target/arm: Clear unused predicate bits for LD1RQ

The 16-byte load only uses 16 predicate bits.  But while
reusing the other load infrastructure, we find other bits
that are set and trigger an assert.  To avoid this and
retain the assert, zero-extend the predicate that we pass
to the LD1 helper.
Tested-by: NLaurent Desnogues <laurent.desnogues@gmail.com>
Reported-by: NLaurent Desnogues <laurent.desnogues@gmail.com>
Reviewed-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NRichard Henderson <richard.henderson@linaro.org>
Message-id: 20181005175350.30752-7-richard.henderson@linaro.org
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

target/arm/translate-sve.c

@@ -4765,12 +4765,33 @@ static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz)
     unsigned vsz = vec_full_reg_size(s);
     TCGv_ptr t_pg;
     TCGv_i32 desc;
+    int poff;
 
     /* Load the first quadword using the normal predicated load helpers.  */
     desc = tcg_const_i32(simd_desc(16, 16, zt));
+
+    poff = pred_full_reg_offset(s, pg);
+    if (vsz > 16) {
+        /*
+         * Zero-extend the first 16 bits of the predicate into a temporary.
+         * This avoids triggering an assert making sure we don't have bits
+         * set within a predicate beyond VQ, but we have lowered VQ to 1
+         * for this load operation.
+         */
+        TCGv_i64 tmp = tcg_temp_new_i64();
+#ifdef HOST_WORDS_BIGENDIAN
+        poff += 6;
+#endif
+        tcg_gen_ld16u_i64(tmp, cpu_env, poff);
+
+        poff = offsetof(CPUARMState, vfp.preg_tmp);
+        tcg_gen_st_i64(tmp, cpu_env, poff);
+        tcg_temp_free_i64(tmp);
+    }
+
     t_pg = tcg_temp_new_ptr();
+    tcg_gen_addi_ptr(t_pg, cpu_env, poff);
 
-    tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg));
     fns[msz](cpu_env, t_pg, addr, desc);
 
     tcg_temp_free_ptr(t_pg);