diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 41306ea878cdc6b0c274fffcf85d338be309027b..c42a0a4d5fbeee744d05b3721380ec4a9816537c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6293,7 +6293,7 @@ The "flags" field is reserved for future extensions and must be '0'. :Architectures: none :Type: vm ioctl :Parameters: struct kvm_create_guest_memfd(in) -:Returns: 0 on success, <0 on error +:Returns: A file descriptor on success, <0 on error KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor that refers to it. guest_memfd files are roughly analogous to files created @@ -7991,7 +7991,11 @@ The valid bits in cap.args[0] are: When this quirk is disabled, the reset value is 0x10000 (APIC_LVT_MASKED). - KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW. + KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW on + AMD CPUs to workaround buggy guest firmware + that runs in perpetuity with CR0.CD, i.e. + with caches in "no fill" mode. + When this quirk is disabled, KVM does not change the value of CR0.CD and CR0.NW. @@ -8119,6 +8123,23 @@ See KVM_EXIT_MEMORY_FAULT for more information. When this capability is enabled, KVM resets the VCPU when setting MP_STATE_INIT_RECEIVED through IOCTL. The original MP_STATE is preserved. +7.36 KVM_CAP_X86_APIC_BUS_CYCLES_NS +----------------------------------- + +:Architectures: x86 +:Target: VM +:Parameters: args[0] is the desired APIC bus clock rate, in nanoseconds +:Returns: 0 on success, -EINVAL if args[0] contains an invalid value for the + frequency or if any vCPUs have been created, -ENXIO if a virtual + local APIC has not been created using KVM_CREATE_IRQCHIP. + +This capability sets the VM's APIC bus clock frequency, used by KVM's in-kernel +virtual APIC when emulating APIC timers. KVM's default value can be retrieved +by KVM_CHECK_EXTENSION. + +Note: Userspace is responsible for correctly configuring CPUID 0x15, a.k.a. the +core crystal clock frequency, if a non-zero CPUID 0x15 is exposed to the guest. + 7.43 KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED ------------------------------------------- @@ -8889,6 +8910,11 @@ means the VM type with value @n is supported. Possible values of @n are:: #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 +Note, KVM_X86_SW_PROTECTED_VM is currently only for development and testing. +Do not use KVM_X86_SW_PROTECTED_VM for "real" VMs, and especially not in +production. The behavior and effective ABI for software-protected VMs is +unstable. + 9. Known KVM API problems ========================= diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 887d9d2fed492bb5baa4fe06346187671e8a1024..198a5a8f26c2dafa5a2801f403949741dd59e733 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -50,10 +50,9 @@ On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock -- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and - kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and - cannot be taken without already holding kvm->arch.mmu_lock (typically with - ``read_lock`` for the TDP MMU, thus the need for additional spinlocks). +- kvm->arch.mmu_lock is an rwlock; critical sections for + kvm->arch.tdp_mmu_pages_lock and kvm->arch.mmu_unsync_pages_lock must + also take kvm->arch.mmu_lock Everything else is a leaf: no other lock is taken inside the critical sections. diff --git a/Documentation/virt/kvm/x86/errata.rst b/Documentation/virt/kvm/x86/errata.rst index 49a05f24747ba43dccbc356d512fe5f3a17bc454..4116045a8744d057c7b36b32a6fe31971fc8ad55 100644 --- a/Documentation/virt/kvm/x86/errata.rst +++ b/Documentation/virt/kvm/x86/errata.rst @@ -48,3 +48,21 @@ have the same physical APIC ID, KVM will deliver events targeting that APIC ID only to the vCPU with the lowest vCPU ID. If KVM_X2APIC_API_USE_32BIT_IDS is not enabled, KVM follows x86 architecture when processing interrupts (all vCPUs matching the target APIC ID receive the interrupt). + +MTRRs +----- +KVM does not virtualize guest MTRR memory types. KVM emulates accesses to MTRR +MSRs, i.e. {RD,WR}MSR in the guest will behave as expected, but KVM does not +honor guest MTRRs when determining the effective memory type, and instead +treats all of guest memory as having Writeback (WB) MTRRs. + +CR0.CD +------ +KVM does not virtualize CR0.CD on Intel CPUs. Similar to MTRR MSRs, KVM +emulates CR0.CD accesses so that loads and stores from/to CR0 behave as +expected, but setting CR0.CD=1 has no impact on the cachaeability of guest +memory. + +Note, this erratum does not affect AMD CPUs, which fully virtualize CR0.CD in +hardware, i.e. put the CPU caches into "no fill" mode when CR0.CD=1, even when +running in the guest. \ No newline at end of file diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 376636eccffa98d4a32099f144fcf886c6166e84..52a465f2ed5819c1dd361483a320c6b38f9c5aaa 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -153,7 +153,6 @@ #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 256 -#define KVM_NR_FIXED_MTRR_REGION 88 #define KVM_NR_VAR_MTRR 8 #define ASYNC_PF_PER_VCPU 64 @@ -593,18 +592,12 @@ enum { KVM_DEBUGREG_WONT_EXIT = 2, }; -struct kvm_mtrr_range { - u64 base; - u64 mask; - struct list_head node; -}; - struct kvm_mtrr { - struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR]; - mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; + u64 var[KVM_NR_VAR_MTRR * 2]; + u64 fixed_64k; + u64 fixed_16k[2]; + u64 fixed_4k[8]; u64 deftype; - - struct list_head head; }; /* Hyper-V SynIC timer */ @@ -1007,9 +1000,6 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; - /* set at EPT violation at this point */ - unsigned long exit_qualification; - /* pv related host specific info */ struct { bool pv_unhalted; @@ -1327,6 +1317,8 @@ struct kvm_arch { */ spinlock_t mmu_unsync_pages_lock; + u64 shadow_mmio_value; + struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; bool iommu_noncoherent; @@ -1375,6 +1367,8 @@ struct kvm_arch { int nr_vcpus_matched_tsc; u32 default_tsc_khz; + bool user_set_tsc; + u64 apic_bus_cycle_ns; seqcount_raw_spinlock_t pvclock_sc; bool use_master_clock; @@ -1453,9 +1447,8 @@ struct kvm_arch { * the MMU lock in read mode + RCU or * the MMU lock in write mode * - * For writes, this list is protected by: - * the MMU lock in read mode + the tdp_mmu_pages_lock or - * the MMU lock in write mode + * For writes, this list is protected by tdp_mmu_pages_lock; see + * below for the details. * * Roots will remain in the list until their tdp_mmu_root_count * drops to zero, at which point the thread that decremented the @@ -1472,8 +1465,10 @@ struct kvm_arch { * - possible_nx_huge_pages; * - the possible_nx_huge_page_link field of kvm_mmu_page structs used * by the TDP MMU - * It is acceptable, but not necessary, to acquire this lock when - * the thread holds the MMU lock in write mode. + * Because the lock is only taken within the MMU lock, strictly + * speaking it is redundant to acquire this lock when the thread + * holds the MMU lock in write mode. However it often simplifies + * the code to do so. */ spinlock_t tdp_mmu_pages_lock; #endif /* CONFIG_X86_64 */ @@ -1485,6 +1480,15 @@ struct kvm_arch { */ bool shadow_root_allocated; +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + /* + * If set, the VM has (or had) an external write tracking user, and + * thus all write tracking metadata has been allocated, even if KVM + * itself isn't using write tracking. + */ + bool external_write_tracking_enabled; +#endif + #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; spinlock_t hv_root_tdp_lock; @@ -2171,10 +2175,15 @@ static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, kvm_set_or_clear_apicv_inhibit(kvm, reason, false); } +unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); +void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, unsigned long roots); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index ee1d460fef48355f2d2167a4722e3073b595d086..a5355de6a942f2235785e166ca3d41c21d3374a8 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -71,6 +71,7 @@ #define SECONDARY_EXEC_ENCLS_EXITING VMCS_CONTROL_BIT(ENCLS_EXITING) #define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING) #define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING) +#define SECONDARY_EXEC_EPT_VIOLATION_VE VMCS_CONTROL_BIT(EPT_VIOLATION_VE) #define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX) #define SECONDARY_EXEC_ENABLE_XSAVES VMCS_CONTROL_BIT(XSAVES) #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) @@ -232,6 +233,8 @@ enum vmcs_field { VMREAD_BITMAP_HIGH = 0x00002027, VMWRITE_BITMAP = 0x00002028, VMWRITE_BITMAP_HIGH = 0x00002029, + VE_INFORMATION_ADDRESS = 0x0000202A, + VE_INFORMATION_ADDRESS_HIGH = 0x0000202B, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, ENCLS_EXITING_BITMAP = 0x0000202E, @@ -522,6 +525,7 @@ enum vmcs_field { #define VMX_EPT_IPAT_BIT (1ull << 6) #define VMX_EPT_ACCESS_BIT (1ull << 8) #define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_SUPPRESS_VE_BIT (1ull << 63) #define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \ VMX_EPT_WRITABLE_MASK | \ VMX_EPT_EXECUTABLE_MASK) @@ -638,4 +642,13 @@ enum vmx_l1d_flush_state { extern enum vmx_l1d_flush_state l1tf_vmx_mitigation; +struct vmx_ve_information { + u32 exit_reason; + u32 delivery; + u64 exit_qualification; + u64 guest_linear_address; + u64 guest_physical_address; + u16 eptp_index; +}; + #endif diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index ba209bdf57d9dc7c59b4cc8cb87432d0b674c708..b056fdf9ef5cf1ae6b02bfbbb0b491c6183d274e 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -76,7 +76,7 @@ #define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */ #define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* "" VM-Exit on RDSEED */ #define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */ -#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */ +#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */ #define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */ #define VMX_FEATURE_XSAVES ( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */ #define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b17f41e1cf8e7eb73fa45aa87a1e72298c9ff2f9..bc8fad66b1137e3f0557b04c834b711b1b9a50c7 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -86,9 +86,10 @@ config KVM_SW_PROTECTED_VM depends on X86_64 select KVM_GENERIC_PRIVATE_MEM help - Enable support for KVM software-protected VMs. Currently "protected" - means the VM can be backed with memory provided by - KVM_CREATE_GUEST_MEMFD. + Enable support for KVM software-protected VMs. Currently, software- + protected VMs are purely a development and testing vehicle for + KVM_CREATE_GUEST_MEMFD. Attempting to run a "real" VM workload as a + software-protected VM will fail miserably. If unsure, say "N". @@ -103,6 +104,21 @@ config KVM_INTEL To compile this as a module, choose M here: the module will be called kvm-intel. +config KVM_INTEL_PROVE_VE + bool "Check that guests do not receive #VE exceptions" + depends on KVM_INTEL && EXPERT + help + Checks that KVM's page table management code will not incorrectly + let guests receive a virtualization exception. Virtualization + exceptions will be trapped by the hypervisor rather than injected + in the guest. + + Note: some CPUs appear to generate spurious EPT Violations #VEs + that trigger KVM's WARN, in particular with eptad=0 and/or nested + virtualization. + + If unsure, say N. + config X86_SGX_KVM bool "Software Guard eXtensions (SGX) Virtualization" depends on X86_SGX && KVM_INTEL diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 8f15e930c8ca94cbfc3db233758feadee3bf865d..e2aacfe1f52f129209b19f549929dfdf16b94225 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -20,7 +20,7 @@ kvm-$(CONFIG_KVM_XEN) += xen.o kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/nested.o vmx/posted_intr.o + vmx/nested.o vmx/posted_intr.o vmx/main.o kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 96c03f95212e27bf85e7c09a0d7b95de37e27cc1..686ff021b0c0bf2c4f718708d8a97733ca46c25f 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1687,7 +1687,8 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, data = (u64)vcpu->arch.virtual_tsc_khz * 1000; break; case HV_X64_MSR_APIC_FREQUENCY: - data = APIC_BUS_FREQUENCY; + data = div64_u64(1000000000ULL, + vcpu->kvm->arch.apic_bus_cycle_ns); break; default: kvm_pr_unimpl_rdmsr(vcpu, msr); diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 89682fd579bba0856dda6a014afa010318b0d42e..ac512a9f602c51ca0a84b55cf1e623b8d98ce900 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -26,6 +26,7 @@ struct x86_exception { bool nested_page_fault; u64 address; /* cr2 or nested page fault gpa */ u8 async_page_fault; + unsigned long exit_qualification; }; /* diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 827961e8dc870cb3b698c1628647cfe3b2377667..d050d1b7d6fc21a4c6e8cf7991afc2b233e0d01b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1562,7 +1562,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) remaining = 0; ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period); - return div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->divide_count)); + return div64_u64(ns, (apic->vcpu->kvm->arch.apic_bus_cycle_ns * + apic->divide_count)); } static void __report_tpr_access(struct kvm_lapic *apic, bool write) @@ -1980,7 +1981,8 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) static inline u64 tmict_to_ns(struct kvm_lapic *apic, u32 tmict) { - return (u64)tmict * APIC_BUS_CYCLE_NS * (u64)apic->divide_count; + return (u64)tmict * apic->vcpu->kvm->arch.apic_bus_cycle_ns * + (u64)apic->divide_count; } static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 43229203080e488b34cd4d8ab1ca0c8ece1536b0..688f42d6b505daa16651f0573fc45d2b8d49d12d 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -17,8 +17,7 @@ #define APIC_DEST_NOSHORT 0x0 #define APIC_DEST_MASK 0x800 -#define APIC_BUS_CYCLE_NS 1 -#define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) +#define APIC_BUS_CYCLE_NS_DEFAULT 1 #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 44e35527bae796ba4588a7b959ed5fe79e01f518..604ba680e357634f2cb41aab06e5310a5dbd4199 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -249,6 +249,8 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } +bool kvm_mmu_may_ignore_guest_pat(void); + int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); int kvm_mmu_post_init_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 5ba19dd278a0b8d64da164407166f8fb38725a10..285bee8d4e9ffb3cd64481dfe42447b54f9a7d0c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -343,16 +343,19 @@ static int is_cpuid_PSE36(void) #ifdef CONFIG_X86_64 static void __set_spte(u64 *sptep, u64 spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); WRITE_ONCE(*sptep, spte); } static void __update_clear_spte_fast(u64 *sptep, u64 spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); WRITE_ONCE(*sptep, spte); } static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(spte)); return xchg(sptep, spte); } @@ -574,9 +577,9 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) if (!is_shadow_present_pte(old_spte) || !spte_has_volatile_bits(old_spte)) - __update_clear_spte_fast(sptep, 0ull); + __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); else - old_spte = __update_clear_spte_slow(sptep, 0ull); + old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE); if (!is_shadow_present_pte(old_spte)) return old_spte; @@ -610,7 +613,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) */ static void mmu_spte_clear_no_track(u64 *sptep) { - __update_clear_spte_fast(sptep, 0ull); + __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE); } static u64 mmu_spte_get_lockless(u64 *sptep) @@ -838,6 +841,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) gfn_t gfn; kvm->arch.indirect_shadow_pages++; + /* + * Ensure indirect_shadow_pages is elevated prior to re-reading guest + * child PTEs in FNAME(gpte_changed), i.e. guarantee either in-flight + * emulated writes are visible before re-reading guest PTEs, or that + * an emulated write will see the elevated count and acquire mmu_lock + * to update SPTEs. Pairs with the smp_mb() in kvm_mmu_track_write(). + */ + smp_mb(); + gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); @@ -1944,7 +1956,8 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) { - if (!sp->spt[i]) + /* sp->spt[i] has initial value of shadow page table allocation */ + if (sp->spt[i] == SHADOW_NONPRESENT_VALUE) return 0; return vcpu->arch.mmu->sync_spte(vcpu, sp, i); @@ -2514,7 +2527,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, return kvm_mmu_prepare_zap_page(kvm, child, invalid_list); } - } else if (is_mmio_spte(pte)) { + } else if (is_mmio_spte(kvm, pte)) { mmu_spte_clear_no_track(spte); } return 0; @@ -3316,9 +3329,19 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, { gva_t gva = fault->is_tdp ? 0 : fault->addr; + if (fault->is_private) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + vcpu_cache_mmio_info(vcpu, gva, fault->gfn, access & shadow_mmio_access_mask); + fault->slot = NULL; + fault->pfn = KVM_PFN_NOSLOT; + fault->map_writable = false; + fault->hva = KVM_HVA_ERR_BAD; + /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an @@ -3480,7 +3503,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) u64 new_spte; if (tdp_mmu_enabled) - sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte); + sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->gfn, &spte); else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); @@ -3589,10 +3612,14 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, if (WARN_ON_ONCE(!sp)) return; - if (is_tdp_mmu_page(sp)) - kvm_tdp_mmu_put_root(kvm, sp, false); - else if (!--sp->root_count && sp->role.invalid) - kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + if (is_tdp_mmu_page(sp)) { + lockdep_assert_held_read(&kvm->mmu_lock); + kvm_tdp_mmu_put_root(kvm, sp); + } else { + lockdep_assert_held_write(&kvm->mmu_lock); + if (!--sp->root_count && sp->role.invalid) + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + } *root_hpa = INVALID_PAGE; } @@ -3601,6 +3628,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free) { + bool is_tdp_mmu = tdp_mmu_enabled && mmu->root_role.direct; int i; LIST_HEAD(invalid_list); bool free_active_root; @@ -3623,7 +3651,10 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, return; } - write_lock(&kvm->mmu_lock); + if (is_tdp_mmu) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) @@ -3649,8 +3680,13 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, mmu->root.pgd = 0; } - kvm_mmu_commit_zap_page(kvm, &invalid_list); - write_unlock(&kvm->mmu_lock); + if (is_tdp_mmu) { + read_unlock(&kvm->mmu_lock); + WARN_ON_ONCE(!list_empty(&invalid_list)); + } else { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + write_unlock(&kvm->mmu_lock); + } } EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); @@ -3707,15 +3743,15 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) unsigned i; int r; + if (tdp_mmu_enabled) + return kvm_tdp_mmu_alloc_root(vcpu); + write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); if (r < 0) goto out_unlock; - if (tdp_mmu_enabled) { - root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); - mmu->root.hpa = root; - } else if (shadow_root_level >= PT64_ROOT_4LEVEL) { + if (shadow_root_level >= PT64_ROOT_4LEVEL) { root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level); mmu->root.hpa = root; } else if (shadow_root_level == PT32E_ROOT_LEVEL) { @@ -4135,23 +4171,31 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level return leaf; } -/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ -static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) +static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level) { - u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; - struct rsvd_bits_validate *rsvd_check; - int root, leaf, level; - bool reserved = false; + int leaf; walk_shadow_page_lockless_begin(vcpu); if (is_tdp_mmu_active(vcpu)) - leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); + leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level); else - leaf = get_walk(vcpu, addr, sptes, &root); + leaf = get_walk(vcpu, addr, sptes, root_level); walk_shadow_page_lockless_end(vcpu); + return leaf; +} +/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ +static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) +{ + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; + struct rsvd_bits_validate *rsvd_check; + int root, leaf, level; + bool reserved = false; + + leaf = get_sptes_lockless(vcpu, addr, sptes, &root); if (unlikely(leaf < 0)) { *sptep = 0ull; return reserved; @@ -4197,7 +4241,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) if (WARN_ON_ONCE(reserved)) return -EINVAL; - if (is_mmio_spte(spte)) { + if (is_mmio_spte(vcpu->kvm, spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); unsigned int access = get_mmio_spte_access(spte); @@ -4323,14 +4367,6 @@ static inline u8 kvm_max_level_for_order(int order) return PG_LEVEL_4K; } -static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault) -{ - kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, - PAGE_SIZE, fault->write, fault->exec, - fault->is_private); -} - static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, u8 max_level, int gmem_order) { @@ -4376,48 +4412,15 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_memory_slot *slot = fault->slot; bool async; - /* - * Retry the page fault if the gfn hit a memslot that is being deleted - * or moved. This ensures any existing SPTEs for the old memslot will - * be zapped before KVM inserts a new MMIO SPTE for the gfn. - */ - if (slot && (slot->flags & KVM_MEMSLOT_INVALID)) - return RET_PF_RETRY; - - if (!kvm_is_visible_memslot(slot)) { - /* Don't expose private memslots to L2. */ - if (is_guest_mode(vcpu)) { - fault->slot = NULL; - fault->pfn = KVM_PFN_NOSLOT; - fault->map_writable = false; - return RET_PF_CONTINUE; - } - /* - * If the APIC access page exists but is disabled, go directly - * to emulation without caching the MMIO access or creating a - * MMIO SPTE. That way the cache doesn't need to be purged - * when the AVIC is re-enabled. - */ - if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT && - !kvm_apicv_activated(vcpu->kvm)) - return RET_PF_EMULATE; - } - - if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { - kvm_mmu_prepare_memory_fault_exit(vcpu, fault); - return -EFAULT; - } - if (fault->is_private) return kvm_faultin_pfn_private(vcpu, fault); async = false; - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, - fault->write, &fault->map_writable, - &fault->hva); + fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, false, + &async, fault->write, + &fault->map_writable, &fault->hva); if (!async) return RET_PF_CONTINUE; /* *pfn has correct page already */ @@ -4437,20 +4440,96 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * to wait for IO. Note, gup always bails if it is unable to quickly * get a page and a fatal signal, i.e. SIGKILL, is pending. */ - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL, - fault->write, &fault->map_writable, - &fault->hva); + fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true, + NULL, fault->write, + &fault->map_writable, &fault->hva); return RET_PF_CONTINUE; } static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, unsigned int access) { + struct kvm_memory_slot *slot = fault->slot; int ret; + /* + * Note that the mmu_invalidate_seq also serves to detect a concurrent + * change in attributes. is_page_fault_stale() will detect an + * invalidation relate to fault->fn and resume the guest without + * installing a mapping in the page tables. + */ fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); + /* + * Now that we have a snapshot of mmu_invalidate_seq we can check for a + * private vs. shared mismatch. + */ + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (unlikely(!slot)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + /* + * Retry the page fault if the gfn hit a memslot that is being deleted + * or moved. This ensures any existing SPTEs for the old memslot will + * be zapped before KVM inserts a new MMIO SPTE for the gfn. + */ + if (slot->flags & KVM_MEMSLOT_INVALID) + return RET_PF_RETRY; + + if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) { + /* + * Don't map L1's APIC access page into L2, KVM doesn't support + * using APICv/AVIC to accelerate L2 accesses to L1's APIC, + * i.e. the access needs to be emulated. Emulating access to + * L1's APIC is also correct if L1 is accelerating L2's own + * virtual APIC, but for some reason L1 also maps _L1's_ APIC + * into L2. Note, vcpu_is_mmio_gpa() always treats access to + * the APIC as MMIO. Allow an MMIO SPTE to be created, as KVM + * uses different roots for L1 vs. L2, i.e. there is no danger + * of breaking APICv/AVIC for L1. + */ + if (is_guest_mode(vcpu)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + /* + * If the APIC access page exists but is disabled, go directly + * to emulation without caching the MMIO access or creating a + * MMIO SPTE. That way the cache doesn't need to be purged + * when the AVIC is re-enabled. + */ + if (!kvm_apicv_activated(vcpu->kvm)) + return RET_PF_EMULATE; + } + + /* + * Check for a relevant mmu_notifier invalidation event before getting + * the pfn from the primary MMU, and before acquiring mmu_lock. + * + * For mmu_lock, if there is an in-progress invalidation and the kernel + * allows preemption, the invalidation task may drop mmu_lock and yield + * in response to mmu_lock being contended, which is *very* counter- + * productive as this vCPU can't actually make forward progress until + * the invalidation completes. + * + * Retrying now can also avoid unnessary lock contention in the primary + * MMU, as the primary MMU doesn't necessarily hold a single lock for + * the duration of the invalidation, i.e. faulting in a conflicting pfn + * can cause the invalidation to take longer by holding locks that are + * needed to complete the invalidation. + * + * Do the pre-check even for non-preemtible kernels, i.e. even if KVM + * will never yield mmu_lock in response to contention, as this vCPU is + * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held + * to detect retry guarantees the worst case latency for the vCPU. + */ + if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + return RET_PF_RETRY; + ret = __kvm_faultin_pfn(vcpu, fault); if (ret != RET_PF_CONTINUE) return ret; @@ -4458,9 +4537,21 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (unlikely(is_error_pfn(fault->pfn))) return kvm_handle_error_pfn(vcpu, fault); - if (unlikely(!fault->slot)) + if (WARN_ON_ONCE(!fault->slot || is_noslot_pfn(fault->pfn))) return kvm_handle_noslot_fault(vcpu, fault, access); + /* + * Check again for a relevant mmu_notifier invalidation event purely to + * avoid contending mmu_lock. Most invalidations will be detected by + * the previous check, but checking is extremely cheap relative to the + * overall cost of failing to detect the invalidation until after + * mmu_lock is acquired. + */ + if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) { + kvm_release_pfn_clean(fault->pfn); + return RET_PF_RETRY; + } + return RET_PF_CONTINUE; } @@ -4488,6 +4579,11 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) return true; + /* + * Check for a relevant mmu_notifier invalidation event one last time + * now that mmu_lock is held, as the "unsafe" checks performed without + * holding mmu_lock can get false negatives. + */ return fault->slot && mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } @@ -4555,6 +4651,13 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, if (WARN_ON_ONCE(fault_address >> 32)) return -EFAULT; #endif + /* + * Legacy #PF exception only have a 32-bit error code. Simply drop the + * upper bits as KVM doesn't use them for #PF (because they are never + * set), and to ensure there are no collisions with KVM-defined bits. + */ + if (WARN_ON_ONCE(error_code >> 32)) + error_code = lower_32_bits(error_code); /* Ensure the above sanity check also covers KVM-defined flags. */ BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK)); @@ -4619,31 +4722,21 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, } #endif -int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +bool kvm_mmu_may_ignore_guest_pat(void) { /* - * If the guest's MTRRs may be used to compute the "real" memtype, - * restrict the mapping level to ensure KVM uses a consistent memtype - * across the entire mapping. If the host MTRRs are ignored by TDP - * (shadow_memtype_mask is non-zero), and the VM has non-coherent DMA - * (DMA doesn't snoop CPU caches), KVM's ABI is to honor the memtype - * from the guest's MTRRs so that guest accesses to memory that is - * DMA'd aren't cached against the guest's wishes. - * - * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs, - * e.g. KVM will force UC memtype for host MMIO. + * When EPT is enabled (shadow_memtype_mask is non-zero), and the VM + * has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is to + * honor the memtype from the guest's PAT so that guest accesses to + * memory that is DMA'd aren't cached against the guest's wishes. As a + * result, KVM _may_ ignore guest PAT, whereas without non-coherent DMA, + * KVM _always_ ignores guest PAT (when EPT is enabled). */ - if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { - for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { - int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); - gfn_t base = gfn_round_for_level(fault->gfn, - fault->max_level); - - if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) - break; - } - } + return shadow_memtype_mask; +} +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +{ #ifdef CONFIG_X86_64 if (tdp_mmu_enabled) return kvm_tdp_mmu_page_fault(vcpu, fault); @@ -4883,7 +4976,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) { - if (unlikely(is_mmio_spte(*sptep))) { + if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) { if (gfn != get_mmio_spte_gfn(*sptep)) { mmu_spte_clear_no_track(sptep); return true; @@ -5652,9 +5745,9 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ - vcpu->arch.root_mmu.root_role.word = 0; - vcpu->arch.guest_mmu.root_role.word = 0; - vcpu->arch.nested_mmu.root_role.word = 0; + vcpu->arch.root_mmu.root_role.invalid = 1; + vcpu->arch.guest_mmu.root_role.invalid = 1; + vcpu->arch.nested_mmu.root_role.invalid = 1; vcpu->arch.root_mmu.cpu_role.ext.valid = 0; vcpu->arch.guest_mmu.cpu_role.ext.valid = 0; vcpu->arch.nested_mmu.cpu_role.ext.valid = 0; @@ -5879,10 +5972,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, bool flush = false; /* - * If we don't have indirect shadow pages, it means no page is - * write-protected, so we can exit simply. + * When emulating guest writes, ensure the written value is visible to + * any task that is handling page faults before checking whether or not + * KVM is shadowing a guest PTE. This ensures either KVM will create + * the correct SPTE in the page fault handler, or this task will see + * a non-zero indirect_shadow_pages. Pairs with the smp_mb() in + * account_shadowed(). */ - if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) + smp_mb(); + if (!vcpu->kvm->arch.indirect_shadow_pages) return; write_lock(&vcpu->kvm->mmu_lock); @@ -5942,12 +6040,17 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { + if (WARN_ON_ONCE(error_code & PFERR_PRIVATE_ACCESS)) + return -EFAULT; + r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct); if (r == RET_PF_EMULATE) goto emulate; } if (r == RET_PF_INVALID) { + vcpu->stat.pf_taken++; + r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false, &emulation_type, NULL); if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) @@ -5999,6 +6102,22 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); +void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg) +{ + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; + int root_level, leaf, level; + + leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level); + if (unlikely(leaf < 0)) + return; + + pr_err("%s %llx", msg, gpa); + for (level = root_level; level >= leaf; level--) + pr_cont(", spte[%d] = 0x%llx", level, sptes[level]); + pr_cont("\n"); +} +EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes); + static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, hpa_t root_hpa) { @@ -6260,7 +6379,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache; vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO; - vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO; + vcpu->arch.mmu_shadow_page_cache.init_value = + SHADOW_NONPRESENT_VALUE; + if (!vcpu->arch.mmu_shadow_page_cache.init_value) + vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO; vcpu->arch.mmu = &vcpu->arch.root_mmu; vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; @@ -6403,6 +6525,7 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) void kvm_mmu_init_vm(struct kvm *kvm) { + kvm->arch.shadow_mmio_value = shadow_mmio_value; INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); @@ -7532,7 +7655,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, * by the memslot, KVM can't use a hugepage due to the * misaligned address regardless of memory attributes. */ - if (gfn >= slot->base_gfn) { + if (gfn >= slot->base_gfn && + gfn + nr_pages <= slot->base_gfn + slot->npages) { if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 0ead070b9cc8eaf1ceda02940d10218b49125c42..c7fad277ac28cb0dc023e14176cc7e800b265b19 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -279,6 +279,14 @@ enum { RET_PF_SPURIOUS, }; +static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err, bool prefetch, int *emulation_type, u8 *level) @@ -300,6 +308,9 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, .is_private = err & PFERR_PRIVATE_ACCESS, + + .pfn = KVM_PFN_ERR_FAULT, + .hva = KVM_HVA_ERR_BAD, }; int r; @@ -308,18 +319,20 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn); } - /* - * Async #PF "faults", a.k.a. prefetch faults, are not faults from the - * guest perspective and have already been counted at the time of the - * original fault. - */ - if (!prefetch) - vcpu->stat.pf_taken++; - if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp) r = kvm_tdp_page_fault(vcpu, &fault); else r = vcpu->arch.mmu->page_fault(vcpu, &fault); + /* + * Not sure what's happening, but punt to userspace and hope that + * they can fix it by changing memory to shared, or they can + * provide a better error. + */ + if (r == RET_PF_EMULATE && fault.is_private) { + pr_warn_ratelimited("kvm: unexpected emulation request on private memory\n"); + kvm_mmu_prepare_memory_fault_exit(vcpu, &fault); + return -EFAULT; + } if (fault.write_fault_to_shadow_pgtable && emulation_type) *emulation_type |= EMULTYPE_WRITE_PF_TO_SP; diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index c87da11f3a049b75e2dc6cae714b37e868666252..f6448284c18e3e1a2820530a4919f151a10c997b 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -20,10 +20,23 @@ #include "mmu_internal.h" #include "page_track.h" +static bool kvm_external_write_tracking_enabled(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + /* + * Read external_write_tracking_enabled before related pointers. Pairs + * with the smp_store_release in kvm_page_track_write_tracking_enable(). + */ + return smp_load_acquire(&kvm->arch.external_write_tracking_enabled); +#else + return false; +#endif +} + bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) { - return IS_ENABLED(CONFIG_KVM_EXTERNAL_WRITE_TRACKING) || - !tdp_enabled || kvm_shadow_root_allocated(kvm); + return kvm_external_write_tracking_enabled(kvm) || + kvm_shadow_root_allocated(kvm) || !tdp_enabled; } void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) @@ -153,6 +166,50 @@ int kvm_page_track_init(struct kvm *kvm) return init_srcu_struct(&head->track_srcu); } +static int kvm_enable_external_write_tracking(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; + int r = 0, i, bkt; + + mutex_lock(&kvm->slots_arch_lock); + + /* + * Check for *any* write tracking user (not just external users) under + * lock. This avoids unnecessary work, e.g. if KVM itself is using + * write tracking, or if two external users raced when registering. + */ + if (kvm_page_track_write_tracking_enabled(kvm)) + goto out_success; + + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(slot, bkt, slots) { + /* + * Intentionally do NOT free allocations on failure to + * avoid having to track which allocations were made + * now versus when the memslot was created. The + * metadata is guaranteed to be freed when the slot is + * freed, and will be kept/used if userspace retries + * the failed ioctl() instead of killing the VM. + */ + r = kvm_page_track_write_tracking_alloc(slot); + if (r) + goto out_unlock; + } + } + +out_success: + /* + * Ensure that external_write_tracking_enabled becomes true strictly + * after all the related pointers are set. + */ + smp_store_release(&kvm->arch.external_write_tracking_enabled, true); +out_unlock: + mutex_unlock(&kvm->slots_arch_lock); + return r; +} + /* * register the notifier so that event interception for the tracked guest * pages can be received. @@ -161,10 +218,17 @@ int kvm_page_track_register_notifier(struct kvm *kvm, struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; + int r; if (!kvm || kvm->mm != current->mm) return -ESRCH; + if (!kvm_external_write_tracking_enabled(kvm)) { + r = kvm_enable_external_write_tracking(kvm); + if (r) + return r; + } + kvm_get_kvm(kvm); head = &kvm->arch.track_notifier_head; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index ab0ed5d66e0c28d7c470e489575dc5b0e947cd08..2fb1919dd49f2285678a1a0eac351f2d877bd8d4 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -497,21 +497,21 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, * The other bits are set to 0. */ if (!(errcode & PFERR_RSVD_MASK)) { - vcpu->arch.exit_qualification &= (EPT_VIOLATION_GVA_IS_VALID | - EPT_VIOLATION_GVA_TRANSLATED); + walker->fault.exit_qualification = 0; + if (write_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_WRITE; if (user_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_READ; if (fetch_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_INSTR; /* * Note, pte_access holds the raw RWX bits from the EPTE, not * ACC_*_MASK flags! */ - vcpu->arch.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) << - EPT_VIOLATION_RWX_SHIFT; + walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) << + EPT_VIOLATION_RWX_SHIFT; } #endif walker->fault.address = addr; @@ -914,7 +914,7 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int gpa_t pte_gpa; gfn_t gfn; - if (WARN_ON_ONCE(!sp->spt[i])) + if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE)) return 0; first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); @@ -936,13 +936,13 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int return 0; /* - * Drop the SPTE if the new protections would result in a RWX=0 - * SPTE or if the gfn is changing. The RWX=0 case only affects - * EPT with execute-only support, i.e. EPT without an effective - * "present" bit, as all other paging modes will create a - * read-only SPTE if pte_access is zero. + * Drop the SPTE if the new protections result in no effective + * "present" bit or if the gfn is changing. The former case + * only affects EPT with execute-only support with pte_access==0; + * all other paging modes will create a read-only SPTE if + * pte_access is zero. */ - if ((!pte_access && !shadow_present_mask) || + if ((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE || gfn != kvm_mmu_page_get_gfn(sp, i)) { drop_spte(vcpu->kvm, &sp->spt[i]); return 1; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index b4c1119cc48b697011509413472b8bf859afb8b5..7e55aaa329fb1b96968e5566e21d4216e73b8aa9 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -74,10 +74,10 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access) u64 spte = generation_mmio_spte_mask(gen); u64 gpa = gfn << PAGE_SHIFT; - WARN_ON_ONCE(!shadow_mmio_value); + WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value); access &= shadow_mmio_access_mask; - spte |= shadow_mmio_value | access; + spte |= vcpu->kvm->arch.shadow_mmio_value | access; spte |= gpa | shadow_nonpresent_or_rsvd_mask; spte |= (gpa & shadow_nonpresent_or_rsvd_mask) << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN; @@ -144,19 +144,19 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 spte = SPTE_MMU_PRESENT_MASK; bool wrprot = false; - WARN_ON_ONCE(!pte_access && !shadow_present_mask); + /* + * For the EPT case, shadow_present_mask has no RWX bits set if + * exec-only page table entries are supported. In that case, + * ACC_USER_MASK and shadow_user_mask are used to represent + * read access. See FNAME(gpte_access) in paging_tmpl.h. + */ + WARN_ON_ONCE((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE); if (sp->role.ad_disabled) spte |= SPTE_TDP_AD_DISABLED; else if (kvm_mmu_page_ad_need_write_protect(sp)) spte |= SPTE_TDP_AD_WRPROT_ONLY; - /* - * For the EPT case, shadow_present_mask is 0 if hardware - * supports exec-only page table entries. In that case, - * ACC_USER_MASK and shadow_user_mask are used to represent - * read access. See FNAME(gpte_access) in paging_tmpl.h. - */ spte |= shadow_present_mask; if (!prefetch) spte |= spte_shadow_accessed_mask(spte); @@ -401,13 +401,13 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask) mmio_value = 0; /* - * The masked MMIO value must obviously match itself and a removed SPTE - * must not get a false positive. Removed SPTEs and MMIO SPTEs should - * never collide as MMIO must set some RWX bits, and removed SPTEs must + * The masked MMIO value must obviously match itself and a frozen SPTE + * must not get a false positive. Frozen SPTEs and MMIO SPTEs should + * never collide as MMIO must set some RWX bits, and frozen SPTEs must * not set any RWX bits. */ if (WARN_ON((mmio_value & mmio_mask) != mmio_value) || - WARN_ON(mmio_value && (REMOVED_SPTE & mmio_mask) == mmio_value)) + WARN_ON(mmio_value && (FROZEN_SPTE & mmio_mask) == mmio_value)) mmio_value = 0; if (!mmio_value) @@ -437,7 +437,9 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only) shadow_dirty_mask = has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull; shadow_nx_mask = 0ull; shadow_x_mask = VMX_EPT_EXECUTABLE_MASK; - shadow_present_mask = has_exec_only ? 0ull : VMX_EPT_READABLE_MASK; + /* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */ + shadow_present_mask = + (has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT; /* * EPT overrides the host MTRRs, and so KVM must program the desired * memtype directly into the SPTEs. Note, this mask is just the mask @@ -454,7 +456,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only) * of an EPT paging-structure entry is 110b (write/execute). */ kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE, - VMX_EPT_RWX_MASK, 0); + VMX_EPT_RWX_MASK | VMX_EPT_SUPPRESS_VE_BIT, 0); } EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks); diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index a129951c9a8856eb3b427c75adcaed7e312dfd78..400f34b48a49f4ad15cc1ad3f27e1a7c2f0961a4 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -3,6 +3,8 @@ #ifndef KVM_X86_MMU_SPTE_H #define KVM_X86_MMU_SPTE_H +#include + #include "mmu.h" #include "mmu_internal.h" @@ -149,6 +151,22 @@ static_assert(MMIO_SPTE_GEN_LOW_BITS == 8 && MMIO_SPTE_GEN_HIGH_BITS == 11); #define MMIO_SPTE_GEN_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0) +/* + * Non-present SPTE value needs to set bit 63 for TDX, in order to suppress + * #VE and get EPT violations on non-present PTEs. We can use the + * same value also without TDX for both VMX and SVM: + * + * For SVM NPT, for non-present spte (bit 0 = 0), other bits are ignored. + * For VMX EPT, bit 63 is ignored if #VE is disabled. (EPT_VIOLATION_VE=0) + * bit 63 is #VE suppress if #VE is enabled. (EPT_VIOLATION_VE=1) + */ +#ifdef CONFIG_X86_64 +#define SHADOW_NONPRESENT_VALUE BIT_ULL(63) +static_assert(!(SHADOW_NONPRESENT_VALUE & SPTE_MMU_PRESENT_MASK)); +#else +#define SHADOW_NONPRESENT_VALUE 0ULL +#endif + extern u64 __read_mostly shadow_host_writable_mask; extern u64 __read_mostly shadow_mmu_writable_mask; extern u64 __read_mostly shadow_nx_mask; @@ -184,24 +202,24 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask; /* * If a thread running without exclusive control of the MMU lock must perform a - * multi-part operation on an SPTE, it can set the SPTE to REMOVED_SPTE as a + * multi-part operation on an SPTE, it can set the SPTE to FROZEN_SPTE as a * non-present intermediate value. Other threads which encounter this value * should not modify the SPTE. * * Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF - * vulnerability. Use only low bits to avoid 64-bit immediates. + * vulnerability. * * Only used by the TDP MMU. */ -#define REMOVED_SPTE 0x5a0ULL +#define FROZEN_SPTE (SHADOW_NONPRESENT_VALUE | 0x5a0ULL) -/* Removed SPTEs must not be misconstrued as shadow present PTEs. */ -static_assert(!(REMOVED_SPTE & SPTE_MMU_PRESENT_MASK)); +/* Frozen SPTEs must not be misconstrued as shadow present PTEs. */ +static_assert(!(FROZEN_SPTE & SPTE_MMU_PRESENT_MASK)); -static inline bool is_removed_spte(u64 spte) +static inline bool is_frozen_spte(u64 spte) { - return spte == REMOVED_SPTE; + return spte == FROZEN_SPTE; } /* Get an SPTE's index into its parent's page table (and the spt array). */ @@ -249,9 +267,9 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root) return spte_to_child_sp(root); } -static inline bool is_mmio_spte(u64 spte) +static inline bool is_mmio_spte(struct kvm *kvm, u64 spte) { - return (spte & shadow_mmio_mask) == shadow_mmio_value && + return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value && likely(enable_mmio_caching); } @@ -260,6 +278,13 @@ static inline bool is_shadow_present_pte(u64 pte) return !!(pte & SPTE_MMU_PRESENT_MASK); } +static inline bool is_ept_ve_possible(u64 spte) +{ + return (shadow_present_mask & VMX_EPT_SUPPRESS_VE_BIT) && + !(spte & VMX_EPT_SUPPRESS_VE_BIT) && + (spte & VMX_EPT_RWX_MASK) != VMX_EPT_MISCONFIG_WX_VALUE; +} + /* * Returns true if A/D bits are supported in hardware and are enabled by KVM. * When enabled, KVM uses A/D bits for all non-nested MMUs. Because L1 can diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index fae559559a806a8121760a637430b858ec5bacab..2880fd392e0cbb9921aed5b8b5992c54e484530f 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -21,11 +21,13 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep) static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte)); return xchg(rcu_dereference(sptep), new_spte); } static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte) { + KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte)); WRITE_ONCE(*rcu_dereference(sptep), new_spte); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 8eef3ed5fe04e252574372ad0f0f5ed152c84702..a85c8c46170df6fcc1be50ad5c8b2f6678995b51 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -73,11 +73,8 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared) +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) { - kvm_lockdep_assert_mmu_lock_held(kvm, shared); - if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; @@ -106,10 +103,16 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool shared, bool only_valid) + bool only_valid) { struct kvm_mmu_page *next_root; + /* + * While the roots themselves are RCU-protected, fields such as + * role.invalid are protected by mmu_lock. + */ + lockdep_assert_held(&kvm->mmu_lock); + rcu_read_lock(); if (prev_root) @@ -132,7 +135,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, rcu_read_unlock(); if (prev_root) - kvm_tdp_mmu_put_root(kvm, prev_root, shared); + kvm_tdp_mmu_put_root(kvm, prev_root); return next_root; } @@ -144,26 +147,22 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * recent root. (Unless keeping a live reference is desirable.) * * If shared is set, this function is operating under the MMU lock in read - * mode. In the unlikely event that this thread must free a root, the lock - * will be temporarily dropped and reacquired in write mode. + * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid)) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + if (_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) { \ } else -#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) +#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \ - if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \ - } else +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, false)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -172,12 +171,19 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * Holding mmu_lock for write obviates the need for RCU protection as the list * is guaranteed to be stable. */ -#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ - list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _only_valid) \ + list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ + if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ + ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \ + ((_only_valid) && (_root)->role.invalid))) { \ } else +#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root(_kvm, _root, _as_id, false) + +#define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root(_kvm, _root, _as_id, true) + static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; @@ -217,22 +223,41 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp, tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role); } -hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) +int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) { - union kvm_mmu_page_role role = vcpu->arch.mmu->root_role; + struct kvm_mmu *mmu = vcpu->arch.mmu; + union kvm_mmu_page_role role = mmu->root_role; + int as_id = kvm_mmu_role_as_id(role); struct kvm *kvm = vcpu->kvm; struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); + /* + * Check for an existing root before acquiring the pages lock to avoid + * unnecessary serialization if multiple vCPUs are loading a new root. + * E.g. when bringing up secondary vCPUs, KVM will already have created + * a valid root on behalf of the primary vCPU. + */ + read_lock(&kvm->mmu_lock); + + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, as_id) { + if (root->role.word == role.word) + goto out_read_unlock; + } + + spin_lock(&kvm->arch.tdp_mmu_pages_lock); /* - * Check for an existing root before allocating a new one. Note, the - * role check prevents consuming an invalid root. + * Recheck for an existing root after acquiring the pages lock, another + * vCPU may have raced ahead and created a new usable root. Manually + * walk the list of roots as the standard macros assume that the pages + * lock is *not* held. WARN if grabbing a reference to a usable root + * fails, as the last reference to a root can only be put *after* the + * root has been invalidated, which requires holding mmu_lock for write. */ - for_each_tdp_mmu_root(kvm, root, kvm_mmu_role_as_id(role)) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { if (root->role.word == role.word && - kvm_tdp_mmu_get_root(root)) - goto out; + !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) + goto out_spin_unlock; } root = tdp_mmu_alloc_sp(vcpu); @@ -246,13 +271,20 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); - - spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots); - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); -out: - return __pa(root->spt); +out_spin_unlock: + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); +out_read_unlock: + read_unlock(&kvm->mmu_lock); + /* + * Note, KVM_REQ_MMU_FREE_OBSOLETE_ROOTS will prevent entering the guest + * and actually consuming the root if it's invalidated after dropping + * mmu_lock, and the root can't be freed as this vCPU holds a reference. + */ + mmu->root.hpa = __pa(root->spt); + mmu->root.pgd = 0; + return 0; } static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, @@ -276,28 +308,18 @@ static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) * * @kvm: kvm instance * @sp: the page to be removed - * @shared: This operation may not be running under the exclusive use of - * the MMU lock and the operation must synchronize with other - * threads that might be adding or removing pages. */ -static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, - bool shared) +static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { tdp_unaccount_mmu_page(kvm, sp); if (!sp->nx_huge_page_disallowed) return; - if (shared) - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - else - lockdep_assert_held_write(&kvm->mmu_lock); - + spin_lock(&kvm->arch.tdp_mmu_pages_lock); sp->nx_huge_page_disallowed = false; untrack_possible_nx_huge_page(kvm, sp); - - if (shared) - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } /** @@ -326,7 +348,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) trace_kvm_mmu_prepare_zap_page(sp); - tdp_mmu_unlink_sp(kvm, sp, shared); + tdp_mmu_unlink_sp(kvm, sp); for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { tdp_ptep_t sptep = pt + i; @@ -337,14 +359,14 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) /* * Set the SPTE to a nonpresent value that other * threads will not overwrite. If the SPTE was - * already marked as removed then another thread + * already marked as frozen then another thread * handling a page fault could overwrite it, so * set the SPTE until it is set from some other - * value to the removed SPTE value. + * value to the frozen SPTE value. */ for (;;) { - old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, REMOVED_SPTE); - if (!is_removed_spte(old_spte)) + old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, FROZEN_SPTE); + if (!is_frozen_spte(old_spte)) break; cpu_relax(); } @@ -375,11 +397,11 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * No retry is needed in the atomic update path as the * sole concern is dropping a Dirty bit, i.e. no other * task can zap/remove the SPTE as mmu_lock is held for - * write. Marking the SPTE as a removed SPTE is not + * write. Marking the SPTE as a frozen SPTE is not * strictly necessary for the same reason, but using - * the remove SPTE value keeps the shared/exclusive + * the frozen SPTE value keeps the shared/exclusive * paths consistent and allows the handle_changed_spte() - * call below to hardcode the new value to REMOVED_SPTE. + * call below to hardcode the new value to FROZEN_SPTE. * * Note, even though dropping a Dirty bit is the only * scenario where a non-atomic update could result in a @@ -391,10 +413,10 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * it here. */ old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, - REMOVED_SPTE, level); + FROZEN_SPTE, level); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_spte, REMOVED_SPTE, level, shared); + old_spte, FROZEN_SPTE, level, shared); } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -468,19 +490,19 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, */ if (!was_present && !is_present) { /* - * If this change does not involve a MMIO SPTE or removed SPTE, + * If this change does not involve a MMIO SPTE or frozen SPTE, * it is unexpected. Log the change, though it should not * impact the guest since both the former and current SPTEs * are nonpresent. */ - if (WARN_ON_ONCE(!is_mmio_spte(old_spte) && - !is_mmio_spte(new_spte) && - !is_removed_spte(new_spte))) + if (WARN_ON_ONCE(!is_mmio_spte(kvm, old_spte) && + !is_mmio_spte(kvm, new_spte) && + !is_frozen_spte(new_spte))) pr_err("Unexpected SPTE change! Nonpresent SPTEs\n" "should not be replaced with another,\n" "different nonpresent SPTE, unless one or both\n" "are MMIO SPTEs, or the new SPTE is\n" - "a temporary removed SPTE.\n" + "a temporary frozen SPTE.\n" "as_id: %d gfn: %llx old_spte: %llx new_spte: %llx level: %d", as_id, gfn, old_spte, new_spte, level); return; @@ -508,6 +530,32 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, kvm_set_pfn_accessed(spte_to_pfn(old_spte)); } +static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, + u64 new_spte) +{ + u64 *sptep = rcu_dereference(iter->sptep); + + /* + * The caller is responsible for ensuring the old SPTE is not a FROZEN + * SPTE. KVM should never attempt to zap or manipulate a FROZEN SPTE, + * and pre-checking before inserting a new SPTE is advantageous as it + * avoids unnecessary work. + */ + WARN_ON_ONCE(iter->yielded || is_frozen_spte(iter->old_spte)); + + /* + * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and + * does not hold the mmu_lock. On failure, i.e. if a different logical + * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with + * the current value, so the caller operates on fresh data, e.g. if it + * retries tdp_mmu_set_spte_atomic() + */ + if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) + return -EBUSY; + + return 0; +} + /* * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically * and handle the associated bookkeeping. Do not mark the page dirty @@ -525,31 +573,17 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * no side-effects other than setting iter->old_spte to the last * known value of the spte. */ -static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, - struct tdp_iter *iter, - u64 new_spte) +static inline int __must_check tdp_mmu_set_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter, + u64 new_spte) { - u64 *sptep = rcu_dereference(iter->sptep); - - /* - * The caller is responsible for ensuring the old SPTE is not a REMOVED - * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE, - * and pre-checking before inserting a new SPTE is advantageous as it - * avoids unnecessary work. - */ - WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte)); + int ret; lockdep_assert_held_read(&kvm->mmu_lock); - /* - * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. On failure, i.e. if a different logical - * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with - * the current value, so the caller operates on fresh data, e.g. if it - * retries tdp_mmu_set_spte_atomic() - */ - if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) - return -EBUSY; + ret = __tdp_mmu_set_spte_atomic(iter, new_spte); + if (ret) + return ret; handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, new_spte, iter->level, true); @@ -557,31 +591,43 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, return 0; } -static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, - struct tdp_iter *iter) +static inline int __must_check tdp_mmu_zap_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter) { int ret; + lockdep_assert_held_read(&kvm->mmu_lock); + /* - * Freeze the SPTE by setting it to a special, - * non-present value. This will stop other threads from - * immediately installing a present entry in its place - * before the TLBs are flushed. + * Freeze the SPTE by setting it to a special, non-present value. This + * will stop other threads from immediately installing a present entry + * in its place before the TLBs are flushed. + * + * Delay processing of the zapped SPTE until after TLBs are flushed and + * the FROZEN_SPTE is replaced (see below). */ - ret = tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE); + ret = __tdp_mmu_set_spte_atomic(iter, FROZEN_SPTE); if (ret) return ret; kvm_flush_remote_tlbs_gfn(kvm, iter->gfn, iter->level); /* - * No other thread can overwrite the removed SPTE as they must either + * No other thread can overwrite the frozen SPTE as they must either * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not - * overwrite the special removed SPTE value. No bookkeeping is needed - * here since the SPTE is going from non-present to non-present. Use - * the raw write helper to avoid an unnecessary check on volatile bits. + * overwrite the special frozen SPTE value. Use the raw write helper to + * avoid an unnecessary check on volatile bits. */ - __kvm_tdp_mmu_write_spte(iter->sptep, 0); + __kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE); + + /* + * Process the zapped SPTE after flushing TLBs, and after replacing + * FROZEN_SPTE with 0. This minimizes the amount of time vCPUs are + * blocked by the FROZEN_SPTE and reduces contention on the child + * SPTEs. + */ + handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + SHADOW_NONPRESENT_VALUE, iter->level, true); return 0; } @@ -607,12 +653,12 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, /* * No thread should be using this function to set SPTEs to or from the - * temporary removed SPTE value. + * temporary frozen SPTE value. * If operating under the MMU lock in read mode, tdp_mmu_set_spte_atomic * should be used. If operating under the MMU lock in write mode, the - * use of the removed SPTE should not be necessary. + * use of the frozen SPTE should not be necessary. */ - WARN_ON_ONCE(is_removed_spte(old_spte) || is_removed_spte(new_spte)); + WARN_ON_ONCE(is_frozen_spte(old_spte) || is_frozen_spte(new_spte)); old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); @@ -718,8 +764,8 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, continue; if (!shared) - tdp_mmu_iter_set_spte(kvm, &iter, 0); - else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0)) + tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE); + else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE)) goto retry; } } @@ -745,15 +791,26 @@ static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); /* - * To avoid RCU stalls due to recursively removing huge swaths of SPs, - * split the zap into two passes. On the first pass, zap at the 1gb - * level, and then zap top-level SPs on the second pass. "1gb" is not - * arbitrary, as KVM must be able to zap a 1gb shadow page without - * inducing a stall to allow in-place replacement with a 1gb hugepage. + * Zap roots in multiple passes of decreasing granularity, i.e. zap at + * 4KiB=>2MiB=>1GiB=>root, in order to better honor need_resched() (all + * preempt models) or mmu_lock contention (full or real-time models). + * Zapping at finer granularity marginally increases the total time of + * the zap, but in most cases the zap itself isn't latency sensitive. * - * Because zapping a SP recurses on its children, stepping down to - * PG_LEVEL_4K in the iterator itself is unnecessary. + * If KVM is configured to prove the MMU, skip the 4KiB and 2MiB zaps + * in order to mimic the page fault path, which can replace a 1GiB page + * table with an equivalent 1GiB hugepage, i.e. can get saddled with + * zapping a 1GiB region that's fully populated with 4KiB SPTEs. This + * allows verifying that KVM can safely zap 1GiB regions, e.g. without + * inducing RCU stalls, without relying on a relatively rare event + * (zapping roots is orders of magnitude more common). Note, because + * zapping a SP recurses on its children, stepping down to PG_LEVEL_4K + * in the iterator itself is unnecessary. */ + if (!IS_ENABLED(CONFIG_KVM_PROVE_MMU)) { + __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_4K); + __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_2M); + } __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_1G); __tdp_mmu_zap_root(kvm, root, shared, root->role.level); @@ -775,8 +832,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte))) return false; - tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0, - sp->gfn, sp->role.level + 1); + tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, + SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1); return true; } @@ -810,8 +867,14 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, !is_last_spte(iter.old_spte, iter.level)) continue; - tdp_mmu_iter_set_spte(kvm, &iter, 0); - flush = true; + tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE); + + /* + * Zappings SPTEs in invalid roots doesn't require a TLB flush, + * see kvm_tdp_mmu_zap_invalidated_roots() for details. + */ + if (!root->role.invalid) + flush = true; } rcu_read_unlock(); @@ -824,15 +887,16 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Zap leaf SPTEs for the range of gfns, [start, end), for all roots. Returns - * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or - * more SPTEs were zapped since the MMU lock was last acquired. + * Zap leaf SPTEs for the range of gfns, [start, end), for all *VALID** roots. + * Returns true if a TLB flush is needed before releasing the MMU lock, i.e. if + * one or more SPTEs were zapped since the MMU lock was last acquired. */ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, false) + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, -1) flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; @@ -854,7 +918,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for_each_tdp_mmu_root_yield_safe(kvm, root, false) + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) tdp_mmu_zap_root(kvm, root, false); } @@ -868,7 +933,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) read_lock(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root, true) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { if (!root->tdp_mmu_scheduled_root_to_zap) continue; @@ -891,7 +956,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * the root must be reachable by mmu_notifiers while it's being * zapped */ - kvm_tdp_mmu_put_root(kvm, root, true); + kvm_tdp_mmu_put_root(kvm, root); } read_unlock(&kvm->mmu_lock); @@ -905,7 +970,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * the VM is being destroyed). * * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. - * See kvm_tdp_mmu_get_vcpu_root_hpa(). + * See kvm_tdp_mmu_alloc_root(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) { @@ -987,7 +1052,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, } /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */ - if (unlikely(is_mmio_spte(new_spte))) { + if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) { vcpu->stat.pf_mmio_spte_created++; trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn, new_spte); @@ -1062,7 +1127,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * If SPTE has been frozen by another thread, just give up and * retry, avoiding unnecessary page table allocation and free. */ - if (is_removed_spte(iter.old_spte)) + if (is_frozen_spte(iter.old_spte)) goto retry; if (iter.level == fault->goal_level) @@ -1125,7 +1190,7 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false) + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); @@ -1314,24 +1379,22 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); return spte_set; } -static struct kvm_mmu_page *__tdp_mmu_alloc_sp_for_split(gfp_t gfp) +static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(void) { struct kvm_mmu_page *sp; - gfp |= __GFP_ZERO; - - sp = kmem_cache_alloc(mmu_page_header_cache, gfp); + sp = kmem_cache_zalloc(mmu_page_header_cache, GFP_KERNEL_ACCOUNT); if (!sp) return NULL; - sp->spt = (void *)__get_free_page(gfp); + sp->spt = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!sp->spt) { kmem_cache_free(mmu_page_header_cache, sp); return NULL; @@ -1340,45 +1403,6 @@ static struct kvm_mmu_page *__tdp_mmu_alloc_sp_for_split(gfp_t gfp) return sp; } -static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm, - struct tdp_iter *iter, - bool shared) -{ - struct kvm_mmu_page *sp; - - /* - * Since we are allocating while under the MMU lock we have to be - * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct - * reclaim and to avoid making any filesystem callbacks (which can end - * up invoking KVM MMU notifiers, resulting in a deadlock). - * - * If this allocation fails we drop the lock and retry with reclaim - * allowed. - */ - sp = __tdp_mmu_alloc_sp_for_split(GFP_NOWAIT | __GFP_ACCOUNT); - if (sp) - return sp; - - rcu_read_unlock(); - - if (shared) - read_unlock(&kvm->mmu_lock); - else - write_unlock(&kvm->mmu_lock); - - iter->yielded = true; - sp = __tdp_mmu_alloc_sp_for_split(GFP_KERNEL_ACCOUNT); - - if (shared) - read_lock(&kvm->mmu_lock); - else - write_lock(&kvm->mmu_lock); - - rcu_read_lock(); - - return sp; -} - /* Note, the caller is responsible for initializing @sp. */ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, struct kvm_mmu_page *sp, bool shared) @@ -1425,7 +1449,6 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm, { struct kvm_mmu_page *sp = NULL; struct tdp_iter iter; - int ret = 0; rcu_read_lock(); @@ -1449,17 +1472,31 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm, continue; if (!sp) { - sp = tdp_mmu_alloc_sp_for_split(kvm, &iter, shared); + rcu_read_unlock(); + + if (shared) + read_unlock(&kvm->mmu_lock); + else + write_unlock(&kvm->mmu_lock); + + sp = tdp_mmu_alloc_sp_for_split(); + + if (shared) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); + if (!sp) { - ret = -ENOMEM; trace_kvm_mmu_split_huge_page(iter.gfn, iter.old_spte, - iter.level, ret); - break; + iter.level, -ENOMEM); + return -ENOMEM; } - if (iter.yielded) - continue; + rcu_read_lock(); + + iter.yielded = true; + continue; } tdp_mmu_init_child_sp(sp, &iter); @@ -1480,7 +1517,7 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm, if (sp) tdp_mmu_free_sp(sp); - return ret; + return 0; } @@ -1496,11 +1533,10 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, int r = 0; kvm_lockdep_assert_mmu_lock_held(kvm, shared); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) { + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) { r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared); if (r) { - kvm_tdp_mmu_put_root(kvm, root, shared); + kvm_tdp_mmu_put_root(kvm, root); break; } } @@ -1571,8 +1607,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); @@ -1641,7 +1676,7 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root(kvm, root, slot->as_id) + for_each_valid_tdp_mmu_root(kvm, root, slot->as_id) clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot); } @@ -1706,8 +1741,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) zap_collapsible_spte_range(kvm, root, slot); } @@ -1760,7 +1794,7 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root(kvm, root, slot->as_id) + for_each_valid_tdp_mmu_root(kvm, root, slot->as_id) spte_set |= write_protect_gfn(kvm, root, gfn, min_level); return spte_set; @@ -1801,12 +1835,11 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, * * WARNING: This function is only intended to be called during fast_page_fault. */ -u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, +u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *spte) { struct tdp_iter iter; struct kvm_mmu *mmu = vcpu->arch.mmu; - gfn_t gfn = addr >> PAGE_SHIFT; tdp_ptep_t sptep = NULL; tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 733a3aef3a96eaa32964e8fc042c26fae0a0ee9c..4f09757e68353f7acaacdbb3ae49df95ea4fb343 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,15 +10,14 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); +int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) { return refcount_inc_not_zero(&root->tdp_mmu_root_count); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); @@ -66,7 +65,7 @@ static inline void kvm_tdp_mmu_walk_lockless_end(void) int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level); -u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, +u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *spte); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 3eb6e7f47e9634c144b448b435fc147eb48cb4ed..05490b9d8a434f62698ce64e93a451c72c9ee82a 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -19,33 +19,21 @@ #include #include "cpuid.h" -#include "mmu.h" -#define IA32_MTRR_DEF_TYPE_E (1ULL << 11) -#define IA32_MTRR_DEF_TYPE_FE (1ULL << 10) -#define IA32_MTRR_DEF_TYPE_TYPE_MASK (0xff) - -static bool is_mtrr_base_msr(unsigned int msr) -{ - /* MTRR base MSRs use even numbers, masks use odd numbers. */ - return !(msr & 0x1); -} - -static struct kvm_mtrr_range *var_mtrr_msr_to_range(struct kvm_vcpu *vcpu, - unsigned int msr) +static u64 *find_mtrr(struct kvm_vcpu *vcpu, unsigned int msr) { - int index = (msr - MTRRphysBase_MSR(0)) / 2; - - return &vcpu->arch.mtrr_state.var_ranges[index]; -} + int index; -static bool msr_mtrr_valid(unsigned msr) -{ switch (msr) { case MTRRphysBase_MSR(0) ... MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1): + index = msr - MTRRphysBase_MSR(0); + return &vcpu->arch.mtrr_state.var[index]; case MSR_MTRRfix64K_00000: + return &vcpu->arch.mtrr_state.fixed_64k; case MSR_MTRRfix16K_80000: case MSR_MTRRfix16K_A0000: + index = msr - MSR_MTRRfix16K_80000; + return &vcpu->arch.mtrr_state.fixed_16k[index]; case MSR_MTRRfix4K_C0000: case MSR_MTRRfix4K_C8000: case MSR_MTRRfix4K_D0000: @@ -54,10 +42,14 @@ static bool msr_mtrr_valid(unsigned msr) case MSR_MTRRfix4K_E8000: case MSR_MTRRfix4K_F0000: case MSR_MTRRfix4K_F8000: + index = msr - MSR_MTRRfix4K_C0000; + return &vcpu->arch.mtrr_state.fixed_4k[index]; case MSR_MTRRdefType: - return true; + return &vcpu->arch.mtrr_state.deftype; + default: + break; } - return false; + return NULL; } static bool valid_mtrr_type(unsigned t) @@ -70,9 +62,6 @@ static bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) int i; u64 mask; - if (!msr_mtrr_valid(msr)) - return false; - if (msr == MSR_MTRRdefType) { if (data & ~0xcff) return false; @@ -85,8 +74,9 @@ static bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) } /* variable MTRRs */ - WARN_ON(!(msr >= MTRRphysBase_MSR(0) && - msr <= MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1))); + if (WARN_ON_ONCE(!(msr >= MTRRphysBase_MSR(0) && + msr <= MTRRphysMask_MSR(KVM_NR_VAR_MTRR - 1)))) + return false; mask = kvm_vcpu_reserved_gpa_bits_raw(vcpu); if ((msr & 1) == 0) { @@ -94,309 +84,32 @@ static bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!valid_mtrr_type(data & 0xff)) return false; mask |= 0xf00; - } else + } else { /* MTRR mask */ mask |= 0x7ff; - - return (data & mask) == 0; -} - -static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state) -{ - return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_E); -} - -static bool fixed_mtrr_is_enabled(struct kvm_mtrr *mtrr_state) -{ - return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_FE); -} - -static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) -{ - return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; -} - -static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu) -{ - /* - * Intel SDM 11.11.2.2: all MTRRs are disabled when - * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC - * memory type is applied to all of physical memory. - * - * However, virtual machines can be run with CPUID such that - * there are no MTRRs. In that case, the firmware will never - * enable MTRRs and it is obviously undesirable to run the - * guest entirely with UC memory and we use WB. - */ - if (guest_cpuid_has(vcpu, X86_FEATURE_MTRR)) - return MTRR_TYPE_UNCACHABLE; - else - return MTRR_TYPE_WRBACK; -} - -/* -* Three terms are used in the following code: -* - segment, it indicates the address segments covered by fixed MTRRs. -* - unit, it corresponds to the MSR entry in the segment. -* - range, a range is covered in one memory cache type. -*/ -struct fixed_mtrr_segment { - u64 start; - u64 end; - - int range_shift; - - /* the start position in kvm_mtrr.fixed_ranges[]. */ - int range_start; -}; - -static struct fixed_mtrr_segment fixed_seg_table[] = { - /* MSR_MTRRfix64K_00000, 1 unit. 64K fixed mtrr. */ - { - .start = 0x0, - .end = 0x80000, - .range_shift = 16, /* 64K */ - .range_start = 0, - }, - - /* - * MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000, 2 units, - * 16K fixed mtrr. - */ - { - .start = 0x80000, - .end = 0xc0000, - .range_shift = 14, /* 16K */ - .range_start = 8, - }, - - /* - * MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000, 8 units, - * 4K fixed mtrr. - */ - { - .start = 0xc0000, - .end = 0x100000, - .range_shift = 12, /* 12K */ - .range_start = 24, - } -}; - -/* - * The size of unit is covered in one MSR, one MSR entry contains - * 8 ranges so that unit size is always 8 * 2^range_shift. - */ -static u64 fixed_mtrr_seg_unit_size(int seg) -{ - return 8 << fixed_seg_table[seg].range_shift; -} - -static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) -{ - switch (msr) { - case MSR_MTRRfix64K_00000: - *seg = 0; - *unit = 0; - break; - case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: - *seg = 1; - *unit = array_index_nospec( - msr - MSR_MTRRfix16K_80000, - MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1); - break; - case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: - *seg = 2; - *unit = array_index_nospec( - msr - MSR_MTRRfix4K_C0000, - MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1); - break; - default: - return false; } - return true; -} - -static void fixed_mtrr_seg_unit_range(int seg, int unit, u64 *start, u64 *end) -{ - struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; - u64 unit_size = fixed_mtrr_seg_unit_size(seg); - - *start = mtrr_seg->start + unit * unit_size; - *end = *start + unit_size; - WARN_ON(*end > mtrr_seg->end); -} - -static int fixed_mtrr_seg_unit_range_index(int seg, int unit) -{ - struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; - - WARN_ON(mtrr_seg->start + unit * fixed_mtrr_seg_unit_size(seg) - > mtrr_seg->end); - - /* each unit has 8 ranges. */ - return mtrr_seg->range_start + 8 * unit; -} - -static int fixed_mtrr_seg_end_range_index(int seg) -{ - struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; - int n; - - n = (mtrr_seg->end - mtrr_seg->start) >> mtrr_seg->range_shift; - return mtrr_seg->range_start + n - 1; -} - -static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end) -{ - int seg, unit; - - if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) - return false; - - fixed_mtrr_seg_unit_range(seg, unit, start, end); - return true; -} - -static int fixed_msr_to_range_index(u32 msr) -{ - int seg, unit; - - if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) - return -1; - - return fixed_mtrr_seg_unit_range_index(seg, unit); -} - -static int fixed_mtrr_addr_to_seg(u64 addr) -{ - struct fixed_mtrr_segment *mtrr_seg; - int seg, seg_num = ARRAY_SIZE(fixed_seg_table); - - for (seg = 0; seg < seg_num; seg++) { - mtrr_seg = &fixed_seg_table[seg]; - if (mtrr_seg->start <= addr && addr < mtrr_seg->end) - return seg; - } - - return -1; -} - -static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg) -{ - struct fixed_mtrr_segment *mtrr_seg; - int index; - - mtrr_seg = &fixed_seg_table[seg]; - index = mtrr_seg->range_start; - index += (addr - mtrr_seg->start) >> mtrr_seg->range_shift; - return index; -} - -static u64 fixed_mtrr_range_end_addr(int seg, int index) -{ - struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; - int pos = index - mtrr_seg->range_start; - - return mtrr_seg->start + ((pos + 1) << mtrr_seg->range_shift); -} - -static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) -{ - u64 mask; - - *start = range->base & PAGE_MASK; - - mask = range->mask & PAGE_MASK; - - /* This cannot overflow because writing to the reserved bits of - * variable MTRRs causes a #GP. - */ - *end = (*start | ~mask) + 1; -} - -static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) -{ - struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; - gfn_t start, end; - - if (!tdp_enabled || !kvm_arch_has_noncoherent_dma(vcpu->kvm)) - return; - - if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) - return; - - /* fixed MTRRs. */ - if (fixed_msr_to_range(msr, &start, &end)) { - if (!fixed_mtrr_is_enabled(mtrr_state)) - return; - } else if (msr == MSR_MTRRdefType) { - start = 0x0; - end = ~0ULL; - } else { - /* variable range MTRRs. */ - var_mtrr_range(var_mtrr_msr_to_range(vcpu, msr), &start, &end); - } - - kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); -} - -static bool var_mtrr_range_is_valid(struct kvm_mtrr_range *range) -{ - return (range->mask & (1 << 11)) != 0; -} - -static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; - struct kvm_mtrr_range *tmp, *cur; - - cur = var_mtrr_msr_to_range(vcpu, msr); - - /* remove the entry if it's in the list. */ - if (var_mtrr_range_is_valid(cur)) - list_del(&cur->node); - - /* - * Set all illegal GPA bits in the mask, since those bits must - * implicitly be 0. The bits are then cleared when reading them. - */ - if (is_mtrr_base_msr(msr)) - cur->base = data; - else - cur->mask = data | kvm_vcpu_reserved_gpa_bits_raw(vcpu); - - /* add it to the list if it's enabled. */ - if (var_mtrr_range_is_valid(cur)) { - list_for_each_entry(tmp, &mtrr_state->head, node) - if (cur->base >= tmp->base) - break; - list_add_tail(&cur->node, &tmp->node); - } + return (data & mask) == 0; } int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { - int index; + u64 *mtrr; - if (!kvm_mtrr_valid(vcpu, msr, data)) + mtrr = find_mtrr(vcpu, msr); + if (!mtrr) return 1; - index = fixed_msr_to_range_index(msr); - if (index >= 0) - *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data; - else if (msr == MSR_MTRRdefType) - vcpu->arch.mtrr_state.deftype = data; - else - set_var_mtrr_msr(vcpu, msr, data); + if (!kvm_mtrr_valid(vcpu, msr, data)) + return 1; - update_mtrr(vcpu, msr); + *mtrr = data; return 0; } int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { - int index; + u64 *mtrr; /* MSR_MTRRcap is a readonly MSR. */ if (msr == MSR_MTRRcap) { @@ -410,311 +123,10 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } - if (!msr_mtrr_valid(msr)) + mtrr = find_mtrr(vcpu, msr); + if (!mtrr) return 1; - index = fixed_msr_to_range_index(msr); - if (index >= 0) { - *pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index]; - } else if (msr == MSR_MTRRdefType) { - *pdata = vcpu->arch.mtrr_state.deftype; - } else { - /* Variable MTRRs */ - if (is_mtrr_base_msr(msr)) - *pdata = var_mtrr_msr_to_range(vcpu, msr)->base; - else - *pdata = var_mtrr_msr_to_range(vcpu, msr)->mask; - - *pdata &= ~kvm_vcpu_reserved_gpa_bits_raw(vcpu); - } - + *pdata = *mtrr; return 0; } - -void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu) -{ - INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head); -} - -struct mtrr_iter { - /* input fields. */ - struct kvm_mtrr *mtrr_state; - u64 start; - u64 end; - - /* output fields. */ - int mem_type; - /* mtrr is completely disabled? */ - bool mtrr_disabled; - /* [start, end) is not fully covered in MTRRs? */ - bool partial_map; - - /* private fields. */ - union { - /* used for fixed MTRRs. */ - struct { - int index; - int seg; - }; - - /* used for var MTRRs. */ - struct { - struct kvm_mtrr_range *range; - /* max address has been covered in var MTRRs. */ - u64 start_max; - }; - }; - - bool fixed; -}; - -static bool mtrr_lookup_fixed_start(struct mtrr_iter *iter) -{ - int seg, index; - - if (!fixed_mtrr_is_enabled(iter->mtrr_state)) - return false; - - seg = fixed_mtrr_addr_to_seg(iter->start); - if (seg < 0) - return false; - - iter->fixed = true; - index = fixed_mtrr_addr_seg_to_range_index(iter->start, seg); - iter->index = index; - iter->seg = seg; - return true; -} - -static bool match_var_range(struct mtrr_iter *iter, - struct kvm_mtrr_range *range) -{ - u64 start, end; - - var_mtrr_range(range, &start, &end); - if (!(start >= iter->end || end <= iter->start)) { - iter->range = range; - - /* - * the function is called when we do kvm_mtrr.head walking. - * Range has the minimum base address which interleaves - * [looker->start_max, looker->end). - */ - iter->partial_map |= iter->start_max < start; - - /* update the max address has been covered. */ - iter->start_max = max(iter->start_max, end); - return true; - } - - return false; -} - -static void __mtrr_lookup_var_next(struct mtrr_iter *iter) -{ - struct kvm_mtrr *mtrr_state = iter->mtrr_state; - - list_for_each_entry_continue(iter->range, &mtrr_state->head, node) - if (match_var_range(iter, iter->range)) - return; - - iter->range = NULL; - iter->partial_map |= iter->start_max < iter->end; -} - -static void mtrr_lookup_var_start(struct mtrr_iter *iter) -{ - struct kvm_mtrr *mtrr_state = iter->mtrr_state; - - iter->fixed = false; - iter->start_max = iter->start; - iter->range = NULL; - iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node); - - __mtrr_lookup_var_next(iter); -} - -static void mtrr_lookup_fixed_next(struct mtrr_iter *iter) -{ - /* terminate the lookup. */ - if (fixed_mtrr_range_end_addr(iter->seg, iter->index) >= iter->end) { - iter->fixed = false; - iter->range = NULL; - return; - } - - iter->index++; - - /* have looked up for all fixed MTRRs. */ - if (iter->index >= ARRAY_SIZE(iter->mtrr_state->fixed_ranges)) - return mtrr_lookup_var_start(iter); - - /* switch to next segment. */ - if (iter->index > fixed_mtrr_seg_end_range_index(iter->seg)) - iter->seg++; -} - -static void mtrr_lookup_var_next(struct mtrr_iter *iter) -{ - __mtrr_lookup_var_next(iter); -} - -static void mtrr_lookup_start(struct mtrr_iter *iter) -{ - if (!mtrr_is_enabled(iter->mtrr_state)) { - iter->mtrr_disabled = true; - return; - } - - if (!mtrr_lookup_fixed_start(iter)) - mtrr_lookup_var_start(iter); -} - -static void mtrr_lookup_init(struct mtrr_iter *iter, - struct kvm_mtrr *mtrr_state, u64 start, u64 end) -{ - iter->mtrr_state = mtrr_state; - iter->start = start; - iter->end = end; - iter->mtrr_disabled = false; - iter->partial_map = false; - iter->fixed = false; - iter->range = NULL; - - mtrr_lookup_start(iter); -} - -static bool mtrr_lookup_okay(struct mtrr_iter *iter) -{ - if (iter->fixed) { - iter->mem_type = iter->mtrr_state->fixed_ranges[iter->index]; - return true; - } - - if (iter->range) { - iter->mem_type = iter->range->base & 0xff; - return true; - } - - return false; -} - -static void mtrr_lookup_next(struct mtrr_iter *iter) -{ - if (iter->fixed) - mtrr_lookup_fixed_next(iter); - else - mtrr_lookup_var_next(iter); -} - -#define mtrr_for_each_mem_type(_iter_, _mtrr_, _gpa_start_, _gpa_end_) \ - for (mtrr_lookup_init(_iter_, _mtrr_, _gpa_start_, _gpa_end_); \ - mtrr_lookup_okay(_iter_); mtrr_lookup_next(_iter_)) - -u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; - struct mtrr_iter iter; - u64 start, end; - int type = -1; - const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK) - | (1 << MTRR_TYPE_WRTHROUGH); - - start = gfn_to_gpa(gfn); - end = start + PAGE_SIZE; - - mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { - int curr_type = iter.mem_type; - - /* - * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR - * Precedences. - */ - - if (type == -1) { - type = curr_type; - continue; - } - - /* - * If two or more variable memory ranges match and the - * memory types are identical, then that memory type is - * used. - */ - if (type == curr_type) - continue; - - /* - * If two or more variable memory ranges match and one of - * the memory types is UC, the UC memory type used. - */ - if (curr_type == MTRR_TYPE_UNCACHABLE) - return MTRR_TYPE_UNCACHABLE; - - /* - * If two or more variable memory ranges match and the - * memory types are WT and WB, the WT memory type is used. - */ - if (((1 << type) & wt_wb_mask) && - ((1 << curr_type) & wt_wb_mask)) { - type = MTRR_TYPE_WRTHROUGH; - continue; - } - - /* - * For overlaps not defined by the above rules, processor - * behavior is undefined. - */ - - /* We use WB for this undefined behavior. :( */ - return MTRR_TYPE_WRBACK; - } - - if (iter.mtrr_disabled) - return mtrr_disabled_type(vcpu); - - /* not contained in any MTRRs. */ - if (type == -1) - return mtrr_default_type(mtrr_state); - - /* - * We just check one page, partially covered by MTRRs is - * impossible. - */ - WARN_ON(iter.partial_map); - - return type; -} -EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); - -bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, - int page_num) -{ - struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; - struct mtrr_iter iter; - u64 start, end; - int type = -1; - - start = gfn_to_gpa(gfn); - end = gfn_to_gpa(gfn + page_num); - mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { - if (type == -1) { - type = iter.mem_type; - continue; - } - - if (type != iter.mem_type) - return false; - } - - if (iter.mtrr_disabled) - return true; - - if (!iter.partial_map) - return true; - - if (type == -1) - return true; - - return type == mtrr_default_type(mtrr_state); -} diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c new file mode 100644 index 0000000000000000000000000000000000000000..a847663da26c16c5ea126fbb954408f312a6e6d2 --- /dev/null +++ b/arch/x86/kvm/vmx/main.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +#include "x86_ops.h" +#include "vmx.h" +#include "nested.h" +#include "pmu.h" +#include "posted_intr.h" + +#define VMX_REQUIRED_APICV_INHIBITS \ + (BIT(APICV_INHIBIT_REASON_DISABLE)| \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED)) + +struct kvm_x86_ops vt_x86_ops __initdata = { + .name = KBUILD_MODNAME, + + .check_processor_compatibility = vmx_check_processor_compat, + + .hardware_unsetup = vmx_hardware_unsetup, + + .hardware_enable = vmx_hardware_enable, + .hardware_disable = vmx_hardware_disable, + .has_emulated_msr = vmx_has_emulated_msr, + + .vm_size = sizeof(struct kvm_vmx), + .vm_init = vmx_vm_init, + .vm_destroy = vmx_vm_destroy, + + .vcpu_precreate = vmx_vcpu_precreate, + .vcpu_create = vmx_vcpu_create, + .vcpu_free = vmx_vcpu_free, + .vcpu_reset = vmx_vcpu_reset, + + .prepare_switch_to_guest = vmx_prepare_switch_to_guest, + .vcpu_load = vmx_vcpu_load, + .vcpu_put = vmx_vcpu_put, + + .HOST_OWNED_DEBUGCTL = DEBUGCTLMSR_FREEZE_IN_SMM, + + .update_exception_bitmap = vmx_update_exception_bitmap, + .get_msr_feature = vmx_get_msr_feature, + .get_msr = vmx_get_msr, + .set_msr = vmx_set_msr, + .get_segment_base = vmx_get_segment_base, + .get_segment = vmx_get_segment, + .set_segment = vmx_set_segment, + .get_cpl = vmx_get_cpl, + .get_cs_db_l_bits = vmx_get_cs_db_l_bits, + .is_valid_cr0 = vmx_is_valid_cr0, + .set_cr0 = vmx_set_cr0, + .is_valid_cr4 = vmx_is_valid_cr4, + .set_cr4 = vmx_set_cr4, + .set_efer = vmx_set_efer, + .get_idt = vmx_get_idt, + .set_idt = vmx_set_idt, + .get_gdt = vmx_get_gdt, + .set_gdt = vmx_set_gdt, + .set_dr7 = vmx_set_dr7, + .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, + .cache_reg = vmx_cache_reg, + .get_rflags = vmx_get_rflags, + .set_rflags = vmx_set_rflags, + .get_if_flag = vmx_get_if_flag, + + .flush_tlb_all = vmx_flush_tlb_all, + .flush_tlb_current = vmx_flush_tlb_current, + .flush_tlb_gva = vmx_flush_tlb_gva, + .flush_tlb_guest = vmx_flush_tlb_guest, + + .vcpu_pre_run = vmx_vcpu_pre_run, + .vcpu_run = vmx_vcpu_run, + .handle_exit = vmx_handle_exit, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, + .set_interrupt_shadow = vmx_set_interrupt_shadow, + .get_interrupt_shadow = vmx_get_interrupt_shadow, + .patch_hypercall = vmx_patch_hypercall, + .inject_irq = vmx_inject_irq, + .inject_nmi = vmx_inject_nmi, + .inject_exception = vmx_inject_exception, + .cancel_injection = vmx_cancel_injection, + .interrupt_allowed = vmx_interrupt_allowed, + .nmi_allowed = vmx_nmi_allowed, + .get_nmi_mask = vmx_get_nmi_mask, + .set_nmi_mask = vmx_set_nmi_mask, + .enable_nmi_window = vmx_enable_nmi_window, + .enable_irq_window = vmx_enable_irq_window, + .update_cr8_intercept = vmx_update_cr8_intercept, + + .x2apic_icr_is_split = false, + .set_virtual_apic_mode = vmx_set_virtual_apic_mode, + .set_apic_access_page_addr = vmx_set_apic_access_page_addr, + .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, + .load_eoi_exitmap = vmx_load_eoi_exitmap, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, + .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, + .hwapic_irr_update = vmx_hwapic_irr_update, + .hwapic_isr_update = vmx_hwapic_isr_update, + .sync_pir_to_irr = vmx_sync_pir_to_irr, + .deliver_interrupt = vmx_deliver_interrupt, + .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, + + .set_tss_addr = vmx_set_tss_addr, + .set_identity_map_addr = vmx_set_identity_map_addr, + .get_mt_mask = vmx_get_mt_mask, + + .get_exit_info = vmx_get_exit_info, + + .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, + + .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, + + .get_l2_tsc_offset = vmx_get_l2_tsc_offset, + .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, + .write_tsc_offset = vmx_write_tsc_offset, + .write_tsc_multiplier = vmx_write_tsc_multiplier, + + .load_mmu_pgd = vmx_load_mmu_pgd, + + .check_intercept = vmx_check_intercept, + .handle_exit_irqoff = vmx_handle_exit_irqoff, + + .sched_in = vmx_sched_in, + + .cpu_dirty_log_size = PML_ENTITY_NUM, + .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, + + .nested_ops = &vmx_nested_ops, + + .pi_update_irte = vmx_pi_update_irte, + .pi_start_assignment = vmx_pi_start_assignment, + +#ifdef CONFIG_X86_64 + .set_hv_timer = vmx_set_hv_timer, + .cancel_hv_timer = vmx_cancel_hv_timer, +#endif + + .setup_mce = vmx_setup_mce, + +#ifdef CONFIG_KVM_SMM + .smi_allowed = vmx_smi_allowed, + .enter_smm = vmx_enter_smm, + .leave_smm = vmx_leave_smm, + .enable_smi_window = vmx_enable_smi_window, +#endif + + .can_emulate_instruction = vmx_can_emulate_instruction, + .apic_init_signal_blocked = vmx_apic_init_signal_blocked, + .migrate_timers = vmx_migrate_timers, + + .recalc_intercepts = vmx_recalc_intercepts, + .complete_emulated_msr = kvm_complete_insn_gp, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, + + .get_untagged_addr = vmx_get_untagged_addr, +}; + +struct kvm_x86_init_ops vt_init_ops __initdata = { + .hardware_setup = vmx_hardware_setup, + .handle_intel_pt_intr = NULL, + + .runtime_ops = &vt_x86_ops, + .pmu_ops = &intel_pmu_ops, +}; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index a87409418f284dda044c5352b817b62dff7ec534..f4ea5d7f3b315f02ad86e347044facf31d09bc31 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -410,18 +410,30 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long exit_qualification; u32 vm_exit_reason; - unsigned long exit_qualification = vcpu->arch.exit_qualification; if (vmx->nested.pml_full) { vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; - exit_qualification &= INTR_INFO_UNBLOCK_NMI; + + /* + * PML Full and EPT Violation VM-Exits both use bit 12 to report + * "NMI unblocking due to IRET", i.e. the bit can be propagated + * as-is from the original EXIT_QUALIFICATION. + */ + exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI; } else { - if (fault->error_code & PFERR_RSVD_MASK) + if (fault->error_code & PFERR_RSVD_MASK) { vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else + exit_qualification = 0; + } else { + exit_qualification = fault->exit_qualification; + exit_qualification |= vmx_get_exit_qual(vcpu) & + (EPT_VIOLATION_GVA_IS_VALID | + EPT_VIOLATION_GVA_TRANSLATED); vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } /* * Although the caller (kvm_inject_emulated_page_fault) would @@ -2221,6 +2233,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL)); + if (vmx->ve_info) + vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info)); + /* All VMFUNCs are currently emulated through L0 vmexits. */ if (cpu_has_vmx_vmfunc()) vmcs_write64(VM_FUNCTION_CONTROL, 0); @@ -6290,6 +6305,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, else if (is_alignment_check(intr_info) && !vmx_guest_inject_ac(vcpu)) return true; + else if (is_ve_fault(intr_info)) + return true; return false; case EXIT_REASON_EXTERNAL_INTERRUPT: return true; diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 4eabed8e5813af72bac6e9d9377747cdf3a219fa..3bf272c2ec8de8b403f84bb1ed7e151b7ea8ed56 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -142,6 +142,11 @@ static inline bool is_nm_fault(u32 intr_info) return is_exception_n(intr_info, NM_VECTOR); } +static inline bool is_ve_fault(u32 intr_info) +{ + return is_exception_n(intr_info, VE_VECTOR); +} + /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 65a7f475dd1e47ac59b7d923db9f171f28bf786e..c7ad9c6fe41a94b698ca04b6f9b47c4ecbe2ef1e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -68,6 +68,7 @@ #include "vmcs12.h" #include "vmx.h" #include "x86.h" +#include "x86_ops.h" #include "smm.h" #include "vmx_onhyperv.h" #include "posted_intr.h" @@ -510,8 +511,6 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) -static struct kvm_x86_ops vmx_x86_ops __initdata; - static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -569,9 +568,8 @@ static __init void hv_init_evmcs(void) } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_l2_tlb_flush + vt_x86_ops.enable_l2_tlb_flush = hv_enable_l2_tlb_flush; - } else { enlightened_vmcs = false; } @@ -830,6 +828,12 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); + /* + * #VE isn't used for VMX. To test against unexpected changes + * related to #VE for VMX, intercept unexpected #VE and warn on it. + */ + if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + eb |= 1u << VE_VECTOR; /* * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. @@ -1428,14 +1432,14 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. */ -static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { vmx_vcpu_load_vmcs(vcpu, cpu, NULL); vmx_vcpu_pi_load(vcpu, cpu); } -static void vmx_vcpu_put(struct kvm_vcpu *vcpu) +void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); @@ -1494,7 +1498,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmx->emulation_required = vmx_emulation_required(vcpu); } -static bool vmx_get_if_flag(struct kvm_vcpu *vcpu) +bool vmx_get_if_flag(struct kvm_vcpu *vcpu) { return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; } @@ -1600,8 +1604,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1685,7 +1689,7 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) * Recognizes a pending MTF VM-exit and records the nested state for later * delivery. */ -static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1716,7 +1720,7 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) } } -static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) { vmx_update_emulated_instruction(vcpu); return skip_emulated_instruction(vcpu); @@ -1735,7 +1739,7 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } -static void vmx_inject_exception(struct kvm_vcpu *vcpu) +void vmx_inject_exception(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; @@ -1856,12 +1860,12 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) return kvm_caps.default_tsc_scaling_ratio; } -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) +void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); } -static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) +void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } @@ -1904,7 +1908,7 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, return !(msr->data & ~valid_bits); } -static int vmx_get_msr_feature(struct kvm_msr_entry *msr) +int vmx_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: @@ -1921,7 +1925,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -2122,7 +2126,7 @@ bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -2426,7 +2430,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return ret; } -static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) +void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { unsigned long guest_owned_bits; @@ -2574,6 +2578,9 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, &_cpu_based_2nd_exec_control)) return -EIO; } + if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; + #ifndef CONFIG_X86_64 if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) @@ -2598,6 +2605,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, return -EIO; vmx_cap->ept = 0; + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; } if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && vmx_cap->vpid) { @@ -2731,7 +2739,7 @@ static bool kvm_is_vmx_supported(void) return supported; } -static int vmx_check_processor_compat(void) +int vmx_check_processor_compat(void) { int cpu = raw_smp_processor_id(); struct vmcs_config vmcs_conf; @@ -2773,7 +2781,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer) return -EFAULT; } -static int vmx_hardware_enable(void) +int vmx_hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2813,7 +2821,7 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } -static void vmx_hardware_disable(void) +void vmx_hardware_disable(void) { vmclear_local_loaded_vmcss(); @@ -3127,7 +3135,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3157,7 +3165,7 @@ static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->vpid; } -static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u64 root_hpa = mmu->root.hpa; @@ -3173,7 +3181,7 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) vpid_sync_context(vmx_get_current_vpid(vcpu)); } -static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in @@ -3182,7 +3190,7 @@ static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } -static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a @@ -3227,7 +3235,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING) -static bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { if (is_guest_mode(vcpu)) return nested_guest_cr0_valid(vcpu, cr0); @@ -3348,8 +3356,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) return eptp; } -static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, - int root_level) +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; @@ -3378,8 +3385,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, vmcs_writel(GUEST_CR3, guest_cr3); } - -static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* * We operate under the default treatment of SMM, so VMX cannot be @@ -3495,7 +3501,7 @@ void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) var->g = (ar >> 15) & 1; } -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) +u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment s; @@ -3572,14 +3578,14 @@ void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); } -static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) +void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { __vmx_set_segment(vcpu, var, seg); to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } -static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); @@ -3587,25 +3593,25 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) *l = (ar >> 13) & 1; } -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_IDTR_LIMIT); dt->address = vmcs_readl(GUEST_IDTR_BASE); } -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_IDTR_LIMIT, dt->size); vmcs_writel(GUEST_IDTR_BASE, dt->address); } -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_GDTR_LIMIT); dt->address = vmcs_readl(GUEST_GDTR_BASE); } -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_GDTR_LIMIT, dt->size); vmcs_writel(GUEST_GDTR_BASE, dt->address); @@ -4266,8 +4272,8 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) return 0; } -static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, - int trig_mode, int vector) +void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) { struct kvm_vcpu *vcpu = apic->vcpu; @@ -4622,6 +4628,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; enable_unrestricted_guest = 0; } if (!enable_unrestricted_guest) @@ -4720,7 +4727,7 @@ static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) return 0; } -static int vmx_vcpu_precreate(struct kvm *kvm) +int vmx_vcpu_precreate(struct kvm *kvm) { return vmx_alloc_ipiv_pid_table(kvm); } @@ -4745,8 +4752,12 @@ static void init_vmcs(struct vcpu_vmx *vmx) exec_controls_set(vmx, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) + if (cpu_has_secondary_exec_ctrls()) { secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); + if (vmx->ve_info) + vmcs_write64(VE_INFORMATION_ADDRESS, + __pa(vmx->ve_info)); + } if (zx_ext_vmcs_cap & MSR_ZX_VMCS_EXEC_CTL3) { zx_tertiary_exec_controls_set(vmx, vmx_zx_tertiary_exec_control(vmx)); @@ -4879,7 +4890,7 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) __pi_set_sn(&vmx->pi_desc); } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4938,12 +4949,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_update_fb_clear_dis(vcpu, vmx); } -static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) +void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } -static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) +void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { @@ -4954,7 +4965,7 @@ static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } -static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) +void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; @@ -4982,7 +4993,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) vmx_clear_hlt(vcpu); } -static void vmx_inject_nmi(struct kvm_vcpu *vcpu) +void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5060,7 +5071,7 @@ bool vmx_nmi_blocked(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_NMI)); } -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; @@ -5087,7 +5098,7 @@ bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) return __vmx_interrupt_blocked(vcpu); } -static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; @@ -5102,7 +5113,7 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_interrupt_blocked(vcpu); } -static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) +int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { void __user *ret; @@ -5122,7 +5133,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return init_rmode_tss(kvm, ret); } -static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) +int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; return 0; @@ -5243,6 +5254,16 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); + if (WARN_ON_ONCE(is_ve_fault(intr_info))) { + struct vmx_ve_information *ve_info = vmx->ve_info; + + WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION, + "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason); + dump_vmcs(vcpu); + kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE"); + return 1; + } + error_code = 0; if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); @@ -5408,8 +5429,7 @@ static int handle_io(struct kvm_vcpu *vcpu) return kvm_fast_pio(vcpu, size, port, in); } -static void -vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) +void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Patch in the VMCALL instruction: @@ -5618,7 +5638,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) return kvm_complete_insn_gp(vcpu, err); } -static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) +void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); @@ -5637,7 +5657,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } -static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) +void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); } @@ -5810,8 +5830,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; - vcpu->arch.exit_qualification = exit_qualification; - /* * Check that the GPA doesn't exceed physical memory limits, as that is * a guest page fault. We have to emulate the instruction here, because @@ -5908,7 +5926,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) return 1; } -static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) +int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) { if (vmx_emulation_required_with_pending_exception(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); @@ -6196,9 +6214,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); -static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, - u64 *info1, u64 *info2, - u32 *intr_info, u32 *error_code) +void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6463,6 +6480,24 @@ void dump_vmcs(struct kvm_vcpu *vcpu) if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) pr_err("Virtual processor ID = 0x%04x\n", vmcs_read16(VIRTUAL_PROCESSOR_ID)); + if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct vmx_ve_information *ve_info = vmx->ve_info; + u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS); + + /* + * If KVM is dumping the VMCS, then something has gone wrong + * already. Derefencing an address from the VMCS, which could + * very well be corrupted, is a terrible idea. The virtual + * address is known so use it. + */ + pr_err("VE info address = 0x%016llx%s\n", ve_info_pa, + ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)"); + pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n", + ve_info->exit_reason, ve_info->delivery, + ve_info->exit_qualification, + ve_info->guest_linear_address, + ve_info->guest_physical_address, ve_info->eptp_index); + } } /* @@ -6579,7 +6614,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason.full; - vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; + vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu); if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { vcpu->run->internal.data[ndata++] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -6648,7 +6683,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } -static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { int ret = __vmx_handle_exit(vcpu, exit_fastpath); @@ -6736,7 +6771,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) : "eax", "ebx", "ecx", "edx"); } -static void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int tpr_threshold; @@ -6806,7 +6841,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) vmx_update_msr_bitmap_x2apic(vcpu); } -static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) +void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; @@ -6875,7 +6910,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) kvm_release_pfn_clean(pfn); } -static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old; @@ -6925,7 +6960,7 @@ static void vmx_set_rvi(int vector) } } -static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) +void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) { /* * When running L2, updating RVI is only relevant when @@ -6939,7 +6974,7 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) vmx_set_rvi(max_irr); } -static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; @@ -6985,7 +7020,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) return; @@ -6996,7 +7031,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) +void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7027,24 +7062,22 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } -static void handle_exception_irqoff(struct vcpu_vmx *vmx) +static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info) { - u32 intr_info = vmx_get_intr_info(&vmx->vcpu); - /* if exit due to PF check for async PF */ if (is_page_fault(intr_info)) - vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); + vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); /* if exit due to NM, handle before interrupts are enabled */ else if (is_nm_fault(intr_info)) - handle_nm_fault_irqoff(&vmx->vcpu); + handle_nm_fault_irqoff(vcpu); /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); } -static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) +static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, + u32 intr_info) { - u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, @@ -7067,7 +7100,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) vcpu->arch.at_instruction_boundary = true; } -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7075,16 +7108,16 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) return; if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) - handle_external_interrupt_irqoff(vcpu); + handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_irqoff(vmx); + handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); } /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. */ -static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) +bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: @@ -7208,7 +7241,7 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) IDT_VECTORING_ERROR_CODE); } -static void vmx_cancel_injection(struct kvm_vcpu *vcpu) +void vmx_cancel_injection(struct kvm_vcpu *vcpu) { __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), @@ -7385,7 +7418,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, guest_state_exit_irqoff(); } -static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7546,7 +7579,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } -static void vmx_vcpu_free(struct kvm_vcpu *vcpu) +void vmx_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7555,9 +7588,10 @@ static void vmx_vcpu_free(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); + free_page((unsigned long)vmx->ve_info); } -static int vmx_vcpu_create(struct kvm_vcpu *vcpu) +int vmx_vcpu_create(struct kvm_vcpu *vcpu) { struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; @@ -7628,6 +7662,20 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) goto free_vmcs; } + err = -ENOMEM; + if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct page *page; + + BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE); + + /* ve_info must be page aligned. */ + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!page) + goto free_vmcs; + + vmx->ve_info = page_to_virt(page); + } + if (vmx_can_use_ipiv(vcpu)) WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id], __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID); @@ -7646,7 +7694,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" #define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" -static int vmx_vm_init(struct kvm *kvm) +int vmx_vm_init(struct kvm *kvm) { if (!ple_gap) kvm->arch.pause_in_guest = true; @@ -7677,44 +7725,25 @@ static int vmx_vm_init(struct kvm *kvm) return 0; } -static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u8 cache; - - /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in - * memory aliases with conflicting memory types and sometimes MCEs. - * We have to be careful as to what are honored and when. - * - * For MMIO, guest CD/MTRR are ignored. The EPT memory type is set to - * UC. The effective memory type is UC or WC depending on guest PAT. - * This was historically the source of MCEs and we want to be - * conservative. - * - * When there is no need to deal with noncoherent DMA (e.g., no VT-d - * or VT-d has snoop control), guest CD/MTRR/PAT are all ignored. The - * EPT memory type is set to WB. The effective memory type is forced - * WB. - * - * Otherwise, we trust guest. Guest CD/MTRR/PAT are all honored. The - * EPT memory type is used to emulate guest CD/MTRR. + /* + * Force UC for host MMIO regions, as allowing the guest to access MMIO + * with cacheable accesses will result in Machine Checks. */ - if (is_mmio) return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; + /* + * Force WB and ignore guest PAT if the VM does NOT have a non-coherent + * device attached. Letting the guest control memory types on Intel + * CPUs may result in unexpected behavior, and so KVM's ABI is to trust + * the guest to behave only as a last resort. + */ if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { - if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; - else - cache = MTRR_TYPE_UNCACHABLE; - - return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - } - - return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; + return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT); } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) @@ -7852,7 +7881,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); } -static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8058,10 +8087,10 @@ static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; } -static int vmx_check_intercept(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info, - enum x86_intercept_stage stage, - struct x86_exception *exception) +int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -8141,8 +8170,8 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift, return 0; } -static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, - bool *expired) +int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; @@ -8181,13 +8210,13 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, return 0; } -static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) +void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif -static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) +void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) { if (!kvm_pause_in_guest(vcpu->kvm)) shrink_ple_window(vcpu); @@ -8216,7 +8245,7 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); } -static void vmx_setup_mce(struct kvm_vcpu *vcpu) +void vmx_setup_mce(struct kvm_vcpu *vcpu) { if (vcpu->arch.mcg_cap & MCG_LMCE_P) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= @@ -8227,7 +8256,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) } #ifdef CONFIG_KVM_SMM -static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ if (to_vmx(vcpu)->nested.nested_run_pending) @@ -8235,7 +8264,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) +int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8256,7 +8285,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) return 0; } -static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) +int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -8277,18 +8306,18 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) return 0; } -static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) +void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } #endif -static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu); } -static void vmx_migrate_timers(struct kvm_vcpu *vcpu) +void vmx_migrate_timers(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer; @@ -8298,7 +8327,7 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu) } } -static void vmx_hardware_unsetup(void) +void vmx_hardware_unsetup(void) { kvm_set_posted_intr_wakeup_handler(NULL); @@ -8308,18 +8337,7 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -#define VMX_REQUIRED_APICV_INHIBITS \ -( \ - BIT(APICV_INHIBIT_REASON_DISABLE)| \ - BIT(APICV_INHIBIT_REASON_ABSENT) | \ - BIT(APICV_INHIBIT_REASON_HYPERV) | \ - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ - BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \ -) - -static void vmx_vm_destroy(struct kvm *kvm) +void vmx_vm_destroy(struct kvm *kvm) { struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); @@ -8370,151 +8388,6 @@ gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); } -static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = KBUILD_MODNAME, - - .check_processor_compatibility = vmx_check_processor_compat, - - .hardware_unsetup = vmx_hardware_unsetup, - - .hardware_enable = vmx_hardware_enable, - .hardware_disable = vmx_hardware_disable, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_size = sizeof(struct kvm_vmx), - .vm_init = vmx_vm_init, - .vm_destroy = vmx_vm_destroy, - - .vcpu_precreate = vmx_vcpu_precreate, - .vcpu_create = vmx_vcpu_create, - .vcpu_free = vmx_vcpu_free, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_switch_to_guest = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .HOST_OWNED_DEBUGCTL = DEBUGCTLMSR_FREEZE_IN_SMM, - - .update_exception_bitmap = vmx_update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .is_valid_cr0 = vmx_is_valid_cr0, - .set_cr0 = vmx_set_cr0, - .is_valid_cr4 = vmx_is_valid_cr4, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - .get_if_flag = vmx_get_if_flag, - - .flush_tlb_all = vmx_flush_tlb_all, - .flush_tlb_current = vmx_flush_tlb_current, - .flush_tlb_gva = vmx_flush_tlb_gva, - .flush_tlb_guest = vmx_flush_tlb_guest, - - .vcpu_pre_run = vmx_vcpu_pre_run, - .vcpu_run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = vmx_skip_emulated_instruction, - .update_emulated_instruction = vmx_update_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .inject_irq = vmx_inject_irq, - .inject_nmi = vmx_inject_nmi, - .inject_exception = vmx_inject_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = vmx_enable_nmi_window, - .enable_irq_window = vmx_enable_irq_window, - .update_cr8_intercept = vmx_update_cr8_intercept, - - .x2apic_icr_is_split = false, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_pre_state_restore = vmx_apicv_pre_state_restore, - .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_interrupt = vmx_deliver_interrupt, - .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .get_l2_tsc_offset = vmx_get_l2_tsc_offset, - .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, - .write_tsc_offset = vmx_write_tsc_offset, - .write_tsc_multiplier = vmx_write_tsc_multiplier, - - .load_mmu_pgd = vmx_load_mmu_pgd, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - - .sched_in = vmx_sched_in, - - .cpu_dirty_log_size = PML_ENTITY_NUM, - .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, - - .nested_ops = &vmx_nested_ops, - - .pi_update_irte = vmx_pi_update_irte, - .pi_start_assignment = vmx_pi_start_assignment, - -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif - - .setup_mce = vmx_setup_mce, - -#ifdef CONFIG_KVM_SMM - .smi_allowed = vmx_smi_allowed, - .enter_smm = vmx_enter_smm, - .leave_smm = vmx_leave_smm, - .enable_smi_window = vmx_enable_smi_window, -#endif - - .can_emulate_instruction = vmx_can_emulate_instruction, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, - .migrate_timers = vmx_migrate_timers, - - .recalc_intercepts = vmx_recalc_intercepts, - .complete_emulated_msr = kvm_complete_insn_gp, - - .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, - - .get_untagged_addr = vmx_get_untagged_addr, -}; - static unsigned int vmx_handle_intel_pt_intr(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); @@ -8580,9 +8453,7 @@ static void __init vmx_setup_me_spte_mask(void) kvm_mmu_set_me_spte_mask(0, me_mask); } -static struct kvm_x86_init_ops vmx_init_ops __initdata; - -static __init int hardware_setup(void) +__init int vmx_hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; @@ -8655,16 +8526,16 @@ static __init int hardware_setup(void) * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) - vmx_x86_ops.set_apic_access_page_addr = NULL; + vt_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) - vmx_x86_ops.update_cr8_intercept = NULL; + vt_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - vmx_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; - vmx_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; + vt_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + vt_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif @@ -8679,7 +8550,7 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; if (!enable_apicv) - vmx_x86_ops.sync_pir_to_irr = NULL; + vt_x86_ops.sync_pir_to_irr = NULL; if (!enable_apicv || !cpu_has_vmx_ipiv()) enable_ipiv = false; @@ -8715,7 +8586,7 @@ static __init int hardware_setup(void) enable_pml = 0; if (!enable_pml) - vmx_x86_ops.cpu_dirty_log_size = 0; + vt_x86_ops.cpu_dirty_log_size = 0; if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; @@ -8740,8 +8611,8 @@ static __init int hardware_setup(void) } if (!enable_preemption_timer) { - vmx_x86_ops.set_hv_timer = NULL; - vmx_x86_ops.cancel_hv_timer = NULL; + vt_x86_ops.set_hv_timer = NULL; + vt_x86_ops.cancel_hv_timer = NULL; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; @@ -8752,9 +8623,9 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; if (pt_mode == PT_MODE_HOST_GUEST) - vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; + vt_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; else - vmx_init_ops.handle_intel_pt_intr = NULL; + vt_init_ops.handle_intel_pt_intr = NULL; setup_default_sgx_lepubkeyhash(); @@ -8777,14 +8648,6 @@ static __init int hardware_setup(void) return r; } -static struct kvm_x86_init_ops vmx_init_ops __initdata = { - .hardware_setup = hardware_setup, - .handle_intel_pt_intr = NULL, - - .runtime_ops = &vmx_x86_ops, - .pmu_ops = &intel_pmu_ops, -}; - static void vmx_cleanup_l1d_flush(void) { if (vmx_l1d_flush_pages) { @@ -8833,7 +8696,7 @@ static int __init vmx_init(void) if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; - r = kvm_x86_vendor_init(&vmx_init_ops); + r = kvm_x86_vendor_init(&vt_init_ops); if (r) return r; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index b779bc28404bc7359d393a0aab3c667cd4fa221a..676d1dd49922b95e841ed64a130c8f4889c6af38 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -345,6 +345,9 @@ struct vcpu_vmx { struct pt_desc pt_desc; struct lbr_desc lbr_desc; + + /* ve_info must be page aligned. */ + struct vmx_ve_information *ve_info; }; struct kvm_vmx { @@ -585,7 +588,8 @@ static inline u8 vmx_get_rvi(void) SECONDARY_EXEC_ENABLE_VMFUNC | \ SECONDARY_EXEC_BUS_LOCK_DETECTION | \ SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) + SECONDARY_EXEC_ENCLS_EXITING | \ + SECONDARY_EXEC_EPT_VIOLATION_VE) #define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0 #define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL \ diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3c226dac29f85c8cace88ca3a4b5d99d67eb860b --- /dev/null +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_X86_OPS_H +#define __KVM_X86_VMX_X86_OPS_H + +#include + +#include "x86.h" + +__init int vmx_hardware_setup(void); + +extern struct kvm_x86_ops vt_x86_ops __initdata; +extern struct kvm_x86_init_ops vt_init_ops __initdata; + +void vmx_hardware_unsetup(void); +int vmx_check_processor_compat(void); +int vmx_hardware_enable(void); +void vmx_hardware_disable(void); +int vmx_vm_init(struct kvm *kvm); +void vmx_vm_destroy(struct kvm *kvm); +int vmx_vcpu_precreate(struct kvm *kvm); +int vmx_vcpu_create(struct kvm_vcpu *vcpu); +int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu); +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags); +void vmx_vcpu_free(struct kvm_vcpu *vcpu); +void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void vmx_vcpu_put(struct kvm_vcpu *vcpu); +int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath); +void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu); +int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu); +void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu); +int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +#ifdef CONFIG_KVM_SMM +int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection); +int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram); +int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram); +void vmx_enable_smi_window(struct kvm_vcpu *vcpu); +#endif +bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); +int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception); +bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu); +void vmx_migrate_timers(struct kvm_vcpu *vcpu); +void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu); +bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason); +void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); +int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu); +void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); +void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu); +bool vmx_has_emulated_msr(struct kvm *kvm, u32 index); +void vmx_recalc_intercepts(struct kvm_vcpu *vcpu); +void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); +void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); +int vmx_get_msr_feature(struct kvm_msr_entry *msr); +int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg); +void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +int vmx_get_cpl(struct kvm_vcpu *vcpu); +void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); +bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); +void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer); +void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val); +void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val); +void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu); +void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg); +unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); +void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); +bool vmx_get_if_flag(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_all(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_current(struct kvm_vcpu *vcpu); +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr); +void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu); +void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask); +u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); +void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall); +void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected); +void vmx_inject_nmi(struct kvm_vcpu *vcpu); +void vmx_inject_exception(struct kvm_vcpu *vcpu); +void vmx_cancel_injection(struct kvm_vcpu *vcpu); +int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection); +int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection); +bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); +void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); +void vmx_enable_nmi_window(struct kvm_vcpu *vcpu); +void vmx_enable_irq_window(struct kvm_vcpu *vcpu); +void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr); +void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu); +void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); +void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); +int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); +int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr); +u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); +void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code); +u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); +u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); +void vmx_write_tsc_offset(struct kvm_vcpu *vcpu); +void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu); +void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu); +void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +#ifdef CONFIG_X86_64 +int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired); +void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu); +#endif +void vmx_setup_mce(struct kvm_vcpu *vcpu); + +#endif /* __KVM_X86_VMX_X86_OPS_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e57fbe59cfcd9b71e9cd51b50baef30d0b4bd4c1..b5fecf79f738768944ee50e458c7f223e749f65f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -94,9 +94,12 @@ #define MAX_IO_MSRS 256 #define KVM_MAX_MCE_BANKS 32 -struct kvm_caps kvm_caps __read_mostly = { - .supported_mce_cap = MCG_CTL_P | MCG_SER_P, -}; +/* + * Note, kvm_caps fields should *never* have default values, all fields must be + * recomputed from scratch during vendor module load, e.g. to account for a + * vendor module being reloaded with different module parameters. + */ +struct kvm_caps kvm_caps __read_mostly; EXPORT_SYMBOL_GPL(kvm_caps); #define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) @@ -978,11 +981,6 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) kvm_mmu_reset_context(vcpu); - - if (((cr0 ^ old_cr0) & X86_CR0_CD) && - kvm_arch_has_noncoherent_dma(vcpu->kvm) && - !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); } EXPORT_SYMBOL_GPL(kvm_post_set_cr0); @@ -2714,8 +2712,9 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, kvm_track_tsc_matching(vcpu); } -static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) +static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) { + u64 data = user_value ? *user_value : 0; struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; @@ -2730,25 +2729,37 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) if (vcpu->arch.virtual_tsc_khz) { if (data == 0) { /* - * detection of vcpu initialization -- need to sync - * with other vCPUs. This particularly helps to keep - * kvm_clock stable after CPU hotplug + * Force synchronization when creating a vCPU, or when + * userspace explicitly writes a zero value. */ synchronizing = true; - } else { + } else if (kvm->arch.user_set_tsc) { u64 tsc_exp = kvm->arch.last_tsc_write + nsec_to_cycles(vcpu, elapsed); u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; /* - * Special case: TSC write with a small delta (1 second) - * of virtual cycle time against real time is - * interpreted as an attempt to synchronize the CPU. + * Here lies UAPI baggage: when a user-initiated TSC write has + * a small delta (1 second) of virtual cycle time against the + * previously set vCPU, we assume that they were intended to be + * in sync and the delta was only due to the racy nature of the + * legacy API. + * + * This trick falls down when restoring a guest which genuinely + * has been running for less time than the 1 second of imprecision + * which we allow for in the legacy API. In this case, the first + * value written by userspace (on any vCPU) should not be subject + * to this 'correction' to make it sync up with values that only + * come from the kernel's default vCPU creation. Make the 1-second + * slop hack only trigger if the user_set_tsc flag is already set. */ synchronizing = data < tsc_exp + tsc_hz && data + tsc_hz > tsc_exp; } } + if (user_value) + kvm->arch.user_set_tsc = true; + /* * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the @@ -3791,7 +3802,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_TSC: if (msr_info->host_initiated) { - kvm_synchronize_tsc(vcpu, data); + kvm_synchronize_tsc(vcpu, &data); } else { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); @@ -4556,6 +4567,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PRE_FAULT_MEMORY: r = tdp_enabled; break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: + r = kvm ? kvm->arch.apic_bus_cycle_ns : APIC_BUS_CYCLE_NS_DEFAULT; + break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; break; @@ -5655,6 +5669,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); + kvm->arch.user_set_tsc = true; __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); @@ -6650,6 +6665,30 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, r = static_call(kvm_x86_enable_hygon_coco_extension)(kvm, (u32)cap->args[0]); break; + case KVM_CAP_X86_APIC_BUS_CYCLES_NS: { + u64 bus_cycle_ns = cap->args[0]; + u64 unused; + + /* + * Guard against overflow in tmict_to_ns(). 128 is the highest + * divide value that can be programmed in APIC_TDCR. + */ + r = -EINVAL; + if (!bus_cycle_ns || + check_mul_overflow((u64)U32_MAX * 128, bus_cycle_ns, &unused)) + break; + + r = 0; + mutex_lock(&kvm->lock); + if (!irqchip_in_kernel(kvm)) + r = -ENXIO; + else if (kvm->created_vcpus) + r = -EINVAL; + else + kvm->arch.apic_bus_cycle_ns = bus_cycle_ns; + mutex_unlock(&kvm->lock); + break; + } default: r = -EINVAL; break; @@ -8801,31 +8840,24 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_release_pfn_clean(pfn); - /* The instructions are well-emulated on direct mmu. */ - if (vcpu->arch.mmu->root_role.direct) { - unsigned int indirect_shadow_pages; - - write_lock(&vcpu->kvm->mmu_lock); - indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; - write_unlock(&vcpu->kvm->mmu_lock); - - if (indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - - return true; - } - /* - * if emulation was due to access to shadowed page table - * and it failed try to unshadow page and re-enter the - * guest to let CPU execute the instruction. + * If emulation may have been triggered by a write to a shadowed page + * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the + * guest to let the CPU re-execute the instruction in the hope that the + * CPU can cleanly execute the instruction that KVM failed to emulate. */ - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + if (vcpu->kvm->arch.indirect_shadow_pages) + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); /* - * If the access faults on its page table, it can not - * be fixed by unprotecting shadow page and it should - * be reported to userspace. + * If the failed instruction faulted on an access to page tables that + * are used to translate any part of the instruction, KVM can't resolve + * the issue by unprotecting the gfn, as zapping the shadow page will + * result in the instruction taking a !PRESENT page fault and thus put + * the vCPU into an infinite loop of page faults. E.g. KVM will create + * a SPTE and write-protect the gfn to resolve the !PRESENT fault, and + * then zap the SPTE to unprotect the gfn, and then do it all over + * again. Report the error to userspace. */ return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); } @@ -9706,6 +9738,8 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return -EIO; } + memset(&kvm_caps, 0, sizeof(kvm_caps)); + x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { pr_err("failed to allocate cache for x86 emulator\n"); @@ -9725,6 +9759,7 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) goto out_free_percpu; kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); + kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P; if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); @@ -10050,26 +10085,15 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl) { - unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit; - - if (kvm_xen_hypercall_enabled(vcpu->kvm)) - return kvm_xen_hypercall(vcpu); - - if (kvm_hv_hypercall_enabled(vcpu)) - return kvm_hv_hypercall(vcpu); - - nr = kvm_rax_read(vcpu); - a0 = kvm_rbx_read(vcpu); - a1 = kvm_rcx_read(vcpu); - a2 = kvm_rdx_read(vcpu); - a3 = kvm_rsi_read(vcpu); + unsigned long ret; trace_kvm_hypercall(nr, a0, a1, a2, a3); - op_64_bit = is_64_bit_hypercall(vcpu); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -10078,11 +10102,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (static_call(kvm_x86_get_cpl)(vcpu) != 0 && - !(is_x86_vendor_hygon() && (nr == KVM_HC_VM_ATTESTATION - || nr == KVM_HC_PSP_OP_OBSOLETE - || nr == KVM_HC_PSP_COPY_FORWARD_OP - || nr == KVM_HC_PSP_FORWARD_OP))) { + if (cpl && !(is_x86_vendor_hygon() && (nr == KVM_HC_VM_ATTESTATION + || nr == KVM_HC_PSP_OP_OBSOLETE + || nr == KVM_HC_PSP_COPY_FORWARD_OP + || nr == KVM_HC_PSP_FORWARD_OP))) { ret = -KVM_EPERM; goto out; } @@ -10143,6 +10166,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); vcpu->arch.complete_userspace_io = complete_hypercall_exit; + /* stat is incremented on completion. */ return 0; } case KVM_HC_VM_ATTESTATION: @@ -10161,12 +10185,42 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) ret = -KVM_ENOSYS; break; } + out: + ++vcpu->stat.hypercalls; + return ret; +} +EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall); + +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) +{ + unsigned long nr, a0, a1, a2, a3, ret; + int op_64_bit; + int cpl; + + if (kvm_xen_hypercall_enabled(vcpu->kvm)) + return kvm_xen_hypercall(vcpu); + + if (kvm_hv_hypercall_enabled(vcpu)) + return kvm_hv_hypercall(vcpu); + + nr = kvm_rax_read(vcpu); + a0 = kvm_rbx_read(vcpu); + a1 = kvm_rcx_read(vcpu); + a2 = kvm_rdx_read(vcpu); + a3 = kvm_rsi_read(vcpu); + op_64_bit = is_64_bit_hypercall(vcpu); + cpl = static_call(kvm_x86_get_cpl)(vcpu); + + ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl); + if (nr == KVM_HC_MAP_GPA_RANGE && !ret) + /* MAP_GPA tosses the request to the user space. */ + return 0; + if (!op_64_bit) ret = (u32)ret; kvm_rax_write(vcpu, ret); - ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); @@ -11147,6 +11201,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_vcpu_srcu_read_lock(vcpu); + /* + * Call this to ensure WC buffers in guest are evicted after each VM + * Exit, so that the evicted WC writes can be snooped across all cpus + */ + smp_mb__after_srcu_read_lock(); + /* * Profile KVM exit RIPs: */ @@ -12311,7 +12371,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_xen_init_vcpu(vcpu); - kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz); kvm_vcpu_reset(vcpu, false); @@ -12343,7 +12402,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); - kvm_synchronize_tsc(vcpu, 0); + kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); /* poll control enabled by default */ @@ -12725,6 +12784,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); kvm->arch.default_tsc_khz = max_tsc_khz ? : tsc_khz; + kvm->arch.apic_bus_cycle_ns = APIC_BUS_CYCLE_NS_DEFAULT; kvm->arch.guest_can_read_msr_platform_info = true; kvm->arch.enable_pmu = enable_pmu; @@ -13583,15 +13643,30 @@ bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); +static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) +{ + /* + * Non-coherent DMA assignment and de-assignment may affect whether or + * not KVM honors guest PAT, and thus may cause changes in EPT SPTEs + * due to toggling the "ignore PAT" bit. Zap all SPTEs when the first + * (or last) non-coherent device is (un)registered to so that new SPTEs + * with the correct "ignore guest PAT" setting are created. + */ + if (kvm_mmu_may_ignore_guest_pat()) + kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL)); +} + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { - atomic_inc(&kvm->arch.noncoherent_dma_count); + if (atomic_inc_return(&kvm->arch.noncoherent_dma_count) == 1) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { - atomic_dec(&kvm->arch.noncoherent_dma_count); + if (!atomic_dec_return(&kvm->arch.noncoherent_dma_count)) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 948eb63cec944768b8946584fd13c5974344a24e..7c651ed83c5383e4c0237e01e5d0db161793875f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -309,12 +309,8 @@ int handle_ud(struct kvm_vcpu *vcpu); void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu, struct kvm_queued_exception *ex); -void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu); -u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); -bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, - int page_num); bool kvm_vector_hashing_enabled(void); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code); int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 455aa6989f318de621f8e49f614e8971d07e00cb..85d54ecadc4865799371bffeeba057cb2fc17824 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2130,6 +2130,32 @@ static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, return 1; return 0; } + +/* + * This lockless version of the range-based retry check *must* be paired with a + * call to the locked version after acquiring mmu_lock, i.e. this is safe to + * use only as a pre-check to avoid contending mmu_lock. This version *will* + * get false negatives and false positives. + */ +static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, + unsigned long mmu_seq, + gfn_t gfn) +{ + /* + * Use READ_ONCE() to ensure the in-progress flag and sequence counter + * are always read from memory, e.g. so that checking for retry in a + * loop won't result in an infinite retry loop. Don't force loads for + * start+end, as the key to avoiding infinite retry loops is observing + * the 1=>0 transition of in-progress, i.e. getting false negatives + * due to stale start+end values is acceptable. + */ + if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) && + gfn >= kvm->mmu_invalidate_range_start && + gfn < kvm->mmu_invalidate_range_end) + return true; + + return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; +} #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 6b2b8f7e0b46a5c5f905142cb63635074cb7bb11..44b2411077dc1e2b8b97d4f1165cad5c1d04c4df 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -118,6 +118,7 @@ struct gfn_to_pfn_cache { struct kvm_mmu_memory_cache { gfp_t gfp_zero; gfp_t gfp_custom; + u64 init_value; struct kmem_cache *kmem_cache; int capacity; int nobjs; diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 236610e4a8fa5d704b7e4bb243b720a7c5fc1283..1cb4527076de9c04571644f8f5390ab3960cfa46 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -343,6 +343,20 @@ static inline void smp_mb__after_srcu_read_unlock(void) /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } +/** + * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock + * + * Converts the preceding srcu_read_lock into a two-way memory barrier. + * + * Call this after srcu_read_lock, to guarantee that all memory operations + * that occur after smp_mb__after_srcu_read_lock will appear to happen after + * the preceding srcu_read_lock. + */ +static inline void smp_mb__after_srcu_read_lock(void) +{ + /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ +} + DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2512693b156d08fa7a0284b56b024be4292ddf1c..26f4e94fb2fce633e532a40886042fcb4b56eecb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1234,6 +1234,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 #define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 #define KVM_CAP_ARM_EL2 240 #define KVM_CAP_ARM_EL2_E2H0 241 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 3c8e90b0ababca587968f8a309d9d5030fe3302c..7598a98d183086f5d6d6d9e313211e203167b59b 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -908,6 +908,7 @@ struct kvm_enable_cap { #define KVM_CAP_MEMORY_ATTRIBUTES 233 #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_PRE_FAULT_MEMORY 236 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1530,4 +1531,13 @@ struct kvm_create_guest_memfd { __u64 reserved[6]; }; +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; + __u64 padding[5]; +}; + #endif /* __LINUX_KVM_H */ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 18a20588823939851f5bd5e056221eacc0b2863a..4033e985c22eb4e0e5e097411899e94530f7330a 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -119,6 +119,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test +TEST_GEN_PROGS_x86_64 += x86_64/apic_bus_clock_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test TEST_GEN_PROGS_x86_64 += x86_64/xcr0_cpuid_test @@ -152,6 +153,7 @@ TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test TEST_GEN_PROGS_x86_64 += system_counter_offset_test +TEST_GEN_PROGS_x86_64 += pre_fault_memory_test # Compiled outputs used by test targets TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index fc3650894cd5025735583d30fc91ea4f6a932752..96241dcc02a010eaa58963657726f1c185737035 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -12,6 +12,7 @@ #include "gic.h" #include "processor.h" #include "timer_test.h" +#include "ucall_common.h" #include "vgic.h" enum guest_stage { diff --git a/tools/testing/selftests/kvm/arch_timer.c b/tools/testing/selftests/kvm/arch_timer.c index ae1f1a6d8312347217de3b616a24e88cbb79f37d..40cb6c1bec0a08b988f30816f6a8ccf516a6d7b5 100644 --- a/tools/testing/selftests/kvm/arch_timer.c +++ b/tools/testing/selftests/kvm/arch_timer.c @@ -29,6 +29,7 @@ #include #include "timer_test.h" +#include "ucall_common.h" struct test_args test_args = { .nr_vcpus = NR_VCPUS_DEF, diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 09c116a82a8499d7b14dc60bdcb088dd6c6914c7..2942b351fb7fe8459631463a0aa8102951d67a5a 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -22,6 +22,7 @@ #include "test_util.h" #include "memstress.h" #include "guest_modes.h" +#include "ucall_common.h" #include "userfaultfd_util.h" #ifdef __NR_userfaultfd diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 53c9d7a2611dea3e3cad0349025835d578ad3a92..7b70f69dc456f0a6c7cc73d3afc8ea3ac6f1f8d4 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -18,6 +18,7 @@ #include "test_util.h" #include "memstress.h" #include "guest_modes.h" +#include "ucall_common.h" #ifdef __aarch64__ #include "aarch64/vgic.h" diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 4ca747c338465411f93882d38621c472b7d61709..447a91cb12aaf2d102afff187e04f532b9e423b2 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -23,6 +23,7 @@ #include "test_util.h" #include "guest_modes.h" #include "processor.h" +#include "ucall_common.h" #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 2f3379b7e67ddf897b67b8fd3a0a40f5cedde9a8..6fdd2d5fce2a02563f420cac1f1074b6beb494c7 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -19,8 +19,8 @@ #include #include +#include "kvm_util.h" #include "test_util.h" -#include "kvm_util_base.h" static void test_file_read_write(int fd) { diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c index 41230b74619023d447f48fc8555936e194ce9387..2545c13dad2cdca2c8d88634c138f38eca02c001 100644 --- a/tools/testing/selftests/kvm/guest_print_test.c +++ b/tools/testing/selftests/kvm/guest_print_test.c @@ -13,6 +13,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" struct guest_vals { uint64_t a; diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 7d618709e33227d6baeafe2e985dc02710abdfb8..871212e7e7977cd876bdc69181ea2711b3d46803 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -8,6 +8,8 @@ #define SELFTEST_KVM_PROCESSOR_H #include "kvm_util.h" +#include "ucall_common.h" + #include #include #include diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/aarch64/ucall.h index 4b68f37efd368aeca9cea55bfd3c489a3f78339e..4ec801f37f00e7a1fbd28818d9e72fc3fd0f4d9c 100644 --- a/tools/testing/selftests/kvm/include/aarch64/ucall.h +++ b/tools/testing/selftests/kvm/include/aarch64/ucall.h @@ -2,7 +2,7 @@ #ifndef SELFTEST_KVM_UCALL_H #define SELFTEST_KVM_UCALL_H -#include "kvm_util_base.h" +#include "kvm_util.h" #define UCALL_EXIT_REASON KVM_EXIT_MMIO diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index c9286811a4cb88e05c235274a27adc4cbee8dcb1..d713db469c678159a4d6aa97d6981f43f08ca0eb 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -1,13 +1,1118 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/kvm_util.h - * * Copyright (C) 2018, Google LLC. */ #ifndef SELFTEST_KVM_UTIL_H #define SELFTEST_KVM_UTIL_H -#include "kvm_util_base.h" -#include "ucall_common.h" +#include "test_util.h" + +#include +#include "linux/hashtable.h" +#include "linux/list.h" +#include +#include +#include "linux/rbtree.h" +#include + +#include +#include + +#include + +#include "kvm_util_arch.h" +#include "kvm_util_types.h" +#include "sparsebit.h" + +#define KVM_DEV_PATH "/dev/kvm" +#define KVM_MAX_VCPUS 1024 + +#define NSEC_PER_SEC 1000000000L + +struct userspace_mem_region { + struct kvm_userspace_memory_region2 region; + struct sparsebit *unused_phy_pages; + struct sparsebit *protected_phy_pages; + int fd; + off_t offset; + enum vm_mem_backing_src_type backing_src_type; + void *host_mem; + void *host_alias; + void *mmap_start; + void *mmap_alias; + size_t mmap_size; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; +}; + +struct kvm_vcpu { + struct list_head list; + uint32_t id; + int fd; + struct kvm_vm *vm; + struct kvm_run *run; +#ifdef __x86_64__ + struct kvm_cpuid2 *cpuid; +#endif + struct kvm_dirty_gfn *dirty_gfns; + uint32_t fetch_index; + uint32_t dirty_gfns_count; +}; + +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + +enum kvm_mem_region_type { + MEM_REGION_CODE, + MEM_REGION_DATA, + MEM_REGION_PT, + MEM_REGION_TEST_DATA, + NR_MEM_REGIONS, +}; + +struct kvm_vm { + int mode; + unsigned long type; + int kvm_fd; + int fd; + unsigned int pgtable_levels; + unsigned int page_size; + unsigned int page_shift; + unsigned int pa_bits; + unsigned int va_bits; + uint64_t max_gfn; + struct list_head vcpus; + struct userspace_mem_regions regions; + struct sparsebit *vpages_valid; + struct sparsebit *vpages_mapped; + bool has_irqchip; + bool pgd_created; + vm_paddr_t ucall_mmio_addr; + vm_paddr_t pgd; + vm_vaddr_t handlers; + uint32_t dirty_ring_size; + uint64_t gpa_tag_mask; + + struct kvm_vm_arch arch; + + /* Cache of information for binary stats interface */ + int stats_fd; + struct kvm_stats_header stats_header; + struct kvm_stats_desc *stats_desc; + + /* + * KVM region slots. These are the default memslots used by page + * allocators, e.g., lib/elf uses the memslots[MEM_REGION_CODE] + * memslot. + */ + uint32_t memslots[NR_MEM_REGIONS]; +}; + +struct vcpu_reg_sublist { + const char *name; + long capability; + int feature; + int feature_type; + bool finalize; + __u64 *regs; + __u64 regs_n; + __u64 *rejects_set; + __u64 rejects_set_n; + __u64 *skips_set; + __u64 skips_set_n; +}; + +struct vcpu_reg_list { + char *name; + struct vcpu_reg_sublist sublists[]; +}; + +#define for_each_sublist(c, s) \ + for ((s) = &(c)->sublists[0]; (s)->regs; ++(s)) + +#define kvm_for_each_vcpu(vm, i, vcpu) \ + for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++) \ + if (!((vcpu) = vm->vcpus[i])) \ + continue; \ + else + +struct userspace_mem_region * +memslot2region(struct kvm_vm *vm, uint32_t memslot); + +static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm, + enum kvm_mem_region_type type) +{ + assert(type < NR_MEM_REGIONS); + return memslot2region(vm, vm->memslots[type]); +} + +/* Minimum allocated guest virtual and physical addresses */ +#define KVM_UTIL_MIN_VADDR 0x2000 +#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 + +#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 +#define DEFAULT_STACK_PGS 5 + +enum vm_guest_mode { + VM_MODE_P52V48_4K, + VM_MODE_P52V48_16K, + VM_MODE_P52V48_64K, + VM_MODE_P48V48_4K, + VM_MODE_P48V48_16K, + VM_MODE_P48V48_64K, + VM_MODE_P40V48_4K, + VM_MODE_P40V48_16K, + VM_MODE_P40V48_64K, + VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, + VM_MODE_P44V64_4K, + VM_MODE_P36V48_4K, + VM_MODE_P36V48_16K, + VM_MODE_P36V48_64K, + VM_MODE_P36V47_16K, + NUM_VM_MODES, +}; + +struct vm_shape { + uint32_t type; + uint8_t mode; + uint8_t pad0; + uint16_t pad1; +}; + +kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); + +#define VM_TYPE_DEFAULT 0 + +#define VM_SHAPE(__mode) \ +({ \ + struct vm_shape shape = { \ + .mode = (__mode), \ + .type = VM_TYPE_DEFAULT \ + }; \ + \ + shape; \ +}) + +#if defined(__aarch64__) + +extern enum vm_guest_mode vm_mode_default; + +#define VM_MODE_DEFAULT vm_mode_default +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__x86_64__) + +#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__s390x__) + +#define VM_MODE_DEFAULT VM_MODE_P44V64_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 16) + +#elif defined(__riscv) + +#if __riscv_xlen == 32 +#error "RISC-V 32-bit kvm selftests not supported" +#endif + +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#endif + +#define VM_SHAPE_DEFAULT VM_SHAPE(VM_MODE_DEFAULT) + +#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) +#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) + +struct vm_guest_mode_params { + unsigned int pa_bits; + unsigned int va_bits; + unsigned int page_size; + unsigned int page_shift; +}; +extern const struct vm_guest_mode_params vm_guest_mode_params[]; + +int open_path_or_exit(const char *path, int flags); +int open_kvm_dev_path_or_exit(void); + +bool get_kvm_param_bool(const char *param); +bool get_kvm_intel_param_bool(const char *param); +bool get_kvm_amd_param_bool(const char *param); + +int get_kvm_param_integer(const char *param); +int get_kvm_intel_param_integer(const char *param); +int get_kvm_amd_param_integer(const char *param); + +unsigned int kvm_check_cap(long cap); + +static inline bool kvm_has_cap(long cap) +{ + return kvm_check_cap(cap); +} + +#define __KVM_SYSCALL_ERROR(_name, _ret) \ + "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) + +/* + * Use the "inner", double-underscore macro when reporting errors from within + * other macros so that the name of ioctl() and not its literal numeric value + * is printed on error. The "outer" macro is strongly preferred when reporting + * errors "directly", i.e. without an additional layer of macros, as it reduces + * the probability of passing in the wrong string. + */ +#define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret) +#define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret) + +#define kvm_do_ioctl(fd, cmd, arg) \ +({ \ + kvm_static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd)); \ + ioctl(fd, cmd, arg); \ +}) + +#define __kvm_ioctl(kvm_fd, cmd, arg) \ + kvm_do_ioctl(kvm_fd, cmd, arg) + +#define kvm_ioctl(kvm_fd, cmd, arg) \ +({ \ + int ret = __kvm_ioctl(kvm_fd, cmd, arg); \ + \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \ +}) + +static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } + +#define __vm_ioctl(vm, cmd, arg) \ +({ \ + static_assert_is_vm(vm); \ + kvm_do_ioctl((vm)->fd, cmd, arg); \ +}) + +/* + * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if + * the ioctl() failed because KVM killed/bugged the VM. To detect a dead VM, + * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before + * selftests existed and (b) should never outright fail, i.e. is supposed to + * return 0 or 1. If KVM kills a VM, KVM returns -EIO for all ioctl()s for the + * VM and its vCPUs, including KVM_CHECK_EXTENSION. + */ +#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm) \ +do { \ + int __errno = errno; \ + \ + static_assert_is_vm(vm); \ + \ + if (cond) \ + break; \ + \ + if (errno == EIO && \ + __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) { \ + TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO"); \ + TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues"); \ + } \ + errno = __errno; \ + TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret)); \ +} while (0) + +#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm) \ + __TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm) + +#define vm_ioctl(vm, cmd, arg) \ +({ \ + int ret = __vm_ioctl(vm, cmd, arg); \ + \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \ +}) + +static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } + +#define __vcpu_ioctl(vcpu, cmd, arg) \ +({ \ + static_assert_is_vcpu(vcpu); \ + kvm_do_ioctl((vcpu)->fd, cmd, arg); \ +}) + +#define vcpu_ioctl(vcpu, cmd, arg) \ +({ \ + int ret = __vcpu_ioctl(vcpu, cmd, arg); \ + \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \ +}) + +/* + * Looks up and returns the value corresponding to the capability + * (KVM_CAP_*) given by cap. + */ +static inline int vm_check_cap(struct kvm_vm *vm, long cap) +{ + int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap); + + TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm); + return ret; +} + +static inline int __vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + return __vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); +} +static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); +} + +static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, + uint64_t size, uint64_t attributes) +{ + struct kvm_memory_attributes attr = { + .attributes = attributes, + .address = gpa, + .size = size, + .flags = 0, + }; + + /* + * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows + * need significant enhancements to support multiple attributes. + */ + TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE, + "Update me to support multiple attributes!"); + + vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr); +} + + +static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); +} + +static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, 0); +} + +void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size, + bool punch_hole); + +static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, true); +} + +static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, false); +} + +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); +const char *vm_guest_mode_string(uint32_t i); + +void kvm_vm_free(struct kvm_vm *vmp); +void kvm_vm_restart(struct kvm_vm *vmp); +void kvm_vm_release(struct kvm_vm *vmp); +int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, + size_t len); +void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); +int kvm_memfd_alloc(size_t size, bool hugepages); + +void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) +{ + struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot }; + + vm_ioctl(vm, KVM_GET_DIRTY_LOG, &args); +} + +static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, + uint64_t first_page, uint32_t num_pages) +{ + struct kvm_clear_dirty_log args = { + .dirty_bitmap = log, + .slot = slot, + .first_page = first_page, + .num_pages = num_pages + }; + + vm_ioctl(vm, KVM_CLEAR_DIRTY_LOG, &args); +} + +static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +{ + return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); +} + +static inline int vm_get_stats_fd(struct kvm_vm *vm) +{ + int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); + + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm); + return fd; +} + +static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header) +{ + ssize_t ret; + + ret = pread(stats_fd, header, sizeof(*header), 0); + TEST_ASSERT(ret == sizeof(*header), + "Failed to read '%lu' header bytes, ret = '%ld'", + sizeof(*header), ret); +} + +struct kvm_stats_desc *read_stats_descriptors(int stats_fd, + struct kvm_stats_header *header); + +static inline ssize_t get_stats_descriptor_size(struct kvm_stats_header *header) +{ + /* + * The base size of the descriptor is defined by KVM's ABI, but the + * size of the name field is variable, as far as KVM's ABI is + * concerned. For a given instance of KVM, the name field is the same + * size for all stats and is provided in the overall stats header. + */ + return sizeof(struct kvm_stats_desc) + header->name_size; +} + +static inline struct kvm_stats_desc *get_stats_descriptor(struct kvm_stats_desc *stats, + int index, + struct kvm_stats_header *header) +{ + /* + * Note, size_desc includes the size of the name field, which is + * variable. i.e. this is NOT equivalent to &stats_desc[i]. + */ + return (void *)stats + index * get_stats_descriptor_size(header); +} + +void read_stat_data(int stats_fd, struct kvm_stats_header *header, + struct kvm_stats_desc *desc, uint64_t *data, + size_t max_elements); + +void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data, + size_t max_elements); + +static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) +{ + uint64_t data; + + __vm_get_stat(vm, stat_name, &data, 1); + return data; +} + +void vm_create_irqchip(struct kvm_vm *vm); + +static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + struct kvm_create_guest_memfd guest_memfd = { + .size = size, + .flags = flags, + }; + + return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd); +} + +static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + int fd = __vm_create_guest_memfd(vm, size, flags); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd)); + return fd; +} + +void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); +int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); +void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); +int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); + +void vm_userspace_mem_region_add(struct kvm_vm *vm, + enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags); +void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset); + +#ifndef vm_arch_has_protected_memory +static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) +{ + return false; +} +#endif + +void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); +void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); +void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +void vm_populate_vaddr_bitmap(struct kvm_vm *vm); +vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); +vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); +vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); +vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, + enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); + +void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + unsigned int npages); +void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); +void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); +vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); + +#ifndef vcpu_arch_put_guest +#define vcpu_arch_put_guest(mem, val) do { (mem) = (val); } while (0) +#endif + +static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) +{ + return gpa & ~vm->gpa_tag_mask; +} + +void vcpu_run(struct kvm_vcpu *vcpu); +int _vcpu_run(struct kvm_vcpu *vcpu); + +static inline int __vcpu_run(struct kvm_vcpu *vcpu) +{ + return __vcpu_ioctl(vcpu, KVM_RUN, NULL); +} + +void vcpu_run_complete_io(struct kvm_vcpu *vcpu); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu); + +static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, uint32_t cap, + uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + vcpu_ioctl(vcpu, KVM_ENABLE_CAP, &enable_cap); +} + +static inline void vcpu_guest_debug_set(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *debug) +{ + vcpu_ioctl(vcpu, KVM_SET_GUEST_DEBUG, debug); +} + +static inline void vcpu_mp_state_get(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_ioctl(vcpu, KVM_GET_MP_STATE, mp_state); +} +static inline void vcpu_mp_state_set(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_ioctl(vcpu, KVM_SET_MP_STATE, mp_state); +} + +static inline void vcpu_regs_get(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_ioctl(vcpu, KVM_GET_REGS, regs); +} + +static inline void vcpu_regs_set(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_ioctl(vcpu, KVM_SET_REGS, regs); +} +static inline void vcpu_sregs_get(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + vcpu_ioctl(vcpu, KVM_GET_SREGS, sregs); + +} +static inline void vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); +} +static inline int _vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + return __vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); +} +static inline void vcpu_fpu_get(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_ioctl(vcpu, KVM_GET_FPU, fpu); +} +static inline void vcpu_fpu_set(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_ioctl(vcpu, KVM_SET_FPU, fpu); +} + +static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + + return __vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); +} +static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); +} +static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) +{ + uint64_t val; + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); + return val; +} +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); +} + +#ifdef __KVM_HAVE_VCPU_EVENTS +static inline void vcpu_events_get(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_ioctl(vcpu, KVM_GET_VCPU_EVENTS, events); +} +static inline void vcpu_events_set(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_ioctl(vcpu, KVM_SET_VCPU_EVENTS, events); +} +#endif +#ifdef __x86_64__ +static inline void vcpu_nested_state_get(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + vcpu_ioctl(vcpu, KVM_GET_NESTED_STATE, state); +} +static inline int __vcpu_nested_state_set(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + return __vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); +} + +static inline void vcpu_nested_state_set(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); +} +#endif +static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) +{ + int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL); + + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm); + return fd; +} + +int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr); + +static inline void kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) +{ + int ret = __kvm_has_device_attr(dev_fd, group, attr); + + TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); +} + +int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val); + +static inline void kvm_device_attr_get(int dev_fd, uint32_t group, + uint64_t attr, void *val) +{ + int ret = __kvm_device_attr_get(dev_fd, group, attr, val); + + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_GET_DEVICE_ATTR, ret)); +} + +int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val); + +static inline void kvm_device_attr_set(int dev_fd, uint32_t group, + uint64_t attr, void *val) +{ + int ret = __kvm_device_attr_set(dev_fd, group, attr, val); + + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); +} + +static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr) +{ + return __kvm_has_device_attr(vcpu->fd, group, attr); +} + +static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr) +{ + kvm_has_device_attr(vcpu->fd, group, attr); +} + +static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + return __kvm_device_attr_get(vcpu->fd, group, attr, val); +} + +static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + kvm_device_attr_get(vcpu->fd, group, attr, val); +} + +static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + return __kvm_device_attr_set(vcpu->fd, group, attr, val); +} + +static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + kvm_device_attr_set(vcpu->fd, group, attr, val); +} + +int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type); +int __kvm_create_device(struct kvm_vm *vm, uint64_t type); + +static inline int kvm_create_device(struct kvm_vm *vm, uint64_t type) +{ + int fd = __kvm_create_device(vm, type); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_DEVICE, fd)); + return fd; +} + +void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); + +/* + * VM VCPU Args Set + * + * Input Args: + * vm - Virtual Machine + * num - number of arguments + * ... - arguments, each of type uint64_t + * + * Output Args: None + * + * Return: None + * + * Sets the first @num input parameters for the function at @vcpu's entry point, + * per the C calling convention of the architecture, to the values given as + * variable args. Each of the variable args is expected to be of type uint64_t. + * The maximum @num can be is specific to the architecture. + */ +void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...); + +void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); +int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); + +#define KVM_MAX_IRQ_ROUTES 4096 + +struct kvm_irq_routing *kvm_gsi_routing_create(void); +void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, + uint32_t gsi, uint32_t pin); +int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); +void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); + +const char *exit_reason_str(unsigned int exit_reason); + +vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, + uint32_t memslot); +vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot, + bool protected); +vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); + +static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot) +{ + /* + * By default, allocate memory as protected for VMs that support + * protected memory, as the majority of memory for such VMs is + * protected, i.e. using shared memory is effectively opt-in. + */ + return __vm_phy_pages_alloc(vm, num, paddr_min, memslot, + vm_arch_has_protected_memory(vm)); +} + +/* + * ____vm_create() does KVM_CREATE_VM and little else. __vm_create() also + * loads the test binary into guest memory and creates an IRQ chip (x86 only). + * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to + * calculate the amount of memory needed for per-vCPU data, e.g. stacks. + */ +struct kvm_vm *____vm_create(struct vm_shape shape); +struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, + uint64_t nr_extra_pages); + +static inline struct kvm_vm *vm_create_barebones(void) +{ + return ____vm_create(VM_SHAPE_DEFAULT); +} + +static inline struct kvm_vm *vm_create_barebones_type(unsigned long type) +{ + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = type, + }; + + return ____vm_create(shape); +} + +static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) +{ + return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0); +} + +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, + uint64_t extra_mem_pages, + void *guest_code, struct kvm_vcpu *vcpus[]); + +static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, + void *guest_code, + struct kvm_vcpu *vcpus[]) +{ + return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0, + guest_code, vcpus); +} + + +struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code); + +/* + * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages + * additional pages of guest memory. Returns the VM and vCPU (via out param). + */ +static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu, + extra_mem_pages, guest_code); +} + +static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + void *guest_code) +{ + return __vm_create_with_one_vcpu(vcpu, 0, guest_code); +} + +static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code); +} + +struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); + +void kvm_pin_this_task_to_pcpu(uint32_t pcpu); +void kvm_print_vcpu_pinning_help(void); +void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], + int nr_vcpus); + +unsigned long vm_compute_max_gfn(struct kvm_vm *vm); +unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); +unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); +unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages); +static inline unsigned int +vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) +{ + unsigned int n; + n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); +#ifdef __s390x__ + /* s390 requires 1M aligned guest sizes */ + n = (n + 255) & ~255; +#endif + return n; +} + +#define sync_global_to_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(_p, &(g), sizeof(g)); \ +}) + +#define sync_global_from_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(&(g), _p, sizeof(g)); \ +}) + +/* + * Write a global value, but only in the VM's (guest's) domain. Primarily used + * for "globals" that hold per-VM values (VMs always duplicate code and global + * data into their own region of physical memory), but can be used anytime it's + * undesirable to change the host's copy of the global. + */ +#define write_guest_global(vm, g, val) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) _val = val; \ + \ + memcpy(_p, &(_val), sizeof(g)); \ +}) + +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu); + +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, + uint8_t indent); + +static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, + uint8_t indent) +{ + vcpu_arch_dump(stream, vcpu, indent); +} + +/* + * Adds a vCPU with reasonable defaults (e.g. a stack) + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - The id of the VCPU to add to the VM. + */ +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code); + +static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code) +{ + struct kvm_vcpu *vcpu = vm_arch_vcpu_add(vm, vcpu_id); + + vcpu_arch_set_entry_point(vcpu, guest_code); + + return vcpu; +} + +/* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */ +struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id); + +static inline struct kvm_vcpu *vm_vcpu_recreate(struct kvm_vm *vm, + uint32_t vcpu_id) +{ + return vm_arch_vcpu_recreate(vm, vcpu_id); +} + +void vcpu_arch_free(struct kvm_vcpu *vcpu); + +void virt_arch_pgd_alloc(struct kvm_vm *vm); + +static inline void virt_pgd_alloc(struct kvm_vm *vm) +{ + virt_arch_pgd_alloc(vm); +} + +/* + * VM Virtual Page Map + * + * Input Args: + * vm - Virtual Machine + * vaddr - VM Virtual Address + * paddr - VM Physical Address + * memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within @vm, creates a virtual translation for the page starting + * at @vaddr to the page starting at @paddr. + */ +void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); + +static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + virt_arch_pg_map(vm, vaddr, paddr); +} + + +/* + * Address Guest Virtual to Guest Physical + * + * Input Args: + * vm - Virtual Machine + * gva - VM virtual address + * + * Output Args: None + * + * Return: + * Equivalent VM physical address + * + * Returns the VM physical address of the translated VM virtual + * address given by @gva. + */ +vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); + +static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + return addr_arch_gva2gpa(vm, gva); +} + +/* + * Virtual Translation Tables Dump + * + * Input Args: + * stream - Output FILE stream + * vm - Virtual Machine + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps to the FILE stream given by @stream, the contents of all the + * virtual translation tables for the VM given by @vm. + */ +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +static inline void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + virt_arch_dump(stream, vm, indent); +} + + +static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) +{ + return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0); +} + +/* + * Arch hook that is invoked via a constructor, i.e. before exeucting main(), + * to allow for arch-specific setup that is common to all tests, e.g. computing + * the default guest "mode". + */ +void kvm_selftest_arch_init(void); + +void kvm_arch_vm_post_create(struct kvm_vm *vm); + +bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); + +uint32_t guest_get_vcpuid(void); #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h deleted file mode 100644 index 71d992ada45ccdffaf49dd444382d3b666e19d2b..0000000000000000000000000000000000000000 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ /dev/null @@ -1,1127 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * tools/testing/selftests/kvm/include/kvm_util_base.h - * - * Copyright (C) 2018, Google LLC. - */ -#ifndef SELFTEST_KVM_UTIL_BASE_H -#define SELFTEST_KVM_UTIL_BASE_H - -#include "test_util.h" - -#include -#include "linux/hashtable.h" -#include "linux/list.h" -#include -#include -#include "linux/rbtree.h" -#include - -#include -#include - -#include - -#include "kvm_util_arch.h" -#include "sparsebit.h" - -/* - * Provide a version of static_assert() that is guaranteed to have an optional - * message param. If _ISOC11_SOURCE is defined, glibc (/usr/include/assert.h) - * #undefs and #defines static_assert() as a direct alias to _Static_assert(), - * i.e. effectively makes the message mandatory. Many KVM selftests #define - * _GNU_SOURCE for various reasons, and _GNU_SOURCE implies _ISOC11_SOURCE. As - * a result, static_assert() behavior is non-deterministic and may or may not - * require a message depending on #include order. - */ -#define __kvm_static_assert(expr, msg, ...) _Static_assert(expr, msg) -#define kvm_static_assert(expr, ...) __kvm_static_assert(expr, ##__VA_ARGS__, #expr) - -#define KVM_DEV_PATH "/dev/kvm" -#define KVM_MAX_VCPUS 1024 - -#define NSEC_PER_SEC 1000000000L - -typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ -typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ - -struct userspace_mem_region { - struct kvm_userspace_memory_region2 region; - struct sparsebit *unused_phy_pages; - struct sparsebit *protected_phy_pages; - int fd; - off_t offset; - enum vm_mem_backing_src_type backing_src_type; - void *host_mem; - void *host_alias; - void *mmap_start; - void *mmap_alias; - size_t mmap_size; - struct rb_node gpa_node; - struct rb_node hva_node; - struct hlist_node slot_node; -}; - -struct kvm_vcpu { - struct list_head list; - uint32_t id; - int fd; - struct kvm_vm *vm; - struct kvm_run *run; -#ifdef __x86_64__ - struct kvm_cpuid2 *cpuid; -#endif - struct kvm_dirty_gfn *dirty_gfns; - uint32_t fetch_index; - uint32_t dirty_gfns_count; -}; - -struct userspace_mem_regions { - struct rb_root gpa_tree; - struct rb_root hva_tree; - DECLARE_HASHTABLE(slot_hash, 9); -}; - -enum kvm_mem_region_type { - MEM_REGION_CODE, - MEM_REGION_DATA, - MEM_REGION_PT, - MEM_REGION_TEST_DATA, - NR_MEM_REGIONS, -}; - -struct kvm_vm { - int mode; - unsigned long type; - int kvm_fd; - int fd; - unsigned int pgtable_levels; - unsigned int page_size; - unsigned int page_shift; - unsigned int pa_bits; - unsigned int va_bits; - uint64_t max_gfn; - struct list_head vcpus; - struct userspace_mem_regions regions; - struct sparsebit *vpages_valid; - struct sparsebit *vpages_mapped; - bool has_irqchip; - bool pgd_created; - vm_paddr_t ucall_mmio_addr; - vm_paddr_t pgd; - vm_vaddr_t gdt; - vm_vaddr_t tss; - vm_vaddr_t idt; - vm_vaddr_t handlers; - uint32_t dirty_ring_size; - uint64_t gpa_tag_mask; - - struct kvm_vm_arch arch; - - /* Cache of information for binary stats interface */ - int stats_fd; - struct kvm_stats_header stats_header; - struct kvm_stats_desc *stats_desc; - - /* - * KVM region slots. These are the default memslots used by page - * allocators, e.g., lib/elf uses the memslots[MEM_REGION_CODE] - * memslot. - */ - uint32_t memslots[NR_MEM_REGIONS]; -}; - -struct vcpu_reg_sublist { - const char *name; - long capability; - int feature; - int feature_type; - bool finalize; - __u64 *regs; - __u64 regs_n; - __u64 *rejects_set; - __u64 rejects_set_n; - __u64 *skips_set; - __u64 skips_set_n; -}; - -struct vcpu_reg_list { - char *name; - struct vcpu_reg_sublist sublists[]; -}; - -#define for_each_sublist(c, s) \ - for ((s) = &(c)->sublists[0]; (s)->regs; ++(s)) - -#define kvm_for_each_vcpu(vm, i, vcpu) \ - for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++) \ - if (!((vcpu) = vm->vcpus[i])) \ - continue; \ - else - -struct userspace_mem_region * -memslot2region(struct kvm_vm *vm, uint32_t memslot); - -static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm, - enum kvm_mem_region_type type) -{ - assert(type < NR_MEM_REGIONS); - return memslot2region(vm, vm->memslots[type]); -} - -/* Minimum allocated guest virtual and physical addresses */ -#define KVM_UTIL_MIN_VADDR 0x2000 -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - -#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 -#define DEFAULT_STACK_PGS 5 - -enum vm_guest_mode { - VM_MODE_P52V48_4K, - VM_MODE_P52V48_16K, - VM_MODE_P52V48_64K, - VM_MODE_P48V48_4K, - VM_MODE_P48V48_16K, - VM_MODE_P48V48_64K, - VM_MODE_P40V48_4K, - VM_MODE_P40V48_16K, - VM_MODE_P40V48_64K, - VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ - VM_MODE_P47V64_4K, - VM_MODE_P44V64_4K, - VM_MODE_P36V48_4K, - VM_MODE_P36V48_16K, - VM_MODE_P36V48_64K, - VM_MODE_P36V47_16K, - NUM_VM_MODES, -}; - -struct vm_shape { - uint32_t type; - uint8_t mode; - uint8_t pad0; - uint16_t pad1; -}; - -kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); - -#define VM_TYPE_DEFAULT 0 - -#define VM_SHAPE(__mode) \ -({ \ - struct vm_shape shape = { \ - .mode = (__mode), \ - .type = VM_TYPE_DEFAULT \ - }; \ - \ - shape; \ -}) - -#if defined(__aarch64__) - -extern enum vm_guest_mode vm_mode_default; - -#define VM_MODE_DEFAULT vm_mode_default -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 8) - -#elif defined(__x86_64__) - -#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 8) - -#elif defined(__s390x__) - -#define VM_MODE_DEFAULT VM_MODE_P44V64_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 16) - -#elif defined(__riscv) - -#if __riscv_xlen == 32 -#error "RISC-V 32-bit kvm selftests not supported" -#endif - -#define VM_MODE_DEFAULT VM_MODE_P40V48_4K -#define MIN_PAGE_SHIFT 12U -#define ptes_per_page(page_size) ((page_size) / 8) - -#endif - -#define VM_SHAPE_DEFAULT VM_SHAPE(VM_MODE_DEFAULT) - -#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) -#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) - -struct vm_guest_mode_params { - unsigned int pa_bits; - unsigned int va_bits; - unsigned int page_size; - unsigned int page_shift; -}; -extern const struct vm_guest_mode_params vm_guest_mode_params[]; - -int open_path_or_exit(const char *path, int flags); -int open_kvm_dev_path_or_exit(void); - -bool get_kvm_param_bool(const char *param); -bool get_kvm_intel_param_bool(const char *param); -bool get_kvm_amd_param_bool(const char *param); - -unsigned int kvm_check_cap(long cap); - -static inline bool kvm_has_cap(long cap) -{ - return kvm_check_cap(cap); -} - -#define __KVM_SYSCALL_ERROR(_name, _ret) \ - "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) - -/* - * Use the "inner", double-underscore macro when reporting errors from within - * other macros so that the name of ioctl() and not its literal numeric value - * is printed on error. The "outer" macro is strongly preferred when reporting - * errors "directly", i.e. without an additional layer of macros, as it reduces - * the probability of passing in the wrong string. - */ -#define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret) -#define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret) - -#define kvm_do_ioctl(fd, cmd, arg) \ -({ \ - kvm_static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd)); \ - ioctl(fd, cmd, arg); \ -}) - -#define __kvm_ioctl(kvm_fd, cmd, arg) \ - kvm_do_ioctl(kvm_fd, cmd, arg) - -#define kvm_ioctl(kvm_fd, cmd, arg) \ -({ \ - int ret = __kvm_ioctl(kvm_fd, cmd, arg); \ - \ - TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \ -}) - -static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } - -#define __vm_ioctl(vm, cmd, arg) \ -({ \ - static_assert_is_vm(vm); \ - kvm_do_ioctl((vm)->fd, cmd, arg); \ -}) - -/* - * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if - * the ioctl() failed because KVM killed/bugged the VM. To detect a dead VM, - * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before - * selftests existed and (b) should never outright fail, i.e. is supposed to - * return 0 or 1. If KVM kills a VM, KVM returns -EIO for all ioctl()s for the - * VM and its vCPUs, including KVM_CHECK_EXTENSION. - */ -#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm) \ -do { \ - int __errno = errno; \ - \ - static_assert_is_vm(vm); \ - \ - if (cond) \ - break; \ - \ - if (errno == EIO && \ - __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) { \ - TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO"); \ - TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues"); \ - } \ - errno = __errno; \ - TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret)); \ -} while (0) - -#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm) \ - __TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm) - -#define vm_ioctl(vm, cmd, arg) \ -({ \ - int ret = __vm_ioctl(vm, cmd, arg); \ - \ - __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \ -}) - -static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } - -#define __vcpu_ioctl(vcpu, cmd, arg) \ -({ \ - static_assert_is_vcpu(vcpu); \ - kvm_do_ioctl((vcpu)->fd, cmd, arg); \ -}) - -#define vcpu_ioctl(vcpu, cmd, arg) \ -({ \ - int ret = __vcpu_ioctl(vcpu, cmd, arg); \ - \ - __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \ -}) - -/* - * Looks up and returns the value corresponding to the capability - * (KVM_CAP_*) given by cap. - */ -static inline int vm_check_cap(struct kvm_vm *vm, long cap) -{ - int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap); - - TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm); - return ret; -} - -static inline int __vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) -{ - struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; - - return __vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); -} -static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) -{ - struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; - - vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); -} - -static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, - uint64_t size, uint64_t attributes) -{ - struct kvm_memory_attributes attr = { - .attributes = attributes, - .address = gpa, - .size = size, - .flags = 0, - }; - - /* - * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows - * need significant enhancements to support multiple attributes. - */ - TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE, - "Update me to support multiple attributes!"); - - vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr); -} - - -static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) -{ - vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); -} - -static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) -{ - vm_set_memory_attributes(vm, gpa, size, 0); -} - -void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size, - bool punch_hole); - -static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) -{ - vm_guest_mem_fallocate(vm, gpa, size, true); -} - -static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa, - uint64_t size) -{ - vm_guest_mem_fallocate(vm, gpa, size, false); -} - -void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); -const char *vm_guest_mode_string(uint32_t i); - -void kvm_vm_free(struct kvm_vm *vmp); -void kvm_vm_restart(struct kvm_vm *vmp); -void kvm_vm_release(struct kvm_vm *vmp); -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, - size_t len); -void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); -int kvm_memfd_alloc(size_t size, bool hugepages); - -void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); - -static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) -{ - struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot }; - - vm_ioctl(vm, KVM_GET_DIRTY_LOG, &args); -} - -static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, - uint64_t first_page, uint32_t num_pages) -{ - struct kvm_clear_dirty_log args = { - .dirty_bitmap = log, - .slot = slot, - .first_page = first_page, - .num_pages = num_pages - }; - - vm_ioctl(vm, KVM_CLEAR_DIRTY_LOG, &args); -} - -static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) -{ - return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); -} - -static inline int vm_get_stats_fd(struct kvm_vm *vm) -{ - int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); - - TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm); - return fd; -} - -static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header) -{ - ssize_t ret; - - ret = pread(stats_fd, header, sizeof(*header), 0); - TEST_ASSERT(ret == sizeof(*header), - "Failed to read '%lu' header bytes, ret = '%ld'", - sizeof(*header), ret); -} - -struct kvm_stats_desc *read_stats_descriptors(int stats_fd, - struct kvm_stats_header *header); - -static inline ssize_t get_stats_descriptor_size(struct kvm_stats_header *header) -{ - /* - * The base size of the descriptor is defined by KVM's ABI, but the - * size of the name field is variable, as far as KVM's ABI is - * concerned. For a given instance of KVM, the name field is the same - * size for all stats and is provided in the overall stats header. - */ - return sizeof(struct kvm_stats_desc) + header->name_size; -} - -static inline struct kvm_stats_desc *get_stats_descriptor(struct kvm_stats_desc *stats, - int index, - struct kvm_stats_header *header) -{ - /* - * Note, size_desc includes the size of the name field, which is - * variable. i.e. this is NOT equivalent to &stats_desc[i]. - */ - return (void *)stats + index * get_stats_descriptor_size(header); -} - -void read_stat_data(int stats_fd, struct kvm_stats_header *header, - struct kvm_stats_desc *desc, uint64_t *data, - size_t max_elements); - -void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data, - size_t max_elements); - -static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) -{ - uint64_t data; - - __vm_get_stat(vm, stat_name, &data, 1); - return data; -} - -void vm_create_irqchip(struct kvm_vm *vm); - -static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, - uint64_t flags) -{ - struct kvm_create_guest_memfd guest_memfd = { - .size = size, - .flags = flags, - }; - - return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd); -} - -static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, - uint64_t flags) -{ - int fd = __vm_create_guest_memfd(vm, size, flags); - - TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd)); - return fd; -} - -void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva); -int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva); -void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset); -int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, - uint64_t gpa, uint64_t size, void *hva, - uint32_t guest_memfd, uint64_t guest_memfd_offset); - -void vm_userspace_mem_region_add(struct kvm_vm *vm, - enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags); -void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset); - -#ifndef vm_arch_has_protected_memory -static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) -{ - return false; -} -#endif - -void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); -void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); -void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); -struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); -void vm_populate_vaddr_bitmap(struct kvm_vm *vm); -vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); -vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); -vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); -vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, - enum kvm_mem_region_type type); -vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); - -void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, - unsigned int npages); -void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); -void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); -vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); -void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); - - -static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) -{ - return gpa & ~vm->gpa_tag_mask; -} - -void vcpu_run(struct kvm_vcpu *vcpu); -int _vcpu_run(struct kvm_vcpu *vcpu); - -static inline int __vcpu_run(struct kvm_vcpu *vcpu) -{ - return __vcpu_ioctl(vcpu, KVM_RUN, NULL); -} - -void vcpu_run_complete_io(struct kvm_vcpu *vcpu); -struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu); - -static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, uint32_t cap, - uint64_t arg0) -{ - struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; - - vcpu_ioctl(vcpu, KVM_ENABLE_CAP, &enable_cap); -} - -static inline void vcpu_guest_debug_set(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *debug) -{ - vcpu_ioctl(vcpu, KVM_SET_GUEST_DEBUG, debug); -} - -static inline void vcpu_mp_state_get(struct kvm_vcpu *vcpu, - struct kvm_mp_state *mp_state) -{ - vcpu_ioctl(vcpu, KVM_GET_MP_STATE, mp_state); -} -static inline void vcpu_mp_state_set(struct kvm_vcpu *vcpu, - struct kvm_mp_state *mp_state) -{ - vcpu_ioctl(vcpu, KVM_SET_MP_STATE, mp_state); -} - -static inline void vcpu_regs_get(struct kvm_vcpu *vcpu, struct kvm_regs *regs) -{ - vcpu_ioctl(vcpu, KVM_GET_REGS, regs); -} - -static inline void vcpu_regs_set(struct kvm_vcpu *vcpu, struct kvm_regs *regs) -{ - vcpu_ioctl(vcpu, KVM_SET_REGS, regs); -} -static inline void vcpu_sregs_get(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) -{ - vcpu_ioctl(vcpu, KVM_GET_SREGS, sregs); - -} -static inline void vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) -{ - vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); -} -static inline int _vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) -{ - return __vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); -} -static inline void vcpu_fpu_get(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - vcpu_ioctl(vcpu, KVM_GET_FPU, fpu); -} -static inline void vcpu_fpu_set(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - vcpu_ioctl(vcpu, KVM_SET_FPU, fpu); -} - -static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) -{ - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; - - return __vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); -} -static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) -{ - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; - - return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); -} -static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) -{ - uint64_t val; - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; - - vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); - return val; -} -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) -{ - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; - - vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); -} - -#ifdef __KVM_HAVE_VCPU_EVENTS -static inline void vcpu_events_get(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events) -{ - vcpu_ioctl(vcpu, KVM_GET_VCPU_EVENTS, events); -} -static inline void vcpu_events_set(struct kvm_vcpu *vcpu, - struct kvm_vcpu_events *events) -{ - vcpu_ioctl(vcpu, KVM_SET_VCPU_EVENTS, events); -} -#endif -#ifdef __x86_64__ -static inline void vcpu_nested_state_get(struct kvm_vcpu *vcpu, - struct kvm_nested_state *state) -{ - vcpu_ioctl(vcpu, KVM_GET_NESTED_STATE, state); -} -static inline int __vcpu_nested_state_set(struct kvm_vcpu *vcpu, - struct kvm_nested_state *state) -{ - return __vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); -} - -static inline void vcpu_nested_state_set(struct kvm_vcpu *vcpu, - struct kvm_nested_state *state) -{ - vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); -} -#endif -static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) -{ - int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL); - - TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm); - return fd; -} - -int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr); - -static inline void kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) -{ - int ret = __kvm_has_device_attr(dev_fd, group, attr); - - TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); -} - -int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val); - -static inline void kvm_device_attr_get(int dev_fd, uint32_t group, - uint64_t attr, void *val) -{ - int ret = __kvm_device_attr_get(dev_fd, group, attr, val); - - TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_GET_DEVICE_ATTR, ret)); -} - -int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val); - -static inline void kvm_device_attr_set(int dev_fd, uint32_t group, - uint64_t attr, void *val) -{ - int ret = __kvm_device_attr_set(dev_fd, group, attr, val); - - TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); -} - -static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr) -{ - return __kvm_has_device_attr(vcpu->fd, group, attr); -} - -static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr) -{ - kvm_has_device_attr(vcpu->fd, group, attr); -} - -static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) -{ - return __kvm_device_attr_get(vcpu->fd, group, attr, val); -} - -static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) -{ - kvm_device_attr_get(vcpu->fd, group, attr, val); -} - -static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) -{ - return __kvm_device_attr_set(vcpu->fd, group, attr, val); -} - -static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, - uint64_t attr, void *val) -{ - kvm_device_attr_set(vcpu->fd, group, attr, val); -} - -int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type); -int __kvm_create_device(struct kvm_vm *vm, uint64_t type); - -static inline int kvm_create_device(struct kvm_vm *vm, uint64_t type) -{ - int fd = __kvm_create_device(vm, type); - - TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_DEVICE, fd)); - return fd; -} - -void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); - -/* - * VM VCPU Args Set - * - * Input Args: - * vm - Virtual Machine - * num - number of arguments - * ... - arguments, each of type uint64_t - * - * Output Args: None - * - * Return: None - * - * Sets the first @num input parameters for the function at @vcpu's entry point, - * per the C calling convention of the architecture, to the values given as - * variable args. Each of the variable args is expected to be of type uint64_t. - * The maximum @num can be is specific to the architecture. - */ -void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...); - -void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); -int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); - -#define KVM_MAX_IRQ_ROUTES 4096 - -struct kvm_irq_routing *kvm_gsi_routing_create(void); -void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, - uint32_t gsi, uint32_t pin); -int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); -void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); - -const char *exit_reason_str(unsigned int exit_reason); - -vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, - uint32_t memslot); -vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot, - bool protected); -vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); - -static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot) -{ - /* - * By default, allocate memory as protected for VMs that support - * protected memory, as the majority of memory for such VMs is - * protected, i.e. using shared memory is effectively opt-in. - */ - return __vm_phy_pages_alloc(vm, num, paddr_min, memslot, - vm_arch_has_protected_memory(vm)); -} - -/* - * ____vm_create() does KVM_CREATE_VM and little else. __vm_create() also - * loads the test binary into guest memory and creates an IRQ chip (x86 only). - * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to - * calculate the amount of memory needed for per-vCPU data, e.g. stacks. - */ -struct kvm_vm *____vm_create(struct vm_shape shape); -struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, - uint64_t nr_extra_pages); - -static inline struct kvm_vm *vm_create_barebones(void) -{ - return ____vm_create(VM_SHAPE_DEFAULT); -} - -static inline struct kvm_vm *vm_create_barebones_type(unsigned long type) -{ - const struct vm_shape shape = { - .mode = VM_MODE_DEFAULT, - .type = type, - }; - - return ____vm_create(shape); -} - -static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) -{ - return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0); -} - -struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, - uint64_t extra_mem_pages, - void *guest_code, struct kvm_vcpu *vcpus[]); - -static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, - void *guest_code, - struct kvm_vcpu *vcpus[]) -{ - return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0, - guest_code, vcpus); -} - - -struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, - struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, - void *guest_code); - -/* - * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages - * additional pages of guest memory. Returns the VM and vCPU (via out param). - */ -static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, - void *guest_code) -{ - return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu, - extra_mem_pages, guest_code); -} - -static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - void *guest_code) -{ - return __vm_create_with_one_vcpu(vcpu, 0, guest_code); -} - -static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape, - struct kvm_vcpu **vcpu, - void *guest_code) -{ - return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code); -} - -struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); - -void kvm_pin_this_task_to_pcpu(uint32_t pcpu); -void kvm_print_vcpu_pinning_help(void); -void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], - int nr_vcpus); - -unsigned long vm_compute_max_gfn(struct kvm_vm *vm); -unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); -unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); -unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages); -static inline unsigned int -vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) -{ - unsigned int n; - n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); -#ifdef __s390x__ - /* s390 requires 1M aligned guest sizes */ - n = (n + 255) & ~255; -#endif - return n; -} - -#define sync_global_to_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ - memcpy(_p, &(g), sizeof(g)); \ -}) - -#define sync_global_from_guest(vm, g) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ - memcpy(&(g), _p, sizeof(g)); \ -}) - -/* - * Write a global value, but only in the VM's (guest's) domain. Primarily used - * for "globals" that hold per-VM values (VMs always duplicate code and global - * data into their own region of physical memory), but can be used anytime it's - * undesirable to change the host's copy of the global. - */ -#define write_guest_global(vm, g, val) ({ \ - typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ - typeof(g) _val = val; \ - \ - memcpy(_p, &(_val), sizeof(g)); \ -}) - -void assert_on_unhandled_exception(struct kvm_vcpu *vcpu); - -void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, - uint8_t indent); - -static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, - uint8_t indent) -{ - vcpu_arch_dump(stream, vcpu, indent); -} - -/* - * Adds a vCPU with reasonable defaults (e.g. a stack) - * - * Input Args: - * vm - Virtual Machine - * vcpu_id - The id of the VCPU to add to the VM. - * guest_code - The vCPU's entry point - */ -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code); - -static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) -{ - return vm_arch_vcpu_add(vm, vcpu_id, guest_code); -} - -/* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */ -struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id); - -static inline struct kvm_vcpu *vm_vcpu_recreate(struct kvm_vm *vm, - uint32_t vcpu_id) -{ - return vm_arch_vcpu_recreate(vm, vcpu_id); -} - -void vcpu_arch_free(struct kvm_vcpu *vcpu); - -void virt_arch_pgd_alloc(struct kvm_vm *vm); - -static inline void virt_pgd_alloc(struct kvm_vm *vm) -{ - virt_arch_pgd_alloc(vm); -} - -/* - * VM Virtual Page Map - * - * Input Args: - * vm - Virtual Machine - * vaddr - VM Virtual Address - * paddr - VM Physical Address - * memslot - Memory region slot for new virtual translation tables - * - * Output Args: None - * - * Return: None - * - * Within @vm, creates a virtual translation for the page starting - * at @vaddr to the page starting at @paddr. - */ -void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); - -static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) -{ - virt_arch_pg_map(vm, vaddr, paddr); -} - - -/* - * Address Guest Virtual to Guest Physical - * - * Input Args: - * vm - Virtual Machine - * gva - VM virtual address - * - * Output Args: None - * - * Return: - * Equivalent VM physical address - * - * Returns the VM physical address of the translated VM virtual - * address given by @gva. - */ -vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); - -static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) -{ - return addr_arch_gva2gpa(vm, gva); -} - -/* - * Virtual Translation Tables Dump - * - * Input Args: - * stream - Output FILE stream - * vm - Virtual Machine - * indent - Left margin indent amount - * - * Output Args: None - * - * Return: None - * - * Dumps to the FILE stream given by @stream, the contents of all the - * virtual translation tables for the VM given by @vm. - */ -void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); - -static inline void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) -{ - virt_arch_dump(stream, vm, indent); -} - - -static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) -{ - return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0); -} - -/* - * Arch hook that is invoked via a constructor, i.e. before exeucting main(), - * to allow for arch-specific setup that is common to all tests, e.g. computing - * the default guest "mode". - */ -void kvm_selftest_arch_init(void); - -void kvm_arch_vm_post_create(struct kvm_vm *vm); - -uint32_t guest_get_vcpuid(void); -bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); - - -#endif /* SELFTEST_KVM_UTIL_BASE_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_types.h b/tools/testing/selftests/kvm/include/kvm_util_types.h new file mode 100644 index 0000000000000000000000000000000000000000..ec787b97cf184e10ca81664ab7fdfe68731ea513 --- /dev/null +++ b/tools/testing/selftests/kvm/include/kvm_util_types.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_TYPES_H +#define SELFTEST_KVM_UTIL_TYPES_H + +/* + * Provide a version of static_assert() that is guaranteed to have an optional + * message param. _GNU_SOURCE is defined for all KVM selftests, _GNU_SOURCE + * implies _ISOC11_SOURCE, and if _ISOC11_SOURCE is defined, glibc #undefs and + * #defines static_assert() as a direct alias to _Static_assert() (see + * usr/include/assert.h). Define a custom macro instead of redefining + * static_assert() to avoid creating non-deterministic behavior that is + * dependent on include order. + */ +#define __kvm_static_assert(expr, msg, ...) _Static_assert(expr, msg) +#define kvm_static_assert(expr, ...) __kvm_static_assert(expr, ##__VA_ARGS__, #expr) + +typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ +typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ + +#endif /* SELFTEST_KVM_UTIL_TYPES_H */ diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390x/ucall.h index b231bf2e49d620a64c48e11caab8587c4a466c95..8035a872a351bb295e2b584669b0c08f755bfc65 100644 --- a/tools/testing/selftests/kvm/include/s390x/ucall.h +++ b/tools/testing/selftests/kvm/include/s390x/ucall.h @@ -2,7 +2,7 @@ #ifndef SELFTEST_KVM_UCALL_H #define SELFTEST_KVM_UCALL_H -#include "kvm_util_base.h" +#include "kvm_util.h" #define UCALL_EXIT_REASON KVM_EXIT_S390_SIEIC diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h index bed316fdecd5f9ffd63f93028125b5127dfce10c..0f268b55fa0670c19e7646a76899f03ec9b562ab 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -60,6 +60,14 @@ #define APIC_VECTOR_MASK 0x000FF #define APIC_ICR2 0x310 #define SET_APIC_DEST_FIELD(x) ((x) << 24) +#define APIC_LVTT 0x320 +#define APIC_LVT_TIMER_ONESHOT (0 << 17) +#define APIC_LVT_TIMER_PERIODIC (1 << 17) +#define APIC_LVT_TIMER_TSCDEADLINE (2 << 17) +#define APIC_LVT_MASKED (1 << 16) +#define APIC_TMICT 0x380 +#define APIC_TMCCT 0x390 +#define APIC_TDCR 0x3E0 void apic_disable(void); void xapic_enable(void); diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h index 9f1725192aa224be9a5ae12c5141903fb1a76ac5..b5f63c5cee5fec62255c5b844102d8e567f56154 100644 --- a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h @@ -5,7 +5,12 @@ #include #include +#include "kvm_util_types.h" + struct kvm_vm_arch { + vm_vaddr_t gdt; + vm_vaddr_t tss; + vm_vaddr_t idt; uint64_t c_bit; uint64_t s_bit; int sev_fd; diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 51e336e60d4a85b9778bf45c2207276ac66660fe..cbc0211bb6312f3d6974ff96ae8e09303611c409 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -18,12 +18,14 @@ #include #include -#include "../kvm_util.h" +#include "kvm_util.h" +#include "ucall_common.h" extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; extern bool host_cpu_is_hygon; extern bool host_cpu_is_zhaoxin; +extern uint64_t guest_tsc_khz; #define NMI_VECTOR 0x02 @@ -802,6 +804,23 @@ static inline void cpu_relax(void) asm volatile("rep; nop" ::: "memory"); } +static inline void udelay(unsigned long usec) +{ + uint64_t start, now, cycles; + + GUEST_ASSERT(guest_tsc_khz); + cycles = guest_tsc_khz / 1000 * usec; + + /* + * Deliberately don't PAUSE, a.k.a. cpu_relax(), so that the delay is + * as accurate as possible, e.g. doesn't trigger PAUSE-Loop VM-Exits. + */ + start = rdtsc(); + do { + now = rdtsc(); + } while (now - start < cycles); +} + #define ud2() \ __asm__ __volatile__( \ "ud2\n" \ @@ -1102,8 +1121,6 @@ struct idt_entry { uint32_t offset2; uint32_t reserved; }; -void vm_init_descriptor_tables(struct kvm_vm *vm); -void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); void vm_install_exception_handler(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)); diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86_64/ucall.h index 06b244bd06eeb8b34cc50410d3c49718a8353f8b..d3825dcc3cd935e1edf9b9d32680fbd82d937f69 100644 --- a/tools/testing/selftests/kvm/include/x86_64/ucall.h +++ b/tools/testing/selftests/kvm/include/x86_64/ucall.h @@ -2,7 +2,7 @@ #ifndef SELFTEST_KVM_UCALL_H #define SELFTEST_KVM_UCALL_H -#include "kvm_util_base.h" +#include "kvm_util.h" #define UCALL_EXIT_REASON KVM_EXIT_IO diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index e37dc9c21888f4bc4ed06bf3bacff89e28c68b5d..346c8bd5d504f15c091c71fb2cd7037d10c17b27 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -21,6 +21,7 @@ #include "kvm_util.h" #include "processor.h" #include "guest_modes.h" +#include "ucall_common.h" #define TEST_MEM_SLOT_INDEX 1 diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index db9af62ca991a269e101d216f1f220e58e479012..07dd60d1a080ed9c27ca8429ccfcc0f495f765cf 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -11,6 +11,8 @@ #include "guest_modes.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" + #include #include @@ -365,8 +367,13 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) indent, "", pstate, pc); } -struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - struct kvm_vcpu_init *init, void *guest_code) +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); +} + +static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_vcpu_init *init) { size_t stack_size; uint64_t stack_vaddr; @@ -381,15 +388,22 @@ struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, aarch64_vcpu_setup(vcpu, init); vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); - vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); + return vcpu; +} + +struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_vcpu_init *init, void *guest_code) +{ + struct kvm_vcpu *vcpu = __aarch64_vcpu_add(vm, vcpu_id, init); + + vcpu_arch_set_entry_point(vcpu, guest_code); return vcpu; } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { - return aarch64_vcpu_add(vm, vcpu_id, NULL, guest_code); + return __aarch64_vcpu_add(vm, vcpu_id, NULL); } void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 179080b60c69e622214b379b480697ab870ff666..c0f775fd0d3885170a7abf67ca81685235011fc3 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -9,6 +9,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" #include #include diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index d05487e5a371df1d17c96d4fbec1b1f6b2e60c0f..c9a5ce4fbc27d81569743c49c22298eafb9f4067 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -10,6 +10,7 @@ #include "kvm_util.h" #include "memstress.h" #include "processor.h" +#include "ucall_common.h" struct memstress_args memstress_args; diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index 0acc776eb8ddc479e48a9881148fc43bdf64d696..06c7763325dfec232cf71195538d8fcb014c0d10 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -10,6 +10,7 @@ #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" #define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 @@ -289,8 +290,12 @@ static void __aligned(16) guest_unexp_trap(void) 0, 0, 0, 0, 0, 0); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code); +} + +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { int r; size_t stack_size; @@ -324,7 +329,6 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, /* Setup stack pointer and program counter of guest */ vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_vaddr + stack_size); - vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code); /* Setup sscratch for guest_get_vcpuid() */ vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(sscratch), vcpu_id); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index 15945121daf17dc46bf38cf8f2a24d23b8f073f3..cd5301cc9788adc3e636c131b039d0e7e79080aa 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -155,15 +155,18 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump_region(stream, vm, indent, vm->pgd); } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + vcpu->run->psw_addr = (uintptr_t)guest_code; +} + +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); uint64_t stack_vaddr; struct kvm_regs regs; struct kvm_sregs sregs; struct kvm_vcpu *vcpu; - struct kvm_run *run; TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", vm->page_size); @@ -184,9 +187,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, sregs.crs[1] = vm->pgd | 0xf; /* Primary region table */ vcpu_sregs_set(vcpu, &sregs); - run = vcpu->run; - run->psw_mask = 0x0400000180000000ULL; /* DAT enabled + 64 bit mode */ - run->psw_addr = (uintptr_t)guest_code; + vcpu->run->psw_mask = 0x0400000180000000ULL; /* DAT enabled + 64 bit mode */ return vcpu; } diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index f5af65a41c296e77f1502f32a8813fcf77dbdf20..42151e5719536078e45083b27c7397ac1a66f308 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -1,9 +1,12 @@ // SPDX-License-Identifier: GPL-2.0-only -#include "kvm_util.h" #include "linux/types.h" #include "linux/bitmap.h" #include "linux/atomic.h" +#include "kvm_util.h" +#include "ucall_common.h" + + #define GUEST_UCALL_FAILED -1 struct ucall_header { diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 5578bad48c43ed8f55f1d4d08cdf2b5c183a5fca..e13c1ce0bb0e370cc357698a30053d1c7634b6c8 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -15,8 +15,9 @@ #define NUM_INTERRUPTS 256 #endif -#define DEFAULT_CODE_SELECTOR 0x8 -#define DEFAULT_DATA_SELECTOR 0x10 +#define KERNEL_CS 0x8 +#define KERNEL_DS 0x10 +#define KERNEL_TSS 0x18 #define MAX_NR_CPUID_ENTRIES 100 @@ -25,6 +26,7 @@ bool host_cpu_is_amd; bool host_cpu_is_intel; bool host_cpu_is_hygon; bool host_cpu_is_zhaoxin; +uint64_t guest_tsc_khz; static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -419,7 +421,7 @@ static void kvm_seg_set_unusable(struct kvm_segment *segp) static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) { - void *gdt = addr_gva2hva(vm, vm->gdt); + void *gdt = addr_gva2hva(vm, vm->arch.gdt); struct desc64 *desc = gdt + (segp->selector >> 3) * 8; desc->limit0 = segp->limit & 0xFFFF; @@ -439,27 +441,10 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->base3 = segp->base >> 32; } - -/* - * Set Long Mode Flat Kernel Code Segment - * - * Input Args: - * vm - VM whose GDT is being filled, or NULL to only write segp - * selector - selector value - * - * Output Args: - * segp - Pointer to KVM segment - * - * Return: None - * - * Sets up the KVM segment pointed to by @segp, to be a code segment - * with the selector value given by @selector. - */ -static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, - struct kvm_segment *segp) +static void kvm_seg_set_kernel_code_64bit(struct kvm_segment *segp) { memset(segp, 0, sizeof(*segp)); - segp->selector = selector; + segp->selector = KERNEL_CS; segp->limit = 0xFFFFFFFFu; segp->s = 0x1; /* kTypeCodeData */ segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed @@ -468,30 +453,12 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, segp->g = true; segp->l = true; segp->present = 1; - if (vm) - kvm_seg_fill_gdt_64bit(vm, segp); } -/* - * Set Long Mode Flat Kernel Data Segment - * - * Input Args: - * vm - VM whose GDT is being filled, or NULL to only write segp - * selector - selector value - * - * Output Args: - * segp - Pointer to KVM segment - * - * Return: None - * - * Sets up the KVM segment pointed to by @segp, to be a data segment - * with the selector value given by @selector. - */ -static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, - struct kvm_segment *segp) +static void kvm_seg_set_kernel_data_64bit(struct kvm_segment *segp) { memset(segp, 0, sizeof(*segp)); - segp->selector = selector; + segp->selector = KERNEL_DS; segp->limit = 0xFFFFFFFFu; segp->s = 0x1; /* kTypeCodeData */ segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed @@ -499,8 +466,6 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, */ segp->g = true; segp->present = true; - if (vm) - kvm_seg_fill_gdt_64bit(vm, segp); } vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) @@ -518,70 +483,159 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level)); } -static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt) +static void kvm_seg_set_tss_64bit(vm_vaddr_t base, struct kvm_segment *segp) { - if (!vm->gdt) - vm->gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - - dt->base = vm->gdt; - dt->limit = getpagesize(); -} - -static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, - int selector) -{ - if (!vm->tss) - vm->tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - memset(segp, 0, sizeof(*segp)); - segp->base = vm->tss; + segp->base = base; segp->limit = 0x67; - segp->selector = selector; + segp->selector = KERNEL_TSS; segp->type = 0xb; segp->present = 1; - kvm_seg_fill_gdt_64bit(vm, segp); } -static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { struct kvm_sregs sregs; + TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXV48_4K); + /* Set mode specific system register values. */ vcpu_sregs_get(vcpu, &sregs); - sregs.idt.limit = 0; + sregs.idt.base = vm->arch.idt; + sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; + sregs.gdt.base = vm->arch.gdt; + sregs.gdt.limit = getpagesize() - 1; - kvm_setup_gdt(vm, &sregs.gdt); + sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG; + sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR; + sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); - switch (vm->mode) { - case VM_MODE_PXXV48_4K: - sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG; - sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR; - sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); + kvm_seg_set_unusable(&sregs.ldt); + kvm_seg_set_kernel_code_64bit(&sregs.cs); + kvm_seg_set_kernel_data_64bit(&sregs.ds); + kvm_seg_set_kernel_data_64bit(&sregs.es); + kvm_seg_set_kernel_data_64bit(&sregs.gs); + kvm_seg_set_tss_64bit(vm->arch.tss, &sregs.tr); - kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); - kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); - kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); - kvm_setup_tss_64bit(vm, &sregs.tr, 0x18); - break; + sregs.cr3 = vm->pgd; + vcpu_sregs_set(vcpu, &sregs); +} - default: - TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); +static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, + int dpl, unsigned short selector) +{ + struct idt_entry *base = + (struct idt_entry *)addr_gva2hva(vm, vm->arch.idt); + struct idt_entry *e = &base[vector]; + + memset(e, 0, sizeof(*e)); + e->offset0 = addr; + e->selector = selector; + e->ist = 0; + e->type = 14; + e->dpl = dpl; + e->p = 1; + e->offset1 = addr >> 16; + e->offset2 = addr >> 32; +} + +static bool kvm_fixup_exception(struct ex_regs *regs) +{ + if (regs->r9 != KVM_EXCEPTION_MAGIC || regs->rip != regs->r10) + return false; + + if (regs->vector == DE_VECTOR) + return false; + + regs->rip = regs->r11; + regs->r9 = regs->vector; + regs->r10 = regs->error_code; + return true; +} + +void route_exception(struct ex_regs *regs) +{ + typedef void(*handler)(struct ex_regs *); + handler *handlers = (handler *)exception_handlers; + + if (handlers && handlers[regs->vector]) { + handlers[regs->vector](regs); + return; } - sregs.cr3 = vm->pgd; - vcpu_sregs_set(vcpu, &sregs); + if (kvm_fixup_exception(regs)) + return; + + ucall_assert(UCALL_UNHANDLED, + "Unhandled exception in guest", __FILE__, __LINE__, + "Unhandled exception '0x%lx' at guest RIP '0x%lx'", + regs->vector, regs->rip); +} + +static void vm_init_descriptor_tables(struct kvm_vm *vm) +{ + extern void *idt_handlers; + struct kvm_segment seg; + int i; + + vm->arch.gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->arch.idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->arch.tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + + /* Handlers have the same address in both address spaces.*/ + for (i = 0; i < NUM_INTERRUPTS; i++) + set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, KERNEL_CS); + + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; + + kvm_seg_set_kernel_code_64bit(&seg); + kvm_seg_fill_gdt_64bit(vm, &seg); + + kvm_seg_set_kernel_data_64bit(&seg); + kvm_seg_fill_gdt_64bit(vm, &seg); + + kvm_seg_set_tss_64bit(vm->arch.tss, &seg); + kvm_seg_fill_gdt_64bit(vm, &seg); +} + +void vm_install_exception_handler(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)) +{ + vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + + handlers[vector] = (vm_vaddr_t)handler; +} + +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) + REPORT_GUEST_ASSERT(uc); } void kvm_arch_vm_post_create(struct kvm_vm *vm) { + int r; + + TEST_ASSERT(kvm_has_cap(KVM_CAP_GET_TSC_KHZ), + "Require KVM_GET_TSC_KHZ to provide udelay() to guest."); + vm_create_irqchip(vm); + vm_init_descriptor_tables(vm); + sync_global_to_guest(vm, host_cpu_is_intel); sync_global_to_guest(vm, host_cpu_is_amd); sync_global_to_guest(vm, host_cpu_is_hygon); sync_global_to_guest(vm, host_cpu_is_zhaoxin); + r = __vm_ioctl(vm, KVM_GET_TSC_KHZ, NULL); + TEST_ASSERT(r > 0, "KVM_GET_TSC_KHZ did not provide a valid TSC frequency."); + guest_tsc_khz = r; + sync_global_to_guest(vm, guest_tsc_khz); + if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) { struct kvm_sev_init init = { 0 }; @@ -589,8 +643,16 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm) } } -struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, - void *guest_code) +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code) +{ + struct kvm_regs regs; + + vcpu_regs_get(vcpu, ®s); + regs.rip = (unsigned long) guest_code; + vcpu_regs_set(vcpu, ®s); +} + +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { struct kvm_mp_state mp_state; struct kvm_regs regs; @@ -618,13 +680,12 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); - vcpu_setup(vm, vcpu); + vcpu_init_sregs(vm, vcpu); /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, ®s); regs.rflags = regs.rflags | 0x2; regs.rsp = stack_vaddr; - regs.rip = (unsigned long) guest_code; vcpu_regs_set(vcpu, ®s); /* Setup the MP state */ @@ -1079,102 +1140,6 @@ void kvm_init_vm_address_properties(struct kvm_vm *vm) } } -static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, - int dpl, unsigned short selector) -{ - struct idt_entry *base = - (struct idt_entry *)addr_gva2hva(vm, vm->idt); - struct idt_entry *e = &base[vector]; - - memset(e, 0, sizeof(*e)); - e->offset0 = addr; - e->selector = selector; - e->ist = 0; - e->type = 14; - e->dpl = dpl; - e->p = 1; - e->offset1 = addr >> 16; - e->offset2 = addr >> 32; -} - - -static bool kvm_fixup_exception(struct ex_regs *regs) -{ - if (regs->r9 != KVM_EXCEPTION_MAGIC || regs->rip != regs->r10) - return false; - - if (regs->vector == DE_VECTOR) - return false; - - regs->rip = regs->r11; - regs->r9 = regs->vector; - regs->r10 = regs->error_code; - return true; -} - -void route_exception(struct ex_regs *regs) -{ - typedef void(*handler)(struct ex_regs *); - handler *handlers = (handler *)exception_handlers; - - if (handlers && handlers[regs->vector]) { - handlers[regs->vector](regs); - return; - } - - if (kvm_fixup_exception(regs)) - return; - - ucall_assert(UCALL_UNHANDLED, - "Unhandled exception in guest", __FILE__, __LINE__, - "Unhandled exception '0x%lx' at guest RIP '0x%lx'", - regs->vector, regs->rip); -} - -void vm_init_descriptor_tables(struct kvm_vm *vm) -{ - extern void *idt_handlers; - int i; - - vm->idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - /* Handlers have the same address in both address spaces.*/ - for (i = 0; i < NUM_INTERRUPTS; i++) - set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, - DEFAULT_CODE_SELECTOR); -} - -void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu) -{ - struct kvm_vm *vm = vcpu->vm; - struct kvm_sregs sregs; - - vcpu_sregs_get(vcpu, &sregs); - sregs.idt.base = vm->idt; - sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; - sregs.gdt.base = vm->gdt; - sregs.gdt.limit = getpagesize() - 1; - kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs); - vcpu_sregs_set(vcpu, &sregs); - *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; -} - -void vm_install_exception_handler(struct kvm_vm *vm, int vector, - void (*handler)(struct ex_regs *)) -{ - vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); - - handlers[vector] = (vm_vaddr_t)handler; -} - -void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) -{ - struct ucall uc; - - if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) - REPORT_GUEST_ASSERT(uc); -} - const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, uint32_t function, uint32_t index) { diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c new file mode 100644 index 0000000000000000000000000000000000000000..0350a8896a2f50953441f7c4e1257e6d83e2c0e3 --- /dev/null +++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024, Intel, Inc + * + * Author: + * Isaku Yamahata + */ +#include + +#include +#include +#include + +/* Arbitrarily chosen values */ +#define TEST_SIZE (SZ_2M + PAGE_SIZE) +#define TEST_NPAGES (TEST_SIZE / PAGE_SIZE) +#define TEST_SLOT 10 + +static void guest_code(uint64_t base_gpa) +{ + volatile uint64_t val __used; + int i; + + for (i = 0; i < TEST_NPAGES; i++) { + uint64_t *src = (uint64_t *)(base_gpa + i * PAGE_SIZE); + + val = *src; + } + + GUEST_DONE(); +} + +static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size, + u64 left) +{ + struct kvm_pre_fault_memory range = { + .gpa = gpa, + .size = size, + .flags = 0, + }; + u64 prev; + int ret, save_errno; + + do { + prev = range.size; + ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range); + save_errno = errno; + TEST_ASSERT((range.size < prev) ^ (ret < 0), + "%sexpecting range.size to change on %s", + ret < 0 ? "not " : "", + ret < 0 ? "failure" : "success"); + } while (ret >= 0 ? range.size : save_errno == EINTR); + + TEST_ASSERT(range.size == left, + "Completed with %lld bytes left, expected %" PRId64, + range.size, left); + + if (left == 0) + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm); + else + /* No memory slot causes RET_PF_EMULATE. it results in -ENOENT. */ + __TEST_ASSERT_VM_VCPU_IOCTL(ret && save_errno == ENOENT, + "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm); +} + +static void __test_pre_fault_memory(unsigned long vm_type, bool private) +{ + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = vm_type, + }; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + + uint64_t guest_test_phys_mem; + uint64_t guest_test_virt_mem; + uint64_t alignment, guest_page_size; + + vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code); + + alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size; + guest_test_phys_mem = (vm->max_gfn - TEST_NPAGES) * guest_page_size; +#ifdef __s390x__ + alignment = max(0x100000UL, guest_page_size); +#else + alignment = SZ_2M; +#endif + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); + guest_test_virt_mem = guest_test_phys_mem & ((1ULL << (vm->va_bits - 1)) - 1); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, TEST_SLOT, TEST_NPAGES, + private ? KVM_MEM_GUEST_MEMFD : 0); + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, TEST_NPAGES); + + if (private) + vm_mem_set_private(vm, guest_test_phys_mem, TEST_SIZE); + pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, 0); + pre_fault_memory(vcpu, guest_test_phys_mem + SZ_2M, PAGE_SIZE * 2, PAGE_SIZE); + pre_fault_memory(vcpu, guest_test_phys_mem + TEST_SIZE, PAGE_SIZE, PAGE_SIZE); + + vcpu_args_set(vcpu, 1, guest_test_virt_mem); + vcpu_run(vcpu); + + run = vcpu->run; + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Wanted KVM_EXIT_IO, got exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + break; + } + + kvm_vm_free(vm); +} + +static void test_pre_fault_memory(unsigned long vm_type, bool private) +{ + if (vm_type && !(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(vm_type))) { + pr_info("Skipping tests for vm_type 0x%lx\n", vm_type); + return; + } + + __test_pre_fault_memory(vm_type, private); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY)); + + test_pre_fault_memory(0, false); +#ifdef __x86_64__ + test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, false); + test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, true); +#endif + return 0; +} diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index 462979a5957b8b5f56f8a3b5e08df5906be64a03..559f54d220414c512a1996ae21c45c9a151b959a 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -14,6 +14,7 @@ #include "kvm_util.h" #include "processor.h" #include "timer_test.h" +#include "ucall_common.h" static int timer_irq = IRQ_S_TIMER; diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index f74e76d03b7e306667221ee9c5411bda2af417d5..751f981bb75079faf54ecb5492aa1131186f73d2 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -19,6 +19,7 @@ #include "kvm_util.h" #include "processor.h" #include "test_util.h" +#include "ucall_common.h" #include "../rseq/rseq.c" diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c index c8e0a6495a63ae2ca55ac97f56b928c72afdb469..bec05ed9af4e8b2cac186d6111dd1164d6218c06 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390x/cmma_test.c @@ -18,6 +18,7 @@ #include "test_util.h" #include "kvm_util.h" #include "kselftest.h" +#include "ucall_common.h" #define MAIN_PAGE_COUNT 512 diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index bb3ca9a5d7318ebe88fbe9f5a7ebfaaf0c2235b6..9b31693be1cba3515da8298f24f3fa6356de77aa 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -15,6 +15,7 @@ #include "test_util.h" #include "kvm_util.h" #include "kselftest.h" +#include "ucall_common.h" enum mop_target { LOGICAL, diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c index c73f948c9b63792cf2776ef3308763547ecec0ca..7a742a673b7c90ee9a606006d526374a7bbb15cb 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -8,6 +8,7 @@ #include "test_util.h" #include "kvm_util.h" #include "kselftest.h" +#include "ucall_common.h" #define PAGE_SHIFT 12 #define PAGE_SIZE (1 << PAGE_SHIFT) diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 4e2b0f27a4cef09427df551c001b69f0ee66d001..45f5d47e53fc62fc00e2df9254878035766fc323 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -221,8 +221,20 @@ static void test_move_memory_region(void) static void guest_code_delete_memory_region(void) { + struct desc_ptr idt; uint64_t val; + /* + * Clobber the IDT so that a #PF due to the memory region being deleted + * escalates to triple-fault shutdown. Because the memory region is + * deleted, there will be no valid mappings. As a result, KVM will + * repeatedly intercepts the state-2 page fault that occurs when trying + * to vector the guest's #PF. I.e. trying to actually handle the #PF + * in the guest will never succeed, and so isn't an option. + */ + memset(&idt, 0, sizeof(idt)); + __asm__ __volatile__("lidt %0" :: "m"(idt)); + GUEST_SYNC(0); /* Spin until the memory region is deleted. */ @@ -373,6 +385,12 @@ static void test_invalid_memory_region_flags(void) TEST_ASSERT(r && errno == EINVAL, "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported"); + r = __vm_set_user_memory_region2(vm, 0, + KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD, + 0, MEM_REGION_SIZE, NULL, guest_memfd, 0); + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION2 should have failed, read-only GUEST_MEMFD memslots are unsupported"); + close(guest_memfd); } } diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 871202a8b3ea8d9460ad0bd3b5d29addacf520da..fdfa68fa61b8ce676f14a04a82e3f8dc054a774d 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -20,6 +20,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" #define NR_VCPUS 4 #define ST_GPA_BASE (1 << 30) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 309ee5c72b46a50f0c0886b2043833a49ae02ee8..cf6fd1be75008f4375b83d4d04c66770d73fbe63 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -246,8 +246,6 @@ int main(int argc, char *argv[]) vcpu_regs_get(vcpu, ®s1); /* Register #NM handler */ - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); /* amx cfg for guest_code */ diff --git a/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c b/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c new file mode 100644 index 0000000000000000000000000000000000000000..f8916bb34405017bb302fcd9eb903e64333d640e --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024 Intel Corporation + * + * Verify KVM correctly emulates the APIC bus frequency when the VMM configures + * the frequency via KVM_CAP_X86_APIC_BUS_CYCLES_NS. Start the APIC timer by + * programming TMICT (timer initial count) to the largest value possible (so + * that the timer will not expire during the test). Then, after an arbitrary + * amount of time has elapsed, verify TMCCT (timer current count) is within 1% + * of the expected value based on the time elapsed, the APIC bus frequency, and + * the programmed TDCR (timer divide configuration register). + */ + +#include "apic.h" +#include "test_util.h" + +/* + * Possible TDCR values with matching divide count. Used to modify APIC + * timer frequency. + */ +static const struct { + const uint32_t tdcr; + const uint32_t divide_count; +} tdcrs[] = { + {0x0, 2}, + {0x1, 4}, + {0x2, 8}, + {0x3, 16}, + {0x8, 32}, + {0x9, 64}, + {0xa, 128}, + {0xb, 1}, +}; + +static bool is_x2apic; + +static void apic_enable(void) +{ + if (is_x2apic) + x2apic_enable(); + else + xapic_enable(); +} + +static uint32_t apic_read_reg(unsigned int reg) +{ + return is_x2apic ? x2apic_read_reg(reg) : xapic_read_reg(reg); +} + +static void apic_write_reg(unsigned int reg, uint32_t val) +{ + if (is_x2apic) + x2apic_write_reg(reg, val); + else + xapic_write_reg(reg, val); +} + +static void apic_guest_code(uint64_t apic_hz, uint64_t delay_ms) +{ + uint64_t tsc_hz = guest_tsc_khz * 1000; + const uint32_t tmict = ~0u; + uint64_t tsc0, tsc1, freq; + uint32_t tmcct; + int i; + + apic_enable(); + + /* + * Setup one-shot timer. The vector does not matter because the + * interrupt should not fire. + */ + apic_write_reg(APIC_LVTT, APIC_LVT_TIMER_ONESHOT | APIC_LVT_MASKED); + + for (i = 0; i < ARRAY_SIZE(tdcrs); i++) { + apic_write_reg(APIC_TDCR, tdcrs[i].tdcr); + apic_write_reg(APIC_TMICT, tmict); + + tsc0 = rdtsc(); + udelay(delay_ms * 1000); + tmcct = apic_read_reg(APIC_TMCCT); + tsc1 = rdtsc(); + + /* + * Stop the timer _after_ reading the current, final count, as + * writing the initial counter also modifies the current count. + */ + apic_write_reg(APIC_TMICT, 0); + + freq = (tmict - tmcct) * tdcrs[i].divide_count * tsc_hz / (tsc1 - tsc0); + /* Check if measured frequency is within 5% of configured frequency. */ + __GUEST_ASSERT(freq < apic_hz * 105 / 100 && freq > apic_hz * 95 / 100, + "Frequency = %lu (wanted %lu - %lu), bus = %lu, div = %u, tsc = %lu", + freq, apic_hz * 95 / 100, apic_hz * 105 / 100, + apic_hz, tdcrs[i].divide_count, tsc_hz); + } + + GUEST_DONE(); +} + +static void test_apic_bus_clock(struct kvm_vcpu *vcpu) +{ + bool done = false; + struct ucall uc; + + while (!done) { + vcpu_run(vcpu); + + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + done = true; + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + break; + } + } +} + +static void run_apic_bus_clock_test(uint64_t apic_hz, uint64_t delay_ms, + bool x2apic) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int ret; + + is_x2apic = x2apic; + + vm = vm_create(1); + + sync_global_to_guest(vm, is_x2apic); + + vm_enable_cap(vm, KVM_CAP_X86_APIC_BUS_CYCLES_NS, + NSEC_PER_SEC / apic_hz); + + vcpu = vm_vcpu_add(vm, 0, apic_guest_code); + vcpu_args_set(vcpu, 2, apic_hz, delay_ms); + + ret = __vm_enable_cap(vm, KVM_CAP_X86_APIC_BUS_CYCLES_NS, + NSEC_PER_SEC / apic_hz); + TEST_ASSERT(ret < 0 && errno == EINVAL, + "Setting of APIC bus frequency after vCPU is created should fail."); + + if (!is_x2apic) + virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); + + test_apic_bus_clock(vcpu); + kvm_vm_free(vm); +} + +static void help(char *name) +{ + puts(""); + printf("usage: %s [-h] [-d delay] [-f APIC bus freq]\n", name); + puts(""); + printf("-d: Delay (in msec) guest uses to measure APIC bus frequency.\n"); + printf("-f: The APIC bus frequency (in MHz) to be configured for the guest.\n"); + puts(""); +} + +int main(int argc, char *argv[]) +{ + /* + * Arbitrarilty default to 25MHz for the APIC bus frequency, which is + * different enough from the default 1GHz to be interesting. + */ + uint64_t apic_hz = 25 * 1000 * 1000; + uint64_t delay_ms = 100; + int opt; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_APIC_BUS_CYCLES_NS)); + + while ((opt = getopt(argc, argv, "d:f:h")) != -1) { + switch (opt) { + case 'f': + apic_hz = atoi_positive("APIC bus frequency", optarg) * 1000 * 1000; + break; + case 'd': + delay_ms = atoi_positive("Delay in milliseconds", optarg); + break; + case 'h': + default: + help(argv[0]); + exit(KSFT_SKIP); + } + } + + run_apic_bus_clock_test(apic_hz, delay_ms, false); + run_apic_bus_clock_test(apic_hz, delay_ms, true); +} diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c index 634c6bfcd5720717e0d4cc93e9cdf92ae96fb1d0..d93e6cb72cf7ad0b45ad86cf86cfbc99c518746f 100644 --- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c +++ b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c @@ -17,6 +17,7 @@ #include "test_util.h" #include "memstress.h" #include "guest_modes.h" +#include "ucall_common.h" #define VCPUS 2 #define SLOTS 2 diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c index 6c2e5e0ceb1f7de859e23b325232c70048b9dbe3..fbac69d49b3972a5a32a22049ddf294971c142a3 100644 --- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c +++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c @@ -8,8 +8,8 @@ #define _GNU_SOURCE /* for program_invocation_short_name */ #include "flds_emulation.h" - #include "test_util.h" +#include "ucall_common.h" #define MMIO_GPA 0x700000000 #define MMIO_GVA MMIO_GPA diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index 789960d5287530c69b04773aefcb49f1e9ff5716..21066f621973427434212b4fc61e59280f71f163 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -110,8 +110,6 @@ static void test_fix_hypercall(bool disable_quirk) vm = vm_create_with_one_vcpu(&vcpu, guest_main); - vm_init_descriptor_tables(vcpu->vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler); if (disable_quirk) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index 7bde0c4dfdbd18b769a2580c68c2e789a7a692a6..b7e2d607afa2cb5dd8ae499c7be58a785f9089a2 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -257,8 +257,6 @@ int main(int argc, char *argv[]) vcpu_args_set(vcpu, 3, vmx_pages_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page)); vcpu_set_msr(vcpu, HV_X64_MSR_VP_INDEX, vcpu->id); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index a726831b80244e517423650d195f21c3bb2c8caa..04fa83bd210160dc88c1388eab849bbaa48210e3 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -156,9 +156,6 @@ static void guest_test_msrs_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - /* TODO: Make this entire test easier to maintain. */ if (stage >= 21) vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_SYNIC2, 0); @@ -532,9 +529,6 @@ static void guest_test_hcalls_access(void) while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_hcall); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - /* Hypercall input/output */ hcall_page = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c index 6feb5ddb031dac66aeabe18b7733f8639f29af63..7c23c658cb689587176d648e4a1ba9826b022864 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c @@ -254,16 +254,13 @@ int main(int argc, char *argv[]) hcall_page = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - vm_init_descriptor_tables(vm); vcpu[1] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_1, receiver_code); - vcpu_init_descriptor_tables(vcpu[1]); vcpu_args_set(vcpu[1], 2, hcall_page, addr_gva2gpa(vm, hcall_page)); vcpu_set_msr(vcpu[1], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_1); vcpu_set_hv_cpuid(vcpu[1]); vcpu[2] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_2, receiver_code); - vcpu_init_descriptor_tables(vcpu[2]); vcpu_args_set(vcpu[2], 2, hcall_page, addr_gva2gpa(vm, hcall_page)); vcpu_set_msr(vcpu[2], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_2); vcpu_set_hv_cpuid(vcpu[2]); diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index 9e2879af7c201fb749120cee94a61e03dfaf162b..cef0bd80038b9ffa639216d516fe30e4b6cd5ed5 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -146,9 +146,6 @@ int main(void) vcpu_clear_cpuid_entry(vcpu, KVM_CPUID_FEATURES); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - enter_guest(vcpu); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c index 80aa3d8b18f803c20092cc938d6822866146beda..e2cb92cebbbffa80670d42097ee2b87efdbc1077 100644 --- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c @@ -78,9 +78,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - while (1) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index c9a07963d68aaedcc6b45d4e00e932e5981645b0..9cf2b9fbf459ad1d687394dc9f23e545f8f78603 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -26,36 +26,18 @@ static void guest_code(void) { uint64_t msr_platform_info; + uint8_t vector; - for (;;) { - msr_platform_info = rdmsr(MSR_PLATFORM_INFO); - GUEST_SYNC(msr_platform_info); - asm volatile ("inc %r11"); - } -} + GUEST_SYNC(true); + msr_platform_info = rdmsr(MSR_PLATFORM_INFO); + GUEST_ASSERT_EQ(msr_platform_info & MSR_PLATFORM_INFO_MAX_TURBO_RATIO, + MSR_PLATFORM_INFO_MAX_TURBO_RATIO); -static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu) -{ - struct ucall uc; - - vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, true); - vcpu_run(vcpu); - TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); - - get_ucall(vcpu, &uc); - TEST_ASSERT(uc.cmd == UCALL_SYNC, - "Received ucall other than UCALL_SYNC: %lu\n", uc.cmd); - TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == - MSR_PLATFORM_INFO_MAX_TURBO_RATIO, - "Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.", - MSR_PLATFORM_INFO_MAX_TURBO_RATIO); -} + GUEST_SYNC(false); + vector = rdmsr_safe(MSR_PLATFORM_INFO, &msr_platform_info); + GUEST_ASSERT_EQ(vector, GP_VECTOR); -static void test_msr_platform_info_disabled(struct kvm_vcpu *vcpu) -{ - vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, false); - vcpu_run(vcpu); - TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + GUEST_DONE(); } int main(int argc, char *argv[]) @@ -63,6 +45,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t msr_platform_info; + struct ucall uc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO)); @@ -71,8 +54,26 @@ int main(int argc, char *argv[]) msr_platform_info = vcpu_get_msr(vcpu, MSR_PLATFORM_INFO); vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); - test_msr_platform_info_enabled(vcpu); - test_msr_platform_info_disabled(vcpu); + + for (;;) { + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + vm_enable_cap(vm, KVM_CAP_MSR_PLATFORM_INFO, uc.args[1]); + break; + case UCALL_DONE: + goto done; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall %lu", uc.cmd); + break; + } + } + +done: vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, msr_platform_info); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 2c32ea361fd8c2294ddbcb99fa63a15c75725205..7b917bf0a9e54187c109a81d753ad1a30a85664c 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -389,9 +389,6 @@ static void test_pmu_config_disable(void (*guest_code)(void)) vm_enable_cap(vm, KVM_CAP_PMU_CAPABILITY, KVM_PMU_CAP_DISABLE); vcpu = vm_vcpu_add(vm, 0, guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - TEST_ASSERT(!sanity_check_pmu(vcpu), "Guest should not be able to use disabled PMU."); @@ -934,9 +931,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - TEST_REQUIRE(sanity_check_pmu(vcpu)); if (use_amd_pmu() || use_hygon_pmu()) diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c index 06edf00a97d61dc3ca265926c2043d839daddeeb..e5b390236d5370291e923dcb707153613d723ad4 100644 --- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c +++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c @@ -60,9 +60,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); vcpu_args_set(vcpu, 1, kvm_is_tdp_enabled()); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR); rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index 32bef39bec2178068238a2de650f87179acc22f6..916e04248fbbdd13c10a109fa89e515b9692d90f 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -93,9 +93,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c index d6fcdcc3af3144b6805cf3d9530614b03476ac79..00135cbba35eacd98f34b4df3e4968a715228fdd 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c @@ -48,12 +48,9 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vcpu_alloc_svm(vm, &svm_gva); - vcpu_args_set(vcpu, 2, svm_gva, vm->idt); + vcpu_args_set(vcpu, 2, svm_gva, vm->arch.idt); vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); 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 7ee44496cf97f62a9dcd2637fad26d210eac43be..59fedff3b2bbbf1e1a0991c792c6ee8a24a9fb23 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 @@ -152,9 +152,6 @@ static void run_test(bool is_nmi) vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); vm_install_exception_handler(vm, BP_VECTOR, guest_bp_handler); vm_install_exception_handler(vm, INT_NR, guest_int_handler); @@ -166,7 +163,7 @@ static void run_test(bool is_nmi) idt_alt_vm = vm_vaddr_alloc_page(vm); idt_alt = addr_gva2hva(vm, idt_alt_vm); - idt = addr_gva2hva(vm, vm->idt); + idt = addr_gva2hva(vm, vm->arch.idt); memcpy(idt_alt, idt, getpagesize()); } else { idt_alt_vm = 0; diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c index 0ed32ec903d03548ce11fa5bcc42eba329808506..ee67ab2f4f23c8b9b8fb3d0894fce6de78a4c6ac 100644 --- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c @@ -24,7 +24,6 @@ #include #include -#include "kvm_util_base.h" #include "kvm_util.h" #include "mce.h" #include "processor.h" @@ -285,10 +284,6 @@ int main(int argc, char *argv[]) cmcidis_vcpu = create_vcpu_with_mce_cap(vm, 1, false, cmci_disabled_guest_code); cmci_vcpu = create_vcpu_with_mce_cap(vm, 2, true, cmci_enabled_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(ucna_vcpu); - vcpu_init_descriptor_tables(cmcidis_vcpu); - vcpu_init_descriptor_tables(cmci_vcpu); vm_install_exception_handler(vm, CMCI_VECTOR, guest_cmci_handler); vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c index 3533dc2fbfeeb136b217eb79e819e2e374e2b0cd..5ca2fa4af413683850ca1c630804877d436dcd85 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -544,9 +544,6 @@ static void test_msr_filter_allow(void) vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); /* Process guest code userspace exits. */ diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c index a9b827c69f32c5f96548d040c72d979166041f19..339929cf221f8f7849988c78d6c8cabeff37f6b2 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -115,9 +115,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); get_set_sigalrm_vcpu(vcpu); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); /* diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index e44f89ce617a80d57095df7b04a9ad37de855283..f764788e175b5f44ff40e49a4be4fe1a07725648 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -86,9 +86,6 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) struct ucall uc; int r, i; - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); vcpu_args_set(vcpu, 1, host_cap.capabilities); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c index 67ac2a3292efd4e5a4ff24073af25849ce375dd9..47d66508a337b035aef6570233c5322c25403076 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c @@ -410,8 +410,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(¶ms[0].vcpu, halter_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(params[0].vcpu); vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c index 77d04a7bdaddd59d04f723d2b6858ca950eb9534..5db2a122defe3181cb1663bc316fe82a2022fcf6 100644 --- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c @@ -109,9 +109,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); run = vcpu->run; - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - while (1) { vcpu_run(vcpu); 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 9ec9ab60b63ee27d2deb6f90d9b38a71e2deb142..4fa1d36fe67332341062ba79b80df689929ef56f 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -522,8 +522,6 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler); if (do_runstate_tests) { diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index ecbe2db0fd6b01ef8562974470240e6511396b79..a3d802b98728e66c2b37486b6c364cc72645895b 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -431,6 +431,7 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) inode->i_private = (void *)(unsigned long)flags; inode->i_op = &kvm_gmem_iops; inode->i_mapping->a_ops = &kvm_gmem_aops; + inode->i_mapping->flags |= AS_INACCESSIBLE; inode->i_mode |= S_IFREG; inode->i_size = size; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 196f42cf94a30249f554e7914880095ef4b51e56..33e0a1ed28c71ed09a5f49fb96f14b523a0b1c6f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -408,12 +408,17 @@ static void kvm_flush_shadow_all(struct kvm *kvm) static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) { + void *page; + gfp_flags |= mc->gfp_zero; if (mc->kmem_cache) return kmem_cache_alloc(mc->kmem_cache, gfp_flags); - else - return (void *)__get_free_page(gfp_flags); + + page = (void *)__get_free_page(gfp_flags); + if (page && mc->init_value) + memset64(page, mc->init_value, PAGE_SIZE / sizeof(u64)); + return page; } int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min) @@ -428,6 +433,13 @@ int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, if (WARN_ON_ONCE(!capacity)) return -EIO; + /* + * Custom init values can be used only for page allocations, + * and obviously conflict with __GFP_ZERO. + */ + if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero))) + return -EIO; + mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp); if (!mc->objects) return -ENOMEM;