target-arm: A64: Implement 2-reg-misc CNT, NOT and RBIT

Implement the 2-reg-misc CNT, NOT and RBIT instructions.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>

3 files changed, 41 insertions, 6 deletions

diff --git a/target-arm/helper.h b/target-arm/helper.h
index 71b8411120..951e6ada07 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -320,6 +320,7 @@ DEF_HELPER_1(neon_cls_s8, i32, i32)
 DEF_HELPER_1(neon_cls_s16, i32, i32)
 DEF_HELPER_1(neon_cls_s32, i32, i32)
 DEF_HELPER_1(neon_cnt_u8, i32, i32)
+DEF_HELPER_FLAGS_1(neon_rbit_u8, TCG_CALL_NO_RWG_SE, i32, i32)
 
 DEF_HELPER_3(neon_qdmulh_s16, i32, env, i32, i32)
 DEF_HELPER_3(neon_qrdmulh_s16, i32, env, i32, i32)
diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index be6fbd997e..b4c86904f4 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -1133,6 +1133,18 @@ uint32_t HELPER(neon_cnt_u8)(uint32_t x)
     return x;
 }
 
+/* Reverse bits in each 8 bit word */
+uint32_t HELPER(neon_rbit_u8)(uint32_t x)
+{
+    x =  ((x & 0xf0f0f0f0) >> 4)
+       | ((x & 0x0f0f0f0f) << 4);
+    x =  ((x & 0x88888888) >> 3)
+       | ((x & 0x44444444) >> 1)
+       | ((x & 0x22222222) << 1)
+       | ((x & 0x11111111) << 3);
+    return x;
+}
+
 #define NEON_QDMULH16(dest, src1, src2, round) do { \
     uint32_t tmp = (int32_t)(int16_t) src1 * (int16_t) src2; \
     if ((tmp ^ (tmp << 1)) & SIGNBIT) { \
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index c071663096..dd1bbeb2ec 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -6222,6 +6222,12 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u,
     TCGCond cond;
 
     switch (opcode) {
+    case 0x5: /* NOT */
+        /* This opcode is shared with CNT and RBIT but we have earlier
+         * enforced that size == 3 if and only if this is the NOT insn.
+         */
+        tcg_gen_not_i64(tcg_rd, tcg_rn);
+        break;
     case 0xa: /* CMLT */
         /* 64 bit integer comparison against zero, result is
          * test ? (2^64 - 1) : 0. We implement via setcond(!test) and
@@ -7385,13 +7391,19 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
     case 0x1: /* REV16 */
         unsupported_encoding(s, insn);
         return;
-    case 0x5: /* CNT, NOT, RBIT  */
-        if ((u == 0 && size > 0) ||
-            (u == 1 && size > 1)) {
-            unallocated_encoding(s);
-            return;
+    case 0x5: /* CNT, NOT, RBIT */
+        if (u && size == 0) {
+            /* NOT: adjust size so we can use the 64-bits-at-a-time loop. */
+            size = 3;
+            break;
+        } else if (u && size == 1) {
+            /* RBIT */
+            break;
+        } else if (!u && size == 0) {
+            /* CNT */
+            break;
         }
-        unsupported_encoding(s, insn);
+        unallocated_encoding(s);
         return;
     case 0x2: /* SADDLP, UADDLP */
     case 0x4: /* CLS, CLZ */
@@ -7553,6 +7565,16 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
             } else {
                 /* Use helpers for 8 and 16 bit elements */
                 switch (opcode) {
+                case 0x5: /* CNT, RBIT */
+                    /* For these two insns size is part of the opcode specifier
+                     * (handled earlier); they always operate on byte elements.
+                     */
+                    if (u) {
+                        gen_helper_neon_rbit_u8(tcg_res, tcg_op);
+                    } else {
+                        gen_helper_neon_cnt_u8(tcg_res, tcg_op);
+                    }
+                    break;
                 case 0x8: /* CMGT, CMGE */
                 case 0x9: /* CMEQ, CMLE */
                 case 0xa: /* CMLT */