diff options
Diffstat (limited to 'arch/x86/kvm')
30 files changed, 1489 insertions, 1126 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 52524e0ca97f..d563a948318b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1135,6 +1135,7 @@ void kvm_set_cpu_caps(void) F(AMD_STIBP), F(AMD_STIBP_ALWAYS_ON), F(AMD_IBRS_SAME_MODE), + PASSTHROUGH_F(EFER_LMSLE_MBZ), F(AMD_PSFD), F(AMD_IBPB_RET), ); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4e3da5b497b8..c8e292e9a24d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -81,9 +81,8 @@ */ /* Operand sizes: 8-bit operands or specified/overridden size. */ -#define ByteOp (1<<0) /* 8-bit operands. */ -/* Destination operand type. */ -#define DstShift 1 +#define ByteOp (1<<0) /* 8-bit operands. */ +#define DstShift 1 /* Destination operand type at bits 1-5 */ #define ImplicitOps (OpImplicit << DstShift) #define DstReg (OpReg << DstShift) #define DstMem (OpMem << DstShift) @@ -95,8 +94,7 @@ #define DstDX (OpDX << DstShift) #define DstAccLo (OpAccLo << DstShift) #define DstMask (OpMask << DstShift) -/* Source operand type. */ -#define SrcShift 6 +#define SrcShift 6 /* Source operand type at bits 6-10 */ #define SrcNone (OpNone << SrcShift) #define SrcReg (OpReg << SrcShift) #define SrcMem (OpMem << SrcShift) @@ -119,10 +117,10 @@ #define SrcAccHi (OpAccHi << SrcShift) #define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) -#define MemAbs (1<<12) /* Memory operand is absolute displacement */ +#define MemAbs (1<<12) /* Memory operand is absolute displacement */ #define String (1<<13) /* String instruction (rep capable) */ #define Stack (1<<14) /* Stack instruction (push/pop) */ -#define GroupMask (7<<15) /* Opcode uses one of the group mechanisms */ +#define GroupMask (7<<15) /* Group mechanisms, at bits 15-17 */ #define Group (1<<15) /* Bits 3:5 of modrm byte extend opcode */ #define GroupDual (2<<15) /* Alternate decoding of mod == 3 */ #define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */ @@ -131,11 +129,8 @@ #define InstrDual (6<<15) /* Alternate instruction decoding of mod == 3 */ #define ModeDual (7<<15) /* Different instruction for 32/64 bit */ #define Sse (1<<18) /* SSE Vector instruction */ -/* Generic ModRM decode. */ -#define ModRM (1<<19) -/* Destination is only written; never read. */ -#define Mov (1<<20) -/* Misc flags */ +#define ModRM (1<<19) /* Generic ModRM decode. */ +#define Mov (1<<20) /* Destination is only written; never read. */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define EmulateOnUD (1<<22) /* Emulate if unsupported by the host */ #define NoAccess (1<<23) /* Don't access memory (lea/invlpg/verr etc) */ @@ -143,11 +138,11 @@ #define Undefined (1<<25) /* No Such Instruction */ #define Lock (1<<26) /* lock prefix is allowed for the instruction */ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ -#define No64 (1<<28) +#define No64 (1<<28) /* Instruction generates #UD in 64-bit mode */ #define PageTable (1 << 29) /* instruction used to write page table */ #define NotImpl (1 << 30) /* instruction is not implemented */ -/* Source 2 operand type */ -#define Src2Shift (31) +#define Avx ((u64)1 << 31) /* Instruction uses VEX prefix */ +#define Src2Shift (32) /* Source 2 operand type at bits 32-36 */ #define Src2None (OpNone << Src2Shift) #define Src2Mem (OpMem << Src2Shift) #define Src2CL (OpCL << Src2Shift) @@ -161,12 +156,13 @@ #define Src2FS (OpFS << Src2Shift) #define Src2GS (OpGS << Src2Shift) #define Src2Mask (OpMask << Src2Shift) +/* free: 37-39 */ #define Mmx ((u64)1 << 40) /* MMX Vector instruction */ -#define AlignMask ((u64)7 << 41) +#define AlignMask ((u64)3 << 41) /* Memory alignment requirement at bits 41-42 */ #define Aligned ((u64)1 << 41) /* Explicitly aligned (e.g. MOVDQA) */ #define Unaligned ((u64)2 << 41) /* Explicitly unaligned (e.g. MOVDQU) */ -#define Avx ((u64)3 << 41) /* Advanced Vector Extensions */ -#define Aligned16 ((u64)4 << 41) /* Aligned to 16 byte boundary (e.g. FXSAVE) */ +#define Aligned16 ((u64)3 << 41) /* Aligned to 16 byte boundary (e.g. FXSAVE) */ +/* free: 43-44 */ #define NoWrite ((u64)1 << 45) /* No writeback */ #define SrcWrite ((u64)1 << 46) /* Write back src operand */ #define NoMod ((u64)1 << 47) /* Mod field is ignored */ @@ -243,6 +239,13 @@ enum x86_transfer_type { X86_TRANSFER_TASK_SWITCH, }; +enum rex_bits { + REX_B = 1, + REX_X = 2, + REX_R = 4, + REX_W = 8, +}; + static void writeback_registers(struct x86_emulate_ctxt *ctxt) { unsigned long dirty = ctxt->regs_dirty; @@ -622,7 +625,6 @@ static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size) switch (alignment) { case Unaligned: - case Avx: return 1; case Aligned16: return 16; @@ -924,7 +926,7 @@ static void *decode_register(struct x86_emulate_ctxt *ctxt, u8 modrm_reg, int byteop) { void *p; - int highbyte_regs = (ctxt->rex_prefix == 0) && byteop; + int highbyte_regs = (ctxt->rex_prefix == REX_NONE) && byteop; if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8) p = (unsigned char *)reg_rmw(ctxt, modrm_reg & 3) + 1; @@ -1030,6 +1032,7 @@ static void fetch_register_operand(struct operand *op) op->val = *(u64 *)op->addr.reg; break; } + op->orig_val = op->val; } static int em_fninit(struct x86_emulate_ctxt *ctxt) @@ -1075,17 +1078,17 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static void decode_register_operand(struct x86_emulate_ctxt *ctxt, - struct operand *op) +static void __decode_register_operand(struct x86_emulate_ctxt *ctxt, + struct operand *op, int reg) { - unsigned int reg; - - if (ctxt->d & ModRM) - reg = ctxt->modrm_reg; - else - reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3); - - if (ctxt->d & Sse) { + if ((ctxt->d & Avx) && ctxt->op_bytes == 32) { + op->type = OP_YMM; + op->bytes = 32; + op->addr.xmm = reg; + kvm_read_avx_reg(reg, &op->vec_val2); + return; + } + if (ctxt->d & (Avx|Sse)) { op->type = OP_XMM; op->bytes = 16; op->addr.xmm = reg; @@ -1103,9 +1106,20 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = decode_register(ctxt, reg, ctxt->d & ByteOp); - fetch_register_operand(op); - op->orig_val = op->val; +} + +static void decode_register_operand(struct x86_emulate_ctxt *ctxt, + struct operand *op) +{ + unsigned int reg; + + if (ctxt->d & ModRM) + reg = ctxt->modrm_reg; + else + reg = (ctxt->b & 7) | (ctxt->rex_bits & REX_B ? 8 : 0); + + __decode_register_operand(ctxt, op, reg); } static void adjust_modrm_seg(struct x86_emulate_ctxt *ctxt, int base_reg) @@ -1122,9 +1136,9 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, int rc = X86EMUL_CONTINUE; ulong modrm_ea = 0; - ctxt->modrm_reg = ((ctxt->rex_prefix << 1) & 8); /* REX.R */ - index_reg = (ctxt->rex_prefix << 2) & 8; /* REX.X */ - base_reg = (ctxt->rex_prefix << 3) & 8; /* REX.B */ + ctxt->modrm_reg = (ctxt->rex_bits & REX_R ? 8 : 0); + index_reg = (ctxt->rex_bits & REX_X ? 8 : 0); + base_reg = (ctxt->rex_bits & REX_B ? 8 : 0); ctxt->modrm_mod = (ctxt->modrm & 0xc0) >> 6; ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3; @@ -1132,24 +1146,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_seg = VCPU_SREG_DS; if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) { - op->type = OP_REG; - op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, - ctxt->d & ByteOp); - if (ctxt->d & Sse) { - op->type = OP_XMM; - op->bytes = 16; - op->addr.xmm = ctxt->modrm_rm; - kvm_read_sse_reg(ctxt->modrm_rm, &op->vec_val); - return rc; - } - if (ctxt->d & Mmx) { - op->type = OP_MM; - op->bytes = 8; - op->addr.mm = ctxt->modrm_rm & 7; - return rc; - } - fetch_register_operand(op); + __decode_register_operand(ctxt, op, ctxt->modrm_rm); return rc; } @@ -1783,7 +1780,15 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) op->data, op->bytes * op->count); case OP_XMM: - kvm_write_sse_reg(op->addr.xmm, &op->vec_val); + if (!(ctxt->d & Avx)) { + kvm_write_sse_reg(op->addr.xmm, &op->vec_val); + break; + } + /* full YMM write but with high bytes cleared */ + memset(op->valptr + 16, 0, 16); + fallthrough; + case OP_YMM: + kvm_write_avx_reg(op->addr.xmm, &op->vec_val2); break; case OP_MM: kvm_write_mmx_reg(op->addr.mm, &op->mm_val); @@ -2466,7 +2471,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) setup_syscalls_segments(&cs, &ss); - if ((ctxt->rex_prefix & 0x8) != 0x0) + if (ctxt->rex_bits & REX_W) usermode = X86EMUL_MODE_PROT64; else usermode = X86EMUL_MODE_PROT32; @@ -3958,6 +3963,8 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) +static const struct opcode ud = I(SrcNone, emulate_ud); + static const struct opcode group7_rm0[] = { N, I(SrcNone | Priv | EmulateOnUD, em_hypercall), @@ -4114,7 +4121,7 @@ static const struct group_dual group15 = { { } }; static const struct gprefix pfx_0f_6f_0f_7f = { - I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov), + I(Mmx, em_mov), I(Sse | Avx | Aligned, em_mov), N, I(Sse | Avx | Unaligned, em_mov), }; static const struct instr_dual instr_dual_0f_2b = { @@ -4133,8 +4140,8 @@ static const struct gprefix pfx_0f_28_0f_29 = { I(Aligned, em_mov), I(Aligned, em_mov), N, N, }; -static const struct gprefix pfx_0f_e7 = { - N, I(Sse, em_mov), N, N, +static const struct gprefix pfx_0f_e7_0f_38_2a = { + N, I(Sse | Avx, em_mov), N, N, }; static const struct escape escape_d9 = { { @@ -4347,8 +4354,8 @@ static const struct opcode twobyte_table[256] = { DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N, /* 0x10 - 0x1F */ - GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_10_0f_11), - GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_10_0f_11), + GP(ModRM | DstReg | SrcMem | Mov | Sse | Avx, &pfx_0f_10_0f_11), + GP(ModRM | DstMem | SrcReg | Mov | Sse | Avx, &pfx_0f_10_0f_11), N, N, N, N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess), /* 4 * prefetch + 4 * reserved NOP */ D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N, @@ -4364,9 +4371,9 @@ static const struct opcode twobyte_table[256] = { IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_dr_write, dr_write, check_dr_write), N, N, N, N, - GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29), - GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29), - N, GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_2b), + GP(ModRM | DstReg | SrcMem | Mov | Sse | Avx, &pfx_0f_28_0f_29), + GP(ModRM | DstMem | SrcReg | Mov | Sse | Avx, &pfx_0f_28_0f_29), + N, GP(ModRM | DstMem | SrcReg | Mov | Sse | Avx, &pfx_0f_2b), N, N, N, N, /* 0x30 - 0x3F */ II(ImplicitOps | Priv, em_wrmsr, wrmsr), @@ -4431,7 +4438,7 @@ static const struct opcode twobyte_table[256] = { /* 0xD0 - 0xDF */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, /* 0xE0 - 0xEF */ - N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_e7), + N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_e7_0f_38_2a), N, N, N, N, N, N, N, N, /* 0xF0 - 0xFF */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N @@ -4458,8 +4465,13 @@ static const struct gprefix three_byte_0f_38_f1 = { * byte. */ static const struct opcode opcode_map_0f_38[256] = { - /* 0x00 - 0x7f */ - X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), + /* 0x00 - 0x1f */ + X16(N), X16(N), + /* 0x20 - 0x2f */ + X8(N), + X2(N), GP(SrcReg | DstMem | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N, + /* 0x30 - 0x7f */ + X16(N), X16(N), X16(N), X16(N), X16(N), /* 0x80 - 0xef */ X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), /* 0xf0 - 0xf1 */ @@ -4618,14 +4630,12 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX); fetch_register_operand(op); - op->orig_val = op->val; break; case OpAccLo: op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 2 : ctxt->op_bytes; op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX); fetch_register_operand(op); - op->orig_val = op->val; break; case OpAccHi: if (ctxt->d & ByteOp) { @@ -4636,7 +4646,6 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, op->bytes = ctxt->op_bytes; op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RDX); fetch_register_operand(op); - op->orig_val = op->val; break; case OpDI: op->type = OP_MEM; @@ -4755,12 +4764,87 @@ done: return rc; } +static int x86_decode_avx(struct x86_emulate_ctxt *ctxt, + u8 vex_1st, u8 vex_2nd, struct opcode *opcode) +{ + u8 vex_3rd, map, pp, l, v; + int rc = X86EMUL_CONTINUE; + + if (ctxt->rep_prefix || ctxt->op_prefix || ctxt->rex_prefix) + goto ud; + + if (vex_1st == 0xc5) { + /* Expand RVVVVlpp to VEX3 format */ + vex_3rd = vex_2nd & ~0x80; /* VVVVlpp from VEX2, w=0 */ + vex_2nd = (vex_2nd & 0x80) | 0x61; /* R from VEX2, X=1 B=1 mmmmm=00001 */ + } else { + vex_3rd = insn_fetch(u8, ctxt); + } + + /* vex_2nd = RXBmmmmm, vex_3rd = wVVVVlpp. Fix polarity */ + vex_2nd ^= 0xE0; /* binary 11100000 */ + vex_3rd ^= 0x78; /* binary 01111000 */ + + ctxt->rex_prefix = REX_PREFIX; + ctxt->rex_bits = (vex_2nd & 0xE0) >> 5; /* RXB */ + ctxt->rex_bits |= (vex_3rd & 0x80) >> 4; /* w */ + if (ctxt->rex_bits && ctxt->mode != X86EMUL_MODE_PROT64) + goto ud; + + map = vex_2nd & 0x1f; + v = (vex_3rd >> 3) & 0xf; + l = vex_3rd & 0x4; + pp = vex_3rd & 0x3; + + ctxt->b = insn_fetch(u8, ctxt); + switch (map) { + case 1: + ctxt->opcode_len = 2; + *opcode = twobyte_table[ctxt->b]; + break; + case 2: + ctxt->opcode_len = 3; + *opcode = opcode_map_0f_38[ctxt->b]; + break; + case 3: + /* no 0f 3a instructions are supported yet */ + return X86EMUL_UNHANDLEABLE; + default: + goto ud; + } + + /* + * No three operand instructions are supported yet; those that + * *are* marked with the Avx flag reserve the VVVV flag. + */ + if (v) + goto ud; + + if (l) + ctxt->op_bytes = 32; + else + ctxt->op_bytes = 16; + + switch (pp) { + case 0: break; + case 1: ctxt->op_prefix = true; break; + case 2: ctxt->rep_prefix = 0xf3; break; + case 3: ctxt->rep_prefix = 0xf2; break; + } + +done: + return rc; +ud: + *opcode = ud; + return rc; +} + int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type) { int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; int def_op_bytes, def_ad_bytes, goffset, simd_prefix; - bool op_prefix = false; + bool vex_prefix = false; bool has_seg_override = false; struct opcode opcode; u16 dummy; @@ -4812,7 +4896,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int for (;;) { switch (ctxt->b = insn_fetch(u8, ctxt)) { case 0x66: /* operand-size override */ - op_prefix = true; + ctxt->op_prefix = true; /* switch between 2/4 bytes */ ctxt->op_bytes = def_op_bytes ^ 6; break; @@ -4851,7 +4935,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int case 0x40 ... 0x4f: /* REX */ if (mode != X86EMUL_MODE_PROT64) goto done_prefixes; - ctxt->rex_prefix = ctxt->b; + ctxt->rex_prefix = REX_PREFIX; + ctxt->rex_bits = ctxt->b & 0xf; continue; case 0xf0: /* LOCK */ ctxt->lock_prefix = 1; @@ -4865,20 +4950,33 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int } /* Any legacy prefix after a REX prefix nullifies its effect. */ - - ctxt->rex_prefix = 0; + ctxt->rex_prefix = REX_NONE; + ctxt->rex_bits = 0; } done_prefixes: /* REX prefix. */ - if (ctxt->rex_prefix & 8) - ctxt->op_bytes = 8; /* REX.W */ + if (ctxt->rex_bits & REX_W) + ctxt->op_bytes = 8; /* Opcode byte(s). */ - opcode = opcode_table[ctxt->b]; - /* Two-byte opcode? */ - if (ctxt->b == 0x0f) { + if (ctxt->b == 0xc4 || ctxt->b == 0xc5) { + /* VEX or LDS/LES */ + u8 vex_2nd = insn_fetch(u8, ctxt); + if (mode != X86EMUL_MODE_PROT64 && (vex_2nd & 0xc0) != 0xc0) { + opcode = opcode_table[ctxt->b]; + ctxt->modrm = vex_2nd; + /* the Mod/RM byte has been fetched already! */ + goto done_modrm; + } + + vex_prefix = true; + rc = x86_decode_avx(ctxt, ctxt->b, vex_2nd, &opcode); + if (rc != X86EMUL_CONTINUE) + goto done; + } else if (ctxt->b == 0x0f) { + /* Two- or three-byte opcode */ ctxt->opcode_len = 2; ctxt->b = insn_fetch(u8, ctxt); opcode = twobyte_table[ctxt->b]; @@ -4889,18 +4987,16 @@ done_prefixes: ctxt->b = insn_fetch(u8, ctxt); opcode = opcode_map_0f_38[ctxt->b]; } + } else { + /* Opcode byte(s). */ + opcode = opcode_table[ctxt->b]; } - ctxt->d = opcode.flags; - if (ctxt->d & ModRM) + if (opcode.flags & ModRM) ctxt->modrm = insn_fetch(u8, ctxt); - /* vex-prefix instructions are not implemented */ - if (ctxt->opcode_len == 1 && (ctxt->b == 0xc5 || ctxt->b == 0xc4) && - (mode == X86EMUL_MODE_PROT64 || (ctxt->modrm & 0xc0) == 0xc0)) { - ctxt->d = NotImpl; - } - +done_modrm: + ctxt->d = opcode.flags; while (ctxt->d & GroupMask) { switch (ctxt->d & GroupMask) { case Group: @@ -4919,9 +5015,9 @@ done_prefixes: opcode = opcode.u.group[goffset]; break; case Prefix: - if (ctxt->rep_prefix && op_prefix) + if (ctxt->rep_prefix && ctxt->op_prefix) return EMULATION_FAILED; - simd_prefix = op_prefix ? 0x66 : ctxt->rep_prefix; + simd_prefix = ctxt->op_prefix ? 0x66 : ctxt->rep_prefix; switch (simd_prefix) { case 0x00: opcode = opcode.u.gprefix->pfx_no; break; case 0x66: opcode = opcode.u.gprefix->pfx_66; break; @@ -4966,6 +5062,19 @@ done_prefixes: if (ctxt->d == 0) return EMULATION_FAILED; + if (unlikely(vex_prefix)) { + /* + * Only specifically marked instructions support VEX. Since many + * instructions support it but are not annotated, return not implemented + * rather than #UD. + */ + if (!(ctxt->d & Avx)) + return EMULATION_FAILED; + + if (!(ctxt->d & AlignMask)) + ctxt->d |= Unaligned; + } + ctxt->execute = opcode.u.execute; /* @@ -5036,8 +5145,10 @@ done_prefixes: if ((ctxt->d & No16) && ctxt->op_bytes == 2) ctxt->op_bytes = 4; - if (ctxt->d & Sse) - ctxt->op_bytes = 16; + if (vex_prefix) + ; + else if (ctxt->d & Sse) + ctxt->op_bytes = 16, ctxt->d &= ~Avx; else if (ctxt->d & Mmx) ctxt->op_bytes = 8; } @@ -5137,8 +5248,10 @@ void init_decode_cache(struct x86_emulate_ctxt *ctxt) { /* Clear fields that are set conditionally but read without a guard. */ ctxt->rip_relative = false; - ctxt->rex_prefix = 0; + ctxt->rex_prefix = REX_NONE; + ctxt->rex_bits = 0; ctxt->lock_prefix = 0; + ctxt->op_prefix = false; ctxt->rep_prefix = 0; ctxt->regs_valid = 0; ctxt->regs_dirty = 0; @@ -5168,20 +5281,34 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, bool check_intercepts) } if (unlikely(ctxt->d & - (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) { + (No64|Undefined|Avx|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) { if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) || (ctxt->d & Undefined)) { rc = emulate_ud(ctxt); goto done; } - if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM))) - || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) { + if ((ctxt->d & (Avx|Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM))) { rc = emulate_ud(ctxt); goto done; } - if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) { + if (ctxt->d & Avx) { + u64 xcr = 0; + if (!(ops->get_cr(ctxt, 4) & X86_CR4_OSXSAVE) + || ops->get_xcr(ctxt, 0, &xcr) + || !(xcr & XFEATURE_MASK_YMM)) { + rc = emulate_ud(ctxt); + goto done; + } + } else if (ctxt->d & Sse) { + if (!(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)) { + rc = emulate_ud(ctxt); + goto done; + } + } + + if ((ctxt->d & (Avx|Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) { rc = emulate_nm(ctxt); goto done; } diff --git a/arch/x86/kvm/fpu.h b/arch/x86/kvm/fpu.h index 3ba12888bf66..f898781b6a06 100644 --- a/arch/x86/kvm/fpu.h +++ b/arch/x86/kvm/fpu.h @@ -15,6 +15,58 @@ typedef u32 __attribute__((vector_size(16))) sse128_t; #define sse128_l3(x) ({ __sse128_u t; t.vec = x; t.as_u32[3]; }) #define sse128(lo, hi) ({ __sse128_u t; t.as_u64[0] = lo; t.as_u64[1] = hi; t.vec; }) +typedef u32 __attribute__((vector_size(32))) avx256_t; + +static inline void _kvm_read_avx_reg(int reg, avx256_t *data) +{ + switch (reg) { + case 0: asm("vmovdqa %%ymm0, %0" : "=m"(*data)); break; + case 1: asm("vmovdqa %%ymm1, %0" : "=m"(*data)); break; + case 2: asm("vmovdqa %%ymm2, %0" : "=m"(*data)); break; + case 3: asm("vmovdqa %%ymm3, %0" : "=m"(*data)); break; + case 4: asm("vmovdqa %%ymm4, %0" : "=m"(*data)); break; + case 5: asm("vmovdqa %%ymm5, %0" : "=m"(*data)); break; + case 6: asm("vmovdqa %%ymm6, %0" : "=m"(*data)); break; + case 7: asm("vmovdqa %%ymm7, %0" : "=m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("vmovdqa %%ymm8, %0" : "=m"(*data)); break; + case 9: asm("vmovdqa %%ymm9, %0" : "=m"(*data)); break; + case 10: asm("vmovdqa %%ymm10, %0" : "=m"(*data)); break; + case 11: asm("vmovdqa %%ymm11, %0" : "=m"(*data)); break; + case 12: asm("vmovdqa %%ymm12, %0" : "=m"(*data)); break; + case 13: asm("vmovdqa %%ymm13, %0" : "=m"(*data)); break; + case 14: asm("vmovdqa %%ymm14, %0" : "=m"(*data)); break; + case 15: asm("vmovdqa %%ymm15, %0" : "=m"(*data)); break; +#endif + default: BUG(); + } +} + +static inline void _kvm_write_avx_reg(int reg, const avx256_t *data) +{ + switch (reg) { + case 0: asm("vmovdqa %0, %%ymm0" : : "m"(*data)); break; + case 1: asm("vmovdqa %0, %%ymm1" : : "m"(*data)); break; + case 2: asm("vmovdqa %0, %%ymm2" : : "m"(*data)); break; + case 3: asm("vmovdqa %0, %%ymm3" : : "m"(*data)); break; + case 4: asm("vmovdqa %0, %%ymm4" : : "m"(*data)); break; + case 5: asm("vmovdqa %0, %%ymm5" : : "m"(*data)); break; + case 6: asm("vmovdqa %0, %%ymm6" : : "m"(*data)); break; + case 7: asm("vmovdqa %0, %%ymm7" : : "m"(*data)); break; +#ifdef CONFIG_X86_64 + case 8: asm("vmovdqa %0, %%ymm8" : : "m"(*data)); break; + case 9: asm("vmovdqa %0, %%ymm9" : : "m"(*data)); break; + case 10: asm("vmovdqa %0, %%ymm10" : : "m"(*data)); break; + case 11: asm("vmovdqa %0, %%ymm11" : : "m"(*data)); break; + case 12: asm("vmovdqa %0, %%ymm12" : : "m"(*data)); break; + case 13: asm("vmovdqa %0, %%ymm13" : : "m"(*data)); break; + case 14: asm("vmovdqa %0, %%ymm14" : : "m"(*data)); break; + case 15: asm("vmovdqa %0, %%ymm15" : : "m"(*data)); break; +#endif + default: BUG(); + } +} + static inline void _kvm_read_sse_reg(int reg, sse128_t *data) { switch (reg) { @@ -109,6 +161,20 @@ static inline void kvm_fpu_put(void) fpregs_unlock(); } +static inline void kvm_read_avx_reg(int reg, avx256_t *data) +{ + kvm_fpu_get(); + _kvm_read_avx_reg(reg, data); + kvm_fpu_put(); +} + +static inline void kvm_write_avx_reg(int reg, const avx256_t *data) +{ + kvm_fpu_get(); + _kvm_write_avx_reg(reg, data); + kvm_fpu_put(); +} + static inline void kvm_read_sse_reg(int reg, sse128_t *data) { kvm_fpu_get(); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 38595ecb990d..de92292eb1f5 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1568,7 +1568,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) * only, there can be valuable data in the rest which needs * to be preserved e.g. on migration. */ - if (__put_user(0, (u32 __user *)addr)) + if (put_user(0, (u32 __user *)addr)) return 1; hv_vcpu->hv_vapic = data; kvm_vcpu_mark_page_dirty(vcpu, gfn); diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 7b5ddb787a25..fb3dab4b5a53 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -237,6 +237,7 @@ struct x86_emulate_ops { bool (*is_smm)(struct x86_emulate_ctxt *ctxt); int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); + int (*get_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 *xcr); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, @@ -248,7 +249,7 @@ struct x86_emulate_ops { /* Type, address-of, and value of an instruction's operand. */ struct operand { - enum { OP_REG, OP_MEM, OP_MEM_STR, OP_IMM, OP_XMM, OP_MM, OP_NONE } type; + enum { OP_REG, OP_MEM, OP_MEM_STR, OP_IMM, OP_XMM, OP_YMM, OP_MM, OP_NONE } type; unsigned int bytes; unsigned int count; union { @@ -267,11 +268,12 @@ struct operand { union { unsigned long val; u64 val64; - char valptr[sizeof(sse128_t)]; + char valptr[sizeof(avx256_t)]; sse128_t vec_val; + avx256_t vec_val2; u64 mm_val; void *data; - }; + } __aligned(32); }; #define X86_MAX_INSTRUCTION_LENGTH 15 @@ -317,6 +319,14 @@ typedef void (*fastop_t)(struct fastop *); #define NR_EMULATOR_GPRS 8 #endif +/* + * Distinguish between no prefix, REX, or in the future REX2. + */ +enum rex_type { + REX_NONE, + REX_PREFIX, +}; + struct x86_emulate_ctxt { void *vcpu; const struct x86_emulate_ops *ops; @@ -348,6 +358,7 @@ struct x86_emulate_ctxt { u8 opcode_len; u8 b; u8 intercept; + bool op_prefix; u8 op_bytes; u8 ad_bytes; union { @@ -357,7 +368,8 @@ struct x86_emulate_ctxt { int (*check_perm)(struct x86_emulate_ctxt *ctxt); bool rip_relative; - u8 rex_prefix; + enum rex_type rex_prefix; + u8 rex_bits; u8 lock_prefix; u8 rep_prefix; /* bitmaps of registers in _regs[] that can be read */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0ae7f913d782..1597dd0b0cc6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2126,23 +2126,41 @@ static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) static void advance_periodic_target_expiration(struct kvm_lapic *apic) { + struct kvm_timer *ktimer = &apic->lapic_timer; ktime_t now = ktime_get(); u64 tscl = rdtsc(); ktime_t delta; /* - * Synchronize both deadlines to the same time source or - * differences in the periods (caused by differences in the - * underlying clocks or numerical approximation errors) will - * cause the two to drift apart over time as the errors - * accumulate. + * Use kernel time as the time source for both the hrtimer deadline and + * TSC-based deadline so that they stay synchronized. Computing each + * deadline independently will cause the two deadlines to drift apart + * over time as differences in the periods accumulate, e.g. due to + * differences in the underlying clocks or numerical approximation errors. */ - apic->lapic_timer.target_expiration = - ktime_add_ns(apic->lapic_timer.target_expiration, - apic->lapic_timer.period); - delta = ktime_sub(apic->lapic_timer.target_expiration, now); - apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + - nsec_to_cycles(apic->vcpu, delta); + ktimer->target_expiration = ktime_add_ns(ktimer->target_expiration, + ktimer->period); + + /* + * If the new expiration is in the past, e.g. because userspace stopped + * running the VM for an extended duration, then force the expiration + * to "now" and don't try to play catch-up with the missed events. KVM + * will only deliver a single interrupt regardless of how many events + * are pending, i.e. restarting the timer with an expiration in the + * past will do nothing more than waste host cycles, and can even lead + * to a hard lockup in extreme cases. + */ + if (ktime_before(ktimer->target_expiration, now)) + ktimer->target_expiration = now; + + /* + * Note, ensuring the expiration isn't in the past also prevents delta + * from going negative, which could cause the TSC deadline to become + * excessively large due to it an unsigned value. + */ + delta = ktime_sub(ktimer->target_expiration, now); + ktimer->tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + + nsec_to_cycles(apic->vcpu, delta); } static void start_sw_period(struct kvm_lapic *apic) @@ -2970,9 +2988,9 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) apic_timer_expired(apic, true); - if (lapic_is_periodic(apic)) { + if (lapic_is_periodic(apic) && !WARN_ON_ONCE(!apic->lapic_timer.period)) { advance_periodic_target_expiration(apic); - hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); + hrtimer_set_expires(&ktimer->timer, ktimer->target_expiration); return HRTIMER_RESTART; } else return HRTIMER_NORESTART; diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index f63074048ec6..830f46145692 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -235,8 +235,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } -bool kvm_mmu_may_ignore_guest_pat(struct kvm *kvm); - int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); @@ -257,8 +255,7 @@ extern bool tdp_mmu_enabled; #define tdp_mmu_enabled false #endif -bool kvm_tdp_mmu_gpa_is_mapped(struct kvm_vcpu *vcpu, u64 gpa); -int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level); +int kvm_tdp_mmu_map_private_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn); static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 667d66cf76d5..02c450686b4a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4859,7 +4859,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, */ BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK)); - vcpu->arch.l1tf_flush_l1d = true; + kvm_request_l1tf_flush_l1d(); if (!flags) { trace_kvm_page_fault(vcpu, fault_address, error_code); @@ -4924,7 +4924,8 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return direct_page_fault(vcpu, fault); } -int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level) +static int kvm_tdp_page_prefault(struct kvm_vcpu *vcpu, gpa_t gpa, + u64 error_code, u8 *level) { int r; @@ -4966,7 +4967,6 @@ int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level return -EIO; } } -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_tdp_map_page); long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range) @@ -5002,7 +5002,7 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, * Shadow paging uses GVA for kvm page fault, so restrict to * two-dimensional paging. */ - r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level); + r = kvm_tdp_page_prefault(vcpu, range->gpa | direct_bits, error_code, &level); if (r < 0) return r; @@ -5014,6 +5014,86 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, return min(range->size, end - range->gpa); } +#ifdef CONFIG_KVM_GUEST_MEMFD +static void kvm_assert_gmem_invalidate_lock_held(struct kvm_memory_slot *slot) +{ +#ifdef CONFIG_PROVE_LOCKING + if (WARN_ON_ONCE(!kvm_slot_has_gmem(slot)) || + WARN_ON_ONCE(!slot->gmem.file) || + WARN_ON_ONCE(!file_count(slot->gmem.file))) + return; + + lockdep_assert_held(&file_inode(slot->gmem.file)->i_mapping->invalidate_lock); +#endif +} + +int kvm_tdp_mmu_map_private_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) +{ + struct kvm_page_fault fault = { + .addr = gfn_to_gpa(gfn), + .error_code = PFERR_GUEST_FINAL_MASK | PFERR_PRIVATE_ACCESS, + .prefetch = true, + .is_tdp = true, + .nx_huge_page_workaround_enabled = is_nx_huge_page_enabled(vcpu->kvm), + + .max_level = PG_LEVEL_4K, + .req_level = PG_LEVEL_4K, + .goal_level = PG_LEVEL_4K, + .is_private = true, + + .gfn = gfn, + .slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn), + .pfn = pfn, + .map_writable = true, + }; + struct kvm *kvm = vcpu->kvm; + int r; + + lockdep_assert_held(&kvm->slots_lock); + + /* + * Mapping a pre-determined private pfn is intended only for use when + * populating a guest_memfd instance. Assert that the slot is backed + * by guest_memfd and that the gmem instance's invalidate_lock is held. + */ + kvm_assert_gmem_invalidate_lock_held(fault.slot); + + if (KVM_BUG_ON(!tdp_mmu_enabled, kvm)) + return -EIO; + + if (kvm_gfn_is_write_tracked(kvm, fault.slot, fault.gfn)) + return -EPERM; + + r = kvm_mmu_reload(vcpu); + if (r) + return r; + + r = mmu_topup_memory_caches(vcpu, false); + if (r) + return r; + + do { + if (signal_pending(current)) + return -EINTR; + + if (kvm_test_request(KVM_REQ_VM_DEAD, vcpu)) + return -EIO; + + cond_resched(); + + guard(read_lock)(&kvm->mmu_lock); + + r = kvm_tdp_mmu_map(vcpu, &fault); + } while (r == RET_PF_RETRY); + + if (r != RET_PF_FIXED) + return -EIO; + + return 0; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_tdp_mmu_map_private_pfn); +#endif + static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; @@ -5997,7 +6077,6 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) out: return r; } -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { @@ -6863,6 +6942,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_unlock(&kvm->mmu_lock); } +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_zap_gfn_range); static bool slot_rmap_write_protect(struct kvm *kvm, struct kvm_rmap_head *rmap_head, @@ -7204,7 +7284,6 @@ restart: return need_tlb_flush; } -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_zap_gfn_range); static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -7364,6 +7443,9 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) { WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); + if (!enable_mmio_caching) + return; + gen &= MMIO_SPTE_GEN_MASK; /* diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index ed5c01df21ba..73cdcbccc89e 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -39,16 +39,6 @@ #define INVALID_PAE_ROOT 0 #define IS_VALID_PAE_ROOT(x) (!!(x)) -static inline hpa_t kvm_mmu_get_dummy_root(void) -{ - return my_zero_pfn(0) << PAGE_SHIFT; -} - -static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page) -{ - return is_zero_pfn(shadow_page >> PAGE_SHIFT); -} - typedef u64 __rcu *tdp_ptep_t; struct kvm_mmu_page { diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index ed762bb4b007..901cd2bd40b8 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -402,7 +402,7 @@ retry_walk: goto error; ptep_user = (pt_element_t __user *)((void *)host_addr + offset); - if (unlikely(__get_user(pte, ptep_user))) + if (unlikely(get_user(pte, ptep_user))) goto error; walker->ptep_user[walker->level - 1] = ptep_user; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 37647afde7d3..85a0473809b0 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -292,7 +292,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, mark_page_dirty_in_slot(vcpu->kvm, slot, gfn); } - if (static_branch_unlikely(&cpu_buf_vm_clear) && + if (cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO) && !kvm_vcpu_can_access_host_mmio(vcpu) && kvm_is_mmio_pfn(pfn, &is_host_mmio)) kvm_track_host_mmio_mapping(vcpu); diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 3133f066927e..91ce29fd6f1b 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -246,6 +246,16 @@ static inline int spte_index(u64 *sptep) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +static inline hpa_t kvm_mmu_get_dummy_root(void) +{ + return my_zero_pfn(0) << PAGE_SHIFT; +} + +static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page) +{ + return is_zero_pfn(shadow_page >> PAGE_SHIFT); +} + static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page) { struct page *page = pfn_to_page((shadow_page) >> PAGE_SHIFT); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index c5734ca5c17d..9c26038f6b77 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -362,9 +362,6 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte, int level) { - kvm_pfn_t old_pfn = spte_to_pfn(old_spte); - int ret; - /* * External (TDX) SPTEs are limited to PG_LEVEL_4K, and external * PTs are removed in a special order, involving free_external_spt(). @@ -377,9 +374,8 @@ static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte, /* Zapping leaf spte is allowed only when write lock is held. */ lockdep_assert_held_write(&kvm->mmu_lock); - /* Because write lock is held, operation should success. */ - ret = kvm_x86_call(remove_external_spte)(kvm, gfn, level, old_pfn); - KVM_BUG_ON(ret, kvm); + + kvm_x86_call(remove_external_spte)(kvm, gfn, level, old_spte); } /** @@ -519,7 +515,6 @@ static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sp bool was_present = is_shadow_present_pte(old_spte); bool is_present = is_shadow_present_pte(new_spte); bool is_leaf = is_present && is_last_spte(new_spte, level); - kvm_pfn_t new_pfn = spte_to_pfn(new_spte); int ret = 0; KVM_BUG_ON(was_present, kvm); @@ -538,7 +533,7 @@ static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sp * external page table, or leaf. */ if (is_leaf) { - ret = kvm_x86_call(set_external_spte)(kvm, gfn, level, new_pfn); + ret = kvm_x86_call(set_external_spte)(kvm, gfn, level, new_spte); } else { void *external_spt = get_external_spt(gfn, new_spte, level); @@ -1273,6 +1268,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) struct kvm_mmu_page *sp; int ret = RET_PF_RETRY; + KVM_MMU_WARN_ON(!root || root->role.invalid); + kvm_mmu_hugepage_adjust(vcpu, fault); trace_kvm_mmu_spte_requested(fault); @@ -1939,13 +1936,16 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, * * Must be called between kvm_tdp_mmu_walk_lockless_{begin,end}. */ -static int __kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, - struct kvm_mmu_page *root) +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level) { + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); struct tdp_iter iter; gfn_t gfn = addr >> PAGE_SHIFT; int leaf = -1; + *root_level = vcpu->arch.mmu->root_role.level; + for_each_tdp_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { leaf = iter.level; sptes[leaf] = iter.old_spte; @@ -1954,36 +1954,6 @@ static int __kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, return leaf; } -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, - int *root_level) -{ - struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); - *root_level = vcpu->arch.mmu->root_role.level; - - return __kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root); -} - -bool kvm_tdp_mmu_gpa_is_mapped(struct kvm_vcpu *vcpu, u64 gpa) -{ - struct kvm *kvm = vcpu->kvm; - bool is_direct = kvm_is_addr_direct(kvm, gpa); - hpa_t root = is_direct ? vcpu->arch.mmu->root.hpa : - vcpu->arch.mmu->mirror_root_hpa; - u64 sptes[PT64_ROOT_MAX_LEVEL + 1], spte; - int leaf; - - lockdep_assert_held(&kvm->mmu_lock); - rcu_read_lock(); - leaf = __kvm_tdp_mmu_get_walk(vcpu, gpa, sptes, root_to_sp(root)); - rcu_read_unlock(); - if (leaf < 0) - return false; - - spte = sptes[leaf]; - return is_shadow_present_pte(spte) && is_last_spte(spte, leaf); -} -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_tdp_mmu_gpa_is_mapped); - /* * Returns the last level spte pointer of the shadow page walk for the given * gpa, and sets *spte to the spte value. This spte may be non-preset. If no diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index fef00546c885..6b77b2033208 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -106,7 +106,7 @@ static u32 next_vm_id = 0; static bool next_vm_id_wrapped = 0; static DEFINE_SPINLOCK(svm_vm_data_hash_lock); static bool x2avic_enabled; - +static u32 x2avic_max_physical_id; static void avic_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) @@ -158,12 +158,40 @@ static void avic_set_x2apic_msr_interception(struct vcpu_svm *svm, svm->x2avic_msrs_intercepted = intercept; } +static u32 __avic_get_max_physical_id(struct kvm *kvm, struct kvm_vcpu *vcpu) +{ + u32 arch_max; + + /* + * Return the largest size (x2APIC) when querying without a vCPU, e.g. + * to allocate the per-VM table.. + */ + if (x2avic_enabled && (!vcpu || apic_x2apic_mode(vcpu->arch.apic))) + arch_max = x2avic_max_physical_id; + else + arch_max = AVIC_MAX_PHYSICAL_ID; + + /* + * Despite its name, KVM_CAP_MAX_VCPU_ID represents the maximum APIC ID + * plus one, so the max possible APIC ID is one less than that. + */ + return min(kvm->arch.max_vcpu_ids - 1, arch_max); +} + +static u32 avic_get_max_physical_id(struct kvm_vcpu *vcpu) +{ + return __avic_get_max_physical_id(vcpu->kvm, vcpu); +} + static void avic_activate_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; + struct kvm_vcpu *vcpu = &svm->vcpu; vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); + vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + vmcb->control.avic_physical_id |= avic_get_max_physical_id(vcpu); vmcb->control.int_ctl |= AVIC_ENABLE_MASK; @@ -176,7 +204,7 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) */ if (x2avic_enabled && apic_x2apic_mode(svm->vcpu.arch.apic)) { vmcb->control.int_ctl |= X2APIC_MODE_MASK; - vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID; + /* Disabling MSR intercept for x2APIC registers */ avic_set_x2apic_msr_interception(svm, false); } else { @@ -186,8 +214,6 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) */ kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, &svm->vcpu); - /* For xAVIC and hybrid-xAVIC modes */ - vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; /* Enabling MSR intercept for x2APIC registers */ avic_set_x2apic_msr_interception(svm, true); } @@ -247,6 +273,30 @@ static int avic_ga_log_notifier(u32 ga_tag) return 0; } +static int avic_get_physical_id_table_order(struct kvm *kvm) +{ + /* Provision for the maximum physical ID supported in x2avic mode */ + return get_order((__avic_get_max_physical_id(kvm, NULL) + 1) * sizeof(u64)); +} + +int avic_alloc_physical_id_table(struct kvm *kvm) +{ + struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + + if (!irqchip_in_kernel(kvm) || !enable_apicv) + return 0; + + if (kvm_svm->avic_physical_id_table) + return 0; + + kvm_svm->avic_physical_id_table = (void *)__get_free_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, + avic_get_physical_id_table_order(kvm)); + if (!kvm_svm->avic_physical_id_table) + return -ENOMEM; + + return 0; +} + void avic_vm_destroy(struct kvm *kvm) { unsigned long flags; @@ -256,7 +306,8 @@ void avic_vm_destroy(struct kvm *kvm) return; free_page((unsigned long)kvm_svm->avic_logical_id_table); - free_page((unsigned long)kvm_svm->avic_physical_id_table); + free_pages((unsigned long)kvm_svm->avic_physical_id_table, + avic_get_physical_id_table_order(kvm)); spin_lock_irqsave(&svm_vm_data_hash_lock, flags); hash_del(&kvm_svm->hnode); @@ -274,10 +325,6 @@ int avic_vm_init(struct kvm *kvm) if (!enable_apicv) return 0; - kvm_svm->avic_physical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!kvm_svm->avic_physical_id_table) - goto free_avic; - kvm_svm->avic_logical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!kvm_svm->avic_logical_id_table) goto free_avic; @@ -342,7 +389,7 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) * fully initialized AVIC. */ if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) || - (id > X2AVIC_MAX_PHYSICAL_ID)) { + (id > x2avic_max_physical_id)) { kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG); vcpu->arch.apic->apicv_active = false; return 0; @@ -562,7 +609,7 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) u32 icrh = svm->vmcb->control.exit_info_1 >> 32; u32 icrl = svm->vmcb->control.exit_info_1; u32 id = svm->vmcb->control.exit_info_2 >> 32; - u32 index = svm->vmcb->control.exit_info_2 & 0x1FF; + u32 index = svm->vmcb->control.exit_info_2 & AVIC_PHYSICAL_MAX_INDEX_MASK; struct kvm_lapic *apic = vcpu->arch.apic; trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index); @@ -962,7 +1009,8 @@ static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu, if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) return; - if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE)) + if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= + PAGE_SIZE << avic_get_physical_id_table_order(vcpu->kvm))) return; /* @@ -1024,7 +1072,8 @@ static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action) lockdep_assert_preemption_disabled(); - if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE)) + if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= + PAGE_SIZE << avic_get_physical_id_table_order(vcpu->kvm))) return; /* @@ -1226,10 +1275,15 @@ bool __init avic_hardware_setup(void) /* AVIC is a prerequisite for x2AVIC. */ x2avic_enabled = boot_cpu_has(X86_FEATURE_X2AVIC); - if (x2avic_enabled) - pr_info("x2AVIC enabled\n"); - else + if (x2avic_enabled) { + if (cpu_feature_enabled(X86_FEATURE_X2AVIC_EXT)) + x2avic_max_physical_id = X2AVIC_4K_MAX_PHYSICAL_ID; + else + x2avic_max_physical_id = X2AVIC_MAX_PHYSICAL_ID; + pr_info("x2AVIC enabled (max %u vCPUs)\n", x2avic_max_physical_id + 1); + } else { svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true; + } /* * Disable IPI virtualization for AMD Family 17h CPUs (Zen1 and Zen2) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index da6e80b3ac35..c81005b24522 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -613,6 +613,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 struct kvm_vcpu *vcpu = &svm->vcpu; nested_vmcb02_compute_g_pat(svm); + vmcb_mark_dirty(vmcb02, VMCB_NPT); /* Load the nested guest state */ if (svm->nested.vmcb12_gpa != svm->nested.last_vmcb12_gpa) { @@ -751,6 +752,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.nested_ctl = vmcb01->control.nested_ctl; vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa; vmcb02->control.msrpm_base_pa = vmcb01->control.msrpm_base_pa; + vmcb_mark_dirty(vmcb02, VMCB_PERM_MAP); /* * Stash vmcb02's counter if the guest hasn't moved past the guilty @@ -1430,16 +1432,6 @@ static int nested_svm_intercept(struct vcpu_svm *svm) case SVM_EXIT_IOIO: vmexit = nested_svm_intercept_ioio(svm); break; - case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { - if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) - vmexit = NESTED_EXIT_DONE; - break; - } - case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { - if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) - vmexit = NESTED_EXIT_DONE; - break; - } case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { /* * Host-intercepted exceptions have been checked already in diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0835c664fbfd..f59c65abe3cf 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -65,20 +65,24 @@ module_param_named(ciphertext_hiding_asids, nr_ciphertext_hiding_asids, uint, 04 #define AP_RESET_HOLD_NAE_EVENT 1 #define AP_RESET_HOLD_MSR_PROTO 2 -/* As defined by SEV-SNP Firmware ABI, under "Guest Policy". */ -#define SNP_POLICY_MASK_API_MINOR GENMASK_ULL(7, 0) -#define SNP_POLICY_MASK_API_MAJOR GENMASK_ULL(15, 8) -#define SNP_POLICY_MASK_SMT BIT_ULL(16) -#define SNP_POLICY_MASK_RSVD_MBO BIT_ULL(17) -#define SNP_POLICY_MASK_DEBUG BIT_ULL(19) -#define SNP_POLICY_MASK_SINGLE_SOCKET BIT_ULL(20) - -#define SNP_POLICY_MASK_VALID (SNP_POLICY_MASK_API_MINOR | \ - SNP_POLICY_MASK_API_MAJOR | \ - SNP_POLICY_MASK_SMT | \ - SNP_POLICY_MASK_RSVD_MBO | \ - SNP_POLICY_MASK_DEBUG | \ - SNP_POLICY_MASK_SINGLE_SOCKET) +/* + * SEV-SNP policy bits that can be supported by KVM. These include policy bits + * that have implementation support within KVM or policy bits that do not + * require implementation support within KVM to enforce the policy. + */ +#define KVM_SNP_POLICY_MASK_VALID (SNP_POLICY_MASK_API_MINOR | \ + SNP_POLICY_MASK_API_MAJOR | \ + SNP_POLICY_MASK_SMT | \ + SNP_POLICY_MASK_RSVD_MBO | \ + SNP_POLICY_MASK_DEBUG | \ + SNP_POLICY_MASK_SINGLE_SOCKET | \ + SNP_POLICY_MASK_CXL_ALLOW | \ + SNP_POLICY_MASK_MEM_AES_256_XTS | \ + SNP_POLICY_MASK_RAPL_DIS | \ + SNP_POLICY_MASK_CIPHERTEXT_HIDING_DRAM | \ + SNP_POLICY_MASK_PAGE_SWAP_DISABLE) + +static u64 snp_supported_policy_bits __ro_after_init; #define INITIAL_VMSA_GPA 0xFFFFFFFFF000 @@ -2143,6 +2147,10 @@ int sev_dev_get_attr(u32 group, u64 attr, u64 *val) *val = sev_supported_vmsa_features; return 0; + case KVM_X86_SNP_POLICY_BITS: + *val = snp_supported_policy_bits; + return 0; + default: return -ENXIO; } @@ -2207,7 +2215,7 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (params.flags) return -EINVAL; - if (params.policy & ~SNP_POLICY_MASK_VALID) + if (params.policy & ~snp_supported_policy_bits) return -EINVAL; /* Check for policy bits that must be set */ @@ -3100,8 +3108,11 @@ out: else if (sev_snp_supported) sev_snp_supported = is_sev_snp_initialized(); - if (sev_snp_supported) + if (sev_snp_supported) { + snp_supported_policy_bits = sev_get_snp_policy_bits() & + KVM_SNP_POLICY_MASK_VALID; nr_ciphertext_hiding_asids = init_args.max_snp_asid; + } /* * If ciphertext hiding is enabled, the joint SEV-ES/SEV-SNP @@ -5085,10 +5096,10 @@ struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu) /* Check if the SEV policy allows debugging */ if (sev_snp_guest(vcpu->kvm)) { - if (!(sev->policy & SNP_POLICY_DEBUG)) + if (!(sev->policy & SNP_POLICY_MASK_DEBUG)) return NULL; } else { - if (sev->policy & SEV_POLICY_NODBG) + if (sev->policy & SEV_POLICY_MASK_NODBG) return NULL; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9d29b2e7e855..f56c2d895011 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -272,6 +272,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) } static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, + int emul_type, bool commit_side_effects) { struct vcpu_svm *svm = to_svm(vcpu); @@ -293,7 +294,7 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, if (unlikely(!commit_side_effects)) old_rflags = svm->vmcb->save.rflags; - if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + if (!kvm_emulate_instruction(vcpu, emul_type)) return 0; if (unlikely(!commit_side_effects)) @@ -311,11 +312,13 @@ done: static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - return __svm_skip_emulated_instruction(vcpu, true); + return __svm_skip_emulated_instruction(vcpu, EMULTYPE_SKIP, true); } -static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) +static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu, u8 vector) { + const int emul_type = EMULTYPE_SKIP | EMULTYPE_SKIP_SOFT_INT | + EMULTYPE_SET_SOFT_INT_VECTOR(vector); unsigned long rip, old_rip = kvm_rip_read(vcpu); struct vcpu_svm *svm = to_svm(vcpu); @@ -331,7 +334,7 @@ static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) * in use, the skip must not commit any side effects such as clearing * the interrupt shadow or RFLAGS.RF. */ - if (!__svm_skip_emulated_instruction(vcpu, !nrips)) + if (!__svm_skip_emulated_instruction(vcpu, emul_type, !nrips)) return -EIO; rip = kvm_rip_read(vcpu); @@ -367,7 +370,7 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu) kvm_deliver_exception_payload(vcpu, ex); if (kvm_exception_is_soft(ex->vector) && - svm_update_soft_interrupt_rip(vcpu)) + svm_update_soft_interrupt_rip(vcpu, ex->vector)) return; svm->vmcb->control.event_inj = ex->vector @@ -1198,6 +1201,11 @@ void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb) svm->vmcb = target_vmcb->ptr; } +static int svm_vcpu_precreate(struct kvm *kvm) +{ + return avic_alloc_physical_id_table(kvm); +} + static int svm_vcpu_create(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; @@ -3442,13 +3450,8 @@ static bool svm_check_exit_valid(u64 exit_code) static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code) { - vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%llx\n", exit_code); dump_vmcb(vcpu); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_code; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + kvm_prepare_unexpected_reason_exit(vcpu, exit_code); return 0; } @@ -3633,11 +3636,12 @@ static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu) static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { + struct kvm_queued_interrupt *intr = &vcpu->arch.interrupt; struct vcpu_svm *svm = to_svm(vcpu); u32 type; - if (vcpu->arch.interrupt.soft) { - if (svm_update_soft_interrupt_rip(vcpu)) + if (intr->soft) { + if (svm_update_soft_interrupt_rip(vcpu, intr->nr)) return; type = SVM_EVTINJ_TYPE_SOFT; @@ -3645,12 +3649,10 @@ static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) type = SVM_EVTINJ_TYPE_INTR; } - trace_kvm_inj_virq(vcpu->arch.interrupt.nr, - vcpu->arch.interrupt.soft, reinjected); + trace_kvm_inj_virq(intr->nr, intr->soft, reinjected); ++vcpu->stat.irq_injections; - svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | - SVM_EVTINJ_VALID | type; + svm->vmcb->control.event_inj = intr->nr | SVM_EVTINJ_VALID | type; } void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, @@ -4251,7 +4253,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) svm_set_dr6(vcpu, DR6_ACTIVE_LOW); clgi(); - kvm_load_guest_xsave_state(vcpu); /* * Hardware only context switches DEBUGCTL if LBR virtualization is @@ -4294,7 +4295,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl) update_debugctlmsr(vcpu->arch.host_debugctl); - kvm_load_host_xsave_state(vcpu); stgi(); /* Any pending NMI will happen here */ @@ -4326,14 +4326,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET; - /* - * We need to handle MC intercepts here before the vcpu has a chance to - * change the physical cpu - */ - if (unlikely(svm->vmcb->control.exit_code == - SVM_EXIT_EXCP_BASE + MC_VECTOR)) - svm_handle_mce(vcpu); - trace_kvm_exit(vcpu, KVM_ISA_SVM); svm_complete_interrupts(vcpu); @@ -4526,31 +4518,45 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, case SVM_EXIT_WRITE_CR0: { unsigned long cr0, val; - if (info->intercept == x86_intercept_cr_write) + /* + * Adjust the exit code accordingly if a CR other than CR0 is + * being written, and skip straight to the common handling as + * only CR0 has an additional selective intercept. + */ + if (info->intercept == x86_intercept_cr_write && info->modrm_reg) { icpt_info.exit_code += info->modrm_reg; - - if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0 || - info->intercept == x86_intercept_clts) break; + } - if (!(vmcb12_is_intercept(&svm->nested.ctl, - INTERCEPT_SELECTIVE_CR0))) + /* + * Convert the exit_code to SVM_EXIT_CR0_SEL_WRITE if a + * selective CR0 intercept is triggered (the common logic will + * treat the selective intercept as being enabled). Note, the + * unconditional intercept has higher priority, i.e. this is + * only relevant if *only* the selective intercept is enabled. + */ + if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_CR0_WRITE) || + !(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))) break; - cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK; - val = info->src_val & ~SVM_CR0_SELECTIVE_MASK; + /* CLTS never triggers INTERCEPT_SELECTIVE_CR0 */ + if (info->intercept == x86_intercept_clts) + break; + /* LMSW always triggers INTERCEPT_SELECTIVE_CR0 */ if (info->intercept == x86_intercept_lmsw) { - cr0 &= 0xfUL; - val &= 0xfUL; - /* lmsw can't clear PE - catch this here */ - if (cr0 & X86_CR0_PE) - val |= X86_CR0_PE; + icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE; + break; } + /* + * MOV-to-CR0 only triggers INTERCEPT_SELECTIVE_CR0 if any bit + * other than SVM_CR0_SELECTIVE_MASK is changed. + */ + cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK; + val = info->src_val & ~SVM_CR0_SELECTIVE_MASK; if (cr0 ^ val) icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE; - break; } case SVM_EXIT_READ_DR0: @@ -4622,8 +4628,16 @@ out: static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { - if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + switch (to_svm(vcpu)->vmcb->control.exit_code) { + case SVM_EXIT_EXCP_BASE + MC_VECTOR: + svm_handle_mce(vcpu); + break; + case SVM_EXIT_INTR: vcpu->arch.at_instruction_boundary = true; + break; + default: + break; + } } static void svm_setup_mce(struct kvm_vcpu *vcpu) @@ -5012,6 +5026,7 @@ struct kvm_x86_ops svm_x86_ops __initdata = { .emergency_disable_virtualization_cpu = svm_emergency_disable_virtualization_cpu, .has_emulated_msr = svm_has_emulated_msr, + .vcpu_precreate = svm_vcpu_precreate, .vcpu_create = svm_vcpu_create, .vcpu_free = svm_vcpu_free, .vcpu_reset = svm_vcpu_reset, @@ -5316,7 +5331,9 @@ static __init int svm_hardware_setup(void) if (nested) { pr_info("Nested Virtualization enabled\n"); - kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); + kvm_enable_efer_bits(EFER_SVME); + if (!boot_cpu_has(X86_FEATURE_EFER_LMSLE_MBZ)) + kvm_enable_efer_bits(EFER_LMSLE); r = nested_svm_init_msrpm_merge_offsets(); if (r) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index dd78e6402345..9e151dbdef25 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -117,9 +117,6 @@ struct kvm_sev_info { cpumask_var_t have_run_cpus; /* CPUs that have done VMRUN for this VM. */ }; -#define SEV_POLICY_NODBG BIT_ULL(0) -#define SNP_POLICY_DEBUG BIT_ULL(19) - struct kvm_svm { struct kvm kvm; @@ -807,6 +804,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops; bool __init avic_hardware_setup(void); void avic_hardware_unsetup(void); +int avic_alloc_physical_id_table(struct kvm *kvm); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb); diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 235c4af6b692..3392bcadfb89 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -52,11 +52,23 @@ * there must not be any returns or indirect branches between this code * and vmentry. */ - movl SVM_spec_ctrl(%_ASM_DI), %eax - cmp PER_CPU_VAR(x86_spec_ctrl_current), %eax +#ifdef CONFIG_X86_64 + mov SVM_spec_ctrl(%rdi), %rdx + cmp PER_CPU_VAR(x86_spec_ctrl_current), %rdx + je 801b + movl %edx, %eax + shr $32, %rdx +#else + mov SVM_spec_ctrl(%edi), %eax + mov PER_CPU_VAR(x86_spec_ctrl_current), %ecx + xor %eax, %ecx + mov SVM_spec_ctrl + 4(%edi), %edx + mov PER_CPU_VAR(x86_spec_ctrl_current + 4), %esi + xor %edx, %esi + or %esi, %ecx je 801b +#endif mov $MSR_IA32_SPEC_CTRL, %ecx - xor %edx, %edx wrmsr jmp 801b .endm @@ -81,17 +93,31 @@ jnz 998f rdmsr movl %eax, SVM_spec_ctrl(%_ASM_DI) + movl %edx, SVM_spec_ctrl + 4(%_ASM_DI) 998: - /* Now restore the host value of the MSR if different from the guest's. */ - movl PER_CPU_VAR(x86_spec_ctrl_current), %eax - cmp SVM_spec_ctrl(%_ASM_DI), %eax +#ifdef CONFIG_X86_64 + mov PER_CPU_VAR(x86_spec_ctrl_current), %rdx + cmp SVM_spec_ctrl(%rdi), %rdx je 901b - xor %edx, %edx + movl %edx, %eax + shr $32, %rdx +#else + mov PER_CPU_VAR(x86_spec_ctrl_current), %eax + mov SVM_spec_ctrl(%edi), %esi + xor %eax, %esi + mov PER_CPU_VAR(x86_spec_ctrl_current + 4), %edx + mov SVM_spec_ctrl + 4(%edi), %edi + xor %edx, %edi + or %edi, %esi + je 901b +#endif wrmsr jmp 901b .endm +#define SVM_CLEAR_CPU_BUFFERS \ + ALTERNATIVE "", __CLEAR_CPU_BUFFERS, X86_FEATURE_CLEAR_CPU_BUF_VM /** * __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode @@ -134,7 +160,7 @@ SYM_FUNC_START(__svm_vcpu_run) mov %_ASM_ARG1, %_ASM_DI .endif - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX (and ESI on 32-bit), consumes RDI (@svm). */ RESTORE_GUEST_SPEC_CTRL /* @@ -170,7 +196,7 @@ SYM_FUNC_START(__svm_vcpu_run) mov VCPU_RDI(%_ASM_DI), %_ASM_DI /* Clobbers EFLAGS.ZF */ - VM_CLEAR_CPU_BUFFERS + SVM_CLEAR_CPU_BUFFERS /* Enter guest mode */ 3: vmrun %_ASM_AX @@ -211,7 +237,10 @@ SYM_FUNC_START(__svm_vcpu_run) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT - /* Clobbers RAX, RCX, RDX. */ + /* + * Clobbers RAX, RCX, RDX (and ESI, EDI on 32-bit), consumes RDI (@svm) + * and RSP (pointer to @spec_ctrl_intercepted). + */ RESTORE_HOST_SPEC_CTRL /* @@ -331,7 +360,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) mov %rdi, SEV_ES_RDI (%rdx) mov %rsi, SEV_ES_RSI (%rdx) - /* Clobbers RAX, RCX, RDX (@hostsa). */ + /* Clobbers RAX, RCX, and RDX (@hostsa), consumes RDI (@svm). */ RESTORE_GUEST_SPEC_CTRL /* Get svm->current_vmcb->pa into RAX. */ @@ -339,7 +368,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) mov KVM_VMCB_pa(%rax), %rax /* Clobbers EFLAGS.ZF */ - VM_CLEAR_CPU_BUFFERS + SVM_CLEAR_CPU_BUFFERS /* Enter guest mode */ 1: vmrun %rax diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 0eb2773b2ae2..a46ccd670785 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -831,6 +831,14 @@ static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp) return tdx_vcpu_ioctl(vcpu, argp); } +static int vt_vcpu_mem_enc_unlocked_ioctl(struct kvm_vcpu *vcpu, void __user *argp) +{ + if (!is_td_vcpu(vcpu)) + return -EINVAL; + + return tdx_vcpu_unlocked_ioctl(vcpu, argp); +} + static int vt_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private) { @@ -1005,6 +1013,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl), .vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl), + .vcpu_mem_enc_unlocked_ioctl = vt_op_tdx_only(vcpu_mem_enc_unlocked_ioctl), .gmem_max_mapping_level = vt_op_tdx_only(gmem_max_mapping_level) }; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bcea087b642f..40777278eabb 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -23,8 +23,8 @@ static bool __read_mostly enable_shadow_vmcs = 1; module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); -static bool __read_mostly nested_early_check = 0; -module_param(nested_early_check, bool, S_IRUGO); +static bool __ro_after_init warn_on_missed_cc; +module_param(warn_on_missed_cc, bool, 0444); #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK @@ -555,6 +555,9 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))) return -EINVAL; + if (CC(!nested_cpu_has_vid(vmcs12) && vmcs12->tpr_threshold >> 4)) + return -EINVAL; + return 0; } @@ -761,7 +764,7 @@ static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu, vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; - kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), + kvm_read_guest_cached(vcpu->kvm, ghc, get_shadow_vmcs12(vcpu), VMCS12_SIZE); } @@ -780,7 +783,7 @@ static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu, vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; - kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), + kvm_write_guest_cached(vcpu->kvm, ghc, get_shadow_vmcs12(vcpu), VMCS12_SIZE); } @@ -2296,15 +2299,6 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx) return; vmx->nested.vmcs02_initialized = true; - /* - * We don't care what the EPTP value is we just need to guarantee - * it's valid so we don't get a false positive when doing early - * consistency checks. - */ - if (enable_ept && nested_early_check) - vmcs_write64(EPT_POINTER, - construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL)); - if (vmx->ve_info) vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info)); @@ -2749,7 +2743,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); vcpu->arch.pat = vmcs12->guest_ia32_pat; } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); + vmcs_write64(GUEST_IA32_PAT, vcpu->arch.pat); } vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( @@ -2961,6 +2955,10 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, } } + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING) && + CC(!vmcs12->tsc_multiplier)) + return -EINVAL; + return 0; } @@ -3078,6 +3076,38 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return 0; } +static int nested_vmx_check_controls_late(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + void *vapic = to_vmx(vcpu)->nested.virtual_apic_map.hva; + u32 vtpr = vapic ? (*(u32 *)(vapic + APIC_TASKPRI)) >> 4 : 0; + + /* + * Don't bother with the consistency checks if KVM isn't configured to + * WARN on missed consistency checks, as KVM needs to rely on hardware + * to fully detect an illegal vTPR vs. TRP Threshold combination due to + * the vTPR being writable by L1 at all times (it's an in-memory value, + * not a VMCS field). I.e. even if the check passes now, it might fail + * at the actual VM-Enter. + * + * Keying off the module param also allows treating an invalid vAPIC + * mapping as a consistency check failure without increasing the risk + * of breaking a "real" VM. + */ + if (!warn_on_missed_cc) + return 0; + + if ((exec_controls_get(to_vmx(vcpu)) & CPU_BASED_TPR_SHADOW) && + nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW) && + !nested_cpu_has_vid(vmcs12) && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) && + (CC(!vapic) || + CC((vmcs12->tpr_threshold & GENMASK(3, 0)) > (vtpr & GENMASK(3, 0))))) + return -EINVAL; + + return 0; +} + static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -3333,84 +3363,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return 0; } -static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; - bool vm_fail; - - if (!nested_early_check) - return 0; - - if (vmx->msr_autoload.host.nr) - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); - if (vmx->msr_autoload.guest.nr) - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); - - preempt_disable(); - - vmx_prepare_switch_to_guest(vcpu); - - /* - * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS, - * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to - * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e. - * there is no need to preserve other bits or save/restore the field. - */ - vmcs_writel(GUEST_RFLAGS, 0); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - - cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { - vmcs_writel(HOST_CR4, cr4); - vmx->loaded_vmcs->host_state.cr4 = cr4; - } - - vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - __vmx_vcpu_run_flags(vmx)); - - if (vmx->msr_autoload.host.nr) - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); - if (vmx->msr_autoload.guest.nr) - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); - - if (vm_fail) { - u32 error = vmcs_read32(VM_INSTRUCTION_ERROR); - - preempt_enable(); - - trace_kvm_nested_vmenter_failed( - "early hardware check VM-instruction error: ", error); - WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD); - return 1; - } - - /* - * VMExit clears RFLAGS.IF and DR7, even on a consistency check. - */ - if (hw_breakpoint_active()) - set_debugreg(__this_cpu_read(cpu_dr7), 7); - local_irq_enable(); - preempt_enable(); - - /* - * A non-failing VMEntry means we somehow entered guest mode with - * an illegal RIP, and that's just the tip of the iceberg. There - * is no telling what memory has been modified or what state has - * been exposed to unknown code. Hitting this all but guarantees - * a (very critical) hardware issue. - */ - WARN_ON(!(vmcs_read32(VM_EXIT_REASON) & - VMX_EXIT_REASONS_FAILED_VMENTRY)); - - return 0; -} - #ifdef CONFIG_KVM_HYPERV static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { @@ -3667,22 +3619,18 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, &vmx->nested.pre_vmenter_ssp_tbl); /* - * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and* - * nested early checks are disabled. In the event of a "late" VM-Fail, - * i.e. a VM-Fail detected by hardware but not KVM, KVM must unwind its - * software model to the pre-VMEntry host state. When EPT is disabled, - * GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, which causes - * nested_vmx_restore_host_state() to corrupt vcpu->arch.cr3. Stuffing - * vmcs01.GUEST_CR3 results in the unwind naturally setting arch.cr3 to - * the correct value. Smashing vmcs01.GUEST_CR3 is safe because nested - * VM-Exits, and the unwind, reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is - * guaranteed to be overwritten with a shadow CR3 prior to re-entering - * L1. Don't stuff vmcs01.GUEST_CR3 when using nested early checks as - * KVM modifies vcpu->arch.cr3 if and only if the early hardware checks - * pass, and early VM-Fails do not reset KVM's MMU, i.e. the VM-Fail - * path would need to manually save/restore vmcs01.GUEST_CR3. + * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled. In the + * event of a "late" VM-Fail, i.e. a VM-Fail detected by hardware but + * not KVM, KVM must unwind its software model to the pre-VM-Entry host + * state. When EPT is disabled, GUEST_CR3 holds KVM's shadow CR3, not + * L1's "real" CR3, which causes nested_vmx_restore_host_state() to + * corrupt vcpu->arch.cr3. Stuffing vmcs01.GUEST_CR3 results in the + * unwind naturally setting arch.cr3 to the correct value. Smashing + * vmcs01.GUEST_CR3 is safe because nested VM-Exits, and the unwind, + * reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is guaranteed to be + * overwritten with a shadow CR3 prior to re-entering L1. */ - if (!enable_ept && !nested_early_check) + if (!enable_ept) vmcs_writel(GUEST_CR3, vcpu->arch.cr3); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); @@ -3695,7 +3643,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, return NVMX_VMENTRY_KVM_INTERNAL_ERROR; } - if (nested_vmx_check_vmentry_hw(vcpu)) { + if (nested_vmx_check_controls_late(vcpu, vmcs12)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); return NVMX_VMENTRY_VMFAIL; } @@ -3880,7 +3828,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) goto vmentry_failed; /* Hide L1D cache contents from the nested guest. */ - vmx->vcpu.arch.l1tf_flush_l1d = true; + kvm_request_l1tf_flush_l1d(); /* * Must happen outside of nested_vmx_enter_non_root_mode() as it will @@ -5164,12 +5112,13 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* * The only expected VM-instruction error is "VM entry with * invalid control field(s)." Anything else indicates a - * problem with L0. And we should never get here with a - * VMFail of any type if early consistency checks are enabled. + * problem with L0. */ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) != VMXERR_ENTRY_INVALID_CONTROL_FIELD); - WARN_ON_ONCE(nested_early_check); + + /* VM-Fail at VM-Entry means KVM missed a consistency check. */ + WARN_ON_ONCE(warn_on_missed_cc); } /* diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index 2f20fb170def..6a87a12135fb 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,12 +2,8 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME_SHIFT 0 -#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 -#define VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO_SHIFT 2 - -#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) -#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) -#define VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO BIT(VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO_SHIFT) +#define VMX_RUN_VMRESUME BIT(0) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(1) +#define VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO BIT(2) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 0a49c863c811..2d7a4d52ccfb 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -24,20 +24,33 @@ #undef pr_fmt #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#define pr_tdx_error(__fn, __err) \ - pr_err_ratelimited("SEAMCALL %s failed: 0x%llx\n", #__fn, __err) +#define __TDX_BUG_ON(__err, __f, __kvm, __fmt, __args...) \ +({ \ + struct kvm *_kvm = (__kvm); \ + bool __ret = !!(__err); \ + \ + if (WARN_ON_ONCE(__ret && (!_kvm || !_kvm->vm_bugged))) { \ + if (_kvm) \ + kvm_vm_bugged(_kvm); \ + pr_err_ratelimited("SEAMCALL " __f " failed: 0x%llx" __fmt "\n",\ + __err, __args); \ + } \ + unlikely(__ret); \ +}) + +#define TDX_BUG_ON(__err, __fn, __kvm) \ + __TDX_BUG_ON(__err, #__fn, __kvm, "%s", "") + +#define TDX_BUG_ON_1(__err, __fn, a1, __kvm) \ + __TDX_BUG_ON(__err, #__fn, __kvm, ", " #a1 " 0x%llx", a1) + +#define TDX_BUG_ON_2(__err, __fn, a1, a2, __kvm) \ + __TDX_BUG_ON(__err, #__fn, __kvm, ", " #a1 " 0x%llx, " #a2 " 0x%llx", a1, a2) + +#define TDX_BUG_ON_3(__err, __fn, a1, a2, a3, __kvm) \ + __TDX_BUG_ON(__err, #__fn, __kvm, ", " #a1 " 0x%llx, " #a2 ", 0x%llx, " #a3 " 0x%llx", \ + a1, a2, a3) -#define __pr_tdx_error_N(__fn_str, __err, __fmt, ...) \ - pr_err_ratelimited("SEAMCALL " __fn_str " failed: 0x%llx, " __fmt, __err, __VA_ARGS__) - -#define pr_tdx_error_1(__fn, __err, __rcx) \ - __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx\n", __rcx) - -#define pr_tdx_error_2(__fn, __err, __rcx, __rdx) \ - __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx\n", __rcx, __rdx) - -#define pr_tdx_error_3(__fn, __err, __rcx, __rdx, __r8) \ - __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx, r8 0x%llx\n", __rcx, __rdx, __r8) bool enable_tdx __ro_after_init; module_param_named(tdx, enable_tdx, bool, 0444); @@ -281,25 +294,34 @@ static inline void tdx_disassociate_vp(struct kvm_vcpu *vcpu) vcpu->cpu = -1; } -static void tdx_no_vcpus_enter_start(struct kvm *kvm) -{ - struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); - - lockdep_assert_held_write(&kvm->mmu_lock); - - WRITE_ONCE(kvm_tdx->wait_for_sept_zap, true); - - kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE); -} - -static void tdx_no_vcpus_enter_stop(struct kvm *kvm) -{ - struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); - - lockdep_assert_held_write(&kvm->mmu_lock); - - WRITE_ONCE(kvm_tdx->wait_for_sept_zap, false); -} +/* + * Execute a SEAMCALL related to removing/blocking S-EPT entries, with a single + * retry (if necessary) after forcing vCPUs to exit and wait for the operation + * to complete. All flows that remove/block S-EPT entries run with mmu_lock + * held for write, i.e. are mutually exclusive with each other, but they aren't + * mutually exclusive with running vCPUs, and so can fail with "operand busy" + * if a vCPU acquires a relevant lock in the TDX-Module, e.g. when doing TDCALL. + * + * Note, the retry is guaranteed to succeed, absent KVM and/or TDX-Module bugs. + */ +#define tdh_do_no_vcpus(tdh_func, kvm, args...) \ +({ \ + struct kvm_tdx *__kvm_tdx = to_kvm_tdx(kvm); \ + u64 __err; \ + \ + lockdep_assert_held_write(&kvm->mmu_lock); \ + \ + __err = tdh_func(args); \ + if (unlikely(tdx_operand_busy(__err))) { \ + WRITE_ONCE(__kvm_tdx->wait_for_sept_zap, true); \ + kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE); \ + \ + __err = tdh_func(args); \ + \ + WRITE_ONCE(__kvm_tdx->wait_for_sept_zap, false); \ + } \ + __err; \ +}) /* TDH.PHYMEM.PAGE.RECLAIM is allowed only when destroying the TD. */ static int __tdx_reclaim_page(struct page *page) @@ -313,10 +335,9 @@ static int __tdx_reclaim_page(struct page *page) * before the HKID is released and control pages have also been * released at this point, so there is no possibility of contention. */ - if (WARN_ON_ONCE(err)) { - pr_tdx_error_3(TDH_PHYMEM_PAGE_RECLAIM, err, rcx, rdx, r8); + if (TDX_BUG_ON_3(err, TDH_PHYMEM_PAGE_RECLAIM, rcx, rdx, r8, NULL)) return -EIO; - } + return 0; } @@ -404,8 +425,8 @@ static void tdx_flush_vp_on_cpu(struct kvm_vcpu *vcpu) return; smp_call_function_single(cpu, tdx_flush_vp, &arg, 1); - if (KVM_BUG_ON(arg.err, vcpu->kvm)) - pr_tdx_error(TDH_VP_FLUSH, arg.err); + + TDX_BUG_ON(arg.err, TDH_VP_FLUSH, vcpu->kvm); } void tdx_disable_virtualization_cpu(void) @@ -464,8 +485,7 @@ static void smp_func_do_phymem_cache_wb(void *unused) } out: - if (WARN_ON_ONCE(err)) - pr_tdx_error(TDH_PHYMEM_CACHE_WB, err); + TDX_BUG_ON(err, TDH_PHYMEM_CACHE_WB, NULL); } void tdx_mmu_release_hkid(struct kvm *kvm) @@ -504,8 +524,7 @@ void tdx_mmu_release_hkid(struct kvm *kvm) err = tdh_mng_vpflushdone(&kvm_tdx->td); if (err == TDX_FLUSHVP_NOT_DONE) goto out; - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error(TDH_MNG_VPFLUSHDONE, err); + if (TDX_BUG_ON(err, TDH_MNG_VPFLUSHDONE, kvm)) { pr_err("tdh_mng_vpflushdone() failed. HKID %d is leaked.\n", kvm_tdx->hkid); goto out; @@ -528,8 +547,7 @@ void tdx_mmu_release_hkid(struct kvm *kvm) * tdh_mng_key_freeid() will fail. */ err = tdh_mng_key_freeid(&kvm_tdx->td); - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error(TDH_MNG_KEY_FREEID, err); + if (TDX_BUG_ON(err, TDH_MNG_KEY_FREEID, kvm)) { pr_err("tdh_mng_key_freeid() failed. HKID %d is leaked.\n", kvm_tdx->hkid); } else { @@ -580,10 +598,9 @@ static void tdx_reclaim_td_control_pages(struct kvm *kvm) * when it is reclaiming TDCS). */ err = tdh_phymem_page_wbinvd_tdr(&kvm_tdx->td); - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err); + if (TDX_BUG_ON(err, TDH_PHYMEM_PAGE_WBINVD, kvm)) return; - } + tdx_quirk_reset_page(kvm_tdx->td.tdr_page); __free_page(kvm_tdx->td.tdr_page); @@ -606,11 +623,8 @@ static int tdx_do_tdh_mng_key_config(void *param) /* TDX_RND_NO_ENTROPY related retries are handled by sc_retry() */ err = tdh_mng_key_config(&kvm_tdx->td); - - if (KVM_BUG_ON(err, &kvm_tdx->kvm)) { - pr_tdx_error(TDH_MNG_KEY_CONFIG, err); + if (TDX_BUG_ON(err, TDH_MNG_KEY_CONFIG, &kvm_tdx->kvm)) return -EIO; - } return 0; } @@ -763,25 +777,6 @@ static bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) return tdx_vcpu_state_details_intr_pending(vcpu_state_details); } -/* - * Compared to vmx_prepare_switch_to_guest(), there is not much to do - * as SEAMCALL/SEAMRET calls take care of most of save and restore. - */ -void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) -{ - struct vcpu_vt *vt = to_vt(vcpu); - - if (vt->guest_state_loaded) - return; - - if (likely(is_64bit_mm(current->mm))) - vt->msr_host_kernel_gs_base = current->thread.gsbase; - else - vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); - - vt->guest_state_loaded = true; -} - struct tdx_uret_msr { u32 msr; unsigned int slot; @@ -795,19 +790,38 @@ static struct tdx_uret_msr tdx_uret_msrs[] = { {.msr = MSR_TSC_AUX,}, }; -static void tdx_user_return_msr_update_cache(void) +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { + struct vcpu_vt *vt = to_vt(vcpu); int i; + if (vt->guest_state_loaded) + return; + + if (likely(is_64bit_mm(current->mm))) + vt->msr_host_kernel_gs_base = current->thread.gsbase; + else + vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); + + vt->guest_state_loaded = true; + + /* + * Explicitly set user-return MSRs that are clobbered by the TDX-Module + * if VP.ENTER succeeds, i.e. on TD-Exit, with the values that would be + * written by the TDX-Module. Don't rely on the TDX-Module to actually + * clobber the MSRs, as the contract is poorly defined and not upheld. + * E.g. the TDX-Module will synthesize an EPT Violation without doing + * VM-Enter if it suspects a zero-step attack, and never "restore" VMM + * state. + */ for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++) - kvm_user_return_msr_update_cache(tdx_uret_msrs[i].slot, - tdx_uret_msrs[i].defval); + kvm_set_user_return_msr(tdx_uret_msrs[i].slot, + tdx_uret_msrs[i].defval, -1ull); } static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu) { struct vcpu_vt *vt = to_vt(vcpu); - struct vcpu_tdx *tdx = to_tdx(vcpu); if (!vt->guest_state_loaded) return; @@ -815,11 +829,6 @@ static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu) ++vcpu->stat.host_state_reload; wrmsrl(MSR_KERNEL_GS_BASE, vt->msr_host_kernel_gs_base); - if (tdx->guest_entered) { - tdx_user_return_msr_update_cache(); - tdx->guest_entered = false; - } - vt->guest_state_loaded = false; } @@ -829,19 +838,52 @@ void tdx_vcpu_put(struct kvm_vcpu *vcpu) tdx_prepare_switch_to_host(vcpu); } +/* + * Life cycles for a TD and a vCPU: + * 1. KVM_CREATE_VM ioctl. + * TD state is TD_STATE_UNINITIALIZED. + * hkid is not assigned at this stage. + * 2. KVM_TDX_INIT_VM ioctl. + * TD transitions to TD_STATE_INITIALIZED. + * hkid is assigned after this stage. + * 3. KVM_CREATE_VCPU ioctl. (only when TD is TD_STATE_INITIALIZED). + * 3.1 tdx_vcpu_create() transitions vCPU state to VCPU_TD_STATE_UNINITIALIZED. + * 3.2 vcpu_load() and vcpu_put() in kvm_arch_vcpu_create(). + * 3.3 (conditional) if any error encountered after kvm_arch_vcpu_create() + * kvm_arch_vcpu_destroy() --> tdx_vcpu_free(). + * 4. KVM_TDX_INIT_VCPU ioctl. + * tdx_vcpu_init() transitions vCPU state to VCPU_TD_STATE_INITIALIZED. + * vCPU control structures are allocated at this stage. + * 5. kvm_destroy_vm(). + * 5.1 tdx_mmu_release_hkid(): (1) tdh_vp_flush(), disassociates all vCPUs. + * (2) puts hkid to !assigned state. + * 5.2 kvm_destroy_vcpus() --> tdx_vcpu_free(): + * transitions vCPU to VCPU_TD_STATE_UNINITIALIZED state. + * 5.3 tdx_vm_destroy() + * transitions TD to TD_STATE_UNINITIALIZED state. + * + * tdx_vcpu_free() can be invoked only at 3.3 or 5.2. + * - If at 3.3, hkid is still assigned, but the vCPU must be in + * VCPU_TD_STATE_UNINITIALIZED state. + * - if at 5.2, hkid must be !assigned and all vCPUs must be in + * VCPU_TD_STATE_INITIALIZED state and have been dissociated. + */ void tdx_vcpu_free(struct kvm_vcpu *vcpu) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); struct vcpu_tdx *tdx = to_tdx(vcpu); int i; + if (vcpu->cpu != -1) { + KVM_BUG_ON(tdx->state == VCPU_TD_STATE_INITIALIZED, vcpu->kvm); + tdx_flush_vp_on_cpu(vcpu); + return; + } + /* * It is not possible to reclaim pages while hkid is assigned. It might - * be assigned if: - * 1. the TD VM is being destroyed but freeing hkid failed, in which - * case the pages are leaked - * 2. TD VCPU creation failed and this on the error path, in which case - * there is nothing to do anyway + * be assigned if the TD VM is being destroyed but freeing hkid failed, + * in which case the pages are leaked. */ if (is_hkid_assigned(kvm_tdx)) return; @@ -856,7 +898,7 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu) } if (tdx->vp.tdvpr_page) { tdx_reclaim_control_page(tdx->vp.tdvpr_page); - tdx->vp.tdvpr_page = 0; + tdx->vp.tdvpr_page = NULL; tdx->vp.tdvpr_pa = 0; } @@ -1059,7 +1101,6 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) update_debugctlmsr(vcpu->arch.host_debugctl); tdx_load_host_xsave_state(vcpu); - tdx->guest_entered = true; vcpu->arch.regs_avail &= TDX_REGS_AVAIL_SET; @@ -1069,9 +1110,6 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) if (unlikely((tdx->vp_enter_ret & TDX_SW_ERROR) == TDX_SW_ERROR)) return EXIT_FASTPATH_NONE; - if (unlikely(vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY)) - kvm_machine_check(); - trace_kvm_exit(vcpu, KVM_ISA_VMX); if (unlikely(tdx_failed_vmentry(vcpu))) @@ -1583,137 +1621,79 @@ void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level) td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa); } -static void tdx_unpin(struct kvm *kvm, struct page *page) +static int tdx_mem_page_add(struct kvm *kvm, gfn_t gfn, enum pg_level level, + kvm_pfn_t pfn) { - put_page(page); + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + u64 err, entry, level_state; + gpa_t gpa = gfn_to_gpa(gfn); + + lockdep_assert_held(&kvm->slots_lock); + + if (KVM_BUG_ON(kvm->arch.pre_fault_allowed, kvm) || + KVM_BUG_ON(!kvm_tdx->page_add_src, kvm)) + return -EIO; + + err = tdh_mem_page_add(&kvm_tdx->td, gpa, pfn_to_page(pfn), + kvm_tdx->page_add_src, &entry, &level_state); + if (unlikely(tdx_operand_busy(err))) + return -EBUSY; + + if (TDX_BUG_ON_2(err, TDH_MEM_PAGE_ADD, entry, level_state, kvm)) + return -EIO; + + return 0; } static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn, - enum pg_level level, struct page *page) + enum pg_level level, kvm_pfn_t pfn) { int tdx_level = pg_level_to_tdx_sept_level(level); struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + struct page *page = pfn_to_page(pfn); gpa_t gpa = gfn_to_gpa(gfn); u64 entry, level_state; u64 err; err = tdh_mem_page_aug(&kvm_tdx->td, gpa, tdx_level, page, &entry, &level_state); - if (unlikely(tdx_operand_busy(err))) { - tdx_unpin(kvm, page); + if (unlikely(tdx_operand_busy(err))) return -EBUSY; - } - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error_2(TDH_MEM_PAGE_AUG, err, entry, level_state); - tdx_unpin(kvm, page); + if (TDX_BUG_ON_2(err, TDH_MEM_PAGE_AUG, entry, level_state, kvm)) return -EIO; - } - - return 0; -} - -/* - * KVM_TDX_INIT_MEM_REGION calls kvm_gmem_populate() to map guest pages; the - * callback tdx_gmem_post_populate() then maps pages into private memory. - * through the a seamcall TDH.MEM.PAGE.ADD(). The SEAMCALL also requires the - * private EPT structures for the page to have been built before, which is - * done via kvm_tdp_map_page(). nr_premapped counts the number of pages that - * were added to the EPT structures but not added with TDH.MEM.PAGE.ADD(). - * The counter has to be zero on KVM_TDX_FINALIZE_VM, to ensure that there - * are no half-initialized shared EPT pages. - */ -static int tdx_mem_page_record_premap_cnt(struct kvm *kvm, gfn_t gfn, - enum pg_level level, kvm_pfn_t pfn) -{ - struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); - - if (KVM_BUG_ON(kvm->arch.pre_fault_allowed, kvm)) - return -EINVAL; - /* nr_premapped will be decreased when tdh_mem_page_add() is called. */ - atomic64_inc(&kvm_tdx->nr_premapped); return 0; } static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, kvm_pfn_t pfn) + enum pg_level level, u64 mirror_spte) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); - struct page *page = pfn_to_page(pfn); + kvm_pfn_t pfn = spte_to_pfn(mirror_spte); /* TODO: handle large pages. */ if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm)) - return -EINVAL; + return -EIO; - /* - * Because guest_memfd doesn't support page migration with - * a_ops->migrate_folio (yet), no callback is triggered for KVM on page - * migration. Until guest_memfd supports page migration, prevent page - * migration. - * TODO: Once guest_memfd introduces callback on page migration, - * implement it and remove get_page/put_page(). - */ - get_page(page); + WARN_ON_ONCE(!is_shadow_present_pte(mirror_spte) || + (mirror_spte & VMX_EPT_RWX_MASK) != VMX_EPT_RWX_MASK); /* - * Read 'pre_fault_allowed' before 'kvm_tdx->state'; see matching - * barrier in tdx_td_finalize(). + * Ensure pre_fault_allowed is read by kvm_arch_vcpu_pre_fault_memory() + * before kvm_tdx->state. Userspace must not be allowed to pre-fault + * arbitrary memory until the initial memory image is finalized. Pairs + * with the smp_wmb() in tdx_td_finalize(). */ smp_rmb(); - if (likely(kvm_tdx->state == TD_STATE_RUNNABLE)) - return tdx_mem_page_aug(kvm, gfn, level, page); - - return tdx_mem_page_record_premap_cnt(kvm, gfn, level, pfn); -} - -static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, struct page *page) -{ - int tdx_level = pg_level_to_tdx_sept_level(level); - struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); - gpa_t gpa = gfn_to_gpa(gfn); - u64 err, entry, level_state; - - /* TODO: handle large pages. */ - if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm)) - return -EINVAL; - - if (KVM_BUG_ON(!is_hkid_assigned(kvm_tdx), kvm)) - return -EINVAL; /* - * When zapping private page, write lock is held. So no race condition - * with other vcpu sept operation. - * Race with TDH.VP.ENTER due to (0-step mitigation) and Guest TDCALLs. + * If the TD isn't finalized/runnable, then userspace is initializing + * the VM image via KVM_TDX_INIT_MEM_REGION; ADD the page to the TD. */ - err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry, - &level_state); - - if (unlikely(tdx_operand_busy(err))) { - /* - * The second retry is expected to succeed after kicking off all - * other vCPUs and prevent them from invoking TDH.VP.ENTER. - */ - tdx_no_vcpus_enter_start(kvm); - err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry, - &level_state); - tdx_no_vcpus_enter_stop(kvm); - } - - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error_2(TDH_MEM_PAGE_REMOVE, err, entry, level_state); - return -EIO; - } - - err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page); + if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE)) + return tdx_mem_page_add(kvm, gfn, level, pfn); - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err); - return -EIO; - } - tdx_quirk_reset_page(page); - tdx_unpin(kvm, page); - return 0; + return tdx_mem_page_aug(kvm, gfn, level, pfn); } static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, @@ -1729,81 +1709,13 @@ static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, if (unlikely(tdx_operand_busy(err))) return -EBUSY; - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error_2(TDH_MEM_SEPT_ADD, err, entry, level_state); + if (TDX_BUG_ON_2(err, TDH_MEM_SEPT_ADD, entry, level_state, kvm)) return -EIO; - } return 0; } /* - * Check if the error returned from a SEPT zap SEAMCALL is due to that a page is - * mapped by KVM_TDX_INIT_MEM_REGION without tdh_mem_page_add() being called - * successfully. - * - * Since tdh_mem_sept_add() must have been invoked successfully before a - * non-leaf entry present in the mirrored page table, the SEPT ZAP related - * SEAMCALLs should not encounter err TDX_EPT_WALK_FAILED. They should instead - * find TDX_EPT_ENTRY_STATE_INCORRECT due to an empty leaf entry found in the - * SEPT. - * - * Further check if the returned entry from SEPT walking is with RWX permissions - * to filter out anything unexpected. - * - * Note: @level is pg_level, not the tdx_level. The tdx_level extracted from - * level_state returned from a SEAMCALL error is the same as that passed into - * the SEAMCALL. - */ -static int tdx_is_sept_zap_err_due_to_premap(struct kvm_tdx *kvm_tdx, u64 err, - u64 entry, int level) -{ - if (!err || kvm_tdx->state == TD_STATE_RUNNABLE) - return false; - - if (err != (TDX_EPT_ENTRY_STATE_INCORRECT | TDX_OPERAND_ID_RCX)) - return false; - - if ((is_last_spte(entry, level) && (entry & VMX_EPT_RWX_MASK))) - return false; - - return true; -} - -static int tdx_sept_zap_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, struct page *page) -{ - int tdx_level = pg_level_to_tdx_sept_level(level); - struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); - gpa_t gpa = gfn_to_gpa(gfn) & KVM_HPAGE_MASK(level); - u64 err, entry, level_state; - - /* For now large page isn't supported yet. */ - WARN_ON_ONCE(level != PG_LEVEL_4K); - - err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state); - - if (unlikely(tdx_operand_busy(err))) { - /* After no vCPUs enter, the second retry is expected to succeed */ - tdx_no_vcpus_enter_start(kvm); - err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state); - tdx_no_vcpus_enter_stop(kvm); - } - if (tdx_is_sept_zap_err_due_to_premap(kvm_tdx, err, entry, level) && - !KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm)) { - atomic64_dec(&kvm_tdx->nr_premapped); - tdx_unpin(kvm, page); - return 0; - } - - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error_2(TDH_MEM_RANGE_BLOCK, err, entry, level_state); - return -EIO; - } - return 1; -} - -/* * Ensure shared and private EPTs to be flushed on all vCPUs. * tdh_mem_track() is the only caller that increases TD epoch. An increase in * the TD epoch (e.g., to value "N + 1") is successful only if no vCPUs are @@ -1836,18 +1748,15 @@ static void tdx_track(struct kvm *kvm) if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE)) return; + /* + * The full sequence of TDH.MEM.TRACK and forcing vCPUs out of guest + * mode must be serialized, as TDH.MEM.TRACK will fail if the previous + * tracking epoch hasn't completed. + */ lockdep_assert_held_write(&kvm->mmu_lock); - err = tdh_mem_track(&kvm_tdx->td); - if (unlikely(tdx_operand_busy(err))) { - /* After no vCPUs enter, the second retry is expected to succeed */ - tdx_no_vcpus_enter_start(kvm); - err = tdh_mem_track(&kvm_tdx->td); - tdx_no_vcpus_enter_stop(kvm); - } - - if (KVM_BUG_ON(err, kvm)) - pr_tdx_error(TDH_MEM_TRACK, err); + err = tdh_do_no_vcpus(tdh_mem_track, kvm, &kvm_tdx->td); + TDX_BUG_ON(err, TDH_MEM_TRACK, kvm); kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE); } @@ -1866,7 +1775,7 @@ static int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, * and slot move/deletion. */ if (KVM_BUG_ON(is_hkid_assigned(kvm_tdx), kvm)) - return -EINVAL; + return -EIO; /* * The HKID assigned to this TD was already freed and cache was @@ -1875,11 +1784,16 @@ static int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn, return tdx_reclaim_page(virt_to_page(private_spt)); } -static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, - enum pg_level level, kvm_pfn_t pfn) +static void tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, + enum pg_level level, u64 mirror_spte) { - struct page *page = pfn_to_page(pfn); - int ret; + struct page *page = pfn_to_page(spte_to_pfn(mirror_spte)); + int tdx_level = pg_level_to_tdx_sept_level(level); + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + gpa_t gpa = gfn_to_gpa(gfn); + u64 err, entry, level_state; + + lockdep_assert_held_write(&kvm->mmu_lock); /* * HKID is released after all private pages have been removed, and set @@ -1887,11 +1801,16 @@ static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, * there can't be anything populated in the private EPT. */ if (KVM_BUG_ON(!is_hkid_assigned(to_kvm_tdx(kvm)), kvm)) - return -EINVAL; + return; - ret = tdx_sept_zap_private_spte(kvm, gfn, level, page); - if (ret <= 0) - return ret; + /* TODO: handle large pages. */ + if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm)) + return; + + err = tdh_do_no_vcpus(tdh_mem_range_block, kvm, &kvm_tdx->td, gpa, + tdx_level, &entry, &level_state); + if (TDX_BUG_ON_2(err, TDH_MEM_RANGE_BLOCK, entry, level_state, kvm)) + return; /* * TDX requires TLB tracking before dropping private page. Do @@ -1899,7 +1818,21 @@ static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn, */ tdx_track(kvm); - return tdx_sept_drop_private_spte(kvm, gfn, level, page); + /* + * When zapping private page, write lock is held. So no race condition + * with other vcpu sept operation. + * Race with TDH.VP.ENTER due to (0-step mitigation) and Guest TDCALLs. + */ + err = tdh_do_no_vcpus(tdh_mem_page_remove, kvm, &kvm_tdx->td, gpa, + tdx_level, &entry, &level_state); + if (TDX_BUG_ON_2(err, TDH_MEM_PAGE_REMOVE, entry, level_state, kvm)) + return; + + err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page); + if (TDX_BUG_ON(err, TDH_PHYMEM_PAGE_WBINVD, kvm)) + return; + + tdx_quirk_reset_page(page); } void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, @@ -2145,11 +2078,7 @@ int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) } unhandled_exit: - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = vp_enter_ret; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + kvm_prepare_unexpected_reason_exit(vcpu, vp_enter_ret); return 0; } @@ -2282,37 +2211,28 @@ static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) if (cmd->flags) return -EINVAL; - caps = kzalloc(sizeof(*caps) + - sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config, - GFP_KERNEL); - if (!caps) - return -ENOMEM; - user_caps = u64_to_user_ptr(cmd->data); - if (get_user(nr_user_entries, &user_caps->cpuid.nent)) { - ret = -EFAULT; - goto out; - } + if (get_user(nr_user_entries, &user_caps->cpuid.nent)) + return -EFAULT; - if (nr_user_entries < td_conf->num_cpuid_config) { - ret = -E2BIG; - goto out; - } + if (nr_user_entries < td_conf->num_cpuid_config) + return -E2BIG; + + caps = kzalloc(struct_size(caps, cpuid.entries, + td_conf->num_cpuid_config), GFP_KERNEL); + if (!caps) + return -ENOMEM; ret = init_kvm_tdx_caps(td_conf, caps); if (ret) goto out; - if (copy_to_user(user_caps, caps, sizeof(*caps))) { + if (copy_to_user(user_caps, caps, struct_size(caps, cpuid.entries, + caps->cpuid.nent))) { ret = -EFAULT; goto out; } - if (copy_to_user(user_caps->cpuid.entries, caps->cpuid.entries, - caps->cpuid.nent * - sizeof(caps->cpuid.entries[0]))) - ret = -EFAULT; - out: /* kfree() accepts NULL. */ kfree(caps); @@ -2537,8 +2457,7 @@ static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, goto free_packages; } - if (WARN_ON_ONCE(err)) { - pr_tdx_error(TDH_MNG_CREATE, err); + if (TDX_BUG_ON(err, TDH_MNG_CREATE, kvm)) { ret = -EIO; goto free_packages; } @@ -2579,8 +2498,7 @@ static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, ret = -EAGAIN; goto teardown; } - if (WARN_ON_ONCE(err)) { - pr_tdx_error(TDH_MNG_ADDCX, err); + if (TDX_BUG_ON(err, TDH_MNG_ADDCX, kvm)) { ret = -EIO; goto teardown; } @@ -2597,8 +2515,7 @@ static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params, *seamcall_err = err; ret = -EINVAL; goto teardown; - } else if (WARN_ON_ONCE(err)) { - pr_tdx_error_1(TDH_MNG_INIT, err, rcx); + } else if (TDX_BUG_ON_1(err, TDH_MNG_INIT, rcx, kvm)) { ret = -EIO; goto teardown; } @@ -2642,7 +2559,7 @@ free_tdcs: free_tdr: if (tdr_page) __free_page(tdr_page); - kvm_tdx->td.tdr_page = 0; + kvm_tdx->td.tdr_page = NULL; free_hkid: tdx_hkid_free(kvm_tdx); @@ -2747,11 +2664,53 @@ err_out: return -EIO; } +typedef void *tdx_vm_state_guard_t; + +static tdx_vm_state_guard_t tdx_acquire_vm_state_locks(struct kvm *kvm) +{ + int r; + + mutex_lock(&kvm->lock); + + if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) { + r = -EBUSY; + goto out_err; + } + + r = kvm_lock_all_vcpus(kvm); + if (r) + goto out_err; + + /* + * Note the unintuitive ordering! vcpu->mutex must be taken outside + * kvm->slots_lock! + */ + mutex_lock(&kvm->slots_lock); + return kvm; + +out_err: + mutex_unlock(&kvm->lock); + return ERR_PTR(r); +} + +static void tdx_release_vm_state_locks(struct kvm *kvm) +{ + mutex_unlock(&kvm->slots_lock); + kvm_unlock_all_vcpus(kvm); + mutex_unlock(&kvm->lock); +} + +DEFINE_CLASS(tdx_vm_state_guard, tdx_vm_state_guard_t, + if (!IS_ERR(_T)) tdx_release_vm_state_locks(_T), + tdx_acquire_vm_state_locks(kvm), struct kvm *kvm); + static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd) { + struct kvm_tdx_init_vm __user *user_data = u64_to_user_ptr(cmd->data); struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); struct kvm_tdx_init_vm *init_vm; struct td_params *td_params = NULL; + u32 nr_user_entries; int ret; BUILD_BUG_ON(sizeof(*init_vm) != 256 + sizeof_field(struct kvm_tdx_init_vm, cpuid)); @@ -2763,28 +2722,16 @@ static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd) if (cmd->flags) return -EINVAL; - init_vm = kmalloc(sizeof(*init_vm) + - sizeof(init_vm->cpuid.entries[0]) * KVM_MAX_CPUID_ENTRIES, - GFP_KERNEL); - if (!init_vm) - return -ENOMEM; - - if (copy_from_user(init_vm, u64_to_user_ptr(cmd->data), sizeof(*init_vm))) { - ret = -EFAULT; - goto out; - } + if (get_user(nr_user_entries, &user_data->cpuid.nent)) + return -EFAULT; - if (init_vm->cpuid.nent > KVM_MAX_CPUID_ENTRIES) { - ret = -E2BIG; - goto out; - } + if (nr_user_entries > KVM_MAX_CPUID_ENTRIES) + return -E2BIG; - if (copy_from_user(init_vm->cpuid.entries, - u64_to_user_ptr(cmd->data) + sizeof(*init_vm), - flex_array_size(init_vm, cpuid.entries, init_vm->cpuid.nent))) { - ret = -EFAULT; - goto out; - } + init_vm = memdup_user(user_data, + struct_size(user_data, cpuid.entries, nr_user_entries)); + if (IS_ERR(init_vm)) + return PTR_ERR(init_vm); if (memchr_inv(init_vm->reserved, 0, sizeof(init_vm->reserved))) { ret = -EINVAL; @@ -2868,24 +2815,14 @@ static int tdx_td_finalize(struct kvm *kvm, struct kvm_tdx_cmd *cmd) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); - guard(mutex)(&kvm->slots_lock); - if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE) return -EINVAL; - /* - * Pages are pending for KVM_TDX_INIT_MEM_REGION to issue - * TDH.MEM.PAGE.ADD(). - */ - if (atomic64_read(&kvm_tdx->nr_premapped)) - return -EINVAL; cmd->hw_error = tdh_mr_finalize(&kvm_tdx->td); if (tdx_operand_busy(cmd->hw_error)) return -EBUSY; - if (KVM_BUG_ON(cmd->hw_error, kvm)) { - pr_tdx_error(TDH_MR_FINALIZE, cmd->hw_error); + if (TDX_BUG_ON(cmd->hw_error, TDH_MR_FINALIZE, kvm)) return -EIO; - } kvm_tdx->state = TD_STATE_RUNNABLE; /* TD_STATE_RUNNABLE must be set before 'pre_fault_allowed' */ @@ -2894,27 +2831,38 @@ static int tdx_td_finalize(struct kvm *kvm, struct kvm_tdx_cmd *cmd) return 0; } -int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) +static int tdx_get_cmd(void __user *argp, struct kvm_tdx_cmd *cmd) { - struct kvm_tdx_cmd tdx_cmd; - int r; - - if (copy_from_user(&tdx_cmd, argp, sizeof(struct kvm_tdx_cmd))) + if (copy_from_user(cmd, argp, sizeof(*cmd))) return -EFAULT; /* - * Userspace should never set hw_error. It is used to fill - * hardware-defined error by the kernel. + * Userspace should never set hw_error. KVM writes hw_error to report + * hardware-defined error back to userspace. */ - if (tdx_cmd.hw_error) + if (cmd->hw_error) return -EINVAL; - mutex_lock(&kvm->lock); + return 0; +} + +int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) +{ + struct kvm_tdx_cmd tdx_cmd; + int r; + + r = tdx_get_cmd(argp, &tdx_cmd); + if (r) + return r; + + if (tdx_cmd.id == KVM_TDX_CAPABILITIES) + return tdx_get_capabilities(&tdx_cmd); + + CLASS(tdx_vm_state_guard, guard)(kvm); + if (IS_ERR(guard)) + return PTR_ERR(guard); switch (tdx_cmd.id) { - case KVM_TDX_CAPABILITIES: - r = tdx_get_capabilities(&tdx_cmd); - break; case KVM_TDX_INIT_VM: r = tdx_td_init(kvm, &tdx_cmd); break; @@ -2922,15 +2870,12 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) r = tdx_td_finalize(kvm, &tdx_cmd); break; default: - r = -EINVAL; - goto out; + return -EINVAL; } if (copy_to_user(argp, &tdx_cmd, sizeof(struct kvm_tdx_cmd))) - r = -EFAULT; + return -EFAULT; -out: - mutex_unlock(&kvm->lock); return r; } @@ -2972,16 +2917,14 @@ static int tdx_td_vcpu_init(struct kvm_vcpu *vcpu, u64 vcpu_rcx) } err = tdh_vp_create(&kvm_tdx->td, &tdx->vp); - if (KVM_BUG_ON(err, vcpu->kvm)) { + if (TDX_BUG_ON(err, TDH_VP_CREATE, vcpu->kvm)) { ret = -EIO; - pr_tdx_error(TDH_VP_CREATE, err); goto free_tdcx; } for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) { err = tdh_vp_addcx(&tdx->vp, tdx->vp.tdcx_pages[i]); - if (KVM_BUG_ON(err, vcpu->kvm)) { - pr_tdx_error(TDH_VP_ADDCX, err); + if (TDX_BUG_ON(err, TDH_VP_ADDCX, vcpu->kvm)) { /* * Pages already added are reclaimed by the vcpu_free * method, but the rest are freed here. @@ -2994,10 +2937,19 @@ static int tdx_td_vcpu_init(struct kvm_vcpu *vcpu, u64 vcpu_rcx) } } - err = tdh_vp_init(&tdx->vp, vcpu_rcx, vcpu->vcpu_id); - if (KVM_BUG_ON(err, vcpu->kvm)) { - pr_tdx_error(TDH_VP_INIT, err); - return -EIO; + /* + * tdh_vp_init() can take an exclusive lock of the TDR resource inside + * the TDX-Module. The TDR resource is also taken as shared in several + * no-fail MMU paths, which could return TDX_OPERAND_BUSY on contention + * (TDX-Module locks are try-lock implementations with no slow path). + * Take mmu_lock for write to reflect the nature of the lock taken by + * the TDX-Module, and to ensure the no-fail MMU paths succeed, e.g. if + * a concurrent PUNCH_HOLE on guest_memfd triggers removal of SPTEs. + */ + scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { + err = tdh_vp_init(&tdx->vp, vcpu_rcx, vcpu->vcpu_id); + if (TDX_BUG_ON(err, TDH_VP_INIT, vcpu->kvm)) + return -EIO; } vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -3016,7 +2968,7 @@ free_tdcx: free_tdvpr: if (tdx->vp.tdvpr_page) __free_page(tdx->vp.tdvpr_page); - tdx->vp.tdvpr_page = 0; + tdx->vp.tdvpr_page = NULL; tdx->vp.tdvpr_pa = 0; return ret; @@ -3054,7 +3006,8 @@ static int tdx_vcpu_get_cpuid_leaf(struct kvm_vcpu *vcpu, u32 leaf, int *entry_i static int tdx_vcpu_get_cpuid(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) { - struct kvm_cpuid2 __user *output, *td_cpuid; + struct kvm_cpuid2 __user *output; + struct kvm_cpuid2 *td_cpuid; int r = 0, i = 0, leaf; u32 level; @@ -3167,15 +3120,15 @@ struct tdx_gmem_post_populate_arg { static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, void __user *src, int order, void *_arg) { - u64 error_code = PFERR_GUEST_FINAL_MASK | PFERR_PRIVATE_ACCESS; - struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); struct tdx_gmem_post_populate_arg *arg = _arg; - struct kvm_vcpu *vcpu = arg->vcpu; + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + u64 err, entry, level_state; gpa_t gpa = gfn_to_gpa(gfn); - u8 level = PG_LEVEL_4K; struct page *src_page; int ret, i; - u64 err, entry, level_state; + + if (KVM_BUG_ON(kvm_tdx->page_add_src, kvm)) + return -EIO; /* * Get the source page if it has been faulted in. Return failure if the @@ -3187,49 +3140,29 @@ static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, if (ret != 1) return -ENOMEM; - ret = kvm_tdp_map_page(vcpu, gpa, error_code, &level); - if (ret < 0) - goto out; - - /* - * The private mem cannot be zapped after kvm_tdp_map_page() - * because all paths are covered by slots_lock and the - * filemap invalidate lock. Check that they are indeed enough. - */ - if (IS_ENABLED(CONFIG_KVM_PROVE_MMU)) { - scoped_guard(read_lock, &kvm->mmu_lock) { - if (KVM_BUG_ON(!kvm_tdp_mmu_gpa_is_mapped(vcpu, gpa), kvm)) { - ret = -EIO; - goto out; - } - } - } + kvm_tdx->page_add_src = src_page; + ret = kvm_tdp_mmu_map_private_pfn(arg->vcpu, gfn, pfn); + kvm_tdx->page_add_src = NULL; - ret = 0; - err = tdh_mem_page_add(&kvm_tdx->td, gpa, pfn_to_page(pfn), - src_page, &entry, &level_state); - if (err) { - ret = unlikely(tdx_operand_busy(err)) ? -EBUSY : -EIO; - goto out; - } + put_page(src_page); - if (!KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm)) - atomic64_dec(&kvm_tdx->nr_premapped); + if (ret || !(arg->flags & KVM_TDX_MEASURE_MEMORY_REGION)) + return ret; - if (arg->flags & KVM_TDX_MEASURE_MEMORY_REGION) { - for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) { - err = tdh_mr_extend(&kvm_tdx->td, gpa + i, &entry, - &level_state); - if (err) { - ret = -EIO; - break; - } - } + /* + * Note, MR.EXTEND can fail if the S-EPT mapping is somehow removed + * between mapping the pfn and now, but slots_lock prevents memslot + * updates, filemap_invalidate_lock() prevents guest_memfd updates, + * mmu_notifier events can't reach S-EPT entries, and KVM's internal + * zapping flows are mutually exclusive with S-EPT mappings. + */ + for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) { + err = tdh_mr_extend(&kvm_tdx->td, gpa + i, &entry, &level_state); + if (TDX_BUG_ON_2(err, TDH_MR_EXTEND, entry, level_state, kvm)) + return -EIO; } -out: - put_page(src_page); - return ret; + return 0; } static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd) @@ -3245,8 +3178,6 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c if (tdx->state != VCPU_TD_STATE_INITIALIZED) return -EINVAL; - guard(mutex)(&kvm->slots_lock); - /* Once TD is finalized, the initial guest memory is fixed. */ if (kvm_tdx->state == TD_STATE_RUNNABLE) return -EINVAL; @@ -3264,7 +3195,6 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c !vt_is_tdx_private_gpa(kvm, region.gpa + (region.nr_pages << PAGE_SHIFT) - 1)) return -EINVAL; - kvm_mmu_reload(vcpu); ret = 0; while (region.nr_pages) { if (signal_pending(current)) { @@ -3301,28 +3231,57 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c return ret; } -int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) +int tdx_vcpu_unlocked_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { - struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct kvm *kvm = vcpu->kvm; + struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); struct kvm_tdx_cmd cmd; - int ret; + int r; - if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE) - return -EINVAL; + r = tdx_get_cmd(argp, &cmd); + if (r) + return r; - if (copy_from_user(&cmd, argp, sizeof(cmd))) - return -EFAULT; + CLASS(tdx_vm_state_guard, guard)(kvm); + if (IS_ERR(guard)) + return PTR_ERR(guard); - if (cmd.hw_error) + if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE) return -EINVAL; + vcpu_load(vcpu); + switch (cmd.id) { + case KVM_TDX_INIT_MEM_REGION: + r = tdx_vcpu_init_mem_region(vcpu, &cmd); + break; case KVM_TDX_INIT_VCPU: - ret = tdx_vcpu_init(vcpu, &cmd); + r = tdx_vcpu_init(vcpu, &cmd); break; - case KVM_TDX_INIT_MEM_REGION: - ret = tdx_vcpu_init_mem_region(vcpu, &cmd); + default: + r = -ENOIOCTLCMD; break; + } + + vcpu_put(vcpu); + + return r; +} + +int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) +{ + struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm); + struct kvm_tdx_cmd cmd; + int ret; + + if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE) + return -EINVAL; + + ret = tdx_get_cmd(argp, &cmd); + if (ret) + return ret; + + switch (cmd.id) { case KVM_TDX_GET_CPUID: ret = tdx_vcpu_get_cpuid(vcpu, &cmd); break; @@ -3447,10 +3406,6 @@ static int __init __tdx_bringup(void) /* * Check if MSRs (tdx_uret_msrs) can be saved/restored * before returning to user space. - * - * this_cpu_ptr(user_return_msrs)->registered isn't checked - * because the registration is done at vcpu runtime by - * tdx_user_return_msr_update_cache(). */ tdx_uret_msrs[i].slot = kvm_find_user_return_msr(tdx_uret_msrs[i].msr); if (tdx_uret_msrs[i].slot == -1) { diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h index ca39a9391db1..45b5183ccb36 100644 --- a/arch/x86/kvm/vmx/tdx.h +++ b/arch/x86/kvm/vmx/tdx.h @@ -36,8 +36,12 @@ struct kvm_tdx { struct tdx_td td; - /* For KVM_TDX_INIT_MEM_REGION. */ - atomic64_t nr_premapped; + /* + * Scratch pointer used to pass the source page to tdx_mem_page_add(). + * Protected by slots_lock, and non-NULL only when mapping a private + * pfn via tdx_gmem_post_populate(). + */ + struct page *page_add_src; /* * Prevent vCPUs from TD entry to ensure SEPT zap related SEAMCALLs do @@ -67,7 +71,6 @@ struct vcpu_tdx { u64 vp_enter_ret; enum vcpu_tdx_state state; - bool guest_entered; u64 map_gpa_next; u64 map_gpa_end; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index bc255d709d8a..4426d34811fc 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -71,6 +71,7 @@ * @regs: unsigned long * (to guest registers) * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH * VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl + * VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO: vCPU can access host MMIO * * Returns: * 0 on VM-Exit, 1 on VM-Fail @@ -92,7 +93,7 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Save @vmx for SPEC_CTRL handling */ push %_ASM_ARG1 - /* Save @flags for SPEC_CTRL handling */ + /* Save @flags (used for VMLAUNCH vs. VMRESUME and mitigations). */ push %_ASM_ARG3 /* @@ -101,9 +102,6 @@ SYM_FUNC_START(__vmx_vcpu_run) */ push %_ASM_ARG2 - /* Copy @flags to EBX, _ASM_ARG3 is volatile. */ - mov %_ASM_ARG3L, %ebx - lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp @@ -118,13 +116,23 @@ SYM_FUNC_START(__vmx_vcpu_run) * and vmentry. */ mov 2*WORD_SIZE(%_ASM_SP), %_ASM_DI - movl VMX_spec_ctrl(%_ASM_DI), %edi - movl PER_CPU_VAR(x86_spec_ctrl_current), %esi - cmp %edi, %esi +#ifdef CONFIG_X86_64 + mov VMX_spec_ctrl(%rdi), %rdx + cmp PER_CPU_VAR(x86_spec_ctrl_current), %rdx je .Lspec_ctrl_done + movl %edx, %eax + shr $32, %rdx +#else + mov VMX_spec_ctrl(%edi), %eax + mov PER_CPU_VAR(x86_spec_ctrl_current), %ecx + xor %eax, %ecx + mov VMX_spec_ctrl + 4(%edi), %edx + mov PER_CPU_VAR(x86_spec_ctrl_current + 4), %edi + xor %edx, %edi + or %edi, %ecx + je .Lspec_ctrl_done +#endif mov $MSR_IA32_SPEC_CTRL, %ecx - xor %edx, %edx - mov %edi, %eax wrmsr .Lspec_ctrl_done: @@ -137,9 +145,6 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load @regs to RAX. */ mov (%_ASM_SP), %_ASM_AX - /* Check if vmlaunch or vmresume is needed */ - bt $VMX_RUN_VMRESUME_SHIFT, %ebx - /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX mov VCPU_RDX(%_ASM_AX), %_ASM_DX @@ -160,11 +165,23 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Clobbers EFLAGS.ZF */ - CLEAR_CPU_BUFFERS - - /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ - jnc .Lvmlaunch + /* + * Note, ALTERNATIVE_2 works in reverse order. If CLEAR_CPU_BUF_VM is + * enabled, do VERW unconditionally. If CPU_BUF_VM_MMIO is enabled, + * check @flags to see if the vCPU has access to host MMIO, and if so, + * do VERW. Else, do nothing (no mitigations needed/enabled). + */ + ALTERNATIVE_2 "", \ + __stringify(testl $VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO, WORD_SIZE(%_ASM_SP); \ + jz .Lskip_mmio_verw; \ + VERW; \ + .Lskip_mmio_verw:), \ + X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO, \ + __stringify(VERW), X86_FEATURE_CLEAR_CPU_BUF_VM + + /* Check @flags to see if VMLAUNCH or VMRESUME is needed. */ + testl $VMX_RUN_VMRESUME, WORD_SIZE(%_ASM_SP) + jz .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 91b6f2f3edc2..4cbe8c84b636 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -203,6 +203,7 @@ module_param(pt_mode, int, S_IRUGO); struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; +#ifdef CONFIG_CPU_MITIGATIONS static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); @@ -225,7 +226,7 @@ static const struct { #define L1D_CACHE_ORDER 4 static void *vmx_l1d_flush_pages; -static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) +static int __vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) { struct page *page; unsigned int i; @@ -302,6 +303,26 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) return 0; } +static int vmx_setup_l1d_flush(void) +{ + /* + * Hand the parameter mitigation value in which was stored in the pre + * module init parser. If no parameter was given, it will contain + * 'auto' which will be turned into the default 'cond' mitigation mode. + */ + return __vmx_setup_l1d_flush(vmentry_l1d_flush_param); +} + +static void vmx_cleanup_l1d_flush(void) +{ + if (vmx_l1d_flush_pages) { + free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); + vmx_l1d_flush_pages = NULL; + } + /* Restore state so sysfs ignores VMX */ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; +} + static int vmentry_l1d_flush_parse(const char *s) { unsigned int i; @@ -339,7 +360,7 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) } mutex_lock(&vmx_l1d_flush_mutex); - ret = vmx_setup_l1d_flush(l1tf); + ret = __vmx_setup_l1d_flush(l1tf); mutex_unlock(&vmx_l1d_flush_mutex); return ret; } @@ -352,6 +373,101 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) return sysfs_emit(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); } +/* + * Software based L1D cache flush which is used when microcode providing + * the cache control MSR is not loaded. + * + * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to + * flush it is required to read in 64 KiB because the replacement algorithm + * is not exactly LRU. This could be sized at runtime via topology + * information but as all relevant affected CPUs have 32KiB L1D cache size + * there is no point in doing so. + */ +static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) +{ + int size = PAGE_SIZE << L1D_CACHE_ORDER; + + if (!static_branch_unlikely(&vmx_l1d_should_flush)) + return; + + /* + * This code is only executed when the flush mode is 'cond' or + * 'always' + */ + if (static_branch_likely(&vmx_l1d_flush_cond)) { + /* + * Clear the per-cpu flush bit, it gets set again if the vCPU + * is reloaded, i.e. if the vCPU is scheduled out or if KVM + * exits to userspace, or if KVM reaches one of the unsafe + * VMEXIT handlers, e.g. if KVM calls into the emulator, + * or from the interrupt handlers. + */ + if (!kvm_get_cpu_l1tf_flush_l1d()) + return; + kvm_clear_cpu_l1tf_flush_l1d(); + } + + vcpu->stat.l1d_flush++; + + if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { + native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + return; + } + + asm volatile( + /* First ensure the pages are in the TLB */ + "xorl %%eax, %%eax\n" + ".Lpopulate_tlb:\n\t" + "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" + "addl $4096, %%eax\n\t" + "cmpl %%eax, %[size]\n\t" + "jne .Lpopulate_tlb\n\t" + "xorl %%eax, %%eax\n\t" + "cpuid\n\t" + /* Now fill the cache */ + "xorl %%eax, %%eax\n" + ".Lfill_cache:\n" + "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" + "addl $64, %%eax\n\t" + "cmpl %%eax, %[size]\n\t" + "jne .Lfill_cache\n\t" + "lfence\n" + :: [flush_pages] "r" (vmx_l1d_flush_pages), + [size] "r" (size) + : "eax", "ebx", "ecx", "edx"); +} + +#else /* CONFIG_CPU_MITIGATIONS*/ +static int vmx_setup_l1d_flush(void) +{ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NEVER; + return 0; +} +static void vmx_cleanup_l1d_flush(void) +{ + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; +} +static __always_inline void vmx_l1d_flush(struct kvm_vcpu *vcpu) +{ + +} +static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) +{ + pr_warn_once("Kernel compiled without mitigations, ignoring vmentry_l1d_flush\n"); + return 0; +} +static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) +{ + return sysfs_emit(s, "never\n"); +} +#endif + +static const struct kernel_param_ops vmentry_l1d_flush_ops = { + .set = vmentry_l1d_flush_set, + .get = vmentry_l1d_flush_get, +}; +module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); + static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx) { u64 msr; @@ -404,12 +520,6 @@ static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) vmx->disable_fb_clear = false; } -static const struct kernel_param_ops vmentry_l1d_flush_ops = { - .set = vmentry_l1d_flush_set, - .get = vmentry_l1d_flush_get, -}; -module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); - static u32 vmx_segment_access_rights(struct kvm_segment *var); void vmx_vmexit(void); @@ -752,7 +862,7 @@ static void __loaded_vmcs_clear(void *arg) loaded_vmcs->launched = 0; } -void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) +static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) { int cpu = loaded_vmcs->cpu; @@ -903,7 +1013,7 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)) flags |= VMX_RUN_SAVE_SPEC_CTRL; - if (static_branch_unlikely(&cpu_buf_vm_clear) && + if (cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO) && kvm_vcpu_can_access_host_mmio(&vmx->vcpu)) flags |= VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO; @@ -3219,6 +3329,40 @@ static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->vpid; } +static u64 construct_eptp(hpa_t root_hpa) +{ + u64 eptp = root_hpa | VMX_EPTP_MT_WB; + struct kvm_mmu_page *root; + + if (kvm_mmu_is_dummy_root(root_hpa)) + return eptp | VMX_EPTP_PWL_4; + + /* + * EPT roots should always have an associated MMU page. Return a "bad" + * EPTP to induce VM-Fail instead of continuing on in a unknown state. + */ + root = root_to_sp(root_hpa); + if (WARN_ON_ONCE(!root)) + return INVALID_PAGE; + + eptp |= (root->role.level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; + + if (enable_ept_ad_bits && !root->role.ad_disabled) + eptp |= VMX_EPTP_AD_ENABLE_BIT; + + return eptp; +} + +static void vmx_flush_tlb_ept_root(hpa_t root_hpa) +{ + u64 eptp = construct_eptp(root_hpa); + + if (VALID_PAGE(eptp)) + ept_sync_context(eptp); + else + ept_sync_global(); +} + void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -3229,8 +3373,7 @@ void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) return; if (enable_ept) - ept_sync_context(construct_eptp(vcpu, root_hpa, - mmu->root_role.level)); + vmx_flush_tlb_ept_root(root_hpa); else vpid_sync_context(vmx_get_current_vpid(vcpu)); } @@ -3396,30 +3539,16 @@ static int vmx_get_max_ept_level(void) return 4; } -u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) -{ - u64 eptp = VMX_EPTP_MT_WB; - - eptp |= (root_level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; - - if (enable_ept_ad_bits && - (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) - eptp |= VMX_EPTP_AD_ENABLE_BIT; - eptp |= root_hpa; - - return eptp; -} - void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; unsigned long guest_cr3; - u64 eptp; if (enable_ept) { - eptp = construct_eptp(vcpu, root_hpa, root_level); - vmcs_write64(EPT_POINTER, eptp); + KVM_MMU_WARN_ON(root_to_sp(root_hpa) && + root_level != root_to_sp(root_hpa)->role.level); + vmcs_write64(EPT_POINTER, construct_eptp(root_hpa)); hv_track_root_tdp(vcpu, root_hpa); @@ -6631,15 +6760,8 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return kvm_vmx_exit_handlers[exit_handler_index](vcpu); unexpected_vmexit: - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", - exit_reason.full); dump_vmcs(vcpu); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_reason.full; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + kvm_prepare_unexpected_reason_exit(vcpu, exit_reason.full); return 0; } @@ -6661,77 +6783,6 @@ int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return ret; } -/* - * Software based L1D cache flush which is used when microcode providing - * the cache control MSR is not loaded. - * - * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to - * flush it is required to read in 64 KiB because the replacement algorithm - * is not exactly LRU. This could be sized at runtime via topology - * information but as all relevant affected CPUs have 32KiB L1D cache size - * there is no point in doing so. - */ -static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu) -{ - int size = PAGE_SIZE << L1D_CACHE_ORDER; - - /* - * This code is only executed when the flush mode is 'cond' or - * 'always' - */ - if (static_branch_likely(&vmx_l1d_flush_cond)) { - bool flush_l1d; - - /* - * Clear the per-vcpu flush bit, it gets set again if the vCPU - * is reloaded, i.e. if the vCPU is scheduled out or if KVM - * exits to userspace, or if KVM reaches one of the unsafe - * VMEXIT handlers, e.g. if KVM calls into the emulator. - */ - flush_l1d = vcpu->arch.l1tf_flush_l1d; - vcpu->arch.l1tf_flush_l1d = false; - - /* - * Clear the per-cpu flush bit, it gets set again from - * the interrupt handlers. - */ - flush_l1d |= kvm_get_cpu_l1tf_flush_l1d(); - kvm_clear_cpu_l1tf_flush_l1d(); - - if (!flush_l1d) - return; - } - - vcpu->stat.l1d_flush++; - - if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { - native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH); - return; - } - - asm volatile( - /* First ensure the pages are in the TLB */ - "xorl %%eax, %%eax\n" - ".Lpopulate_tlb:\n\t" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $4096, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lpopulate_tlb\n\t" - "xorl %%eax, %%eax\n\t" - "cpuid\n\t" - /* Now fill the cache */ - "xorl %%eax, %%eax\n" - ".Lfill_cache:\n" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $64, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lfill_cache\n\t" - "lfence\n" - :: [flush_pages] "r" (vmx_l1d_flush_pages), - [size] "r" (size) - : "eax", "ebx", "ecx", "edx"); -} - void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -7050,10 +7101,19 @@ void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) if (to_vt(vcpu)->emulation_required) return; - if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXTERNAL_INTERRUPT) + switch (vmx_get_exit_reason(vcpu).basic) { + case EXIT_REASON_EXTERNAL_INTERRUPT: handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu)); - else if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXCEPTION_NMI) + break; + case EXIT_REASON_EXCEPTION_NMI: handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu)); + break; + case EXIT_REASON_MCE_DURING_VMENTRY: + kvm_machine_check(); + break; + default: + break; + } } /* @@ -7328,21 +7388,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, guest_state_enter_irqoff(); - /* - * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW - * mitigation for MDS is done late in VMentry and is still - * executed in spite of L1D Flush. This is because an extra VERW - * should not matter much after the big hammer L1D Flush. - * - * cpu_buf_vm_clear is used when system is not vulnerable to MDS/TAA, - * and is affected by MMIO Stale Data. In such cases mitigation in only - * needed against an MMIO capable guest. - */ - if (static_branch_unlikely(&vmx_l1d_should_flush)) - vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&cpu_buf_vm_clear) && - (flags & VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO)) - x86_clear_cpu_buffers(); + vmx_l1d_flush(vcpu); vmx_disable_fb_clear(vmx); @@ -7454,8 +7500,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - kvm_load_guest_xsave_state(vcpu); - pt_guest_enter(vmx); atomic_switch_perf_msrs(vmx); @@ -7499,8 +7543,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) pt_guest_exit(vmx); - kvm_load_host_xsave_state(vcpu); - if (is_guest_mode(vcpu)) { /* * Track VMLAUNCH/VMRESUME that have made past guest state @@ -7516,9 +7558,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; - if (unlikely((u16)vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY)) - kvm_machine_check(); - trace_kvm_exit(vcpu, KVM_ISA_VMX); if (unlikely(vmx_get_exit_reason(vcpu).failed_vmentry)) @@ -8679,16 +8718,6 @@ __init int vmx_hardware_setup(void) return r; } -static void vmx_cleanup_l1d_flush(void) -{ - if (vmx_l1d_flush_pages) { - free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); - vmx_l1d_flush_pages = NULL; - } - /* Restore state so sysfs ignores VMX */ - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; -} - void vmx_exit(void) { allow_smaller_maxphyaddr = false; @@ -8724,14 +8753,8 @@ int __init vmx_init(void) if (r) return r; - /* - * Must be called after common x86 init so enable_ept is properly set - * up. Hand the parameter mitigation value in which was stored in - * the pre module init parser. If no parameter was given, it will - * contain 'auto' which will be turned into the default 'cond' - * mitigation mode. - */ - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); + /* Must be called after common x86 init so enable_ept is setup. */ + r = vmx_setup_l1d_flush(); if (r) goto err_l1d_flush; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index ea93121029f9..bc3ed3145d7e 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -369,7 +369,6 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx); void ept_save_pdptrs(struct kvm_vcpu *vcpu); void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); -u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); @@ -681,7 +680,6 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags); void free_vmcs(struct vmcs *vmcs); int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); -void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs); static inline struct vmcs *alloc_vmcs(bool shadow) { diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 9697368d65b3..d09abeac2b56 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -73,7 +73,6 @@ void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); -void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val); void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val); void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu); void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg); @@ -149,6 +148,7 @@ int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp); +int tdx_vcpu_unlocked_ioctl(struct kvm_vcpu *vcpu, void __user *argp); void tdx_flush_tlb_current(struct kvm_vcpu *vcpu); void tdx_flush_tlb_all(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c9c2aa6f4705..0c6d899d53dd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -159,9 +159,6 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(report_ignored_msrs); unsigned int min_timer_period_us = 200; module_param(min_timer_period_us, uint, 0644); -static bool __read_mostly kvmclock_periodic_sync = true; -module_param(kvmclock_periodic_sync, bool, 0444); - /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, 0644); @@ -212,7 +209,7 @@ struct kvm_user_return_msrs { u32 __read_mostly kvm_nr_uret_msrs; EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_nr_uret_msrs); static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; -static struct kvm_user_return_msrs __percpu *user_return_msrs; +static DEFINE_PER_CPU(struct kvm_user_return_msrs, user_return_msrs); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ @@ -575,24 +572,26 @@ static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) vcpu->arch.apf.gfns[i] = ~0; } +static void kvm_destroy_user_return_msrs(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + WARN_ON_ONCE(per_cpu(user_return_msrs, cpu).registered); + + kvm_nr_uret_msrs = 0; +} + static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; struct kvm_user_return_msrs *msrs = container_of(urn, struct kvm_user_return_msrs, urn); struct kvm_user_return_msr_values *values; - unsigned long flags; - /* - * Disabling irqs at this point since the following code could be - * interrupted and executed through kvm_arch_disable_virtualization_cpu() - */ - local_irq_save(flags); - if (msrs->registered) { - msrs->registered = false; - user_return_notifier_unregister(urn); - } - local_irq_restore(flags); + msrs->registered = false; + user_return_notifier_unregister(urn); + for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { @@ -643,7 +642,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { - struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); u64 value; int i; @@ -665,7 +664,7 @@ static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs) int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) { - struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); int err; value = (value & mask) | (msrs->values[slot].host & ~mask); @@ -681,24 +680,15 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_set_user_return_msr); -void kvm_user_return_msr_update_cache(unsigned int slot, u64 value) -{ - struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); - - msrs->values[slot].curr = value; - kvm_user_return_register_notifier(msrs); -} -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_user_return_msr_update_cache); - u64 kvm_get_user_return_msr(unsigned int slot) { - return this_cpu_ptr(user_return_msrs)->values[slot].curr; + return this_cpu_ptr(&user_return_msrs)->values[slot].curr; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_user_return_msr); static void drop_user_return_notifiers(void) { - struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(&user_return_msrs); if (msrs->registered) kvm_on_user_return(&msrs->urn); @@ -1045,6 +1035,13 @@ bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_require_dr); +static bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) +{ + u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; + + return (vcpu->arch.apf.msr_en_val & mask) == mask; +} + static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); @@ -1137,15 +1134,20 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon } if ((cr0 ^ old_cr0) & X86_CR0_PG) { - kvm_clear_async_pf_completion_queue(vcpu); - kvm_async_pf_hash_reset(vcpu); - /* * Clearing CR0.PG is defined to flush the TLB from the guest's * perspective. */ if (!(cr0 & X86_CR0_PG)) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + /* + * Check for async #PF completion events when enabling paging, + * as the vCPU may have previously encountered async #PFs (it's + * entirely legal for the guest to toggle paging on/off without + * waiting for the async #PF queue to drain). + */ + else if (kvm_pv_async_pf_enabled(vcpu)) + kvm_make_request(KVM_REQ_APF_READY, vcpu); } if ((cr0 ^ old_cr0) & KVM_MMU_CR0_ROLE_BITS) @@ -1203,20 +1205,27 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_lmsw); -void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) +static void kvm_load_xfeatures(struct kvm_vcpu *vcpu, bool load_guest) { if (vcpu->arch.guest_state_protected) return; - if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) + return; - if (vcpu->arch.xcr0 != kvm_host.xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); + if (vcpu->arch.xcr0 != kvm_host.xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, + load_guest ? vcpu->arch.xcr0 : kvm_host.xcr0); - if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && - vcpu->arch.ia32_xss != kvm_host.xss) - wrmsrq(MSR_IA32_XSS, vcpu->arch.ia32_xss); - } + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && + vcpu->arch.ia32_xss != kvm_host.xss) + wrmsrq(MSR_IA32_XSS, load_guest ? vcpu->arch.ia32_xss : kvm_host.xss); +} + +static void kvm_load_guest_pkru(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.guest_state_protected) + return; if (cpu_feature_enabled(X86_FEATURE_PKU) && vcpu->arch.pkru != vcpu->arch.host_pkru && @@ -1224,9 +1233,8 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) wrpkru(vcpu->arch.pkru); } -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_load_guest_xsave_state); -void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) +static void kvm_load_host_pkru(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) return; @@ -1238,19 +1246,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.pkru != vcpu->arch.host_pkru) wrpkru(vcpu->arch.host_pkru); } - - if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { - - if (vcpu->arch.xcr0 != kvm_host.xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, kvm_host.xcr0); - - if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && - vcpu->arch.ia32_xss != kvm_host.xss) - wrmsrq(MSR_IA32_XSS, kvm_host.xss); - } - } -EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_load_host_xsave_state); #ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) @@ -3505,27 +3501,17 @@ uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm) /* * kvmclock updates which are isolated to a given vcpu, such as * vcpu->cpu migration, should not allow system_timestamp from - * the rest of the vcpus to remain static. Otherwise ntp frequency - * correction applies to one vcpu's system_timestamp but not - * the others. + * the rest of the vcpus to remain static. * * So in those cases, request a kvmclock update for all vcpus. - * We need to rate-limit these requests though, as they can - * considerably slow guests that have a large number of vcpus. - * The time for a remote vcpu to update its kvmclock is bound - * by the delay we use to rate-limit the updates. + * The worst case for a remote vcpu to update its kvmclock + * is then bounded by maximum nohz sleep latency. */ - -#define KVMCLOCK_UPDATE_DELAY msecs_to_jiffies(100) - -static void kvmclock_update_fn(struct work_struct *work) +static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) { unsigned long i; - struct delayed_work *dwork = to_delayed_work(work); - struct kvm_arch *ka = container_of(dwork, struct kvm_arch, - kvmclock_update_work); - struct kvm *kvm = container_of(ka, struct kvm, arch); struct kvm_vcpu *vcpu; + struct kvm *kvm = v->kvm; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -3533,29 +3519,6 @@ static void kvmclock_update_fn(struct work_struct *work) } } -static void kvm_gen_kvmclock_update(struct kvm_vcpu *v) -{ - struct kvm *kvm = v->kvm; - - kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); - schedule_delayed_work(&kvm->arch.kvmclock_update_work, - KVMCLOCK_UPDATE_DELAY); -} - -#define KVMCLOCK_SYNC_PERIOD (300 * HZ) - -static void kvmclock_sync_fn(struct work_struct *work) -{ - struct delayed_work *dwork = to_delayed_work(work); - struct kvm_arch *ka = container_of(dwork, struct kvm_arch, - kvmclock_sync_work); - struct kvm *kvm = container_of(ka, struct kvm, arch); - - schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); -} - /* These helpers are safe iff @msr is known to be an MCx bank MSR. */ static bool is_mci_control_msr(u32 msr) { @@ -3650,13 +3613,6 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) -{ - u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; - - return (vcpu->arch.apf.msr_en_val & mask) == mask; -} - static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; @@ -4182,7 +4138,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) return 1; if (data & 0x1) { - vcpu->arch.apf.pageready_pending = false; + /* + * Pairs with the smp_mb__after_atomic() in + * kvm_arch_async_page_present_queued(). + */ + smp_store_mb(vcpu->arch.apf.pageready_pending, false); + kvm_check_async_pf_completion(vcpu); } break; @@ -5188,7 +5149,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - vcpu->arch.l1tf_flush_l1d = true; + kvm_request_l1tf_flush_l1d(); if (vcpu->scheduled_out && pmu->version && pmu->event_count) { pmu->need_cleanup = true; @@ -7239,6 +7200,19 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) return 0; } +long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + + if (ioctl == KVM_MEMORY_ENCRYPT_OP && + kvm_x86_ops.vcpu_mem_enc_unlocked_ioctl) + return kvm_x86_call(vcpu_mem_enc_unlocked_ioctl)(vcpu, argp); + + return -ENOIOCTLCMD; +} + int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; @@ -7998,7 +7972,7 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { /* kvm_write_guest_virt_system can pull in tons of pages. */ - vcpu->arch.l1tf_flush_l1d = true; + kvm_request_l1tf_flush_l1d(); return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, PFERR_WRITE_MASK, exception); @@ -8842,6 +8816,14 @@ static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) kvm_make_request(KVM_REQ_TRIPLE_FAULT, emul_to_vcpu(ctxt)); } +static int emulator_get_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 *xcr) +{ + if (index != XCR_XFEATURE_ENABLED_MASK) + return 1; + *xcr = emul_to_vcpu(ctxt)->arch.xcr0; + return 0; +} + static int emulator_set_xcr(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr) { return __kvm_set_xcr(emul_to_vcpu(ctxt), index, xcr); @@ -8914,6 +8896,7 @@ static const struct x86_emulate_ops emulate_ops = { .is_smm = emulator_is_smm, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, + .get_xcr = emulator_get_xcr, .set_xcr = emulator_set_xcr, .get_untagged_addr = emulator_get_untagged_addr, .is_canonical_addr = emulator_is_canonical_addr, @@ -9109,6 +9092,18 @@ void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_event_vectoring_exit); +void kvm_prepare_unexpected_reason_exit(struct kvm_vcpu *vcpu, u64 exit_reason) +{ + vcpu_unimpl(vcpu, "unexpected exit reason 0x%llx\n", exit_reason); + + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = exit_reason; + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_prepare_unexpected_reason_exit); + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; @@ -9337,6 +9332,23 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } +static bool is_soft_int_instruction(struct x86_emulate_ctxt *ctxt, + int emulation_type) +{ + u8 vector = EMULTYPE_GET_SOFT_INT_VECTOR(emulation_type); + + switch (ctxt->b) { + case 0xcc: + return vector == BP_VECTOR; + case 0xcd: + return vector == ctxt->src.val; + case 0xce: + return vector == OF_VECTOR; + default: + return false; + } +} + /* * Decode an instruction for emulation. The caller is responsible for handling * code breakpoints. Note, manually detecting code breakpoints is unnecessary @@ -9394,7 +9406,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return handle_emulation_failure(vcpu, emulation_type); } - vcpu->arch.l1tf_flush_l1d = true; + kvm_request_l1tf_flush_l1d(); if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); @@ -9447,6 +9459,10 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { + if (emulation_type & EMULTYPE_SKIP_SOFT_INT && + !is_soft_int_instruction(ctxt, emulation_type)) + return 0; + if (ctxt->mode != X86EMUL_MODE_PROT64) ctxt->eip = (u32)ctxt->_eip; else @@ -10031,17 +10047,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return -ENOMEM; } - user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); - if (!user_return_msrs) { - pr_err("failed to allocate percpu kvm_user_return_msrs\n"); - r = -ENOMEM; - goto out_free_x86_emulator_cache; - } - kvm_nr_uret_msrs = 0; - r = kvm_mmu_vendor_module_init(); if (r) - goto out_free_percpu; + goto out_free_x86_emulator_cache; kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM); kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P; @@ -10066,6 +10074,8 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) rdmsrq(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities); + WARN_ON_ONCE(kvm_nr_uret_msrs); + r = ops->hardware_setup(); if (r != 0) goto out_mmu_exit; @@ -10138,9 +10148,8 @@ out_unwind_ops: kvm_x86_ops.enable_virtualization_cpu = NULL; kvm_x86_call(hardware_unsetup)(); out_mmu_exit: + kvm_destroy_user_return_msrs(); kvm_mmu_vendor_module_exit(); -out_free_percpu: - free_percpu(user_return_msrs); out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); return r; @@ -10168,8 +10177,8 @@ void kvm_x86_vendor_exit(void) cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_call(hardware_unsetup)(); + kvm_destroy_user_return_msrs(); kvm_mmu_vendor_module_exit(); - free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); #ifdef CONFIG_KVM_XEN static_key_deferred_flush(&kvm_xen_enabled); @@ -11291,6 +11300,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_fpu.xfd_err) wrmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); + kvm_load_xfeatures(vcpu, true); + if (unlikely(vcpu->arch.switch_db_regs && !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) { set_debugreg(DR7_FIXED_1, 7); @@ -11319,6 +11330,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) guest_timing_enter_irqoff(); + /* + * Swap PKRU with hardware breakpoints disabled to minimize the number + * of flows where non-KVM code can run with guest state loaded. + */ + kvm_load_guest_pkru(vcpu); + for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv @@ -11347,6 +11364,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) ++vcpu->stat.exits; } + kvm_load_host_pkru(vcpu); + /* * Do this here before restoring debug registers on the host. And * since we do this before handling the vmexit, a DR access vmexit @@ -11377,6 +11396,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + kvm_load_xfeatures(vcpu, false); + /* * Sync xfd before calling handle_exit_irqoff() which may * rely on the fact that guest_fpu::xfd is up-to-date (e.g. @@ -12734,8 +12755,6 @@ fail_mmu_destroy: void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; - if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); @@ -12746,10 +12765,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) vcpu->arch.msr_kvm_poll_control = 1; mutex_unlock(&vcpu->mutex); - - if (kvmclock_periodic_sync && vcpu->vcpu_idx == 0) - schedule_delayed_work(&kvm->arch.kvmclock_sync_work, - KVMCLOCK_SYNC_PERIOD); } void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) @@ -13088,7 +13103,21 @@ int kvm_arch_enable_virtualization_cpu(void) void kvm_arch_disable_virtualization_cpu(void) { kvm_x86_call(disable_virtualization_cpu)(); - drop_user_return_notifiers(); + + /* + * Leave the user-return notifiers as-is when disabling virtualization + * for reboot, i.e. when disabling via IPI function call, and instead + * pin kvm.ko (if it's a module) to defend against use-after-free (in + * the *very* unlikely scenario module unload is racing with reboot). + * On a forced reboot, tasks aren't frozen before shutdown, and so KVM + * could be actively modifying user-return MSR state when the IPI to + * disable virtualization arrives. Handle the extreme edge case here + * instead of trying to account for it in the normal flows. + */ + if (in_task() || WARN_ON_ONCE(!kvm_rebooting)) + drop_user_return_notifiers(); + else + __module_get(THIS_MODULE); } bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) @@ -13160,9 +13189,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.hv_root_tdp = INVALID_PAGE; #endif - INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); - INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); - kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); @@ -13269,9 +13295,6 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm) * is unsafe, i.e. will lead to use-after-free. The PIT also needs to * be stopped before IRQ routing is freed. */ - cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work); - cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work); - #ifdef CONFIG_KVM_IOAPIC kvm_free_pit(kvm); #endif @@ -13888,7 +13911,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, if ((work->wakeup_all || work->notpresent_injected) && kvm_pv_async_pf_enabled(vcpu) && !apf_put_user_ready(vcpu, work->arch.token)) { - vcpu->arch.apf.pageready_pending = true; + WRITE_ONCE(vcpu->arch.apf.pageready_pending, true); kvm_apic_set_irq(vcpu, &irq, NULL); } @@ -13899,7 +13922,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) { kvm_make_request(KVM_REQ_APF_READY, vcpu); - if (!vcpu->arch.apf.pageready_pending) + + /* Pairs with smp_store_mb() in kvm_set_msr_common(). */ + smp_mb__after_atomic(); + + if (!READ_ONCE(vcpu->arch.apf.pageready_pending)) kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index f3dc77f006f9..fdab0ad49098 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -420,6 +420,20 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) return !(kvm->arch.disabled_quirks & quirk); } +static __always_inline void kvm_request_l1tf_flush_l1d(void) +{ +#if IS_ENABLED(CONFIG_CPU_MITIGATIONS) && IS_ENABLED(CONFIG_KVM_INTEL) + /* + * Use a raw write to set the per-CPU flag, as KVM will ensure a flush + * even if preemption is currently enabled.. If the current vCPU task + * is migrated to a different CPU (or userspace runs the vCPU on a + * different task) before the next VM-Entry, then kvm_arch_vcpu_load() + * will request a flush on the new CPU. + */ + raw_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); +#endif +} + void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); @@ -622,8 +636,6 @@ static inline void kvm_machine_check(void) #endif } -void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); -void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); int kvm_spec_ctrl_test_value(u64 value); int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e); |