diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/emulate.c | 867 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.c | 6 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 123 | ||||
-rw-r--r-- | arch/x86/kvm/irq.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_cache_regs.h | 7 | ||||
-rw-r--r-- | arch/x86/kvm/kvm_timer.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 167 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 4 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 5 | ||||
-rw-r--r-- | arch/x86/kvm/mmu_audit.c | 6 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 24 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 93 | ||||
-rw-r--r-- | arch/x86/kvm/trace.h | 118 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 131 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 277 |
15 files changed, 1068 insertions, 766 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8b4cc5f067de..f1e3be18a08f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -29,6 +29,39 @@ #include "tss.h" /* + * Operand types + */ +#define OpNone 0ull +#define OpImplicit 1ull /* No generic decode */ +#define OpReg 2ull /* Register */ +#define OpMem 3ull /* Memory */ +#define OpAcc 4ull /* Accumulator: AL/AX/EAX/RAX */ +#define OpDI 5ull /* ES:DI/EDI/RDI */ +#define OpMem64 6ull /* Memory, 64-bit */ +#define OpImmUByte 7ull /* Zero-extended 8-bit immediate */ +#define OpDX 8ull /* DX register */ +#define OpCL 9ull /* CL register (for shifts) */ +#define OpImmByte 10ull /* 8-bit sign extended immediate */ +#define OpOne 11ull /* Implied 1 */ +#define OpImm 12ull /* Sign extended immediate */ +#define OpMem16 13ull /* Memory operand (16-bit). */ +#define OpMem32 14ull /* Memory operand (32-bit). */ +#define OpImmU 15ull /* Immediate operand, zero extended */ +#define OpSI 16ull /* SI/ESI/RSI */ +#define OpImmFAddr 17ull /* Immediate far address */ +#define OpMemFAddr 18ull /* Far address in memory */ +#define OpImmU16 19ull /* Immediate operand, 16 bits, zero extended */ +#define OpES 20ull /* ES */ +#define OpCS 21ull /* CS */ +#define OpSS 22ull /* SS */ +#define OpDS 23ull /* DS */ +#define OpFS 24ull /* FS */ +#define OpGS 25ull /* GS */ + +#define OpBits 5 /* Width of operand field */ +#define OpMask ((1ull << OpBits) - 1) + +/* * Opcode effective-address decode tables. * Note that we only emulate instructions that have at least one memory * operand (excluding implicit stack references). We assume that stack @@ -40,37 +73,35 @@ /* Operand sizes: 8-bit operands or specified/overridden size. */ #define ByteOp (1<<0) /* 8-bit operands. */ /* Destination operand type. */ -#define ImplicitOps (1<<1) /* Implicit in opcode. No generic decode. */ -#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 DstImmUByte (7<<1) /* 8-bit unsigned immediate operand */ -#define DstDX (8<<1) /* Destination is in DX register */ -#define DstMask (0xf<<1) +#define DstShift 1 +#define ImplicitOps (OpImplicit << DstShift) +#define DstReg (OpReg << DstShift) +#define DstMem (OpMem << DstShift) +#define DstAcc (OpAcc << DstShift) +#define DstDI (OpDI << DstShift) +#define DstMem64 (OpMem64 << DstShift) +#define DstImmUByte (OpImmUByte << DstShift) +#define DstDX (OpDX << DstShift) +#define DstMask (OpMask << DstShift) /* Source operand type. */ -#define SrcNone (0<<5) /* No source operand. */ -#define SrcReg (1<<5) /* Register operand. */ -#define SrcMem (2<<5) /* Memory operand. */ -#define SrcMem16 (3<<5) /* Memory operand (16-bit). */ -#define SrcMem32 (4<<5) /* Memory operand (32-bit). */ -#define SrcImm (5<<5) /* Immediate operand. */ -#define SrcImmByte (6<<5) /* 8-bit sign-extended immediate operand. */ -#define SrcOne (7<<5) /* Implied '1' */ -#define SrcImmUByte (8<<5) /* 8-bit unsigned immediate operand. */ -#define SrcImmU (9<<5) /* Immediate operand, unsigned */ -#define SrcSI (0xa<<5) /* Source is in the DS:RSI */ -#define SrcImmFAddr (0xb<<5) /* Source is immediate far address */ -#define SrcMemFAddr (0xc<<5) /* Source is far address in memory */ -#define SrcAcc (0xd<<5) /* Source Accumulator */ -#define SrcImmU16 (0xe<<5) /* Immediate operand, unsigned, 16 bits */ -#define SrcDX (0xf<<5) /* Source is in DX register */ -#define SrcMask (0xf<<5) -/* Generic ModRM decode. */ -#define ModRM (1<<9) -/* Destination is only written; never read. */ -#define Mov (1<<10) +#define SrcShift 6 +#define SrcNone (OpNone << SrcShift) +#define SrcReg (OpReg << SrcShift) +#define SrcMem (OpMem << SrcShift) +#define SrcMem16 (OpMem16 << SrcShift) +#define SrcMem32 (OpMem32 << SrcShift) +#define SrcImm (OpImm << SrcShift) +#define SrcImmByte (OpImmByte << SrcShift) +#define SrcOne (OpOne << SrcShift) +#define SrcImmUByte (OpImmUByte << SrcShift) +#define SrcImmU (OpImmU << SrcShift) +#define SrcSI (OpSI << SrcShift) +#define SrcImmFAddr (OpImmFAddr << SrcShift) +#define SrcMemFAddr (OpMemFAddr << SrcShift) +#define SrcAcc (OpAcc << SrcShift) +#define SrcImmU16 (OpImmU16 << SrcShift) +#define SrcDX (OpDX << SrcShift) +#define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) #define MemAbs (1<<12) /* Memory operand is absolute displacement */ #define String (1<<13) /* String instruction (rep capable) */ @@ -81,6 +112,10 @@ #define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */ #define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */ #define Sse (1<<18) /* SSE Vector instruction */ +/* Generic ModRM decode. */ +#define ModRM (1<<19) +/* Destination is only written; never read. */ +#define Mov (1<<20) /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define VendorSpecific (1<<22) /* Vendor specific instruction */ @@ -91,12 +126,19 @@ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) /* Source 2 operand type */ -#define Src2None (0<<29) -#define Src2CL (1<<29) -#define Src2ImmByte (2<<29) -#define Src2One (3<<29) -#define Src2Imm (4<<29) -#define Src2Mask (7<<29) +#define Src2Shift (29) +#define Src2None (OpNone << Src2Shift) +#define Src2CL (OpCL << Src2Shift) +#define Src2ImmByte (OpImmByte << Src2Shift) +#define Src2One (OpOne << Src2Shift) +#define Src2Imm (OpImm << Src2Shift) +#define Src2ES (OpES << Src2Shift) +#define Src2CS (OpCS << Src2Shift) +#define Src2SS (OpSS << Src2Shift) +#define Src2DS (OpDS << Src2Shift) +#define Src2FS (OpFS << Src2Shift) +#define Src2GS (OpGS << Src2Shift) +#define Src2Mask (OpMask << Src2Shift) #define X2(x...) x, x #define X3(x...) X2(x), x @@ -108,8 +150,8 @@ #define X16(x...) X8(x), X8(x) struct opcode { - u32 flags; - u8 intercept; + u64 flags : 56; + u64 intercept : 8; union { int (*execute)(struct x86_emulate_ctxt *ctxt); struct opcode *group; @@ -205,105 +247,100 @@ struct gprefix { #define ON64(x) #endif -#define ____emulate_2op(_op, _src, _dst, _eflags, _x, _y, _suffix, _dsttype) \ +#define ____emulate_2op(ctxt, _op, _x, _y, _suffix, _dsttype) \ do { \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "4", "2") \ _op _suffix " %"_x"3,%1; " \ _POST_EFLAGS("0", "4", "2") \ - : "=m" (_eflags), "+q" (*(_dsttype*)&(_dst).val),\ + : "=m" ((ctxt)->eflags), \ + "+q" (*(_dsttype*)&(ctxt)->dst.val), \ "=&r" (_tmp) \ - : _y ((_src).val), "i" (EFLAGS_MASK)); \ + : _y ((ctxt)->src.val), "i" (EFLAGS_MASK)); \ } while (0) /* Raw emulation: instruction has two explicit operands. */ -#define __emulate_2op_nobyte(_op,_src,_dst,_eflags,_wx,_wy,_lx,_ly,_qx,_qy) \ +#define __emulate_2op_nobyte(ctxt,_op,_wx,_wy,_lx,_ly,_qx,_qy) \ do { \ unsigned long _tmp; \ \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 2: \ - ____emulate_2op(_op,_src,_dst,_eflags,_wx,_wy,"w",u16);\ + ____emulate_2op(ctxt,_op,_wx,_wy,"w",u16); \ break; \ case 4: \ - ____emulate_2op(_op,_src,_dst,_eflags,_lx,_ly,"l",u32);\ + ____emulate_2op(ctxt,_op,_lx,_ly,"l",u32); \ break; \ case 8: \ - ON64(____emulate_2op(_op,_src,_dst,_eflags,_qx,_qy,"q",u64)); \ + ON64(____emulate_2op(ctxt,_op,_qx,_qy,"q",u64)); \ break; \ } \ } while (0) -#define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ +#define __emulate_2op(ctxt,_op,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ do { \ unsigned long _tmp; \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 1: \ - ____emulate_2op(_op,_src,_dst,_eflags,_bx,_by,"b",u8); \ + ____emulate_2op(ctxt,_op,_bx,_by,"b",u8); \ break; \ default: \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ + __emulate_2op_nobyte(ctxt, _op, \ _wx, _wy, _lx, _ly, _qx, _qy); \ break; \ } \ } while (0) /* Source operand is byte-sized and may be restricted to just %cl. */ -#define emulate_2op_SrcB(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "c", "b", "c", "b", "c", "b", "c") +#define emulate_2op_SrcB(ctxt, _op) \ + __emulate_2op(ctxt, _op, "b", "c", "b", "c", "b", "c", "b", "c") /* Source operand is byte, word, long or quad sized. */ -#define emulate_2op_SrcV(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "q", "w", "r", _LO32, "r", "", "r") +#define emulate_2op_SrcV(ctxt, _op) \ + __emulate_2op(ctxt, _op, "b", "q", "w", "r", _LO32, "r", "", "r") /* Source operand is word, long or quad sized. */ -#define emulate_2op_SrcV_nobyte(_op, _src, _dst, _eflags) \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ - "w", "r", _LO32, "r", "", "r") +#define emulate_2op_SrcV_nobyte(ctxt, _op) \ + __emulate_2op_nobyte(ctxt, _op, "w", "r", _LO32, "r", "", "r") /* Instruction has three operands and one operand is stored in ECX register */ -#define __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, _suffix, _type) \ +#define __emulate_2op_cl(ctxt, _op, _suffix, _type) \ do { \ unsigned long _tmp; \ - _type _clv = (_cl).val; \ - _type _srcv = (_src).val; \ - _type _dstv = (_dst).val; \ + _type _clv = (ctxt)->src2.val; \ + _type _srcv = (ctxt)->src.val; \ + _type _dstv = (ctxt)->dst.val; \ \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "5", "2") \ _op _suffix " %4,%1 \n" \ _POST_EFLAGS("0", "5", "2") \ - : "=m" (_eflags), "+r" (_dstv), "=&r" (_tmp) \ + : "=m" ((ctxt)->eflags), "+r" (_dstv), "=&r" (_tmp) \ : "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK) \ ); \ \ - (_cl).val = (unsigned long) _clv; \ - (_src).val = (unsigned long) _srcv; \ - (_dst).val = (unsigned long) _dstv; \ + (ctxt)->src2.val = (unsigned long) _clv; \ + (ctxt)->src2.val = (unsigned long) _srcv; \ + (ctxt)->dst.val = (unsigned long) _dstv; \ } while (0) -#define emulate_2op_cl(_op, _cl, _src, _dst, _eflags) \ +#define emulate_2op_cl(ctxt, _op) \ do { \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 2: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "w", unsigned short); \ + __emulate_2op_cl(ctxt, _op, "w", u16); \ break; \ case 4: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "l", unsigned int); \ + __emulate_2op_cl(ctxt, _op, "l", u32); \ break; \ case 8: \ - ON64(__emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "q", unsigned long)); \ + ON64(__emulate_2op_cl(ctxt, _op, "q", ulong)); \ break; \ } \ } while (0) -#define __emulate_1op(_op, _dst, _eflags, _suffix) \ +#define __emulate_1op(ctxt, _op, _suffix) \ do { \ unsigned long _tmp; \ \ @@ -311,39 +348,27 @@ struct gprefix { _PRE_EFLAGS("0", "3", "2") \ _op _suffix " %1; " \ _POST_EFLAGS("0", "3", "2") \ - : "=m" (_eflags), "+m" ((_dst).val), \ + : "=m" ((ctxt)->eflags), "+m" ((ctxt)->dst.val), \ "=&r" (_tmp) \ : "i" (EFLAGS_MASK)); \ } while (0) /* Instruction has only one explicit operand (no source operand). */ -#define emulate_1op(_op, _dst, _eflags) \ +#define emulate_1op(ctxt, _op) \ do { \ - switch ((_dst).bytes) { \ - case 1: __emulate_1op(_op, _dst, _eflags, "b"); break; \ - case 2: __emulate_1op(_op, _dst, _eflags, "w"); break; \ - case 4: __emulate_1op(_op, _dst, _eflags, "l"); break; \ - case 8: ON64(__emulate_1op(_op, _dst, _eflags, "q")); break; \ + switch ((ctxt)->dst.bytes) { \ + case 1: __emulate_1op(ctxt, _op, "b"); break; \ + case 2: __emulate_1op(ctxt, _op, "w"); break; \ + case 4: __emulate_1op(ctxt, _op, "l"); break; \ + case 8: ON64(__emulate_1op(ctxt, _op, "q")); break; \ } \ } while (0) -#define __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags, _suffix) \ - do { \ - unsigned long _tmp; \ - \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "4", "1") \ - _op _suffix " %5; " \ - _POST_EFLAGS("0", "4", "1") \ - : "=m" (_eflags), "=&r" (_tmp), \ - "+a" (_rax), "+d" (_rdx) \ - : "i" (EFLAGS_MASK), "m" ((_src).val), \ - "a" (_rax), "d" (_rdx)); \ - } while (0) - -#define __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, _eflags, _suffix, _ex) \ +#define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex) \ do { \ unsigned long _tmp; \ + ulong *rax = &(ctxt)->regs[VCPU_REGS_RAX]; \ + ulong *rdx = &(ctxt)->regs[VCPU_REGS_RDX]; \ \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "5", "1") \ @@ -356,53 +381,27 @@ struct gprefix { "jmp 2b \n\t" \ ".popsection \n\t" \ _ASM_EXTABLE(1b, 3b) \ - : "=m" (_eflags), "=&r" (_tmp), \ - "+a" (_rax), "+d" (_rdx), "+qm"(_ex) \ - : "i" (EFLAGS_MASK), "m" ((_src).val), \ - "a" (_rax), "d" (_rdx)); \ + : "=m" ((ctxt)->eflags), "=&r" (_tmp), \ + "+a" (*rax), "+d" (*rdx), "+qm"(_ex) \ + : "i" (EFLAGS_MASK), "m" ((ctxt)->src.val), \ + "a" (*rax), "d" (*rdx)); \ } while (0) /* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */ -#define emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags) \ +#define emulate_1op_rax_rdx(ctxt, _op, _ex) \ do { \ - switch((_src).bytes) { \ + switch((ctxt)->src.bytes) { \ case 1: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "b"); \ + __emulate_1op_rax_rdx(ctxt, _op, "b", _ex); \ break; \ case 2: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "w"); \ + __emulate_1op_rax_rdx(ctxt, _op, "w", _ex); \ break; \ case 4: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "l"); \ - break; \ - case 8: \ - ON64(__emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "q")); \ - break; \ - } \ - } while (0) - -#define emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, _eflags, _ex) \ - do { \ - switch((_src).bytes) { \ - case 1: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "b", _ex); \ - break; \ - case 2: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "w", _ex); \ - break; \ - case 4: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "l", _ex); \ + __emulate_1op_rax_rdx(ctxt, _op, "l", _ex); \ break; \ case 8: ON64( \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "q", _ex)); \ + __emulate_1op_rax_rdx(ctxt, _op, "q", _ex)); \ break; \ } \ } while (0) @@ -651,41 +650,50 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt, return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception); } -static int do_insn_fetch_byte(struct x86_emulate_ctxt *ctxt, - unsigned long eip, u8 *dest) +/* + * Fetch the next byte of the instruction being emulated which is pointed to + * by ctxt->_eip, then increment ctxt->_eip. + * + * Also prefetch the remaining bytes of the instruction without crossing page + * boundary if they are not in fetch_cache yet. + */ +static int do_insn_fetch_byte(struct x86_emulate_ctxt *ctxt, u8 *dest) { struct fetch_cache *fc = &ctxt->fetch; int rc; int size, cur_size; - if (eip == fc->end) { + if (ctxt->_eip == fc->end) { unsigned long linear; - struct segmented_address addr = { .seg=VCPU_SREG_CS, .ea=eip}; + struct segmented_address addr = { .seg = VCPU_SREG_CS, + .ea = ctxt->_eip }; cur_size = fc->end - fc->start; - size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip)); + size = min(15UL - cur_size, + PAGE_SIZE - offset_in_page(ctxt->_eip)); rc = __linearize(ctxt, addr, size, false, true, &linear); - if (rc != X86EMUL_CONTINUE) + if (unlikely(rc != X86EMUL_CONTINUE)) return rc; rc = ctxt->ops->fetch(ctxt, linear, fc->data + cur_size, size, &ctxt->exception); - if (rc != X86EMUL_CONTINUE) + if (unlikely(rc != X86EMUL_CONTINUE)) return rc; fc->end += size; } - *dest = fc->data[eip - fc->start]; + *dest = fc->data[ctxt->_eip - fc->start]; + ctxt->_eip++; return X86EMUL_CONTINUE; } static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, - unsigned long eip, void *dest, unsigned size) + void *dest, unsigned size) { int rc; /* x86 instructions are limited to 15 bytes. */ - if (eip + size - ctxt->eip > 15) + if (unlikely(ctxt->_eip + size - ctxt->eip > 15)) return X86EMUL_UNHANDLEABLE; while (size--) { - rc = do_insn_fetch_byte(ctxt, eip++, dest++); + rc = do_insn_fetch_byte(ctxt, dest++); if (rc != X86EMUL_CONTINUE) return rc; } @@ -693,20 +701,18 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, } /* Fetch next part of the instruction being emulated. */ -#define insn_fetch(_type, _size, _eip) \ +#define insn_fetch(_type, _ctxt) \ ({ unsigned long _x; \ - rc = do_insn_fetch(ctxt, (_eip), &_x, (_size)); \ + rc = do_insn_fetch(_ctxt, &_x, sizeof(_type)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ - (_eip) += (_size); \ (_type)_x; \ }) -#define insn_fetch_arr(_arr, _size, _eip) \ -({ rc = do_insn_fetch(ctxt, (_eip), _arr, (_size)); \ +#define insn_fetch_arr(_arr, _size, _ctxt) \ +({ rc = do_insn_fetch(_ctxt, _arr, (_size)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ - (_eip) += (_size); \ }) /* @@ -894,7 +900,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_rm = base_reg = (ctxt->rex_prefix & 1) << 3; /* REG.B */ } - ctxt->modrm = insn_fetch(u8, 1, ctxt->_eip); + ctxt->modrm = insn_fetch(u8, ctxt); ctxt->modrm_mod |= (ctxt->modrm & 0xc0) >> 6; ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3; ctxt->modrm_rm |= (ctxt->modrm & 0x07); @@ -928,13 +934,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 6) - modrm_ea += insn_fetch(u16, 2, ctxt->_eip); + modrm_ea += insn_fetch(u16, ctxt); break; case 1: - modrm_ea += insn_fetch(s8, 1, ctxt->_eip); + modrm_ea += insn_fetch(s8, ctxt); break; case 2: - modrm_ea += insn_fetch(u16, 2, ctxt->_eip); + modrm_ea += insn_fetch(u16, ctxt); break; } switch (ctxt->modrm_rm) { @@ -971,13 +977,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, } else { /* 32/64-bit ModR/M decode. */ if ((ctxt->modrm_rm & 7) == 4) { - sib = insn_fetch(u8, 1, ctxt->_eip); + sib = insn_fetch(u8, ctxt); index_reg |= (sib >> 3) & 7; base_reg |= sib & 7; scale = sib >> 6; if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0) - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); else modrm_ea += ctxt->regs[base_reg]; if (index_reg != 4) @@ -990,13 +996,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 5) - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); break; case 1: - modrm_ea += insn_fetch(s8, 1, ctxt->_eip); + modrm_ea += insn_fetch(s8, ctxt); break; case 2: - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); break; } } @@ -1013,13 +1019,13 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt, op->type = OP_MEM; switch (ctxt->ad_bytes) { case 2: - op->addr.mem.ea = insn_fetch(u16, 2, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u16, ctxt); break; case 4: - op->addr.mem.ea = insn_fetch(u32, 4, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u32, ctxt); break; case 8: - op->addr.mem.ea = insn_fetch(u64, 8, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u64, ctxt); break; } done: @@ -1452,15 +1458,18 @@ static int em_popf(struct x86_emulate_ctxt *ctxt) return emulate_popf(ctxt, &ctxt->dst.val, ctxt->op_bytes); } -static int emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg) +static int em_push_sreg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; + ctxt->src.val = get_segment_selector(ctxt, seg); return em_push(ctxt); } -static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, int seg) +static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; unsigned long selector; int rc; @@ -1674,64 +1683,74 @@ static int em_grp2(struct x86_emulate_ctxt *ctxt) { switch (ctxt->modrm_reg) { case 0: /* rol */ - emulate_2op_SrcB("rol", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rol"); break; case 1: /* ror */ - emulate_2op_SrcB("ror", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "ror"); break; case 2: /* rcl */ - emulate_2op_SrcB("rcl", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rcl"); break; case 3: /* rcr */ - emulate_2op_SrcB("rcr", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rcr"); break; case 4: /* sal/shl */ case 6: /* sal/shl */ - emulate_2op_SrcB("sal", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "sal"); break; case 5: /* shr */ - emulate_2op_SrcB("shr", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "shr"); break; case 7: /* sar */ - emulate_2op_SrcB("sar", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "sar"); break; } return X86EMUL_CONTINUE; } -static int em_grp3(struct x86_emulate_ctxt *ctxt) +static int em_not(struct x86_emulate_ctxt *ctxt) +{ + ctxt->dst.val = ~ctxt->dst.val; + return X86EMUL_CONTINUE; +} + +static int em_neg(struct x86_emulate_ctxt *ctxt) +{ + emulate_1op(ctxt, "neg"); + return X86EMUL_CONTINUE; +} + +static int em_mul_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 ex = 0; + + emulate_1op_rax_rdx(ctxt, "mul", ex); + return X86EMUL_CONTINUE; +} + +static int em_imul_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 ex = 0; + + emulate_1op_rax_rdx(ctxt, "imul", ex); + return X86EMUL_CONTINUE; +} + +static int em_div_ex(struct x86_emulate_ctxt *ctxt) { - unsigned long *rax = &ctxt->regs[VCPU_REGS_RAX]; - unsigned long *rdx = &ctxt->regs[VCPU_REGS_RDX]; u8 de = 0; - switch (ctxt->modrm_reg) { - case 0 ... 1: /* test */ - emulate_2op_SrcV("test", ctxt->src, ctxt->dst, ctxt->eflags); - break; - case 2: /* not */ - ctxt->dst.val = ~ctxt->dst.val; - break; - case 3: /* neg */ - emulate_1op("neg", ctxt->dst, ctxt->eflags); - break; - case 4: /* mul */ - emulate_1op_rax_rdx("mul", ctxt->src, *rax, *rdx, ctxt->eflags); - break; - case 5: /* imul */ - emulate_1op_rax_rdx("imul", ctxt->src, *rax, *rdx, ctxt->eflags); - break; - case 6: /* div */ - emulate_1op_rax_rdx_ex("div", ctxt->src, *rax, *rdx, - ctxt->eflags, de); - break; - case 7: /* idiv */ - emulate_1op_rax_rdx_ex("idiv", ctxt->src, *rax, *rdx, - ctxt->eflags, de); - break; - default: - return X86EMUL_UNHANDLEABLE; - } + emulate_1op_rax_rdx(ctxt, "div", de); + if (de) + return emulate_de(ctxt); + return X86EMUL_CONTINUE; +} + +static int em_idiv_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 de = 0; + + emulate_1op_rax_rdx(ctxt, "idiv", de); if (de) return emulate_de(ctxt); return X86EMUL_CONTINUE; @@ -1743,10 +1762,10 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) switch (ctxt->modrm_reg) { case 0: /* inc */ - emulate_1op("inc", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "inc"); break; case 1: /* dec */ - emulate_1op("dec", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "dec"); break; case 2: /* call near abs */ { long int old_eip; @@ -1812,8 +1831,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) return rc; } -static int emulate_load_segment(struct x86_emulate_ctxt *ctxt, int seg) +static int em_lseg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; unsigned short sel; int rc; @@ -2452,7 +2472,7 @@ static int em_das(struct x86_emulate_ctxt *ctxt) ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; - emulate_2op_SrcV("or", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "or"); ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF); if (cf) ctxt->eflags |= X86_EFLAGS_CF; @@ -2502,49 +2522,49 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) static int em_add(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("add", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "add"); return X86EMUL_CONTINUE; } static int em_or(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("or", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "or"); return X86EMUL_CONTINUE; } static int em_adc(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("adc", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "adc"); return X86EMUL_CONTINUE; } static int em_sbb(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("sbb", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "sbb"); return X86EMUL_CONTINUE; } static int em_and(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("and", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "and"); return X86EMUL_CONTINUE; } static int em_sub(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("sub", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "sub"); return X86EMUL_CONTINUE; } static int em_xor(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("xor", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "xor"); return X86EMUL_CONTINUE; } static int em_cmp(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("cmp", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "cmp"); /* Disable writeback. */ ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; @@ -2552,7 +2572,9 @@ static int em_cmp(struct x86_emulate_ctxt *ctxt) static int em_test(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("test", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "test"); + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } @@ -2570,7 +2592,7 @@ static int em_xchg(struct x86_emulate_ctxt *ctxt) static int em_imul(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV_nobyte("imul", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "imul"); return X86EMUL_CONTINUE; } @@ -3025,9 +3047,14 @@ static struct opcode group1A[] = { }; static struct opcode group3[] = { - D(DstMem | SrcImm | ModRM), D(DstMem | SrcImm | ModRM), - D(DstMem | SrcNone | ModRM | Lock), D(DstMem | SrcNone | ModRM | Lock), - X4(D(SrcMem | ModRM)), + I(DstMem | SrcImm | ModRM, em_test), + I(DstMem | SrcImm | ModRM, em_test), + I(DstMem | SrcNone | ModRM | Lock, em_not), + I(DstMem | SrcNone | ModRM | Lock, em_neg), + I(SrcMem | ModRM, em_mul_ex), + I(SrcMem | ModRM, em_imul_ex), + I(SrcMem | ModRM, em_div_ex), + I(SrcMem | ModRM, em_idiv_ex), }; static struct opcode group4[] = { @@ -3090,16 +3117,20 @@ static struct gprefix pfx_0f_6f_0f_7f = { static struct opcode opcode_table[256] = { /* 0x00 - 0x07 */ I6ALU(Lock, em_add), - D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), + I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg), + I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg), /* 0x08 - 0x0F */ I6ALU(Lock, em_or), - D(ImplicitOps | Stack | No64), N, + I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg), + N, /* 0x10 - 0x17 */ I6ALU(Lock, em_adc), - D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), + I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg), + I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg), /* 0x18 - 0x1F */ I6ALU(Lock, em_sbb), - D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), + I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg), + I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg), /* 0x20 - 0x27 */ I6ALU(Lock, em_and), N, N, /* 0x28 - 0x2F */ @@ -3167,7 +3198,8 @@ static struct opcode opcode_table[256] = { D2bv(DstMem | SrcImmByte | ModRM), I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm), I(ImplicitOps | Stack, em_ret), - D(DstReg | SrcMemFAddr | ModRM | No64), D(DstReg | SrcMemFAddr | ModRM | No64), + I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg), + I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg), G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ N, N, N, I(ImplicitOps | Stack, em_ret_far), @@ -3242,20 +3274,22 @@ static struct opcode twobyte_table[256] = { /* 0x90 - 0x9F */ X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ - D(ImplicitOps | Stack), D(ImplicitOps | Stack), + I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), DI(ImplicitOps, cpuid), D(DstMem | SrcReg | ModRM | BitOp), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ - D(ImplicitOps | Stack), D(ImplicitOps | Stack), + I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), DI(ImplicitOps, rsm), D(DstMem | SrcReg | ModRM | BitOp | Lock), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ D2bv(DstMem | SrcReg | ModRM | Lock), - D(DstReg | SrcMemFAddr | ModRM), D(DstMem | SrcReg | ModRM | BitOp | Lock), - D(DstReg | SrcMemFAddr | ModRM), D(DstReg | SrcMemFAddr | ModRM), + I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), + D(DstMem | SrcReg | ModRM | BitOp | Lock), + I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), + I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, @@ -3309,13 +3343,13 @@ static int decode_imm(struct x86_emulate_ctxt *ctxt, struct operand *op, /* NB. Immediates are sign-extended as necessary. */ switch (op->bytes) { case 1: - op->val = insn_fetch(s8, 1, ctxt->_eip); + op->val = insn_fetch(s8, ctxt); break; case 2: - op->val = insn_fetch(s16, 2, ctxt->_eip); + op->val = insn_fetch(s16, ctxt); break; case 4: - op->val = insn_fetch(s32, 4, ctxt->_eip); + op->val = insn_fetch(s32, ctxt); break; } if (!sign_extension) { @@ -3335,6 +3369,125 @@ done: return rc; } +static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, + unsigned d) +{ + int rc = X86EMUL_CONTINUE; + + switch (d) { + case OpReg: + decode_register_operand(ctxt, op, + op == &ctxt->dst && + ctxt->twobyte && (ctxt->b == 0xb6 || ctxt->b == 0xb7)); + break; + case OpImmUByte: + rc = decode_imm(ctxt, op, 1, false); + break; + case OpMem: + ctxt->memop.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + mem_common: + *op = ctxt->memop; + ctxt->memopp = op; + if ((ctxt->d & BitOp) && op == &ctxt->dst) + fetch_bit_operand(ctxt); + op->orig_val = op->val; + break; + case OpMem64: + ctxt->memop.bytes = 8; + goto mem_common; + case OpAcc: + op->type = OP_REG; + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.reg = &ctxt->regs[VCPU_REGS_RAX]; + fetch_register_operand(op); + op->orig_val = op->val; + break; + case OpDI: + op->type = OP_MEM; + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.mem.ea = + register_address(ctxt, ctxt->regs[VCPU_REGS_RDI]); + op->addr.mem.seg = VCPU_SREG_ES; + op->val = 0; + break; + case OpDX: + op->type = OP_REG; + op->bytes = 2; + op->addr.reg = &ctxt->regs[VCPU_REGS_RDX]; + fetch_register_operand(op); + break; + case OpCL: + op->bytes = 1; + op->val = ctxt->regs[VCPU_REGS_RCX] & 0xff; + break; + case OpImmByte: + rc = decode_imm(ctxt, op, 1, true); + break; + case OpOne: + op->bytes = 1; + op->val = 1; + break; + case OpImm: + rc = decode_imm(ctxt, op, imm_size(ctxt), true); + break; + case OpMem16: + ctxt->memop.bytes = 2; + goto mem_common; + case OpMem32: + ctxt->memop.bytes = 4; + goto mem_common; + case OpImmU16: + rc = decode_imm(ctxt, op, 2, false); + break; + case OpImmU: + rc = decode_imm(ctxt, op, imm_size(ctxt), false); + break; + case OpSI: + op->type = OP_MEM; + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.mem.ea = + register_address(ctxt, ctxt->regs[VCPU_REGS_RSI]); + op->addr.mem.seg = seg_override(ctxt); + op->val = 0; + break; + case OpImmFAddr: + op->type = OP_IMM; + op->addr.mem.ea = ctxt->_eip; + op->bytes = ctxt->op_bytes + 2; + insn_fetch_arr(op->valptr, op->bytes, ctxt); + break; + case OpMemFAddr: + ctxt->memop.bytes = ctxt->op_bytes + 2; + goto mem_common; + case OpES: + op->val = VCPU_SREG_ES; + break; + case OpCS: + op->val = VCPU_SREG_CS; + break; + case OpSS: + op->val = VCPU_SREG_SS; + break; + case OpDS: + op->val = VCPU_SREG_DS; + break; + case OpFS: + op->val = VCPU_SREG_FS; + break; + case OpGS: + op->val = VCPU_SREG_GS; + break; + case OpImplicit: + /* Special instructions do their own operand decoding. */ + default: + op->type = OP_NONE; /* Disable writeback. */ + break; + } + +done: + return rc; +} + int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) { int rc = X86EMUL_CONTINUE; @@ -3342,8 +3495,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) int def_op_bytes, def_ad_bytes, goffset, simd_prefix; bool op_prefix = false; struct opcode opcode; - struct operand memop = { .type = OP_NONE }, *memopp = NULL; + ctxt->memop.type = OP_NONE; + ctxt->memopp = NULL; ctxt->_eip = ctxt->eip; ctxt->fetch.start = ctxt->_eip; ctxt->fetch.end = ctxt->fetch.start + insn_len; @@ -3366,7 +3520,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) break; #endif default: - return -1; + return EMULATION_FAILED; } ctxt->op_bytes = def_op_bytes; @@ -3374,7 +3528,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) /* Legacy prefixes. */ for (;;) { - switch (ctxt->b = insn_fetch(u8, 1, ctxt->_eip)) { + switch (ctxt->b = insn_fetch(u8, ctxt)) { case 0x66: /* operand-size override */ op_prefix = true; /* switch between 2/4 bytes */ @@ -3430,7 +3584,7 @@ done_prefixes: /* Two-byte opcode? */ if (ctxt->b == 0x0f) { ctxt->twobyte = 1; - ctxt->b = insn_fetch(u8, 1, ctxt->_eip); + ctxt->b = insn_fetch(u8, ctxt); opcode = twobyte_table[ctxt->b]; } ctxt->d = opcode.flags; @@ -3438,13 +3592,13 @@ done_prefixes: while (ctxt->d & GroupMask) { switch (ctxt->d & GroupMask) { case Group: - ctxt->modrm = insn_fetch(u8, 1, ctxt->_eip); + ctxt->modrm = insn_fetch(u8, ctxt); --ctxt->_eip; goffset = (ctxt->modrm >> 3) & 7; opcode = opcode.u.group[goffset]; break; case GroupDual: - ctxt->modrm = insn_fetch(u8, 1, ctxt->_eip); + ctxt->modrm = insn_fetch(u8, ctxt); --ctxt->_eip; goffset = (ctxt->modrm >> 3) & 7; if ((ctxt->modrm >> 6) == 3) @@ -3458,7 +3612,7 @@ done_prefixes: break; case Prefix: if (ctxt->rep_prefix && op_prefix) - return X86EMUL_UNHANDLEABLE; + return EMULATION_FAILED; simd_prefix = op_prefix ? 0x66 : ctxt->rep_prefix; switch (simd_prefix) { case 0x00: opcode = opcode.u.gprefix->pfx_no; break; @@ -3468,10 +3622,10 @@ done_prefixes: } break; default: - return X86EMUL_UNHANDLEABLE; + return EMULATION_FAILED; } - ctxt->d &= ~GroupMask; + ctxt->d &= ~(u64)GroupMask; ctxt->d |= opcode.flags; } @@ -3481,10 +3635,10 @@ done_prefixes: /* Unrecognised? */ if (ctxt->d == 0 || (ctxt->d & Undefined)) - return -1; + return EMULATION_FAILED; if (!(ctxt->d & VendorSpecific) && ctxt->only_vendor_specific_insn) - return -1; + return EMULATION_FAILED; if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack)) ctxt->op_bytes = 8; @@ -3501,96 +3655,27 @@ done_prefixes: /* ModRM and SIB bytes. */ if (ctxt->d & ModRM) { - rc = decode_modrm(ctxt, &memop); + rc = decode_modrm(ctxt, &ctxt->memop); if (!ctxt->has_seg_override) set_seg_override(ctxt, ctxt->modrm_seg); } else if (ctxt->d & MemAbs) - rc = decode_abs(ctxt, &memop); + rc = decode_abs(ctxt, &ctxt->memop); if (rc != X86EMUL_CONTINUE) goto done; if (!ctxt->has_seg_override) set_seg_override(ctxt, VCPU_SREG_DS); - memop.addr.mem.seg = seg_override(ctxt); + ctxt->memop.addr.mem.seg = seg_override(ctxt); - if (memop.type == OP_MEM && ctxt->ad_bytes != 8) - memop.addr.mem.ea = (u32)memop.addr.mem.ea; + if (ctxt->memop.type == OP_MEM && ctxt->ad_bytes != 8) + ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea; /* * Decode and fetch the source operand: register, memory * or immediate. */ - switch (ctxt->d & SrcMask) { - case SrcNone: - break; - case SrcReg: - decode_register_operand(ctxt, &ctxt->src, 0); - break; - case SrcMem16: - memop.bytes = 2; - goto srcmem_common; - case SrcMem32: - memop.bytes = 4; - goto srcmem_common; - case SrcMem: - memop.bytes = (ctxt->d & ByteOp) ? 1 : - ctxt->op_bytes; - srcmem_common: - ctxt->src = memop; - memopp = &ctxt->src; - break; - case SrcImmU16: - rc = decode_imm(ctxt, &ctxt->src, 2, false); - break; - case SrcImm: - rc = decode_imm(ctxt, &ctxt->src, imm_size(ctxt), true); - break; - case SrcImmU: - rc = decode_imm(ctxt, &ctxt->src, imm_size(ctxt), false); - break; - case SrcImmByte: - rc = decode_imm(ctxt, &ctxt->src, 1, true); - break; - case SrcImmUByte: - rc = decode_imm(ctxt, &ctxt->src, 1, false); - break; - case SrcAcc: - ctxt->src.type = OP_REG; - ctxt->src.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->src.addr.reg = &ctxt->regs[VCPU_REGS_RAX]; - fetch_register_operand(&ctxt->src); - break; - case SrcOne: - ctxt->src.bytes = 1; - ctxt->src.val = 1; - break; - case SrcSI: - ctxt->src.type = OP_MEM; - ctxt->src.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->src.addr.mem.ea = - register_address(ctxt, ctxt->regs[VCPU_REGS_RSI]); - ctxt->src.addr.mem.seg = seg_override(ctxt); - ctxt->src.val = 0; - break; - case SrcImmFAddr: - ctxt->src.type = OP_IMM; - ctxt->src.addr.mem.ea = ctxt->_eip; - ctxt->src.bytes = ctxt->op_bytes + 2; - insn_fetch_arr(ctxt->src.valptr, ctxt->src.bytes, ctxt->_eip); - break; - case SrcMemFAddr: - memop.bytes = ctxt->op_bytes + 2; - goto srcmem_common; - break; - case SrcDX: - ctxt->src.type = OP_REG; - ctxt->src.bytes = 2; - ctxt->src.addr.reg = &ctxt->regs[VCPU_REGS_RDX]; - fetch_register_operand(&ctxt->src); - break; - } - + rc = decode_operand(ctxt, &ctxt->src, (ctxt->d >> SrcShift) & OpMask); if (rc != X86EMUL_CONTINUE) goto done; @@ -3598,85 +3683,18 @@ done_prefixes: * Decode and fetch the second source operand: register, memory * or immediate. */ - switch (ctxt->d & Src2Mask) { - case Src2None: - break; - case Src2CL: - ctxt->src2.bytes = 1; - ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff; - break; - case Src2ImmByte: - rc = decode_imm(ctxt, &ctxt->src2, 1, true); - break; - case Src2One: - ctxt->src2.bytes = 1; - ctxt->src2.val = 1; - break; - case Src2Imm: - rc = decode_imm(ctxt, &ctxt->src2, imm_size(ctxt), true); - break; - } - + rc = decode_operand(ctxt, &ctxt->src2, (ctxt->d >> Src2Shift) & OpMask); if (rc != X86EMUL_CONTINUE) goto done; /* Decode and fetch the destination operand: register or memory. */ - switch (ctxt->d & DstMask) { - case DstReg: - decode_register_operand(ctxt, &ctxt->dst, - ctxt->twobyte && (ctxt->b == 0xb6 || ctxt->b == 0xb7)); - break; - case DstImmUByte: - ctxt->dst.type = OP_IMM; - ctxt->dst.addr.mem.ea = ctxt->_eip; - ctxt->dst.bytes = 1; - ctxt->dst.val = insn_fetch(u8, 1, ctxt->_eip); - break; - case DstMem: - case DstMem64: - ctxt->dst = memop; - memopp = &ctxt->dst; - if ((ctxt->d & DstMask) == DstMem64) - ctxt->dst.bytes = 8; - else - ctxt->dst.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - if (ctxt->d & BitOp) - fetch_bit_operand(ctxt); - ctxt->dst.orig_val = ctxt->dst.val; - break; - case DstAcc: - ctxt->dst.type = OP_REG; - ctxt->dst.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->dst.addr.reg = &ctxt->regs[VCPU_REGS_RAX]; - fetch_register_operand(&ctxt->dst); - ctxt->dst.orig_val = ctxt->dst.val; - break; - case DstDI: - ctxt->dst.type = OP_MEM; - ctxt->dst.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->dst.addr.mem.ea = - register_address(ctxt, ctxt->regs[VCPU_REGS_RDI]); - ctxt->dst.addr.mem.seg = VCPU_SREG_ES; - ctxt->dst.val = 0; - break; - case DstDX: - ctxt->dst.type = OP_REG; - ctxt->dst.bytes = 2; - ctxt->dst.addr.reg = &ctxt->regs[VCPU_REGS_RDX]; - fetch_register_operand(&ctxt->dst); - break; - case ImplicitOps: - /* Special instructions do their own operand decoding. */ - default: - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - break; - } + rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask); done: - if (memopp && memopp->type == OP_MEM && ctxt->rip_relative) - memopp->addr.mem.ea += ctxt->_eip; + if (ctxt->memopp && ctxt->memopp->type == OP_MEM && ctxt->rip_relative) + ctxt->memopp->addr.mem.ea += ctxt->_eip; - return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; + return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) @@ -3825,32 +3843,11 @@ special_insn: goto twobyte_insn; switch (ctxt->b) { - case 0x06: /* push es */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_ES); - break; - case 0x07: /* pop es */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_ES); - break; - case 0x0e: /* push cs */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_CS); - break; - case 0x16: /* push ss */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_SS); - break; - case 0x17: /* pop ss */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_SS); - break; - case 0x1e: /* push ds */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_DS); - break; - case 0x1f: /* pop ds */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_DS); - break; case 0x40 ... 0x47: /* inc r16/r32 */ - emulate_1op("inc", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "inc"); break; case 0x48 ... 0x4f: /* dec r16/r32 */ - emulate_1op("dec", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "dec"); break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) @@ -3891,12 +3888,6 @@ special_insn: case 0xc0 ... 0xc1: rc = em_grp2(ctxt); break; - case 0xc4: /* les */ - rc = emulate_load_segment(ctxt, VCPU_SREG_ES); - break; - case 0xc5: /* lds */ - rc = emulate_load_segment(ctxt, VCPU_SREG_DS); - break; case 0xcc: /* int3 */ rc = emulate_int(ctxt, 3); break; @@ -3953,9 +3944,6 @@ special_insn: /* complement carry flag from eflags reg */ ctxt->eflags ^= EFLG_CF; break; - case 0xf6 ... 0xf7: /* Grp3 */ - rc = em_grp3(ctxt); - break; case 0xf8: /* clc */ ctxt->eflags &= ~EFLG_CF; break; @@ -4103,36 +4091,24 @@ twobyte_insn: case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); break; - case 0xa0: /* push fs */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_FS); - break; - case 0xa1: /* pop fs */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_FS); - break; case 0xa3: bt: /* bt */ ctxt->dst.type = OP_NONE; /* only subword offset */ ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; - emulate_2op_SrcV_nobyte("bt", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "bt"); break; case 0xa4: /* shld imm8, r, r/m */ case 0xa5: /* shld cl, r, r/m */ - emulate_2op_cl("shld", ctxt->src2, ctxt->src, ctxt->dst, ctxt->eflags); - break; - case 0xa8: /* push gs */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_GS); - break; - case 0xa9: /* pop gs */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_GS); + emulate_2op_cl(ctxt, "shld"); break; case 0xab: bts: /* bts */ - emulate_2op_SrcV_nobyte("bts", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "bts"); break; case 0xac: /* shrd imm8, r, r/m */ case 0xad: /* shrd cl, r, r/m */ - emulate_2op_cl("shrd", ctxt->src2, ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_cl(ctxt, "shrd"); break; case 0xae: /* clflush */ break; @@ -4143,7 +4119,7 @@ twobyte_insn: */ ctxt->src.orig_val = ctxt->src.val; ctxt->src.val = ctxt->regs[VCPU_REGS_RAX]; - emulate_2op_SrcV("cmp", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "cmp"); if (ctxt->eflags & EFLG_ZF) { /* Success: write back to memory. */ ctxt->dst.val = ctxt->src.orig_val; @@ -4153,18 +4129,9 @@ twobyte_insn: ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX]; } break; - case 0xb2: /* lss */ - rc = emulate_load_segment(ctxt, VCPU_SREG_SS); - break; case 0xb3: btr: /* btr */ - emulate_2op_SrcV_nobyte("btr", ctxt->src, ctxt->dst, ctxt->eflags); - break; - case 0xb4: /* lfs */ - rc = emulate_load_segment(ctxt, VCPU_SREG_FS); - break; - case 0xb5: /* lgs */ - rc = emulate_load_segment(ctxt, VCPU_SREG_GS); + emulate_2op_SrcV_nobyte(ctxt, "btr"); break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; @@ -4185,7 +4152,7 @@ twobyte_insn: break; case 0xbb: btc: /* btc */ - emulate_2op_SrcV_nobyte("btc", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "btc"); break; case 0xbc: { /* bsf */ u8 zf; @@ -4217,7 +4184,7 @@ twobyte_insn: (s16) ctxt->src.val; break; case 0xc0 ... 0xc1: /* xadd */ - emulate_2op_SrcV("add", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "add"); /* Write back the register source. */ ctxt->src.val = ctxt->dst.orig_val; write_register_operand(&ctxt->src); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index efad72385058..76e3f1cd0369 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -713,14 +713,16 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); kvm_iodevice_init(&pit->dev, &pit_dev_ops); - ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &pit->dev); + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS, + KVM_PIT_MEM_LENGTH, &pit->dev); if (ret < 0) goto fail; if (flags & KVM_PIT_SPEAKER_DUMMY) { kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops); ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, - &pit->speaker_dev); + KVM_SPEAKER_BASE_ADDRESS, 4, + &pit->speaker_dev); if (ret < 0) goto fail_unregister; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 19fe855e7953..cac4746d7ffb 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -34,6 +34,9 @@ #include <linux/kvm_host.h> #include "trace.h" +#define pr_pic_unimpl(fmt, ...) \ + pr_err_ratelimited("kvm: pic: " fmt, ## __VA_ARGS__) + static void pic_irq_request(struct kvm *kvm, int level); static void pic_lock(struct kvm_pic *s) @@ -306,10 +309,10 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) } s->init_state = 1; if (val & 0x02) - printk(KERN_ERR "single mode not supported"); + pr_pic_unimpl("single mode not supported"); if (val & 0x08) - printk(KERN_ERR - "level sensitive irq not supported"); + pr_pic_unimpl( + "level sensitive irq not supported"); } else if (val & 0x08) { if (val & 0x04) s->poll = 1; @@ -459,22 +462,15 @@ static int picdev_in_range(gpa_t addr) } } -static inline struct kvm_pic *to_pic(struct kvm_io_device *dev) -{ - return container_of(dev, struct kvm_pic, dev); -} - -static int picdev_write(struct kvm_io_device *this, +static int picdev_write(struct kvm_pic *s, gpa_t addr, int len, const void *val) { - struct kvm_pic *s = to_pic(this); unsigned char data = *(unsigned char *)val; if (!picdev_in_range(addr)) return -EOPNOTSUPP; if (len != 1) { - if (printk_ratelimit()) - printk(KERN_ERR "PIC: non byte write\n"); + pr_pic_unimpl("non byte write\n"); return 0; } pic_lock(s); @@ -494,17 +490,15 @@ static int picdev_write(struct kvm_io_device *this, return 0; } -static int picdev_read(struct kvm_io_device *this, +static int picdev_read(struct kvm_pic *s, gpa_t addr, int len, void *val) { - struct kvm_pic *s = to_pic(this); unsigned char data = 0; if (!picdev_in_range(addr)) return -EOPNOTSUPP; if (len != 1) { - if (printk_ratelimit()) - printk(KERN_ERR "PIC: non byte read\n"); + pr_pic_unimpl("non byte read\n"); return 0; } pic_lock(s); @@ -525,6 +519,48 @@ static int picdev_read(struct kvm_io_device *this, return 0; } +static int picdev_master_write(struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + return picdev_write(container_of(dev, struct kvm_pic, dev_master), + addr, len, val); +} + +static int picdev_master_read(struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + return picdev_read(container_of(dev, struct kvm_pic, dev_master), + addr, len, val); +} + +static int picdev_slave_write(struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + return picdev_write(container_of(dev, struct kvm_pic, dev_slave), + addr, len, val); +} + +static int picdev_slave_read(struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + return picdev_read(container_of(dev, struct kvm_pic, dev_slave), + addr, len, val); +} + +static int picdev_eclr_write(struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + return picdev_write(container_of(dev, struct kvm_pic, dev_eclr), + addr, len, val); +} + +static int picdev_eclr_read(struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + return picdev_read(container_of(dev, struct kvm_pic, dev_eclr), + addr, len, val); +} + /* * callback when PIC0 irq status changed */ @@ -537,9 +573,19 @@ static void pic_irq_request(struct kvm *kvm, int level) s->output = level; } -static const struct kvm_io_device_ops picdev_ops = { - .read = picdev_read, - .write = picdev_write, +static const struct kvm_io_device_ops picdev_master_ops = { + .read = picdev_master_read, + .write = picdev_master_write, +}; + +static const struct kvm_io_device_ops picdev_slave_ops = { + .read = picdev_slave_read, + .write = picdev_slave_write, +}; + +static const struct kvm_io_device_ops picdev_eclr_ops = { + .read = picdev_eclr_read, + .write = picdev_eclr_write, }; struct kvm_pic *kvm_create_pic(struct kvm *kvm) @@ -560,16 +606,39 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) /* * Initialize PIO device */ - kvm_iodevice_init(&s->dev, &picdev_ops); + kvm_iodevice_init(&s->dev_master, &picdev_master_ops); + kvm_iodevice_init(&s->dev_slave, &picdev_slave_ops); + kvm_iodevice_init(&s->dev_eclr, &picdev_eclr_ops); mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &s->dev); + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x20, 2, + &s->dev_master); + if (ret < 0) + goto fail_unlock; + + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0xa0, 2, &s->dev_slave); + if (ret < 0) + goto fail_unreg_2; + + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x4d0, 2, &s->dev_eclr); + if (ret < 0) + goto fail_unreg_1; + mutex_unlock(&kvm->slots_lock); - if (ret < 0) { - kfree(s); - return NULL; - } return s; + +fail_unreg_1: + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_slave); + +fail_unreg_2: + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_master); + +fail_unlock: + mutex_unlock(&kvm->slots_lock); + + kfree(s); + + return NULL; } void kvm_destroy_pic(struct kvm *kvm) @@ -577,7 +646,9 @@ void kvm_destroy_pic(struct kvm *kvm) struct kvm_pic *vpic = kvm->arch.vpic; if (vpic) { - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr); kvm->arch.vpic = NULL; kfree(vpic); } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 53e2d084bffb..2086f2bfba33 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -66,7 +66,9 @@ struct kvm_pic { struct kvm *kvm; struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */ int output; /* intr from master PIC */ - struct kvm_io_device dev; + struct kvm_io_device dev_master; + struct kvm_io_device dev_slave; + struct kvm_io_device dev_eclr; void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[16]; }; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 3377d53fcd36..544076c4f44b 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -45,13 +45,6 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) return vcpu->arch.walk_mmu->pdptrs[index]; } -static inline u64 kvm_pdptr_read_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, int index) -{ - load_pdptrs(vcpu, mmu, mmu->get_cr3(vcpu)); - - return mmu->pdptrs[index]; -} - static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h index 64bc6ea78d90..497dbaa366d4 100644 --- a/arch/x86/kvm/kvm_timer.h +++ b/arch/x86/kvm/kvm_timer.h @@ -2,6 +2,8 @@ struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ + u32 timer_mode_mask; + u64 tscdeadline; atomic_t pending; /* accumulated triggered timers */ bool reinject; struct kvm_timer_ops *t_ops; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 57dcbd4308fa..54abb40199d6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -68,6 +68,9 @@ #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) +static unsigned int min_timer_period_us = 500; +module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); + static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off) { return *((u32 *) (apic->regs + reg_off)); @@ -135,9 +138,23 @@ static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; } +static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) +{ + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT); +} + static inline int apic_lvtt_period(struct kvm_lapic *apic) { - return apic_get_reg(apic, APIC_LVTT) & APIC_LVT_TIMER_PERIODIC; + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC); +} + +static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic) +{ + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == + APIC_LVT_TIMER_TSCDEADLINE); } static inline int apic_lvt_nmi_mode(u32 lvt_val) @@ -166,7 +183,7 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) } static unsigned int apic_lvt_mask[APIC_LVT_NUM] = { - LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */ + LVT_MASK , /* part LVTT mask, timer mode mask added at runtime */ LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */ LVT_MASK | APIC_MODE_MASK, /* LVTPC */ LINT_MASK, LINT_MASK, /* LVT0-1 */ @@ -316,8 +333,8 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) result = 1; break; default: - printk(KERN_WARNING "Bad DFR vcpu %d: %08x\n", - apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR)); + apic_debug("Bad DFR vcpu %d: %08x\n", + apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR)); break; } @@ -354,8 +371,8 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, result = (target != source); break; default: - printk(KERN_WARNING "Bad dest shorthand value %x\n", - short_hand); + apic_debug("kvm: apic: Bad dest shorthand value %x\n", + short_hand); break; } @@ -401,11 +418,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_REMRD: - printk(KERN_DEBUG "Ignoring delivery mode 3\n"); + apic_debug("Ignoring delivery mode 3\n"); break; case APIC_DM_SMI: - printk(KERN_DEBUG "Ignoring guest SMI\n"); + apic_debug("Ignoring guest SMI\n"); break; case APIC_DM_NMI: @@ -565,11 +582,13 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) val = kvm_apic_id(apic) << 24; break; case APIC_ARBPRI: - printk(KERN_WARNING "Access APIC ARBPRI register " - "which is for P6\n"); + apic_debug("Access APIC ARBPRI register which is for P6\n"); break; case APIC_TMCCT: /* Timer CCR */ + if (apic_lvtt_tscdeadline(apic)) + return 0; + val = apic_get_tmcct(apic); break; @@ -664,29 +683,40 @@ static void update_divide_count(struct kvm_lapic *apic) static void start_apic_timer(struct kvm_lapic *apic) { - ktime_t now = apic->lapic_timer.timer.base->get_time(); - - apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) * - APIC_BUS_CYCLE_NS * apic->divide_count; + ktime_t now; atomic_set(&apic->lapic_timer.pending, 0); - if (!apic->lapic_timer.period) - return; - /* - * Do not allow the guest to program periodic timers with small - * interval, since the hrtimers are not throttled by the host - * scheduler. - */ - if (apic_lvtt_period(apic)) { - if (apic->lapic_timer.period < NSEC_PER_MSEC/2) - apic->lapic_timer.period = NSEC_PER_MSEC/2; - } + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { + /* lapic timer in oneshot or peroidic mode */ + now = apic->lapic_timer.timer.base->get_time(); + apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) + * APIC_BUS_CYCLE_NS * apic->divide_count; + + if (!apic->lapic_timer.period) + return; + /* + * Do not allow the guest to program periodic timers with small + * interval, since the hrtimers are not throttled by the host + * scheduler. + */ + if (apic_lvtt_period(apic)) { + s64 min_period = min_timer_period_us * 1000LL; + + if (apic->lapic_timer.period < min_period) { + pr_info_ratelimited( + "kvm: vcpu %i: requested %lld ns " + "lapic timer period limited to %lld ns\n", + apic->vcpu->vcpu_id, + apic->lapic_timer.period, min_period); + apic->lapic_timer.period = min_period; + } + } - hrtimer_start(&apic->lapic_timer.timer, - ktime_add_ns(now, apic->lapic_timer.period), - HRTIMER_MODE_ABS); + hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, apic->lapic_timer.period), + HRTIMER_MODE_ABS); - apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" + apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " "timer initial count 0x%x, period %lldns, " "expire @ 0x%016" PRIx64 ".\n", __func__, @@ -695,6 +725,30 @@ static void start_apic_timer(struct kvm_lapic *apic) apic->lapic_timer.period, ktime_to_ns(ktime_add_ns(now, apic->lapic_timer.period))); + } else if (apic_lvtt_tscdeadline(apic)) { + /* lapic timer in tsc deadline mode */ + u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + u64 ns = 0; + struct kvm_vcpu *vcpu = apic->vcpu; + unsigned long this_tsc_khz = vcpu_tsc_khz(vcpu); + unsigned long flags; + + if (unlikely(!tscdeadline || !this_tsc_khz)) + return; + + local_irq_save(flags); + + now = apic->lapic_timer.timer.base->get_time(); + guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); + if (likely(tscdeadline > guest_tsc)) { + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + } + hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, ns), HRTIMER_MODE_ABS); + + local_irq_restore(flags); + } } static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) @@ -782,7 +836,6 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVT0: apic_manage_nmi_watchdog(apic, val); - case APIC_LVTT: case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: @@ -796,7 +849,22 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; + case APIC_LVTT: + if ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) != + (val & apic->lapic_timer.timer_mode_mask)) + hrtimer_cancel(&apic->lapic_timer.timer); + + if (!apic_sw_enabled(apic)) + val |= APIC_LVT_MASKED; + val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); + apic_set_reg(apic, APIC_LVTT, val); + break; + case APIC_TMICT: + if (apic_lvtt_tscdeadline(apic)) + break; + hrtimer_cancel(&apic->lapic_timer.timer); apic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); @@ -804,14 +872,14 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_TDCR: if (val & 4) - printk(KERN_ERR "KVM_WRITE:TDCR %x\n", val); + apic_debug("KVM_WRITE:TDCR %x\n", val); apic_set_reg(apic, APIC_TDCR, val); update_divide_count(apic); break; case APIC_ESR: if (apic_x2apic_mode(apic) && val != 0) { - printk(KERN_ERR "KVM_WRITE:ESR not zero %x\n", val); + apic_debug("KVM_WRITE:ESR not zero %x\n", val); ret = 1; } break; @@ -864,6 +932,15 @@ static int apic_mmio_write(struct kvm_io_device *this, return 0; } +void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (apic) + apic_reg_write(vcpu->arch.apic, APIC_EOI, 0); +} +EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); + void kvm_free_lapic(struct kvm_vcpu *vcpu) { if (!vcpu->arch.apic) @@ -883,6 +960,32 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) *---------------------------------------------------------------------- */ +u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + if (!apic) + return 0; + + if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) + return 0; + + return apic->lapic_timer.tscdeadline; +} + +void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + if (!apic) + return; + + if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) + return; + + hrtimer_cancel(&apic->lapic_timer.timer); + apic->lapic_timer.tscdeadline = data; + start_apic_timer(apic); +} + void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) { struct kvm_lapic *apic = vcpu->arch.apic; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 52c9e6b9e725..138e8cc6fea6 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -26,6 +26,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); +void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); @@ -41,6 +42,9 @@ int kvm_lapic_enabled(struct kvm_vcpu *vcpu); bool kvm_apic_present(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); +u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); +void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); + void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8e8da7960dbe..f1b36cf3e3d0 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2770,7 +2770,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { - pdptr = kvm_pdptr_read_mmu(vcpu, &vcpu->arch.mmu, i); + pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i); if (!is_present_gpte(pdptr)) { vcpu->arch.mmu.pae_root[i] = 0; continue; @@ -3318,6 +3318,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->direct_map = true; context->set_cr3 = kvm_x86_ops->set_tdp_cr3; context->get_cr3 = get_cr3; + context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; context->nx = is_nx(vcpu); @@ -3376,6 +3377,7 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu->set_cr3 = kvm_x86_ops->set_cr3; vcpu->arch.walk_mmu->get_cr3 = get_cr3; + vcpu->arch.walk_mmu->get_pdptr = kvm_pdptr_read; vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; return r; @@ -3386,6 +3388,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; g_context->get_cr3 = get_cr3; + g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; /* diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 2460a265be23..746ec259d024 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -121,16 +121,16 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) { + static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); unsigned long *rmapp; struct kvm_mmu_page *rev_sp; gfn_t gfn; - rev_sp = page_header(__pa(sptep)); gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt); if (!gfn_to_memslot(kvm, gfn)) { - if (!printk_ratelimit()) + if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no memslot for gfn %llx\n", gfn); audit_printk(kvm, "index %ld of sp (gfn=%llx)\n", @@ -141,7 +141,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); if (!*rmapp) { - if (!printk_ratelimit()) + if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no rmap for writable spte %llx\n", *sptep); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 507e2b844cfa..92994100638b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -147,7 +147,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gfn_t table_gfn; unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; - bool eperm; + bool eperm, last_gpte; int offset; const int write_fault = access & PFERR_WRITE_MASK; const int user_fault = access & PFERR_USER_MASK; @@ -163,7 +163,7 @@ retry_walk: #if PTTYPE == 64 if (walker->level == PT32E_ROOT_LEVEL) { - pte = kvm_pdptr_read_mmu(vcpu, mmu, (addr >> 30) & 3); + pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); if (!is_present_gpte(pte)) goto error; @@ -221,6 +221,17 @@ retry_walk: eperm = true; #endif + last_gpte = FNAME(is_last_gpte)(walker, vcpu, mmu, pte); + if (last_gpte) { + pte_access = pt_access & + FNAME(gpte_access)(vcpu, pte, true); + /* check if the kernel is fetching from user page */ + if (unlikely(pte_access & PT_USER_MASK) && + kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) + if (fetch_fault && !user_fault) + eperm = true; + } + if (!eperm && unlikely(!(pte & PT_ACCESSED_MASK))) { int ret; trace_kvm_mmu_set_accessed_bit(table_gfn, index, @@ -238,18 +249,12 @@ retry_walk: walker->ptes[walker->level - 1] = pte; - if (FNAME(is_last_gpte)(walker, vcpu, mmu, pte)) { + if (last_gpte) { int lvl = walker->level; gpa_t real_gpa; gfn_t gfn; u32 ac; - /* check if the kernel is fetching from user page */ - if (unlikely(pte_access & PT_USER_MASK) && - kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) - if (fetch_fault && !user_fault) - eperm = true; - gfn = gpte_to_gfn_lvl(pte, lvl); gfn += (addr & PT_LVL_OFFSET_MASK(lvl)) >> PAGE_SHIFT; @@ -295,7 +300,6 @@ retry_walk: walker->ptes[walker->level - 1] = pte; } - pte_access = pt_access & FNAME(gpte_access)(vcpu, pte, true); walker->pt_access = pt_access; walker->pte_access = pte_access; pgprintk("%s: pte %llx pte_access %x pt_access %x\n", diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 475d1c948501..e32243eac2f4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1084,7 +1084,6 @@ static void init_vmcb(struct vcpu_svm *svm) if (npt_enabled) { /* Setup VMCB for Nested Paging */ control->nested_ctl = 1; - clr_intercept(svm, INTERCEPT_TASK_SWITCH); clr_intercept(svm, INTERCEPT_INVLPG); clr_exception_intercept(svm, PF_VECTOR); clr_cr_intercept(svm, INTERCEPT_CR3_READ); @@ -1844,6 +1843,20 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) return svm->nested.nested_cr3; } +static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr3 = svm->nested.nested_cr3; + u64 pdpte; + int ret; + + ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); + if (ret) + return 0; + return pdpte; +} + static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) { @@ -1875,6 +1888,7 @@ static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3; vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3; + vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; @@ -2182,7 +2196,8 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) vmcb->control.exit_info_1, vmcb->control.exit_info_2, vmcb->control.exit_int_info, - vmcb->control.exit_int_info_err); + vmcb->control.exit_int_info_err, + KVM_ISA_SVM); nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page); if (!nested_vmcb) @@ -2894,15 +2909,20 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } +u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); + return vmcb->control.tsc_offset + + svm_scale_tsc(vcpu, native_read_tsc()); +} + static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) { struct vcpu_svm *svm = to_svm(vcpu); switch (ecx) { case MSR_IA32_TSC: { - struct vmcb *vmcb = get_host_vmcb(svm); - - *data = vmcb->control.tsc_offset + + *data = svm->vmcb->control.tsc_offset + svm_scale_tsc(vcpu, native_read_tsc()); break; @@ -3314,8 +3334,6 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); - if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3335,7 +3353,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) svm->vmcb->control.exit_info_1, svm->vmcb->control.exit_info_2, svm->vmcb->control.exit_int_info, - svm->vmcb->control.exit_int_info_err); + svm->vmcb->control.exit_int_info_err, + KVM_ISA_SVM); vmexit = nested_svm_exit_special(svm); @@ -3768,6 +3787,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; + trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); @@ -3897,60 +3918,6 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) } } -static const struct trace_print_flags svm_exit_reasons_str[] = { - { SVM_EXIT_READ_CR0, "read_cr0" }, - { SVM_EXIT_READ_CR3, "read_cr3" }, - { SVM_EXIT_READ_CR4, "read_cr4" }, - { SVM_EXIT_READ_CR8, "read_cr8" }, - { SVM_EXIT_WRITE_CR0, "write_cr0" }, - { SVM_EXIT_WRITE_CR3, "write_cr3" }, - { SVM_EXIT_WRITE_CR4, "write_cr4" }, - { SVM_EXIT_WRITE_CR8, "write_cr8" }, - { SVM_EXIT_READ_DR0, "read_dr0" }, - { SVM_EXIT_READ_DR1, "read_dr1" }, - { SVM_EXIT_READ_DR2, "read_dr2" }, - { SVM_EXIT_READ_DR3, "read_dr3" }, - { SVM_EXIT_WRITE_DR0, "write_dr0" }, - { SVM_EXIT_WRITE_DR1, "write_dr1" }, - { SVM_EXIT_WRITE_DR2, "write_dr2" }, - { SVM_EXIT_WRITE_DR3, "write_dr3" }, - { SVM_EXIT_WRITE_DR5, "write_dr5" }, - { SVM_EXIT_WRITE_DR7, "write_dr7" }, - { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, - { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, - { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, - { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, - { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, - { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, - { SVM_EXIT_INTR, "interrupt" }, - { SVM_EXIT_NMI, "nmi" }, - { SVM_EXIT_SMI, "smi" }, - { SVM_EXIT_INIT, "init" }, - { SVM_EXIT_VINTR, "vintr" }, - { SVM_EXIT_CPUID, "cpuid" }, - { SVM_EXIT_INVD, "invd" }, - { SVM_EXIT_HLT, "hlt" }, - { SVM_EXIT_INVLPG, "invlpg" }, - { SVM_EXIT_INVLPGA, "invlpga" }, - { SVM_EXIT_IOIO, "io" }, - { SVM_EXIT_MSR, "msr" }, - { SVM_EXIT_TASK_SWITCH, "task_switch" }, - { SVM_EXIT_SHUTDOWN, "shutdown" }, - { SVM_EXIT_VMRUN, "vmrun" }, - { SVM_EXIT_VMMCALL, "hypercall" }, - { SVM_EXIT_VMLOAD, "vmload" }, - { SVM_EXIT_VMSAVE, "vmsave" }, - { SVM_EXIT_STGI, "stgi" }, - { SVM_EXIT_CLGI, "clgi" }, - { SVM_EXIT_SKINIT, "skinit" }, - { SVM_EXIT_WBINVD, "wbinvd" }, - { SVM_EXIT_MONITOR, "monitor" }, - { SVM_EXIT_MWAIT, "mwait" }, - { SVM_EXIT_XSETBV, "xsetbv" }, - { SVM_EXIT_NPF, "npf" }, - { -1, NULL } -}; - static int svm_get_lpage_level(void) { return PT_PDPE_LEVEL; @@ -4223,7 +4190,6 @@ static struct kvm_x86_ops svm_x86_ops = { .get_mt_mask = svm_get_mt_mask, .get_exit_info = svm_get_exit_info, - .exit_reasons_str = svm_exit_reasons_str, .get_lpage_level = svm_get_lpage_level, @@ -4239,6 +4205,7 @@ static struct kvm_x86_ops svm_x86_ops = { .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset = svm_adjust_tsc_offset, .compute_tsc_offset = svm_compute_tsc_offset, + .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 3ff898c104f7..911d2641f14c 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -2,6 +2,8 @@ #define _TRACE_KVM_H #include <linux/tracepoint.h> +#include <asm/vmx.h> +#include <asm/svm.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm @@ -181,6 +183,95 @@ TRACE_EVENT(kvm_apic, #define KVM_ISA_VMX 1 #define KVM_ISA_SVM 2 +#define VMX_EXIT_REASONS \ + { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ + { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ + { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ + { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ + { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ + { EXIT_REASON_CPUID, "CPUID" }, \ + { EXIT_REASON_HLT, "HLT" }, \ + { EXIT_REASON_INVLPG, "INVLPG" }, \ + { EXIT_REASON_RDPMC, "RDPMC" }, \ + { EXIT_REASON_RDTSC, "RDTSC" }, \ + { EXIT_REASON_VMCALL, "VMCALL" }, \ + { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ + { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ + { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ + { EXIT_REASON_VMPTRST, "VMPTRST" }, \ + { EXIT_REASON_VMREAD, "VMREAD" }, \ + { EXIT_REASON_VMRESUME, "VMRESUME" }, \ + { EXIT_REASON_VMWRITE, "VMWRITE" }, \ + { EXIT_REASON_VMOFF, "VMOFF" }, \ + { EXIT_REASON_VMON, "VMON" }, \ + { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ + { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ + { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ + { EXIT_REASON_MSR_READ, "MSR_READ" }, \ + { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ + { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ + { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ + { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ + { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ + { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ + { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ + { EXIT_REASON_WBINVD, "WBINVD" } + +#define SVM_EXIT_REASONS \ + { SVM_EXIT_READ_CR0, "read_cr0" }, \ + { SVM_EXIT_READ_CR3, "read_cr3" }, \ + { SVM_EXIT_READ_CR4, "read_cr4" }, \ + { SVM_EXIT_READ_CR8, "read_cr8" }, \ + { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ + { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ + { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ + { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ + { SVM_EXIT_READ_DR0, "read_dr0" }, \ + { SVM_EXIT_READ_DR1, "read_dr1" }, \ + { SVM_EXIT_READ_DR2, "read_dr2" }, \ + { SVM_EXIT_READ_DR3, "read_dr3" }, \ + { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ + { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ + { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ + { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ + { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ + { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ + { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ + { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ + { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ + { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ + { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ + { SVM_EXIT_INTR, "interrupt" }, \ + { SVM_EXIT_NMI, "nmi" }, \ + { SVM_EXIT_SMI, "smi" }, \ + { SVM_EXIT_INIT, "init" }, \ + { SVM_EXIT_VINTR, "vintr" }, \ + { SVM_EXIT_CPUID, "cpuid" }, \ + { SVM_EXIT_INVD, "invd" }, \ + { SVM_EXIT_HLT, "hlt" }, \ + { SVM_EXIT_INVLPG, "invlpg" }, \ + { SVM_EXIT_INVLPGA, "invlpga" }, \ + { SVM_EXIT_IOIO, "io" }, \ + { SVM_EXIT_MSR, "msr" }, \ + { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ + { SVM_EXIT_SHUTDOWN, "shutdown" }, \ + { SVM_EXIT_VMRUN, "vmrun" }, \ + { SVM_EXIT_VMMCALL, "hypercall" }, \ + { SVM_EXIT_VMLOAD, "vmload" }, \ + { SVM_EXIT_VMSAVE, "vmsave" }, \ + { SVM_EXIT_STGI, "stgi" }, \ + { SVM_EXIT_CLGI, "clgi" }, \ + { SVM_EXIT_SKINIT, "skinit" }, \ + { SVM_EXIT_WBINVD, "wbinvd" }, \ + { SVM_EXIT_MONITOR, "monitor" }, \ + { SVM_EXIT_MWAIT, "mwait" }, \ + { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_NPF, "npf" } + /* * Tracepoint for kvm guest exit: */ @@ -205,8 +296,9 @@ TRACE_EVENT(kvm_exit, ), TP_printk("reason %s rip 0x%lx info %llx %llx", - ftrace_print_symbols_seq(p, __entry->exit_reason, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS), __entry->guest_rip, __entry->info1, __entry->info2) ); @@ -486,9 +578,9 @@ TRACE_EVENT(kvm_nested_intercepts, TRACE_EVENT(kvm_nested_vmexit, TP_PROTO(__u64 rip, __u32 exit_code, __u64 exit_info1, __u64 exit_info2, - __u32 exit_int_info, __u32 exit_int_info_err), + __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa), TP_ARGS(rip, exit_code, exit_info1, exit_info2, - exit_int_info, exit_int_info_err), + exit_int_info, exit_int_info_err, isa), TP_STRUCT__entry( __field( __u64, rip ) @@ -497,6 +589,7 @@ TRACE_EVENT(kvm_nested_vmexit, __field( __u64, exit_info2 ) __field( __u32, exit_int_info ) __field( __u32, exit_int_info_err ) + __field( __u32, isa ) ), TP_fast_assign( @@ -506,12 +599,14 @@ TRACE_EVENT(kvm_nested_vmexit, __entry->exit_info2 = exit_info2; __entry->exit_int_info = exit_int_info; __entry->exit_int_info_err = exit_int_info_err; + __entry->isa = isa; ), TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", __entry->rip, - ftrace_print_symbols_seq(p, __entry->exit_code, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); @@ -522,9 +617,9 @@ TRACE_EVENT(kvm_nested_vmexit, TRACE_EVENT(kvm_nested_vmexit_inject, TP_PROTO(__u32 exit_code, __u64 exit_info1, __u64 exit_info2, - __u32 exit_int_info, __u32 exit_int_info_err), + __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa), TP_ARGS(exit_code, exit_info1, exit_info2, - exit_int_info, exit_int_info_err), + exit_int_info, exit_int_info_err, isa), TP_STRUCT__entry( __field( __u32, exit_code ) @@ -532,6 +627,7 @@ TRACE_EVENT(kvm_nested_vmexit_inject, __field( __u64, exit_info2 ) __field( __u32, exit_int_info ) __field( __u32, exit_int_info_err ) + __field( __u32, isa ) ), TP_fast_assign( @@ -540,12 +636,14 @@ TRACE_EVENT(kvm_nested_vmexit_inject, __entry->exit_info2 = exit_info2; __entry->exit_int_info = exit_int_info; __entry->exit_int_info_err = exit_int_info_err; + __entry->isa = isa; ), TP_printk("reason: %s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", - ftrace_print_symbols_seq(p, __entry->exit_code, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e65a158dee64..a0d6bd9ad442 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -71,6 +71,9 @@ module_param(vmm_exclusive, bool, S_IRUGO); static int __read_mostly yield_on_hlt = 1; module_param(yield_on_hlt, bool, S_IRUGO); +static int __read_mostly fasteoi = 1; +module_param(fasteoi, 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 @@ -1748,6 +1751,21 @@ static u64 guest_read_tsc(void) } /* + * Like guest_read_tsc, but always returns L1's notion of the timestamp + * counter, even if a nested guest (L2) is currently running. + */ +u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu) +{ + u64 host_tsc, tsc_offset; + + rdtscll(host_tsc); + tsc_offset = is_guest_mode(vcpu) ? + to_vmx(vcpu)->nested.vmcs01_tsc_offset : + vmcs_read64(TSC_OFFSET); + return host_tsc + tsc_offset; +} + +/* * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ * ioctl. In this case the call-back should update internal vmx state to make * the changes effective. @@ -1762,15 +1780,23 @@ 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)) + 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. + * We're here if L1 chose not to trap WRMSR to TSC. According + * to the spec, this should set L1's TSC; The offset that L1 + * set for L2 remains unchanged, and still needs to be added + * to the newly set TSC to get L2's TSC. */ - get_vmcs12(vcpu)->tsc_offset = offset - - to_vmx(vcpu)->nested.vmcs01_tsc_offset; + struct vmcs12 *vmcs12; + to_vmx(vcpu)->nested.vmcs01_tsc_offset = offset; + /* recalculate vmcs02.TSC_OFFSET: */ + vmcs12 = get_vmcs12(vcpu); + vmcs_write64(TSC_OFFSET, offset + + (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ? + vmcs12->tsc_offset : 0)); + } else { + vmcs_write64(TSC_OFFSET, offset); + } } static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) @@ -2736,8 +2762,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu) guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { - printk(KERN_DEBUG "%s: tss fixup for long mode. \n", - __func__); + pr_debug_ratelimited("%s: tss fixup for long mode. \n", + __func__); vmcs_write32(GUEST_TR_AR_BYTES, (guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS); @@ -4115,8 +4141,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (is_page_fault(intr_info)) { /* EPT won't cause page fault directly */ - if (enable_ept) - BUG(); + BUG_ON(enable_ept); cr2 = vmcs_readl(EXIT_QUALIFICATION); trace_kvm_page_fault(cr2, error_code); @@ -4518,6 +4543,24 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) static int handle_apic_access(struct kvm_vcpu *vcpu) { + if (likely(fasteoi)) { + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + int access_type, offset; + + access_type = exit_qualification & APIC_ACCESS_TYPE; + offset = exit_qualification & APIC_ACCESS_OFFSET; + /* + * Sane guest uses MOV to write EOI, with written value + * not cared. So make a short-circuit here by avoiding + * heavy instruction emulation. + */ + if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) && + (offset == APIC_EOI)) { + kvm_lapic_set_eoi(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + } return emulate_instruction(vcpu, 0) == EMULATE_DONE; } @@ -5591,8 +5634,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return 0; if (unlikely(vmx->fail)) { - printk(KERN_INFO "%s failed vm entry %x\n", - __func__, vmcs_read32(VM_INSTRUCTION_ERROR)); + pr_info_ratelimited("%s failed vm entry %x\n", __func__, + vmcs_read32(VM_INSTRUCTION_ERROR)); return 1; } @@ -5696,8 +5739,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; - trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); - /* If guest state is invalid, start emulating */ if (vmx->emulation_required && emulate_invalid_guest_state) return handle_invalid_guest_state(vcpu); @@ -6101,6 +6142,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); + trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); @@ -6241,49 +6283,6 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return ret; } -#define _ER(x) { EXIT_REASON_##x, #x } - -static const struct trace_print_flags vmx_exit_reasons_str[] = { - _ER(EXCEPTION_NMI), - _ER(EXTERNAL_INTERRUPT), - _ER(TRIPLE_FAULT), - _ER(PENDING_INTERRUPT), - _ER(NMI_WINDOW), - _ER(TASK_SWITCH), - _ER(CPUID), - _ER(HLT), - _ER(INVLPG), - _ER(RDPMC), - _ER(RDTSC), - _ER(VMCALL), - _ER(VMCLEAR), - _ER(VMLAUNCH), - _ER(VMPTRLD), - _ER(VMPTRST), - _ER(VMREAD), - _ER(VMRESUME), - _ER(VMWRITE), - _ER(VMOFF), - _ER(VMON), - _ER(CR_ACCESS), - _ER(DR_ACCESS), - _ER(IO_INSTRUCTION), - _ER(MSR_READ), - _ER(MSR_WRITE), - _ER(MWAIT_INSTRUCTION), - _ER(MONITOR_INSTRUCTION), - _ER(PAUSE_INSTRUCTION), - _ER(MCE_DURING_VMENTRY), - _ER(TPR_BELOW_THRESHOLD), - _ER(APIC_ACCESS), - _ER(EPT_VIOLATION), - _ER(EPT_MISCONFIG), - _ER(WBINVD), - { -1, NULL } -}; - -#undef _ER - static int vmx_get_lpage_level(void) { if (enable_ept && !cpu_has_vmx_ept_1g_page()) @@ -6514,8 +6513,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) set_cr4_guest_host_mask(vmx); - vmcs_write64(TSC_OFFSET, - vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vmcs_write64(TSC_OFFSET, + vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); + else + vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); if (enable_vpid) { /* @@ -6610,9 +6612,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (vmcs12->vm_entry_msr_load_count > 0 || vmcs12->vm_exit_msr_load_count > 0 || vmcs12->vm_exit_msr_store_count > 0) { - if (printk_ratelimit()) - printk(KERN_WARNING - "%s: VMCS MSR_{LOAD,STORE} unsupported\n", __func__); + pr_warn_ratelimited("%s: VMCS MSR_{LOAD,STORE} unsupported\n", + __func__); nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -6922,7 +6923,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) load_vmcs12_host_state(vcpu, vmcs12); - /* Update TSC_OFFSET if vmx_adjust_tsc_offset() was used while L2 ran */ + /* Update TSC_OFFSET if TSC was changed while L2 ran */ vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); /* This is needed for same reason as it was needed in prepare_vmcs02 */ @@ -7039,7 +7040,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .get_mt_mask = vmx_get_mt_mask, .get_exit_info = vmx_get_exit_info, - .exit_reasons_str = vmx_exit_reasons_str, .get_lpage_level = vmx_get_lpage_level, @@ -7055,6 +7055,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .write_tsc_offset = vmx_write_tsc_offset, .adjust_tsc_offset = vmx_adjust_tsc_offset, .compute_tsc_offset = vmx_compute_tsc_offset, + .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 84a28ea45fa4..c38efd7b792e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -44,6 +44,7 @@ #include <linux/perf_event.h> #include <linux/uaccess.h> #include <linux/hash.h> +#include <linux/pci.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -83,6 +84,7 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static void update_cr8_intercept(struct kvm_vcpu *vcpu); static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -359,8 +361,8 @@ void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) void kvm_inject_nmi(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, vcpu); - vcpu->arch.nmi_pending = 1; + atomic_inc(&vcpu->arch.nmi_queued); + kvm_make_request(KVM_REQ_NMI, vcpu); } EXPORT_SYMBOL_GPL(kvm_inject_nmi); @@ -599,6 +601,8 @@ static bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) static void update_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; + struct kvm_lapic *apic = vcpu->arch.apic; + u32 timer_mode_mask; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (!best) @@ -610,6 +614,16 @@ static void update_cpuid(struct kvm_vcpu *vcpu) if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) best->ecx |= bit(X86_FEATURE_OSXSAVE); } + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + best->function == 0x1) { + best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER); + timer_mode_mask = 3 << 17; + } else + timer_mode_mask = 1 << 17; + + if (apic) + apic->lapic_timer.timer_mode_mask = timer_mode_mask; } int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -825,6 +839,7 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; static u32 emulated_msrs[] = { + MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -1000,7 +1015,7 @@ static inline int kvm_tsc_changes_freq(void) return ret; } -static u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) +u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) { if (vcpu->arch.virtual_tsc_khz) return vcpu->arch.virtual_tsc_khz; @@ -1098,7 +1113,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp); + tsc_timestamp = kvm_x86_ops->read_l1_tsc(v); kernel_ns = get_kernel_ns(); this_tsc_khz = vcpu_tsc_khz(v); if (unlikely(this_tsc_khz == 0)) { @@ -1564,6 +1579,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_write(vcpu, msr, data); + case MSR_IA32_TSCDEADLINE: + kvm_set_lapic_tscdeadline_msr(vcpu, data); + break; case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; @@ -1825,6 +1843,9 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); case HV_X64_MSR_TPR: return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = vcpu->arch.hv_vapic; + break; default: pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; @@ -1839,7 +1860,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) switch (msr) { case MSR_IA32_PLATFORM_ID: - case MSR_IA32_UCODE_REV: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_DEBUGCTLMSR: case MSR_IA32_LASTBRANCHFROMIP: @@ -1860,6 +1880,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_FAM10H_MMIO_CONF_BASE: data = 0; break; + case MSR_IA32_UCODE_REV: + data = 0x100000000ULL; + break; case MSR_MTRRcap: data = 0x500 | KVM_NR_VAR_MTRR; break; @@ -1888,6 +1911,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_read(vcpu, msr, pdata); break; + case MSR_IA32_TSCDEADLINE: + data = kvm_get_lapic_tscdeadline_msr(vcpu); + break; case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; @@ -2086,6 +2112,9 @@ int kvm_dev_ioctl_check_extension(long ext) r = !kvm_x86_ops->cpu_has_accelerated_tpr(); break; case KVM_CAP_NR_VCPUS: + r = KVM_SOFT_MAX_VCPUS; + break; + case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; case KVM_CAP_NR_MEMSLOTS: @@ -2095,7 +2124,7 @@ int kvm_dev_ioctl_check_extension(long ext) r = 0; break; case KVM_CAP_IOMMU: - r = iommu_found(); + r = iommu_present(&pci_bus_type); break; case KVM_CAP_MCE: r = KVM_MAX_MCE_BANKS; @@ -2210,7 +2239,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) s64 tsc_delta; u64 tsc; - kvm_get_msr(vcpu, MSR_IA32_TSC, &tsc); + tsc = kvm_x86_ops->read_l1_tsc(vcpu); tsc_delta = !vcpu->arch.last_guest_tsc ? 0 : tsc - vcpu->arch.last_guest_tsc; @@ -2234,7 +2263,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); } static int is_efer_nx(void) @@ -2819,6 +2848,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { + process_nmi(vcpu); events->exception.injected = vcpu->arch.exception.pending && !kvm_exception_is_soft(vcpu->arch.exception.nr); @@ -2836,7 +2866,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.pending = vcpu->arch.nmi_pending != 0; events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); events->nmi.pad = 0; @@ -2856,6 +2886,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SHADOW)) return -EINVAL; + process_nmi(vcpu); vcpu->arch.exception.pending = events->exception.injected; vcpu->arch.exception.nr = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; @@ -3556,7 +3587,11 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r) { mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev); + &vpic->dev_master); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_slave); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_eclr); mutex_unlock(&kvm->slots_lock); kfree(vpic); goto create_irqchip_unlock; @@ -4045,84 +4080,105 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, return 0; } -static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, - unsigned long addr, - void *val, - unsigned int bytes, - struct x86_exception *exception) +int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - gpa_t gpa; - int handled, ret; + int ret; + ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); + if (ret < 0) + return 0; + kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1); + return 1; +} + +struct read_write_emulator_ops { + int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val, + int bytes); + int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + int bytes, void *val); + int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + bool write; +}; + +static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) +{ if (vcpu->mmio_read_completed) { memcpy(val, vcpu->mmio_data, bytes); trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, vcpu->mmio_phys_addr, *(u64 *)val); vcpu->mmio_read_completed = 0; - return X86EMUL_CONTINUE; + return 1; } - ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, false); - - if (ret < 0) - return X86EMUL_PROPAGATE_FAULT; - - if (ret) - goto mmio; - - if (kvm_read_guest_virt(ctxt, addr, val, bytes, exception) - == X86EMUL_CONTINUE) - return X86EMUL_CONTINUE; + return 0; +} -mmio: - /* - * Is this MMIO handled locally? - */ - handled = vcpu_mmio_read(vcpu, gpa, bytes, val); +static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); +} - if (handled == bytes) - return X86EMUL_CONTINUE; +static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return emulator_write_phys(vcpu, gpa, val, bytes); +} - gpa += handled; - bytes -= handled; - val += handled; +static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + return vcpu_mmio_write(vcpu, gpa, bytes, val); +} +static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); - - vcpu->mmio_needed = 1; - vcpu->run->exit_reason = KVM_EXIT_MMIO; - vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->run->mmio.len = min(vcpu->mmio_size, 8); - vcpu->run->mmio.is_write = vcpu->mmio_is_write = 0; - vcpu->mmio_index = 0; - return X86EMUL_IO_NEEDED; } -int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, - const void *val, int bytes) +static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) { - int ret; - - ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); - if (ret < 0) - return 0; - kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1); - return 1; + memcpy(vcpu->mmio_data, val, bytes); + memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + return X86EMUL_CONTINUE; } -static int emulator_write_emulated_onepage(unsigned long addr, - const void *val, - unsigned int bytes, - struct x86_exception *exception, - struct kvm_vcpu *vcpu) +static struct read_write_emulator_ops read_emultor = { + .read_write_prepare = read_prepare, + .read_write_emulate = read_emulate, + .read_write_mmio = vcpu_mmio_read, + .read_write_exit_mmio = read_exit_mmio, +}; + +static struct read_write_emulator_ops write_emultor = { + .read_write_emulate = write_emulate, + .read_write_mmio = write_mmio, + .read_write_exit_mmio = write_exit_mmio, + .write = true, +}; + +static int emulator_read_write_onepage(unsigned long addr, void *val, + unsigned int bytes, + struct x86_exception *exception, + struct kvm_vcpu *vcpu, + struct read_write_emulator_ops *ops) { gpa_t gpa; int handled, ret; + bool write = ops->write; - ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, true); + if (ops->read_write_prepare && + ops->read_write_prepare(vcpu, val, bytes)) + return X86EMUL_CONTINUE; + + ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); if (ret < 0) return X86EMUL_PROPAGATE_FAULT; @@ -4131,15 +4187,14 @@ static int emulator_write_emulated_onepage(unsigned long addr, if (ret) goto mmio; - if (emulator_write_phys(vcpu, gpa, val, bytes)) + if (ops->read_write_emulate(vcpu, gpa, val, bytes)) return X86EMUL_CONTINUE; mmio: - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); /* * Is this MMIO handled locally? */ - handled = vcpu_mmio_write(vcpu, gpa, bytes, val); + handled = ops->read_write_mmio(vcpu, gpa, bytes, val); if (handled == bytes) return X86EMUL_CONTINUE; @@ -4148,23 +4203,20 @@ mmio: val += handled; vcpu->mmio_needed = 1; - memcpy(vcpu->mmio_data, val, bytes); vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; vcpu->mmio_size = bytes; vcpu->run->mmio.len = min(vcpu->mmio_size, 8); - vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1; - memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + vcpu->run->mmio.is_write = vcpu->mmio_is_write = write; vcpu->mmio_index = 0; - return X86EMUL_CONTINUE; + return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); } -int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, - unsigned long addr, - const void *val, - unsigned int bytes, - struct x86_exception *exception) +int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, + void *val, unsigned int bytes, + struct x86_exception *exception, + struct read_write_emulator_ops *ops) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); @@ -4173,16 +4225,38 @@ int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, int rc, now; now = -addr & ~PAGE_MASK; - rc = emulator_write_emulated_onepage(addr, val, now, exception, - vcpu); + rc = emulator_read_write_onepage(addr, val, now, exception, + vcpu, ops); + if (rc != X86EMUL_CONTINUE) return rc; addr += now; val += now; bytes -= now; } - return emulator_write_emulated_onepage(addr, val, bytes, exception, - vcpu); + + return emulator_read_write_onepage(addr, val, bytes, exception, + vcpu, ops); +} + +static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, val, bytes, + exception, &read_emultor); +} + +int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + const void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, (void *)val, bytes, + exception, &write_emultor); } #define CMPXCHG_TYPE(t, ptr, old, new) \ @@ -4712,7 +4786,7 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) kvm_set_rflags(vcpu, ctxt->eflags); if (irq == NMI_VECTOR) - vcpu->arch.nmi_pending = false; + vcpu->arch.nmi_pending = 0; else vcpu->arch.interrupt.pending = false; @@ -4788,7 +4862,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; - if (r) { + if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; if (reexecute_instruction(vcpu, cr2)) @@ -5521,7 +5595,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) /* try to inject new event if pending */ if (vcpu->arch.nmi_pending) { if (kvm_x86_ops->nmi_allowed(vcpu)) { - vcpu->arch.nmi_pending = false; + --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; kvm_x86_ops->set_nmi(vcpu); } @@ -5553,10 +5627,26 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) } } +static void process_nmi(struct kvm_vcpu *vcpu) +{ + unsigned limit = 2; + + /* + * x86 is limited to one NMI running, and one NMI pending after it. + * If an NMI is already in progress, limit further NMIs to just one. + * Otherwise, allow two (and we'll inject the first one immediately). + */ + if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + limit = 1; + + vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool nmi_pending; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; @@ -5596,6 +5686,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_NMI, vcpu)) + process_nmi(vcpu); } @@ -5603,19 +5695,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (unlikely(r)) goto out; - /* - * An NMI can be injected between local nmi_pending read and - * vcpu->arch.nmi_pending read inside inject_pending_event(). - * But in that case, KVM_REQ_EVENT will be set, which makes - * the race described above benign. - */ - nmi_pending = ACCESS_ONCE(vcpu->arch.nmi_pending); - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ - if (nmi_pending) + if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); else if (kvm_cpu_has_interrupt(vcpu) || req_int_win) kvm_x86_ops->enable_irq_window(vcpu); @@ -5678,7 +5762,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -6323,7 +6407,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) { - vcpu->arch.nmi_pending = false; + atomic_set(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; vcpu->arch.switch_db_regs = 0; @@ -6598,7 +6683,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted) || !list_empty_careful(&vcpu->async_pf.done) || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED - || vcpu->arch.nmi_pending || + || atomic_read(&vcpu->arch.nmi_queued) || (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)); } |