target/arm: Enforce alignment for VLDn/VSTn (single)

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210419202257.161730-25-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

target/arm/translate-neon.c.inc

@@ -629,6 +629,7 @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a)
     int nregs = a->n + 1;
     int vd = a->vd;
     TCGv_i32 addr, tmp;
+    MemOp mop;
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
         return false;
@@ -678,23 +679,58 @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a)
         return true;
     }
 
+    /* Pick up SCTLR settings */
+    mop = finalize_memop(s, a->size);
+
+    if (a->align) {
+        MemOp align_op;
+
+        switch (nregs) {
+        case 1:
+            /* For VLD1, use natural alignment. */
+            align_op = MO_ALIGN;
+            break;
+        case 2:
+            /* For VLD2, use double alignment. */
+            align_op = pow2_align(a->size + 1);
+            break;
+        case 4:
+            if (a->size == MO_32) {
+                /*
+                 * For VLD4.32, align = 1 is double alignment, align = 2 is
+                 * quad alignment; align = 3 is rejected above.
+                 */
+                align_op = pow2_align(a->size + a->align);
+            } else {
+                /* For VLD4.8 and VLD.16, we want quad alignment. */
+                align_op = pow2_align(a->size + 2);
+            }
+            break;
+        default:
+            /* For VLD3, the alignment field is zero and rejected above. */
+            g_assert_not_reached();
+        }
+
+        mop = (mop & ~MO_AMASK) | align_op;
+    }
+
     tmp = tcg_temp_new_i32();
     addr = tcg_temp_new_i32();
     load_reg_var(s, addr, a->rn);
-    /*
+
-     * TODO: if we implemented alignment exceptions, we should check
-     * addr against the alignment encoded in a->align here.
-     */
     for (reg = 0; reg < nregs; reg++) {
         if (a->l) {
-            gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), a->size);
+            gen_aa32_ld_internal_i32(s, tmp, addr, get_mem_index(s), mop);
             neon_store_element(vd, a->reg_idx, a->size, tmp);
         } else { /* Store */
             neon_load_element(tmp, vd, a->reg_idx, a->size);
-            gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), a->size);
+            gen_aa32_st_internal_i32(s, tmp, addr, get_mem_index(s), mop);
         }
         vd += a->stride;
         tcg_gen_addi_i32(addr, addr, 1 << a->size);
+
+        /* Subsequent memory operations inherit alignment */
+        mop &= ~MO_AMASK;
     }
     tcg_temp_free_i32(addr);
     tcg_temp_free_i32(tmp);