Whack sha with a style(9) stick.

No change in generated assembly.

4 files changed, 706 insertions, 505 deletions

diff --git a/src/lib/libcrypto/sha/sha1_one.c b/src/lib/libcrypto/sha/sha1_one.c
index 91602ee503..085c1db23e 100644
--- a/src/lib/libcrypto/sha/sha1_one.c
+++ b/src/lib/libcrypto/sha/sha1_one.c
@@ -1,25 +1,25 @@
-/* $OpenBSD: sha1_one.c,v 1.12 2015/09/10 15:56:26 jsing Exp $ */
+/* $OpenBSD: sha1_one.c,v 1.13 2023/03/26 16:40:07 jsing Exp $ */
 /* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
  * All rights reserved.
  *
  * This package is an SSL implementation written
  * by Eric Young (eay@cryptsoft.com).
  * The implementation was written so as to conform with Netscapes SSL.
- * 
+ *
  * This library is free for commercial and non-commercial use as long as
  * the following conditions are aheared to.  The following conditions
  * apply to all code found in this distribution, be it the RC4, RSA,
  * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
  * included with this distribution is covered by the same copyright terms
  * except that the holder is Tim Hudson (tjh@cryptsoft.com).
- * 
+ *
  * Copyright remains Eric Young's, and as such any Copyright notices in
  * the code are not to be removed.
  * If this package is used in a product, Eric Young should be given attribution
  * as the author of the parts of the library used.
  * This can be in the form of a textual message at program startup or
  * in documentation (online or textual) provided with the package.
- * 
+ *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
  * are met:
@@ -34,10 +34,10 @@
  *     Eric Young (eay@cryptsoft.com)"
  *    The word 'cryptographic' can be left out if the rouines from the library
  *    being used are not cryptographic related :-).
- * 4. If you include any Windows specific code (or a derivative thereof) from 
+ * 4. If you include any Windows specific code (or a derivative thereof) from
  *    the apps directory (application code) you must include an acknowledgement:
  *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
- * 
+ *
  * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
@@ -49,7 +49,7 @@
  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE.
- * 
+ *
  * The licence and distribution terms for any publically available version or
  * derivative of this code cannot be changed.  i.e. this code cannot simply be
  * copied and put under another distribution licence
@@ -65,17 +65,19 @@
 #include <openssl/sha.h>
 
 #ifndef OPENSSL_NO_SHA1
-unsigned char *SHA1(const unsigned char *d, size_t n, unsigned char *md)
-        {
+unsigned char *
+SHA1(const unsigned char *d, size_t n, unsigned char *md)
+{
         SHA_CTX c;
         static unsigned char m[SHA_DIGEST_LENGTH];
 
-        if (md == NULL) md=m;
+        if (md == NULL)
+                md = m;
         if (!SHA1_Init(&c))
                 return NULL;
-        SHA1_Update(&c,d,n);
-        SHA1_Final(md,&c);
-        explicit_bzero(&c,sizeof(c));
-        return(md);
-        }
+        SHA1_Update(&c, d, n);
+        SHA1_Final(md, &c);
+        explicit_bzero(&c, sizeof(c));
+        return (md);
+}
 #endif
diff --git a/src/lib/libcrypto/sha/sha1dgst.c b/src/lib/libcrypto/sha/sha1dgst.c
index 16580dcbdd..4fb449d763 100644
--- a/src/lib/libcrypto/sha/sha1dgst.c
+++ b/src/lib/libcrypto/sha/sha1dgst.c
@@ -1,25 +1,25 @@
-/* $OpenBSD: sha1dgst.c,v 1.15 2022/11/26 16:08:54 tb Exp $ */
+/* $OpenBSD: sha1dgst.c,v 1.16 2023/03/26 16:40:07 jsing Exp $ */
 /* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
  * All rights reserved.
  *
  * This package is an SSL implementation written
  * by Eric Young (eay@cryptsoft.com).
  * The implementation was written so as to conform with Netscapes SSL.
- * 
+ *
  * This library is free for commercial and non-commercial use as long as
  * the following conditions are aheared to.  The following conditions
  * apply to all code found in this distribution, be it the RC4, RSA,
  * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
  * included with this distribution is covered by the same copyright terms
  * except that the holder is Tim Hudson (tjh@cryptsoft.com).
- * 
+ *
  * Copyright remains Eric Young's, and as such any Copyright notices in
  * the code are not to be removed.
  * If this package is used in a product, Eric Young should be given attribution
  * as the author of the parts of the library used.
  * This can be in the form of a textual message at program startup or
  * in documentation (online or textual) provided with the package.
- * 
+ *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
  * are met:
@@ -34,10 +34,10 @@
  *     Eric Young (eay@cryptsoft.com)"
  *    The word 'cryptographic' can be left out if the rouines from the library
  *    being used are not cryptographic related :-).
- * 4. If you include any Windows specific code (or a derivative thereof) from 
+ * 4. If you include any Windows specific code (or a derivative thereof) from
  *    the apps directory (application code) you must include an acknowledgement:
  *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
- * 
+ *
  * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
@@ -49,7 +49,7 @@
  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE.
- * 
+ *
  * The licence and distribution terms for any publically available version or
  * derivative of this code cannot be changed.  i.e. this code cannot simply be
  * copied and put under another distribution licence
@@ -69,4 +69,3 @@
 #include "sha_local.h"
 
 #endif
-
diff --git a/src/lib/libcrypto/sha/sha256.c b/src/lib/libcrypto/sha/sha256.c
index e826ca9e19..86c7f6c61a 100644
--- a/src/lib/libcrypto/sha/sha256.c
+++ b/src/lib/libcrypto/sha/sha256.c
@@ -1,4 +1,4 @@
-/* $OpenBSD: sha256.c,v 1.11 2021/11/09 18:40:21 bcook Exp $ */
+/* $OpenBSD: sha256.c,v 1.12 2023/03/26 16:40:07 jsing Exp $ */
 /* ====================================================================
  * Copyright (c) 2004 The OpenSSL Project.  All rights reserved
  * according to the OpenSSL license [found in ../../LICENSE].
@@ -17,58 +17,79 @@
 #include <openssl/sha.h>
 #include <openssl/opensslv.h>
 
-int SHA224_Init(SHA256_CTX *c)
-        {
-        memset (c,0,sizeof(*c));
-        c->h[0]=0xc1059ed8UL;   c->h[1]=0x367cd507UL;
-        c->h[2]=0x3070dd17UL;   c->h[3]=0xf70e5939UL;
-        c->h[4]=0xffc00b31UL;   c->h[5]=0x68581511UL;
-        c->h[6]=0x64f98fa7UL;   c->h[7]=0xbefa4fa4UL;
-        c->md_len=SHA224_DIGEST_LENGTH;
+int
+SHA224_Init(SHA256_CTX *c)
+{
+        memset (c, 0, sizeof(*c));
+        c->h[0] = 0xc1059ed8UL;
+        c->h[1] = 0x367cd507UL;
+        c->h[2] = 0x3070dd17UL;
+        c->h[3] = 0xf70e5939UL;
+        c->h[4] = 0xffc00b31UL;
+        c->h[5] = 0x68581511UL;
+        c->h[6] = 0x64f98fa7UL;
+        c->h[7] = 0xbefa4fa4UL;
+        c->md_len = SHA224_DIGEST_LENGTH;
         return 1;
-        }
+}
 
-int SHA256_Init(SHA256_CTX *c)
-        {
-        memset (c,0,sizeof(*c));
-        c->h[0]=0x6a09e667UL;   c->h[1]=0xbb67ae85UL;
-        c->h[2]=0x3c6ef372UL;   c->h[3]=0xa54ff53aUL;
-        c->h[4]=0x510e527fUL;   c->h[5]=0x9b05688cUL;
-        c->h[6]=0x1f83d9abUL;   c->h[7]=0x5be0cd19UL;
-        c->md_len=SHA256_DIGEST_LENGTH;
+int
+SHA256_Init(SHA256_CTX *c)
+{
+        memset (c, 0, sizeof(*c));
+        c->h[0] = 0x6a09e667UL;
+        c->h[1] = 0xbb67ae85UL;
+        c->h[2] = 0x3c6ef372UL;
+        c->h[3] = 0xa54ff53aUL;
+        c->h[4] = 0x510e527fUL;
+        c->h[5] = 0x9b05688cUL;
+        c->h[6] = 0x1f83d9abUL;
+        c->h[7] = 0x5be0cd19UL;
+        c->md_len = SHA256_DIGEST_LENGTH;
         return 1;
-        }
+}
 
-unsigned char *SHA224(const unsigned char *d, size_t n, unsigned char *md)
-        {
+unsigned char *
+SHA224(const unsigned char *d, size_t n, unsigned char *md)
+{
         SHA256_CTX c;
         static unsigned char m[SHA224_DIGEST_LENGTH];
 
-        if (md == NULL) md=m;
+        if (md == NULL)
+                md = m;
         SHA224_Init(&c);
-        SHA256_Update(&c,d,n);
-        SHA256_Final(md,&c);
-        explicit_bzero(&c,sizeof(c));
-        return(md);
-        }
+        SHA256_Update(&c, d, n);
+        SHA256_Final(md, &c);
+        explicit_bzero(&c, sizeof(c));
+        return (md);
+}
 
-unsigned char *SHA256(const unsigned char *d, size_t n, unsigned char *md)
-        {
+unsigned char *
+SHA256(const unsigned char *d, size_t n, unsigned char *md)
+{
         SHA256_CTX c;
         static unsigned char m[SHA256_DIGEST_LENGTH];
 
-        if (md == NULL) md=m;
+        if (md == NULL)
+                md = m;
         SHA256_Init(&c);
-        SHA256_Update(&c,d,n);
-        SHA256_Final(md,&c);
-        explicit_bzero(&c,sizeof(c));
-        return(md);
-        }
+        SHA256_Update(&c, d, n);
+        SHA256_Final(md, &c);
+        explicit_bzero(&c, sizeof(c));
+        return (md);
+}
 
-int SHA224_Update(SHA256_CTX *c, const void *data, size_t len)
-{   return SHA256_Update (c,data,len);   }
-int SHA224_Final (unsigned char *md, SHA256_CTX *c)
-{   return SHA256_Final (md,c);   }
+int
+SHA224_Update(SHA256_CTX *c, const void *data, size_t len)
+{
+        return SHA256_Update(c, data, len);
+}
+
+int
+SHA224_Final(unsigned char *md, SHA256_CTX *c)
+{
+        return SHA256_Final(md, c);
+}
 
 #define DATA_ORDER_IS_BIG_ENDIAN
 
@@ -109,30 +130,31 @@ int SHA224_Final (unsigned char *md, SHA256_CTX *c)
 #define HASH_FINAL              SHA256_Final
 #define HASH_BLOCK_DATA_ORDER   sha256_block_data_order
 #ifndef SHA256_ASM
-static
+                                static
 #endif
-void sha256_block_data_order (SHA256_CTX *ctx, const void *in, size_t num);
+                                void sha256_block_data_order (SHA256_CTX *ctx, const void *in, size_t num);
 
 #include "md32_common.h"
 
 #ifndef SHA256_ASM
 static const SHA_LONG K256[64] = {
-        0x428a2f98UL,0x71374491UL,0xb5c0fbcfUL,0xe9b5dba5UL,
-        0x3956c25bUL,0x59f111f1UL,0x923f82a4UL,0xab1c5ed5UL,
-        0xd807aa98UL,0x12835b01UL,0x243185beUL,0x550c7dc3UL,
-        0x72be5d74UL,0x80deb1feUL,0x9bdc06a7UL,0xc19bf174UL,
-        0xe49b69c1UL,0xefbe4786UL,0x0fc19dc6UL,0x240ca1ccUL,
-        0x2de92c6fUL,0x4a7484aaUL,0x5cb0a9dcUL,0x76f988daUL,
-        0x983e5152UL,0xa831c66dUL,0xb00327c8UL,0xbf597fc7UL,
-        0xc6e00bf3UL,0xd5a79147UL,0x06ca6351UL,0x14292967UL,
-        0x27b70a85UL,0x2e1b2138UL,0x4d2c6dfcUL,0x53380d13UL,
-        0x650a7354UL,0x766a0abbUL,0x81c2c92eUL,0x92722c85UL,
-        0xa2bfe8a1UL,0xa81a664bUL,0xc24b8b70UL,0xc76c51a3UL,
-        0xd192e819UL,0xd6990624UL,0xf40e3585UL,0x106aa070UL,
-        0x19a4c116UL,0x1e376c08UL,0x2748774cUL,0x34b0bcb5UL,
-        0x391c0cb3UL,0x4ed8aa4aUL,0x5b9cca4fUL,0x682e6ff3UL,
-        0x748f82eeUL,0x78a5636fUL,0x84c87814UL,0x8cc70208UL,
-        0x90befffaUL,0xa4506cebUL,0xbef9a3f7UL,0xc67178f2UL };
+        0x428a2f98UL, 0x71374491UL, 0xb5c0fbcfUL, 0xe9b5dba5UL,
+        0x3956c25bUL, 0x59f111f1UL, 0x923f82a4UL, 0xab1c5ed5UL,
+        0xd807aa98UL, 0x12835b01UL, 0x243185beUL, 0x550c7dc3UL,
+        0x72be5d74UL, 0x80deb1feUL, 0x9bdc06a7UL, 0xc19bf174UL,
+        0xe49b69c1UL, 0xefbe4786UL, 0x0fc19dc6UL, 0x240ca1ccUL,
+        0x2de92c6fUL, 0x4a7484aaUL, 0x5cb0a9dcUL, 0x76f988daUL,
+        0x983e5152UL, 0xa831c66dUL, 0xb00327c8UL, 0xbf597fc7UL,
+        0xc6e00bf3UL, 0xd5a79147UL, 0x06ca6351UL, 0x14292967UL,
+        0x27b70a85UL, 0x2e1b2138UL, 0x4d2c6dfcUL, 0x53380d13UL,
+        0x650a7354UL, 0x766a0abbUL, 0x81c2c92eUL, 0x92722c85UL,
+        0xa2bfe8a1UL, 0xa81a664bUL, 0xc24b8b70UL, 0xc76c51a3UL,
+        0xd192e819UL, 0xd6990624UL, 0xf40e3585UL, 0x106aa070UL,
+        0x19a4c116UL, 0x1e376c08UL, 0x2748774cUL, 0x34b0bcb5UL,
+        0x391c0cb3UL, 0x4ed8aa4aUL, 0x5b9cca4fUL, 0x682e6ff3UL,
+        0x748f82eeUL, 0x78a5636fUL, 0x84c87814UL, 0x8cc70208UL,
+        0x90befffaUL, 0xa4506cebUL, 0xbef9a3f7UL, 0xc67178f2UL,
+};
 
 /*
  * FIPS specification refers to right rotations, while our ROTATE macro
@@ -149,43 +171,69 @@ static const SHA_LONG K256[64] = {
 
 #ifdef OPENSSL_SMALL_FOOTPRINT
 
-static void sha256_block_data_order (SHA256_CTX *ctx, const void *in, size_t num)
-        {
-        unsigned MD32_REG_T a,b,c,d,e,f,g,h,s0,s1,T1,T2;
-        SHA_LONG        X[16],l;
+static void
+sha256_block_data_order(SHA256_CTX *ctx, const void *in, size_t num)
+{
+        unsigned MD32_REG_T a, b,c, d,e, f,g, h,s0, s1, T1, T2;
+        SHA_LONG        X[16], l;
         int i;
-        const unsigned char *data=in;
-
-                        while (num--) {
-
-        a = ctx->h[0];  b = ctx->h[1];  c = ctx->h[2];  d = ctx->h[3];
-        e = ctx->h[4];  f = ctx->h[5];  g = ctx->h[6];  h = ctx->h[7];
-
-        for (i=0;i<16;i++)
-                {
-                HOST_c2l(data,l); T1 = X[i] = l;
-                T1 += h + Sigma1(e) + Ch(e,f,g) + K256[i];
-                T2 = Sigma0(a) + Maj(a,b,c);
-                h = g;  g = f;  f = e;  e = d + T1;
-                d = c;  c = b;  b = a;  a = T1 + T2;
+        const unsigned char *data = in;
+
+        while (num--) {
+
+                a = ctx->h[0];
+                b = ctx->h[1];
+                c = ctx->h[2];
+                d = ctx->h[3];
+                e = ctx->h[4];
+                f = ctx->h[5];
+                g = ctx->h[6];
+                h = ctx->h[7];
+
+                for (i = 0; i < 16; i++) {
+                        HOST_c2l(data, l);
+                        T1 = X[i] = l;
+                        T1 += h + Sigma1(e) + Ch(e, f, g) + K256[i];
+                        T2 = Sigma0(a) + Maj(a, b, c);
+                        h = g;
+                        g = f;
+                        f = e;
+                        e = d + T1;
+                        d = c;
+                        c = b;
+                        b = a;
+                        a = T1 + T2;
                 }
 
-        for (;i<64;i++)
-                {
-                s0 = X[(i+1)&0x0f];     s0 = sigma0(s0);
-                s1 = X[(i+14)&0x0f];    s1 = sigma1(s1);
-
-                T1 = X[i&0xf] += s0 + s1 + X[(i+9)&0xf];
-                T1 += h + Sigma1(e) + Ch(e,f,g) + K256[i];
-                T2 = Sigma0(a) + Maj(a,b,c);
-                h = g;  g = f;  f = e;  e = d + T1;
-                d = c;  c = b;  b = a;  a = T1 + T2;
+                for (; i < 64; i++) {
+                        s0 = X[(i + 1)&0x0f];
+                        s0 = sigma0(s0);
+                        s1 = X[(i + 14)&0x0f];
+                        s1 = sigma1(s1);
+
+                        T1 = X[i&0xf] += s0 + s1 + X[(i + 9)&0xf];
+                        T1 += h + Sigma1(e) + Ch(e, f, g) + K256[i];
+                        T2 = Sigma0(a) + Maj(a, b, c);
+                        h = g;
+                        g = f;
+                        f = e;
+                        e = d + T1;
+                        d = c;
+                        c = b;
+                        b = a;
+                        a = T1 + T2;
                 }
 
-        ctx->h[0] += a; ctx->h[1] += b; ctx->h[2] += c; ctx->h[3] += d;
-        ctx->h[4] += e; ctx->h[5] += f; ctx->h[6] += g; ctx->h[7] += h;
+                ctx->h[0] += a;
+                ctx->h[1] += b;
+                ctx->h[2] += c;
+                ctx->h[3] += d;
+                ctx->h[4] += e;
+                ctx->h[5] += f;
+                ctx->h[6] += g;
+                ctx->h[7] += h;
 
-                        }
+        }
 }
 
 #else
@@ -201,81 +249,137 @@ static void sha256_block_data_order (SHA256_CTX *ctx, const void *in, size_t num
         T1 = X[(i)&0x0f] += s0 + s1 + X[(i+9)&0x0f];    \
         ROUND_00_15(i,a,b,c,d,e,f,g,h);         } while (0)
 
-static void sha256_block_data_order (SHA256_CTX *ctx, const void *in, size_t num)
-        {
-        unsigned MD32_REG_T a,b,c,d,e,f,g,h,s0,s1,T1;
+static void
+sha256_block_data_order(SHA256_CTX *ctx, const void *in, size_t num)
+{
+        unsigned MD32_REG_T a, b,c, d,e, f,g, h,s0, s1, T1;
         SHA_LONG        X[16];
         int i;
-        const unsigned char *data=in;
-
-                        while (num--) {
-
-        a = ctx->h[0];  b = ctx->h[1];  c = ctx->h[2];  d = ctx->h[3];
-        e = ctx->h[4];  f = ctx->h[5];  g = ctx->h[6];  h = ctx->h[7];
-
-        if (BYTE_ORDER != LITTLE_ENDIAN &&
-            sizeof(SHA_LONG)==4 && ((size_t)in%4)==0)
-                {
-                const SHA_LONG *W=(const SHA_LONG *)data;
-
-                T1 = X[0] = W[0];       ROUND_00_15(0,a,b,c,d,e,f,g,h);
-                T1 = X[1] = W[1];       ROUND_00_15(1,h,a,b,c,d,e,f,g);
-                T1 = X[2] = W[2];       ROUND_00_15(2,g,h,a,b,c,d,e,f);
-                T1 = X[3] = W[3];       ROUND_00_15(3,f,g,h,a,b,c,d,e);
-                T1 = X[4] = W[4];       ROUND_00_15(4,e,f,g,h,a,b,c,d);
-                T1 = X[5] = W[5];       ROUND_00_15(5,d,e,f,g,h,a,b,c);
-                T1 = X[6] = W[6];       ROUND_00_15(6,c,d,e,f,g,h,a,b);
-                T1 = X[7] = W[7];       ROUND_00_15(7,b,c,d,e,f,g,h,a);
-                T1 = X[8] = W[8];       ROUND_00_15(8,a,b,c,d,e,f,g,h);
-                T1 = X[9] = W[9];       ROUND_00_15(9,h,a,b,c,d,e,f,g);
-                T1 = X[10] = W[10];     ROUND_00_15(10,g,h,a,b,c,d,e,f);
-                T1 = X[11] = W[11];     ROUND_00_15(11,f,g,h,a,b,c,d,e);
-                T1 = X[12] = W[12];     ROUND_00_15(12,e,f,g,h,a,b,c,d);
-                T1 = X[13] = W[13];     ROUND_00_15(13,d,e,f,g,h,a,b,c);
-                T1 = X[14] = W[14];     ROUND_00_15(14,c,d,e,f,g,h,a,b);
-                T1 = X[15] = W[15];     ROUND_00_15(15,b,c,d,e,f,g,h,a);
-
-                data += SHA256_CBLOCK;
-                }
-        else
-                {
-                SHA_LONG l;
-
-                HOST_c2l(data,l); T1 = X[0] = l;  ROUND_00_15(0,a,b,c,d,e,f,g,h);
-                HOST_c2l(data,l); T1 = X[1] = l;  ROUND_00_15(1,h,a,b,c,d,e,f,g);
-                HOST_c2l(data,l); T1 = X[2] = l;  ROUND_00_15(2,g,h,a,b,c,d,e,f);
-                HOST_c2l(data,l); T1 = X[3] = l;  ROUND_00_15(3,f,g,h,a,b,c,d,e);
-                HOST_c2l(data,l); T1 = X[4] = l;  ROUND_00_15(4,e,f,g,h,a,b,c,d);
-                HOST_c2l(data,l); T1 = X[5] = l;  ROUND_00_15(5,d,e,f,g,h,a,b,c);
-                HOST_c2l(data,l); T1 = X[6] = l;  ROUND_00_15(6,c,d,e,f,g,h,a,b);
-                HOST_c2l(data,l); T1 = X[7] = l;  ROUND_00_15(7,b,c,d,e,f,g,h,a);
-                HOST_c2l(data,l); T1 = X[8] = l;  ROUND_00_15(8,a,b,c,d,e,f,g,h);
-                HOST_c2l(data,l); T1 = X[9] = l;  ROUND_00_15(9,h,a,b,c,d,e,f,g);
-                HOST_c2l(data,l); T1 = X[10] = l; ROUND_00_15(10,g,h,a,b,c,d,e,f);
-                HOST_c2l(data,l); T1 = X[11] = l; ROUND_00_15(11,f,g,h,a,b,c,d,e);
-                HOST_c2l(data,l); T1 = X[12] = l; ROUND_00_15(12,e,f,g,h,a,b,c,d);
-                HOST_c2l(data,l); T1 = X[13] = l; ROUND_00_15(13,d,e,f,g,h,a,b,c);
-                HOST_c2l(data,l); T1 = X[14] = l; ROUND_00_15(14,c,d,e,f,g,h,a,b);
-                HOST_c2l(data,l); T1 = X[15] = l; ROUND_00_15(15,b,c,d,e,f,g,h,a);
+        const unsigned char *data = in;
+
+        while (num--) {
+
+                a = ctx->h[0];
+                b = ctx->h[1];
+                c = ctx->h[2];
+                d = ctx->h[3];
+                e = ctx->h[4];
+                f = ctx->h[5];
+                g = ctx->h[6];
+                h = ctx->h[7];
+
+                if (BYTE_ORDER != LITTLE_ENDIAN &&
+                    sizeof(SHA_LONG) == 4 && ((size_t)in % 4) == 0) {
+                        const SHA_LONG *W = (const SHA_LONG *)data;
+
+                        T1 = X[0] = W[0];
+                        ROUND_00_15(0, a,b, c,d, e,f, g, h);
+                        T1 = X[1] = W[1];
+                        ROUND_00_15(1, h,a, b,c, d,e, f, g);
+                        T1 = X[2] = W[2];
+                        ROUND_00_15(2, g,h, a,b, c,d, e, f);
+                        T1 = X[3] = W[3];
+                        ROUND_00_15(3, f,g, h,a, b,c, d, e);
+                        T1 = X[4] = W[4];
+                        ROUND_00_15(4, e,f, g,h, a,b, c, d);
+                        T1 = X[5] = W[5];
+                        ROUND_00_15(5, d,e, f,g, h,a, b, c);
+                        T1 = X[6] = W[6];
+                        ROUND_00_15(6, c,d, e,f, g,h, a, b);
+                        T1 = X[7] = W[7];
+                        ROUND_00_15(7, b,c, d,e, f,g, h, a);
+                        T1 = X[8] = W[8];
+                        ROUND_00_15(8, a,b, c,d, e,f, g, h);
+                        T1 = X[9] = W[9];
+                        ROUND_00_15(9, h,a, b,c, d,e, f, g);
+                        T1 = X[10] = W[10];
+                        ROUND_00_15(10, g,h, a,b, c,d, e, f);
+                        T1 = X[11] = W[11];
+                        ROUND_00_15(11, f,g, h,a, b,c, d, e);
+                        T1 = X[12] = W[12];
+                        ROUND_00_15(12, e,f, g,h, a,b, c, d);
+                        T1 = X[13] = W[13];
+                        ROUND_00_15(13, d,e, f,g, h,a, b, c);
+                        T1 = X[14] = W[14];
+                        ROUND_00_15(14, c,d, e,f, g,h, a, b);
+                        T1 = X[15] = W[15];
+                        ROUND_00_15(15, b,c, d,e, f,g, h, a);
+
+                        data += SHA256_CBLOCK;
+                } else {
+                        SHA_LONG l;
+
+                        HOST_c2l(data, l);
+                        T1 = X[0] = l;
+                        ROUND_00_15(0, a,b, c,d, e,f, g, h);
+                        HOST_c2l(data, l);
+                        T1 = X[1] = l;
+                        ROUND_00_15(1, h,a, b,c, d,e, f, g);
+                        HOST_c2l(data, l);
+                        T1 = X[2] = l;
+                        ROUND_00_15(2, g,h, a,b, c,d, e, f);
+                        HOST_c2l(data, l);
+                        T1 = X[3] = l;
+                        ROUND_00_15(3, f,g, h,a, b,c, d, e);
+                        HOST_c2l(data, l);
+                        T1 = X[4] = l;
+                        ROUND_00_15(4, e,f, g,h, a,b, c, d);
+                        HOST_c2l(data, l);
+                        T1 = X[5] = l;
+                        ROUND_00_15(5, d,e, f,g, h,a, b, c);
+                        HOST_c2l(data, l);
+                        T1 = X[6] = l;
+                        ROUND_00_15(6, c,d, e,f, g,h, a, b);
+                        HOST_c2l(data, l);
+                        T1 = X[7] = l;
+                        ROUND_00_15(7, b,c, d,e, f,g, h, a);
+                        HOST_c2l(data, l);
+                        T1 = X[8] = l;
+                        ROUND_00_15(8, a,b, c,d, e,f, g, h);
+                        HOST_c2l(data, l);
+                        T1 = X[9] = l;
+                        ROUND_00_15(9, h,a, b,c, d,e, f, g);
+                        HOST_c2l(data, l);
+                        T1 = X[10] = l;
+                        ROUND_00_15(10, g,h, a,b, c,d, e, f);
+                        HOST_c2l(data, l);
+                        T1 = X[11] = l;
+                        ROUND_00_15(11, f,g, h,a, b,c, d, e);
+                        HOST_c2l(data, l);
+                        T1 = X[12] = l;
+                        ROUND_00_15(12, e,f, g,h, a,b, c, d);
+                        HOST_c2l(data, l);
+                        T1 = X[13] = l;
+                        ROUND_00_15(13, d,e, f,g, h,a, b, c);
+                        HOST_c2l(data, l);
+                        T1 = X[14] = l;
+                        ROUND_00_15(14, c,d, e,f, g,h, a, b);
+                        HOST_c2l(data, l);
+                        T1 = X[15] = l;
+                        ROUND_00_15(15, b,c, d,e, f,g, h, a);
                 }
 
-        for (i=16;i<64;i+=8)
-                {
-                ROUND_16_63(i+0,a,b,c,d,e,f,g,h,X);
-                ROUND_16_63(i+1,h,a,b,c,d,e,f,g,X);
-                ROUND_16_63(i+2,g,h,a,b,c,d,e,f,X);
-                ROUND_16_63(i+3,f,g,h,a,b,c,d,e,X);
-                ROUND_16_63(i+4,e,f,g,h,a,b,c,d,X);
-                ROUND_16_63(i+5,d,e,f,g,h,a,b,c,X);
-                ROUND_16_63(i+6,c,d,e,f,g,h,a,b,X);
-                ROUND_16_63(i+7,b,c,d,e,f,g,h,a,X);
+                for (i = 16; i < 64; i += 8) {
+                        ROUND_16_63(i + 0, a,b, c,d, e,f, g,h, X);
+                        ROUND_16_63(i + 1, h,a, b,c, d,e, f,g, X);
+                        ROUND_16_63(i + 2, g,h, a,b, c,d, e,f, X);
+                        ROUND_16_63(i + 3, f,g, h,a, b,c, d,e, X);
+                        ROUND_16_63(i + 4, e,f, g,h, a,b, c,d, X);
+                        ROUND_16_63(i + 5, d,e, f,g, h,a, b,c, X);
+                        ROUND_16_63(i + 6, c,d, e,f, g,h, a,b, X);
+                        ROUND_16_63(i + 7, b,c, d,e, f,g, h,a, X);
                 }
 
-        ctx->h[0] += a; ctx->h[1] += b; ctx->h[2] += c; ctx->h[3] += d;
-        ctx->h[4] += e; ctx->h[5] += f; ctx->h[6] += g; ctx->h[7] += h;
-
-                        }
+                ctx->h[0] += a;
+                ctx->h[1] += b;
+                ctx->h[2] += c;
+                ctx->h[3] += d;
+                ctx->h[4] += e;
+                ctx->h[5] += f;
+                ctx->h[6] += g;
+                ctx->h[7] += h;
         }
+}
 
 #endif
 #endif /* SHA256_ASM */
diff --git a/src/lib/libcrypto/sha/sha512.c b/src/lib/libcrypto/sha/sha512.c
index 56a207f7d0..7c76c42b5b 100644
--- a/src/lib/libcrypto/sha/sha512.c
+++ b/src/lib/libcrypto/sha/sha512.c
@@ -1,4 +1,4 @@
-/* $OpenBSD: sha512.c,v 1.16 2021/11/09 18:40:21 bcook Exp $ */
+/* $OpenBSD: sha512.c,v 1.17 2023/03/26 16:40:07 jsing Exp $ */
 /* ====================================================================
  * Copyright (c) 2004 The OpenSSL Project.  All rights reserved
  * according to the OpenSSL license [found in ../../LICENSE].
@@ -56,256 +56,276 @@
 #define SHA512_BLOCK_CAN_MANAGE_UNALIGNED_DATA
 #endif
 
-int SHA384_Init(SHA512_CTX *c)
-        {
-        c->h[0]=U64(0xcbbb9d5dc1059ed8);
-        c->h[1]=U64(0x629a292a367cd507);
-        c->h[2]=U64(0x9159015a3070dd17);
-        c->h[3]=U64(0x152fecd8f70e5939);
-        c->h[4]=U64(0x67332667ffc00b31);
-        c->h[5]=U64(0x8eb44a8768581511);
-        c->h[6]=U64(0xdb0c2e0d64f98fa7);
-        c->h[7]=U64(0x47b5481dbefa4fa4);
-
-        c->Nl=0;        c->Nh=0;
-        c->num=0;       c->md_len=SHA384_DIGEST_LENGTH;
-        return 1;
-        }
-
-int SHA512_Init(SHA512_CTX *c)
-        {
-        c->h[0]=U64(0x6a09e667f3bcc908);
-        c->h[1]=U64(0xbb67ae8584caa73b);
-        c->h[2]=U64(0x3c6ef372fe94f82b);
-        c->h[3]=U64(0xa54ff53a5f1d36f1);
-        c->h[4]=U64(0x510e527fade682d1);
-        c->h[5]=U64(0x9b05688c2b3e6c1f);
-        c->h[6]=U64(0x1f83d9abfb41bd6b);
-        c->h[7]=U64(0x5be0cd19137e2179);
-
-        c->Nl=0;        c->Nh=0;
-        c->num=0;       c->md_len=SHA512_DIGEST_LENGTH;
-        return 1;
-        }
+int
+SHA384_Init(SHA512_CTX *c)
+{
+        c->h[0] = U64(0xcbbb9d5dc1059ed8);
+        c->h[1] = U64(0x629a292a367cd507);
+        c->h[2] = U64(0x9159015a3070dd17);
+        c->h[3] = U64(0x152fecd8f70e5939);
+        c->h[4] = U64(0x67332667ffc00b31);
+        c->h[5] = U64(0x8eb44a8768581511);
+        c->h[6] = U64(0xdb0c2e0d64f98fa7);
+        c->h[7] = U64(0x47b5481dbefa4fa4);
+
+        c->Nl = 0;
+        c->Nh = 0;
+        c->num = 0;
+        c->md_len = SHA384_DIGEST_LENGTH;
+        return 1;
+}
+
+int
+SHA512_Init(SHA512_CTX *c)
+{
+        c->h[0] = U64(0x6a09e667f3bcc908);
+        c->h[1] = U64(0xbb67ae8584caa73b);
+        c->h[2] = U64(0x3c6ef372fe94f82b);
+        c->h[3] = U64(0xa54ff53a5f1d36f1);
+        c->h[4] = U64(0x510e527fade682d1);
+        c->h[5] = U64(0x9b05688c2b3e6c1f);
+        c->h[6] = U64(0x1f83d9abfb41bd6b);
+        c->h[7] = U64(0x5be0cd19137e2179);
+
+        c->Nl = 0;
+        c->Nh = 0;
+        c->num = 0;
+        c->md_len = SHA512_DIGEST_LENGTH;
+        return 1;
+}
 
 #ifndef SHA512_ASM
 static
 #endif
 void sha512_block_data_order (SHA512_CTX *ctx, const void *in, size_t num);
 
-int SHA512_Final (unsigned char *md, SHA512_CTX *c)
-        {
-        unsigned char *p=(unsigned char *)c->u.p;
-        size_t n=c->num;
+int
+SHA512_Final(unsigned char *md, SHA512_CTX *c)
+{
+        unsigned char *p = (unsigned char *)c->u.p;
+        size_t n = c->num;
 
         p[n]=0x80;      /* There always is a room for one */
         n++;
-        if (n > (sizeof(c->u)-16))
-                memset (p+n,0,sizeof(c->u)-n), n=0,
-                sha512_block_data_order (c,p,1);
+        if (n > (sizeof(c->u) - 16))
+                memset (p + n, 0, sizeof(c->u) - n), n = 0,
+                    sha512_block_data_order (c, p, 1);
 
-        memset (p+n,0,sizeof(c->u)-16-n);
+        memset (p + n, 0, sizeof(c->u) - 16 - n);
 #if BYTE_ORDER == BIG_ENDIAN
-        c->u.d[SHA_LBLOCK-2] = c->Nh;
-        c->u.d[SHA_LBLOCK-1] = c->Nl;
+        c->u.d[SHA_LBLOCK - 2] = c->Nh;
+        c->u.d[SHA_LBLOCK - 1] = c->Nl;
 #else
-        p[sizeof(c->u)-1]  = (unsigned char)(c->Nl);
-        p[sizeof(c->u)-2]  = (unsigned char)(c->Nl>>8);
-        p[sizeof(c->u)-3]  = (unsigned char)(c->Nl>>16);
-        p[sizeof(c->u)-4]  = (unsigned char)(c->Nl>>24);
-        p[sizeof(c->u)-5]  = (unsigned char)(c->Nl>>32);
-        p[sizeof(c->u)-6]  = (unsigned char)(c->Nl>>40);
-        p[sizeof(c->u)-7]  = (unsigned char)(c->Nl>>48);
-        p[sizeof(c->u)-8]  = (unsigned char)(c->Nl>>56);
-        p[sizeof(c->u)-9]  = (unsigned char)(c->Nh);
-        p[sizeof(c->u)-10] = (unsigned char)(c->Nh>>8);
-        p[sizeof(c->u)-11] = (unsigned char)(c->Nh>>16);
-        p[sizeof(c->u)-12] = (unsigned char)(c->Nh>>24);
-        p[sizeof(c->u)-13] = (unsigned char)(c->Nh>>32);
-        p[sizeof(c->u)-14] = (unsigned char)(c->Nh>>40);
-        p[sizeof(c->u)-15] = (unsigned char)(c->Nh>>48);
-        p[sizeof(c->u)-16] = (unsigned char)(c->Nh>>56);
+        p[sizeof(c->u) - 1] = (unsigned char)(c->Nl);
+        p[sizeof(c->u) - 2] = (unsigned char)(c->Nl >> 8);
+        p[sizeof(c->u) - 3] = (unsigned char)(c->Nl >> 16);
+        p[sizeof(c->u) - 4] = (unsigned char)(c->Nl >> 24);
+        p[sizeof(c->u) - 5] = (unsigned char)(c->Nl >> 32);
+        p[sizeof(c->u) - 6] = (unsigned char)(c->Nl >> 40);
+        p[sizeof(c->u) - 7] = (unsigned char)(c->Nl >> 48);
+        p[sizeof(c->u) - 8] = (unsigned char)(c->Nl >> 56);
+        p[sizeof(c->u) - 9] = (unsigned char)(c->Nh);
+        p[sizeof(c->u) - 10] = (unsigned char)(c->Nh >> 8);
+        p[sizeof(c->u) - 11] = (unsigned char)(c->Nh >> 16);
+        p[sizeof(c->u) - 12] = (unsigned char)(c->Nh >> 24);
+        p[sizeof(c->u) - 13] = (unsigned char)(c->Nh >> 32);
+        p[sizeof(c->u) - 14] = (unsigned char)(c->Nh >> 40);
+        p[sizeof(c->u) - 15] = (unsigned char)(c->Nh >> 48);
+        p[sizeof(c->u) - 16] = (unsigned char)(c->Nh >> 56);
 #endif
 
-        sha512_block_data_order (c,p,1);
+        sha512_block_data_order (c, p, 1);
 
-        if (md==0) return 0;
+        if (md == 0)
+                return 0;
 
-        switch (c->md_len)
-                {
+        switch (c->md_len) {
                 /* Let compiler decide if it's appropriate to unroll... */
-                case SHA384_DIGEST_LENGTH:
-                        for (n=0;n<SHA384_DIGEST_LENGTH/8;n++)
-                                {
-                                SHA_LONG64 t = c->h[n];
-
-                                *(md++) = (unsigned char)(t>>56);
-                                *(md++) = (unsigned char)(t>>48);
-                                *(md++) = (unsigned char)(t>>40);
-                                *(md++) = (unsigned char)(t>>32);
-                                *(md++) = (unsigned char)(t>>24);
-                                *(md++) = (unsigned char)(t>>16);
-                                *(md++) = (unsigned char)(t>>8);
-                                *(md++) = (unsigned char)(t);
-                                }
-                        break;
-                case SHA512_DIGEST_LENGTH:
-                        for (n=0;n<SHA512_DIGEST_LENGTH/8;n++)
-                                {
-                                SHA_LONG64 t = c->h[n];
-
-                                *(md++) = (unsigned char)(t>>56);
-                                *(md++) = (unsigned char)(t>>48);
-                                *(md++) = (unsigned char)(t>>40);
-                                *(md++) = (unsigned char)(t>>32);
-                                *(md++) = (unsigned char)(t>>24);
-                                *(md++) = (unsigned char)(t>>16);
-                                *(md++) = (unsigned char)(t>>8);
-                                *(md++) = (unsigned char)(t);
-                                }
-                        break;
-                /* ... as well as make sure md_len is not abused. */
-                default:        return 0;
+        case SHA384_DIGEST_LENGTH:
+                for (n = 0; n < SHA384_DIGEST_LENGTH/8; n++) {
+                        SHA_LONG64 t = c->h[n];
+
+                        *(md++) = (unsigned char)(t >> 56);
+                        *(md++) = (unsigned char)(t >> 48);
+                        *(md++) = (unsigned char)(t >> 40);
+                        *(md++) = (unsigned char)(t >> 32);
+                        *(md++) = (unsigned char)(t >> 24);
+                        *(md++) = (unsigned char)(t >> 16);
+                        *(md++) = (unsigned char)(t >> 8);
+                        *(md++) = (unsigned char)(t);
+                }
+                break;
+        case SHA512_DIGEST_LENGTH:
+                for (n = 0; n < SHA512_DIGEST_LENGTH/8; n++) {
+                        SHA_LONG64 t = c->h[n];
+
+                        *(md++) = (unsigned char)(t >> 56);
+                        *(md++) = (unsigned char)(t >> 48);
+                        *(md++) = (unsigned char)(t >> 40);
+                        *(md++) = (unsigned char)(t >> 32);
+                        *(md++) = (unsigned char)(t >> 24);
+                        *(md++) = (unsigned char)(t >> 16);
+                        *(md++) = (unsigned char)(t >> 8);
+                        *(md++) = (unsigned char)(t);
                 }
+                break;
+                /* ... as well as make sure md_len is not abused. */
+        default:
+                return 0;
+        }
 
         return 1;
-        }
+}
 
-int SHA384_Final (unsigned char *md,SHA512_CTX *c)
-{   return SHA512_Final (md,c);   }
+int
+SHA384_Final(unsigned char *md, SHA512_CTX *c)
+{
+        return SHA512_Final(md, c);
+}
 
-int SHA512_Update (SHA512_CTX *c, const void *_data, size_t len)
-        {
+int
+SHA512_Update(SHA512_CTX *c, const void *_data, size_t len)
+{
         SHA_LONG64      l;
-        unsigned char  *p=c->u.p;
-        const unsigned char *data=(const unsigned char *)_data;
+        unsigned char  *p = c->u.p;
+        const unsigned char *data = (const unsigned char *)_data;
 
-        if (len==0) return  1;
+        if (len == 0)
+                return 1;
 
-        l = (c->Nl+(((SHA_LONG64)len)<<3))&U64(0xffffffffffffffff);
-        if (l < c->Nl)          c->Nh++;
-        if (sizeof(len)>=8)     c->Nh+=(((SHA_LONG64)len)>>61);
-        c->Nl=l;
+        l = (c->Nl + (((SHA_LONG64)len) << 3))&U64(0xffffffffffffffff);
+        if (l < c->Nl)
+                c->Nh++;
+        if (sizeof(len) >= 8)
+                c->Nh += (((SHA_LONG64)len) >> 61);
+        c->Nl = l;
 
-        if (c->num != 0)
-                {
+        if (c->num != 0) {
                 size_t n = sizeof(c->u) - c->num;
 
-                if (len < n)
-                        {
-                        memcpy (p+c->num,data,len), c->num += (unsigned int)len;
+                if (len < n) {
+                        memcpy (p + c->num, data, len), c->num += (unsigned int)len;
                         return 1;
-                        }
+                }
                 else    {
-                        memcpy (p+c->num,data,n), c->num = 0;
-                        len-=n, data+=n;
-                        sha512_block_data_order (c,p,1);
-                        }
+                        memcpy (p + c->num, data, n), c->num = 0;
+                        len -= n, data += n;
+                        sha512_block_data_order (c, p, 1);
                 }
+        }
 
-        if (len >= sizeof(c->u))
-                {
+        if (len >= sizeof(c->u)) {
 #ifndef SHA512_BLOCK_CAN_MANAGE_UNALIGNED_DATA
-                if ((size_t)data%sizeof(c->u.d[0]) != 0)
+                if ((size_t)data % sizeof(c->u.d[0]) != 0)
                         while (len >= sizeof(c->u))
-                                memcpy (p,data,sizeof(c->u)),
-                                sha512_block_data_order (c,p,1),
-                                len  -= sizeof(c->u),
-                                data += sizeof(c->u);
+                                memcpy (p, data, sizeof(c->u)),
+                                    sha512_block_data_order (c, p, 1),
+                                    len -= sizeof(c->u),
+                                    data += sizeof(c->u);
                 else
 #endif
-                        sha512_block_data_order (c,data,len/sizeof(c->u)),
-                        data += len,
-                        len  %= sizeof(c->u),
-                        data -= len;
-                }
+                        sha512_block_data_order (c, data, len/sizeof(c->u)),
+                            data += len,
+                            len  %= sizeof(c->u),
+                            data -= len;
+        }
 
-        if (len != 0)   memcpy (p,data,len), c->num = (int)len;
+        if (len != 0)
+                memcpy (p, data, len), c->num = (int)len;
 
         return 1;
-        }
+}
 
-int SHA384_Update (SHA512_CTX *c, const void *data, size_t len)
-{   return SHA512_Update (c,data,len);   }
+int
+SHA384_Update(SHA512_CTX *c, const void *data, size_t len)
+{
+        return SHA512_Update (c, data, len);
+}
 
-void SHA512_Transform (SHA512_CTX *c, const unsigned char *data)
-        {
+void
+SHA512_Transform(SHA512_CTX *c, const unsigned char *data)
+{
 #ifndef SHA512_BLOCK_CAN_MANAGE_UNALIGNED_DATA
-        if ((size_t)data%sizeof(c->u.d[0]) != 0)
-                memcpy(c->u.p,data,sizeof(c->u.p)),
-                data = c->u.p;
+        if ((size_t)data % sizeof(c->u.d[0]) != 0)
+                memcpy(c->u.p, data, sizeof(c->u.p)),
+                    data = c->u.p;
 #endif
-        sha512_block_data_order (c,data,1);
-        }
+        sha512_block_data_order (c, data, 1);
+}
 
-unsigned char *SHA384(const unsigned char *d, size_t n, unsigned char *md)
-        {
+unsigned char *
+SHA384(const unsigned char *d, size_t n, unsigned char *md)
+{
         SHA512_CTX c;
         static unsigned char m[SHA384_DIGEST_LENGTH];
 
-        if (md == NULL) md=m;
+        if (md == NULL)
+                md = m;
         SHA384_Init(&c);
-        SHA512_Update(&c,d,n);
-        SHA512_Final(md,&c);
-        explicit_bzero(&c,sizeof(c));
-        return(md);
-        }
-
-unsigned char *SHA512(const unsigned char *d, size_t n, unsigned char *md)
-        {
+        SHA512_Update(&c, d, n);
+        SHA512_Final(md, &c);
+        explicit_bzero(&c, sizeof(c));
+        return (md);
+}
+
+unsigned char *
+SHA512(const unsigned char *d, size_t n, unsigned char *md)
+{
         SHA512_CTX c;
         static unsigned char m[SHA512_DIGEST_LENGTH];
 
-        if (md == NULL) md=m;
+        if (md == NULL)
+                md = m;
         SHA512_Init(&c);
-        SHA512_Update(&c,d,n);
-        SHA512_Final(md,&c);
-        explicit_bzero(&c,sizeof(c));
-        return(md);
-        }
+        SHA512_Update(&c, d, n);
+        SHA512_Final(md, &c);
+        explicit_bzero(&c, sizeof(c));
+        return (md);
+}
 
 #ifndef SHA512_ASM
 static const SHA_LONG64 K512[80] = {
-        U64(0x428a2f98d728ae22),U64(0x7137449123ef65cd),
-        U64(0xb5c0fbcfec4d3b2f),U64(0xe9b5dba58189dbbc),
-        U64(0x3956c25bf348b538),U64(0x59f111f1b605d019),
-        U64(0x923f82a4af194f9b),U64(0xab1c5ed5da6d8118),
-        U64(0xd807aa98a3030242),U64(0x12835b0145706fbe),
-        U64(0x243185be4ee4b28c),U64(0x550c7dc3d5ffb4e2),
-        U64(0x72be5d74f27b896f),U64(0x80deb1fe3b1696b1),
-        U64(0x9bdc06a725c71235),U64(0xc19bf174cf692694),
-        U64(0xe49b69c19ef14ad2),U64(0xefbe4786384f25e3),
-        U64(0x0fc19dc68b8cd5b5),U64(0x240ca1cc77ac9c65),
-        U64(0x2de92c6f592b0275),U64(0x4a7484aa6ea6e483),
-        U64(0x5cb0a9dcbd41fbd4),U64(0x76f988da831153b5),
-        U64(0x983e5152ee66dfab),U64(0xa831c66d2db43210),
-        U64(0xb00327c898fb213f),U64(0xbf597fc7beef0ee4),
-        U64(0xc6e00bf33da88fc2),U64(0xd5a79147930aa725),
-        U64(0x06ca6351e003826f),U64(0x142929670a0e6e70),
-        U64(0x27b70a8546d22ffc),U64(0x2e1b21385c26c926),
-        U64(0x4d2c6dfc5ac42aed),U64(0x53380d139d95b3df),
-        U64(0x650a73548baf63de),U64(0x766a0abb3c77b2a8),
-        U64(0x81c2c92e47edaee6),U64(0x92722c851482353b),
-        U64(0xa2bfe8a14cf10364),U64(0xa81a664bbc423001),
-        U64(0xc24b8b70d0f89791),U64(0xc76c51a30654be30),
-        U64(0xd192e819d6ef5218),U64(0xd69906245565a910),
-        U64(0xf40e35855771202a),U64(0x106aa07032bbd1b8),
-        U64(0x19a4c116b8d2d0c8),U64(0x1e376c085141ab53),
-        U64(0x2748774cdf8eeb99),U64(0x34b0bcb5e19b48a8),
-        U64(0x391c0cb3c5c95a63),U64(0x4ed8aa4ae3418acb),
-        U64(0x5b9cca4f7763e373),U64(0x682e6ff3d6b2b8a3),
-        U64(0x748f82ee5defb2fc),U64(0x78a5636f43172f60),
-        U64(0x84c87814a1f0ab72),U64(0x8cc702081a6439ec),
-        U64(0x90befffa23631e28),U64(0xa4506cebde82bde9),
-        U64(0xbef9a3f7b2c67915),U64(0xc67178f2e372532b),
-        U64(0xca273eceea26619c),U64(0xd186b8c721c0c207),
-        U64(0xeada7dd6cde0eb1e),U64(0xf57d4f7fee6ed178),
-        U64(0x06f067aa72176fba),U64(0x0a637dc5a2c898a6),
-        U64(0x113f9804bef90dae),U64(0x1b710b35131c471b),
-        U64(0x28db77f523047d84),U64(0x32caab7b40c72493),
-        U64(0x3c9ebe0a15c9bebc),U64(0x431d67c49c100d4c),
-        U64(0x4cc5d4becb3e42b6),U64(0x597f299cfc657e2a),
-        U64(0x5fcb6fab3ad6faec),U64(0x6c44198c4a475817) };
+        U64(0x428a2f98d728ae22), U64(0x7137449123ef65cd),
+        U64(0xb5c0fbcfec4d3b2f), U64(0xe9b5dba58189dbbc),
+        U64(0x3956c25bf348b538), U64(0x59f111f1b605d019),
+        U64(0x923f82a4af194f9b), U64(0xab1c5ed5da6d8118),
+        U64(0xd807aa98a3030242), U64(0x12835b0145706fbe),
+        U64(0x243185be4ee4b28c), U64(0x550c7dc3d5ffb4e2),
+        U64(0x72be5d74f27b896f), U64(0x80deb1fe3b1696b1),
+        U64(0x9bdc06a725c71235), U64(0xc19bf174cf692694),
+        U64(0xe49b69c19ef14ad2), U64(0xefbe4786384f25e3),
+        U64(0x0fc19dc68b8cd5b5), U64(0x240ca1cc77ac9c65),
+        U64(0x2de92c6f592b0275), U64(0x4a7484aa6ea6e483),
+        U64(0x5cb0a9dcbd41fbd4), U64(0x76f988da831153b5),
+        U64(0x983e5152ee66dfab), U64(0xa831c66d2db43210),
+        U64(0xb00327c898fb213f), U64(0xbf597fc7beef0ee4),
+        U64(0xc6e00bf33da88fc2), U64(0xd5a79147930aa725),
+        U64(0x06ca6351e003826f), U64(0x142929670a0e6e70),
+        U64(0x27b70a8546d22ffc), U64(0x2e1b21385c26c926),
+        U64(0x4d2c6dfc5ac42aed), U64(0x53380d139d95b3df),
+        U64(0x650a73548baf63de), U64(0x766a0abb3c77b2a8),
+        U64(0x81c2c92e47edaee6), U64(0x92722c851482353b),
+        U64(0xa2bfe8a14cf10364), U64(0xa81a664bbc423001),
+        U64(0xc24b8b70d0f89791), U64(0xc76c51a30654be30),
+        U64(0xd192e819d6ef5218), U64(0xd69906245565a910),
+        U64(0xf40e35855771202a), U64(0x106aa07032bbd1b8),
+        U64(0x19a4c116b8d2d0c8), U64(0x1e376c085141ab53),
+        U64(0x2748774cdf8eeb99), U64(0x34b0bcb5e19b48a8),
+        U64(0x391c0cb3c5c95a63), U64(0x4ed8aa4ae3418acb),
+        U64(0x5b9cca4f7763e373), U64(0x682e6ff3d6b2b8a3),
+        U64(0x748f82ee5defb2fc), U64(0x78a5636f43172f60),
+        U64(0x84c87814a1f0ab72), U64(0x8cc702081a6439ec),
+        U64(0x90befffa23631e28), U64(0xa4506cebde82bde9),
+        U64(0xbef9a3f7b2c67915), U64(0xc67178f2e372532b),
+        U64(0xca273eceea26619c), U64(0xd186b8c721c0c207),
+        U64(0xeada7dd6cde0eb1e), U64(0xf57d4f7fee6ed178),
+        U64(0x06f067aa72176fba), U64(0x0a637dc5a2c898a6),
+        U64(0x113f9804bef90dae), U64(0x1b710b35131c471b),
+        U64(0x28db77f523047d84), U64(0x32caab7b40c72493),
+        U64(0x3c9ebe0a15c9bebc), U64(0x431d67c49c100d4c),
+        U64(0x4cc5d4becb3e42b6), U64(0x597f299cfc657e2a),
+        U64(0x5fcb6fab3ad6faec), U64(0x6c44198c4a475817),
+};
 
 #if defined(__GNUC__) && __GNUC__>=2 && !defined(OPENSSL_NO_ASM) && !defined(OPENSSL_NO_INLINE_ASM)
 # if defined(__x86_64) || defined(__x86_64__)
@@ -356,100 +376,132 @@ static const SHA_LONG64 K512[80] = {
  * This code should give better results on 32-bit CPU with less than
  * ~24 registers, both size and performance wise...
  */
-static void sha512_block_data_order (SHA512_CTX *ctx, const void *in, size_t num)
-        {
-        const SHA_LONG64 *W=in;
-        SHA_LONG64      A,E,T;
-        SHA_LONG64      X[9+80],*F;
+static void
+sha512_block_data_order(SHA512_CTX *ctx, const void *in, size_t num)
+{
+        const SHA_LONG64 *W = in;
+        SHA_LONG64      A, E, T;
+        SHA_LONG64      X[9 + 80], *F;
         int i;
 
-                        while (num--) {
-
-        F    = X+80;
-        A    = ctx->h[0];       F[1] = ctx->h[1];
-        F[2] = ctx->h[2];       F[3] = ctx->h[3];
-        E    = ctx->h[4];       F[5] = ctx->h[5];
-        F[6] = ctx->h[6];       F[7] = ctx->h[7];
-
-        for (i=0;i<16;i++,F--)
-                {
-                T = PULL64(W[i]);
-                F[0] = A;
-                F[4] = E;
-                F[8] = T;
-                T   += F[7] + Sigma1(E) + Ch(E,F[5],F[6]) + K512[i];
-                E    = F[3] + T;
-                A    = T + Sigma0(A) + Maj(A,F[1],F[2]);
+        while (num--) {
+
+                F = X + 80;
+                A = ctx->h[0];
+                F[1] = ctx->h[1];
+                F[2] = ctx->h[2];
+                F[3] = ctx->h[3];
+                E = ctx->h[4];
+                F[5] = ctx->h[5];
+                F[6] = ctx->h[6];
+                F[7] = ctx->h[7];
+
+                for (i = 0; i < 16; i++, F--) {
+                        T = PULL64(W[i]);
+                        F[0] = A;
+                        F[4] = E;
+                        F[8] = T;
+                        T += F[7] + Sigma1(E) + Ch(E, F[5], F[6]) + K512[i];
+                        E = F[3] + T;
+                        A = T + Sigma0(A) + Maj(A, F[1], F[2]);
                 }
 
-        for (;i<80;i++,F--)
-                {
-                T    = sigma0(F[8+16-1]);
-                T   += sigma1(F[8+16-14]);
-                T   += F[8+16] + F[8+16-9];
-
-                F[0] = A;
-                F[4] = E;
-                F[8] = T;
-                T   += F[7] + Sigma1(E) + Ch(E,F[5],F[6]) + K512[i];
-                E    = F[3] + T;
-                A    = T + Sigma0(A) + Maj(A,F[1],F[2]);
+                for (; i < 80; i++, F--) {
+                        T = sigma0(F[8 + 16 - 1]);
+                        T += sigma1(F[8 + 16 - 14]);
+                        T += F[8 + 16] + F[8 + 16 - 9];
+
+                        F[0] = A;
+                        F[4] = E;
+                        F[8] = T;
+                        T += F[7] + Sigma1(E) + Ch(E, F[5], F[6]) + K512[i];
+                        E = F[3] + T;
+                        A = T + Sigma0(A) + Maj(A, F[1], F[2]);
                 }
 
-        ctx->h[0] += A;         ctx->h[1] += F[1];
-        ctx->h[2] += F[2];      ctx->h[3] += F[3];
-        ctx->h[4] += E;         ctx->h[5] += F[5];
-        ctx->h[6] += F[6];      ctx->h[7] += F[7];
+                ctx->h[0] += A;
+                ctx->h[1] += F[1];
+                ctx->h[2] += F[2];
+                ctx->h[3] += F[3];
+                ctx->h[4] += E;
+                ctx->h[5] += F[5];
+                ctx->h[6] += F[6];
+                ctx->h[7] += F[7];
 
-                        W+=SHA_LBLOCK;
-                        }
+                W += SHA_LBLOCK;
         }
+}
 
 #elif defined(OPENSSL_SMALL_FOOTPRINT)
 
-static void sha512_block_data_order (SHA512_CTX *ctx, const void *in, size_t num)
-        {
-        const SHA_LONG64 *W=in;
-        SHA_LONG64      a,b,c,d,e,f,g,h,s0,s1,T1,T2;
+static void
+sha512_block_data_order(SHA512_CTX *ctx, const void *in, size_t num)
+{
+        const SHA_LONG64 *W = in;
+        SHA_LONG64      a, b,c, d,e, f,g, h,s0, s1, T1, T2;
         SHA_LONG64      X[16];
         int i;
 
-                        while (num--) {
+        while (num--) {
 
-        a = ctx->h[0];  b = ctx->h[1];  c = ctx->h[2];  d = ctx->h[3];
-        e = ctx->h[4];  f = ctx->h[5];  g = ctx->h[6];  h = ctx->h[7];
+                a = ctx->h[0];
+                b = ctx->h[1];
+                c = ctx->h[2];
+                d = ctx->h[3];
+                e = ctx->h[4];
+                f = ctx->h[5];
+                g = ctx->h[6];
+                h = ctx->h[7];
 
-        for (i=0;i<16;i++)
-                {
+                for (i = 0; i < 16; i++) {
 #if BYTE_ORDER == BIG_ENDIAN
-                T1 = X[i] = W[i];
+                        T1 = X[i] = W[i];
 #else
-                T1 = X[i] = PULL64(W[i]);
+                        T1 = X[i] = PULL64(W[i]);
 #endif
-                T1 += h + Sigma1(e) + Ch(e,f,g) + K512[i];
-                T2 = Sigma0(a) + Maj(a,b,c);
-                h = g;  g = f;  f = e;  e = d + T1;
-                d = c;  c = b;  b = a;  a = T1 + T2;
+                        T1 += h + Sigma1(e) + Ch(e, f, g) + K512[i];
+                        T2 = Sigma0(a) + Maj(a, b, c);
+                        h = g;
+                        g = f;
+                        f = e;
+                        e = d + T1;
+                        d = c;
+                        c = b;
+                        b = a;
+                        a = T1 + T2;
                 }
 
-        for (;i<80;i++)
-                {
-                s0 = X[(i+1)&0x0f];     s0 = sigma0(s0);
-                s1 = X[(i+14)&0x0f];    s1 = sigma1(s1);
-
-                T1 = X[i&0xf] += s0 + s1 + X[(i+9)&0xf];
-                T1 += h + Sigma1(e) + Ch(e,f,g) + K512[i];
-                T2 = Sigma0(a) + Maj(a,b,c);
-                h = g;  g = f;  f = e;  e = d + T1;
-                d = c;  c = b;  b = a;  a = T1 + T2;
+                for (; i < 80; i++) {
+                        s0 = X[(i + 1)&0x0f];
+                        s0 = sigma0(s0);
+                        s1 = X[(i + 14)&0x0f];
+                        s1 = sigma1(s1);
+
+                        T1 = X[i&0xf] += s0 + s1 + X[(i + 9)&0xf];
+                        T1 += h + Sigma1(e) + Ch(e, f, g) + K512[i];
+                        T2 = Sigma0(a) + Maj(a, b, c);
+                        h = g;
+                        g = f;
+                        f = e;
+                        e = d + T1;
+                        d = c;
+                        c = b;
+                        b = a;
+                        a = T1 + T2;
                 }
 
-        ctx->h[0] += a; ctx->h[1] += b; ctx->h[2] += c; ctx->h[3] += d;
-        ctx->h[4] += e; ctx->h[5] += f; ctx->h[6] += g; ctx->h[7] += h;
+                ctx->h[0] += a;
+                ctx->h[1] += b;
+                ctx->h[2] += c;
+                ctx->h[3] += d;
+                ctx->h[4] += e;
+                ctx->h[5] += f;
+                ctx->h[6] += g;
+                ctx->h[7] += h;
 
-                        W+=SHA_LBLOCK;
-                        }
+                W += SHA_LBLOCK;
         }
+}
 
 #else
 
@@ -464,80 +516,124 @@ static void sha512_block_data_order (SHA512_CTX *ctx, const void *in, size_t num
         T1 = X[(j)&0x0f] += s0 + s1 + X[(j+9)&0x0f];    \
         ROUND_00_15(i+j,a,b,c,d,e,f,g,h);               } while (0)
 
-static void sha512_block_data_order (SHA512_CTX *ctx, const void *in, size_t num)
-        {
-        const SHA_LONG64 *W=in;
-        SHA_LONG64      a,b,c,d,e,f,g,h,s0,s1,T1;
+static void
+sha512_block_data_order(SHA512_CTX *ctx, const void *in, size_t num)
+{
+        const SHA_LONG64 *W = in;
+        SHA_LONG64      a, b,c, d,e, f,g, h,s0, s1, T1;
         SHA_LONG64      X[16];
         int i;
 
-                        while (num--) {
+        while (num--) {
 
-        a = ctx->h[0];  b = ctx->h[1];  c = ctx->h[2];  d = ctx->h[3];
-        e = ctx->h[4];  f = ctx->h[5];  g = ctx->h[6];  h = ctx->h[7];
+                a = ctx->h[0];
+                b = ctx->h[1];
+                c = ctx->h[2];
+                d = ctx->h[3];
+                e = ctx->h[4];
+                f = ctx->h[5];
+                g = ctx->h[6];
+                h = ctx->h[7];
 
 #if BYTE_ORDER == BIG_ENDIAN
-        T1 = X[0] = W[0];       ROUND_00_15(0,a,b,c,d,e,f,g,h);
-        T1 = X[1] = W[1];       ROUND_00_15(1,h,a,b,c,d,e,f,g);
-        T1 = X[2] = W[2];       ROUND_00_15(2,g,h,a,b,c,d,e,f);
-        T1 = X[3] = W[3];       ROUND_00_15(3,f,g,h,a,b,c,d,e);
-        T1 = X[4] = W[4];       ROUND_00_15(4,e,f,g,h,a,b,c,d);
-        T1 = X[5] = W[5];       ROUND_00_15(5,d,e,f,g,h,a,b,c);
-        T1 = X[6] = W[6];       ROUND_00_15(6,c,d,e,f,g,h,a,b);
-        T1 = X[7] = W[7];       ROUND_00_15(7,b,c,d,e,f,g,h,a);
-        T1 = X[8] = W[8];       ROUND_00_15(8,a,b,c,d,e,f,g,h);
-        T1 = X[9] = W[9];       ROUND_00_15(9,h,a,b,c,d,e,f,g);
-        T1 = X[10] = W[10];     ROUND_00_15(10,g,h,a,b,c,d,e,f);
-        T1 = X[11] = W[11];     ROUND_00_15(11,f,g,h,a,b,c,d,e);
-        T1 = X[12] = W[12];     ROUND_00_15(12,e,f,g,h,a,b,c,d);
-        T1 = X[13] = W[13];     ROUND_00_15(13,d,e,f,g,h,a,b,c);
-        T1 = X[14] = W[14];     ROUND_00_15(14,c,d,e,f,g,h,a,b);
-        T1 = X[15] = W[15];     ROUND_00_15(15,b,c,d,e,f,g,h,a);
+                T1 = X[0] = W[0];
+                ROUND_00_15(0, a,b, c,d, e,f, g, h);
+                T1 = X[1] = W[1];
+                ROUND_00_15(1, h,a, b,c, d,e, f, g);
+                T1 = X[2] = W[2];
+                ROUND_00_15(2, g,h, a,b, c,d, e, f);
+                T1 = X[3] = W[3];
+                ROUND_00_15(3, f,g, h,a, b,c, d, e);
+                T1 = X[4] = W[4];
+                ROUND_00_15(4, e,f, g,h, a,b, c, d);
+                T1 = X[5] = W[5];
+                ROUND_00_15(5, d,e, f,g, h,a, b, c);
+                T1 = X[6] = W[6];
+                ROUND_00_15(6, c,d, e,f, g,h, a, b);
+                T1 = X[7] = W[7];
+                ROUND_00_15(7, b,c, d,e, f,g, h, a);
+                T1 = X[8] = W[8];
+                ROUND_00_15(8, a,b, c,d, e,f, g, h);
+                T1 = X[9] = W[9];
+                ROUND_00_15(9, h,a, b,c, d,e, f, g);
+                T1 = X[10] = W[10];
+                ROUND_00_15(10, g,h, a,b, c,d, e, f);
+                T1 = X[11] = W[11];
+                ROUND_00_15(11, f,g, h,a, b,c, d, e);
+                T1 = X[12] = W[12];
+                ROUND_00_15(12, e,f, g,h, a,b, c, d);
+                T1 = X[13] = W[13];
+                ROUND_00_15(13, d,e, f,g, h,a, b, c);
+                T1 = X[14] = W[14];
+                ROUND_00_15(14, c,d, e,f, g,h, a, b);
+                T1 = X[15] = W[15];
+                ROUND_00_15(15, b,c, d,e, f,g, h, a);
 #else
-        T1 = X[0]  = PULL64(W[0]);      ROUND_00_15(0,a,b,c,d,e,f,g,h);
-        T1 = X[1]  = PULL64(W[1]);      ROUND_00_15(1,h,a,b,c,d,e,f,g);
-        T1 = X[2]  = PULL64(W[2]);      ROUND_00_15(2,g,h,a,b,c,d,e,f);
-        T1 = X[3]  = PULL64(W[3]);      ROUND_00_15(3,f,g,h,a,b,c,d,e);
-        T1 = X[4]  = PULL64(W[4]);      ROUND_00_15(4,e,f,g,h,a,b,c,d);
-        T1 = X[5]  = PULL64(W[5]);      ROUND_00_15(5,d,e,f,g,h,a,b,c);
-        T1 = X[6]  = PULL64(W[6]);      ROUND_00_15(6,c,d,e,f,g,h,a,b);
-        T1 = X[7]  = PULL64(W[7]);      ROUND_00_15(7,b,c,d,e,f,g,h,a);
-        T1 = X[8]  = PULL64(W[8]);      ROUND_00_15(8,a,b,c,d,e,f,g,h);
-        T1 = X[9]  = PULL64(W[9]);      ROUND_00_15(9,h,a,b,c,d,e,f,g);
-        T1 = X[10] = PULL64(W[10]);     ROUND_00_15(10,g,h,a,b,c,d,e,f);
-        T1 = X[11] = PULL64(W[11]);     ROUND_00_15(11,f,g,h,a,b,c,d,e);
-        T1 = X[12] = PULL64(W[12]);     ROUND_00_15(12,e,f,g,h,a,b,c,d);
-        T1 = X[13] = PULL64(W[13]);     ROUND_00_15(13,d,e,f,g,h,a,b,c);
-        T1 = X[14] = PULL64(W[14]);     ROUND_00_15(14,c,d,e,f,g,h,a,b);
-        T1 = X[15] = PULL64(W[15]);     ROUND_00_15(15,b,c,d,e,f,g,h,a);
+                T1 = X[0] = PULL64(W[0]);
+                ROUND_00_15(0, a,b, c,d, e,f, g, h);
+                T1 = X[1] = PULL64(W[1]);
+                ROUND_00_15(1, h,a, b,c, d,e, f, g);
+                T1 = X[2] = PULL64(W[2]);
+                ROUND_00_15(2, g,h, a,b, c,d, e, f);
+                T1 = X[3] = PULL64(W[3]);
+                ROUND_00_15(3, f,g, h,a, b,c, d, e);
+                T1 = X[4] = PULL64(W[4]);
+                ROUND_00_15(4, e,f, g,h, a,b, c, d);
+                T1 = X[5] = PULL64(W[5]);
+                ROUND_00_15(5, d,e, f,g, h,a, b, c);
+                T1 = X[6] = PULL64(W[6]);
+                ROUND_00_15(6, c,d, e,f, g,h, a, b);
+                T1 = X[7] = PULL64(W[7]);
+                ROUND_00_15(7, b,c, d,e, f,g, h, a);
+                T1 = X[8] = PULL64(W[8]);
+                ROUND_00_15(8, a,b, c,d, e,f, g, h);
+                T1 = X[9] = PULL64(W[9]);
+                ROUND_00_15(9, h,a, b,c, d,e, f, g);
+                T1 = X[10] = PULL64(W[10]);
+                ROUND_00_15(10, g,h, a,b, c,d, e, f);
+                T1 = X[11] = PULL64(W[11]);
+                ROUND_00_15(11, f,g, h,a, b,c, d, e);
+                T1 = X[12] = PULL64(W[12]);
+                ROUND_00_15(12, e,f, g,h, a,b, c, d);
+                T1 = X[13] = PULL64(W[13]);
+                ROUND_00_15(13, d,e, f,g, h,a, b, c);
+                T1 = X[14] = PULL64(W[14]);
+                ROUND_00_15(14, c,d, e,f, g,h, a, b);
+                T1 = X[15] = PULL64(W[15]);
+                ROUND_00_15(15, b,c, d,e, f,g, h, a);
 #endif
 
-        for (i=16;i<80;i+=16)
-                {
-                ROUND_16_80(i, 0,a,b,c,d,e,f,g,h,X);
-                ROUND_16_80(i, 1,h,a,b,c,d,e,f,g,X);
-                ROUND_16_80(i, 2,g,h,a,b,c,d,e,f,X);
-                ROUND_16_80(i, 3,f,g,h,a,b,c,d,e,X);
-                ROUND_16_80(i, 4,e,f,g,h,a,b,c,d,X);
-                ROUND_16_80(i, 5,d,e,f,g,h,a,b,c,X);
-                ROUND_16_80(i, 6,c,d,e,f,g,h,a,b,X);
-                ROUND_16_80(i, 7,b,c,d,e,f,g,h,a,X);
-                ROUND_16_80(i, 8,a,b,c,d,e,f,g,h,X);
-                ROUND_16_80(i, 9,h,a,b,c,d,e,f,g,X);
-                ROUND_16_80(i,10,g,h,a,b,c,d,e,f,X);
-                ROUND_16_80(i,11,f,g,h,a,b,c,d,e,X);
-                ROUND_16_80(i,12,e,f,g,h,a,b,c,d,X);
-                ROUND_16_80(i,13,d,e,f,g,h,a,b,c,X);
-                ROUND_16_80(i,14,c,d,e,f,g,h,a,b,X);
-                ROUND_16_80(i,15,b,c,d,e,f,g,h,a,X);
+                for (i = 16; i < 80; i += 16) {
+                        ROUND_16_80(i, 0, a,b, c,d, e,f, g,h, X);
+                        ROUND_16_80(i, 1, h,a, b,c, d,e, f,g, X);
+                        ROUND_16_80(i, 2, g,h, a,b, c,d, e,f, X);
+                        ROUND_16_80(i, 3, f,g, h,a, b,c, d,e, X);
+                        ROUND_16_80(i, 4, e,f, g,h, a,b, c,d, X);
+                        ROUND_16_80(i, 5, d,e, f,g, h,a, b,c, X);
+                        ROUND_16_80(i, 6, c,d, e,f, g,h, a,b, X);
+                        ROUND_16_80(i, 7, b,c, d,e, f,g, h,a, X);
+                        ROUND_16_80(i, 8, a,b, c,d, e,f, g,h, X);
+                        ROUND_16_80(i, 9, h,a, b,c, d,e, f,g, X);
+                        ROUND_16_80(i, 10, g,h, a,b, c,d, e,f, X);
+                        ROUND_16_80(i, 11, f,g, h,a, b,c, d,e, X);
+                        ROUND_16_80(i, 12, e,f, g,h, a,b, c,d, X);
+                        ROUND_16_80(i, 13, d,e, f,g, h,a, b,c, X);
+                        ROUND_16_80(i, 14, c,d, e,f, g,h, a,b, X);
+                        ROUND_16_80(i, 15, b,c, d,e, f,g, h,a, X);
                 }
 
-        ctx->h[0] += a; ctx->h[1] += b; ctx->h[2] += c; ctx->h[3] += d;
-        ctx->h[4] += e; ctx->h[5] += f; ctx->h[6] += g; ctx->h[7] += h;
+                ctx->h[0] += a;
+                ctx->h[1] += b;
+                ctx->h[2] += c;
+                ctx->h[3] += d;
+                ctx->h[4] += e;
+                ctx->h[5] += f;
+                ctx->h[6] += g;
+                ctx->h[7] += h;
 
-                        W+=SHA_LBLOCK;
-                        }
+                W += SHA_LBLOCK;
         }
+}
 
 #endif