diff options
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 364 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 351 |
2 files changed, 352 insertions, 363 deletions
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index ebe500f48bdf..6e3da6486471 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -60,6 +60,7 @@ #include "vmcs.h" #include "vmcs12.h" #include "x86.h" +#include "vmx.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) #define __ex_clear(x, reg) \ @@ -120,10 +121,6 @@ static u64 __read_mostly host_xss; bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -#define MSR_TYPE_RW 3 - #define MSR_BITMAP_MODE_X2APIC 1 #define MSR_BITMAP_MODE_X2APIC_APICV 2 @@ -345,317 +342,6 @@ static const struct kernel_param_ops vmentry_l1d_flush_ops = { }; module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); -enum ept_pointers_status { - EPT_POINTERS_CHECK = 0, - EPT_POINTERS_MATCH = 1, - EPT_POINTERS_MISMATCH = 2 -}; - -struct kvm_vmx { - struct kvm kvm; - - unsigned int tss_addr; - bool ept_identity_pagetable_done; - gpa_t ept_identity_map_addr; - - enum ept_pointers_status ept_pointers_match; - spinlock_t ept_pointer_lock; -}; - -struct shared_msr_entry { - unsigned index; - u64 data; - u64 mask; -}; - -/* - * 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; - gpa_t vmxon_ptr; - bool pml_full; - - /* The guest-physical address of the current VMCS L1 keeps for L2 */ - gpa_t current_vmptr; - /* - * Cache of the guest's VMCS, existing outside of guest memory. - * Loaded from guest memory during VMPTRLD. Flushed to guest - * memory during VMCLEAR and VMPTRLD. - */ - struct vmcs12 *cached_vmcs12; - /* - * Cache of the guest's shadow VMCS, existing outside of guest - * memory. Loaded from guest memory during VM entry. Flushed - * to guest memory during VM exit. - */ - struct vmcs12 *cached_shadow_vmcs12; - /* - * Indicates if the shadow vmcs or enlightened vmcs must be updated - * with the data held by struct vmcs12. - */ - bool need_vmcs12_sync; - bool dirty_vmcs12; - - /* - * vmcs02 has been initialized, i.e. state that is constant for - * vmcs02 has been written to the backing VMCS. Initialization - * is delayed until L1 actually attempts to run a nested VM. - */ - bool vmcs02_initialized; - - bool change_vmcs01_virtual_apic_mode; - - /* - * Enlightened VMCS has been enabled. It does not mean that L1 has to - * use it. However, VMX features available to L1 will be limited based - * on what the enlightened VMCS supports. - */ - bool enlightened_vmcs_enabled; - - /* L2 must run next, and mustn't decide to exit to L1. */ - bool nested_run_pending; - - struct loaded_vmcs vmcs02; - - /* - * Guest pages referred to in the vmcs02 with host-physical - * pointers, so we must keep them pinned while L2 runs. - */ - struct page *apic_access_page; - struct page *virtual_apic_page; - struct page *pi_desc_page; - struct pi_desc *pi_desc; - bool pi_pending; - u16 posted_intr_nv; - - struct hrtimer preemption_timer; - bool preemption_timer_expired; - - /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ - u64 vmcs01_debugctl; - u64 vmcs01_guest_bndcfgs; - - u16 vpid02; - u16 last_vpid; - - struct nested_vmx_msrs msrs; - - /* SMM related state */ - struct { - /* in VMX operation on SMM entry? */ - bool vmxon; - /* in guest mode on SMM entry? */ - bool guest_mode; - } smm; - - gpa_t hv_evmcs_vmptr; - struct page *hv_evmcs_page; - struct hv_enlightened_vmcs *hv_evmcs; -}; - -#define POSTED_INTR_ON 0 -#define POSTED_INTR_SN 1 - -/* Posted-Interrupt Descriptor */ -struct pi_desc { - u32 pir[8]; /* Posted interrupt requested */ - union { - struct { - /* bit 256 - Outstanding Notification */ - u16 on : 1, - /* bit 257 - Suppress Notification */ - sn : 1, - /* bit 271:258 - Reserved */ - rsvd_1 : 14; - /* bit 279:272 - Notification Vector */ - u8 nv; - /* bit 287:280 - Reserved */ - u8 rsvd_2; - /* bit 319:288 - Notification Destination */ - u32 ndst; - }; - u64 control; - }; - u32 rsvd[6]; -} __aligned(64); - -static bool pi_test_and_set_on(struct pi_desc *pi_desc) -{ - return test_and_set_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static bool pi_test_and_clear_on(struct pi_desc *pi_desc) -{ - return test_and_clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) -{ - return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); -} - -static inline void pi_clear_sn(struct pi_desc *pi_desc) -{ - return clear_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_set_sn(struct pi_desc *pi_desc) -{ - return set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_clear_on(struct pi_desc *pi_desc) -{ - clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline int pi_test_on(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline int pi_test_sn(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -#define NR_AUTOLOAD_MSRS 8 - -struct vmx_msrs { - unsigned int nr; - struct vmx_msr_entry val[NR_AUTOLOAD_MSRS]; -}; - -struct vcpu_vmx { - struct kvm_vcpu vcpu; - unsigned long host_rsp; - u8 fail; - u8 msr_bitmap_mode; - u32 exit_intr_info; - u32 idt_vectoring_info; - ulong rflags; - struct shared_msr_entry *guest_msrs; - int nmsrs; - int save_nmsrs; - bool guest_msrs_dirty; - unsigned long host_idt_base; -#ifdef CONFIG_X86_64 - u64 msr_host_kernel_gs_base; - u64 msr_guest_kernel_gs_base; -#endif - - u64 arch_capabilities; - u64 spec_ctrl; - - u32 vm_entry_controls_shadow; - u32 vm_exit_controls_shadow; - u32 secondary_exec_control; - - /* - * 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. loaded_cpu_state points - * to the VMCS whose state is loaded into the CPU registers that only - * need to be switched when transitioning to/from the kernel; a NULL - * value indicates that host state is loaded. - */ - struct loaded_vmcs vmcs01; - struct loaded_vmcs *loaded_vmcs; - struct loaded_vmcs *loaded_cpu_state; - bool __launched; /* temporary, used in vmx_vcpu_run */ - struct msr_autoload { - struct vmx_msrs guest; - struct vmx_msrs host; - } msr_autoload; - - struct { - int vm86_active; - ulong save_rflags; - struct kvm_segment segs[8]; - } rmode; - struct { - u32 bitmask; /* 4 bits per segment (1 bit per field) */ - struct kvm_save_segment { - u16 selector; - unsigned long base; - u32 limit; - u32 ar; - } seg[8]; - } segment_cache; - int vpid; - bool emulation_required; - - u32 exit_reason; - - /* Posted interrupt descriptor */ - struct pi_desc pi_desc; - - /* Support for a guest hypervisor (nested VMX) */ - struct nested_vmx nested; - - /* Dynamic PLE window. */ - int ple_window; - bool ple_window_dirty; - - bool req_immediate_exit; - - /* Support for PML */ -#define PML_ENTITY_NUM 512 - struct page *pml_pg; - - /* apic deadline value in host tsc */ - u64 hv_deadline_tsc; - - u64 current_tsc_ratio; - - u32 host_pkru; - - unsigned long host_debugctlmsr; - - /* - * Only bits masked by msr_ia32_feature_control_valid_bits can be set in - * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included - * in msr_ia32_feature_control_valid_bits. - */ - u64 msr_ia32_feature_control; - u64 msr_ia32_feature_control_valid_bits; - u64 ept_pointer; -}; - -enum segment_cache_field { - SEG_FIELD_SEL = 0, - SEG_FIELD_BASE = 1, - SEG_FIELD_LIMIT = 2, - SEG_FIELD_AR = 3, - - SEG_FIELD_NR = 4 -}; - -static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) -{ - return container_of(kvm, struct kvm_vmx, kvm); -} - -static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) -{ - return container_of(vcpu, struct vcpu_vmx, vcpu); -} - -static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) -{ - return &(to_vmx(vcpu)->pi_desc); -} - static u16 shadow_read_only_fields[] = { #define SHADOW_FIELD_RO(x) x, #include "vmcs_shadow_fields.h" @@ -1625,11 +1311,6 @@ static inline void vm_exit_controls_clearbit(struct vcpu_vmx *vmx, u32 val) vm_exit_controls_set(vmx, vm_exit_controls_get(vmx) & ~val); } -static void vmx_segment_cache_clear(struct vcpu_vmx *vmx) -{ - vmx->segment_cache.bitmask = 0; -} - static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, unsigned field) { @@ -5152,8 +4833,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) return mode; } -#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) - static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, u8 mode) { @@ -5478,47 +5157,6 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) vmx_update_msr_bitmap(vcpu); } -static u32 vmx_vmentry_ctrl(void) -{ - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmcs_config.vmentry_ctrl & - ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); -} - -static u32 vmx_vmexit_ctrl(void) -{ - /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ - return vmcs_config.vmexit_ctrl & - ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); -} - -static u32 vmx_exec_control(struct vcpu_vmx *vmx) -{ - u32 exec_control = vmcs_config.cpu_based_exec_ctrl; - - if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) - exec_control &= ~CPU_BASED_MOV_DR_EXITING; - - if (!cpu_need_tpr_shadow(&vmx->vcpu)) { - exec_control &= ~CPU_BASED_TPR_SHADOW; -#ifdef CONFIG_X86_64 - exec_control |= CPU_BASED_CR8_STORE_EXITING | - CPU_BASED_CR8_LOAD_EXITING; -#endif - } - if (!enable_ept) - exec_control |= CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_INVLPG_EXITING; - if (kvm_mwait_in_guest(vmx->vcpu.kvm)) - exec_control &= ~(CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING); - if (kvm_hlt_in_guest(vmx->vcpu.kvm)) - exec_control &= ~CPU_BASED_HLT_EXITING; - return exec_control; -} - - static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) { struct kvm_vcpu *vcpu = &vmx->vcpu; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h new file mode 100644 index 000000000000..c9aa150aa014 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx.h @@ -0,0 +1,351 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __KVM_X86_VMX_H +#define __KVM_X86_VMX_H + +#include <linux/kvm_host.h> + +#include <asm/kvm.h> + +#include "capabilities.h" +#include "vmcs.h" + +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +#define MSR_TYPE_RW 3 + +#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) + +#define NR_AUTOLOAD_MSRS 8 + +struct vmx_msrs { + unsigned int nr; + struct vmx_msr_entry val[NR_AUTOLOAD_MSRS]; +}; + +struct shared_msr_entry { + unsigned index; + u64 data; + u64 mask; +}; + +enum segment_cache_field { + SEG_FIELD_SEL = 0, + SEG_FIELD_BASE = 1, + SEG_FIELD_LIMIT = 2, + SEG_FIELD_AR = 3, + + SEG_FIELD_NR = 4 +}; + +/* Posted-Interrupt Descriptor */ +struct pi_desc { + u32 pir[8]; /* Posted interrupt requested */ + union { + struct { + /* bit 256 - Outstanding Notification */ + u16 on : 1, + /* bit 257 - Suppress Notification */ + sn : 1, + /* bit 271:258 - Reserved */ + rsvd_1 : 14; + /* bit 279:272 - Notification Vector */ + u8 nv; + /* bit 287:280 - Reserved */ + u8 rsvd_2; + /* bit 319:288 - Notification Destination */ + u32 ndst; + }; + u64 control; + }; + u32 rsvd[6]; +} __aligned(64); + + +/* + * 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; + gpa_t vmxon_ptr; + bool pml_full; + + /* The guest-physical address of the current VMCS L1 keeps for L2 */ + gpa_t current_vmptr; + /* + * Cache of the guest's VMCS, existing outside of guest memory. + * Loaded from guest memory during VMPTRLD. Flushed to guest + * memory during VMCLEAR and VMPTRLD. + */ + struct vmcs12 *cached_vmcs12; + /* + * Cache of the guest's shadow VMCS, existing outside of guest + * memory. Loaded from guest memory during VM entry. Flushed + * to guest memory during VM exit. + */ + struct vmcs12 *cached_shadow_vmcs12; + /* + * Indicates if the shadow vmcs or enlightened vmcs must be updated + * with the data held by struct vmcs12. + */ + bool need_vmcs12_sync; + bool dirty_vmcs12; + + /* + * vmcs02 has been initialized, i.e. state that is constant for + * vmcs02 has been written to the backing VMCS. Initialization + * is delayed until L1 actually attempts to run a nested VM. + */ + bool vmcs02_initialized; + + bool change_vmcs01_virtual_apic_mode; + + /* + * Enlightened VMCS has been enabled. It does not mean that L1 has to + * use it. However, VMX features available to L1 will be limited based + * on what the enlightened VMCS supports. + */ + bool enlightened_vmcs_enabled; + + /* L2 must run next, and mustn't decide to exit to L1. */ + bool nested_run_pending; + + struct loaded_vmcs vmcs02; + + /* + * Guest pages referred to in the vmcs02 with host-physical + * pointers, so we must keep them pinned while L2 runs. + */ + struct page *apic_access_page; + struct page *virtual_apic_page; + struct page *pi_desc_page; + struct pi_desc *pi_desc; + bool pi_pending; + u16 posted_intr_nv; + + struct hrtimer preemption_timer; + bool preemption_timer_expired; + + /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ + u64 vmcs01_debugctl; + u64 vmcs01_guest_bndcfgs; + + u16 vpid02; + u16 last_vpid; + + struct nested_vmx_msrs msrs; + + /* SMM related state */ + struct { + /* in VMX operation on SMM entry? */ + bool vmxon; + /* in guest mode on SMM entry? */ + bool guest_mode; + } smm; + + gpa_t hv_evmcs_vmptr; + struct page *hv_evmcs_page; + struct hv_enlightened_vmcs *hv_evmcs; +}; + +struct vcpu_vmx { + struct kvm_vcpu vcpu; + unsigned long host_rsp; + u8 fail; + u8 msr_bitmap_mode; + u32 exit_intr_info; + u32 idt_vectoring_info; + ulong rflags; + struct shared_msr_entry *guest_msrs; + int nmsrs; + int save_nmsrs; + bool guest_msrs_dirty; + unsigned long host_idt_base; +#ifdef CONFIG_X86_64 + u64 msr_host_kernel_gs_base; + u64 msr_guest_kernel_gs_base; +#endif + + u64 arch_capabilities; + u64 spec_ctrl; + + u32 vm_entry_controls_shadow; + u32 vm_exit_controls_shadow; + u32 secondary_exec_control; + + /* + * 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. loaded_cpu_state points + * to the VMCS whose state is loaded into the CPU registers that only + * need to be switched when transitioning to/from the kernel; a NULL + * value indicates that host state is loaded. + */ + struct loaded_vmcs vmcs01; + struct loaded_vmcs *loaded_vmcs; + struct loaded_vmcs *loaded_cpu_state; + bool __launched; /* temporary, used in vmx_vcpu_run */ + struct msr_autoload { + struct vmx_msrs guest; + struct vmx_msrs host; + } msr_autoload; + + struct { + int vm86_active; + ulong save_rflags; + struct kvm_segment segs[8]; + } rmode; + struct { + u32 bitmask; /* 4 bits per segment (1 bit per field) */ + struct kvm_save_segment { + u16 selector; + unsigned long base; + u32 limit; + u32 ar; + } seg[8]; + } segment_cache; + int vpid; + bool emulation_required; + + u32 exit_reason; + + /* Posted interrupt descriptor */ + struct pi_desc pi_desc; + + /* Support for a guest hypervisor (nested VMX) */ + struct nested_vmx nested; + + /* Dynamic PLE window. */ + int ple_window; + bool ple_window_dirty; + + bool req_immediate_exit; + + /* Support for PML */ +#define PML_ENTITY_NUM 512 + struct page *pml_pg; + + /* apic deadline value in host tsc */ + u64 hv_deadline_tsc; + + u64 current_tsc_ratio; + + u32 host_pkru; + + unsigned long host_debugctlmsr; + + /* + * Only bits masked by msr_ia32_feature_control_valid_bits can be set in + * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included + * in msr_ia32_feature_control_valid_bits. + */ + u64 msr_ia32_feature_control; + u64 msr_ia32_feature_control_valid_bits; + u64 ept_pointer; +}; + +enum ept_pointers_status { + EPT_POINTERS_CHECK = 0, + EPT_POINTERS_MATCH = 1, + EPT_POINTERS_MISMATCH = 2 +}; + +struct kvm_vmx { + struct kvm kvm; + + unsigned int tss_addr; + bool ept_identity_pagetable_done; + gpa_t ept_identity_map_addr; + + enum ept_pointers_status ept_pointers_match; + spinlock_t ept_pointer_lock; +}; + +#define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 + +static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) +{ + return test_and_set_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +{ + return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); +} + +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + return clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline void pi_set_sn(struct pi_desc *pi_desc) +{ + return set_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline void pi_clear_on(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_on(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_sn(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +{ + vmx->segment_cache.bitmask = 0; +} + +static inline u32 vmx_vmentry_ctrl(void) +{ + /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ + return vmcs_config.vmentry_ctrl & + ~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER); +} + +static inline u32 vmx_vmexit_ctrl(void) +{ + /* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */ + return vmcs_config.vmexit_ctrl & + ~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER); +} + +u32 vmx_exec_control(struct vcpu_vmx *vmx); + +static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) +{ + return container_of(kvm, struct kvm_vmx, kvm); +} + +static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) +{ + return container_of(vcpu, struct vcpu_vmx, vcpu); +} + +static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) +{ + return &(to_vmx(vcpu)->pi_desc); +} + +#endif /* __KVM_X86_VMX_H */ |