target/arm: Convert Neon 64-bit element 3-reg-same insns

Convert the 64-bit element insns in the 3-reg-same group
to decodetree. This covers VQSHL, VRSHL and VQRSHL where
size==0b11.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 47 insertions, 36 deletions

diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 68b0a44793..fe64903854 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -73,6 +73,27 @@ VCGE_U_3s        1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same
 VSHL_S_3s        1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev
 VSHL_U_3s        1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
 
+# Insns operating on 64-bit elements (size!=0b11 handled elsewhere)
+# The _rev suffix indicates that Vn and Vm are reversed. This is
+# the case for shifts. In the Arm ARM these insns are documented
+# with the Vm and Vn fields in their usual places, but in the
+# assembly the operands are listed "backwards", ie in the order
+# Dd, Dm, Dn where other insns use Dd, Dn, Dm. For QEMU we choose
+# to consider Vm and Vm as being in different fields in the insn,
+# which allows us to avoid special-casing shifts in the trans_
+# function code (where we would otherwise need to manually swap
+# the operands over to call Neon helper functions that are shared
+# with AArch64 which does not have this odd reversed-operand situation).
+@3same_64_rev    .... ... . . . 11 .... .... .... . q:1 . . .... \
+                 &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3
+
+VQSHL_S64_3s     1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+VQSHL_U64_3s     1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
+VRSHL_S64_3s     1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+VRSHL_U64_3s     1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
+VQRSHL_S64_3s    1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+VQRSHL_U64_3s    1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
+
 VMAX_S_3s        1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
 VMAX_U_3s        1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
 VMIN_S_3s        1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index 03b3337e46..05c6dcdc9b 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -825,3 +825,27 @@ static bool trans_SHA256SU1_3s(DisasContext *s, arg_SHA256SU1_3s *a)
 
     return true;
 }
+
+#define DO_3SAME_64(INSN, FUNC)                                         \
+    static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs,         \
+                                uint32_t rn_ofs, uint32_t rm_ofs,       \
+                                uint32_t oprsz, uint32_t maxsz)         \
+    {                                                                   \
+        static const GVecGen3 op = { .fni8 = FUNC };                    \
+        tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &op);      \
+    }                                                                   \
+    DO_3SAME(INSN, gen_##INSN##_3s)
+
+#define DO_3SAME_64_ENV(INSN, FUNC)                                     \
+    static void gen_##INSN##_elt(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m)    \
+    {                                                                   \
+        FUNC(d, cpu_env, n, m);                                         \
+    }                                                                   \
+    DO_3SAME_64(INSN, gen_##INSN##_elt)
+
+DO_3SAME_64(VRSHL_S64, gen_helper_neon_rshl_s64)
+DO_3SAME_64(VRSHL_U64, gen_helper_neon_rshl_u64)
+DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64)
+DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64)
+DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64)
+DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64)
diff --git a/target/arm/translate.c b/target/arm/translate.c
index ee2b8d6f6e..1ce3e18286 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5459,42 +5459,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         }
 
         if (size == 3) {
-            /* 64-bit element instructions. */
-            for (pass = 0; pass < (q ? 2 : 1); pass++) {
-                neon_load_reg64(cpu_V0, rn + pass);
-                neon_load_reg64(cpu_V1, rm + pass);
-                switch (op) {
-                case NEON_3R_VQSHL:
-                    if (u) {
-                        gen_helper_neon_qshl_u64(cpu_V0, cpu_env,
-                                                 cpu_V1, cpu_V0);
-                    } else {
-                        gen_helper_neon_qshl_s64(cpu_V0, cpu_env,
-                                                 cpu_V1, cpu_V0);
-                    }
-                    break;
-                case NEON_3R_VRSHL:
-                    if (u) {
-                        gen_helper_neon_rshl_u64(cpu_V0, cpu_V1, cpu_V0);
-                    } else {
-                        gen_helper_neon_rshl_s64(cpu_V0, cpu_V1, cpu_V0);
-                    }
-                    break;
-                case NEON_3R_VQRSHL:
-                    if (u) {
-                        gen_helper_neon_qrshl_u64(cpu_V0, cpu_env,
-                                                  cpu_V1, cpu_V0);
-                    } else {
-                        gen_helper_neon_qrshl_s64(cpu_V0, cpu_env,
-                                                  cpu_V1, cpu_V0);
-                    }
-                    break;
-                default:
-                    abort();
-                }
-                neon_store_reg64(cpu_V0, rd + pass);
-            }
-            return 0;
+            /* 64-bit element instructions: handled by decodetree */
+            return 1;
         }
         pairwise = 0;
         switch (op) {