[PATCH v6 08/13] target/s390x: vxeh2: vector shift double by bit

[David Hildenbrand <david@redhat.com>]

From: David Miller <dmiller423@gmail.com>

Signed-off-by: David Miller <dmiller423@gmail.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Tested-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/tcg/insn-data.def      |  6 +++-
 target/s390x/tcg/translate_vx.c.inc | 55 +++++++++++++++++++++++++----
 2 files changed, 53 insertions(+), 8 deletions(-)

diff --git a/target/s390x/tcg/insn-data.def b/target/s390x/tcg/insn-data.def
index f487a64abf..98a31a557d 100644
--- a/target/s390x/tcg/insn-data.def
+++ b/target/s390x/tcg/insn-data.def
@@ -1207,12 +1207,16 @@
     E(0xe774, VSL,     VRR_c, V,   0, 0, 0, 0, vsl, 0, 0, IF_VEC)
 /* VECTOR SHIFT LEFT BY BYTE */
     E(0xe775, VSLB,    VRR_c, V,   0, 0, 0, 0, vsl, 0, 1, IF_VEC)
+/* VECTOR SHIFT LEFT DOUBLE BY BIT */
+    E(0xe786, VSLD,    VRI_d, VE2, 0, 0, 0, 0, vsld, 0, 0, IF_VEC)
 /* VECTOR SHIFT LEFT DOUBLE BY BYTE */
-    F(0xe777, VSLDB,   VRI_d, V,   0, 0, 0, 0, vsldb, 0, IF_VEC)
+    E(0xe777, VSLDB,   VRI_d, V,   0, 0, 0, 0, vsld, 0, 1, IF_VEC)
 /* VECTOR SHIFT RIGHT ARITHMETIC */
     E(0xe77e, VSRA,    VRR_c, V,   0, 0, 0, 0, vsra, 0, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT ARITHMETIC BY BYTE */
     E(0xe77f, VSRAB,   VRR_c, V,   0, 0, 0, 0, vsra, 0, 1, IF_VEC)
+/* VECTOR SHIFT RIGHT DOUBLE BY BIT */
+    F(0xe787, VSRD,    VRI_d, VE2, 0, 0, 0, 0, vsrd, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT LOGICAL */
     E(0xe77c, VSRL,    VRR_c, V,   0, 0, 0, 0, vsrl, 0, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT LOGICAL BY BYTE */
diff --git a/target/s390x/tcg/translate_vx.c.inc b/target/s390x/tcg/translate_vx.c.inc
index 81673ea68f..cb6540673d 100644
--- a/target/s390x/tcg/translate_vx.c.inc
+++ b/target/s390x/tcg/translate_vx.c.inc
@@ -2056,14 +2056,23 @@ static DisasJumpType op_vsrl(DisasContext *s, DisasOps *o)
                             gen_helper_gvec_vsrl_ve2);
 }
 
-static DisasJumpType op_vsldb(DisasContext *s, DisasOps *o)
+static DisasJumpType op_vsld(DisasContext *s, DisasOps *o)
 {
-    const uint8_t i4 = get_field(s, i4) & 0xf;
-    const int left_shift = (i4 & 7) * 8;
-    const int right_shift = 64 - left_shift;
-    TCGv_i64 t0 = tcg_temp_new_i64();
-    TCGv_i64 t1 = tcg_temp_new_i64();
-    TCGv_i64 t2 = tcg_temp_new_i64();
+    const bool byte = s->insn->data;
+    const uint8_t mask = byte ? 15 : 7;
+    const uint8_t mul  = byte ?  8 : 1;
+    const uint8_t i4   = get_field(s, i4);
+    const int right_shift = 64 - (i4 & 7) * mul;
+    TCGv_i64 t0, t1, t2;
+
+    if (i4 & ~mask) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
 
     if ((i4 & 8) == 0) {
         read_vec_element_i64(t0, get_field(s, v2), 0, ES_64);
@@ -2074,8 +2083,40 @@ static DisasJumpType op_vsldb(DisasContext *s, DisasOps *o)
         read_vec_element_i64(t1, get_field(s, v3), 0, ES_64);
         read_vec_element_i64(t2, get_field(s, v3), 1, ES_64);
     }
+
     tcg_gen_extract2_i64(t0, t1, t0, right_shift);
     tcg_gen_extract2_i64(t1, t2, t1, right_shift);
+
+    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);
+    tcg_temp_free(t2);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_vsrd(DisasContext *s, DisasOps *o)
+{
+    const uint8_t i4 = get_field(s, i4);
+    TCGv_i64 t0, t1, t2;
+
+    if (i4 & ~7) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+
+    read_vec_element_i64(t0, get_field(s, v2), 1, ES_64);
+    read_vec_element_i64(t1, get_field(s, v3), 0, ES_64);
+    read_vec_element_i64(t2, get_field(s, v3), 1, ES_64);
+
+    tcg_gen_extract2_i64(t0, t1, t0, i4);
+    tcg_gen_extract2_i64(t1, t2, t1, i4);
+
     write_vec_element_i64(t0, get_field(s, v1), 0, ES_64);
     write_vec_element_i64(t1, get_field(s, v1), 1, ES_64);
 
-- 
2.35.1