diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 1 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 5 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 293 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.c | 31 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.h | 7 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 31 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 345 | ||||
-rw-r--r-- | arch/x86/kvm/mmu_audit.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 41 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 280 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 2 |
13 files changed, 649 insertions, 408 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 1a7fe868f37..a28f338843e 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -36,6 +36,7 @@ config KVM select TASKSTATS select TASK_DELAY_ACCT select PERF_EVENTS + select HAVE_KVM_MSI ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9fed5bedaad..7df1c6d839f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -247,7 +247,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ebx */ const u32 kvm_supported_word9_x86_features = - F(FSGSBASE) | F(BMI1) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS); + F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | + F(BMI2) | F(ERMS) | F(RTM); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -397,7 +398,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case KVM_CPUID_SIGNATURE: { char signature[12] = "KVMKVMKVM\0\0"; u32 *sigptr = (u32 *)signature; - entry->eax = 0; + entry->eax = KVM_CPUID_FEATURES; entry->ebx = sigptr[0]; entry->ecx = sigptr[1]; entry->edx = sigptr[2]; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 83756223f8a..f95d242ee9f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -142,6 +142,10 @@ #define Src2FS (OpFS << Src2Shift) #define Src2GS (OpGS << Src2Shift) #define Src2Mask (OpMask << Src2Shift) +#define Mmx ((u64)1 << 40) /* MMX Vector instruction */ +#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 X2(x...) x, x #define X3(x...) X2(x), x @@ -557,6 +561,29 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector, ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg); } +/* + * x86 defines three classes of vector instructions: explicitly + * aligned, explicitly unaligned, and the rest, which change behaviour + * depending on whether they're AVX encoded or not. + * + * Also included is CMPXCHG16B which is not a vector instruction, yet it is + * subject to the same check. + */ +static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size) +{ + if (likely(size < 16)) + return false; + + if (ctxt->d & Aligned) + return true; + else if (ctxt->d & Unaligned) + return false; + else if (ctxt->d & Avx) + return false; + else + return true; +} + static int __linearize(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, unsigned size, bool write, bool fetch, @@ -621,6 +648,8 @@ static int __linearize(struct x86_emulate_ctxt *ctxt, } if (fetch ? ctxt->mode != X86EMUL_MODE_PROT64 : ctxt->ad_bytes != 8) la &= (u32)-1; + if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) + return emulate_gp(ctxt, 0); *linear = la; return X86EMUL_CONTINUE; bad: @@ -859,6 +888,40 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, ctxt->ops->put_fpu(ctxt); } +static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +{ + ctxt->ops->get_fpu(ctxt); + switch (reg) { + case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; + case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; + case 2: asm("movq %%mm2, %0" : "=m"(*data)); break; + case 3: asm("movq %%mm3, %0" : "=m"(*data)); break; + case 4: asm("movq %%mm4, %0" : "=m"(*data)); break; + case 5: asm("movq %%mm5, %0" : "=m"(*data)); break; + case 6: asm("movq %%mm6, %0" : "=m"(*data)); break; + case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; + default: BUG(); + } + ctxt->ops->put_fpu(ctxt); +} + +static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) +{ + ctxt->ops->get_fpu(ctxt); + switch (reg) { + case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; + case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; + case 2: asm("movq %0, %%mm2" : : "m"(*data)); break; + case 3: asm("movq %0, %%mm3" : : "m"(*data)); break; + case 4: asm("movq %0, %%mm4" : : "m"(*data)); break; + case 5: asm("movq %0, %%mm5" : : "m"(*data)); break; + case 6: asm("movq %0, %%mm6" : : "m"(*data)); break; + case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; + default: BUG(); + } + ctxt->ops->put_fpu(ctxt); +} + static void decode_register_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { @@ -875,6 +938,13 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, read_sse_reg(ctxt, &op->vec_val, reg); return; } + if (ctxt->d & Mmx) { + reg &= 7; + op->type = OP_MM; + op->bytes = 8; + op->addr.mm = reg; + return; + } op->type = OP_REG; if (ctxt->d & ByteOp) { @@ -902,7 +972,6 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_rm = base_reg = (ctxt->rex_prefix & 1) << 3; /* REG.B */ } - ctxt->modrm = insn_fetch(u8, ctxt); ctxt->modrm_mod |= (ctxt->modrm & 0xc0) >> 6; ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3; ctxt->modrm_rm |= (ctxt->modrm & 0x07); @@ -920,6 +989,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm); return rc; } + if (ctxt->d & Mmx) { + op->type = OP_MM; + op->bytes = 8; + op->addr.xmm = ctxt->modrm_rm & 7; + return rc; + } fetch_register_operand(op); return rc; } @@ -1387,6 +1462,9 @@ static int writeback(struct x86_emulate_ctxt *ctxt) case OP_XMM: write_sse_reg(ctxt, &ctxt->dst.vec_val, ctxt->dst.addr.xmm); break; + case OP_MM: + write_mmx_reg(ctxt, &ctxt->dst.mm_val, ctxt->dst.addr.mm); + break; case OP_NONE: /* no writeback */ break; @@ -2790,7 +2868,7 @@ static int em_rdpmc(struct x86_emulate_ctxt *ctxt) static int em_mov(struct x86_emulate_ctxt *ctxt) { - ctxt->dst.val = ctxt->src.val; + memcpy(ctxt->dst.valptr, ctxt->src.valptr, ctxt->op_bytes); return X86EMUL_CONTINUE; } @@ -2870,12 +2948,6 @@ static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg); } -static int em_movdqu(struct x86_emulate_ctxt *ctxt) -{ - memcpy(&ctxt->dst.vec_val, &ctxt->src.vec_val, ctxt->op_bytes); - return X86EMUL_CONTINUE; -} - static int em_invlpg(struct x86_emulate_ctxt *ctxt) { int rc; @@ -3061,35 +3133,13 @@ static int em_btc(struct x86_emulate_ctxt *ctxt) static int em_bsf(struct x86_emulate_ctxt *ctxt) { - u8 zf; - - __asm__ ("bsf %2, %0; setz %1" - : "=r"(ctxt->dst.val), "=q"(zf) - : "r"(ctxt->src.val)); - - ctxt->eflags &= ~X86_EFLAGS_ZF; - if (zf) { - ctxt->eflags |= X86_EFLAGS_ZF; - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - } + emulate_2op_SrcV_nobyte(ctxt, "bsf"); return X86EMUL_CONTINUE; } static int em_bsr(struct x86_emulate_ctxt *ctxt) { - u8 zf; - - __asm__ ("bsr %2, %0; setz %1" - : "=r"(ctxt->dst.val), "=q"(zf) - : "r"(ctxt->src.val)); - - ctxt->eflags &= ~X86_EFLAGS_ZF; - if (zf) { - ctxt->eflags |= X86_EFLAGS_ZF; - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - } + emulate_2op_SrcV_nobyte(ctxt, "bsr"); return X86EMUL_CONTINUE; } @@ -3286,8 +3336,8 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) .check_perm = (_p) } #define N D(0) #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) } -#define G(_f, _g) { .flags = ((_f) | Group), .u.group = (_g) } -#define GD(_f, _g) { .flags = ((_f) | GroupDual), .u.gdual = (_g) } +#define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) } +#define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) } #define I(_f, _e) { .flags = (_f), .u.execute = (_e) } #define II(_f, _e, _i) \ { .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i } @@ -3307,25 +3357,25 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) static struct opcode group7_rm1[] = { - DI(SrcNone | ModRM | Priv, monitor), - DI(SrcNone | ModRM | Priv, mwait), + DI(SrcNone | Priv, monitor), + DI(SrcNone | Priv, mwait), N, N, N, N, N, N, }; static struct opcode group7_rm3[] = { - DIP(SrcNone | ModRM | Prot | Priv, vmrun, check_svme_pa), - II(SrcNone | ModRM | Prot | VendorSpecific, em_vmmcall, vmmcall), - DIP(SrcNone | ModRM | Prot | Priv, vmload, check_svme_pa), - DIP(SrcNone | ModRM | Prot | Priv, vmsave, check_svme_pa), - DIP(SrcNone | ModRM | Prot | Priv, stgi, check_svme), - DIP(SrcNone | ModRM | Prot | Priv, clgi, check_svme), - DIP(SrcNone | ModRM | Prot | Priv, skinit, check_svme), - DIP(SrcNone | ModRM | Prot | Priv, invlpga, check_svme), + DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), + II(SrcNone | Prot | VendorSpecific, em_vmmcall, vmmcall), + DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), + DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), + DIP(SrcNone | Prot | Priv, stgi, check_svme), + DIP(SrcNone | Prot | Priv, clgi, check_svme), + DIP(SrcNone | Prot | Priv, skinit, check_svme), + DIP(SrcNone | Prot | Priv, invlpga, check_svme), }; static struct opcode group7_rm7[] = { N, - DIP(SrcNone | ModRM, rdtscp, check_rdtsc), + DIP(SrcNone, rdtscp, check_rdtsc), N, N, N, N, N, N, }; @@ -3341,81 +3391,86 @@ static struct opcode group1[] = { }; static struct opcode group1A[] = { - I(DstMem | SrcNone | ModRM | Mov | Stack, em_pop), N, N, N, N, N, N, N, + I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N, }; static struct opcode group3[] = { - I(DstMem | SrcImm | ModRM, em_test), - I(DstMem | SrcImm | ModRM, em_test), - I(DstMem | SrcNone | ModRM | Lock, em_not), - I(DstMem | SrcNone | ModRM | Lock, em_neg), - I(SrcMem | ModRM, em_mul_ex), - I(SrcMem | ModRM, em_imul_ex), - I(SrcMem | ModRM, em_div_ex), - I(SrcMem | ModRM, em_idiv_ex), + I(DstMem | SrcImm, em_test), + I(DstMem | SrcImm, em_test), + I(DstMem | SrcNone | Lock, em_not), + I(DstMem | SrcNone | Lock, em_neg), + I(SrcMem, em_mul_ex), + I(SrcMem, em_imul_ex), + I(SrcMem, em_div_ex), + I(SrcMem, em_idiv_ex), }; static struct opcode group4[] = { - I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45), - I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45), + I(ByteOp | DstMem | SrcNone | Lock, em_grp45), + I(ByteOp | DstMem | SrcNone | Lock, em_grp45), N, N, N, N, N, N, }; static struct opcode group5[] = { - I(DstMem | SrcNone | ModRM | Lock, em_grp45), - I(DstMem | SrcNone | ModRM | Lock, em_grp45), - I(SrcMem | ModRM | Stack, em_grp45), - I(SrcMemFAddr | ModRM | ImplicitOps | Stack, em_call_far), - I(SrcMem | ModRM | Stack, em_grp45), - I(SrcMemFAddr | ModRM | ImplicitOps, em_grp45), - I(SrcMem | ModRM | Stack, em_grp45), N, + I(DstMem | SrcNone | Lock, em_grp45), + I(DstMem | SrcNone | Lock, em_grp45), + I(SrcMem | Stack, em_grp45), + I(SrcMemFAddr | ImplicitOps | Stack, em_call_far), + I(SrcMem | Stack, em_grp45), + I(SrcMemFAddr | ImplicitOps, em_grp45), + I(SrcMem | Stack, em_grp45), N, }; static struct opcode group6[] = { - DI(ModRM | Prot, sldt), - DI(ModRM | Prot, str), - DI(ModRM | Prot | Priv, lldt), - DI(ModRM | Prot | Priv, ltr), + DI(Prot, sldt), + DI(Prot, str), + DI(Prot | Priv, lldt), + DI(Prot | Priv, ltr), N, N, N, N, }; static struct group_dual group7 = { { - DI(ModRM | Mov | DstMem | Priv, sgdt), - DI(ModRM | Mov | DstMem | Priv, sidt), - II(ModRM | SrcMem | Priv, em_lgdt, lgdt), - II(ModRM | SrcMem | Priv, em_lidt, lidt), - II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N, - II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw), - II(SrcMem | ModRM | ByteOp | Priv | NoAccess, em_invlpg, invlpg), + DI(Mov | DstMem | Priv, sgdt), + DI(Mov | DstMem | Priv, sidt), + II(SrcMem | Priv, em_lgdt, lgdt), + II(SrcMem | Priv, em_lidt, lidt), + II(SrcNone | DstMem | Mov, em_smsw, smsw), N, + II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), + II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg), }, { - I(SrcNone | ModRM | Priv | VendorSpecific, em_vmcall), + I(SrcNone | Priv | VendorSpecific, em_vmcall), EXT(0, group7_rm1), N, EXT(0, group7_rm3), - II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N, - II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7), + II(SrcNone | DstMem | Mov, em_smsw, smsw), N, + II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), + EXT(0, group7_rm7), } }; static struct opcode group8[] = { N, N, N, N, - I(DstMem | SrcImmByte | ModRM, em_bt), - I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_bts), - I(DstMem | SrcImmByte | ModRM | Lock, em_btr), - I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_btc), + 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), }; static struct group_dual group9 = { { - N, I(DstMem64 | ModRM | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, + N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { N, N, N, N, N, N, N, N, } }; static struct opcode group11[] = { - I(DstMem | SrcImm | ModRM | Mov | PageTable, em_mov), + I(DstMem | SrcImm | Mov | PageTable, em_mov), X7(D(Undefined)), }; static struct gprefix pfx_0f_6f_0f_7f = { - N, N, N, I(Sse, em_movdqu), + I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov), +}; + +static struct gprefix pfx_vmovntpx = { + I(0, em_mov), N, N, N, }; static struct opcode opcode_table[256] = { @@ -3464,10 +3519,10 @@ static struct opcode opcode_table[256] = { /* 0x70 - 0x7F */ X16(D(SrcImmByte)), /* 0x80 - 0x87 */ - G(ByteOp | DstMem | SrcImm | ModRM | Group, group1), - G(DstMem | SrcImm | ModRM | Group, group1), - G(ByteOp | DstMem | SrcImm | ModRM | No64 | Group, group1), - G(DstMem | SrcImmByte | ModRM | Group, group1), + G(ByteOp | DstMem | SrcImm, group1), + G(DstMem | SrcImm, group1), + G(ByteOp | DstMem | SrcImm | No64, group1), + G(DstMem | SrcImmByte, group1), I2bv(DstMem | SrcReg | ModRM, em_test), I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg), /* 0x88 - 0x8F */ @@ -3549,7 +3604,8 @@ static struct opcode twobyte_table[256] = { IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write), IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write), N, N, N, N, - N, N, N, N, N, N, N, N, + N, N, N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx), + N, N, N, N, /* 0x30 - 0x3F */ II(ImplicitOps | Priv, em_wrmsr, wrmsr), IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), @@ -3897,17 +3953,16 @@ done_prefixes: } ctxt->d = opcode.flags; + if (ctxt->d & ModRM) + ctxt->modrm = insn_fetch(u8, ctxt); + while (ctxt->d & GroupMask) { switch (ctxt->d & GroupMask) { case Group: - ctxt->modrm = insn_fetch(u8, ctxt); - --ctxt->_eip; goffset = (ctxt->modrm >> 3) & 7; opcode = opcode.u.group[goffset]; break; case GroupDual: - ctxt->modrm = insn_fetch(u8, ctxt); - --ctxt->_eip; goffset = (ctxt->modrm >> 3) & 7; if ((ctxt->modrm >> 6) == 3) opcode = opcode.u.gdual->mod3[goffset]; @@ -3960,6 +4015,8 @@ done_prefixes: if (ctxt->d & Sse) ctxt->op_bytes = 16; + else if (ctxt->d & Mmx) + ctxt->op_bytes = 8; /* ModRM and SIB bytes. */ if (ctxt->d & ModRM) { @@ -4030,6 +4087,35 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) return false; } +static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) +{ + bool fault = false; + + ctxt->ops->get_fpu(ctxt); + asm volatile("1: fwait \n\t" + "2: \n\t" + ".pushsection .fixup,\"ax\" \n\t" + "3: \n\t" + "movb $1, %[fault] \n\t" + "jmp 2b \n\t" + ".popsection \n\t" + _ASM_EXTABLE(1b, 3b) + : [fault]"+qm"(fault)); + ctxt->ops->put_fpu(ctxt); + + if (unlikely(fault)) + return emulate_exception(ctxt, MF_VECTOR, 0, false); + + return X86EMUL_CONTINUE; +} + +static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, + struct operand *op) +{ + if (op->type == OP_MM) + read_mmx_reg(ctxt, &op->mm_val, op->addr.mm); +} + int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) { struct x86_emulate_ops *ops = ctxt->ops; @@ -4054,18 +4140,31 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if ((ctxt->d & Sse) - && ((ops->get_cr(ctxt, 0) & X86_CR0_EM) - || !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) { + if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM))) + || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) { rc = emulate_ud(ctxt); goto done; } - if ((ctxt->d & Sse) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) { + if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) { rc = emulate_nm(ctxt); goto done; } + if (ctxt->d & Mmx) { + rc = flush_pending_x87_faults(ctxt); + if (rc != X86EMUL_CONTINUE) + goto done; + /* + * Now that we know the fpu is exception safe, we can fetch + * operands from it. + */ + fetch_possible_mmx_operand(ctxt, &ctxt->src); + fetch_possible_mmx_operand(ctxt, &ctxt->src2); + if (!(ctxt->d & Mov)) + fetch_possible_mmx_operand(ctxt, &ctxt->dst); + } + if (unlikely(ctxt->guest_mode) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index d68f99df690..adba28f88d1 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -34,7 +34,6 @@ #include <linux/kvm_host.h> #include <linux/slab.h> -#include <linux/workqueue.h> #include "irq.h" #include "i8254.h" @@ -249,7 +248,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) /* in this case, we had multiple outstanding pit interrupts * that we needed to inject. Reinject */ - queue_work(ps->pit->wq, &ps->pit->expired); + queue_kthread_work(&ps->pit->worker, &ps->pit->expired); ps->irq_ack = 1; spin_unlock(&ps->inject_lock); } @@ -270,7 +269,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) static void destroy_pit_timer(struct kvm_pit *pit) { hrtimer_cancel(&pit->pit_state.pit_timer.timer); - cancel_work_sync(&pit->expired); + flush_kthread_work(&pit->expired); } static bool kpit_is_periodic(struct kvm_timer *ktimer) @@ -284,7 +283,7 @@ static struct kvm_timer_ops kpit_ops = { .is_periodic = kpit_is_periodic, }; -static void pit_do_work(struct work_struct *work) +static void pit_do_work(struct kthread_work *work) { struct kvm_pit *pit = container_of(work, struct kvm_pit, expired); struct kvm *kvm = pit->kvm; @@ -328,7 +327,7 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) if (ktimer->reinject || !atomic_read(&ktimer->pending)) { atomic_inc(&ktimer->pending); - queue_work(pt->wq, &pt->expired); + queue_kthread_work(&pt->worker, &pt->expired); } if (ktimer->t_ops->is_periodic(ktimer)) { @@ -353,7 +352,7 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) /* TODO The new value only affected after the retriggered */ hrtimer_cancel(&pt->timer); - cancel_work_sync(&ps->pit->expired); + flush_kthread_work(&ps->pit->expired); pt->period = interval; ps->is_periodic = is_period; @@ -669,6 +668,8 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) { struct kvm_pit *pit; struct kvm_kpit_state *pit_state; + struct pid *pid; + pid_t pid_nr; int ret; pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL); @@ -685,14 +686,20 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) mutex_lock(&pit->pit_state.lock); spin_lock_init(&pit->pit_state.inject_lock); - pit->wq = create_singlethread_workqueue("kvm-pit-wq"); - if (!pit->wq) { + pid = get_pid(task_tgid(current)); + pid_nr = pid_vnr(pid); + put_pid(pid); + + init_kthread_worker(&pit->worker); + pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker, + "kvm-pit/%d", pid_nr); + if (IS_ERR(pit->worker_task)) { mutex_unlock(&pit->pit_state.lock); kvm_free_irq_source_id(kvm, pit->irq_source_id); kfree(pit); return NULL; } - INIT_WORK(&pit->expired, pit_do_work); + init_kthread_work(&pit->expired, pit_do_work); kvm->arch.vpit = pit; pit->kvm = kvm; @@ -736,7 +743,7 @@ fail: kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier); kvm_unregister_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier); kvm_free_irq_source_id(kvm, pit->irq_source_id); - destroy_workqueue(pit->wq); + kthread_stop(pit->worker_task); kfree(pit); return NULL; } @@ -756,10 +763,10 @@ void kvm_free_pit(struct kvm *kvm) mutex_lock(&kvm->arch.vpit->pit_state.lock); timer = &kvm->arch.vpit->pit_state.pit_timer.timer; hrtimer_cancel(timer); - cancel_work_sync(&kvm->arch.vpit->expired); + flush_kthread_work(&kvm->arch.vpit->expired); + kthread_stop(kvm->arch.vpit->worker_task); kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - destroy_workqueue(kvm->arch.vpit->wq); kfree(kvm->arch.vpit); } } diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index 51a97426e79..fdf40425ea1 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -1,6 +1,8 @@ #ifndef __I8254_H #define __I8254_H +#include <linux/kthread.h> + #include "iodev.h" struct kvm_kpit_channel_state { @@ -39,8 +41,9 @@ struct kvm_pit { struct kvm_kpit_state pit_state; int irq_source_id; struct kvm_irq_mask_notifier mask_notifier; - struct workqueue_struct *wq; - struct work_struct expired; + struct kthread_worker worker; + struct task_struct *worker_task; + struct kthread_work expired; }; #define KVM_PIT_BASE_ADDRESS 0x40 diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 858432287ab..93c15743f1e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -92,6 +92,11 @@ static inline int apic_test_and_clear_vector(int vec, void *bitmap) return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } +static inline int apic_test_vector(int vec, void *bitmap) +{ + return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + static inline void apic_set_vector(int vec, void *bitmap) { set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -480,7 +485,6 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) static void apic_set_eoi(struct kvm_lapic *apic) { int vector = apic_find_highest_isr(apic); - int trigger_mode; /* * Not every write EOI will has corresponding ISR, * one example is when Kernel check timer on setup_IO_APIC @@ -491,12 +495,15 @@ static void apic_set_eoi(struct kvm_lapic *apic) apic_clear_vector(vector, apic->regs + APIC_ISR); apic_update_ppr(apic); - if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR)) - trigger_mode = IOAPIC_LEVEL_TRIG; - else - trigger_mode = IOAPIC_EDGE_TRIG; - if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) + if (!(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_make_request(KVM_REQ_EVENT, apic->vcpu); } @@ -1081,6 +1088,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_update_ppr(apic); vcpu->arch.apic_arb_prio = 0; + vcpu->arch.apic_attention = 0; apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr=" "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__, @@ -1280,7 +1288,7 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) u32 data; void *vapic; - if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr) + if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; vapic = kmap_atomic(vcpu->arch.apic->vapic_page); @@ -1297,7 +1305,7 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) struct kvm_lapic *apic; void *vapic; - if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr) + if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; apic = vcpu->arch.apic; @@ -1317,10 +1325,11 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) { - if (!irqchip_in_kernel(vcpu->kvm)) - return; - vcpu->arch.apic->vapic_addr = vapic_addr; + if (vapic_addr) + __set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention); + else + __clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention); } int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 4cb16426884..72102e0ab7c 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -135,8 +135,6 @@ module_param(dbg, bool, 0644); #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \ | PT64_NX_MASK) -#define PTE_LIST_EXT 4 - #define ACC_EXEC_MASK 1 #define ACC_WRITE_MASK PT_WRITABLE_MASK #define ACC_USER_MASK PT_USER_MASK @@ -151,6 +149,9 @@ module_param(dbg, bool, 0644); #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) +/* make pte_list_desc fit well in cache line */ +#define PTE_LIST_EXT 3 + struct pte_list_desc { u64 *sptes[PTE_LIST_EXT]; struct pte_list_desc *more; @@ -550,19 +551,29 @@ static u64 mmu_spte_get_lockless(u64 *sptep) static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { - rcu_read_lock(); - atomic_inc(&vcpu->kvm->arch.reader_counter); - - /* Increase the counter before walking shadow page table */ - smp_mb__after_atomic_inc(); + /* + * Prevent page table teardown by making any free-er wait during + * kvm_flush_remote_tlbs() IPI to all active vcpus. + */ + local_irq_disable(); + vcpu->mode = READING_SHADOW_PAGE_TABLES; + /* + * Make sure a following spte read is not reordered ahead of the write + * to vcpu->mode. + */ + smp_mb(); } static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { - /* Decrease the counter after walking shadow page table finished */ - smp_mb__before_atomic_dec(); - atomic_dec(&vcpu->kvm->arch.reader_counter); - rcu_read_unlock(); + /* + * Make sure the write to vcpu->mode is not reordered in front of + * reads to sptes. If it does, kvm_commit_zap_page() can see us + * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. + */ + smp_mb(); + vcpu->mode = OUTSIDE_GUEST_MODE; + local_irq_enable(); } static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, @@ -841,32 +852,6 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, return count; } -static u64 *pte_list_next(unsigned long *pte_list, u64 *spte) -{ - struct pte_list_desc *desc; - u64 *prev_spte; - int i; - - if (!*pte_list) - return NULL; - else if (!(*pte_list & 1)) { - if (!spte) - return (u64 *)*pte_list; - return NULL; - } - desc = (struct pte_list_desc *)(*pte_list & ~1ul); - prev_spte = NULL; - while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) { - if (prev_spte == spte) - return desc->sptes[i]; - prev_spte = desc->sptes[i]; - } - desc = desc->more; - } - return NULL; -} - static void pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc, int i, struct pte_list_desc *prev_desc) @@ -987,11 +972,6 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) return pte_list_add(vcpu, spte, rmapp); } -static u64 *rmap_next(unsigned long *rmapp, u64 *spte) -{ - return pte_list_next(rmapp, spte); -} - static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_mmu_page *sp; @@ -1004,106 +984,201 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) pte_list_remove(spte, rmapp); } +/* + * Used by the following functions to iterate through the sptes linked by a + * rmap. All fields are private and not assumed to be used outside. + */ +struct rmap_iterator { + /* private fields */ + struct pte_list_desc *desc; /* holds the sptep if not NULL */ + int pos; /* index of the sptep */ +}; + +/* + * Iteration must be started by this function. This should also be used after + * removing/dropping sptes from the rmap link because in such cases the + * information in the itererator may not be valid. + * + * Returns sptep if found, NULL otherwise. + */ +static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) +{ + if (!rmap) + return NULL; + + if (!(rmap & 1)) { + iter->desc = NULL; + return (u64 *)rmap; + } + + iter->desc = (struct pte_list_desc *)(rmap & ~1ul); + iter->pos = 0; + return iter->desc->sptes[iter->pos]; +} + +/* + * Must be used with a valid iterator: e.g. after rmap_get_first(). + * + * Returns sptep if found, NULL otherwise. + */ +static u64 *rmap_get_next(struct rmap_iterator *iter) +{ + if (iter->desc) { + if (iter->pos < PTE_LIST_EXT - 1) { + u64 *sptep; + + ++iter->pos; + sptep = iter->desc->sptes[iter->pos]; + if (sptep) + return sptep; + } + + iter->desc = iter->desc->more; + + if (iter->desc) { + iter->pos = 0; + /* desc->sptes[0] cannot be NULL */ + return iter->desc->sptes[iter->pos]; + } + } + + return NULL; +} + static void drop_spte(struct kvm *kvm, u64 *sptep) { if (mmu_spte_clear_track_bits(sptep)) rmap_remove(kvm, sptep); } -int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, - struct kvm_memory_slot *slot) +static int __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, int level) { - unsigned long *rmapp; - u64 *spte; - int i, write_protected = 0; - - rmapp = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot); - spte = rmap_next(rmapp, NULL); - while (spte) { - BUG_ON(!(*spte & PT_PRESENT_MASK)); - rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); - if (is_writable_pte(*spte)) { - mmu_spte_update(spte, *spte & ~PT_WRITABLE_MASK); - write_protected = 1; + u64 *sptep; + struct rmap_iterator iter; + int write_protected = 0; + + for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { + BUG_ON(!(*sptep & PT_PRESENT_MASK)); + rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); + + if (!is_writable_pte(*sptep)) { + sptep = rmap_get_next(&iter); + continue; } - spte = rmap_next(rmapp, spte); - } - /* check for huge page mappings */ - for (i = PT_DIRECTORY_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - rmapp = __gfn_to_rmap(gfn, i, slot); - spte = rmap_next(rmapp, NULL); - while (spte) { - BUG_ON(!(*spte & PT_PRESENT_MASK)); - BUG_ON(!is_large_pte(*spte)); - pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); - if (is_writable_pte(*spte)) { - drop_spte(kvm, spte); - --kvm->stat.lpages; - spte = NULL; - write_protected = 1; - } - spte = rmap_next(rmapp, spte); + if (level == PT_PAGE_TABLE_LEVEL) { + mmu_spte_update(sptep, *sptep & ~PT_WRITABLE_MASK); + sptep = rmap_get_next(&iter); + } else { + BUG_ON(!is_large_pte(*sptep)); + drop_spte(kvm, sptep); + --kvm->stat.lpa |