qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-arm@nongnu.org, qemu-devel@nongnu.org
Cc: Richard Henderson <richard.henderson@linaro.org>
Subject: [PATCH v2 02/17] target/arm: Convert Neon 3-reg-same SHA to decodetree
Date: Tue, 12 May 2020 17:38:49 +0100	[thread overview]
Message-ID: <20200512163904.10918-3-peter.maydell@linaro.org> (raw)
In-Reply-To: <20200512163904.10918-1-peter.maydell@linaro.org>

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

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 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 04aff438410..68b0a44793f 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -91,4 +91,14 @@ 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



  parent reply	other threads:[~2020-05-12 16:40 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-12 16:38 [PATCH v2 00/17] target/arm: Convert rest of Neon 3-reg-same to decodetree Peter Maydell
2020-05-12 16:38 ` [PATCH v2 01/17] target/arm: Convert Neon 3-reg-same VQRDMLAH/VQRDMLSH " Peter Maydell
2020-05-13 16:39   ` Richard Henderson
2020-05-12 16:38 ` Peter Maydell [this message]
2020-05-12 16:38 ` [PATCH v2 03/17] target/arm: Convert Neon 64-bit element 3-reg-same insns Peter Maydell
2020-05-13 20:27   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 04/17] target/arm: Convert Neon VHADD " Peter Maydell
2020-05-13 16:47   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 05/17] target/arm: Convert Neon VABA/VABD 3-reg-same to decodetree Peter Maydell
2020-05-13 16:48   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 06/17] target/arm: Convert Neon VRHADD, VHSUB 3-reg-same insns " Peter Maydell
2020-05-13 16:50   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 07/17] target/arm: Convert Neon VQSHL, VRSHL, VQRSHL " Peter Maydell
2020-05-13 16:55   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 08/17] target/arm: Convert Neon VPMAX/VPMIN " Peter Maydell
2020-05-12 16:38 ` [PATCH v2 09/17] target/arm: Convert Neon VPADD " Peter Maydell
2020-05-12 16:38 ` [PATCH v2 10/17] target/arm: Convert Neon VQDMULH/VQRDMULH 3-reg-same " Peter Maydell
2020-05-13 16:58   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 11/17] target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns " Peter Maydell
2020-05-13 20:06   ` Richard Henderson
2020-05-12 16:38 ` [PATCH v2 12/17] target/arm: Convert Neon VPMIN/VPMAX/VPADD float " Peter Maydell
2020-05-12 16:39 ` [PATCH v2 13/17] target/arm: Convert Neon fp VMUL, VMLA, VMLS " Peter Maydell
2020-05-13 20:28   ` Richard Henderson
2020-05-12 16:39 ` [PATCH v2 14/17] target/arm: Convert Neon 3-reg-same compare " Peter Maydell
2020-05-12 16:39 ` [PATCH v2 15/17] target/arm: Move 'env' argument of recps_f32 and rsqrts_f32 helpers to usual place Peter Maydell
2020-05-13 20:16   ` Richard Henderson
2020-05-12 16:39 ` [PATCH v2 16/17] target/arm: Convert Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS to decodetree Peter Maydell
2020-05-13 20:20   ` Richard Henderson
2020-05-12 16:39 ` [PATCH v2 17/17] target/arm: Convert NEON VFMA, VFMS 3-reg-same insns " Peter Maydell
2020-05-12 23:44 ` [PATCH v2 00/17] target/arm: Convert rest of Neon 3-reg-same " no-reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200512163904.10918-3-peter.maydell@linaro.org \
    --to=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).