diff mbox series

[v2,14/67] target/arm: Convert Cryptographic 4-register to decodetree

Message ID 20240524232121.284515-15-richard.henderson@linaro.org
State Superseded
Headers show
Series target/arm: Convert a64 advsimd to decodetree (part 1) | expand

Commit Message

Richard Henderson May 24, 2024, 11:20 p.m. UTC
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/a64.decode      |   8 ++
 target/arm/tcg/translate-a64.c | 132 +++++++++++----------------------
 2 files changed, 51 insertions(+), 89 deletions(-)
diff mbox series

Patch

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 5a46205751..ef6902e86a 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -27,11 +27,13 @@ 
 &i              imm
 &qrr_e          q rd rn esz
 &qrrr_e         q rd rn rm esz
+&qrrrr_e        q rd rn rm ra esz
 
 @rr_q1e0        ........ ........ ...... rn:5 rd:5      &qrr_e q=1 esz=0
 @r2r_q1e0       ........ ........ ...... rm:5 rd:5      &qrrr_e rn=%rd q=1 esz=0
 @rrr_q1e0       ........ ... rm:5 ...... rn:5 rd:5      &qrrr_e q=1 esz=0
 @rrr_q1e3       ........ ... rm:5 ...... rn:5 rd:5      &qrrr_e q=1 esz=3
+@rrrr_q1e3      ........ ... rm:5 . ra:5 rn:5 rd:5      &qrrrr_e q=1 esz=3
 
 ### Data Processing - Immediate
 
@@ -636,3 +638,9 @@  SM4EKEY         1100 1110 011 ..... 110010 ..... .....  @rrr_q1e0
 
 SHA512SU0       1100 1110 110 00000 100000 ..... .....  @rr_q1e0
 SM4E            1100 1110 110 00000 100001 ..... .....  @r2r_q1e0
+
+### Cryptographic four-register
+
+EOR3            1100 1110 000 ..... 0 ..... ..... ..... @rrrr_q1e3
+BCAX            1100 1110 001 ..... 0 ..... ..... ..... @rrrr_q1e3
+SM3SS1          1100 1110 010 ..... 0 ..... ..... ..... @rrrr_q1e3
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index eed0abe912..2951e7eb59 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -1352,6 +1352,17 @@  static bool do_gvec_fn3(DisasContext *s, arg_qrrr_e *a, GVecGen3Fn *fn)
     return true;
 }
 
+static bool do_gvec_fn4(DisasContext *s, arg_qrrrr_e *a, GVecGen4Fn *fn)
+{
+    if (!a->q && a->esz == MO_64) {
+        return false;
+    }
+    if (fp_access_check(s)) {
+        gen_gvec_fn4(s, a->q, a->rd, a->rn, a->rm, a->ra, fn, a->esz);
+    }
+    return true;
+}
+
 /*
  * This utility function is for doing register extension with an
  * optional shift. You will likely want to pass a temporary for the
@@ -4632,6 +4643,38 @@  TRANS_FEAT(SM4EKEY, aa64_sm4, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm4ekey)
 TRANS_FEAT(SHA512SU0, aa64_sha512, do_gvec_op2_ool, a, 0, gen_helper_crypto_sha512su0)
 TRANS_FEAT(SM4E, aa64_sm4, do_gvec_op3_ool, a, 0, gen_helper_crypto_sm4e)
 
+TRANS_FEAT(EOR3, aa64_sha3, do_gvec_fn4, a, gen_gvec_eor3)
+TRANS_FEAT(BCAX, aa64_sha3, do_gvec_fn4, a, gen_gvec_bcax)
+
+static bool trans_SM3SS1(DisasContext *s, arg_SM3SS1 *a)
+{
+    if (!dc_isar_feature(aa64_sm3, s)) {
+        return false;
+    }
+    if (fp_access_check(s)) {
+        TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+        TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+        TCGv_i32 tcg_op3 = tcg_temp_new_i32();
+        TCGv_i32 tcg_res = tcg_temp_new_i32();
+        unsigned vsz, dofs;
+
+        read_vec_element_i32(s, tcg_op1, a->rn, 3, MO_32);
+        read_vec_element_i32(s, tcg_op2, a->rm, 3, MO_32);
+        read_vec_element_i32(s, tcg_op3, a->ra, 3, MO_32);
+
+        tcg_gen_rotri_i32(tcg_res, tcg_op1, 20);
+        tcg_gen_add_i32(tcg_res, tcg_res, tcg_op2);
+        tcg_gen_add_i32(tcg_res, tcg_res, tcg_op3);
+        tcg_gen_rotri_i32(tcg_res, tcg_res, 25);
+
+        /* Clear the whole register first, then store bits [127:96]. */
+        vsz = vec_full_reg_size(s);
+        dofs = vec_full_reg_offset(s, a->rd);
+        tcg_gen_gvec_dup_imm(MO_64, dofs, vsz, vsz, 0);
+        write_vec_element_i32(s, tcg_res, a->rd, 3, MO_32);
+    }
+    return true;
+}
 
 /* Shift a TCGv src by TCGv shift_amount, put result in dst.
  * Note that it is the caller's responsibility to ensure that the
@@ -13533,94 +13576,6 @@  static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Crypto four-register
- *  31               23 22 21 20  16 15  14  10 9    5 4    0
- * +-------------------+-----+------+---+------+------+------+
- * | 1 1 0 0 1 1 1 0 0 | Op0 |  Rm  | 0 |  Ra  |  Rn  |  Rd  |
- * +-------------------+-----+------+---+------+------+------+
- */
-static void disas_crypto_four_reg(DisasContext *s, uint32_t insn)
-{
-    int op0 = extract32(insn, 21, 2);
-    int rm = extract32(insn, 16, 5);
-    int ra = extract32(insn, 10, 5);
-    int rn = extract32(insn, 5, 5);
-    int rd = extract32(insn, 0, 5);
-    bool feature;
-
-    switch (op0) {
-    case 0: /* EOR3 */
-    case 1: /* BCAX */
-        feature = dc_isar_feature(aa64_sha3, s);
-        break;
-    case 2: /* SM3SS1 */
-        feature = dc_isar_feature(aa64_sm3, s);
-        break;
-    default:
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!feature) {
-        unallocated_encoding(s);
-        return;
-    }
-
-    if (!fp_access_check(s)) {
-        return;
-    }
-
-    if (op0 < 2) {
-        TCGv_i64 tcg_op1, tcg_op2, tcg_op3, tcg_res[2];
-        int pass;
-
-        tcg_op1 = tcg_temp_new_i64();
-        tcg_op2 = tcg_temp_new_i64();
-        tcg_op3 = tcg_temp_new_i64();
-        tcg_res[0] = tcg_temp_new_i64();
-        tcg_res[1] = tcg_temp_new_i64();
-
-        for (pass = 0; pass < 2; pass++) {
-            read_vec_element(s, tcg_op1, rn, pass, MO_64);
-            read_vec_element(s, tcg_op2, rm, pass, MO_64);
-            read_vec_element(s, tcg_op3, ra, pass, MO_64);
-
-            if (op0 == 0) {
-                /* EOR3 */
-                tcg_gen_xor_i64(tcg_res[pass], tcg_op2, tcg_op3);
-            } else {
-                /* BCAX */
-                tcg_gen_andc_i64(tcg_res[pass], tcg_op2, tcg_op3);
-            }
-            tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1);
-        }
-        write_vec_element(s, tcg_res[0], rd, 0, MO_64);
-        write_vec_element(s, tcg_res[1], rd, 1, MO_64);
-    } else {
-        TCGv_i32 tcg_op1, tcg_op2, tcg_op3, tcg_res, tcg_zero;
-
-        tcg_op1 = tcg_temp_new_i32();
-        tcg_op2 = tcg_temp_new_i32();
-        tcg_op3 = tcg_temp_new_i32();
-        tcg_res = tcg_temp_new_i32();
-        tcg_zero = tcg_constant_i32(0);
-
-        read_vec_element_i32(s, tcg_op1, rn, 3, MO_32);
-        read_vec_element_i32(s, tcg_op2, rm, 3, MO_32);
-        read_vec_element_i32(s, tcg_op3, ra, 3, MO_32);
-
-        tcg_gen_rotri_i32(tcg_res, tcg_op1, 20);
-        tcg_gen_add_i32(tcg_res, tcg_res, tcg_op2);
-        tcg_gen_add_i32(tcg_res, tcg_res, tcg_op3);
-        tcg_gen_rotri_i32(tcg_res, tcg_res, 25);
-
-        write_vec_element_i32(s, tcg_zero, rd, 0, MO_32);
-        write_vec_element_i32(s, tcg_zero, rd, 1, MO_32);
-        write_vec_element_i32(s, tcg_zero, rd, 2, MO_32);
-        write_vec_element_i32(s, tcg_res, rd, 3, MO_32);
-    }
-}
-
 /* Crypto XAR
  *  31                   21 20  16 15    10 9    5 4    0
  * +-----------------------+------+--------+------+------+
@@ -13707,7 +13662,6 @@  static const AArch64DecodeTable data_proc_simd[] = {
     { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy },
     { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */
     { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm },
-    { 0xce000000, 0xff808000, disas_crypto_four_reg },
     { 0xce800000, 0xffe00000, disas_crypto_xar },
     { 0xce408000, 0xffe0c000, disas_crypto_three_reg_imm2 },
     { 0x0e400400, 0x9f60c400, disas_simd_three_reg_same_fp16 },