s390x/tcg: Implement VECTOR LOAD MULTIPLE

Try to load the last element first. Access to the first element will
be checked afterwards. This way, we can guarantee that the vector is
not modified before we checked for all possible exceptions. (16 vectors
cannot cross more than two pages)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20190307121539.12842-14-david@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>

diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index 2b36205c84295356b728e5a4764781776730d857..fa0f3a90034d73b1f2cacf9af53a67bd4b0e2cd0 100644 (file)
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1000,6 +1000,8 @@
     F(0xe721, VLGV,    VRS_c, V,   la2, 0, r1, 0, vlgv, 0, IF_VEC)
 /* VECTOR LOAD LOGICAL ELEMENT AND ZERO */
     F(0xe704, VLLEZ,   VRX,   V,   la2, 0, 0, 0, vllez, 0, IF_VEC)
+/* VECTOR LOAD MULTIPLE */
+    F(0xe736, VLM,     VRS_a, V,   la2, 0, 0, 0, vlm, 0, IF_VEC)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */

diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index cdad2a52f0957ffad05b36d27ec9177e5c48e6af..083f5c621334ca928068c62c6b8b2ecedaffac30 100644 (file)
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -406,3 +406,43 @@ static DisasJumpType op_vllez(DisasContext *s, DisasOps *o)
     tcg_temp_free_i64(t);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vlm(DisasContext *s, DisasOps *o)
+{
+    const uint8_t v3 = get_field(s->fields, v3);
+    uint8_t v1 = get_field(s->fields, v1);
+    TCGv_i64 t0, t1;
+
+    if (v3 < v1 || (v3 - v1 + 1) > 16) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    /*
+     * Check for possible access exceptions by trying to load the last
+     * element. The first element will be checked first next.
+     */
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    gen_addi_and_wrap_i64(s, t0, o->addr1, (v3 - v1) * 16 + 8);
+    tcg_gen_qemu_ld_i64(t0, t0, get_mem_index(s), MO_TEQ);
+
+    for (;; v1++) {
+        tcg_gen_qemu_ld_i64(t1, o->addr1, get_mem_index(s), MO_TEQ);
+        write_vec_element_i64(t1, v1, 0, ES_64);
+        if (v1 == v3) {
+            break;
+        }
+        gen_addi_and_wrap_i64(s, o->addr1, o->addr1, 8);
+        tcg_gen_qemu_ld_i64(t1, o->addr1, get_mem_index(s), MO_TEQ);
+        write_vec_element_i64(t1, v1, 1, ES_64);
+        gen_addi_and_wrap_i64(s, o->addr1, o->addr1, 8);
+    }
+
+    /* Store the last element, loaded first */
+    write_vec_element_i64(t0, v1, 1, ES_64);
+
+    tcg_temp_free_i64(t0);
+    tcg_temp_free_i64(t1);
+    return DISAS_NEXT;
+}