diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
-rw-r--r-- | arch/x86/kvm/x86.c | 232 |
1 files changed, 41 insertions, 191 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c4da7fbabe01..f1f8ff2f1fa2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -39,7 +39,6 @@ #include <asm/uaccess.h> #include <asm/msr.h> #include <asm/desc.h> -#include <asm/mtrr.h> #define MAX_IO_MSRS 256 #define CR0_RESERVED_BITS \ @@ -68,8 +67,6 @@ static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL; static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -89,7 +86,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, - { "request_nmi", VCPU_STAT(request_nmi_exits) }, { "irq_exits", VCPU_STAT(irq_exits) }, { "host_state_reload", VCPU_STAT(host_state_reload) }, { "efer_reload", VCPU_STAT(efer_reload) }, @@ -97,7 +93,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "insn_emulation", VCPU_STAT(insn_emulation) }, { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, { "irq_injections", VCPU_STAT(irq_injections) }, - { "nmi_injections", VCPU_STAT(nmi_injections) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, @@ -106,7 +101,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_recycled", VM_STAT(mmu_recycled) }, { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, - { "mmu_unsync_global", VM_STAT(mmu_unsync_global) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, { "largepages", VM_STAT(lpages) }, { NULL } @@ -174,7 +168,6 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, u32 error_code) { ++vcpu->stat.pf_guest; - if (vcpu->arch.exception.pending) { if (vcpu->arch.exception.nr == PF_VECTOR) { printk(KERN_DEBUG "kvm: inject_page_fault:" @@ -319,7 +312,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) kvm_x86_ops->set_cr0(vcpu, cr0); vcpu->arch.cr0 = cr0; - kvm_mmu_sync_global(vcpu); kvm_mmu_reset_context(vcpu); return; } @@ -363,7 +355,6 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } kvm_x86_ops->set_cr4(vcpu, cr4); vcpu->arch.cr4 = cr4; - kvm_mmu_sync_global(vcpu); kvm_mmu_reset_context(vcpu); } EXPORT_SYMBOL_GPL(kvm_set_cr4); @@ -444,11 +435,6 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. @@ -463,7 +449,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA + MSR_IA32_PERF_STATUS, }; static unsigned num_msrs_to_save; @@ -488,17 +474,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) return; } - if (efer & EFER_SVME) { - struct kvm_cpuid_entry2 *feat; - - feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) { - printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n"); - kvm_inject_gp(vcpu, 0); - return; - } - } - kvm_x86_ops->set_efer(vcpu, efer); efer &= ~EFER_LMA; @@ -673,38 +648,10 @@ static bool msr_mtrr_valid(unsigned msr) static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - if (!msr_mtrr_valid(msr)) return 1; - if (msr == MSR_MTRRdefType) { - vcpu->arch.mtrr_state.def_type = data; - vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; - } else if (msr == MSR_MTRRfix64K_00000) - p[0] = data; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - p[1 + msr - MSR_MTRRfix16K_80000] = data; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - p[3 + msr - MSR_MTRRfix4K_C0000] = data; - else if (msr == MSR_IA32_CR_PAT) - vcpu->arch.pat = data; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pt = data; - } - - kvm_mmu_reset_context(vcpu); + vcpu->arch.mtrr[msr - 0x200] = data; return 0; } @@ -800,37 +747,10 @@ int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - if (!msr_mtrr_valid(msr)) return 1; - if (msr == MSR_MTRRdefType) - *pdata = vcpu->arch.mtrr_state.def_type + - (vcpu->arch.mtrr_state.enabled << 10); - else if (msr == MSR_MTRRfix64K_00000) - *pdata = p[0]; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; - else if (msr == MSR_IA32_CR_PAT) - *pdata = vcpu->arch.pat; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pdata = *pt; - } - + *pdata = vcpu->arch.mtrr[msr - 0x200]; return 0; } @@ -983,6 +903,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IRQCHIP: case KVM_CAP_HLT: case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: + case KVM_CAP_USER_MEMORY: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: case KVM_CAP_CLOCKSOURCE: @@ -1197,6 +1118,11 @@ out: return r; } +static inline u32 bit(int bitno) +{ + return 1 << (bitno & 31); +} + static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, u32 index) { @@ -1239,8 +1165,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, const u32 kvm_supported_word3_x86_features = bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16); const u32 kvm_supported_word6_x86_features = - bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY) | - bit(X86_FEATURE_SVM); + bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY); /* all func 2 cpuid_count() should be called on the same cpu */ get_cpu(); @@ -1263,7 +1188,6 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, int t, times = entry->eax & 0xff; entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; for (t = 1; t < times && *nent < maxnent; ++t) { do_cpuid_1_ent(&entry[t], function, 0); entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; @@ -1294,7 +1218,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* read more entries until level_type is zero */ for (i = 1; *nent < maxnent; ++i) { - level_type = entry[i - 1].ecx & 0xff00; + level_type = entry[i - 1].ecx & 0xff; if (!level_type) break; do_cpuid_1_ent(&entry[i], function, i); @@ -1394,15 +1318,6 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, return 0; } -static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) -{ - vcpu_load(vcpu); - kvm_inject_nmi(vcpu); - vcpu_put(vcpu); - - return 0; -} - static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { @@ -1462,13 +1377,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = 0; break; } - case KVM_NMI: { - r = kvm_vcpu_ioctl_nmi(vcpu); - if (r) - goto out; - r = 0; - break; - } case KVM_SET_CPUID: { struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; @@ -2060,7 +1968,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); if (ret < 0) return 0; - kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1); + kvm_mmu_pte_write(vcpu, gpa, val, bytes); return 1; } @@ -2496,6 +2404,8 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, val = kvm_register_read(vcpu, VCPU_REGS_RAX); memcpy(vcpu->arch.pio_data, &val, 4); + kvm_x86_ops->skip_emulated_instruction(vcpu); + pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in); if (pio_dev) { kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data); @@ -2631,7 +2541,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_nonpresent_ptes(0ull, 0ull); kvm_mmu_set_base_ptes(PT_PRESENT_MASK); kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, - PT_DIRTY_MASK, PT64_NX_MASK, 0, 0); + PT_DIRTY_MASK, PT64_NX_MASK, 0); return 0; out: @@ -2819,7 +2729,7 @@ static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; ; j = (j + 1) % nent) { + for (j = i + 1; j == i; j = (j + 1) % nent) { struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; if (ej->function == e->function) { ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; @@ -2844,15 +2754,20 @@ static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, return 1; } -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index) +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) { int i; - struct kvm_cpuid_entry2 *best = NULL; + u32 function, index; + struct kvm_cpuid_entry2 *e, *best; + function = kvm_register_read(vcpu, VCPU_REGS_RAX); + index = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_register_write(vcpu, VCPU_REGS_RAX, 0); + kvm_register_write(vcpu, VCPU_REGS_RBX, 0); + kvm_register_write(vcpu, VCPU_REGS_RCX, 0); + kvm_register_write(vcpu, VCPU_REGS_RDX, 0); + best = NULL; for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - struct kvm_cpuid_entry2 *e; - e = &vcpu->arch.cpuid_entries[i]; if (is_matching_cpuid_entry(e, function, index)) { if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) @@ -2867,22 +2782,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, if (!best || e->function > best->function) best = e; } - - return best; -} - -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) -{ - u32 function, index; - struct kvm_cpuid_entry2 *best; - - function = kvm_register_read(vcpu, VCPU_REGS_RAX); - index = kvm_register_read(vcpu, VCPU_REGS_RCX); - kvm_register_write(vcpu, VCPU_REGS_RAX, 0); - kvm_register_write(vcpu, VCPU_REGS_RBX, 0); - kvm_register_write(vcpu, VCPU_REGS_RCX, 0); - kvm_register_write(vcpu, VCPU_REGS_RDX, 0); - best = kvm_find_cpuid_entry(vcpu, function, index); if (best) { kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); @@ -3002,6 +2901,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } + if (vcpu->guest_debug.enabled) + kvm_x86_ops->guest_debug_pre(vcpu); + vcpu->guest_mode = 1; /* * Make sure that guest_mode assignment won't happen after @@ -3022,34 +2924,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_guest_enter(); - get_debugreg(vcpu->arch.host_dr6, 6); - get_debugreg(vcpu->arch.host_dr7, 7); - if (unlikely(vcpu->arch.switch_db_regs)) { - get_debugreg(vcpu->arch.host_db[0], 0); - get_debugreg(vcpu->arch.host_db[1], 1); - get_debugreg(vcpu->arch.host_db[2], 2); - get_debugreg(vcpu->arch.host_db[3], 3); - - set_debugreg(0, 7); - set_debugreg(vcpu->arch.eff_db[0], 0); - set_debugreg(vcpu->arch.eff_db[1], 1); - set_debugreg(vcpu->arch.eff_db[2], 2); - set_debugreg(vcpu->arch.eff_db[3], 3); - } KVMTRACE_0D(VMENTRY, vcpu, entryexit); kvm_x86_ops->run(vcpu, kvm_run); - if (unlikely(vcpu->arch.switch_db_regs)) { - set_debugreg(0, 7); - set_debugreg(vcpu->arch.host_db[0], 0); - set_debugreg(vcpu->arch.host_db[1], 1); - set_debugreg(vcpu->arch.host_db[2], 2); - set_debugreg(vcpu->arch.host_db[3], 3); - } - set_debugreg(vcpu->arch.host_dr6, 6); - set_debugreg(vcpu->arch.host_dr7, 7); - vcpu->guest_mode = 0; local_irq_enable(); @@ -3095,7 +2973,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) pr_debug("vcpu %d received sipi with vector # %x\n", vcpu->vcpu_id, vcpu->arch.sipi_vector); kvm_lapic_reset(vcpu); - r = kvm_arch_vcpu_reset(vcpu); + r = kvm_x86_ops->vcpu_reset(vcpu); if (r) return r; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -3236,7 +3114,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) /* * Don't leak debug flags in case they were set for guest debugging */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); vcpu_put(vcpu); @@ -3397,9 +3275,9 @@ static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, kvm_desct->padding = 0; } -static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu, - u16 selector, - struct descriptor_table *dtable) +static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu, + u16 selector, + struct descriptor_table *dtable) { if (selector & 1 << 2) { struct kvm_segment kvm_seg; @@ -3424,7 +3302,7 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, struct descriptor_table dtable; u16 index = selector >> 3; - get_segment_descriptor_dtable(vcpu, selector, &dtable); + get_segment_descritptor_dtable(vcpu, selector, &dtable); if (dtable.limit < index * 8 + 7) { kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); @@ -3443,7 +3321,7 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, struct descriptor_table dtable; u16 index = selector >> 3; - get_segment_descriptor_dtable(vcpu, selector, &dtable); + get_segment_descritptor_dtable(vcpu, selector, &dtable); if (dtable.limit < index * 8 + 7) return 1; @@ -3855,32 +3733,15 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg) +int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, + struct kvm_debug_guest *dbg) { - int i, r; + int r; vcpu_load(vcpu); - if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) == - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) { - for (i = 0; i < KVM_NR_DB_REGS; ++i) - vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; - vcpu->arch.switch_db_regs = - (dbg->arch.debugreg[7] & DR7_BP_EN_MASK); - } else { - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; - vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); - } - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); - if (dbg->control & KVM_GUESTDBG_INJECT_DB) - kvm_queue_exception(vcpu, DB_VECTOR); - else if (dbg->control & KVM_GUESTDBG_INJECT_BP) - kvm_queue_exception(vcpu, BP_VECTOR); - vcpu_put(vcpu); return r; @@ -4039,7 +3900,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) /* We do fxsave: this must be aligned. */ BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF); - vcpu->arch.mtrr_state.have_fixed = 1; vcpu_load(vcpu); r = kvm_arch_vcpu_reset(vcpu); if (r == 0) @@ -4065,14 +3925,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) { - vcpu->arch.nmi_pending = false; - vcpu->arch.nmi_injected = false; - - vcpu->arch.switch_db_regs = 0; - memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); - vcpu->arch.dr6 = DR6_FIXED_1; - vcpu->arch.dr7 = DR7_FIXED_1; - return kvm_x86_ops->vcpu_reset(vcpu); } @@ -4160,7 +4012,6 @@ struct kvm *kvm_arch_create_vm(void) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); - INIT_LIST_HEAD(&kvm->arch.oos_global_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ @@ -4197,8 +4048,8 @@ static void kvm_free_vcpus(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - kvm_free_all_assigned_devices(kvm); kvm_iommu_unmap_guest(kvm); + kvm_free_all_assigned_devices(kvm); kvm_free_pit(kvm); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); @@ -4276,8 +4127,7 @@ void kvm_arch_flush_shadow(struct kvm *kvm) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE - || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED - || vcpu->arch.nmi_pending; + || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED; } static void vcpu_kick_intr(void *info) |