diff options
Diffstat (limited to 'arch/x86/kvm/vmx.c')
-rw-r--r-- | arch/x86/kvm/vmx.c | 2784 |
1 files changed, 2615 insertions, 169 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d48ec60ea421..e65a158dee64 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -43,13 +43,12 @@ #include "trace.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) +#define __ex_clear(x, reg) \ + ____kvm_handle_fault_on_reboot(x, "xor " reg " , " reg) MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static int __read_mostly bypass_guest_pf = 1; -module_param(bypass_guest_pf, bool, S_IRUGO); - static int __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); @@ -72,6 +71,14 @@ module_param(vmm_exclusive, bool, S_IRUGO); static int __read_mostly yield_on_hlt = 1; module_param(yield_on_hlt, bool, S_IRUGO); +/* + * If nested=1, nested virtualization is supported, i.e., guests may use + * VMX and be a hypervisor for its own guests. If nested=0, guests may not + * use VMX instructions. + */ +static int __read_mostly nested = 0; +module_param(nested, bool, S_IRUGO); + #define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \ (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD) #define KVM_GUEST_CR0_MASK \ @@ -109,6 +116,7 @@ static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, int, S_IRUGO); #define NR_AUTOLOAD_MSRS 1 +#define VMCS02_POOL_SIZE 1 struct vmcs { u32 revision_id; @@ -116,17 +124,237 @@ struct vmcs { char data[0]; }; +/* + * Track a VMCS that may be loaded on a certain CPU. If it is (cpu!=-1), also + * remember whether it was VMLAUNCHed, and maintain a linked list of all VMCSs + * loaded on this CPU (so we can clear them if the CPU goes down). + */ +struct loaded_vmcs { + struct vmcs *vmcs; + int cpu; + int launched; + struct list_head loaded_vmcss_on_cpu_link; +}; + struct shared_msr_entry { unsigned index; u64 data; u64 mask; }; +/* + * struct vmcs12 describes the state that our guest hypervisor (L1) keeps for a + * single nested guest (L2), hence the name vmcs12. Any VMX implementation has + * a VMCS structure, and vmcs12 is our emulated VMX's VMCS. This structure is + * stored in guest memory specified by VMPTRLD, but is opaque to the guest, + * which must access it using VMREAD/VMWRITE/VMCLEAR instructions. + * More than one of these structures may exist, if L1 runs multiple L2 guests. + * nested_vmx_run() will use the data here to build a vmcs02: a VMCS for the + * underlying hardware which will be used to run L2. + * This structure is packed to ensure that its layout is identical across + * machines (necessary for live migration). + * If there are changes in this struct, VMCS12_REVISION must be changed. + */ +typedef u64 natural_width; +struct __packed vmcs12 { + /* According to the Intel spec, a VMCS region must start with the + * following two fields. Then follow implementation-specific data. + */ + u32 revision_id; + u32 abort; + + u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */ + u32 padding[7]; /* room for future expansion */ + + u64 io_bitmap_a; + u64 io_bitmap_b; + u64 msr_bitmap; + u64 vm_exit_msr_store_addr; + u64 vm_exit_msr_load_addr; + u64 vm_entry_msr_load_addr; + u64 tsc_offset; + u64 virtual_apic_page_addr; + u64 apic_access_addr; + u64 ept_pointer; + u64 guest_physical_address; + u64 vmcs_link_pointer; + u64 guest_ia32_debugctl; + u64 guest_ia32_pat; + u64 guest_ia32_efer; + u64 guest_ia32_perf_global_ctrl; + u64 guest_pdptr0; + u64 guest_pdptr1; + u64 guest_pdptr2; + u64 guest_pdptr3; + u64 host_ia32_pat; + u64 host_ia32_efer; + u64 host_ia32_perf_global_ctrl; + u64 padding64[8]; /* room for future expansion */ + /* + * To allow migration of L1 (complete with its L2 guests) between + * machines of different natural widths (32 or 64 bit), we cannot have + * unsigned long fields with no explict size. We use u64 (aliased + * natural_width) instead. Luckily, x86 is little-endian. + */ + natural_width cr0_guest_host_mask; + natural_width cr4_guest_host_mask; + natural_width cr0_read_shadow; + natural_width cr4_read_shadow; + natural_width cr3_target_value0; + natural_width cr3_target_value1; + natural_width cr3_target_value2; + natural_width cr3_target_value3; + natural_width exit_qualification; + natural_width guest_linear_address; + natural_width guest_cr0; + natural_width guest_cr3; + natural_width guest_cr4; + natural_width guest_es_base; + natural_width guest_cs_base; + natural_width guest_ss_base; + natural_width guest_ds_base; + natural_width guest_fs_base; + natural_width guest_gs_base; + natural_width guest_ldtr_base; + natural_width guest_tr_base; + natural_width guest_gdtr_base; + natural_width guest_idtr_base; + natural_width guest_dr7; + natural_width guest_rsp; + natural_width guest_rip; + natural_width guest_rflags; + natural_width guest_pending_dbg_exceptions; + natural_width guest_sysenter_esp; + natural_width guest_sysenter_eip; + natural_width host_cr0; + natural_width host_cr3; + natural_width host_cr4; + natural_width host_fs_base; + natural_width host_gs_base; + natural_width host_tr_base; + natural_width host_gdtr_base; + natural_width host_idtr_base; + natural_width host_ia32_sysenter_esp; + natural_width host_ia32_sysenter_eip; + natural_width host_rsp; + natural_width host_rip; + natural_width paddingl[8]; /* room for future expansion */ + u32 pin_based_vm_exec_control; + u32 cpu_based_vm_exec_control; + u32 exception_bitmap; + u32 page_fault_error_code_mask; + u32 page_fault_error_code_match; + u32 cr3_target_count; + u32 vm_exit_controls; + u32 vm_exit_msr_store_count; + u32 vm_exit_msr_load_count; + u32 vm_entry_controls; + u32 vm_entry_msr_load_count; + u32 vm_entry_intr_info_field; + u32 vm_entry_exception_error_code; + u32 vm_entry_instruction_len; + u32 tpr_threshold; + u32 secondary_vm_exec_control; + u32 vm_instruction_error; + u32 vm_exit_reason; + u32 vm_exit_intr_info; + u32 vm_exit_intr_error_code; + u32 idt_vectoring_info_field; + u32 idt_vectoring_error_code; + u32 vm_exit_instruction_len; + u32 vmx_instruction_info; + u32 guest_es_limit; + u32 guest_cs_limit; + u32 guest_ss_limit; + u32 guest_ds_limit; + u32 guest_fs_limit; + u32 guest_gs_limit; + u32 guest_ldtr_limit; + u32 guest_tr_limit; + u32 guest_gdtr_limit; + u32 guest_idtr_limit; + u32 guest_es_ar_bytes; + u32 guest_cs_ar_bytes; + u32 guest_ss_ar_bytes; + u32 guest_ds_ar_bytes; + u32 guest_fs_ar_bytes; + u32 guest_gs_ar_bytes; + u32 guest_ldtr_ar_bytes; + u32 guest_tr_ar_bytes; + u32 guest_interruptibility_info; + u32 guest_activity_state; + u32 guest_sysenter_cs; + u32 host_ia32_sysenter_cs; + u32 padding32[8]; /* room for future expansion */ + u16 virtual_processor_id; + u16 guest_es_selector; + u16 guest_cs_selector; + u16 guest_ss_selector; + u16 guest_ds_selector; + u16 guest_fs_selector; + u16 guest_gs_selector; + u16 guest_ldtr_selector; + u16 guest_tr_selector; + u16 host_es_selector; + u16 host_cs_selector; + u16 host_ss_selector; + u16 host_ds_selector; + u16 host_fs_selector; + u16 host_gs_selector; + u16 host_tr_selector; +}; + +/* + * VMCS12_REVISION is an arbitrary id that should be changed if the content or + * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and + * VMPTRLD verifies that the VMCS region that L1 is loading contains this id. + */ +#define VMCS12_REVISION 0x11e57ed0 + +/* + * VMCS12_SIZE is the number of bytes L1 should allocate for the VMXON region + * and any VMCS region. Although only sizeof(struct vmcs12) are used by the + * current implementation, 4K are reserved to avoid future complications. + */ +#define VMCS12_SIZE 0x1000 + +/* Used to remember the last vmcs02 used for some recently used vmcs12s */ +struct vmcs02_list { + struct list_head list; + gpa_t vmptr; + struct loaded_vmcs vmcs02; +}; + +/* + * The nested_vmx structure is part of vcpu_vmx, and holds information we need + * for correct emulation of VMX (i.e., nested VMX) on this vcpu. + */ +struct nested_vmx { + /* Has the level1 guest done vmxon? */ + bool vmxon; + + /* The guest-physical address of the current VMCS L1 keeps for L2 */ + gpa_t current_vmptr; + /* The host-usable pointer to the above */ + struct page *current_vmcs12_page; + struct vmcs12 *current_vmcs12; + + /* vmcs02_list cache of VMCSs recently used to run L2 guests */ + struct list_head vmcs02_pool; + int vmcs02_num; + u64 vmcs01_tsc_offset; + /* L2 must run next, and mustn't decide to exit to L1. */ + bool nested_run_pending; + /* + * Guest pages referred to in vmcs02 with host-physical pointers, so + * we must keep them pinned while L2 runs. + */ + struct page *apic_access_page; +}; + struct vcpu_vmx { struct kvm_vcpu vcpu; - struct list_head local_vcpus_link; unsigned long host_rsp; - int launched; u8 fail; u8 cpl; bool nmi_known_unmasked; @@ -140,7 +368,14 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif - struct vmcs *vmcs; + /* + * loaded_vmcs points to the VMCS currently used in this vcpu. For a + * non-nested (L1) guest, it always points to vmcs01. For a nested + * guest (L2), it points to a different VMCS. + */ + struct loaded_vmcs vmcs01; + struct loaded_vmcs *loaded_vmcs; + bool __launched; /* temporary, used in vmx_vcpu_run */ struct msr_autoload { unsigned nr; struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS]; @@ -176,6 +411,9 @@ struct vcpu_vmx { u32 exit_reason; bool rdtscp_enabled; + + /* Support for a guest hypervisor (nested VMX) */ + struct nested_vmx nested; }; enum segment_cache_field { @@ -192,6 +430,174 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } +#define VMCS12_OFFSET(x) offsetof(struct vmcs12, x) +#define FIELD(number, name) [number] = VMCS12_OFFSET(name) +#define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ + [number##_HIGH] = VMCS12_OFFSET(name)+4 + +static unsigned short vmcs_field_to_offset_table[] = { + FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id), + FIELD(GUEST_ES_SELECTOR, guest_es_selector), + FIELD(GUEST_CS_SELECTOR, guest_cs_selector), + FIELD(GUEST_SS_SELECTOR, guest_ss_selector), + FIELD(GUEST_DS_SELECTOR, guest_ds_selector), + FIELD(GUEST_FS_SELECTOR, guest_fs_selector), + FIELD(GUEST_GS_SELECTOR, guest_gs_selector), + FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector), + FIELD(GUEST_TR_SELECTOR, guest_tr_selector), + FIELD(HOST_ES_SELECTOR, host_es_selector), + FIELD(HOST_CS_SELECTOR, host_cs_selector), + FIELD(HOST_SS_SELECTOR, host_ss_selector), + FIELD(HOST_DS_SELECTOR, host_ds_selector), + FIELD(HOST_FS_SELECTOR, host_fs_selector), + FIELD(HOST_GS_SELECTOR, host_gs_selector), + FIELD(HOST_TR_SELECTOR, host_tr_selector), + FIELD64(IO_BITMAP_A, io_bitmap_a), + FIELD64(IO_BITMAP_B, io_bitmap_b), + FIELD64(MSR_BITMAP, msr_bitmap), + FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr), + FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr), + FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr), + FIELD64(TSC_OFFSET, tsc_offset), + FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr), + FIELD64(APIC_ACCESS_ADDR, apic_access_addr), + FIELD64(EPT_POINTER, ept_pointer), + FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address), + FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer), + FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl), + FIELD64(GUEST_IA32_PAT, guest_ia32_pat), + FIELD64(GUEST_IA32_EFER, guest_ia32_efer), + FIELD64(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl), + FIELD64(GUEST_PDPTR0, guest_pdptr0), + FIELD64(GUEST_PDPTR1, guest_pdptr1), + FIELD64(GUEST_PDPTR2, guest_pdptr2), + FIELD64(GUEST_PDPTR3, guest_pdptr3), + FIELD64(HOST_IA32_PAT, host_ia32_pat), + FIELD64(HOST_IA32_EFER, host_ia32_efer), + FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl), + FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control), + FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control), + FIELD(EXCEPTION_BITMAP, exception_bitmap), + FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask), + FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match), + FIELD(CR3_TARGET_COUNT, cr3_target_count), + FIELD(VM_EXIT_CONTROLS, vm_exit_controls), + FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count), + FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count), + FIELD(VM_ENTRY_CONTROLS, vm_entry_controls), + FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count), + FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field), + FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, vm_entry_exception_error_code), + FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len), + FIELD(TPR_THRESHOLD, tpr_threshold), + FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control), + FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error), + FIELD(VM_EXIT_REASON, vm_exit_reason), + FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info), + FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code), + FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field), + FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code), + FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len), + FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info), + FIELD(GUEST_ES_LIMIT, guest_es_limit), + FIELD(GUEST_CS_LIMIT, guest_cs_limit), + FIELD(GUEST_SS_LIMIT, guest_ss_limit), + FIELD(GUEST_DS_LIMIT, guest_ds_limit), + FIELD(GUEST_FS_LIMIT, guest_fs_limit), + FIELD(GUEST_GS_LIMIT, guest_gs_limit), + FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit), + FIELD(GUEST_TR_LIMIT, guest_tr_limit), + FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit), + FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit), + FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes), + FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes), + FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes), + FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes), + FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes), + FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes), + FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes), + FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes), + FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info), + FIELD(GUEST_ACTIVITY_STATE, guest_activity_state), + FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs), + FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs), + FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask), + FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask), + FIELD(CR0_READ_SHADOW, cr0_read_shadow), + FIELD(CR4_READ_SHADOW, cr4_read_shadow), + FIELD(CR3_TARGET_VALUE0, cr3_target_value0), + FIELD(CR3_TARGET_VALUE1, cr3_target_value1), + FIELD(CR3_TARGET_VALUE2, cr3_target_value2), + FIELD(CR3_TARGET_VALUE3, cr3_target_value3), + FIELD(EXIT_QUALIFICATION, exit_qualification), + FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address), + FIELD(GUEST_CR0, guest_cr0), + FIELD(GUEST_CR3, guest_cr3), + FIELD(GUEST_CR4, guest_cr4), + FIELD(GUEST_ES_BASE, guest_es_base), + FIELD(GUEST_CS_BASE, guest_cs_base), + FIELD(GUEST_SS_BASE, guest_ss_base), + FIELD(GUEST_DS_BASE, guest_ds_base), + FIELD(GUEST_FS_BASE, guest_fs_base), + FIELD(GUEST_GS_BASE, guest_gs_base), + FIELD(GUEST_LDTR_BASE, guest_ldtr_base), + FIELD(GUEST_TR_BASE, guest_tr_base), + FIELD(GUEST_GDTR_BASE, guest_gdtr_base), + FIELD(GUEST_IDTR_BASE, guest_idtr_base), + FIELD(GUEST_DR7, guest_dr7), + FIELD(GUEST_RSP, guest_rsp), + FIELD(GUEST_RIP, guest_rip), + FIELD(GUEST_RFLAGS, guest_rflags), + FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions), + FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp), + FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip), + FIELD(HOST_CR0, host_cr0), + FIELD(HOST_CR3, host_cr3), + FIELD(HOST_CR4, host_cr4), + FIELD(HOST_FS_BASE, host_fs_base), + FIELD(HOST_GS_BASE, host_gs_base), + FIELD(HOST_TR_BASE, host_tr_base), + FIELD(HOST_GDTR_BASE, host_gdtr_base), + FIELD(HOST_IDTR_BASE, host_idtr_base), + FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp), + FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip), + FIELD(HOST_RSP, host_rsp), + FIELD(HOST_RIP, host_rip), +}; +static const int max_vmcs_field = ARRAY_SIZE(vmcs_field_to_offset_table); + +static inline short vmcs_field_to_offset(unsigned long field) +{ + if (field >= max_vmcs_field || vmcs_field_to_offset_table[field] == 0) + return -1; + return vmcs_field_to_offset_table[field]; +} + +static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.current_vmcs12; +} + +static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr) +{ + struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT); + if (is_error_page(page)) { + kvm_release_page_clean(page); + return NULL; + } + return page; +} + +static void nested_release_page(struct page *page) +{ + kvm_release_page_dirty(page); +} + +static void nested_release_page_clean(struct page *page) +{ + kvm_release_page_clean(page); +} + static u64 construct_eptp(unsigned long root_hpa); static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); @@ -200,7 +606,11 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); -static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu); +/* + * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed + * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it. + */ +static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DEFINE_PER_CPU(struct desc_ptr, host_gdt); static unsigned long *vmx_io_bitmap_a; @@ -442,6 +852,35 @@ static inline bool report_flexpriority(void) return flexpriority_enabled; } +static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit) +{ + return vmcs12->cpu_based_vm_exec_control & bit; +} + +static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit) +{ + return (vmcs12->cpu_based_vm_exec_control & + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) && + (vmcs12->secondary_vm_exec_control & bit); +} + +static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12, + struct kvm_vcpu *vcpu) +{ + return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; +} + +static inline bool is_exception(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) + == (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK); +} + +static void nested_vmx_vmexit(struct kvm_vcpu *vcpu); +static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12, + u32 reason, unsigned long qualification); + static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -501,6 +940,13 @@ static void vmcs_clear(struct vmcs *vmcs) vmcs, phys_addr); } +static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) +{ + vmcs_clear(loaded_vmcs->vmcs); + loaded_vmcs->cpu = -1; + loaded_vmcs->launched = 0; +} + static void vmcs_load(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); @@ -510,29 +956,28 @@ static void vmcs_load(struct vmcs *vmcs) : "=qm"(error) : "a"(&phys_addr), "m"(phys_addr) : "cc", "memory"); if (error) - printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n", + printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n", vmcs, phys_addr); } -static void __vcpu_clear(void *arg) +static void __loaded_vmcs_clear(void *arg) { - struct vcpu_vmx *vmx = arg; + struct loaded_vmcs *loaded_vmcs = arg; int cpu = raw_smp_processor_id(); - if (vmx->vcpu.cpu == cpu) - vmcs_clear(vmx->vmcs); - if (per_cpu(current_vmcs, cpu) == vmx->vmcs) + if (loaded_vmcs->cpu != cpu) + return; /* vcpu migration can race with cpu offline */ + if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) per_cpu(current_vmcs, cpu) = NULL; - list_del(&vmx->local_vcpus_link); - vmx->vcpu.cpu = -1; - vmx->launched = 0; + list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); + loaded_vmcs_init(loaded_vmcs); } -static void vcpu_clear(struct vcpu_vmx *vmx) +static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) { - if (vmx->vcpu.cpu == -1) - return; - smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, vmx, 1); + if (loaded_vmcs->cpu != -1) + smp_call_function_single( + loaded_vmcs->cpu, __loaded_vmcs_clear, loaded_vmcs, 1); } static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx) @@ -585,26 +1030,26 @@ static inline void ept_sync_individual_addr(u64 eptp, gpa_t gpa) } } -static unsigned long vmcs_readl(unsigned long field) +static __always_inline unsigned long vmcs_readl(unsigned long field) { - unsigned long value = 0; + unsigned long value; - asm volatile (__ex(ASM_VMX_VMREAD_RDX_RAX) - : "+a"(value) : "d"(field) : "cc"); + asm volatile (__ex_clear(ASM_VMX_VMREAD_RDX_RAX, "%0") + : "=a"(value) : "d"(field) : "cc"); return value; } -static u16 vmcs_read16(unsigned long field) +static __always_inline u16 vmcs_read16(unsigned long field) { return vmcs_readl(field); } -static u32 vmcs_read32(unsigned long field) +static __always_inline u32 vmcs_read32(unsigned long field) { return vmcs_readl(field); } -static u64 vmcs_read64(unsigned long field) +static __always_inline u64 vmcs_read64(unsigned long field) { #ifdef CONFIG_X86_64 return vmcs_readl(field); @@ -731,6 +1176,15 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) 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 + * them to L1. When running L2, we will only handle the exceptions + * specified above if L1 did not want them. + */ + if (is_guest_mode(vcpu)) + eb |= get_vmcs12(vcpu)->exception_bitmap; + vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -971,22 +1425,22 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (!vmm_exclusive) kvm_cpu_vmxon(phys_addr); - else if (vcpu->cpu != cpu) - vcpu_clear(vmx); + else if (vmx->loaded_vmcs->cpu != cpu) + loaded_vmcs_clear(vmx->loaded_vmcs); - if (per_cpu(current_vmcs, cpu) != vmx->vmcs) { - per_cpu(current_vmcs, cpu) = vmx->vmcs; - vmcs_load(vmx->vmcs); + if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { + per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; + vmcs_load(vmx->loaded_vmcs->vmcs); } - if (vcpu->cpu != cpu) { + if (vmx->loaded_vmcs->cpu != cpu) { struct desc_ptr *gdt = &__get_cpu_var(host_gdt); unsigned long sysenter_esp; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); local_irq_disable(); - list_add(&vmx->local_vcpus_link, - &per_cpu(vcpus_on_cpu, cpu)); + list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, + &per_cpu(loaded_vmcss_on_cpu, cpu)); local_irq_enable(); /* @@ -998,6 +1452,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + vmx->loaded_vmcs->cpu = cpu; } } @@ -1005,7 +1460,8 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { __vmx_load_host_state(to_vmx(vcpu)); if (!vmm_exclusive) { - __vcpu_clear(to_vmx(vcpu)); + __loaded_vmcs_clear(to_vmx(vcpu)->loaded_vmcs); + vcpu->cpu = -1; kvm_cpu_vmxoff(); } } @@ -1023,19 +1479,55 @@ static void vmx_fpu_activate(struct kvm_vcpu *vcpu) 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); +/* + * Return the cr0 value that a nested guest would read. This is a combination + * of the real cr0 used to run the guest (guest_cr0), and the bits shadowed by + * its hypervisor (cr0_read_shadow). + */ +static inline unsigned long nested_read_cr0(struct vmcs12 *fields) +{ + return (fields->guest_cr0 & ~fields->cr0_guest_host_mask) | + (fields->cr0_read_shadow & fields->cr0_guest_host_mask); +} +static inline unsigned long nested_read_cr4(struct vmcs12 *fields) +{ + return (fields->guest_cr4 & ~fields->cr4_guest_host_mask) | + (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); - vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); + 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) @@ -1119,6 +1611,25 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); } +/* + * KVM wants to inject page-faults which it got to the guest. This function + * checks whether in a nested guest, we need to inject them to L1 or L2. + * This function assumes it is called with the exit reason in vmcs02 being + * a #PF exception (this is the only case in which KVM injects a #PF when L2 + * is running). + */ +static int nested_pf_handled(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + /* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */ + if (!(vmcs12->exception_bitmap & PF_VECTOR)) + return 0; + + nested_vmx_vmexit(vcpu); + return 1; +} + static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error_code, u32 error_code, bool reinject) @@ -1126,6 +1637,10 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, struct vcpu_vmx *vmx = to_vmx(vcpu); u32 intr_info = nr | INTR_INFO_VALID_MASK; + if (nr == PF_VECTOR && is_guest_mode(vcpu) && + nested_pf_handled(vcpu)) + return; + if (has_error_code) { vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; @@ -1248,12 +1763,24 @@ static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { vmcs_write64(TSC_OFFSET, offset); + if (is_guest_mode(vcpu)) + /* + * We're here if L1 chose not to trap the TSC MSR. Since + * prepare_vmcs12() does not copy tsc_offset, we need to also + * set the vmcs12 field here. + */ + get_vmcs12(vcpu)->tsc_offset = offset - + to_vmx(vcpu)->nested.vmcs01_tsc_offset; } static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) { u64 offset = vmcs_read64(TSC_OFFSET); vmcs_write64(TSC_OFFSET, offset + adjustment); + if (is_guest_mode(vcpu)) { + /* Even when running L2, the adjustment needs to apply to L1 */ + to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment; + } } static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) @@ -1261,6 +1788,236 @@ static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) return target_tsc - native_read_tsc(); } +static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->ecx & (1 << (X86_FEATURE_VMX & 31))); +} + +/* + * nested_vmx_allowed() checks whether a guest should be allowed to use VMX + * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for + * all guests if the "nested" module option is off, and can also be disabled + * for a single guest by disabling its VMX cpuid bit. + */ +static inline bool nested_vmx_allowed(struct kvm_vcpu *vcpu) +{ + return nested && guest_cpuid_has_vmx(vcpu); +} + +/* + * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be + * returned for the various VMX controls MSRs when nested VMX is enabled. + * The same values should also be used to verify that vmcs12 control fields are + * valid during nested entry from L1 to L2. + * Each of these control msrs has a low and high 32-bit half: A low bit is on + * if the corresponding bit in the (32-bit) control field *must* be on, and a + * bit in the high half is on if the corresponding bit in the control field + * may be on. See also vmx_control_verify(). + * TODO: allow these variables to be modified (downgraded) by module options + * or other means. + */ +static u32 nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high; +static u32 nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high; +static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high; +static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high; +static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high; +static __init void nested_vmx_setup_ctls_msrs(void) +{ + /* + * Note that as a general rule, the high half of the MSRs (bits in + * the control fields which may be 1) should be initialized by the + * intersection of the underlying hardware's MSR (i.e., features which + * can be supported) and the list of features we want to expose - + * because they are known to be properly supported in our code. + * Also, usually, the low half of the MSRs (bits which must be 1) can + * be set to 0, meaning that L1 may turn off any of these bits. The + * reason is that if one of these bits is necessary, it will appear + * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control + * fields of vmcs01 and vmcs02, will turn these bits off - and + * nested_vmx_exit_handled() will not pass related exits to L1. + * These rules have exceptions below. + */ + + /* pin-based controls */ + /* + * According to the Intel spec, if bit 55 of VMX_BASIC is off (as it is + * in our case), bits 1, 2 and 4 (i.e., 0x16) must be 1 in this MSR. + */ + nested_vmx_pinbased_ctls_low = 0x16 ; + nested_vmx_pinbased_ctls_high = 0x16 | + PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | + PIN_BASED_VIRTUAL_NMIS; + + /* exit controls */ + nested_vmx_exit_ctls_low = 0; + /* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */ +#ifdef CONFIG_X86_64 + nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE; +#else + nested_vmx_exit_ctls_high = 0; +#endif + + /* entry controls */ + rdmsr(MSR_IA32_VMX_ENTRY_CTLS, + nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high); + nested_vmx_entry_ctls_low = 0; + nested_vmx_entry_ctls_high &= + VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE; + + /* cpu-based controls */ + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, + nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high); + nested_vmx_procbased_ctls_low = 0; + nested_vmx_procbased_ctls_high &= + CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_USE_TSC_OFFSETING | + CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING | + CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING | + CPU_BASED_CR3_STORE_EXITING | +#ifdef CONFIG_X86_64 + CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | +#endif + CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | + CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; + /* + * We can allow some features even when not supported by the + * hardware. For example, L1 can specify an MSR bitmap - and we + * can use it to avoid exits to L1 - even when L0 runs L2 + * without MSR bitmaps. + */ + nested_vmx_procbased_ctls_high |= CPU_BASED_USE_MSR_BITMAPS; + + /* secondary cpu-based controls */ + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, + nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high); + nested_vmx_secondary_ctls_low = 0; + nested_vmx_secondary_ctls_high &= + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; +} + +static inline bool vmx_control_verify(u32 control, u32 low, u32 high) +{ + /* + * Bits 0 in high must be 0, and bits 1 in low must be 1. + */ + return ((control & high) | low) == control; +} + +static inline u64 vmx_control_msr(u32 low, u32 high) +{ + return low | ((u64)high << 32); +} + +/* + * If we allow our guest to use VMX instructions (i.e., nested VMX), we should + * also let it use VMX-specific MSRs. + * vmx_get_vmx_msr() and vmx_set_vmx_msr() return 1 when we handled a + * VMX-specific MSR, or 0 when we haven't (and the caller should handle it + * like all other MSRs). + */ +static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +{ + if (!nested_vmx_allowed(vcpu) && msr_index >= MSR_IA32_VMX_BASIC && + msr_index <= MSR_IA32_VMX_TRUE_ENTRY_CTLS) { + /* + * According to the spec, processors which do not support VMX + * should throw a #GP(0) when VMX capability MSRs are read. + */ + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + + switch (msr_index) { + case MSR_IA32_FEATURE_CONTROL: + *pdata = 0; + break; + case MSR_IA32_VMX_BASIC: + /* + * This MSR reports some information about VMX support. We + * should return information about the VMX we emulate for the + * guest, and the VMCS structure we give it - not about the + * VMX support of the underlying hardware. + */ + *pdata = VMCS12_REVISION | + ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | + (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); + break; + case MSR_IA32_VMX_TRUE_PINBASED_CTLS: + case MSR_IA32_VMX_PINBASED_CTLS: + *pdata = vmx_control_msr(nested_vmx_pinbased_ctls_low, + nested_vmx_pinbased_ctls_high); + break; + case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: + case MSR_IA32_VMX_PROCBASED_CTLS: + *pdata = vmx_control_msr(nested_vmx_procbased_ctls_low, + nested_vmx_procbased_ctls_high); + break; + case MSR_IA32_VMX_TRUE_EXIT_CTLS: + case MSR_IA32_VMX_EXIT_CTLS: + *pdata = vmx_control_msr(nested_vmx_exit_ctls_low, + nested_vmx_exit_ctls_high); + break; + case MSR_IA32_VMX_TRUE_ENTRY_CTLS: + case MSR_IA32_VMX_ENTRY_CTLS: + *pdata = vmx_control_msr(nested_vmx_entry_ctls_low, + nested_vmx_entry_ctls_high); + break; + case MSR_IA32_VMX_MISC: + *pdata = 0; + break; + /* + * These MSRs specify bits which the guest must keep fixed (on or off) + * while L1 is in VMXON mode (in L1's root mode, or running an L2). + * We picked the standard core2 setting. + */ +#define VMXON_CR0_ALWAYSON (X86_CR0_PE | X86_CR0_PG | X86_CR0_NE) +#define VMXON_CR4_ALWAYSON X86_CR4_VMXE + case MSR_IA32_VMX_CR0_FIXED0: + *pdata = VMXON_CR0_ALWAYSON; + break; + case MSR_IA32_VMX_CR0_FIXED1: + *pdata = -1ULL; + break; + case MSR_IA32_VMX_CR4_FIXED0: + *pdata = VMXON_CR4_ALWAYSON; + break; + case MSR_IA32_VMX_CR4_FIXED1: + *pdata = -1ULL; + break; + case MSR_IA32_VMX_VMCS_ENUM: + *pdata = 0x1f; + break; + case MSR_IA32_VMX_PROCBASED_CTLS2: + *pdata = vmx_control_msr(nested_vmx_secondary_ctls_low, + nested_vmx_secondary_ctls_high); + break; + case MSR_IA32_VMX_EPT_VPID_CAP: + /* Currently, no nested ept or nested vpid */ + *pdata = 0; + break; + default: + return 0; + } + + return 1; +} + +static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) +{ + if (!nested_vmx_allowed(vcpu)) + return 0; + + if (msr_index == MSR_IA32_FEATURE_CONTROL) + /* TODO: the right thing. */ + return 1; + /* + * No need to treat VMX capability MSRs specially: If we don't handle + * them, handle_wrmsr will #GP(0), which is correct (they are readonly) + */ + return 0; +} + /* * Reads an msr value (of 'msr_index') into 'pdata'. * Returns 0 on success, non-0 otherwise. @@ -1309,6 +2066,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) /* Otherwise falls through */ default: vmx_load_host_state(to_vmx(vcpu)); + if (vmx_get_vmx_msr(vcpu, msr_index, pdata)) + return 0; msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { vmx_load_host_state(to_vmx(vcpu)); @@ -1380,6 +2139,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) return 1; /* Otherwise falls through */ default: + if (vmx_set_vm |