/* * Kernel-based Virtual Machine driver for Linux * * This module enables machines with Intel VT-x extensions to run virtual * machines without emulation or binary translation. * * Copyright (C) 2006 Qumranet, Inc. * * Authors: * Avi Kivity * Yaniv Kamay * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. * */ #include "irq.h" #include "vmx.h" #include "mmu.h" #include #include #include #include #include #include #include #include "kvm_cache_regs.h" #include #include #define __ex(x) __kvm_handle_fault_on_reboot(x) MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); static int bypass_guest_pf = 1; module_param(bypass_guest_pf, bool, 0); static int enable_vpid = 1; module_param(enable_vpid, bool, 0); static int flexpriority_enabled = 1; module_param(flexpriority_enabled, bool, 0); static int enable_ept = 1; module_param(enable_ept, bool, 0); struct vmcs { u32 revision_id; u32 abort; char data[0]; }; struct vcpu_vmx { struct kvm_vcpu vcpu; struct list_head local_vcpus_link; int launched; u8 fail; u32 idt_vectoring_info; struct kvm_msr_entry *guest_msrs; struct kvm_msr_entry *host_msrs; int nmsrs; int save_nmsrs; int msr_offset_efer; #ifdef CONFIG_X86_64 int msr_offset_kernel_gs_base; #endif struct vmcs *vmcs; struct { int loaded; u16 fs_sel, gs_sel, ldt_sel; int gs_ldt_reload_needed; int fs_reload_needed; int guest_efer_loaded; } host_state; struct { struct { bool pending; u8 vector; unsigned rip; } irq; } rmode; int vpid; }; static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_vmx, vcpu); } static int init_rmode(struct kvm *kvm); static u64 construct_eptp(unsigned long root_hpa); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu); static struct page *vmx_io_bitmap_a; static struct page *vmx_io_bitmap_b; static struct page *vmx_msr_bitmap; static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); static struct vmcs_config { int size; int order; u32 revision_id; u32 pin_based_exec_ctrl; u32 cpu_based_exec_ctrl; u32 cpu_based_2nd_exec_ctrl; u32 vmexit_ctrl; u32 vmentry_ctrl; } vmcs_config; struct vmx_capability { u32 ept; u32 vpid; } vmx_capability; #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ .selector = GUEST_##seg##_SELECTOR, \ .base = GUEST_##seg##_BASE, \ .limit = GUEST_##seg##_LIMIT, \ .ar_bytes = GUEST_##seg##_AR_BYTES, \ } static struct kvm_vmx_segment_field { unsigned selector; unsigned base; unsigned limit; unsigned ar_bytes; } kvm_vmx_segment_fields[] = { VMX_SEGMENT_FIELD(CS), VMX_SEGMENT_FIELD(DS), VMX_SEGMENT_FIELD(ES), VMX_SEGMENT_FIELD(FS), VMX_SEGMENT_FIELD(GS), VMX_SEGMENT_FIELD(SS), VMX_SEGMENT_FIELD(TR), VMX_SEGMENT_FIELD(LDTR), }; /* * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it * away by decrementing the array size. */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE, #endif MSR_EFER, MSR_K6_STAR, }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) static void load_msrs(struct kvm_msr_entry *e, int n) { int i; for (i = 0; i < n; ++i) wrmsrl(e[i].index, e[i].data); } static void save_msrs(struct kvm_msr_entry *e, int n) { int i; for (i = 0; i < n; ++i) rdmsrl(e[i].index, e[i].data); } static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_no_device(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_invalid_opcode(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_external_interrupt(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); } static inline int cpu_has_vmx_msr_bitmap(void) { return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS); } static inline int cpu_has_vmx_tpr_shadow(void) { return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW); } static inline int vm_need_tpr_shadow(struct kvm *kvm) { return ((cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm))); } static inline int cpu_has_secondary_exec_ctrls(void) { return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS); } static inline bool cpu_has_vmx_virtualize_apic_accesses(void) { return flexpriority_enabled && (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); } static inline int cpu_has_vmx_invept_individual_addr(void) { return (!!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT)); } static inline int cpu_has_vmx_invept_context(void) { return (!!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT)); } static inline int cpu_has_vmx_invept_global(void) { return (!!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT)); } static inline int cpu_has_vmx_ept(void) { return (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_EPT); } static inline int vm_need_ept(void) { return (cpu_has_vmx_ept() && enable_ept); } static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) { return ((cpu_has_vmx_virtualize_apic_accesses()) && (irqchip_in_kernel(kvm))); } static inline int cpu_has_vmx_vpid(void) { return (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_VPID); } static inline int cpu_has_virtual_nmis(void) { return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; } static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) { int i; for (i = 0; i < vmx->nmsrs; ++i) if (vmx->guest_msrs[i].index == msr) return i; return -1; } static inline void __invvpid(int ext, u16 vpid, gva_t gva) { struct { u64 vpid : 16; u64 rsvd : 48; u64 gva; } operand = { vpid, 0, gva }; asm volatile (__ex(ASM_VMX_INVVPID) /* CF==1 or ZF==1 --> rc = -1 */ "; ja 1f ; ud2 ; 1:" : : "a"(&operand), "c"(ext) : "cc", "memory"); } static inline void __invept(int ext, u64 eptp, gpa_t gpa) { struct { u64 eptp, gpa; } operand = {eptp, gpa}; asm volatile (__ex(ASM_VMX_INVEPT) /* CF==1 or ZF==1 --> rc = -1 */ "; ja 1f ; ud2 ; 1:\n" : : "a" (&operand), "c" (ext) : "cc", "memory"); } static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; i = __find_msr_index(vmx, msr); if (i >= 0) return &vmx->guest_msrs[i]; return NULL; } static void vmcs_clear(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); u8 error; asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) "; setna %0" : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) : "cc", "memory"); if (error) printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n", vmcs, phys_addr); } static void __vcpu_clear(void *arg) { struct vcpu_vmx *vmx = arg; int cpu = raw_smp_processor_id(); if (vmx->vcpu.cpu == cpu) vmcs_clear(vmx->vmcs); if (per_cpu(current_vmcs, cpu) == vmx->vmcs) per_cpu(current_vmcs, cpu) = NULL; rdtscll(vmx->vcpu.arch.host_tsc); list_del(&vmx->local_vcpus_link); vmx->vcpu.cpu = -1; vmx->launched = 0; } static void vcpu_clear(struct vcpu_vmx *vmx) { if (vmx->vcpu.cpu == -1) return; smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1); } static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx) { if (vmx->vpid == 0) return; __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); } static inline void ept_sync_global(void) { if (cpu_has_vmx_invept_global()) __invept(VMX_EPT_EXTENT_GLOBAL, 0, 0); } static inline void ept_sync_context(u64 eptp) { if (vm_need_ept()) { if (cpu_has_vmx_invept_context()) __invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0); else ept_sync_global(); } } static inline void ept_sync_individual_addr(u64 eptp, gpa_t gpa) { if (vm_need_ept()) { if (cpu_has_vmx_invept_individual_addr()) __invept(VMX_EPT_EXTENT_INDIVIDUAL_ADDR, eptp, gpa); else ept_sync_context(eptp); } } static unsigned long vmcs_readl(unsigned long field) { unsigned long value; asm volatile (__ex(ASM_VMX_VMREAD_RDX_RAX) : "=a"(value) : "d"(field) : "cc"); return value; } static u16 vmcs_read16(unsigned long field) { return vmcs_readl(field); } static u32 vmcs_read32(unsigned long field) { return vmcs_readl(field); } static u64 vmcs_read64(unsigned long field) { #ifdef CONFIG_X86_64 return vmcs_readl(field); #else return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32); #endif } static noinline void vmwrite_error(unsigned long field, unsigned long value) { printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); dump_stack(); } static void vmcs_writel(unsigned long field, unsigned long value) { u8 error; asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) "; setna %0" : "=q"(error) : "a"(value), "d"(field) : "cc"); if (unlikely(error)) vmwrite_error(field, value); } static void vmcs_write16(unsigned long field, u16 value) { vmcs_writel(field, value); } static void vmcs_write32(unsigned long field, u32 value) { vmcs_writel(field, value); } static void vmcs_write64(unsigned long field, u64 value) { vmcs_writel(field, value); #ifndef CONFIG_X86_64 asm volatile (""); vmcs_writel(field+1, value >> 32); #endif } static void vmcs_clear_bits(unsigned long field, u32 mask) { vmcs_writel(field, vmcs_readl(field) & ~mask); } static void vmcs_set_bits(unsigned long field, u32 mask) { vmcs_writel(field, vmcs_readl(field) | mask); } static void update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR); if (!vcpu->fpu_active) eb |= 1u << NM_VECTOR; if (vcpu->guest_debug.enabled) eb |= 1u << 1; if (vcpu->arch.rmode.active) eb = ~0; if (vm_need_ept()) eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ vmcs_write32(EXCEPTION_BITMAP, eb); } static void reload_tss(void) { /* * VT restores TR but not its size. Useless. */ struct descriptor_table gdt; struct desc_struct *descs; kvm_get_gdt(&gdt); descs = (void *)gdt.base; descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ load_TR_desc(); } static void load_transition_efer(struct vcpu_vmx *vmx) { int efer_offset = vmx->msr_offset_efer; u64 host_efer = vmx->host_msrs[efer_offset].data; u64 guest_efer = vmx->guest_msrs[efer_offset].data; u64 ignore_bits; if (efer_offset < 0) return; /* * NX is emulated; LMA and LME handled by hardware; SCE meaninless * outside long mode */ ignore_bits = EFER_NX | 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 if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits)) return; vmx->host_state.guest_efer_loaded = 1; guest_efer &= ~ignore_bits; guest_efer |= host_efer & ignore_bits; wrmsrl(MSR_EFER, guest_efer); vmx->vcpu.stat.efer_reload++; } static void reload_host_efer(struct vcpu_vmx *vmx) { if (vmx->host_state.guest_efer_loaded) { vmx->host_state.guest_efer_loaded = 0; load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1); } } static void vmx_save_host_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (vmx->host_state.loaded) return; vmx->host_state.loaded = 1; /* * Set host fs and gs selectors. Unfortunately, 22.2.3 does not * allow segment selectors with cpl > 0 or ti == 1. */ vmx->host_state.ldt_sel = kvm_read_ldt(); vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; vmx->host_state.fs_sel = kvm_read_fs(); if (!(vmx->host_state.fs_sel & 7)) { vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); vmx->host_state.fs_reload_needed = 0; } else { vmcs_write16(HOST_FS_SELECTOR, 0); vmx->host_state.fs_reload_needed = 1; } vmx->host_state.gs_sel = kvm_read_gs(); if (!(vmx->host_state.gs_sel & 7)) vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel); else { vmcs_write16(HOST_GS_SELECTOR, 0); vmx->host_state.gs_ldt_reload_needed = 1; } #ifdef CONFIG_X86_64 vmcs_writel(HOST_FS_BASE, read_msr(MSR_FS_BASE)); vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE)); #else vmcs_writel(HOST_FS_BASE, segment_base(vmx->host_state.fs_sel)); vmcs_writel(HOST_GS_BASE, segment_base(vmx->host_state.gs_sel)); #endif #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) save_msrs(vmx->host_msrs + vmx->msr_offset_kernel_gs_base, 1); #endif load_msrs(vmx->guest_msrs, vmx->save_nmsrs); load_transition_efer(vmx); } static void __vmx_load_host_state(struct vcpu_vmx *vmx) { unsigned long flags; if (!vmx->host_state.loaded) return; ++vmx->vcpu.stat.host_state_reload; vmx->host_state.loaded = 0; if (vmx->host_state.fs_reload_needed) kvm_load_fs(vmx->host_state.fs_sel); if (vmx->host_state.gs_ldt_reload_needed) { kvm_load_ldt(vmx->host_state.ldt_sel); /* * If we have to reload gs, we must take care to * preserve our gs base. */ local_irq_save(flags); kvm_load_gs(vmx->host_state.gs_sel); #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE)); #endif local_irq_restore(flags); } reload_tss(); save_msrs(vmx->guest_msrs, vmx->save_nmsrs); load_msrs(vmx->host_msrs, vmx->save_nmsrs); reload_host_efer(vmx); } static void vmx_load_host_state(struct vcpu_vmx *vmx) { preempt_disable(); __vmx_load_host_state(vmx); preempt_enable(); } /* * 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) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 phys_addr = __pa(vmx->vmcs); u64 tsc_this, delta, new_offset; if (vcpu->cpu != cpu) { vcpu_clear(vmx); kvm_migrate_timers(vcpu); vpid_sync_vcpu_all(vmx); local_irq_disable(); list_add(&vmx->local_vcpus_link, &per_cpu(vcpus_on_cpu, cpu)); local_irq_enable(); } if (per_cpu(current_vmcs, cpu) != vmx->vmcs) { u8 error; per_cpu(current_vmcs, cpu) = vmx->vmcs; asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0" : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) : "cc"); if (error) printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n", vmx->vmcs, phys_addr); } if (vcpu->cpu != cpu) { struct descriptor_table dt; unsigned long sysenter_esp; vcpu->cpu = cpu; /* * Linux uses per-cpu TSS and GDT, so set these when switching * processors. */ vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */ kvm_get_gdt(&dt); vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */ rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ /* * Make sure the time stamp counter is monotonous. */ rdtscll(tsc_this); if (tsc_this < vcpu->arch.host_tsc) { delta = vcpu->arch.host_tsc - tsc_this; new_offset = vmcs_read64(TSC_OFFSET) + delta; vmcs_write64(TSC_OFFSET, new_offset); } } } static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { __vmx_load_host_state(to_vmx(vcpu)); } static void vmx_fpu_activate(struct kvm_vcpu *vcpu) { if (vcpu->fpu_active) return; vcpu->fpu_active = 1; vmcs_clear_bits(GUEST_CR0, X86_CR0_TS); if (vcpu->arch.cr0 & X86_CR0_TS) vmcs_set_bits(GUEST_CR0, X86_CR0_TS); update_exception_bitmap(vcpu); } static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) { if (!vcpu->fpu_active) return; vcpu->fpu_active = 0; vmcs_set_bits(GUEST_CR0, X86_CR0_TS); update_exception_bitmap(vcpu); } static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { return vmcs_readl(GUEST_RFLAGS); } static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { if (vcpu->arch.rmode.active) rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; vmcs_writel(GUEST_RFLAGS, rflags); } static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { unsigned long rip; u32 interruptibility; rip = kvm_rip_read(vcpu); rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); kvm_rip_write(vcpu, rip); /* * We emulated an instruction, so temporary interrupt blocking * should be removed, if set. */ interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); if (interruptibility & 3) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility & ~3); vcpu->arch.interrupt_window_open = 1; } static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error_code, u32 error_code) { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, nr | INTR_TYPE_EXCEPTION | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) | INTR_INFO_VALID_MASK); if (has_error_code) vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); } static bool vmx_exception_injected(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); return !(vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); } /* * Swap MSR entry in host/guest MSR entry array. */ #ifdef CONFIG_X86_64 static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) { struct kvm_msr_entry tmp; tmp = vmx->guest_msrs[to]; vmx->guest_msrs[to] = vmx->guest_msrs[from]; vmx->guest_msrs[from] = tmp; tmp = vmx->host_msrs[to]; vmx->host_msrs[to] = vmx->host_msrs[from]; vmx->host_msrs[from] = tmp; } #endif /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy * mode, as fiddling with msrs is very expensive. */ static void setup_msrs(struct vcpu_vmx *vmx) { int save_nmsrs; vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { int index; index = __find_msr_index(vmx, MSR_SYSCALL_MASK); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); index = __find_msr_index(vmx, MSR_LSTAR); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); index = __find_msr_index(vmx, MSR_CSTAR); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); index = __find_msr_index(vmx, MSR_KERNEL_GS_BASE); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); /* * MSR_K6_STAR is only needed on long mode guests, and only * if efer.sce is enabled. */ index = __find_msr_index(vmx, MSR_K6_STAR); if ((index >= 0) && (vmx->vcpu.arch.shadow_efer & EFER_SCE)) move_msr_up(vmx, index, save_nmsrs++); } #endif vmx->save_nmsrs = save_nmsrs; #ifdef CONFIG_X86_64 vmx->msr_offset_kernel_gs_base = __find_msr_index(vmx, MSR_KERNEL_GS_BASE); #endif vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER); } /* * reads and returns guest's timestamp counter "register" * guest_tsc = host_tsc + tsc_offset -- 21.3 */ static u64 guest_read_tsc(void) { u64 host_tsc, tsc_offset; rdtscll(host_tsc); tsc_offset = vmcs_read64(TSC_OFFSET); return host_tsc + tsc_offset; } /* * writes 'guest_tsc' into guest's timestamp counter "register" * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc */ static void guest_write_tsc(u64 guest_tsc) { u64 host_tsc; rdtscll(host_tsc); vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); } /* * Reads an msr value (of 'msr_index') into '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) { u64 data; struct kvm_msr_entry *msr; if (!pdata) { printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); return -EINVAL; } switch (msr_index) { #ifdef CONFIG_X86_64 case MSR_FS_BASE: data = vmcs_readl(GUEST_FS_BASE); break; case MSR_GS_BASE: data = vmcs_readl(GUEST_GS_BASE); break; case MSR_EFER: return kvm_get_msr_common(vcpu, msr_index, pdata); #endif case MSR_IA32_TIME_STAMP_COUNTER: data = guest_read_tsc(); break; case MSR_IA32_SYSENTER_CS: data = vmcs_read32(GUEST_SYSENTER_CS); break; case MSR_IA32_SYSENTER_EIP: data = vmcs_readl(GUEST_SYSENTER_EIP); break; case MSR_IA32_SYSENTER_ESP: data = vmcs_readl(GUEST_SYSENTER_ESP); break; default: msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { data = msr->data; break; } return kvm_get_msr_common(vcpu, msr_index, pdata); } *pdata = data; return 0; } /* * Writes msr value into 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, u32 msr_index, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_msr_entry *msr; int ret = 0; switch (msr_index) { #ifdef CONFIG_X86_64 case MSR_EFER: vmx_load_host_state(vmx); ret = kvm_set_msr_common(vcpu, msr_index, data); break; case MSR_FS_BASE: vmcs_writel(GUEST_FS_BASE, data); break; case MSR_GS_BASE: vmcs_writel(GUEST_GS_BASE, data); break; #endif case MSR_IA32_SYSENTER_CS: vmcs_write32(GUEST_SYSENTER_CS, data); break; case MSR_IA32_SYSENTER_EIP: vmcs_writel(GUEST_SYSENTER_EIP, data); break; case MSR_IA32_SYSENTER_ESP: vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_TIME_STAMP_COUNTER: guest_write_tsc(data); break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0: case MSR_P6_EVNTSEL1: /* * Just discard all writes to the performance counters; this * should keep both older linux and windows 64-bit guests * happy */ pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data); break; default: vmx_load_host_state(vmx); msr = find_msr_entry(vmx, msr_index); if (msr) { msr->data = data; break; } ret = kvm_set_msr_common(vcpu, msr_index, data); } return ret; } static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); switch (reg) { case VCPU_REGS_RSP: vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); break; case VCPU_REGS_RIP: vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP); break; default: break; } } static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) { unsigned long dr7 = 0x400; int old_singlestep; old_singlestep = vcpu->guest_debug.singlestep; vcpu->guest_debug.enabled = dbg->enabled; if (vcpu->guest_debug.enabled) { int i; dr7 |= 0x200; /* exact */ for (i = 0; i < 4; ++i) { if (!dbg->breakpoints[i].enabled) continue; vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address; dr7 |= 2 << (i*2); /* global enable */ dr7 |= 0 << (i*4+16); /* execution breakpoint */ } vcpu->guest_debug.singlestep = dbg->singlestep; } else vcpu->guest_debug.singlestep = 0; if (old_singlestep && !vcpu->guest_debug.singlestep) { unsigned long flags; flags = vmcs_readl(GUEST_RFLAGS); flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); vmcs_writel(GUEST_RFLAGS, flags); } update_exception_bitmap(vcpu); vmcs_writel(GUEST_DR7, dr7); return 0; } static int vmx_get_irq(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 idtv_info_field; idtv_info_field = vmx->idt_vectoring_info; if (idtv_info_field & INTR_INFO_VALID_MASK) { if (is_external_interrupt(idtv_info_field)) return idtv_info_field & VECTORING_INFO_VECTOR_MASK; else printk(KERN_DEBUG "pending exception: not handled yet\n"); } return -1; } static __init int cpu_has_kvm_support(void) { unsigned long ecx = cpuid_ecx(1); return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */ } static __init int vmx_disabled_by_bios(void) { u64 msr; rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); return (msr & (IA32_FEATURE_CONTROL_LOCKED_BIT | IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT)) == IA32_FEATURE_CONTROL_LOCKED_BIT; /* locked but not enabled */ } static void hardware_enable(void *garbage) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); u64 old; INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu)); rdmsrl(MSR_IA32_FEATURE_CONTROL, old); if ((old & (IA32_FEATURE_CONTROL_LOCKED_BIT | IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT)) != (IA32_FEATURE_CONTROL_LOCKED_BIT | IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT)) /* enable and lock */ wrmsrl(MSR_IA32_FEATURE_CONTROL, old | IA32_FEATURE_CONTROL_LOCKED_BIT | IA32_FEATURE_CONTROL_VMXON_ENABLED_BIT); write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */ asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) : "memory", "cc"); } static void vmclear_local_vcpus(void) { int cpu = raw_smp_processor_id(); struct vcpu_vmx *vmx, *n; list_for_each_entry_safe(vmx, n, &per_cpu(vcpus_on_cpu, cpu), local_vcpus_link) __vcpu_clear(vmx); } static void hardware_disable(void *garbage) { vmclear_local_vcpus(); asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); write_cr4(read_cr4() & ~X86_CR4_VMXE); } static __init 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; rdmsr(msr, vmx_msr_low, vmx_msr_high); ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */ ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */ /* Ensure minimum (required) set of control bits are supported. */ if (ctl_min & ~ctl) return -EIO; *result = ctl; return 0; } static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) { u32 vmx_msr_low, vmx_msr_high; u32 min, opt, min2, opt2; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; opt = PIN_BASED_VIRTUAL_NMIS; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, &_pin_based_exec_control) < 0) return -EIO; min = CPU_BASED_HLT_EXITING | #ifdef CONFIG_X86_64 CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | #endif CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MOV_DR_EXITING | CPU_BASED_USE_TSC_OFFSETING; opt = CPU_BASED_TPR_SHADOW | CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, &_cpu_based_exec_control) < 0) return -EIO; #ifdef CONFIG_X86_64 if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & ~CPU_BASED_CR8_STORE_EXITING; #endif if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { min2 = 0; opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_ENABLE_EPT; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) return -EIO; } #ifndef CONFIG_X86_64 if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; #endif if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { /* CR3 accesses don't need to cause VM Exits when EPT enabled */ min &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING); if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, &_cpu_based_exec_control) < 0) return -EIO; rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, vmx_capability.ept, vmx_capability.vpid); } min = 0; #ifdef CONFIG_X86_64 min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; #endif opt = 0; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, &_vmexit_control) < 0) return -EIO; min = opt = 0; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, &_vmentry_control) < 0) return -EIO; rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ if ((vmx_msr_high & 0x1fff) > 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)) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ if (((vmx_msr_high >> 18) & 15) != 6) return -EIO; vmcs_conf->size = vmx_msr_high & 0x1fff; vmcs_conf->order = get_order(vmcs_config.size); vmcs_conf->revision_id = vmx_msr_low; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; vmcs_conf->vmexit_ctrl = _vmexit_control; vmcs_conf->vmentry_ctrl = _vmentry_control; return 0; } static struct vmcs *alloc_vmcs_cpu(int cpu) { int node = cpu_to_node(cpu); struct page *pages; struct vmcs *vmcs; pages = alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); memset(vmcs, 0, vmcs_config.size); vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */ return vmcs; } static struct vmcs *alloc_vmcs(void) { return alloc_vmcs_cpu(raw_smp_processor_id()); } static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); } static void free_kvm_area(void) { int cpu; for_each_online_cpu(cpu) free_vmcs(per_cpu(vmxarea, cpu)); } static __init int alloc_kvm_area(void) { int cpu; for_each_online_cpu(cpu) { struct vmcs *vmcs; vmcs = alloc_vmcs_cpu(cpu); if (!vmcs) { free_kvm_area(); return -ENOMEM; } per_cpu(vmxarea, cpu) = vmcs; } return 0; } static __init int hardware_setup(void) { if (setup_vmcs_config(&vmcs_config) < 0) return -EIO; if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); return alloc_kvm_area(); } static __exit void hardware_unsetup(void) { free_kvm_area(); } static void fix_pmode_dataseg(int seg, struct kvm_save_segment *save) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; if (vmcs_readl(sf->base) == save->base && (save->base & AR_S_MASK)) { vmcs_write16(sf->selector, save->selector); vmcs_writel(sf->base, save->base); vmcs_write32(sf->limit, save->limit); vmcs_write32(sf->ar_bytes, save->ar); } else { u32 dpl = (vmcs_read16(sf->selector) & SELECTOR_RPL_MASK) << AR_DPL_SHIFT; vmcs_write32(sf->ar_bytes, 0x93 | dpl); } } static void enter_pmode(struct kvm_vcpu *vcpu) { unsigned long flags; vcpu->arch.rmode.active = 0; vmcs_writel(GUEST_TR_BASE, vcpu->arch.rmode.tr.base); vmcs_write32(GUEST_TR_LIMIT, vcpu->arch.rmode.tr.limit); vmcs_write32(GUEST_TR_AR_BYTES, vcpu->arch.rmode.tr.ar); flags = vmcs_readl(GUEST_RFLAGS); flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM); flags |= (vcpu->arch.rmode.save_iopl << IOPL_SHIFT); vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); update_exception_bitmap(vcpu); fix_pmode_dataseg(VCPU_SREG_ES, &vcpu->arch.rmode.es); fix_pmode_dataseg(VCPU_SREG_DS, &vcpu->arch.rmode.ds); fix_pmode_dataseg(VCPU_SREG_GS, &vcpu->arch.rmode.gs); fix_pmode_dataseg(VCPU_SREG_FS, &vcpu->arch.rmode.fs); vmcs_write16(GUEST_SS_SELECTOR, 0); vmcs_write32(GUEST_SS_AR_BYTES, 0x93); vmcs_write16(GUEST_CS_SELECTOR, vmcs_read16(GUEST_CS_SELECTOR) & ~SELECTOR_RPL_MASK); vmcs_write32(GUEST_CS_AR_BYTES, 0x9b); } static gva_t rmode_tss_base(struct kvm *kvm) { if (!kvm->arch.tss_addr) { gfn_t base_gfn = kvm->memslots[0].base_gfn + kvm->memslots[0].npages - 3; return base_gfn << PAGE_SHIFT; } return kvm->arch.tss_addr; } static void fix_rmode_seg(int seg, struct kvm_save_segment *save) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; save->selector = vmcs_read16(sf->selector); save->base = vmcs_readl(sf->base); save->limit = vmcs_read32(sf->limit); save->ar = vmcs_read32(sf->ar_bytes); vmcs_write16(sf->selector, save->base >> 4); vmcs_write32(sf->base, save->base & 0xfffff); vmcs_write32(sf->limit, 0xffff); vmcs_write32(sf->ar_bytes, 0xf3); } static void enter_rmode(struct kvm_vcpu *vcpu) { unsigned long flags; vcpu->arch.rmode.active = 1; vcpu->arch.rmode.tr.base = vmcs_readl(GUEST_TR_BASE); vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); vcpu->arch.rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT); vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); vcpu->arch.rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); flags = vmcs_readl(GUEST_RFLAGS); vcpu->arch.rmode.save_iopl = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; vmcs_writel(GUEST_RFLAGS, flags); vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); update_exception_bitmap(vcpu); vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4); vmcs_write32(GUEST_SS_LIMIT, 0xffff); vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); vmcs_write32(GUEST_CS_LIMIT, 0xffff); if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) vmcs_writel(GUEST_CS_BASE, 0xf0000); vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); fix_rmode_seg(VCPU_SREG_ES, &vcpu->arch.rmode.es); fix_rmode_seg(VCPU_SREG_DS, &vcpu->arch.rmode.ds); fix_rmode_seg(VCPU_SREG_GS, &vcpu->arch.rmode.gs); fix_rmode_seg(VCPU_SREG_FS, &vcpu->arch.rmode.fs); kvm_mmu_reset_context(vcpu); init_rmode(vcpu->kvm); } #ifdef CONFIG_X86_64 static void enter_lmode(struct kvm_vcpu *vcpu) { u32 guest_tr_ar; guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { printk(KERN_DEBUG "%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); } vcpu->arch.shadow_efer |= EFER_LMA; find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME; vmcs_write32(VM_ENTRY_CONTROLS, vmcs_read32(VM_ENTRY_CONTROLS) | VM_ENTRY_IA32E_MODE); } static void exit_lmode(struct kvm_vcpu *vcpu) { vcpu->arch.shadow_efer &= ~EFER_LMA; vmcs_write32(VM_ENTRY_CONTROLS, vmcs_read32(VM_ENTRY_CONTROLS) & ~VM_ENTRY_IA32E_MODE); } #endif static void vmx_flush_tlb(struct kvm_vcpu *vcpu) { vpid_sync_vcpu_all(to_vmx(vcpu)); if (vm_need_ept()) ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa)); } static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK; vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK; } static void ept_load_pdptrs(struct kvm_vcpu *vcpu) { if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) { if (!load_pdptrs(vcpu, vcpu->arch.cr3)) { printk(KERN_ERR "EPT: Fail to load pdptrs!\n"); return; } vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]); vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]); vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]); vmcs_write64(GUEST_PDPTR3, vcpu->arch.pdptrs[3]); } } static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, unsigned long cr0, struct kvm_vcpu *vcpu) { if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) | (CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING)); vcpu->arch.cr0 = cr0; vmx_set_cr4(vcpu, vcpu->arch.cr4); *hw_cr0 |= X86_CR0_PE | X86_CR0_PG; *hw_cr0 &= ~X86_CR0_WP; } else if (!is_paging(vcpu)) { /* From nonpaging to paging */ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) & ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING)); vcpu->arch.cr0 = cr0; vmx_set_cr4(vcpu, vcpu->arch.cr4); if (!(vcpu->arch.cr0 & X86_CR0_WP)) *hw_cr0 &= ~X86_CR0_WP; } } static void ept_update_paging_mode_cr4(unsigned long *hw_cr4, struct kvm_vcpu *vcpu) { if (!is_paging(vcpu)) { *hw_cr4 &= ~X86_CR4_PAE; *hw_cr4 |= X86_CR4_PSE; } else if (!(vcpu->arch.cr4 & X86_CR4_PAE)) *hw_cr4 &= ~X86_CR4_PAE; } static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON; vmx_fpu_deactivate(vcpu); if (vcpu->arch.rmode.active && (cr0 & X86_CR0_PE)) enter_pmode(vcpu); if (!vcpu->arch.rmode.active && !(cr0 & X86_CR0_PE)) enter_rmode(vcpu); #ifdef CONFIG_X86_64 if (vcpu->arch.shadow_efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) enter_lmode(vcpu); if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) exit_lmode(vcpu); } #endif if (vm_need_ept()) ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE)) vmx_fpu_activate(vcpu); } static u64 construct_eptp(unsigned long root_hpa) { u64 eptp; /* TODO write the value reading from MSR */ eptp = VMX_EPT_DEFAULT_MT | VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT; eptp |= (root_hpa & PAGE_MASK); return eptp; } static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { unsigned long guest_cr3; u64 eptp; guest_cr3 = cr3; if (vm_need_ept()) { eptp = construct_eptp(cr3); vmcs_write64(EPT_POINTER, eptp); ept_sync_context(eptp); ept_load_pdptrs(vcpu); guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 : VMX_EPT_IDENTITY_PAGETABLE_ADDR; } vmx_flush_tlb(vcpu); vmcs_writel(GUEST_CR3, guest_cr3); if (vcpu->arch.cr0 & X86_CR0_PE) vmx_fpu_deactivate(vcpu); } static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long hw_cr4 = cr4 | (vcpu->arch.rmode.active ? KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); vcpu->arch.cr4 = cr4; if (vm_need_ept()) ept_update_paging_mode_cr4(&hw_cr4, vcpu); vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); } static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); vcpu->arch.shadow_efer = efer; if (!msr) return; if (efer & EFER_LMA) { vmcs_write32(VM_ENTRY_CONTROLS, vmcs_read32(VM_ENTRY_CONTROLS) | VM_ENTRY_IA32E_MODE); msr->data = efer; } else { vmcs_write32(VM_ENTRY_CONTROLS, vmcs_read32(VM_ENTRY_CONTROLS) & ~VM_ENTRY_IA32E_MODE); msr->data = efer & ~EFER_LME; } setup_msrs(vmx); } static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; return vmcs_readl(sf->base); } static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; u32 ar; var->base = vmcs_readl(sf->base); var->limit = vmcs_read32(sf->limit); var->selector = vmcs_read16(sf->selector); ar = vmcs_read32(sf->ar_bytes); if (ar & AR_UNUSABLE_MASK) ar = 0; var->type = ar & 15; var->s = (ar >> 4) & 1; var->dpl = (ar >> 5) & 3; var->present = (ar >> 7) & 1; var->avl = (ar >> 12) & 1; var->l = (ar >> 13) & 1; var->db = (ar >> 14) & 1; var->g = (ar >> 15) & 1; var->unusable = (ar >> 16) & 1; } static int vmx_get_cpl(struct kvm_vcpu *vcpu) { struct kvm_segment kvm_seg; if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */ return 0; if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */ return 3; vmx_get_segment(vcpu, &kvm_seg, VCPU_SREG_CS); return kvm_seg.selector & 3; } static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; if (var->unusable) ar = 1 << 16; else { ar = var->type & 15; ar |= (var->s & 1) << 4; ar |= (var->dpl & 3) << 5; ar |= (var->present & 1) << 7; ar |= (var->avl & 1) << 12; ar |= (var->l & 1) << 13; ar |= (var->db & 1) << 14; ar |= (var->g & 1) << 15; } if (ar == 0) /* a 0 value means unusable */ ar = AR_UNUSABLE_MASK; return ar; } static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; u32 ar; if (vcpu->arch.rmode.active && seg == VCPU_SREG_TR) { vcpu->arch.rmode.tr.selector = var->selector; vcpu->arch.rmode.tr.base = var->base; vcpu->arch.rmode.tr.limit = var->limit; vcpu->arch.rmode.tr.ar = vmx_segment_access_rights(var); return; } vmcs_writel(sf->base, var->base); vmcs_write32(sf->limit, var->limit); vmcs_write16(sf->selector, var->selector); if (vcpu->arch.rmode.active && var->s) { /* * Hack real-mode segments into vm86 compatibility. */ if (var->base == 0xffff0000 && var->selector == 0xf000) vmcs_writel(sf->base, 0xf0000); ar = 0xf3; } else ar = vmx_segment_access_rights(var); vmcs_write32(sf->ar_bytes, ar); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { u32 ar = vmcs_read32(GUEST_CS_AR_BYTES); *db = (ar >> 14) & 1; *l = (ar >> 13) & 1; } static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) { dt->limit = vmcs_read32(GUEST_IDTR_LIMIT); dt->base = vmcs_readl(GUEST_IDTR_BASE); } static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) { vmcs_write32(GUEST_IDTR_LIMIT, dt->limit); vmcs_writel(GUEST_IDTR_BASE, dt->base); } static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) { dt->limit = vmcs_read32(GUEST_GDTR_LIMIT); dt->base = vmcs_readl(GUEST_GDTR_BASE); } static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) { vmcs_write32(GUEST_GDTR_LIMIT, dt->limit); vmcs_writel(GUEST_GDTR_BASE, dt->base); } static int init_rmode_tss(struct kvm *kvm) { gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT; u16 data = 0; int ret = 0; int r; r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; r = kvm_write_guest_page(kvm, fn++, &data, 0x66, sizeof(u16)); if (r < 0) goto out; r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE); if (r < 0) goto out; r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; data = ~0; r = kvm_write_guest_page(kvm, fn, &data, RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1, sizeof(u8)); if (r < 0) goto out; ret = 1; out: return ret; } static int init_rmode_identity_map(struct kvm *kvm) { int i, r, ret; pfn_t identity_map_pfn; u32 tmp; if (!vm_need_ept()) return 1; if (unlikely(!kvm->arch.ept_identity_pagetable)) { printk(KERN_ERR "EPT: identity-mapping pagetable " "haven't been allocated!\n"); return 0; } if (likely(kvm->arch.ept_identity_pagetable_done)) return 1; ret = 0; identity_map_pfn = VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT; r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); if (r < 0) goto out; /* Set up identity-mapping pagetable for EPT in real mode */ for (i = 0; i < PT32_ENT_PER_PAGE; i++) { tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); r = kvm_write_guest_page(kvm, identity_map_pfn, &tmp, i * sizeof(tmp), sizeof(tmp)); if (r < 0) goto out; } kvm->arch.ept_identity_pagetable_done = true; ret = 1; out: return ret; } static void seg_setup(int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; vmcs_write16(sf->selector, 0); vmcs_writel(sf->base, 0); vmcs_write32(sf->limit, 0xffff); vmcs_write32(sf->ar_bytes, 0x93); } static int alloc_apic_access_page(struct kvm *kvm) { struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; down_write(&kvm->slots_lock); if (kvm->arch.apic_access_page) goto out; kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; kvm_userspace_mem.flags = 0; kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL; kvm_userspace_mem.memory_size = PAGE_SIZE; r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); if (r) goto out; down_read(¤t->mm->mmap_sem); kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); up_read(¤t->mm->mmap_sem); out: up_write(&kvm->slots_lock); return r; } static int alloc_identity_pagetable(struct kvm *kvm) { struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; down_write(&kvm->slots_lock); if (kvm->arch.ept_identity_pagetable) goto out; kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; kvm_userspace_mem.flags = 0; kvm_userspace_mem.guest_phys_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; kvm_userspace_mem.memory_size = PAGE_SIZE; r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); if (r) goto out; down_read(¤t->mm->mmap_sem); kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, VMX_EPT_IDENTITY_PAGETABLE_ADDR >> PAGE_SHIFT); up_read(¤t->mm->mmap_sem); out: up_write(&kvm->slots_lock); return r; } static void allocate_vpid(struct vcpu_vmx *vmx) { int vpid; vmx->vpid = 0; if (!enable_vpid || !cpu_has_vmx_vpid()) return; spin_lock(&vmx_vpid_lock); vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); if (vpid < VMX_NR_VPIDS) { vmx->vpid = vpid; __set_bit(vpid, vmx_vpid_bitmap); } spin_unlock(&vmx_vpid_lock); } static void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr) { void *va; if (!cpu_has_vmx_msr_bitmap()) return; /* * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals * have the write-low and read-high bitmap offsets the wrong way round. * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. */ va = kmap(msr_bitmap); if (msr <= 0x1fff) { __clear_bit(msr, va + 0x000); /* read-low */ __clear_bit(msr, va + 0x800); /* write-low */ } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { msr &= 0x1fff; __clear_bit(msr, va + 0x400); /* read-high */ __clear_bit(msr, va + 0xc00); /* write-high */ } kunmap(msr_bitmap); } /* * Sets up the vmcs for emulated real mode. */ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) { u32 host_sysenter_cs; u32 junk; unsigned long a; struct descriptor_table dt; int i; unsigned long kvm_vmx_return; u32 exec_control; /* I/O */ vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a)); vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b)); if (cpu_has_vmx_msr_bitmap()) vmcs_write64(MSR_BITMAP, page_to_phys(vmx_msr_bitmap)); vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ /* Control */ vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmcs_config.pin_based_exec_ctrl); exec_control = vmcs_config.cpu_based_exec_ctrl; if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) { exec_control &= ~CPU_BASED_TPR_SHADOW; #ifdef CONFIG_X86_64 exec_control |= CPU_BASED_CR8_STORE_EXITING | CPU_BASED_CR8_LOAD_EXITING; #endif } if (!vm_need_ept()) exec_control |= CPU_BASED_CR3_STORE_EXITING | CPU_BASED_CR3_LOAD_EXITING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control); if (cpu_has_secondary_exec_ctrls()) { exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; if (!vm_need_ept()) exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ vmcs_writel(HOST_CR0, read_cr0()); /* 22.2.3 */ vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_FS_SELECTOR, kvm_read_fs()); /* 22.2.4 */ vmcs_write16(HOST_GS_SELECTOR, kvm_read_gs()); /* 22.2.4 */ vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ #ifdef CONFIG_X86_64 rdmsrl(MSR_FS_BASE, a); vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */ rdmsrl(MSR_GS_BASE, a); vmcs_writel(HOST_GS_BASE, a); /* 22.2.4 */ #else vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ #endif vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ kvm_get_idt(&dt); vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */ asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return)); vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */ vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk); vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs); rdmsrl(MSR_IA32_SYSENTER_ESP, a); vmcs_writel(HOST_IA32_SYSENTER_ESP, a); /* 22.2.3 */ rdmsrl(MSR_IA32_SYSENTER_EIP, a); vmcs_writel(HOST_IA32_SYSENTER_EIP, a); /* 22.2.3 */ for (i = 0; i < NR_VMX_MSR; ++i) { u32 index = vmx_msr_index[i]; u32 data_low, data_high; u64 data; int j = vmx->nmsrs; if (rdmsr_safe(index, &data_low, &data_high) < 0) continue; if (wrmsr_safe(index, data_low, data_high) < 0) continue; data = data_low | ((u64)data_high << 32); vmx->host_msrs[j].index = index; vmx->host_msrs[j].reserved = 0; vmx->host_msrs[j].data = data; vmx->guest_msrs[j] = vmx->host_msrs[j]; ++vmx->nmsrs; } vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); /* 22.2.1, 20.8.1 */ vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl); vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); return 0; } static int init_rmode(struct kvm *kvm) { if (!init_rmode_tss(kvm)) return 0; if (!init_rmode_identity_map(kvm)) return 0; return 1; } static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 msr; int ret; vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); down_read(&vcpu->kvm->slots_lock); if (!init_rmode(vmx->vcpu.kvm)) { ret = -ENOMEM; goto out; } vmx->vcpu.arch.rmode.active = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (vmx->vcpu.vcpu_id == 0) msr |= MSR_IA32_APICBASE_BSP; kvm_set_apic_base(&vmx->vcpu, msr); fx_init(&vmx->vcpu); /* * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh. */ if (vmx->vcpu.vcpu_id == 0) { vmcs_write16(GUEST_CS_SELECTOR, 0xf000); vmcs_writel(GUEST_CS_BASE, 0x000f0000); } else { vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8); vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12); } vmcs_write32(GUEST_CS_LIMIT, 0xffff); vmcs_write32(GUEST_CS_AR_BYTES, 0x9b); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); seg_setup(VCPU_SREG_FS); seg_setup(VCPU_SREG_GS); seg_setup(VCPU_SREG_SS); vmcs_write16(GUEST_TR_SELECTOR, 0); vmcs_writel(GUEST_TR_BASE, 0); vmcs_write32(GUEST_TR_LIMIT, 0xffff); vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); vmcs_write16(GUEST_LDTR_SELECTOR, 0); vmcs_writel(GUEST_LDTR_BASE, 0); 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); vmcs_writel(GUEST_RFLAGS, 0x02); if (vmx->vcpu.vcpu_id == 0) kvm_rip_write(vcpu, 0xfff0); else kvm_rip_write(vcpu, 0); kvm_register_write(vcpu, VCPU_REGS_RSP, 0); /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */ vmcs_writel(GUEST_DR7, 0x400); vmcs_writel(GUEST_GDTR_BASE, 0); vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); vmcs_writel(GUEST_IDTR_BASE, 0); vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); vmcs_write32(GUEST_ACTIVITY_STATE, 0); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); guest_write_tsc(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()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); if (vm_need_tpr_shadow(vmx->vcpu.kvm)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, page_to_phys(vmx->vcpu.arch.apic->regs_page)); vmcs_write32(TPR_THRESHOLD, 0); } if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->vcpu.kvm->arch.apic_access_page)); if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); vmx->vcpu.arch.cr0 = 0x60000010; vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */ vmx_set_cr4(&vmx->vcpu, 0); vmx_set_efer(&vmx->vcpu, 0); vmx_fpu_activate(&vmx->vcpu); update_exception_bitmap(&vmx->vcpu); vpid_sync_vcpu_all(vmx); ret = 0; out: up_read(&vcpu->kvm->slots_lock); return ret; } static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq) { struct vcpu_vmx *vmx = to_vmx(vcpu); KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler); if (vcpu->arch.rmode.active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = irq; vmx->rmode.irq.rip = kvm_rip_read(vcpu); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, irq | INTR_TYPE_SOFT_INTR | INTR_INFO_VALID_MASK); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1); return; } vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); } static void vmx_inject_nmi(struct kvm_vcpu *vcpu) { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); vcpu->arch.nmi_pending = 0; } static void kvm_do_inject_irq(struct kvm_vcpu *vcpu) { int word_index = __ffs(vcpu->arch.irq_summary); int bit_index = __ffs(vcpu->arch.irq_pending[word_index]); int irq = word_index * BITS_PER_LONG + bit_index; clear_bit(bit_index, &vcpu->arch.irq_pending[word_index]); if (!vcpu->arch.irq_pending[word_index]) clear_bit(word_index, &vcpu->arch.irq_summary); vmx_inject_irq(vcpu, irq); } static void do_interrupt_requests(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 cpu_based_vm_exec_control; vcpu->arch.interrupt_window_open = ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0); if (vcpu->arch.interrupt_window_open && vcpu->arch.irq_summary && !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK)) /* * If interrupts enabled, and not blocked by sti or mov ss. Good. */ kvm_do_inject_irq(vcpu); cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); if (!vcpu->arch.interrupt_window_open && (vcpu->arch.irq_summary || kvm_run->request_interrupt_window)) /* * Interrupts blocked. Wait for unblock. */ cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; else cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); } static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { int ret; struct kvm_userspace_memory_region tss_mem = { .slot = 8, .guest_phys_addr = addr, .memory_size = PAGE_SIZE * 3, .flags = 0, }; ret = kvm_set_memory_region(kvm, &tss_mem, 0); if (ret) return ret; kvm->arch.tss_addr = addr; return 0; } static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu) { struct kvm_guest_debug *dbg = &vcpu->guest_debug; set_debugreg(dbg->bp[0], 0); set_debugreg(dbg->bp[1], 1); set_debugreg(dbg->bp[2], 2); set_debugreg(dbg->bp[3], 3); if (dbg->singlestep) { unsigned long flags; flags = vmcs_readl(GUEST_RFLAGS); flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; vmcs_writel(GUEST_RFLAGS, flags); } } static int handle_rmode_exception(struct kvm_vcpu *vcpu, int vec, u32 err_code) { if (!vcpu->arch.rmode.active) return 0; /* * Instruction with address size override prefix opcode 0x67 * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE) return 1; return 0; } static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info, error_code; unsigned long cr2, rip; u32 vect_info; enum emulation_result er; vect_info = vmx->idt_vectoring_info; intr_info = vmcs_read32(VM_EXIT_INTR_INFO); if ((vect_info & VECTORING_INFO_VALID_MASK) && !is_page_fault(intr_info)) printk(KERN_ERR "%s: unexpected, vectoring info 0x%x " "intr info 0x%x\n", __func__, vect_info, intr_info); if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) { int irq = vect_info & VECTORING_INFO_VECTOR_MASK; set_bit(irq, vcpu->arch.irq_pending); set_bit(irq / BITS_PER_LONG, &vcpu->arch.irq_summary); } if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */ return 1; /* already handled by vmx_vcpu_run() */ if (is_no_device(intr_info)) { vmx_fpu_activate(vcpu); return 1; } if (is_invalid_opcode(intr_info)) { er = emulate_instruction(vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); return 1; } error_code = 0; rip = kvm_rip_read(vcpu); if (intr_info & INTR_INFO_DELIVER_CODE_MASK) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (is_page_fault(intr_info)) { /* EPT won't cause page fault directly */ if (vm_need_ept()) BUG(); cr2 = vmcs_readl(EXIT_QUALIFICATION); KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2, (u32)((u64)cr2 >> 32), handler); if (vect_info & VECTORING_INFO_VALID_MASK) kvm_mmu_unprotect_page_virt(vcpu, cr2); return kvm_mmu_page_fault(vcpu, cr2, error_code); } if (vcpu->arch.rmode.active && handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK, error_code)) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_emulate_halt(vcpu); } return 1; } if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == (INTR_TYPE_EXCEPTION | 1)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; return 0; } kvm_run->exit_reason = KVM_EXIT_EXCEPTION; kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK; kvm_run->ex.error_code = error_code; return 0; } static int handle_external_interrupt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { ++vcpu->stat.irq_exits; KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler); return 1; } static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; } static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { unsigned long exit_qualification; int size, down, in, string, rep; unsigned port; ++vcpu->stat.io_exits; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); string = (exit_qualification & 16) != 0; if (string) { if (emulate_instruction(vcpu, kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) return 0; return 1; } size = (exit_qualification & 7) + 1; in = (exit_qualification & 8) != 0; down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0; rep = (exit_qualification & 32) != 0; port = exit_qualification >> 16; return kvm_emulate_pio(vcpu, kvm_run, in, size, port); } static void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { /* * Patch in the VMCALL instruction: */ hypercall[0] = 0x0f; hypercall[1] = 0x01; hypercall[2] = 0xc1; } static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { unsigned long exit_qualification; int cr; int reg; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); cr = exit_qualification & 15; reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)kvm_register_read(vcpu, reg), (u32)((u64)kvm_register_read(vcpu, reg) >> 32), handler); switch (cr) { case 0: kvm_set_cr0(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); return 1; case 3: kvm_set_cr3(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); return 1; case 4: kvm_set_cr4(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); return 1; case 8: kvm_set_cr8(vcpu, kvm_register_read(vcpu, reg)); skip_emulated_instruction(vcpu); if (irqchip_in_kernel(vcpu->kvm)) return 1; kvm_run->exit_reason = KVM_EXIT_SET_TPR; return 0; }; break; case 2: /* clts */ vmx_fpu_deactivate(vcpu); vcpu->arch.cr0 &= ~X86_CR0_TS; vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); vmx_fpu_activate(vcpu); KVMTRACE_0D(CLTS, vcpu, handler); skip_emulated_instruction(vcpu); return 1; case 1: /*mov from cr*/ switch (cr) { case 3: kvm_register_write(vcpu, reg, vcpu->arch.cr3); KVMTRACE_3D(CR_READ, vcpu, (u32)cr, (u32)kvm_register_read(vcpu, reg), (u32)((u64)kvm_register_read(vcpu, reg) >> 32), handler); skip_emulated_instruction(vcpu); return 1; case 8: kvm_register_write(vcpu, reg, kvm_get_cr8(vcpu)); KVMTRACE_2D(CR_READ, vcpu, (u32)cr, (u32)kvm_register_read(vcpu, reg), handler); skip_emulated_instruction(vcpu); return 1; } break; case 3: /* lmsw */ kvm_lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f); skip_emulated_instruction(vcpu); return 1; default: break; } kvm_run->exit_reason = 0; pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { unsigned long exit_qualification; unsigned long val; int dr, reg; /* * FIXME: this code assumes the host is debugging the guest. * need to deal with guest debugging itself too. */ exit_qualification = vmcs_readl(EXIT_QUALIFICATION); dr = exit_qualification & 7; reg = (exit_qualification >> 8) & 15; if (exit_qualification & 16) { /* mov from dr */ switch (dr) { case 6: val = 0xffff0ff0; break; case 7: val = 0x400; break; default: val = 0; } kvm_register_write(vcpu, reg, val); KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); } else { /* mov to dr */ } skip_emulated_instruction(vcpu); return 1; } static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { kvm_emulate_cpuid(vcpu); return 1; } static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data; if (vmx_get_msr(vcpu, ecx, &data)) { kvm_inject_gp(vcpu, 0); return 1; } KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32), handler); /* 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; skip_emulated_instruction(vcpu); return 1; } static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32); KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32), handler); if (vmx_set_msr(vcpu, ecx, data) != 0) { kvm_inject_gp(vcpu, 0); return 1; } skip_emulated_instruction(vcpu); return 1; } static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { return 1; } static int handle_interrupt_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 cpu_based_vm_exec_control; /* clear pending irq */ cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); KVMTRACE_0D(PEND_INTR, vcpu, handler); /* * If the user space waits to inject interrupts, exit as soon as * possible */ if (kvm_run->request_interrupt_window && !vcpu->arch.irq_summary) { kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.irq_window_exits; return 0; } return 1; } static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { skip_emulated_instruction(vcpu); return kvm_emulate_halt(vcpu); } static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { skip_emulated_instruction(vcpu); /* TODO: Add support for VT-d/pass-through device */ return 1; } static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u64 exit_qualification; enum emulation_result er; unsigned long offset; exit_qualification = vmcs_read64(EXIT_QUALIFICATION); offset = exit_qualification & 0xffful; er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); if (er != EMULATE_DONE) { printk(KERN_ERR "Fail to handle apic access vmexit! Offset is 0x%lx\n", offset); return -ENOTSUPP; } return 1; } static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { unsigned long exit_qualification; u16 tss_selector; int reason; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); reason = (u32)exit_qualification >> 30; tss_selector = exit_qualification; return kvm_task_switch(vcpu, tss_selector, reason); } static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u64 exit_qualification; enum emulation_result er; gpa_t gpa; unsigned long hva; int gla_validity; int r; exit_qualification = vmcs_read64(EXIT_QUALIFICATION); if (exit_qualification & (1 << 6)) { printk(KERN_ERR "EPT: GPA exceeds GAW!\n"); return -ENOTSUPP; } gla_validity = (exit_qualification >> 7) & 0x3; if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) { printk(KERN_ERR "EPT: Handling EPT violation failed!\n"); printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n", (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS), (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS)); printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", (long unsigned int)exit_qualification); kvm_run->exit_reason = KVM_EXIT_UNKNOWN; kvm_run->hw.hardware_exit_reason = 0; return -ENOTSUPP; } gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); hva = gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT); if (!kvm_is_error_hva(hva)) { r = kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0); if (r < 0) { printk(KERN_ERR "EPT: Not enough memory!\n"); return -ENOMEM; } return 1; } else { /* must be MMIO */ er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); if (er == EMULATE_FAIL) { printk(KERN_ERR "EPT: Fail to handle EPT violation vmexit!er is %d\n", er); printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n", (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS), (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS)); printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", (long unsigned int)exit_qualification); return -ENOTSUPP; } else if (er == EMULATE_DO_MMIO) return 0; } return 1; } static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u32 cpu_based_vm_exec_control; /* clear pending NMI */ cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); ++vcpu->stat.nmi_window_exits; 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 * to be done to userspace and return 0. */ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) = { [EXIT_REASON_EXCEPTION_NMI] = handle_exception, [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, [EXIT_REASON_NMI_WINDOW] = handle_nmi_window, [EXIT_REASON_IO_INSTRUCTION] = handle_io, [EXIT_REASON_CR_ACCESS] = handle_cr, [EXIT_REASON_DR_ACCESS] = handle_dr, [EXIT_REASON_CPUID] = handle_cpuid, [EXIT_REASON_MSR_READ] = handle_rdmsr, [EXIT_REASON_MSR_WRITE] = handle_wrmsr, [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, [EXIT_REASON_HLT] = handle_halt, [EXIT_REASON_VMCALL] = handle_vmcall, [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, [EXIT_REASON_WBINVD] = handle_wbinvd, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, }; static const int kvm_vmx_max_exit_handlers = ARRAY_SIZE(kvm_vmx_exit_handlers); /* * The guest has exited. See if we can fix it or if we need userspace * assistance. */ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { u32 exit_reason = vmcs_read32(VM_EXIT_REASON); struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vectoring_info = vmx->idt_vectoring_info; KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)kvm_rip_read(vcpu), (u32)((u64)kvm_rip_read(vcpu) >> 32), entryexit); /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ if (vm_need_ept() && is_paging(vcpu)) { vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); ept_load_pdptrs(vcpu); } if (unlikely(vmx->fail)) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; kvm_run->fail_entry.hardware_entry_failure_reason = vmcs_read32(VM_INSTRUCTION_ERROR); return 0; } if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason != EXIT_REASON_EXCEPTION_NMI && exit_reason != EXIT_REASON_EPT_VIOLATION)) printk(KERN_WARNING "%s: unexpected, valid vectoring info and " "exit reason is 0x%x\n", __func__, exit_reason); if (exit_reason < kvm_vmx_max_exit_handlers && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); else { kvm_run->exit_reason = KVM_EXIT_UNKNOWN; kvm_run->hw.hardware_exit_reason = exit_reason; } return 0; } static void update_tpr_threshold(struct kvm_vcpu *vcpu) { int max_irr, tpr; if (!vm_need_tpr_shadow(vcpu->kvm)) return; if (!kvm_lapic_enabled(vcpu) || ((max_irr = kvm_lapic_find_highest_irr(vcpu)) == -1)) { vmcs_write32(TPR_THRESHOLD, 0); return; } tpr = (kvm_lapic_get_cr8(vcpu) & 0x0f) << 4; vmcs_write32(TPR_THRESHOLD, (max_irr > tpr) ? tpr >> 4 : max_irr >> 4); } static void enable_irq_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); } static void enable_nmi_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; if (!cpu_has_virtual_nmis()) return; cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING; vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); } static int vmx_nmi_enabled(struct kvm_vcpu *vcpu) { u32 guest_intr = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); return !(guest_intr & (GUEST_INTR_STATE_NMI | GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI)); } static int vmx_irq_enabled(struct kvm_vcpu *vcpu) { u32 guest_intr = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); return (!(guest_intr & (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI)) && (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF)); } static void enable_intr_window(struct kvm_vcpu *vcpu) { if (vcpu->arch.nmi_pending) enable_nmi_window(vcpu); else if (kvm_cpu_has_interrupt(vcpu)) enable_irq_window(vcpu); } static void vmx_intr_assist(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 idtv_info_field, intr_info_field, exit_intr_info_field; int vector; update_tpr_threshold(vcpu); intr_info_field = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); exit_intr_info_field = vmcs_read32(VM_EXIT_INTR_INFO); idtv_info_field = vmx->idt_vectoring_info; if (intr_info_field & INTR_INFO_VALID_MASK) { if (idtv_info_field & INTR_INFO_VALID_MASK) { /* TODO: fault when IDT_Vectoring */ if (printk_ratelimit()) printk(KERN_ERR "Fault when IDT_Vectoring\n"); } enable_intr_window(vcpu); return; } if (unlikely(idtv_info_field & INTR_INFO_VALID_MASK)) { if ((idtv_info_field & VECTORING_INFO_TYPE_MASK) == INTR_TYPE_EXT_INTR && vcpu->arch.rmode.active) { u8 vect = idtv_info_field & VECTORING_INFO_VECTOR_MASK; vmx_inject_irq(vcpu, vect); enable_intr_window(vcpu); return; } KVMTRACE_1D(REDELIVER_EVT, vcpu, idtv_info_field, handler); /* * SDM 3: 25.7.1.2 * Clear bit "block by NMI" before VM entry if a NMI delivery * faulted. */ if ((idtv_info_field & VECTORING_INFO_TYPE_MASK) == INTR_TYPE_NMI_INTR && cpu_has_virtual_nmis()) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & ~GUEST_INTR_STATE_NMI); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field & ~INTR_INFO_RESVD_BITS_MASK); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); if (unlikely(idtv_info_field & INTR_INFO_DELIVER_CODE_MASK)) vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, vmcs_read32(IDT_VECTORING_ERROR_CODE)); enable_intr_window(vcpu); return; } if (cpu_has_virtual_nmis()) { /* * SDM 3: 25.7.1.2 * Re-set bit "block by NMI" before VM entry if vmexit caused by * a guest IRET fault. */ if ((exit_intr_info_field & INTR_INFO_UNBLOCK_NMI) && (exit_intr_info_field & INTR_INFO_VECTOR_MASK) != 8) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) | GUEST_INTR_STATE_NMI); else if (vcpu->arch.nmi_pending) { if (vmx_nmi_enabled(vcpu)) vmx_inject_nmi(vcpu); enable_intr_window(vcpu); return; } } if (!kvm_cpu_has_interrupt(vcpu)) return; if (vmx_irq_enabled(vcpu)) { vector = kvm_cpu_get_interrupt(vcpu); vmx_inject_irq(vcpu, vector); kvm_timer_intr_post(vcpu, vector); } else enable_irq_window(vcpu); } /* * Failure to inject an interrupt should give us the information * in IDT_VECTORING_INFO_FIELD. However, if the failure occurs * when fetching the interrupt redirection bitmap in the real-mode * tss, this doesn't happen. So we do it ourselves. */ static void fixup_rmode_irq(struct vcpu_vmx *vmx) { vmx->rmode.irq.pending = 0; if (kvm_rip_read(&vmx->vcpu) + 1 != vmx->rmode.irq.rip) return; kvm_rip_write(&vmx->vcpu, vmx->rmode.irq.rip); if (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) { vmx->idt_vectoring_info &= ~VECTORING_INFO_TYPE_MASK; vmx->idt_vectoring_info |= INTR_TYPE_EXT_INTR; return; } vmx->idt_vectoring_info = VECTORING_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | vmx->rmode.irq.vector; } static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info; if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); /* * Loading guest fpu may have cleared host cr0.ts */ vmcs_writel(HOST_CR0, read_cr0()); asm( /* Store host registers */ #ifdef CONFIG_X86_64 "push %%rdx; push %%rbp;" "push %%rcx \n\t" #else "push %%edx; push %%ebp;" "push %%ecx \n\t" #endif __ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t" /* Check if vmlaunch of vmresume is needed */ "cmpl $0, %c[launched](%0) \n\t" /* Load guest registers. Don't clobber flags. */ #ifdef CONFIG_X86_64 "mov %c[cr2](%0), %%rax \n\t" "mov %%rax, %%cr2 \n\t" "mov %c[rax](%0), %%rax \n\t" "mov %c[rbx](%0), %%rbx \n\t" "mov %c[rdx](%0), %%rdx \n\t" "mov %c[rsi](%0), %%rsi \n\t" "mov %c[rdi](%0), %%rdi \n\t" "mov %c[rbp](%0), %%rbp \n\t" "mov %c[r8](%0), %%r8 \n\t" "mov %c[r9](%0), %%r9 \n\t" "mov %c[r10](%0), %%r10 \n\t" "mov %c[r11](%0), %%r11 \n\t" "mov %c[r12](%0), %%r12 \n\t" "mov %c[r13](%0), %%r13 \n\t" "mov %c[r14](%0), %%r14 \n\t" "mov %c[r15](%0), %%r15 \n\t" "mov %c[rcx](%0), %%rcx \n\t" /* kills %0 (rcx) */ #else "mov %c[cr2](%0), %%eax \n\t" "mov %%eax, %%cr2 \n\t" "mov %c[rax](%0), %%eax \n\t" "mov %c[rbx](%0), %%ebx \n\t" "mov %c[rdx](%0), %%edx \n\t" "mov %c[rsi](%0), %%esi \n\t" "mov %c[rdi](%0), %%edi \n\t" "mov %c[rbp](%0), %%ebp \n\t" "mov %c[rcx](%0), %%ecx \n\t" /* kills %0 (ecx) */ #endif /* Enter guest mode */ "jne .Llaunched \n\t" __ex(ASM_VMX_VMLAUNCH) "\n\t" "jmp .Lkvm_vmx_return \n\t" ".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t" ".Lkvm_vmx_return: " /* Save guest registers, load host registers, keep flags */ #ifdef CONFIG_X86_64 "xchg %0, (%%rsp) \n\t" "mov %%rax, %c[rax](%0) \n\t" "mov %%rbx, %c[rbx](%0) \n\t" "pushq (%%rsp); popq %c[rcx](%0) \n\t" "mov %%rdx, %c[rdx](%0) \n\t" "mov %%rsi, %c[rsi](%0) \n\t" "mov %%rdi, %c[rdi](%0) \n\t" "mov %%rbp, %c[rbp](%0) \n\t" "mov %%r8, %c[r8](%0) \n\t" "mov %%r9, %c[r9](%0) \n\t" "mov %%r10, %c[r10](%0) \n\t" "mov %%r11, %c[r11](%0) \n\t" "mov %%r12, %c[r12](%0) \n\t" "mov %%r13, %c[r13](%0) \n\t" "mov %%r14, %c[r14](%0) \n\t" "mov %%r15, %c[r15](%0) \n\t" "mov %%cr2, %%rax \n\t" "mov %%rax, %c[cr2](%0) \n\t" "pop %%rbp; pop %%rbp; pop %%rdx \n\t" #else "xchg %0, (%%esp) \n\t" "mov %%eax, %c[rax](%0) \n\t" "mov %%ebx, %c[rbx](%0) \n\t" "pushl (%%esp); popl %c[rcx](%0) \n\t" "mov %%edx, %c[rdx](%0) \n\t" "mov %%esi, %c[rsi](%0) \n\t" "mov %%edi, %c[rdi](%0) \n\t" "mov %%ebp, %c[rbp](%0) \n\t" "mov %%cr2, %%eax \n\t" "mov %%eax, %c[cr2](%0) \n\t" "pop %%ebp; pop %%ebp; pop %%edx \n\t" #endif "setbe %c[fail](%0) \n\t" : : "c"(vmx), "d"((unsigned long)HOST_RSP), [launched]"i"(offsetof(struct vcpu_vmx, launched)), [fail]"i"(offsetof(struct vcpu_vmx, fail)), [rax]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RAX])), [rbx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBX])), [rcx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RCX])), [rdx]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDX])), [rsi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RSI])), [rdi]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RDI])), [rbp]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_RBP])), #ifdef CONFIG_X86_64 [r8]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R8])), [r9]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R9])), [r10]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R10])), [r11]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R11])), [r12]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R12])), [r13]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R13])), [r14]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R14])), [r15]"i"(offsetof(struct vcpu_vmx, vcpu.arch.regs[VCPU_REGS_R15])), #endif [cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)) : "cc", "memory" #ifdef CONFIG_X86_64 , "rbx", "rdi", "rsi" , "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15" #else , "ebx", "edi", "rsi" #endif ); vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); vcpu->arch.regs_dirty = 0; vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); if (vmx->rmode.irq.pending) fixup_rmode_irq(vmx); vcpu->arch.interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)) == 0; asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS)); vmx->launched = 1; intr_info = vmcs_read32(VM_EXIT_INTR_INFO); /* We need to handle NMIs before interrupts are enabled */ if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200 && (intr_info & INTR_INFO_VALID_MASK)) { KVMTRACE_0D(NMI, vcpu, handler); asm("int $2"); } } static void vmx_free_vmcs(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (vmx->vmcs) { vcpu_clear(vmx); free_vmcs(vmx->vmcs); vmx->vmcs = NULL; } } static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); spin_lock(&vmx_vpid_lock); if (vmx->vpid != 0) __clear_bit(vmx->vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); vmx_free_vmcs(vcpu); kfree(vmx->host_msrs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); } static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) { int err; struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); int cpu; if (!vmx) return ERR_PTR(-ENOMEM); allocate_vpid(vmx); err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) goto free_vcpu; vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!vmx->guest_msrs) { err = -ENOMEM; goto uninit_vcpu; } vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!vmx->host_msrs) goto free_guest_msrs; vmx->vmcs = alloc_vmcs(); if (!vmx->vmcs) goto free_msrs; vmcs_clear(vmx->vmcs); cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); err = vmx_vcpu_setup(vmx); vmx_vcpu_put(&vmx->vcpu); put_cpu(); if (err) goto free_vmcs; if (vm_need_virtualize_apic_accesses(kvm)) if (alloc_apic_access_page(kvm) != 0) goto free_vmcs; if (vm_need_ept()) if (alloc_identity_pagetable(kvm) != 0) goto free_vmcs; return &vmx->vcpu; free_vmcs: free_vmcs(vmx->vmcs); free_msrs: kfree(vmx->host_msrs); free_guest_msrs: kfree(vmx->guest_msrs); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); free_vcpu: kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); } static void __init vmx_check_processor_compat(void *rtn) { struct vmcs_config vmcs_conf; *(int *)rtn = 0; if (setup_vmcs_config(&vmcs_conf) < 0) *(int *)rtn = -EIO; if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); *(int *)rtn = -EIO; } } static int get_ept_level(void) { return VMX_EPT_DEFAULT_GAW + 1; } static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, .hardware_setup = hardware_setup, .hardware_unsetup = hardware_unsetup, .check_processor_compatibility = vmx_check_processor_compat, .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = cpu_has_vmx_virtualize_apic_accesses, .vcpu_create = vmx_create_vcpu, .vcpu_free = vmx_free_vcpu, .vcpu_reset = vmx_vcpu_reset, .prepare_guest_switch = vmx_save_host_state, .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, .set_guest_debug = set_guest_debug, .guest_debug_pre = kvm_guest_debug_pre, .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, .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, .set_cr0 = vmx_set_cr0, .set_cr3 = vmx_set_cr3, .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, .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, .handle_exit = kvm_handle_exit, .skip_emulated_instruction = skip_emulated_instruction, .patch_hypercall = vmx_patch_hypercall, .get_irq = vmx_get_irq, .set_irq = vmx_inject_irq, .queue_exception = vmx_queue_exception, .exception_injected = vmx_exception_injected, .inject_pending_irq = vmx_intr_assist, .inject_pending_vectors = do_interrupt_requests, .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, }; static int __init vmx_init(void) { void *va; int r; vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); if (!vmx_io_bitmap_a) return -ENOMEM; vmx_io_bitmap_b = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); if (!vmx_io_bitmap_b) { r = -ENOMEM; goto out; } vmx_msr_bitmap = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); if (!vmx_msr_bitmap) { r = -ENOMEM; goto out1; } /* * Allow direct access to the PC debug port (it is often used for I/O * delays, but the vmexits simply slow things down). */ va = kmap(vmx_io_bitmap_a); memset(va, 0xff, PAGE_SIZE); clear_bit(0x80, va); kunmap(vmx_io_bitmap_a); va = kmap(vmx_io_bitmap_b); memset(va, 0xff, PAGE_SIZE); kunmap(vmx_io_bitmap_b); va = kmap(vmx_msr_bitmap); memset(va, 0xff, PAGE_SIZE); kunmap(vmx_msr_bitmap); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE); if (r) goto out2; vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_FS_BASE); vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_GS_BASE); vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_CS); vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP); vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP); if (vm_need_ept()) { bypass_guest_pf = 0; kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK | VMX_EPT_WRITABLE_MASK | VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT); kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull, VMX_EPT_EXECUTABLE_MASK); kvm_enable_tdp(); } else kvm_disable_tdp(); if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); ept_sync_global(); return 0; out2: __free_page(vmx_msr_bitmap); out1: __free_page(vmx_io_bitmap_b); out: __free_page(vmx_io_bitmap_a); return r; } static void __exit vmx_exit(void) { __free_page(vmx_msr_bitmap); __free_page(vmx_io_bitmap_b); __free_page(vmx_io_bitmap_a); kvm_exit(); } module_init(vmx_init) module_exit(vmx_exit)