diff options
Diffstat (limited to 'arch/x86/kvm/vmx/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 3433 |
1 files changed, 1800 insertions, 1633 deletions
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7eec0226d56a..4cbe8c84b636 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> @@ -27,7 +28,6 @@ #include <linux/slab.h> #include <linux/tboot.h> #include <linux/trace_events.h> -#include <linux/entry-kvm.h> #include <asm/apic.h> #include <asm/asm.h> @@ -37,19 +37,23 @@ #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/msr.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 "common.h" #include "cpuid.h" #include "hyperv.h" #include "kvm_onhyperv.h" @@ -65,9 +69,15 @@ #include "vmcs12.h" #include "vmx.h" #include "x86.h" +#include "x86_ops.h" #include "smm.h" +#include "vmx_onhyperv.h" +#include "posted_intr.h" + +#include "mmu/spte.h" MODULE_AUTHOR("Qumranet"); +MODULE_DESCRIPTION("KVM support for VMX (Intel VT-x) extensions"); MODULE_LICENSE("GPL"); #ifdef MODULE @@ -82,42 +92,42 @@ 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(enable_apicv, bool, S_IRUGO); +module_param(fasteoi, bool, 0444); -bool __read_mostly enable_ipiv = true; +module_param(enable_apicv, bool, 0444); module_param(enable_ipiv, bool, 0444); +module_param(enable_device_posted_irqs, bool, 0444); + /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not * 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); @@ -157,30 +167,6 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); RTIT_STATUS_BYTECNT)) /* - * List of MSRs that can be directly passed to the guest. - * In addition to these x2apic and PT MSRs are handled specially. - */ -static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { - MSR_IA32_SPEC_CTRL, - MSR_IA32_PRED_CMD, - MSR_IA32_TSC, -#ifdef CONFIG_X86_64 - MSR_FS_BASE, - MSR_GS_BASE, - MSR_KERNEL_GS_BASE, - MSR_IA32_XFD, - MSR_IA32_XFD_ERR, -#endif - MSR_IA32_SYSENTER_CS, - MSR_IA32_SYSENTER_ESP, - MSR_IA32_SYSENTER_EIP, - MSR_CORE_C1_RES, - MSR_CORE_C3_RESIDENCY, - MSR_CORE_C6_RESIDENCY, - MSR_CORE_C7_RESIDENCY, -}; - -/* * These 2 parameters are used to config the controls for Pause-Loop Exiting: * ple_gap: upper bound on the amount of time between two successive * executions of PAUSE in a loop. Also indicate if ple enabled. @@ -209,10 +195,15 @@ module_param(ple_window_shrink, uint, 0444); static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; module_param(ple_window_max, uint, 0444); -/* Default is SYSTEM mode, 1 for host-guest mode */ +/* Default is SYSTEM mode, 1 for host-guest mode (which is BROKEN) */ int __read_mostly pt_mode = PT_MODE_SYSTEM; +#ifdef CONFIG_BROKEN module_param(pt_mode, int, S_IRUGO); +#endif +struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; + +#ifdef CONFIG_CPU_MITIGATIONS static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); @@ -235,10 +226,7 @@ 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) +static int __vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; unsigned int i; @@ -253,14 +241,9 @@ 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 (kvm_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 */ @@ -269,6 +252,7 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) case L1TF_MITIGATION_OFF: l1tf = VMENTER_L1D_FLUSH_NEVER; break; + case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH_NOWARN: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: @@ -319,6 +303,26 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) return 0; } +static int vmx_setup_l1d_flush(void) +{ + /* + * 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. + */ + return __vmx_setup_l1d_flush(vmentry_l1d_flush_param); +} + +static void vmx_cleanup_l1d_flush(void) +{ + if (vmx_l1d_flush_pages) { + free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); + vmx_l1d_flush_pages = NULL; + } + /* Restore state so sysfs ignores VMX */ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; +} + static int vmentry_l1d_flush_parse(const char *s) { unsigned int i; @@ -356,7 +360,7 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) } mutex_lock(&vmx_l1d_flush_mutex); - ret = vmx_setup_l1d_flush(l1tf); + ret = __vmx_setup_l1d_flush(l1tf); mutex_unlock(&vmx_l1d_flush_mutex); return ret; } @@ -364,24 +368,106 @@ 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 sysfs_emit(s, "???\n"); - return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); + return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } -static void vmx_setup_fb_clear_ctrl(void) +/* + * Software based L1D cache flush which is used when microcode providing + * the cache control MSR is not loaded. + * + * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to + * flush it is required to read in 64 KiB because the replacement algorithm + * is not exactly LRU. This could be sized at runtime via topology + * information but as all relevant affected CPUs have 32KiB L1D cache size + * there is no point in doing so. + */ +static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) { - u64 msr; + int size = PAGE_SIZE << L1D_CACHE_ORDER; + + if (!static_branch_unlikely(&vmx_l1d_should_flush)) + return; + + /* + * This code is only executed when the flush mode is 'cond' or + * 'always' + */ + if (static_branch_likely(&vmx_l1d_flush_cond)) { + /* + * Clear the per-cpu flush bit, it gets set again if the vCPU + * is reloaded, i.e. if the vCPU is scheduled out or if KVM + * exits to userspace, or if KVM reaches one of the unsafe + * VMEXIT handlers, e.g. if KVM calls into the emulator, + * or from the interrupt handlers. + */ + if (!kvm_get_cpu_l1tf_flush_l1d()) + return; + kvm_clear_cpu_l1tf_flush_l1d(); + } + + vcpu->stat.l1d_flush++; - 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; + if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { + native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + return; } + + asm volatile( + /* First ensure the pages are in the TLB */ + "xorl %%eax, %%eax\n" + ".Lpopulate_tlb:\n\t" + "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" + "addl $4096, %%eax\n\t" + "cmpl %%eax, %[size]\n\t" + "jne .Lpopulate_tlb\n\t" + "xorl %%eax, %%eax\n\t" + "cpuid\n\t" + /* Now fill the cache */ + "xorl %%eax, %%eax\n" + ".Lfill_cache:\n" + "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" + "addl $64, %%eax\n\t" + "cmpl %%eax, %[size]\n\t" + "jne .Lfill_cache\n\t" + "lfence\n" + :: [flush_pages] "r" (vmx_l1d_flush_pages), + [size] "r" (size) + : "eax", "ebx", "ecx", "edx"); } +#else /* CONFIG_CPU_MITIGATIONS*/ +static int vmx_setup_l1d_flush(void) +{ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NEVER; + return 0; +} +static void vmx_cleanup_l1d_flush(void) +{ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; +} +static __always_inline void vmx_l1d_flush(struct kvm_vcpu *vcpu) +{ + +} +static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) +{ + pr_warn_once("Kernel compiled without mitigations, ignoring vmentry_l1d_flush\n"); + return 0; +} +static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) +{ + return sysfs_emit(s, "never\n"); +} +#endif + +static const struct kernel_param_ops vmentry_l1d_flush_ops = { + .set = vmentry_l1d_flush_set, + .get = vmentry_l1d_flush_get, +}; +module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); + static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) { u64 msr; @@ -389,9 +475,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) if (!vmx->disable_fb_clear) return; - msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); + msr = native_rdmsrq(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; - native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } @@ -402,12 +488,23 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) return; vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; - native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); + native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); } 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) && + (kvm_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 @@ -423,12 +520,6 @@ static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) vmx->disable_fb_clear = false; } -static const struct kernel_param_ops vmentry_l1d_flush_ops = { - .set = vmentry_l1d_flush_set, - .get = vmentry_l1d_flush_get, -}; -module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); - static u32 vmx_segment_access_rights(struct kvm_segment *var); void vmx_vmexit(void); @@ -439,42 +530,51 @@ do { \ pr_warn_ratelimited(fmt); \ } while (0) -void vmread_error(unsigned long field, bool fault) +noinline void vmread_error(unsigned long field) { - if (fault) + 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) { 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=%u\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 err=%u\n", + 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 err=%u\n", + 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) +noinline void invept_error(unsigned long ext, u64 eptp) { - vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", - ext, eptp, gpa); + vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx\n", ext, eptp); } static DEFINE_PER_CPU(struct vmcs *, vmxarea); @@ -488,8 +588,8 @@ 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] = { \ @@ -515,10 +615,6 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; -static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) -{ - vmx->segment_cache.bitmask = 0; -} static unsigned long host_idt_base; @@ -529,28 +625,84 @@ module_param(enlightened_vmcs, bool, 0444); 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) + vt_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) */ /* @@ -606,49 +758,6 @@ 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) -{ - bool r; - - switch (msr) { - case 0x800 ... 0x8ff: - /* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */ - return true; - case MSR_IA32_RTIT_STATUS: - case MSR_IA32_RTIT_OUTPUT_BASE: - case MSR_IA32_RTIT_OUTPUT_MASK: - case MSR_IA32_RTIT_CR3_MATCH: - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - /* PT MSRs. These are handled in pt_update_intercept_for_msr() */ - case MSR_LBR_SELECT: - case MSR_LBR_TOS: - case MSR_LBR_INFO_0 ... MSR_LBR_INFO_0 + 31: - case MSR_LBR_NHM_FROM ... MSR_LBR_NHM_FROM + 31: - case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31: - 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; - } - - r = possible_passthrough_msr_slot(msr) != -ENOENT; - - WARN(!r, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); - - return r; -} - struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -675,17 +784,54 @@ 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; +} + +void vmx_emergency_disable_virtualization_cpu(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) + loaded_vmcss_on_cpu_link) { vmcs_clear(v->vmcs); + if (v->shadow_vmcs) + vmcs_clear(v->shadow_vmcs); + } + + kvm_cpu_vmxoff(); } -#endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) { @@ -716,7 +862,7 @@ static void __loaded_vmcs_clear(void *arg) loaded_vmcs->launched = 0; } -void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) +static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) { int cpu = loaded_vmcs->cpu; @@ -783,6 +929,12 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); /* + * #VE isn't used for VMX. To test against unexpected changes + * related to #VE for VMX, intercept unexpected #VE and warn on it. + */ + if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + eb |= 1u << VE_VECTOR; + /* * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway @@ -806,7 +958,7 @@ 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))) { @@ -861,6 +1013,10 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)) flags |= VMX_RUN_SAVE_SPEC_CTRL; + if (cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO) && + kvm_vcpu_can_access_host_mmio(&vmx->vcpu)) + flags |= VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO; + return flags; } @@ -969,7 +1125,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, * provide that period, so a CPU could write host's record into * guest's memory. */ - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); + wrmsrq(MSR_IA32_PEBS_ENABLE, 0); } i = vmx_find_loadstore_msr_slot(&m->guest, msr); @@ -1027,12 +1183,12 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) * atomically, since it's faster than switching it manually. */ if (cpu_has_load_ia32_efer() || - (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { + (enable_ept && ((vmx->vcpu.arch.efer ^ kvm_host.efer) & EFER_NX))) { if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; - if (guest_efer != host_efer) + if (guest_efer != kvm_host.efer) add_atomic_switch_msr(vmx, MSR_EFER, - guest_efer, host_efer, false); + guest_efer, kvm_host.efer, false); else clear_atomic_switch_msr(vmx, MSR_EFER); return false; @@ -1045,7 +1201,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) clear_atomic_switch_msr(vmx, MSR_EFER); guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; + guest_efer |= kvm_host.efer & ignore_bits; vmx->guest_uret_msrs[i].data = guest_efer; vmx->guest_uret_msrs[i].mask = ~ignore_bits; @@ -1098,13 +1254,13 @@ static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; - wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); + wrmsrq(MSR_IA32_RTIT_STATUS, ctx->status); + wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); + wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); + wrmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { - wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); + wrmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); + wrmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } @@ -1112,13 +1268,13 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) { u32 i; - rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); + rdmsrq(MSR_IA32_RTIT_STATUS, ctx->status); + rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); + rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); + rdmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); for (i = 0; i < addr_range; i++) { - rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); + rdmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); + rdmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); } } @@ -1131,9 +1287,9 @@ static void pt_guest_enter(struct vcpu_vmx *vmx) * GUEST_IA32_RTIT_CTL is already set in the VMCS. * Save host state before VM entry. */ - rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); + rdmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { - wrmsrl(MSR_IA32_RTIT_CTL, 0); + wrmsrq(MSR_IA32_RTIT_CTL, 0); pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges); pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges); } @@ -1154,7 +1310,7 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) * i.e. RTIT_CTL is always cleared on VM-Exit. Restore it if necessary. */ if (vmx->pt_desc.host.ctl) - wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); + wrmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, @@ -1187,6 +1343,7 @@ void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); struct vmcs_host_state *host_state; #ifdef CONFIG_X86_64 int cpu = raw_smp_processor_id(); @@ -1195,8 +1352,6 @@ 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 @@ -1214,10 +1369,10 @@ 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) + if (vt->guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; @@ -1238,15 +1393,15 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) fs_sel = current->thread.fsindex; gs_sel = current->thread.gsindex; fs_base = current->thread.fsbase; - vmx->msr_host_kernel_gs_base = current->thread.gsbase; + vt->msr_host_kernel_gs_base = current->thread.gsbase; } else { savesegment(fs, fs_sel); savesegment(gs, gs_sel); fs_base = read_msr(MSR_FS_BASE); - vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else savesegment(fs, fs_sel); savesegment(gs, gs_sel); @@ -1255,14 +1410,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) #endif vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); - vmx->guest_state_loaded = true; + vt->guest_state_loaded = true; } static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) { struct vmcs_host_state *host_state; - if (!vmx->guest_state_loaded) + if (!vmx->vt.guest_state_loaded) return; host_state = &vmx->loaded_vmcs->host_state; @@ -1270,7 +1425,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) ++vmx->vcpu.stat.host_state_reload; #ifdef CONFIG_X86_64 - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif if (host_state->ldt_sel || (host_state->gs_sel & 7)) { kvm_load_ldt(host_state->ldt_sel); @@ -1290,35 +1445,79 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) #endif invalidate_tss_limit(); #ifdef CONFIG_X86_64 - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + wrmsrq(MSR_KERNEL_GS_BASE, vmx->vt.msr_host_kernel_gs_base); #endif load_fixmap_gdt(raw_smp_processor_id()); - vmx->guest_state_loaded = false; + vmx->vt.guest_state_loaded = false; vmx->guest_uret_msrs_loaded = false; } #ifdef CONFIG_X86_64 -static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) +static u64 vmx_read_guest_host_msr(struct vcpu_vmx *vmx, u32 msr, u64 *cache) { preempt_disable(); - if (vmx->guest_state_loaded) - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + if (vmx->vt.guest_state_loaded) + *cache = read_msr(msr); preempt_enable(); - return vmx->msr_guest_kernel_gs_base; + return *cache; } -static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) +static void vmx_write_guest_host_msr(struct vcpu_vmx *vmx, u32 msr, u64 data, + u64 *cache) { preempt_disable(); - if (vmx->guest_state_loaded) - wrmsrl(MSR_KERNEL_GS_BASE, data); + if (vmx->vt.guest_state_loaded) + wrmsrns(msr, data); preempt_enable(); - vmx->msr_guest_kernel_gs_base = data; + *cache = data; +} + +static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) +{ + return vmx_read_guest_host_msr(vmx, MSR_KERNEL_GS_BASE, + &vmx->msr_guest_kernel_gs_base); +} + +static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) +{ + vmx_write_guest_host_msr(vmx, MSR_KERNEL_GS_BASE, data, + &vmx->msr_guest_kernel_gs_base); } #endif -void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, - struct loaded_vmcs *buddy) +static void grow_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned int old = vmx->ple_window; + + vmx->ple_window = __grow_ple_window(old, ple_window, + ple_window_grow, + ple_window_max); + + if (vmx->ple_window != old) { + vmx->ple_window_dirty = true; + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } +} + +static void shrink_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned int old = vmx->ple_window; + + vmx->ple_window = __shrink_ple_window(old, ple_window, + ple_window_shrink, + ple_window); + + if (vmx->ple_window != old) { + vmx->ple_window_dirty = true; + trace_kvm_ple_window_update(vcpu->vcpu_id, + vmx->ple_window, old); + } +} + +void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool already_loaded = vmx->loaded_vmcs->cpu == cpu; @@ -1345,16 +1544,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, if (prev != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); - - /* - * No indirect branch prediction barrier needed when switching - * 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(); } if (!already_loaded) { @@ -1388,18 +1577,17 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. */ -static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); + if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm)) + shrink_ple_window(vcpu); - vmx_vcpu_load_vmcs(vcpu, cpu, NULL); + vmx_vcpu_load_vmcs(vcpu, cpu); vmx_vcpu_pi_load(vcpu, cpu); - - vmx->host_debugctlmsr = get_debugctlmsr(); } -static void vmx_vcpu_put(struct kvm_vcpu *vcpu) +void vmx_vcpu_put(struct kvm_vcpu *vcpu) { vmx_vcpu_pi_put(vcpu); @@ -1434,6 +1622,11 @@ 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; @@ -1450,10 +1643,10 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = vmx_emulation_required(vcpu); + vmx->vt.emulation_required = vmx_emulation_required(vcpu); } -static bool vmx_get_if_flag(struct kvm_vcpu *vcpu) +bool vmx_get_if_flag(struct kvm_vcpu *vcpu) { return vmx_get_rflags(vcpu) & X86_EFLAGS_IF; } @@ -1504,7 +1697,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) * result in a #GP unless the same write also clears TraceEn. */ if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && - ((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN)) + (data & RTIT_CTL_TRACEEN) && + data != vmx->pt_desc.guest.ctl) return 1; /* @@ -1559,8 +1753,8 @@ 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) +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 @@ -1569,16 +1763,22 @@ static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * so that guest userspace can't DoS the guest simply by triggering * emulation (enclaves are CPL3 only). */ - if (to_vmx(vcpu)->exit_reason.enclave_mode) { + if (vmx_get_exit_reason(vcpu).enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); - return false; + return X86EMUL_PROPAGATE_FAULT; } - return true; + + /* Check that emulation is possible during event vectoring */ + if ((to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && + !kvm_can_emulate_event_vectoring(emul_type)) + return X86EMUL_UNHANDLEABLE_VECTORING; + + return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { - union vmx_exit_reason exit_reason = to_vmx(vcpu)->exit_reason; + union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); unsigned long rip, orig_rip; u32 instr_len; @@ -1613,8 +1813,8 @@ 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; @@ -1644,7 +1844,7 @@ rip_updated: * Recognizes a pending MTF VM-exit and records the nested state for later * delivery. */ -static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -1675,7 +1875,7 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) } } -static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) { vmx_update_emulated_instruction(vcpu); return skip_emulated_instruction(vcpu); @@ -1694,7 +1894,7 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } -static void vmx_inject_exception(struct kvm_vcpu *vcpu) +void vmx_inject_exception(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; u32 intr_info = ex->vector | INTR_INFO_VALID_MASK; @@ -1711,7 +1911,7 @@ static void vmx_inject_exception(struct kvm_vcpu *vcpu) * 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 - * does't really exist is preferable to killing the VM. + * 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; @@ -1725,7 +1925,7 @@ static void vmx_inject_exception(struct kvm_vcpu *vcpu) return; } - WARN_ON_ONCE(vmx->emulation_required); + WARN_ON_ONCE(vmx->vt.emulation_required); if (kvm_exception_is_soft(ex->vector)) { vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, @@ -1776,8 +1976,8 @@ static void vmx_setup_uret_msrs(struct vcpu_vmx *vmx) vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); vmx_setup_uret_msr(vmx, MSR_TSC_AUX, - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDPID)); /* * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new @@ -1815,25 +2015,14 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) return kvm_caps.default_tsc_scaling_ratio; } -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +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) +void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu) { - vmcs_write64(TSC_MULTIPLIER, multiplier); -} - -/* - * 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. - */ -bool nested_vmx_allowed(struct kvm_vcpu *vcpu) -{ - return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX); + vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); } /* @@ -1874,15 +2063,15 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, return !(msr->data & ~valid_bits); } -static int vmx_get_msr_feature(struct kvm_msr_entry *msr) +int vmx_get_feature_msr(u32 msr, u64 *data) { - switch (msr->index) { - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + switch (msr) { + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; - return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); + return vmx_get_vmx_msr(&vmcs_config.nested, msr, data); default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } } @@ -1891,7 +2080,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -1941,7 +2130,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -1957,17 +2146,18 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) return 1; 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_cpu_cap_has(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 @@ -1975,9 +2165,10 @@ 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 && guest_cpuid_has_evmcs(vcpu)) + if (!msr_info->host_initiated && guest_cpu_cap_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()) @@ -2024,8 +2215,17 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; + case MSR_IA32_S_CET: + msr_info->data = vmcs_readl(GUEST_S_CET); + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + msr_info->data = vmcs_readl(GUEST_SSP); + break; + case MSR_IA32_INT_SSP_TAB: + msr_info->data = vmcs_readl(GUEST_INTR_SSP_TABLE); + break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: @@ -2044,33 +2244,49 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, u64 data) { #ifdef CONFIG_X86_64 - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return (u32)data; #endif return (unsigned long)data; } -static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { u64 debugctl = 0; if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && - (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && + if ((kvm_caps.supported_perf_cap & PERF_CAP_LBR_FMT) && (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; + if (boot_cpu_has(X86_FEATURE_RTM) && + (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_RTM))) + debugctl |= DEBUGCTLMSR_RTM_DEBUG; + return debugctl; } +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated) +{ + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated); + if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) { + kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data); + invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR); + } + return !invalid; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmx_uret_msr *msr; @@ -2133,37 +2349,28 @@ 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; - - 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); - data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - } - - if (invalid) + case MSR_IA32_DEBUGCTLMSR: + if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated)) return 1; + data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; - } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; - if (is_noncanonical_address(data & PAGE_MASK, vcpu) || + if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) return 1; @@ -2219,47 +2426,17 @@ 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 && @@ -2293,17 +2470,17 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * behavior, but it's close enough. */ if (!msr_info->host_initiated && - (!guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC) || + (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC) || ((vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED) && !(vmx->msr_ia32_feature_control & FEAT_CTL_SGX_LC_ENABLED)))) return 1; 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_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: @@ -2358,19 +2535,26 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (index >= 2 * vmx->pt_desc.num_address_ranges) return 1; - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; else vmx->pt_desc.guest.addr_a[index / 2] = data; break; + case MSR_IA32_S_CET: + vmcs_writel(GUEST_S_CET, data); + break; + case MSR_KVM_INTERNAL_GUEST_SSP: + vmcs_writel(GUEST_SSP, data); + break; + case MSR_IA32_INT_SSP_TAB: + vmcs_writel(GUEST_INTR_SSP_TABLE, data); + break; case MSR_IA32_PERF_CAPABILITIES: - if (data && !vcpu_to_pmu(vcpu)->version) - return 1; - if (data & PMU_CAP_LBR_FMT) { - if ((data & PMU_CAP_LBR_FMT) != - (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT)) + if (data & PERF_CAP_LBR_FMT) { + if ((data & PERF_CAP_LBR_FMT) != + (kvm_caps.supported_perf_cap & PERF_CAP_LBR_FMT)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; @@ -2379,9 +2563,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) 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)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DS)) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_DTES64)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DTES64)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; @@ -2405,7 +2589,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return ret; } -static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) +void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { unsigned long guest_owned_bits; @@ -2448,88 +2632,6 @@ 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 @@ -2541,32 +2643,7 @@ static bool cpu_has_sgx(void) return cpuid_eax(0) >= 0x12 && (cpuid_eax(0x12) & BIT(0)); } -/* - * 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 __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32 *result) +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; @@ -2584,27 +2661,54 @@ static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, return 0; } -static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) +static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) { u64 allowed; - rdmsrl(msr, allowed); + rdmsrq(msr, allowed); return ctl_opt & allowed; } -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, - struct vmx_capability *vmx_cap) +#define vmx_check_entry_exit_pairs(pairs, entry_controls, exit_controls) \ +({ \ + int i, r = 0; \ + \ + BUILD_BUG_ON(sizeof(pairs[0].entry_control) != sizeof(entry_controls)); \ + BUILD_BUG_ON(sizeof(pairs[0].exit_control) != sizeof(exit_controls)); \ + \ + for (i = 0; i < ARRAY_SIZE(pairs); i++) { \ + typeof(entry_controls) n_ctrl = pairs[i].entry_control; \ + typeof(exit_controls) x_ctrl = pairs[i].exit_control; \ + \ + if (!(entry_controls & n_ctrl) == !(exit_controls & x_ctrl)) \ + continue; \ + \ + pr_warn_once("Inconsistent VM-Entry/VM-Exit pair, " \ + "entry = %llx (%llx), exit = %llx (%llx)\n", \ + (u64)(entry_controls & n_ctrl), (u64)n_ctrl, \ + (u64)(exit_controls & x_ctrl), (u64)x_ctrl); \ + \ + if (error_on_inconsistent_vmcs_config) \ + r = -EIO; \ + \ + entry_controls &= ~n_ctrl; \ + exit_controls &= ~x_ctrl; \ + } \ + r; \ +}) + +static int setup_vmcs_config(struct vmcs_config *vmcs_conf, + struct vmx_capability *vmx_cap) { - u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; + u64 basic_msr; u64 misc_msr; - int i; /* * LOAD/SAVE_DEBUG_CONTROLS are absent because both are mandatory. @@ -2620,6 +2724,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, { 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 }, + { VM_ENTRY_LOAD_CET_STATE, VM_EXIT_LOAD_CET_STATE }, }; memset(vmcs_conf, 0, sizeof(*vmcs_conf)); @@ -2636,6 +2741,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, &_cpu_based_2nd_exec_control)) return -EIO; } + if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE)) + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; + #ifndef CONFIG_X86_64 if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) @@ -2660,6 +2768,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, return -EIO; vmx_cap->ept = 0; + _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; } if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && vmx_cap->vpid) { @@ -2704,46 +2813,54 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, &_vmentry_control)) return -EIO; - 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; + if (vmx_check_entry_exit_pairs(vmcs_entry_exit_pairs, + _vmentry_control, _vmexit_control)) + return -EIO; - _vmentry_control &= ~n_ctrl; - _vmexit_control &= ~x_ctrl; + /* + * 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. + */ + switch (boot_cpu_data.x86_vfm) { + case INTEL_NEHALEM_EP: /* AAK155 */ + case INTEL_NEHALEM: /* AAP115 */ + case INTEL_WESTMERE: /* AAT100 */ + case INTEL_WESTMERE_EP: /* BC86,AAY89,BD102 */ + case INTEL_NEHALEM_EX: /* BA97 */ + _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + "does not work properly. Using workaround\n"); + break; + default: + break; } - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); + rdmsrq(MSR_IA32_VMX_BASIC, basic_msr); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) + if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE) return -EIO; #ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) + /* + * KVM expects to be able to shove all legal physical addresses into + * VMCS fields for 64-bit kernels, and per the SDM, "This bit is always + * 0 for processors that support Intel 64 architecture". + */ + if (basic_msr & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) + if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB) return -EIO; - rdmsrl(MSR_IA32_VMX_MISC, misc_msr); - - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - - vmcs_conf->revision_id = vmx_msr_low; + rdmsrq(MSR_IA32_VMX_MISC, misc_msr); + vmcs_conf->basic = basic_msr; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; @@ -2752,9 +2869,134 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmcs_conf->vmentry_ctrl = _vmentry_control; vmcs_conf->misc = misc_msr; +#if IS_ENABLED(CONFIG_HYPERV) + if (enlightened_vmcs) + evmcs_sanitize_exec_ctrls(vmcs_conf); +#endif + + 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; +} + +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", + rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + cr4_clear_bits(X86_CR4_VMXE); + + return -EFAULT; +} + +int vmx_enable_virtualization_cpu(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; + } + 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); +} + +void vmx_disable_virtualization_cpu(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); @@ -2765,13 +3007,13 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) if (!pages) return NULL; vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); + memset(vmcs, 0, vmx_basic_vmcs_size(vmcs_config.basic)); /* KVM supports Enlightened VMCS v1 only */ - if (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; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); if (shadow) vmcs->hdr.shadow_vmcs = 1; @@ -2863,8 +3105,8 @@ static __init int alloc_kvm_area(void) * still be marked with revision_id reported by * physical CPU. */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs->hdr.revision_id = vmcs_config.revision_id; + if (kvm_is_using_evmcs()) + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); per_cpu(vmxarea, cpu) = vmcs; } @@ -2950,9 +3192,8 @@ 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); @@ -2967,6 +3208,15 @@ 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); @@ -2977,14 +3227,6 @@ 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); @@ -3057,7 +3299,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3082,12 +3324,46 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu) && nested_cpu_has_vpid(get_vmcs12(vcpu))) return nested_get_vpid02(vcpu); return to_vmx(vcpu)->vpid; } -static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) +static u64 construct_eptp(hpa_t root_hpa) +{ + u64 eptp = root_hpa | VMX_EPTP_MT_WB; + struct kvm_mmu_page *root; + + if (kvm_mmu_is_dummy_root(root_hpa)) + return eptp | VMX_EPTP_PWL_4; + + /* + * EPT roots should always have an associated MMU page. Return a "bad" + * EPTP to induce VM-Fail instead of continuing on in a unknown state. + */ + root = root_to_sp(root_hpa); + if (WARN_ON_ONCE(!root)) + return INVALID_PAGE; + + eptp |= (root->role.level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; + + if (enable_ept_ad_bits && !root->role.ad_disabled) + eptp |= VMX_EPTP_AD_ENABLE_BIT; + + return eptp; +} + +static void vmx_flush_tlb_ept_root(hpa_t root_hpa) +{ + u64 eptp = construct_eptp(root_hpa); + + if (VALID_PAGE(eptp)) + ept_sync_context(eptp); + else + ept_sync_global(); +} + +void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; u64 root_hpa = mmu->root.hpa; @@ -3097,13 +3373,12 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) return; if (enable_ept) - ept_sync_context(construct_eptp(vcpu, root_hpa, - mmu->root_role.level)); + vmx_flush_tlb_ept_root(root_hpa); else vpid_sync_context(vmx_get_current_vpid(vcpu)); } -static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { /* * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in @@ -3112,7 +3387,7 @@ static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr); } -static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) +void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) { /* * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a @@ -3157,6 +3432,17 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING) +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); @@ -3166,7 +3452,7 @@ 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; @@ -3194,7 +3480,7 @@ 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 @@ -3243,41 +3529,26 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = vmx_emulation_required(vcpu); + vmx->vt.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; return 4; } -u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) -{ - u64 eptp = VMX_EPTP_MT_WB; - - eptp |= (root_level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; - - if (enable_ept_ad_bits && - (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) - eptp |= VMX_EPTP_AD_ENABLE_BIT; - eptp |= root_hpa; - - return eptp; -} - -static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, - int root_level) +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; unsigned long guest_cr3; - u64 eptp; if (enable_ept) { - eptp = construct_eptp(vcpu, root_hpa, root_level); - vmcs_write64(EPT_POINTER, eptp); + KVM_MMU_WARN_ON(root_to_sp(root_hpa) && + root_level != root_to_sp(root_hpa)->role.level); + vmcs_write64(EPT_POINTER, construct_eptp(root_hpa)); hv_track_root_tdp(vcpu, root_hpa); @@ -3289,15 +3560,15 @@ 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) vmcs_writel(GUEST_CR3, guest_cr3); } - -static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { /* * We operate under the default treatment of SMM, so VMX cannot be @@ -3315,24 +3586,24 @@ 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; @@ -3345,7 +3616,7 @@ 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; @@ -3374,7 +3645,7 @@ void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_writel(GUEST_CR4, hw_cr4); if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) - kvm_update_cpuid_runtime(vcpu); + vcpu->arch.cpuid_dynamic_bits_dirty = true; } void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) @@ -3413,7 +3684,7 @@ void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) var->g = (ar >> 15) & 1; } -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) +u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_segment s; @@ -3424,16 +3695,29 @@ static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) return vmx_read_guest_seg_base(to_vmx(vcpu), seg); } -int vmx_get_cpl(struct kvm_vcpu *vcpu) +static int __vmx_get_cpl(struct kvm_vcpu *vcpu, bool no_cache) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int ar; if (unlikely(vmx->rmode.vm86_active)) return 0; - else { - int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return VMX_AR_DPL(ar); - } + + if (no_cache) + ar = vmcs_read32(GUEST_SS_AR_BYTES); + else + ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); + return VMX_AR_DPL(ar); +} + +int vmx_get_cpl(struct kvm_vcpu *vcpu) +{ + return __vmx_get_cpl(vcpu, false); +} + +int vmx_get_cpl_no_cache(struct kvm_vcpu *vcpu) +{ + return __vmx_get_cpl(vcpu, true); } static u32 vmx_segment_access_rights(struct kvm_segment *var) @@ -3490,14 +3774,14 @@ void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); } -static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) +void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { __vmx_set_segment(vcpu, var, seg); - to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); + to_vmx(vcpu)->vt.emulation_required = vmx_emulation_required(vcpu); } -static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); @@ -3505,25 +3789,25 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) *l = (ar >> 13) & 1; } -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_IDTR_LIMIT); dt->address = vmcs_readl(GUEST_IDTR_BASE); } -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_IDTR_LIMIT, dt->size); vmcs_writel(GUEST_IDTR_BASE, dt->address); } -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { dt->size = vmcs_read32(GUEST_GDTR_LIMIT); dt->address = vmcs_readl(GUEST_GDTR_BASE); } -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { vmcs_write32(GUEST_GDTR_LIMIT, dt->size); vmcs_writel(GUEST_GDTR_BASE, dt->address); @@ -3800,39 +4084,6 @@ 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; @@ -3865,57 +4116,18 @@ 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(); - - vmx->nested.force_msr_bitmap_recalc = true; -} - -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; - - if (!cpu_has_vmx_msr_bitmap()) - return; - - vmx_msr_bitmap_l01_changed(vmx); - - /* - * 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); - } - } - - if ((type & MSR_TYPE_R) && - !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) { - vmx_set_msr_bitmap_read(msr_bitmap, msr); - type &= ~MSR_TYPE_R; - } + if (kvm_is_using_evmcs()) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; - if ((type & MSR_TYPE_W) && - !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) { - vmx_set_msr_bitmap_write(msr_bitmap, msr); - type &= ~MSR_TYPE_W; + if (evmcs->hv_enlightenments_control.msr_bitmap) + evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; } - if (type & MSR_TYPE_R) - vmx_clear_msr_bitmap_read(msr_bitmap, msr); - - if (type & MSR_TYPE_W) - vmx_clear_msr_bitmap_write(msr_bitmap, msr); + vmx->nested.force_msr_bitmap_recalc = true; } -void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) +void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; @@ -3925,51 +4137,35 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) vmx_msr_bitmap_l01_changed(vmx); - /* - * 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); - } + if (type & MSR_TYPE_R) { + if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) + vmx_clear_msr_bitmap_read(msr_bitmap, msr); + else + vmx_set_msr_bitmap_read(msr_bitmap, msr); } - if (type & MSR_TYPE_R) - vmx_set_msr_bitmap_read(msr_bitmap, msr); - - if (type & MSR_TYPE_W) - 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; + if (type & MSR_TYPE_W) { + if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) + vmx_clear_msr_bitmap_write(msr_bitmap, msr); + else + vmx_set_msr_bitmap_write(msr_bitmap, msr); } } 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() && @@ -3987,7 +4183,18 @@ 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 @@ -4021,96 +4228,81 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu) } } -static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - void *vapic_page; - u32 vppr; - int rvi; + bool intercept; - if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || - !nested_cpu_has_vid(get_vmcs12(vcpu)) || - WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn)) - return false; + if (!cpu_has_vmx_msr_bitmap()) + return; - rvi = vmx_get_rvi(); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); +#ifdef CONFIG_X86_64 + vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); +#endif + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); + if (kvm_cstate_in_guest(vcpu->kvm)) { + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); + } + if (kvm_aperfmperf_in_guest(vcpu->kvm)) { + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R); + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R); + } - vapic_page = vmx->nested.virtual_apic_map.hva; - vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); + /* 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); - return ((rvi & 0xf0) > (vppr & 0xf0)); -} + if (vcpu->arch.xfd_no_write_intercept) + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW); -static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 i; + vmx_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW, + !to_vmx(vcpu)->spec_ctrl); - /* - * 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]; + if (kvm_cpu_cap_has(X86_FEATURE_XFD)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); - if (!test_bit(i, vmx->shadow_msr_intercept.read)) - vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_R); + if (cpu_feature_enabled(X86_FEATURE_IBPB)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, + !guest_has_pred_cmd_msr(vcpu)); - if (!test_bit(i, vmx->shadow_msr_intercept.write)) - vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_W); - } + if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); - /* 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); -} + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { + intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); -static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, - int pi_vec) -{ -#ifdef CONFIG_SMP - if (vcpu->mode == IN_GUEST_MODE) { - /* - * The vector of the virtual has already been set in the PIR. - * Send a notification event to deliver the virtual interrupt - * unless the vCPU is the currently running vCPU, i.e. the - * event is being sent from a fastpath VM-Exit handler, in - * which case the PIR will be synced to the vIRR before - * re-entering the guest. - * - * When the target is not the running vCPU, the following - * possibilities emerge: - * - * Case 1: vCPU stays in non-root mode. Sending a notification - * event posts the interrupt to the vCPU. - * - * Case 2: vCPU exits to root mode and is still runnable. The - * PIR will be synced to the vIRR before re-entering the guest. - * Sending a notification event is ok as the host IRQ handler - * will ignore the spurious event. - * - * Case 3: vCPU exits to root mode and is blocked. vcpu_block() - * has already synced PIR to vIRR and never blocks the vCPU if - * the vIRR is not empty. Therefore, a blocked vCPU here does - * not wait for any requested interrupts in PIR, and sending a - * notification event also results in a benign, spurious event. - */ + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP, MSR_TYPE_RW, intercept); + } - if (vcpu != kvm_get_running_vcpu()) - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); - return; + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK) || kvm_cpu_cap_has(X86_FEATURE_IBT)) { + intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK); + + vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET, MSR_TYPE_RW, intercept); + vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET, MSR_TYPE_RW, intercept); } -#endif + /* - * The vCPU isn't in the guest; wake the vCPU in case it is blocking, - * otherwise do nothing as KVM will grab the highest priority pending - * IRQ via ->sync_pir_to_irr() in vcpu_enter_guest(). + * x2APIC and LBR MSR intercepts are modified on-demand and cannot be + * filtered by userspace. */ - kvm_vcpu_wake_up(vcpu); +} + +void vmx_recalc_intercepts(struct kvm_vcpu *vcpu) +{ + vmx_recalc_msr_intercepts(vcpu); } static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, @@ -4118,6 +4310,13 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated + * and freed, and must not be accessed outside of vcpu->mutex. The + * vCPU's cached PI NV is valid if and only if posted interrupts + * enabled in its vmcs12, i.e. checking the vector also checks that + * L1 has enabled posted interrupts for L2. + */ if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* @@ -4154,7 +4353,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, */ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { - struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); @@ -4165,25 +4364,12 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (!vcpu->arch.apic->apicv_active) return -1; - if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return 0; - - /* If a previous notification has sent the IPI, nothing to do. */ - if (pi_test_and_set_on(&vmx->pi_desc)) - return 0; - - /* - * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*() - * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is - * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a - * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE. - */ - kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR); + __vmx_deliver_posted_interrupt(vcpu, &vt->pi_desc, vector); return 0; } -static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, - int trig_mode, int vector) +void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) { struct kvm_vcpu *vcpu = apic->vcpu; @@ -4258,7 +4444,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32)) vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); - rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); + rdmsrq(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) { @@ -4267,7 +4453,22 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) } if (cpu_has_load_ia32_efer()) - vmcs_write64(HOST_IA32_EFER, host_efer); + vmcs_write64(HOST_IA32_EFER, kvm_host.efer); + + /* + * Supervisor shadow stack is not enabled on host side, i.e., + * host IA32_S_CET.SHSTK_EN bit is guaranteed to 0 now, per SDM + * description(RDSSP instruction), SSP is not readable in CPL0, + * so resetting the two registers to 0s at VM-Exit does no harm + * to kernel execution. When execution flow exits to userspace, + * SSP is reloaded from IA32_PL3_SSP. Check SDM Vol.2A/B Chapter + * 3 and 4 for details. + */ + if (cpu_has_load_cet_ctrl()) { + vmcs_writel(HOST_S_CET, kvm_host.s_cet); + vmcs_writel(HOST_SSP, 0); + vmcs_writel(HOST_INTR_SSP_TABLE, 0); + } } void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) @@ -4302,7 +4503,7 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) return pin_based_exec_ctrl; } -static u32 vmx_vmentry_ctrl(void) +static u32 vmx_get_initial_vmentry_ctrl(void) { u32 vmentry_ctrl = vmcs_config.vmentry_ctrl; @@ -4316,13 +4517,10 @@ static u32 vmx_vmentry_ctrl(void) 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) +static u32 vmx_get_initial_vmexit_ctrl(void) { u32 vmexit_ctrl = vmcs_config.vmexit_ctrl; @@ -4336,16 +4534,12 @@ static u32 vmx_vmexit_ctrl(void) 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); } -static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4356,19 +4550,13 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - 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); - } + secondary_exec_controls_changebit(vmx, + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY, + kvm_vcpu_apicv_active(vcpu)); + if (enable_ipiv) + tertiary_exec_controls_changebit(vmx, TERTIARY_EXEC_IPI_VIRT, + kvm_vcpu_apicv_active(vcpu)); vmx_update_msr_bitmap_x2apic(vcpu); } @@ -4455,7 +4643,8 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, * Update the nested MSR settings so that a nested VMM can/can't set * controls for features that are/aren't exposed to the guest. */ - if (nested) { + if (nested && + kvm_check_has_quirk(vmx->vcpu.kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { /* * All features that can be added or removed to VMX MSRs must * be supported in the first place for nested virtualization. @@ -4475,16 +4664,16 @@ 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()) { \ + __enabled = guest_cpu_cap_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. */ @@ -4508,6 +4697,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE; enable_unrestricted_guest = 0; } if (!enable_unrestricted_guest) @@ -4519,6 +4709,12 @@ 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; @@ -4535,22 +4731,10 @@ 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 @@ -4562,13 +4746,14 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) */ if (cpu_has_vmx_rdtscp()) { bool rdpid_or_rdtscp_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); vmx_adjust_secondary_exec_control(vmx, &exec_control, 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); @@ -4602,7 +4787,8 @@ static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) if (kvm_vmx->pid_table) return 0; - pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, vmx_get_pid_table_order(kvm)); + pages = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, + vmx_get_pid_table_order(kvm)); if (!pages) return -ENOMEM; @@ -4610,7 +4796,7 @@ static int vmx_alloc_ipiv_pid_table(struct kvm *kvm) return 0; } -static int vmx_vcpu_precreate(struct kvm *kvm) +int vmx_vcpu_precreate(struct kvm *kvm) { return vmx_alloc_ipiv_pid_table(kvm); } @@ -4635,8 +4821,12 @@ static void init_vmcs(struct vcpu_vmx *vmx) exec_controls_set(vmx, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) + if (cpu_has_secondary_exec_ctrls()) { secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx)); + if (vmx->ve_info) + vmcs_write64(VE_INFORMATION_ADDRESS, + __pa(vmx->ve_info)); + } if (cpu_has_tertiary_exec_ctrls()) tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx)); @@ -4650,7 +4840,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write16(GUEST_INTR_STATUS, 0); vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); - vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); + vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->vt.pi_desc))); } if (vmx_can_use_ipiv(&vmx->vcpu)) { @@ -4689,12 +4879,12 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); + vm_exit_controls_set(vmx, vmx_get_initial_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ - vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); + vm_entry_controls_set(vmx, vmx_get_initial_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); @@ -4707,7 +4897,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (enable_pml) { vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } vmx_write_encls_bitmap(&vmx->vcpu, NULL); @@ -4722,7 +4912,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + vmx_guest_debugctl_write(&vmx->vcpu, 0); if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); @@ -4741,7 +4932,8 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) init_vmcs(vmx); - if (nested) + if (nested && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs)); vcpu_setup_sgx_lepubkeyhash(vcpu); @@ -4749,20 +4941,24 @@ 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; + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) + vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; /* * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR * or POSTED_INTR_WAKEUP_VECTOR. */ - vmx->pi_desc.nv = POSTED_INTR_VECTOR; - vmx->pi_desc.sn = 1; + vmx->vt.pi_desc.nv = POSTED_INTR_VECTOR; + __pi_set_sn(&vmx->vt.pi_desc); } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4777,9 +4973,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); - vmx_segment_cache_clear(vmx); - kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); - seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); @@ -4806,6 +4999,9 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_writel(GUEST_IDTR_BASE, 0); vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); + vmx_segment_cache_clear(vmx); + kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); + vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); @@ -4814,6 +5010,14 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ + if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) { + vmcs_writel(GUEST_SSP, 0); + vmcs_writel(GUEST_INTR_SSP_TABLE, 0); + } + if (kvm_cpu_cap_has(X86_FEATURE_IBT) || + kvm_cpu_cap_has(X86_FEATURE_SHSTK)) + vmcs_writel(GUEST_S_CET, 0); + kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); vpid_sync_context(vmx->vpid); @@ -4821,12 +5025,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_update_fb_clear_dis(vcpu, vmx); } -static void vmx_enable_irq_window(struct kvm_vcpu *vcpu) +void vmx_enable_irq_window(struct kvm_vcpu *vcpu) { exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); } -static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) +void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) { if (!enable_vnmi || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { @@ -4837,7 +5041,7 @@ static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } -static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) +void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; @@ -4865,7 +5069,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) vmx_clear_hlt(vcpu); } -static void vmx_inject_nmi(struct kvm_vcpu *vcpu) +void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4943,7 +5147,7 @@ bool vmx_nmi_blocked(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_NMI)); } -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; @@ -4955,32 +5159,37 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_nmi_blocked(vcpu); } +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu) +{ + return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); +} + bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return false; - return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || - (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); + return __vmx_interrupt_blocked(vcpu); } -static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) return -EBUSY; - /* - * 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; return !vmx_interrupt_blocked(vcpu); } -static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) +int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { void __user *ret; @@ -5000,7 +5209,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return init_rmode_tss(kvm, ret); } -static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) +int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; return 0; @@ -5084,10 +5293,16 @@ 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); } +static bool is_xfd_nm_fault(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_fpu.fpstate->xfd && + !kvm_is_cr0_bit_set(vcpu, X86_CR0_TS); +} + static int handle_exception_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5099,8 +5314,13 @@ 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(). @@ -5109,13 +5329,24 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * point. */ if (is_nm_fault(intr_info)) { - kvm_queue_exception(vcpu, NM_VECTOR); + kvm_queue_exception_p(vcpu, NM_VECTOR, + is_xfd_nm_fault(vcpu) ? vcpu->arch.guest_fpu.xfd_err : 0); return 1; } if (is_invalid_opcode(intr_info)) return handle_ud(vcpu); + if (WARN_ON_ONCE(is_ve_fault(intr_info))) { + struct vmx_ve_information *ve_info = vmx->ve_info; + + WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION, + "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason); + dump_vmcs(vcpu); + kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE"); + return 1; + } + error_code = 0; if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); @@ -5281,8 +5512,7 @@ static int handle_io(struct kvm_vcpu *vcpu) return kvm_fast_pio(vcpu, size, port, in); } -static void -vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) +void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Patch in the VMCALL instruction: @@ -5310,18 +5540,11 @@ 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); } } @@ -5345,7 +5568,13 @@ 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); } @@ -5416,7 +5645,7 @@ 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); @@ -5479,10 +5708,7 @@ 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)); @@ -5492,7 +5718,7 @@ out: return kvm_complete_insn_gp(vcpu, err); } -static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) +void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); @@ -5511,7 +5737,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } -static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) +void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); } @@ -5648,11 +5874,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) static int handle_ept_violation(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification; + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); gpa_t gpa; - u64 error_code; - - exit_qualification = vmx_get_exit_qual(vcpu); /* * EPT violation happened while executing iret from NMI, @@ -5668,24 +5891,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(vcpu, gpa, exit_qualification); - /* Is it a read fault? */ - error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) - ? PFERR_USER_MASK : 0; - /* Is it a write fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) - ? PFERR_WRITE_MASK : 0; - /* Is it a fetch fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) - ? PFERR_FETCH_MASK : 0; - /* ept page table entry is present? */ - error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK) - ? PFERR_PRESENT_MASK : 0; - - error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? - PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; - - vcpu->arch.exit_qualification = exit_qualification; - /* * Check that the GPA doesn't exceed physical memory limits, as that is * a guest page fault. We have to emulate the instruction here, because @@ -5694,17 +5899,17 @@ 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); + return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification); } 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; /* @@ -5733,11 +5938,35 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu) return 1; } -static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) +/* + * Returns true if emulation is required (due to the vCPU having invalid state + * with unsrestricted guest mode disabled) and KVM can't faithfully emulate the + * current vCPU state. + */ +static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - return vmx->emulation_required && !vmx->rmode.vm86_active && + if (!vmx->vt.emulation_required) + return false; + + /* + * It is architecturally impossible for emulation to be required when a + * nested VM-Enter is pending completion, as VM-Enter will VM-Fail if + * guest state is invalid and unrestricted guest is disabled, i.e. KVM + * should synthesize VM-Fail instead emulation L2 code. This path is + * only reachable if userspace modifies L2 guest state after KVM has + * performed the nested VM-Enter consistency checks. + */ + if (vmx->nested.nested_run_pending) + return true; + + /* + * KVM only supports emulating exceptions if the vCPU is in Real Mode. + * If emulation is required, KVM can't perform a successful VM-Enter to + * inject the exception. + */ + return !vmx->rmode.vm86_active && (kvm_is_exception_pending(vcpu) || vcpu->arch.exception.injected); } @@ -5750,17 +5979,24 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) intr_window_requested = exec_controls_get(vmx) & CPU_BASED_INTR_WINDOW_EXITING; - while (vmx->emulation_required && count-- != 0) { + while (vmx->vt.emulation_required && count-- != 0) { if (intr_window_requested && !vmx_interrupt_blocked(vcpu)) return handle_interrupt_window(&vmx->vcpu); if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; + /* + * Ensure that any updates to kvm->buses[] observed by the + * previous instruction (emulated or otherwise) are also + * visible to the instruction KVM is about to emulate. + */ + smp_rmb(); + if (!kvm_emulate_instruction(vcpu, 0)) return 0; - if (vmx_emulation_required_with_pending_exception(vcpu)) { + if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } @@ -5782,9 +6018,9 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) return 1; } -static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) +int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) { - if (vmx_emulation_required_with_pending_exception(vcpu)) { + if (vmx_unhandleable_emulation_required(vcpu)) { kvm_prepare_emulation_failure_exit(vcpu); return 0; } @@ -5792,38 +6028,6 @@ static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu) return 1; } -static void grow_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __grow_ple_window(old, ple_window, - ple_window_grow, - ple_window_max); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - -static void shrink_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __shrink_ple_window(old, ple_window, - ple_window_shrink, - ple_window); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - /* * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE * exiting, so only get here on cpu with PAUSE-Loop-Exiting. @@ -5859,7 +6063,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } operand; int gpr_index; - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -5904,28 +6108,52 @@ 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; } /* * When nested=0, all VMX instruction VM Exits filter here. The handlers - * are overwritten by nested_vmx_setup() when nested=1. + * are overwritten by nested_vmx_hardware_setup() when nested=1. */ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) { @@ -5933,6 +6161,12 @@ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) return 1; } +static int handle_tdx_instruction(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + #ifndef CONFIG_X86_SGX_KVM static int handle_encls(struct kvm_vcpu *vcpu) { @@ -5953,7 +6187,7 @@ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu) * VM-Exits. Unconditionally set the flag here and leave the handling to * vmx_handle_exit(). */ - to_vmx(vcpu)->exit_reason.bus_lock_detected = true; + to_vt(vcpu)->exit_reason.bus_lock_detected = true; return 1; } @@ -5983,6 +6217,23 @@ static int handle_notify(struct kvm_vcpu *vcpu) return 1; } +static int vmx_get_msr_imm_reg(struct kvm_vcpu *vcpu) +{ + return vmx_get_instr_info_reg(vmcs_read32(VMX_INSTRUCTION_INFO)); +} + +static int handle_rdmsr_imm(struct kvm_vcpu *vcpu) +{ + return kvm_emulate_rdmsr_imm(vcpu, vmx_get_exit_qual(vcpu), + vmx_get_msr_imm_reg(vcpu)); +} + +static int handle_wrmsr_imm(struct kvm_vcpu *vcpu) +{ + return kvm_emulate_wrmsr_imm(vcpu, vmx_get_exit_qual(vcpu), + vmx_get_msr_imm_reg(vcpu)); +} + /* * 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 @@ -6041,20 +6292,23 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_ENCLS] = handle_encls, [EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit, [EXIT_REASON_NOTIFY] = handle_notify, + [EXIT_REASON_SEAMCALL] = handle_tdx_instruction, + [EXIT_REASON_TDCALL] = handle_tdx_instruction, + [EXIT_REASON_MSR_READ_IMM] = handle_rdmsr_imm, + [EXIT_REASON_MSR_WRITE_IMM] = handle_wrmsr_imm, }; static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); -static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, - u64 *info1, u64 *info2, - u32 *intr_info, u32 *error_code) +void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); - *reason = vmx->exit_reason.full; + *reason = vmx->vt.exit_reason.full; *info1 = vmx_get_exit_qual(vcpu); - if (!(vmx->exit_reason.failed_vmentry)) { + if (!(vmx->vt.exit_reason.failed_vmentry)) { *info2 = vmx->idt_vectoring_info; *intr_info = vmx_get_intr_info(vcpu); if (is_exception_with_error_code(*intr_info)) @@ -6068,6 +6322,15 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, } } +void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) +{ + *intr_info = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); + if (is_exception_with_error_code(*intr_info)) + *error_code = vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE); + else + *error_code = 0; +} + static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { if (vmx->pml_pg) { @@ -6079,32 +6342,40 @@ static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u16 pml_idx, pml_tail_index; u64 *pml_buf; - u16 pml_idx; + int i; pml_idx = vmcs_read16(GUEST_PML_INDEX); /* Do nothing if PML buffer is empty */ - if (pml_idx == (PML_ENTITY_NUM - 1)) + if (pml_idx == PML_HEAD_INDEX) return; + /* + * PML index always points to the next available PML buffer entity + * unless PML log has just overflowed. + */ + pml_tail_index = (pml_idx >= PML_LOG_NR_ENTRIES) ? 0 : pml_idx + 1; - /* PML index always points to next available PML buffer entity */ - if (pml_idx >= PML_ENTITY_NUM) - pml_idx = 0; - else - pml_idx++; - + /* + * PML log is written backwards: the CPU first writes the entry 511 + * then the entry 510, and so on. + * + * Read the entries in the same order they were written, to ensure that + * the dirty ring is filled in the same order the CPU wrote them. + */ pml_buf = page_address(vmx->pml_pg); - for (; pml_idx < PML_ENTITY_NUM; pml_idx++) { + + for (i = PML_HEAD_INDEX; i >= pml_tail_index; i--) { u64 gpa; - gpa = pml_buf[pml_idx]; + gpa = pml_buf[i]; WARN_ON(gpa & (PAGE_SIZE - 1)); kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } static void vmx_dump_sel(char *name, uint32_t sel) @@ -6229,6 +6500,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu) if (vmcs_read32(VM_EXIT_MSR_STORE_COUNT) > 0) vmx_dump_msrs("guest autostore", &vmx->msr_autostore.guest); + if (vmentry_ctl & VM_ENTRY_LOAD_CET_STATE) + pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n", + vmcs_readl(GUEST_S_CET), vmcs_readl(GUEST_SSP), + vmcs_readl(GUEST_INTR_SSP_TABLE)); pr_err("*** Host State ***\n"); pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); @@ -6259,6 +6534,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu) vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); if (vmcs_read32(VM_EXIT_MSR_LOAD_COUNT) > 0) vmx_dump_msrs("host autoload", &vmx->msr_autoload.host); + if (vmexit_ctl & VM_EXIT_LOAD_CET_STATE) + pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n", + vmcs_readl(HOST_S_CET), vmcs_readl(HOST_SSP), + vmcs_readl(HOST_INTR_SSP_TABLE)); pr_err("*** Control State ***\n"); pr_err("CPUBased=0x%08x SecondaryExec=0x%08x TertiaryExec=0x%016llx\n", @@ -6306,6 +6585,24 @@ void dump_vmcs(struct kvm_vcpu *vcpu) if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) pr_err("Virtual processor ID = 0x%04x\n", vmcs_read16(VIRTUAL_PROCESSOR_ID)); + if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct vmx_ve_information *ve_info = vmx->ve_info; + u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS); + + /* + * If KVM is dumping the VMCS, then something has gone wrong + * already. Derefencing an address from the VMCS, which could + * very well be corrupted, is a terrible idea. The virtual + * address is known so use it. + */ + pr_err("VE info address = 0x%016llx%s\n", ve_info_pa, + ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)"); + pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n", + ve_info->exit_reason, ve_info->delivery, + ve_info->exit_qualification, + ve_info->guest_linear_address, + ve_info->guest_physical_address, ve_info->eptp_index); + } } /* @@ -6315,7 +6612,7 @@ void dump_vmcs(struct kvm_vcpu *vcpu) static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); - union vmx_exit_reason exit_reason = vmx->exit_reason; + union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu); u32 vectoring_info = vmx->idt_vectoring_info; u16 exit_handler_index; @@ -6371,7 +6668,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * the least awful solution for the userspace case without * risking false positives. */ - if (vmx->emulation_required) { + if (vmx->vt.emulation_required) { nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); return 1; } @@ -6381,7 +6678,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) } /* If guest state is invalid, start emulating. L2 is handled above. */ - if (vmx->emulation_required) + if (vmx->vt.emulation_required) return handle_invalid_guest_state(vcpu); if (exit_reason.failed_vmentry) { @@ -6402,33 +6699,15 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - /* - * Note: - * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by - * delivery event since it indicates guest is accessing MMIO. - * The vm-exit can be triggered again after return to guest that - * will cause infinite loop. - */ if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && 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_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; - if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.data[ndata++] = - vmcs_read64(GUEST_PHYSICAL_ADDRESS); - } - vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; - vcpu->run->internal.ndata = ndata; + exit_reason.basic != EXIT_REASON_NOTIFY && + exit_reason.basic != EXIT_REASON_EPT_MISCONFIG)) { + kvm_prepare_event_vectoring_exit(vcpu, INVALID_GPA); return 0; } @@ -6456,9 +6735,11 @@ 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_MSR_WRITE_IMM) + return handle_wrmsr_imm(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) return handle_preemption_timer(vcpu); else if (exit_reason.basic == EXIT_REASON_INTERRUPT_WINDOW) @@ -6479,19 +6760,12 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return kvm_vmx_exit_handlers[exit_handler_index](vcpu); unexpected_vmexit: - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", - exit_reason.full); dump_vmcs(vcpu); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_reason.full; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + kvm_prepare_unexpected_reason_exit(vcpu, exit_reason.full); return 0; } -static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { int ret = __vmx_handle_exit(vcpu, exit_fastpath); @@ -6499,7 +6773,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) * Exit to user space when bus lock detected to inform that there is * a bus lock in guest. */ - if (to_vmx(vcpu)->exit_reason.bus_lock_detected) { + if (vmx_get_exit_reason(vcpu).bus_lock_detected) { if (ret > 0) vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK; @@ -6509,77 +6783,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return ret; } -/* - * Software based L1D cache flush which is used when microcode providing - * the cache control MSR is not loaded. - * - * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to - * flush it is required to read in 64 KiB because the replacement algorithm - * is not exactly LRU. This could be sized at runtime via topology - * information but as all relevant affected CPUs have 32KiB L1D cache size - * there is no point in doing so. - */ -static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) -{ - int size = PAGE_SIZE << L1D_CACHE_ORDER; - - /* - * This code is only executed when the flush mode is 'cond' or - * 'always' - */ - if (static_branch_likely(&vmx_l1d_flush_cond)) { - bool flush_l1d; - - /* - * Clear the per-vcpu flush bit, it gets set again - * either from vcpu_run() or from one of the unsafe - * VMEXIT handlers. - */ - flush_l1d = vcpu->arch.l1tf_flush_l1d; - vcpu->arch.l1tf_flush_l1d = false; - - /* - * Clear the per-cpu flush bit, it gets set again from - * the interrupt handlers. - */ - flush_l1d |= kvm_get_cpu_l1tf_flush_l1d(); - kvm_clear_cpu_l1tf_flush_l1d(); - - if (!flush_l1d) - return; - } - - vcpu->stat.l1d_flush++; - - if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { - native_wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); - return; - } - - asm volatile( - /* First ensure the pages are in the TLB */ - "xorl %%eax, %%eax\n" - ".Lpopulate_tlb:\n\t" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $4096, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lpopulate_tlb\n\t" - "xorl %%eax, %%eax\n\t" - "cpuid\n\t" - /* Now fill the cache */ - "xorl %%eax, %%eax\n" - ".Lfill_cache:\n" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $64, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lfill_cache\n\t" - "lfence\n" - :: [flush_pages] "r" (vmx_l1d_flush_pages), - [size] "r" (size) - : "eax", "ebx", "ecx", "edx"); -} - -static void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); int tpr_threshold; @@ -6649,9 +6853,16 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) vmx_update_msr_bitmap_x2apic(vcpu); } -static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) +void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { - 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; + struct page *refcounted_page; + unsigned long mmu_seq; + kvm_pfn_t pfn; + bool writable; /* Defer reload until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { @@ -6663,25 +6874,82 @@ 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 = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &refcounted_page); + 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); + else + vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn)); + + /* + * Do not pin the APIC access page in memory so that it can be freely + * migrated, the MMU notifier will call us again if it is migrated or + * swapped out. KVM backs the memslot with anonymous memory, the pfn + * should always point at a refcounted page (if the pfn is valid). + */ + if (!WARN_ON_ONCE(!refcounted_page)) + kvm_release_page_clean(refcounted_page); /* - * Do not pin apic access page in memory, the MMU notifier - * will call us again if it is migrated or swapped out. + * 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. */ - put_page(page); + read_unlock(&vcpu->kvm->mmu_lock); } -static void vmx_hwapic_isr_update(int max_isr) +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old; + /* + * If L2 is active, defer the SVI update until vmcs01 is loaded, as SVI + * is only relevant for if and only if Virtual Interrupt Delivery is + * enabled in vmcs12, and if VID is enabled then L2 EOIs affect L2's + * vAPIC, not L1's vAPIC. KVM must update vmcs01 on the next nested + * VM-Exit, otherwise L1 with run with a stale SVI. + */ + if (is_guest_mode(vcpu)) { + /* + * KVM is supposed to forward intercepted L2 EOIs to L1 if VID + * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC. + * Note, userspace can stuff state while L2 is active; assert + * that VID is disabled if and only if the vCPU is in KVM_RUN + * to avoid false positives if userspace is setting APIC state. + */ + WARN_ON_ONCE(vcpu->wants_to_run && + nested_cpu_has_vid(get_vmcs12(vcpu))); + to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true; + return; + } + if (max_isr == -1) max_isr = 0; @@ -6711,38 +6979,24 @@ static void vmx_set_rvi(int vector) } } -static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ - /* - * When running L2, updating RVI is only relevant when - * vmcs12 virtual-interrupt-delivery enabled. - * However, it can be enabled only when L1 also - * intercepts external-interrupts and in that case - * we should not update vmcs02 RVI but instead intercept - * interrupt. Therefore, do nothing when running L2. - */ - if (!is_guest_mode(vcpu)) - vmx_set_rvi(max_irr); -} - -static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vcpu_vt *vt = to_vt(vcpu); int max_irr; bool got_posted_interrupt; if (KVM_BUG_ON(!enable_apicv, vcpu->kvm)) return -EIO; - if (pi_test_on(&vmx->pi_desc)) { - pi_clear_on(&vmx->pi_desc); + if (pi_test_on(&vt->pi_desc)) { + pi_clear_on(&vt->pi_desc); /* * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); got_posted_interrupt = - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); + kvm_apic_update_irr(vcpu, vt->pi_desc.pir, &max_irr); } else { max_irr = kvm_lapic_find_highest_irr(vcpu); got_posted_interrupt = false; @@ -6771,7 +7025,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) return; @@ -6782,25 +7036,8 @@ 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) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - pi_clear_on(&vmx->pi_desc); - 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) { @@ -6809,70 +7046,81 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) * MSR value is not clobbered by the host activity before the guest * has chance to consume it. * - * Do not blindly read xfd_err here, since this exception might - * be caused by L1 interception on a platform which doesn't - * support xfd at all. - * - * Do it conditionally upon guest_fpu::xfd. xfd_err matters - * only when xfd contains a non-zero value. + * Update the guest's XFD_ERR if and only if XFD is enabled, as the #NM + * interception may have been caused by L1 interception. Per the SDM, + * XFD_ERR is not modified for non-XFD #NM, i.e. if CR0.TS=1. * - * Queuing exception is done in vmx_handle_exit. See comment there. + * Note, XFD_ERR is updated _before_ the #NM interception check, i.e. + * unlike CR2 and DR6, the value is not a payload that is attached to + * the #NM exception. */ - if (vcpu->arch.guest_fpu.fpstate->xfd) - rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); + if (is_xfd_nm_fault(vcpu)) + rdmsrq(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 kvm_vcpu *vcpu, u32 intr_info) { - 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 */ if (is_page_fault(intr_info)) - vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); + vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); /* if exit due to NM, handle before interrupts are enabled */ else if (is_nm_fault(intr_info)) - handle_nm_fault_irqoff(&vmx->vcpu); + handle_nm_fault_irqoff(vcpu); /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); - /* 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) +static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, + u32 intr_info) { - u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - 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)); + /* + * Invoke the kernel's IRQ handler for the vector. Use the FRED path + * when it's available even if FRED isn't fully enabled, e.g. even if + * FRED isn't supported in hardware, in order to avoid the indirect + * CALL in the non-FRED path. + */ + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); + if (IS_ENABLED(CONFIG_X86_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; } -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) +void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (vmx->emulation_required) + if (to_vt(vcpu)->emulation_required) return; - 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); + switch (vmx_get_exit_reason(vcpu).basic) { + case EXIT_REASON_EXTERNAL_INTERRUPT: + handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); + break; + case EXIT_REASON_EXCEPTION_NMI: + handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); + break; + case EXIT_REASON_MCE_DURING_VMENTRY: + kvm_machine_check(); + break; + default: + break; + } } /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. */ -static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) +bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: @@ -6883,7 +7131,7 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) * 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: @@ -6970,13 +7218,17 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, case INTR_TYPE_SOFT_EXCEPTION: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; - case INTR_TYPE_HARD_EXCEPTION: - if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { - u32 err = vmcs_read32(error_code_field); - kvm_requeue_exception_e(vcpu, vector, err); - } else - kvm_requeue_exception(vcpu, vector); + case INTR_TYPE_HARD_EXCEPTION: { + u32 error_code = 0; + + if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) + error_code = vmcs_read32(error_code_field); + + kvm_requeue_exception(vcpu, vector, + idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK, + error_code); break; + } case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); fallthrough; @@ -6995,7 +7247,7 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) IDT_VECTORING_ERROR_CODE); } -static void vmx_cancel_injection(struct kvm_vcpu *vcpu) +void vmx_cancel_injection(struct kvm_vcpu *vcpu) { __vmx_complete_interrupts(vcpu, vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), @@ -7028,13 +7280,13 @@ 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) { @@ -7071,7 +7323,7 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, return; if (flags & VMX_RUN_SAVE_SPEC_CTRL) - vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL); + vmx->spec_ctrl = native_rdmsrq(MSR_IA32_SPEC_CTRL); /* * If the guest/host SPEC_CTRL values differ, restore the host value. @@ -7082,37 +7334,61 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, */ if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) || vmx->spec_ctrl != hostval) - native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + native_wrmsrq(MSR_IA32_SPEC_CTRL, hostval); 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) { - switch (to_vmx(vcpu)->exit_reason.basic) { + /* + * 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) && + vmx_get_exit_reason(vcpu).basic != EXIT_REASON_PREEMPTION_TIMER) + return EXIT_FASTPATH_NONE; + + switch (vmx_get_exit_reason(vcpu).basic) { case EXIT_REASON_MSR_WRITE: - return handle_fastpath_set_msr_irqoff(vcpu); + return handle_fastpath_wrmsr(vcpu); + case EXIT_REASON_MSR_WRITE_IMM: + return handle_fastpath_wrmsr_imm(vcpu, vmx_get_exit_qual(vcpu), + vmx_get_msr_imm_reg(vcpu)); case EXIT_REASON_PREEMPTION_TIMER: - return handle_fastpath_preemption_timer(vcpu); + return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); + case EXIT_REASON_HLT: + return handle_fastpath_hlt(vcpu); + case EXIT_REASON_INVD: + return handle_fastpath_invd(vcpu); default: return EXIT_FASTPATH_NONE; } } +noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu) +{ + if ((u16)vmx_get_exit_reason(vcpu).basic != EXIT_REASON_EXCEPTION_NMI || + !is_nmi(vmx_get_intr_info(vcpu))) + return; + + 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); +} + 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 */ - 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(); + vmx_l1d_flush(vcpu); vmx_disable_fb_clear(vmx); @@ -7123,14 +7399,30 @@ 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->vt.exit_reason.full = 0xdead; + goto out; + } + + vmx->vt.exit_reason.full = vmcs_read32(VM_EXIT_REASON); + if (likely(!vmx_get_exit_reason(vcpu).failed_vmentry)) + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); + + vmx_handle_nmi(vcpu); + +out: guest_state_exit_irqoff(); } -static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7144,19 +7436,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * start emulation until we arrive back to a valid state. Synthesize a * consistency check VM-Exit due to invalid guest state and bail. */ - if (unlikely(vmx->emulation_required)) { + if (unlikely(vmx->vt.emulation_required)) { vmx->fail = 0; - vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; - vmx->exit_reason.failed_vmentry = 1; + vmx->vt.exit_reason.full = EXIT_REASON_INVALID_STATE; + vmx->vt.exit_reason.failed_vmentry = 1; kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); - vmx->exit_qualification = ENTRY_FAIL_DEFAULT; + vmx->vt.exit_qualification = ENTRY_FAIL_DEFAULT; kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); - vmx->exit_intr_info = 0; + vmx->vt.exit_intr_info = 0; 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; @@ -7175,6 +7467,12 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + if (run_flags & KVM_RUN_LOAD_GUEST_DR6) + set_debugreg(vcpu->arch.dr6, 6); + + if (run_flags & KVM_RUN_LOAD_DEBUGCTL) + vmx_reload_guest_debugctl(vcpu); + /* * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time @@ -7194,10 +7492,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->host_state.cr4 = cr4; } - /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - set_debugreg(vcpu->arch.dr6, 6); - /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug @@ -7206,8 +7500,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - kvm_load_guest_xsave_state(vcpu); - pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); @@ -7215,15 +7507,17 @@ 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; @@ -7231,8 +7525,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) } /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ - if (vmx->host_debugctlmsr) - update_debugctlmsr(vmx->host_debugctlmsr); + if (vcpu->arch.host_debugctl) + update_debugctlmsr(vcpu->arch.host_debugctl); #ifndef CONFIG_X86_64 /* @@ -7247,41 +7541,26 @@ 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); - if (is_guest_mode(vcpu)) { /* * Track VMLAUNCH/VMRESUME that have made past guest state * checking. */ if (vmx->nested.nested_run_pending && - !vmx->exit_reason.failed_vmentry) + !vmx_get_exit_reason(vcpu).failed_vmentry) ++vcpu->stat.nested_run; 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)) + if (unlikely(vmx_get_exit_reason(vcpu).failed_vmentry)) return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; @@ -7289,13 +7568,10 @@ 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) +void vmx_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7304,9 +7580,10 @@ static void vmx_vcpu_free(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); + free_page((unsigned long)vmx->ve_info); } -static int vmx_vcpu_create(struct kvm_vcpu *vcpu) +int vmx_vcpu_create(struct kvm_vcpu *vcpu) { struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; @@ -7315,7 +7592,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); vmx = to_vmx(vcpu); - INIT_LIST_HEAD(&vmx->pi_wakeup_list); + INIT_LIST_HEAD(&vmx->vt.pi_wakeup_list); err = -ENOMEM; @@ -7356,37 +7633,17 @@ 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; evmcs->hv_enlightenments_control.msr_bitmap = 1; } - /* The MSR bitmap starts with all ones */ - bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); - bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); - - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); -#ifdef CONFIG_X86_64 - vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); -#endif - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); - if (kvm_cstate_in_guest(vcpu->kvm)) { - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R); - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); - } - 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; } @@ -7397,9 +7654,23 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) goto free_vmcs; } + err = -ENOMEM; + if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) { + struct page *page; + + BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE); + + /* ve_info must be page aligned. */ + page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!page) + goto free_vmcs; + + vmx->ve_info = page_to_virt(page); + } + if (vmx_can_use_ipiv(vcpu)) WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id], - __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID); + __pa(&vmx->vt.pi_desc) | PID_TABLE_ENTRY_VALID); return 0; @@ -7415,10 +7686,10 @@ free_vpid: #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" #define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" -static int vmx_vm_init(struct kvm *kvm) +int vmx_vm_init(struct kvm *kvm) { if (!ple_gap) - kvm->arch.pause_in_guest = true; + kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE); if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) { switch (l1tf_mitigation) { @@ -7426,6 +7697,7 @@ static int vmx_vm_init(struct kvm *kvm) case L1TF_MITIGATION_FLUSH_NOWARN: /* 'I explicitly don't care' is set */ break; + case L1TF_MITIGATION_AUTO: case L1TF_MITIGATION_FLUSH: case L1TF_MITIGATION_FLUSH_NOSMT: case L1TF_MITIGATION_FULL: @@ -7443,70 +7715,37 @@ static int vmx_vm_init(struct kvm *kvm) break; } } + + if (enable_pml) + kvm->arch.cpu_dirty_log_size = PML_LOG_NR_ENTRIES; return 0; } -static int __init vmx_check_processor_compat(void) +static inline bool vmx_ignore_guest_pat(struct kvm *kvm) { - 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, 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; + /* + * Non-coherent DMA devices need the guest to flush CPU properly. + * In that case it is not possible to map all guest RAM as WB, so + * always trust guest PAT. + */ + return !kvm_arch_has_noncoherent_dma(kvm) && + kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT); } -static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u8 cache; - - /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in - * memory aliases with conflicting memory types and sometimes MCEs. - * We have to be careful as to what are honored and when. - * - * For MMIO, guest CD/MTRR are ignored. The EPT memory type is set to - * UC. The effective memory type is UC or WC depending on guest PAT. - * This was historically the source of MCEs and we want to be - * conservative. - * - * When there is no need to deal with noncoherent DMA (e.g., no VT-d - * or VT-d has snoop control), guest CD/MTRR/PAT are all ignored. The - * EPT memory type is set to WB. The effective memory type is forced - * WB. - * - * Otherwise, we trust guest. Guest CD/MTRR/PAT are all honored. The - * EPT memory type is used to emulate guest CD/MTRR. + /* + * Force UC for host MMIO regions, as allowing the guest to access MMIO + * with cacheable accesses will result in Machine Checks. */ - if (is_mmio) return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) + /* Force WB if ignoring guest PAT */ + if (vmx_ignore_guest_pat(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_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; - else - cache = MTRR_TYPE_UNCACHABLE; - - return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - } - - return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; + return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT); } static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl) @@ -7568,6 +7807,11 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU)); cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); + cr4_fixed1_update(X86_CR4_CET, ecx, feature_bit(SHSTK)); + cr4_fixed1_update(X86_CR4_CET, edx, feature_bit(IBT)); + + entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); + cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); #undef cr4_fixed1_update } @@ -7641,12 +7885,17 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); } -static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* 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 (!guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)) + guest_cpu_cap_clear(vcpu, X86_FEATURE_XSAVES); vmx_setup_uret_msrs(vmx); @@ -7654,7 +7903,7 @@ 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_cpu_cap_has(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; @@ -7663,36 +7912,31 @@ 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_cpu_cap_has(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); if (boot_cpu_has(X86_FEATURE_INTEL_PT) && - guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) + guest_cpu_cap_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); if (boot_cpu_has(X86_FEATURE_RTM)) { struct vmx_uret_msr *msr; msr = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (msr) { - bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + bool enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RTM); vmx_set_guest_uret_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); } } - if (kvm_cpu_cap_has(X86_FEATURE_XFD)) - vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)); - - set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_ENABLED; else vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_ENABLED; - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_LC_ENABLED; else @@ -7703,26 +7947,55 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } -static u64 vmx_get_perf_capabilities(void) +static __init u64 vmx_get_perf_capabilities(void) { - u64 perf_cap = PMU_CAP_FW_WRITES; - struct x86_pmu_lbr lbr; + u64 perf_cap = PERF_CAP_FW_WRITES; 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); + rdmsrq(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); + + if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { + x86_perf_get_lbr(&vmx_lbr_caps); - x86_perf_get_lbr(&lbr); - if (lbr.nr) - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + /* + * KVM requires LBR callstack support, as the overhead due to + * context switching LBRs without said support is too high. + * See intel_pmu_create_guest_lbr_event() for more info. + */ + if (!vmx_lbr_caps.has_callstack) + memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); + else if (vmx_lbr_caps.nr) + perf_cap |= host_perf_cap & PERF_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; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; @@ -7757,13 +8030,13 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); kvm_cpu_cap_clear(X86_FEATURE_SGX1); kvm_cpu_cap_clear(X86_FEATURE_SGX2); + kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA); } if (vmx_umip_emulated()) kvm_cpu_cap_set(X86_FEATURE_UMIP); /* CPUID 0xD.1 */ - kvm_caps.supported_xss = 0; if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); @@ -7775,73 +8048,100 @@ static __init void vmx_set_cpu_caps(void) if (cpu_has_vmx_waitpkg()) 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; + /* + * Disable CET if unrestricted_guest is unsupported as KVM doesn't + * enforce CET HW behaviors in emulator. On platforms with + * VMX_BASIC[bit56] == 0, inject #CP at VMX entry with error code + * fails, so disable CET in this case too. + */ + if (!cpu_has_load_cet_ctrl() || !enable_unrestricted_guest || + !cpu_has_vmx_basic_no_hw_errcode_cc()) { + kvm_cpu_cap_clear(X86_FEATURE_SHSTK); + kvm_cpu_cap_clear(X86_FEATURE_IBT); + } } -static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info) +static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + unsigned long *exit_qualification) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); unsigned short port; - bool intercept; int size; + bool imm; + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); if (info->intercept == x86_intercept_in || info->intercept == x86_intercept_ins) { port = info->src_val; size = info->dst_bytes; + imm = info->src_type == OP_IMM; } else { port = info->dst_val; size = info->src_bytes; + imm = info->dst_type == OP_IMM; } - /* - * If the 'use IO bitmaps' VM-execution control is 0, IO instruction - * VM-exits depend on the 'unconditional IO exiting' VM-execution - * control. - * - * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. - */ - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - intercept = nested_cpu_has(vmcs12, - CPU_BASED_UNCOND_IO_EXITING); - else - intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); - /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ - return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; + *exit_qualification = ((unsigned long)port << 16) | (size - 1); + + if (info->intercept == x86_intercept_ins || + info->intercept == x86_intercept_outs) + *exit_qualification |= BIT(4); + + if (info->rep_prefix) + *exit_qualification |= BIT(5); + + if (imm) + *exit_qualification |= BIT(6); + + return nested_vmx_check_io_bitmaps(vcpu, port, size); } -static int vmx_check_intercept(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info, - enum x86_intercept_stage stage, - struct x86_exception *exception) +int vmx_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned long exit_qualification = 0; + u32 vm_exit_reason; + u64 exit_insn_len; switch (info->intercept) { - /* - * RDPID causes #UD if disabled through secondary execution controls. - * Because it is marked as EmulateOnUD, we need to intercept it here. - * Note, RDPID is hidden behind ENABLE_RDTSCP. - */ case x86_intercept_rdpid: + /* + * RDPID causes #UD if not enabled through secondary execution + * controls (ENABLE_RDTSCP). Note, the implicit MSR access to + * TSC_AUX is NOT subject to interception, i.e. checking only + * the dedicated execution control is architecturally correct. + */ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; return X86EMUL_PROPAGATE_FAULT; } - break; + return X86EMUL_CONTINUE; case x86_intercept_in: case x86_intercept_ins: case x86_intercept_out: case x86_intercept_outs: - return vmx_check_intercept_io(vcpu, info); + if (!vmx_is_io_intercepted(vcpu, info, &exit_qualification)) + return X86EMUL_CONTINUE; + + vm_exit_reason = EXIT_REASON_IO_INSTRUCTION; + break; case x86_intercept_lgdt: case x86_intercept_lidt: @@ -7854,15 +8154,54 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) return X86EMUL_CONTINUE; - /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + if (info->intercept == x86_intercept_lldt || + info->intercept == x86_intercept_ltr || + info->intercept == x86_intercept_sldt || + info->intercept == x86_intercept_str) + vm_exit_reason = EXIT_REASON_LDTR_TR; + else + vm_exit_reason = EXIT_REASON_GDTR_IDTR; + /* + * FIXME: Decode the ModR/M to generate the correct exit + * qualification for memory operands. + */ + break; + + case x86_intercept_hlt: + if (!nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING)) + return X86EMUL_CONTINUE; + + vm_exit_reason = EXIT_REASON_HLT; + 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_has(vmcs12, CPU_BASED_PAUSE_EXITING)) + return X86EMUL_CONTINUE; + + vm_exit_reason = EXIT_REASON_PAUSE_INSTRUCTION; break; /* TODO: check more intercepts... */ default: - break; + return X86EMUL_UNHANDLEABLE; } - return X86EMUL_UNHANDLEABLE; + exit_insn_len = abs_diff((s64)info->next_rip, (s64)info->rip); + if (!exit_insn_len || exit_insn_len > X86_MAX_INSTRUCTION_LENGTH) + return X86EMUL_UNHANDLEABLE; + + __nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification, + exit_insn_len); + return X86EMUL_INTERCEPTED; } #ifdef CONFIG_X86_64 @@ -7884,8 +8223,8 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift, return 0; } -static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, - bool *expired) +int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; @@ -7924,39 +8263,36 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, return 0; } -static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) +void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif -static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) -{ - if (!kvm_pause_in_guest(vcpu->kvm)) - shrink_ple_window(vcpu); -} - 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); } -static void vmx_setup_mce(struct kvm_vcpu *vcpu) +void vmx_setup_mce(struct kvm_vcpu *vcpu) { if (vcpu->arch.mcg_cap & MCG_LMCE_P) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= @@ -7967,7 +8303,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) } #ifdef CONFIG_KVM_SMM -static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ if (to_vmx(vcpu)->nested.nested_run_pending) @@ -7975,7 +8311,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) +int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7996,7 +8332,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) return 0; } -static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) +int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -8017,18 +8353,18 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) return 0; } -static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) +void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } #endif -static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu); } -static void vmx_migrate_timers(struct kvm_vcpu *vcpu) +void vmx_migrate_timers(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer; @@ -8038,7 +8374,7 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu) } } -static void vmx_hardware_unsetup(void) +void vmx_hardware_unsetup(void) { kvm_set_posted_intr_wakeup_handler(NULL); @@ -8048,163 +8384,56 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) -{ - 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); - - return supported & BIT(reason); -} - -static void vmx_vm_destroy(struct kvm *kvm) +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)); } -static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = "kvm_intel", - - .hardware_unsetup = vmx_hardware_unsetup, - - .hardware_enable = vmx_hardware_enable, - .hardware_disable = vmx_hardware_disable, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_size = sizeof(struct kvm_vmx), - .vm_init = vmx_vm_init, - .vm_destroy = vmx_vm_destroy, - - .vcpu_precreate = vmx_vcpu_precreate, - .vcpu_create = vmx_vcpu_create, - .vcpu_free = vmx_vcpu_free, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_switch_to_guest = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .update_exception_bitmap = vmx_update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .set_cr0 = vmx_set_cr0, - .is_valid_cr4 = vmx_is_valid_cr4, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - .get_if_flag = vmx_get_if_flag, - - .flush_tlb_all = vmx_flush_tlb_all, - .flush_tlb_current = vmx_flush_tlb_current, - .flush_tlb_gva = vmx_flush_tlb_gva, - .flush_tlb_guest = vmx_flush_tlb_guest, - - .vcpu_pre_run = vmx_vcpu_pre_run, - .vcpu_run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = vmx_skip_emulated_instruction, - .update_emulated_instruction = vmx_update_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .inject_irq = vmx_inject_irq, - .inject_nmi = vmx_inject_nmi, - .inject_exception = vmx_inject_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = vmx_enable_nmi_window, - .enable_irq_window = vmx_enable_irq_window, - .update_cr8_intercept = vmx_update_cr8_intercept, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, - .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_interrupt = vmx_deliver_interrupt, - .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .get_l2_tsc_offset = vmx_get_l2_tsc_offset, - .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier, - .write_tsc_offset = vmx_write_tsc_offset, - .write_tsc_multiplier = vmx_write_tsc_multiplier, - - .load_mmu_pgd = vmx_load_mmu_pgd, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - - .request_immediate_exit = vmx_request_immediate_exit, - - .sched_in = vmx_sched_in, - - .cpu_dirty_log_size = PML_ENTITY_NUM, - .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, - - .nested_ops = &vmx_nested_ops, - - .pi_update_irte = vmx_pi_update_irte, - .pi_start_assignment = vmx_pi_start_assignment, +/* + * 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) +{ + int lam_bit; + unsigned long cr3_bits; -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif + if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG)) + return gva; - .setup_mce = vmx_setup_mce, + if (!is_64_bit_mode(vcpu)) + return gva; -#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 + /* + * 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; - .can_emulate_instruction = vmx_can_emulate_instruction, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, - .migrate_timers = vmx_migrate_timers, + /* 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; - .msr_filter_changed = vmx_msr_filter_changed, - .complete_emulated_msr = kvm_complete_insn_gp, + lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47; + } - .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, -}; + /* + * 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 unsigned int vmx_handle_intel_pt_intr(void) { @@ -8251,18 +8480,16 @@ static void __init vmx_setup_me_spte_mask(void) u64 me_mask = 0; /* - * kvm_get_shadow_phys_bits() returns shadow_phys_bits. Use - * the former to avoid exposing shadow_phys_bits. - * * On pre-MKTME system, boot_cpu_data.x86_phys_bits equals to - * shadow_phys_bits. On MKTME and/or TDX capable systems, + * kvm_host.maxphyaddr. On MKTME and/or TDX capable systems, * boot_cpu_data.x86_phys_bits holds the actual physical address - * w/o the KeyID bits, and shadow_phys_bits equals to MAXPHYADDR - * reported by CPUID. Those bits between are KeyID bits. + * w/o the KeyID bits, and kvm_host.maxphyaddr equals to + * MAXPHYADDR reported by CPUID. Those bits between are KeyID bits. */ - if (boot_cpu_data.x86_phys_bits != kvm_get_shadow_phys_bits()) + if (boot_cpu_data.x86_phys_bits != kvm_host.maxphyaddr) me_mask = rsvd_bits(boot_cpu_data.x86_phys_bits, - kvm_get_shadow_phys_bits() - 1); + kvm_host.maxphyaddr - 1); + /* * Unlike SME, host kernel doesn't support setting up any * MKTME KeyID on Intel platforms. No memory encryption @@ -8271,9 +8498,7 @@ static void __init vmx_setup_me_spte_mask(void) kvm_mmu_set_me_spte_mask(0, me_mask); } -static struct kvm_x86_init_ops vmx_init_ops __initdata; - -static __init int hardware_setup(void) +__init int vmx_hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; @@ -8284,19 +8509,13 @@ static __init int hardware_setup(void) vmx_setup_user_return_msrs(); - if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) - return -EIO; - - if (cpu_has_perf_global_ctrl_bug()) - pr_warn_once("kvm: 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"); + rdmsrq(MSR_IA32_BNDCFGS, host_bndcfgs); + WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } if (!cpu_has_vmx_mpx()) @@ -8315,10 +8534,18 @@ 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; } + /* + * Shadow paging doesn't have a (further) performance penalty + * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it + * by default + */ + if (!enable_ept) + allow_smaller_maxphyaddr = true; + if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; @@ -8342,17 +8569,16 @@ static __init int hardware_setup(void) * using the APIC_ACCESS_ADDR VMCS field. */ if (!flexpriority_enabled) - vmx_x86_ops.set_apic_access_page_addr = NULL; + vt_x86_ops.set_apic_access_page_addr = NULL; if (!cpu_has_vmx_tpr_shadow()) - vmx_x86_ops.update_cr8_intercept = NULL; + vt_x86_ops.update_cr8_intercept = NULL; #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - vmx_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; - vmx_x86_ops.tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; + vt_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + vt_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif @@ -8367,7 +8593,7 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; if (!enable_apicv) - vmx_x86_ops.sync_pir_to_irr = NULL; + vt_x86_ops.sync_pir_to_irr = NULL; if (!enable_apicv || !cpu_has_vmx_ipiv()) enable_ipiv = false; @@ -8385,6 +8611,8 @@ static __init int hardware_setup(void) if (enable_ept) kvm_mmu_set_ept_masks(enable_ept_ad_bits, cpu_has_vmx_ept_execute_only()); + else + vt_x86_ops.get_mt_mask = NULL; /* * Setup shadow_me_value/shadow_me_mask to include MKTME KeyID @@ -8392,7 +8620,7 @@ 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)); /* @@ -8402,9 +8630,6 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) enable_pml = 0; - if (!enable_pml) - vmx_x86_ops.cpu_dirty_log_size = 0; - if (!cpu_has_vmx_preemption_timer()) enable_preemption_timer = false; @@ -8412,7 +8637,7 @@ static __init int hardware_setup(void) u64 use_timer_freq = 5000ULL * 1000 * 1000; cpu_preemption_timer_multi = - vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmx_misc_preemption_timer_rate(vmcs_config.misc); if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8428,9 +8653,8 @@ static __init int hardware_setup(void) } if (!enable_preemption_timer) { - vmx_x86_ops.set_hv_timer = NULL; - vmx_x86_ops.cancel_hv_timer = NULL; - vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; + vt_x86_ops.set_hv_timer = NULL; + vt_x86_ops.cancel_hv_timer = NULL; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; @@ -8441,12 +8665,19 @@ static __init int hardware_setup(void) if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt()) pt_mode = PT_MODE_SYSTEM; if (pt_mode == PT_MODE_HOST_GUEST) - vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; + vt_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr; else - vmx_init_ops.handle_intel_pt_intr = NULL; + vt_init_ops.handle_intel_pt_intr = NULL; setup_default_sgx_lepubkeyhash(); + vmx_set_cpu_caps(); + + /* + * Configure nested capabilities after core CPU capabilities so that + * nested support can be conditional on base support, e.g. so that KVM + * can hide/show features based on kvm_cpu_cap_has(). + */ if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept); @@ -8455,132 +8686,77 @@ static __init int hardware_setup(void) return r; } - vmx_set_cpu_caps(); - r = alloc_kvm_area(); if (r && nested) nested_vmx_hardware_unsetup(); kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); - return r; -} - -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, + /* + * On Intel CPUs that lack self-snoop feature, letting the guest control + * memory types may result in unexpected behavior. So always ignore guest + * PAT on those CPUs and map VM as writeback, not allowing userspace to + * disable the quirk. + * + * On certain Intel CPUs (e.g. SPR, ICX), though self-snoop feature is + * supported, UC is slow enough to cause issues with some older guests (e.g. + * an old version of bochs driver uses ioremap() instead of ioremap_wc() to + * map the video RAM, causing wayland desktop to fail to get started + * correctly). To avoid breaking those older guests that rely on KVM to force + * memory type to WB, provide KVM_X86_QUIRK_IGNORE_GUEST_PAT to preserve the + * safer (for performance) default behavior. + * + * On top of this, non-coherent DMA devices need the guest to flush CPU + * caches properly. This also requires honoring guest PAT, and is forced + * independent of the quirk in vmx_ignore_guest_pat(). + */ + if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) + kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; - .runtime_ops = &vmx_x86_ops, - .pmu_ops = &intel_pmu_ops, -}; + kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT; -static void vmx_cleanup_l1d_flush(void) -{ - if (vmx_l1d_flush_pages) { - free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); - vmx_l1d_flush_pages = NULL; - } - /* Restore state so sysfs ignores VMX */ - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; + return r; } -static void vmx_exit(void) +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; - - vp_ap->nested_control.features.directhypercall = 0; - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } + allow_smaller_maxphyaddr = false; - static_branch_disable(&enable_evmcs); - } -#endif vmx_cleanup_l1d_flush(); - allow_smaller_maxphyaddr = false; + kvm_x86_vendor_exit(); } -module_exit(vmx_exit); -static int __init vmx_init(void) +int __init vmx_init(void) { int r, cpu; -#if IS_ENABLED(CONFIG_HYPERV) - /* - * 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. - */ - 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); - } + KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_vmx); - 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; - } -#endif + if (!kvm_is_vmx_supported()) + return -EOPNOTSUPP; - r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); - if (r) - return r; + /* + * Note, VMCS and eVMCS configuration only touch VMX knobs/variables, + * i.e. there's nothing to unwind if a later step fails. + */ + hv_init_evmcs(); /* - * Must be called after kvm_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. + * Parse the VMCS config and VMX capabilities before anything else, so + * that the information is available to all setup flows. */ - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); + if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) + return -EIO; + + r = kvm_x86_vendor_init(&vt_init_ops); + if (r) return r; - } - vmx_setup_fb_clear_ctrl(); + /* Must be called after common x86 init so enable_ept is setup. */ + r = vmx_setup_l1d_flush(); + if (r) + goto err_l1d_flush; for_each_possible_cpu(cpu) { INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); @@ -8588,20 +8764,11 @@ 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 vmx_check_vmcs12_offsets(); - /* - * Shadow paging doesn't have a (further) performance penalty - * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it - * by default - */ - if (!enable_ept) - allow_smaller_maxphyaddr = true; - return 0; + +err_l1d_flush: + kvm_x86_vendor_exit(); + return r; } -module_init(vmx_init); |