diff options
Diffstat (limited to 'arch/x86/kvm/svm.c')
-rw-r--r-- | arch/x86/kvm/svm.c | 1243 |
1 files changed, 839 insertions, 404 deletions
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1d9b338..ce438e0 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -26,7 +26,9 @@ #include <linux/highmem.h> #include <linux/sched.h> #include <linux/ftrace_event.h> +#include <linux/slab.h> +#include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/virtext.h> @@ -43,10 +45,11 @@ MODULE_LICENSE("GPL"); #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_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_PAUSE_FILTER (1 << 10) +#define SVM_FEATURE_NPT (1 << 0) +#define SVM_FEATURE_LBRV (1 << 1) +#define SVM_FEATURE_SVML (1 << 2) +#define SVM_FEATURE_NRIP (1 << 3) +#define SVM_FEATURE_PAUSE_FILTER (1 << 10) #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ @@ -54,6 +57,8 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) +static bool erratum_383_found __read_mostly; + static const u32 host_save_user_msrs[] = { #ifdef CONFIG_X86_64 MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, @@ -69,6 +74,7 @@ struct kvm_vcpu; struct nested_state { struct vmcb *hsave; u64 hsave_msr; + u64 vm_cr_msr; u64 vmcb; /* These are the merged vectors */ @@ -76,6 +82,7 @@ struct nested_state { /* gpa pointers to the real vectors */ u64 vmcb_msrpm; + u64 vmcb_iopm; /* A VMEXIT is required but not yet emulated */ bool exit_required; @@ -90,6 +97,9 @@ struct nested_state { }; +#define MSRPM_OFFSETS 16 +static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; + struct vcpu_svm { struct kvm_vcpu vcpu; struct vmcb *vmcb; @@ -109,13 +119,39 @@ struct vcpu_svm { struct nested_state nested; bool nmi_singlestep; + + unsigned int3_injected; + unsigned long int3_rip; +}; + +#define MSR_INVALID 0xffffffffU + +static struct svm_direct_access_msrs { + u32 index; /* Index of the MSR */ + bool always; /* True if intercept is always on */ +} direct_access_msrs[] = { + { .index = MSR_K6_STAR, .always = true }, + { .index = MSR_IA32_SYSENTER_CS, .always = true }, +#ifdef CONFIG_X86_64 + { .index = MSR_GS_BASE, .always = true }, + { .index = MSR_FS_BASE, .always = true }, + { .index = MSR_KERNEL_GS_BASE, .always = true }, + { .index = MSR_LSTAR, .always = true }, + { .index = MSR_CSTAR, .always = true }, + { .index = MSR_SYSCALL_MASK, .always = true }, +#endif + { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, + { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, + { .index = MSR_IA32_LASTINTFROMIP, .always = false }, + { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_INVALID, .always = false }, }; /* enable NPT for AMD64 and X86 with PAE */ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static bool npt_enabled = true; #else -static bool npt_enabled = false; +static bool npt_enabled; #endif static int npt = 1; @@ -128,6 +164,7 @@ static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); static int nested_svm_exit_handled(struct vcpu_svm *svm); +static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); @@ -162,8 +199,8 @@ static unsigned long iopm_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; + unsigned base1:8, type:5, dpl:2, p:1; + unsigned limit1:4, zero0:3, g:1, base2:8; u32 base3; u32 zero1; } __attribute__((packed)); @@ -193,6 +230,27 @@ static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; #define MSRS_RANGE_SIZE 2048 #define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) +static u32 svm_msrpm_offset(u32 msr) +{ + u32 offset; + int i; + + for (i = 0; i < NUM_MSR_MAPS; i++) { + if (msr < msrpm_ranges[i] || + msr >= msrpm_ranges[i] + MSRS_IN_RANGE) + continue; + + offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */ + offset += (i * MSRS_RANGE_SIZE); /* add range offset */ + + /* Now we have the u8 offset - but need the u32 offset */ + return offset / 4; + } + + /* MSR not in any range */ + return MSR_INVALID; +} + #define MAX_INST_SIZE 15 static inline u32 svm_has(u32 feat) @@ -212,7 +270,7 @@ static inline void stgi(void) static inline void invlpga(unsigned long addr, u32 asid) { - asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid)); + asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid)); } static inline void force_new_asid(struct kvm_vcpu *vcpu) @@ -231,24 +289,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) efer &= ~EFER_LME; to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; - 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); - - /* If we are within a nested VM we'd better #VMEXIT and let the - guest handle the exception */ - if (nested_svm_check_exception(svm, nr, has_error_code, error_code)) - return; - - 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; + vcpu->arch.efer = efer; } static int is_external_interrupt(u32 info) @@ -263,7 +304,7 @@ static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) u32 ret = 0; if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) - ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS; + ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS; return ret & mask; } @@ -282,6 +323,9 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (svm->vmcb->control.next_rip != 0) + svm->next_rip = svm->vmcb->control.next_rip; + if (!svm->next_rip) { if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) != EMULATE_DONE) @@ -296,6 +340,68 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) svm_set_interrupt_shadow(vcpu, 0); } +static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, + bool has_error_code, u32 error_code, + bool reinject) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * If we are within a nested VM we'd better #VMEXIT and let the guest + * handle the exception + */ + if (!reinject && + nested_svm_check_exception(svm, nr, has_error_code, error_code)) + return; + + if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) { + unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu); + + /* + * For guest debugging where we have to reinject #BP if some + * INT3 is guest-owned: + * Emulate nRIP by moving RIP forward. Will fail if injection + * raises a fault that is not intercepted. Still better than + * failing in all cases. + */ + skip_emulated_instruction(&svm->vcpu); + rip = kvm_rip_read(&svm->vcpu); + svm->int3_rip = rip + svm->vmcb->save.cs.base; + svm->int3_injected = rip - old_rip; + } + + 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 void svm_init_erratum_383(void) +{ + u32 low, high; + int err; + u64 val; + + /* Only Fam10h is affected */ + if (boot_cpu_data.x86 != 0x10) + return; + + /* Use _safe variants to not break nested virtualization */ + val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err); + if (err) + return; + + val |= (1ULL << 47); + + low = lower_32_bits(val); + high = upper_32_bits(val); + + native_write_msr_safe(MSR_AMD64_DC_CFG, low, high); + + erratum_383_found = true; +} + static int has_svm(void) { const char *msg; @@ -318,7 +424,7 @@ static int svm_hardware_enable(void *garbage) struct svm_cpu_data *sd; uint64_t efer; - struct descriptor_table gdt_descr; + struct desc_ptr gdt_descr; struct desc_struct *gdt; int me = raw_smp_processor_id(); @@ -343,14 +449,16 @@ static int svm_hardware_enable(void *garbage) sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; - kvm_get_gdt(&gdt_descr); - gdt = (struct desc_struct *)gdt_descr.base; + native_store_gdt(&gdt_descr); + gdt = (struct desc_struct *)gdt_descr.address; sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT); + svm_init_erratum_383(); + return 0; } @@ -390,42 +498,98 @@ err_1: } +static bool valid_msr_intercept(u32 index) +{ + int i; + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) + if (direct_access_msrs[i].index == index) + return true; + + return false; +} + static void set_msr_interception(u32 *msrpm, unsigned msr, int read, int write) { + u8 bit_read, bit_write; + unsigned long tmp; + u32 offset; + + /* + * If this warning triggers extend the direct_access_msrs list at the + * beginning of the file + */ + WARN_ON(!valid_msr_intercept(msr)); + + offset = svm_msrpm_offset(msr); + bit_read = 2 * (msr & 0x0f); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp); + write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp); + + msrpm[offset] = tmp; +} + +static void svm_vcpu_init_msrpm(u32 *msrpm) +{ 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); + memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + if (!direct_access_msrs[i].always) + continue; + + set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1); + } +} + +static void add_msr_offset(u32 offset) +{ + int i; + + for (i = 0; i < MSRPM_OFFSETS; ++i) { + + /* Offset already in list? */ + if (msrpm_offsets[i] == offset) return; - } + + /* Slot used by another offset? */ + if (msrpm_offsets[i] != MSR_INVALID) + continue; + + /* Add offset to list */ + msrpm_offsets[i] = offset; + + return; } + + /* + * If this BUG triggers the msrpm_offsets table has an overflow. Just + * increase MSRPM_OFFSETS in this case. + */ BUG(); } -static void svm_vcpu_init_msrpm(u32 *msrpm) +static void init_msrpm_offsets(void) { - memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); + int i; -#ifdef CONFIG_X86_64 - set_msr_interception(msrpm, MSR_GS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_FS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1); - set_msr_interception(msrpm, MSR_LSTAR, 1, 1); - set_msr_interception(msrpm, MSR_CSTAR, 1, 1); - set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1); -#endif - set_msr_interception(msrpm, MSR_K6_STAR, 1, 1); - set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1); + memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets)); + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + u32 offset; + + offset = svm_msrpm_offset(direct_access_msrs[i].index); + BUG_ON(offset == MSR_INVALID); + + add_msr_offset(offset); + } } static void svm_enable_lbrv(struct vcpu_svm *svm) @@ -466,6 +630,8 @@ static __init int svm_hardware_setup(void) memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + init_msrpm_offsets(); + if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); @@ -522,7 +688,7 @@ 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 */ + SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ seg->limit = 0xffff; seg->base = 0; } @@ -540,25 +706,33 @@ static void init_vmcb(struct vcpu_svm *svm) struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; - control->intercept_cr_read = INTERCEPT_CR0_MASK | + svm->vcpu.fpu_active = 1; + + control->intercept_cr_read = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | INTERCEPT_CR4_MASK; - control->intercept_cr_write = INTERCEPT_CR0_MASK | + control->intercept_cr_write = INTERCEPT_CR0_MASK | INTERCEPT_CR3_MASK | INTERCEPT_CR4_MASK | INTERCEPT_CR8_MASK; - control->intercept_dr_read = INTERCEPT_DR0_MASK | + control->intercept_dr_read = INTERCEPT_DR0_MASK | INTERCEPT_DR1_MASK | INTERCEPT_DR2_MASK | - INTERCEPT_DR3_MASK; + INTERCEPT_DR3_MASK | + INTERCEPT_DR4_MASK | + INTERCEPT_DR5_MASK | + INTERCEPT_DR6_MASK | + INTERCEPT_DR7_MASK; - control->intercept_dr_write = INTERCEPT_DR0_MASK | + control->intercept_dr_write = INTERCEPT_DR0_MASK | INTERCEPT_DR1_MASK | INTERCEPT_DR2_MASK | INTERCEPT_DR3_MASK | + INTERCEPT_DR4_MASK | INTERCEPT_DR5_MASK | + INTERCEPT_DR6_MASK | INTERCEPT_DR7_MASK; control->intercept_exceptions = (1 << PF_VECTOR) | @@ -566,9 +740,10 @@ static void init_vmcb(struct vcpu_svm *svm) (1 << MC_VECTOR); - control->intercept = (1ULL << INTERCEPT_INTR) | + control->intercept = (1ULL << INTERCEPT_INTR) | (1ULL << INTERCEPT_NMI) | (1ULL << INTERCEPT_SMI) | + (1ULL << INTERCEPT_SELECTIVE_CR0) | (1ULL << INTERCEPT_CPUID) | (1ULL << INTERCEPT_INVD) | (1ULL << INTERCEPT_HLT) | @@ -626,7 +801,8 @@ static void init_vmcb(struct vcpu_svm *svm) save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; - /* This is the guest-visible cr0 value. + /* + * This is the guest-visible cr0 value. * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. */ svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; @@ -641,10 +817,8 @@ static void init_vmcb(struct vcpu_svm *svm) control->intercept &= ~((1ULL << INTERCEPT_TASK_SWITCH) | (1ULL << INTERCEPT_INVLPG)); control->intercept_exceptions &= ~(1 << PF_VECTOR); - control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK| - INTERCEPT_CR3_MASK); - control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK| - INTERCEPT_CR3_MASK); + control->intercept_cr_read &= ~INTERCEPT_CR3_MASK; + control->intercept_cr_write &= ~INTERCEPT_CR3_MASK; save->g_pat = 0x0007040600070406ULL; save->cr3 = 0; save->cr4 = 0; @@ -698,30 +872,30 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) if (err) goto free_svm; + err = -ENOMEM; page = alloc_page(GFP_KERNEL); - if (!page) { - err = -ENOMEM; + if (!page) goto uninit; - } - err = -ENOMEM; msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); if (!msrpm_pages) - goto uninit; + goto free_page1; nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); if (!nested_msrpm_pages) - goto uninit; - - svm->msrpm = page_address(msrpm_pages); - svm_vcpu_init_msrpm(svm->msrpm); + goto free_page2; hsave_page = alloc_page(GFP_KERNEL); if (!hsave_page) - goto uninit; + goto free_page3; + svm->nested.hsave = page_address(hsave_page); + svm->msrpm = page_address(msrpm_pages); + svm_vcpu_init_msrpm(svm->msrpm); + svm->nested.msrpm = page_address(nested_msrpm_pages); + svm_vcpu_init_msrpm(svm->nested.msrpm); svm->vmcb = page_address(page); clear_page(svm->vmcb); @@ -730,13 +904,18 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) init_vmcb(svm); fx_init(&svm->vcpu); - svm->vcpu.fpu_active = 1; svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; return &svm->vcpu; +free_page3: + __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER); +free_page2: + __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); +free_page1: + __free_page(page); uninit: kvm_vcpu_uninit(&svm->vcpu); free_svm: @@ -765,14 +944,16 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (unlikely(cpu != vcpu->cpu)) { u64 delta; - /* - * Make sure that the guest sees a monotonically - * increasing TSC. - */ - delta = vcpu->arch.host_tsc - native_read_tsc(); - svm->vmcb->control.tsc_offset += delta; - if (is_nested(svm)) - svm->nested.hsave->control.tsc_offset += delta; + if (check_tsc_unstable()) { + /* + * Make sure that the guest sees a monotonically + * increasing TSC. + */ + delta = vcpu->arch.host_tsc - native_read_tsc(); + svm->vmcb->control.tsc_offset += delta; + if (is_nested(svm)) + svm->nested.hsave->control.tsc_offset += delta; + } vcpu->cpu = cpu; kvm_migrate_timers(vcpu); svm->asid_generation = 0; @@ -868,7 +1049,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; - /* AMD's VMCB does not have an explicit unusable field, so emulate it + /* + * AMD's VMCB does not have an explicit unusable field, so emulate it * for cross vendor migration purposes by "not present" */ var->unusable = !var->present || (var->type == 0); @@ -904,7 +1086,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->type |= 0x1; break; case VCPU_SREG_SS: - /* On AMD CPUs sometimes the DB bit in the segment + /* + * On AMD CPUs sometimes the DB bit in the segment * descriptor is left as 1, although the whole segment has * been made unusable. Clear it here to pass an Intel VMX * entry check when cross vendor migrating. @@ -922,74 +1105,127 @@ static int svm_get_cpl(struct kvm_vcpu *vcpu) return save->cpl; } -static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - dt->limit = svm->vmcb->save.idtr.limit; - dt->base = svm->vmcb->save.idtr.base; + dt->size = svm->vmcb->save.idtr.limit; + dt->address = svm->vmcb->save.idtr.base; } -static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.idtr.limit = dt->limit; - svm->vmcb->save.idtr.base = dt->base ; + svm->vmcb->save.idtr.limit = dt->size; + svm->vmcb->save.idtr.base = dt->address ; } -static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - dt->limit = svm->vmcb->save.gdtr.limit; - dt->base = svm->vmcb->save.gdtr.base; + dt->size = svm->vmcb->save.gdtr.limit; + dt->address = svm->vmcb->save.gdtr.base; } -static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) +static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.gdtr.limit = dt->limit; - svm->vmcb->save.gdtr.base = dt->base ; + svm->vmcb->save.gdtr.limit = dt->size; + svm->vmcb->save.gdtr.base = dt->address ; +} + +static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) +{ } static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { } +static void update_cr0_intercept(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb; + ulong gcr0 = svm->vcpu.arch.cr0; + u64 *hcr0 = &svm->vmcb->save.cr0; + + if (!svm->vcpu.fpu_active) + *hcr0 |= SVM_CR0_SELECTIVE_MASK; + else + *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) + | (gcr0 & SVM_CR0_SELECTIVE_MASK); + + + if (gcr0 == *hcr0 && svm->vcpu.fpu_active) { + vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + if (is_nested(svm)) { + struct vmcb *hsave = svm->nested.hsave; + + hsave->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; + hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; + vmcb->control.intercept_cr_read |= svm->nested.intercept_cr_read; + vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write; + } + } else { + svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK; + svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK; + if (is_nested(svm)) { + struct vmcb *hsave = svm->nested.hsave; + + hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK; + hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK; + } + } +} + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm)) { + /* + * We are here because we run in nested mode, the host kvm + * intercepts cr0 writes but the l1 hypervisor does not. + * But the L1 hypervisor may intercept selective cr0 writes. + * This needs to be checked here. + */ + unsigned long old, new; + + /* Remove bits that would trigger a real cr0 write intercept */ + old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK; + new = cr0 & SVM_CR0_SELECTIVE_MASK; + + if (old == new) { + /* cr0 write with ts and mp unchanged */ + svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; + if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE) + return; + } + } + #ifdef CONFIG_X86_64 - if (vcpu->arch.shadow_efer & EFER_LME) { + if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { - vcpu->arch.shadow_efer |= EFER_LMA; + vcpu->arch.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; + vcpu->arch.efer &= ~EFER_LMA; svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); } } #endif - if (npt_enabled) - goto set; + vcpu->arch.cr0 = cr0; - if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) { - svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); - vcpu->fpu_active = 1; - } + if (!npt_enabled) + cr0 |= X86_CR0_PG | X86_CR0_WP; - vcpu->arch.cr0 = cr0; - cr0 |= X86_CR0_PG | X86_CR0_WP; - if (!vcpu->fpu_active) { - svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); + if (!vcpu->fpu_active) cr0 |= X86_CR0_TS; - } -set: /* * re-enable caching here because the QEMU bios * does not do it - this results in some delay at @@ -997,6 +1233,7 @@ set: */ cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; + update_cr0_intercept(svm); } static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -1102,76 +1339,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) svm->vmcb->control.asid = sd->next_asid++; } -static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) +static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) { struct vcpu_svm *svm = to_svm(vcpu); - unsigned long val; - switch (dr) { - case 0 ... 3: - val = vcpu->arch.db[dr]; - break; - case 6: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - val = vcpu->arch.dr6; - else - val = svm->vmcb->save.dr6; - break; - case 7: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - val = vcpu->arch.dr7; - else - val = svm->vmcb->save.dr7; - break; - default: - val = 0; - } - - return val; -} - -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; - - switch (dr) { - case 0 ... 3: - vcpu->arch.db[dr] = value; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - vcpu->arch.eff_db[dr] = value; - return; - case 4 ... 5: - if (vcpu->arch.cr4 & X86_CR4_DE) - *exception = UD_VECTOR; - return; - case 6: - if (value & 0xffffffff00000000ULL) { - *exception = GP_VECTOR; - return; - } - vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1; - return; - case 7: - if (value & 0xffffffff00000000ULL) { - *exception = GP_VECTOR; - return; - } - vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1; - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { - svm->vmcb->save.dr7 = vcpu->arch.dr7; - vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK); - } - return; - default: - /* FIXME: Possible case? */ - printk(KERN_DEBUG "%s: unexpected dr %u\n", - __func__, dr); - *exception = UD_VECTOR; - return; - } + svm->vmcb->save.dr7 = value; } static int pf_interception(struct vcpu_svm *svm) @@ -1208,7 +1380,7 @@ static int db_interception(struct vcpu_svm *svm) } if (svm->vcpu.guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){ + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; @@ -1239,18 +1411,88 @@ static int ud_interception(struct vcpu_svm *svm) return 1; } -static int nm_interception(struct vcpu_svm *svm) +static void svm_fpu_activate(struct kvm_vcpu *vcpu) { - svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); - if (!(svm->vcpu.arch.cr0 & X86_CR0_TS)) - svm->vmcb->save.cr0 &= ~X86_CR0_TS; + struct vcpu_svm *svm = to_svm(vcpu); + u32 excp; + + if (is_nested(svm)) { + u32 h_excp, n_excp; + + h_excp = svm->nested.hsave->control.intercept_exceptions; + n_excp = svm->nested.intercept_exceptions; + h_excp &= ~(1 << NM_VECTOR); + excp = h_excp | n_excp; + } else { + excp = svm->vmcb->control.intercept_exceptions; + excp &= ~(1 << NM_VECTOR); + } + + svm->vmcb->control.intercept_exceptions = excp; + svm->vcpu.fpu_active = 1; + update_cr0_intercept(svm); +} +static int nm_interception(struct vcpu_svm *svm) +{ + svm_fpu_activate(&svm->vcpu); return 1; } -static int mc_interception(struct vcpu_svm *svm) +static bool is_erratum_383(void) { + int err, i; + u64 value; + + if (!erratum_383_found) + return false; + + value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err); + if (err) + return false; + + /* Bit 62 may or may not be set for this mce */ + value &= ~(1ULL << 62); + + if (value != 0xb600000000010015ULL) + return false; + + /* Clear MCi_STATUS registers */ + for (i = 0; i < 6; ++i) + native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0); + + value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err); + if (!err) { + u32 low, high; + + value &= ~(1ULL << 2); + low = lower_32_bits(value); + high = upper_32_bits(value); + + native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high); + } + + /* Flush tlb to evict multi-match entries */ + __flush_tlb_all(); + + return true; +} + +static void svm_handle_mce(struct vcpu_svm *svm) +{ + if (is_erratum_383()) { + /* + * Erratum 383 triggered. Guest state is corrupt so kill the + * guest. + */ + pr_err("KVM: Guest triggered AMD Erratum 383\n"); + + set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests); + + return; + } + /* * On an #MC intercept the MCE handler is not called automatically in * the host. So do it by hand here. @@ -1259,6 +1501,11 @@ static int mc_interception(struct vcpu_svm *svm) "int $0x12\n"); /* not sure if we ever come back to this point */ + return; +} + +static int mc_interception(struct vcpu_svm *svm) +{ return 1; } @@ -1279,29 +1526,23 @@ static int shutdown_interception(struct vcpu_svm *svm) static int io_interception(struct vcpu_svm *svm) { + struct kvm_vcpu *vcpu = &svm->vcpu; u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ int size, in, string; 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, - 0, 0, 0) == EMULATE_DO_MMIO) - return 0; - return 1; - } - in = (io_info & SVM_IOIO_TYPE_MASK) != 0; + if (string || in) + return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO); + port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; - + svm->next_rip = svm->vmcb->control.exit_info_2; skip_emulated_instruction(&svm->vcpu); - return kvm_emulate_pio(&svm->vcpu, in, size, port); + + return kvm_fast_pio_out(vcpu, size, port); } static int nmi_interception(struct vcpu_svm *svm) @@ -1337,7 +1578,7 @@ static int vmmcall_interception(struct vcpu_svm *svm) static int nested_svm_check_permissions(struct vcpu_svm *svm) { - if (!(svm->vcpu.arch.shadow_efer & EFER_SVME) + if (!(svm->vcpu.arch.efer & EFER_SVME) || !is_paging(&svm->vcpu)) { kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; @@ -1354,6 +1595,8 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code) { + int vmexit; + if (!is_nested(svm)) return 0; @@ -1362,21 +1605,28 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, svm->vmcb->control.exit_info_1 = error_code; svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - return nested_svm_exit_handled(svm); + vmexit = nested_svm_intercept(svm); + if (vmexit == NESTED_EXIT_DONE) + svm->nested.exit_required = true; + + return vmexit; } -static inline int nested_svm_intr(struct vcpu_svm *svm) +/* This function returns true if it is save to enable the irq window */ +static inline bool nested_svm_intr(struct vcpu_svm *svm) { if (!is_nested(svm)) - return 0; + return true; if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - return 0; + return true; if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) - return 0; + return false; - svm->vmcb->control.exit_code = SVM_EXIT_INTR; + svm->vmcb->control.exit_code = SVM_EXIT_INTR; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; if (svm->nested.intercept & 1ULL) { /* @@ -1387,21 +1637,40 @@ static inline int nested_svm_intr(struct vcpu_svm *svm) */ svm->nested.exit_required = true; trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); - return 1; + return false; } - return 0; + return true; +} + +/* This function returns true if it is save to enable the nmi window */ +static inline bool nested_svm_nmi(struct vcpu_svm *svm) +{ + if (!is_nested(svm)) + return true; + + if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI))) + return true; + + svm->vmcb->control.exit_code = SVM_EXIT_NMI; + svm->nested.exit_required = true; + + return false; } -static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx) +static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page) { struct page *page; + might_sleep(); + page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto error; - return kmap_atomic(page, idx); + *_page = page; + + return kmap(page); error: kvm_release_page_clean(page); @@ -1410,61 +1679,55 @@ error: return NULL; } -static void nested_svm_unmap(void *addr, enum km_type idx) +static void nested_svm_unmap(struct page *page) { - struct page *page; + kunmap(page); + kvm_release_page_dirty(page); +} - if (!addr) - return; +static int nested_svm_intercept_ioio(struct vcpu_svm *svm) +{ + unsigned port; + u8 val, bit; + u64 gpa; - page = kmap_atomic_to_page(addr); + if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT))) + return NESTED_EXIT_HOST; - kunmap_atomic(addr, idx); - kvm_release_page_dirty(page); + port = svm->vmcb->control.exit_info_1 >> 16; + gpa = svm->nested.vmcb_iopm + (port / 8); + bit = port % 8; + val = 0; + + if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1)) + val &= (1 << bit); + + return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } -static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm) +static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) { - u32 param = svm->vmcb->control.exit_info_1 & 1; - u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - bool ret = false; - u32 t0, t1; - u8 *msrpm; + u32 offset, msr, value; + int write, mask; if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) - return false; + return NESTED_EXIT_HOST; - msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); + msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + offset = svm_msrpm_offset(msr); + write = svm->vmcb->control.exit_info_1 & 1; + mask = 1 << ((2 * (msr & 0xf)) + write); - if (!msrpm) - goto out; + if (offset == MSR_INVALID) + return NESTED_EXIT_DONE; - switch (msr) { - case 0 ... 0x1fff: - t0 = (msr * 2) % 8; - t1 = msr / 8; - break; - case 0xc0000000 ... 0xc0001fff: - t0 = (8192 + msr - 0xc0000000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - case 0xc0010000 ... 0xc0011fff: - t0 = (16384 + msr - 0xc0010000) * 2; - t1 = (t0 / 8); - t0 %= 8; - break; - default: - ret = true; - goto out; - } - - ret = msrpm[t1] & ((1 << param) << t0); + /* Offset is in 32 bit units but need in 8 bit units */ + offset *= 4; -out: - nested_svm_unmap(msrpm, KM_USER0); + if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4)) + return NESTED_EXIT_DONE; - return ret; + return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } static int nested_svm_exit_special(struct vcpu_svm *svm) @@ -1474,17 +1737,21 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) switch (exit_code) { case SVM_EXIT_INTR: case SVM_EXIT_NMI: + case SVM_EXIT_EXCP_BASE + MC_VECTOR: return NESTED_EXIT_HOST; - /* For now we are always handling NPFs when using them */ case SVM_EXIT_NPF: + /* For now we are always handling NPFs when using them */ if (npt_enabled) return NESTED_EXIT_HOST; break; - /* When we're shadowing, trap PFs */ case SVM_EXIT_EXCP_BASE + PF_VECTOR: + /* When we're shadowing, trap PFs */ if (!npt_enabled) return NESTED_EXIT_HOST; break; + case SVM_EXIT_EXCP_BASE + NM_VECTOR: + nm_interception(svm); + break; default: break; } @@ -1495,7 +1762,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) /* * If this function returns true, this #vmexit was already handled */ -static int nested_svm_exit_handled(struct vcpu_svm *svm) +static int nested_svm_intercept(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; int vmexit = NESTED_EXIT_HOST; @@ -1504,6 +1771,9 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) case SVM_EXIT_MSR: vmexit = nested_svm_exit_handled_msr(svm); break; + case SVM_EXIT_IOIO: + vmexit = nested_svm_intercept_ioio(svm); + break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: { u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0); if (svm->nested.intercept_cr_read & cr_bits) @@ -1534,6 +1804,10 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) vmexit = NESTED_EXIT_DONE; break; } + case SVM_EXIT_ERR: { + vmexit = NESTED_EXIT_DONE; + break; + } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); if (svm->nested.intercept & exit_bits) @@ -1541,9 +1815,17 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) } } - if (vmexit == NESTED_EXIT_DONE) { + return vmexit; +} + +static int nested_svm_exit_handled(struct vcpu_svm *svm) +{ + int vmexit; + + vmexit = nested_svm_intercept(svm); + + if (vmexit == NESTED_EXIT_DONE) nested_svm_vmexit(svm); - } return vmexit; } @@ -1585,6 +1867,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + struct page *page; trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, vmcb->control.exit_info_1, @@ -1592,10 +1875,13 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) vmcb->control.exit_int_info, vmcb->control.exit_int_info_err); - nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page); if (!nested_vmcb) return 1; + /* Exit nested SVM mode */ + svm->nested.vmcb = 0; + /* Give the current vmcb to the guest */ disable_gif(svm); @@ -1605,9 +1891,10 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.ds = vmcb->save.ds; nested_vmcb->save.gdtr = vmcb->save.gdtr; nested_vmcb->save.idtr = vmcb->save.idtr; - if (npt_enabled) - nested_vmcb->save.cr3 = vmcb->save.cr3; + nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu); + nested_vmcb->save.cr3 = svm->vcpu.arch.cr3; nested_vmcb->save.cr2 = vmcb->save.cr2; + nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; nested_vmcb->save.rflags = vmcb->save.rflags; nested_vmcb->save.rip = vmcb->save.rip; nested_vmcb->save.rsp = vmcb->save.rsp; @@ -1679,10 +1966,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.cpl = 0; svm->vmcb->control.exit_int_info = 0; - /* Exit nested SVM mode */ - svm->nested.vmcb = 0; - - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); kvm_mmu_reset_context(&svm->vcpu); kvm_mmu_load(&svm->vcpu); @@ -1692,19 +1976,33 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - u32 *nested_msrpm; + /* + * This function merges the msr permission bitmaps of kvm and the + * nested vmcb. It is omptimized in that it only merges the parts where + * the kvm msr permission bitmap may contain zero bits + */ int i; - nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0); - if (!nested_msrpm) - return false; + if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return true; - for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++) - svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; + for (i = 0; i < MSRPM_OFFSETS; i++) { + u32 value, p; + u64 offset; - svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); + if (msrpm_offsets[i] == 0xffffffff) + break; - nested_svm_unmap(nested_msrpm, KM_USER0); + p = msrpm_offsets[i]; + offset = svm->nested.vmcb_msrpm + (p * 4); + + if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4)) + return false; + + svm->nested.msrpm[p] = svm->msrpm[p] | value; + } + + svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm); return true; } @@ -1714,34 +2012,42 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) struct vmcb *nested_vmcb; struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + struct page *page; + u64 vmcb_gpa; - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + vmcb_gpa = svm->vmcb->save.rax; + + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return false; - /* nested_vmcb is our indicator if nested SVM is activated */ - svm->nested.vmcb = svm->vmcb->save.rax; - - trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb, + trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, vmcb_gpa, nested_vmcb->save.rip, nested_vmcb->control.int_ctl, nested_vmcb->control.event_inj, nested_vmcb->control.nested_ctl); + trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read, + nested_vmcb->control.intercept_cr_write, + nested_vmcb->control.intercept_exceptions, + nested_vmcb->control.intercept); + /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); - /* Save the old vmcb, so we don't need to pick what we save, but - can restore everything when a VMEXIT occurs */ + /* + * Save the old vmcb, so we don't need to pick what we save, but can + * restore everything when a VMEXIT occurs + */ hsave->save.es = vmcb->save.es; hsave->save.cs = vmcb->save.cs; hsave->save.ss = vmcb->save.ss; hsave->save.ds = vmcb->save.ds; hsave->save.gdtr = vmcb->save.gdtr; hsave->save.idtr = vmcb->save.idtr; - hsave->save.efer = svm->vcpu.arch.shadow_efer; - hsave->save.cr0 = svm->vcpu.arch.cr0; + hsave->save.efer = svm->vcpu.arch.efer; + hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); hsave->save.cr4 = svm->vcpu.arch.cr4; hsave->save.rflags = vmcb->save.rflags; hsave->save.rip = svm->next_rip; @@ -1773,14 +2079,17 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) if (npt_enabled) { svm->vmcb->save.cr3 = nested_vmcb->save.cr3; svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; - } else { + } else kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); - kvm_mmu_reset_context(&svm->vcpu); - } + + /* Guest paging mode is active - reset mmu */ + kvm_mmu_reset_context(&svm->vcpu); + svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2; kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax); kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp); kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip); + /* In case we don't even reach vcpu_run, the fields are not updated */ svm->vmcb->save.rax = nested_vmcb->save.rax; svm->vmcb->save.rsp = nested_vmcb->save.rsp; @@ -1789,22 +2098,8 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->vmcb->save.dr6 = nested_vmcb->save.dr6; svm->vmcb->save.cpl = nested_vmcb->save.cpl; - /* We don't want a nested guest to be more powerful than the guest, - so all intercepts are ORed */ - svm->vmcb->control.intercept_cr_read |= - nested_vmcb->control.intercept_cr_read; - svm->vmcb->control.intercept_cr_write |= - nested_vmcb->control.intercept_cr_write; - svm->vmcb->control.intercept_dr_read |= - nested_vmcb->control.intercept_dr_read; - svm->vmcb->control.intercept_dr_write |= - nested_vmcb->control.intercept_dr_write; - svm->vmcb->control.intercept_exceptions |= - nested_vmcb->control.intercept_exceptions; - - svm->vmcb->control.intercept |= nested_vmcb->control.intercept; - - svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; + svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL; /* cache intercepts */ svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read; @@ -1821,13 +2116,43 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; + if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { + /* We only want the cr8 intercept bits of the guest */ + svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK; + svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; + } + + /* We don't want to see VMMCALLs from a nested guest */ + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VMMCALL); + + /* + * We don't want a nested guest to be more powerful than the guest, so + * all intercepts are ORed + */ + svm->vmcb->control.intercept_cr_read |= + nested_vmcb->control.intercept_cr_read; + svm->vmcb->control.intercept_cr_write |= + nested_vmcb->control.intercept_cr_write; + svm->vmcb->control.intercept_dr_read |= + nested_vmcb->control.intercept_dr_read; + svm->vmcb->control.intercept_dr_write |= + nested_vmcb->control.intercept_dr_write; + svm->vmcb->control.intercept_exceptions |= + nested_vmcb->control.intercept_exceptions; + + svm->vmcb->control.intercept |= nested_vmcb->control.intercept; + + svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); + + /* nested_vmcb is our indicator if nested SVM is activated */ + svm->nested.vmcb = vmcb_gpa; enable_gif(svm); @@ -1853,6 +2178,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; + struct page *page; if (nested_svm_check_permissions(svm)) return 1; @@ -1860,12 +2186,12 @@ static int vmload_interception(struct vcpu_svm *svm) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; nested_svm_vmloadsave(nested_vmcb, svm->vmcb); - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); return 1; } @@ -1873,6 +2199,7 @@ static int vmload_interception(struct vcpu_svm *svm) static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; + struct page *page; if (nested_svm_check_permissions(svm)) return 1; @@ -1880,12 +2207,12 @@ static int vmsave_interception(struct vcpu_svm *svm) svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0); + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; nested_svm_vmloadsave(svm->vmcb, nested_vmcb); - nested_svm_unmap(nested_vmcb, KM_USER0); + nested_svm_unmap(page); return 1; } @@ -1988,6 +2315,8 @@ static int task_switch_interception(struct vcpu_svm *svm) svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK; uint32_t idt_v = svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID; + bool has_error_code = false; + u32 error_code = 0; tss_selector = (u16)svm->vmcb->control.exit_info_1; @@ -2008,6 +2337,12 @@ static int task_switch_interception(struct vcpu_svm *svm) svm->vcpu.arch.nmi_injected = false; break; case SVM_EXITINTINFO_TYPE_EXEPT: + if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) { + has_error_code = true; + error_code = + (u32)svm->vmcb->control.exit_info_2; + } kvm_clear_exception_queue(&svm->vcpu); break; case SVM_EXITINTINFO_TYPE_INTR: @@ -2024,7 +2359,14 @@ static int task_switch_interception(struct vcpu_svm *svm) (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) skip_emulated_instruction(&svm->vcpu); - return kvm_task_switch(&svm->vcpu, tss_selector, reason); + if (kvm_task_switch(&svm->vcpu, tss_selector, reason, + has_error_code, error_code) == EMULATE_FAIL) { + svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + svm->vcpu.run->internal.ndata = 0; + return 0; + } + return 1; } static int cpuid_interception(struct vcpu_svm *svm) @@ -2037,7 +2379,7 @@ static int cpuid_interception(struct vcpu_svm *svm) static int iret_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.nmi_window_exits; - svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET); svm->vcpu.arch.hflags |= HF_IRET_MASK; return 1; } @@ -2115,9 +2457,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_SYSENTER_ESP: *data = svm->sysenter_esp; break; - /* Nobody will change the following 5 values in the VMCB so - we can safely return them on rdmsr. They will always be 0 - until LBRV is implemented. */ + /* + * Nobody will change the following 5 values in the VMCB so we can + * safely return them on rdmsr. They will always be 0 until LBRV is + * implemented. + */ case MSR_IA32_DEBUGCTLMSR: *data = svm->vmcb->save.dbgctl; break; @@ -2137,7 +2481,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = svm->nested.hsave_msr; break; case MSR_VM_CR: - *data = 0; + *data = svm->nested.vm_cr_msr; break; case MSR_IA32_UCODE_REV: *data = 0x01000065; @@ -2153,9 +2497,10 @@ static int rdmsr_interception(struct vcpu_svm *svm) u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data; - if (svm_get_msr(&svm->vcpu, ecx, &data)) + if (svm_get_msr(&svm->vcpu, ecx, &data)) { + trace_kvm_msr_read_ex(ecx); kvm_inject_gp(&svm->vcpu, 0); - else { + } else { trace_kvm_msr_read(ecx, data); svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff; @@ -2166,6 +2511,31 @@ static int rdmsr_interception(struct vcpu_svm *svm) return 1; } +static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int svm_dis, chg_mask; + + if (data & ~SVM_VM_CR_VALID_MASK) + return 1; + + chg_mask = SVM_VM_CR_VALID_MASK; + + if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK) + chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK); + + svm->nested.vm_cr_msr &= ~chg_mask; + svm->nested.vm_cr_msr |= (data & chg_mask); + + svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK; + + /* check for svm_disable while efer.svme is set */ + if (svm_dis && (vcpu->arch.efer & EFER_SVME)) + return 1; + + return 0; +} + static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2232,6 +2602,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) svm->nested.hsave_msr = data; break; case MSR_VM_CR: + return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; @@ -2247,13 +2618,15 @@ static int wrmsr_interception(struct vcpu_svm *svm) u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); - trace_kvm_msr_write(ecx, data); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (svm_set_msr(&svm->vcpu, ecx, data)) + if (svm_set_msr(&svm->vcpu, ecx, data)) { + trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); - else + } else { + trace_kvm_msr_write(ecx, data); skip_emulated_instruction(&svm->vcpu); + } return 1; } @@ -2293,37 +2666,42 @@ static int pause_interception(struct vcpu_svm *svm) } static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { - [SVM_EXIT_READ_CR0] = emulate_on_interception, - [SVM_EXIT_READ_CR3] = emulate_on_interception, - [SVM_EXIT_READ_CR4] = emulate_on_interception, - [SVM_EXIT_READ_CR8] = emulate_on_interception, - /* for now: */ - [SVM_EXIT_WRITE_CR0] = emulate_on_interception, - [SVM_EXIT_WRITE_CR3] = emulate_on_interception, - [SVM_EXIT_WRITE_CR4] = emulate_on_interception, - [SVM_EXIT_WRITE_CR8] = cr8_write_interception, - [SVM_EXIT_READ_DR0] = emulate_on_interception, + [SVM_EXIT_READ_CR0] = emulate_on_interception, + [SVM_EXIT_READ_CR3] = emulate_on_interception, + [SVM_EXIT_READ_CR4] = emulate_on_interception, + [SVM_EXIT_READ_CR8] = emulate_on_interception, + [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, + [SVM_EXIT_WRITE_CR0] = emulate_on_interception, + [SVM_EXIT_WRITE_CR3] = emulate_on_interception, + [SVM_EXIT_WRITE_CR4] = emulate_on_interception, + [SVM_EXIT_WRITE_CR8] = cr8_write_interception, + [SVM_EXIT_READ_DR0] = emulate_on_interception, [SVM_EXIT_READ_DR1] = emulate_on_interception, [SVM_EXIT_READ_DR2] = emulate_on_interception, [SVM_EXIT_READ_DR3] = emulate_on_interception, + [SVM_EXIT_READ_DR4] = emulate_on_interception, + [SVM_EXIT_READ_DR5] = emulate_on_interception, + [SVM_EXIT_READ_DR6] = emulate_on_interception, + [SVM_EXIT_READ_DR7] = emulate_on_interception, [SVM_EXIT_WRITE_DR0] = emulate_on_interception, [SVM_EXIT_WRITE_DR1] = emulate_on_interception, [SVM_EXIT_WRITE_DR2] = emulate_on_interception, [SVM_EXIT_WRITE_DR3] = emulate_on_interception, + [SVM_EXIT_WRITE_DR4] = emulate_on_interception, [SVM_EXIT_WRITE_DR5] = emulate_on_interception, + [SVM_EXIT_WRITE_DR6] = emulate_on_interception, [SVM_EXIT_WRITE_DR7] = emulate_on_interception, [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, - [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, - [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, - [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, - [SVM_EXIT_INTR] = intr_interception, + [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, + [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, + [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = nop_on_interception, [SVM_EXIT_INIT] = nop_on_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, - /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */ [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, @@ -2331,7 +2709,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, [SVM_EXIT_INVLPGA] = invlpga_interception, - [SVM_EXIT_IOIO] = io_interception, + [SVM_EXIT_IOIO] = io_interception, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, [SVM_EXIT_SHUTDOWN] = shutdown_interception, @@ -2354,7 +2732,12 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(exit_code, svm->vmcb->save.rip); + trace_kvm_exit(exit_code, vcpu); + + if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK)) + vcpu->arch.cr0 = svm->vmcb->save.cr0; + if (npt_enabled) + vcpu->arch.cr3 = svm->vmcb->save.cr3; if (unlikely(svm->nested.exit_required)) { nested_svm_vmexit(svm); @@ -2383,21 +2766,6 @@ static int handle_exit(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); - if (npt_enabled) { - int mmu_reload = 0; - if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) { - svm_set_cr0(vcpu, svm->vmcb->save.cr0); - mmu_reload = 1; - } - vcpu->arch.cr0 = svm->vmcb->save.cr0; - vcpu->arch.cr3 = svm->vmcb->save.cr3; - if (mmu_reload) { - kvm_mmu_reset_context(vcpu); - kvm_mmu_load(vcpu); - } - } - - if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; kvm_run->fail_entry.hardware_entry_failure_reason @@ -2450,7 +2818,7 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; vcpu->arch.hflags |= HF_NMI_MASK; - svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET); + svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET); ++vcpu->stat.nmi_injections; } @@ -2482,6 +2850,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + if (irr == -1) return; @@ -2493,8 +2864,12 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - !(svm->vcpu.arch.hflags & HF_NMI_MASK); + int ret; + ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && + !(svm->vcpu.arch.hflags & HF_NMI_MASK); + ret = ret && gif_set(svm) && nested_svm_nmi(svm); + + return ret; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) @@ -2510,10 +2885,10 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) if (masked) { svm->vcpu.arch.hflags |= HF_NMI_MASK; - svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET); + svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET); } else { svm->vcpu.arch.hflags &= ~HF_NMI_MASK; - svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET); } } @@ -2539,13 +2914,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - nested_svm_intr(svm); - - /* In case GIF=0 we can't rely on the CPU to tell us when - * GIF becomes 1, because that's a separate STGI/VMRUN intercept. - * The next time we get that intercept, this function will be - * called again though and we'll get the vintr intercept. */ - if (gif_set(svm)) { + /* + * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes + * 1, because that's a separate STGI/VMRUN intercept. The next time we + * get that intercept, this function will be called again though and + * we'll get the vintr intercept. + */ + if (gif_set(svm) && nested_svm_intr(svm)) { svm_set_vintr(svm); svm_inject_irq(svm, 0x0); } @@ -2559,9 +2934,10 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) == HF_NMI_MASK) return; /* IRET will cause a vm exit */ - /* Something prevents NMI from been injected. Single step over - possible problem (IRET or exception injection or interrupt - shadow) */ + /* + * Something prevents NMI from been injected. Single step over possible + * problem (IRET or exception injection or interrupt shadow) + */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); update_db_intercept(vcpu); @@ -2585,6 +2961,9 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) { int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK; kvm_set_cr8(vcpu, cr8); @@ -2596,6 +2975,9 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); u64 cr8; + if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + return; + cr8 = kvm_get_cr8(vcpu); svm->vmcb->control.int_ctl &= ~V_TPR_MASK; svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; @@ -2606,6 +2988,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) u8 vector; int type; u32 exitintinfo = svm->vmcb->control.exit_int_info; + unsigned int3_injected = svm->int3_injected; + + svm->int3_injected = 0; if (svm->vcpu.arch.hflags & HF_IRET_MASK) svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); @@ -2625,18 +3010,25 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) svm->vcpu.arch.nmi_injected = true; break; case SVM_EXITINTINFO_TYPE_EXEPT: - /* In case of software exception do not reinject an exception - vector, but re-execute and instruction instead */ - if (is_nested(svm)) - break; - if (kvm_exception_is_soft(vector)) + /* + * In case of software exceptions, do not reinject the vector, + * but re-execute the instruction instead. Rewind RIP first + * if we emulated INT3 before. + */ + if (kvm_exception_is_soft(vector)) { + if (vector == BP_VECTOR && int3_injected && + kvm_is_linear_rip(&svm->vcpu, svm->int3_rip)) + kvm_rip_write(&svm->vcpu, + kvm_rip_read(&svm->vcpu) - + int3_injected); break; + } if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { u32 err = svm->vmcb->control.exit_int_info_err; - kvm_queue_exception_e(&svm->vcpu, vector, err); + kvm_requeue_exception_e(&svm->vcpu, vector, err); } else - kvm_queue_exception(&svm->vcpu, vector); + kvm_requeue_exception(&svm->vcpu, vector); break; case SVM_EXITINTINFO_TYPE_INTR: kvm_queue_interrupt(&svm->vcpu, vector, false); @@ -2659,6 +3051,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) u16 gs_selector; u16 ldt_selector; + 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.regs[VCPU_REGS_RIP]; + /* * A vmexit emulation is required before the vcpu can be executed * again. @@ -2666,10 +3062,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->nested.exit_required)) return; - 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.regs[VCPU_REGS_RIP]; - pre_svm_run(svm); sync_lapic_to_cr8(vcpu); @@ -2782,6 +3174,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); } + + /* + * We need to handle MC intercepts here before the vcpu has a chance to + * change the physical cpu + */ + if (unlikely(svm->vmcb->control.exit_code == + SVM_EXIT_EXCP_BASE + MC_VECTOR)) + svm_handle_mce(svm); } #undef R @@ -2798,12 +3198,6 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = root; force_new_asid(vcpu); - - if (vcpu->fpu_active) { - svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); - svm->vmcb->save.cr0 |= X86_CR0_TS; - vcpu->fpu_active = 0; - } } static int is_disabled(void) @@ -2852,25 +3246,43 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return 0; } +static void svm_cpuid_update(struct kvm_vcpu *vcpu) +{ +} + +static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) +{ + switch (func) { + case 0x8000000A: + entry->eax = 1; /* SVM revision 1 */ + entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper + ASID emulation to nested SVM */ + entry->ecx = 0; /* Reserved */ + entry->edx = 0; /* Do not support any additional features */ + + break; + } +} + static const struct trace_print_flags svm_exit_reasons_str[] = { - { SVM_EXIT_READ_CR0, "read_cr0" }, - { SVM_EXIT_READ_CR3, "read_cr3" }, - { SVM_EXIT_READ_CR4, "read_cr4" }, - { SVM_EXIT_READ_CR8, "read_cr8" }, - { SVM_EXIT_WRITE_CR0, "write_cr0" }, - { SVM_EXIT_WRITE_CR3, "write_cr3" }, - { SVM_EXIT_WRITE_CR4, "write_cr4" }, - { SVM_EXIT_WRITE_CR8, "write_cr8" }, - { SVM_EXIT_READ_DR0, "read_dr0" }, - { SVM_EXIT_READ_DR1, "read_dr1" }, - { SVM_EXIT_READ_DR2, "read_dr2" }, - { SVM_EXIT_READ_DR3, "read_dr3" }, - { SVM_EXIT_WRITE_DR0, "write_dr0" }, - { SVM_EXIT_WRITE_DR1, "write_dr1" }, - { SVM_EXIT_WRITE_DR2, "write_dr2" }, - { SVM_EXIT_WRITE_DR3, "write_dr3" }, - { SVM_EXIT_WRITE_DR5, "write_dr5" }, - { SVM_EXIT_WRITE_DR7, "write_dr7" }, + { SVM_EXIT_READ_CR0, "read_cr0" }, + { SVM_EXIT_READ_CR3, "read_cr3" }, + { SVM_EXIT_READ_CR4, "read_cr4" }, + { SVM_EXIT_READ_CR8, "read_cr8" }, + { SVM_EXIT_WRITE_CR0, "write_cr0" }, + { SVM_EXIT_WRITE_CR3, "write_cr3" }, + { SVM_EXIT_WRITE_CR4, "write_cr4" }, + { SVM_EXIT_WRITE_CR8, "write_cr8" }, + { SVM_EXIT_READ_DR0, "read_dr0" }, + { SVM_EXIT_READ_DR1, "read_dr1" }, + { SVM_EXIT_READ_DR2, "read_dr2" }, + { SVM_EXIT_READ_DR3, "read_dr3" }, + { SVM_EXIT_WRITE_DR0, "write_dr0" }, + { SVM_EXIT_WRITE_DR1, "write_dr1" }, + { SVM_EXIT_WRITE_DR2, "write_dr2" }, + { SVM_EXIT_WRITE_DR3, "write_dr3" }, + { SVM_EXIT_WRITE_DR5, "write_dr5" }, + { SVM_EXIT_WRITE_DR7, "write_dr7" }, { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, @@ -2905,9 +3317,24 @@ static const struct trace_print_flags svm_exit_reasons_str[] = { { -1, NULL } }; -static bool svm_gb_page_enable(void) +static int svm_get_lpage_level(void) { - return true; + return PT_PDPE_LEVEL; +} + +static bool svm_rdtscp_supported(void) +{ + return false; +} + +static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR; + if (is_nested(svm)) + svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR; + update_cr0_intercept(svm); } static struct kvm_x86_ops svm_x86_ops = { @@ -2936,6 +3363,7 @@ static struct kvm_x86_ops svm_x86_ops = { .set_segment = svm_set_segment, .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, + .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, .set_cr3 = svm_set_cr3, @@ -2945,11 +3373,12 @@ static struct kvm_x86_ops svm_x86_ops = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .get_dr = svm_get_dr, - .set_dr = svm_set_dr, + .set_dr7 = svm_set_dr7, .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, + .fpu_activate = svm_fpu_activate, + .fpu_deactivate = svm_fpu_deactivate, .tlb_flush = svm_flush_tlb, @@ -2975,13 +3404,19 @@ static struct kvm_x86_ops svm_x86_ops = { .get_mt_mask = svm_get_mt_mask, .exit_reasons_str = svm_exit_reasons_str, - .gb_page_enable = svm_gb_page_enable, + .get_lpage_level = svm_get_lpage_level, + + .cpuid_update = svm_cpuid_update, + + .rdtscp_supported = svm_rdtscp_supported, + + .set_supported_cpuid = svm_set_supported_cpuid, }; static int __init svm_init(void) { return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm), - THIS_MODULE); + __alignof__(struct vcpu_svm), THIS_MODULE); } static void __exit svm_exit(void) |