diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/emulate.c | 673 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.c | 1 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/irq.c | 74 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 140 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 34 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 168 | ||||
-rw-r--r-- | arch/x86/kvm/mmutrace.h | 6 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 106 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 24 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 714 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 168 |
12 files changed, 1364 insertions, 746 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a27e763..a335cc6 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -24,6 +24,7 @@ #include "kvm_cache_regs.h" #include <linux/module.h> #include <asm/kvm_emulate.h> +#include <linux/stringify.h> #include "x86.h" #include "tss.h" @@ -43,7 +44,7 @@ #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 OpImm 12ull /* Sign extended up to 32-bit immediate */ #define OpMem16 13ull /* Memory operand (16-bit). */ #define OpMem32 14ull /* Memory operand (32-bit). */ #define OpImmU 15ull /* Immediate operand, zero extended */ @@ -58,6 +59,7 @@ #define OpFS 24ull /* FS */ #define OpGS 25ull /* GS */ #define OpMem8 26ull /* 8-bit zero extended memory operand */ +#define OpImm64 27ull /* Sign extended 16/32/64-bit immediate */ #define OpBits 5 /* Width of operand field */ #define OpMask ((1ull << OpBits) - 1) @@ -101,6 +103,7 @@ #define SrcMemFAddr (OpMemFAddr << SrcShift) #define SrcAcc (OpAcc << SrcShift) #define SrcImmU16 (OpImmU16 << SrcShift) +#define SrcImm64 (OpImm64 << SrcShift) #define SrcDX (OpDX << SrcShift) #define SrcMem8 (OpMem8 << SrcShift) #define SrcMask (OpMask << SrcShift) @@ -113,6 +116,7 @@ #define GroupDual (2<<15) /* Alternate decoding of mod == 3 */ #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 Escape (5<<15) /* Escape to coprocessor instruction */ #define Sse (1<<18) /* SSE Vector instruction */ /* Generic ModRM decode. */ #define ModRM (1<<19) @@ -146,6 +150,8 @@ #define Aligned ((u64)1 << 41) /* Explicitly aligned (e.g. MOVDQA) */ #define Unaligned ((u64)1 << 42) /* Explicitly unaligned (e.g. MOVDQU) */ #define Avx ((u64)1 << 43) /* Advanced Vector Extensions */ +#define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */ +#define NoWrite ((u64)1 << 45) /* No writeback */ #define X2(x...) x, x #define X3(x...) X2(x), x @@ -156,6 +162,27 @@ #define X8(x...) X4(x), X4(x) #define X16(x...) X8(x), X8(x) +#define NR_FASTOP (ilog2(sizeof(ulong)) + 1) +#define FASTOP_SIZE 8 + +/* + * fastop functions have a special calling convention: + * + * dst: [rdx]:rax (in/out) + * src: rbx (in/out) + * src2: rcx (in) + * flags: rflags (in/out) + * + * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for + * different operand sizes can be reached by calculation, rather than a jump + * table (which would be bigger than the code). + * + * fastop functions are declared as taking a never-defined fastop parameter, + * so they can't be called from C directly. + */ + +struct fastop; + struct opcode { u64 flags : 56; u64 intercept : 8; @@ -164,6 +191,8 @@ struct opcode { const struct opcode *group; const struct group_dual *gdual; const struct gprefix *gprefix; + const struct escape *esc; + void (*fastop)(struct fastop *fake); } u; int (*check_perm)(struct x86_emulate_ctxt *ctxt); }; @@ -180,6 +209,11 @@ struct gprefix { struct opcode pfx_f3; }; +struct escape { + struct opcode op[8]; + struct opcode high[64]; +}; + /* EFLAGS bit definitions. */ #define EFLG_ID (1<<21) #define EFLG_VIP (1<<20) @@ -407,6 +441,97 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) } \ } while (0) +static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); + +#define FOP_ALIGN ".align " __stringify(FASTOP_SIZE) " \n\t" +#define FOP_RET "ret \n\t" + +#define FOP_START(op) \ + extern void em_##op(struct fastop *fake); \ + asm(".pushsection .text, \"ax\" \n\t" \ + ".global em_" #op " \n\t" \ + FOP_ALIGN \ + "em_" #op ": \n\t" + +#define FOP_END \ + ".popsection") + +#define FOPNOP() FOP_ALIGN FOP_RET + +#define FOP1E(op, dst) \ + FOP_ALIGN #op " %" #dst " \n\t" FOP_RET + +#define FASTOP1(op) \ + FOP_START(op) \ + FOP1E(op##b, al) \ + FOP1E(op##w, ax) \ + FOP1E(op##l, eax) \ + ON64(FOP1E(op##q, rax)) \ + FOP_END + +#define FOP2E(op, dst, src) \ + FOP_ALIGN #op " %" #src ", %" #dst " \n\t" FOP_RET + +#define FASTOP2(op) \ + FOP_START(op) \ + FOP2E(op##b, al, bl) \ + FOP2E(op##w, ax, bx) \ + FOP2E(op##l, eax, ebx) \ + ON64(FOP2E(op##q, rax, rbx)) \ + FOP_END + +/* 2 operand, word only */ +#define FASTOP2W(op) \ + FOP_START(op) \ + FOPNOP() \ + FOP2E(op##w, ax, bx) \ + FOP2E(op##l, eax, ebx) \ + ON64(FOP2E(op##q, rax, rbx)) \ + FOP_END + +/* 2 operand, src is CL */ +#define FASTOP2CL(op) \ + FOP_START(op) \ + FOP2E(op##b, al, cl) \ + FOP2E(op##w, ax, cl) \ + FOP2E(op##l, eax, cl) \ + ON64(FOP2E(op##q, rax, cl)) \ + FOP_END + +#define FOP3E(op, dst, src, src2) \ + FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET + +/* 3-operand, word-only, src2=cl */ +#define FASTOP3WCL(op) \ + FOP_START(op) \ + FOPNOP() \ + FOP3E(op##w, ax, bx, cl) \ + FOP3E(op##l, eax, ebx, cl) \ + ON64(FOP3E(op##q, rax, rbx, cl)) \ + FOP_END + +/* Special case for SETcc - 1 instruction per cc */ +#define FOP_SETCC(op) ".align 4; " #op " %al; ret \n\t" + +FOP_START(setcc) +FOP_SETCC(seto) +FOP_SETCC(setno) +FOP_SETCC(setc) +FOP_SETCC(setnc) +FOP_SETCC(setz) +FOP_SETCC(setnz) +FOP_SETCC(setbe) +FOP_SETCC(setnbe) +FOP_SETCC(sets) +FOP_SETCC(setns) +FOP_SETCC(setp) +FOP_SETCC(setnp) +FOP_SETCC(setl) +FOP_SETCC(setnl) +FOP_SETCC(setle) +FOP_SETCC(setnle) +FOP_END; + #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex) \ do { \ unsigned long _tmp; \ @@ -663,7 +788,7 @@ static int __linearize(struct x86_emulate_ctxt *ctxt, ulong la; u32 lim; u16 sel; - unsigned cpl, rpl; + unsigned cpl; la = seg_base(ctxt, addr.seg) + addr.ea; switch (ctxt->mode) { @@ -697,11 +822,6 @@ static int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; } cpl = ctxt->ops->cpl(ctxt); - if (ctxt->mode == X86EMUL_MODE_REAL) - rpl = 0; - else - rpl = sel & 3; - cpl = max(cpl, rpl); if (!(desc.type & 8)) { /* data segment */ if (cpl > desc.dpl) @@ -852,39 +972,50 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt, return rc; } -static int test_cc(unsigned int condition, unsigned int flags) -{ - int rc = 0; - - switch ((condition & 15) >> 1) { - case 0: /* o */ - rc |= (flags & EFLG_OF); - break; - case 1: /* b/c/nae */ - rc |= (flags & EFLG_CF); - break; - case 2: /* z/e */ - rc |= (flags & EFLG_ZF); - break; - case 3: /* be/na */ - rc |= (flags & (EFLG_CF|EFLG_ZF)); - break; - case 4: /* s */ - rc |= (flags & EFLG_SF); - break; - case 5: /* p/pe */ - rc |= (flags & EFLG_PF); - break; - case 7: /* le/ng */ - rc |= (flags & EFLG_ZF); - /* fall through */ - case 6: /* l/nge */ - rc |= (!(flags & EFLG_SF) != !(flags & EFLG_OF)); - break; - } - - /* Odd condition identifiers (lsb == 1) have inverted sense. */ - return (!!rc ^ (condition & 1)); +FASTOP2(add); +FASTOP2(or); +FASTOP2(adc); +FASTOP2(sbb); +FASTOP2(and); +FASTOP2(sub); +FASTOP2(xor); +FASTOP2(cmp); +FASTOP2(test); + +FASTOP3WCL(shld); +FASTOP3WCL(shrd); + +FASTOP2W(imul); + +FASTOP1(not); +FASTOP1(neg); +FASTOP1(inc); +FASTOP1(dec); + +FASTOP2CL(rol); +FASTOP2CL(ror); +FASTOP2CL(rcl); +FASTOP2CL(rcr); +FASTOP2CL(shl); +FASTOP2CL(shr); +FASTOP2CL(sar); + +FASTOP2W(bsf); +FASTOP2W(bsr); +FASTOP2W(bt); +FASTOP2W(bts); +FASTOP2W(btr); +FASTOP2W(btc); + +static u8 test_cc(unsigned int condition, unsigned long flags) +{ + u8 rc; + void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf); + + flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; + asm("push %[flags]; popf; call *%[fastop]" + : "=a"(rc) : [fastop]"r"(fop), [flags]"r"(flags)); + return rc; } static void fetch_register_operand(struct operand *op) @@ -994,6 +1125,53 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) ctxt->ops->put_fpu(ctxt); } +static int em_fninit(struct x86_emulate_ctxt *ctxt) +{ + if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) + return emulate_nm(ctxt); + + ctxt->ops->get_fpu(ctxt); + asm volatile("fninit"); + ctxt->ops->put_fpu(ctxt); + return X86EMUL_CONTINUE; +} + +static int em_fnstcw(struct x86_emulate_ctxt *ctxt) +{ + u16 fcw; + + if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) + return emulate_nm(ctxt); + + ctxt->ops->get_fpu(ctxt); + asm volatile("fnstcw %0": "+m"(fcw)); + ctxt->ops->put_fpu(ctxt); + + /* force 2 byte destination */ + ctxt->dst.bytes = 2; + ctxt->dst.val = fcw; + + return X86EMUL_CONTINUE; +} + +static int em_fnstsw(struct x86_emulate_ctxt *ctxt) +{ + u16 fsw; + + if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) + return emulate_nm(ctxt); + + ctxt->ops->get_fpu(ctxt); + asm volatile("fnstsw %0": "+m"(fsw)); + ctxt->ops->put_fpu(ctxt); + + /* force 2 byte destination */ + ctxt->dst.bytes = 2; + ctxt->dst.val = fsw; + + return X86EMUL_CONTINUE; +} + static void decode_register_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { @@ -1534,6 +1712,9 @@ static int writeback(struct x86_emulate_ctxt *ctxt) { int rc; + if (ctxt->d & NoWrite) + return X86EMUL_CONTINUE; + switch (ctxt->dst.type) { case OP_REG: write_register_operand(&ctxt->dst); @@ -1918,47 +2099,6 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_grp2(struct x86_emulate_ctxt *ctxt) -{ - switch (ctxt->modrm_reg) { - case 0: /* rol */ - emulate_2op_SrcB(ctxt, "rol"); - break; - case 1: /* ror */ - emulate_2op_SrcB(ctxt, "ror"); - break; - case 2: /* rcl */ - emulate_2op_SrcB(ctxt, "rcl"); - break; - case 3: /* rcr */ - emulate_2op_SrcB(ctxt, "rcr"); - break; - case 4: /* sal/shl */ - case 6: /* sal/shl */ - emulate_2op_SrcB(ctxt, "sal"); - break; - case 5: /* shr */ - emulate_2op_SrcB(ctxt, "shr"); - break; - case 7: /* sar */ - emulate_2op_SrcB(ctxt, "sar"); - break; - } - return X86EMUL_CONTINUE; -} - -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; @@ -2000,12 +2140,6 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) int rc = X86EMUL_CONTINUE; switch (ctxt->modrm_reg) { - case 0: /* inc */ - emulate_1op(ctxt, "inc"); - break; - case 1: /* dec */ - emulate_1op(ctxt, "dec"); - break; case 2: /* call near abs */ { long int old_eip; old_eip = ctxt->_eip; @@ -2075,7 +2209,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) /* Save real source value, then compare EAX against destination. */ ctxt->src.orig_val = ctxt->src.val; ctxt->src.val = reg_read(ctxt, VCPU_REGS_RAX); - emulate_2op_SrcV(ctxt, "cmp"); + fastop(ctxt, em_cmp); if (ctxt->eflags & EFLG_ZF) { /* Success: write back to memory. */ @@ -2843,7 +2977,7 @@ 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(ctxt, "or"); + fastop(ctxt, em_or); ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF); if (cf) ctxt->eflags |= X86_EFLAGS_CF; @@ -2852,6 +2986,24 @@ static int em_das(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_aad(struct x86_emulate_ctxt *ctxt) +{ + u8 al = ctxt->dst.val & 0xff; + u8 ah = (ctxt->dst.val >> 8) & 0xff; + + al = (al + (ah * ctxt->src.val)) & 0xff; + + ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al; + + /* Set PF, ZF, SF */ + ctxt->src.type = OP_IMM; + ctxt->src.val = 0; + ctxt->src.bytes = 1; + fastop(ctxt, em_or); + + return X86EMUL_CONTINUE; +} + static int em_call(struct x86_emulate_ctxt *ctxt) { long rel = ctxt->src.val; @@ -2900,64 +3052,6 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_add(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "add"); - return X86EMUL_CONTINUE; -} - -static int em_or(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "or"); - return X86EMUL_CONTINUE; -} - -static int em_adc(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "adc"); - return X86EMUL_CONTINUE; -} - -static int em_sbb(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "sbb"); - return X86EMUL_CONTINUE; -} - -static int em_and(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "and"); - return X86EMUL_CONTINUE; -} - -static int em_sub(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "sub"); - return X86EMUL_CONTINUE; -} - -static int em_xor(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "xor"); - return X86EMUL_CONTINUE; -} - -static int em_cmp(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "cmp"); - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - return X86EMUL_CONTINUE; -} - -static int em_test(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV(ctxt, "test"); - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - return X86EMUL_CONTINUE; -} - static int em_xchg(struct x86_emulate_ctxt *ctxt) { /* Write back the register source. */ @@ -2970,16 +3064,10 @@ static int em_xchg(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_imul(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV_nobyte(ctxt, "imul"); - return X86EMUL_CONTINUE; -} - static int em_imul_3op(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = ctxt->src2.val; - return em_imul(ctxt); + return fastop(ctxt, em_imul); } static int em_cwd(struct x86_emulate_ctxt *ctxt) @@ -3300,47 +3388,6 @@ static int em_sti(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_bt(struct x86_emulate_ctxt *ctxt) -{ - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - /* only subword offset */ - ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; - - emulate_2op_SrcV_nobyte(ctxt, "bt"); - return X86EMUL_CONTINUE; -} - -static int em_bts(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV_nobyte(ctxt, "bts"); - return X86EMUL_CONTINUE; -} - -static int em_btr(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV_nobyte(ctxt, "btr"); - return X86EMUL_CONTINUE; -} - -static int em_btc(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV_nobyte(ctxt, "btc"); - return X86EMUL_CONTINUE; -} - -static int em_bsf(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV_nobyte(ctxt, "bsf"); - return X86EMUL_CONTINUE; -} - -static int em_bsr(struct x86_emulate_ctxt *ctxt) -{ - emulate_2op_SrcV_nobyte(ctxt, "bsr"); - return X86EMUL_CONTINUE; -} - static int em_cpuid(struct x86_emulate_ctxt *ctxt) { u32 eax, ebx, ecx, edx; @@ -3572,7 +3619,9 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) } #define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) } #define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) } +#define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) } #define I(_f, _e) { .flags = (_f), .u.execute = (_e) } +#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) } #define II(_f, _e, _i) \ { .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i } #define IIP(_f, _e, _i, _p) \ @@ -3583,12 +3632,13 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) #define D2bv(_f) D((_f) | ByteOp), D(_f) #define D2bvIP(_f, _i, _p) DIP((_f) | ByteOp, _i, _p), DIP(_f, _i, _p) #define I2bv(_f, _e) I((_f) | ByteOp, _e), I(_f, _e) +#define F2bv(_f, _e) F((_f) | ByteOp, _e), F(_f, _e) #define I2bvIP(_f, _e, _i, _p) \ IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p) -#define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e), \ - I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ - I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) +#define F6ALU(_f, _e) F2bv((_f) | DstMem | SrcReg | ModRM, _e), \ + F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ + F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) static const struct opcode group7_rm1[] = { DI(SrcNone | Priv, monitor), @@ -3614,25 +3664,36 @@ static const struct opcode group7_rm7[] = { }; static const struct opcode group1[] = { - I(Lock, em_add), - I(Lock | PageTable, em_or), - I(Lock, em_adc), - I(Lock, em_sbb), - I(Lock | PageTable, em_and), - I(Lock, em_sub), - I(Lock, em_xor), - I(0, em_cmp), + F(Lock, em_add), + F(Lock | PageTable, em_or), + F(Lock, em_adc), + F(Lock, em_sbb), + F(Lock | PageTable, em_and), + F(Lock, em_sub), + F(Lock, em_xor), + F(NoWrite, em_cmp), }; static const struct opcode group1A[] = { I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N, }; +static const struct opcode group2[] = { + F(DstMem | ModRM, em_rol), + F(DstMem | ModRM, em_ror), + F(DstMem | ModRM, em_rcl), + F(DstMem | ModRM, em_rcr), + F(DstMem | ModRM, em_shl), + F(DstMem | ModRM, em_shr), + F(DstMem | ModRM, em_shl), + F(DstMem | ModRM, em_sar), +}; + static const struct opcode group3[] = { - I(DstMem | SrcImm, em_test), - I(DstMem | SrcImm, em_test), - I(DstMem | SrcNone | Lock, em_not), - I(DstMem | SrcNone | Lock, em_neg), + F(DstMem | SrcImm | NoWrite, em_test), + F(DstMem | SrcImm | NoWrite, em_test), + F(DstMem | SrcNone | Lock, em_not), + F(DstMem | SrcNone | Lock, em_neg), I(SrcMem, em_mul_ex), I(SrcMem, em_imul_ex), I(SrcMem, em_div_ex), @@ -3640,14 +3701,14 @@ static const struct opcode group3[] = { }; static const struct opcode group4[] = { - I(ByteOp | DstMem | SrcNone | Lock, em_grp45), - I(ByteOp | DstMem | SrcNone | Lock, em_grp45), + F(ByteOp | DstMem | SrcNone | Lock, em_inc), + F(ByteOp | DstMem | SrcNone | Lock, em_dec), N, N, N, N, N, N, }; static const struct opcode group5[] = { - I(DstMem | SrcNone | Lock, em_grp45), - I(DstMem | SrcNone | Lock, em_grp45), + F(DstMem | SrcNone | Lock, em_inc), + F(DstMem | SrcNone | Lock, em_dec), I(SrcMem | Stack, em_grp45), I(SrcMemFAddr | ImplicitOps | Stack, em_call_far), I(SrcMem | Stack, em_grp45), @@ -3682,10 +3743,10 @@ static const struct group_dual group7 = { { static const struct opcode group8[] = { N, N, N, N, - I(DstMem | SrcImmByte, em_bt), - I(DstMem | SrcImmByte | Lock | PageTable, em_bts), - I(DstMem | SrcImmByte | Lock, em_btr), - I(DstMem | SrcImmByte | Lock | PageTable, em_btc), + F(DstMem | SrcImmByte | NoWrite, em_bt), + F(DstMem | SrcImmByte | Lock | PageTable, em_bts), + F(DstMem | SrcImmByte | Lock, em_btr), + F(DstMem | SrcImmByte | Lock | PageTable, em_btc), }; static const struct group_dual group9 = { { @@ -3707,33 +3768,96 @@ static const struct gprefix pfx_vmovntpx = { I(0, em_mov), N, N, N, }; +static const struct escape escape_d9 = { { + N, N, N, N, N, N, N, I(DstMem, em_fnstcw), +}, { + /* 0xC0 - 0xC7 */ + N, N, N, N, N, N, N, N, + /* 0xC8 - 0xCF */ + N, N, N, N, N, N, N, N, + /* 0xD0 - 0xC7 */ + N, N, N, N, N, N, N, N, + /* 0xD8 - 0xDF */ + N, N, N, N, N, N, N, N, + /* 0xE0 - 0xE7 */ + N, N, N, N, N, N, N, N, + /* 0xE8 - 0xEF */ + N, N, N, N, N, N, N, N, + /* 0xF0 - 0xF7 */ + N, N, N, N, N, N, N, N, + /* 0xF8 - 0xFF */ + N, N, N, N, N, N, N, N, +} }; + +static const struct escape escape_db = { { + N, N, N, N, N, N, N, N, +}, { + /* 0xC0 - 0xC7 */ + N, N, N, N, N, N, N, N, + /* 0xC8 - 0xCF */ + N, N, N, N, N, N, N, N, + /* 0xD0 - 0xC7 */ + N, N, N, N, N, N, N, N, + /* 0xD8 - 0xDF */ + N, N, N, N, N, N, N, N, + /* 0xE0 - 0xE7 */ + N, N, N, I(ImplicitOps, em_fninit), N, N, N, N, + /* 0xE8 - 0xEF */ + N, N, N, N, N, N, N, N, + /* 0xF0 - 0xF7 */ + N, N, N, N, N, N, N, N, + /* 0xF8 - 0xFF */ + N, N, N, N, N, N, N, N, +} }; + +static const struct escape escape_dd = { { + N, N, N, N, N, N, N, I(DstMem, em_fnstsw), +}, { + /* 0xC0 - 0xC7 */ + N, N, N, N, N, N, N, N, + /* 0xC8 - 0xCF */ + N, N, N, N, N, N, N, N, + /* 0xD0 - 0xC7 */ + N, N, N, N, N, N, N, N, + /* 0xD8 - 0xDF */ + N, N, N, N, N, N, N, N, + /* 0xE0 - 0xE7 */ + N, N, N, N, N, N, N, N, + /* 0xE8 - 0xEF */ + N, N, N, N, N, N, N, N, + /* 0xF0 - 0xF7 */ + N, N, N, N, N, N, N, N, + /* 0xF8 - 0xFF */ + N, N, N, N, N, N, N, N, +} }; + static const struct opcode opcode_table[256] = { /* 0x00 - 0x07 */ - I6ALU(Lock, em_add), + F6ALU(Lock, em_add), I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg), /* 0x08 - 0x0F */ - I6ALU(Lock | PageTable, em_or), + F6ALU(Lock | PageTable, em_or), I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg), N, /* 0x10 - 0x17 */ - I6ALU(Lock, em_adc), + F6ALU(Lock, em_adc), I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg), /* 0x18 - 0x1F */ - I6ALU(Lock, em_sbb), + F6ALU(Lock, em_sbb), I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg), /* 0x20 - 0x27 */ - I6ALU(Lock | PageTable, em_and), N, N, + F6ALU(Lock | PageTable, em_and), N, N, /* 0x28 - 0x2F */ - I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), + F6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), /* 0x30 - 0x37 */ - I6ALU(Lock, em_xor), N, N, + F6ALU(Lock, em_xor), N, N, /* 0x38 - 0x3F */ - I6ALU(0, em_cmp), N, N, + F6ALU(NoWrite, em_cmp), N, N, /* 0x40 - 0x4F */ - X16(D(DstReg)), + X8(F(DstReg, em_inc)), X8(F(DstReg, em_dec)), /* 0x50 - 0x57 */ X8(I(SrcReg | Stack, em_push)), /* 0x58 - 0x5F */ @@ -3757,7 +3881,7 @@ static const struct opcode opcode_table[256] = { G(DstMem | SrcImm, group1), G(ByteOp | DstMem | SrcImm | No64, group1), G(DstMem | SrcImmByte, group1), - I2bv(DstMem | SrcReg | ModRM, em_test), + F2bv(DstMem | SrcReg | ModRM | NoWrite, em_test), I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg), /* 0x88 - 0x8F */ I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov), @@ -3777,18 +3901,18 @@ static const struct opcode opcode_table[256] = { I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), I2bv(SrcSI | DstDI | Mov | String, em_mov), - I2bv(SrcSI | DstDI | String, em_cmp), + F2bv(SrcSI | DstDI | String | NoWrite, em_cmp), /* 0xA8 - 0xAF */ - I2bv(DstAcc | SrcImm, em_test), + F2bv(DstAcc | SrcImm | NoWrite, em_test), I2bv(SrcAcc | DstDI | Mov | String, em_mov), I2bv(SrcSI | DstAcc | Mov | String, em_mov), - I2bv(SrcAcc | DstDI | String, em_cmp), + F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp), /* 0xB0 - 0xB7 */ X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)), /* 0xB8 - 0xBF */ - X8(I(DstReg | SrcImm | Mov, em_mov)), + X8(I(DstReg | SrcImm64 | Mov, em_mov)), /* 0xC0 - 0xC7 */ - D2bv(DstMem | SrcImmByte | ModRM), + G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2), I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm), I(ImplicitOps | Stack, em_ret), I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg), @@ -3800,10 +3924,11 @@ static const struct opcode opcode_table[256] = { D(ImplicitOps), DI(SrcImmByte, intn), D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret), /* 0xD0 - 0xD7 */ - D2bv(DstMem | SrcOne | ModRM), D2bv(DstMem | ModRM), - N, N, N, N, + G(Src2One | ByteOp, group2), G(Src2One, group2), + G(Src2CL | ByteOp, group2), G(Src2CL, group2), + N, I(DstAcc | SrcImmByte | No64, em_aad), N, N, /* 0xD8 - 0xDF */ - N, N, N, N, N, N, N, N, + N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N, /* 0xE0 - 0xE7 */ X3(I(SrcImmByte, em_loop)), I(SrcImmByte, em_jcxz), @@ -3870,28 +3995,29 @@ static const struct opcode twobyte_table[256] = { X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), - II(ImplicitOps, em_cpuid, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt), - D(DstMem | SrcReg | Src2ImmByte | ModRM), - D(DstMem | SrcReg | Src2CL | ModRM), N, N, + II(ImplicitOps, em_cpuid, cpuid), + F(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt), + F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld), + F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), DI(ImplicitOps, rsm), - I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), - D(DstMem | SrcReg | Src2ImmByte | ModRM), - D(DstMem | SrcReg | Src2CL | ModRM), - D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), + F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), + F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd), + F(DstMem | SrcReg | Src2CL | ModRM, em_shrd), + D(ModRM), F(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg), I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), - I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), + F(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, G(BitOp, group8), - I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), - I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr), + F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), + F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ D2bv(DstMem | SrcReg | ModRM | Lock), @@ -3950,6 +4076,9 @@ static int decode_imm(struct x86_emulate_ctxt *ctxt, struct operand *op, case 4: op->val = insn_fetch(s32, ctxt); break; + case 8: + op->val = insn_fetch(s64, ctxt); + break; } if (!sign_extension) { switch (op->bytes) { @@ -4028,6 +4157,9 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, case OpImm: rc = decode_imm(ctxt, op, imm_size(ctxt), true); break; + case OpImm64: + rc = decode_imm(ctxt, op, ctxt->op_bytes, true); + break; case OpMem8: ctxt->memop.bytes = 1; goto mem_common; @@ -4222,6 +4354,12 @@ done_prefixes: case 0xf3: opcode = opcode.u.gprefix->pfx_f3; break; } break; + case Escape: + if (ctxt->modrm > 0xbf) + opcode = opcode.u.esc->high[ctxt->modrm - 0xc0]; + else + opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7]; + break; default: return EMULATION_FAILED; } @@ -4354,6 +4492,16 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, read_mmx_reg(ctxt, &op->mm_val, op->addr.mm); } +static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) +{ + ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; + fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; + asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" + : "+a"(ctxt->dst.val), "+b"(ctxt->src.val), [flags]"+D"(flags) + : "c"(ctxt->src2.val), [fastop]"S"(fop)); + ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); + return X86EMUL_CONTINUE; +} int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) { @@ -4483,6 +4631,13 @@ special_insn: } if (ctxt->execute) { + if (ctxt->d & Fastop) { + void (*fop)(struct fastop *) = (void *)ctxt->execute; + rc = fastop(ctxt, fop); + if (rc != X86EMUL_CONTINUE) + goto done; + goto writeback; + } rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) goto done; @@ -4493,12 +4648,6 @@ special_insn: goto twobyte_insn; switch (ctxt->b) { - case 0x40 ... 0x47: /* inc r16/r32 */ - emulate_1op(ctxt, "inc"); - break; - case 0x48 ... 0x4f: /* dec r16/r32 */ - emulate_1op(ctxt, "dec"); - break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) goto cannot_emulate; @@ -4523,9 +4672,6 @@ special_insn: case 8: ctxt->dst.val = (s32)ctxt->dst.val; break; } break; - case 0xc0 ... 0xc1: - rc = em_grp2(ctxt); - break; case 0xcc: /* int3 */ rc = emulate_int(ctxt, 3); break; @@ -4536,13 +4682,6 @@ special_insn: if (ctxt->eflags & EFLG_OF) rc = emulate_int(ctxt, 4); break; - case 0xd0 ... 0xd1: /* Grp2 */ - rc = em_grp2(ctxt); - break; - case 0xd2 ... 0xd3: /* Grp2 */ - ctxt->src.val = reg_read(ctxt, VCPU_REGS_RCX); - rc = em_grp2(ctxt); - break; case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ jmp_rel(ctxt, ctxt->src.val); @@ -4661,14 +4800,6 @@ twobyte_insn: case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); break; - case 0xa4: /* shld imm8, r, r/m */ - case 0xa5: /* shld cl, r, r/m */ - emulate_2op_cl(ctxt, "shld"); - break; - case 0xac: /* shrd imm8, r, r/m */ - case 0xad: /* shrd cl, r, r/m */ - emulate_2op_cl(ctxt, "shrd"); - break; case 0xae: /* clflush */ break; case 0xb6 ... 0xb7: /* movzx */ @@ -4682,7 +4813,7 @@ twobyte_insn: (s16) ctxt->src.val; break; case 0xc0 ... 0xc1: /* xadd */ - emulate_2op_SrcV(ctxt, "add"); + fastop(ctxt, em_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 11300d2..c1d30b2 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -122,7 +122,6 @@ static s64 __kpit_elapsed(struct kvm *kvm) */ remaining = hrtimer_get_remaining(&ps->timer); elapsed = ps->period - ktime_to_ns(remaining); - elapsed = mod_64(elapsed, ps->period); return elapsed; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 848206d..cc31f7c 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -241,6 +241,8 @@ int kvm_pic_read_irq(struct kvm *kvm) int irq, irq2, intno; struct kvm_pic *s = pic_irqchip(kvm); + s->output = 0; + pic_lock(s); irq = pic_get_irq(&s->pics[0]); if (irq >= 0) { diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 7e06ba1..484bc87 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -38,49 +38,81 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) EXPORT_SYMBOL(kvm_cpu_has_pending_timer); /* + * check if there is pending interrupt from + * non-APIC source without intack. + */ +static int kvm_cpu_has_extint(struct kvm_vcpu *v) +{ + if (kvm_apic_accept_pic_intr(v)) + return pic_irqchip(v->kvm)->output; /* PIC */ + else + return 0; +} + +/* + * check if there is injectable interrupt: + * when virtual interrupt delivery enabled, + * interrupt from apic will handled by hardware, + * we don't need to check it here. + */ +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) +{ + if (!irqchip_in_kernel(v->kvm)) + return v->arch.interrupt.pending; + + if (kvm_cpu_has_extint(v)) + return 1; + + if (kvm_apic_vid_enabled(v->kvm)) + return 0; + + return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ +} + +/* * check if there is pending interrupt without * intack. */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - struct kvm_pic *s; - if (!irqchip_in_kernel(v->kvm)) return v->arch.interrupt.pending; - if (kvm_apic_has_interrupt(v) == -1) { /* LAPIC */ - if (kvm_apic_accept_pic_intr(v)) { - s = pic_irqchip(v->kvm); /* PIC */ - return s->output; - } else - return 0; - } - return 1; + if (kvm_cpu_has_extint(v)) + return 1; + + return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ } EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); /* + * Read pending interrupt(from non-APIC source) + * vector and intack. + */ +static int kvm_cpu_get_extint(struct kvm_vcpu *v) +{ + if (kvm_cpu_has_extint(v)) + return kvm_pic_read_irq(v->kvm); /* PIC */ + return -1; +} + +/* * Read pending interrupt vector and intack. */ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { - struct kvm_pic *s; int vector; if (!irqchip_in_kernel(v->kvm)) return v->arch.interrupt.nr; - vector = kvm_get_apic_interrupt(v); /* APIC */ - if (vector == -1) { - if (kvm_apic_accept_pic_intr(v)) { - s = pic_irqchip(v->kvm); - s->output = 0; /* PIC */ - vector = kvm_pic_read_irq(v->kvm); - } - } - return vector; + vector = kvm_cpu_get_extint(v); + + if (kvm_apic_vid_enabled(v->kvm) || vector != -1) + return vector; /* PIC */ + + return kvm_get_apic_interrupt(v); /* APIC */ } -EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9392f52..02b51dd 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -140,31 +140,56 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline int apic_x2apic_mode(struct kvm_lapic *apic) -{ - return apic->vcpu->arch.apic_base & X2APIC_ENABLE; -} - static inline int kvm_apic_id(struct kvm_lapic *apic) { return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } -static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr) +void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, + struct kvm_lapic_irq *irq, + u64 *eoi_exit_bitmap) { - u16 cid; - ldr >>= 32 - map->ldr_bits; - cid = (ldr >> map->cid_shift) & map->cid_mask; + struct kvm_lapic **dst; + struct kvm_apic_map *map; + unsigned long bitmap = 1; + int i; - BUG_ON(cid >= ARRAY_SIZE(map->logical_map)); + rcu_read_lock(); + map = rcu_dereference(vcpu->kvm->arch.apic_map); - return cid; -} + if (unlikely(!map)) { + __set_bit(irq->vector, (unsigned long *)eoi_exit_bitmap); + goto out; + } -static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) -{ - ldr >>= (32 - map->ldr_bits); - return ldr & map->lid_mask; + if (irq->dest_mode == 0) { /* physical mode */ + if (irq->delivery_mode == APIC_DM_LOWEST || + irq->dest_id == 0xff) { + __set_bit(irq->vector, + (unsigned long *)eoi_exit_bitmap); + goto out; + } + dst = &map->phys_map[irq->dest_id & 0xff]; + } else { + u32 mda = irq->dest_id << (32 - map->ldr_bits); + + dst = map->logical_map[apic_cluster_id(map, mda)]; + + bitmap = apic_logical_id(map, mda); + } + + for_each_set_bit(i, &bitmap, 16) { + if (!dst[i]) + continue; + if (dst[i]->vcpu == vcpu) { + __set_bit(irq->vector, + (unsigned long *)eoi_exit_bitmap); + break; + } + } + +out: + rcu_read_unlock(); } static void recalculate_apic_map(struct kvm *kvm) @@ -230,6 +255,8 @@ out: if (old) kfree_rcu(old, rcu); + + kvm_ioapic_make_eoibitmap_request(kvm); } static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id) @@ -345,6 +372,10 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) { int result; + /* + * Note that irr_pending is just a hint. It will be always + * true with virtual interrupt delivery enabled. + */ if (!apic->irr_pending) return -1; @@ -461,6 +492,8 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) static inline int apic_find_highest_isr(struct kvm_lapic *apic) { int result; + + /* Note that isr_count is always 1 with vid enabled */ if (!apic->isr_count) return -1; if (likely(apic->highest_isr_cache != -1)) @@ -740,6 +773,19 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } +static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) +{ + if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && + kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { + int trigger_mode; + if (apic_test_vector(vector, apic->regs + APIC_TMR)) + trigger_mode = IOAPIC_LEVEL_TRIG; + else + trigger_mode = IOAPIC_EDGE_TRIG; + kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); + } +} + static int apic_set_eoi(struct kvm_lapic *apic) { int vector = apic_find_highest_isr(apic); @@ -756,19 +802,26 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); - if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && - kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { - int trigger_mode; - if (apic_test_vector(vector, apic->regs + APIC_TMR)) - trigger_mode = IOAPIC_LEVEL_TRIG; - else - trigger_mode = IOAPIC_EDGE_TRIG; - kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); - } + kvm_ioapic_send_eoi(apic, vector); kvm_make_request(KVM_REQ_EVENT, apic->vcpu); return vector; } +/* + * this interface assumes a trap-like exit, which has already finished + * desired side effect including vISR and vPPR update. + */ +void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + trace_kvm_eoi(apic, vector); + + kvm_ioapic_send_eoi(apic, vector); + kvm_make_request(KVM_REQ_EVENT, apic->vcpu); +} +EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); + static void apic_send_ipi(struct kvm_lapic *apic) { u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR); @@ -1212,6 +1265,21 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); +/* emulate APIC access in a trap manner */ +void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) +{ + u32 val = 0; + + /* hw has done the conditional check and inst decode */ + offset &= 0xff0; + + apic_reg_read(vcpu->arch.apic, offset, 4, &val); + + /* TODO: optimize to just emulate side effect w/o one more write */ + apic_reg_write(vcpu->arch.apic, offset, val); +} +EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); + void kvm_free_lapic(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1288,6 +1356,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) { + u64 old_value = vcpu->arch.apic_base; struct kvm_lapic *apic = vcpu->arch.apic; if (!apic) { @@ -1309,11 +1378,16 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) value &= ~MSR_IA32_APICBASE_BSP; vcpu->arch.apic_base = value; - if (apic_x2apic_mode(apic)) { - u32 id = kvm_apic_id(apic); - u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); - kvm_apic_set_ldr(apic, ldr); + if ((old_value ^ value) & X2APIC_ENABLE) { + if (value & X2APIC_ENABLE) { + u32 id = kvm_apic_id(apic); + u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); + kvm_apic_set_ldr(apic, ldr); + kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true); + } else + kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false); } + apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; @@ -1359,8 +1433,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = false; - apic->isr_count = 0; + apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm); + apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm); apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -1575,8 +1649,10 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; - apic->isr_count = count_vectors(apic->regs + APIC_ISR); + apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ? + 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); kvm_make_request(KVM_REQ_EVENT, vcpu); } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index e5ebf9f..1676d34 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -64,6 +64,9 @@ 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_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset); +void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector); + 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); @@ -124,4 +127,35 @@ static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu) return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic); } +static inline int apic_x2apic_mode(struct kvm_lapic *apic) +{ + return apic->vcpu->arch.apic_base & X2APIC_ENABLE; +} + +static inline bool kvm_apic_vid_enabled(struct kvm *kvm) +{ + return kvm_x86_ops->vm_has_apicv(kvm); +} + +static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr) +{ + u16 cid; + ldr >>= 32 - map->ldr_bits; + cid = (ldr >> map->cid_shift) & map->cid_mask; + + BUG_ON(cid >= ARRAY_SIZE(map->logical_map)); + + return cid; +} + +static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) +{ + ldr >>= (32 - map->ldr_bits); + return ldr & map->lid_mask; +} + +void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, + struct kvm_lapic_irq *irq, + u64 *eoi_bitmap); + #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 01d7c2ad..4ed3edb 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -448,7 +448,8 @@ static bool __check_direct_spte_mmio_pf(u64 spte) static bool spte_is_locklessly_modifiable(u64 spte) { - return !(~spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)); + return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) == + (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE); } static bool spte_has_volatile_bits(u64 spte) @@ -831,8 +832,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) if (host_level == PT_PAGE_TABLE_LEVEL) return host_level; - max_level = kvm_x86_ops->get_lpage_level() < host_level ? - kvm_x86_ops->get_lpage_level() : host_level; + max_level = min(kvm_x86_ops->get_lpage_level(), host_level); for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) if (has_wrprotected_page(vcpu->kvm, large_gfn, level)) @@ -1142,7 +1142,7 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect) } static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, - int level, bool pt_protect) + bool pt_protect) { u64 *sptep; struct rmap_iterator iter; @@ -1180,7 +1180,7 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, while (mask) { rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PT_PAGE_TABLE_LEVEL, slot); - __rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false); + __rmap_write_protect(kvm, rmapp, false); /* clear the first set bit */ mask &= mask - 1; @@ -1199,7 +1199,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn) for (i = PT_PAGE_TABLE_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmapp, i, true); + write_protected |= __rmap_write_protect(kvm, rmapp, true); } return write_protected; @@ -1460,28 +1460,14 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) percpu_counter_add(&kvm_total_used_mmu_pages, nr); } -/* - * Remove the sp from shadow page cache, after call it, - * we can not find this sp from the cache, and the shadow - * page table is still valid. - * It should be under the protection of mmu lock. - */ -static void kvm_mmu_isolate_page(struct kvm_mmu_page *sp) +static void kvm_mmu_free_page(struct kvm_mmu_page *sp) { ASSERT(is_empty_shadow_page(sp->spt)); hlist_del(&sp->hash_link); - if (!sp->role.direct) - free_page((unsigned long)sp->gfns); -} - -/* - * Free the shadow page table and the sp, we can do it - * out of the protection of mmu lock. - */ -static void kvm_mmu_free_page(struct kvm_mmu_page *sp) -{ list_del(&sp->link); free_page((unsigned long)sp->spt); + if (!sp->role.direct) + free_page((unsigned long)sp->gfns); kmem_cache_free(mmu_page_header_cache, sp); } @@ -1522,7 +1508,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM); sp->parent_ptes = 0; mmu_page_add_parent_pte(vcpu, sp, parent_pte); kvm_mod_used_mmu_pages(vcpu->kvm, +1); @@ -1973,9 +1958,9 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp) { u64 spte; - spte = __pa(sp->spt) - | PT_PRESENT_MASK | PT_ACCESSED_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; + spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | + shadow_user_mask | shadow_x_mask | shadow_accessed_mask; + mmu_spte_set(sptep, spte); } @@ -2126,7 +2111,6 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, do { sp = list_first_entry(invalid_list, struct kvm_mmu_page, link); WARN_ON(!sp->role.invalid || sp->root_count); - kvm_mmu_isolate_page(sp); kvm_mmu_free_page(sp); } while (!list_empty(invalid_list)); } @@ -2144,6 +2128,8 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) * change the value */ + spin_lock(&kvm->mmu_lock); + if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) { while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages && !list_empty(&kvm->arch.active_mmu_pages)) { @@ -2158,6 +2144,8 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) } kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; + + spin_unlock(&kvm->mmu_lock); } int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) @@ -2183,14 +2171,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); -static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) -{ - int slot = memslot_id(kvm, gfn); - struct kvm_mmu_page *sp = page_header(__pa(pte)); - - __set_bit(slot, sp->slot_bitmap); -} - /* * The function is based on mtrr_type_lookup() in * arch/x86/kernel/cpu/mtrr/generic.c @@ -2332,9 +2312,8 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, if (s->role.level != PT_PAGE_TABLE_LEVEL) return 1; - if (!need_unsync && !s->unsync) { + if (!s->unsync) need_unsync = true; - } } if (need_unsync) kvm_unsync_pages(vcpu, gfn); @@ -2342,8 +2321,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, } static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pte_access, int user_fault, - int write_fault, int level, + unsigned pte_access, int level, gfn_t gfn, pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { @@ -2378,20 +2356,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= (u64)pfn << PAGE_SHIFT; - if ((pte_access & ACC_WRITE_MASK) - || (!vcpu->arch.mmu.direct_map && write_fault - && !is_write_protection(vcpu) && !user_fault)) { + if (pte_access & ACC_WRITE_MASK) { /* - * There are two cases: - * - the one is other vcpu creates new sp in the window - * between mapping_level() and acquiring mmu-lock. - * - the another case is the new sp is created by itself - * (page-fault path) when guest uses the target gfn as - * its page table. - * Both of these cases can be fixed by allowing guest to - * retry the access, it will refault, then we can establish - * the mapping by using small page. + * Other vcpu creates new sp in the window between + * mapping_level() and acquiring mmu-lock. We can + * allow guest to retry the access, the mapping can + * be fixed if guest refault. */ if (level > PT_PAGE_TABLE_LEVEL && has_wrprotected_page(vcpu->kvm, gfn, level)) @@ -2399,19 +2370,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; - if (!vcpu->arch.mmu.direct_map - && !(pte_access & ACC_WRITE_MASK)) { - spte &= ~PT_USER_MASK; - /* - * If we converted a user page to a kernel page, - * so that the kernel can write to it when cr0.wp=0, - * then we should prevent the kernel from executing it - * if SMEP is enabled. - */ - if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) - spte |= PT64_NX_MASK; - } - /* * Optimization: for pte sync, if spte was writable the hash * lookup is unnecessary (and expensive). Write protection @@ -2441,19 +2399,15 @@ done: } static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pt_access, unsigned pte_access, - int user_fault, int write_fault, - int *emulate, int level, gfn_t gfn, - pfn_t pfn, bool speculative, + unsigned pte_access, int write_fault, int *emulate, + int level, gfn_t gfn, pfn_t pfn, bool speculative, bool host_writable) { int was_rmapped = 0; int rmap_count; - pgprintk("%s: spte %llx access %x write_fault %d" - " user_fault %d gfn %llx\n", - __func__, *sptep, pt_access, - write_fault, user_fault, gfn); + pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, + *sptep, write_fault, gfn); if (is_rmap_spte(*sptep)) { /* @@ -2477,9 +2431,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, was_rmapped = 1; } - if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault, - level, gfn, pfn, speculative, true, - host_writable)) { + if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, + true, host_writable)) { if (write_fault) *emulate = 1; kvm_mmu_flush_tlb(vcpu); @@ -2497,7 +2450,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, ++vcpu->kvm->stat.lpages; if (is_shadow_present_pte(*sptep)) { - page_header_update_slot(vcpu->kvm, sptep, gfn); if (!was_rmapped) { rmap_count = rmap_add(vcpu, sptep, gfn); if (rmap_count > RMAP_RECYCLE_THRESHOLD) @@ -2571,10 +2523,9 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, return -1; for (i = 0; i < ret; i++, gfn++, start++) - mmu_set_spte(vcpu, start, ACC_ALL, - access, 0, 0, NULL, - sp->role.level, gfn, - page_to_pfn(pages[i]), true, true); + mmu_set_spte(vcpu, start, access, 0, NULL, + sp->role.level, gfn, page_to_pfn(pages[i]), + true, true); return 0; } @@ -2633,11 +2584,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { if (iterator.level == level) { - unsigned pte_access = ACC_ALL; - - mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access, - 0, write, &emulate, - level, gfn, pfn, prefault, map_writable); + mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, + write, &emulate, level, gfn, pfn, + prefault, map_writable); direct_pte_prefetch(vcpu, iterator.sptep); ++vcpu->stat.pf_fixed; break; @@ -2652,11 +2601,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, iterator.level - 1, 1, ACC_ALL, iterator.sptep); - mmu_spte_set(iterator.sptep, - __pa(sp->spt) - | PT_PRESENT_MASK | PT_WRITABLE_MASK - | shadow_user_mask | shadow_x_mask - | shadow_accessed_mask); + link_shadow_page(iterator.sptep, sp); } } return emulate; @@ -3719,6 +3664,7 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) else r = paging32_init_context(vcpu, context); + vcpu->arch.mmu.base_role.nxe = is_nx(vcpu); vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu); vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu); vcpu->arch.mmu.base_role.smep_andnot_wp @@ -3885,7 +3831,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ *gpa &= ~(gpa_t)7; *bytes = 8; - r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, min(*bytes, 8)); + r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8); if (r) gentry = 0; new = (const u8 *)&gentry; @@ -4039,7 +3985,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, !((sp->role.word ^ vcpu->arch.mmu.base_role.word) & mask.word) && rmap_can_add(vcpu)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); - if (!remote_flush && need_remote_flush(entry, *spte)) + if (need_remote_flush(entry, *spte)) remote_flush = true; ++spte; } @@ -4198,26 +4144,36 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu) void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) { - struct kvm_mmu_page *sp; - bool flush = false; + struct kvm_memory_slot *memslot; + gfn_t last_gfn; + int i; - list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) { - int i; - u64 *pt; + memslot = id_to_memslot(kvm->memslots, slot); + last_gfn = memslot->base_gfn + memslot->npages - 1; - if (!test_bit(slot, sp->slot_bitmap)) - continue; + spin_lock(&kvm->mmu_lock); - pt = sp->spt; - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - if (!is_shadow_present_pte(pt[i]) || - !is_last_spte(pt[i], sp->role.level)) - continue; + for (i = PT_PAGE_TABLE_LEVEL; + i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + unsigned long *rmapp; + unsigned long last_index, index; - spte_write_protect(kvm, &pt[i], &flush, false); + rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; + last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); + + for (index = 0; index <= last_index; ++index, ++rmapp) { + if (*rmapp) + __rmap_write_protect(kvm, rmapp, false); + + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_flush_remote_tlbs(kvm); + cond_resched_lock(&kvm->mmu_lock); + } } } + kvm_flush_remote_tlbs(kvm); + spin_unlock(&kvm->mmu_lock); } void kvm_mmu_zap_all(struct kvm *kvm) diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index cd6e983..b8f6172 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -195,12 +195,6 @@ DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page, TP_ARGS(sp) ); -DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_delay_free_pages, - TP_PROTO(struct kvm_mmu_page *sp), - - TP_ARGS(sp) -); - TRACE_EVENT( mark_mmio_spte, TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access), diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 891eb6d..105dd5b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -151,7 +151,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, pt_element_t pte; pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; - unsigned index, pt_access, pte_access, accessed_dirty, shift; + unsigned index, pt_access, pte_access, accessed_dirty; gpa_t pte_gpa; int offset; const int write_fault = access & PFERR_WRITE_MASK; @@ -249,16 +249,12 @@ retry_walk: if (!write_fault) protect_clean_gpte(&pte_access, pte); - - /* - * On a write fault, fold the dirty bit into accessed_dirty by shifting it one - * place right. - * - * On a read fault, do nothing. - */ - shift = write_fault >> ilog2(PFERR_WRITE_MASK); - shift *= PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT; - accessed_dirty &= pte >> shift; + else + /* + * On a write fault, fold the dirty bit into accessed_dirty by + * shifting it one place right. + */ + accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); @@ -330,8 +326,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * we call mmu_set_spte() with host_writable = true because * pte_prefetch_gfn_to_pfn always gets a writable pfn. */ - mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0, - NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true); + mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL, + gfn, pfn, true, true); return true; } @@ -405,7 +401,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, */ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, - int user_fault, int write_fault, int hlevel, + int write_fault, int hlevel, pfn_t pfn, bool map_writable, bool prefault) { struct kvm_mmu_page *sp = NULL; @@ -413,9 +409,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, unsigned direct_access, access = gw->pt_access; int top_level, emulate = 0; - if (!is_present_gpte(gw->ptes[gw->level - 1])) - return 0; - direct_access = gw->pte_access; top_level = vcpu->arch.mmu.root_level; @@ -477,9 +470,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, } clear_sp_write_flooding_count(it.sptep); - mmu_set_spte(vcpu, it.sptep, access, gw->pte_access, - user_fault, write_fault, &emulate, it.level, - gw->gfn, pfn, prefault, map_writable); + mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate, + it.level, gw->gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); return emulate; @@ -491,6 +483,46 @@ out_gpte_changed: return 0; } + /* + * To see whether the mapped gfn can write its page table in the current + * mapping. + * + * It is the helper function of FNAME(page_fault). When guest uses large page + * size to map the writable gfn which is used as current page table, we should + * force kvm to use small page size to map it because new shadow page will be + * created when kvm establishes shadow page table that stop kvm using large + * page size. Do it early can avoid unnecessary #PF and emulation. + * + * @write_fault_to_shadow_pgtable will return true if the fault gfn is + * currently used as its page table. + * + * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok + * since the PDPT is always shadowed, that means, we can not use large page + * size to map the gfn which is used as PDPT. + */ +static bool +FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, + struct guest_walker *walker, int user_fault, + bool *write_fault_to_shadow_pgtable) +{ + int level; + gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1); + bool self_changed = false; + + if (!(walker->pte_access & ACC_WRITE_MASK || + (!is_write_protection(vcpu) && !user_fault))) + return false; + + for (level = walker->level; level <= walker->max_level; level++) { + gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1]; + + self_changed |= !(gfn & mask); + *write_fault_to_shadow_pgtable |= !gfn; + } + + return self_changed; +} + /* * Page fault handler. There are several causes for a page fault: * - there is no shadow pte for the guest pte @@ -516,7 +548,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int level = PT_PAGE_TABLE_LEVEL; int force_pt_level; unsigned long mmu_seq; - bool map_writable; + bool map_writable, is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -544,8 +576,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, return 0; } + vcpu->arch.write_fault_to_shadow_pgtable = false; + + is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, + &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); + if (walker.level >= PT_DIRECTORY_LEVEL) - force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn); + force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn) + || is_self_change_mapping; else force_pt_level = 1; if (!force_pt_level) { @@ -564,6 +602,26 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, walker.gfn, pfn, walker.pte_access, &r)) return r; + /* + * Do not change pte_access if the pfn is a mmio page, otherwise + * we will cache the incorrect access into mmio spte. + */ + if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) && + !is_write_protection(vcpu) && !user_fault && + !is_noslot_pfn(pfn)) { + walker.pte_access |= ACC_WRITE_MASK; + walker.pte_access &= ~ACC_USER_MASK; + + /* + * If we converted a user page to a kernel page, + * so that the kernel can write to it when cr0.wp=0, + * then we should prevent the kernel from executing it + * if SMEP is enabled. + */ + if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) + walker.pte_access &= ~ACC_EXEC_MASK; + } + spin_lock(&vcpu->kvm->mmu_lock); if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) goto out_unlock; @@ -572,7 +630,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, kvm_mmu_free_some_pages(vcpu); if (!force_pt_level) transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); - r = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, + r = FNAME(fetch)(vcpu, addr, &walker, write_fault, level, pfn, map_writable, prefault); ++vcpu->stat.pf_fixed; kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); @@ -747,7 +805,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE; - set_spte(vcpu, &sp->spt[i], pte_access, 0, 0, + set_spte(vcpu, &sp->spt[i], pte_access, PT_PAGE_TABLE_LEVEL, gfn, spte_to_pfn(sp->spt[i]), true, false, host_writable); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d29d3cd..e1b1ce2 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3571,6 +3571,26 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) set_cr_intercept(svm, INTERCEPT_CR8_WRITE); } +static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) +{ + return; +} + +static int svm_vm_has_apicv(struct kvm *kvm) +{ + return 0; +} + +static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + return; +} + +static void svm_hwapic_isr_update(struct kvm *kvm, int isr) +{ + return; +} + static int svm_nmi_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4290,6 +4310,10 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, + .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, + .vm_has_apicv = svm_vm_has_apicv, + .load_eoi_exitmap = svm_load_eoi_exitmap, + .hwapic_isr_update = svm_hwapic_isr_update, .set_tss_addr = svm_set_tss_addr, .get_tdp_level = get_npt_level, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 9120ae1..6667042 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -84,6 +84,8 @@ module_param(vmm_exclusive, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); +static bool __read_mostly enable_apicv_reg_vid; + /* * 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 @@ -92,12 +94,8 @@ module_param(fasteoi, bool, S_IRUGO); static bool __read_mostly nested = 0; module_param(nested, bool, S_IRUGO); -#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \ - (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD) -#define KVM_GUEST_CR0_MASK \ - (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE) -#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \ - (X86_CR0_WP | X86_CR0_NE) +#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD) +#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE) #define KVM_VM_CR0_ALWAYS_ON \ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE) #define KVM_CR4_GUEST_OWNED_BITS \ @@ -624,6 +622,8 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +static bool guest_state_valid(struct kvm_vcpu *vcpu); +static u32 vmx_segment_access_rights(struct kvm_segment *var); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -638,6 +638,8 @@ static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; +static unsigned long *vmx_msr_bitmap_legacy_x2apic; +static unsigned long *vmx_msr_bitmap_longmode_x2apic; static bool cpu_has_load_ia32_efer; static bool cpu_has_load_perf_global_ctrl; @@ -762,6 +764,24 @@ static inline bool cpu_has_vmx_virtualize_apic_accesses(void) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; } +static inline bool cpu_has_vmx_virtualize_x2apic_mode(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; +} + +static inline bool cpu_has_vmx_apic_register_virt(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_APIC_REGISTER_VIRT; +} + +static inline bool cpu_has_vmx_virtual_intr_delivery(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; +} + static inline bool cpu_has_vmx_flexpriority(void) { return cpu_has_vmx_tpr_shadow() && @@ -1694,7 +1714,6 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { __set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail); - __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); to_vmx(vcpu)->rflags = rflags; if (to_vmx(vcpu)->rmode.vm86_active) { to_vmx(vcpu)->rmode.save_rflags = rflags; @@ -1820,6 +1839,25 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) vmx->guest_msrs[from] = tmp; } +static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) +{ + unsigned long *msr_bitmap; + + if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) { + if (is_long_mode(vcpu)) + msr_bitmap = vmx_msr_bitmap_longmode_x2apic; + else + msr_bitmap = vmx_msr_bitmap_legacy_x2apic; + } else { + if (is_long_mode(vcpu)) + msr_bitmap = vmx_msr_bitmap_longmode; + else + msr_bitmap = vmx_msr_bitmap_legacy; + } + + vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); +} + /* * Set up the vmcs to automatically save and restore system * msrs. Don't touch the 64-bit msrs if the guest is in legacy @@ -1828,7 +1866,6 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) static void setup_msrs(struct vcpu_vmx *vmx) { int save_nmsrs, index; - unsigned long *msr_bitmap; save_nmsrs = 0; #ifdef CONFIG_X86_64 @@ -1860,14 +1897,8 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx->save_nmsrs = save_nmsrs; - if (cpu_has_vmx_msr_bitmap()) { - if (is_long_mode(&vmx->vcpu)) - msr_bitmap = vmx_msr_bitmap_longmode; - else - msr_bitmap = vmx_msr_bitmap_legacy; - - vmcs_write64(MSR_BITMAP, __pa(msr_bitmap)); - } + if (cpu_has_vmx_msr_bitmap()) + vmx_set_msr_bitmap(&vmx->vcpu); } /* @@ -2533,13 +2564,16 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { min2 = 0; opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_ENABLE_EPT | SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_PAUSE_LOOP_EXITING | SECONDARY_EXEC_RDTSCP | - SECONDARY_EXEC_ENABLE_INVPCID; + SECONDARY_EXEC_ENABLE_INVPCID | + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2550,6 +2584,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; #endif + + if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) + _cpu_based_2nd_exec_control &= ~( + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); + if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { /* CR3 accesses and invlpg don't need to cause VM Exits when EPT enabled */ @@ -2747,6 +2788,15 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ple()) ple_gap = 0; + if (!cpu_has_vmx_apic_register_virt() || + !cpu_has_vmx_virtual_intr_delivery()) + enable_apicv_reg_vid = 0; + + if (enable_apicv_reg_vid) + kvm_x86_ops->update_cr8_intercept = NULL; + else + kvm_x86_ops->hwapic_irr_update = NULL; + if (nested) nested_vmx_setup_ctls_msrs(); @@ -2758,18 +2808,28 @@ static __exit void hardware_unsetup(void) free_kvm_area(); } -static void fix_pmode_dataseg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save) +static bool emulation_required(struct kvm_vcpu *vcpu) { - const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - struct kvm_segment tmp = *save; + return emulate_invalid_guest_state && !guest_state_valid(vcpu); +} - if (!(vmcs_readl(sf->base) == tmp.base && tmp.s)) { - tmp.base = vmcs_readl(sf->base); - tmp.selector = vmcs_read16(sf->selector); - tmp.dpl = tmp.selector & SELECTOR_RPL_MASK; - tmp.s = 1; +static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, + struct kvm_segment *save) +{ + if (!emulate_invalid_guest_state) { + /* + * CS and SS RPL should be equal during guest entry according + * to VMX spec, but in reality it is not always so. Since vcpu + * is in the middle of the transition from real mode to + * protected mode it is safe to assume that RPL 0 is a good + * default value. + */ + if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) + save->selector &= ~SELECTOR_RPL_MASK; + save->dpl = save->selector & SELECTOR_RPL_MASK; + save->s = 1; } - vmx_set_segment(vcpu, &tmp, seg); + vmx_set_segment(vcpu, save, seg); } static void enter_pmode(struct kvm_vcpu *vcpu) @@ -2777,7 +2837,17 @@ static void enter_pmode(struct kvm_vcpu *vcpu) unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->emulation_required = 1; + /* + * Update real mode segment cache. It may be not up-to-date if sement + * register was written while vcpu was in a guest mode. + */ + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); + vmx->rmode.vm86_active = 0; vmx_segment_cache_clear(vmx); @@ -2794,22 +2864,16 @@ static void enter_pmode(struct kvm_vcpu *vcpu) update_exception_bitmap(vcpu); - if (emulate_invalid_guest_state) - return; - - fix_pmode_dataseg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); - fix_pmode_dataseg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); - fix_pmode_dataseg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); - fix_pmode_dataseg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); - - vmx_segment_cache_clear(vmx); + fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); + fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); + fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); + fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); + fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); + fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); - vmcs_write16(GUEST_SS_SELECTOR, 0); - vmcs_write32(GUEST_SS_AR_BYTES, 0x93); - - vmcs_write16(GUEST_CS_SELECTOR, - vmcs_read16(GUEST_CS_SELECTOR) & ~SELECTOR_RPL_MASK); - vmcs_write32(GUEST_CS_AR_BYTES, 0x9b); + /* CPL is always 0 when CPU enters protected mode */ + __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + vmx->cpl = 0; } static gva_t rmode_tss_base(struct kvm *kvm) @@ -2831,36 +2895,51 @@ static gva_t rmode_tss_base(struct kvm *kvm) static void fix_rmode_seg(int seg, struct kvm_segment *save) { const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - vmcs_write16(sf->selector, save->base >> 4); - vmcs_write32(sf->base, save->base & 0xffff0); - vmcs_write32(sf->limit, 0xffff); - vmcs_write32(sf->ar_bytes, 0xf3); - if (save->base & 0xf) - printk_once(KERN_WARNING "kvm: segment base is not paragraph" - " aligned when entering protected mode (seg=%d)", - seg); + struct kvm_segment var = *save; + + var.dpl = 0x3; + if (seg == VCPU_SREG_CS) + var.type = 0x3; + + if (!emulate_invalid_guest_state) { + var.selector = var.base >> 4; + var.base = var.base & 0xffff0; + var.limit = 0xffff; + var.g = 0; + var.db = 0; + var.present = 1; + var.s = 1; + var.l = 0; + var.unusable = 0; + var.type = 0x3; + var.avl = 0; + if (save->base & 0xf) + printk_once(KERN_WARNING "kvm: segment base is not " + "paragraph aligned when entering " + "protected mode (seg=%d)", seg); + } + + vmcs_write16(sf->selector, var.selector); + vmcs_write32(sf->base, var.base); + vmcs_write32(sf->limit, var.limit); + vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } static void enter_rmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_segment var; - - if (enable_unrestricted_guest) - return; vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); + vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); - vmx->emulation_required = 1; vmx->rmode.vm86_active = 1; - /* * Very old userspace does not call KVM_SET_TSS_ADDR before entering * vcpu. Call it here with phys address pointing 16M below 4G. @@ -2888,28 +2967,13 @@ static void enter_rmode(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); update_exception_bitmap(vcpu); - if (emulate_invalid_guest_state) - goto continue_rmode; - - vmx_get_segment(vcpu, &var, VCPU_SREG_SS); - vmx_set_segment(vcpu, &var, VCPU_SREG_SS); - - vmx_get_segment(vcpu, &var, VCPU_SREG_CS); - vmx_set_segment(vcpu, &var, VCPU_SREG_CS); - - vmx_get_segment(vcpu, &var, VCPU_SREG_ES); - vmx_set_segment(vcpu, &var, VCPU_SREG_ES); - - vmx_get_segment(vcpu, &var, VCPU_SREG_DS); - vmx_set_segment(vcpu, &var, VCPU_SREG_DS); + fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); + fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); + fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); + fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); + fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); + fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); - vmx_get_segment(vcpu, &var, VCPU_SREG_GS); - vmx_set_segment(vcpu, &var, VCPU_SREG_GS); - - vmx_get_segment(vcpu, &var, VCPU_SREG_FS); - vmx_set_segment(vcpu, &var, VCPU_SREG_FS); - -continue_rmode: kvm_mmu_reset_context(vcpu); } @@ -3068,17 +3132,18 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long hw_cr0; + hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK); if (enable_unrestricted_guest) - hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST) - | KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; - else - hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON; + hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; + else { + hw_cr0 |= KVM_VM_CR0_ALWAYS_ON; - if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) - enter_pmode(vcpu); + if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) + enter_pmode(vcpu); - if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE)) - enter_rmode(vcpu); + if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE)) + enter_rmode(vcpu); + } #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { @@ -3098,7 +3163,9 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; - __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + + /* depends on vcpu->arch.cr0 to be set to a new value */ + vmx->emulation_required = emulation_required(vcpu); } static u64 construct_eptp(unsigned long root_hpa) @@ -3155,6 +3222,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; + /* + * SMEP is disabled if CPU is in non-paging mode in + * hardware. However KVM always uses paging mode to + * emulate guest non-paging mode with TDP. + * To emulate this behavior, SMEP needs to be manually + * disabled when guest switches to non-paging mode. + */ + hw_cr4 &= ~X86_CR4_SMEP; } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } @@ -3171,10 +3246,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); u32 ar; - if (vmx->rmode.vm86_active - && (seg == VCPU_SREG_TR || seg == VCPU_SREG_ES - || seg == VCPU_SREG_DS || seg == VCPU_SREG_FS - || seg == VCPU_SREG_GS)) { + if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { *var = vmx->rmode.segs[seg]; if (seg == VCPU_SREG_TR || var->selector == vmx_read_guest_seg_selector(vmx, seg)) @@ -3187,8 +3259,6 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->limit = vmx_read_guest_seg_limit(vmx, seg); var->selector = vmx_read_guest_seg_selector(vmx, seg); ar = vmx_read_guest_seg_ar(vmx, seg); - if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state) - ar = 0; var->type = ar & 15; var->s = (ar >> 4) & 1; var->dpl = (ar >> 5) & 3; @@ -3211,8 +3281,10 @@ static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) return vmx_read_guest_seg_base(to_vmx(vcpu), seg); } -static int __vmx_get_cpl(struct kvm_vcpu *vcpu) +static int vmx_get_cpl(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + if (!is_protmode(vcpu)) return 0; @@ -3220,24 +3292,9 @@ static int __vmx_get_cpl(struct kvm_vcpu *vcpu) && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */ return 3; - return vmx_read_guest_seg_selector(to_vmx(vcpu), VCPU_SREG_CS) & 3; -} - -static int vmx_get_cpl(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - /* - * If we enter real mode with cs.sel & 3 != 0, the normal CPL calculations - * fail; use the cache instead. - */ - if (unlikely(vmx->emulation_required && emulate_invalid_guest_state)) { - return vmx->cpl; - } - if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - vmx->cpl = __vmx_get_cpl(vcpu); + vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3; } return vmx->cpl; @@ -3269,28 +3326,23 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - u32 ar; vmx_segment_cache_clear(vmx); + if (seg == VCPU_SREG_CS) + __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) { - vmcs_write16(sf->selector, var->selector); - vmx->rmode.segs[VCPU_SREG_TR] = *var; - return; + if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { + vmx->rmode.segs[seg] = *var; + if (seg == VCPU_SREG_TR) + vmcs_write16(sf->selector, var->selector); + else if (var->s) + fix_rmode_seg(seg, &vmx->rmode.segs[seg]); + goto out; } + vmcs_writel(sf->base, var->base); vmcs_write32(sf->limit, var->limit); vmcs_write16(sf->selector, var->selector); - if (vmx->rmode.vm86_active && var->s) { - vmx->rmode.segs[seg] = *var; - /* - * Hack real-mode segments into vm86 compatibility. - */ - if (var->base == 0xffff0000 && var->selector == 0xf000) - vmcs_writel(sf->base, 0xf0000); - ar = 0xf3; - } else - ar = vmx_segment_access_rights(var); /* * Fix the "Accessed" bit in AR field of segment registers for older @@ -3304,42 +3356,12 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, * kvm hack. */ if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR)) - ar |= 0x1; /* Accessed */ + var->type |= 0x1; /* Accessed */ - vmcs_write32(sf->ar_bytes, ar); - __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); - /* - * Fix segments for real mode guest in hosts that don't have - * "unrestricted_mode" or it was disabled. - * This is done to allow migration of the guests from hosts with - * unrestricted guest like Westmere to older host that don't have - * unrestricted guest like Nehelem. - */ - if (vmx->rmode.vm86_active) { - switch (seg) { - case VCPU_SREG_CS: - vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); - vmcs_write32(GUEST_CS_LIMIT, 0xffff); - if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) - vmcs_writel(GUEST_CS_BASE, 0xf0000); - vmcs_write16(GUEST_CS_SELECTOR, - vmcs_readl(GUEST_CS_BASE) >> 4); - break; - case VCPU_SREG_ES: - case VCPU_SREG_DS: - case VCPU_SREG_GS: - case VCPU_SREG_FS: - fix_rmode_seg(seg, &vmx->rmode.segs[seg]); - break; - case VCPU_SREG_SS: - vmcs_write16(GUEST_SS_SELECTOR, - vmcs_readl(GUEST_SS_BASE) >> 4); - vmcs_write32(GUEST_SS_LIMIT, 0xffff); - vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); - break; - } - } +out: + vmx->emulation_required |= emulation_required(vcpu); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -3380,13 +3402,16 @@ static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg) u32 ar; vmx_get_segment(vcpu, &var, seg); + var.dpl = 0x3; + if (seg == VCPU_SREG_CS) + var.type = 0x3; ar = vmx_segment_access_rights(&var); if (var.base != (var.selector << 4)) return false; - if (var.limit < 0xffff) + if (var.limit != 0xffff) return false; - if (((ar | (3 << AR_DPL_SHIFT)) & ~(AR_G_MASK | AR_DB_MASK)) != 0xf3) + if (ar != 0xf3) return false; return true; @@ -3521,6 +3546,9 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) */ static bool guest_state_valid(struct kvm_vcpu *vcpu) { + if (enable_unrestricted_guest) + return true; + /* real mode guest state checks */ if (!is_protmode(vcpu)) { if (!rmode_segment_valid(vcpu, VCPU_SREG_CS)) @@ -3644,12 +3672,9 @@ static void seg_setup(int seg) vmcs_write16(sf->selector, 0); vmcs_writel(sf->base, 0); vmcs_write32(sf->limit, 0xffff); - if (enable_unrestricted_guest) { - ar = 0x93; - if (seg == VCPU_SREG_CS) - ar |= 0x08; /* code segment */ - } else - ar = 0xf3; + ar = 0x93; + if (seg == VCPU_SREG_CS) + ar |= 0x08; /* code segment */ vmcs_write32(sf->ar_bytes, ar); } @@ -3667,7 +3692,7 @@ static int alloc_apic_access_page(struct kvm *kvm) kvm_userspace_mem.flags = 0; kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false); if (r) goto out; @@ -3697,7 +3722,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) kvm_userspace_mem.guest_phys_addr = kvm->arch.ept_identity_map_addr; kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, 0); + r = __kvm_set_memory_region(kvm, &kvm_userspace_mem, false); if (r) goto out; @@ -3739,7 +3764,10 @@ static void free_vpid(struct vcpu_vmx *vmx) spin_unlock(&vmx_vpid_lock); } -static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr) +#define MSR_TYPE_R 1 +#define MSR_TYPE_W 2 +static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) { int f = sizeof(unsigned long); @@ -3752,20 +3780,93 @@ static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr) * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. */ if (msr <= 0x1fff) { - __clear_bit(msr, msr_bitmap + 0x000 / f); /* read-low */ - __clear_bit(msr, msr_bitmap + 0x800 / f); /* write-low */ + if (type & MSR_TYPE_R) + /* read-low */ + __clear_bit(msr, msr_bitmap + 0x000 / f); + + if (type & MSR_TYPE_W) + /* write-low */ + __clear_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { msr &= 0x1fff; - __clear_bit(msr, msr_bitmap + 0x400 / f); /* read-high */ - __clear_bit(msr, msr_bitmap + 0xc00 / f); /* write-high */ + if (type & MSR_TYPE_R) + /* read-high */ + __clear_bit(msr, msr_bitmap + 0x400 / f); + + if (type & MSR_TYPE_W) + /* write-high */ + __clear_bit(msr, msr_bitmap + 0xc00 / f); + + } +} + +static void __vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type) +{ + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return; + + /* + * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals + * have the write-low and read-high bitmap offsets the wrong way round. + * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. + */ + if (msr <= 0x1fff) { + if (type & MSR_TYPE_R) + /* read-low */ + __set_bit(msr, msr_bitmap + 0x000 / f); + + if (type & MSR_TYPE_W) + /* write-low */ + __set_bit(msr, msr_bitmap + 0x800 / f); + + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + if (type & MSR_TYPE_R) + /* read-high */ + __set_bit(msr, msr_bitmap + 0x400 / f); + + if (type & MSR_TYPE_W) + /* write-high */ + __set_bit(msr, msr_bitmap + 0xc00 / f); + } } static void vmx_disable_intercept_for_msr(u32 msr, bool longmode_only) { if (!longmode_only) - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, msr); - __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, msr); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy, + msr, MSR_TYPE_R | MSR_TYPE_W); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode, + msr, MSR_TYPE_R | MSR_TYPE_W); +} + +static void vmx_enable_intercept_msr_read_x2apic(u32 msr) +{ + __vmx_enable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, + msr, MSR_TYPE_R); + __vmx_enable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, + msr, MSR_TYPE_R); +} + +static void vmx_disable_intercept_msr_read_x2apic(u32 msr) +{ + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, + msr, MSR_TYPE_R); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, + msr, MSR_TYPE_R); +} + +static void vmx_disable_intercept_msr_write_x2apic(u32 msr) +{ + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_legacy_x2apic, + msr, MSR_TYPE_W); + __vmx_disable_intercept_for_msr(vmx_msr_bitmap_longmode_x2apic, + msr, MSR_TYPE_W); } /* @@ -3844,6 +3945,11 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) return exec_control; } +static int vmx_vm_has_apicv(struct kvm *kvm) +{ + return enable_apicv_reg_vid && irqchip_in_kernel(kvm); +} + static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; @@ -3861,6 +3967,10 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; + if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); + exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; return exec_control; } @@ -3905,6 +4015,15 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmx_secondary_exec_control(vmx)); } + if (enable_apicv_reg_vid) { + vmcs_write64(EOI_EXIT_BITMAP0, 0); + vmcs_write64(EOI_EXIT_BITMAP1, 0); + vmcs_write64(EOI_EXIT_BITMAP2, 0); + vmcs_write64(EOI_EXIT_BITMAP3, 0); + + vmcs_write16(GUEST_INTR_STATUS, 0); + } + if (ple_gap) { vmcs_write32(PLE_GAP, ple_gap); vmcs_write32(PLE_WINDOW, ple_window); @@ -3990,14 +4109,9 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx_segment_cache_clear(vmx); seg_setup(VCPU_SREG_CS); - /* - * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode - * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh. - */ - if (kvm_vcpu_is_bsp(&vmx->vcpu)) { + if (kvm_vcpu_is_bsp(&vmx->vcpu)) vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - vmcs_writel(GUEST_CS_BASE, 0x000f0000); - } else { + else { vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8); vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12); } @@ -4073,9 +4187,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) ret = 0; - /* HACK: Don't enable emulation on guest boot/reset */ - vmx->emulation_required = 0; - return ret; } @@ -4251,7 +4362,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) .flags = 0, }; - ret = kvm_set_memory_region(kvm, &tss_mem, 0); + ret = kvm_set_memory_region(kvm, &tss_mem, false); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -4261,28 +4372,9 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static int handle_rmode_exception(struct kvm_vcpu *vcpu, - int vec, u32 err_code) +static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) { - /* - * Instruction with address size override prefix opcode 0x67 - * Cause the #SS fault with 0 error code in VM86 mode. - */ - if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) - if (emulate_instruction(vcpu, 0) == EMULATE_DONE) - return 1; - /* - * Forward all other exceptions that are valid in real mode. - * FIXME: Breaks guest debugging in real mode, needs to be fixed with - * the required debugging infrastructure rework. - */ switch (vec) { - case DB_VECTOR: - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - return 0; - kvm_queue_exception(vcpu, vec); - return 1; case BP_VECTOR: /* * Update instruction length as we may reinject the exception @@ -4291,7 +4383,12 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, to_vmx(vcpu)->vcpu.arch.event_exit_inst_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) - return 0; + return false; + /* fall through */ + case DB_VECTOR: + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + return false; /* fall through */ case DE_VECTOR: case OF_VECTOR: @@ -4301,10 +4398,37 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, case SS_VECTOR: case GP_VECTOR: case MF_VECTOR: - kvm_queue_exception(vcpu, vec); - return 1; + return true; + break; } - return 0; + return false; +} + +static int handle_rmode_exception(struct kvm_vcpu *vcpu, + int vec, u32 err_code) +{ + /* + * Instruction with address size override prefix opcode 0x67 + * Cause the #SS fault with 0 error code in VM86 mode. + */ + if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { + if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { + if (vcpu->arch.halt_request) { + vcpu->arch.halt_request = 0; + return kvm_emulate_halt(vcpu); + } + return 1; + } + return 0; + } + + /* + * Forward all other exceptions that are valid in real mode. + * FIXME: Breaks guest debugging in real mode, needs to be fixed with + * the required debugging infrastructure rework. + */ + kvm_queue_exception(vcpu, vec); + return 1; } /* @@ -4392,17 +4516,11 @@ static int handle_exception(struct kvm_vcpu *vcpu) return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0); } - if (vmx->rmode.vm86_active && - handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK, - error_code)) { - if (vcpu->arch.halt_request) { - vcpu->arch.halt_request = 0; - return kvm_emulate_halt(vcpu); - } - return 1; - } - ex_no = intr_info & INTR_INFO_VECTOR_MASK; + + if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no)) + return handle_rmode_exception(vcpu, ex_no, error_code); + switch (ex_no) { case DB_VECTOR: dr6 = vmcs_readl(EXIT_QUALIFICATION); @@ -4820,6 +4938,26 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return emulate_instruction(vcpu, 0) == EMULATE_DONE; } +static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) +{ + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + int vector = exit_qualification & 0xff; + + /* EOI-induced VM exit is trap-like and thus no need to adjust IP */ + kvm_apic_set_eoi_accelerated(vcpu, vector); + return 1; +} + +static int handle_apic_write(struct kvm_vcpu *vcpu) +{ + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + u32 offset = exit_qualification & 0xfff; + + /* APIC-write VM exit is trap-like and thus no need to adjust IP */ + kvm_apic_write_nodecode(vcpu, offset); + return 1; +} + static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -5065,7 +5203,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) schedule(); } - vmx->emulation_required = !guest_state_valid(vcpu); + vmx->emulation_required = emulation_required(vcpu); out: return ret; } @@ -5754,6 +5892,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_VMON] = handle_vmon, [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, [EXIT_REASON_APIC_ACCESS] = handle_apic_access, + [EXIT_REASON_APIC_WRITE] = handle_apic_write, + [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced, [EXIT_REASON_WBINVD] = handle_wbinvd, [EXIT_REASON_XSETBV] = handle_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, @@ -5780,7 +5920,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX]; gpa_t bitmap; - if (!nested_cpu_has(get_vmcs12(vcpu), CPU_BASED_USE_MSR_BITMAPS)) + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return 1; /* @@ -6008,7 +6148,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 vectoring_info = vmx->idt_vectoring_info; /* If guest state is invalid, start emulating */ - if (vmx->emulation_required && emulate_invalid_guest_state) + if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); /* @@ -6103,6 +6243,85 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) vmcs_write32(TPR_THRESHOLD, irr); } +static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) +{ + u32 sec_exec_control; + + /* + * There is not point to enable virtualize x2apic without enable + * apicv + */ + if (!cpu_has_vmx_virtualize_x2apic_mode() || + !vmx_vm_has_apicv(vcpu->kvm)) + return; + + if (!vm_need_tpr_shadow(vcpu->kvm)) + return; + + sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + if (set) { + sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + } else { + sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + } + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); + + vmx_set_msr_bitmap(vcpu); +} + +static void vmx_hwapic_isr_update(struct kvm *kvm, int isr) +{ + u16 status; + u8 old; + + if (!vmx_vm_has_apicv(kvm)) + return; + + if (isr == -1) + isr = 0; + + status = vmcs_read16(GUEST_INTR_STATUS); + old = status >> 8; + if (isr != old) { + status &= 0xff; + status |= isr << 8; + vmcs_write16(GUEST_INTR_STATUS, status); + } +} + +static void vmx_set_rvi(int vector) +{ + u16 status; + u8 old; + + status = vmcs_read16(GUEST_INTR_STATUS); + old = (u8)status & 0xff; + if ((u8)vector != old) { + status &= ~0xff; + status |= (u8)vector; + vmcs_write16(GUEST_INTR_STATUS, status); + } +} + +static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) +{ + if (max_irr == -1) + return; + + vmx_set_rvi(max_irr); +} + +static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); + vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); + vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); + vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); +} + static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -6291,7 +6510,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) /* Don't enter VMX if guest state is invalid, let the exit handler start emulation until we arrive back to a valid state */ - if (vmx->emulation_required && emulate_invalid_guest_state) + if (vmx->emulation_required) return; if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) @@ -7366,6 +7585,11 @@ static struct kvm_x86_ops vmx_x86_ops = { .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, + .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, + .vm_has_apicv = vmx_vm_has_apicv, + .load_eoi_exitmap = vmx_load_eoi_exitmap, + .hwapic_irr_update = vmx_hwapic_irr_update, + .hwapic_isr_update = vmx_hwapic_isr_update, .set_tss_addr = vmx_set_tss_addr, .get_tdp_level = get_ept_level, @@ -7398,7 +7622,7 @@ static struct kvm_x86_ops vmx_x86_ops = { static int __init vmx_init(void) { - int r, i; + int r, i, msr; rdmsrl_safe(MSR_EFER, &host_efer); @@ -7419,11 +7643,19 @@ static int __init vmx_init(void) if (!vmx_msr_bitmap_legacy) goto out1; + vmx_msr_bitmap_legacy_x2apic = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_msr_bitmap_legacy_x2apic) + goto out2; vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_msr_bitmap_longmode) - goto out2; + goto out3; + vmx_msr_bitmap_longmode_x2apic = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx_msr_bitmap_longmode_x2apic) + goto out4; /* * Allow direct access to the PC debug port (it is often used for I/O @@ -7455,6 +7687,28 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); + memcpy(vmx_msr_bitmap_legacy_x2apic, + vmx_msr_bitmap_legacy, PAGE_SIZE); + memcpy(vmx_msr_bitmap_longmode_x2apic, + vmx_msr_bitmap_longmode, PAGE_SIZE); + + if (enable_apicv_reg_vid) { + for (msr = 0x800; msr <= 0x8ff; msr++) + vmx_disable_intercept_msr_read_x2apic(msr); + + /* According SDM, in x2apic mode, the whole id reg is used. + * But in KVM, it only use the highest eight bits. Need to + * intercept it */ + vmx_enable_intercept_msr_read_x2apic(0x802); + /* TMCCT */ + vmx_enable_intercept_msr_read_x2apic(0x839); + /* TPR */ + vmx_disable_intercept_msr_write_x2apic(0x808); + /* EOI */ + vmx_disable_intercept_msr_write_x2apic(0x80b); + /* SELF-IPI */ + vmx_disable_intercept_msr_write_x2apic(0x83f); + } if (enable_ept) { kvm_mmu_set_mask_ptes(0ull, @@ -7468,8 +7722,10 @@ static int __init vmx_init(void) return 0; -out3: +out4: free_page((unsigned long)vmx_msr_bitmap_longmode); +out3: + free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); out2: free_page((unsigned long)vmx_msr_bitmap_legacy); out1: @@ -7481,6 +7737,8 @@ out: static void __exit vmx_exit(void) { + free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic); + free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); free_page((unsigned long)vmx_msr_bitmap_legacy); free_page((unsigned long)vmx_msr_bitmap_longmode); free_page((unsigned long)vmx_io_bitmap_b); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3704007..f71500a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -872,8 +872,6 @@ static int set_efer(struct kvm_vcpu *vcpu, u64 efer) kvm_x86_ops->set_efer(vcpu, efer); - vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled; - /* Update reserved bits */ if ((efer ^ old_efer) & EFER_NX) kvm_mmu_reset_context(vcpu); @@ -2522,7 +2520,7 @@ int kvm_dev_ioctl_check_extension(long ext) r = KVM_MAX_VCPUS; break; case KVM_CAP_NR_MEMSLOTS: - r = KVM_MEMORY_SLOTS; + r = KVM_USER_MEM_SLOTS; break; case KVM_CAP_PV_MMU: /* obsolete */ r = 0; @@ -3274,12 +3272,10 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return -EINVAL; mutex_lock(&kvm->slots_lock); - spin_lock(&kvm->mmu_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; - spin_unlock(&kvm->mmu_lock); mutex_unlock(&kvm->slots_lock); return 0; } @@ -3439,7 +3435,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) mutex_lock(&kvm->slots_lock); r = -EINVAL; - if (log->slot >= KVM_MEMORY_SLOTS) + if (log->slot >= KVM_USER_MEM_SLOTS) goto out; memslot = id_to_memslot(kvm->memslots, log->slot); @@ -4495,8 +4491,10 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, kvm_get_segment(emul_to_vcpu(ctxt), &var, seg); *selector = var.selector; - if (var.unusable) + if (var.unusable) { + memset(desc, 0, sizeof(*desc)); return false; + } if (var.g) var.limit >>= 12; @@ -4757,26 +4755,26 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) return r; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva) +static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, + bool write_fault_to_shadow_pgtable) { - gpa_t gpa; + gpa_t gpa = cr2; pfn_t pfn; - if (tdp_enabled) - return false; - - /* - * if emulation was due to access to shadowed page table - * and it failed try to unshadow page and re-enter the - * guest to let CPU execute the instruction. - */ - if (kvm_mmu_unprotect_page_virt(vcpu, gva)) - return true; - - gpa = kvm_mmu_gva_to_gpa_system(vcpu, gva, NULL); + if (!vcpu->arch.mmu.direct_map) { + /* + * Write permission should be allowed since only + * write access need to be emulated. + */ + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); - if (gpa == UNMAPPED_GVA) - return true; /* let cpu generate fault */ + /* + * If the mapping is invalid in guest, let cpu retry + * it to generate fault. + */ + if (gpa == UNMAPPED_GVA) + return true; + } /* * Do not retry the unhandleable instruction if it faults on the @@ -4785,12 +4783,43 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva) * instruction -> ... */ pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); - if (!is_error_noslot_pfn(pfn)) { - kvm_release_pfn_clean(pfn); + + /* + * If the instruction failed on the error pfn, it can not be fixed, + * report the error to userspace. + */ + if (is_error_noslot_pfn(pfn)) + return false; + + kvm_release_pfn_clean(pfn); + + /* The instructions are well-emulated on direct mmu. */ + if (vcpu->arch.mmu.direct_map) { + unsigned int indirect_shadow_pages; + + spin_lock(&vcpu->kvm->mmu_lock); + indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; + spin_unlock(&vcpu->kvm->mmu_lock); + + if (indirect_shadow_pages) + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + return true; } - return false; + /* + * if emulation was due to access to shadowed page table + * and it failed try to unshadow page and re-enter the + * guest to let CPU execute the instruction. + */ + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + + /* + * If the access faults on its page table, it can not + * be fixed by unprotecting shadow page and it should + * be reported to userspace. + */ + return !write_fault_to_shadow_pgtable; } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, @@ -4832,7 +4861,7 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, if (!vcpu->arch.mmu.direct_map) gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); - kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); return true; } @@ -4849,7 +4878,13 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, int r; struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; bool writeback = true; + bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; + /* + * Clear write_fault_to_shadow_pgtable here to ensure it is + * never reused. + */ + vcpu->arch.write_fault_to_shadow_pgtable = false; kvm_clear_exception_queue(vcpu); if (!(emulation_type & EMULTYPE_NO_DECODE)) { @@ -4868,7 +4903,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; - if (reexecute_instruction(vcpu, cr2)) + if (reexecute_instruction(vcpu, cr2, + write_fault_to_spt)) return EMULATE_DONE; if (emulation_type & EMULTYPE_SKIP) return EMULATE_FAIL; @@ -4898,7 +4934,7 @@ restart: return EMULATE_DONE; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2)) + if (reexecute_instruction(vcpu, cr2, write_fault_to_spt)) return EMULATE_DONE; return handle_emulation_failure(vcpu); @@ -5541,7 +5577,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) vcpu->arch.nmi_injected = true; kvm_x86_ops->set_nmi(vcpu); } - } else if (kvm_cpu_has_interrupt(vcpu)) { + } else if (kvm_cpu_has_injectable_intr(vcpu)) { if (kvm_x86_ops->interrupt_allowed(vcpu)) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); @@ -5609,6 +5645,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) #endif } +static void update_eoi_exitmap(struct kvm_vcpu *vcpu) +{ + u64 eoi_exit_bitmap[4]; + + memset(eoi_exit_bitmap, 0, 32); + + kvm_ioapic_calculate_eoi_exitmap(vcpu, eoi_exit_bitmap); + kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; @@ -5662,6 +5708,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_handle_pmu_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) kvm_deliver_pmi(vcpu); + if (kvm_check_request(KVM_REQ_EOIBITMAP, vcpu)) + update_eoi_exitmap(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -5670,10 +5718,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); - else if (kvm_cpu_has_interrupt(vcpu) || req_int_win) + else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) kvm_x86_ops->enable_irq_window(vcpu); if (kvm_lapic_enabled(vcpu)) { + /* + * Update architecture specific hints for APIC + * virtual interrupt delivery. + */ + if (kvm_x86_ops->hwapic_irr_update) + kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_lapic_find_highest_irr(vcpu)); update_cr8_intercept(vcpu); kvm_lapic_sync_to_vapic(vcpu); } @@ -6853,48 +6908,43 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, struct kvm_userspace_memory_region *mem, - int user_alloc) + bool user_alloc) { int npages = memslot->npages; - int map_flags = MAP_PRIVATE | MAP_ANONYMOUS; - /* Prevent internal slot pages from being moved by fork()/COW. */ - if (memslot->id >= KVM_MEMORY_SLOTS) - map_flags = MAP_SHARED | MAP_ANONYMOUS; - - /*To keep backward compatibility with older userspace, - *x86 needs to handle !user_alloc case. + /* + * Only private memory slots need to be mapped here since + * KVM_SET_MEMORY_REGION ioctl is no longer supported. */ - if (!user_alloc) { - if (npages && !old.npages) { - unsigned long userspace_addr; + if ((memslot->id >= KVM_USER_MEM_SLOTS) && npages && !old.npages) { + unsigned long userspace_addr; - userspace_addr = vm_mmap(NULL, 0, - npages * PAGE_SIZE, - PROT_READ | PROT_WRITE, - map_flags, - 0); + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); - if (IS_ERR((void *)userspace_addr)) - return PTR_ERR((void *)userspace_addr); + if (IS_ERR((void *)userspace_addr)) + return PTR_ERR((void *)userspace_addr); - memslot->userspace_addr = userspace_addr; - } + memslot->userspace_addr = userspace_addr; } - return 0; } void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, - int user_alloc) + bool user_alloc) { int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT; - if (!user_alloc && !old.user_alloc && old.npages && !npages) { + if ((mem->slot >= KVM_USER_MEM_SLOTS) && old.npages && !npages) { int ret; ret = vm_munmap(old.userspace_addr, @@ -6908,11 +6958,15 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, if (!kvm->arch.n_requested_mmu_pages) nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); - spin_lock(&kvm->mmu_lock); if (nr_mmu_pages) kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); - kvm_mmu_slot_remove_write_access(kvm, mem->slot); - spin_unlock(&kvm->mmu_lock); + /* + * Write protect all pages for dirty logging. + * Existing largepage mappings are destroyed here and new ones will + * not be created until the end of the logging. + */ + if (npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) + kvm_mmu_slot_remove_write_access(kvm, mem->slot); /* * If memory slot is created, or moved, we need to clear all * mmio sptes. |