diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index c82aa1412e..18d9042130 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -494,11 +494,13 @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a)
                 int tt = a->vd + reg + spacing * xs;
 
                 if (a->l) {
-                    gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size);
+                    gen_aa32_ld_internal_i64(s, tmp64, addr, mmu_idx,
+                                             endian | size);
                     neon_store_element64(tt, n, size, tmp64);
                 } else {
                     neon_load_element64(tmp64, tt, n, size);
-                    gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size);
+                    gen_aa32_st_internal_i64(s, tmp64, addr, mmu_idx,
+                                             endian | size);
                 }
                 tcg_gen_add_i32(addr, addr, tmp);
             }
diff --git a/target/arm/translate.c b/target/arm/translate.c
index e99c0ab5cb..21b241b1ce 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -949,6 +949,37 @@ static void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val,
     tcg_temp_free(addr);
 }
 
+static void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val,
+                                     TCGv_i32 a32, int index, MemOp opc)
+{
+    TCGv addr = gen_aa32_addr(s, a32, opc);
+
+    tcg_gen_qemu_ld_i64(val, addr, index, opc);
+
+    /* Not needed for user-mode BE32, where we use MO_BE instead.  */
+    if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) {
+        tcg_gen_rotri_i64(val, val, 32);
+    }
+    tcg_temp_free(addr);
+}
+
+static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val,
+                                     TCGv_i32 a32, int index, MemOp opc)
+{
+    TCGv addr = gen_aa32_addr(s, a32, opc);
+
+    /* Not needed for user-mode BE32, where we use MO_BE instead.  */
+    if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) {
+        TCGv_i64 tmp = tcg_temp_new_i64();
+        tcg_gen_rotri_i64(tmp, val, 32);
+        tcg_gen_qemu_st_i64(tmp, addr, index, opc);
+        tcg_temp_free_i64(tmp);
+    } else {
+        tcg_gen_qemu_st_i64(val, addr, index, opc);
+    }
+    tcg_temp_free(addr);
+}
+
 static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32,
                             int index, MemOp opc)
 {
@@ -961,6 +992,18 @@ static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32,
     gen_aa32_st_internal_i32(s, val, a32, index, finalize_memop(s, opc));
 }
 
+static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32,
+                            int index, MemOp opc)
+{
+    gen_aa32_ld_internal_i64(s, val, a32, index, finalize_memop(s, opc));
+}
+
+static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32,
+                            int index, MemOp opc)
+{
+    gen_aa32_st_internal_i64(s, val, a32, index, finalize_memop(s, opc));
+}
+
 #define DO_GEN_LD(SUFF, OPC)                                            \
     static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \
                                          TCGv_i32 a32, int index)       \
@@ -975,47 +1018,16 @@ static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32,
         gen_aa32_st_i32(s, val, a32, index, OPC);                       \
     }
 
-static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32,
-                            int index, MemOp opc)
-{
-    TCGv addr = gen_aa32_addr(s, a32, opc);
-    tcg_gen_qemu_ld_i64(val, addr, index, opc);
-
-    /* Not needed for user-mode BE32, where we use MO_BE instead.  */
-    if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) {
-        tcg_gen_rotri_i64(val, val, 32);
-    }
-
-    tcg_temp_free(addr);
-}
-
 static inline void gen_aa32_ld64(DisasContext *s, TCGv_i64 val,
                                  TCGv_i32 a32, int index)
 {
-    gen_aa32_ld_i64(s, val, a32, index, MO_Q | s->be_data);
-}
-
-static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32,
-                            int index, MemOp opc)
-{
-    TCGv addr = gen_aa32_addr(s, a32, opc);
-
-    /* Not needed for user-mode BE32, where we use MO_BE instead.  */
-    if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) {
-        TCGv_i64 tmp = tcg_temp_new_i64();
-        tcg_gen_rotri_i64(tmp, val, 32);
-        tcg_gen_qemu_st_i64(tmp, addr, index, opc);
-        tcg_temp_free_i64(tmp);
-    } else {
-        tcg_gen_qemu_st_i64(val, addr, index, opc);
-    }
-    tcg_temp_free(addr);
+    gen_aa32_ld_i64(s, val, a32, index, MO_Q);
 }
 
 static inline void gen_aa32_st64(DisasContext *s, TCGv_i64 val,
                                  TCGv_i32 a32, int index)
 {
-    gen_aa32_st_i64(s, val, a32, index, MO_Q | s->be_data);
+    gen_aa32_st_i64(s, val, a32, index, MO_Q);
 }
 
 DO_GEN_LD(8u, MO_UB)