[PATCH v3 06/11] target/s390x: vxeh2: vector {load, store} elements reversed

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

From: David Miller <dmiller423@gmail.com>

Signed-off-by: David Miller <dmiller423@gmail.com>
Message-Id: <20220307020327.3003-5-dmiller423@gmail.com>
[rth: Use new hswap and wswap tcg expanders.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/s390x/tcg/translate_vx.c.inc | 84 +++++++++++++++++++++++++++++
 target/s390x/tcg/insn-data.def      |  4 ++
 2 files changed, 88 insertions(+)

diff --git a/target/s390x/tcg/translate_vx.c.inc b/target/s390x/tcg/translate_vx.c.inc
index a5283ef2f8..ac807122a3 100644
--- a/target/s390x/tcg/translate_vx.c.inc
+++ b/target/s390x/tcg/translate_vx.c.inc
@@ -492,6 +492,46 @@ static DisasJumpType op_vlei(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
+static DisasJumpType op_vler(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s, m3);
+
+    if (es < ES_16 || es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+
+    /* Begin with the two doublewords swapped... */
+    tcg_gen_qemu_ld_i64(t1, o->addr1, get_mem_index(s), MO_TEUQ);
+    gen_addi_and_wrap_i64(s, o->addr1, o->addr1, 8);
+    tcg_gen_qemu_ld_i64(t0, o->addr1, get_mem_index(s), MO_TEUQ);
+
+    /* ... then swap smaller elements within the doublewords as required. */
+    switch (es) {
+    case MO_16:
+        tcg_gen_hswap_i64(t1, t1);
+        tcg_gen_hswap_i64(t0, t0);
+        break;
+    case MO_32:
+        tcg_gen_wswap_i64(t1, t1);
+        tcg_gen_wswap_i64(t0, t0);
+        break;
+    case MO_64:
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    write_vec_element_i64(t0, get_field(s, v1), 0, ES_64);
+    write_vec_element_i64(t1, get_field(s, v1), 1, ES_64);
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+    return DISAS_NEXT;
+}
+
 static DisasJumpType op_vlgv(DisasContext *s, DisasOps *o)
 {
     const uint8_t es = get_field(s, m4);
@@ -976,6 +1016,50 @@ static DisasJumpType op_vste(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
+static DisasJumpType op_vster(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s, m3);
+    TCGv_i64 t0, t1;
+
+    if (es < ES_16 || es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    /* Probe write access before actually modifying memory */
+    gen_helper_probe_write_access(cpu_env, o->addr1, tcg_constant_i64(16));
+
+    /* Begin with the two doublewords swapped... */
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    read_vec_element_i64(t1,  get_field(s, v1), 0, ES_64);
+    read_vec_element_i64(t0,  get_field(s, v1), 1, ES_64);
+
+    /* ... then swap smaller elements within the doublewords as required. */
+    switch (es) {
+    case MO_16:
+        tcg_gen_hswap_i64(t1, t1);
+        tcg_gen_hswap_i64(t0, t0);
+        break;
+    case MO_32:
+        tcg_gen_wswap_i64(t1, t1);
+        tcg_gen_wswap_i64(t0, t0);
+        break;
+    case MO_64:
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    tcg_gen_qemu_st_i64(t0, o->addr1, get_mem_index(s), MO_TEUQ);
+    gen_addi_and_wrap_i64(s, o->addr1, o->addr1, 8);
+    tcg_gen_qemu_st_i64(t1, o->addr1, get_mem_index(s), MO_TEUQ);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+    return DISAS_NEXT;
+}
+
 static DisasJumpType op_vstm(DisasContext *s, DisasOps *o)
 {
     const uint8_t v3 = get_field(s, v3);
diff --git a/target/s390x/tcg/insn-data.def b/target/s390x/tcg/insn-data.def
index 98a31a557d..b524541a7d 100644
--- a/target/s390x/tcg/insn-data.def
+++ b/target/s390x/tcg/insn-data.def
@@ -1037,6 +1037,8 @@
     E(0xe741, VLEIH,   VRI_a, V,   0, 0, 0, 0, vlei, 0, ES_16, IF_VEC)
     E(0xe743, VLEIF,   VRI_a, V,   0, 0, 0, 0, vlei, 0, ES_32, IF_VEC)
     E(0xe742, VLEIG,   VRI_a, V,   0, 0, 0, 0, vlei, 0, ES_64, IF_VEC)
+/* VECTOR LOAD ELEMENTS REVERSED */
+    F(0xe607, VLER,    VRX,   VE2, la2, 0, 0, 0, vler, 0, IF_VEC)
 /* VECTOR LOAD GR FROM VR ELEMENT */
     F(0xe721, VLGV,    VRS_c, V,   la2, 0, r1, 0, vlgv, 0, IF_VEC)
 /* VECTOR LOAD LOGICAL ELEMENT AND ZERO */
@@ -1082,6 +1084,8 @@
     E(0xe709, VSTEH,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_16, IF_VEC)
     E(0xe70b, VSTEF,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_32, IF_VEC)
     E(0xe70a, VSTEG,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_64, IF_VEC)
+/* VECTOR STORE ELEMENTS REVERSED */
+    F(0xe60f, VSTER,   VRX,   VE2, la2, 0, 0, 0, vster, 0, IF_VEC)
 /* VECTOR STORE MULTIPLE */
     F(0xe73e, VSTM,    VRS_a, V,   la2, 0, 0, 0, vstm, 0, IF_VEC)
 /* VECTOR STORE WITH LENGTH */
-- 
2.25.1