diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index ee9dfa8e43..abbcdbb53a 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -5315,19 +5315,39 @@ static void handle_crc32(DisasContext *s,
  */
 static void disas_data_proc_2src(DisasContext *s, uint32_t insn)
 {
-    unsigned int sf, rm, opcode, rn, rd;
+    unsigned int sf, rm, opcode, rn, rd, setflag;
     sf = extract32(insn, 31, 1);
+    setflag = extract32(insn, 29, 1);
     rm = extract32(insn, 16, 5);
     opcode = extract32(insn, 10, 6);
     rn = extract32(insn, 5, 5);
     rd = extract32(insn, 0, 5);
 
-    if (extract32(insn, 29, 1)) {
+    if (setflag && opcode != 0) {
         unallocated_encoding(s);
         return;
     }
 
     switch (opcode) {
+    case 0: /* SUBP(S) */
+        if (sf == 0 || !dc_isar_feature(aa64_mte_insn_reg, s)) {
+            goto do_unallocated;
+        } else {
+            TCGv_i64 tcg_n, tcg_m, tcg_d;
+
+            tcg_n = read_cpu_reg_sp(s, rn, true);
+            tcg_m = read_cpu_reg_sp(s, rm, true);
+            tcg_gen_sextract_i64(tcg_n, tcg_n, 0, 56);
+            tcg_gen_sextract_i64(tcg_m, tcg_m, 0, 56);
+            tcg_d = cpu_reg(s, rd);
+
+            if (setflag) {
+                gen_sub_CC(true, tcg_d, tcg_n, tcg_m);
+            } else {
+                tcg_gen_sub_i64(tcg_d, tcg_n, tcg_m);
+            }
+        }
+        break;
     case 2: /* UDIV */
         handle_div(s, false, sf, rm, rn, rd);
         break;