diff options
Diffstat (limited to 'kernel/arch/x86/kvm/vmx.c')
| -rw-r--r-- | kernel/arch/x86/kvm/vmx.c | 1445 |
1 files changed, 1034 insertions, 411 deletions
diff --git a/kernel/arch/x86/kvm/vmx.c b/kernel/arch/x86/kvm/vmx.c index 2d73807f0..0958fa2b7 100644 --- a/kernel/arch/x86/kvm/vmx.c +++ b/kernel/arch/x86/kvm/vmx.c @@ -28,26 +28,28 @@ #include <linux/sched.h> #include <linux/moduleparam.h> #include <linux/mod_devicetable.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> #include "kvm_cache_regs.h" #include "x86.h" +#include <asm/cpu.h> #include <asm/io.h> #include <asm/desc.h> #include <asm/vmx.h> #include <asm/virtext.h> #include <asm/mce.h> -#include <asm/i387.h> -#include <asm/xcr.h> +#include <asm/fpu/internal.h> #include <asm/perf_event.h> #include <asm/debugreg.h> #include <asm/kexec.h> #include <asm/apic.h> +#include <asm/irq_remapping.h> #include "trace.h" +#include "pmu.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) #define __ex_clear(x, reg) \ @@ -105,6 +107,8 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL + #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE) #define KVM_VM_CR0_ALWAYS_ON \ @@ -424,6 +428,9 @@ struct nested_vmx { /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ u64 vmcs01_debugctl; + u16 vpid02; + u16 last_vpid; + u32 nested_vmx_procbased_ctls_low; u32 nested_vmx_procbased_ctls_high; u32 nested_vmx_true_procbased_ctls_low; @@ -440,14 +447,33 @@ struct nested_vmx { u32 nested_vmx_misc_low; u32 nested_vmx_misc_high; u32 nested_vmx_ept_caps; + u32 nested_vmx_vpid_caps; }; #define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 + /* Posted-Interrupt Descriptor */ struct pi_desc { u32 pir[8]; /* Posted interrupt requested */ - u32 control; /* bit 0 of control is outstanding notification bit */ - u32 rsvd[7]; + union { + struct { + /* bit 256 - Outstanding Notification */ + u16 on : 1, + /* bit 257 - Suppress Notification */ + sn : 1, + /* bit 271:258 - Reserved */ + rsvd_1 : 14; + /* bit 279:272 - Notification Vector */ + u8 nv; + /* bit 287:280 - Reserved */ + u8 rsvd_2; + /* bit 319:288 - Notification Destination */ + u32 ndst; + }; + u64 control; + }; + u32 rsvd[6]; } __aligned(64); static bool pi_test_and_set_on(struct pi_desc *pi_desc) @@ -467,6 +493,30 @@ static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + return clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline void pi_set_sn(struct pi_desc *pi_desc) +{ + return set_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_on(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_sn(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; @@ -532,8 +582,6 @@ struct vcpu_vmx { s64 vnmi_blocked_time; u32 exit_reason; - bool rdtscp_enabled; - /* Posted interrupt descriptor */ struct pi_desc pi_desc; @@ -547,6 +595,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -563,6 +613,11 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } +static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) +{ + return &(to_vmx(vcpu)->pi_desc); +} + #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x) #define FIELD(number, name) [number] = VMCS12_OFFSET(name) #define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ @@ -786,7 +841,7 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr) { - struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT); + struct page *page = kvm_vcpu_gfn_to_page(vcpu, addr >> PAGE_SHIFT); if (is_error_page(page)) return NULL; @@ -809,7 +864,7 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static bool vmx_mpx_supported(void); static bool vmx_xsaves_supported(void); -static int vmx_vm_has_apicv(struct kvm *kvm); +static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -831,6 +886,13 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs); static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DEFINE_PER_CPU(struct desc_ptr, host_gdt); +/* + * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we + * can find which vCPU should be waken up. + */ +static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); + static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; static unsigned long *vmx_msr_bitmap_legacy; @@ -946,9 +1008,9 @@ static inline bool cpu_has_vmx_tpr_shadow(void) return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW; } -static inline bool vm_need_tpr_shadow(struct kvm *kvm) +static inline bool cpu_need_tpr_shadow(struct kvm_vcpu *vcpu) { - return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm)); + return cpu_has_vmx_tpr_shadow() && lapic_in_kernel(vcpu); } static inline bool cpu_has_secondary_exec_ctrls(void) @@ -983,7 +1045,8 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void) static inline bool cpu_has_vmx_posted_intr(void) { - return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; + return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && + vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; } static inline bool cpu_has_vmx_apicv(void) @@ -1062,9 +1125,9 @@ static inline bool cpu_has_vmx_ple(void) SECONDARY_EXEC_PAUSE_LOOP_EXITING; } -static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm) +static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) { - return flexpriority_enabled && irqchip_in_kernel(kvm); + return flexpriority_enabled && lapic_in_kernel(vcpu); } static inline bool cpu_has_vmx_vpid(void) @@ -1113,6 +1176,12 @@ static inline bool cpu_has_vmx_pml(void) return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML; } +static inline bool cpu_has_vmx_tsc_scaling(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_TSC_SCALING; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -1157,6 +1226,11 @@ static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); } +static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12) +{ + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID); +} + static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT); @@ -1264,7 +1338,7 @@ static void vmcs_load(struct vmcs *vmcs) vmcs, phys_addr); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* * This bitmap is used to indicate whether the vmclear * operation is enabled on all cpus. All disabled by @@ -1302,7 +1376,7 @@ static void crash_vmclear_local_loaded_vmcss(void) #else static inline void crash_enable_local_vmclear(int cpu) { } static inline void crash_disable_local_vmclear(int cpu) { } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) { @@ -1337,13 +1411,13 @@ static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) __loaded_vmcs_clear, loaded_vmcs, 1); } -static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx) +static inline void vpid_sync_vcpu_single(int vpid) { - if (vmx->vpid == 0) + if (vpid == 0) return; if (cpu_has_vmx_invvpid_single()) - __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); + __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0); } static inline void vpid_sync_vcpu_global(void) @@ -1352,10 +1426,10 @@ static inline void vpid_sync_vcpu_global(void) __invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0); } -static inline void vpid_sync_context(struct vcpu_vmx *vmx) +static inline void vpid_sync_context(int vpid) { if (cpu_has_vmx_invvpid_single()) - vpid_sync_vcpu_single(vmx); + vpid_sync_vcpu_single(vpid); else vpid_sync_vcpu_global(); } @@ -1567,7 +1641,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR); + (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -1674,6 +1748,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1711,26 +1792,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1741,16 +1827,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -1883,7 +1974,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) * If the FPU is not active (through the host task or * the guest vcpu), then restore the cr0.TS bit. */ - if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded) + if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded) stts(); load_gdt(this_cpu_ptr(&host_gdt)); } @@ -1895,6 +1986,52 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx) preempt_enable(); } +static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + do { + old.control = new.control = pi_desc->control; + + /* + * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there + * are two possible cases: + * 1. After running 'pre_block', context switch + * happened. For this case, 'sn' was set in + * vmx_vcpu_put(), so we need to clear it here. + * 2. After running 'pre_block', we were blocked, + * and woken up by some other guy. For this case, + * we don't need to do anything, 'pi_post_block' + * will do everything for us. However, we cannot + * check whether it is case #1 or case #2 here + * (maybe, not needed), so we also clear sn here, + * I think it is not a big deal. + */ + if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { + if (vcpu->cpu != cpu) { + dest = cpu_physical_id(cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + } + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } + + /* Allow posting non-urgent interrupts */ + new.sn = 0; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); +} /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -1943,12 +2080,37 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + vmx->loaded_vmcs->cpu = cpu; } + + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + + vmx_vcpu_pi_load(vcpu, cpu); +} + +static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + /* Set SN when the vCPU is preempted */ + if (vcpu->preempted) + pi_set_sn(pi_desc); } static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { + vmx_vcpu_pi_put(vcpu); + __vmx_load_host_state(to_vmx(vcpu)); if (!vmm_exclusive) { __loaded_vmcs_clear(to_vmx(vcpu)->loaded_vmcs); @@ -2170,8 +2332,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_nested; - else if (irqchip_in_kernel(vcpu->kvm) && - apic_x2apic_mode(vcpu->arch.apic)) { + else if (vcpu->arch.apic_base & X2APIC_ENABLE) { if (is_long_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_longmode_x2apic; else @@ -2208,7 +2369,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); index = __find_msr_index(vmx, MSR_TSC_AUX); - if (index >= 0 && vmx->rdtscp_enabled) + if (index >= 0 && guest_cpuid_has_rdtscp(&vmx->vcpu)) move_msr_up(vmx, index, save_nmsrs++); /* * MSR_STAR is only needed on long mode guests, and only @@ -2231,15 +2392,16 @@ static void setup_msrs(struct vcpu_vmx *vmx) /* * reads and returns guest's timestamp counter "register" - * guest_tsc = host_tsc + tsc_offset -- 21.3 + * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset + * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3 */ -static u64 guest_read_tsc(void) +static u64 guest_read_tsc(struct kvm_vcpu *vcpu) { u64 host_tsc, tsc_offset; - rdtscll(host_tsc); + host_tsc = rdtsc(); tsc_offset = vmcs_read64(TSC_OFFSET); - return host_tsc + tsc_offset; + return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset; } /* @@ -2256,22 +2418,6 @@ static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) return host_tsc + tsc_offset; } -/* - * Engage any workarounds for mis-matched TSC rates. Currently limited to - * software catchup for faster rates on slower CPUs. - */ -static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) -{ - if (!scale) - return; - - if (user_tsc_khz > tsc_khz) { - vcpu->arch.tsc_catchup = 1; - vcpu->arch.tsc_always_catchup = 1; - } else - WARN(1, "user requested TSC rate below hardware speed\n"); -} - static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu) { return vmcs_read64(TSC_OFFSET); @@ -2303,7 +2449,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) } } -static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) +static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { u64 offset = vmcs_read64(TSC_OFFSET); @@ -2316,11 +2462,6 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho offset + adjustment); } -static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) -{ - return target_tsc - native_read_tsc(); -} - static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0); @@ -2378,7 +2519,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; - if (vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (vmx_cpu_uses_apicv(&vmx->vcpu)) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_POSTED_INTR; @@ -2444,10 +2585,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | #endif CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | - CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING | - CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; + CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG | + CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING | + CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING | + CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the * hardware. For example, L1 can specify an MSR bitmap - and we @@ -2472,10 +2613,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_XSAVES; + SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_PCOMMIT; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ @@ -2494,6 +2637,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + if (enable_vpid) + vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | + VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; + else + vmx->nested.nested_vmx_vpid_caps = 0; + if (enable_unrestricted_guest) vmx->nested.nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_UNRESTRICTED_GUEST; @@ -2609,7 +2758,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) break; case MSR_IA32_VMX_EPT_VPID_CAP: /* Currently, no nested vpid support */ - *pdata = vmx->nested.nested_vmx_ept_caps; + *pdata = vmx->nested.nested_vmx_ept_caps | + ((u64)vmx->nested.nested_vmx_vpid_caps << 32); break; default: return 1; @@ -2623,76 +2773,69 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 data; struct shared_msr_entry *msr; - if (!pdata) { - printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); - return -EINVAL; - } - - switch (msr_index) { + switch (msr_info->index) { #ifdef CONFIG_X86_64 case MSR_FS_BASE: - data = vmcs_readl(GUEST_FS_BASE); + msr_info->data = vmcs_readl(GUEST_FS_BASE); break; case MSR_GS_BASE: - data = vmcs_readl(GUEST_GS_BASE); + msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: vmx_load_host_state(to_vmx(vcpu)); - data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base; break; #endif case MSR_EFER: - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSC: - data = guest_read_tsc(); + msr_info->data = guest_read_tsc(vcpu); break; case MSR_IA32_SYSENTER_CS: - data = vmcs_read32(GUEST_SYSENTER_CS); + msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; case MSR_IA32_SYSENTER_EIP: - data = vmcs_readl(GUEST_SYSENTER_EIP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); break; case MSR_IA32_SYSENTER_ESP: - data = vmcs_readl(GUEST_SYSENTER_ESP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: if (!vmx_mpx_supported()) return 1; - data = vmcs_read64(GUEST_BNDCFGS); + msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; case MSR_IA32_FEATURE_CONTROL: if (!nested_vmx_allowed(vcpu)) return 1; - data = to_vmx(vcpu)->nested.msr_ia32_feature_control; + msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) return 1; - return vmx_get_vmx_msr(vcpu, msr_index, pdata); + return vmx_get_vmx_msr(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_XSS: if (!vmx_xsaves_supported()) return 1; - data = vcpu->arch.ia32_xss; + msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: - if (!to_vmx(vcpu)->rdtscp_enabled) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Otherwise falls through */ default: - msr = find_msr_entry(to_vmx(vcpu), msr_index); + msr = find_msr_entry(to_vmx(vcpu), msr_info->index); if (msr) { - data = msr->data; + msr_info->data = msr->data; break; } - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); } - *pdata = data; return 0; } @@ -2787,7 +2930,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; case MSR_TSC_AUX: - if (!vmx->rdtscp_enabled) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -2882,6 +3025,8 @@ static int hardware_enable(void) return -EBUSY; INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); + spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); /* * Now we can enable the vmclear operation in kdump @@ -3023,7 +3168,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_ENABLE_PML; + SECONDARY_EXEC_ENABLE_PML | + SECONDARY_EXEC_PCOMMIT | + SECONDARY_EXEC_TSC_SCALING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -3158,7 +3305,7 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) struct page *pages; struct vmcs *vmcs; - pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order); + pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); @@ -3431,12 +3578,12 @@ static void enter_lmode(struct kvm_vcpu *vcpu) vmx_segment_cache_clear(to_vmx(vcpu)); guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); - if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { + if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { pr_debug_ratelimited("%s: tss fixup for long mode. \n", __func__); vmcs_write32(GUEST_TR_AR_BYTES, - (guest_tr_ar & ~AR_TYPE_MASK) - | AR_TYPE_BUSY_64_TSS); + (guest_tr_ar & ~VMX_AR_TYPE_MASK) + | VMX_AR_TYPE_BUSY_64_TSS); } vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } @@ -3449,9 +3596,9 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) { - vpid_sync_context(to_vmx(vcpu)); + vpid_sync_context(vpid); if (enable_ept) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; @@ -3459,6 +3606,11 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu) } } +static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +{ + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -3652,20 +3804,21 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; - /* - * SMEP/SMAP is disabled if CPU is in non-paging mode - * in hardware. However KVM always uses paging mode to - * emulate guest non-paging mode with TDP. - * To emulate this behavior, SMEP/SMAP needs to be - * manually disabled when guest switches to non-paging - * mode. - */ - hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } } + if (!enable_unrestricted_guest && !is_paging(vcpu)) + /* + * SMEP/SMAP is disabled if CPU is in non-paging mode in + * hardware. However KVM always uses paging mode without + * unrestricted guest. + * To emulate this behavior, SMEP/SMAP needs to be manually + * disabled when guest switches to non-paging mode. + */ + hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); + vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); return 0; @@ -3727,7 +3880,7 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu) return 0; else { int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return AR_DPL(ar); + return VMX_AR_DPL(ar); } } @@ -3855,11 +4008,11 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) if (cs.unusable) return false; - if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK)) + if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; - if (cs.type & AR_TYPE_WRITEABLE_MASK) { + if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; } else { @@ -3909,7 +4062,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) return false; if (!var.present) return false; - if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) { + if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { if (var.dpl < rpl) /* DPL < RPL */ return false; } @@ -4113,17 +4266,13 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { struct page *page; - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) goto out; - kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); if (r) goto out; @@ -4148,44 +4297,38 @@ static int alloc_identity_pagetable(struct kvm *kvm) { /* Called with kvm->slots_lock held. */ - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; BUG_ON(kvm->arch.ept_identity_pagetable_done); - kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = - kvm->arch.ept_identity_map_addr; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + kvm->arch.ept_identity_map_addr, PAGE_SIZE); return r; } -static void allocate_vpid(struct vcpu_vmx *vmx) +static int allocate_vpid(void) { int vpid; - vmx->vpid = 0; if (!enable_vpid) - return; + return 0; spin_lock(&vmx_vpid_lock); vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); - if (vpid < VMX_NR_VPIDS) { - vmx->vpid = vpid; + if (vpid < VMX_NR_VPIDS) __set_bit(vpid, vmx_vpid_bitmap); - } + else + vpid = 0; spin_unlock(&vmx_vpid_lock); + return vpid; } -static void free_vpid(struct vcpu_vmx *vmx) +static void free_vpid(int vpid) { - if (!enable_vpid) + if (!enable_vpid || vpid == 0) return; spin_lock(&vmx_vpid_lock); - if (vmx->vpid != 0) - __clear_bit(vmx->vpid, vmx_vpid_bitmap); + __clear_bit(vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); } @@ -4340,9 +4483,9 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr) msr, MSR_TYPE_W); } -static int vmx_vm_has_apicv(struct kvm *kvm) +static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu) { - return enable_apicv && irqchip_in_kernel(kvm); + return enable_apicv && lapic_in_kernel(vcpu); } static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4386,6 +4529,22 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) { #ifdef CONFIG_SMP if (vcpu->mode == IN_GUEST_MODE) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * Currently, we don't support urgent interrupt, + * all interrupts are recognized as non-urgent + * interrupt, so we cannot post interrupts when + * 'SN' is set. + * + * If the vcpu is in guest mode, it means it is + * running instead of being scheduled out and + * waiting in the run queue, and that's the only + * case when 'SN' is set currently, warning if + * 'SN' is set. + */ + WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), POSTED_INTR_VECTOR); return true; @@ -4522,7 +4681,7 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; - if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (!vmx_cpu_uses_apicv(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; return pin_based_exec_ctrl; } @@ -4534,7 +4693,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; - if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) { + if (!cpu_need_tpr_shadow(&vmx->vcpu)) { exec_control &= ~CPU_BASED_TPR_SHADOW; #ifdef CONFIG_X86_64 exec_control |= CPU_BASED_CR8_STORE_EXITING | @@ -4551,7 +4710,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; - if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) + if (!cpu_need_virtualize_apic_accesses(&vmx->vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; @@ -4565,7 +4724,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (!vmx_cpu_uses_apicv(&vmx->vcpu)) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; @@ -4575,8 +4734,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) a current VMCS12 */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - /* PML is enabled/disabled in creating/destorying vcpu */ - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; + + if (!enable_pml) + exec_control &= ~SECONDARY_EXEC_ENABLE_PML; + + /* Currently, we allow L1 guest to directly run pcommit instruction. */ + exec_control &= ~SECONDARY_EXEC_PCOMMIT; return exec_control; } @@ -4621,12 +4784,11 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) { + if (cpu_has_secondary_exec_ctrls()) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, vmx_secondary_exec_control(vmx)); - } - if (vmx_vm_has_apicv(vmx->vcpu.kvm)) { + if (vmx_cpu_uses_apicv(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); @@ -4667,16 +4829,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - u32 msr_low, msr_high; - u64 host_pat; - rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high); - host_pat = msr_low | ((u64) msr_high << 32); - /* Write the default value follow host pat */ - vmcs_write64(GUEST_IA32_PAT, host_pat); - /* Keep arch.pat sync with GUEST_IA32_PAT */ - vmx->vcpu.arch.pat = host_pat; - } + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { u32 index = vmx_msr_index[i]; @@ -4708,22 +4862,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) +static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct msr_data apic_base_msr; + u64 cr0; vmx->rmode.vm86_active = 0; vmx->soft_vnmi_blocked = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - kvm_set_cr8(&vmx->vcpu, 0); - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&vmx->vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); + kvm_set_cr8(vcpu, 0); + + if (!init_event) { + apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(vcpu)) + apic_base_msr.data |= MSR_IA32_APICBASE_BSP; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(vcpu, &apic_base_msr); + } vmx_segment_cache_clear(vmx); @@ -4747,9 +4906,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); + if (!init_event) { + vmcs_write32(GUEST_SYSENTER_CS, 0); + vmcs_writel(GUEST_SYSENTER_ESP, 0); + vmcs_writel(GUEST_SYSENTER_EIP, 0); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + } vmcs_writel(GUEST_RFLAGS, 0x02); kvm_rip_write(vcpu, 0xfff0); @@ -4764,37 +4926,35 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - /* Special registers */ - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - setup_msrs(vmx); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - if (cpu_has_vmx_tpr_shadow()) { + if (cpu_has_vmx_tpr_shadow() && !init_event) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (vm_need_tpr_shadow(vmx->vcpu.kvm)) + if (cpu_need_tpr_shadow(vcpu)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - __pa(vmx->vcpu.arch.apic->regs)); + __pa(vcpu->arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); } kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx_vm_has_apicv(vcpu->kvm)) + if (vmx_cpu_uses_apicv(vcpu)) memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ - vmx_set_cr4(&vmx->vcpu, 0); - vmx_set_efer(&vmx->vcpu, 0); - vmx_fpu_activate(&vmx->vcpu); - update_exception_bitmap(&vmx->vcpu); + cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + vmx_set_cr0(vcpu, cr0); /* enter rmode */ + vmx->vcpu.arch.cr0 = cr0; + vmx_set_cr4(vcpu, 0); + vmx_set_efer(vcpu, 0); + vmx_fpu_activate(vcpu); + update_exception_bitmap(vcpu); - vpid_sync_context(vmx); + vpid_sync_context(vmx->vpid); } /* @@ -4958,14 +5118,9 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { int ret; - struct kvm_userspace_memory_region tss_mem = { - .slot = TSS_PRIVATE_MEMSLOT, - .guest_phys_addr = addr, - .memory_size = PAGE_SIZE * 3, - .flags = 0, - }; - ret = kvm_set_memory_region(kvm, &tss_mem); + ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -5127,6 +5282,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) return handle_rmode_exception(vcpu, ex_no, error_code); switch (ex_no) { + case AC_VECTOR: + kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); + return 1; case DB_VECTOR: dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & @@ -5319,7 +5477,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) u8 cr8 = (u8)val; err = kvm_set_cr8(vcpu, cr8); kvm_complete_insn_gp(vcpu, err); - if (irqchip_in_kernel(vcpu->kvm)) + if (lapic_in_kernel(vcpu)) return 1; if (cr8_prev <= cr8) return 1; @@ -5475,19 +5633,21 @@ static int handle_cpuid(struct kvm_vcpu *vcpu) static int handle_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; - u64 data; + struct msr_data msr_info; - if (vmx_get_msr(vcpu, ecx, &data)) { + msr_info.index = ecx; + msr_info.host_initiated = false; + if (vmx_get_msr(vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(vcpu, 0); return 1; } - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(ecx, msr_info.data); /* FIXME: handling of bits 32:63 of rax, rdx */ - vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u; - vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u; + vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u; + vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u; skip_emulated_instruction(vcpu); return 1; } @@ -5531,17 +5691,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); ++vcpu->stat.irq_window_exits; - - /* - * If the user space waits to inject interrupts, exit as soon as - * possible - */ - if (!irqchip_in_kernel(vcpu->kvm) && - vcpu->run->request_interrupt_window && - !kvm_cpu_has_interrupt(vcpu)) { - vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - return 0; - } return 1; } @@ -5710,9 +5859,6 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) return 0; } - /* clear all local breakpoint enable flags */ - vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155); - /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? @@ -5769,82 +5915,19 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } -static u64 ept_rsvd_mask(u64 spte, int level) -{ - int i; - u64 mask = 0; - - for (i = 51; i > boot_cpu_data.x86_phys_bits; i--) - mask |= (1ULL << i); - - if (level == 4) - /* bits 7:3 reserved */ - mask |= 0xf8; - else if (spte & (1ULL << 7)) - /* - * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively, - * level == 1 if the hypervisor is using the ignored bit 7. - */ - mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE; - else if (level > 1) - /* bits 6:3 reserved */ - mask |= 0x78; - - return mask; -} - -static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, - int level) -{ - printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level); - - /* 010b (write-only) */ - WARN_ON((spte & 0x7) == 0x2); - - /* 110b (write/execute) */ - WARN_ON((spte & 0x7) == 0x6); - - /* 100b (execute-only) and value not supported by logical processor */ - if (!cpu_has_vmx_ept_execute_only()) - WARN_ON((spte & 0x7) == 0x4); - - /* not 000b */ - if ((spte & 0x7)) { - u64 rsvd_bits = spte & ept_rsvd_mask(spte, level); - - if (rsvd_bits != 0) { - printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n", - __func__, rsvd_bits); - WARN_ON(1); - } - - /* bits 5:3 are _not_ reserved for large page or leaf page */ - if ((rsvd_bits & 0x38) == 0) { - u64 ept_mem_type = (spte & 0x38) >> 3; - - if (ept_mem_type == 2 || ept_mem_type == 3 || - ept_mem_type == 7) { - printk(KERN_ERR "%s: ept_mem_type=0x%llx\n", - __func__, ept_mem_type); - WARN_ON(1); - } - } - } -} - static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { - u64 sptes[4]; - int nr_sptes, i, ret; + int ret; gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { skip_emulated_instruction(vcpu); + trace_kvm_fast_mmio(gpa); return 1; } - ret = handle_mmio_page_fault_common(vcpu, gpa, true); + ret = handle_mmio_page_fault(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; @@ -5856,13 +5939,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) return 1; /* It is the real ept misconfig */ - printk(KERN_ERR "EPT: Misconfiguration.\n"); - printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa); - - nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes); - - for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) - ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); + WARN_ON(1); vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; @@ -6004,6 +6081,25 @@ static void update_ple_window_actual_max(void) ple_window_grow, INT_MIN); } +/* + * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. + */ +static void wakeup_handler(void) +{ + struct kvm_vcpu *vcpu; + int cpu = smp_processor_id(); + + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu), + blocked_vcpu_list) { + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (pi_test_on(pi_desc) == 1) + kvm_vcpu_kick(vcpu); + } + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); +} + static __init int hardware_setup(void) { int r = -ENOMEM, i, msr; @@ -6122,6 +6218,12 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; + if (cpu_has_vmx_tsc_scaling()) { + kvm_has_tsc_control = true; + kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; + kvm_tsc_scaling_ratio_frac_bits = 48; + } + if (enable_apicv) kvm_x86_ops->update_cr8_intercept = NULL; else { @@ -6144,6 +6246,8 @@ static __init int hardware_setup(void) memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ + if (enable_apicv) { for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); @@ -6188,6 +6292,8 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + kvm_set_posted_intr_wakeup_handler(wakeup_handler); + return alloc_kvm_area(); out8: @@ -6256,6 +6362,11 @@ static int handle_mwait(struct kvm_vcpu *vcpu) return handle_nop(vcpu); } +static int handle_monitor_trap(struct kvm_vcpu *vcpu) +{ + return 1; +} + static int handle_monitor(struct kvm_vcpu *vcpu) { printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); @@ -6418,8 +6529,12 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) */ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, - u32 vmx_instruction_info, gva_t *ret) + u32 vmx_instruction_info, bool wr, gva_t *ret) { + gva_t off; + bool exn; + struct kvm_segment s; + /* * According to Vol. 3B, "Information for VM Exits Due to Instruction * Execution", on an exit, vmx_instruction_info holds most of the @@ -6444,22 +6559,63 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Addr = segment_base + offset */ /* offset = base + [index * scale] + displacement */ - *ret = vmx_get_segment_base(vcpu, seg_reg); + off = exit_qualification; /* holds the displacement */ if (base_is_valid) - *ret += kvm_register_read(vcpu, base_reg); + off += kvm_register_read(vcpu, base_reg); if (index_is_valid) - *ret += kvm_register_read(vcpu, index_reg)<<scaling; - *ret += exit_qualification; /* holds the displacement */ + off += kvm_register_read(vcpu, index_reg)<<scaling; + vmx_get_segment(vcpu, &s, seg_reg); + *ret = s.base + off; if (addr_size == 1) /* 32 bit */ *ret &= 0xffffffff; - /* - * TODO: throw #GP (and return 1) in various cases that the VM* - * instructions require it - e.g., offset beyond segment limit, - * unusable or unreadable/unwritable segment, non-canonical 64-bit - * address, and so on. Currently these are not checked. - */ + /* Checks for #GP/#SS exceptions. */ + exn = false; + if (is_protmode(vcpu)) { + /* Protected mode: apply checks for segment validity in the + * following order: + * - segment type check (#GP(0) may be thrown) + * - usability check (#GP(0)/#SS(0)) + * - limit check (#GP(0)/#SS(0)) + */ + if (wr) + /* #GP(0) if the destination operand is located in a + * read-only data segment or any code segment. + */ + exn = ((s.type & 0xa) == 0 || (s.type & 8)); + else + /* #GP(0) if the source operand is located in an + * execute-only code segment + */ + exn = ((s.type & 0xa) == 8); + } + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is an only check for long mode. + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { + /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. + */ + exn = (s.unusable != 0); + /* Protected mode: #GP(0)/#SS(0) if the memory + * operand is outside the segment limit. + */ + exn = exn || (off + sizeof(u64) > s.limit); + } + if (exn) { + kvm_queue_exception_e(vcpu, + seg_reg == VCPU_SREG_SS ? + SS_VECTOR : GP_VECTOR, + 0); + return 1; + } + return 0; } @@ -6481,7 +6637,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, int maxphyaddr = cpuid_maxphyaddr(vcpu); if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) + vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, @@ -6669,7 +6825,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) { - u32 exec_control; if (vmx->nested.current_vmptr == -1ull) return; @@ -6682,9 +6837,8 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) they were modified */ copy_shadow_to_vmcs12(vmx); vmx->nested.sync_shadow_vmcs = false; - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, -1ull); } vmx->nested.posted_intr_nv = -1; @@ -6704,6 +6858,7 @@ static void free_nested(struct vcpu_vmx *vmx) return; vmx->nested.vmxon = false; + free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); @@ -7009,7 +7164,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) field_value); } else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, true, &gva)) return 1; /* _system ok, as nested_vmx_check_permission verified cpl=0 */ kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva, @@ -7046,7 +7201,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) (((vmx_instruction_info) >> 3) & 0xf)); else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) { @@ -7080,7 +7235,6 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); gpa_t vmptr; - u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -7112,9 +7266,8 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; if (enable_shadow_vmcs) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_SHADOW_VMCS; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, __pa(vmx->nested.current_shadow_vmcs)); vmx->nested.sync_shadow_vmcs = true; @@ -7138,7 +7291,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return 1; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &vmcs_gva)) + vmx_instruction_info, true, &vmcs_gva)) return 1; /* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */ if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva, @@ -7194,7 +7347,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, sizeof(operand), &e)) { @@ -7220,7 +7373,58 @@ static int handle_invept(struct kvm_vcpu *vcpu) static int handle_invvpid(struct kvm_vcpu *vcpu) { - kvm_queue_exception(vcpu, UD_VECTOR); + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 vmx_instruction_info; + unsigned long type, types; + gva_t gva; + struct x86_exception e; + int vpid; + + if (!(vmx->nested.nested_vmx_secondary_ctls_high & + SECONDARY_EXEC_ENABLE_VPID) || + !(vmx->nested.nested_vmx_vpid_caps & VMX_VPID_INVVPID_BIT)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); + + types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7; + + if (!(types & (1UL << type))) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return 1; + } + + /* according to the intel vmx instruction reference, the memory + * operand is read even if it isn't needed (e.g., for type==global) + */ + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmx_instruction_info, false, &gva)) + return 1; + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid, + sizeof(u32), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + switch (type) { + case VMX_VPID_EXTENT_ALL_CONTEXT: + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + nested_vmx_succeed(vcpu); + break; + default: + /* Trap single context invalidation invvpid calls */ + BUG_ON(1); + break; + } + + skip_emulated_instruction(vcpu); return 1; } @@ -7249,6 +7453,13 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } +static int handle_pcommit(struct kvm_vcpu *vcpu) +{ + /* we never catch pcommit instruct for L1 guest. */ + WARN_ON(1); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -7292,12 +7503,14 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, [EXIT_REASON_INVEPT] = handle_invept, [EXIT_REASON_INVVPID] = handle_invvpid, [EXIT_REASON_XSAVES] = handle_xsaves, [EXIT_REASON_XRSTORS] = handle_xrstors, [EXIT_REASON_PML_FULL] = handle_pml_full, + [EXIT_REASON_PCOMMIT] = handle_pcommit, }; static const int kvm_vmx_max_exit_handlers = @@ -7333,7 +7546,7 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) - if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1)) return true; if (b & (1 << (port & 7))) return true; @@ -7377,7 +7590,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, /* Then read the msr_index'th bit from this bitmap: */ if (msr_index < 1024*8) { unsigned char b; - if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1)) return true; return 1 & (b >> (msr_index & 7)); } else @@ -7552,6 +7765,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); + case EXIT_REASON_MONITOR_TRAP_FLAG: + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: @@ -7597,6 +7812,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * the XSS exit bitmap in vmcs12. */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); + case EXIT_REASON_PCOMMIT: + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT); default: return true; } @@ -7608,10 +7825,9 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = vmcs_read32(VM_EXIT_INTR_INFO); } -static int vmx_enable_pml(struct vcpu_vmx *vmx) +static int vmx_create_pml_buffer(struct vcpu_vmx *vmx) { struct page *pml_pg; - u32 exec_control; pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!pml_pg) @@ -7622,29 +7838,20 @@ static int vmx_enable_pml(struct vcpu_vmx *vmx) vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_ENABLE_PML; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); - return 0; } -static void vmx_disable_pml(struct vcpu_vmx *vmx) +static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { - u32 exec_control; - - ASSERT(vmx->pml_pg); - __free_page(vmx->pml_pg); - vmx->pml_pg = NULL; - - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + if (vmx->pml_pg) { + __free_page(vmx->pml_pg); + vmx->pml_pg = NULL; + } } -static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) +static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vmx->vcpu.kvm; + struct vcpu_vmx *vmx = to_vmx(vcpu); u64 *pml_buf; u16 pml_idx; @@ -7666,7 +7873,7 @@ static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) gpa = pml_buf[pml_idx]; WARN_ON(gpa & (PAGE_SIZE - 1)); - mark_page_dirty(kvm, gpa >> PAGE_SHIFT); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ @@ -7691,6 +7898,161 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) kvm_vcpu_kick(vcpu); } +static void vmx_dump_sel(char *name, uint32_t sel) +{ + pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(sel), + vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), + vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), + vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); +} + +static void vmx_dump_dtsel(char *name, uint32_t limit) +{ + pr_err("%s limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(limit), + vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); +} + +static void dump_vmcs(void) +{ + u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); + u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); + u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); + u32 secondary_exec_control = 0; + unsigned long cr4 = vmcs_readl(GUEST_CR4); + u64 efer = vmcs_readl(GUEST_IA32_EFER); + int i, n; + + if (cpu_has_secondary_exec_ctrls()) + secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + pr_err("*** Guest State ***\n"); + pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), + vmcs_readl(CR0_GUEST_HOST_MASK)); + pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); + pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && + (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) + { + pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1)); + pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3)); + } + pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", + vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); + pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", + vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(GUEST_SYSENTER_ESP), + vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); + vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); + vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); + vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); + vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); + vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); + vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); + vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); + vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); + vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); + vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); + if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || + (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) + pr_err("EFER = 0x%016llx PAT = 0x%016lx\n", + efer, vmcs_readl(GUEST_IA32_PAT)); + pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n", + vmcs_readl(GUEST_IA32_DEBUGCTL), + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); + if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL)); + if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) + pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS)); + pr_err("Interruptibility = %08x ActivityState = %08x\n", + vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), + vmcs_read32(GUEST_ACTIVITY_STATE)); + if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) + pr_err("InterruptStatus = %04x\n", + vmcs_read16(GUEST_INTR_STATUS)); + + pr_err("*** Host State ***\n"); + pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", + vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); + pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", + vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), + vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), + vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), + vmcs_read16(HOST_TR_SELECTOR)); + pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", + vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), + vmcs_readl(HOST_TR_BASE)); + pr_err("GDTBase=%016lx IDTBase=%016lx\n", + vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); + pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", + vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), + vmcs_readl(HOST_CR4)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(HOST_IA32_SYSENTER_ESP), + vmcs_read32(HOST_IA32_SYSENTER_CS), + vmcs_readl(HOST_IA32_SYSENTER_EIP)); + if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) + pr_err("EFER = 0x%016lx PAT = 0x%016lx\n", + vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT)); + if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL)); + + pr_err("*** Control State ***\n"); + pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", + pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control); + pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl); + pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", + vmcs_read32(EXCEPTION_BITMAP), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); + pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), + vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), + vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); + pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_EXIT_INTR_INFO), + vmcs_read32(VM_EXIT_INTR_ERROR_CODE), + vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); + pr_err(" reason=%08x qualification=%016lx\n", + vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); + pr_err("IDTVectoring: info=%08x errcode=%08x\n", + vmcs_read32(IDT_VECTORING_INFO_FIELD), + vmcs_read32(IDT_VECTORING_ERROR_CODE)); + pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET)); + if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) + pr_err("TSC Multiplier = 0x%016lx\n", + vmcs_readl(TSC_MULTIPLIER)); + if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) + pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); + if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) + pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) + pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER)); + n = vmcs_read32(CR3_TARGET_COUNT); + for (i = 0; i + 1 < n; i += 4) + pr_err("CR3 target%u=%016lx target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2), + i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2)); + if (i < n) + pr_err("CR3 target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2)); + if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) + pr_err("PLE Gap=%08x Window=%08x\n", + vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); + if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) + pr_err("Virtual processor ID = 0x%04x\n", + vmcs_read16(VIRTUAL_PROCESSOR_ID)); +} + /* * The guest has exited. See if we can fix it or if we need userspace * assistance. @@ -7701,6 +8063,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -7709,7 +8073,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) * flushed already. */ if (enable_pml) - vmx_flush_pml_buffer(vmx); + vmx_flush_pml_buffer(vcpu); /* If guest state is invalid, start emulating */ if (vmx->emulation_required) @@ -7723,6 +8087,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { + dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason; @@ -7810,10 +8175,10 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) * apicv */ if (!cpu_has_vmx_virtualize_x2apic_mode() || - !vmx_vm_has_apicv(vcpu->kvm)) + !vmx_cpu_uses_apicv(vcpu)) return; - if (!vm_need_tpr_shadow(vcpu->kvm)) + if (!cpu_need_tpr_shadow(vcpu)) return; sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); @@ -7915,9 +8280,10 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) } } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu) { - if (!vmx_vm_has_apicv(vcpu->kvm)) + u64 *eoi_exit_bitmap = vcpu->arch.eoi_exit_bitmap; + if (!vmx_cpu_uses_apicv(vcpu)) return; vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); @@ -7996,6 +8362,11 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) local_irq_enable(); } +static bool vmx_has_high_real_mode_segbase(void) +{ + return enable_unrestricted_guest || emulate_invalid_guest_state; +} + static bool vmx_mpx_supported(void) { return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) && @@ -8320,7 +8691,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); /* * the KVM_REQ_EVENT optimization bit is only on for one entry, and if @@ -8358,8 +8728,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); if (enable_pml) - vmx_disable_pml(vmx); - free_vpid(vmx); + vmx_destroy_pml_buffer(vmx); + free_vpid(vmx->vpid); leave_guest_mode(vcpu); vmx_load_vmcs01(vcpu); free_nested(vmx); @@ -8378,7 +8748,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); - allocate_vpid(vmx); + vmx->vpid = allocate_vpid(); err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) @@ -8411,7 +8781,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) put_cpu(); if (err) goto free_vmcs; - if (vm_need_virtualize_apic_accesses(kvm)) { + if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { err = alloc_apic_access_page(kvm); if (err) goto free_vmcs; @@ -8426,8 +8796,10 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) + if (nested) { nested_vmx_setup_ctls_msrs(vmx); + vmx->nested.vpid02 = allocate_vpid(); + } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -8440,7 +8812,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) * for the guest, etc. */ if (enable_pml) { - err = vmx_enable_pml(vmx); + err = vmx_create_pml_buffer(vmx); if (err) goto free_vmcs; } @@ -8448,13 +8820,14 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: + free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); free_vcpu: - free_vpid(vmx); + free_vpid(vmx->vpid); kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); } @@ -8480,7 +8853,8 @@ static int get_ept_level(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u64 ret; + u8 cache; + u64 ipat = 0; /* For VT-d and EPT combination * 1. MMIO: always map as UC @@ -8493,16 +8867,30 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (is_mmio) - ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - else if (kvm_arch_has_noncoherent_dma(vcpu->kvm)) - ret = kvm_get_guest_memory_type(vcpu, gfn) << - VMX_EPT_MT_EPTE_SHIFT; - else - ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) - | VMX_EPT_IPAT_BIT; + if (is_mmio) { + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } - return ret; + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + ipat = VMX_EPT_IPAT_BIT; + cache = MTRR_TYPE_WRBACK; + goto exit; + } + + if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + ipat = VMX_EPT_IPAT_BIT; + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cache = MTRR_TYPE_WRBACK; + else + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } + + cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + +exit: + return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; } static int vmx_get_lpage_level(void) @@ -8514,49 +8902,68 @@ static int vmx_get_lpage_level(void) return PT_PDPE_LEVEL; } +static void vmcs_set_secondary_exec_control(u32 new_ctl) +{ + /* + * These bits in the secondary execution controls field + * are dynamic, the others are mostly based on the hypervisor + * architecture and the guest's CPUID. Do not touch the + * dynamic bits. + */ + u32 mask = + SECONDARY_EXEC_SHADOW_VMCS | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + + u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + (new_ctl & ~mask) | (cur_ctl & mask)); +} + static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exec_control; + u32 secondary_exec_ctl = vmx_secondary_exec_control(vmx); - vmx->rdtscp_enabled = false; if (vmx_rdtscp_supported()) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - if (exec_control & SECONDARY_EXEC_RDTSCP) { - best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (best && (best->edx & bit(X86_FEATURE_RDTSCP))) - vmx->rdtscp_enabled = true; - else { - exec_control &= ~SECONDARY_EXEC_RDTSCP; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } + bool rdtscp_enabled = guest_cpuid_has_rdtscp(vcpu); + if (!rdtscp_enabled) + secondary_exec_ctl &= ~SECONDARY_EXEC_RDTSCP; + + if (nested) { + if (rdtscp_enabled) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_RDTSCP; + else + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_RDTSCP; } - if (nested && !vmx->rdtscp_enabled) - vmx->nested.nested_vmx_secondary_ctls_high &= - ~SECONDARY_EXEC_RDTSCP; } /* Exposing INVPCID only when PCID is exposed */ best = kvm_find_cpuid_entry(vcpu, 0x7, 0); if (vmx_invpcid_supported() && - best && (best->ebx & bit(X86_FEATURE_INVPCID)) && - guest_cpuid_has_pcid(vcpu)) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } else { - if (cpu_has_secondary_exec_ctrls()) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } + (!best || !(best->ebx & bit(X86_FEATURE_INVPCID)) || + !guest_cpuid_has_pcid(vcpu))) { + secondary_exec_ctl &= ~SECONDARY_EXEC_ENABLE_INVPCID; + if (best) best->ebx &= ~bit(X86_FEATURE_INVPCID); } + + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); + + if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { + if (guest_cpuid_has_pcommit(vcpu)) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_PCOMMIT; + else + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_PCOMMIT; + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -8924,7 +9331,7 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { /* x2APIC MSR accesses are not allowed */ - if (apic_x2apic_mode(vcpu->arch.apic) && e->index >> 8 == 0x8) + if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8) return -EINVAL; if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */ e->index == MSR_IA32_UCODE_REV) @@ -8966,8 +9373,8 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) msr.host_initiated = false; for (i = 0; i < count; i++) { - if (kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e), - &e, sizeof(e))) { + if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), + &e, sizeof(e))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -8999,9 +9406,10 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) struct vmx_msr_entry e; for (i = 0; i < count; i++) { - if (kvm_read_guest(vcpu->kvm, - gpa + i * sizeof(e), - &e, 2 * sizeof(u32))) { + struct msr_data msr_info; + if (kvm_vcpu_read_guest(vcpu, + gpa + i * sizeof(e), + &e, 2 * sizeof(u32))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -9013,19 +9421,21 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); return -EINVAL; } - if (kvm_get_msr(vcpu, e.index, &e.value)) { + msr_info.host_initiated = false; + msr_info.index = e.index; + if (kvm_get_msr(vcpu, &msr_info)) { pr_warn_ratelimited( "%s cannot read MSR (%u, 0x%x)\n", __func__, i, e.index); return -EINVAL; } - if (kvm_write_guest(vcpu->kvm, - gpa + i * sizeof(e) + - offsetof(struct vmx_msr_entry, value), - &e.value, sizeof(e.value))) { + if (kvm_vcpu_write_guest(vcpu, + gpa + i * sizeof(e) + + offsetof(struct vmx_msr_entry, value), + &msr_info.data, sizeof(msr_info.data))) { pr_warn_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", - __func__, i, e.index, e.value); + __func__, i, e.index, msr_info.data); return -EINVAL; } } @@ -9161,13 +9571,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (cpu_has_secondary_exec_ctrls()) { exec_control = vmx_secondary_exec_control(vmx); - if (!vmx->rdtscp_enabled) - exec_control &= ~SECONDARY_EXEC_RDTSCP; + /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_APIC_REGISTER_VIRT); + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_PCOMMIT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -9186,7 +9596,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->nested.apic_access_page)); } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && - (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))) { + cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; kvm_vcpu_reload_apic_access_page(vcpu); @@ -9296,12 +9706,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (enable_vpid) { /* - * Trivially support vpid by letting L2s share their parent - * L1's vpid. TODO: move to a more elaborate solution, giving - * each L2 its own vpid and exposing the vpid feature to L1. + * There is no direct mapping between vpid02 and vpid12, the + * vpid02 is per-vCPU for L0 and reused while the value of + * vpid12 is changed w/ one invvpid during nested vmentry. + * The vpid12 is allocated by L1 for L2, so it will not + * influence global bitmap(for vpid01 and vpid02 allocation) + * even if spawn a lot of nested vCPUs. */ - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx_flush_tlb(vcpu); + if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) { + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); + if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + vmx->nested.last_vpid = vmcs12->virtual_processor_id; + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + } + } else { + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + vmx_flush_tlb(vcpu); + } + } if (nested_cpu_has_ept(vmcs12)) { @@ -10141,6 +10563,201 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +/* + * This routine does the following things for vCPU which is going + * to be blocked if VT-d PI is enabled. + * - Store the vCPU to the wakeup list, so when interrupts happen + * we can find the right vCPU to wake up. + * - Change the Posted-interrupt descriptor as below: + * 'NDST' <-- vcpu->pre_pcpu + * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR + * - If 'ON' is set during this process, which means at least one + * interrupt is posted for this vCPU, we cannot block it, in + * this case, return 1, otherwise, return 0. + * + */ +static int vmx_pre_block(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + unsigned int dest; + struct pi_desc old, new; + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + vcpu->pre_pcpu = vcpu->cpu; + spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + + do { + old.control = new.control = pi_desc->control; + + /* + * We should not block the vCPU if + * an interrupt is posted for it. + */ + if (pi_test_on(pi_desc) == 1) { + spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock_irqrestore( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + vcpu->pre_pcpu = -1; + + return 1; + } + + WARN((pi_desc->sn == 1), + "Warning: SN field of posted-interrupts " + "is set before blocking\n"); + + /* + * Since vCPU can be preempted during this process, + * vcpu->cpu could be different with pre_pcpu, we + * need to set pre_pcpu as the destination of wakeup + * notification event, then we can find the right vCPU + * to wakeup in wakeup handler if interrupts happen + * when the vCPU is in blocked state. + */ + dest = cpu_physical_id(vcpu->pre_pcpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'wakeup vector' */ + new.nv = POSTED_INTR_WAKEUP_VECTOR; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); + + return 0; +} + +static void vmx_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + unsigned long flags; + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + do { + old.control = new.control = pi_desc->control; + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* Allow posting non-urgent interrupts */ + new.sn = 0; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); + + if(vcpu->pre_pcpu != -1) { + spin_lock_irqsave( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock_irqrestore( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + vcpu->pre_pcpu = -1; + } +} + +/* + * vmx_update_pi_irte - set IRTE for Posted-Interrupts + * + * @kvm: kvm + * @host_irq: host irq of the interrupt + * @guest_irq: gsi of the interrupt + * @set: set or unset PI + * returns 0 on success, < 0 on failure + */ +static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + struct kvm_kernel_irq_routing_entry *e; + struct kvm_irq_routing_table *irq_rt; + struct kvm_lapic_irq irq; + struct kvm_vcpu *vcpu; + struct vcpu_data vcpu_info; + int idx, ret = -EINVAL; + + if (!kvm_arch_has_assigned_device(kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + BUG_ON(guest_irq >= irq_rt->nr_rt_entries); + + hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { + if (e->type != KVM_IRQ_ROUTING_MSI) + continue; + /* + * VT-d PI cannot support posting multicast/broadcast + * interrupts to a vCPU, we still use interrupt remapping + * for these kind of interrupts. + * + * For lowest-priority interrupts, we only support + * those with single CPU as the destination, e.g. user + * configures the interrupts via /proc/irq or uses + * irqbalance to make the interrupts single-CPU. + * + * We will support full lowest-priority interrupt later. + */ + + kvm_set_msi_irq(e, &irq); + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) + continue; + + vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); + vcpu_info.vector = irq.vector; + + trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi, + vcpu_info.vector, vcpu_info.pi_desc_addr, set); + + if (set) + ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); + else { + /* suppress notification event before unposting */ + pi_set_sn(vcpu_to_pi_desc(vcpu)); + ret = irq_set_vcpu_affinity(host_irq, NULL); + pi_clear_sn(vcpu_to_pi_desc(vcpu)); + } + + if (ret < 0) { + printk(KERN_INFO "%s: failed to update PI IRTE\n", + __func__); + goto out; + } + } + + ret = 0; +out: + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -10150,6 +10767,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = report_flexpriority, + .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase, .vcpu_create = vmx_create_vcpu, .vcpu_free = vmx_free_vcpu, @@ -10159,7 +10777,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, - .update_db_bp_intercept = update_exception_bitmap, + .update_bp_intercept = update_exception_bitmap, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, @@ -10209,7 +10827,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .vm_has_apicv = vmx_vm_has_apicv, + .cpu_uses_apicv = vmx_cpu_uses_apicv, .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, @@ -10233,11 +10851,9 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .set_tsc_khz = vmx_set_tsc_khz, .read_tsc_offset = vmx_read_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, - .adjust_tsc_offset = vmx_adjust_tsc_offset, - .compute_tsc_offset = vmx_compute_tsc_offset, + .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest, .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, @@ -10255,6 +10871,13 @@ static struct kvm_x86_ops vmx_x86_ops = { .slot_disable_log_dirty = vmx_slot_disable_log_dirty, .flush_log_dirty = vmx_flush_log_dirty, .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + + .pre_block = vmx_pre_block, + .post_block = vmx_post_block, + + .pmu_ops = &intel_pmu_ops, + + .update_pi_irte = vmx_update_pi_irte, }; static int __init vmx_init(void) @@ -10264,7 +10887,7 @@ static int __init vmx_init(void) if (r) return r; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); #endif @@ -10274,7 +10897,7 @@ static int __init vmx_init(void) static void __exit vmx_exit(void) { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif |