SM4 optimization for ARM by ASIMD

This patch optimizes SM4 for ARM processor using ASIMD instruction

It will improve performance if both of following conditions are met:
1) Input data equal to or more than 4 blocks
2) Cipher mode allows parallelism, including ECB,CTR,GCM or CBC decryption

This patch implements SM4 SBOX lookup in vector registers, with the
benefit of constant processing time over existing C implementation.

It is only enabled for micro-architecture N1/V1. In the ideal scenario,
performance can reach up to 2.7X

When either of above two conditions is not met, e.g. single block input
or CFB/OFB mode, CBC encryption, performance could drop about 50%.

The assembly code has been reviewed internally by ARM engineer
Fangming.Fang@arm.com

Signed-off-by: Daniel Hu <Daniel.Hu@arm.com>

Reviewed-by: Paul Dale <pauli@openssl.org>
Reviewed-by: Tomas Mraz <tomas@openssl.org>
(Merged from #17951)

(cherry picked from commit 4908787)

crypto/evp/e_sm4.c

@@ -76,6 +76,17 @@ static int sm4_init_key(EVP_CIPHER_CTX *ctx, const unsigned char *key,
                 dat->stream.ecb = (ecb128_f) HWSM4_ecb_encrypt;
 # endif
         } else
+#endif
+#ifdef VPSM4_CAPABLE
+        if (VPSM4_CAPABLE) {
+            vpsm4_set_decrypt_key(key, &dat->ks.ks);
+            dat->block = (block128_f) vpsm4_decrypt;
+            dat->stream.cbc = NULL;
+            if (mode == EVP_CIPH_CBC_MODE)
+                dat->stream.cbc = (cbc128_f) vpsm4_cbc_encrypt;
+            else if (mode == EVP_CIPH_ECB_MODE)
+                dat->stream.ecb = (ecb128_f) vpsm4_ecb_encrypt;
+        } else
 #endif
         {
             dat->block = (block128_f) ossl_sm4_decrypt;
@@ -104,6 +115,19 @@ static int sm4_init_key(EVP_CIPHER_CTX *ctx, const unsigned char *key,
 # endif
             (void)0;            /* terminate potentially open 'else' */
     } else
+#endif
+#ifdef VPSM4_CAPABLE
+    if (VPSM4_CAPABLE) {
+        vpsm4_set_encrypt_key(key, &dat->ks.ks);
+        dat->block = (block128_f) vpsm4_encrypt;
+        dat->stream.cbc = NULL;
+        if (mode == EVP_CIPH_CBC_MODE)
+            dat->stream.cbc = (cbc128_f) vpsm4_cbc_encrypt;
+        else if (mode == EVP_CIPH_ECB_MODE)
+            dat->stream.ecb = (ecb128_f) vpsm4_ecb_encrypt;
+        else if (mode == EVP_CIPH_CTR_MODE)
+            dat->stream.ctr = (ctr128_f) vpsm4_ctr32_encrypt_blocks;
+    } else
 #endif
     {
         dat->block = (block128_f) ossl_sm4_encrypt;