[PULL 30/45] target/arm: Convert Neon 3-reg-same SHA to decodetree

[Peter Maydell]

Convert the Neon SHA instructions in the 3-reg-same group
to decodetree.

Signed-off-by: Peter Maydell <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
Message-id: address@hidden
---
 target/arm/neon-dp.decode       |  10 +++
 target/arm/translate-neon.inc.c | 139 ++++++++++++++++++++++++++++++++
 target/arm/translate.c          |  46 +----------
 3 files changed, 151 insertions(+), 44 deletions(-)

diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 82503c582ef..72eae12b265 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -99,4 +99,14 @@ VMUL_3s          1111 001 0 0 . .. .... .... 1001 . . . 1 
.... @3same
 VMUL_p_3s        1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same
 
 VQRDMLAH_3s      1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same
+
+SHA1_3s          1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \
+                 vm=%vm_dp vn=%vn_dp vd=%vd_dp
+SHA256H_3s       1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... \
+                 vm=%vm_dp vn=%vn_dp vd=%vd_dp
+SHA256H2_3s      1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... \
+                 vm=%vm_dp vn=%vn_dp vd=%vd_dp
+SHA256SU1_3s     1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... \
+                 vm=%vm_dp vn=%vn_dp vd=%vd_dp
+
 VQRDMLSH_3s      1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index 661b5fc4cf2..03b3337e460 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -686,3 +686,142 @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a)
 
 DO_VQRDMLAH(VQRDMLAH, gen_gvec_sqrdmlah_qc)
 DO_VQRDMLAH(VQRDMLSH, gen_gvec_sqrdmlsh_qc)
+
+static bool trans_SHA1_3s(DisasContext *s, arg_SHA1_3s *a)
+{
+    TCGv_ptr ptr1, ptr2, ptr3;
+    TCGv_i32 tmp;
+
+    if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+        !dc_isar_feature(aa32_sha1, s)) {
+        return false;
+    }
+
+    /* UNDEF accesses to D16-D31 if they don't exist. */
+    if (!dc_isar_feature(aa32_simd_r32, s) &&
+        ((a->vd | a->vn | a->vm) & 0x10)) {
+        return false;
+    }
+
+    if ((a->vn | a->vm | a->vd) & 1) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    ptr1 = vfp_reg_ptr(true, a->vd);
+    ptr2 = vfp_reg_ptr(true, a->vn);
+    ptr3 = vfp_reg_ptr(true, a->vm);
+    tmp = tcg_const_i32(a->optype);
+    gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp);
+    tcg_temp_free_i32(tmp);
+    tcg_temp_free_ptr(ptr1);
+    tcg_temp_free_ptr(ptr2);
+    tcg_temp_free_ptr(ptr3);
+
+    return true;
+}
+
+static bool trans_SHA256H_3s(DisasContext *s, arg_SHA256H_3s *a)
+{
+    TCGv_ptr ptr1, ptr2, ptr3;
+
+    if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+        !dc_isar_feature(aa32_sha2, s)) {
+        return false;
+    }
+
+    /* UNDEF accesses to D16-D31 if they don't exist. */
+    if (!dc_isar_feature(aa32_simd_r32, s) &&
+        ((a->vd | a->vn | a->vm) & 0x10)) {
+        return false;
+    }
+
+    if ((a->vn | a->vm | a->vd) & 1) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    ptr1 = vfp_reg_ptr(true, a->vd);
+    ptr2 = vfp_reg_ptr(true, a->vn);
+    ptr3 = vfp_reg_ptr(true, a->vm);
+    gen_helper_crypto_sha256h(ptr1, ptr2, ptr3);
+    tcg_temp_free_ptr(ptr1);
+    tcg_temp_free_ptr(ptr2);
+    tcg_temp_free_ptr(ptr3);
+
+    return true;
+}
+
+static bool trans_SHA256H2_3s(DisasContext *s, arg_SHA256H2_3s *a)
+{
+    TCGv_ptr ptr1, ptr2, ptr3;
+
+    if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+        !dc_isar_feature(aa32_sha2, s)) {
+        return false;
+    }
+
+    /* UNDEF accesses to D16-D31 if they don't exist. */
+    if (!dc_isar_feature(aa32_simd_r32, s) &&
+        ((a->vd | a->vn | a->vm) & 0x10)) {
+        return false;
+    }
+
+    if ((a->vn | a->vm | a->vd) & 1) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    ptr1 = vfp_reg_ptr(true, a->vd);
+    ptr2 = vfp_reg_ptr(true, a->vn);
+    ptr3 = vfp_reg_ptr(true, a->vm);
+    gen_helper_crypto_sha256h2(ptr1, ptr2, ptr3);
+    tcg_temp_free_ptr(ptr1);
+    tcg_temp_free_ptr(ptr2);
+    tcg_temp_free_ptr(ptr3);
+
+    return true;
+}
+
+static bool trans_SHA256SU1_3s(DisasContext *s, arg_SHA256SU1_3s *a)
+{
+    TCGv_ptr ptr1, ptr2, ptr3;
+
+    if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+        !dc_isar_feature(aa32_sha2, s)) {
+        return false;
+    }
+
+    /* UNDEF accesses to D16-D31 if they don't exist. */
+    if (!dc_isar_feature(aa32_simd_r32, s) &&
+        ((a->vd | a->vn | a->vm) & 0x10)) {
+        return false;
+    }
+
+    if ((a->vn | a->vm | a->vd) & 1) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    ptr1 = vfp_reg_ptr(true, a->vd);
+    ptr2 = vfp_reg_ptr(true, a->vn);
+    ptr3 = vfp_reg_ptr(true, a->vm);
+    gen_helper_crypto_sha256su1(ptr1, ptr2, ptr3);
+    tcg_temp_free_ptr(ptr1);
+    tcg_temp_free_ptr(ptr2);
+    tcg_temp_free_ptr(ptr3);
+
+    return true;
+}
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 1f06cb5a87f..ee2b8d6f6e3 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5359,7 +5359,7 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t 
insn)
     int vec_size;
     uint32_t imm;
     TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5;
-    TCGv_ptr ptr1, ptr2, ptr3;
+    TCGv_ptr ptr1, ptr2;
     TCGv_i64 tmp64;
 
     if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@@ -5403,49 +5403,6 @@ static int disas_neon_data_insn(DisasContext *s, 
uint32_t insn)
             return 1;
         }
         switch (op) {
-        case NEON_3R_SHA:
-            /* The SHA-1/SHA-256 3-register instructions require special
-             * treatment here, as their size field is overloaded as an
-             * op type selector, and they all consume their input in a
-             * single pass.
-             */
-            if (!q) {
-                return 1;
-            }
-            if (!u) { /* SHA-1 */
-                if (!dc_isar_feature(aa32_sha1, s)) {
-                    return 1;
-                }
-                ptr1 = vfp_reg_ptr(true, rd);
-                ptr2 = vfp_reg_ptr(true, rn);
-                ptr3 = vfp_reg_ptr(true, rm);
-                tmp4 = tcg_const_i32(size);
-                gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp4);
-                tcg_temp_free_i32(tmp4);
-            } else { /* SHA-256 */
-                if (!dc_isar_feature(aa32_sha2, s) || size == 3) {
-                    return 1;
-                }
-                ptr1 = vfp_reg_ptr(true, rd);
-                ptr2 = vfp_reg_ptr(true, rn);
-                ptr3 = vfp_reg_ptr(true, rm);
-                switch (size) {
-                case 0:
-                    gen_helper_crypto_sha256h(ptr1, ptr2, ptr3);
-                    break;
-                case 1:
-                    gen_helper_crypto_sha256h2(ptr1, ptr2, ptr3);
-                    break;
-                case 2:
-                    gen_helper_crypto_sha256su1(ptr1, ptr2, ptr3);
-                    break;
-                }
-            }
-            tcg_temp_free_ptr(ptr1);
-            tcg_temp_free_ptr(ptr2);
-            tcg_temp_free_ptr(ptr3);
-            return 0;
-
         case NEON_3R_VPADD_VQRDMLAH:
             if (!u) {
                 break;  /* VPADD */
@@ -5496,6 +5453,7 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t 
insn)
         case NEON_3R_VMUL:
         case NEON_3R_VML:
         case NEON_3R_VSHL:
+        case NEON_3R_SHA:
             /* Already handled by decodetree */
             return 1;
         }
-- 
2.20.1