s390x/tcg: Implement VECTOR FIND ANY ELEMENT EQUAL

Complicated stuff. Provide two different helpers for CC an !CC handling.
We might want to add more helpers later.

zero_search() and match_index() are courtesy of Richard H.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>

5 files changed, 198 insertions, 1 deletions

diff --git a/target/s390x/Makefile.objs b/target/s390x/Makefile.objs
index 0316457..ffdd484 100644
--- a/target/s390x/Makefile.objs
+++ b/target/s390x/Makefile.objs
@@ -1,7 +1,7 @@
 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-$(CONFIG_TCG) += vec_helper.o vec_int_helper.o
+obj-$(CONFIG_TCG) += vec_helper.o vec_int_helper.o vec_string_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
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 7755a96..c45328c 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -211,6 +211,14 @@ DEF_HELPER_FLAGS_4(gvec_vscbi8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vscbi16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_4(gvec_vtm, void, ptr, cptr, env, i32)
 
+/* === Vector String Instructions === */
+DEF_HELPER_FLAGS_4(gvec_vfae8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfae16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vfae32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_5(gvec_vfae_cc8, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfae_cc16, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_5(gvec_vfae_cc32, void, ptr, cptr, cptr, env, i32)
+
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)
 DEF_HELPER_4(diag, void, env, i32, i32, i32)
diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index e61475b..070ce2a 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1191,6 +1191,11 @@
 /* VECTOR TEST UNDER MASK */
     F(0xe7d8, VTM,     VRR_a, V,   0, 0, 0, 0, vtm, 0, IF_VEC)
 
+/* === Vector String Instructions === */
+
+/* VECTOR FIND ANY ELEMENT EQUAL */
+    F(0xe782, VFAE,    VRR_b, V,   0, 0, 0, 0, vfae, 0, IF_VEC)
+
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */
     E(0xb250, CSP,     RRE,   Z,   r1_32u, ra2, r1_P, 0, csp, 0, MO_TEUL, IF_PRIV)
diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index 7e0bfcb..ebd7a87 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2353,3 +2353,33 @@ static DisasJumpType op_vtm(DisasContext *s, DisasOps *o)
     set_cc_static(s);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vfae(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    const uint8_t m5 = get_field(s->fields, m5);
+    static gen_helper_gvec_3 * const g[3] = {
+        gen_helper_gvec_vfae8,
+        gen_helper_gvec_vfae16,
+        gen_helper_gvec_vfae32,
+    };
+    static gen_helper_gvec_3_ptr * const g_cc[3] = {
+        gen_helper_gvec_vfae_cc8,
+        gen_helper_gvec_vfae_cc16,
+        gen_helper_gvec_vfae_cc32,
+    };
+    if (es > ES_32) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m5, 0, 1)) {
+        gen_gvec_3_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), cpu_env, m5, g_cc[es]);
+        set_cc_static(s);
+    } else {
+        gen_gvec_3_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                       get_field(s->fields, v3), m5, g[es]);
+    }
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_string_helper.c b/target/s390x/vec_string_helper.c
new file mode 100644
index 0000000..56dc89c
--- /dev/null
+++ b/target/s390x/vec_string_helper.c
@@ -0,0 +1,154 @@
+/*
+ * QEMU TCG support -- s390x vector string 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 "internal.h"
+#include "vec.h"
+#include "tcg/tcg.h"
+#include "tcg/tcg-gvec-desc.h"
+#include "exec/helper-proto.h"
+
+/*
+ * Returns a bit set in the MSB of each element that is zero,
+ * as defined by the mask.
+ */
+static inline uint64_t zero_search(uint64_t a, uint64_t mask)
+{
+    return ~(((a & mask) + mask) | a | mask);
+}
+
+/*
+ * Returns the byte offset for the first match, or 16 for no match.
+ */
+static inline int match_index(uint64_t c0, uint64_t c1)
+{
+    return (c0 ? clz64(c0) : clz64(c1) + 64) >> 3;
+}
+
+/*
+ * Returns the number of bits composing one element.
+ */
+static uint8_t get_element_bits(uint8_t es)
+{
+    return (1 << es) * BITS_PER_BYTE;
+}
+
+/*
+ * Returns the bitmask for a single element.
+ */
+static uint64_t get_single_element_mask(uint8_t es)
+{
+    return -1ull >> (64 - get_element_bits(es));
+}
+
+/*
+ * Returns the bitmask for a single element (excluding the MSB).
+ */
+static uint64_t get_single_element_lsbs_mask(uint8_t es)
+{
+    return -1ull >> (65 - get_element_bits(es));
+}
+
+/*
+ * Returns the bitmasks for multiple elements (excluding the MSBs).
+ */
+static uint64_t get_element_lsbs_mask(uint8_t es)
+{
+    return dup_const(es, get_single_element_lsbs_mask(es));
+}
+
+static int vfae(void *v1, const void *v2, const void *v3, bool in,
+                bool rt, bool zs, uint8_t es)
+{
+    const uint64_t mask = get_element_lsbs_mask(es);
+    const int bits = get_element_bits(es);
+    uint64_t a0, a1, b0, b1, e0, e1, t0, t1, z0, z1;
+    uint64_t first_zero = 16;
+    uint64_t first_equal;
+    int i;
+
+    a0 = s390_vec_read_element64(v2, 0);
+    a1 = s390_vec_read_element64(v2, 1);
+    b0 = s390_vec_read_element64(v3, 0);
+    b1 = s390_vec_read_element64(v3, 1);
+    e0 = 0;
+    e1 = 0;
+    /* compare against equality with every other element */
+    for (i = 0; i < 64; i += bits) {
+        t0 = rol64(b0, i);
+        t1 = rol64(b1, i);
+        e0 |= zero_search(a0 ^ t0, mask);
+        e0 |= zero_search(a0 ^ t1, mask);
+        e1 |= zero_search(a1 ^ t0, mask);
+        e1 |= zero_search(a1 ^ t1, mask);
+    }
+    /* invert the result if requested - invert only the MSBs */
+    if (in) {
+        e0 = ~e0 & ~mask;
+        e1 = ~e1 & ~mask;
+    }
+    first_equal = match_index(e0, e1);
+
+    if (zs) {
+        z0 = zero_search(a0, mask);
+        z1 = zero_search(a1, mask);
+        first_zero = match_index(z0, z1);
+    }
+
+    if (rt) {
+        e0 = (e0 >> (bits - 1)) * get_single_element_mask(es);
+        e1 = (e1 >> (bits - 1)) * get_single_element_mask(es);
+        s390_vec_write_element64(v1, 0, e0);
+        s390_vec_write_element64(v1, 1, e1);
+    } else {
+        s390_vec_write_element64(v1, 0, MIN(first_equal, first_zero));
+        s390_vec_write_element64(v1, 1, 0);
+    }
+
+    if (first_zero == 16 && first_equal == 16) {
+        return 3; /* no match */
+    } else if (first_zero == 16) {
+        return 1; /* matching elements, no match for zero */
+    } else if (first_equal < first_zero) {
+        return 2; /* matching elements before match for zero */
+    }
+    return 0; /* match for zero */
+}
+
+#define DEF_VFAE_HELPER(BITS)                                                  \
+void HELPER(gvec_vfae##BITS)(void *v1, const void *v2, const void *v3,         \
+                             uint32_t desc)                                    \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool rt = extract32(simd_data(desc), 2, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    vfae(v1, v2, v3, in, rt, zs, MO_##BITS);                                   \
+}
+DEF_VFAE_HELPER(8)
+DEF_VFAE_HELPER(16)
+DEF_VFAE_HELPER(32)
+
+#define DEF_VFAE_CC_HELPER(BITS)                                               \
+void HELPER(gvec_vfae_cc##BITS)(void *v1, const void *v2, const void *v3,      \
+                                CPUS390XState *env, uint32_t desc)             \
+{                                                                              \
+    const bool in = extract32(simd_data(desc), 3, 1);                          \
+    const bool rt = extract32(simd_data(desc), 2, 1);                          \
+    const bool zs = extract32(simd_data(desc), 1, 1);                          \
+                                                                               \
+    env->cc_op = vfae(v1, v2, v3, in, rt, zs, MO_##BITS);                      \
+}
+DEF_VFAE_CC_HELPER(8)
+DEF_VFAE_CC_HELPER(16)
+DEF_VFAE_CC_HELPER(32)