path: root/arch/x86/kvm/vmx/vmx.h

/* 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 <asm/intel_pt.h>

#include "capabilities.h"
#include "kvm_cache_regs.h"
#include "posted_intr.h"
#include "vmcs.h"
#include "vmx_ops.h"
#include "cpuid.h"

extern const u32 vmx_msr_index[];

#define MSR_TYPE_R	1
#define MSR_TYPE_W	2
#define MSR_TYPE_RW	3

#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))

#ifdef CONFIG_X86_64
#define MAX_NR_USER_RETURN_MSRS	7
#else
#define MAX_NR_USER_RETURN_MSRS	4
#endif

#define MAX_NR_LOADSTORE_MSRS	8

struct vmx_msrs {
	unsigned int		nr;
	struct vmx_msr_entry	val[MAX_NR_LOADSTORE_MSRS];
};

struct vmx_uret_msr {
	bool load_into_hardware;
	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
};

#define RTIT_ADDR_RANGE		4

struct pt_ctx {
	u64 ctl;
	u64 status;
	u64 output_base;
	u64 output_mask;
	u64 cr3_match;
	u64 addr_a[RTIT_ADDR_RANGE];
	u64 addr_b[RTIT_ADDR_RANGE];
};

struct pt_desc {
	u64 ctl_bitmask;
	u32 addr_range;
	u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
	struct pt_ctx host;
	struct pt_ctx guest;
};

union vmx_exit_reason {
	struct {
		u32	basic			: 16;
		u32	reserved16		: 1;
		u32	reserved17		: 1;
		u32	reserved18		: 1;
		u32	reserved19		: 1;
		u32	reserved20		: 1;
		u32	reserved21		: 1;
		u32	reserved22		: 1;
		u32	reserved23		: 1;
		u32	reserved24		: 1;
		u32	reserved25		: 1;
		u32	bus_lock_detected	: 1;
		u32	enclave_mode		: 1;
		u32	smi_pending_mtf		: 1;
		u32	smi_from_vmx_root	: 1;
		u32	reserved30		: 1;
		u32	failed_vmentry		: 1;
	};
	u32 full;
};

#define vcpu_to_lbr_desc(vcpu) (&to_vmx(vcpu)->lbr_desc)
#define vcpu_to_lbr_records(vcpu) (&to_vmx(vcpu)->lbr_desc.records)

bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu);
bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu);

int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu);
void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu);

struct lbr_desc {
	/* Basic info about guest LBR records. */
	struct x86_pmu_lbr records;

	/*
	 * Emulate LBR feature via passthrough LBR registers when the
	 * per-vcpu guest LBR event is scheduled on the current pcpu.
	 *
	 * The records may be inaccurate if the host reclaims the LBR.
	 */
	struct perf_event *event;

	/* True if LBRs are marked as not intercepted in the MSR bitmap */
	bool msr_passthrough;
};

/*
 * 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_to_shadow_sync;
	bool dirty_vmcs12;

	/*
	 * Indicates lazily loaded guest state has not yet been decached from
	 * vmcs02.
	 */
	bool need_sync_vmcs02_to_vmcs12_rare;

	/*
	 * 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;
	bool reload_vmcs01_apic_access_page;
	bool update_vmcs01_cpu_dirty_logging;

	/*
	 * 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;

	/* Pending MTF VM-exit into L1.  */
	bool mtf_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 kvm_host_map virtual_apic_map;
	struct kvm_host_map pi_desc_map;

	struct kvm_host_map msr_bitmap_map;

	struct pi_desc *pi_desc;
	bool pi_pending;
	u16 posted_intr_nv;

	struct hrtimer preemption_timer;
	u64 preemption_timer_deadline;
	bool has_preemption_timer_deadline;
	bool preemption_timer_expired;

	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
	u64 vmcs01_debugctl;
	u64 vmcs01_guest_bndcfgs;

	/* to migrate it to L1 if L2 writes to L1's CR8 directly */
	int l1_tpr_threshold;

	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 kvm_host_map hv_evmcs_map;
	struct hv_enlightened_vmcs *hv_evmcs;
};

struct vcpu_vmx {
	struct kvm_vcpu       vcpu;
	u8                    fail;
	u8		      msr_bitmap_mode;

	/*
	 * If true, host state has been stored in vmx->loaded_vmcs for
	 * the CPU registers that only need to be switched when transitioning
	 * to/from the kernel, and the registers have been loaded with guest
	 * values.  If false, host state is loaded in the CPU registers
	 * and vmx->loaded_vmcs->host_state is invalid.
	 */
	bool		      guest_state_loaded;

	unsigned long         exit_qualification;
	u32                   exit_intr_info;
	u32                   idt_vectoring_info;
	ulong                 rflags;

	/*
	 * User return MSRs are always emulated when enabled in the guest, but
	 * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside
	 * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to
	 * be loaded into hardware if those conditions aren't met.
	 * nr_active_uret_msrs tracks the number of MSRs that need to be loaded
	 * into hardware when running the guest.  guest_uret_msrs[] is resorted
	 * whenever the number of "active" uret MSRs is modified.
	 */
	struct vmx_uret_msr   guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
	int                   nr_active_uret_msrs;
	bool                  guest_uret_msrs_loaded;
#ifdef CONFIG_X86_64
	u64		      msr_host_kernel_gs_base;
	u64		      msr_guest_kernel_gs_base;
#endif

	u64		      spec_ctrl;
	u32		      msr_ia32_umwait_control;

	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.
	 */
	struct loaded_vmcs    vmcs01;
	struct loaded_vmcs   *loaded_vmcs;

	struct msr_autoload {
		struct vmx_msrs guest;
		struct vmx_msrs host;
	} msr_autoload;

	struct msr_autostore {
		struct vmx_msrs guest;
	} msr_autostore;

	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;

	union vmx_exit_reason exit_reason;

	/* Posted interrupt descriptor */
	struct pi_desc pi_desc;

	/* Support for a guest hypervisor (nested VMX) */
	struct nested_vmx nested;

	/* Dynamic PLE window. */
	unsigned 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;

	unsigned long host_debugctlmsr;

	/*
	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
	 * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included
	 * in msr_ia32_feature_control_valid_bits.
	 */
	u64 msr_ia32_feature_control;
	u64 msr_ia32_feature_control_valid_bits;
	/* SGX Launch Control public key hash */
	u64 msr_ia32_sgxlepubkeyhash[4];

#if IS_ENABLED(CONFIG_HYPERV)
	u64 hv_root_ept;
#endif

	struct pt_desc pt_desc;
	struct lbr_desc lbr_desc;

	/* Save desired MSR intercept (read: pass-through) state */
#define MAX_POSSIBLE_PASSTHROUGH_MSRS	13
	struct {
		DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
		DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
	} shadow_msr_intercept;
};

struct kvm_vmx {
	struct kvm kvm;

	unsigned int tss_addr;
	bool ept_identity_pagetable_done;
	gpa_t ept_identity_map_addr;

#if IS_ENABLED(CONFIG_HYPERV)
	hpa_t hv_root_ept;
	spinlock_t hv_root_ept_lock;
#endif
};

bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
			struct loaded_vmcs *buddy);
int allocate_vpid(void);
void free_vpid(int vpid);
void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
			unsigned long fs_base, unsigned long gs_base);
int vmx_get_cpl(struct kvm_vcpu *vcpu);
unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);
void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask);
int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer);
void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
void set_cr4_guest_host_mask(struct vcpu_vmx *vmx);
void ept_save_pdptrs(struct kvm_vcpu *vcpu);
void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);

void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
bool vmx_nmi_blocked(struct kvm_vcpu *vcpu);
bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr);
void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu);
void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);
int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);

void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);
void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);

static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
					     int type, bool value)
{
	if (value)
		vmx_enable_intercept_for_msr(vcpu, msr, type);
	else
		vmx_disable_intercept_for_msr(vcpu, msr, type);
}

void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);

static inline u8 vmx_get_rvi(void)
{
	return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
}

#define BUILD_CONTROLS_SHADOW(lname, uname)				    \
static inline void lname##_controls_set(struct vcpu_vmx *vmx, u32 val)	    \
{									    \
	if (vmx->loaded_vmcs->controls_shadow.lname != val) {		    \
		vmcs_write32(uname, val);				    \
		vmx->loaded_vmcs->controls_shadow.lname = val;		    \
	}								    \
}									    \
static inline u32 lname##_controls_get(struct vcpu_vmx *vmx)		    \
{									    \
	return vmx->loaded_vmcs->controls_shadow.lname;			    \
}									    \
static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u32 val)   \
{									    \
	lname##_controls_set(vmx, lname##_controls_get(vmx) | val);	    \
}									    \
static inline void lname##_controls_clearbit(struct vcpu_vmx *vmx, u32 val) \
{									    \
	lname##_controls_set(vmx, lname##_controls_get(vmx) & ~val);	    \
}
BUILD_CONTROLS_SHADOW(vm_entry, VM_ENTRY_CONTROLS)
BUILD_CONTROLS_SHADOW(vm_exit, VM_EXIT_CONTROLS)
BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL)
BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL)
BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL)

static inline void vmx_register_cache_reset(struct kvm_vcpu *vcpu)
{
	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
				  | (1 << VCPU_EXREG_RFLAGS)
				  | (1 << VCPU_EXREG_PDPTR)
				  | (1 << VCPU_EXREG_SEGMENTS)
				  | (1 << VCPU_EXREG_CR0)
				  | (1 << VCPU_EXREG_CR3)
				  | (1 << VCPU_EXREG_CR4)
				  | (1 << VCPU_EXREG_EXIT_INFO_1)
				  | (1 << VCPU_EXREG_EXIT_INFO_2));
	vcpu->arch.regs_dirty = 0;
}

static inline u32 vmx_vmentry_ctrl(void)
{
	u32 vmentry_ctrl = vmcs_config.vmentry_ctrl;
	if (vmx_pt_mode_is_system())
		vmentry_ctrl &= ~(VM_ENTRY_PT_CONCEAL_PIP |
				  VM_ENTRY_LOAD_IA32_RTIT_CTL);
	/* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
	return vmentry_ctrl &
		~(VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_EFER);
}

static inline u32 vmx_vmexit_ctrl(void)
{
	u32 vmexit_ctrl = vmcs_config.vmexit_ctrl;
	if (vmx_pt_mode_is_system())
		vmexit_ctrl &= ~(VM_EXIT_PT_CONCEAL_PIP |
				 VM_EXIT_CLEAR_IA32_RTIT_CTL);
	/* Loading of EFER and PERF_GLOBAL_CTRL are toggled dynamically */
	return vmexit_ctrl &
		~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER);
}

u32 vmx_exec_control(struct vcpu_vmx *vmx);
u32 vmx_pin_based_exec_ctrl(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 unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) {
		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1);
		vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
	}
	return vmx->exit_qualification;
}

static inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu)
{
	struct vcpu_vmx *vmx = to_vmx(vcpu);

	if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) {
		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2);
		vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
	}
	return vmx->exit_intr_info;
}

struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags);
void free_vmcs(struct vmcs *vmcs);
int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs);

static inline struct vmcs *alloc_vmcs(bool shadow)
{
	return alloc_vmcs_cpu(shadow, raw_smp_processor_id(),
			      GFP_KERNEL_ACCOUNT);
}

static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
{
	vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}

static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
{
	return vmx->secondary_exec_control &
		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
}

static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
{
	if (!enable_ept)
		return true;

	return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
}

static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu)
{
	return enable_unrestricted_guest && (!is_guest_mode(vcpu) ||
	    (secondary_exec_controls_get(to_vmx(vcpu)) &
	    SECONDARY_EXEC_UNRESTRICTED_GUEST));
}

bool __vmx_guest_state_valid(struct kvm_vcpu *vcpu);
static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu)
{
	return is_unrestricted_guest(vcpu) || __vmx_guest_state_valid(vcpu);
}

void dump_vmcs(struct kvm_vcpu *vcpu);

#endif /* __KVM_X86_VMX_H */