diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1b3da3ba26b8..3a66741b6c8c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -245,6 +245,7 @@ enum {
 	REX_X = 2,
 	REX_R = 4,
 	REX_W = 8,
+	REX_M = 0x80,
 };
 
 static void writeback_registers(struct x86_emulate_ctxt *ctxt)
@@ -4849,6 +4850,18 @@ static int x86_decode_avx(struct x86_emulate_ctxt *ctxt,
 	return rc;
 }
 
+static inline bool rex2_invalid(struct x86_emulate_ctxt *ctxt)
+{
+	const struct x86_emulate_ops *ops = ctxt->ops;
+	u64 xcr = 0;
+
+	return ctxt->rex_prefix == REX_PREFIX ||
+	       (ctxt->rex_prefix == REX2_PREFIX && !(ctxt->rex_bits & REX_M)) ||
+	       !(ops->get_cr(ctxt, 4) & X86_CR4_OSXSAVE) ||
+	       ops->get_xcr(ctxt, 0, &xcr) ||
+	       !(xcr & XFEATURE_MASK_APX);
+}
+
 int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type)
 {
 	int rc = X86EMUL_CONTINUE;
@@ -4902,7 +4915,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int
 	ctxt->op_bytes = def_op_bytes;
 	ctxt->ad_bytes = def_ad_bytes;
 
-	/* Legacy prefixes. */
+	/* Legacy and REX/REX2 prefixes. */
 	for (;;) {
 		switch (ctxt->b = insn_fetch(u8, ctxt)) {
 		case 0x66:	/* operand-size override */
@@ -4945,9 +4958,23 @@ 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;
+			if (ctxt->rex_prefix == REX2_PREFIX) {
+				opcode = ud;
+				goto done_modrm;
+			}
 			ctxt->rex_prefix = REX_PREFIX;
 			ctxt->rex_bits   = ctxt->b & 0xf;
 			continue;
+		case 0xd5: /* REX2 */
+			if (mode != X86EMUL_MODE_PROT64)
+				goto done_prefixes;
+			if (rex2_invalid(ctxt)) {
+				opcode = ud;
+				goto done_modrm;
+			}
+			ctxt->rex_prefix = REX2_PREFIX;
+			ctxt->rex_bits   = insn_fetch(u8, ctxt);
+			continue;
 		case 0xf0:	/* LOCK */
 			ctxt->lock_prefix = 1;
 			break;
@@ -4970,6 +4997,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int
 	if (ctxt->rex_bits & REX_W)
 		ctxt->op_bytes = 8;
 
+	if (ctxt->rex_bits & REX_M)
+		goto decode_twobytes;
+
 	/* Opcode byte(s). */
 	if (ctxt->b == 0xc4 || ctxt->b == 0xc5) {
 		/* VEX or LDS/LES */
@@ -4987,8 +5017,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int
 			goto done;
 	} else if (ctxt->b == 0x0f) {
 		/* Two- or three-byte opcode */
-		ctxt->opcode_len = 2;
 		ctxt->b = insn_fetch(u8, ctxt);
+decode_twobytes:
+		ctxt->opcode_len = 2;
 		opcode = twobyte_table[ctxt->b];
 
 		/* 0F_38 opcode map */