diff options
Diffstat (limited to 'arch/x86/kvm/vmx/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 2143 |
1 files changed, 1301 insertions, 842 deletions
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index be7c19374fdd..c37a89eda90f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -12,6 +12,7 @@ * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/highmem.h> #include <linux/hrtimer.h> @@ -37,21 +38,22 @@ #include <asm/desc.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> +#include <asm/fred.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> -#include <asm/kexec.h> +#include <asm/reboot.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> #include <asm/mshyperv.h> #include <asm/mwait.h> #include <asm/spec-ctrl.h> -#include <asm/virtext.h> #include <asm/vmx.h> +#include <trace/events/ipi.h> + #include "capabilities.h" #include "cpuid.h" -#include "evmcs.h" #include "hyperv.h" #include "kvm_onhyperv.h" #include "irq.h" @@ -66,6 +68,8 @@ #include "vmcs12.h" #include "vmx.h" #include "x86.h" +#include "smm.h" +#include "vmx_onhyperv.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -82,28 +86,31 @@ bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); static bool __read_mostly enable_vnmi = 1; -module_param_named(vnmi, enable_vnmi, bool, S_IRUGO); +module_param_named(vnmi, enable_vnmi, bool, 0444); bool __read_mostly flexpriority_enabled = 1; -module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); +module_param_named(flexpriority, flexpriority_enabled, bool, 0444); bool __read_mostly enable_ept = 1; -module_param_named(ept, enable_ept, bool, S_IRUGO); +module_param_named(ept, enable_ept, bool, 0444); bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, - enable_unrestricted_guest, bool, S_IRUGO); + enable_unrestricted_guest, bool, 0444); bool __read_mostly enable_ept_ad_bits = 1; -module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); +module_param_named(eptad, enable_ept_ad_bits, bool, 0444); static bool __read_mostly emulate_invalid_guest_state = true; -module_param(emulate_invalid_guest_state, bool, S_IRUGO); +module_param(emulate_invalid_guest_state, bool, 0444); static bool __read_mostly fasteoi = 1; -module_param(fasteoi, bool, S_IRUGO); +module_param(fasteoi, bool, 0444); + +module_param(enable_apicv, bool, 0444); -module_param(enable_apicv, bool, S_IRUGO); +bool __read_mostly enable_ipiv = true; +module_param(enable_ipiv, bool, 0444); /* * If nested=1, nested virtualization is supported, i.e., guests may use @@ -111,10 +118,13 @@ module_param(enable_apicv, bool, S_IRUGO); * use VMX instructions. */ static bool __read_mostly nested = 1; -module_param(nested, bool, S_IRUGO); +module_param(nested, bool, 0444); bool __read_mostly enable_pml = 1; -module_param_named(pml, enable_pml, bool, S_IRUGO); +module_param_named(pml, enable_pml, bool, 0444); + +static bool __read_mostly error_on_inconsistent_vmcs_config = true; +module_param(error_on_inconsistent_vmcs_config, bool, 0444); static bool __read_mostly dump_invalid_vmcs = 0; module_param(dump_invalid_vmcs, bool, 0644); @@ -152,11 +162,12 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); /* * List of MSRs that can be directly passed to the guest. - * In addition to these x2apic and PT MSRs are handled specially. + * In addition to these x2apic, PT and LBR MSRs are handled specially. */ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_IA32_SPEC_CTRL, MSR_IA32_PRED_CMD, + MSR_IA32_FLUSH_CMD, MSR_IA32_TSC, #ifdef CONFIG_X86_64 MSR_FS_BASE, @@ -229,9 +240,6 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; -/* Control for disabling CPU Fill buffer clear */ -static bool __read_mostly vmx_fb_clear_ctrl_available; - static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; @@ -247,14 +255,9 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) return 0; } - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { - u64 msr; - - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); - if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; - return 0; - } + if (host_arch_capabilities & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; } /* If set to auto use the default l1tf mitigation method */ @@ -358,22 +361,9 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) { if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param))) - return sprintf(s, "???\n"); - - return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); -} - -static void vmx_setup_fb_clear_ctrl(void) -{ - u64 msr; + return sysfs_emit(s, "???\n"); - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) && - !boot_cpu_has_bug(X86_BUG_MDS) && - !boot_cpu_has_bug(X86_BUG_TAA)) { - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); - if (msr & ARCH_CAP_FB_CLEAR_CTRL) - vmx_fb_clear_ctrl_available = true; - } + return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) @@ -401,7 +391,18 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + /* + * Disable VERW's behavior of clearing CPU buffers for the guest if the + * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled + * the mitigation. Disabling the clearing behavior provides a + * performance boost for guests that aren't aware that manually clearing + * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry + * and VM-Exit. + */ + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && + !boot_cpu_has_bug(X86_BUG_MDS) && + !boot_cpu_has_bug(X86_BUG_TAA); /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS @@ -433,39 +434,51 @@ do { \ pr_warn_ratelimited(fmt); \ } while (0) -asmlinkage void vmread_error(unsigned long field, bool fault) +noinline void vmread_error(unsigned long field) +{ + vmx_insn_failed("vmread failed: field=%lx\n", field); +} + +#ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +noinstr void vmread_error_trampoline2(unsigned long field, bool fault) { - if (fault) + if (fault) { kvm_spurious_fault(); - else - vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); + } else { + instrumentation_begin(); + vmread_error(field); + instrumentation_end(); + } } +#endif noinline void vmwrite_error(unsigned long field, unsigned long value) { - vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n", + vmx_insn_failed("vmwrite failed: field=%lx val=%lx err=%u\n", field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr); + vmx_insn_failed("vmclear failed: %p/%llx err=%u\n", + vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr); + vmx_insn_failed("vmptrld failed: %p/%llx err=%u\n", + vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) { - vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", + vmx_insn_failed("invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", ext, vpid, gva); } noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) { - vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", + vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", ext, eptp, gpa); } @@ -480,8 +493,8 @@ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); -struct vmcs_config vmcs_config; -struct vmx_capability vmx_capability; +struct vmcs_config vmcs_config __ro_after_init; +struct vmx_capability vmx_capability __ro_after_init; #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ @@ -515,34 +528,93 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) +static struct kvm_x86_ops vmx_x86_ops __initdata; + static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); -static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; - struct hv_partition_assist_pg **p_hv_pa_pg = - &to_kvm_hv(vcpu->kvm)->hv_pa_pg; - /* - * Synthetic VM-Exit is not enabled in current code and so All - * evmcs in singe VM shares same assist page. - */ - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); + hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); - if (!*p_hv_pa_pg) + if (partition_assist_page == INVALID_PAGE) return -ENOMEM; evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; - evmcs->partition_assist_page = - __pa(*p_hv_pa_pg); + evmcs->partition_assist_page = partition_assist_page; evmcs->hv_vm_id = (unsigned long)vcpu->kvm; evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; return 0; } +static __init void hv_init_evmcs(void) +{ + int cpu; + + if (!enlightened_vmcs) + return; + + /* + * Enlightened VMCS usage should be recommended and the host needs + * to support eVMCS v1 or above. + */ + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && + (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= + KVM_EVMCS_VERSION) { + + /* Check that we have assist pages on all online CPUs */ + for_each_online_cpu(cpu) { + if (!hv_get_vp_assist_page(cpu)) { + enlightened_vmcs = false; + break; + } + } + + if (enlightened_vmcs) { + pr_info("Using Hyper-V Enlightened VMCS\n"); + static_branch_enable(&__kvm_is_using_evmcs); + } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) + vmx_x86_ops.enable_l2_tlb_flush + = hv_enable_l2_tlb_flush; + + } else { + enlightened_vmcs = false; + } +} + +static void hv_reset_evmcs(void) +{ + struct hv_vp_assist_page *vp_ap; + + if (!kvm_is_using_evmcs()) + return; + + /* + * KVM should enable eVMCS if and only if all CPUs have a VP assist + * page, and should reject CPU onlining if eVMCS is enabled the CPU + * doesn't have a VP assist page allocated. + */ + vp_ap = hv_get_vp_assist_page(smp_processor_id()); + if (WARN_ON_ONCE(!vp_ap)) + return; + + /* + * Reset everything to support using non-enlightened VMCS access later + * (e.g. when we reload the module with enlightened_vmcs=0) + */ + vp_ap->nested_control.features.directhypercall = 0; + vp_ap->current_nested_vmcs = 0; + vp_ap->enlighten_vmentry = 0; +} + +#else /* IS_ENABLED(CONFIG_HYPERV) */ +static void hv_init_evmcs(void) {} +static void hv_reset_evmcs(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* @@ -598,25 +670,14 @@ static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) return flexpriority_enabled && lapic_in_kernel(vcpu); } -static int possible_passthrough_msr_slot(u32 msr) -{ - u32 i; - - for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) - if (vmx_possible_passthrough_msrs[i] == msr) - return i; - - return -ENOENT; -} - -static bool is_valid_passthrough_msr(u32 msr) +static int vmx_get_passthrough_msr_slot(u32 msr) { - bool r; + int i; switch (msr) { case 0x800 ... 0x8ff: /* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */ - return true; + return -ENOENT; case MSR_IA32_RTIT_STATUS: case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: @@ -631,14 +692,16 @@ static bool is_valid_passthrough_msr(u32 msr) case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8: case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8: /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */ - return true; + return -ENOENT; } - r = possible_passthrough_msr_slot(msr) != -ENOENT; - - WARN(!r, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); + for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { + if (vmx_possible_passthrough_msrs[i] == msr) + return i; + } - return r; + WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); + return -ENOENT; } struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) @@ -667,17 +730,51 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, return ret; } -#ifdef CONFIG_KEXEC_CORE -static void crash_vmclear_local_loaded_vmcss(void) +/* + * Disable VMX and clear CR4.VMXE (even if VMXOFF faults) + * + * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to + * atomically track post-VMXON state, e.g. this may be called in NMI context. + * Eat all faults as all other faults on VMXOFF faults are mode related, i.e. + * faults are guaranteed to be due to the !post-VMXON check unless the CPU is + * magically in RM, VM86, compat mode, or at CPL>0. + */ +static int kvm_cpu_vmxoff(void) +{ + asm goto("1: vmxoff\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "cc", "memory" : fault); + + cr4_clear_bits(X86_CR4_VMXE); + return 0; + +fault: + cr4_clear_bits(X86_CR4_VMXE); + return -EIO; +} + +static void vmx_emergency_disable(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; + kvm_rebooting = true; + + /* + * Note, CR4.VMXE can be _cleared_ in NMI context, but it can only be + * set in task context. If this races with VMX is disabled by an NMI, + * VMCLEAR and VMXOFF may #UD, but KVM will eat those faults due to + * kvm_rebooting set. + */ + if (!(__read_cr4() & X86_CR4_VMXE)) + return; + list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), loaded_vmcss_on_cpu_link) vmcs_clear(v->vmcs); + + kvm_cpu_vmxoff(); } -#endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) { @@ -798,7 +895,7 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; - else { + else { int mask = 0, match = 0; if (enable_ept && (eb & (1u << PF_VECTOR))) { @@ -835,8 +932,7 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; - return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, - MSR_IA32_SPEC_CTRL); + return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, msr); } unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) @@ -851,13 +947,13 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) * to change it directly without causing a vmexit. In that case read * it after vmexit and store it in vmx->spec_ctrl. */ - if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) + if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)) flags |= VMX_RUN_SAVE_SPEC_CTRL; return flags; } -static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, +static __always_inline void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { vm_entry_controls_clearbit(vmx, entry); @@ -915,7 +1011,7 @@ skip_guest: vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); } -static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, +static __always_inline void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit, unsigned long guest_val_vmcs, unsigned long host_val_vmcs, u64 guest_val, u64 host_val) @@ -1188,8 +1284,6 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i; - vmx->req_immediate_exit = false; - /* * Note that guest MSRs to be saved/restored can also be changed * when guest state is loaded. This happens when guest transitions @@ -1207,7 +1301,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) } } - if (vmx->nested.need_vmcs12_to_shadow_sync) + if (vmx->nested.need_vmcs12_to_shadow_sync) nested_sync_vmcs12_to_shadow(vcpu); if (vmx->guest_state_loaded) @@ -1341,8 +1435,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, /* * No indirect branch prediction barrier needed when switching - * the active VMCS within a guest, e.g. on nested VM-Enter. - * The L1 VMM can protect itself with retpolines, IBPB or IBRS. + * the active VMCS within a vCPU, unless IBRS is advertised to + * the vCPU. To minimize the number of IBPBs executed, KVM + * performs IBPB on nested VM-Exit (a single nested transition + * may switch the active VMCS multiple times). */ if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)) indirect_branch_prediction_barrier(); @@ -1425,6 +1521,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long old_rflags; + /* + * Unlike CR0 and CR4, RFLAGS handling requires checking if the vCPU + * is an unrestricted guest in order to mark L2 as needing emulation + * if L1 runs L2 as a restricted guest. + */ if (is_unrestricted_guest(vcpu)) { kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); vmx->rflags = rflags; @@ -1550,8 +1651,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1562,9 +1663,9 @@ static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, */ if (to_vmx(vcpu)->exit_reason.enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); - return false; + return X86EMUL_PROPAGATE_FAULT; } - return true; + return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -1604,8 +1705,8 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) if (!instr_len) goto rip_updated; - WARN(exit_reason.enclave_mode, - "KVM: skipping instruction after SGX enclave VM-Exit"); + WARN_ONCE(exit_reason.enclave_mode, + "skipping instruction after SGX enclave VM-Exit"); orig_rip = kvm_rip_read(vcpu); rip = orig_rip + instr_len; @@ -1645,17 +1746,25 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) /* * Per the SDM, MTF takes priority over debug-trap exceptions besides - * T-bit traps. As instruction emulation is completed (i.e. at the - * instruction boundary), any #DB exception pending delivery must be a - * debug-trap. Record the pending MTF state to be delivered in + * TSS T-bit traps and ICEBP (INT1). KVM doesn't emulate T-bit traps + * or ICEBP (in the emulator proper), and skipping of ICEBP after an + * intercepted #DB deliberately avoids single-step #DB and MTF updates + * as ICEBP is higher priority than both. As instruction emulation is + * completed at this point (i.e. KVM is at the instruction boundary), + * any #DB exception pending delivery must be a debug-trap of lower + * priority than MTF. Record the pending MTF state to be delivered in * vmx_check_nested_events(). */ if (nested_cpu_has_mtf(vmcs12) && (!vcpu->arch.exception.pending || - vcpu->arch.exception.nr == DB_VECTOR)) + vcpu->arch.exception.vector == DB_VECTOR) && + (!vcpu->arch.exception_vmexit.pending || + vcpu->arch.exception_vmexit.vector == DB_VECTOR)) { vmx->nested.mtf_pending = true; - else + kvm_make_request(KVM_REQ_EVENT, vcpu); + } else { vmx->nested.mtf_pending = false; + } } static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -1677,32 +1786,40 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } -static void vmx_queue_exception(struct kvm_vcpu *vcpu) +static void vmx_inject_exception(struct kvm_vcpu *vcpu) { + struct kvm_queued_exception *ex = &vcpu->arch.exception; + u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned nr = vcpu->arch.exception.nr; - bool has_error_code = vcpu->arch.exception.has_error_code; - u32 error_code = vcpu->arch.exception.error_code; - u32 intr_info = nr | INTR_INFO_VALID_MASK; - kvm_deliver_exception_payload(vcpu); + kvm_deliver_exception_payload(vcpu, ex); - if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + if (ex->has_error_code) { + /* + * Despite the error code being architecturally defined as 32 + * bits, and the VMCS field being 32 bits, Intel CPUs and thus + * VMX don't actually supporting setting bits 31:16. Hardware + * will (should) never provide a bogus error code, but AMD CPUs + * do generate error codes with bits 31:16 set, and so KVM's + * ABI lets userspace shove in arbitrary 32-bit values. Drop + * the upper bits to avoid VM-Fail, losing information that + * doesn't really exist is preferable to killing the VM. + */ + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; } if (vmx->rmode.vm86_active) { int inc_eip = 0; - if (kvm_exception_is_soft(nr)) + if (kvm_exception_is_soft(ex->vector)) inc_eip = vcpu->arch.event_exit_inst_len; - kvm_inject_realmode_interrupt(vcpu, nr, inc_eip); + kvm_inject_realmode_interrupt(vcpu, ex->vector, inc_eip); return; } WARN_ON_ONCE(vmx->emulation_required); - if (kvm_exception_is_soft(nr)) { + if (kvm_exception_is_soft(ex->vector)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmx->vcpu.arch.event_exit_inst_len); intr_info |= INTR_TYPE_SOFT_EXCEPTION; @@ -1787,48 +1904,64 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) return vmcs12->tsc_multiplier; - return kvm_default_tsc_scaling_ratio; + return kvm_caps.default_tsc_scaling_ratio; } -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu) { - vmcs_write64(TSC_OFFSET, offset); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); } -static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { - vmcs_write64(TSC_MULTIPLIER, multiplier); + vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } /* - * nested_vmx_allowed() checks whether a guest should be allowed to use VMX - * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for - * all guests if the "nested" module option is off, and can also be disabled - * for a single guest by disabling its VMX cpuid bit. + * Userspace is allowed to set any supported IA32_FEATURE_CONTROL regardless of + * guest CPUID. Note, KVM allows userspace to set "VMX in SMX" to maintain + * backwards compatibility even though KVM doesn't support emulating SMX. And + * because userspace set "VMX in SMX", the guest must also be allowed to set it, + * e.g. if the MSR is left unlocked and the guest does a RMW operation. */ -bool nested_vmx_allowed(struct kvm_vcpu *vcpu) -{ - return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX); -} +#define KVM_SUPPORTED_FEATURE_CONTROL (FEAT_CTL_LOCKED | \ + FEAT_CTL_VMX_ENABLED_INSIDE_SMX | \ + FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX | \ + FEAT_CTL_SGX_LC_ENABLED | \ + FEAT_CTL_SGX_ENABLED | \ + FEAT_CTL_LMCE_ENABLED) -static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, - uint64_t val) +static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, + struct msr_data *msr) { - uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits; + uint64_t valid_bits; + + /* + * Ensure KVM_SUPPORTED_FEATURE_CONTROL is updated when new bits are + * exposed to the guest. + */ + WARN_ON_ONCE(vmx->msr_ia32_feature_control_valid_bits & + ~KVM_SUPPORTED_FEATURE_CONTROL); + + if (!msr->host_initiated && + (vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED)) + return false; + + if (msr->host_initiated) + valid_bits = KVM_SUPPORTED_FEATURE_CONTROL; + else + valid_bits = vmx->msr_ia32_feature_control_valid_bits; - return !(val & ~valid_bits); + return !(msr->data & ~valid_bits); } static int vmx_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + 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); - case MSR_IA32_PERF_CAPABILITIES: - msr->data = vmx_get_perf_capabilities(); - return 0; default: return KVM_MSR_RET_INVALID; } @@ -1910,12 +2043,13 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - if (!nested_vmx_allowed(vcpu)) + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: + if (!guest_can_use(vcpu, X86_FEATURE_VMX)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) return 1; +#ifdef CONFIG_KVM_HYPERV /* * Enlightened VMCS v1 doesn't have certain VMCS fields but * instead of just ignoring the features, different Hyper-V @@ -1923,10 +2057,10 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * sanity checking and refuse to boot. Filter all unsupported * features out. */ - if (!msr_info->host_initiated && - vmx->nested.enlightened_vmcs_enabled) - nested_evmcs_filter_control_msr(msr_info->index, + if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) + nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); +#endif break; case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest()) @@ -1999,15 +2133,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) +static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { - u64 debugctl = vmx_supported_debugctl(); + u64 debugctl = 0; - if (!intel_pmu_lbr_is_enabled(vcpu)) - debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && + (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) - debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && + (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) + debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; return debugctl; } @@ -2081,11 +2217,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: { - u64 invalid = data & ~vcpu_supported_debugctl(vcpu); + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); } @@ -2111,6 +2247,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (is_noncanonical_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) return 1; + + if (is_guest_mode(vcpu) && + ((vmx->nested.msrs.entry_ctls_high & VM_ENTRY_LOAD_BNDCFGS) || + (vmx->nested.msrs.exit_ctls_high & VM_EXIT_CLEAR_BNDCFGS))) + get_vmcs12(vcpu)->guest_bndcfgs = data; + vmcs_write64(GUEST_BNDCFGS, data); break; case MSR_IA32_UMWAIT_CONTROL: @@ -2158,47 +2300,17 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) return 1; goto find_uret_msr; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && - !guest_has_pred_cmd_msr(vcpu)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - if (!boot_cpu_has(X86_FEATURE_IBPB)) - return 1; - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. - */ - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W); - break; case MSR_IA32_CR_PAT: - if (!kvm_pat_valid(data)) - return 1; + ret = kvm_set_msr_common(vcpu, msr_info); + if (ret) + break; if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) get_vmcs12(vcpu)->guest_ia32_pat = data; - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, data); - vcpu->arch.pat = data; - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); break; case MSR_IA32_MCG_EXT_CTL: if ((!msr_info->host_initiated && @@ -2209,10 +2321,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.mcg_ext_ctl = data; break; case MSR_IA32_FEAT_CTL: - if (!vmx_feature_control_msr_valid(vcpu, data) || - (to_vmx(vcpu)->msr_ia32_feature_control & - FEAT_CTL_LOCKED && !msr_info->host_initiated)) + if (!is_vmx_feature_control_msr_valid(vmx, msr_info)) return 1; + vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) vmx_leave_nested(vcpu); @@ -2240,10 +2351,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx->msr_ia32_sgxlepubkeyhash [msr_index - MSR_IA32_SGXLEPUBKEYHASH0] = data; break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ - if (!nested_vmx_allowed(vcpu)) + if (!guest_can_use(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: @@ -2310,9 +2421,20 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (data & PMU_CAP_LBR_FMT) { if ((data & PMU_CAP_LBR_FMT) != - (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)) + (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT)) return 1; - if (!intel_pmu_lbr_is_compatible(vcpu)) + if (!cpuid_model_is_consistent(vcpu)) + return 1; + } + if (data & PERF_CAP_PEBS_FORMAT) { + if ((data & PERF_CAP_PEBS_MASK) != + (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) + return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_DS)) + return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_DTES64)) + return 1; + if (!cpuid_model_is_consistent(vcpu)) return 1; } ret = kvm_set_msr_common(vcpu, msr_info); @@ -2377,88 +2499,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static __init int cpu_has_kvm_support(void) -{ - return cpu_has_vmx(); -} - -static __init int vmx_disabled_by_bios(void) -{ - return !boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !boot_cpu_has(X86_FEATURE_VMX); -} - -static int kvm_cpu_vmxon(u64 vmxon_pointer) -{ - u64 msr; - - cr4_set_bits(X86_CR4_VMXE); - - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" - _ASM_EXTABLE(1b, %l[fault]) - : : [vmxon_pointer] "m"(vmxon_pointer) - : : fault); - return 0; - -fault: - WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", - rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); - cr4_clear_bits(X86_CR4_VMXE); - - return -EFAULT; -} - -static int vmx_hardware_enable(void) -{ - int cpu = raw_smp_processor_id(); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - int r; - - if (cr4_read_shadow() & X86_CR4_VMXE) - return -EBUSY; - - /* - * This can happen if we hot-added a CPU but failed to allocate - * VP assist page for it. - */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) - return -EFAULT; - - intel_pt_handle_vmx(1); - - r = kvm_cpu_vmxon(phys_addr); - if (r) { - intel_pt_handle_vmx(0); - return r; - } - - if (enable_ept) - ept_sync_global(); - - return 0; -} - -static void vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v, *n; - - list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - __loaded_vmcs_clear(v); -} - -static void vmx_hardware_disable(void) -{ - vmclear_local_loaded_vmcss(); - - if (cpu_vmxoff()) - kvm_spurious_fault(); - - intel_pt_handle_vmx(0); -} - /* * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID * directly instead of going through cpu_has(), to ensure KVM is trapping @@ -2470,8 +2510,31 @@ static bool cpu_has_sgx(void) return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); } -static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32 *result) +/* + * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they + * can't be used due to errata where VM Exit may incorrectly clear + * IA32_PERF_GLOBAL_CTRL[34:32]. Work around the errata by using the + * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. + */ +static bool cpu_has_perf_global_ctrl_bug(void) +{ + if (boot_cpu_data.x86 == 0x6) { + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_NEHALEM_EP: /* AAK155 */ + case INTEL_FAM6_NEHALEM: /* AAP115 */ + case INTEL_FAM6_WESTMERE: /* AAT100 */ + case INTEL_FAM6_WESTMERE_EP: /* BC86,AAY89,BD102 */ + case INTEL_FAM6_NEHALEM_EX: /* BA97 */ + return true; + default: + break; + } + } + + return false; +} + +static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { u32 vmx_msr_low, vmx_msr_high; u32 ctl = ctl_min | ctl_opt; @@ -2489,74 +2552,56 @@ static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, return 0; } -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, - struct vmx_capability *vmx_cap) +static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) +{ + u64 allowed; + + rdmsrl(msr, allowed); + + return ctl_opt & allowed; +} + +static int setup_vmcs_config(struct vmcs_config *vmcs_conf, + struct vmx_capability *vmx_cap) { u32 vmx_msr_low, vmx_msr_high; - u32 min, opt, min2, opt2; 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 misc_msr; + int i; + + /* + * LOAD/SAVE_DEBUG_CONTROLS are absent because both are mandatory. + * SAVE_IA32_PAT and SAVE_IA32_EFER are absent because KVM always + * intercepts writes to PAT and EFER, i.e. never enables those controls. + */ + struct { + u32 entry_control; + u32 exit_control; + } const vmcs_entry_exit_pairs[] = { + { VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL }, + { VM_ENTRY_LOAD_IA32_PAT, VM_EXIT_LOAD_IA32_PAT }, + { VM_ENTRY_LOAD_IA32_EFER, VM_EXIT_LOAD_IA32_EFER }, + { VM_ENTRY_LOAD_BNDCFGS, VM_EXIT_CLEAR_BNDCFGS }, + { VM_ENTRY_LOAD_IA32_RTIT_CTL, VM_EXIT_CLEAR_IA32_RTIT_CTL }, + }; memset(vmcs_conf, 0, sizeof(*vmcs_conf)); - min = CPU_BASED_HLT_EXITING | -#ifdef CONFIG_X86_64 - CPU_BASED_CR8_LOAD_EXITING | - CPU_BASED_CR8_STORE_EXITING | -#endif - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETTING | - CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING | - CPU_BASED_INVLPG_EXITING | - CPU_BASED_RDPMC_EXITING; - - opt = CPU_BASED_TPR_SHADOW | - CPU_BASED_USE_MSR_BITMAPS | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) + + if (adjust_vmx_controls(KVM_REQUIRED_VMX_CPU_BASED_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_CPU_BASED_VM_EXEC_CONTROL, + MSR_IA32_VMX_PROCBASED_CTLS, + &_cpu_based_exec_control)) return -EIO; -#ifdef CONFIG_X86_64 - if (_cpu_based_exec_control & CPU_BASED_TPR_SHADOW) - _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & - ~CPU_BASED_CR8_STORE_EXITING; -#endif if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { - min2 = 0; - opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_ENABLE_VPID | - SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST | - SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_DESC | - SECONDARY_EXEC_ENABLE_RDTSCP | - SECONDARY_EXEC_ENABLE_INVPCID | - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_SHADOW_VMCS | - SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_RDRAND_EXITING | - SECONDARY_EXEC_ENABLE_PML | - SECONDARY_EXEC_TSC_SCALING | - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | - SECONDARY_EXEC_PT_USE_GPA | - SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_BUS_LOCK_DETECTION; - if (cpu_has_sgx()) - opt2 |= SECONDARY_EXEC_ENCLS_EXITING; - if (adjust_vmx_controls(min2, opt2, + if (adjust_vmx_controls(KVM_REQUIRED_VMX_SECONDARY_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_SECONDARY_VM_EXEC_CONTROL, MSR_IA32_VMX_PROCBASED_CTLS2, - &_cpu_based_2nd_exec_control) < 0) + &_cpu_based_2nd_exec_control)) return -EIO; } #ifndef CONFIG_X86_64 @@ -2574,43 +2619,45 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, &vmx_cap->ept, &vmx_cap->vpid); - if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { - /* CR3 accesses and invlpg don't need to cause VM Exits when EPT - enabled */ - _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_INVLPG_EXITING); - } else if (vmx_cap->ept) { - vmx_cap->ept = 0; + if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) && + vmx_cap->ept) { pr_warn_once("EPT CAP should not exist if not support " "1-setting enable EPT VM-execution control\n"); + + if (error_on_inconsistent_vmcs_config) + return -EIO; + + vmx_cap->ept = 0; } if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && - vmx_cap->vpid) { - vmx_cap->vpid = 0; + vmx_cap->vpid) { pr_warn_once("VPID CAP should not exist if not support " "1-setting enable VPID VM-execution control\n"); + + if (error_on_inconsistent_vmcs_config) + return -EIO; + + vmx_cap->vpid = 0; } - min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT; -#ifdef CONFIG_X86_64 - min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; -#endif - opt = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_EXIT_LOAD_IA32_PAT | - VM_EXIT_LOAD_IA32_EFER | - VM_EXIT_CLEAR_BNDCFGS | - VM_EXIT_PT_CONCEAL_PIP | - VM_EXIT_CLEAR_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, - &_vmexit_control) < 0) + if (!cpu_has_sgx()) + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_ENCLS_EXITING; + + if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) + _cpu_based_3rd_exec_control = + adjust_vmx_controls64(KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL, + MSR_IA32_VMX_PROCBASED_CTLS3); + + if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_EXIT_CONTROLS, + KVM_OPTIONAL_VMX_VM_EXIT_CONTROLS, + MSR_IA32_VMX_EXIT_CTLS, + &_vmexit_control)) return -EIO; - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR | - PIN_BASED_VMX_PREEMPTION_TIMER; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, - &_pin_based_exec_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_PIN_BASED_VM_EXEC_CONTROL, + KVM_OPTIONAL_VMX_PIN_BASED_VM_EXEC_CONTROL, + MSR_IA32_VMX_PINBASED_CTLS, + &_pin_based_exec_control)) return -EIO; if (cpu_has_broken_vmx_preemption_timer()) @@ -2619,40 +2666,28 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; - min = VM_ENTRY_LOAD_DEBUG_CONTROLS; - opt = VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_ENTRY_LOAD_IA32_PAT | - VM_ENTRY_LOAD_IA32_EFER | - VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_PT_CONCEAL_PIP | - VM_ENTRY_LOAD_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, - &_vmentry_control) < 0) + if (adjust_vmx_controls(KVM_REQUIRED_VMX_VM_ENTRY_CONTROLS, + KVM_OPTIONAL_VMX_VM_ENTRY_CONTROLS, + MSR_IA32_VMX_ENTRY_CTLS, + &_vmentry_control)) return -EIO; - /* - * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they - * can't be used due to an errata where VM Exit may incorrectly clear - * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the - * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. - */ - if (boot_cpu_data.x86 == 0x6) { - switch (boot_cpu_data.x86_model) { - case 26: /* AAK155 */ - case 30: /* AAP115 */ - case 37: /* AAT100 */ - case 44: /* BC86,AAY89,BD102 */ - case 46: /* BA97 */ - _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " - "does not work properly. Using workaround\n"); - break; - default: - break; - } - } + for (i = 0; i < ARRAY_SIZE(vmcs_entry_exit_pairs); i++) { + u32 n_ctrl = vmcs_entry_exit_pairs[i].entry_control; + u32 x_ctrl = vmcs_entry_exit_pairs[i].exit_control; + + if (!(_vmentry_control & n_ctrl) == !(_vmexit_control & x_ctrl)) + continue; + + pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, entry = %x, exit = %x\n", + _vmentry_control & n_ctrl, _vmexit_control & x_ctrl); + if (error_on_inconsistent_vmcs_config) + return -EIO; + + _vmentry_control &= ~n_ctrl; + _vmexit_control &= ~x_ctrl; + } rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); @@ -2670,6 +2705,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, if (((vmx_msr_high >> 18) & 15) != 6) return -EIO; + rdmsrl(MSR_IA32_VMX_MISC, misc_msr); + vmcs_conf->size = vmx_msr_high & 0x1fff; vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; @@ -2678,8 +2715,10 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, 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; + vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control; vmcs_conf->vmexit_ctrl = _vmexit_control; vmcs_conf->vmentry_ctrl = _vmentry_control; + vmcs_conf->misc = misc_msr; #if IS_ENABLED(CONFIG_HYPERV) if (enlightened_vmcs) @@ -2689,6 +2728,129 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, return 0; } +static bool __kvm_is_vmx_supported(void) +{ + int cpu = smp_processor_id(); + + if (!(cpuid_ecx(1) & feature_bit(VMX))) { + pr_err("VMX not supported by CPU %d\n", cpu); + return false; + } + + if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !this_cpu_has(X86_FEATURE_VMX)) { + pr_err("VMX not enabled (by BIOS) in MSR_IA32_FEAT_CTL on CPU %d\n", cpu); + return false; + } + + return true; +} + +static bool kvm_is_vmx_supported(void) +{ + bool supported; + + migrate_disable(); + supported = __kvm_is_vmx_supported(); + migrate_enable(); + + return supported; +} + +static int vmx_check_processor_compat(void) +{ + int cpu = raw_smp_processor_id(); + struct vmcs_config vmcs_conf; + struct vmx_capability vmx_cap; + + if (!__kvm_is_vmx_supported()) + return -EIO; + + if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) { + pr_err("Failed to setup VMCS config on CPU %d\n", cpu); + return -EIO; + } + if (nested) + nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); + if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config))) { + pr_err("Inconsistent VMCS config on CPU %d\n", cpu); + return -EIO; + } + return 0; +} + +static int kvm_cpu_vmxon(u64 vmxon_pointer) +{ + u64 msr; + + cr4_set_bits(X86_CR4_VMXE); + + asm goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); + return 0; + +fault: + WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", + rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + cr4_clear_bits(X86_CR4_VMXE); + + return -EFAULT; +} + +static int vmx_hardware_enable(void) +{ + int cpu = raw_smp_processor_id(); + u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + int r; + + if (cr4_read_shadow() & X86_CR4_VMXE) + return -EBUSY; + + /* + * This can happen if we hot-added a CPU but failed to allocate + * VP assist page for it. + */ + if (kvm_is_using_evmcs() && !hv_get_vp_assist_page(cpu)) + return -EFAULT; + + intel_pt_handle_vmx(1); + + r = kvm_cpu_vmxon(phys_addr); + if (r) { + intel_pt_handle_vmx(0); + return r; + } + + if (enable_ept) + ept_sync_global(); + + return 0; +} + +static void vmclear_local_loaded_vmcss(void) +{ + int cpu = raw_smp_processor_id(); + struct loaded_vmcs *v, *n; + + list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), + loaded_vmcss_on_cpu_link) + __loaded_vmcs_clear(v); +} + +static void vmx_hardware_disable(void) +{ + vmclear_local_loaded_vmcss(); + + if (kvm_cpu_vmxoff()) + kvm_spurious_fault(); + + hv_reset_evmcs(); + + intel_pt_handle_vmx(0); +} + struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); @@ -2702,7 +2864,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) memset(vmcs, 0, vmcs_config.size); /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else vmcs->hdr.revision_id = vmcs_config.revision_id; @@ -2797,7 +2959,7 @@ static __init int alloc_kvm_area(void) * still be marked with revision_id reported by * physical CPU. */ - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = vmcs_config.revision_id; per_cpu(vmxarea, cpu) = vmcs; @@ -2884,9 +3046,8 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) var.type = 0x3; var.avl = 0; if (save->base & 0xf) - printk_once(KERN_WARNING "kvm: segment base is not " - "paragraph aligned when entering " - "protected mode (seg=%d)", seg); + pr_warn_once("segment base is not paragraph aligned " + "when entering protected mode (seg=%d)", seg); } vmcs_write16(sf->selector, var.selector); @@ -2901,6 +3062,15 @@ static void enter_rmode(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); + /* + * KVM should never use VM86 to virtualize Real Mode when L2 is active, + * as using VM86 is unnecessary if unrestricted guest is enabled, and + * if unrestricted guest is disabled, VM-Enter (from L1) with CR0.PG=0 + * should VM-Fail and KVM should reject userspace attempts to stuff + * CR0.PG=0 when L2 is active. + */ + WARN_ON_ONCE(is_guest_mode(vcpu)); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); @@ -2911,14 +3081,6 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmx->rmode.vm86_active = 1; - /* - * Very old userspace does not call KVM_SET_TSS_ADDR before entering - * vcpu. Warn the user that an update is overdue. - */ - if (!kvm_vmx->tss_addr) - printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " - "called before entering vcpu\n"); - vmx_segment_cache_clear(vmx); vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr); @@ -2951,10 +3113,15 @@ int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; vcpu->arch.efer = efer; +#ifdef CONFIG_X86_64 if (efer & EFER_LMA) vm_entry_controls_setbit(vmx, VM_ENTRY_IA32E_MODE); else vm_entry_controls_clearbit(vmx, VM_ENTRY_IA32E_MODE); +#else + if (KVM_BUG_ON(efer & EFER_LMA, vcpu->kvm)) + return 1; +#endif vmx_setup_uret_msrs(vmx); return 0; @@ -3086,6 +3253,17 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING) +static bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + if (is_guest_mode(vcpu)) + return nested_guest_cr0_valid(vcpu, cr0); + + if (to_vmx(vcpu)->nested.vmxon) + return nested_host_cr0_valid(vcpu, cr0); + + return true; +} + void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3095,7 +3273,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) old_cr0_pg = kvm_read_cr0_bits(vcpu, X86_CR0_PG); hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF); - if (is_unrestricted_guest(vcpu)) + if (enable_unrestricted_guest) hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; else { hw_cr0 |= KVM_VM_CR0_ALWAYS_ON; @@ -3123,7 +3301,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } #endif - if (enable_ept && !is_unrestricted_guest(vcpu)) { + if (enable_ept && !enable_unrestricted_guest) { /* * Ensure KVM has an up-to-date snapshot of the guest's CR3. If * the below code _enables_ CR3 exiting, vmx_cache_reg() will @@ -3175,7 +3353,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vmx->emulation_required = vmx_emulation_required(vcpu); } -static int vmx_get_max_tdp_level(void) +static int vmx_get_max_ept_level(void) { if (cpu_has_vmx_ept_5levels()) return 5; @@ -3218,7 +3396,8 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { - guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu); + guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) | + kvm_get_active_cr3_lam_bits(vcpu); } if (update_guest_cr3) @@ -3230,8 +3409,8 @@ static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* * We operate under the default treatment of SMM, so VMX cannot be - * enabled under SMM. Note, whether or not VMXE is allowed at all is - * handled by kvm_is_valid_cr4(). + * enabled under SMM. Note, whether or not VMXE is allowed at all, + * i.e. is a reserved bit, is handled by common x86 code. */ if ((cr4 & X86_CR4_VMXE) && is_smm(vcpu)) return false; @@ -3244,24 +3423,24 @@ static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long old_cr4 = vcpu->arch.cr4; + unsigned long old_cr4 = kvm_read_cr4(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long hw_cr4; + /* * Pass through host's Machine Check Enable value to hw_cr4, which * is in force while we are in guest mode. Do not let guests control * this bit, even if host CR4.MCE == 0. */ - unsigned long hw_cr4; - hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE); - if (is_unrestricted_guest(vcpu)) + if (enable_unrestricted_guest) hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST; else if (vmx->rmode.vm86_active) hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON; else hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; - if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { + if (vmx_umip_emulated()) { if (cr4 & X86_CR4_UMIP) { secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; @@ -3274,7 +3453,7 @@ void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vcpu->arch.cr4 = cr4; kvm_register_mark_available(vcpu, VCPU_EXREG_CR4); - if (!is_unrestricted_guest(vcpu)) { + if (!enable_unrestricted_guest) { if (enable_ept) { if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; @@ -3369,18 +3548,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + ar |= (var->unusable || !var->present) << 16; return ar; } @@ -3702,7 +3878,7 @@ static int init_rmode_identity_map(struct kvm *kvm) } /* Set up identity-mapping pagetable for EPT in real mode */ - for (i = 0; i < PT32_ENT_PER_PAGE; i++) { + for (i = 0; i < (PAGE_SIZE / sizeof(tmp)); i++) { tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); if (__copy_to_user(uaddr + i * sizeof(tmp), &tmp, sizeof(tmp))) { @@ -3732,39 +3908,6 @@ static void seg_setup(int seg) vmcs_write32(sf->ar_bytes, ar); } -static int alloc_apic_access_page(struct kvm *kvm) -{ - struct page *page; - void __user *hva; - int ret = 0; - - mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_memslot_enabled) - goto out; - hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); - if (IS_ERR(hva)) { - ret = PTR_ERR(hva); - goto out; - } - - page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) { - ret = -EFAULT; - goto out; - } - - /* - * Do not pin the page in memory, so that memory hot-unplug - * is able to migrate it. - */ - put_page(page); - kvm->arch.apic_access_memslot_enabled = true; -out: - mutex_unlock(&kvm->slots_lock); - return ret; -} - int allocate_vpid(void) { int vpid; @@ -3797,8 +3940,13 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + if (kvm_is_using_evmcs()) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + if (evmcs->hv_enlightenments_control.msr_bitmap) + evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + } vmx->nested.force_msr_bitmap_recalc = true; } @@ -3807,6 +3955,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + int idx; if (!cpu_has_vmx_msr_bitmap()) return; @@ -3816,16 +3965,13 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filters change. - */ - if (is_valid_passthrough_msr(msr)) { - int idx = possible_passthrough_msr_slot(msr); - - if (idx != -ENOENT) { - if (type & MSR_TYPE_R) - clear_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - clear_bit(idx, vmx->shadow_msr_intercept.write); - } + */ + idx = vmx_get_passthrough_msr_slot(msr); + if (idx >= 0) { + if (type & MSR_TYPE_R) + clear_bit(idx, vmx->shadow_msr_intercept.read); + if (type & MSR_TYPE_W) + clear_bit(idx, vmx->shadow_msr_intercept.write); } if ((type & MSR_TYPE_R) && @@ -3851,6 +3997,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + int idx; if (!cpu_has_vmx_msr_bitmap()) return; @@ -3860,16 +4007,13 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filter changes. - */ - if (is_valid_passthrough_msr(msr)) { - int idx = possible_passthrough_msr_slot(msr); - - if (idx != -ENOENT) { - if (type & MSR_TYPE_R) - set_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - set_bit(idx, vmx->shadow_msr_intercept.write); - } + */ + idx = vmx_get_passthrough_msr_slot(msr); + if (idx >= 0) { + if (type & MSR_TYPE_R) + set_bit(idx, vmx->shadow_msr_intercept.read); + if (type & MSR_TYPE_W) + set_bit(idx, vmx->shadow_msr_intercept.write); } if (type & MSR_TYPE_R) @@ -3879,29 +4023,20 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) vmx_set_msr_bitmap_write(msr_bitmap, msr); } -static void vmx_reset_x2apic_msrs(struct kvm_vcpu *vcpu, u8 mode) -{ - unsigned long *msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - unsigned long read_intercept; - int msr; - - read_intercept = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; - - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned int read_idx = msr / BITS_PER_LONG; - unsigned int write_idx = read_idx + (0x800 / sizeof(long)); - - msr_bitmap[read_idx] = read_intercept; - msr_bitmap[write_idx] = ~0ul; - } -} - static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) { + /* + * x2APIC indices for 64-bit accesses into the RDMSR and WRMSR halves + * of the MSR bitmap. KVM emulates APIC registers up through 0x3f0, + * i.e. MSR 0x83f, and so only needs to dynamically manipulate 64 bits. + */ + const int read_idx = APIC_BASE_MSR / BITS_PER_LONG_LONG; + const int write_idx = read_idx + (0x800 / sizeof(u64)); struct vcpu_vmx *vmx = to_vmx(vcpu); + u64 *msr_bitmap = (u64 *)vmx->vmcs01.msr_bitmap; u8 mode; - if (!cpu_has_vmx_msr_bitmap()) + if (!cpu_has_vmx_msr_bitmap() || WARN_ON_ONCE(!lapic_in_kernel(vcpu))) return; if (cpu_has_secondary_exec_ctrls() && @@ -3919,7 +4054,18 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) vmx->x2apic_msr_bitmap_mode = mode; - vmx_reset_x2apic_msrs(vcpu, mode); + /* + * Reset the bitmap for MSRs 0x800 - 0x83f. Leave AMD's uber-extended + * registers (0x840 and above) intercepted, KVM doesn't support them. + * Intercept all writes by default and poke holes as needed. Pass + * through reads for all valid registers by default in x2APIC+APICv + * mode, only the current timer count needs on-demand emulation by KVM. + */ + if (mode & MSR_BITMAP_MODE_X2APIC_APICV) + msr_bitmap[read_idx] = ~kvm_lapic_readable_reg_mask(vcpu->arch.apic); + else + msr_bitmap[read_idx] = ~0ull; + msr_bitmap[write_idx] = ~0ull; /* * TPR reads and writes can be virtualized even if virtual interrupt @@ -3932,6 +4078,8 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu) vmx_enable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); + if (enable_ipiv) + vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_ICR), MSR_TYPE_RW); } } @@ -3976,21 +4124,30 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 i; + if (!cpu_has_vmx_msr_bitmap()) + return; + /* - * Set intercept permissions for all potentially passed through MSRs - * again. They will automatically get filtered through the MSR filter, - * so we are back in sync after this. + * Redo intercept permissions for MSRs that KVM is passing through to + * the guest. Disabling interception will check the new MSR filter and + * ensure that KVM enables interception if usersepace wants to filter + * the MSR. MSRs that KVM is already intercepting don't need to be + * refreshed since KVM is going to intercept them regardless of what + * userspace wants. */ for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { u32 msr = vmx_possible_passthrough_msrs[i]; - bool read = test_bit(i, vmx->shadow_msr_intercept.read); - bool write = test_bit(i, vmx->shadow_msr_intercept.write); - vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_R, read); - vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_W, write); + if (!test_bit(i, vmx->shadow_msr_intercept.read)) + vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_R); + + if (!test_bit(i, vmx->shadow_msr_intercept.write)) + vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_W); } - pt_update_intercept_for_msr(vcpu); + /* PT MSRs can be passed through iff PT is exposed to the guest. */ + if (vmx_pt_mode_is_host_guest()) + pt_update_intercept_for_msr(vcpu); } static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, @@ -4025,7 +4182,7 @@ static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, */ if (vcpu != kvm_get_running_vcpu()) - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); + __apic_send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); return; } #endif @@ -4085,7 +4242,8 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (!r) return 0; - if (!vcpu->arch.apicv_active) + /* Note, this is called iff the local APIC is in-kernel. */ + if (!vcpu->arch.apic->apicv_active) return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) @@ -4232,18 +4390,37 @@ static u32 vmx_vmentry_ctrl(void) if (vmx_pt_mode_is_system()) vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP | VM_ENTRY_LOAD_IA32_RTIT_CTL); - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmentry_ctrl & - ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); + /* + * IA32e mode, and loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically. + */ + vmentry_ctrl &= ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | + VM_ENTRY_LOAD_IA32_EFER | + VM_ENTRY_IA32E_MODE); + + if (cpu_has_perf_global_ctrl_bug()) + vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + + return vmentry_ctrl; } static u32 vmx_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; + /* + * Not used by KVM and never set in vmcs01 or vmcs02, but emulated for + * nested virtualization and thus allowed to be set in vmcs12. + */ + vmexit_ctrl &= ~(VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER | + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER); + if (vmx_pt_mode_is_system()) vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP | VM_EXIT_CLEAR_IA32_RTIT_CTL); + + if (cpu_has_perf_global_ctrl_bug()) + vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ return vmexit_ctrl & ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); @@ -4259,15 +4436,19 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) } pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - if (cpu_has_secondary_exec_ctrls()) { - if (kvm_vcpu_apicv_active(vcpu)) - secondary_exec_controls_setbit(vmx, - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - else - secondary_exec_controls_clearbit(vmx, - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); + + if (kvm_vcpu_apicv_active(vcpu)) { + secondary_exec_controls_setbit(vmx, + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); + if (enable_ipiv) + tertiary_exec_controls_setbit(vmx, TERTIARY_EXEC_IPI_VIRT); + } else { + secondary_exec_controls_clearbit(vmx, + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); + if (enable_ipiv) + tertiary_exec_controls_clearbit(vmx, TERTIARY_EXEC_IPI_VIRT); } vmx_update_msr_bitmap_x2apic(vcpu); @@ -4277,20 +4458,38 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; + /* + * Not used by KVM, but fully supported for nesting, i.e. are allowed in + * vmcs12 and propagated to vmcs02 when set in vmcs12. + */ + exec_control &= ~(CPU_BASED_RDTSC_EXITING | + CPU_BASED_USE_IO_BITMAPS | + CPU_BASED_MONITOR_TRAP_FLAG | + CPU_BASED_PAUSE_EXITING); + + /* INTR_WINDOW_EXITING and NMI_WINDOW_EXITING are toggled dynamically */ + exec_control &= ~(CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING); + if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; - if (!cpu_need_tpr_shadow(&vmx->vcpu)) { + if (!cpu_need_tpr_shadow(&vmx->vcpu)) exec_control &= ~CPU_BASED_TPR_SHADOW; + #ifdef CONFIG_X86_64 + if (exec_control & CPU_BASED_TPR_SHADOW) + exec_control &= ~(CPU_BASED_CR8_LOAD_EXITING | + CPU_BASED_CR8_STORE_EXITING); + else exec_control |= CPU_BASED_CR8_STORE_EXITING | CPU_BASED_CR8_LOAD_EXITING; #endif - } - if (!enable_ept) - exec_control |= CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_INVLPG_EXITING; + /* No need to intercept CR3 access or INVPLG when using EPT. */ + if (enable_ept) + exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING | + CPU_BASED_INVLPG_EXITING); if (kvm_mwait_in_guest(vmx->vcpu.kvm)) exec_control &= ~(CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING); @@ -4299,6 +4498,20 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) return exec_control; } +static u64 vmx_tertiary_exec_control(struct vcpu_vmx *vmx) +{ + u64 exec_control = vmcs_config.cpu_based_3rd_exec_ctrl; + + /* + * IPI virtualization relies on APICv. Disable IPI virtualization if + * APICv is inhibited. + */ + if (!enable_ipiv || !kvm_vcpu_apicv_active(&vmx->vcpu)) + exec_control &= ~TERTIARY_EXEC_IPI_VIRT; + + return exec_control; +} + /* * Adjust a single secondary execution control bit to intercept/allow an * instruction in the guest. This is usually done based on whether or not a @@ -4324,6 +4537,13 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * controls for features that are/aren't exposed to the guest. */ if (nested) { + /* + * All features that can be added or removed to VMX MSRs must + * be supported in the first place for nested virtualization. + */ + if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control))) + enabled = false; + if (enabled) vmx->nested.msrs.secondary_ctls_high |= control; else @@ -4336,16 +4556,19 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * based on a single guest CPUID bit, with a dedicated feature bit. This also * verifies that the control is actually supported by KVM and hardware. */ -#define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \ -({ \ - bool __enabled; \ - \ - if (cpu_has_vmx_##name()) { \ - __enabled = guest_cpuid_has(&(vmx)->vcpu, \ - X86_FEATURE_##feat_name); \ - vmx_adjust_secondary_exec_control(vmx, exec_control, \ - SECONDARY_EXEC_##ctrl_name, __enabled, exiting); \ - } \ +#define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \ +({ \ + struct kvm_vcpu *__vcpu = &(vmx)->vcpu; \ + bool __enabled; \ + \ + if (cpu_has_vmx_##name()) { \ + if (kvm_is_governed_feature(X86_FEATURE_##feat_name)) \ + __enabled = guest_can_use(__vcpu, X86_FEATURE_##feat_name); \ + else \ + __enabled = guest_cpuid_has(__vcpu, X86_FEATURE_##feat_name); \ + vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\ + __enabled, exiting); \ + } \ }) /* More macro magic for ENABLE_/opt-in versus _EXITING/opt-out controls. */ @@ -4380,6 +4603,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + /* + * KVM doesn't support VMFUNC for L1, but the control is set in KVM's + * base configuration as KVM emulates VMFUNC[EPTP_SWITCHING] for L2. + */ + exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC; + /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, * in vmx_set_cr4. */ exec_control &= ~SECONDARY_EXEC_DESC; @@ -4396,22 +4625,10 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) * it needs to be set here when dirty logging is already active, e.g. * if this vCPU was created after dirty logging was enabled. */ - if (!vcpu->kvm->arch.cpu_dirty_logging_count) + if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; - if (cpu_has_vmx_xsaves()) { - /* Exposing XSAVES only when XSAVE is exposed */ - bool xsaves_enabled = - boot_cpu_has(X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); - - vcpu->arch.xsaves_enabled = xsaves_enabled; - - vmx_adjust_secondary_exec_control(vmx, &exec_control, - SECONDARY_EXEC_XSAVES, - xsaves_enabled, false); - } + vmx_adjust_sec_exec_feature(vmx, &exec_control, xsaves, XSAVES); /* * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either @@ -4430,6 +4647,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) SECONDARY_EXEC_ENABLE_RDTSCP, rdpid_or_rdtscp_enabled, false); } + vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); @@ -4441,13 +4659,49 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) if (!vcpu->kvm->arch.bus_lock_detection_enabled) exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION; + if (!kvm_notify_vmexit_enabled(vcpu->kvm)) + exec_control &= ~SECONDARY_EXEC_NOTIFY_VM_EXITING; + return exec_control; } +static inline int vmx_get_pid_table_order(struct kvm *kvm) +{ + return get_order(kvm->arch.max_vcpu_ids * sizeof(*to_kvm_vmx(kvm)->pid_table)); +} + +static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) +{ + struct page *pages; + struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); + + if (!irqchip_in_kernel(kvm) || !enable_ipiv) + return 0; + + if (kvm_vmx->pid_table) + return 0; + + pages = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, + vmx_get_pid_table_order(kvm)); + if (!pages) + return -ENOMEM; + + kvm_vmx->pid_table = (void *)page_address(pages); + return 0; +} + +static int vmx_vcpu_precreate(struct kvm *kvm) +{ + return vmx_alloc_ipiv_pid_table(kvm); +} + #define VMX_XSS_EXIT_BITMAP 0 static void init_vmcs(struct vcpu_vmx *vmx) { + struct kvm *kvm = vmx->vcpu.kvm; + struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); + if (nested) nested_vmx_set_vmcs_shadowing_bitmap(); @@ -4464,6 +4718,9 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (cpu_has_secondary_exec_ctrls()) secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); + if (cpu_has_tertiary_exec_ctrls()) + tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx)); + if (enable_apicv && lapic_in_kernel(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); @@ -4476,12 +4733,20 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); } - if (!kvm_pause_in_guest(vmx->vcpu.kvm)) { + if (vmx_can_use_ipiv(&vmx->vcpu)) { + vmcs_write64(PID_POINTER_TABLE, __pa(kvm_vmx->pid_table)); + vmcs_write16(LAST_PID_POINTER_INDEX, kvm->arch.max_vcpu_ids - 1); + } + + if (!kvm_pause_in_guest(kvm)) { vmcs_write32(PLE_GAP, ple_gap); vmx->ple_window = ple_window; vmx->ple_window_dirty = true; } + if (kvm_notify_vmexit_enabled(kvm)) + vmcs_write32(NOTIFY_WINDOW, kvm->arch.notify_window); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ @@ -4509,7 +4774,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); @@ -4564,7 +4829,10 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->nested.posted_intr_nv = -1; vmx->nested.vmxon_ptr = INVALID_GPA; vmx->nested.current_vmptr = INVALID_GPA; + +#ifdef CONFIG_KVM_HYPERV vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; +#endif vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; @@ -4652,13 +4920,13 @@ static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } -static void vmx_inject_irq(struct kvm_vcpu *vcpu) +static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; int irq = vcpu->arch.interrupt.nr; - trace_kvm_inj_virq(irq); + trace_kvm_inj_virq(irq, vcpu->arch.interrupt.soft, reinjected); ++vcpu->stat.irq_injections; if (vmx->rmode.vm86_active) { @@ -4785,10 +5053,10 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; - /* - * An IRQ must not be injected into L2 if it's supposed to VM-Exit, - * e.g. if the IRQ arrived asynchronously after checking nested events. - */ + /* + * An IRQ must not be injected into L2 if it's supposed to VM-Exit, + * e.g. if the IRQ arrived asynchronously after checking nested events. + */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return -EBUSY; @@ -4899,7 +5167,7 @@ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu) if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) return true; - return vmx_get_cpl(vcpu) == 3 && kvm_read_cr0_bits(vcpu, X86_CR0_AM) && + return vmx_get_cpl(vcpu) == 3 && kvm_is_cr0_bit_set(vcpu, X86_CR0_AM) && (kvm_get_rflags(vcpu) & X86_EFLAGS_AC); } @@ -4914,8 +5182,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vect_info = vmx->idt_vectoring_info; intr_info = vmx_get_intr_info(vcpu); + /* + * Machine checks are handled by handle_exception_irqoff(), or by + * vmx_vcpu_run() if a #MC occurs on VM-Entry. NMIs are handled by + * vmx_vcpu_enter_exit(). + */ if (is_machine_check(intr_info) || is_nmi(intr_info)) - return 1; /* handled by handle_exception_nmi_irqoff() */ + return 1; /* * Queue the exception here instead of in handle_nm_fault_irqoff(). @@ -4996,8 +5269,10 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * instruction. ICEBP generates a trap-like #DB, but * despite its interception control being tied to #DB, * is an instruction intercept, i.e. the VM-Exit occurs - * on the ICEBP itself. Note, skipping ICEBP also - * clears STI and MOVSS blocking. + * on the ICEBP itself. Use the inner "skip" helper to + * avoid single-step #DB and MTF updates, as ICEBP is + * higher priority. Note, skipping ICEBP still clears + * STI and MOVSS blocking. * * For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS * if single-step is enabled in RFLAGS and STI or MOVSS @@ -5123,18 +5398,11 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) val = (val & ~vmcs12->cr0_guest_host_mask) | (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); - if (!nested_guest_cr0_valid(vcpu, val)) - return 1; - if (kvm_set_cr0(vcpu, val)) return 1; vmcs_writel(CR0_READ_SHADOW, orig_val); return 0; } else { - if (to_vmx(vcpu)->nested.vmxon && - !nested_host_cr0_valid(vcpu, val)) - return 1; - return kvm_set_cr0(vcpu, val); } } @@ -5158,7 +5426,13 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { - WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); + /* + * UMIP emulation relies on intercepting writes to CR4.UMIP, i.e. this + * and other code needs to be updated if UMIP can be guest owned. + */ + BUILD_BUG_ON(KVM_POSSIBLE_CR4_GUEST_BITS & X86_CR4_UMIP); + + WARN_ON_ONCE(!kvm_is_cr4_bit_set(vcpu, X86_CR4_UMIP)); return kvm_emulate_instruction(vcpu, 0); } @@ -5229,7 +5503,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; case 3: /* lmsw */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; - trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val); + trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val)); kvm_lmsw(vcpu, val); return kvm_skip_emulated_instruction(vcpu); @@ -5292,10 +5566,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { - unsigned long val; - - kvm_get_dr(vcpu, dr, &val); - kvm_register_write(vcpu, reg, val); + kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr)); err = 0; } else { err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); @@ -5479,7 +5750,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - trace_kvm_page_fault(gpa, exit_qualification); + trace_kvm_page_fault(vcpu, gpa, exit_qualification); /* Is it a read fault? */ error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) @@ -5507,7 +5778,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(allow_smaller_maxphyaddr && kvm_vcpu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -5517,7 +5788,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) + if (vmx_check_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* @@ -5551,7 +5822,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); return vmx->emulation_required && !vmx->rmode.vm86_active && - (vcpu->arch.exception.pending || vcpu->arch.exception.injected); + (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) @@ -5717,22 +5988,46 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } -static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu) +static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx->req_immediate_exit && - !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) { - kvm_lapic_expired_hv_timer(vcpu); + /* + * In the *extremely* unlikely scenario that this is a spurious VM-Exit + * due to the timer expiring while it was "soft" disabled, just eat the + * exit and re-enter the guest. + */ + if (unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) return EXIT_FASTPATH_REENTER_GUEST; - } - return EXIT_FASTPATH_NONE; + /* + * If the timer expired because KVM used it to force an immediate exit, + * then mission accomplished. + */ + if (force_immediate_exit) + return EXIT_FASTPATH_EXIT_HANDLED; + + /* + * If L2 is active, go down the slow path as emulating the guest timer + * expiration likely requires synthesizing a nested VM-Exit. + */ + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + + kvm_lapic_expired_hv_timer(vcpu); + return EXIT_FASTPATH_REENTER_GUEST; } static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - handle_fastpath_preemption_timer(vcpu); + /* + * This non-fastpath handler is reached if and only if the preemption + * timer was being used to emulate a guest timer while L2 is active. + * All other scenarios are supposed to be handled in the fastpath. + */ + WARN_ON_ONCE(!is_guest_mode(vcpu)); + kvm_lapic_expired_hv_timer(vcpu); return 1; } @@ -5770,6 +6065,32 @@ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) return 1; } +static int handle_notify(struct kvm_vcpu *vcpu) +{ + unsigned long exit_qual = vmx_get_exit_qual(vcpu); + bool context_invalid = exit_qual & NOTIFY_VM_CONTEXT_INVALID; + + ++vcpu->stat.notify_window_exits; + + /* + * Notify VM exit happened while executing iret from NMI, + * "blocked by NMI" bit has to be set before next VM entry. + */ + if (enable_vnmi && (exit_qual & INTR_INFO_UNBLOCK_NMI)) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + + if (vcpu->kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_USER || + context_invalid) { + vcpu->run->exit_reason = KVM_EXIT_NOTIFY; + vcpu->run->notify.flags = context_invalid ? + KVM_NOTIFY_CONTEXT_INVALID : 0; + return 0; + } + + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5827,6 +6148,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, + [EXIT_REASON_NOTIFY] = handle_notify, }; static const int kvm_vmx_max_exit_handlers = @@ -5924,6 +6246,7 @@ void dump_vmcs(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vmentry_ctl, vmexit_ctl; u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control; + u64 tertiary_exec_control; unsigned long cr4; int efer_slot; @@ -5937,9 +6260,16 @@ void dump_vmcs(struct kvm_vcpu *vcpu) cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); cr4 = vmcs_readl(GUEST_CR4); - secondary_exec_control = 0; + if (cpu_has_secondary_exec_ctrls()) secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + else + secondary_exec_control = 0; + + if (cpu_has_tertiary_exec_ctrls()) + tertiary_exec_control = vmcs_read64(TERTIARY_VM_EXEC_CONTROL); + else + tertiary_exec_control = 0; pr_err("VMCS %p, last attempted VM-entry on CPU %d\n", vmx->loaded_vmcs->vmcs, vcpu->arch.last_vmentry_cpu); @@ -6039,9 +6369,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu) vmx_dump_msrs("host autoload", &vmx->msr_autoload.host); pr_err("*** Control State ***\n"); - pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", - pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control); - pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl); + pr_err("CPUBased=0x%08x SecondaryExec=0x%08x TertiaryExec=0x%016llx\n", + cpu_based_exec_ctrl, secondary_exec_control, tertiary_exec_control); + pr_err("PinBased=0x%08x EntryControls=%08x ExitControls=%08x\n", + pin_based_exec_ctrl, vmentry_ctl, vmexit_ctl); pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", vmcs_read32(EXCEPTION_BITMAP), vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), @@ -6191,14 +6522,15 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) exit_reason.basic != EXIT_REASON_EPT_VIOLATION && exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && - exit_reason.basic != EXIT_REASON_TASK_SWITCH)) { + exit_reason.basic != EXIT_REASON_TASK_SWITCH && + exit_reason.basic != EXIT_REASON_NOTIFY)) { int ndata = 3; vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason.full; - vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; + vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu); if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { vcpu->run->internal.data[ndata++] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -6232,7 +6564,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) @@ -6427,7 +6759,12 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { - struct page *page; + const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT; + struct kvm *kvm = vcpu->kvm; + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *slot; + unsigned long mmu_seq; + kvm_pfn_t pfn; /* Defer reload until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { @@ -6439,21 +6776,57 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) return; - page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) + /* + * Explicitly grab the memslot using KVM's internal slot ID to ensure + * KVM doesn't unintentionally grab a userspace memslot. It _should_ + * be impossible for userspace to create a memslot for the APIC when + * APICv is enabled, but paranoia won't hurt in this case. + */ + slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return; + + /* + * Ensure that the mmu_notifier sequence count is read before KVM + * retrieves the pfn from the primary MMU. Note, the memslot is + * protected by SRCU, not the mmu_notifier. Pairs with the smp_wmb() + * in kvm_mmu_invalidate_end(). + */ + mmu_seq = kvm->mmu_invalidate_seq; + smp_rmb(); + + /* + * No need to retry if the memslot does not exist or is invalid. KVM + * controls the APIC-access page memslot, and only deletes the memslot + * if APICv is permanently inhibited, i.e. the memslot won't reappear. + */ + pfn = gfn_to_pfn_memslot(slot, gfn); + if (is_error_noslot_pfn(pfn)) return; - vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(page)); - vmx_flush_tlb_current(vcpu); + read_lock(&vcpu->kvm->mmu_lock); + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { + kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); + read_unlock(&vcpu->kvm->mmu_lock); + goto out; + } + + vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); + read_unlock(&vcpu->kvm->mmu_lock); /* + * No need for a manual TLB flush at this point, KVM has already done a + * flush if there were SPTEs pointing at the previous page. + */ +out: + /* * Do not pin apic access page in memory, the MMU notifier * will call us again if it is migrated or swapped out. */ - put_page(page); + kvm_release_pfn_clean(pfn); } -static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) +static void vmx_hwapic_isr_update(int max_isr) { u16 status; u8 old; @@ -6558,7 +6931,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6566,17 +6939,8 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); } -void vmx_do_interrupt_nmi_irqoff(unsigned long entry); - -static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, - unsigned long entry) -{ - bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist; - - kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ); - vmx_do_interrupt_nmi_irqoff(entry); - kvm_after_interrupt(vcpu); -} +void vmx_do_interrupt_irqoff(unsigned long entry); +void vmx_do_nmi_irqoff(void); static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) { @@ -6598,9 +6962,8 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } -static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) +static void handle_exception_irqoff(struct vcpu_vmx *vmx) { - const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist; u32 intr_info = vmx_get_intr_info(&vmx->vcpu); /* if exit due to PF check for async PF */ @@ -6612,22 +6975,24 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); - /* We need to handle NMIs before interrupts are enabled */ - else if (is_nmi(intr_info)) - handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) { u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - gate_desc *desc = (gate_desc *)host_idt_base + vector; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, - "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) + "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; - handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); + else + vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); + kvm_after_interrupt(vcpu); + vcpu->arch.at_instruction_boundary = true; } @@ -6641,7 +7006,7 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_nmi_irqoff(vmx); + handle_exception_irqoff(vmx); } /* @@ -6652,12 +7017,14 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + return false; /* * We cannot do SMM unless we can run the guest in big * real mode. */ return enable_unrestricted_guest || emulate_invalid_guest_state; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: return nested; case MSR_AMD64_VIRT_SPEC_CTRL: case MSR_AMD64_TSC_RATIO: @@ -6783,9 +7150,14 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) { int i, nr_msrs; struct perf_guest_switch_msr *msrs; + struct kvm_pmu *pmu = vcpu_to_pmu(&vmx->vcpu); + + pmu->host_cross_mapped_mask = 0; + if (pmu->pebs_enable & pmu->global_ctrl) + intel_pmu_cross_mapped_check(pmu); /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */ - msrs = perf_guest_get_msrs(&nr_msrs); + msrs = perf_guest_get_msrs(&nr_msrs, (void *)pmu); if (!msrs) return; @@ -6797,13 +7169,13 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; - if (vmx->req_immediate_exit) { + if (force_immediate_exit) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (vmx->hv_deadline_tsc != -1) { @@ -6856,29 +7228,42 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, barrier_nospec(); } -static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { + /* + * If L2 is active, some VMX preemption timer exits can be handled in + * the fastpath even, all other exits must use the slow path. + */ + if (is_guest_mode(vcpu) && + to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_PREEMPTION_TIMER) + return EXIT_FASTPATH_NONE; + switch (to_vmx(vcpu)->exit_reason.basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: - return handle_fastpath_preemption_timer(vcpu); + return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); default: return EXIT_FASTPATH_NONE; } } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, - struct vcpu_vmx *vmx, - unsigned long flags) + unsigned int flags) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + guest_state_enter_irqoff(); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); @@ -6892,13 +7277,36 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, flags); vcpu->arch.cr2 = native_read_cr2(); + vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; + + vmx->idt_vectoring_info = 0; vmx_enable_fb_clear(vmx); + if (unlikely(vmx->fail)) { + vmx->exit_reason.full = 0xdead; + goto out; + } + + vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + if (likely(!vmx->exit_reason.failed_vmentry)) + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); + + if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && + is_nmi(vmx_get_intr_info(vcpu))) { + kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); + else + vmx_do_nmi_irqoff(); + kvm_after_interrupt(vcpu); + } + +out: guest_state_exit_irqoff(); } -static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) +static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -6925,7 +7333,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } - trace_kvm_entry(vcpu); + trace_kvm_entry(vcpu, force_immediate_exit); if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; @@ -6984,15 +7392,17 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_passthrough_lbr_msrs(vcpu); if (enable_preemption_timer) - vmx_update_hv_timer(vcpu); + vmx_update_hv_timer(vcpu, force_immediate_exit); + else if (force_immediate_exit) + smp_send_reschedule(vcpu->cpu); kvm_wait_lapic_expire(vcpu); /* The actual VMENTER/EXIT is in the .noinstr.text section. */ - vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx)); + vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ - if (static_branch_unlikely(&enable_evmcs)) { + if (kvm_is_using_evmcs()) { current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; @@ -7016,8 +7426,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(es, __USER_DS); #endif - vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET; - pt_guest_exit(vmx); kvm_load_host_xsave_state(vcpu); @@ -7034,20 +7442,12 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->nested.nested_run_pending = 0; } - vmx->idt_vectoring_info = 0; - - if (unlikely(vmx->fail)) { - vmx->exit_reason.full = 0xdead; + if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; - } - vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); - if (likely(!vmx->exit_reason.failed_vmentry)) - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - trace_kvm_exit(vcpu, KVM_ISA_VMX); if (unlikely(vmx->exit_reason.failed_vmentry)) @@ -7058,10 +7458,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); - if (is_guest_mode(vcpu)) - return EXIT_FASTPATH_NONE; - - return vmx_exit_handlers_fastpath(vcpu); + return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } static void vmx_vcpu_free(struct kvm_vcpu *vcpu) @@ -7125,7 +7522,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) * feature only for vmcs01, KVM currently isn't equipped to realize any * performance benefits from enabling it for vmcs02. */ - if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + if (kvm_is_using_evmcs() && (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; @@ -7155,7 +7552,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) vmx->loaded_vmcs = &vmx->vmcs01; if (cpu_need_virtualize_apic_accesses(vcpu)) { - err = alloc_apic_access_page(vcpu->kvm); + err = kvm_alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } @@ -7166,6 +7563,10 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) goto free_vmcs; } + if (vmx_can_use_ipiv(vcpu)) + WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id], + __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID); + return 0; free_vmcs: @@ -7211,33 +7612,8 @@ static int vmx_vm_init(struct kvm *kvm) return 0; } -static int __init vmx_check_processor_compat(void) +static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - struct vmcs_config vmcs_conf; - struct vmx_capability vmx_cap; - - if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !this_cpu_has(X86_FEATURE_VMX)) { - pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id()); - return -EIO; - } - - if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) - return -EIO; - if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); - if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { - printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", - smp_processor_id()); - return -EIO; - } - return 0; -} - -static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - u8 cache; - /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. * We have to be careful as to what are honored and when. @@ -7262,13 +7638,12 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; + return MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT; else - cache = MTRR_TYPE_UNCACHABLE; - - return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + return (MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT) | + VMX_EPT_IPAT_BIT; } return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; @@ -7310,7 +7685,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask); \ } while (0) - entry = kvm_find_cpuid_entry(vcpu, 0x1, 0); + entry = kvm_find_cpuid_entry(vcpu, 0x1); cr4_fixed1_update(X86_CR4_VME, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_PVI, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_TSD, edx, feature_bit(TSC)); @@ -7326,7 +7701,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_PCIDE, ecx, feature_bit(PCID)); cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, feature_bit(XSAVE)); - entry = kvm_find_cpuid_entry(vcpu, 0x7, 0); + entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 0); cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, feature_bit(FSGSBASE)); cr4_fixed1_update(X86_CR4_SMEP, ebx, feature_bit(SMEP)); cr4_fixed1_update(X86_CR4_SMAP, ebx, feature_bit(SMAP)); @@ -7334,24 +7709,10 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); -#undef cr4_fixed1_update -} - -static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); + entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); + cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); - if (kvm_mpx_supported()) { - bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX); - - if (mpx_enabled) { - vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; - vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; - } else { - vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS; - vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS; - } - } +#undef cr4_fixed1_update } static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) @@ -7361,7 +7722,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) int i; for (i = 0; i < PT_CPUID_LEAVES; i++) { - best = kvm_find_cpuid_entry(vcpu, 0x14, i); + best = kvm_find_cpuid_entry_index(vcpu, 0x14, i); if (!best) return; vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax; @@ -7427,8 +7788,17 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ - vcpu->arch.xsaves_enabled = false; + /* + * XSAVES is effectively enabled if and only if XSAVE is also exposed + * to the guest. XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be + * set if and only if XSAVE is supported. + */ + if (boot_cpu_has(X86_FEATURE_XSAVE) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES); + + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM); vmx_setup_uret_msrs(vmx); @@ -7436,7 +7806,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmcs_set_secondary_exec_control(vmx, vmx_secondary_exec_control(vmx)); - if (nested_vmx_allowed(vcpu)) + if (guest_can_use(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; @@ -7445,10 +7815,8 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); - if (nested_vmx_allowed(vcpu)) { + if (guest_can_use(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); - nested_vmx_entry_exit_ctls_update(vcpu); - } if (boot_cpu_has(X86_FEATURE_INTEL_PT) && guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) @@ -7467,6 +7835,13 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, !guest_cpuid_has(vcpu, X86_FEATURE_XFD)); + if (boot_cpu_has(X86_FEATURE_IBPB)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, + !guest_has_pred_cmd_msr(vcpu)); + + if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, + !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); set_cr4_guest_host_mask(vmx); @@ -7487,6 +7862,33 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } +static u64 vmx_get_perf_capabilities(void) +{ + u64 perf_cap = PMU_CAP_FW_WRITES; + struct x86_pmu_lbr lbr; + u64 host_perf_cap = 0; + + if (!enable_pmu) + return 0; + + if (boot_cpu_has(X86_FEATURE_PDCM)) + rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); + + if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { + x86_perf_get_lbr(&lbr); + if (lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + } + + if (vmx_pebs_supported()) { + perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; + if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) + perf_cap &= ~PERF_CAP_PEBS_BASELINE; + } + + return perf_cap; +} + static __init void vmx_set_cpu_caps(void) { kvm_set_cpu_caps(); @@ -7502,6 +7904,14 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_INVPCID); if (vmx_pt_mode_is_host_guest()) kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT); + if (vmx_pebs_supported()) { + kvm_cpu_cap_check_and_set(X86_FEATURE_DS); + kvm_cpu_cap_check_and_set(X86_FEATURE_DTES64); + } + + if (!enable_pmu) + kvm_cpu_cap_clear(X86_FEATURE_PDCM); + kvm_caps.supported_perf_cap = vmx_get_perf_capabilities(); if (!enable_sgx) { kvm_cpu_cap_clear(X86_FEATURE_SGX); @@ -7514,7 +7924,7 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_UMIP); /* CPUID 0xD.1 */ - supported_xss = 0; + kvm_caps.supported_xss = 0; if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); @@ -7528,11 +7938,6 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); } -static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->req_immediate_exit = true; -} - static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, struct x86_instruction_info *info) { @@ -7608,6 +8013,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ break; + case x86_intercept_pause: + /* + * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides + * with vanilla NOPs in the emulator. Apply the interception + * check only to actual PAUSE instructions. Don't check + * PAUSE-loop-exiting, software can't expect a given PAUSE to + * exit, i.e. KVM is within its rights to allow L2 to execute + * the PAUSE. + */ + if ((info->rep_prefix != REPE_PREFIX) || + !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING)) + return X86EMUL_CONTINUE; + + break; + /* TODO: check more intercepts... */ default: break; @@ -7655,9 +8075,9 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, delta_tsc = 0; /* Convert to host delta tsc if tsc scaling is enabled */ - if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio && delta_tsc && u64_shl_div_u64(delta_tsc, - kvm_tsc_scaling_ratio_frac_bits, + kvm_caps.tsc_scaling_ratio_frac_bits, vcpu->arch.l1_tsc_scaling_ratio, &delta_tsc)) return -ERANGE; @@ -7691,17 +8111,20 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (WARN_ON_ONCE(!enable_pml)) + return; + if (is_guest_mode(vcpu)) { vmx->nested.update_vmcs01_cpu_dirty_logging = true; return; } /* - * Note, cpu_dirty_logging_count can be changed concurrent with this + * Note, nr_memslots_dirty_logging can be changed concurrent with this * code, but in that case another update request will be made and so * the guest will never run with a stale PML value. */ - if (vcpu->kvm->arch.cpu_dirty_logging_count) + if (atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); else secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); @@ -7717,6 +8140,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEAT_CTL_LMCE_ENABLED; } +#ifdef CONFIG_KVM_SMM static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ @@ -7725,10 +8149,17 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * TODO: Implement custom flows for forcing the vCPU out/in of L2 on + * SMI and RSM. Using the common VM-Exit + VM-Enter routines is wrong + * SMI and RSM only modify state that is saved and restored via SMRAM. + * E.g. most MSRs are left untouched, but many are modified by VM-Exit + * and VM-Enter, and thus L2's values may be corrupted on SMI+RSM. + */ vmx->nested.smm.guest_mode = is_guest_mode(vcpu); if (vmx->nested.smm.guest_mode) nested_vmx_vmexit(vcpu, -1, 0, 0); @@ -7739,7 +8170,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -7764,6 +8195,7 @@ static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } +#endif static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { @@ -7790,20 +8222,72 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) +#define VMX_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE)| \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \ +) + +static void vmx_vm_destroy(struct kvm *kvm) +{ + struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); + + free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm)); +} + +/* + * Note, the SDM states that the linear address is masked *after* the modified + * canonicality check, whereas KVM masks (untags) the address and then performs + * a "normal" canonicality check. Functionally, the two methods are identical, + * and when the masking occurs relative to the canonicality check isn't visible + * to software, i.e. KVM's behavior doesn't violate the SDM. + */ +gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags) { - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_ABSENT) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); + int lam_bit; + unsigned long cr3_bits; + + if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG)) + return gva; + + if (!is_64_bit_mode(vcpu)) + return gva; + + /* + * Bit 63 determines if the address should be treated as user address + * or a supervisor address. + */ + if (!(gva & BIT_ULL(63))) { + cr3_bits = kvm_get_active_cr3_lam_bits(vcpu); + if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48))) + return gva; + + /* LAM_U48 is ignored if LAM_U57 is set. */ + lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47; + } else { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP)) + return gva; - return supported & BIT(reason); + lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47; + } + + /* + * Untag the address by sign-extending the lam_bit, but NOT to bit 63. + * Bit 63 is retained from the raw virtual address so that untagging + * doesn't change a user access to a supervisor access, and vice versa. + */ + return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); } static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = "kvm_intel", + .name = KBUILD_MODNAME, + + .check_processor_compatibility = vmx_check_processor_compat, .hardware_unsetup = vmx_hardware_unsetup, @@ -7813,7 +8297,9 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .vm_size = sizeof(struct kvm_vmx), .vm_init = vmx_vm_init, + .vm_destroy = vmx_vm_destroy, + .vcpu_precreate = vmx_vcpu_precreate, .vcpu_create = vmx_vcpu_create, .vcpu_free = vmx_vcpu_free, .vcpu_reset = vmx_vcpu_reset, @@ -7831,6 +8317,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_segment = vmx_set_segment, .get_cpl = vmx_get_cpl, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, + .is_valid_cr0 = vmx_is_valid_cr0, .set_cr0 = vmx_set_cr0, .is_valid_cr4 = vmx_is_valid_cr4, .set_cr4 = vmx_set_cr4, @@ -7861,7 +8348,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .patch_hypercall = vmx_patch_hypercall, .inject_irq = vmx_inject_irq, .inject_nmi = vmx_inject_nmi, - .queue_exception = vmx_queue_exception, + .inject_exception = vmx_inject_exception, .cancel_injection = vmx_cancel_injection, .interrupt_allowed = vmx_interrupt_allowed, .nmi_allowed = vmx_nmi_allowed, @@ -7874,8 +8361,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, - .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, + .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, @@ -7903,8 +8390,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff, - .request_immediate_exit = vmx_request_immediate_exit, - .sched_in = vmx_sched_in, .cpu_dirty_log_size = PML_ENTITY_NUM, @@ -7922,12 +8407,14 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .setup_mce = vmx_setup_mce, +#ifdef CONFIG_KVM_SMM .smi_allowed = vmx_smi_allowed, .enter_smm = vmx_enter_smm, .leave_smm = vmx_leave_smm, .enable_smi_window = vmx_enable_smi_window, +#endif - .can_emulate_instruction = vmx_can_emulate_instruction, + .check_emulate_instruction = vmx_check_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, .migrate_timers = vmx_migrate_timers, @@ -7935,6 +8422,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .complete_emulated_msr = kvm_complete_insn_gp, .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, + + .get_untagged_addr = vmx_get_untagged_addr, }; static unsigned int vmx_handle_intel_pt_intr(void) @@ -8018,17 +8507,21 @@ static __init int hardware_setup(void) if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; + if (cpu_has_perf_global_ctrl_bug()) + pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + "does not work properly. Using workaround\n"); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); if (boot_cpu_has(X86_FEATURE_MPX)) { rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); - WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); + WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } if (!cpu_has_vmx_mpx()) - supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | - XFEATURE_MASK_BNDCSR); + kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | + XFEATURE_MASK_BNDCSR); if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) @@ -8042,7 +8535,7 @@ static __init int hardware_setup(void) /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { - pr_err_ratelimited("kvm: NX (Execute Disable) not supported\n"); + pr_err_ratelimited("NX (Execute Disable) not supported\n"); return -EOPNOTSUPP; } @@ -8058,6 +8551,11 @@ static __init int hardware_setup(void) if (!cpu_has_virtual_nmis()) enable_vnmi = 0; +#ifdef CONFIG_X86_SGX_KVM + if (!cpu_has_vmx_encls_vmexit()) + enable_sgx = false; +#endif + /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not @@ -8072,9 +8570,8 @@ static __init int hardware_setup(void) #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - vmx_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; - vmx_x86_ops.tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; + vmx_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + vmx_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif @@ -8091,12 +8588,16 @@ static __init int hardware_setup(void) if (!enable_apicv) vmx_x86_ops.sync_pir_to_irr = NULL; + if (!enable_apicv || !cpu_has_vmx_ipiv()) + enable_ipiv = false; + if (cpu_has_vmx_tsc_scaling()) - kvm_has_tsc_control = true; + kvm_caps.has_tsc_control = true; - kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; - kvm_tsc_scaling_ratio_frac_bits = 48; - kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); + kvm_caps.max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; + kvm_caps.tsc_scaling_ratio_frac_bits = 48; + kvm_caps.has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); + kvm_caps.has_notify_vmexit = cpu_has_notify_vmexit(); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ @@ -8110,7 +8611,7 @@ static __init int hardware_setup(void) */ vmx_setup_me_spte_mask(); - kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(), + kvm_configure_mmu(enable_ept, 0, vmx_get_max_ept_level(), ept_caps_to_lpage_level(vmx_capability.ept)); /* @@ -8128,11 +8629,9 @@ static __init int hardware_setup(void) if (enable_preemption_timer) { u64 use_timer_freq = 5000ULL * 1000 * 1000; - u64 vmx_msr; - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); cpu_preemption_timer_multi = - vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8150,14 +8649,14 @@ static __init int hardware_setup(void) if (!enable_preemption_timer) { vmx_x86_ops.set_hv_timer = NULL; vmx_x86_ops.cancel_hv_timer = NULL; - vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } - kvm_mce_cap_supported |= MCG_LMCE_P; + kvm_caps.supported_mce_cap |= MCG_LMCE_P; + kvm_caps.supported_mce_cap |= MCG_CMCI_P; if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) return -EINVAL; - if (!enable_ept || !cpu_has_vmx_intel_pt()) + if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; if (pt_mode == PT_MODE_HOST_GUEST) vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; @@ -8167,8 +8666,7 @@ static __init int hardware_setup(void) setup_default_sgx_lepubkeyhash(); if (nested) { - nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept); + nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) @@ -8187,9 +8685,6 @@ static __init int hardware_setup(void) } static struct kvm_x86_init_ops vmx_init_ops __initdata = { - .cpu_has_kvm_support = cpu_has_kvm_support, - .disabled_by_bios = vmx_disabled_by_bios, - .check_processor_compatibility = vmx_check_processor_compat, .hardware_setup = hardware_setup, .handle_intel_pt_intr = NULL, @@ -8207,41 +8702,21 @@ static void vmx_cleanup_l1d_flush(void) l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } -static void vmx_exit(void) +static void __vmx_exit(void) { -#ifdef CONFIG_KEXEC_CORE - RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); - synchronize_rcu(); -#endif - - kvm_exit(); - -#if IS_ENABLED(CONFIG_HYPERV) - if (static_branch_unlikely(&enable_evmcs)) { - int cpu; - struct hv_vp_assist_page *vp_ap; - /* - * Reset everything to support using non-enlightened VMCS - * access later (e.g. when we reload the module with - * enlightened_vmcs=0) - */ - for_each_online_cpu(cpu) { - vp_ap = hv_get_vp_assist_page(cpu); - - if (!vp_ap) - continue; + allow_smaller_maxphyaddr = false; - vp_ap->nested_control.features.directhypercall = 0; - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } + cpu_emergency_unregister_virt_callback(vmx_emergency_disable); - static_branch_disable(&enable_evmcs); - } -#endif vmx_cleanup_l1d_flush(); +} - allow_smaller_maxphyaddr = false; +static void vmx_exit(void) +{ + kvm_exit(); + kvm_x86_vendor_exit(); + + __vmx_exit(); } module_exit(vmx_exit); @@ -8249,58 +8724,29 @@ static int __init vmx_init(void) { int r, cpu; -#if IS_ENABLED(CONFIG_HYPERV) + if (!kvm_is_vmx_supported()) + return -EOPNOTSUPP; + /* - * Enlightened VMCS usage should be recommended and the host needs - * to support eVMCS v1 or above. We can also disable eVMCS support - * with module parameter. + * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing + * to unwind if a later step fails. */ - if (enlightened_vmcs && - ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && - (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= - KVM_EVMCS_VERSION) { - - /* Check that we have assist pages on all online CPUs */ - for_each_online_cpu(cpu) { - if (!hv_get_vp_assist_page(cpu)) { - enlightened_vmcs = false; - break; - } - } - - if (enlightened_vmcs) { - pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); - } - - if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_direct_tlbflush - = hv_enable_direct_tlbflush; + hv_init_evmcs(); - } else { - enlightened_vmcs = false; - } -#endif - - r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + r = kvm_x86_vendor_init(&vmx_init_ops); if (r) return r; /* - * Must be called after kvm_init() so enable_ept is properly set + * Must be called after common x86 init so enable_ept is properly set * up. Hand the parameter mitigation value in which was stored in * the pre module init parser. If no parameter was given, it will * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } - - vmx_setup_fb_clear_ctrl(); + if (r) + goto err_l1d_flush; for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); @@ -8308,10 +8754,8 @@ static int __init vmx_init(void) pi_init_cpu(cpu); } -#ifdef CONFIG_KEXEC_CORE - rcu_assign_pointer(crash_vmclear_loaded_vmcss, - crash_vmclear_local_loaded_vmcss); -#endif + cpu_emergency_register_virt_callback(vmx_emergency_disable); + vmx_check_vmcs12_offsets(); /* @@ -8322,6 +8766,21 @@ static int __init vmx_init(void) if (!enable_ept) allow_smaller_maxphyaddr = true; + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), + THIS_MODULE); + if (r) + goto err_kvm_init; + return 0; + +err_kvm_init: + __vmx_exit(); +err_l1d_flush: + kvm_x86_vendor_exit(); + return r; } module_init(vmx_init); |