s390x/tcg: Implement VECTOR AVERAGE

Handle 32/64-bit elements via gvec expansion and the 8/16 bits via
ool helpers.
Reviewed-by: NRichard Henderson <richard.henderson@linaro.org>
Signed-off-by: NDavid Hildenbrand <david@redhat.com>

target/s390x/Makefile.objs

 obj-y += cpu.o cpu_models.o cpu_features.o gdbstub.o interrupt.o helper.o
 obj-$(CONFIG_TCG) += translate.o cc_helper.o excp_helper.o fpu_helper.o
 obj-$(CONFIG_TCG) += int_helper.o mem_helper.o misc_helper.o crypto_helper.o
-obj-$(CONFIG_TCG) += vec_helper.o
+obj-$(CONFIG_TCG) += vec_helper.o vec_int_helper.o
 obj-$(CONFIG_SOFTMMU) += machine.o ioinst.o arch_dump.o mmu_helper.o diag.o
 obj-$(CONFIG_SOFTMMU) += sigp.o
 obj-$(CONFIG_KVM) += kvm.o

target/s390x/helper.h

@@ -145,6 +145,10 @@ DEF_HELPER_5(gvec_vpkls_cc64, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vperm, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(vstl, TCG_CALL_NO_WG, void, env, cptr, i64, i64)
 
+/* === Vector Integer Instructions === */
+DEF_HELPER_FLAGS_4(gvec_vavg8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vavg16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)
 DEF_HELPER_4(diag, void, env, i32, i32, i32)

target/s390x/insn-data.def

@@ -1068,6 +1068,8 @@
     F(0xe768, VN,      VRR_c, V,   0, 0, 0, 0, vn, 0, IF_VEC)
 /* VECTOR AND WITH COMPLEMENT */
     F(0xe769, VNC,     VRR_c, V,   0, 0, 0, 0, vnc, 0, IF_VEC)
+/* VECTOR AVERAGE */
+    F(0xe7f2, VAVG,    VRR_c, V,   0, 0, 0, 0, vavg, 0, IF_VEC)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */

target/s390x/translate_vx.inc.c

@@ -256,6 +256,17 @@ static void zero_vec(uint8_t reg)
     tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, 0);
 }
 
+static void gen_addi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al, TCGv_i64 ah,
+                          uint64_t b)
+{
+    TCGv_i64 bl = tcg_const_i64(b);
+    TCGv_i64 bh = tcg_const_i64(0);
+
+    tcg_gen_add2_i64(dl, dh, al, ah, bl, bh);
+    tcg_temp_free_i64(bl);
+    tcg_temp_free_i64(bh);
+}
+
 static DisasJumpType op_vge(DisasContext *s, DisasOps *o)
 {
     const uint8_t es = s->insn->data;
@@ -1192,3 +1203,56 @@ static DisasJumpType op_vnc(DisasContext *s, DisasOps *o)
                   get_field(s->fields, v2), get_field(s->fields, v3));
     return DISAS_NEXT;
 }
+
+static void gen_avg_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+
+    tcg_gen_ext_i32_i64(t0, a);
+    tcg_gen_ext_i32_i64(t1, b);
+    tcg_gen_add_i64(t0, t0, t1);
+    tcg_gen_addi_i64(t0, t0, 1);
+    tcg_gen_shri_i64(t0, t0, 1);
+    tcg_gen_extrl_i64_i32(d, t0);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+}
+
+static void gen_avg_i64(TCGv_i64 dl, TCGv_i64 al, TCGv_i64 bl)
+{
+    TCGv_i64 dh = tcg_temp_new_i64();
+    TCGv_i64 ah = tcg_temp_new_i64();
+    TCGv_i64 bh = tcg_temp_new_i64();
+
+    /* extending the sign by one bit is sufficient */
+    tcg_gen_extract_i64(ah, al, 63, 1);
+    tcg_gen_extract_i64(bh, bl, 63, 1);
+    tcg_gen_add2_i64(dl, dh, al, ah, bl, bh);
+    gen_addi2_i64(dl, dh, dl, dh, 1);
+    tcg_gen_extract2_i64(dl, dl, dh, 1);
+
+    tcg_temp_free_i64(dh);
+    tcg_temp_free_i64(ah);
+    tcg_temp_free_i64(bh);
+}
+
+static DisasJumpType op_vavg(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    static const GVecGen3 g[4] = {
+        { .fno = gen_helper_gvec_vavg8, },
+        { .fno = gen_helper_gvec_vavg16, },
+        { .fni4 = gen_avg_i32, },
+        { .fni8 = gen_avg_i64, },
+    };
+
+    if (es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+    gen_gvec_3(get_field(s->fields, v1), get_field(s->fields, v2),
+               get_field(s->fields, v3), &g[es]);
+    return DISAS_NEXT;
+}

target/s390x/vec_int_helper.c

+/*
+ * QEMU TCG support -- s390x vector integer instruction support
+ *
+ * Copyright (C) 2019 Red Hat Inc
+ *
+ * Authors:
+ *   David Hildenbrand <david@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "cpu.h"
+#include "vec.h"
+#include "exec/helper-proto.h"
+
+#define DEF_VAVG(BITS)                                                         \
+void HELPER(gvec_vavg##BITS)(void *v1, const void *v2, const void *v3,         \
+                             uint32_t desc)                                    \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const int32_t a = (int##BITS##_t)s390_vec_read_element##BITS(v2, i);   \
+        const int32_t b = (int##BITS##_t)s390_vec_read_element##BITS(v3, i);   \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, (a + b + 1) >> 1);                 \
+    }                                                                          \
+}
+DEF_VAVG(8)
+DEF_VAVG(16)