with the return address + * increased by 2, so the "pop rbp" must be after the ud2 and we cannot + * use vmmcall() directly. + */ + __asm__ __volatile__("push %%rbp; vmmcall; ud2; pop %%rbp" + : : "a"(0xdeadbeef), "c"(0xbeefdead) + : "rbx", "rdx", "rsi", "rdi", "r8", "r9", + "r10", "r11", "r12", "r13", "r14", "r15"); GUEST_ASSERT_1(bp_fired == 1, bp_fired); hlt(); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index 5943187e8594..ff8ecdf32ae0 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -49,11 +49,6 @@ enum { NUM_VMX_PAGES, }; -struct kvm_single_msr { - struct kvm_msrs header; - struct kvm_msr_entry entry; -} __attribute__((packed)); - /* The virtual machine object. */ static struct kvm_vm *vm; diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 721f6a693799..dae510c263b4 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -962,6 +962,12 @@ int main(int argc, char *argv[]) } done: + struct kvm_xen_hvm_attr evt_reset = { + .type = KVM_XEN_ATTR_TYPE_EVTCHN, + .u.evtchn.flags = KVM_XEN_EVTCHN_RESET, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset); + alarm(0); clock_gettime(CLOCK_REALTIME, &max_ts); diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index a1ab15006af3..180f1a09e6ba 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -14,14 +14,10 @@ #define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock) #define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock) #define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_LOCK(kvm) read_lock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_UNLOCK(kvm) read_unlock(&(kvm)->mmu_lock) #else #define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock) #define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) #define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) -#define KVM_MMU_READ_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) #endif /* KVM_HAVE_MMU_RWLOCK */ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible, |