diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
| -rw-r--r-- | arch/x86/kvm/vmx.c | 909 |
1 files changed, 444 insertions, 465 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a236decb81e4..ef4ba71dbb66 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1856,7 +1856,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); + (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -1865,8 +1865,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = ~0; if (enable_ept) eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ - if (vcpu->fpu_active) - eb &= ~(1u << NM_VECTOR); /* When we are running a nested L2 guest and L1 specified for it a * certain exception bitmap, we must trap the same exceptions and pass @@ -1992,19 +1990,6 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, m->host[i].value = host_val; } -static void reload_tss(void) -{ - /* - * VT restores TR but not its size. Useless. - */ - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); - struct desc_struct *descs; - - descs = (void *)gdt->address; - descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ - load_TR_desc(); -} - static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { u64 guest_efer = vmx->vcpu.arch.efer; @@ -2059,41 +2044,36 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) } } +#ifdef CONFIG_X86_32 +/* + * On 32-bit kernels, VM exits still load the FS and GS bases from the + * VMCS rather than the segment table. KVM uses this helper to figure + * out the current bases to poke them into the VMCS before entry. + */ static unsigned long segment_base(u16 selector) { struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); struct desc_struct *d; - unsigned long table_base; + struct desc_struct *table; unsigned long v; - if (!(selector & ~3)) + if (!(selector & ~SEGMENT_RPL_MASK)) return 0; - table_base = gdt->address; + table = (struct desc_struct *)gdt->address; - if (selector & 4) { /* from ldt */ + if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { u16 ldt_selector = kvm_read_ldt(); - if (!(ldt_selector & ~3)) + if (!(ldt_selector & ~SEGMENT_RPL_MASK)) return 0; - table_base = segment_base(ldt_selector); + table = (struct desc_struct *)segment_base(ldt_selector); } - d = (struct desc_struct *)(table_base + (selector & ~7)); - v = get_desc_base(d); -#ifdef CONFIG_X86_64 - if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; -#endif + v = get_desc_base(&table[selector >> 3]); return v; } - -static inline unsigned long kvm_read_tr_base(void) -{ - u16 tr; - asm("str %0" : "=g"(tr)); - return segment_base(tr); -} +#endif static void vmx_save_host_state(struct kvm_vcpu *vcpu) { @@ -2179,7 +2159,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) loadsegment(es, vmx->host_state.es_sel); } #endif - reload_tss(); + invalidate_tss_limit(); #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif @@ -2294,10 +2274,19 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* * Linux uses per-cpu TSS and GDT, so set these when switching - * processors. + * processors. See 22.2.4. */ - vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */ - vmcs_writel(HOST_GDTR_BASE, gdt->address); /* 22.2.4 */ + vmcs_writel(HOST_TR_BASE, + (unsigned long)this_cpu_ptr(&cpu_tss)); + vmcs_writel(HOST_GDTR_BASE, gdt->address); + + /* + * VM exits change the host TR limit to 0x67 after a VM + * exit. This is okay, since 0x67 covers everything except + * the IO bitmap and have have code to handle the IO bitmap + * being lost after a VM exit. + */ + BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67); rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ @@ -2340,25 +2329,6 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) } } -static void vmx_fpu_activate(struct kvm_vcpu *vcpu) -{ - ulong cr0; - - if (vcpu->fpu_active) - return; - vcpu->fpu_active = 1; - cr0 = vmcs_readl(GUEST_CR0); - cr0 &= ~(X86_CR0_TS | X86_CR0_MP); - cr0 |= kvm_read_cr0_bits(vcpu, X86_CR0_TS | X86_CR0_MP); - vmcs_writel(GUEST_CR0, cr0); - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; - if (is_guest_mode(vcpu)) - vcpu->arch.cr0_guest_owned_bits &= - ~get_vmcs12(vcpu)->cr0_guest_host_mask; - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); -} - static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); /* @@ -2377,33 +2347,6 @@ static inline unsigned long nested_read_cr4(struct vmcs12 *fields) (fields->cr4_read_shadow & fields->cr4_guest_host_mask); } -static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) -{ - /* Note that there is no vcpu->fpu_active = 0 here. The caller must - * set this *before* calling this function. - */ - vmx_decache_cr0_guest_bits(vcpu); - vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP); - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = 0; - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - if (is_guest_mode(vcpu)) { - /* - * L1's specified read shadow might not contain the TS bit, - * so now that we turned on shadowing of this bit, we need to - * set this bit of the shadow. Like in nested_vmx_run we need - * nested_read_cr0(vmcs12), but vmcs12->guest_cr0 is not yet - * up-to-date here because we just decached cr0.TS (and we'll - * only update vmcs12->guest_cr0 on nested exit). - */ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - vmcs12->guest_cr0 = (vmcs12->guest_cr0 & ~X86_CR0_TS) | - (vcpu->arch.cr0 & X86_CR0_TS); - vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12)); - } else - vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); -} - static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags, save_rflags; @@ -3962,7 +3905,7 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) } vmcs_write16(sf->selector, var.selector); - vmcs_write32(sf->base, var.base); + vmcs_writel(sf->base, var.base); vmcs_write32(sf->limit, var.limit); vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } @@ -4232,9 +4175,6 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (enable_ept) ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); - if (!vcpu->fpu_active) - hw_cr0 |= X86_CR0_TS | X86_CR0_MP; - vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; @@ -4953,7 +4893,7 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } -static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; @@ -4964,19 +4904,15 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmx->nested.pi_pending) { vmx->nested.pi_pending = false; if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return 0; + return; max_irr = find_last_bit( (unsigned long *)vmx->nested.pi_desc->pir, 256); if (max_irr == 256) - return 0; + return; vapic_page = kmap(vmx->nested.virtual_apic_page); - if (!vapic_page) { - WARN_ON(1); - return -ENOMEM; - } __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4987,7 +4923,6 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } - return 0; } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) @@ -5056,26 +4991,12 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_pir(vector, &vmx->pi_desc)) return; - r = pi_test_and_set_on(&vmx->pi_desc); - kvm_make_request(KVM_REQ_EVENT, vcpu); - if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu)) - kvm_vcpu_kick(vcpu); -} - -static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!pi_test_on(&vmx->pi_desc)) + /* If a previous notification has sent the IPI, nothing to do. */ + if (pi_test_and_set_on(&vmx->pi_desc)) return; - pi_clear_on(&vmx->pi_desc); - /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. - * But on x86 this is just a compiler barrier anyway. - */ - smp_mb__after_atomic(); - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + kvm_vcpu_kick(vcpu); } /* @@ -5236,10 +5157,8 @@ static void ept_set_mmio_spte_mask(void) /* * EPT Misconfigurations can be generated if the value of bits 2:0 * of an EPT paging-structure entry is 110b (write/execute). - * Also, magic bits (0x3ull << 62) is set to quickly identify mmio - * spte. */ - kvm_mmu_set_mmio_spte_mask((0x3ull << 62) | 0x6ull); + kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE); } #define VMX_XSS_EXIT_BITMAP 0 @@ -5342,7 +5261,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl); - vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); + vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; + vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); + set_cr4_guest_host_mask(vmx); if (vmx_xsaves_supported()) @@ -5446,7 +5367,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); - vmx_fpu_activate(vcpu); + update_exception_bitmap(vcpu); vpid_sync_context(vmx->vpid); @@ -5480,26 +5401,20 @@ static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) static void enable_irq_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_INTR_PENDING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - if (!cpu_has_virtual_nmis() || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { enable_irq_window(vcpu); return; } - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_NMI_PENDING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -5725,11 +5640,6 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (is_nmi(intr_info)) return 1; /* already handled by vmx_vcpu_run() */ - if (is_no_device(intr_info)) { - vmx_fpu_activate(vcpu); - return 1; - } - if (is_invalid_opcode(intr_info)) { if (is_guest_mode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); @@ -5919,22 +5829,6 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) return kvm_set_cr4(vcpu, val); } -/* called to set cr0 as appropriate for clts instruction exit. */ -static void handle_clts(struct kvm_vcpu *vcpu) -{ - if (is_guest_mode(vcpu)) { - /* - * We get here when L2 did CLTS, and L1 didn't shadow CR0.TS - * but we did (!fpu_active). We need to keep GUEST_CR0.TS on, - * just pretend it's off (also in arch.cr0 for fpu_activate). - */ - vmcs_writel(CR0_READ_SHADOW, - vmcs_readl(CR0_READ_SHADOW) & ~X86_CR0_TS); - vcpu->arch.cr0 &= ~X86_CR0_TS; - } else - vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); -} - static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; @@ -5980,9 +5874,9 @@ static int handle_cr(struct kvm_vcpu *vcpu) } break; case 2: /* clts */ - handle_clts(vcpu); + WARN_ONCE(1, "Guest should always own CR0.TS"); + vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); trace_kvm_cr_write(0, kvm_read_cr0(vcpu)); - vmx_fpu_activate(vcpu); return kvm_skip_emulated_instruction(vcpu); case 1: /*mov from cr*/ switch (cr) { @@ -6152,18 +6046,14 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu) static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_apic_update_ppr(vcpu); return 1; } static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - /* clear pending irq */ - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_INTR_PENDING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -6374,15 +6264,22 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(gpa, exit_qualification); - /* it is a read fault? */ - error_code = (exit_qualification << 2) & PFERR_USER_MASK; - /* it is a write fault? */ - error_code |= exit_qualification & PFERR_WRITE_MASK; - /* It is a fetch fault? */ - error_code |= (exit_qualification << 2) & PFERR_FETCH_MASK; - /* ept page table is present? */ - error_code |= (exit_qualification & 0x38) != 0; - + /* Is it a read fault? */ + error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) + ? PFERR_USER_MASK : 0; + /* Is it a write fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) + ? PFERR_WRITE_MASK : 0; + /* Is it a fetch fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) + ? PFERR_FETCH_MASK : 0; + /* ept page table entry is present? */ + error_code |= (exit_qualification & + (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE | + EPT_VIOLATION_EXECUTABLE)) + ? PFERR_PRESENT_MASK : 0; + + vcpu->arch.gpa_available = true; vcpu->arch.exit_qualification = exit_qualification; return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -6400,6 +6297,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) } ret = handle_mmio_page_fault(vcpu, gpa, true); + vcpu->arch.gpa_available = true; if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; @@ -6421,12 +6319,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - /* clear pending NMI */ - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_NMI_PENDING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -6572,6 +6466,19 @@ static void wakeup_handler(void) spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); } +void vmx_enable_tdp(void) +{ + kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, + enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull, + enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK, + cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, + enable_ept_ad_bits ? 0ull : VMX_EPT_RWX_MASK); + + ept_set_mmio_spte_mask(); + kvm_enable_tdp(); +} + static __init int hardware_setup(void) { int r = -ENOMEM, i, msr; @@ -6651,8 +6558,10 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ple()) ple_gap = 0; - if (!cpu_has_vmx_apicv()) + if (!cpu_has_vmx_apicv()) { enable_apicv = 0; + kvm_x86_ops->sync_pir_to_irr = NULL; + } if (cpu_has_vmx_tsc_scaling()) { kvm_has_tsc_control = true; @@ -6697,16 +6606,9 @@ static __init int hardware_setup(void) /* SELF-IPI */ vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true); - if (enable_ept) { - kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, - (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, - (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK, - cpu_has_vmx_ept_execute_only() ? - 0ull : VMX_EPT_READABLE_MASK); - ept_set_mmio_spte_mask(); - kvm_enable_tdp(); - } else + if (enable_ept) + vmx_enable_tdp(); + else kvm_disable_tdp(); update_ple_window_actual_max(); @@ -7085,13 +6987,18 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, } page = nested_get_page(vcpu, vmptr); - if (page == NULL || - *(u32 *)kmap(page) != VMCS12_REVISION) { + if (page == NULL) { nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + if (*(u32 *)kmap(page) != VMCS12_REVISION) { kunmap(page); + nested_release_page_clean(page); + nested_vmx_failInvalid(vcpu); return kvm_skip_emulated_instruction(vcpu); } kunmap(page); + nested_release_page_clean(page); vmx->nested.vmxon_ptr = vmptr; break; case EXIT_REASON_VMCLEAR: @@ -7129,6 +7036,53 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, return 0; } +static int enter_vmx_operation(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs *shadow_vmcs; + + if (cpu_has_vmx_msr_bitmap()) { + vmx->nested.msr_bitmap = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx->nested.msr_bitmap) + goto out_msr_bitmap; + } + + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); + if (!vmx->nested.cached_vmcs12) + goto out_cached_vmcs12; + + if (enable_shadow_vmcs) { + shadow_vmcs = alloc_vmcs(); + if (!shadow_vmcs) + goto out_shadow_vmcs; + /* mark vmcs as shadow */ + shadow_vmcs->revision_id |= (1u << 31); + /* init shadow vmcs */ + vmcs_clear(shadow_vmcs); + vmx->vmcs01.shadow_vmcs = shadow_vmcs; + } + + INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); + vmx->nested.vmcs02_num = 0; + + hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + + vmx->nested.vmxon = true; + return 0; + +out_shadow_vmcs: + kfree(vmx->nested.cached_vmcs12); + +out_cached_vmcs12: + free_page((unsigned long)vmx->nested.msr_bitmap); + +out_msr_bitmap: + return -ENOMEM; +} + /* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even @@ -7139,9 +7093,9 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, */ static int handle_vmon(struct kvm_vcpu *vcpu) { + int ret; struct kvm_segment cs; struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmcs *shadow_vmcs; const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; @@ -7168,9 +7122,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) - return 1; - if (vmx->nested.vmxon) { nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); return kvm_skip_emulated_instruction(vcpu); @@ -7182,48 +7133,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } - - vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); - if (!vmx->nested.cached_vmcs12) - goto out_cached_vmcs12; - - if (enable_shadow_vmcs) { - shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) - goto out_shadow_vmcs; - /* mark vmcs as shadow */ - shadow_vmcs->revision_id |= (1u << 31); - /* init shadow vmcs */ - vmcs_clear(shadow_vmcs); - vmx->vmcs01.shadow_vmcs = shadow_vmcs; - } - - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED); - vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; - - vmx->nested.vmxon = true; + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + return 1; + + ret = enter_vmx_operation(vcpu); + if (ret) + return ret; nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); - -out_shadow_vmcs: - kfree(vmx->nested.cached_vmcs12); - -out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); - -out_msr_bitmap: - return -ENOMEM; } /* @@ -7672,6 +7590,18 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } +static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) +{ + vmx->nested.current_vmptr = vmptr; + if (enable_shadow_vmcs) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); + vmcs_write64(VMCS_LINK_POINTER, + __pa(vmx->vmcs01.shadow_vmcs)); + vmx->nested.sync_shadow_vmcs = true; + } +} + /* Emulate the VMPTRLD instruction */ static int handle_vmptrld(struct kvm_vcpu *vcpu) { @@ -7702,7 +7632,6 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) } nested_release_vmcs12(vmx); - vmx->nested.current_vmptr = vmptr; vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; /* @@ -7711,14 +7640,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) */ memcpy(vmx->nested.cached_vmcs12, vmx->nested.current_vmcs12, VMCS12_SIZE); - - if (enable_shadow_vmcs) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, - __pa(vmx->vmcs01.shadow_vmcs)); - vmx->nested.sync_shadow_vmcs = true; - } + set_current_vmptr(vmx, vmptr); } nested_vmx_succeed(vcpu); @@ -8191,8 +8113,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: - if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return false; return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); @@ -8350,7 +8270,7 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", - name, vmcs_read32(sel), + name, vmcs_read16(sel), vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); @@ -8514,6 +8434,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 vectoring_info = vmx->idt_vectoring_info; trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + vcpu->arch.gpa_available = false; /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more @@ -8732,6 +8653,27 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) } } +static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int max_irr; + + WARN_ON(!vcpu->arch.apicv_active); + if (pi_test_on(&vmx->pi_desc)) { + pi_clear_on(&vmx->pi_desc); + /* + * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * But on x86 this is just a compiler barrier anyway. + */ + smp_mb__after_atomic(); + max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + } else { + max_irr = kvm_lapic_find_highest_irr(vcpu); + } + vmx_hwapic_irr_update(vcpu, max_irr); + return max_irr; +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -8743,6 +8685,14 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } +static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + pi_clear_on(&vmx->pi_desc); + memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); +} + static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -9588,17 +9538,16 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, kvm_inject_page_fault(vcpu, fault); } -static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, +static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12); + +static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); + u64 hpa; if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - if (!PAGE_ALIGNED(vmcs12->apic_access_addr) || - vmcs12->apic_access_addr >> maxphyaddr) - return false; - /* * Translate L1 physical address to host physical * address for vmcs02. Keep the page pinned, so this @@ -9609,59 +9558,80 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, nested_release_page(vmx->nested.apic_access_page); vmx->nested.apic_access_page = nested_get_page(vcpu, vmcs12->apic_access_addr); + /* + * If translation failed, no matter: This feature asks + * to exit when accessing the given address, and if it + * can never be accessed, this feature won't do + * anything anyway. + */ + if (vmx->nested.apic_access_page) { + hpa = page_to_phys(vmx->nested.apic_access_page); + vmcs_write64(APIC_ACCESS_ADDR, hpa); + } else { + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + } + } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && + cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + kvm_vcpu_reload_apic_access_page(vcpu); } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { - if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr) || - vmcs12->virtual_apic_page_addr >> maxphyaddr) - return false; - if (vmx->nested.virtual_apic_page) /* shouldn't happen */ nested_release_page(vmx->nested.virtual_apic_page); vmx->nested.virtual_apic_page = nested_get_page(vcpu, vmcs12->virtual_apic_page_addr); /* - * Failing the vm entry is _not_ what the processor does - * but it's basically the only possibility we have. - * We could still enter the guest if CR8 load exits are - * enabled, CR8 store exits are enabled, and virtualize APIC - * access is disabled; in this case the processor would never - * use the TPR shadow and we could simply clear the bit from - * the execution control. But such a configuration is useless, - * so let's keep the code simple. + * If translation failed, VM entry will fail because + * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull. + * Failing the vm entry is _not_ what the processor + * does but it's basically the only possibility we + * have. We could still enter the guest if CR8 load + * exits are enabled, CR8 store exits are enabled, and + * virtualize APIC access is disabled; in this case + * the processor would never use the TPR shadow and we + * could simply clear the bit from the execution + * control. But such a configuration is useless, so + * let's keep the code simple. */ - if (!vmx->nested.virtual_apic_page) - return false; + if (vmx->nested.virtual_apic_page) { + hpa = page_to_phys(vmx->nested.virtual_apic_page); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa); + } } if (nested_cpu_has_posted_intr(vmcs12)) { - if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64) || - vmcs12->posted_intr_desc_addr >> maxphyaddr) - return false; - if (vmx->nested.pi_desc_page) { /* shouldn't happen */ kunmap(vmx->nested.pi_desc_page); nested_release_page(vmx->nested.pi_desc_page); } vmx->nested.pi_desc_page = nested_get_page(vcpu, vmcs12->posted_intr_desc_addr); - if (!vmx->nested.pi_desc_page) - return false; - vmx->nested.pi_desc = (struct pi_desc *)kmap(vmx->nested.pi_desc_page); if (!vmx->nested.pi_desc) { nested_release_page_clean(vmx->nested.pi_desc_page); - return false; + return; } vmx->nested.pi_desc = (struct pi_desc *)((void *)vmx->nested.pi_desc + (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); + vmcs_write64(POSTED_INTR_DESC_ADDR, + page_to_phys(vmx->nested.pi_desc_page) + + (unsigned long)(vmcs12->posted_intr_desc_addr & + (PAGE_SIZE - 1))); } - - return true; + if (cpu_has_vmx_msr_bitmap() && + nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; + else + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); } static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) @@ -9730,11 +9700,6 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, return false; } msr_bitmap_l1 = (unsigned long *)kmap(page); - if (!msr_bitmap_l1) { - nested_release_page_clean(page); - WARN_ON(1); - return false; - } memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -9982,7 +9947,7 @@ static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) * is assigned to entry_failure_code on failure. */ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, - unsigned long *entry_failure_code) + u32 *entry_failure_code) { if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) { if (!nested_cr3_valid(vcpu, cr3)) { @@ -10022,7 +9987,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - unsigned long *entry_failure_code) + bool from_vmentry, u32 *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; @@ -10065,21 +10030,26 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); } - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - vmcs12->vm_entry_intr_info_field); - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, - vmcs12->vm_entry_exception_error_code); - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmcs12->vm_entry_instruction_len); - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, - vmcs12->guest_interruptibility_info); + if (from_vmentry) { + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, + vmcs12->vm_entry_intr_info_field); + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, + vmcs12->vm_entry_exception_error_code); + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, + vmcs12->vm_entry_instruction_len); + vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, + vmcs12->guest_interruptibility_info); + } else { + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); + } vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, @@ -10108,12 +10078,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); - vmcs_write64(POSTED_INTR_DESC_ADDR, - page_to_phys(vmx->nested.pi_desc_page) + - (unsigned long)(vmcs12->posted_intr_desc_addr & - (PAGE_SIZE - 1))); - } else + } else { exec_control &= ~PIN_BASED_POSTED_INTR; + } vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control); @@ -10158,26 +10125,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; - if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) { - /* - * If translation failed, no matter: This feature asks - * to exit when accessing the given address, and if it - * can never be accessed, this feature won't do - * anything anyway. - */ - if (!vmx->nested.apic_access_page) - exec_control &= - ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - else - vmcs_write64(APIC_ACCESS_ADDR, - page_to_phys(vmx->nested.apic_access_page)); - } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && - cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - exec_control |= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - kvm_vcpu_reload_apic_access_page(vcpu); - } - if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0); @@ -10192,6 +10139,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0; + + /* + * Write an illegal value to APIC_ACCESS_ADDR. Later, + * nested_get_vmcs12_pages will either fix it up or + * remove the VM execution control. + */ + if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) + vmcs_write64(APIC_ACCESS_ADDR, -1ull); + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } @@ -10228,19 +10184,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; + /* + * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if + * nested_get_vmcs12_pages can't fix it up, the illegal value + * will result in a VM entry failure. + */ if (exec_control & CPU_BASED_TPR_SHADOW) { - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - page_to_phys(vmx->nested.virtual_apic_page)); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); } - if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS && - nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) - ; /* MSR_BITMAP will be set by following vmx_set_efer. */ - else - exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; - /* * Merging of IO bitmap not currently supported. * Rather, exit every time. @@ -10272,16 +10225,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, ~VM_ENTRY_IA32E_MODE) | (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE)); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) { + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) { vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); vcpu->arch.pat = vmcs12->guest_ia32_pat; - } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - + } set_cr4_guest_host_mask(vmx); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) + if (from_vmentry && + vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) @@ -10320,8 +10275,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } /* - * This sets GUEST_CR0 to vmcs12->guest_cr0, with possibly a modified - * TS bit (for lazy fpu) and bits which we consider mandatory enabled. + * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those + * bits which we consider mandatory enabled. * The CR0_READ_SHADOW is what L2 should have expected to read given * the specifications by L1; It's not enough to take * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we @@ -10333,7 +10288,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_set_cr4(vcpu, vmcs12->guest_cr4); vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12)); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) vcpu->arch.efer = vmcs12->guest_ia32_efer; else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); @@ -10367,73 +10323,22 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, return 0; } -/* - * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1 - * for running an L2 nested guest. - */ -static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) +static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - int cpu; - struct loaded_vmcs *vmcs02; - bool ia32e; - u32 msr_entry_idx; - unsigned long exit_qualification; - - if (!nested_vmx_check_permission(vcpu)) - return 1; - - if (!nested_vmx_check_vmcs12(vcpu)) - goto out; - - vmcs12 = get_vmcs12(vcpu); - - if (enable_shadow_vmcs) - copy_shadow_to_vmcs12(vmx); - - /* - * The nested entry process starts with enforcing various prerequisites - * on vmcs12 as required by the Intel SDM, and act appropriately when - * they fail: As the SDM explains, some conditions should cause the - * instruction to fail, while others will cause the instruction to seem - * to succeed, but return an EXIT_REASON_INVALID_STATE. - * To speed up the normal (success) code path, we should avoid checking - * for misconfigurations which will anyway be caught by the processor - * when using the merged vmcs02. - */ - if (vmcs12->launch_state == launch) { - nested_vmx_failValid(vcpu, - launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS - : VMXERR_VMRESUME_NONLAUNCHED_VMCS); - goto out; - } if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && - vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (!nested_get_vmcs12_pages(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_apicv_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (nested_vmx_check_apicv_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } - - if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, vmx->nested.nested_vmx_procbased_ctls_low, @@ -10450,28 +10355,30 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !vmx_control_verify(vmcs12->vm_entry_controls, vmx->nested.nested_vmx_entry_ctls_low, vmx->nested.nested_vmx_entry_ctls_high)) - { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) || !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || - !nested_cr3_valid(vcpu, vmcs12->host_cr3)) { - nested_vmx_failValid(vcpu, - VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); - goto out; - } + !nested_cr3_valid(vcpu, vmcs12->host_cr3)) + return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD; + + return 0; +} + +static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + u32 *exit_qual) +{ + bool ia32e; + + *exit_qual = ENTRY_FAIL_DEFAULT; if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) || - !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) return 1; - } - if (vmcs12->vmcs_link_pointer != -1ull) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_VMCS_LINK_PTR); + + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS) && + vmcs12->vmcs_link_pointer != -1ull) { + *exit_qual = ENTRY_FAIL_VMCS_LINK_PTR; return 1; } @@ -10484,16 +10391,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * to bit 8 (LME) if bit 31 in the CR0 field (corresponding to * CR0.PG) is 1. */ - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) { + if (to_vmx(vcpu)->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || ((vmcs12->guest_cr0 & X86_CR0_PG) && - ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) return 1; - } } /* @@ -10507,28 +10412,26 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || - ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) return 1; - } } - /* - * We're finally done with prerequisite checking, and can start with - * the nested entry. - */ + return 0; +} + +static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct loaded_vmcs *vmcs02; + int cpu; + u32 msr_entry_idx; + u32 exit_qual; vmcs02 = nested_get_current_vmcs02(vmx); if (!vmcs02) return -ENOMEM; - /* - * After this point, the trap flag no longer triggers a singlestep trap - * on the vm entry instructions. Don't call - * kvm_skip_emulated_instruction. - */ - skip_emulated_instruction(vcpu); enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -10543,14 +10446,16 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmx_segment_cache_clear(vmx); - if (prepare_vmcs02(vcpu, vmcs12, &exit_qualification)) { + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { leave_guest_mode(vcpu); vmx_load_vmcs01(vcpu); nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, exit_qualification); + EXIT_REASON_INVALID_STATE, exit_qual); return 1; } + nested_get_vmcs12_pages(vcpu, vmcs12); + msr_entry_idx = nested_vmx_load_msr(vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); @@ -10564,17 +10469,90 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12->launch_state = 1; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) - return kvm_vcpu_halt(vcpu); - - vmx->nested.nested_run_pending = 1; - /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ + return 0; +} + +/* + * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1 + * for running an L2 nested guest. + */ +static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) +{ + struct vmcs12 *vmcs12; + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 exit_qual; + int ret; + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + if (!nested_vmx_check_vmcs12(vcpu)) + goto out; + + vmcs12 = get_vmcs12(vcpu); + + if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + + /* + * The nested entry process starts with enforcing various prerequisites + * on vmcs12 as required by the Intel SDM, and act appropriately when + * they fail: As the SDM explains, some conditions should cause the + * instruction to fail, while others will cause the instruction to seem + * to succeed, but return an EXIT_REASON_INVALID_STATE. + * To speed up the normal (success) code path, we should avoid checking + * for misconfigurations which will anyway be caught by the processor + * when using the merged vmcs02. + */ + if (vmcs12->launch_state == launch) { + nested_vmx_failValid(vcpu, + launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS + : VMXERR_VMRESUME_NONLAUNCHED_VMCS); + goto out; + } + + ret = check_vmentry_prereqs(vcpu, vmcs12); + if (ret) { + nested_vmx_failValid(vcpu, ret); + goto out; + } + + /* + * After this point, the trap flag no longer triggers a singlestep trap + * on the vm entry instructions; don't call kvm_skip_emulated_instruction. + * This is not 100% correct; for performance reasons, we delegate most + * of the checks on host state to the processor. If those fail, + * the singlestep trap is missed. + */ + skip_emulated_instruction(vcpu); + + ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual); + if (ret) { + nested_vmx_entry_failure(vcpu, vmcs12, + EXIT_REASON_INVALID_STATE, exit_qual); + return 1; + } + + /* + * We're finally done with prerequisite checking, and can start with + * the nested entry. + */ + + ret = enter_vmx_non_root_mode(vcpu, true); + if (ret) + return ret; + + if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + return kvm_vcpu_halt(vcpu); + + vmx->nested.nested_run_pending = 1; + return 1; out: @@ -10696,7 +10674,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - return vmx_complete_nested_posted_interrupt(vcpu); + vmx_complete_nested_posted_interrupt(vcpu); + return 0; } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -10714,21 +10693,13 @@ static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) } /* - * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits - * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), - * and this function updates it to reflect the changes to the guest state while - * L2 was running (and perhaps made some exits which were handled directly by L0 - * without going back to L1), and to reflect the exit reason. - * Note that we do not have to copy here all VMCS fields, just those that - * could have changed by the L2 guest or the exit - i.e., the guest-state and - * exit-information fields only. Other fields are modified by L1 with VMWRITE, - * which already writes to vmcs12 directly. + * Update the guest state fields of vmcs12 to reflect changes that + * occurred while L2 was running. (The "IA-32e mode guest" bit of the + * VM-entry controls is also updated, since this is really a guest + * state bit.) */ -static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - u32 exit_reason, u32 exit_intr_info, - unsigned long exit_qualification) +static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - /* update guest state fields: */ vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -10834,6 +10805,25 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); if (nested_cpu_has_xsaves(vmcs12)) vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP); +} + +/* + * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits + * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), + * and this function updates it to reflect the changes to the guest state while + * L2 was running (and perhaps made some exits which were handled directly by L0 + * without going back to L1), and to reflect the exit reason. + * Note that we do not have to copy here all VMCS fields, just those that + * could have changed by the L2 guest or the exit - i.e., the guest-state and + * exit-information fields only. Other fields are modified by L1 with VMWRITE, + * which already writes to vmcs12 directly. + */ +static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + u32 exit_reason, u32 exit_intr_info, + unsigned long exit_qualification) +{ + /* update guest state fields: */ + sync_vmcs12(vcpu, vmcs12); /* update exit information fields: */ @@ -10884,7 +10874,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct kvm_segment seg; - unsigned long entry_failure_code; + u32 entry_failure_code; if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; @@ -10899,24 +10889,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmx_set_rflags(vcpu, X86_EFLAGS_FIXED); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't - * actually changed, because it depends on the current state of - * fpu_active (which may have changed). - * Note that vmx_set_cr0 refers to efer set above. + * actually changed, because vmx_set_cr0 refers to efer set above. + * + * CR0_GUEST_HOST_MASK is already set in the original vmcs01 + * (KVM doesn't change it); */ + vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; vmx_set_cr0(vcpu, vmcs12->host_cr0); - /* - * If we did fpu_activate()/fpu_deactivate() during L2's run, we need - * to apply the same changes to L1's vmcs. We just set cr0 correctly, - * but we also need to update cr0_guest_host_mask and exception_bitmap. - */ - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = (vcpu->fpu_active ? X86_CR0_TS : 0); - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - /* - * Note that CR4_GUEST_HOST_MASK is already set in the original vmcs01 - * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask(); - */ + /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); kvm_set_cr4(vcpu, vmcs12->host_cr4); @@ -11545,9 +11526,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_pkru = vmx_get_pkru, - .fpu_activate = vmx_fpu_activate, - .fpu_deactivate = vmx_fpu_deactivate, - .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, @@ -11572,6 +11550,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_enable_apicv = vmx_get_enable_apicv, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, + .apicv_post_state_restore = vmx_apicv_post_state_restore, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .sync_pir_to_irr = vmx_sync_pir_to_irr, |