diff options
Diffstat (limited to 'include/asm-x86')
-rw-r--r-- | include/asm-x86/kvm_host.h | 601 | ||||
-rw-r--r-- | include/asm-x86/kvm_x86_emulate.h | 186 |
2 files changed, 787 insertions, 0 deletions
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h new file mode 100644 index 000000000000..28940e1a9713 --- /dev/null +++ b/include/asm-x86/kvm_host.h @@ -0,0 +1,601 @@ +#/* + * Kernel-based Virtual Machine driver for Linux + * + * This header defines architecture specific interfaces, x86 version + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef ASM_KVM_HOST_H +#define ASM_KVM_HOST_H + +#include <linux/types.h> +#include <linux/mm.h> + +#include <linux/kvm.h> +#include <linux/kvm_para.h> +#include <linux/kvm_types.h> + +#include <asm/desc.h> + +#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) +#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) +#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS|0xFFFFFF0000000000ULL) + +#define KVM_GUEST_CR0_MASK \ + (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \ + | X86_CR0_NW | X86_CR0_CD) +#define KVM_VM_CR0_ALWAYS_ON \ + (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \ + | X86_CR0_MP) +#define KVM_GUEST_CR4_MASK \ + (X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE) +#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) +#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE) + +#define INVALID_PAGE (~(hpa_t)0) +#define UNMAPPED_GVA (~(gpa_t)0) + +#define DE_VECTOR 0 +#define UD_VECTOR 6 +#define NM_VECTOR 7 +#define DF_VECTOR 8 +#define TS_VECTOR 10 +#define NP_VECTOR 11 +#define SS_VECTOR 12 +#define GP_VECTOR 13 +#define PF_VECTOR 14 + +#define SELECTOR_TI_MASK (1 << 2) +#define SELECTOR_RPL_MASK 0x03 + +#define IOPL_SHIFT 12 + +#define KVM_ALIAS_SLOTS 4 + +#define KVM_PERMILLE_MMU_PAGES 20 +#define KVM_MIN_ALLOC_MMU_PAGES 64 +#define KVM_NUM_MMU_PAGES 1024 +#define KVM_MIN_FREE_MMU_PAGES 5 +#define KVM_REFILL_PAGES 25 +#define KVM_MAX_CPUID_ENTRIES 40 + +extern spinlock_t kvm_lock; +extern struct list_head vm_list; + +struct kvm_vcpu; +struct kvm; + +enum { + VCPU_REGS_RAX = 0, + VCPU_REGS_RCX = 1, + VCPU_REGS_RDX = 2, + VCPU_REGS_RBX = 3, + VCPU_REGS_RSP = 4, + VCPU_REGS_RBP = 5, + VCPU_REGS_RSI = 6, + VCPU_REGS_RDI = 7, +#ifdef CONFIG_X86_64 + VCPU_REGS_R8 = 8, + VCPU_REGS_R9 = 9, + VCPU_REGS_R10 = 10, + VCPU_REGS_R11 = 11, + VCPU_REGS_R12 = 12, + VCPU_REGS_R13 = 13, + VCPU_REGS_R14 = 14, + VCPU_REGS_R15 = 15, +#endif + NR_VCPU_REGS +}; + +enum { + VCPU_SREG_CS, + VCPU_SREG_DS, + VCPU_SREG_ES, + VCPU_SREG_FS, + VCPU_SREG_GS, + VCPU_SREG_SS, + VCPU_SREG_TR, + VCPU_SREG_LDTR, +}; + +#include <asm/kvm_x86_emulate.h> + +#define KVM_NR_MEM_OBJS 40 + +/* + * We don't want allocation failures within the mmu code, so we preallocate + * enough memory for a single page fault in a cache. + */ +struct kvm_mmu_memory_cache { + int nobjs; + void *objects[KVM_NR_MEM_OBJS]; +}; + +#define NR_PTE_CHAIN_ENTRIES 5 + +struct kvm_pte_chain { + u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES]; + struct hlist_node link; +}; + +/* + * kvm_mmu_page_role, below, is defined as: + * + * bits 0:3 - total guest paging levels (2-4, or zero for real mode) + * bits 4:7 - page table level for this shadow (1-4) + * bits 8:9 - page table quadrant for 2-level guests + * bit 16 - "metaphysical" - gfn is not a real page (huge page/real mode) + * bits 17:19 - common access permissions for all ptes in this shadow page + */ +union kvm_mmu_page_role { + unsigned word; + struct { + unsigned glevels : 4; + unsigned level : 4; + unsigned quadrant : 2; + unsigned pad_for_nice_hex_output : 6; + unsigned metaphysical : 1; + unsigned access : 3; + }; +}; + +struct kvm_mmu_page { + struct list_head link; + struct hlist_node hash_link; + + /* + * The following two entries are used to key the shadow page in the + * hash table. + */ + gfn_t gfn; + union kvm_mmu_page_role role; + + u64 *spt; + /* hold the gfn of each spte inside spt */ + gfn_t *gfns; + unsigned long slot_bitmap; /* One bit set per slot which has memory + * in this shadow page. + */ + int multimapped; /* More than one parent_pte? */ + int root_count; /* Currently serving as active root */ + union { + u64 *parent_pte; /* !multimapped */ + struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */ + }; +}; + +/* + * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level + * 32-bit). The kvm_mmu structure abstracts the details of the current mmu + * mode. + */ +struct kvm_mmu { + void (*new_cr3)(struct kvm_vcpu *vcpu); + int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err); + void (*free)(struct kvm_vcpu *vcpu); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva); + void (*prefetch_page)(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *page); + hpa_t root_hpa; + int root_level; + int shadow_root_level; + + u64 *pae_root; +}; + +struct kvm_vcpu_arch { + u64 host_tsc; + int interrupt_window_open; + unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */ + DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS); + unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */ + unsigned long rip; /* needs vcpu_load_rsp_rip() */ + + unsigned long cr0; + unsigned long cr2; + unsigned long cr3; + unsigned long cr4; + unsigned long cr8; + u64 pdptrs[4]; /* pae */ + u64 shadow_efer; + u64 apic_base; + struct kvm_lapic *apic; /* kernel irqchip context */ +#define VCPU_MP_STATE_RUNNABLE 0 +#define VCPU_MP_STATE_UNINITIALIZED 1 +#define VCPU_MP_STATE_INIT_RECEIVED 2 +#define VCPU_MP_STATE_SIPI_RECEIVED 3 +#define VCPU_MP_STATE_HALTED 4 + int mp_state; + int sipi_vector; + u64 ia32_misc_enable_msr; + + struct kvm_mmu mmu; + + struct kvm_mmu_memory_cache mmu_pte_chain_cache; + struct kvm_mmu_memory_cache mmu_rmap_desc_cache; + struct kvm_mmu_memory_cache mmu_page_cache; + struct kvm_mmu_memory_cache mmu_page_header_cache; + + gfn_t last_pt_write_gfn; + int last_pt_write_count; + u64 *last_pte_updated; + + struct i387_fxsave_struct host_fx_image; + struct i387_fxsave_struct guest_fx_image; + + gva_t mmio_fault_cr2; + struct kvm_pio_request pio; + void *pio_data; + + struct kvm_queued_exception { + bool pending; + bool has_error_code; + u8 nr; + u32 error_code; + } exception; + + struct { + int active; + u8 save_iopl; + struct kvm_save_segment { + u16 selector; + unsigned long base; + u32 limit; + u32 ar; + } tr, es, ds, fs, gs; + } rmode; + int halt_request; /* real mode on Intel only */ + + int cpuid_nent; + struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES]; + /* emulate context */ + + struct x86_emulate_ctxt emulate_ctxt; +}; + +struct kvm_mem_alias { + gfn_t base_gfn; + unsigned long npages; + gfn_t target_gfn; +}; + +struct kvm_arch{ + int naliases; + struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS]; + + unsigned int n_free_mmu_pages; + unsigned int n_requested_mmu_pages; + unsigned int n_alloc_mmu_pages; + struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; + /* + * Hash table of struct kvm_mmu_page. + */ + struct list_head active_mmu_pages; + struct kvm_pic *vpic; + struct kvm_ioapic *vioapic; + + int round_robin_prev_vcpu; + unsigned int tss_addr; + struct page *apic_access_page; +}; + +struct kvm_vm_stat { + u32 mmu_shadow_zapped; + u32 mmu_pte_write; + u32 mmu_pte_updated; + u32 mmu_pde_zapped; + u32 mmu_flooded; + u32 mmu_recycled; + u32 remote_tlb_flush; +}; + +struct kvm_vcpu_stat { + u32 pf_fixed; + u32 pf_guest; + u32 tlb_flush; + u32 invlpg; + + u32 exits; + u32 io_exits; + u32 mmio_exits; + u32 signal_exits; + u32 irq_window_exits; + u32 halt_exits; + u32 halt_wakeup; + u32 request_irq_exits; + u32 irq_exits; + u32 host_state_reload; + u32 efer_reload; + u32 fpu_reload; + u32 insn_emulation; + u32 insn_emulation_fail; +}; + +struct descriptor_table { + u16 limit; + unsigned long base; +} __attribute__((packed)); + +struct kvm_x86_ops { + int (*cpu_has_kvm_support)(void); /* __init */ + int (*disabled_by_bios)(void); /* __init */ + void (*hardware_enable)(void *dummy); /* __init */ + void (*hardware_disable)(void *dummy); + void (*check_processor_compatibility)(void *rtn); + int (*hardware_setup)(void); /* __init */ + void (*hardware_unsetup)(void); /* __exit */ + + /* Create, but do not attach this VCPU */ + struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); + void (*vcpu_free)(struct kvm_vcpu *vcpu); + int (*vcpu_reset)(struct kvm_vcpu *vcpu); + + void (*prepare_guest_switch)(struct kvm_vcpu *vcpu); + void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); + void (*vcpu_put)(struct kvm_vcpu *vcpu); + void (*vcpu_decache)(struct kvm_vcpu *vcpu); + + int (*set_guest_debug)(struct kvm_vcpu *vcpu, + struct kvm_debug_guest *dbg); + void (*guest_debug_pre)(struct kvm_vcpu *vcpu); + int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); + int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); + u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); + void (*get_segment)(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); + void (*set_segment)(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); + void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); + void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu); + void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); + void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); + void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); + void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); + void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); + void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); + void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); + void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); + unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr); + void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value, + int *exception); + void (*cache_regs)(struct kvm_vcpu *vcpu); + void (*decache_regs)(struct kvm_vcpu *vcpu); + unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); + void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + + void (*tlb_flush)(struct kvm_vcpu *vcpu); + + void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run); + int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu); + void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*patch_hypercall)(struct kvm_vcpu *vcpu, + unsigned char *hypercall_addr); + int (*get_irq)(struct kvm_vcpu *vcpu); + void (*set_irq)(struct kvm_vcpu *vcpu, int vec); + void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr, + bool has_error_code, u32 error_code); + bool (*exception_injected)(struct kvm_vcpu *vcpu); + void (*inject_pending_irq)(struct kvm_vcpu *vcpu); + void (*inject_pending_vectors)(struct kvm_vcpu *vcpu, + struct kvm_run *run); + + int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); +}; + +extern struct kvm_x86_ops *kvm_x86_ops; + +int kvm_mmu_module_init(void); +void kvm_mmu_module_exit(void); + +void kvm_mmu_destroy(struct kvm_vcpu *vcpu); +int kvm_mmu_create(struct kvm_vcpu *vcpu); +int kvm_mmu_setup(struct kvm_vcpu *vcpu); +void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte); + +int kvm_mmu_reset_context(struct kvm_vcpu *vcpu); +void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot); +void kvm_mmu_zap_all(struct kvm *kvm); +unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); + +enum emulation_result { + EMULATE_DONE, /* no further processing */ + EMULATE_DO_MMIO, /* kvm_run filled with mmio request */ + EMULATE_FAIL, /* can't emulate this instruction */ +}; + +int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run, + unsigned long cr2, u16 error_code, int no_decode); +void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); +void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); +void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); +void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, + unsigned long *rflags); + +unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr); +void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value, + unsigned long *rflags); +int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); +int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); + +struct x86_emulate_ctxt; + +int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, + int size, unsigned port); +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, + int size, unsigned long count, int down, + gva_t address, int rep, unsigned port); +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); +int kvm_emulate_halt(struct kvm_vcpu *vcpu); +int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address); +int emulate_clts(struct kvm_vcpu *vcpu); +int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long *dest); +int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long value); + +void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr0); +void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr0); +void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr0); +unsigned long get_cr8(struct kvm_vcpu *vcpu); +void lmsw(struct kvm_vcpu *vcpu, unsigned long msw); +void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); + +int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); + +void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); +void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); +void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, + u32 error_code); + +void fx_init(struct kvm_vcpu *vcpu); + +int emulator_read_std(unsigned long addr, + void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu); +int emulator_write_emulated(unsigned long addr, + const void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu); + +unsigned long segment_base(u16 selector); + +void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu); +void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, + const u8 *new, int bytes); +int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); +void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); +int kvm_mmu_load(struct kvm_vcpu *vcpu); +void kvm_mmu_unload(struct kvm_vcpu *vcpu); + +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); + +int kvm_fix_hypercall(struct kvm_vcpu *vcpu); + +int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code); + +int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); +int complete_pio(struct kvm_vcpu *vcpu); + +static inline struct kvm_mmu_page *page_header(hpa_t shadow_page) +{ + struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); + + return (struct kvm_mmu_page *)page_private(page); +} + +static inline u16 read_fs(void) +{ + u16 seg; + asm("mov %%fs, %0" : "=g"(seg)); + return seg; +} + +static inline u16 read_gs(void) +{ + u16 seg; + asm("mov %%gs, %0" : "=g"(seg)); + return seg; +} + +static inline u16 read_ldt(void) +{ + u16 ldt; + asm("sldt %0" : "=g"(ldt)); + return ldt; +} + +static inline void load_fs(u16 sel) +{ + asm("mov %0, %%fs" : : "rm"(sel)); +} + +static inline void load_gs(u16 sel) +{ + asm("mov %0, %%gs" : : "rm"(sel)); +} + +#ifndef load_ldt +static inline void load_ldt(u16 sel) +{ + asm("lldt %0" : : "rm"(sel)); +} +#endif + +static inline void get_idt(struct descriptor_table *table) +{ + asm("sidt %0" : "=m"(*table)); +} + +static inline void get_gdt(struct descriptor_table *table) +{ + asm("sgdt %0" : "=m"(*table)); +} + +static inline unsigned long read_tr_base(void) +{ + u16 tr; + asm("str %0" : "=g"(tr)); + return segment_base(tr); +} + +#ifdef CONFIG_X86_64 +static inline unsigned long read_msr(unsigned long msr) +{ + u64 value; + + rdmsrl(msr, value); + return value; +} +#endif + +static inline void fx_save(struct i387_fxsave_struct *image) +{ + asm("fxsave (%0)":: "r" (image)); +} + +static inline void fx_restore(struct i387_fxsave_struct *image) +{ + asm("fxrstor (%0)":: "r" (image)); +} + +static inline void fpu_init(void) +{ + asm("finit"); +} + +static inline u32 get_rdx_init_val(void) +{ + return 0x600; /* P6 family */ +} + +static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) +{ + kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); +} + +#define ASM_VMX_VMCLEAR_RAX ".byte 0x66, 0x0f, 0xc7, 0x30" +#define ASM_VMX_VMLAUNCH ".byte 0x0f, 0x01, 0xc2" +#define ASM_VMX_VMRESUME ".byte 0x0f, 0x01, 0xc3" +#define ASM_VMX_VMPTRLD_RAX ".byte 0x0f, 0xc7, 0x30" +#define ASM_VMX_VMREAD_RDX_RAX ".byte 0x0f, 0x78, 0xd0" +#define ASM_VMX_VMWRITE_RAX_RDX ".byte 0x0f, 0x79, 0xd0" +#define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4" +#define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4" +#define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30" + +#define MSR_IA32_TIME_STAMP_COUNTER 0x010 + +#define TSS_IOPB_BASE_OFFSET 0x66 +#define TSS_BASE_SIZE 0x68 +#define TSS_IOPB_SIZE (65536 / 8) +#define TSS_REDIRECTION_SIZE (256 / 8) +#define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1) + +#endif diff --git a/include/asm-x86/kvm_x86_emulate.h b/include/asm-x86/kvm_x86_emulate.h new file mode 100644 index 000000000000..7db91b9bdcd4 --- /dev/null +++ b/include/asm-x86/kvm_x86_emulate.h @@ -0,0 +1,186 @@ +/****************************************************************************** + * x86_emulate.h + * + * Generic x86 (32-bit and 64-bit) instruction decoder and emulator. + * + * Copyright (c) 2005 Keir Fraser + * + * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 + */ + +#ifndef __X86_EMULATE_H__ +#define __X86_EMULATE_H__ + +struct x86_emulate_ctxt; + +/* + * x86_emulate_ops: + * + * These operations represent the instruction emulator's interface to memory. + * There are two categories of operation: those that act on ordinary memory + * regions (*_std), and those that act on memory regions known to require + * special treatment or emulation (*_emulated). + * + * The emulator assumes that an instruction accesses only one 'emulated memory' + * location, that this location is the given linear faulting address (cr2), and + * that this is one of the instruction's data operands. Instruction fetches and + * stack operations are assumed never to access emulated memory. The emulator + * automatically deduces which operand of a string-move operation is accessing + * emulated memory, and assumes that the other operand accesses normal memory. + * + * NOTES: + * 1. The emulator isn't very smart about emulated vs. standard memory. + * 'Emulated memory' access addresses should be checked for sanity. + * 'Normal memory' accesses may fault, and the caller must arrange to + * detect and handle reentrancy into the emulator via recursive faults. + * Accesses may be unaligned and may cross page boundaries. + * 2. If the access fails (cannot emulate, or a standard access faults) then + * it is up to the memop to propagate the fault to the guest VM via + * some out-of-band mechanism, unknown to the emulator. The memop signals + * failure by returning X86EMUL_PROPAGATE_FAULT to the emulator, which will + * then immediately bail. + * 3. Valid access sizes are 1, 2, 4 and 8 bytes. On x86/32 systems only + * cmpxchg8b_emulated need support 8-byte accesses. + * 4. The emulator cannot handle 64-bit mode emulation on an x86/32 system. + */ +/* Access completed successfully: continue emulation as normal. */ +#define X86EMUL_CONTINUE 0 +/* Access is unhandleable: bail from emulation and return error to caller. */ +#define X86EMUL_UNHANDLEABLE 1 +/* Terminate emulation but return success to the caller. */ +#define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */ +#define X86EMUL_RETRY_INSTR 2 /* retry the instruction for some reason */ +#define X86EMUL_CMPXCHG_FAILED 2 /* cmpxchg did not see expected value */ +struct x86_emulate_ops { + /* + * read_std: Read bytes of standard (non-emulated/special) memory. + * Used for instruction fetch, stack operations, and others. + * @addr: [IN ] Linear address from which to read. + * @val: [OUT] Value read from memory, zero-extended to 'u_long'. + * @bytes: [IN ] Number of bytes to read from memory. + */ + int (*read_std)(unsigned long addr, void *val, + unsigned int bytes, struct kvm_vcpu *vcpu); + + /* + * read_emulated: Read bytes from emulated/special memory area. + * @addr: [IN ] Linear address from which to read. + * @val: [OUT] Value read from memory, zero-extended to 'u_long'. + * @bytes: [IN ] Number of bytes to read from memory. + */ + int (*read_emulated) (unsigned long addr, + void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu); + + /* + * write_emulated: Read bytes from emulated/special memory area. + * @addr: [IN ] Linear address to which to write. + * @val: [IN ] Value to write to memory (low-order bytes used as + * required). + * @bytes: [IN ] Number of bytes to write to memory. + */ + int (*write_emulated) (unsigned long addr, + const void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu); + + /* + * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an + * emulated/special memory area. + * @addr: [IN ] Linear address to access. + * @old: [IN ] Value expected to be current at @addr. + * @new: [IN ] Value to write to @addr. + * @bytes: [IN ] Number of bytes to access using CMPXCHG. + */ + int (*cmpxchg_emulated) (unsigned long addr, + const void *old, + const void *new, + unsigned int bytes, + struct kvm_vcpu *vcpu); + +}; + +/* Type, address-of, and value of an instruction's operand. */ +struct operand { + enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type; + unsigned int bytes; + unsigned long val, orig_val, *ptr; +}; + +struct fetch_cache { + u8 data[15]; + unsigned long start; + unsigned long end; +}; + +struct decode_cache { + u8 twobyte; + u8 b; + u8 lock_prefix; + u8 rep_prefix; + u8 op_bytes; + u8 ad_bytes; + u8 rex_prefix; + struct operand src; + struct operand dst; + unsigned long *override_base; + unsigned int d; + unsigned long regs[NR_VCPU_REGS]; + unsigned long eip; + /* modrm */ + u8 modrm; + u8 modrm_mod; + u8 modrm_reg; + u8 modrm_rm; + u8 use_modrm_ea; + unsigned long modrm_ea; + unsigned long modrm_val; + struct fetch_cache fetch; +}; + +struct x86_emulate_ctxt { + /* Register state before/after emulation. */ + struct kvm_vcpu *vcpu; + + /* Linear faulting address (if emulating a page-faulting instruction). */ + unsigned long eflags; + + /* Emulated execution mode, represented by an X86EMUL_MODE value. */ + int mode; + + unsigned long cs_base; + unsigned long ds_base; + unsigned long es_base; + unsigned long ss_base; + unsigned long gs_base; + unsigned long fs_base; + + /* decode cache */ + + struct decode_cache decode; +}; + +/* Repeat String Operation Prefix */ +#define REPE_PREFIX 1 +#define REPNE_PREFIX 2 + +/* Execution mode, passed to the emulator. */ +#define X86EMUL_MODE_REAL 0 /* Real mode. */ +#define X86EMUL_MODE_PROT16 2 /* 16-bit protected mode. */ +#define X86EMUL_MODE_PROT32 4 /* 32-bit protected mode. */ +#define X86EMUL_MODE_PROT64 8 /* 64-bit (long) mode. */ + +/* Host execution mode. */ +#if defined(__i386__) +#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32 +#elif defined(CONFIG_X86_64) +#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64 +#endif + +int x86_decode_insn(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops); +int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops); + +#endif /* __X86_EMULATE_H__ */ |