diff options
Diffstat (limited to 'arch/x86/kvm/emulate.c')
-rw-r--r-- | arch/x86/kvm/emulate.c | 1247 |
1 files changed, 916 insertions, 331 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4dade6ac082..5ac0bb465ed 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -33,6 +33,7 @@ #include <asm/kvm_emulate.h> #include "x86.h" +#include "tss.h" /* * Opcode effective-address decode tables. @@ -50,6 +51,8 @@ #define DstReg (2<<1) /* Register operand. */ #define DstMem (3<<1) /* Memory operand. */ #define DstAcc (4<<1) /* Destination Accumulator */ +#define DstDI (5<<1) /* Destination is in ES:(E)DI */ +#define DstMem64 (6<<1) /* 64bit memory operand */ #define DstMask (7<<1) /* Source operand type. */ #define SrcNone (0<<4) /* No source operand. */ @@ -63,6 +66,7 @@ #define SrcOne (7<<4) /* Implied '1' */ #define SrcImmUByte (8<<4) /* 8-bit unsigned immediate operand. */ #define SrcImmU (9<<4) /* Immediate operand, unsigned */ +#define SrcSI (0xa<<4) /* Source is in the DS:RSI */ #define SrcMask (0xf<<4) /* Generic ModRM decode. */ #define ModRM (1<<8) @@ -85,6 +89,9 @@ #define Src2ImmByte (2<<29) #define Src2One (3<<29) #define Src2Imm16 (4<<29) +#define Src2Mem16 (5<<29) /* Used for Ep encoding. First argument has to be + in memory and second argument is located + immediately after the first one in memory. */ #define Src2Mask (7<<29) enum { @@ -147,8 +154,8 @@ static u32 opcode_table[256] = { 0, 0, 0, 0, /* 0x68 - 0x6F */ SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* insb, insw/insd */ - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* outsb, outsw/outsd */ + DstDI | ByteOp | Mov | String, DstDI | Mov | String, /* insb, insw/insd */ + SrcSI | ByteOp | ImplicitOps | String, SrcSI | ImplicitOps | String, /* outsb, outsw/outsd */ /* 0x70 - 0x77 */ SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte, @@ -173,12 +180,12 @@ static u32 opcode_table[256] = { /* 0xA0 - 0xA7 */ ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs, ByteOp | DstMem | SrcReg | Mov | MemAbs, DstMem | SrcReg | Mov | MemAbs, - ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | String, ImplicitOps | String, + ByteOp | SrcSI | DstDI | Mov | String, SrcSI | DstDI | Mov | String, + ByteOp | SrcSI | DstDI | String, SrcSI | DstDI | String, /* 0xA8 - 0xAF */ - 0, 0, ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String, - ByteOp | ImplicitOps | String, ImplicitOps | String, + 0, 0, ByteOp | DstDI | Mov | String, DstDI | Mov | String, + ByteOp | SrcSI | DstAcc | Mov | String, SrcSI | DstAcc | Mov | String, + ByteOp | DstDI | String, DstDI | String, /* 0xB0 - 0xB7 */ ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov, @@ -204,13 +211,13 @@ static u32 opcode_table[256] = { 0, 0, 0, 0, 0, 0, 0, 0, /* 0xE0 - 0xE7 */ 0, 0, 0, 0, - ByteOp | SrcImmUByte, SrcImmUByte, - ByteOp | SrcImmUByte, SrcImmUByte, + ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc, + ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, + SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, + SrcNone | ByteOp | DstAcc, SrcNone | DstAcc, /* 0xF0 - 0xF7 */ 0, 0, 0, 0, ImplicitOps | Priv, ImplicitOps, Group | Group3_Byte, Group | Group3, @@ -343,7 +350,8 @@ static u32 group_table[] = { [Group5*8] = DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, SrcMem | ModRM | Stack, 0, - SrcMem | ModRM | Stack, 0, SrcMem | ModRM | Stack, 0, + SrcMem | ModRM | Stack, SrcMem | ModRM | Src2Mem16 | ImplicitOps, + SrcMem | ModRM | Stack, 0, [Group7*8] = 0, 0, ModRM | SrcMem | Priv, ModRM | SrcMem | Priv, SrcNone | ModRM | DstMem | Mov, 0, @@ -353,14 +361,14 @@ static u32 group_table[] = { DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock, [Group9*8] = - 0, ImplicitOps | ModRM | Lock, 0, 0, 0, 0, 0, 0, + 0, DstMem64 | ModRM | Lock, 0, 0, 0, 0, 0, 0, }; static u32 group2_table[] = { [Group7*8] = - SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM, + SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM | Priv, SrcNone | ModRM | DstMem | Mov, 0, - SrcMem16 | ModRM | Mov, 0, + SrcMem16 | ModRM | Mov | Priv, 0, [Group9*8] = 0, 0, 0, 0, 0, 0, 0, 0, }; @@ -562,7 +570,7 @@ static u32 group2_table[] = { #define insn_fetch(_type, _size, _eip) \ ({ unsigned long _x; \ rc = do_insn_fetch(ctxt, ops, (_eip), &_x, (_size)); \ - if (rc != 0) \ + if (rc != X86EMUL_CONTINUE) \ goto done; \ (_eip) += (_size); \ (_type)_x; \ @@ -638,40 +646,40 @@ static unsigned long ss_base(struct x86_emulate_ctxt *ctxt) static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, - unsigned long linear, u8 *dest) + unsigned long eip, u8 *dest) { struct fetch_cache *fc = &ctxt->decode.fetch; int rc; - int size; + int size, cur_size; - if (linear < fc->start || linear >= fc->end) { - size = min(15UL, PAGE_SIZE - offset_in_page(linear)); - rc = ops->fetch(linear, fc->data, size, ctxt->vcpu, NULL); - if (rc) + if (eip == fc->end) { + cur_size = fc->end - fc->start; + size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip)); + rc = ops->fetch(ctxt->cs_base + eip, fc->data + cur_size, + size, ctxt->vcpu, NULL); + if (rc != X86EMUL_CONTINUE) return rc; - fc->start = linear; - fc->end = linear + size; + fc->end += size; } - *dest = fc->data[linear - fc->start]; - return 0; + *dest = fc->data[eip - fc->start]; + return X86EMUL_CONTINUE; } static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, unsigned long eip, void *dest, unsigned size) { - int rc = 0; + int rc; /* x86 instructions are limited to 15 bytes. */ - if (eip + size - ctxt->decode.eip_orig > 15) + if (eip + size - ctxt->eip > 15) return X86EMUL_UNHANDLEABLE; - eip += ctxt->cs_base; while (size--) { rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; } - return 0; + return X86EMUL_CONTINUE; } /* @@ -702,7 +710,7 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt, *address = 0; rc = ops->read_std((unsigned long)ptr, (unsigned long *)size, 2, ctxt->vcpu, NULL); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; rc = ops->read_std((unsigned long)ptr + 2, address, op_bytes, ctxt->vcpu, NULL); @@ -782,7 +790,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; u8 sib; int index_reg = 0, base_reg = 0, scale; - int rc = 0; + int rc = X86EMUL_CONTINUE; if (c->rex_prefix) { c->modrm_reg = (c->rex_prefix & 4) << 1; /* REX.R */ @@ -895,7 +903,7 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; switch (c->ad_bytes) { case 2: @@ -916,14 +924,18 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; int def_op_bytes, def_ad_bytes, group; - /* Shadow copy of register state. Committed on successful emulation. */ + /* we cannot decode insn before we complete previous rep insn */ + WARN_ON(ctxt->restart); + + /* Shadow copy of register state. Committed on successful emulation. */ memset(c, 0, sizeof(struct decode_cache)); - c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu); + c->eip = ctxt->eip; + c->fetch.start = c->fetch.end = c->eip; ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); @@ -1015,11 +1027,6 @@ done_prefixes: } } - if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { - kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction"); - return -1; - } - if (c->d & Group) { group = c->d & GroupMask; c->modrm = insn_fetch(u8, 1, c->eip); @@ -1046,7 +1053,7 @@ done_prefixes: rc = decode_modrm(ctxt, ops); else if (c->d & MemAbs) rc = decode_abs(ctxt, ops); - if (rc) + if (rc != X86EMUL_CONTINUE) goto done; if (!c->has_seg_override) @@ -1057,6 +1064,10 @@ done_prefixes: if (c->ad_bytes != 8) c->modrm_ea = (u32)c->modrm_ea; + + if (c->rip_relative) + c->modrm_ea += c->eip; + /* * Decode and fetch the source operand: register, memory * or immediate. @@ -1091,6 +1102,8 @@ done_prefixes: break; } c->src.type = OP_MEM; + c->src.ptr = (unsigned long *)c->modrm_ea; + c->src.val = 0; break; case SrcImm: case SrcImmU: @@ -1139,6 +1152,14 @@ done_prefixes: c->src.bytes = 1; c->src.val = 1; break; + case SrcSI: + c->src.type = OP_MEM; + c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->src.ptr = (unsigned long *) + register_address(c, seg_override_base(ctxt, c), + c->regs[VCPU_REGS_RSI]); + c->src.val = 0; + break; } /* @@ -1168,6 +1189,12 @@ done_prefixes: c->src2.bytes = 1; c->src2.val = 1; break; + case Src2Mem16: + c->src2.type = OP_MEM; + c->src2.bytes = 2; + c->src2.ptr = (unsigned long *)(c->modrm_ea + c->src.bytes); + c->src2.val = 0; + break; } /* Decode and fetch the destination operand: register or memory. */ @@ -1180,6 +1207,7 @@ done_prefixes: c->twobyte && (c->b == 0xb6 || c->b == 0xb7)); break; case DstMem: + case DstMem64: if ((c->d & ModRM) && c->modrm_mod == 3) { c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->dst.type = OP_REG; @@ -1188,12 +1216,24 @@ done_prefixes: break; } c->dst.type = OP_MEM; + c->dst.ptr = (unsigned long *)c->modrm_ea; + if ((c->d & DstMask) == DstMem64) + c->dst.bytes = 8; + else + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.val = 0; + if (c->d & BitOp) { + unsigned long mask = ~(c->dst.bytes * 8 - 1); + + c->dst.ptr = (void *)c->dst.ptr + + (c->src.val & mask) / 8; + } break; case DstAcc: c->dst.type = OP_REG; - c->dst.bytes = c->op_bytes; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; c->dst.ptr = &c->regs[VCPU_REGS_RAX]; - switch (c->op_bytes) { + switch (c->dst.bytes) { case 1: c->dst.val = *(u8 *)c->dst.ptr; break; @@ -1203,18 +1243,248 @@ done_prefixes: case 4: c->dst.val = *(u32 *)c->dst.ptr; break; + case 8: + c->dst.val = *(u64 *)c->dst.ptr; + break; } c->dst.orig_val = c->dst.val; break; + case DstDI: + c->dst.type = OP_MEM; + c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes; + c->dst.ptr = (unsigned long *) + register_address(c, es_base(ctxt), + c->regs[VCPU_REGS_RDI]); + c->dst.val = 0; + break; } - if (c->rip_relative) - c->modrm_ea += c->eip; - done: return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; } +static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + unsigned int size, unsigned short port, + void *dest) +{ + struct read_cache *rc = &ctxt->decode.io_read; + + if (rc->pos == rc->end) { /* refill pio read ahead */ + struct decode_cache *c = &ctxt->decode; + unsigned int in_page, n; + unsigned int count = c->rep_prefix ? + address_mask(c, c->regs[VCPU_REGS_RCX]) : 1; + in_page = (ctxt->eflags & EFLG_DF) ? + offset_in_page(c->regs[VCPU_REGS_RDI]) : + PAGE_SIZE - offset_in_page(c->regs[VCPU_REGS_RDI]); + n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size, + count); + if (n == 0) + n = 1; + rc->pos = rc->end = 0; + if (!ops->pio_in_emulated(size, port, rc->data, n, ctxt->vcpu)) + return 0; + rc->end = n * size; + } + + memcpy(dest, rc->data + rc->pos, size); + rc->pos += size; + return 1; +} + +static u32 desc_limit_scaled(struct desc_struct *desc) +{ + u32 limit = get_desc_limit(desc); + + return desc->g ? (limit << 12) | 0xfff : limit; +} + +static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_ptr *dt) +{ + if (selector & 1 << 2) { + struct desc_struct desc; + memset (dt, 0, sizeof *dt); + if (!ops->get_cached_descriptor(&desc, VCPU_SREG_LDTR, ctxt->vcpu)) + return; + + dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */ + dt->address = get_desc_base(&desc); + } else + ops->get_gdt(dt, ctxt->vcpu); +} + +/* allowed just for 8 bytes segments */ +static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_struct *desc) +{ + struct desc_ptr dt; + u16 index = selector >> 3; + int ret; + u32 err; + ulong addr; + + get_descriptor_table_ptr(ctxt, ops, selector, &dt); + + if (dt.size < index * 8 + 7) { + kvm_inject_gp(ctxt->vcpu, selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + addr = dt.address + index * 8; + ret = ops->read_std(addr, desc, sizeof *desc, ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) + kvm_inject_page_fault(ctxt->vcpu, addr, err); + + return ret; +} + +/* allowed just for 8 bytes segments */ +static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, struct desc_struct *desc) +{ + struct desc_ptr dt; + u16 index = selector >> 3; + u32 err; + ulong addr; + int ret; + + get_descriptor_table_ptr(ctxt, ops, selector, &dt); + + if (dt.size < index * 8 + 7) { + kvm_inject_gp(ctxt->vcpu, selector & 0xfffc); + return X86EMUL_PROPAGATE_FAULT; + } + + addr = dt.address + index * 8; + ret = ops->write_std(addr, desc, sizeof *desc, ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) + kvm_inject_page_fault(ctxt->vcpu, addr, err); + + return ret; +} + +static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 selector, int seg) +{ + struct desc_struct seg_desc; + u8 dpl, rpl, cpl; + unsigned err_vec = GP_VECTOR; + u32 err_code = 0; + bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ + int ret; + + memset(&seg_desc, 0, sizeof seg_desc); + + if ((seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86) + || ctxt->mode == X86EMUL_MODE_REAL) { + /* set real mode segment descriptor */ + set_desc_base(&seg_desc, selector << 4); + set_desc_limit(&seg_desc, 0xffff); + seg_desc.type = 3; + seg_desc.p = 1; + seg_desc.s = 1; + goto load; + } + + /* NULL selector is not valid for TR, CS and SS */ + if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) + && null_selector) + goto exception; + + /* TR should be in GDT only */ + if (seg == VCPU_SREG_TR && (selector & (1 << 2))) + goto exception; + + if (null_selector) /* for NULL selector skip all following checks */ + goto load; + + ret = read_segment_descriptor(ctxt, ops, selector, &seg_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + + err_code = selector & 0xfffc; + err_vec = GP_VECTOR; + + /* can't load system descriptor into segment selecor */ + if (seg <= VCPU_SREG_GS && !seg_desc.s) + goto exception; + + if (!seg_desc.p) { + err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; + goto exception; + } + + rpl = selector & 3; + dpl = seg_desc.dpl; + cpl = ops->cpl(ctxt->vcpu); + + switch (seg) { + case VCPU_SREG_SS: + /* + * segment is not a writable data segment or segment + * selector's RPL != CPL or segment selector's RPL != CPL + */ + if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl) + goto exception; + break; + case VCPU_SREG_CS: + if (!(seg_desc.type & 8)) + goto exception; + + if (seg_desc.type & 4) { + /* conforming */ + if (dpl > cpl) + goto exception; + } else { + /* nonconforming */ + if (rpl > cpl || dpl != cpl) + goto exception; + } + /* CS(RPL) <- CPL */ + selector = (selector & 0xfffc) | cpl; + break; + case VCPU_SREG_TR: + if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) + goto exception; + break; + case VCPU_SREG_LDTR: + if (seg_desc.s || seg_desc.type != 2) + goto exception; + break; + default: /* DS, ES, FS, or GS */ + /* + * segment is not a data or readable code segment or + * ((segment is a data or nonconforming code segment) + * and (both RPL and CPL > DPL)) + */ + if ((seg_desc.type & 0xa) == 0x8 || + (((seg_desc.type & 0xc) != 0xc) && + (rpl > dpl && cpl > dpl))) + goto exception; + break; + } + + if (seg_desc.s) { + /* mark segment as accessed */ + seg_desc.type |= 1; + ret = write_segment_descriptor(ctxt, ops, selector, &seg_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + } +load: + ops->set_segment_selector(selector, seg, ctxt->vcpu); + ops->set_cached_descriptor(&seg_desc, seg, ctxt->vcpu); + return X86EMUL_CONTINUE; +exception: + kvm_queue_exception_e(ctxt->vcpu, err_vec, err_code); + return X86EMUL_PROPAGATE_FAULT; +} + static inline void emulate_push(struct x86_emulate_ctxt *ctxt) { struct decode_cache *c = &ctxt->decode; @@ -1251,7 +1521,7 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, int rc; unsigned long val, change_mask; int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - int cpl = kvm_x86_ops->get_cpl(ctxt->vcpu); + int cpl = ops->cpl(ctxt->vcpu); rc = emulate_pop(ctxt, ops, &val, len); if (rc != X86EMUL_CONTINUE) @@ -1306,10 +1576,10 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, int rc; rc = emulate_pop(ctxt, ops, &selector, c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) return rc; - rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, seg); + rc = load_segment_descriptor(ctxt, ops, (u16)selector, seg); return rc; } @@ -1332,7 +1602,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; + int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; while (reg >= VCPU_REGS_RAX) { @@ -1343,7 +1613,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt, } rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes); - if (rc != 0) + if (rc != X86EMUL_CONTINUE) break; --reg; } @@ -1354,12 +1624,8 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc; - rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); - if (rc != 0) - return rc; - return 0; + return emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); } static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt) @@ -1395,7 +1661,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - int rc = 0; switch (c->modrm_reg) { case 0 ... 1: /* test */ @@ -1408,11 +1673,9 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt, emulate_1op("neg", c->dst, ctxt->eflags); break; default: - DPRINTF("Cannot emulate %02x\n", c->b); - rc = X86EMUL_UNHANDLEABLE; - break; + return 0; } - return rc; + return 1; } static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, @@ -1442,20 +1705,14 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt, emulate_push(ctxt); break; } - return 0; + return X86EMUL_CONTINUE; } static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, - unsigned long memop) + struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - u64 old, new; - int rc; - - rc = ops->read_emulated(memop, &old, 8, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; + u64 old = c->dst.orig_val; if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) || ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) { @@ -1463,17 +1720,13 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, c->regs[VCPU_REGS_RAX] = (u32) (old >> 0); c->regs[VCPU_REGS_RDX] = (u32) (old >> 32); ctxt->eflags &= ~EFLG_ZF; - } else { - new = ((u64)c->regs[VCPU_REGS_RCX] << 32) | + c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) | (u32) c->regs[VCPU_REGS_RBX]; - rc = ops->cmpxchg_emulated(memop, &old, &new, 8, ctxt->vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; ctxt->eflags |= EFLG_ZF; } - return 0; + return X86EMUL_CONTINUE; } static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, @@ -1484,14 +1737,14 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, unsigned long cs; rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; if (c->op_bytes == 4) c->eip = (u32)c->eip; rc = emulate_pop(ctxt, ops, &cs, c->op_bytes); - if (rc) + if (rc != X86EMUL_CONTINUE) return rc; - rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, VCPU_SREG_CS); + rc = load_segment_descriptor(ctxt, ops, (u16)cs, VCPU_SREG_CS); return rc; } @@ -1544,7 +1797,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt, default: break; } - return 0; + return X86EMUL_CONTINUE; } static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask) @@ -1598,8 +1851,11 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt) u64 msr_data; /* syscall is not available in real mode */ - if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) - return X86EMUL_UNHANDLEABLE; + if (ctxt->mode == X86EMUL_MODE_REAL || + ctxt->mode == X86EMUL_MODE_VM86) { + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + return X86EMUL_PROPAGATE_FAULT; + } setup_syscalls_segments(ctxt, &cs, &ss); @@ -1649,14 +1905,16 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt) /* inject #GP if in real mode */ if (ctxt->mode == X86EMUL_MODE_REAL) { kvm_inject_gp(ctxt->vcpu, 0); - return X86EMUL_UNHANDLEABLE; + return X86EMUL_PROPAGATE_FAULT; } /* XXX sysenter/sysexit have not been tested in 64bit mode. * Therefore, we inject an #UD. */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - return X86EMUL_UNHANDLEABLE; + if (ctxt->mode == X86EMUL_MODE_PROT64) { + kvm_queue_exception(ctxt->vcpu, UD_VECTOR); + return X86EMUL_PROPAGATE_FAULT; + } setup_syscalls_segments(ctxt, &cs, &ss); @@ -1711,7 +1969,7 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) { kvm_inject_gp(ctxt->vcpu, 0); - return X86EMUL_UNHANDLEABLE; + return X86EMUL_PROPAGATE_FAULT; } setup_syscalls_segments(ctxt, &cs, &ss); @@ -1756,7 +2014,8 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) +static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) { int iopl; if (ctxt->mode == X86EMUL_MODE_REAL) @@ -1764,7 +2023,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) if (ctxt->mode == X86EMUL_MODE_VM86) return true; iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; - return kvm_x86_ops->get_cpl(ctxt->vcpu) > iopl; + return ops->cpl(ctxt->vcpu) > iopl; } static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, @@ -1801,22 +2060,419 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops, u16 port, u16 len) { - if (emulator_bad_iopl(ctxt)) + if (emulator_bad_iopl(ctxt, ops)) if (!emulator_io_port_access_allowed(ctxt, ops, port, len)) return false; return true; } +static u32 get_cached_descriptor_base(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + int seg) +{ + struct desc_struct desc; + if (ops->get_cached_descriptor(&desc, seg, ctxt->vcpu)) + return get_desc_base(&desc); + else + return ~0; +} + +static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_16 *tss) +{ + struct decode_cache *c = &ctxt->decode; + + tss->ip = c->eip; + tss->flag = ctxt->eflags; + tss->ax = c->regs[VCPU_REGS_RAX]; + tss->cx = c->regs[VCPU_REGS_RCX]; + tss->dx = c->regs[VCPU_REGS_RDX]; + tss->bx = c->regs[VCPU_REGS_RBX]; + tss->sp = c->regs[VCPU_REGS_RSP]; + tss->bp = c->regs[VCPU_REGS_RBP]; + tss->si = c->regs[VCPU_REGS_RSI]; + tss->di = c->regs[VCPU_REGS_RDI]; + + tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); + tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); + tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); + tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); + tss->ldt = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); +} + +static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_16 *tss) +{ + struct decode_cache *c = &ctxt->decode; + int ret; + + c->eip = tss->ip; + ctxt->eflags = tss->flag | 2; + c->regs[VCPU_REGS_RAX] = tss->ax; + c->regs[VCPU_REGS_RCX] = tss->cx; + c->regs[VCPU_REGS_RDX] = tss->dx; + c->regs[VCPU_REGS_RBX] = tss->bx; + c->regs[VCPU_REGS_RSP] = tss->sp; + c->regs[VCPU_REGS_RBP] = tss->bp; + c->regs[VCPU_REGS_RSI] = tss->si; + c->regs[VCPU_REGS_RDI] = tss->di; + + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + ops->set_segment_selector(tss->ldt, VCPU_SREG_LDTR, ctxt->vcpu); + ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); + ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + ret = load_segment_descriptor(ctxt, ops, tss->ldt, VCPU_SREG_LDTR); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS); + if (ret != X86EMUL_CONTINUE) + return ret; + + return X86EMUL_CONTINUE; +} + +static int task_switch_16(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, u16 old_tss_sel, + ulong old_tss_base, struct desc_struct *new_desc) +{ + struct tss_segment_16 tss_seg; + int ret; + u32 err, new_tss_base = get_desc_base(new_desc); + + ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + save_state_to_tss16(ctxt, ops, &tss_seg); + + ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + + if (old_tss_sel != 0xffff) { + tss_seg.prev_task_link = old_tss_sel; + + ret = ops->write_std(new_tss_base, + &tss_seg.prev_task_link, + sizeof tss_seg.prev_task_link, + ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + } + + return load_state_from_tss16(ctxt, ops, &tss_seg); +} + +static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_32 *tss) +{ + struct decode_cache *c = &ctxt->decode; + + tss->cr3 = ops->get_cr(3, ctxt->vcpu); + tss->eip = c->eip; + tss->eflags = ctxt->eflags; + tss->eax = c->regs[VCPU_REGS_RAX]; + tss->ecx = c->regs[VCPU_REGS_RCX]; + tss->edx = c->regs[VCPU_REGS_RDX]; + tss->ebx = c->regs[VCPU_REGS_RBX]; + tss->esp = c->regs[VCPU_REGS_RSP]; + tss->ebp = c->regs[VCPU_REGS_RBP]; + tss->esi = c->regs[VCPU_REGS_RSI]; + tss->edi = c->regs[VCPU_REGS_RDI]; + + tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu); + tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu); + tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu); + tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu); + tss->fs = ops->get_segment_selector(VCPU_SREG_FS, ctxt->vcpu); + tss->gs = ops->get_segment_selector(VCPU_SREG_GS, ctxt->vcpu); + tss->ldt_selector = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu); +} + +static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + struct tss_segment_32 *tss) +{ + struct decode_cache *c = &ctxt->decode; + int ret; + + ops->set_cr(3, tss->cr3, ctxt->vcpu); + c->eip = tss->eip; + ctxt->eflags = tss->eflags | 2; + c->regs[VCPU_REGS_RAX] = tss->eax; + c->regs[VCPU_REGS_RCX] = tss->ecx; + c->regs[VCPU_REGS_RDX] = tss->edx; + c->regs[VCPU_REGS_RBX] = tss->ebx; + c->regs[VCPU_REGS_RSP] = tss->esp; + c->regs[VCPU_REGS_RBP] = tss->ebp; + c->regs[VCPU_REGS_RSI] = tss->esi; + c->regs[VCPU_REGS_RDI] = tss->edi; + + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + ops->set_segment_selector(tss->ldt_selector, VCPU_SREG_LDTR, ctxt->vcpu); + ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu); + ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu); + ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu); + ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu); + ops->set_segment_selector(tss->fs, VCPU_SREG_FS, ctxt->vcpu); + ops->set_segment_selector(tss->gs, VCPU_SREG_GS, ctxt->vcpu); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + ret = load_segment_descriptor(ctxt, ops, tss->ldt_selector, VCPU_SREG_LDTR); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->fs, VCPU_SREG_FS); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = load_segment_descriptor(ctxt, ops, tss->gs, VCPU_SREG_GS); + if (ret != X86EMUL_CONTINUE) + return ret; + + return X86EMUL_CONTINUE; +} + +static int task_switch_32(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, u16 old_tss_sel, + ulong old_tss_base, struct desc_struct *new_desc) +{ + struct tss_segment_32 tss_seg; + int ret; + u32 err, new_tss_base = get_desc_base(new_desc); + + ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + save_state_to_tss32(ctxt, ops, &tss_seg); + + ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err); + return ret; + } + + ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu, + &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + + if (old_tss_sel != 0xffff) { + tss_seg.prev_task_link = old_tss_sel; + + ret = ops->write_std(new_tss_base, + &tss_seg.prev_task_link, + sizeof tss_seg.prev_task_link, + ctxt->vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) { + /* FIXME: need to provide precise fault address */ + kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err); + return ret; + } + } + + return load_state_from_tss32(ctxt, ops, &tss_seg); +} + +static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, + u16 tss_selector, int reason, + bool has_error_code, u32 error_code) +{ + struct desc_struct curr_tss_desc, next_tss_desc; + int ret; + u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu); + ulong old_tss_base = + get_cached_descriptor_base(ctxt, ops, VCPU_SREG_TR); + u32 desc_limit; + + /* FIXME: old_tss_base == ~0 ? */ + + ret = read_segment_descriptor(ctxt, ops, tss_selector, &next_tss_desc); + if (ret != X86EMUL_CONTINUE) + return ret; + ret = read_segment_descriptor(ctxt, ops, old_tss_sel, &curr_tss_desc); + if (ret != X86EMUL_CONTINUE) |