target/arm: Require alignment for load exclusive

According to the ARM ARM exclusive loads require the same alignment as
exclusive stores. Let's update the memops used for the load to match
that of the store. This adds the alignment requirement to the memops.

Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Signed-off-by: Alistair Francis <alistair.francis@xilinx.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20170815145714.17635-4-richard.henderson@linaro.org
[rth: Require 16-byte alignment for 64-bit LDXP.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

target/arm/translate-a64.c

@@ -1861,7 +1861,7 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
         g_assert(size >= 2);
         if (size == 2) {
             /* The pair must be single-copy atomic for the doubleword.  */
-            memop |= MO_64;
+            memop |= MO_64 | MO_ALIGN;
             tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop);
             if (s->be_data == MO_LE) {
                 tcg_gen_extract_i64(cpu_reg(s, rt), cpu_exclusive_val, 0, 32);
@@ -1871,10 +1871,11 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
                 tcg_gen_extract_i64(cpu_reg(s, rt2), cpu_exclusive_val, 0, 32);
             }
         } else {
-            /* The pair must be single-copy atomic for *each* doubleword,
-               but not the entire quadword.  */
+            /* The pair must be single-copy atomic for *each* doubleword, not
+               the entire quadword, however it must be quadword aligned.  */
             memop |= MO_64;
-            tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop);
+            tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx,
+                                memop | MO_ALIGN_16);
 
             TCGv_i64 addr2 = tcg_temp_new_i64();
             tcg_gen_addi_i64(addr2, addr, 8);
@@ -1885,7 +1886,7 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
             tcg_gen_mov_i64(cpu_reg(s, rt2), cpu_exclusive_high);
         }
     } else {
-        memop |= size;
+        memop |= size | MO_ALIGN;
         tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop);
         tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val);
     }