From b0160ec99ae886d1e4961fc5dbf70bf8becfb339 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Mar 2019 23:18:59 +0100
Subject: [PATCH] s390x/tcg: Implement VECTOR CHECKSUM

Time to introduce read_vec_element_i32 and write_vec_element_i32.
Take proper care of properly adding the carry. We can perform both
additions including the carry via tcg_gen_add2_i32().

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/insn-data.def      |  2 +
 target/s390x/translate_vx.inc.c | 65 +++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)

diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index 9889dc0b01..64459465c5 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1072,6 +1072,8 @@
     F(0xe7f2, VAVG,    VRR_c, V,   0, 0, 0, 0, vavg, 0, IF_VEC)
 /* VECTOR AVERAGE LOGICAL */
     F(0xe7f0, VAVGL,   VRR_c, V,   0, 0, 0, 0, vavgl, 0, IF_VEC)
+/* VECTOR CHECKSUM */
+    F(0xe766, VCKSM,   VRR_c, V,   0, 0, 0, 0, vcksm, 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 3ff0682135..b9d40ffeb7 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -90,6 +90,33 @@ static void read_vec_element_i64(TCGv_i64 dst, uint8_t reg, uint8_t enr,
     }
 }
 
+static void read_vec_element_i32(TCGv_i32 dst, uint8_t reg, uint8_t enr,
+                                 TCGMemOp memop)
+{
+    const int offs = vec_reg_offset(reg, enr, memop & MO_SIZE);
+
+    switch (memop) {
+    case ES_8:
+        tcg_gen_ld8u_i32(dst, cpu_env, offs);
+        break;
+    case ES_16:
+        tcg_gen_ld16u_i32(dst, cpu_env, offs);
+        break;
+    case ES_8 | MO_SIGN:
+        tcg_gen_ld8s_i32(dst, cpu_env, offs);
+        break;
+    case ES_16 | MO_SIGN:
+        tcg_gen_ld16s_i32(dst, cpu_env, offs);
+        break;
+    case ES_32:
+    case ES_32 | MO_SIGN:
+        tcg_gen_ld_i32(dst, cpu_env, offs);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static void write_vec_element_i64(TCGv_i64 src, int reg, uint8_t enr,
                                   TCGMemOp memop)
 {
@@ -113,6 +140,25 @@ static void write_vec_element_i64(TCGv_i64 src, int reg, uint8_t enr,
     }
 }
 
+static void write_vec_element_i32(TCGv_i32 src, int reg, uint8_t enr,
+                                  TCGMemOp memop)
+{
+    const int offs = vec_reg_offset(reg, enr, memop & MO_SIZE);
+
+    switch (memop) {
+    case ES_8:
+        tcg_gen_st8_i32(src, cpu_env, offs);
+        break;
+    case ES_16:
+        tcg_gen_st16_i32(src, cpu_env, offs);
+        break;
+    case ES_32:
+        tcg_gen_st_i32(src, cpu_env, offs);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
 
 static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
                                     uint8_t es)
@@ -1304,3 +1350,22 @@ static DisasJumpType op_vavgl(DisasContext *s, DisasOps *o)
                get_field(s->fields, v3), &g[es]);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vcksm(DisasContext *s, DisasOps *o)
+{
+    TCGv_i32 tmp = tcg_temp_new_i32();
+    TCGv_i32 sum = tcg_temp_new_i32();
+    int i;
+
+    read_vec_element_i32(sum, get_field(s->fields, v3), 1, ES_32);
+    for (i = 0; i < 4; i++) {
+        read_vec_element_i32(tmp, get_field(s->fields, v2), i, ES_32);
+        tcg_gen_add2_i32(tmp, sum, sum, sum, tmp, tmp);
+    }
+    zero_vec(get_field(s->fields, v1));
+    write_vec_element_i32(sum, get_field(s->fields, v1), 1, ES_32);
+
+    tcg_temp_free_i32(tmp);
+    tcg_temp_free_i32(sum);
+    return DISAS_NEXT;
+}