diff options
Diffstat (limited to 'arch/x86/kvm/svm.c')
-rw-r--r-- | arch/x86/kvm/svm.c | 1725 |
1 files changed, 1725 insertions, 0 deletions
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c new file mode 100644 index 000000000000..3d4b71a94440 --- /dev/null +++ b/arch/x86/kvm/svm.c @@ -0,0 +1,1725 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#include <linux/kvm_host.h> + +#include "kvm_svm.h" +#include "irq.h" +#include "mmu.h" + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/vmalloc.h> +#include <linux/highmem.h> +#include <linux/sched.h> + +#include <asm/desc.h> + +MODULE_AUTHOR("Qumranet"); +MODULE_LICENSE("GPL"); + +#define IOPM_ALLOC_ORDER 2 +#define MSRPM_ALLOC_ORDER 1 + +#define DB_VECTOR 1 +#define UD_VECTOR 6 +#define GP_VECTOR 13 + +#define DR7_GD_MASK (1 << 13) +#define DR6_BD_MASK (1 << 13) + +#define SEG_TYPE_LDT 2 +#define SEG_TYPE_BUSY_TSS16 3 + +#define SVM_FEATURE_NPT (1 << 0) +#define SVM_FEATURE_LBRV (1 << 1) +#define SVM_DEATURE_SVML (1 << 2) + +static void kvm_reput_irq(struct vcpu_svm *svm); + +static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) +{ + return container_of(vcpu, struct vcpu_svm, vcpu); +} + +unsigned long iopm_base; +unsigned long msrpm_base; + +struct kvm_ldttss_desc { + u16 limit0; + u16 base0; + unsigned base1 : 8, type : 5, dpl : 2, p : 1; + unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; + u32 base3; + u32 zero1; +} __attribute__((packed)); + +struct svm_cpu_data { + int cpu; + + u64 asid_generation; + u32 max_asid; + u32 next_asid; + struct kvm_ldttss_desc *tss_desc; + + struct page *save_area; +}; + +static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); +static uint32_t svm_features; + +struct svm_init_data { + int cpu; + int r; +}; + +static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; + +#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges) +#define MSRS_RANGE_SIZE 2048 +#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) + +#define MAX_INST_SIZE 15 + +static inline u32 svm_has(u32 feat) +{ + return svm_features & feat; +} + +static inline u8 pop_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); + return irq; +} + +static inline void push_irq(struct kvm_vcpu *vcpu, u8 irq) +{ + set_bit(irq, vcpu->arch.irq_pending); + set_bit(irq / BITS_PER_LONG, &vcpu->arch.irq_summary); +} + +static inline void clgi(void) +{ + asm volatile (SVM_CLGI); +} + +static inline void stgi(void) +{ + asm volatile (SVM_STGI); +} + +static inline void invlpga(unsigned long addr, u32 asid) +{ + asm volatile (SVM_INVLPGA :: "a"(addr), "c"(asid)); +} + +static inline unsigned long kvm_read_cr2(void) +{ + unsigned long cr2; + + asm volatile ("mov %%cr2, %0" : "=r" (cr2)); + return cr2; +} + +static inline void kvm_write_cr2(unsigned long val) +{ + asm volatile ("mov %0, %%cr2" :: "r" (val)); +} + +static inline unsigned long read_dr6(void) +{ + unsigned long dr6; + + asm volatile ("mov %%dr6, %0" : "=r" (dr6)); + return dr6; +} + +static inline void write_dr6(unsigned long val) +{ + asm volatile ("mov %0, %%dr6" :: "r" (val)); +} + +static inline unsigned long read_dr7(void) +{ + unsigned long dr7; + + asm volatile ("mov %%dr7, %0" : "=r" (dr7)); + return dr7; +} + +static inline void write_dr7(unsigned long val) +{ + asm volatile ("mov %0, %%dr7" :: "r" (val)); +} + +static inline void force_new_asid(struct kvm_vcpu *vcpu) +{ + to_svm(vcpu)->asid_generation--; +} + +static inline void flush_guest_tlb(struct kvm_vcpu *vcpu) +{ + force_new_asid(vcpu); +} + +static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + + to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK; + vcpu->arch.shadow_efer = efer; +} + +static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, + bool has_error_code, u32 error_code) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.event_inj = nr + | SVM_EVTINJ_VALID + | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) + | SVM_EVTINJ_TYPE_EXEPT; + svm->vmcb->control.event_inj_err = error_code; +} + +static bool svm_exception_injected(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return !(svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID); +} + +static int is_external_interrupt(u32 info) +{ + info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; + return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); +} + +static void skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!svm->next_rip) { + printk(KERN_DEBUG "%s: NOP\n", __FUNCTION__); + return; + } + if (svm->next_rip - svm->vmcb->save.rip > MAX_INST_SIZE) + printk(KERN_ERR "%s: ip 0x%llx next 0x%llx\n", + __FUNCTION__, + svm->vmcb->save.rip, + svm->next_rip); + + vcpu->arch.rip = svm->vmcb->save.rip = svm->next_rip; + svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; + + vcpu->arch.interrupt_window_open = 1; +} + +static int has_svm(void) +{ + uint32_t eax, ebx, ecx, edx; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + printk(KERN_INFO "has_svm: not amd\n"); + return 0; + } + + cpuid(0x80000000, &eax, &ebx, &ecx, &edx); + if (eax < SVM_CPUID_FUNC) { + printk(KERN_INFO "has_svm: can't execute cpuid_8000000a\n"); + return 0; + } + + cpuid(0x80000001, &eax, &ebx, &ecx, &edx); + if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) { + printk(KERN_DEBUG "has_svm: svm not available\n"); + return 0; + } + return 1; +} + +static void svm_hardware_disable(void *garbage) +{ + struct svm_cpu_data *svm_data + = per_cpu(svm_data, raw_smp_processor_id()); + + if (svm_data) { + uint64_t efer; + + wrmsrl(MSR_VM_HSAVE_PA, 0); + rdmsrl(MSR_EFER, efer); + wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK); + per_cpu(svm_data, raw_smp_processor_id()) = NULL; + __free_page(svm_data->save_area); + kfree(svm_data); + } +} + +static void svm_hardware_enable(void *garbage) +{ + + struct svm_cpu_data *svm_data; + uint64_t efer; +#ifdef CONFIG_X86_64 + struct desc_ptr gdt_descr; +#else + struct desc_ptr gdt_descr; +#endif + struct desc_struct *gdt; + int me = raw_smp_processor_id(); + + if (!has_svm()) { + printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); + return; + } + svm_data = per_cpu(svm_data, me); + + if (!svm_data) { + printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", + me); + return; + } + + svm_data->asid_generation = 1; + svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; + svm_data->next_asid = svm_data->max_asid + 1; + svm_features = cpuid_edx(SVM_CPUID_FUNC); + + asm volatile ("sgdt %0" : "=m"(gdt_descr)); + gdt = (struct desc_struct *)gdt_descr.address; + svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); + + rdmsrl(MSR_EFER, efer); + wrmsrl(MSR_EFER, efer | MSR_EFER_SVME_MASK); + + wrmsrl(MSR_VM_HSAVE_PA, + page_to_pfn(svm_data->save_area) << PAGE_SHIFT); +} + +static int svm_cpu_init(int cpu) +{ + struct svm_cpu_data *svm_data; + int r; + + svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); + if (!svm_data) + return -ENOMEM; + svm_data->cpu = cpu; + svm_data->save_area = alloc_page(GFP_KERNEL); + r = -ENOMEM; + if (!svm_data->save_area) + goto err_1; + + per_cpu(svm_data, cpu) = svm_data; + + return 0; + +err_1: + kfree(svm_data); + return r; + +} + +static void set_msr_interception(u32 *msrpm, unsigned msr, + int read, int write) +{ + int i; + + for (i = 0; i < NUM_MSR_MAPS; i++) { + if (msr >= msrpm_ranges[i] && + msr < msrpm_ranges[i] + MSRS_IN_RANGE) { + u32 msr_offset = (i * MSRS_IN_RANGE + msr - + msrpm_ranges[i]) * 2; + + u32 *base = msrpm + (msr_offset / 32); + u32 msr_shift = msr_offset % 32; + u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1); + *base = (*base & ~(0x3 << msr_shift)) | + (mask << msr_shift); + return; + } + } + BUG(); +} + +static __init int svm_hardware_setup(void) +{ + int cpu; + struct page *iopm_pages; + struct page *msrpm_pages; + void *iopm_va, *msrpm_va; + int r; + + iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER); + + if (!iopm_pages) + return -ENOMEM; + + iopm_va = page_address(iopm_pages); + memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); + clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */ + iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + + + msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + + r = -ENOMEM; + if (!msrpm_pages) + goto err_1; + + msrpm_va = page_address(msrpm_pages); + memset(msrpm_va, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + msrpm_base = page_to_pfn(msrpm_pages) << PAGE_SHIFT; + +#ifdef CONFIG_X86_64 + set_msr_interception(msrpm_va, MSR_GS_BASE, 1, 1); + set_msr_interception(msrpm_va, MSR_FS_BASE, 1, 1); + set_msr_interception(msrpm_va, MSR_KERNEL_GS_BASE, 1, 1); + set_msr_interception(msrpm_va, MSR_LSTAR, 1, 1); + set_msr_interception(msrpm_va, MSR_CSTAR, 1, 1); + set_msr_interception(msrpm_va, MSR_SYSCALL_MASK, 1, 1); +#endif + set_msr_interception(msrpm_va, MSR_K6_STAR, 1, 1); + set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_CS, 1, 1); + set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_ESP, 1, 1); + set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_EIP, 1, 1); + + for_each_online_cpu(cpu) { + r = svm_cpu_init(cpu); + if (r) + goto err_2; + } + return 0; + +err_2: + __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); + msrpm_base = 0; +err_1: + __free_pages(iopm_pages, IOPM_ALLOC_ORDER); + iopm_base = 0; + return r; +} + +static __exit void svm_hardware_unsetup(void) +{ + __free_pages(pfn_to_page(msrpm_base >> PAGE_SHIFT), MSRPM_ALLOC_ORDER); + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); + iopm_base = msrpm_base = 0; +} + +static void init_seg(struct vmcb_seg *seg) +{ + seg->selector = 0; + seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK | + SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ + seg->limit = 0xffff; + seg->base = 0; +} + +static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) +{ + seg->selector = 0; + seg->attrib = SVM_SELECTOR_P_MASK | type; + seg->limit = 0xffff; + seg->base = 0; +} + +static void init_vmcb(struct vmcb *vmcb) +{ + struct vmcb_control_area *control = &vmcb->control; + struct vmcb_save_area *save = &vmcb->save; + + control->intercept_cr_read = INTERCEPT_CR0_MASK | + INTERCEPT_CR3_MASK | + INTERCEPT_CR4_MASK | + INTERCEPT_CR8_MASK; + + control->intercept_cr_write = INTERCEPT_CR0_MASK | + INTERCEPT_CR3_MASK | + INTERCEPT_CR4_MASK | + INTERCEPT_CR8_MASK; + + control->intercept_dr_read = INTERCEPT_DR0_MASK | + INTERCEPT_DR1_MASK | + INTERCEPT_DR2_MASK | + INTERCEPT_DR3_MASK; + + control->intercept_dr_write = INTERCEPT_DR0_MASK | + INTERCEPT_DR1_MASK | + INTERCEPT_DR2_MASK | + INTERCEPT_DR3_MASK | + INTERCEPT_DR5_MASK | + INTERCEPT_DR7_MASK; + + control->intercept_exceptions = (1 << PF_VECTOR) | + (1 << UD_VECTOR); + + + control->intercept = (1ULL << INTERCEPT_INTR) | + (1ULL << INTERCEPT_NMI) | + (1ULL << INTERCEPT_SMI) | + /* + * selective cr0 intercept bug? + * 0: 0f 22 d8 mov %eax,%cr3 + * 3: 0f 20 c0 mov %cr0,%eax + * 6: 0d 00 00 00 80 or $0x80000000,%eax + * b: 0f 22 c0 mov %eax,%cr0 + * set cr3 ->interception + * get cr0 ->interception + * set cr0 -> no interception + */ + /* (1ULL << INTERCEPT_SELECTIVE_CR0) | */ + (1ULL << INTERCEPT_CPUID) | + (1ULL << INTERCEPT_INVD) | + (1ULL << INTERCEPT_HLT) | + (1ULL << INTERCEPT_INVLPGA) | + (1ULL << INTERCEPT_IOIO_PROT) | + (1ULL << INTERCEPT_MSR_PROT) | + (1ULL << INTERCEPT_TASK_SWITCH) | + (1ULL << INTERCEPT_SHUTDOWN) | + (1ULL << INTERCEPT_VMRUN) | + (1ULL << INTERCEPT_VMMCALL) | + (1ULL << INTERCEPT_VMLOAD) | + (1ULL << INTERCEPT_VMSAVE) | + (1ULL << INTERCEPT_STGI) | + (1ULL << INTERCEPT_CLGI) | + (1ULL << INTERCEPT_SKINIT) | + (1ULL << INTERCEPT_WBINVD) | + (1ULL << INTERCEPT_MONITOR) | + (1ULL << INTERCEPT_MWAIT); + + control->iopm_base_pa = iopm_base; + control->msrpm_base_pa = msrpm_base; + control->tsc_offset = 0; + control->int_ctl = V_INTR_MASKING_MASK; + + init_seg(&save->es); + init_seg(&save->ss); + init_seg(&save->ds); + init_seg(&save->fs); + init_seg(&save->gs); + + save->cs.selector = 0xf000; + /* Executable/Readable Code Segment */ + save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK | + SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK; + save->cs.limit = 0xffff; + /* + * cs.base should really be 0xffff0000, but vmx can't handle that, so + * be consistent with it. + * + * Replace when we have real mode working for vmx. + */ + save->cs.base = 0xf0000; + + save->gdtr.limit = 0xffff; + save->idtr.limit = 0xffff; + + init_sys_seg(&save->ldtr, SEG_TYPE_LDT); + init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); + + save->efer = MSR_EFER_SVME_MASK; + save->dr6 = 0xffff0ff0; + save->dr7 = 0x400; + save->rflags = 2; + save->rip = 0x0000fff0; + + /* + * cr0 val on cpu init should be 0x60000010, we enable cpu + * cache by default. the orderly way is to enable cache in bios. + */ + save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP; + save->cr4 = X86_CR4_PAE; + /* rdx = ?? */ +} + +static int svm_vcpu_reset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + init_vmcb(svm->vmcb); + + if (vcpu->vcpu_id != 0) { + svm->vmcb->save.rip = 0; + svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12; + svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8; + } + + return 0; +} + +static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) +{ + struct vcpu_svm *svm; + struct page *page; + int err; + + svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); + if (!svm) { + err = -ENOMEM; + goto out; + } + + err = kvm_vcpu_init(&svm->vcpu, kvm, id); + if (err) + goto free_svm; + + page = alloc_page(GFP_KERNEL); + if (!page) { + err = -ENOMEM; + goto uninit; + } + + svm->vmcb = page_address(page); + clear_page(svm->vmcb); + svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; + svm->asid_generation = 0; + memset(svm->db_regs, 0, sizeof(svm->db_regs)); + init_vmcb(svm->vmcb); + + fx_init(&svm->vcpu); + svm->vcpu.fpu_active = 1; + svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; + if (svm->vcpu.vcpu_id == 0) + svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + + return &svm->vcpu; + +uninit: + kvm_vcpu_uninit(&svm->vcpu); +free_svm: + kmem_cache_free(kvm_vcpu_cache, svm); +out: + return ERR_PTR(err); +} + +static void svm_free_vcpu(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); + kvm_vcpu_uninit(vcpu); + kmem_cache_free(kvm_vcpu_cache, svm); +} + +static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int i; + + if (unlikely(cpu != vcpu->cpu)) { + u64 tsc_this, delta; + + /* + * Make sure that the guest sees a monotonically + * increasing TSC. + */ + rdtscll(tsc_this); + delta = vcpu->arch.host_tsc - tsc_this; + svm->vmcb->control.tsc_offset += delta; + vcpu->cpu = cpu; + kvm_migrate_apic_timer(vcpu); + } + + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); +} + +static void svm_vcpu_put(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int i; + + ++vcpu->stat.host_state_reload; + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) + wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + + rdtscll(vcpu->arch.host_tsc); +} + +static void svm_vcpu_decache(struct kvm_vcpu *vcpu) +{ +} + +static void svm_cache_regs(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; + vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; + vcpu->arch.rip = svm->vmcb->save.rip; +} + +static void svm_decache_regs(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.rip; +} + +static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) +{ + return to_svm(vcpu)->vmcb->save.rflags; +} + +static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + to_svm(vcpu)->vmcb->save.rflags = rflags; +} + +static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) +{ + struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; + + switch (seg) { + case VCPU_SREG_CS: return &save->cs; + case VCPU_SREG_DS: return &save->ds; + case VCPU_SREG_ES: return &save->es; + case VCPU_SREG_FS: return &save->fs; + case VCPU_SREG_GS: return &save->gs; + case VCPU_SREG_SS: return &save->ss; + case VCPU_SREG_TR: return &save->tr; + case VCPU_SREG_LDTR: return &save->ldtr; + } + BUG(); + return NULL; +} + +static u64 svm_get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + struct vmcb_seg *s = svm_seg(vcpu, seg); + + return s->base; +} + +static void svm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct vmcb_seg *s = svm_seg(vcpu, seg); + + var->base = s->base; + var->limit = s->limit; + var->selector = s->selector; + var->type = s->attrib & SVM_SELECTOR_TYPE_MASK; + var->s = (s->attrib >> SVM_SELECTOR_S_SHIFT) & 1; + var->dpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; + var->present = (s->attrib >> SVM_SELECTOR_P_SHIFT) & 1; + var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1; + var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1; + var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; + var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; + var->unusable = !var->present; +} + +static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + dt->limit = svm->vmcb->save.idtr.limit; + dt->base = svm->vmcb->save.idtr.base; +} + +static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.idtr.limit = dt->limit; + svm->vmcb->save.idtr.base = dt->base ; +} + +static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + dt->limit = svm->vmcb->save.gdtr.limit; + dt->base = svm->vmcb->save.gdtr.base; +} + +static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.gdtr.limit = dt->limit; + svm->vmcb->save.gdtr.base = dt->base ; +} + +static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) +{ +} + +static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + struct vcpu_svm *svm = to_svm(vcpu); + +#ifdef CONFIG_X86_64 + if (vcpu->arch.shadow_efer & EFER_LME) { + if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { + vcpu->arch.shadow_efer |= EFER_LMA; + svm->vmcb->save.efer |= EFER_LMA | EFER_LME; + } + + if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) { + vcpu->arch.shadow_efer &= ~EFER_LMA; + svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); + } + } +#endif + if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) { + svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + vcpu->fpu_active = 1; + } + + vcpu->arch.cr0 = cr0; + cr0 |= X86_CR0_PG | X86_CR0_WP; + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + svm->vmcb->save.cr0 = cr0; +} + +static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + vcpu->arch.cr4 = cr4; + to_svm(vcpu)->vmcb->save.cr4 = cr4 | X86_CR4_PAE; +} + +static void svm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_seg *s = svm_seg(vcpu, seg); + + s->base = var->base; + s->limit = var->limit; + s->selector = var->selector; + if (var->unusable) + s->attrib = 0; + else { + s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); + s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; + s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; + s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT; + s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; + s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; + s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; + s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; + } + if (seg == VCPU_SREG_CS) + svm->vmcb->save.cpl + = (svm->vmcb->save.cs.attrib + >> SVM_SELECTOR_DPL_SHIFT) & 3; + +} + +/* FIXME: + + svm(vcpu)->vmcb->control.int_ctl &= ~V_TPR_MASK; + svm(vcpu)->vmcb->control.int_ctl |= (sregs->cr8 & V_TPR_MASK); + +*/ + +static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +{ + return -EOPNOTSUPP; +} + +static int svm_get_irq(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 exit_int_info = svm->vmcb->control.exit_int_info; + + if (is_external_interrupt(exit_int_info)) + return exit_int_info & SVM_EVTINJ_VEC_MASK; + return -1; +} + +static void load_host_msrs(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); +#endif +} + +static void save_host_msrs(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_X86_64 + rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); +#endif +} + +static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data) +{ + if (svm_data->next_asid > svm_data->max_asid) { + ++svm_data->asid_generation; + svm_data->next_asid = 1; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; + } + + svm->vcpu.cpu = svm_data->cpu; + svm->asid_generation = svm_data->asid_generation; + svm->vmcb->control.asid = svm_data->next_asid++; +} + +static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) +{ + return to_svm(vcpu)->db_regs[dr]; +} + +static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, + int *exception) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + *exception = 0; + + if (svm->vmcb->save.dr7 & DR7_GD_MASK) { + svm->vmcb->save.dr7 &= ~DR7_GD_MASK; + svm->vmcb->save.dr6 |= DR6_BD_MASK; + *exception = DB_VECTOR; + return; + } + + switch (dr) { + case 0 ... 3: + svm->db_regs[dr] = value; + return; + case 4 ... 5: + if (vcpu->arch.cr4 & X86_CR4_DE) { + *exception = UD_VECTOR; + return; + } + case 7: { + if (value & ~((1ULL << 32) - 1)) { + *exception = GP_VECTOR; + return; + } + svm->vmcb->save.dr7 = value; + return; + } + default: + printk(KERN_DEBUG "%s: unexpected dr %u\n", + __FUNCTION__, dr); + *exception = UD_VECTOR; + return; + } +} + +static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 exit_int_info = svm->vmcb->control.exit_int_info; + struct kvm *kvm = svm->vcpu.kvm; + u64 fault_address; + u32 error_code; + + if (!irqchip_in_kernel(kvm) && + is_external_interrupt(exit_int_info)) + push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK); + + fault_address = svm->vmcb->control.exit_info_2; + error_code = svm->vmcb->control.exit_info_1; + return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); +} + +static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + int er; + + er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0); + if (er != EMULATE_DONE) + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + +static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); + if (!(svm->vcpu.arch.cr0 & X86_CR0_TS)) + svm->vmcb->save.cr0 &= ~X86_CR0_TS; + svm->vcpu.fpu_active = 1; + + return 1; +} + +static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + /* + * VMCB is undefined after a SHUTDOWN intercept + * so reinitialize it. + */ + clear_page(svm->vmcb); + init_vmcb(svm->vmcb); + + kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + return 0; +} + +static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ + int size, down, in, string, rep; + unsigned port; + + ++svm->vcpu.stat.io_exits; + + svm->next_rip = svm->vmcb->control.exit_info_2; + + string = (io_info & SVM_IOIO_STR_MASK) != 0; + + if (string) { + if (emulate_instruction(&svm->vcpu, + kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + return 0; + return 1; + } + + in = (io_info & SVM_IOIO_TYPE_MASK) != 0; + port = io_info >> 16; + size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; + rep = (io_info & SVM_IOIO_REP_MASK) != 0; + down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0; + + return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); +} + +static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + return 1; +} + +static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->next_rip = svm->vmcb->save.rip + 1; + skip_emulated_instruction(&svm->vcpu); + return kvm_emulate_halt(&svm->vcpu); +} + +static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->next_rip = svm->vmcb->save.rip + 3; + skip_emulated_instruction(&svm->vcpu); + kvm_emulate_hypercall(&svm->vcpu); + return 1; +} + +static int invalid_op_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + +static int task_switch_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + pr_unimpl(&svm->vcpu, "%s: task switch is unsupported\n", __FUNCTION__); + kvm_run->exit_reason = KVM_EXIT_UNKNOWN; + return 0; +} + +static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + svm->next_rip = svm->vmcb->save.rip + 2; + kvm_emulate_cpuid(&svm->vcpu); + return 1; +} + +static int emulate_on_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE) + pr_unimpl(&svm->vcpu, "%s: failed\n", __FUNCTION__); + return 1; +} + +static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + emulate_instruction(&svm->vcpu, NULL, 0, 0, 0); + if (irqchip_in_kernel(svm->vcpu.kvm)) + return 1; + kvm_run->exit_reason = KVM_EXIT_SET_TPR; + return 0; +} + +static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + switch (ecx) { + case MSR_IA32_TIME_STAMP_COUNTER: { + u64 tsc; + + rdtscll(tsc); + *data = svm->vmcb->control.tsc_offset + tsc; + break; + } + case MSR_K6_STAR: + *data = svm->vmcb->save.star; + break; +#ifdef CONFIG_X86_64 + case MSR_LSTAR: + *data = svm->vmcb->save.lstar; + break; + case MSR_CSTAR: + *data = svm->vmcb->save.cstar; + break; + case MSR_KERNEL_GS_BASE: + *data = svm->vmcb->save.kernel_gs_base; + break; + case MSR_SYSCALL_MASK: + *data = svm->vmcb->save.sfmask; + break; +#endif + case MSR_IA32_SYSENTER_CS: + *data = svm->vmcb->save.sysenter_cs; + break; + case MSR_IA32_SYSENTER_EIP: + *data = svm->vmcb->save.sysenter_eip; + break; + case MSR_IA32_SYSENTER_ESP: + *data = svm->vmcb->save.sysenter_esp; + break; + default: + return kvm_get_msr_common(vcpu, ecx, data); + } + return 0; +} + +static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u64 data; + + if (svm_get_msr(&svm->vcpu, ecx, &data)) + kvm_inject_gp(&svm->vcpu, 0); + else { + svm->vmcb->save.rax = data & 0xffffffff; + svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; + svm->next_rip = svm->vmcb->save.rip + 2; + skip_emulated_instruction(&svm->vcpu); + } + return 1; +} + +static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + switch (ecx) { + case MSR_IA32_TIME_STAMP_COUNTER: { + u64 tsc; + + rdtscll(tsc); + svm->vmcb->control.tsc_offset = data - tsc; + break; + } + case MSR_K6_STAR: + svm->vmcb->save.star = data; + break; +#ifdef CONFIG_X86_64 + case MSR_LSTAR: + svm->vmcb->save.lstar = data; + break; + case MSR_CSTAR: + svm->vmcb->save.cstar = data; + break; + case MSR_KERNEL_GS_BASE: + svm->vmcb->save.kernel_gs_base = data; + break; + case MSR_SYSCALL_MASK: + svm->vmcb->save.sfmask = data; + break; +#endif + case MSR_IA32_SYSENTER_CS: + svm->vmcb->save.sysenter_cs = data; + break; + case MSR_IA32_SYSENTER_EIP: + svm->vmcb->save.sysenter_eip = data; + break; + case MSR_IA32_SYSENTER_ESP: + svm->vmcb->save.sysenter_esp = data; + break; + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + /* + * only support writing 0 to the performance counters for now + * to make Windows happy. Should be replaced by a real + * performance counter emulation later. + */ + if (data != 0) + goto unhandled; + break; + default: + unhandled: + return kvm_set_msr_common(vcpu, ecx, data); + } + return 0; +} + +static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u64 data = (svm->vmcb->save.rax & -1u) + | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + svm->next_rip = svm->vmcb->save.rip + 2; + if (svm_set_msr(&svm->vcpu, ecx, data)) + kvm_inject_gp(&svm->vcpu, 0); + else + skip_emulated_instruction(&svm->vcpu); + return 1; +} + +static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (svm->vmcb->control.exit_info_1) + return wrmsr_interception(svm, kvm_run); + else + return rdmsr_interception(svm, kvm_run); +} + +static int interrupt_window_interception(struct vcpu_svm *svm, + struct kvm_run *kvm_run) +{ + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + /* + * If the user space waits to inject interrupts, exit as soon as + * possible + */ + if (kvm_run->request_interrupt_window && + !svm->vcpu.arch.irq_summary) { + ++svm->vcpu.stat.irq_window_exits; + kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; + return 0; + } + + return 1; +} + +static int (*svm_exit_handlers[])(struct vcpu_svm *svm, + struct kvm_run *kvm_run) = { + [SVM_EXIT_READ_CR0] = emulate_on_interception, + [SVM_EXIT_READ_CR3] = emulate_on_interception, + [SVM_EXIT_READ_CR4] = emulate_on_interception, + [ |