[PATCH v3 08/11] target/s390x: vxeh2: vector {load, store} byte reversed element

[Richard Henderson <richard.henderson@linaro.org>]

From: David Miller <dmiller423@gmail.com>

This includes VLEBR* and VSTEBR* (single element);
VLBRREP (load single element and replicate); and
VLLEBRZ (load single element and zero).

Signed-off-by: David Miller <dmiller423@gmail.com>
Message-Id: <20220307020327.3003-6-dmiller423@gmail.com>
[rth: Split out elements (plural) from element (scalar),
      Use tcg little-endian memory operations.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/s390x/tcg/translate_vx.c.inc | 85 +++++++++++++++++++++++++++++
 target/s390x/tcg/insn-data.def      | 12 ++++
 2 files changed, 97 insertions(+)

diff --git a/target/s390x/tcg/translate_vx.c.inc b/target/s390x/tcg/translate_vx.c.inc
index 9a82401d71..ce77578325 100644
--- a/target/s390x/tcg/translate_vx.c.inc
+++ b/target/s390x/tcg/translate_vx.c.inc
@@ -457,6 +457,73 @@ static DisasJumpType op_vlrep(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
+static DisasJumpType op_vlebr(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = s->insn->data;
+    const uint8_t enr = get_field(s, m3);
+    TCGv_i64 tmp;
+
+    if (!valid_vec_element(enr, es)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    tmp = tcg_temp_new_i64();
+    tcg_gen_qemu_ld_i64(tmp, o->addr1, get_mem_index(s), MO_LE | es);
+    write_vec_element_i64(tmp, get_field(s, v1), enr, es);
+    tcg_temp_free_i64(tmp);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vlbrrep(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s, m3);
+    TCGv_i64 tmp;
+
+    if (es < ES_16 || es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    tmp = tcg_temp_new_i64();
+    tcg_gen_qemu_ld_i64(tmp, o->addr1, get_mem_index(s), MO_LE | es);
+    gen_gvec_dup_i64(es, get_field(s, v1), tmp);
+    tcg_temp_free_i64(tmp);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vllebrz(DisasContext *s, DisasOps *o)
+{
+    const uint8_t m3 = get_field(s, m3);
+    TCGv_i64 tmp;
+    int es, lshift;
+
+    switch (m3) {
+    case ES_16:
+    case ES_32:
+    case ES_64:
+        es = m3;
+        lshift = 0;
+        break;
+    case 6:
+        es = ES_32;
+        lshift = 32;
+        break;
+    default:
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    tmp = tcg_temp_new_i64();
+    tcg_gen_qemu_ld_i64(tmp, o->addr1, get_mem_index(s), MO_LE | es);
+    tcg_gen_shli_i64(tmp, tmp, lshift);
+
+    write_vec_element_i64(tmp, get_field(s, v1), 0, ES_64);
+    write_vec_element_i64(tcg_constant_i64(0), get_field(s, v1), 1, ES_64);
+    tcg_temp_free_i64(tmp);
+    return DISAS_NEXT;
+}
+
 static DisasJumpType op_vlbr(DisasContext *s, DisasOps *o)
 {
     const uint8_t es = get_field(s, m3);
@@ -1048,6 +1115,24 @@ static DisasJumpType op_vst(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
+static DisasJumpType op_vstebr(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = s->insn->data;
+    const uint8_t enr = get_field(s, m3);
+    TCGv_i64 tmp;
+
+    if (!valid_vec_element(enr, es)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    tmp = tcg_temp_new_i64();
+    read_vec_element_i64(tmp, get_field(s, v1), enr, es);
+    tcg_gen_qemu_st_i64(tmp, o->addr1, get_mem_index(s), MO_LE | es);
+    tcg_temp_free_i64(tmp);
+    return DISAS_NEXT;
+}
+
 static DisasJumpType op_vstbr(DisasContext *s, DisasOps *o)
 {
     const uint8_t es = get_field(s, m3);
diff --git a/target/s390x/tcg/insn-data.def b/target/s390x/tcg/insn-data.def
index ee6e1dc9e5..b80f989002 100644
--- a/target/s390x/tcg/insn-data.def
+++ b/target/s390x/tcg/insn-data.def
@@ -1027,6 +1027,14 @@
     F(0xe756, VLR,     VRR_a, V,   0, 0, 0, 0, vlr, 0, IF_VEC)
 /* VECTOR LOAD AND REPLICATE */
     F(0xe705, VLREP,   VRX,   V,   la2, 0, 0, 0, vlrep, 0, IF_VEC)
+/* VECTOR LOAD BYTE REVERSED ELEMENT */
+    E(0xe601, VLEBRH,  VRX,   VE2, la2, 0, 0, 0, vlebr, 0, ES_16, IF_VEC)
+    E(0xe603, VLEBRF,  VRX,   VE2, la2, 0, 0, 0, vlebr, 0, ES_32, IF_VEC)
+    E(0xe602, VLEBRG,  VRX,   VE2, la2, 0, 0, 0, vlebr, 0, ES_64, IF_VEC)
+/* VECTOR LOAD BYTE REVERSED ELEMENT AND REPLOCATE */
+    F(0xe605, VLBRREP, VRX,   VE2, la2, 0, 0, 0, vlbrrep, 0, IF_VEC)
+/* VECTOR LOAD BYTE REVERSED ELEMENT AND ZERO */
+    F(0xe604, VLLEBRZ, VRX,   VE2, la2, 0, 0, 0, vllebrz, 0, IF_VEC)
 /* VECTOR LOAD BYTE REVERSED ELEMENTS */
     F(0xe606, VLBR,    VRX,   VE2, la2, 0, 0, 0, vlbr, 0, IF_VEC)
 /* VECTOR LOAD ELEMENT */
@@ -1081,6 +1089,10 @@
     F(0xe75f, VSEG,    VRR_a, V,   0, 0, 0, 0, vseg, 0, IF_VEC)
 /* VECTOR STORE */
     F(0xe70e, VST,     VRX,   V,   la2, 0, 0, 0, vst, 0, IF_VEC)
+/* VECTOR STORE BYTE REVERSED ELEMENT */
+    E(0xe609, VSTEBRH,  VRX,   VE2, la2, 0, 0, 0, vstebr, 0, ES_16, IF_VEC)
+    E(0xe60b, VSTEBRF,  VRX,   VE2, la2, 0, 0, 0, vstebr, 0, ES_32, IF_VEC)
+    E(0xe60a, VSTEBRG,  VRX,   VE2, la2, 0, 0, 0, vstebr, 0, ES_64, IF_VEC)
 /* VECTOR STORE BYTE REVERSED ELEMENTS */
     F(0xe60e, VSTBR,    VRX,   VE2, la2, 0, 0, 0, vstbr, 0, IF_VEC)
 /* VECTOR STORE ELEMENT */
-- 
2.25.1