diff --git a/target/arm/translate.c b/target/arm/translate.c
index 5bf68b782a..2f2a6d76b4 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -975,20 +975,17 @@ static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32,
         gen_aa32_st_i32(s, val, a32, index, OPC);                       \
     }
 
-static inline void gen_aa32_frob64(DisasContext *s, TCGv_i64 val)
-{
-    /* Not needed for user-mode BE32, where we use MO_BE instead.  */
-    if (!IS_USER_ONLY && s->sctlr_b) {
-        tcg_gen_rotri_i64(val, val, 32);
-    }
-}
-
 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);
-    gen_aa32_frob64(s, val);
+
+    /* Not needed for user-mode BE32, where we use MO_BE instead.  */
+    if (!IS_USER_ONLY && s->sctlr_b) {
+        tcg_gen_rotri_i64(val, val, 32);
+    }
+
     tcg_temp_free(addr);
 }
 
@@ -4987,16 +4984,13 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
         TCGv_i32 tmp2 = tcg_temp_new_i32();
         TCGv_i64 t64 = tcg_temp_new_i64();
 
-        /* For AArch32, architecturally the 32-bit word at the lowest
+        /*
+         * For AArch32, architecturally the 32-bit word at the lowest
          * address is always Rt and the one at addr+4 is Rt2, even if
          * the CPU is big-endian. That means we don't want to do a
-         * gen_aa32_ld_i64(), which invokes gen_aa32_frob64() as if
-         * for an architecturally 64-bit access, but instead do a
-         * 64-bit access using MO_BE if appropriate and then split
-         * the two halves.
-         * This only makes a difference for BE32 user-mode, where
-         * frob64() must not flip the two halves of the 64-bit data
-         * but this code must treat BE32 user-mode like BE32 system.
+         * gen_aa32_ld_i64(), which checks SCTLR_B as if for an
+         * architecturally 64-bit access, but instead do a 64-bit access
+         * using MO_BE if appropriate and then split the two halves.
          */
         TCGv taddr = gen_aa32_addr(s, addr, opc);
 
@@ -5056,14 +5050,15 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
         TCGv_i64 n64 = tcg_temp_new_i64();
 
         t2 = load_reg(s, rt2);
-        /* For AArch32, architecturally the 32-bit word at the lowest
+
+        /*
+         * For AArch32, architecturally the 32-bit word at the lowest
          * address is always Rt and the one at addr+4 is Rt2, even if
          * the CPU is big-endian. Since we're going to treat this as a
          * single 64-bit BE store, we need to put the two halves in the
          * opposite order for BE to LE, so that they end up in the right
-         * places.
-         * We don't want gen_aa32_frob64() because that does the wrong
-         * thing for BE32 usermode.
+         * places.  We don't want gen_aa32_st_i64, because that checks
+         * SCTLR_B as if for an architectural 64-bit access.
          */
         if (s->be_data == MO_BE) {
             tcg_gen_concat_i32_i64(n64, t2, t1);