diff mbox series

[3/6] target/arm: Convert sha512 and sm3 to gvec helpers

Message ID 20200514212831.31248-4-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 
Do not yet convert the helpers to loop over opr_sz, but the
descriptor allows the vector tail to be cleared.  Which fixes
an existing bug vs SVE.

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

---
 target/arm/helper.h        | 15 +++++++-----
 target/arm/crypto_helper.c | 37 +++++++++++++++++++++++-----
 target/arm/translate-a64.c | 50 ++++++++++++--------------------------
 3 files changed, 55 insertions(+), 47 deletions(-)

-- 
2.20.1
diff mbox series

Patch

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 6c4eb9befb..784dc29ce2 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -522,14 +522,17 @@  DEF_HELPER_FLAGS_3(crypto_sha256h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_2(crypto_sha256su0, TCG_CALL_NO_RWG, void, ptr, ptr)
 DEF_HELPER_FLAGS_3(crypto_sha256su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
 
-DEF_HELPER_FLAGS_3(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
-DEF_HELPER_FLAGS_3(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
-DEF_HELPER_FLAGS_2(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr)
-DEF_HELPER_FLAGS_3(crypto_sha512su1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(crypto_sha512h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha512h2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(crypto_sha512su0, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sha512su1, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(crypto_sm3tt, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
-DEF_HELPER_FLAGS_3(crypto_sm3partw1, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
-DEF_HELPER_FLAGS_3(crypto_sm3partw2, TCG_CALL_NO_RWG, void, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(crypto_sm3partw1, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(crypto_sm3partw2, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, i32)
 
 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)
diff --git a/target/arm/crypto_helper.c b/target/arm/crypto_helper.c
index 372d8350e4..637e4c00bb 100644
--- a/target/arm/crypto_helper.c
+++ b/target/arm/crypto_helper.c
@@ -31,6 +31,19 @@  union CRYPTO_STATE {
 #define CR_ST_WORD(state, i)   (state.words[i])
 #endif
 
+/*
+ * The caller has not been converted to full gvec, and so only
+ * modifies the low 16 bytes of the vector register.
+ */
+static void clear_tail_16(void *vd, uint32_t desc)
+{
+    int opr_sz = simd_oprsz(desc);
+    int max_sz = simd_maxsz(desc);
+
+    assert(opr_sz == 16);
+    clear_tail(vd, opr_sz, max_sz);
+}
+
 static void do_crypto_aese(uint64_t *rd, uint64_t *rn,
                            uint64_t *rm, bool decrypt)
 {
@@ -470,7 +483,7 @@  static uint64_t s1_512(uint64_t x)
     return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6);
 }
 
-void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm)
+void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     uint64_t *rd = vd;
     uint64_t *rn = vn;
@@ -483,9 +496,11 @@  void HELPER(crypto_sha512h)(void *vd, void *vn, void *vm)
 
     rd[0] = d0;
     rd[1] = d1;
+
+    clear_tail_16(vd, desc);
 }
 
-void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm)
+void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     uint64_t *rd = vd;
     uint64_t *rn = vn;
@@ -498,9 +513,11 @@  void HELPER(crypto_sha512h2)(void *vd, void *vn, void *vm)
 
     rd[0] = d0;
     rd[1] = d1;
+
+    clear_tail_16(vd, desc);
 }
 
-void HELPER(crypto_sha512su0)(void *vd, void *vn)
+void HELPER(crypto_sha512su0)(void *vd, void *vn, uint32_t desc)
 {
     uint64_t *rd = vd;
     uint64_t *rn = vn;
@@ -512,9 +529,11 @@  void HELPER(crypto_sha512su0)(void *vd, void *vn)
 
     rd[0] = d0;
     rd[1] = d1;
+
+    clear_tail_16(vd, desc);
 }
 
-void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm)
+void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     uint64_t *rd = vd;
     uint64_t *rn = vn;
@@ -522,9 +541,11 @@  void HELPER(crypto_sha512su1)(void *vd, void *vn, void *vm)
 
     rd[0] += s1_512(rn[0]) + rm[0];
     rd[1] += s1_512(rn[1]) + rm[1];
+
+    clear_tail_16(vd, desc);
 }
 
-void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm)
+void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     uint64_t *rd = vd;
     uint64_t *rn = vn;
@@ -548,9 +569,11 @@  void HELPER(crypto_sm3partw1)(void *vd, void *vn, void *vm)
 
     rd[0] = d.l[0];
     rd[1] = d.l[1];
+
+    clear_tail_16(vd, desc);
 }
 
-void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm)
+void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm, uint32_t desc)
 {
     uint64_t *rd = vd;
     uint64_t *rn = vn;
@@ -568,6 +591,8 @@  void HELPER(crypto_sm3partw2)(void *vd, void *vn, void *vm)
 
     rd[0] = d.l[0];
     rd[1] = d.l[1];
+
+    clear_tail_16(vd, desc);
 }
 
 void HELPER(crypto_sm3tt)(void *vd, void *vn, void *vm, uint32_t imm2,
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 4d7a8fd2bb..96e20fa401 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -13619,7 +13619,6 @@  static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn)
     int rn = extract32(insn, 5, 5);
     int rd = extract32(insn, 0, 5);
     bool feature;
-    CryptoThreeOpFn *genfn = NULL;
     gen_helper_gvec_3 *oolfn = NULL;
     GVecGen3Fn *gvecfn = NULL;
 
@@ -13627,15 +13626,15 @@  static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn)
         switch (opcode) {
         case 0: /* SHA512H */
             feature = dc_isar_feature(aa64_sha512, s);
-            genfn = gen_helper_crypto_sha512h;
+            oolfn = gen_helper_crypto_sha512h;
             break;
         case 1: /* SHA512H2 */
             feature = dc_isar_feature(aa64_sha512, s);
-            genfn = gen_helper_crypto_sha512h2;
+            oolfn = gen_helper_crypto_sha512h2;
             break;
         case 2: /* SHA512SU1 */
             feature = dc_isar_feature(aa64_sha512, s);
-            genfn = gen_helper_crypto_sha512su1;
+            oolfn = gen_helper_crypto_sha512su1;
             break;
         case 3: /* RAX1 */
             feature = dc_isar_feature(aa64_sha3, s);
@@ -13648,11 +13647,11 @@  static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn)
         switch (opcode) {
         case 0: /* SM3PARTW1 */
             feature = dc_isar_feature(aa64_sm3, s);
-            genfn = gen_helper_crypto_sm3partw1;
+            oolfn = gen_helper_crypto_sm3partw1;
             break;
         case 1: /* SM3PARTW2 */
             feature = dc_isar_feature(aa64_sm3, s);
-            genfn = gen_helper_crypto_sm3partw2;
+            oolfn = gen_helper_crypto_sm3partw2;
             break;
         case 2: /* SM4EKEY */
             feature = dc_isar_feature(aa64_sm4, s);
@@ -13675,20 +13674,8 @@  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);
-    } 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);
-        tcg_rn_ptr = vec_full_reg_ptr(s, rn);
-        tcg_rm_ptr = vec_full_reg_ptr(s, rm);
-
-        genfn(tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr);
-
-        tcg_temp_free_ptr(tcg_rd_ptr);
-        tcg_temp_free_ptr(tcg_rn_ptr);
-        tcg_temp_free_ptr(tcg_rm_ptr);
+        gen_gvec_fn3(s, true, rd, rn, rm, gvecfn, MO_64);
     }
 }
 
@@ -13703,19 +13690,14 @@  static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn)
     int opcode = extract32(insn, 10, 2);
     int rn = extract32(insn, 5, 5);
     int rd = extract32(insn, 0, 5);
-    TCGv_ptr tcg_rd_ptr, tcg_rn_ptr;
     bool feature;
-    CryptoTwoOpFn *genfn;
-    gen_helper_gvec_3 *oolfn = NULL;
 
     switch (opcode) {
     case 0: /* SHA512SU0 */
         feature = dc_isar_feature(aa64_sha512, s);
-        genfn = gen_helper_crypto_sha512su0;
         break;
     case 1: /* SM4E */
         feature = dc_isar_feature(aa64_sm4, s);
-        oolfn = gen_helper_crypto_sm4e;
         break;
     default:
         unallocated_encoding(s);
@@ -13731,18 +13713,16 @@  static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn)
         return;
     }
 
-    if (oolfn) {
-        gen_gvec_op3_ool(s, true, rd, rd, rn, 0, oolfn);
-        return;
+    switch (opcode) {
+    case 0: /* SHA512SU0 */
+        gen_gvec_op2_ool(s, true, rd, rn, 0, gen_helper_crypto_sha512su0);
+        break;
+    case 1: /* SM4E */
+        gen_gvec_op3_ool(s, true, rd, rd, rn, 0, gen_helper_crypto_sm4e);
+        break;
+    default:
+        g_assert_not_reached();
     }
-
-    tcg_rd_ptr = vec_full_reg_ptr(s, rd);
-    tcg_rn_ptr = vec_full_reg_ptr(s, rn);
-
-    genfn(tcg_rd_ptr, tcg_rn_ptr);
-
-    tcg_temp_free_ptr(tcg_rd_ptr);
-    tcg_temp_free_ptr(tcg_rn_ptr);
 }
 
 /* Crypto four-register