diff options
82 files changed, 2799 insertions, 1448 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bb48ae24ae69..1518343bbe22 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2677,6 +2677,23 @@ Default is Y (on). + kvm.enable_virt_at_load=[KVM,ARM64,LOONGARCH,MIPS,RISCV,X86] + If enabled, KVM will enable virtualization in hardware + when KVM is loaded, and disable virtualization when KVM + is unloaded (if KVM is built as a module). + + If disabled, KVM will dynamically enable and disable + virtualization on-demand when creating and destroying + VMs, i.e. on the 0=>1 and 1=>0 transitions of the + number of VMs. + + Enabling virtualization at module lode avoids potential + latency for creation of the 0=>1 VM, as KVM serializes + virtualization enabling across all online CPUs. The + "cost" of enabling virtualization when KVM is loaded, + is that doing so may interfere with using out-of-tree + hypervisors that want to "own" virtualization hardware. + kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. Default is false (don't support). diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index b3be87489108..e32471977d0a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4214,7 +4214,9 @@ whether or not KVM_CAP_X86_USER_SPACE_MSR's KVM_MSR_EXIT_REASON_FILTER is enabled. If KVM_MSR_EXIT_REASON_FILTER is enabled, KVM will exit to userspace on denied accesses, i.e. userspace effectively intercepts the MSR access. If KVM_MSR_EXIT_REASON_FILTER is not enabled, KVM will inject a #GP into the guest -on denied accesses. +on denied accesses. Note, if an MSR access is denied during emulation of MSR +load/stores during VMX transitions, KVM ignores KVM_MSR_EXIT_REASON_FILTER. +See the below warning for full details. If an MSR access is allowed by userspace, KVM will emulate and/or virtualize the access in accordance with the vCPU model. Note, KVM may still ultimately @@ -4229,9 +4231,22 @@ filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes an error. .. warning:: - MSR accesses as part of nested VM-Enter/VM-Exit are not filtered. - This includes both writes to individual VMCS fields and reads/writes - through the MSR lists pointed to by the VMCS. + MSR accesses that are side effects of instruction execution (emulated or + native) are not filtered as hardware does not honor MSR bitmaps outside of + RDMSR and WRMSR, and KVM mimics that behavior when emulating instructions + to avoid pointless divergence from hardware. E.g. RDPID reads MSR_TSC_AUX, + SYSENTER reads the SYSENTER MSRs, etc. + + MSRs that are loaded/stored via dedicated VMCS fields are not filtered as + part of VM-Enter/VM-Exit emulation. + + MSRs that are loaded/store via VMX's load/store lists _are_ filtered as part + of VM-Enter/VM-Exit emulation. If an MSR access is denied on VM-Enter, KVM + synthesizes a consistency check VM-Exit(EXIT_REASON_MSR_LOAD_FAIL). If an + MSR access is denied on VM-Exit, KVM synthesizes a VM-Abort. In short, KVM + extends Intel's architectural list of MSRs that cannot be loaded/saved via + the VM-Enter/VM-Exit MSR list. It is platform owner's responsibility to + to communicate any such restrictions to their end users. x2APIC MSR accesses cannot be filtered (KVM silently ignores filters that cover any x2APIC MSRs). @@ -8082,6 +8097,14 @@ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if guest CPUID on writes to MISC_ENABLE if KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is disabled. + +KVM_X86_QUIRK_SLOT_ZAP_ALL By default, KVM invalidates all SPTEs in + fast way for memslot deletion when VM type + is KVM_X86_DEFAULT_VM. + When this quirk is disabled or when VM type + is other than KVM_X86_DEFAULT_VM, KVM zaps + only leaf SPTEs that are within the range of + the memslot being deleted. =================================== ============================================ 7.32 KVM_CAP_MAX_VCPU_ID diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 02880d5552d5..20a9a37d1cdd 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -11,6 +11,8 @@ The acquisition orders for mutexes are as follows: - cpus_read_lock() is taken outside kvm_lock +- kvm_usage_lock is taken outside cpus_read_lock() + - kvm->lock is taken outside vcpu->mutex - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock @@ -24,6 +26,13 @@ The acquisition orders for mutexes are as follows: are taken on the waiting side when modifying memslots, so MMU notifiers must not take either kvm->slots_lock or kvm->slots_arch_lock. +cpus_read_lock() vs kvm_lock: + +- Taking cpus_read_lock() outside of kvm_lock is problematic, despite that + being the official ordering, as it is quite easy to unknowingly trigger + cpus_read_lock() while holding kvm_lock. Use caution when walking vm_list, + e.g. avoid complex operations when possible. + For SRCU: - ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections @@ -227,10 +236,16 @@ time it will be set using the Dirty tracking mechanism described above. :Type: mutex :Arch: any :Protects: - vm_list - - kvm_usage_count + +``kvm_usage_lock`` +^^^^^^^^^^^^^^^^^^ + +:Type: mutex +:Arch: any +:Protects: - kvm_usage_count - hardware virtualization enable/disable -:Comment: KVM also disables CPU hotplug via cpus_read_lock() during - enable/disable. +:Comment: Exists to allow taking cpus_read_lock() while kvm_usage_count is + protected, which simplifies the virtualization enabling logic. ``kvm->mn_invalidate_lock`` ^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -290,11 +305,12 @@ time it will be set using the Dirty tracking mechanism described above. wakeup. ``vendor_module_lock`` -^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +^^^^^^^^^^^^^^^^^^^^^^ :Type: mutex :Arch: x86 :Protects: loading a vendor module (kvm_amd or kvm_intel) -:Comment: Exists because using kvm_lock leads to deadlock. cpu_hotplug_lock is - taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and - many operations need to take cpu_hotplug_lock when loading a vendor module, - e.g. updating static calls. +:Comment: Exists because using kvm_lock leads to deadlock. kvm_lock is taken + in notifiers, e.g. __kvmclock_cpufreq_notifier(), that may be invoked while + cpu_hotplug_lock is held, e.g. from cpufreq_boost_trigger_state(), and many + operations need to take cpu_hotplug_lock when loading a vendor module, e.g. + updating static calls. diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index fe0764173cd0..a0d01c46e408 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2164,7 +2164,7 @@ static void cpu_hyp_uninit(void *discard) } } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { /* * Most calls to this function are made with migration @@ -2184,7 +2184,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_timer_cpu_down(); kvm_vgic_cpu_down(); @@ -2380,7 +2380,7 @@ static int __init do_pkvm_init(u32 hyp_va_bits) /* * The stub hypercalls are now disabled, so set our local flag to - * prevent a later re-init attempt in kvm_arch_hardware_enable(). + * prevent a later re-init attempt in kvm_arch_enable_virtualization_cpu(). */ __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 844736b99d38..27e9b94c0a0b 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -261,7 +261,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -ENOIOCTLCMD; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { unsigned long env, gcfg = 0; @@ -300,7 +300,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { write_csr_gcfg(0); write_csr_gstat(0); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6743a57c1ab4..f7222eb594ea 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -728,8 +728,8 @@ struct kvm_mips_callbacks { int (*handle_fpe)(struct kvm_vcpu *vcpu); int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); int (*handle_guest_exit)(struct kvm_vcpu *vcpu); - int (*hardware_enable)(void); - void (*hardware_disable)(void); + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); int (*check_extension)(struct kvm *kvm, long ext); int (*vcpu_init)(struct kvm_vcpu *vcpu); void (*vcpu_uninit)(struct kvm_vcpu *vcpu); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b5de770b092e..60b43ea85c12 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -125,14 +125,14 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return 1; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { - return kvm_mips_callbacks->hardware_enable(); + return kvm_mips_callbacks->enable_virtualization_cpu(); } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { - kvm_mips_callbacks->hardware_disable(); + kvm_mips_callbacks->disable_virtualization_cpu(); } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index 99d5a71e4300..ccab4d76b126 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -2869,7 +2869,7 @@ static unsigned int kvm_vz_resize_guest_vtlb(unsigned int size) return ret + 1; } -static int kvm_vz_hardware_enable(void) +static int kvm_vz_enable_virtualization_cpu(void) { unsigned int mmu_size, guest_mmu_size, ftlb_size; u64 guest_cvmctl, cvmvmconfig; @@ -2983,7 +2983,7 @@ static int kvm_vz_hardware_enable(void) return 0; } -static void kvm_vz_hardware_disable(void) +static void kvm_vz_disable_virtualization_cpu(void) { u64 cvmvmconfig; unsigned int mmu_size; @@ -3280,8 +3280,8 @@ static struct kvm_mips_callbacks kvm_vz_callbacks = { .handle_msa_disabled = kvm_trap_vz_handle_msa_disabled, .handle_guest_exit = kvm_trap_vz_handle_guest_exit, - .hardware_enable = kvm_vz_hardware_enable, - .hardware_disable = kvm_vz_hardware_disable, + .enable_virtualization_cpu = kvm_vz_enable_virtualization_cpu, + .disable_virtualization_cpu = kvm_vz_disable_virtualization_cpu, .check_extension = kvm_vz_check_extension, .vcpu_init = kvm_vz_vcpu_init, .vcpu_uninit = kvm_vz_vcpu_uninit, diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index bab2ec34cd87..f3427f6de608 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -20,7 +20,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { csr_write(CSR_HEDELEG, KVM_HEDELEG_DEFAULT); csr_write(CSR_HIDELEG, KVM_HIDELEG_DEFAULT); @@ -35,7 +35,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_riscv_aia_disable(); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 7ec1b8cd0de9..9b57add02cd5 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -59,6 +59,7 @@ CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_S390_HYPFS_FS=y CONFIG_KVM=m +CONFIG_KVM_S390_UCONTROL=y CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m CONFIG_S390_MODULES_SANITY_TEST=m diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 0fd96860fc45..bb7134faaebf 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -348,20 +348,29 @@ static inline int plo_test_bit(unsigned char nr) return cc == 0; } -static __always_inline void __insn32_query(unsigned int opcode, u8 *query) +static __always_inline void __sortl_query(u8 (*query)[32]) { asm volatile( " lghi 0,0\n" - " lgr 1,%[query]\n" + " la 1,%[query]\n" /* Parameter registers are ignored */ - " .insn rrf,%[opc] << 16,2,4,6,0\n" + " .insn rre,0xb9380000,2,4\n" + : [query] "=R" (*query) : - : [query] "d" ((unsigned long)query), [opc] "i" (opcode) - : "cc", "memory", "0", "1"); + : "cc", "0", "1"); } -#define INSN_SORTL 0xb938 -#define INSN_DFLTCC 0xb939 +static __always_inline void __dfltcc_query(u8 (*query)[32]) +{ + asm volatile( + " lghi 0,0\n" + " la 1,%[query]\n" + /* Parameter registers are ignored */ + " .insn rrf,0xb9390000,2,4,6,0\n" + : [query] "=R" (*query) + : + : "cc", "0", "1"); +} static void __init kvm_s390_cpu_feat_init(void) { @@ -415,10 +424,10 @@ static void __init kvm_s390_cpu_feat_init(void) kvm_s390_available_subfunc.kdsa); if (test_facility(150)) /* SORTL */ - __insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl); + __sortl_query(&kvm_s390_available_subfunc.sortl); if (test_facility(151)) /* DFLTCC */ - __insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc); + __dfltcc_query(&kvm_s390_available_subfunc.dfltcc); if (MACHINE_HAS_ESOP) allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP); diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 80cc6386d7b1..ca4243318aad 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -179,6 +179,7 @@ static __always_inline bool cpuid_function_is_indexed(u32 function) case 0x1d: case 0x1e: case 0x1f: + case 0x24: case 0x8000001d: return true; } diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 68ad4f923664..861d080ed4c6 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -14,8 +14,8 @@ BUILD_BUG_ON(1) * be __static_call_return0. */ KVM_X86_OP(check_processor_compatibility) -KVM_X86_OP(hardware_enable) -KVM_X86_OP(hardware_disable) +KVM_X86_OP(enable_virtualization_cpu) +KVM_X86_OP(disable_virtualization_cpu) KVM_X86_OP(hardware_unsetup) KVM_X86_OP(has_emulated_msr) KVM_X86_OP(vcpu_after_set_cpuid) @@ -125,7 +125,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) -KVM_X86_OP(get_msr_feature) +KVM_X86_OP(get_feature_msr) KVM_X86_OP(check_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4a68cb3eba78..6d9f763a7bb9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -36,6 +36,7 @@ #include <asm/kvm_page_track.h> #include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> +#include <asm/reboot.h> #define __KVM_HAVE_ARCH_VCPU_DEBUGFS @@ -211,6 +212,7 @@ enum exit_fastpath_completion { EXIT_FASTPATH_NONE, EXIT_FASTPATH_REENTER_GUEST, EXIT_FASTPATH_EXIT_HANDLED, + EXIT_FASTPATH_EXIT_USERSPACE, }; typedef enum exit_fastpath_completion fastpath_t; @@ -280,10 +282,6 @@ enum x86_intercept_stage; #define PFERR_PRIVATE_ACCESS BIT_ULL(49) #define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) -#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ - PFERR_WRITE_MASK | \ - PFERR_PRESENT_MASK) - /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -1629,8 +1627,10 @@ struct kvm_x86_ops { int (*check_processor_compatibility)(void); - int (*hardware_enable)(void); - void (*hardware_disable)(void); + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); + cpu_emergency_virt_cb *emergency_disable_virtualization_cpu; + void (*hardware_unsetup)(void); bool (*has_emulated_msr)(struct kvm *kvm, u32 index); void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); @@ -1727,6 +1727,8 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); + + const bool x2apic_icr_is_split; const unsigned long required_apicv_inhibits; bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); @@ -1806,7 +1808,7 @@ struct kvm_x86_ops { int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); void (*guest_memory_reclaimed)(struct kvm *kvm); - int (*get_msr_feature)(struct kvm_msr_entry *entry); + int (*get_feature_msr)(u32 msr, u64 *data); int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len); @@ -2060,6 +2062,8 @@ void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); +int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data); +int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data); int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data); @@ -2136,7 +2140,15 @@ int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry); + +static inline bool kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa) +{ + return __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, false); +} + void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); @@ -2254,6 +2266,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); +int kvm_cpu_get_extint(struct kvm_vcpu *v); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); @@ -2345,7 +2358,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_OUT_7E_INC_RIP | \ KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \ KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \ - KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) + KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \ + KVM_X86_QUIRK_SLOT_ZAP_ALL) /* * KVM previously used a u32 field in kvm_run to indicate the hypercall was diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a7c06a46fb76..3ae84c3b8e6d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,6 +36,20 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) +/* + * Architectural memory types that are common to MTRRs, PAT, VMX MSRs, etc. + * Most MSRs support/allow only a subset of memory types, but the values + * themselves are common across all relevant MSRs. + */ +#define X86_MEMTYPE_UC 0ull /* Uncacheable, a.k.a. Strong Uncacheable */ +#define X86_MEMTYPE_WC 1ull /* Write Combining */ +/* RESERVED 2 */ +/* RESERVED 3 */ +#define X86_MEMTYPE_WT 4ull /* Write Through */ +#define X86_MEMTYPE_WP 5ull /* Write Protected */ +#define X86_MEMTYPE_WB 6ull /* Write Back */ +#define X86_MEMTYPE_UC_MINUS 7ull /* Weak Uncacheabled (PAT only) */ + /* FRED MSRs */ #define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ #define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ @@ -365,6 +379,12 @@ #define MSR_IA32_CR_PAT 0x00000277 +#define PAT_VALUE(p0, p1, p2, p3, p4, p5, p6, p7) \ + ((X86_MEMTYPE_ ## p0) | (X86_MEMTYPE_ ## p1 << 8) | \ + (X86_MEMTYPE_ ## p2 << 16) | (X86_MEMTYPE_ ## p3 << 24) | \ + (X86_MEMTYPE_ ## p4 << 32) | (X86_MEMTYPE_ ## p5 << 40) | \ + (X86_MEMTYPE_ ## p6 << 48) | (X86_MEMTYPE_ ## p7 << 56)) + #define MSR_IA32_DEBUGCTLMSR 0x000001d9 #define MSR_IA32_LASTBRANCHFROMIP 0x000001db #define MSR_IA32_LASTBRANCHTOIP 0x000001dc @@ -1159,15 +1179,6 @@ #define MSR_IA32_VMX_VMFUNC 0x00000491 #define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 -/* VMX_BASIC bits and bitmasks */ -#define VMX_BASIC_VMCS_SIZE_SHIFT 32 -#define VMX_BASIC_TRUE_CTLS (1ULL << 55) -#define VMX_BASIC_64 0x0001000000000000LLU -#define VMX_BASIC_MEM_TYPE_SHIFT 50 -#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU -#define VMX_BASIC_MEM_TYPE_WB 6LLU -#define VMX_BASIC_INOUT 0x0040000000000000LLU - /* Resctrl MSRs: */ /* - Intel: */ #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -1185,11 +1196,6 @@ #define MSR_IA32_SMBA_BW_BASE 0xc0000280 #define MSR_IA32_EVT_CFG_BASE 0xc0000400 -/* MSR_IA32_VMX_MISC bits */ -#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) -#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) -#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F - /* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 #define MSR_VM_IGNNE 0xc0010115 diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 6536873f8fc0..d0ef2a678d66 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,8 +25,8 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 -#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) typedef void (cpu_emergency_virt_cb)(void); +#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_disable_virtualization(void); diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f0dea3750ca9..2b59b9951c90 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -516,6 +516,20 @@ struct ghcb { u32 ghcb_usage; } __packed; +struct vmcb { + struct vmcb_control_area control; + union { + struct vmcb_save_area save; + + /* + * For SEV-ES VMs, the save area in the VMCB is used only to + * save/load host state. Guest state resides in a separate + * page, the aptly named VM Save Area (VMSA), that is encrypted + * with the guest's private key. + */ + struct sev_es_save_area host_sev_es_save; + }; +} __packed; #define EXPECTED_VMCB_SAVE_AREA_SIZE 744 #define EXPECTED_GHCB_SAVE_AREA_SIZE 1032 @@ -532,6 +546,7 @@ static inline void __unused_size_checks(void) BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(offsetof(struct vmcb, save) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); /* Check offsets of reserved fields */ @@ -568,11 +583,6 @@ static inline void __unused_size_checks(void) BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0); } -struct vmcb { - struct vmcb_control_area control; - struct vmcb_save_area save; -} __packed; - #define SVM_CPUID_FUNC 0x8000000a #define SVM_SELECTOR_S_SHIFT 4 diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index d77a31039f24..f7fd4369b821 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -122,19 +122,17 @@ #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff -#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f -#define VMX_MISC_SAVE_EFER_LMA 0x00000020 -#define VMX_MISC_ACTIVITY_HLT 0x00000040 -#define VMX_MISC_ACTIVITY_WAIT_SIPI 0x00000100 -#define VMX_MISC_ZERO_LEN_INS 0x40000000 -#define VMX_MISC_MSR_LIST_MULTIPLIER 512 - /* VMFUNC functions */ #define VMFUNC_CONTROL_BIT(x) BIT((VMX_FEATURE_##x & 0x1f) - 28) #define VMX_VMFUNC_EPTP_SWITCHING VMFUNC_CONTROL_BIT(EPTP_SWITCHING) #define VMFUNC_EPTP_ENTRIES 512 +#define VMX_BASIC_32BIT_PHYS_ADDR_ONLY BIT_ULL(48) +#define VMX_BASIC_DUAL_MONITOR_TREATMENT BIT_ULL(49) +#define VMX_BASIC_INOUT BIT_ULL(54) +#define VMX_BASIC_TRUE_CTLS BIT_ULL(55) + static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic) { return vmx_basic & GENMASK_ULL(30, 0); @@ -145,9 +143,30 @@ static inline u32 vmx_basic_vmcs_size(u64 vmx_basic) return (vmx_basic & GENMASK_ULL(44, 32)) >> 32; } +static inline u32 vmx_basic_vmcs_mem_type(u64 vmx_basic) +{ + return (vmx_basic & GENMASK_ULL(53, 50)) >> 50; +} + +static inline u64 vmx_basic_encode_vmcs_info(u32 revision, u16 size, u8 memtype) +{ + return revision | ((u64)size << 32) | ((u64)memtype << 50); +} + +#define VMX_MISC_SAVE_EFER_LMA BIT_ULL(5) +#define VMX_MISC_ACTIVITY_HLT BIT_ULL(6) +#define VMX_MISC_ACTIVITY_SHUTDOWN BIT_ULL(7) +#define VMX_MISC_ACTIVITY_WAIT_SIPI BIT_ULL(8) +#define VMX_MISC_INTEL_PT BIT_ULL(14) +#define VMX_MISC_RDMSR_IN_SMM BIT_ULL(15) +#define VMX_MISC_VMXOFF_BLOCK_SMI BIT_ULL(28) +#define VMX_MISC_VMWRITE_SHADOW_RO_FIELDS BIT_ULL(29) +#define VMX_MISC_ZERO_LEN_INS BIT_ULL(30) +#define VMX_MISC_MSR_LIST_MULTIPLIER 512 + static inline int vmx_misc_preemption_timer_rate(u64 vmx_misc) { - return vmx_misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + return vmx_misc & GENMASK_ULL(4, 0); } static inline int vmx_misc_cr3_count(u64 vmx_misc) @@ -508,9 +527,10 @@ enum vmcs_field { #define VMX_EPTP_PWL_4 0x18ull #define VMX_EPTP_PWL_5 0x20ull #define VMX_EPTP_AD_ENABLE_BIT (1ull << 6) +/* The EPTP memtype is encoded in bits 2:0, i.e. doesn't need to be shifted. */ #define VMX_EPTP_MT_MASK 0x7ull -#define VMX_EPTP_MT_WB 0x6ull -#define VMX_EPTP_MT_UC 0x0ull +#define VMX_EPTP_MT_WB X86_MEMTYPE_WB +#define VMX_EPTP_MT_UC X86_MEMTYPE_UC #define VMX_EPT_READABLE_MASK 0x1ull #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index bf57a824f722..a8debbf2f702 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -439,6 +439,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) +#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 2a2fc14955cd..989d368be04f 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -55,6 +55,12 @@ #include "mtrr.h" +static_assert(X86_MEMTYPE_UC == MTRR_TYPE_UNCACHABLE); +static_assert(X86_MEMTYPE_WC == MTRR_TYPE_WRCOMB); +static_assert(X86_MEMTYPE_WT == MTRR_TYPE_WRTHROUGH); +static_assert(X86_MEMTYPE_WP == MTRR_TYPE_WRPROT); +static_assert(X86_MEMTYPE_WB == MTRR_TYPE_WRBACK); + /* arch_phys_wc_add returns an MTRR register index plus this offset. */ #define MTRR_TO_PHYS_WC_OFFSET 1000 diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2617be544480..41786b834b16 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -705,7 +705,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) | - F(AMX_COMPLEX) + F(AMX_COMPLEX) | F(AVX10) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, @@ -721,6 +721,10 @@ void kvm_set_cpu_caps(void) SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) ); + kvm_cpu_cap_init_kvm_defined(CPUID_24_0_EBX, + F(AVX10_128) | F(AVX10_256) | F(AVX10_512) + ); + kvm_cpu_cap_mask(CPUID_8000_0001_ECX, F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | @@ -949,7 +953,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) switch (function) { case 0: /* Limited to the highest leaf implemented in KVM. */ - entry->eax = min(entry->eax, 0x1fU); + entry->eax = min(entry->eax, 0x24U); break; case 1: cpuid_entry_override(entry, CPUID_1_EDX); @@ -1174,6 +1178,28 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; } break; + case 0x24: { + u8 avx10_version; + + if (!kvm_cpu_cap_has(X86_FEATURE_AVX10)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + + /* + * The AVX10 version is encoded in EBX[7:0]. Note, the version + * is guaranteed to be >=1 if AVX10 is supported. Note #2, the + * version needs to be captured before overriding EBX features! + */ + avx10_version = min_t(u8, entry->ebx & 0xff, 1); + cpuid_entry_override(entry, CPUID_24_0_EBX); + entry->ebx |= avx10_version; + + entry->eax = 0; + entry->ecx = 0; + entry->edx = 0; + break; + } case KVM_CPUID_SIGNATURE: { const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 3d7eb11d0e45..63f66c51975a 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -108,7 +108,7 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); * Read pending interrupt(from non-APIC source) * vector and intack. */ -static int kvm_cpu_get_extint(struct kvm_vcpu *v) +int kvm_cpu_get_extint(struct kvm_vcpu *v) { if (!kvm_cpu_has_extint(v)) { WARN_ON(!lapic_in_kernel(v)); @@ -131,6 +131,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) } else return kvm_pic_read_irq(v->kvm); /* PIC */ } +EXPORT_SYMBOL_GPL(kvm_cpu_get_extint); /* * Read pending interrupt vector and intack. @@ -141,9 +142,12 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) if (vector != -1) return vector; /* PIC */ - return kvm_get_apic_interrupt(v); /* APIC */ + vector = kvm_apic_has_interrupt(v); /* APIC */ + if (vector != -1) + kvm_apic_ack_interrupt(v, vector); + + return vector; } -EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5bb481aefcbc..2098dc689088 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1944,7 +1944,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; - unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; + u32 this_tsc_khz = vcpu->arch.virtual_tsc_khz; unsigned long flags; ktime_t now; @@ -2453,6 +2453,43 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); +#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13)) + +int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) +{ + if (data & X2APIC_ICR_RESERVED_BITS) + return 1; + + /* + * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but + * only AMD requires it to be zero, Intel essentially just ignores the + * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled, + * the CPU performs the reserved bits checks, i.e. the underlying CPU + * behavior will "win". Arbitrarily clear the BUSY bit, as there is no + * sane way to provide consistent behavior with respect to hardware. + */ + data &= ~APIC_ICR_BUSY; + + kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); + if (kvm_x86_ops.x2apic_icr_is_split) { + kvm_lapic_set_reg(apic, APIC_ICR, data); + kvm_lapic_set_reg(apic, APIC_ICR2, data >> 32); + } else { + kvm_lapic_set_reg64(apic, APIC_ICR, data); + } + trace_kvm_apic_write(APIC_ICR, data); + return 0; +} + +static u64 kvm_x2apic_icr_read(struct kvm_lapic *apic) +{ + if (kvm_x86_ops.x2apic_icr_is_split) + return (u64)kvm_lapic_get_reg(apic, APIC_ICR) | + (u64)kvm_lapic_get_reg(apic, APIC_ICR2) << 32; + + return kvm_lapic_get_reg64(apic, APIC_ICR); +} + /* emulate APIC access in a trap manner */ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { @@ -2470,7 +2507,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) * maybe-unecessary write, and both are in the noise anyways. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) - kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_x2apic_icr_read(apic))); else kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } @@ -2922,14 +2959,13 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) } } -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) +void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector) { - int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (vector == -1) - return -1; + if (WARN_ON_ONCE(vector < 0 || !apic)) + return; /* * We get here even with APIC virtualization enabled, if doing @@ -2957,8 +2993,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) __apic_update_ppr(apic, &ppr); } - return vector; } +EXPORT_SYMBOL_GPL(kvm_apic_ack_interrupt); static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s, bool set) @@ -2990,18 +3026,22 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, /* * In x2APIC mode, the LDR is fixed and based on the id. And - * ICR is internally a single 64-bit register, but needs to be - * split to ICR+ICR2 in userspace for backwards compatibility. + * if the ICR is _not_ split, ICR is internally a single 64-bit + * register, but needs to be split to ICR+ICR2 in userspace for + * backwards compatibility. */ - if (set) { + if (set) *ldr = kvm_apic_calc_x2apic_ldr(x2apic_id); - icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | - (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; - __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr); - } else { - icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); - __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); + if (!kvm_x86_ops.x2apic_icr_is_split) { + if (set) { + icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | + (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; + __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr); + } else { + icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); + __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); + } } } @@ -3194,22 +3234,12 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) return 0; } -int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) -{ - data &= ~APIC_ICR_BUSY; - - kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); - kvm_lapic_set_reg64(apic, APIC_ICR, data); - trace_kvm_apic_write(APIC_ICR, data); - return 0; -} - static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) { u32 low; if (reg == APIC_ICR) { - *data = kvm_lapic_get_reg64(apic, APIC_ICR); + *data = kvm_x2apic_icr_read(apic); return 0; } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 7ef8ae73e82d..1b8ef9856422 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -88,15 +88,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); +void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_events(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); -u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_recalculate_apic_map(struct kvm *kvm); void kvm_apic_set_version(struct kvm_vcpu *vcpu); void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 4341e0e28571..9dc5dd43ae7f 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -223,8 +223,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, 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); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7813d28b082f..e52f990548df 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -614,32 +614,6 @@ static u64 mmu_spte_get_lockless(u64 *sptep) return __get_spte_lockless(sptep); } -/* Returns the Accessed status of the PTE and resets it at the same time. */ -static bool mmu_spte_age(u64 *sptep) -{ - u64 spte = mmu_spte_get_lockless(sptep); - - if (!is_accessed_spte(spte)) - return false; - - if (spte_ad_enabled(spte)) { - clear_bit((ffs(shadow_accessed_mask) - 1), - (unsigned long *)sptep); - } else { - /* - * Capture the dirty status of the page, so that it doesn't get - * lost when the SPTE is marked for access tracking. - */ - if (is_writable_pte(spte)) - kvm_set_pfn_dirty(spte_to_pfn(spte)); - - spte = mark_spte_for_access_track(spte); - mmu_spte_update_no_track(sptep, spte); - } - - return true; -} - static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) { return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; @@ -938,6 +912,7 @@ static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct * pte_list_desc containing more mappings. */ +#define KVM_RMAP_MANY BIT(0) /* * Returns the number of pointers in the rmap chain, not counting the new one. @@ -950,16 +925,16 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, if (!rmap_head->val) { rmap_head->val = (unsigned long)spte; - } else if (!(rmap_head->val & 1)) { + } else if (!(rmap_head->val & KVM_RMAP_MANY)) { desc = kvm_mmu_memory_cache_alloc(cache); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; desc->spte_count = 2; desc->tail_count = 0; - rmap_head->val = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY; ++count; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); count = desc->tail_count + desc->spte_count; /* @@ -968,10 +943,10 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, */ if (desc->spte_count == PTE_LIST_EXT) { desc = kvm_mmu_memory_cache_alloc(cache); - desc->more = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc->more = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); desc->spte_count = 0; desc->tail_count = count; - rmap_head->val = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY; } desc->sptes[desc->spte_count++] = spte; } @@ -982,7 +957,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct pte_list_desc *desc, int i) { - struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); int j = head_desc->spte_count - 1; /* @@ -1011,7 +986,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, if (!head_desc->more) rmap_head->val = 0; else - rmap_head->val = (unsigned long)head_desc->more | 1; + rmap_head->val = (unsigned long)head_desc->more | KVM_RMAP_MANY; mmu_free_pte_list_desc(head_desc); } @@ -1024,13 +999,13 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte, if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm)) return; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm)) return; rmap_head->val = 0; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { @@ -1063,12 +1038,12 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm, if (!rmap_head->val) return false; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val); goto out; } - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); for (; desc; desc = next) { for (i = 0; i < desc->spte_count; i++) @@ -1088,10 +1063,10 @@ unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) if (!rmap_head->val) return 0; - else if (!(rmap_head->val & 1)) + else if (!(rmap_head->val & KVM_RMAP_MANY)) return 1; - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); return desc->tail_count + desc->spte_count; } @@ -1153,13 +1128,13 @@ static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, if (!rmap_head->val) return NULL; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { iter->desc = NULL; sptep = (u64 *)rmap_head->val; goto out; } - iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + iter->desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); iter->pos = 0; sptep = iter->desc->sptes[iter->pos]; out: @@ -1307,15 +1282,6 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, return flush; } -/** - * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages - * @kvm: kvm instance - * @slot: slot to protect - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should protect - * - * Used when we do not need to care about huge page mappings. - */ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1339,16 +1305,6 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, } } -/** - * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write - * protect the page if the D-bit isn't supported. - * @kvm: kvm instance - * @slot: slot to clear D-bit - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should clear D-bit - * - * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap. - */ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1372,24 +1328,16 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, } } -/** - * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected - * PT level pages. - * - * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to - * enable dirty logging for them. - * - * We need to care about huge page mappings: e.g. during dirty logging we may - * have such mappings. - */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { /* - * Huge pages are NOT write protected when we start dirty logging in - * initially-all-set mode; must write protect them here so that they - * are split to 4K on the first write. + * If the slot was assumed to be "initially all dirty", write-protect + * huge pages to ensure they are split to 4KiB on the first write (KVM + * dirty logs at 4KiB granularity). If eager page splitting is enabled, + * immediately try to split huge pages, e.g. so that vCPUs don't get + * saddled with the cost of splitting. * * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn * of memslot has no such restriction, so the range can cross two large @@ -1411,7 +1359,16 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, PG_LEVEL_2M); } - /* Now handle 4K PTEs. */ + /* + * (Re)Enable dirty logging for all 4KiB SPTEs that map the GFNs in + * mask. If PML is enabled and the GFN doesn't need to be write- + * protected for other reasons, e.g. shadow paging, clear the Dirty bit. + * Otherwise clear the Writable bit. + * + * Note that kvm_mmu_clear_dirty_pt_masked() is called whenever PML is + * enabled but it chooses between clearing the Dirty bit and Writeable + * bit based on the context. + */ if (kvm_x86_ops.cpu_dirty_log_size) kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else @@ -1453,16 +1410,10 @@ static bool kvm_vcpu_write_protect_gfn(struct kvm_vcpu *vcpu, u64 gfn) return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K); } -static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot) -{ - return kvm_zap_all_rmap_sptes(kvm, rmap_head); -} - static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) + const struct kvm_memory_slot *slot) { - return __kvm_zap_rmap(kvm, rmap_head, slot); + return kvm_zap_all_rmap_sptes(kvm, rmap_head); } struct slot_rmap_walk_iterator { @@ -1513,7 +1464,7 @@ static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) { while (++iterator->rmap <= iterator->end_rmap) { - iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level)); + iterator->gfn += KVM_PAGES_PER_HPAGE(iterator->level); if (iterator->rmap->val) return; @@ -1534,23 +1485,71 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) slot_rmap_walk_okay(_iter_); \ slot_rmap_walk_next(_iter_)) -typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, - int level); +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_rmaps_handler) (struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + const struct kvm_memory_slot *slot); -static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, - struct kvm_gfn_range *range, - rmap_handler_t handler) +static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, + bool can_yield, bool flush_on_yield, + bool flush) { struct slot_rmap_walk_iterator iterator; - bool ret = false; - for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - range->start, range->end - 1, &iterator) - ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn, - iterator.level); + lockdep_assert_held_write(&kvm->mmu_lock); - return ret; + for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap, slot); + + if (!can_yield) + continue; + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { + if (flush && flush_on_yield) { + kvm_flush_remote_tlbs_range(kvm, start_gfn, + iterator.gfn - start_gfn + 1); + flush = false; + } + cond_resched_rwlock_write(&kvm->mmu_lock); + } + } + + return flush; +} + +static __always_inline bool walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + bool flush_on_yield) +{ + return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, + slot->base_gfn, slot->base_gfn + slot->npages - 1, + true, flush_on_yield, false); +} + +static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + bool flush_on_yield) +{ + return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); +} + +static bool __kvm_rmap_zap_gfn_range(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t start, gfn_t end, bool can_yield, + bool flush) +{ + return __walk_slot_rmaps(kvm, slot, kvm_zap_rmap, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + start, end - 1, can_yield, true, flush); } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1558,7 +1557,9 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool flush = false; if (kvm_memslots_have_rmaps(kvm)) - flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap); + flush = __kvm_rmap_zap_gfn_range(kvm, range->slot, + range->start, range->end, + range->may_block, flush); if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); @@ -1570,31 +1571,6 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) return flush; } -static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) -{ - u64 *sptep; - struct rmap_iterator iter; - int young = 0; - - for_each_rmap_spte(rmap_head, &iter, sptep) - young |= mmu_spte_age(sptep); - - return young; -} - -static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) -{ - u64 *sptep; - struct rmap_iterator iter; - - for_each_rmap_spte(rmap_head, &iter, sptep) - if (is_accessed_spte(*sptep)) - return true; - return false; -} - #define RMAP_RECYCLE_THRESHOLD 1000 static void __rmap_add(struct kvm *kvm, @@ -1629,12 +1605,52 @@ static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot, __rmap_add(vcpu->kvm, cache, slot, spte, gfn, access); } +static bool kvm_rmap_age_gfn_range(struct kvm *kvm, + struct kvm_gfn_range *range, bool test_only) +{ + struct slot_rmap_walk_iterator iterator; + struct rmap_iterator iter; + bool young = false; + u64 *sptep; + + for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + range->start, range->end - 1, &iterator) { + for_each_rmap_spte(iterator.rmap, &iter, sptep) { + u64 spte = *sptep; + + if (!is_accessed_spte(spte)) + continue; + + if (test_only) + return true; + + if (spte_ad_enabled(spte)) { + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); + } else { + /* + * Capture the dirty status of the page, so that + * it doesn't get lost when the SPTE is marked + * for access tracking. + */ + if (is_writable_pte(spte)) + kvm_set_pfn_dirty(spte_to_pfn(spte)); + + spte = mark_spte_for_access_track(spte); + mmu_spte_update_no_track(sptep, spte); + } + young = true; + } + } + return young; +} + bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { bool young = false; if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap); + young = kvm_rmap_age_gfn_range(kvm, range, false); if (tdp_mmu_enabled) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); @@ -1647,7 +1663,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool young = false; if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap); + young = kvm_rmap_age_gfn_range(kvm, range, true); if (tdp_mmu_enabled) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); @@ -2713,36 +2729,49 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) write_unlock(&kvm->mmu_lock); } -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry) { - struct kvm_mmu_page *sp; + struct kvm *kvm = vcpu->kvm; LIST_HEAD(invalid_list); - int r; + struct kvm_mmu_page *sp; + gpa_t gpa = cr2_or_gpa; + bool r = false; + + /* + * Bail early if there aren't any write-protected shadow pages to avoid + * unnecessarily taking mmu_lock lock, e.g. if the gfn is write-tracked + * by a third party. Reading indirect_shadow_pages without holding + * mmu_lock is safe, as this is purely an optimization, i.e. a false + * positive is benign, and a false negative will simply result in KVM + * skipping the unprotect+retry path, which is also an optimization. + */ + if (!READ_ONCE(kvm->arch.indirect_shadow_pages)) + goto out; + + if (!vcpu->arch.mmu->root_role.direct) { + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); + if (gpa == INVALID_GPA) + goto out; + } - r = 0; write_lock(&kvm->mmu_lock); - for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) { - r = 1; + for_each_gfn_valid_sp_with_gptes(kvm, sp, gpa_to_gfn(gpa)) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - } + + /* + * Snapshot the result before zapping, as zapping will remove all list + * entries, i.e. checking the list later would yield a false negative. + */ + r = !list_empty(&invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); write_unlock(&kvm->mmu_lock); - return r; -} - -static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa; - int r; - - if (vcpu->arch.mmu->root_role.direct) - return 0; - - gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - +out: + if (r || always_retry) { + vcpu->arch.last_retry_eip = kvm_rip_read(vcpu); + vcpu->arch.last_retry_addr = cr2_or_gpa; + } return r; } @@ -2914,10 +2943,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, trace_kvm_mmu_set_spte(level, gfn, sptep); } - if (wrprot) { - if (write_fault) - ret = RET_PF_EMULATE; - } + if (wrprot && write_fault) + ret = RET_PF_WRITE_PROTECTED; if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); @@ -4549,7 +4576,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_RETRY; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4618,8 +4645,6 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, if (!flags) { trace_kvm_page_fault(vcpu, fault_address, error_code); - if (kvm_event_needs_reinjection(vcpu)) - kvm_mmu_unprotect_page_virt(vcpu, fault_address); r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, insn_len); } else if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) { @@ -4642,7 +4667,7 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, int r; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4719,6 +4744,7 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, switch (r) { case RET_PF_FIXED: case RET_PF_SPURIOUS: + case RET_PF_WRITE_PROTECTED: return 0; case RET_PF_EMULATE: @@ -5963,6 +5989,106 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, write_unlock(&vcpu->kvm->mmu_lock); } +static bool is_write_to_guest_page_table(u64 error_code) +{ + const u64 mask = PFERR_GUEST_PAGE_MASK | PFERR_WRITE_MASK | PFERR_PRESENT_MASK; + + return (error_code & mask) == mask; +} + +static int kvm_mmu_write_protect_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u64 error_code, int *emulation_type) +{ + bool direct = vcpu->arch.mmu->root_role.direct; + + /* + * Do not try to unprotect and retry if the vCPU re-faulted on the same + * RIP with the same address that was previously unprotected, as doing + * so will likely put the vCPU into an infinite. E.g. if the vCPU uses + * a non-page-table modifying instruction on the PDE that points to the + * instruction, then unprotecting the gfn will unmap the instruction's + * code, i.e. make it impossible for the instruction to ever complete. + */ + if (vcpu->arch.last_retry_eip == kvm_rip_read(vcpu) && + vcpu->arch.last_retry_addr == cr2_or_gpa) + return RET_PF_EMULATE; + + /* + * Reset the unprotect+retry values that guard against infinite loops. + * The values will be refreshed if KVM explicitly unprotects a gfn and + * retries, in all other cases it's safe to retry in the future even if + * the next page fault happens on the same RIP+address. + */ + vcpu->arch.last_retry_eip = 0; + vcpu->arch.last_retry_addr = 0; + + /* + * It should be impossible to reach this point with an MMIO cache hit, + * as RET_PF_WRITE_PROTECTED is returned if and only if there's a valid, + * writable memslot, and creating a memslot should invalidate the MMIO + * cache by way of changing the memslot generation. WARN and disallow + * retry if MMIO is detected, as retrying MMIO emulation is pointless + * and could put the vCPU into an infinite loop because the processor + * will keep faulting on the non-existent MMIO address. + */ + if (WARN_ON_ONCE(mmio_info_in_cache(vcpu, cr2_or_gpa, direct))) + return RET_PF_EMULATE; + + /* + * Before emulating the instruction, check to see if the access was due + * to a read-only violation while the CPU was walking non-nested NPT + * page tables, i.e. for a direct MMU, for _guest_ page tables in L1. + * If L1 is sharing (a subset of) its page tables with L2, e.g. by + * having nCR3 share lower level page tables with hCR3, then when KVM + * (L0) write-protects the nested NPTs, i.e. npt12 entries, KVM is also + * unknowingly write-protecting L1's guest page tables, which KVM isn't + * shadowing. + * + * Because the CPU (by default) walks NPT page tables using a write + * access (to ensure the CPU can do A/D updates), page walks in L1 can + * trigger write faults for the above case even when L1 isn't modifying + * PTEs. As a result, KVM will unnecessarily emulate (or at least, try + * to emulate) an excessive number of L1 instructions; because L1's MMU + * isn't shadowed by KVM, there is no need to write-protect L1's gPTEs + * and thus no need to emulate in order to guarantee forward progress. + * + * Try to unprotect the gfn, i.e. zap any shadow pages, so that L1 can + * proceed without triggering emulation. If one or more shadow pages + * was zapped, skip emulation and resume L1 to let it natively execute + * the instruction. If no shadow pages were zapped, then the write- + * fault is due to something else entirely, i.e. KVM needs to emulate, + * as resuming the guest will put it into an infinite loop. + * + * Note, this code also applies to Intel CPUs, even though it is *very* + * unlikely that an L1 will share its page tables (IA32/PAE/paging64 + * format) with L2's page tables (EPT format). + * + * For indirect MMUs, i.e. if KVM is shadowing the current MMU, try to + * unprotect the gfn and retry if an event is awaiting reinjection. If + * KVM emulates multiple instructions before completing event injection, + * the event could be delayed beyond what is architecturally allowed, + * e.g. KVM could inject an IRQ after the TPR has been raised. + */ + if (((direct && is_write_to_guest_page_table(error_code)) || + (!direct && kvm_event_needs_reinjection(vcpu))) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) + return RET_PF_RETRY; + + /* + * The gfn is write-protected, but if KVM detects its emulating an + * instruction that is unlikely to be used to modify page tables, or if + * emulation fails, KVM can try to unprotect the gfn and let the CPU + * re-execute the instruction that caused the page fault. Do not allow + * retrying an instruction from a nested guest as KVM is only explicitly + * shadowing L1's page tables, i.e. unprotecting something for L1 isn't + * going to magically fix whatever issue caused L2 to fail. + */ + if (!is_guest_mode(vcpu)) + *emulation_type |= EMULTYPE_ALLOW_RETRY_PF; + + return RET_PF_EMULATE; +} + int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { @@ -6008,6 +6134,10 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r < 0) return r; + if (r == RET_PF_WRITE_PROTECTED) + r = kvm_mmu_write_protect_fault(vcpu, cr2_or_gpa, error_code, + &emulation_type); + if (r == RET_PF_FIXED) vcpu->stat.pf_fixed++; else if (r == RET_PF_EMULATE) @@ -6018,32 +6148,6 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r != RET_PF_EMULATE) return 1; - /* - * Before emulating the instruction, check if the error code - * was due to a RO violation while translating the guest page. - * This can occur when using nested virtualization with nested - * paging in both guests. If true, we simply unprotect the page - * and resume the guest. - */ - if (vcpu->arch.mmu->root_role.direct && - (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); - return 1; - } - - /* - * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still - * optimistically try to just unprotect the page and let the processor - * re-execute the instruction that caused the page fault. Do not allow - * retrying MMIO emulation, as it's not only pointless but could also - * cause us to enter an infinite loop because the processor will keep - * faulting on the non-existent MMIO address. Retrying an instruction - * from a nested guest is also pointless and dangerous as we are only - * explicitly shadowing L1's page tables, i.e. unprotecting something - * for L1 isn't going to magically fix whatever issue cause L2 to fail. - */ - if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) - emulation_type |= EMULTYPE_ALLOW_RETRY_PF; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); @@ -6202,59 +6306,6 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, } EXPORT_SYMBOL_GPL(kvm_configure_mmu); -/* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_rmaps_handler) (struct kvm *kvm, - struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot); - -static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, - bool flush_on_yield, bool flush) -{ - struct slot_rmap_walk_iterator iterator; - - lockdep_assert_held_write(&kvm->mmu_lock); - - for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, - end_gfn, &iterator) { - if (iterator.rmap) - flush |= fn(kvm, iterator.rmap, slot); - - if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - if (flush && flush_on_yield) { - kvm_flush_remote_tlbs_range(kvm, start_gfn, - iterator.gfn - start_gfn + 1); - flush = false; - } - cond_resched_rwlock_write(&kvm->mmu_lock); - } - } - - return flush; -} - -static __always_inline bool walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - bool flush_on_yield) -{ - return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, - slot->base_gfn, slot->base_gfn + slot->npages - 1, - flush_on_yield, false); -} - -static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - bool flush_on_yield) -{ - return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); -} - static void free_mmu_pages(struct kvm_mmu *mmu) { if (!tdp_enabled && mmu->pae_root) @@ -6528,9 +6579,8 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (WARN_ON_ONCE(start >= end)) continue; - flush = __walk_slot_rmaps(kvm, memslot, __kvm_zap_rmap, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = __kvm_rmap_zap_gfn_range(kvm, memslot, start, + end, true, flush); } } @@ -6818,7 +6868,7 @@ static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm, */ for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) __walk_slot_rmaps(kvm, slot, shadow_mmu_try_split_huge_pages, - level, level, start, end - 1, true, false); + level, level, start, end - 1, true, true, false); } /* Must be called with the mmu_lock held in write-mode. */ @@ -6997,10 +7047,42 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) kvm_mmu_zap_all(kvm); } +/* + * Zapping leaf SPTEs with memslot range when a memslot is moved/deleted. + * + * Zapping non-leaf SPTEs, a.k.a. not-last SPTEs, isn't required, worst + * case scenario we'll have unused shadow pages lying around until they + * are recycled due to age or when the VM is destroyed. + */ +static void kvm_mmu_zap_memslot_leafs(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + struct kvm_gfn_range range = { + .slot = slot, + .start = slot->base_gfn, + .end = slot->base_gfn + slot->npages, + .may_block = true, + }; + + write_lock(&kvm->mmu_lock); + if (kvm_unmap_gfn_range(kvm, &range)) + kvm_flush_remote_tlbs_memslot(kvm, slot); + + write_unlock(&kvm->mmu_lock); +} + +static inline bool kvm_memslot_flush_zap_all(struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_DEFAULT_VM && + kvm_check_has_quirk(kvm, KVM_X86_QUIRK_SLOT_ZAP_ALL); +} + void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_zap_all_fast(kvm); + if (kvm_memslot_flush_zap_all(kvm)) + kvm_mmu_zap_all_fast(kvm); + else + kvm_mmu_zap_memslot_leafs(kvm, slot); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 1721d97743e9..c98827840e07 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -258,6 +258,8 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); * RET_PF_CONTINUE: So far, so good, keep handling the page fault. * RET_PF_RETRY: let CPU fault again on the address. * RET_PF_EMULATE: mmio page fault, emulate the instruction directly. + * RET_PF_WRITE_PROTECTED: the gfn is write-protected, either unprotected the + * gfn and retry, or emulate the instruction directly. * RET_PF_INVALID: the spte is invalid, let the real page fault path update it. * RET_PF_FIXED: The faulting entry has been fixed. * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU. @@ -274,6 +276,7 @@ enum { RET_PF_CONTINUE = 0, RET_PF_RETRY, RET_PF_EMULATE, + RET_PF_WRITE_PROTECTED, RET_PF_INVALID, RET_PF_FIXED, RET_PF_SPURIOUS, @@ -349,8 +352,6 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level); -void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); - void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index 195d98bc8de8..f35a830ce469 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -57,6 +57,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE); TRACE_DEFINE_ENUM(RET_PF_RETRY); TRACE_DEFINE_ENUM(RET_PF_EMULATE); +TRACE_DEFINE_ENUM(RET_PF_WRITE_PROTECTED); TRACE_DEFINE_ENUM(RET_PF_INVALID); TRACE_DEFINE_ENUM(RET_PF_FIXED); TRACE_DEFINE_ENUM(RET_PF_SPURIOUS); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 69941cebb3a8..ae7d39ff2d07 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -646,10 +646,10 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, * really care if it changes underneath us after this point). */ if (FNAME(gpte_changed)(vcpu, gw, top_level)) - goto out_gpte_changed; + return RET_PF_RETRY; if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) - goto out_gpte_changed; + return RET_PF_RETRY; /* * Load a new root and retry the faulting instruction in the extremely @@ -659,7 +659,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, */ if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) { kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu); - goto out_gpte_changed; + return RET_PF_RETRY; } for_each_shadow_entry(vcpu, fault->addr, it) { @@ -674,34 +674,38 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, sp = kvm_mmu_get_child_sp(vcpu, it.sptep, table_gfn, false, access); - if (sp != ERR_PTR(-EEXIST)) { - /* - * We must synchronize the pagetable before linking it - * because the guest doesn't need to flush tlb when - * the gpte is changed from non-present to present. - * Otherwise, the guest may use the wrong mapping. - * - * For PG_LEVEL_4K, kvm_mmu_get_page() has already - * synchronized it transiently via kvm_sync_page(). - * - * For higher level pagetable, we synchronize it via - * the slower mmu_sync_children(). If it needs to - * break, some progress has been made; return - * RET_PF_RETRY and retry on the next #PF. - * KVM_REQ_MMU_SYNC is not necessary but it - * expedites the process. - */ - if (sp->unsync_children && - mmu_sync_children(vcpu, sp, false)) - return RET_PF_RETRY; - } + /* + * Synchronize the new page before linking it, as the CPU (KVM) + * is architecturally disallowed from inserting non-present + * entries into the TLB, i.e. the guest isn't required to flush + * the TLB when changing the gPTE from non-present to present. + * + * For PG_LEVEL_4K, kvm_mmu_find_shadow_page() has already + * synchronized the page via kvm_sync_page(). + * + * For higher level pages, which cannot be unsync themselves + * but can have unsync children, synchronize via the slower + * mmu_sync_children(). If KVM needs to drop mmu_lock due to + * contention or to reschedule, instruct the caller to retry + * the #PF (mmu_sync_children() ensures forward progress will + * be made). + */ + if (sp != ERR_PTR(-EEXIST) && sp->unsync_children && + mmu_sync_children(vcpu, sp, false)) + return RET_PF_RETRY; /* - * Verify that the gpte in the page we've just write - * protected is still there. + * Verify that the gpte in the page, which is now either + * write-protected or unsync, wasn't modified between the fault + * and acquiring mmu_lock. This needs to be done even when + * reusing an existing shadow page to ensure the information + * gathered by the walker matches the information stored in the + * shadow page (which could have been modified by a different + * vCPU even if the page was already linked). Holding mmu_lock + * prevents the shadow page from changing after this point. */ if (FNAME(gpte_changed)(vcpu, gw, it.level - 1)) - goto out_gpte_changed; + return RET_PF_RETRY; if (sp != ERR_PTR(-EEXIST)) link_shadow_page(vcpu, it.sptep, sp); @@ -755,9 +759,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, FNAME(pte_prefetch)(vcpu, gw, it.sptep); return ret; - -out_gpte_changed: - return RET_PF_RETRY; } /* @@ -805,7 +806,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (page_fault_handle_page_track(vcpu, fault)) { shadow_page_table_clear_flood(vcpu, fault->addr); - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; } r = mmu_topup_memory_caches(vcpu, true); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 3c55955bcaf8..3b996c1fdaab 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1046,10 +1046,8 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, * protected, emulation is needed. If the emulation was skipped, * the vCPU would have the same fault again. */ - if (wrprot) { - if (fault->write) - ret = RET_PF_EMULATE; - } + if (wrprot && fault->write) + ret = RET_PF_WRITE_PROTECTED; /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */ if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) { diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 2f4e155080ba..0d17d6b70639 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -17,6 +17,7 @@ enum kvm_only_cpuid_leafs { CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, CPUID_7_2_EDX, + CPUID_24_0_EBX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -46,6 +47,7 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) #define X86_FEATURE_AMX_COMPLEX KVM_X86_FEATURE(CPUID_7_1_EDX, 8) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +#define X86_FEATURE_AVX10 KVM_X86_FEATURE(CPUID_7_1_EDX, 19) /* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ #define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) @@ -55,6 +57,11 @@ enum kvm_only_cpuid_leafs { #define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) #define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) +/* Intel-defined sub-features, CPUID level 0x00000024:0 (EBX) */ +#define X86_FEATURE_AVX10_128 KVM_X86_FEATURE(CPUID_24_0_EBX, 16) +#define X86_FEATURE_AVX10_256 KVM_X86_FEATURE(CPUID_24_0_EBX, 17) +#define X86_FEATURE_AVX10_512 KVM_X86_FEATURE(CPUID_24_0_EBX, 18) + /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) @@ -90,6 +97,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, + [CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX}, }; /* diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 00e3c27d2a87..85241c0c7f56 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -624,17 +624,31 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) #endif /* - * Give leave_smm() a chance to make ISA-specific changes to the vCPU - * state (e.g. enter guest mode) before loading state from the SMM - * state-save area. + * FIXME: When resuming L2 (a.k.a. guest mode), the transition to guest + * mode should happen _after_ loading state from SMRAM. However, KVM + * piggybacks the nested VM-Enter flows (which is wrong for many other + * reasons), and so nSVM/nVMX would clobber state that is loaded from + * SMRAM and from the VMCS/VMCB. */ if (kvm_x86_call(leave_smm)(vcpu, &smram)) return X86EMUL_UNHANDLEABLE; #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - return rsm_load_state_64(ctxt, &smram.smram64); + ret = rsm_load_state_64(ctxt, &smram.smram64); else #endif - return rsm_load_state_32(ctxt, &smram.smram32); + ret = rsm_load_state_32(ctxt, &smram.smram32); + + /* + * If RSM fails and triggers shutdown, architecturally the shutdown + * occurs *before* the transition to guest mode. But due to KVM's + * flawed handling of RSM to L2 (see above), the vCPU may already be + * in_guest_mode(). Force the vCPU out of guest mode before delivering + * the shutdown, so that L1 enters shutdown instead of seeing a VM-Exit + * that architecturally shouldn't be possible. + */ + if (ret != X86EMUL_CONTINUE && is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + return ret; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 6f704c1037e5..d5314cb7dff4 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1693,8 +1693,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; ret = -ENOMEM; - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL_ACCOUNT); - save = kzalloc(sizeof(*save), GFP_KERNEL_ACCOUNT); + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + save = kzalloc(sizeof(*save), GFP_KERNEL); if (!ctl || !save) goto out_free; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5ab2c92c7331..9df3e1e5ae81 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -573,7 +573,7 @@ static void __svm_write_tsc_multiplier(u64 multiplier) static __always_inline struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) { - return page_address(sd->save_area) + 0x400; + return &sd->save_area->host_sev_es_save; } static inline void kvm_cpu_svm_disable(void) @@ -592,14 +592,14 @@ static inline void kvm_cpu_svm_disable(void) } } -static void svm_emergency_disable(void) +static void svm_emergency_disable_virtualization_cpu(void) { kvm_rebooting = true; kvm_cpu_svm_disable(); } -static void svm_hardware_disable(void) +static void svm_disable_virtualization_cpu(void) { /* Make sure we clean up behind us */ if (tsc_scaling) @@ -610,7 +610,7 @@ static void svm_hardware_disable(void) amd_pmu_disable_virt(); } -static int svm_hardware_enable(void) +static int svm_enable_virtualization_cpu(void) { struct svm_cpu_data *sd; @@ -696,7 +696,7 @@ static void svm_cpu_uninit(int cpu) return; kfree(sd->sev_vmcbs); - __free_page(sd->save_area); + __free_page(__sme_pa_to_page(sd->save_area_pa)); sd->save_area_pa = 0; sd->save_area = NULL; } @@ -704,23 +704,24 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); + struct page *save_area_page; int ret = -ENOMEM; memset(sd, 0, sizeof(struct svm_cpu_data)); - sd->save_area = snp_safe_alloc_page_node(cpu_to_node(cpu), GFP_KERNEL); - if (!sd->save_area) + save_area_page = snp_safe_alloc_page_node(cpu_to_node(cpu), GFP_KERNEL); + if (!save_area_page) return ret; ret = sev_cpu_init(sd); if (ret) goto free_save_area; - sd->save_area_pa = __sme_page_pa(sd->save_area); + sd->save_area = page_address(save_area_page); + sd->save_area_pa = __sme_page_pa(save_area_page); return 0; free_save_area: - __free_page(sd->save_area); - sd->save_area = NULL; + __free_page(save_area_page); return ret; } @@ -1124,8 +1125,7 @@ static void svm_hardware_unsetup(void) for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), - get_order(IOPM_SIZE)); + __free_pages(__sme_pa_to_page(iopm_base), get_order(IOPM_SIZE)); iopm_base = 0; } @@ -1301,7 +1301,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu) if (!kvm_hlt_in_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_HLT); - control->iopm_base_pa = __sme_set(iopm_base); + control->iopm_base_pa = iopm_base; control->msrpm_base_pa = __sme_set(__pa(svm->msrpm)); control->int_ctl = V_INTR_MASKING_MASK; @@ -1503,7 +1503,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) sev_free_vcpu(vcpu); - __free_page(pfn_to_page(__sme_clr(svm->vmcb01.pa) >> PAGE_SHIFT)); + __free_page(__sme_pa_to_page(svm->vmcb01.pa)); __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } @@ -1533,7 +1533,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * TSC_AUX is always virtualized for SEV-ES guests when the feature is * available. The user return MSR support is not required in this case * because TSC_AUX is restored on #VMEXIT from the host save area - * (which has been initialized in svm_hardware_enable()). + * (which has been initialized in svm_enable_virtualization_cpu()). */ if (likely(tsc_aux_uret_slot >= 0) && (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) @@ -2825,17 +2825,17 @@ static int efer_trap(struct kvm_vcpu *vcpu) return kvm_complete_insn_gp(vcpu, ret); } -static int svm_get_msr_feature(struct kvm_msr_entry *msr) +static int svm_get_feature_msr(u32 msr, u64 *data) { - msr->data = 0; + *data = 0; - switch (msr->index) { + switch (msr) { case MSR_AMD64_DE_CFG: if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) - msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; + *data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; @@ -3144,7 +3144,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * feature is available. The user return MSR support is not * required in this case because TSC_AUX is restored on #VMEXIT * from the host save area (which has been initialized in - * svm_hardware_enable()). + * svm_enable_virtualization_cpu()). */ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) break; @@ -3191,18 +3191,21 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; case MSR_AMD64_DE_CFG: { - struct kvm_msr_entry msr_entry; + u64 supported_de_cfg; - msr_entry.index = msr->index; - if (svm_get_msr_feature(&msr_entry)) + if (svm_get_feature_msr(ecx, &supported_de_cfg)) return 1; - /* Check the supported bits */ - if (data & ~msr_entry.data) + if (data & ~supported_de_cfg) return 1; - /* Don't allow the guest to change a bit, #GP */ - if (!msr->host_initiated && (data ^ msr_entry.data)) + /* + * Don't let the guest change the host-programmed value. The + * MSR is very model specific, i.e. contains multiple bits that + * are completely unknown to KVM, and the one bit known to KVM + * is simply a reflection of hardware capabilities. + */ + if (!msr->host_initiated && data != svm->msr_decfg) return 1; svm->msr_decfg = data; @@ -4156,12 +4159,21 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; - if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && - to_svm(vcpu)->vmcb->control.exit_info_1) + switch (svm->vmcb->control.exit_code) { + case SVM_EXIT_MSR: + if (!svm->vmcb->control.exit_info_1) + break; return handle_fastpath_set_msr_irqoff(vcpu); + case SVM_EXIT_HLT: + return handle_fastpath_hlt(vcpu); + default: + break; + } return EXIT_FASTPATH_NONE; } @@ -4992,8 +5004,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_processor_compatibility = svm_check_processor_compat, .hardware_unsetup = svm_hardware_unsetup, - .hardware_enable = svm_hardware_enable, - .hardware_disable = svm_hardware_disable, + .enable_virtualization_cpu = svm_enable_virtualization_cpu, + .disable_virtualization_cpu = svm_disable_virtualization_cpu, + .emergency_disable_virtualization_cpu = svm_emergency_disable_virtualization_cpu, .has_emulated_msr = svm_has_emulated_msr, .vcpu_create = svm_vcpu_create, @@ -5011,7 +5024,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_unblocking = avic_vcpu_unblocking, .update_exception_bitmap = svm_update_exception_bitmap, - .get_msr_feature = svm_get_msr_feature, + .get_feature_msr = svm_get_feature_msr, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, @@ -5062,6 +5075,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_nmi_window = svm_enable_nmi_window, .enable_irq_window = svm_enable_irq_window, .update_cr8_intercept = svm_update_cr8_intercept, + + .x2apic_icr_is_split = true, .set_virtual_apic_mode = avic_refresh_virtual_apic_mode, .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, .apicv_post_state_restore = avic_apicv_post_state_restore, @@ -5266,7 +5281,7 @@ static __init int svm_hardware_setup(void) iopm_va = page_address(iopm_pages); memset(iopm_va, 0xff, PAGE_SIZE * (1 << order)); - iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + iopm_base = __sme_page_pa(iopm_pages); init_msrpm_offsets(); @@ -5425,8 +5440,6 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static void __svm_exit(void) { kvm_x86_vendor_exit(); - - cpu_emergency_unregister_virt_callback(svm_emergency_disable); } static int __init svm_init(void) @@ -5442,8 +5455,6 @@ static int __init svm_init(void) if (r) return r; - cpu_emergency_register_virt_callback(svm_emergency_disable); - /* * Common KVM initialization _must_ come last, after this, /dev/kvm is * exposed to userspace! diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 76107c7d0595..43fa6a16eb19 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -25,7 +25,21 @@ #include "cpuid.h" #include "kvm_cache_regs.h" -#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) +/* + * Helpers to convert to/from physical addresses for pages whose address is + * consumed directly by hardware. Even though it's a physical address, SVM + * often restricts the address to the natural width, hence 'unsigned long' + * instead of 'hpa_t'. + */ +static inline unsigned long __sme_page_pa(struct page *page) +{ + return __sme_set(page_to_pfn(page) << PAGE_SHIFT); +} + +static inline struct page *__sme_pa_to_page(unsigned long pa) +{ + return pfn_to_page(__sme_clr(pa) >> PAGE_SHIFT); +} #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 @@ -321,7 +335,7 @@ struct svm_cpu_data { u32 next_asid; u32 min_asid; - struct page *save_area; + struct vmcb *save_area; unsigned long save_area_pa; struct vmcb *current_vmcb; diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index a0c8eb37d3e1..2ed80aea3bb1 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -209,10 +209,8 @@ SYM_FUNC_START(__svm_vcpu_run) 7: vmload %_ASM_AX 8: -#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT /* Clobbers RAX, RCX, RDX. */ RESTORE_HOST_SPEC_CTRL @@ -348,10 +346,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) 2: cli -#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 41a4533f9989..cb6588238f46 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -54,9 +54,7 @@ struct nested_vmx_msrs { }; struct vmcs_config { - int size; - u32 basic_cap; - u32 revision_id; + u64 basic; u32 pin_based_exec_ctrl; u32 cpu_based_exec_ctrl; u32 cpu_based_2nd_exec_ctrl; @@ -76,7 +74,7 @@ extern struct vmx_capability vmx_capability __ro_after_init; static inline bool cpu_has_vmx_basic_inout(void) { - return (((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT); + return vmcs_config.basic & VMX_BASIC_INOUT; } static inline bool cpu_has_virtual_nmis(void) @@ -225,7 +223,7 @@ static inline bool cpu_has_vmx_vmfunc(void) static inline bool cpu_has_vmx_shadow_vmcs(void) { /* check if the cpu supports writing r/o exit information fields */ - if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + if (!(vmcs_config.misc & VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) return false; return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -367,7 +365,7 @@ static inline bool cpu_has_vmx_invvpid_global(void) static inline bool cpu_has_vmx_intel_pt(void) { - return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) && + return (vmcs_config.misc & VMX_MISC_INTEL_PT) && (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 0bf35ebe8a1b..7668e2fb8043 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -23,8 +23,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .hardware_unsetup = vmx_hardware_unsetup, - .hardware_enable = vmx_hardware_enable, - .hardware_disable = vmx_hardware_disable, + .enable_virtualization_cpu = vmx_enable_virtualization_cpu, + .disable_virtualization_cpu = vmx_disable_virtualization_cpu, + .emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu, + .has_emulated_msr = vmx_has_emulated_msr, .vm_size = sizeof(struct kvm_vmx), @@ -41,7 +43,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vcpu_put = vmx_vcpu_put, .update_exception_bitmap = vmx_update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, + .get_feature_msr = vmx_get_feature_msr, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, @@ -89,6 +91,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .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, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 2392a7ef254d..a8e7bc04d9bf 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -981,7 +981,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); goto fail; } - if (kvm_set_msr(vcpu, e.index, e.value)) { + if (kvm_set_msr_with_filter(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); @@ -1017,7 +1017,7 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, } } - if (kvm_get_msr(vcpu, msr_index, data)) { + if (kvm_get_msr_with_filter(vcpu, msr_index, data)) { pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, msr_index); return false; @@ -1112,9 +1112,9 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, /* * Emulated VMEntry does not fail here. Instead a less * accurate value will be returned by - * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() - * instead of reading the value from the vmcs02 VMExit - * MSR-store area. + * nested_vmx_get_vmexit_msr_value() by reading KVM's + * internal MSR state instead of reading the value from + * the vmcs02 VMExit MSR-store area. */ pr_warn_ratelimited( "Not enough msr entries in msr_autostore. Can't add msr %x\n", @@ -1251,21 +1251,32 @@ static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved = - /* feature (except bit 48; see below) */ - BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) | - /* reserved */ - BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56); + const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT | + VMX_BASIC_INOUT | + VMX_BASIC_TRUE_CTLS; + + const u64 reserved_bits = GENMASK_ULL(63, 56) | + GENMASK_ULL(47, 45) | + BIT_ULL(31); + u64 vmx_basic = vmcs_config.nested.basic; - if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * Except for 32BIT_PHYS_ADDR_ONLY, which is an anti-feature bit (has + * inverted polarity), the incoming value must not set feature bits or + * reserved bits that aren't allowed/supported by KVM. Fields, i.e. + * multi-bit values, are explicitly checked below. + */ + if (!is_bitwise_subset(vmx_basic, data, feature_bits | reserved_bits)) return -EINVAL; /* * KVM does not emulate a version of VMX that constrains physical * addresses of VMX structures (e.g. VMCS) to 32-bits. */ - if (data & BIT_ULL(48)) + if (data & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EINVAL; if (vmx_basic_vmcs_revision_id(vmx_basic) != @@ -1334,16 +1345,29 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved_bits = - /* feature */ - BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) | - BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) | - /* reserved */ - GENMASK_ULL(13, 9) | BIT_ULL(31); + const u64 feature_bits = VMX_MISC_SAVE_EFER_LMA | + VMX_MISC_ACTIVITY_HLT | + VMX_MISC_ACTIVITY_SHUTDOWN | + VMX_MISC_ACTIVITY_WAIT_SIPI | + VMX_MISC_INTEL_PT | + VMX_MISC_RDMSR_IN_SMM | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMXOFF_BLOCK_SMI | + VMX_MISC_ZERO_LEN_INS; + + const u64 reserved_bits = BIT_ULL(31) | GENMASK_ULL(13, 9); + u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low, vmcs_config.nested.misc_high); - if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * The incoming value must not set feature bits or reserved bits that + * aren't allowed/supported by KVM. Fields, i.e. multi-bit values, are + * explicitly checked below. + */ + if (!is_bitwise_subset(vmx_misc, data, feature_bits | reserved_bits)) return -EINVAL; if ((vmx->nested.msrs.pinbased_ctls_high & @@ -2317,10 +2341,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 /* Posted interrupts setting is only taken from vmcs12. */ vmx->nested.pi_pending = false; - if (nested_cpu_has_posted_intr(vmcs12)) + if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; - else + } else { + vmx->nested.posted_intr_nv = -1; exec_control &= ~PIN_BASED_POSTED_INTR; + } pin_controls_set(vmx, exec_control); /* @@ -2470,6 +2496,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { + vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector); @@ -2507,7 +2534,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - vmx->segment_cache.bitmask = 0; + vmx_segment_cache_clear(vmx); } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & @@ -4284,11 +4311,52 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) } if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { + int irq; + if (block_nested_events) return -EBUSY; if (!nested_exit_on_intr(vcpu)) goto no_vmexit; - nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + + if (!nested_exit_intr_ack_set(vcpu)) { + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + return 0; + } + + irq = kvm_cpu_get_extint(vcpu); + if (irq != -1) { + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + return 0; + } + + irq = kvm_apic_has_interrupt(vcpu); + if (WARN_ON_ONCE(irq < 0)) + goto no_vmexit; + + /* + * If the IRQ is L2's PI notification vector, process posted + * interrupts for L2 instead of injecting VM-Exit, as the + * detection/morphing architecturally occurs when the IRQ is + * delivered to the CPU. Note, only interrupts that are routed + * through the local APIC trigger posted interrupt processing, + * and enabling posted interrupts requires ACK-on-exit. + */ + if (irq == vmx->nested.posted_intr_nv) { + vmx->nested.pi_pending = true; + kvm_apic_clear_irr(vcpu, irq); + goto no_vmexit; + } + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + + /* + * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must + * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI + * if APICv is active. + */ + kvm_apic_ack_interrupt(vcpu, irq); return 0; } @@ -4806,7 +4874,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) goto vmabort; } - if (kvm_set_msr(vcpu, h.index, h.value)) { + if (kvm_set_msr_with_filter(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); @@ -4969,14 +5037,6 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - nested_exit_intr_ack_set(vcpu)) { - int irq = kvm_cpu_get_interrupt(vcpu); - WARN_ON(irq < 0); - vmcs12->vm_exit_intr_info = irq | - INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; - } - if (vm_exit_reason != -1) trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, @@ -7051,7 +7111,7 @@ static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, { msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; @@ -7066,12 +7126,10 @@ static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) * guest, and the VMCS structure we give it - not about the * VMX support of the underlying hardware. */ - msrs->basic = - VMCS12_REVISION | - VMX_BASIC_TRUE_CTLS | - ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | - (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); + msrs->basic = vmx_basic_encode_vmcs_info(VMCS12_REVISION, VMCS12_SIZE, + X86_MEMTYPE_WB); + msrs->basic |= VMX_BASIC_TRUE_CTLS; if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; } diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index cce4e2aa30fb..2c296b6abb8c 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -39,11 +39,17 @@ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_vmcs12; } static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_shadow_vmcs12; } @@ -109,7 +115,7 @@ static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu) static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.msrs.misc_low & - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 6fef01e0536e..a3c3d2a51f47 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -274,7 +274,7 @@ static int handle_encls_ecreate(struct kvm_vcpu *vcpu) * simultaneously set SGX_ATTR_PROVISIONKEY to bypass the check to * enforce restriction of access to the PROVISIONKEY. */ - contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL_ACCOUNT); + contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL); if (!contents) return -ENOMEM; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 733a0c45d1a6..1a4438358c5e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -525,10 +525,6 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; -static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) -{ - vmx->segment_cache.bitmask = 0; -} static unsigned long host_idt_base; @@ -755,7 +751,7 @@ fault: return -EIO; } -static void vmx_emergency_disable(void) +void vmx_emergency_disable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; @@ -1998,15 +1994,15 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, return !(msr->data & ~valid_bits); } -int vmx_get_msr_feature(struct kvm_msr_entry *msr) +int vmx_get_feature_msr(u32 msr, u64 *data) { - switch (msr->index) { + switch (msr) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; - return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); + return vmx_get_vmx_msr(&vmcs_config.nested, msr, data); default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } } @@ -2605,13 +2601,13 @@ static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) static int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { - u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; + u64 basic_msr; u64 misc_msr; int i; @@ -2734,29 +2730,29 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, _vmexit_control &= ~x_ctrl; } - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); + rdmsrl(MSR_IA32_VMX_BASIC, basic_msr); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) + if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE) return -EIO; #ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) + /* + * KVM expects to be able to shove all legal physical addresses into + * VMCS fields for 64-bit kernels, and per the SDM, "This bit is always + * 0 for processors that support Intel 64 architecture". + */ + if (basic_msr & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) + if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB) return -EIO; rdmsrl(MSR_IA32_VMX_MISC, misc_msr); - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - - vmcs_conf->revision_id = vmx_msr_low; - + vmcs_conf->basic = basic_msr; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; @@ -2844,7 +2840,7 @@ fault: return -EFAULT; } -int vmx_hardware_enable(void) +int vmx_enable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2881,7 +2877,7 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } -void vmx_hardware_disable(void) +void vmx_disable_virtualization_cpu(void) { vmclear_local_loaded_vmcss(); @@ -2903,13 +2899,13 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) if (!pages) return NULL; vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); + memset(vmcs, 0, vmx_basic_vmcs_size(vmcs_config.basic)); /* KVM supports Enlightened VMCS v1 only */ if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); if (shadow) vmcs->hdr.shadow_vmcs = 1; @@ -3002,7 +2998,7 @@ static __init int alloc_kvm_area(void) * physical CPU. */ if (kvm_is_using_evmcs()) - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); per_cpu(vmxarea, cpu) = vmcs; } @@ -4219,6 +4215,13 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated + * and freed, and must not be accessed outside of vcpu->mutex. The + * vCPU's cached PI NV is valid if and only if posted interrupts + * enabled in its vmcs12, i.e. checking the vector also checks that + * L1 has enabled posted interrupts for L2. + */ if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* @@ -5804,8 +5807,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK) ? PFERR_PRESENT_MASK : 0; - error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? - PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; + if (error_code & EPT_VIOLATION_GVA_IS_VALID) + error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ? + PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; /* * Check that the GPA doesn't exceed physical memory limits, as that is @@ -7265,6 +7269,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); + case EXIT_REASON_HLT: + return handle_fastpath_hlt(vcpu); default: return EXIT_FASTPATH_NONE; } @@ -7965,6 +7971,7 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); kvm_cpu_cap_clear(X86_FEATURE_SGX1); kvm_cpu_cap_clear(X86_FEATURE_SGX2); + kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA); } if (vmx_umip_emulated()) @@ -8515,7 +8522,7 @@ __init int vmx_hardware_setup(void) u64 use_timer_freq = 5000ULL * 1000 * 1000; cpu_preemption_timer_multi = - vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmx_misc_preemption_timer_rate(vmcs_config.misc); if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8582,8 +8589,6 @@ static void __vmx_exit(void) { allow_smaller_maxphyaddr = false; - cpu_emergency_unregister_virt_callback(vmx_emergency_disable); - vmx_cleanup_l1d_flush(); } @@ -8630,8 +8635,6 @@ static int __init vmx_init(void) pi_init_cpu(cpu); } - cpu_emergency_register_virt_callback(vmx_emergency_disable); - vmx_check_vmcs12_offsets(); /* diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 42498fa63abb..2325f773a20b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -17,10 +17,6 @@ #include "run_flags.h" #include "../mmu.h" -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -#define MSR_TYPE_RW 3 - #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) #ifdef CONFIG_X86_64 @@ -756,4 +752,9 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } +static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +{ + vmx->segment_cache.bitmask = 0; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h index eb48153bfd73..bba24ed99ee6 100644 --- a/arch/x86/kvm/vmx/vmx_onhyperv.h +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -104,6 +104,14 @@ static inline void evmcs_load(u64 phys_addr) struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(smp_processor_id()); + /* + * When enabling eVMCS, KVM verifies that every CPU has a valid hv_vp_assist_page() + * and aborts enabling the feature otherwise. CPU onlining path is also checked in + * vmx_hardware_enable(). + */ + if (KVM_BUG_ON(!vp_ap, kvm_get_running_vcpu()->kvm)) + return; + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) vp_ap->nested_control.features.directhypercall = 1; vp_ap->current_nested_vmcs = phys_addr; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 8060e5fc6dbd..93e020dc88f6 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -47,7 +47,7 @@ static __always_inline void vmcs_check16(unsigned long field) BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, "16-bit accessor invalid for 64-bit high field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, - "16-bit accessor invalid for 32-bit high field"); + "16-bit accessor invalid for 32-bit field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, "16-bit accessor invalid for natural width field"); } diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index ce3221cd1d01..a55981c5216e 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -13,8 +13,9 @@ 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_enable_virtualization_cpu(void); +void vmx_disable_virtualization_cpu(void); +void vmx_emergency_disable_virtualization_cpu(void); int vmx_vm_init(struct kvm *kvm); void vmx_vm_destroy(struct kvm *kvm); int vmx_vcpu_precreate(struct kvm *kvm); @@ -56,7 +57,7 @@ bool vmx_has_emulated_msr(struct kvm *kvm, u32 index); void vmx_msr_filter_changed(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_feature_msr(u32 msr, u64 *data); 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); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c983c8e434b8..83fe0a78146f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -305,24 +305,237 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { static struct kmem_cache *x86_emulator_cache; /* - * When called, it means the previous get/set msr reached an invalid msr. - * Return true if we want to ignore/silent this failed msr access. + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track + * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, + * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that + * require host support, i.e. should be probed via RDMSR. emulated_msrs holds + * MSRs that KVM emulates without strictly requiring host support. + * msr_based_features holds MSRs that enumerate features, i.e. are effectively + * CPUID leafs. Note, msr_based_features isn't mutually exclusive with + * msrs_to_save and emulated_msrs. */ -static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) + +static const u32 msrs_to_save_base[] = { + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_STAR, +#ifdef CONFIG_X86_64 + MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, +#endif + MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, + MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, + MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, + MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, + MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, + MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, + MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, + MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, + MSR_IA32_UMWAIT_CONTROL, + + MSR_IA32_XFD, MSR_IA32_XFD_ERR, +}; + +static const u32 msrs_to_save_pmu[] = { + MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, + MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, + MSR_CORE_PERF_GLOBAL_CTRL, + MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, + + /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ + MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, + MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, + MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, + MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, + MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, + MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, + MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, + MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + + /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + + MSR_AMD64_PERF_CNTR_GLOBAL_CTL, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, +}; + +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; +static unsigned num_msrs_to_save; + +static const u32 emulated_msrs_all[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, + HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, + HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, + HV_X64_MSR_RESET, + HV_X64_MSR_VP_INDEX, + HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_SCONTROL, + HV_X64_MSR_STIMER0_CONFIG, + HV_X64_MSR_VP_ASSIST_PAGE, + HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, + HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, + HV_X64_MSR_SYNDBG_OPTIONS, + HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, + HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, + HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif + + MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, + + MSR_IA32_TSC_ADJUST, + MSR_IA32_TSC_DEADLINE, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, + MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, + MSR_IA32_MCG_EXT_CTL, + MSR_IA32_SMBASE, + MSR_SMI_COUNT, + MSR_PLATFORM_INFO, + MSR_MISC_FEATURES_ENABLES, + MSR_AMD64_VIRT_SPEC_CTRL, + MSR_AMD64_TSC_RATIO, + MSR_IA32_POWER_CTL, + MSR_IA32_UCODE_REV, + + /* + * KVM always supports the "true" VMX control MSRs, even if the host + * does not. The VMX MSRs as a whole are considered "emulated" as KVM + * doesn't strictly require them to exist in the host (ignoring that + * KVM would refuse to load in the first place if the core set of MSRs + * aren't supported). + */ + MSR_IA32_VMX_BASIC, + MSR_IA32_VMX_TRUE_PINBASED_CTLS, + MSR_IA32_VMX_TRUE_PROCBASED_CTLS, + MSR_IA32_VMX_TRUE_EXIT_CTLS, + MSR_IA32_VMX_TRUE_ENTRY_CTLS, + MSR_IA32_VMX_MISC, + MSR_IA32_VMX_CR0_FIXED0, + MSR_IA32_VMX_CR4_FIXED0, + MSR_IA32_VMX_VMCS_ENUM, + MSR_IA32_VMX_PROCBASED_CTLS2, + MSR_IA32_VMX_EPT_VPID_CAP, + MSR_IA32_VMX_VMFUNC, + + MSR_K7_HWCR, + MSR_KVM_POLL_CONTROL, +}; + +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; +static unsigned num_emulated_msrs; + +/* + * List of MSRs that control the existence of MSR-based features, i.e. MSRs + * that are effectively CPUID leafs. VMX MSRs are also included in the set of + * feature MSRs, but are handled separately to allow expedited lookups. + */ +static const u32 msr_based_features_all_except_vmx[] = { + MSR_AMD64_DE_CFG, + MSR_IA32_UCODE_REV, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, +}; + +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; +static unsigned int num_msr_based_features; + +/* + * All feature MSRs except uCode revID, which tracks the currently loaded uCode + * patch, are immutable once the vCPU model is defined. + */ +static bool kvm_is_immutable_feature_msr(u32 msr) { - const char *op = write ? "wrmsr" : "rdmsr"; + int i; - if (ignore_msrs) { - if (report_ignored_msrs) - kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", - op, msr, data); - /* Mask the error */ + if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) return true; - } else { + + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { + if (msr == msr_based_features_all_except_vmx[i]) + return msr != MSR_IA32_UCODE_REV; + } + + return false; +} + +static bool kvm_is_advertised_msr(u32 msr_index) +{ + unsigned int i; + + for (i = 0; i < num_msrs_to_save; i++) { + if (msrs_to_save[i] == msr_index) + return true; + } + + for (i = 0; i < num_emulated_msrs; i++) { + if (emulated_msrs[i] == msr_index) + return true; + } + + return false; +} + +typedef int (*msr_access_t)(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated); + +static __always_inline int kvm_do_msr_access(struct kvm_vcpu *vcpu, u32 msr, + u64 *data, bool host_initiated, + enum kvm_msr_access rw, + msr_access_t msr_access_fn) +{ + const char *op = rw == MSR_TYPE_W ? "wrmsr" : "rdmsr"; + int ret; + + BUILD_BUG_ON(rw != MSR_TYPE_R && rw != MSR_TYPE_W); + + /* + * Zero the data on read failures to avoid leaking stack data to the + * guest and/or userspace, e.g. if the failure is ignored below. + */ + ret = msr_access_fn(vcpu, msr, data, host_initiated); + if (ret && rw == MSR_TYPE_R) + *data = 0; + + if (ret != KVM_MSR_RET_UNSUPPORTED) + return ret; + + /* + * Userspace is allowed to read MSRs, and write '0' to MSRs, that KVM + * advertises to userspace, even if an MSR isn't fully supported. + * Simply check that @data is '0', which covers both the write '0' case + * and all reads (in which case @data is zeroed on failure; see above). + */ + if (host_initiated && !*data && kvm_is_advertised_msr(msr)) + return 0; + + if (!ignore_msrs) { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", - op, msr, data); - return false; + op, msr, *data); + return ret; } + + if (report_ignored_msrs) + kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, *data); + + return 0; } static struct kmem_cache *kvm_alloc_emulator_cache(void) @@ -355,7 +568,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn) /* * Disabling irqs at this point since the following code could be - * interrupted and executed through kvm_arch_hardware_disable() + * interrupted and executed through kvm_arch_disable_virtualization_cpu() */ local_irq_save(flags); if (msrs->registered) { @@ -413,8 +626,7 @@ EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); u64 value; int i; @@ -621,12 +833,6 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } -/* Forcibly leave the nested mode in cases like a vCPU reset */ -static void kvm_leave_nested(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops.nested_ops->leave_nested(vcpu); -} - static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -1412,178 +1618,6 @@ int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); /* - * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track - * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, - * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that - * require host support, i.e. should be probed via RDMSR. emulated_msrs holds - * MSRs that KVM emulates without strictly requiring host support. - * msr_based_features holds MSRs that enumerate features, i.e. are effectively - * CPUID leafs. Note, msr_based_features isn't mutually exclusive with - * msrs_to_save and emulated_msrs. - */ - -static const u32 msrs_to_save_base[] = { - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_STAR, -#ifdef CONFIG_X86_64 - MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, -#endif - MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, - MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, - MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, - MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, - MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, - MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, - MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, - MSR_IA32_UMWAIT_CONTROL, - - MSR_IA32_XFD, MSR_IA32_XFD_ERR, -}; - -static const u32 msrs_to_save_pmu[] = { - MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, - MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, - MSR_CORE_PERF_GLOBAL_CTRL, - MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, - - /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ - MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, - MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, - MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, - MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, - MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, - MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, - MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, - MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, - - MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, - MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, - - /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ - MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, - MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, - MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, - MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, - - MSR_AMD64_PERF_CNTR_GLOBAL_CTL, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, -}; - -static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + - ARRAY_SIZE(msrs_to_save_pmu)]; -static unsigned num_msrs_to_save; - -static const u32 emulated_msrs_all[] = { - MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, - -#ifdef CONFIG_KVM_HYPERV - HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, - HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, - HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, - HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, - HV_X64_MSR_RESET, - HV_X64_MSR_VP_INDEX, - HV_X64_MSR_VP_RUNTIME, - HV_X64_MSR_SCONTROL, - HV_X64_MSR_STIMER0_CONFIG, - HV_X64_MSR_VP_ASSIST_PAGE, - HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, - HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, - HV_X64_MSR_SYNDBG_OPTIONS, - HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, - HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, - HV_X64_MSR_SYNDBG_PENDING_BUFFER, -#endif - - MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, - - MSR_IA32_TSC_ADJUST, - MSR_IA32_TSC_DEADLINE, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, - MSR_IA32_MISC_ENABLE, - MSR_IA32_MCG_STATUS, - MSR_IA32_MCG_CTL, - MSR_IA32_MCG_EXT_CTL, - MSR_IA32_SMBASE, - MSR_SMI_COUNT, - MSR_PLATFORM_INFO, - MSR_MISC_FEATURES_ENABLES, - MSR_AMD64_VIRT_SPEC_CTRL, - MSR_AMD64_TSC_RATIO, - MSR_IA32_POWER_CTL, - MSR_IA32_UCODE_REV, - - /* - * KVM always supports the "true" VMX control MSRs, even if the host - * does not. The VMX MSRs as a whole are considered "emulated" as KVM - * doesn't strictly require them to exist in the host (ignoring that - * KVM would refuse to load in the first place if the core set of MSRs - * aren't supported). - */ - MSR_IA32_VMX_BASIC, - MSR_IA32_VMX_TRUE_PINBASED_CTLS, - MSR_IA32_VMX_TRUE_PROCBASED_CTLS, - MSR_IA32_VMX_TRUE_EXIT_CTLS, - MSR_IA32_VMX_TRUE_ENTRY_CTLS, - MSR_IA32_VMX_MISC, - MSR_IA32_VMX_CR0_FIXED0, - MSR_IA32_VMX_CR4_FIXED0, - MSR_IA32_VMX_VMCS_ENUM, - MSR_IA32_VMX_PROCBASED_CTLS2, - MSR_IA32_VMX_EPT_VPID_CAP, - MSR_IA32_VMX_VMFUNC, - - MSR_K7_HWCR, - MSR_KVM_POLL_CONTROL, -}; - -static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; -static unsigned num_emulated_msrs; - -/* - * List of MSRs that control the existence of MSR-based features, i.e. MSRs - * that are effectively CPUID leafs. VMX MSRs are also included in the set of - * feature MSRs, but are handled separately to allow expedited lookups. - */ -static const u32 msr_based_features_all_except_vmx[] = { - MSR_AMD64_DE_CFG, - MSR_IA32_UCODE_REV, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, -}; - -static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + - (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; -static unsigned int num_msr_based_features; - -/* - * All feature MSRs except uCode revID, which tracks the currently loaded uCode - * patch, are immutable once the vCPU model is defined. - */ -static bool kvm_is_immutable_feature_msr(u32 msr) -{ - int i; - - if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) - return true; - - for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { - if (msr == msr_based_features_all_except_vmx[i]) - return msr != MSR_IA32_UCODE_REV; - } - - return false; -} - -/* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM * does not yet virtualize. These include: * 10 - MISC_PACKAGE_CTRLS @@ -1660,40 +1694,31 @@ static u64 kvm_get_arch_capabilities(void) return data; } -static int kvm_get_msr_feature(struct kvm_msr_entry *msr) +static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { - switch (msr->index) { + WARN_ON_ONCE(!host_initiated); + + switch (index) { case MSR_IA32_ARCH_CAPABILITIES: - msr->data = kvm_get_arch_capabilities(); + *data = kvm_get_arch_capabilities(); break; case MSR_IA32_PERF_CAPABILITIES: - msr->data = kvm_caps.supported_perf_cap; + *data = kvm_caps.supported_perf_cap; break; case MSR_IA32_UCODE_REV: - rdmsrl_safe(msr->index, &msr->data); + rdmsrl_safe(index, data); break; default: - return kvm_x86_call(get_msr_feature)(msr); + return kvm_x86_call(get_feature_msr)(index, data); } return 0; } -static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +static int do_get_feature_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { - struct kvm_msr_entry msr; - int r; - - /* Unconditionally clear the output for simplicity */ - msr.data = 0; - msr.index = index; - r = kvm_get_msr_feature(&msr); - - if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false)) - r = 0; - - *data = msr.data; - - return r; + return kvm_do_msr_access(vcpu, index, data, true, MSR_TYPE_R, + kvm_get_feature_msr); } static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) @@ -1880,16 +1905,17 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, return kvm_x86_call(set_msr)(vcpu, &msr); } +static int _kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) +{ + return __kvm_set_msr(vcpu, index, *data, host_initiated); +} + static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { - int ret = __kvm_set_msr(vcpu, index, data, host_initiated); - - if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(index, data, true)) - ret = 0; - - return ret; + return kvm_do_msr_access(vcpu, index, &data, host_initiated, MSR_TYPE_W, + _kvm_set_msr); } /* @@ -1928,31 +1954,25 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { - int ret = __kvm_get_msr(vcpu, index, data, host_initiated); - - if (ret == KVM_MSR_RET_INVALID) { - /* Unconditionally clear *data for simplicity */ - *data = 0; - if (kvm_msr_ignored_check(index, 0, false)) - ret = 0; - } - - return ret; + return kvm_do_msr_access(vcpu, index, data, host_initiated, MSR_TYPE_R, + __kvm_get_msr); } -static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) +int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; return kvm_get_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_GPL(kvm_get_msr_with_filter); -static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) +int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) return KVM_MSR_RET_FILTERED; return kvm_set_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_GPL(kvm_set_msr_with_filter); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { @@ -1999,7 +2019,7 @@ static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) static u64 kvm_msr_reason(int r) { switch (r) { - case KVM_MSR_RET_INVALID: + case KVM_MSR_RET_UNSUPPORTED: return KVM_MSR_EXIT_REASON_UNKNOWN; case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; @@ -2162,31 +2182,34 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); u64 data; - fastpath_t ret = EXIT_FASTPATH_NONE; + fastpath_t ret; + bool handled; kvm_vcpu_srcu_read_lock(vcpu); switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_EXIT_HANDLED; - } + handled = !handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); break; case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_tscdeadline(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_REENTER_GUEST; - } + handled = !handle_fastpath_set_tscdeadline(vcpu, data); break; default: + handled = false; break; } - if (ret != EXIT_FASTPATH_NONE) + if (handled) { + if (!kvm_skip_emulated_instruction(vcpu)) + ret = EXIT_FASTPATH_EXIT_USERSPACE; + else + ret = EXIT_FASTPATH_REENTER_GUEST; trace_kvm_msr_write(msr, data); + } else { + ret = EXIT_FASTPATH_NONE; + } kvm_vcpu_srcu_read_unlock(vcpu); @@ -3746,18 +3769,6 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } -static bool kvm_is_msr_to_save(u32 msr_index) -{ - unsigned int i; - - for (i = 0; i < num_msrs_to_save; i++) { - if (msrs_to_save[i] == msr_index) - return true; - } - - return false; -} - int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u32 msr = msr_info->index; @@ -4139,15 +4150,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - /* - * Userspace is allowed to write '0' to MSRs that KVM reports - * as to-be-saved, even if an MSRs isn't fully supported. - */ - if (msr_info->host_initiated && !data && - kvm_is_msr_to_save(msr)) - break; - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } @@ -4498,17 +4501,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); - /* - * Userspace is allowed to read MSRs that KVM reports as - * to-be-saved, even if an MSR isn't fully supported. - */ - if (msr_info->host_initiated && - kvm_is_msr_to_save(msr_info->index)) { - msr_info->data = 0; - break; - } - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } @@ -4946,7 +4939,7 @@ long kvm_arch_dev_ioctl(struct file *filp, break; } case KVM_GET_MSRS: - r = msr_io(NULL, argp, do_get_msr_feature, 1); + r = msr_io(NULL, argp, do_get_feature_msr, 1); break; #ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: @@ -7383,11 +7376,9 @@ out: static void kvm_probe_feature_msr(u32 msr_index) { - struct kvm_msr_entry msr = { - .index = msr_index, - }; + u64 data; - if (kvm_get_msr_feature(&msr)) + if (kvm_get_feature_msr(NULL, msr_index, &data, true)) return; msr_based_features[num_msr_based_features++] = msr_index; @@ -8865,60 +8856,13 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - int emulation_type) +static bool kvm_unprotect_and_retry_on_failure(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa, + int emulation_type) { - gpa_t gpa = cr2_or_gpa; - kvm_pfn_t pfn; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (!vcpu->arch.mmu->root_role.direct) { - /* - * Write permission should be allowed since only - * write access need to be emulated. - */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - /* - * If the mapping is invalid in guest, let cpu retry - * it to generate fault. - */ - if (gpa == INVALID_GPA) - return true; - } - - /* - * Do not retry the unhandleable instruction if it faults on the - * readonly host memory, otherwise it will goto a infinite loop: - * retry instruction -> write #PF -> emulation fail -> retry - * instruction -> ... - */ - pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); - - /* - * If the instruction failed on the error pfn, it can not be fixed, - * report the error to userspace. - */ - if (is_error_noslot_pfn(pfn)) - return false; - - kvm_release_pfn_clean(pfn); - - /* - * 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. - */ - if (vcpu->kvm->arch.indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - /* * 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 @@ -8929,54 +8873,24 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * 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); -} - -static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - gpa_t cr2_or_gpa, int emulation_type) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; - - last_retry_eip = vcpu->arch.last_retry_eip; - last_retry_addr = vcpu->arch.last_retry_addr; + if (emulation_type & EMULTYPE_WRITE_PF_TO_SP) + return false; /* - * If the emulation is caused by #PF and it is non-page_table - * writing instruction, it means the VM-EXIT is caused by shadow - * page protected, we can zap the shadow page and retry this - * instruction directly. - * - * Note: if the guest uses a non-page-table modifying instruction - * on the PDE that points to the instruction, then we will unmap - * the instruction and go to an infinite loop. So, we cache the - * last retried eip and the last fault address, if we meet the eip - * and the address again, we can break out of the potential infinite - * loop. + * 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. */ - vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) - return false; - - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (x86_page_table_writing_insn(ctxt)) - return false; - - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) - return false; - - vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2_or_gpa; - - if (!vcpu->arch.mmu->root_role.direct) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, true); + /* + * Retry even if _this_ vCPU didn't unprotect the gfn, as it's possible + * all SPTEs were already zapped by a different task. The alternative + * is to report the error to userspace and likely terminate the guest, + * and the last_retry_{eip,addr} checks will prevent retrying the page + * fault indefinitely, i.e. there's nothing to lose by retrying. + */ return true; } @@ -9176,6 +9090,11 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF)))) + emulation_type &= ~EMULTYPE_ALLOW_RETRY_PF; + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); if (r != X86EMUL_CONTINUE) { if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) @@ -9206,8 +9125,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - if (reexecute_instruction(vcpu, cr2_or_gpa, - emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; if (ctxt->have_exception && @@ -9254,7 +9173,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return 1; } - if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) + /* + * If emulation was caused by a write-protection #PF on a non-page_table + * writing instruction, try to unprotect the gfn, i.e. zap shadow pages, + * and retry the instruction, as the vCPU is likely no longer using the + * gfn as a page table. + */ + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + !x86_page_table_writing_insn(ctxt) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) return 1; /* this is needed for vmware backdoor interface to work since it @@ -9285,7 +9212,8 @@ restart: return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); @@ -9753,7 +9681,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) guard(mutex)(&vendor_module_lock); - if (kvm_x86_ops.hardware_enable) { + if (kvm_x86_ops.enable_virtualization_cpu) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } @@ -9880,7 +9808,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return 0; out_unwind_ops: - kvm_x86_ops.hardware_enable = NULL; + kvm_x86_ops.enable_virtualization_cpu = NULL; kvm_x86_call(hardware_unsetup)(); out_mmu_exit: kvm_mmu_vendor_module_exit(); @@ -9921,56 +9849,11 @@ void kvm_x86_vendor_exit(void) WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif mutex_lock(&vendor_module_lock); - kvm_x86_ops.hardware_enable = NULL; + kvm_x86_ops.enable_virtualization_cpu = NULL; mutex_unlock(&vendor_module_lock); } EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); -static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) -{ - /* - * The vCPU has halted, e.g. executed HLT. Update the run state if the - * local APIC is in-kernel, the run loop will detect the non-runnable - * state and halt the vCPU. Exit to userspace if the local APIC is - * managed by userspace, in which case userspace is responsible for - * handling wake events. - */ - ++vcpu->stat.halt_exits; - if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = state; - return 1; - } else { - vcpu->run->exit_reason = reason; - return 0; - } -} - -int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) -{ - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); - -int kvm_emulate_halt(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - /* - * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ - return kvm_emulate_halt_noskip(vcpu) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt); - -int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, - KVM_EXIT_AP_RESET_HOLD) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); - #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -11207,6 +11090,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); + if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) + return 0; + r = kvm_x86_call(handle_exit)(vcpu, exit_fastpath); return r; @@ -11220,6 +11106,67 @@ out: return r; } +static bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + +static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_pending_init_or_sipi(vcpu) && + kvm_apic_init_sipi_allowed(vcpu)) + return true; + + if (vcpu->arch.pv.pv_unhalted) + return true; + + if (kvm_is_exception_pending(vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + (vcpu->arch.nmi_pending && + kvm_x86_call(nmi_allowed)(vcpu, false))) + return true; + +#ifdef CONFIG_KVM_SMM + if (kvm_test_request(KVM_REQ_SMI, vcpu) || + (vcpu->arch.smi_pending && + kvm_x86_call(smi_allowed)(vcpu, false))) + return true; +#endif + + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) + return true; + + if (kvm_hv_has_stimer_pending(vcpu)) + return true; + + if (is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu, false)) + return true; + + if (kvm_xen_has_pending_events(vcpu)) + return true; + + return false; +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); +} + /* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm_vcpu *vcpu) { @@ -11291,12 +11238,6 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) return 1; } -static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) -{ - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted); -} - /* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { @@ -11348,6 +11289,98 @@ static int vcpu_run(struct kvm_vcpu *vcpu) return r; } +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) +{ + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ + ++vcpu->stat.halt_exits; + if (lapic_in_kernel(vcpu)) { + if (kvm_vcpu_has_events(vcpu)) + vcpu->arch.pv.pv_unhalted = false; + else + vcpu->arch.mp_state = state; + return 1; + } else { + vcpu->run->exit_reason = reason; + return 0; + } +} + +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) +{ + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + /* + * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered + * KVM_EXIT_DEBUG here. + */ + return kvm_emulate_halt_noskip(vcpu) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt); + +fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu) +{ + int ret; + + kvm_vcpu_srcu_read_lock(vcpu); + ret = kvm_emulate_halt(vcpu); + kvm_vcpu_srcu_read_unlock(vcpu); + + if (!ret) + return EXIT_FASTPATH_EXIT_USERSPACE; + + if (kvm_vcpu_running(vcpu)) + return EXIT_FASTPATH_REENTER_GUEST; + + return EXIT_FASTPATH_EXIT_HANDLED; +} +EXPORT_SYMBOL_GPL(handle_fastpath_hlt); + +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + +bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_apicv_active(vcpu) && + kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); +} + +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.preempted_in_kernel; +} + +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || +#ifdef CONFIG_KVM_SMM + kvm_test_request(KVM_REQ_SMI, vcpu) || +#endif + kvm_test_request(KVM_REQ_EVENT, vcpu)) + return true; + + return kvm_arch_dy_has_pending_interrupt(vcpu); +} + static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); @@ -12264,8 +12297,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - kvm_async_pf_hash_reset(vcpu); vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; @@ -12431,6 +12462,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (!init_event) { vcpu->arch.smbase = 0x30000; + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + vcpu->arch.msr_misc_features_enables = 0; vcpu->arch.ia32_misc_enable_msr = MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL; @@ -12516,7 +12549,17 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) } EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); -int kvm_arch_hardware_enable(void) +void kvm_arch_enable_virtualization(void) +{ + cpu_emergency_register_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} + +void kvm_arch_disable_virtualization(void) +{ + cpu_emergency_unregister_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} + +int kvm_arch_enable_virtualization_cpu(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; @@ -12532,7 +12575,7 @@ int kvm_arch_hardware_enable(void) if (ret) return ret; - ret = kvm_x86_call(hardware_enable)(); + ret = kvm_x86_call(enable_virtualization_cpu)(); if (ret != 0) return ret; @@ -12612,9 +12655,9 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { - kvm_x86_call(hardware_disable)(); + kvm_x86_call(disable_virtualization_cpu)(); drop_user_return_notifiers(); } @@ -13162,87 +13205,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_arch_free_memslot(kvm, old); } -static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) -{ - if (!list_empty_careful(&vcpu->async_pf.done)) - return true; - - if (kvm_apic_has_pending_init_or_sipi(vcpu) && - kvm_apic_init_sipi_allowed(vcpu)) - return true; - - if (vcpu->arch.pv.pv_unhalted) - return true; - - if (kvm_is_exception_pending(vcpu)) - return true; - - if (kvm_test_request(KVM_REQ_NMI, vcpu) || - (vcpu->arch.nmi_pending && - kvm_x86_call(nmi_allowed)(vcpu, false))) - return true; - -#ifdef CONFIG_KVM_SMM - if (kvm_test_request(KVM_REQ_SMI, vcpu) || - (vcpu->arch.smi_pending && - kvm_x86_call(smi_allowed)(vcpu, false))) - return true; -#endif - - if (kvm_test_request(KVM_REQ_PMI, vcpu)) - return true; - - if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) - return true; - - if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) - return true; - - if (kvm_hv_has_stimer_pending(vcpu)) - return true; - - if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu, false)) - return true; - - if (kvm_xen_has_pending_events(vcpu)) - return true; - - return false; -} - -int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); -} - -bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_apicv_active(vcpu) && - kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); -} - -bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.preempted_in_kernel; -} - -bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) -{ - if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) - return true; - - if (kvm_test_request(KVM_REQ_NMI, vcpu) || -#ifdef CONFIG_KVM_SMM - kvm_test_request(KVM_REQ_SMI, vcpu) || -#endif - kvm_test_request(KVM_REQ_EVENT, vcpu)) - return true; - - return kvm_arch_dy_has_pending_interrupt(vcpu); -} - bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 50596f6f8320..a84c48ef5278 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -103,11 +103,18 @@ static inline unsigned int __shrink_ple_window(unsigned int val, return max(val, min); } -#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL +#define MSR_IA32_CR_PAT_DEFAULT \ + PAT_VALUE(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC) void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static inline void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu) { return vcpu->arch.last_vmentry_cpu != -1; @@ -334,6 +341,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); +fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu); extern struct kvm_caps kvm_caps; extern struct kvm_host_values kvm_host; @@ -504,13 +512,26 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); +enum kvm_msr_access { + MSR_TYPE_R = BIT(0), + MSR_TYPE_W = BIT(1), + MSR_TYPE_RW = MSR_TYPE_R | MSR_TYPE_W, +}; + /* * Internal error codes that are used to indicate that MSR emulation encountered - * an error that should result in #GP in the guest, unless userspace - * handles it. + * an error that should result in #GP in the guest, unless userspace handles it. + * Note, '1', '0', and negative numbers are off limits, as they are used by KVM + * as part of KVM's lightly documented internal KVM_RUN return codes. + * + * UNSUPPORTED - The MSR isn't supported, either because it is completely + * unknown to KVM, or because the MSR should not exist according + * to the vCPU model. + * + * FILTERED - Access to the MSR is denied by a userspace MSR filter. */ -#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */ -#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */ +#define KVM_MSR_RET_UNSUPPORTED 2 +#define KVM_MSR_RET_FILTERED 3 #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index f73b5ce270b3..feb8cc6a12bf 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -176,15 +176,6 @@ static inline void set_page_memtype(struct page *pg, } #endif -enum { - PAT_UC = 0, /* uncached */ - PAT_WC = 1, /* Write combining */ - PAT_WT = 4, /* Write Through */ - PAT_WP = 5, /* Write Protected */ - PAT_WB = 6, /* Write Back (default) */ - PAT_UC_MINUS = 7, /* UC, but can be overridden by MTRR */ -}; - #define CM(c) (_PAGE_CACHE_MODE_ ## c) static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, @@ -194,13 +185,13 @@ static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, char *cache_mode; switch (pat_val) { - case PAT_UC: cache = CM(UC); cache_mode = "UC "; break; - case PAT_WC: cache = CM(WC); cache_mode = "WC "; break; - case PAT_WT: cache = CM(WT); cache_mode = "WT "; break; - case PAT_WP: cache = CM(WP); cache_mode = "WP "; break; - case PAT_WB: cache = CM(WB); cache_mode = "WB "; break; - case PAT_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break; - default: cache = CM(WB); cache_mode = "WB "; break; + case X86_MEMTYPE_UC: cache = CM(UC); cache_mode = "UC "; break; + case X86_MEMTYPE_WC: cache = CM(WC); cache_mode = "WC "; break; + case X86_MEMTYPE_WT: cache = CM(WT); cache_mode = "WT "; break; + case X86_MEMTYPE_WP: cache = CM(WP); cache_mode = "WP "; break; + case X86_MEMTYPE_WB: cache = CM(WB); cache_mode = "WB "; break; + case X86_MEMTYPE_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break; + default: cache = CM(WB); cache_mode = "WB "; break; } memcpy(msg, cache_mode, 4); @@ -257,12 +248,6 @@ void pat_cpu_init(void) void __init pat_bp_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; -#define PAT(p0, p1, p2, p3, p4, p5, p6, p7) \ - (((u64)PAT_ ## p0) | ((u64)PAT_ ## p1 << 8) | \ - ((u64)PAT_ ## p2 << 16) | ((u64)PAT_ ## p3 << 24) | \ - ((u64)PAT_ ## p4 << 32) | ((u64)PAT_ ## p5 << 40) | \ - ((u64)PAT_ ## p6 << 48) | ((u64)PAT_ ## p7 << 56)) - if (!IS_ENABLED(CONFIG_X86_PAT)) pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); @@ -293,7 +278,7 @@ void __init pat_bp_init(void) * NOTE: When WC or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat_msr_val = PAT(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); + pat_msr_val = PAT_VALUE(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); } /* @@ -328,7 +313,7 @@ void __init pat_bp_init(void) * NOTE: When WT or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); + pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); } else { /* * Full PAT support. We put WT in slot 7 to improve @@ -356,13 +341,12 @@ void __init pat_bp_init(void) * The reserved slots are unused, but mapped to their * corresponding types in the presence of PAT errata. */ - pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); + pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); } memory_caching_control |= CACHE_PAT; init_cache_modes(pat_msr_val); -#undef PAT } static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0d5125a3e31a..db567d26f7b9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1529,8 +1529,22 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING -int kvm_arch_hardware_enable(void); -void kvm_arch_hardware_disable(void); +/* + * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under + * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of + * kvm_usage_count, i.e. at the beginning of the generic hardware enabling + * sequence, and at the end of the generic hardware disabling sequence. + */ +void kvm_arch_enable_virtualization(void); +void kvm_arch_disable_virtualization(void); +/* + * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to + * do the actual twiddling of hardware bits. The hooks are called on all + * online CPUs when KVM enables/disabled virtualization, and on a single CPU + * when that CPU is onlined/offlined (including for Resume/Suspend). + */ +int kvm_arch_enable_virtualization_cpu(void); +void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 6d9381d60172..7f57abf936e7 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -5,3 +5,7 @@ !*.h !*.S !*.sh +!.gitignore +!config +!settings +!Makefile diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0c4b254ab56b..960cf6a77198 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -130,6 +130,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test +TEST_GEN_PROGS_x86_64 += coalesced_io_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test @@ -167,6 +168,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access TEST_GEN_PROGS_aarch64 += aarch64/no-vgic-v3 TEST_GEN_PROGS_aarch64 += access_tracking_perf_test TEST_GEN_PROGS_aarch64 += arch_timer +TEST_GEN_PROGS_aarch64 += coalesced_io_test TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test @@ -188,6 +190,7 @@ TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += s390x/cmma_test TEST_GEN_PROGS_s390x += s390x/debug_test TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test +TEST_GEN_PROGS_s390x += s390x/ucontrol_test TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += guest_print_test @@ -200,6 +203,7 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test TEST_GEN_PROGS_riscv += riscv/ebreak_test TEST_GEN_PROGS_riscv += arch_timer +TEST_GEN_PROGS_riscv += coalesced_io_test TEST_GEN_PROGS_riscv += demand_paging_test TEST_GEN_PROGS_riscv += dirty_log_test TEST_GEN_PROGS_riscv += get-reg-list diff --git a/tools/testing/selftests/kvm/coalesced_io_test.c b/tools/testing/selftests/kvm/coalesced_io_test.c new file mode 100644 index 000000000000..60cb25454899 --- /dev/null +++ b/tools/testing/selftests/kvm/coalesced_io_test.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include <linux/sizes.h> + +#include <kvm_util.h> +#include <processor.h> + +#include "ucall_common.h" + +struct kvm_coalesced_io { + struct kvm_coalesced_mmio_ring *ring; + uint32_t ring_size; + uint64_t mmio_gpa; + uint64_t *mmio; + + /* + * x86-only, but define pio_port for all architectures to minimize the + * amount of #ifdeffery and complexity, without having to sacrifice + * verbose error messages. + */ + uint8_t pio_port; +}; + +static struct kvm_coalesced_io kvm_builtin_io_ring; + +#ifdef __x86_64__ +static const int has_pio = 1; +#else +static const int has_pio = 0; +#endif + +static void guest_code(struct kvm_coalesced_io *io) +{ + int i, j; + + for (;;) { + for (j = 0; j < 1 + has_pio; j++) { + /* + * KVM always leaves one free entry, i.e. exits to + * userspace before the last entry is filled. + */ + for (i = 0; i < io->ring_size - 1; i++) { +#ifdef __x86_64__ + if (i & 1) + outl(io->pio_port, io->pio_port + i); + else +#endif + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); + } +#ifdef __x86_64__ + if (j & 1) + outl(io->pio_port, io->pio_port + i); + else +#endif + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); + } + GUEST_SYNC(0); + + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); +#ifdef __x86_64__ + outl(io->pio_port, io->pio_port + i); +#endif + } +} + +static void vcpu_run_and_verify_io_exit(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, + uint32_t ring_start, + uint32_t expected_exit) +{ + const bool want_pio = expected_exit == KVM_EXIT_IO; + struct kvm_coalesced_mmio_ring *ring = io->ring; + struct kvm_run *run = vcpu->run; + uint32_t pio_value; + + WRITE_ONCE(ring->first, ring_start); + WRITE_ONCE(ring->last, ring_start); + + vcpu_run(vcpu); + + /* + * Annoyingly, reading PIO data is safe only for PIO exits, otherwise + * data_offset is garbage, e.g. an MMIO gpa. + */ + if (run->exit_reason == KVM_EXIT_IO) + pio_value = *(uint32_t *)((void *)run + run->io.data_offset); + else + pio_value = 0; + + TEST_ASSERT((!want_pio && (run->exit_reason == KVM_EXIT_MMIO && run->mmio.is_write && + run->mmio.phys_addr == io->mmio_gpa && run->mmio.len == 8 && + *(uint64_t *)run->mmio.data == io->mmio_gpa + io->ring_size - 1)) || + (want_pio && (run->exit_reason == KVM_EXIT_IO && run->io.port == io->pio_port && + run->io.direction == KVM_EXIT_IO_OUT && run->io.count == 1 && + pio_value == io->pio_port + io->ring_size - 1)), + "For start = %u, expected exit on %u-byte %s write 0x%llx = %lx, got exit_reason = %u (%s)\n " + "(MMIO addr = 0x%llx, write = %u, len = %u, data = %lx)\n " + "(PIO port = 0x%x, write = %u, len = %u, count = %u, data = %x", + ring_start, want_pio ? 4 : 8, want_pio ? "PIO" : "MMIO", + want_pio ? (unsigned long long)io->pio_port : io->mmio_gpa, + (want_pio ? io->pio_port : io->mmio_gpa) + io->ring_size - 1, run->exit_reason, + run->exit_reason == KVM_EXIT_MMIO ? "MMIO" : run->exit_reason == KVM_EXIT_IO ? "PIO" : "other", + run->mmio.phys_addr, run->mmio.is_write, run->mmio.len, *(uint64_t *)run->mmio.data, + run->io.port, run->io.direction, run->io.size, run->io.count, pio_value); +} + +static void vcpu_run_and_verify_coalesced_io(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, + uint32_t ring_start, + uint32_t expected_exit) +{ + struct kvm_coalesced_mmio_ring *ring = io->ring; + int i; + + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, expected_exit); + + TEST_ASSERT((ring->last + 1) % io->ring_size == ring->first, + "Expected ring to be full (minus 1), first = %u, last = %u, max = %u, start = %u", + ring->first, ring->last, io->ring_size, ring_start); + + for (i = 0; i < io->ring_size - 1; i++) { + uint32_t idx = (ring->first + i) % io->ring_size; + struct kvm_coalesced_mmio *entry = &ring->coalesced_mmio[idx]; + +#ifdef __x86_64__ + if (i & 1) + TEST_ASSERT(entry->phys_addr == io->pio_port && + entry->len == 4 && entry->pio && + *(uint32_t *)entry->data == io->pio_port + i, + "Wanted 4-byte port I/O 0x%x = 0x%x in entry %u, got %u-byte %s 0x%llx = 0x%x", + io->pio_port, io->pio_port + i, i, + entry->len, entry->pio ? "PIO" : "MMIO", + entry->phys_addr, *(uint32_t *)entry->data); + else +#endif + TEST_ASSERT(entry->phys_addr == io->mmio_gpa && + entry->len == 8 && !entry->pio, + "Wanted 8-byte MMIO to 0x%lx = %lx in entry %u, got %u-byte %s 0x%llx = 0x%lx", + io->mmio_gpa, io->mmio_gpa + i, i, + entry->len, entry->pio ? "PIO" : "MMIO", + entry->phys_addr, *(uint64_t *)entry->data); + } +} + +static void test_coalesced_io(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, uint32_t ring_start) +{ + struct kvm_coalesced_mmio_ring *ring = io->ring; + + kvm_vm_register_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */); +#ifdef __x86_64__ + kvm_vm_register_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */); +#endif + + vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_MMIO); +#ifdef __x86_64__ + vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_IO); +#endif + + /* + * Verify ucall, which may use non-coalesced MMIO or PIO, generates an + * immediate exit. + */ + WRITE_ONCE(ring->first, ring_start); + WRITE_ONCE(ring->last, ring_start); + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); + TEST_ASSERT_EQ(ring->first, ring_start); + TEST_ASSERT_EQ(ring->last, ring_start); + + /* Verify that non-coalesced MMIO/PIO generates an exit to userspace. */ + kvm_vm_unregister_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */); + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_MMIO); + +#ifdef __x86_64__ + kvm_vm_unregister_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */); + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_IO); +#endif +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int i; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_MMIO)); + +#ifdef __x86_64__ + TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_PIO)); +#endif + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + kvm_builtin_io_ring = (struct kvm_coalesced_io) { + /* + * The I/O ring is a kernel-allocated page whose address is + * relative to each vCPU's run page, with the page offset + * provided by KVM in the return of KVM_CAP_COALESCED_MMIO. + */ + .ring = (void *)vcpu->run + + (kvm_check_cap(KVM_CAP_COALESCED_MMIO) * getpagesize()), + + /* + * The size of the I/O ring is fixed, but KVM defines the sized + * based on the kernel's PAGE_SIZE. Thus, userspace must query + * the host's page size at runtime to compute the ring size. + */ + .ring_size = (getpagesize() - sizeof(struct kvm_coalesced_mmio_ring)) / + sizeof(struct kvm_coalesced_mmio), + + /* + * Arbitrary address+port (MMIO mustn't overlap memslots), with + * the MMIO GPA identity mapped in the guest. + */ + .mmio_gpa = 4ull * SZ_1G, + .mmio = (uint64_t *)(4ull * SZ_1G), + .pio_port = 0x80, + }; + + virt_map(vm, (uint64_t)kvm_builtin_io_ring.mmio, kvm_builtin_io_ring.mmio_gpa, 1); + + sync_global_to_guest(vm, kvm_builtin_io_ring); + vcpu_args_set(vcpu, 1, &kvm_builtin_io_ring); + + for (i = 0; i < kvm_builtin_io_ring.ring_size; i++) + test_coalesced_io(vcpu, &kvm_builtin_io_ring, i); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c index 8092c2d0f5d6..bcf582852db9 100644 --- a/tools/testing/selftests/kvm/guest_print_test.c +++ b/tools/testing/selftests/kvm/guest_print_test.c @@ -107,6 +107,21 @@ static void ucall_abort(const char *assert_msg, const char *expected_assert_msg) expected_assert_msg, &assert_msg[offset]); } +/* + * Open code vcpu_run(), sans the UCALL_ABORT handling, so that intentional + * guest asserts guest can be verified instead of being reported as failures. + */ +static void do_vcpu_run(struct kvm_vcpu *vcpu) +{ + int r; + + do { + r = __vcpu_run(vcpu); + } while (r == -1 && errno == EINTR); + + TEST_ASSERT(!r, KVM_IOCTL_ERROR(KVM_RUN, r)); +} + static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, const char *expected_assert) { @@ -114,7 +129,7 @@ static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, struct ucall uc; while (1) { - vcpu_run(vcpu); + do_vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, "Unexpected exit reason: %u (%s),", @@ -159,7 +174,7 @@ static void test_limits(void) vm = vm_create_with_one_vcpu(&vcpu, guest_code_limits); run = vcpu->run; - vcpu_run(vcpu); + do_vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, "Unexpected exit reason: %u (%s),", diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 63c2aaae51f3..bc7c242480d6 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -428,8 +428,6 @@ 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); @@ -460,6 +458,32 @@ static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); } +static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm, + uint64_t address, + uint64_t size, bool pio) +{ + struct kvm_coalesced_mmio_zone zone = { + .addr = address, + .size = size, + .pio = pio, + }; + + vm_ioctl(vm, KVM_REGISTER_COALESCED_MMIO, &zone); +} + +static inline void kvm_vm_unregister_coalesced_io(struct kvm_vm *vm, + uint64_t address, + uint64_t size, bool pio) +{ + struct kvm_coalesced_mmio_zone zone = { + .addr = address, + .size = size, + .pio = pio, + }; + + vm_ioctl(vm, KVM_UNREGISTER_COALESCED_MMIO, &zone); +} + static inline int vm_get_stats_fd(struct kvm_vm *vm) { int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390x/debug_print.h new file mode 100644 index 000000000000..1bf275631cc6 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/debug_print.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Definition for kernel virtual machines on s390x + * + * Copyright IBM Corp. 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + */ + +#ifndef SELFTEST_KVM_DEBUG_PRINT_H +#define SELFTEST_KVM_DEBUG_PRINT_H + +#include "asm/ptrace.h" +#include "kvm_util.h" +#include "sie.h" + +static inline void print_hex_bytes(const char *name, u64 addr, size_t len) +{ + u64 pos; + + pr_debug("%s (%p)\n", name, (void *)addr); + pr_debug(" 0/0x00---------|"); + if (len > 8) + pr_debug(" 8/0x08---------|"); + if (len > 16) + pr_debug(" 16/0x10--------|"); + if (len > 24) + pr_debug(" 24/0x18--------|"); + for (pos = 0; pos < len; pos += 8) { + if ((pos % 32) == 0) + pr_debug("\n %3lu 0x%.3lx ", pos, pos); + pr_debug(" %16lx", *((u64 *)(addr + pos))); + } + pr_debug("\n"); +} + +static inline void print_hex(const char *name, u64 addr) +{ + print_hex_bytes(name, addr, 512); +} + +static inline void print_psw(struct kvm_run *run, struct kvm_s390_sie_block *sie_block) +{ + pr_debug("flags:0x%x psw:0x%.16llx:0x%.16llx exit:%u %s\n", + run->flags, + run->psw_mask, run->psw_addr, + run->exit_reason, exit_reason_str(run->exit_reason)); + pr_debug("sie_block psw:0x%.16llx:0x%.16llx\n", + sie_block->psw_mask, sie_block->psw_addr); +} + +static inline void print_run(struct kvm_run *run, struct kvm_s390_sie_block *sie_block) +{ + print_hex_bytes("run", (u64)run, 0x150); + print_hex("sie_block", (u64)sie_block); + print_psw(run, sie_block); +} + +static inline void print_regs(struct kvm_run *run) +{ + struct kvm_sync_regs *sync_regs = &run->s.regs; + + print_hex_bytes("GPRS", (u64)sync_regs->gprs, 8 * NUM_GPRS); + print_hex_bytes("ACRS", (u64)sync_regs->acrs, 4 * NUM_ACRS); + print_hex_bytes("CRS", (u64)sync_regs->crs, 8 * NUM_CRS); +} + +#endif /* SELFTEST_KVM_DEBUG_PRINT_H */ diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h index 255c9b990f4c..481bd2fd6a32 100644 --- a/tools/testing/selftests/kvm/include/s390x/processor.h +++ b/tools/testing/selftests/kvm/include/s390x/processor.h @@ -21,6 +21,11 @@ #define PAGE_PROTECT 0x200 /* HW read-only bit */ #define PAGE_NOEXEC 0x100 /* HW no-execute bit */ +/* Page size definitions */ +#define PAGE_SHIFT 12 +#define PAGE_SIZE BIT_ULL(PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE - 1)) + /* Is there a portable way to do this? */ static inline void cpu_relax(void) { diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390x/sie.h new file mode 100644 index 000000000000..160acd4a1db9 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/sie.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Definition for kernel virtual machines on s390. + * + * Adapted copy of struct definition kvm_s390_sie_block from + * arch/s390/include/asm/kvm_host.h for use in userspace selftest programs. + * + * Copyright IBM Corp. 2008, 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + * Carsten Otte <cotte@de.ibm.com> + */ + +#ifndef SELFTEST_KVM_SIE_H +#define SELFTEST_KVM_SIE_H + +#include <linux/types.h> + +struct kvm_s390_sie_block { +#define CPUSTAT_STOPPED 0x80000000 +#define CPUSTAT_WAIT 0x10000000 +#define CPUSTAT_ECALL_PEND 0x08000000 +#define CPUSTAT_STOP_INT 0x04000000 +#define CPUSTAT_IO_INT 0x02000000 +#define CPUSTAT_EXT_INT 0x01000000 +#define CPUSTAT_RUNNING 0x00800000 +#define CPUSTAT_RETAINED 0x00400000 +#define CPUSTAT_TIMING_SUB 0x00020000 +#define CPUSTAT_SIE_SUB 0x00010000 +#define CPUSTAT_RRF 0x00008000 +#define CPUSTAT_SLSV 0x00004000 +#define CPUSTAT_SLSR 0x00002000 +#define CPUSTAT_ZARCH 0x00000800 +#define CPUSTAT_MCDS 0x00000100 +#define CPUSTAT_KSS 0x00000200 +#define CPUSTAT_SM 0x00000080 +#define CPUSTAT_IBS 0x00000040 +#define CPUSTAT_GED2 0x00000010 +#define CPUSTAT_G 0x00000008 +#define CPUSTAT_GED 0x00000004 +#define CPUSTAT_J 0x00000002 +#define CPUSTAT_P 0x00000001 + __u32 cpuflags; /* 0x0000 */ + __u32: 1; /* 0x0004 */ + __u32 prefix : 18; + __u32: 1; + __u32 ibc : 12; + __u8 reserved08[4]; /* 0x0008 */ +#define PROG_IN_SIE BIT(0) + __u32 prog0c; /* 0x000c */ + union { + __u8 reserved10[16]; /* 0x0010 */ + struct { + __u64 pv_handle_cpu; + __u64 pv_handle_config; + }; + }; +#define PROG_BLOCK_SIE BIT(0) +#define PROG_REQUEST BIT(1) + __u32 prog20; /* 0x0020 */ + __u8 reserved24[4]; /* 0x0024 */ + __u64 cputm; /* 0x0028 */ + __u64 ckc; /* 0x0030 */ + __u64 epoch; /* 0x0038 */ + __u32 svcc; /* 0x0040 */ +#define LCTL_CR0 0x8000 +#define LCTL_CR6 0x0200 +#define LCTL_CR9 0x0040 +#define LCTL_CR10 0x0020 +#define LCTL_CR11 0x0010 +#define LCTL_CR14 0x0002 + __u16 lctl; /* 0x0044 */ + __s16 icpua; /* 0x0046 */ +#define ICTL_OPEREXC 0x80000000 +#define ICTL_PINT 0x20000000 +#define ICTL_LPSW 0x00400000 +#define ICTL_STCTL 0x00040000 +#define ICTL_ISKE 0x00004000 +#define ICTL_SSKE 0x00002000 +#define ICTL_RRBE 0x00001000 +#define ICTL_TPROT 0x00000200 + __u32 ictl; /* 0x0048 */ +#define ECA_CEI 0x80000000 +#define ECA_IB 0x40000000 +#define ECA_SIGPI 0x10000000 +#define ECA_MVPGI 0x01000000 +#define ECA_AIV 0x00200000 +#define ECA_VX 0x00020000 +#define ECA_PROTEXCI 0x00002000 +#define ECA_APIE 0x00000008 +#define ECA_SII 0x00000001 + __u32 eca; /* 0x004c */ +#define ICPT_INST 0x04 +#define ICPT_PROGI 0x08 +#define ICPT_INSTPROGI 0x0C +#define ICPT_EXTREQ 0x10 +#define ICPT_EXTINT 0x14 +#define ICPT_IOREQ 0x18 +#define ICPT_WAIT 0x1c +#define ICPT_VALIDITY 0x20 +#define ICPT_STOP 0x28 +#define ICPT_OPEREXC 0x2C +#define ICPT_PARTEXEC 0x38 +#define ICPT_IOINST 0x40 +#define ICPT_KSS 0x5c +#define ICPT_MCHKREQ 0x60 +#define ICPT_INT_ENABLE 0x64 +#define ICPT_PV_INSTR 0x68 +#define ICPT_PV_NOTIFY 0x6c +#define ICPT_PV_PREF 0x70 + __u8 icptcode; /* 0x0050 */ + __u8 icptstatus; /* 0x0051 */ + __u16 ihcpu; /* 0x0052 */ + __u8 reserved54; /* 0x0054 */ +#define IICTL_CODE_NONE 0x00 +#define IICTL_CODE_MCHK 0x01 +#define IICTL_CODE_EXT 0x02 +#define IICTL_CODE_IO 0x03 +#define IICTL_CODE_RESTART 0x04 +#define IICTL_CODE_SPECIFICATION 0x10 +#define IICTL_CODE_OPERAND 0x11 + __u8 iictl; /* 0x0055 */ + __u16 ipa; /* 0x0056 */ + __u32 ipb; /* 0x0058 */ + __u32 scaoh; /* 0x005c */ +#define FPF_BPBC 0x20 + __u8 fpf; /* 0x0060 */ +#define ECB_GS 0x40 +#define ECB_TE 0x10 +#define ECB_SPECI 0x08 +#define ECB_SRSI 0x04 +#define ECB_HOSTPROTINT 0x02 +#define ECB_PTF 0x01 + __u8 ecb; /* 0x0061 */ +#define ECB2_CMMA 0x80 +#define ECB2_IEP 0x20 +#define ECB2_PFMFI 0x08 +#define ECB2_ESCA 0x04 +#define ECB2_ZPCI_LSI 0x02 + __u8 ecb2; /* 0x0062 */ +#define ECB3_AISI 0x20 +#define ECB3_AISII 0x10 +#define ECB3_DEA 0x08 +#define ECB3_AES 0x04 +#define ECB3_RI 0x01 + __u8 ecb3; /* 0x0063 */ +#define ESCA_SCAOL_MASK ~0x3fU + __u32 scaol; /* 0x0064 */ + __u8 sdf; /* 0x0068 */ + __u8 epdx; /* 0x0069 */ + __u8 cpnc; /* 0x006a */ + __u8 reserved6b; /* 0x006b */ + __u32 todpr; /* 0x006c */ +#define GISA_FORMAT1 0x00000001 + __u32 gd; /* 0x0070 */ + __u8 reserved74[12]; /* 0x0074 */ + __u64 mso; /* 0x0080 */ + __u64 msl; /* 0x0088 */ + __u64 psw_mask; /* 0x0090 */ + __u64 psw_addr; /* 0x0098 */ + __u64 gg14; /* 0x00a0 */ + __u64 gg15; /* 0x00a8 */ + __u8 reservedb0[8]; /* 0x00b0 */ +#define HPID_KVM 0x4 +#define HPID_VSIE 0x5 + __u8 hpid; /* 0x00b8 */ + __u8 reservedb9[7]; /* 0x00b9 */ + union { + struct { + __u32 eiparams; /* 0x00c0 */ + __u16 extcpuaddr; /* 0x00c4 */ + __u16 eic; /* 0x00c6 */ + }; + __u64 mcic; /* 0x00c0 */ + } __packed; + __u32 reservedc8; /* 0x00c8 */ + union { + struct { + __u16 pgmilc; /* 0x00cc */ + __u16 iprcc; /* 0x00ce */ + }; + __u32 edc; /* 0x00cc */ + } __packed; + union { + struct { + __u32 dxc; /* 0x00d0 */ + __u16 mcn; /* 0x00d4 */ + __u8 perc; /* 0x00d6 */ + __u8 peratmid; /* 0x00d7 */ + }; + __u64 faddr; /* 0x00d0 */ + } __packed; + __u64 peraddr; /* 0x00d8 */ + __u8 eai; /* 0x00e0 */ + __u8 peraid; /* 0x00e1 */ + __u8 oai; /* 0x00e2 */ + __u8 armid; /* 0x00e3 */ + __u8 reservede4[4]; /* 0x00e4 */ + union { + __u64 tecmc; /* 0x00e8 */ + struct { + __u16 subchannel_id; /* 0x00e8 */ + __u16 subchannel_nr; /* 0x00ea */ + __u32 io_int_parm; /* 0x00ec */ + __u32 io_int_word; /* 0x00f0 */ + }; + } __packed; + __u8 reservedf4[8]; /* 0x00f4 */ +#define CRYCB_FORMAT_MASK 0x00000003 +#define CRYCB_FORMAT0 0x00000000 +#define CRYCB_FORMAT1 0x00000001 +#define CRYCB_FORMAT2 0x00000003 + __u32 crycbd; /* 0x00fc */ + __u64 gcr[16]; /* 0x0100 */ + union { + __u64 gbea; /* 0x0180 */ + __u64 sidad; + }; + __u8 reserved188[8]; /* 0x0188 */ + __u64 sdnxo; /* 0x0190 */ + __u8 reserved198[8]; /* 0x0198 */ + __u32 fac; /* 0x01a0 */ + __u8 reserved1a4[20]; /* 0x01a4 */ + __u64 cbrlo; /* 0x01b8 */ + __u8 reserved1c0[8]; /* 0x01c0 */ +#define ECD_HOSTREGMGMT 0x20000000 +#define ECD_MEF 0x08000000 +#define ECD_ETOKENF 0x02000000 +#define ECD_ECC 0x00200000 + __u32 ecd; /* 0x01c8 */ + __u8 reserved1cc[18]; /* 0x01cc */ + __u64 pp; /* 0x01de */ + __u8 reserved1e6[2]; /* 0x01e6 */ + __u64 itdba; /* 0x01e8 */ + __u64 riccbd; /* 0x01f0 */ + __u64 gvrd; /* 0x01f8 */ +} __packed __aligned(512); + +#endif /* SELFTEST_KVM_SIE_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h index 0f268b55fa06..51990094effd 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -11,6 +11,7 @@ #include <stdint.h> #include "processor.h" +#include "ucall_common.h" #define APIC_DEFAULT_GPA 0xfee00000ULL @@ -93,9 +94,27 @@ static inline uint64_t x2apic_read_reg(unsigned int reg) return rdmsr(APIC_BASE_MSR + (reg >> 4)); } +static inline uint8_t x2apic_write_reg_safe(unsigned int reg, uint64_t value) +{ + return wrmsr_safe(APIC_BASE_MSR + (reg >> 4), value); +} + static inline void x2apic_write_reg(unsigned int reg, uint64_t value) { - wrmsr(APIC_BASE_MSR + (reg >> 4), value); + uint8_t fault = x2apic_write_reg_safe(reg, value); + + __GUEST_ASSERT(!fault, "Unexpected fault 0x%x on WRMSR(%x) = %lx\n", + fault, APIC_BASE_MSR + (reg >> 4), value); } +static inline void x2apic_write_reg_fault(unsigned int reg, uint64_t value) +{ + uint8_t fault = x2apic_write_reg_safe(reg, value); + + __GUEST_ASSERT(fault == GP_VECTOR, + "Wanted #GP on WRMSR(%x) = %lx, got 0x%x\n", + APIC_BASE_MSR + (reg >> 4), value, fault); +} + + #endif /* SELFTEST_KVM_APIC_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index fa65b908b13e..6849e2552f1b 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -186,6 +186,18 @@ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED \ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14) +/* HYPERV_CPUID_NESTED_FEATURES.EAX */ +#define HV_X64_NESTED_DIRECT_FLUSH \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 17) +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 18) +#define HV_X64_NESTED_MSR_BITMAP \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 19) + +/* HYPERV_CPUID_NESTED_FEATURES.EBX */ +#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EBX, 0) + /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ #define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING \ KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1) @@ -343,4 +355,10 @@ struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); + +bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature); + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index a0c1440017bb..e247f99e0473 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -25,6 +25,10 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; extern uint64_t guest_tsc_khz; +#ifndef MAX_NR_CPUID_ENTRIES +#define MAX_NR_CPUID_ENTRIES 100 +#endif + /* Forced emulation prefix, used to invoke the emulator unconditionally. */ #define KVM_FEP "ud2; .byte 'k', 'v', 'm';" @@ -908,8 +912,6 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, uint32_t function, uint32_t index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); -const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); static inline uint32_t kvm_cpu_fms(void) { @@ -1009,7 +1011,6 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries) } void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid); -void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function, diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 56b170b725b3..a2b7df5f1d39 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -712,16 +712,13 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region, - bool unlink) + struct userspace_mem_region *region) { int ret; - if (unlink) { - rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); - rb_erase(®ion->hva_node, &vm->regions.hva_tree); - hash_del(®ion->slot_node); - } + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); region->region.memory_size = 0; vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); @@ -762,7 +759,7 @@ void kvm_vm_free(struct kvm_vm *vmp) /* Free userspace_mem_regions. */ hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) - __vm_mem_region_delete(vmp, region, false); + __vm_mem_region_delete(vmp, region); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -794,76 +791,6 @@ int kvm_memfd_alloc(size_t size, bool hugepages) return fd; } -/* - * Memory Compare, host virtual to guest virtual - * - * Input Args: - * hva - Starting host virtual address - * vm - Virtual Machine - * gva - Starting guest virtual address - * len - number of bytes to compare - * - * Output Args: None - * - * Input/Output Args: None - * - * Return: - * Returns 0 if the bytes starting at hva for a length of len - * are equal the guest virtual bytes starting at gva. Returns - * a value < 0, if bytes at hva are less than those at gva. - * Otherwise a value > 0 is returned. - * - * Compares the bytes starting at the host virtual address hva, for - * a length of len, to the guest bytes starting at the guest virtual - * address given by gva. - */ -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) -{ - size_t amt; - - /* - * Compare a batch of bytes until either a match is found - * or all the bytes have been compared. - */ - for (uintptr_t offset = 0; offset < len; offset += amt) { - uintptr_t ptr1 = (uintptr_t)hva + offset; - - /* - * Determine host address for guest virtual address - * at offset. - */ - uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset); - - /* - * Determine amount to compare on this pass. - * Don't allow the comparsion to cross a page boundary. - */ - amt = len - offset; - if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr1 % vm->page_size); - if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr2 % vm->page_size); - - assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift)); - assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift)); - - /* - * Perform the comparison. If there is a difference - * return that result to the caller, otherwise need - * to continue on looking for a mismatch. - */ - int ret = memcmp((void *)ptr1, (void *)ptr2, amt); - if (ret != 0) - return ret; - } - - /* - * No mismatch found. Let the caller know the two memory - * areas are equal. - */ - return 0; -} - static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, struct userspace_mem_region *region) { @@ -1270,7 +1197,7 @@ 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) { - __vm_mem_region_delete(vm, memslot2region(vm, slot), true); + __vm_mem_region_delete(vm, memslot2region(vm, slot)); } void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index 4ad4492eea1d..20cfe970e3e3 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -14,7 +14,7 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) { vm_paddr_t paddr; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); if (vm->pgd_created) @@ -79,7 +79,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) } /* Fill in page table entry */ - idx = (gva >> 12) & 0x0ffu; /* page index */ + idx = (gva >> PAGE_SHIFT) & 0x0ffu; /* page index */ if (!(entry[idx] & PAGE_INVALID)) fprintf(stderr, "WARNING: PTE for gpa=0x%"PRIx64" already set!\n", gpa); @@ -91,7 +91,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) int ri, idx; uint64_t *entry; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); entry = addr_gpa2hva(vm, vm->pgd); @@ -103,7 +103,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN); } - idx = (gva >> 12) & 0x0ffu; /* page index */ + idx = (gva >> PAGE_SHIFT) & 0x0ffu; /* page index */ TEST_ASSERT(!(entry[idx] & PAGE_INVALID), "No page mapping for vm virtual address 0x%lx", gva); @@ -168,7 +168,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) struct kvm_sregs sregs; struct kvm_vcpu *vcpu; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); stack_vaddr = __vm_vaddr_alloc(vm, stack_size, diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c index efb7e7a1354d..15bc8cd583aa 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c +++ b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c @@ -8,6 +8,73 @@ #include "processor.h" #include "hyperv.h" +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) +{ + static struct kvm_cpuid2 *cpuid; + int kvm_fd; + + if (cpuid) + return cpuid; + + cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); + kvm_fd = open_kvm_dev_path_or_exit(); + + kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + + close(kvm_fd); + return cpuid; +} + +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu) +{ + static struct kvm_cpuid2 *cpuid_full; + const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; + int i, nent = 0; + + if (!cpuid_full) { + cpuid_sys = kvm_get_supported_cpuid(); + cpuid_hv = kvm_get_supported_hv_cpuid(); + + cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent); + if (!cpuid_full) { + perror("malloc"); + abort(); + } + + /* Need to skip KVM CPUID leaves 0x400000xx */ + for (i = 0; i < cpuid_sys->nent; i++) { + if (cpuid_sys->entries[i].function >= 0x40000000 && + cpuid_sys->entries[i].function < 0x40000100) + continue; + cpuid_full->entries[nent] = cpuid_sys->entries[i]; + nent++; + } + + memcpy(&cpuid_full->entries[nent], cpuid_hv->entries, + cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2)); + cpuid_full->nent = nent + cpuid_hv->nent; + } + + vcpu_init_cpuid(vcpu, cpuid_full); +} + +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); + + vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + + return cpuid; +} + +bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature) +{ + if (!kvm_has_cap(KVM_CAP_SYS_HYPERV_CPUID)) + return false; + + return kvm_cpuid_has(kvm_get_supported_hv_cpuid(), feature); +} + struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, vm_vaddr_t *p_hv_pages_gva) { diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 153739f2e201..974bcd2df6d7 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,8 +19,6 @@ #define KERNEL_DS 0x10 #define KERNEL_TSS 0x18 -#define MAX_NR_CPUID_ENTRIES 100 - vm_vaddr_t exception_handlers; bool host_cpu_is_amd; bool host_cpu_is_intel; @@ -566,10 +564,8 @@ void route_exception(struct ex_regs *regs) 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); + GUEST_FAIL("Unhandled exception '0x%lx' at guest RIP '0x%lx'", + regs->vector, regs->rip); } static void vm_init_descriptor_tables(struct kvm_vm *vm) @@ -611,7 +607,7 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { struct ucall uc; - if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) + if (get_ucall(vcpu, &uc) == UCALL_ABORT) REPORT_GUEST_ASSERT(uc); } @@ -1195,65 +1191,6 @@ void xen_hypercall(uint64_t nr, uint64_t a0, void *a1) GUEST_ASSERT(!__xen_hypercall(nr, a0, a1)); } -const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) -{ - static struct kvm_cpuid2 *cpuid; - int kvm_fd; - - if (cpuid) - return cpuid; - - cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); - kvm_fd = open_kvm_dev_path_or_exit(); - - kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); - - close(kvm_fd); - return cpuid; -} - -void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu) -{ - static struct kvm_cpuid2 *cpuid_full; - const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; - int i, nent = 0; - - if (!cpuid_full) { - cpuid_sys = kvm_get_supported_cpuid(); - cpuid_hv = kvm_get_supported_hv_cpuid(); - - cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent); - if (!cpuid_full) { - perror("malloc"); - abort(); - } - - /* Need to skip KVM CPUID leaves 0x400000xx */ - for (i = 0; i < cpuid_sys->nent; i++) { - if (cpuid_sys->entries[i].function >= 0x40000000 && - cpuid_sys->entries[i].function < 0x40000100) - continue; - cpuid_full->entries[nent] = cpuid_sys->entries[i]; - nent++; - } - - memcpy(&cpuid_full->entries[nent], cpuid_hv->entries, - cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2)); - cpuid_full->nent = nent + cpuid_hv->nent; - } - - vcpu_init_cpuid(vcpu, cpuid_full); -} - -const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); - - vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid); - - return cpuid; -} - unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 49f162573126..e3343f0df9e1 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -79,6 +79,7 @@ struct test_params { useconds_t delay; uint64_t nr_iterations; bool partition_vcpu_memory_access; + bool disable_slot_zap_quirk; }; static void run_test(enum vm_guest_mode mode, void *arg) @@ -89,6 +90,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, VM_MEM_SRC_ANONYMOUS, p->partition_vcpu_memory_access); +#ifdef __x86_64__ + if (p->disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + + pr_info("Memslot zap quirk %s\n", p->disable_slot_zap_quirk ? + "disabled" : "enabled"); +#endif pr_info("Finished creating vCPUs\n"); @@ -107,11 +115,12 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-d delay_usec]\n" + printf("usage: %s [-h] [-m mode] [-d delay_usec] [-q]\n" " [-b memory] [-v vcpus] [-o] [-i iterations]\n", name); guest_modes_help(); printf(" -d: add a delay between each iteration of adding and\n" " deleting a memslot in usec.\n"); + printf(" -q: Disable memslot zap quirk.\n"); printf(" -b: specify the size of the memory region which should be\n" " accessed by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); @@ -137,7 +146,7 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:d:b:v:oi:")) != -1) { + while ((opt = getopt(argc, argv, "hm:d:qb:v:oi:")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -160,6 +169,12 @@ int main(int argc, char *argv[]) case 'i': p.nr_iterations = atoi_positive("Number of iterations", optarg); break; + case 'q': + p.disable_slot_zap_quirk = true; + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & + KVM_X86_QUIRK_SLOT_ZAP_ALL); + break; case 'h': default: help(argv[0]); diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 579a64f97333..893366982f77 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -113,6 +113,7 @@ static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); static sem_t vcpu_ready; static bool map_unmap_verify; +static bool disable_slot_zap_quirk; static bool verbose; #define pr_info_v(...) \ @@ -578,6 +579,9 @@ static bool test_memslot_move_prepare(struct vm_data *data, uint32_t guest_page_size = data->vm->page_size; uint64_t movesrcgpa, movetestgpa; + if (disable_slot_zap_quirk) + vm_enable_cap(data->vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); if (isactive) { @@ -896,6 +900,7 @@ static void help(char *name, struct test_args *targs) pr_info(" -h: print this help screen.\n"); pr_info(" -v: enable verbose mode (not for benchmarking).\n"); pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -q: Disable memslot zap quirk during memslot move.\n"); pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", targs->nslots); pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", @@ -954,7 +959,7 @@ static bool parse_args(int argc, char *argv[], uint32_t max_mem_slots; int opt; - while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + while ((opt = getopt(argc, argv, "hvdqs:f:e:l:r:")) != -1) { switch (opt) { case 'h': default: @@ -966,6 +971,11 @@ static bool parse_args(int argc, char *argv[], case 'd': map_unmap_verify = true; break; + case 'q': + disable_slot_zap_quirk = true; + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & + KVM_X86_QUIRK_SLOT_ZAP_ALL); + break; case 's': targs->nslots = atoi_paranoid(optarg); if (targs->nslots <= 1 && targs->nslots != -1) { diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c index b39033844756..e32dd59703a0 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390x/cmma_test.c @@ -17,16 +17,17 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" #define MAIN_PAGE_COUNT 512 #define TEST_DATA_PAGE_COUNT 512 #define TEST_DATA_MEMSLOT 1 -#define TEST_DATA_START_GFN 4096 +#define TEST_DATA_START_GFN PAGE_SIZE #define TEST_DATA_TWO_PAGE_COUNT 256 #define TEST_DATA_TWO_MEMSLOT 2 -#define TEST_DATA_TWO_START_GFN 8192 +#define TEST_DATA_TWO_START_GFN (2 * PAGE_SIZE) static char cmma_value_buf[MAIN_PAGE_COUNT + TEST_DATA_PAGE_COUNT]; @@ -66,7 +67,7 @@ static void guest_dirty_test_data(void) " lghi 5,%[page_count]\n" /* r5 += r1 */ "2: agfr 5,1\n" - /* r2 = r1 << 12 */ + /* r2 = r1 << PAGE_SHIFT */ "1: sllg 2,1,12(0)\n" /* essa(r4, r2, SET_STABLE) */ " .insn rrf,0xb9ab0000,4,2,1,0\n" diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390x/config new file mode 100644 index 000000000000..23270f2d679f --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/config @@ -0,0 +1,2 @@ +CONFIG_KVM=y +CONFIG_KVM_S390_UCONTROL=y diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390x/debug_test.c index 84313fb27529..ad8095968601 100644 --- a/tools/testing/selftests/kvm/s390x/debug_test.c +++ b/tools/testing/selftests/kvm/s390x/debug_test.c @@ -2,12 +2,12 @@ /* Test KVM debugging features. */ #include "kvm_util.h" #include "test_util.h" +#include "sie.h" #include <linux/kvm.h> #define __LC_SVC_NEW_PSW 0x1c0 #define __LC_PGM_NEW_PSW 0x1d0 -#define ICPT_INSTRUCTION 0x04 #define IPA0_DIAG 0x8300 #define PGM_SPECIFICATION 0x06 @@ -85,7 +85,7 @@ static void test_step_pgm_diag(void) vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code, __LC_PGM_NEW_PSW, new_psw); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); - TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INSTRUCTION); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INST); TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG); vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq); vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index f2df7416be84..4374b4cd2a80 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -16,6 +16,7 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" enum mop_target { LOGICAL, @@ -226,9 +227,6 @@ static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) -#define PAGE_SHIFT 12 -#define PAGE_SIZE (1ULL << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c index 7a742a673b7c..12d5e1cb62e3 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -9,9 +9,8 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" -#define PAGE_SHIFT 12 -#define PAGE_SIZE (1 << PAGE_SHIFT) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) @@ -151,7 +150,7 @@ static enum stage perform_next_stage(int *i, bool mapped_0) * instead. * In order to skip these tests we detect this inside the guest */ - skip = tests[*i].addr < (void *)4096 && + skip = tests[*i].addr < (void *)PAGE_SIZE && tests[*i].expected != TRANSL_UNAVAIL && !mapped_0; if (!skip) { diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c new file mode 100644 index 000000000000..f257beec1430 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test code for the s390x kvm ucontrol interface + * + * Copyright IBM Corp. 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + */ +#include "debug_print.h" +#include "kselftest_harness.h" +#include "kvm_util.h" +#include "processor.h" +#include "sie.h" + +#include <linux/capability.h> +#include <linux/sizes.h> + +#define VM_MEM_SIZE (4 * SZ_1M) + +/* so directly declare capget to check caps without libcap */ +int capget(cap_user_header_t header, cap_user_data_t data); + +/** + * In order to create user controlled virtual machines on S390, + * check KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL + * as privileged user (SYS_ADMIN). + */ +void require_ucontrol_admin(void) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + int rc; + + rc = capget(&hdr, data); + TEST_ASSERT_EQ(0, rc); + TEST_REQUIRE((data->effective & CAP_TO_MASK(CAP_SYS_ADMIN)) > 0); + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_UCONTROL)); +} + +/* Test program setting some registers and looping */ +extern char test_gprs_asm[]; +asm("test_gprs_asm:\n" + "xgr %r0, %r0\n" + "lgfi %r1,1\n" + "lgfi %r2,2\n" + "lgfi %r3,3\n" + "lgfi %r4,4\n" + "lgfi %r5,5\n" + "lgfi %r6,6\n" + "lgfi %r7,7\n" + "0:\n" + " diag 0,0,0x44\n" + " ahi %r0,1\n" + " j 0b\n" +); + +FIXTURE(uc_kvm) +{ + struct kvm_s390_sie_block *sie_block; + struct kvm_run *run; + uintptr_t base_gpa; + uintptr_t code_gpa; + uintptr_t base_hva; + uintptr_t code_hva; + int kvm_run_size; + void *vm_mem; + int vcpu_fd; + int kvm_fd; + int vm_fd; +}; + +/** + * create VM with single vcpu, map kvm_run and SIE control block for easy access + */ +FIXTURE_SETUP(uc_kvm) +{ + struct kvm_s390_vm_cpu_processor info; + int rc; + + require_ucontrol_admin(); + + self->kvm_fd = open_kvm_dev_path_or_exit(); + self->vm_fd = ioctl(self->kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL); + ASSERT_GE(self->vm_fd, 0); + + kvm_device_attr_get(self->vm_fd, KVM_S390_VM_CPU_MODEL, + KVM_S390_VM_CPU_PROCESSOR, &info); + TH_LOG("create VM 0x%llx", info.cpuid); + + self->vcpu_fd = ioctl(self->vm_fd, KVM_CREATE_VCPU, 0); + ASSERT_GE(self->vcpu_fd, 0); + + self->kvm_run_size = ioctl(self->kvm_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); + ASSERT_GE(self->kvm_run_size, sizeof(struct kvm_run)) + TH_LOG(KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, self->kvm_run_size)); + self->run = (struct kvm_run *)mmap(NULL, self->kvm_run_size, + PROT_READ | PROT_WRITE, MAP_SHARED, self->vcpu_fd, 0); + ASSERT_NE(self->run, MAP_FAILED); + /** + * For virtual cpus that have been created with S390 user controlled + * virtual machines, the resulting vcpu fd can be memory mapped at page + * offset KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of + * the virtual cpu's hardware control block. + */ + self->sie_block = (struct kvm_s390_sie_block *)mmap(NULL, PAGE_SIZE, + PROT_READ | PROT_WRITE, MAP_SHARED, + self->vcpu_fd, KVM_S390_SIE_PAGE_OFFSET << PAGE_SHIFT); + ASSERT_NE(self->sie_block, MAP_FAILED); + + TH_LOG("VM created %p %p", self->run, self->sie_block); + + self->base_gpa = 0; + self->code_gpa = self->base_gpa + (3 * SZ_1M); + + self->vm_mem = aligned_alloc(SZ_1M, VM_MEM_SIZE); + ASSERT_NE(NULL, self->vm_mem) TH_LOG("malloc failed %u", errno); + self->base_hva = (uintptr_t)self->vm_mem; + self->code_hva = self->base_hva - self->base_gpa + self->code_gpa; + struct kvm_s390_ucas_mapping map = { + .user_addr = self->base_hva, + .vcpu_addr = self->base_gpa, + .length = VM_MEM_SIZE, + }; + TH_LOG("ucas map %p %p 0x%llx", + (void *)map.user_addr, (void *)map.vcpu_addr, map.length); + rc = ioctl(self->vcpu_fd, KVM_S390_UCAS_MAP, &map); + ASSERT_EQ(0, rc) TH_LOG("ucas map result %d not expected, %s", + rc, strerror(errno)); + + TH_LOG("page in %p", (void *)self->base_gpa); + rc = ioctl(self->vcpu_fd, KVM_S390_VCPU_FAULT, self->base_gpa); + ASSERT_EQ(0, rc) TH_LOG("vcpu fault (%p) result %d not expected, %s", + (void *)self->base_hva, rc, strerror(errno)); + + self->sie_block->cpuflags &= ~CPUSTAT_STOPPED; +} + +FIXTURE_TEARDOWN(uc_kvm) +{ + munmap(self->sie_block, PAGE_SIZE); + munmap(self->run, self->kvm_run_size); + close(self->vcpu_fd); + close(self->vm_fd); + close(self->kvm_fd); + free(self->vm_mem); +} + +TEST_F(uc_kvm, uc_sie_assertions) +{ + /* assert interception of Code 08 (Program Interruption) is set */ + EXPECT_EQ(0, self->sie_block->ecb & ECB_SPECI); +} + +TEST_F(uc_kvm, uc_attr_mem_limit) +{ + u64 limit; + struct kvm_device_attr attr = { + .group = KVM_S390_VM_MEM_CTRL, + .attr = KVM_S390_VM_MEM_LIMIT_SIZE, + .addr = (unsigned long)&limit, + }; + int rc; + + rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr); + EXPECT_EQ(0, rc); + EXPECT_EQ(~0UL, limit); + + /* assert set not supported */ + rc = ioctl(self->vm_fd, KVM_SET_DEVICE_ATTR, &attr); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +TEST_F(uc_kvm, uc_no_dirty_log) +{ + struct kvm_dirty_log dlog; + int rc; + + rc = ioctl(self->vm_fd, KVM_GET_DIRTY_LOG, &dlog); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +/** + * Assert HPAGE CAP cannot be enabled on UCONTROL VM + */ +TEST(uc_cap_hpage) +{ + int rc, kvm_fd, vm_fd, vcpu_fd; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_S390_HPAGE_1M, + }; + + require_ucontrol_admin(); + + kvm_fd = open_kvm_dev_path_or_exit(); + vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL); + ASSERT_GE(vm_fd, 0); + + /* assert hpages are not supported on ucontrol vm */ + rc = ioctl(vm_fd, KVM_CHECK_EXTENSION, KVM_CAP_S390_HPAGE_1M); + EXPECT_EQ(0, rc); + + /* Test that KVM_CAP_S390_HPAGE_1M can't be enabled for a ucontrol vm */ + rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); + + /* assert HPAGE CAP is rejected after vCPU creation */ + vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0); + ASSERT_GE(vcpu_fd, 0); + rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EBUSY, errno); + + close(vcpu_fd); + close(vm_fd); + close(kvm_fd); +} + +/* verify SIEIC exit + * * fail on codes not expected in the test cases + */ +static bool uc_handle_sieic(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_s390_sie_block *sie_block = self->sie_block; + struct kvm_run *run = self->run; + + /* check SIE interception code */ + pr_info("sieic: 0x%.2x 0x%.4x 0x%.4x\n", + run->s390_sieic.icptcode, + run->s390_sieic.ipa, + run->s390_sieic.ipb); + switch (run->s390_sieic.icptcode) { + case ICPT_INST: + /* end execution in caller on intercepted instruction */ + pr_info("sie instruction interception\n"); + return false; + case ICPT_OPEREXC: + /* operation exception */ + TEST_FAIL("sie exception on %.4x%.8x", sie_block->ipa, sie_block->ipb); + default: + TEST_FAIL("UNEXPECTED SIEIC CODE %d", run->s390_sieic.icptcode); + } + return true; +} + +/* verify VM state on exit */ +static bool uc_handle_exit(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_run *run = self->run; + + switch (run->exit_reason) { + case KVM_EXIT_S390_SIEIC: + return uc_handle_sieic(self); + default: + pr_info("exit_reason %2d not handled\n", run->exit_reason); + } + return true; +} + +/* run the VM until interrupted */ +static int uc_run_once(FIXTURE_DATA(uc_kvm) * self) +{ + int rc; + + rc = ioctl(self->vcpu_fd, KVM_RUN, NULL); + print_run(self->run, self->sie_block); + print_regs(self->run); + pr_debug("run %d / %d %s\n", rc, errno, strerror(errno)); + return rc; +} + +static void uc_assert_diag44(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_s390_sie_block *sie_block = self->sie_block; + + /* assert vm was interrupted by diag 0x0044 */ + TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason); + TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode); + TEST_ASSERT_EQ(0x8300, sie_block->ipa); + TEST_ASSERT_EQ(0x440000, sie_block->ipb); +} + +TEST_F(uc_kvm, uc_gprs) +{ + struct kvm_sync_regs *sync_regs = &self->run->s.regs; + struct kvm_run *run = self->run; + struct kvm_regs regs = {}; + + /* Set registers to values that are different from the ones that we expect below */ + for (int i = 0; i < 8; i++) + sync_regs->gprs[i] = 8; + run->kvm_dirty_regs |= KVM_SYNC_GPRS; + + /* copy test_gprs_asm to code_hva / code_gpa */ + TH_LOG("copy code %p to vm mapped memory %p / %p", + &test_gprs_asm, (void *)self->code_hva, (void *)self->code_gpa); + memcpy((void *)self->code_hva, &test_gprs_asm, PAGE_SIZE); + + /* DAT disabled + 64 bit mode */ + run->psw_mask = 0x0000000180000000ULL; + run->psw_addr = self->code_gpa; + + /* run and expect interception of diag 44 */ + ASSERT_EQ(0, uc_run_once(self)); + ASSERT_EQ(false, uc_handle_exit(self)); + uc_assert_diag44(self); + + /* Retrieve and check guest register values */ + ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, ®s)); + for (int i = 0; i < 8; i++) { + ASSERT_EQ(i, regs.gprs[i]); + ASSERT_EQ(i, sync_regs->gprs[i]); + } + + /* run and expect interception of diag 44 again */ + ASSERT_EQ(0, uc_run_once(self)); + ASSERT_EQ(false, uc_handle_exit(self)); + uc_assert_diag44(self); + + /* check continued increment of register 0 value */ + ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, ®s)); + ASSERT_EQ(1, regs.gprs[0]); + ASSERT_EQ(1, sync_regs->gprs[0]); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index bb8002084f52..a8267628e9ed 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -175,7 +175,7 @@ static void guest_code_move_memory_region(void) GUEST_DONE(); } -static void test_move_memory_region(void) +static void test_move_memory_region(bool disable_slot_zap_quirk) { pthread_t vcpu_thread; struct kvm_vcpu *vcpu; @@ -184,6 +184,9 @@ static void test_move_memory_region(void) vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_move_memory_region); + if (disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + hva = addr_gpa2hva(vm, MEM_REGION_GPA); /* @@ -266,7 +269,7 @@ static void guest_code_delete_memory_region(void) GUEST_ASSERT(0); } -static void test_delete_memory_region(void) +static void test_delete_memory_region(bool disable_slot_zap_quirk) { pthread_t vcpu_thread; struct kvm_vcpu *vcpu; @@ -276,6 +279,9 @@ static void test_delete_memory_region(void) vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_delete_memory_region); + if (disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + /* Delete the memory region, the guest should not die. */ vm_mem_region_delete(vm, MEM_REGION_SLOT); wait_for_vcpu(); @@ -553,7 +559,10 @@ int main(int argc, char *argv[]) { #ifdef __x86_64__ int i, loops; + int j, disable_slot_zap_quirk = 0; + if (kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_SLOT_ZAP_ALL) + disable_slot_zap_quirk = 1; /* * FIXME: the zero-memslot test fails on aarch64 and s390x because * KVM_RUN fails with ENOEXEC or EFAULT. @@ -579,13 +588,17 @@ int main(int argc, char *argv[]) else loops = 10; - pr_info("Testing MOVE of in-use region, %d loops\n", loops); - for (i = 0; i < loops; i++) - test_move_memory_region(); + for (j = 0; j <= disable_slot_zap_quirk; j++) { + pr_info("Testing MOVE of in-use region, %d loops, slot zap quirk %s\n", + loops, j ? "disabled" : "enabled"); + for (i = 0; i < loops; i++) + test_move_memory_region(!!j); - pr_info("Testing DELETE of in-use region, %d loops\n", loops); - for (i = 0; i < loops; i++) - test_delete_memory_region(); + pr_info("Testing DELETE of in-use region, %d loops, slot zap quirk %s\n", + loops, j ? "disabled" : "enabled"); + for (i = 0; i < loops; i++) + test_delete_memory_region(!!j); + } #endif return 0; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index f6b295e0b2d2..76cc2df9238a 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -47,15 +47,18 @@ static void guest_code(void) /* * Single step test, covers 2 basic instructions and 2 emulated * - * Enable interrupts during the single stepping to see that - * pending interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ + * Enable interrupts during the single stepping to see that pending + * interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ. + * + * Write MSR_IA32_TSC_DEADLINE to verify that KVM's fastpath handler + * exits to userspace due to single-step being enabled. */ asm volatile("ss_start: " "sti\n\t" "xor %%eax,%%eax\n\t" "cpuid\n\t" - "movl $0x1a0,%%ecx\n\t" - "rdmsr\n\t" + "movl $" __stringify(MSR_IA32_TSC_DEADLINE) ", %%ecx\n\t" + "wrmsr\n\t" "cli\n\t" : : : "eax", "ebx", "ecx", "edx"); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index e192720bfe14..74cf19661309 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -242,7 +242,7 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); + TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index b987a3d79715..0ddb63229bcb 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -157,7 +157,7 @@ int main(int argc, char *argv[]) int stage; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); + TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH)); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c index 7c70c0da4fb7..2e9197eb1652 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c @@ -160,6 +160,36 @@ static void test_sev(void *guest_code, uint64_t policy) kvm_vm_free(vm); } +static void guest_shutdown_code(void) +{ + struct desc_ptr idt; + + /* Clobber the IDT so that #UD is guaranteed to trigger SHUTDOWN. */ + memset(&idt, 0, sizeof(idt)); + __asm__ __volatile__("lidt %0" :: "m"(idt)); + + __asm__ __volatile__("ud2"); +} + +static void test_sev_es_shutdown(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + uint32_t type = KVM_X86_SEV_ES_VM; + + vm = vm_sev_create_with_one_vcpu(type, guest_shutdown_code, &vcpu); + + vm_sev_launch(vm, SEV_POLICY_ES, NULL); + + vcpu_run(vcpu); + TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SHUTDOWN, + "Wanted SHUTDOWN, got %s", + exit_reason_str(vcpu->run->exit_reason)); + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); @@ -171,6 +201,8 @@ int main(int argc, char *argv[]) test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG); test_sev(guest_sev_es_code, SEV_POLICY_ES); + test_sev_es_shutdown(); + if (kvm_has_cap(KVM_CAP_XCRS) && (xgetbv(0) & XFEATURE_MASK_X87_AVX) == XFEATURE_MASK_X87_AVX) { test_sync_vmsa(0); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 618cd2442390..88bcca188799 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -13,6 +13,7 @@ struct xapic_vcpu { struct kvm_vcpu *vcpu; bool is_x2apic; + bool has_xavic_errata; }; static void xapic_guest_code(void) @@ -31,6 +32,10 @@ static void xapic_guest_code(void) } } +#define X2APIC_RSVD_BITS_MASK (GENMASK_ULL(31, 20) | \ + GENMASK_ULL(17, 16) | \ + GENMASK_ULL(13, 13)) + static void x2apic_guest_code(void) { asm volatile("cli"); @@ -41,7 +46,12 @@ static void x2apic_guest_code(void) uint64_t val = x2apic_read_reg(APIC_IRR) | x2apic_read_reg(APIC_IRR + 0x10) << 32; - x2apic_write_reg(APIC_ICR, val); + if (val & X2APIC_RSVD_BITS_MASK) { + x2apic_write_reg_fault(APIC_ICR, val); + } else { + x2apic_write_reg(APIC_ICR, val); + GUEST_ASSERT_EQ(x2apic_read_reg(APIC_ICR), val); + } GUEST_SYNC(val); } while (1); } @@ -71,27 +81,28 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val) icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; if (!x->is_x2apic) { - val &= (-1u | (0xffull << (32 + 24))); - TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); - } else { - TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + if (!x->has_xavic_errata) + val &= (-1u | (0xffull << (32 + 24))); + } else if (val & X2APIC_RSVD_BITS_MASK) { + return; } -} -#define X2APIC_RSVED_BITS_MASK (GENMASK_ULL(31,20) | \ - GENMASK_ULL(17,16) | \ - GENMASK_ULL(13,13)) + if (x->has_xavic_errata) + TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + else + TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); +} static void __test_icr(struct xapic_vcpu *x, uint64_t val) { - if (x->is_x2apic) { - /* Hardware writing vICR register requires reserved bits 31:20, - * 17:16 and 13 kept as zero to avoid #GP exception. Data value - * written to vICR should mask out those bits above. - */ - val &= ~X2APIC_RSVED_BITS_MASK; - } - ____test_icr(x, val | APIC_ICR_BUSY); + /* + * The BUSY bit is reserved on both AMD and Intel, but only AMD treats + * it is as _must_ be zero. Intel simply ignores the bit. Don't test + * the BUSY bit for x2APIC, as there is no single correct behavior. + */ + if (!x->is_x2apic) + ____test_icr(x, val | APIC_ICR_BUSY); + ____test_icr(x, val & ~(u64)APIC_ICR_BUSY); } @@ -231,6 +242,15 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&x.vcpu, xapic_guest_code); x.is_x2apic = false; + /* + * AMD's AVIC implementation is buggy (fails to clear the ICR BUSY bit), + * and also diverges from KVM with respect to ICR2[23:0] (KVM and Intel + * drops writes, AMD does not). Account for the errata when checking + * that KVM reads back what was written. + */ + x.has_xavic_errata = host_cpu_is_amd && + get_kvm_amd_param_bool("avic"); + vcpu_clear_cpuid_feature(x.vcpu, X86_FEATURE_X2APIC); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index e149d0574961..2585087cdf5c 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -10,6 +10,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "hyperv.h" #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 1b90acb6e3fe..375d6285475e 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -40,27 +40,6 @@ static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, return 1; } -static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev, u32 last) -{ - struct kvm_coalesced_mmio_ring *ring; - unsigned avail; - - /* Are we able to batch it ? */ - - /* last is the first free entry - * check if we don't meet the first used entry - * there is always one unused entry in the buffer - */ - ring = dev->kvm->coalesced_mmio_ring; - avail = (ring->first - last - 1) % KVM_COALESCED_MMIO_MAX; - if (avail == 0) { - /* full */ - return 0; - } - - return 1; -} - static int coalesced_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val) @@ -74,9 +53,15 @@ static int coalesced_mmio_write(struct kvm_vcpu *vcpu, spin_lock(&dev->kvm->ring_lock); + /* + * last is the index of the entry to fill. Verify userspace hasn't + * set last to be out of range, and that there is room in the ring. + * Leave one entry free in the ring so that userspace can differentiate + * between an empty ring and a full ring. + */ insert = READ_ONCE(ring->last); - if (!coalesced_mmio_has_room(dev, insert) || - insert >= KVM_COALESCED_MMIO_MAX) { + if (insert >= KVM_COALESCED_MMIO_MAX || + (insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4f81366f8b61..05cbb2548d99 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -136,8 +136,8 @@ static int kvm_no_compat_open(struct inode *inode, struct file *file) #define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ .open = kvm_no_compat_open #endif -static int hardware_enable_all(void); -static void hardware_disable_all(void); +static int kvm_enable_virtualization(void); +static void kvm_disable_virtualization(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); @@ -1220,7 +1220,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) if (r) goto out_err_no_arch_destroy_vm; - r = hardware_enable_all(); + r = kvm_enable_virtualization(); if (r) goto out_err_no_disable; @@ -1263,7 +1263,7 @@ out_no_coalesced_mmio: mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); #endif out_err_no_mmu_notifier: - hardware_disable_all(); + kvm_disable_virtualization(); out_err_no_disable: kvm_arch_destroy_vm(kvm); out_err_no_arch_destroy_vm: @@ -1360,7 +1360,7 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); - hardware_disable_all(); + kvm_disable_virtualization(); mmdrop(mm); } @@ -3270,6 +3270,9 @@ static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3343,6 +3346,9 @@ static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3373,6 +3379,9 @@ static int __kvm_write_guest_page(struct kvm *kvm, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3576,7 +3585,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) int ret; while ((seg = next_segment(len, offset)) != 0) { - ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len); + ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, seg); if (ret < 0) return ret; offset = 0; @@ -5566,137 +5575,67 @@ static struct miscdevice kvm_dev = { }; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +static bool enable_virt_at_load = true; +module_param(enable_virt_at_load, bool, 0444); + __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); -static DEFINE_PER_CPU(bool, hardware_enabled); +static DEFINE_PER_CPU(bool, virtualization_enabled); +static DEFINE_MUTEX(kvm_usage_lock); static int kvm_usage_count; -static int __hardware_enable_nolock(void) +__weak void kvm_arch_enable_virtualization(void) +{ + +} + +__weak void kvm_arch_disable_virtualization(void) +{ + +} + +static int kvm_enable_virtualization_cpu(void) { - if (__this_cpu_read(hardware_enabled)) + if (__this_cpu_read(virtualization_enabled)) return 0; - if (kvm_arch_hardware_enable()) { + if (kvm_arch_enable_virtualization_cpu()) { pr_info("kvm: enabling virtualization on CPU%d failed\n", raw_smp_processor_id()); return -EIO; } - __this_cpu_write(hardware_enabled, true); + __this_cpu_write(virtualization_enabled, true); return 0; } -static void hardware_enable_nolock(void *failed) -{ - if (__hardware_enable_nolock()) - atomic_inc(failed); -} - static int kvm_online_cpu(unsigned int cpu) { - int ret = 0; - /* * Abort the CPU online process if hardware virtualization cannot * be enabled. Otherwise running VMs would encounter unrecoverable * errors when scheduled to this CPU. */ - mutex_lock(&kvm_lock); - if (kvm_usage_count) - ret = __hardware_enable_nolock(); - mutex_unlock(&kvm_lock); - return ret; + return kvm_enable_virtualization_cpu(); } -static void hardware_disable_nolock(void *junk) +static void kvm_disable_virtualization_cpu(void *ign) { - /* - * Note, hardware_disable_all_nolock() tells all online CPUs to disable - * hardware, not just CPUs that successfully enabled hardware! - */ - if (!__this_cpu_read(hardware_enabled)) + if (!__this_cpu_read(virtualization_enabled)) return; - kvm_arch_hardware_disable(); + kvm_arch_disable_virtualization_cpu(); - __this_cpu_write(hardware_enabled, false); + __this_cpu_write(virtualization_enabled, false); } static int kvm_offline_cpu(unsigned int cpu) { - mutex_lock(&kvm_lock); - if (kvm_usage_count) - hardware_disable_nolock(NULL); - mutex_unlock(&kvm_lock); + kvm_disable_virtualization_cpu(NULL); return 0; } -static void hardware_disable_all_nolock(void) -{ - BUG_ON(!kvm_usage_count); - - kvm_usage_count--; - if (!kvm_usage_count) - on_each_cpu(hardware_disable_nolock, NULL, 1); -} - -static void hardware_disable_all(void) -{ - cpus_read_lock(); - mutex_lock(&kvm_lock); - hardware_disable_all_nolock(); - mutex_unlock(&kvm_lock); - cpus_read_unlock(); -} - -static int hardware_enable_all(void) -{ - atomic_t failed = ATOMIC_INIT(0); - int r; - - /* - * Do not enable hardware virtualization if the system is going down. - * If userspace initiated a forced reboot, e.g. reboot -f, then it's - * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling - * after kvm_reboot() is called. Note, this relies on system_state - * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops - * hook instead of registering a dedicated reboot notifier (the latter - * runs before system_state is updated). - */ - if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || - system_state == SYSTEM_RESTART) - return -EBUSY; - - /* - * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() - * is called, and so on_each_cpu() between them includes the CPU that - * is being onlined. As a result, hardware_enable_nolock() may get - * invoked before kvm_online_cpu(), which also enables hardware if the - * usage count is non-zero. Disable CPU hotplug to avoid attempting to - * enable hardware multiple times. - */ - cpus_read_lock(); - mutex_lock(&kvm_lock); - - r = 0; - - kvm_usage_count++; - if (kvm_usage_count == 1) { - on_each_cpu(hardware_enable_nolock, &failed, 1); - - if (atomic_read(&failed)) { - hardware_disable_all_nolock(); - r = -EBUSY; - } - } - - mutex_unlock(&kvm_lock); - cpus_read_unlock(); - - return r; -} - static void kvm_shutdown(void) { /* @@ -5712,34 +5651,32 @@ static void kvm_shutdown(void) */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; - on_each_cpu(hardware_disable_nolock, NULL, 1); + on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1); } static int kvm_suspend(void) { /* * Secondary CPUs and CPU hotplug are disabled across the suspend/resume - * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count - * is stable. Assert that kvm_lock is not held to ensure the system - * isn't suspended while KVM is enabling hardware. Hardware enabling - * can be preempted, but the task cannot be frozen until it has dropped - * all locks (userspace tasks are frozen via a fake signal). + * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage + * count is stable. Assert that kvm_usage_lock is not held to ensure + * the system isn't suspended while KVM is enabling hardware. Hardware + * enabling can be preempted, but the task cannot be frozen until it has + * dropped all locks (userspace tasks are frozen via a fake signal). */ - lockdep_assert_not_held(&kvm_lock); + lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); - if (kvm_usage_count) - hardware_disable_nolock(NULL); + kvm_disable_virtualization_cpu(NULL); return 0; } static void kvm_resume(void) { - lockdep_assert_not_held(&kvm_lock); + lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); - if (kvm_usage_count) - WARN_ON_ONCE(__hardware_enable_nolock()); + WARN_ON_ONCE(kvm_enable_virtualization_cpu()); } static struct syscore_ops kvm_syscore_ops = { @@ -5747,13 +5684,95 @@ static struct syscore_ops kvm_syscore_ops = { .resume = kvm_resume, .shutdown = kvm_shutdown, }; + +static int kvm_enable_virtualization(void) +{ + int r; + + guard(mutex)(&kvm_usage_lock); + + if (kvm_usage_count++) + return 0; + + kvm_arch_enable_virtualization(); + + r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); + if (r) + goto err_cpuhp; + + register_syscore_ops(&kvm_syscore_ops); + + /* + * Undo virtualization enabling and bail if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight operation to enable virtualization after + * syscore_shutdown() is called, i.e. without kvm_shutdown() being + * invoked. Note, this relies on system_state being set _before_ + * kvm_shutdown(), e.g. to ensure either kvm_shutdown() is invoked + * or this CPU observes the impending shutdown. Which is why KVM uses + * a syscore ops hook instead of registering a dedicated reboot + * notifier (the latter runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) { + r = -EBUSY; + goto err_rebooting; + } + + return 0; + +err_rebooting: + unregister_syscore_ops(&kvm_syscore_ops); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); +err_cpuhp: + kvm_arch_disable_virtualization(); + --kvm_usage_count; + return r; +} + +static void kvm_disable_virtualization(void) +{ + guard(mutex)(&kvm_usage_lock); + + if (--kvm_usage_count) + return; + + unregister_syscore_ops(&kvm_syscore_ops); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); + kvm_arch_disable_virtualization(); +} + +static int kvm_init_virtualization(void) +{ + if (enable_virt_at_load) + return kvm_enable_virtualization(); + + return 0; +} + +static void kvm_uninit_virtualization(void) +{ + if (enable_virt_at_load) + kvm_disable_virtualization(); +} #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ -static int hardware_enable_all(void) +static int kvm_enable_virtualization(void) +{ + return 0; +} + +static int kvm_init_virtualization(void) { return 0; } -static void hardware_disable_all(void) +static void kvm_disable_virtualization(void) +{ + +} + +static void kvm_uninit_virtualization(void) { } @@ -6454,15 +6473,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) int r; int cpu; -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", - kvm_online_cpu, kvm_offline_cpu); - if (r) - return r; - - register_syscore_ops(&kvm_syscore_ops); -#endif - /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); @@ -6473,10 +6483,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) offsetofend(struct kvm_vcpu, stats_id) - offsetof(struct kvm_vcpu, arch), NULL); - if (!kvm_vcpu_cache) { - r = -ENOMEM; - goto err_vcpu_cache; - } + if (!kvm_vcpu_cache) + return -ENOMEM; for_each_possible_cpu(cpu) { if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), @@ -6510,6 +6518,10 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kvm_gmem_init(module); + r = kvm_init_virtualization(); + if (r) + goto err_virt; + /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! @@ -6523,6 +6535,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) return 0; err_register: + kvm_uninit_virtualization(); +err_virt: kvm_vfio_ops_exit(); err_vfio: kvm_async_pf_deinit(); @@ -6533,11 +6547,6 @@ err_cpu_kick_mask: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); -err_vcpu_cache: -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - unregister_syscore_ops(&kvm_syscore_ops); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); -#endif return r; } EXPORT_SYMBOL_GPL(kvm_init); @@ -6553,16 +6562,14 @@ void kvm_exit(void) */ misc_deregister(&kvm_dev); + kvm_uninit_virtualization(); + debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_vfio_ops_exit(); kvm_async_pf_deinit(); -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - unregister_syscore_ops(&kvm_syscore_ops); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); -#endif kvm_irqfd_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); |