From: "Chang S. Bae" <chang.seok.bae@intel.com>
To: seanjc@google.com, jmattson@google.com
Cc: pbonzini@redhat.com, kvm@vger.kernel.org, x86@kernel.org,
linux-kernel@vger.kernel.org, zhao1.liu@intel.com,
chang.seok.bae@intel.com
Subject: [PATCH v9 12/20] KVM: x86: Handle EGPR index and REX2-incompatible opcodes
Date: Tue, 17 Nov 2026 18:03:02 +0000 [thread overview]
Message-ID: <20261117180310.921701-13-chang.seok.bae@intel.com> (raw)
In-Reply-To: <20261117180310.921701-1-chang.seok.bae@intel.com>
Prepare the emulator for REX2 handling by introducing the NoRex2 opcode
flag and supporting extended register indices. For the latter, factor out
common logic for calculating register IDs.
REX2 does not support three-byte opcodes. Instead, the REX2.M bit selects
between one- and two-byte opcode tables, which were previously
distinguished by the 0x0F escape byte.
Some legacy instructions in those tables never reference extended
registers. When prefixed with REX, such instructions are treated as if
the prefix were absent. In contrast, a REX2 prefix causes a #UD, which
should be handled explicitly.
JMPABS (0xA1) is an exception: it is defined for REX2 but mark it as not
implemented, since emulating non-memory operation isn't practically
that useful here.
Also, ignore the high-order register index bits when accessing vector
registers (XMM and YMM).
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Link: https://lore.kernel.org/1ebf3a23-5671-41c1-8daa-c83f2f105936@redhat.com
---
V8 -> V9:
* Fix the vector register ID (Jim Mattson)
* Clarify that JMPABS is not implemented (Jim Mattson)
* Move the NoRex2 check below group flag handling (Jim Mattson)
---
arch/x86/kvm/emulate.c | 91 +++++++++++++++++++++++++-------------
arch/x86/kvm/kvm_emulate.h | 1 +
2 files changed, 61 insertions(+), 31 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c1b21282187f..c6e11f551438 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -176,6 +176,7 @@
#define TwoMemOp ((u64)1 << 55) /* Instruction has two memory operand */
#define IsBranch ((u64)1 << 56) /* Instruction is considered a branch. */
#define ShadowStack ((u64)1 << 57) /* Instruction affects Shadow Stacks. */
+#define NoRex2 ((u64)1 << 58) /* Instruction not present in REX2 maps */
#define DstXacc (DstAccLo | SrcAccHi | SrcWrite)
@@ -245,6 +246,7 @@ enum rex_bits {
REX_X = 2,
REX_R = 4,
REX_W = 8,
+ REX_M = 0x80,
};
static void writeback_registers(struct x86_emulate_ctxt *ctxt)
@@ -1061,10 +1063,24 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
return X86EMUL_CONTINUE;
}
+static __always_inline int rex_get_rxb(u8 rex, u8 fld)
+{
+ BUILD_BUG_ON(!__builtin_constant_p(fld));
+ BUILD_BUG_ON(fld != REX_B && fld != REX_X && fld != REX_R);
+
+ rex >>= ffs(fld) - 1;
+ return (rex & 1 ? 8 : 0) + (rex & 0x10 ? 16 : 0);
+}
+
+/*
+ * With EGPR support, @reg may exceed the number of available vector
+ * registers. Mask off the higher bits accordingly.
+ */
static void __decode_register_operand(struct x86_emulate_ctxt *ctxt,
struct operand *op, int reg)
{
if ((ctxt->d & Avx) && ctxt->op_bytes == 32) {
+ reg &= 0xf;
op->type = OP_YMM;
op->bytes = 32;
op->addr.xmm = reg;
@@ -1072,6 +1088,7 @@ static void __decode_register_operand(struct x86_emulate_ctxt *ctxt,
return;
}
if (ctxt->d & (Avx|Sse)) {
+ reg &= 0xf;
op->type = OP_XMM;
op->bytes = 16;
op->addr.xmm = reg;
@@ -1100,7 +1117,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
if (ctxt->d & ModRM)
reg = ctxt->modrm_reg;
else
- reg = (ctxt->b & 7) | (ctxt->rex_bits & REX_B ? 8 : 0);
+ reg = (ctxt->b & 7) | rex_get_rxb(ctxt->rex_bits, REX_B);
__decode_register_operand(ctxt, op, reg);
}
@@ -1119,9 +1136,9 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
int rc = X86EMUL_CONTINUE;
ulong modrm_ea = 0;
- ctxt->modrm_reg = (ctxt->rex_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_reg = rex_get_rxb(ctxt->rex_bits, REX_R);
+ index_reg = rex_get_rxb(ctxt->rex_bits, REX_X);
+ base_reg = rex_get_rxb(ctxt->rex_bits, REX_B);
ctxt->modrm_mod = (ctxt->modrm & 0xc0) >> 6;
ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3;
@@ -4255,7 +4272,7 @@ static const struct opcode opcode_table[256] = {
/* 0x38 - 0x3F */
I6ALU(NoWrite, em_cmp), N, N,
/* 0x40 - 0x4F */
- X8(I(DstReg, em_inc)), X8(I(DstReg, em_dec)),
+ X8(I(DstReg | NoRex2, em_inc)), X8(I(DstReg | NoRex2, em_dec)),
/* 0x50 - 0x57 */
X8(I(SrcReg | Stack, em_push)),
/* 0x58 - 0x5F */
@@ -4273,7 +4290,7 @@ static const struct opcode opcode_table[256] = {
I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */
I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */
/* 0x70 - 0x7F */
- X16(D(SrcImmByte | NearBranch | IsBranch)),
+ X16(D(SrcImmByte | NearBranch | IsBranch | NoRex2)),
/* 0x80 - 0x87 */
G(ByteOp | DstMem | SrcImm, group1),
G(DstMem | SrcImm, group1),
@@ -4297,15 +4314,15 @@ static const struct opcode opcode_table[256] = {
II(ImplicitOps | Stack, em_popf, popf),
I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf),
/* 0xA0 - 0xA7 */
- I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
- I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
- I2bv(SrcSI | DstDI | Mov | String | TwoMemOp, em_mov),
- I2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r),
+ I2bv(DstAcc | SrcMem | Mov | MemAbs | NoRex2, em_mov),
+ I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable | NoRex2, em_mov),
+ I2bv(SrcSI | DstDI | Mov | String | TwoMemOp | NoRex2, em_mov),
+ I2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp | NoRex2, em_cmp_r),
/* 0xA8 - 0xAF */
- I2bv(DstAcc | SrcImm | NoWrite, em_test),
- I2bv(SrcAcc | DstDI | Mov | String, em_mov),
- I2bv(SrcSI | DstAcc | Mov | String, em_mov),
- I2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r),
+ I2bv(DstAcc | SrcImm | NoWrite | NoRex2, em_test),
+ I2bv(SrcAcc | DstDI | Mov | String | NoRex2, em_mov),
+ I2bv(SrcSI | DstAcc | Mov | String | NoRex2, em_mov),
+ I2bv(SrcAcc | DstDI | String | NoWrite | NoRex2, em_cmp_r),
/* 0xB0 - 0xB7 */
X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
/* 0xB8 - 0xBF */
@@ -4335,17 +4352,17 @@ static const struct opcode opcode_table[256] = {
/* 0xD8 - 0xDF */
N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
/* 0xE0 - 0xE7 */
- X3(I(SrcImmByte | NearBranch | IsBranch, em_loop)),
- I(SrcImmByte | NearBranch | IsBranch, em_jcxz),
- I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in),
- I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out),
+ X3(I(SrcImmByte | NearBranch | IsBranch | NoRex2, em_loop)),
+ I(SrcImmByte | NearBranch | IsBranch | NoRex2, em_jcxz),
+ I2bvIP(SrcImmUByte | DstAcc | NoRex2, em_in, in, check_perm_in),
+ I2bvIP(SrcAcc | DstImmUByte | NoRex2, em_out, out, check_perm_out),
/* 0xE8 - 0xEF */
- I(SrcImm | NearBranch | IsBranch | ShadowStack, em_call),
- D(SrcImm | ImplicitOps | NearBranch | IsBranch),
- I(SrcImmFAddr | No64 | IsBranch, em_jmp_far),
- D(SrcImmByte | ImplicitOps | NearBranch | IsBranch),
- I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in),
- I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out),
+ I(SrcImm | NearBranch | IsBranch | ShadowStack | NoRex2, em_call),
+ D(SrcImm | ImplicitOps | NearBranch | IsBranch | NoRex2),
+ I(SrcImmFAddr | No64 | IsBranch | NoRex2, em_jmp_far),
+ D(SrcImmByte | ImplicitOps | NearBranch | IsBranch | NoRex2),
+ I2bvIP(SrcDX | DstAcc | NoRex2, em_in, in, check_perm_in),
+ I2bvIP(SrcAcc | DstDX | NoRex2, em_out, out, check_perm_out),
/* 0xF0 - 0xF7 */
N, DI(ImplicitOps, icebp), N, N,
DI(ImplicitOps | Priv, hlt), D(ImplicitOps),
@@ -4385,12 +4402,12 @@ static const struct opcode twobyte_table[256] = {
N, GP(ModRM | DstMem | SrcReg | Mov | Sse | Avx, &pfx_0f_2b),
N, N, N, N,
/* 0x30 - 0x3F */
- II(ImplicitOps | Priv, em_wrmsr, wrmsr),
- IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc),
- II(ImplicitOps | Priv, em_rdmsr, rdmsr),
- IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc),
- I(ImplicitOps | EmulateOnUD | IsBranch | ShadowStack, em_sysenter),
- I(ImplicitOps | Priv | EmulateOnUD | IsBranch | ShadowStack, em_sysexit),
+ II(ImplicitOps | Priv | NoRex2, em_wrmsr, wrmsr),
+ IIP(ImplicitOps | NoRex2, em_rdtsc, rdtsc, check_rdtsc),
+ II(ImplicitOps | Priv | NoRex2, em_rdmsr, rdmsr),
+ IIP(ImplicitOps | NoRex2, em_rdpmc, rdpmc, check_rdpmc),
+ I(ImplicitOps | EmulateOnUD | IsBranch | ShadowStack | NoRex2, em_sysenter),
+ I(ImplicitOps | Priv | EmulateOnUD | IsBranch | ShadowStack | NoRex2, em_sysexit),
N, N,
N, N, N, N, N, N, N, N,
/* 0x40 - 0x4F */
@@ -4408,7 +4425,7 @@ static const struct opcode twobyte_table[256] = {
N, N, N, N,
N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f),
/* 0x80 - 0x8F */
- X16(D(SrcImm | NearBranch | IsBranch)),
+ X16(D(SrcImm | NearBranch | IsBranch | NoRex2)),
/* 0x90 - 0x9F */
X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
/* 0xA0 - 0xA7 */
@@ -5065,6 +5082,18 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int
ctxt->d |= opcode.flags;
}
+ /*
+ * Instructions marked with NoRex2 ignore a legacy REX prefix, but #UD
+ * should be raised when prefixed with REX2.
+ */
+ if (ctxt->d & NoRex2 && ctxt->rex_prefix == REX2_PREFIX) {
+ ctxt->d = Undefined;
+
+ /* JMPABS is not a memory operation so not implemented. */
+ if (ctxt->b == 0xa1)
+ ctxt->d = NotImpl;
+ }
+
ctxt->is_branch = opcode.flags & IsBranch;
/* Unrecognised? */
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 52f0aaa38c4c..7d2312d1a1a6 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -335,6 +335,7 @@ typedef void (*fastop_t)(struct fastop *);
enum rex_type {
REX_NONE,
REX_PREFIX,
+ REX2_PREFIX,
};
struct x86_emulate_ctxt {
--
2.53.0
next prev parent reply other threads:[~2026-11-17 18:32 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-17 18:02 [PATCH v9 00/20] KVM: x86: Enable APX for guest Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 01/20] KVM: x86: Extend VCPU registers for EGPRs Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 02/20] KVM: VMX: Save guest EGPRs in VCPU cache Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 03/20] KVM: x86: Support EGPRs on VCPU RESET/INIT events Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 04/20] KVM: x86: Support APX state for XSAVE ABI Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 05/20] KVM: VMX: Refactor VMX instruction information access Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 06/20] KVM: VMX: Refactor instruction information decoding Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 07/20] KVM: VMX: Remove unused control-register access defines Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 08/20] KVM: VMX: Refactor register index retrieval from exit qualification Chang S. Bae
2026-11-17 18:02 ` [PATCH v9 09/20] KVM: VMX: Support instruction information extension Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 10/20] KVM: nVMX: Propagate extended instruction information Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 11/20] KVM: x86: Support EGPR accessing and tracking for emulator Chang S. Bae
2026-11-17 18:03 ` Chang S. Bae [this message]
2026-11-17 18:03 ` [PATCH v9 13/20] KVM: x86: Support REX2-prefixed opcode decode Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 14/20] KVM: x86: Document EVEX-prefix not implemented Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 15/20] KVM: x86: Move KVM_SUPPORTED_{XCR0,XSS} into kvm_x86_vendor_init() Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 16/20] KVM: x86: Guard valid XCR0.APX settings Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 17/20] KVM: x86: Add APX to supported XCR0 Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 18/20] KVM: x86: Expose APX feature to userspace Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 19/20] KVM: selftests: Add APX state and ABI test Chang S. Bae
2026-11-17 18:03 ` [PATCH v9 20/20] KVM: selftests: Add APX state handling and XCR0 sanity checks Chang S. Bae
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261117180310.921701-13-chang.seok.bae@intel.com \
--to=chang.seok.bae@intel.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=x86@kernel.org \
--cc=zhao1.liu@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®