diff mbox series

[2/6] target/arm: Convert rax1 to gvec helpers

Message ID 20200514212831.31248-3-richard.henderson@linaro.org
State New
Headers show
Series target/arm: Convert crypto to gvec | expand

Commit Message

Richard Henderson May 14, 2020, 9:28 p.m. UTC 
With this conversion, we will be able to use the same helpers
with sve.  This also fixes a bug in which we failed to clear
the high bits of the SVE register after an AdvSIMD operation.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 target/arm/helper.h        |  2 ++
 target/arm/translate-a64.h |  3 ++
 target/arm/crypto_helper.c | 11 +++++++
 target/arm/translate-a64.c | 59 ++++++++++++++++++++------------------
 4 files changed, 47 insertions(+), 28 deletions(-)

-- 
2.20.1
diff mbox series

Patch

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 42759f82aa..6c4eb9befb 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -534,6 +534,8 @@  DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(crypto_sm4e, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(crypto_sm4ekey, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(crypto_rax1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
 DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32)
 
diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h
index f02fbb63a4..da0f59a2ce 100644
--- a/target/arm/translate-a64.h
+++ b/target/arm/translate-a64.h
@@ -115,4 +115,7 @@  static inline int vec_full_reg_size(DisasContext *s)
 
 bool disas_sve(DisasContext *, uint32_t);
 
+void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                   uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz);
+
 #endif /* TARGET_ARM_TRANSLATE_A64_H */
diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c
index 6bd5a3d2d0..372d8350e4 100644
--- a/target/arm/crypto_helper.c
+++ b/target/arm/crypto_helper.c
@@ -725,3 +725,14 @@  void HELPER(crypto_sm4ekey)(void *vd, void *vn, void* vm, uint32_t desc)
     }
     clear_tail(vd, opr_sz, simd_maxsz(desc));
 }
+
+void HELPER(crypto_rax1)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint64_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 8; ++i) {
+        d[i] = n[i] ^ rol64(m[i], 1);
+    }
+    clear_tail(vd, opr_sz, simd_maxsz(desc));
+}
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 1e511529b8..4d7a8fd2bb 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -13579,6 +13579,32 @@  static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn)
     tcg_temp_free_ptr(tcg_rn_ptr);
 }
 
+static void gen_rax1_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m)
+{
+    tcg_gen_rotli_i64(d, m, 1);
+    tcg_gen_xor_i64(d, d, n);
+}
+
+static void gen_rax1_vec(unsigned vece, TCGv_vec d, TCGv_vec n, TCGv_vec m)
+{
+    tcg_gen_rotli_vec(vece, d, m, 1);
+    tcg_gen_xor_vec(vece, d, d, n);
+}
+
+void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+                   uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+    static const TCGOpcode vecop_list[] = { INDEX_op_rotli_vec, 0 };
+    static const GVecGen3 op = {
+        .fni8 = gen_rax1_i64,
+        .fniv = gen_rax1_vec,
+        .opt_opc = vecop_list,
+        .fno = gen_helper_crypto_rax1,
+        .vece = MO_64,
+    };
+    tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &op);
+}
+
 /* Crypto three-reg SHA512
  *  31                   21 20  16 15  14  13 12  11  10  9    5 4    0
  * +-----------------------+------+---+---+-----+--------+------+------+
@@ -13595,6 +13621,7 @@  static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn)
     bool feature;
     CryptoThreeOpFn *genfn = NULL;
     gen_helper_gvec_3 *oolfn = NULL;
+    GVecGen3Fn *gvecfn = NULL;
 
     if (o == 0) {
         switch (opcode) {
@@ -13612,7 +13639,7 @@  static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn)
             break;
         case 3: /* RAX1 */
             feature = dc_isar_feature(aa64_sha3, s);
-            genfn = NULL;
+            gvecfn = gen_gvec_rax1;
             break;
         default:
             g_assert_not_reached();
@@ -13648,10 +13675,9 @@  static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn)
 
     if (oolfn) {
         gen_gvec_op3_ool(s, true, rd, rn, rm, 0, oolfn);
-        return;
-    }
-
-    if (genfn) {
+    } else if (gvecfn) {
+        gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64);
+    } else {
         TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr;
 
         tcg_rd_ptr = vec_full_reg_ptr(s, rd);
@@ -13663,29 +13689,6 @@  static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn)
         tcg_temp_free_ptr(tcg_rd_ptr);
         tcg_temp_free_ptr(tcg_rn_ptr);
         tcg_temp_free_ptr(tcg_rm_ptr);
-    } else {
-        TCGv_i64 tcg_op1, tcg_op2, tcg_res[2];
-        int pass;
-
-        tcg_op1 = tcg_temp_new_i64();
-        tcg_op2 = 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);
-
-            tcg_gen_rotli_i64(tcg_res[pass], tcg_op2, 1);
-            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);
-
-        tcg_temp_free_i64(tcg_op1);
-        tcg_temp_free_i64(tcg_op2);
-        tcg_temp_free_i64(tcg_res[0]);
-        tcg_temp_free_i64(tcg_res[1]);
     }
 }