Merge branch 'master' into int-new

15 files changed, 1983 insertions, 207 deletions

diff --git a/lib/Modules b/lib/Modules
index 7254df2d..745306d9 100644
--- a/lib/Modules
+++ b/lib/Modules
@@ -1,3 +1,9 @@
+sha256.c
+sha256.h
+sha512.c
+sha512.h
+sha1.c
+sha1.h
 birdlib.h
 bitops.c
 bitops.h
diff --git a/lib/birdlib.h b/lib/birdlib.h
index ad41dca3..16f437ef 100644
--- a/lib/birdlib.h
+++ b/lib/birdlib.h
@@ -30,6 +30,7 @@
 #define MAX(a,b) MAX_(a,b)
 #endif
 
+#define U64(c) UINT64_C(c)
 #define ABS(a)   ((a)>=0 ? (a) : -(a))
 #define DELTA(a,b) (((a)>=(b))?(a)-(b):(b)-(a))
 #define ARRAY_SIZE(a) (sizeof(a)/sizeof(*(a)))
diff --git a/lib/ip.c b/lib/ip.c
index 6b0b0bc2..6205915a 100644
--- a/lib/ip.c
+++ b/lib/ip.c
@@ -233,7 +233,7 @@ ip6_ntop(ip6_addr a, char *b)
 }
 
 int
-ip4_pton(char *a, ip4_addr *o)
+ip4_pton(const char *a, ip4_addr *o)
 {
   int i;
   unsigned long int l;
@@ -258,11 +258,11 @@ ip4_pton(char *a, ip4_addr *o)
 }
 
 int
-ip6_pton(char *a, ip6_addr *o)
+ip6_pton(const char *a, ip6_addr *o)
 {
   u16 words[8];
   int i, j, k, l, hfil;
-  char *start;
+  const char *start;
 
   if (a[0] == ':')			/* Leading :: */
   {
diff --git a/lib/ip.h b/lib/ip.h
index 9b4400ba..66fdd8c2 100644
--- a/lib/ip.h
+++ b/lib/ip.h
@@ -469,8 +469,8 @@ static inline char * ip4_ntox(ip4_addr a, char *b)
 static inline char * ip6_ntox(ip6_addr a, char *b)
 { return b + bsprintf(b, "%08x.%08x.%08x.%08x", _I0(a), _I1(a), _I2(a), _I3(a)); }
 
-int ip4_pton(char *a, ip4_addr *o);
-int ip6_pton(char *a, ip6_addr *o);
+int ip4_pton(const char *a, ip4_addr *o);
+int ip6_pton(const char *a, ip6_addr *o);
 
 // XXXX these functions must be redesigned or removed
 #ifdef IPV6
diff --git a/lib/md5.c b/lib/md5.c
index ad284f07..8efa62d6 100644
--- a/lib/md5.c
+++ b/lib/md5.c
@@ -1,154 +1,159 @@
 /*
- * This code implements the MD5 message-digest algorithm.
- * The algorithm is due to Ron Rivest.  This code was
- * written by Colin Plumb in 1993, no copyright is claimed.
- * This code is in the public domain; do with it what you wish.
+ *	BIRD Library -- MD5 Hash Function and HMAC-MD5 Function
  *
- * Equivalent code is available from RSA Data Security, Inc.
- * This code has been tested against that, and is equivalent,
- * except that you don't need to include two pages of legalese
- * with every copy.
+ *	(c) 2015 CZ.NIC z.s.p.o.
  *
- * To compute the message digest of a chunk of bytes, declare an
- * MD5Context structure, pass it to MD5Init, call MD5Update as
- * needed on buffers full of bytes, and then call MD5Final, which
- * will fill a supplied 16-byte array with the digest.
- */
-
-/*
- * Adapted for BIRD by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ *	The code was written by Colin Plumb in 1993, no copyright is claimed.
+ *
+ *	Adapted for BIRD by Martin Mares <mj@ucw.cz>
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
  */
 
-#include "nest/bird.h"
-#include "lib/string.h"
-#include "md5.h"
+#include "lib/md5.h"
 
 #ifdef CPU_LITTLE_ENDIAN
 #define byteReverse(buf, len)	/* Nothing */
 #else
-void byteReverse(unsigned char *buf, unsigned longs);
+void byteReverse(byte *buf, uint longs);
 
 /*
  * Note: this code is harmless on little-endian machines.
  */
-void byteReverse(unsigned char *buf, unsigned longs)
+void byteReverse(byte *buf, uint longs)
 {
-    u32 t;
-    do {
-	t = (u32) ((unsigned) buf[3] << 8 | buf[2]) << 16 |
-	    ((unsigned) buf[1] << 8 | buf[0]);
-	*(u32 *) buf = t;
-	buf += 4;
-    } while (--longs);
+  u32 t;
+  do {
+    t = (u32) ((uint) buf[3] << 8 | buf[2]) << 16 |
+	((uint) buf[1] << 8 | buf[0]);
+    *(u32 *) buf = t;
+    buf += 4;
+  } while (--longs);
 }
 #endif
 
+static void md5_transform(u32 buf[4], u32 const in[16]);
+
 /*
  * Start MD5 accumulation.  Set bit count to 0 and buffer to mysterious
  * initialization constants.
  */
-void MD5Init(struct MD5Context *ctx)
+void
+md5_init(struct md5_context *ctx)
 {
-    ctx->buf[0] = 0x67452301;
-    ctx->buf[1] = 0xefcdab89;
-    ctx->buf[2] = 0x98badcfe;
-    ctx->buf[3] = 0x10325476;
+  ctx->buf[0] = 0x67452301;
+  ctx->buf[1] = 0xefcdab89;
+  ctx->buf[2] = 0x98badcfe;
+  ctx->buf[3] = 0x10325476;
 
-    ctx->bits[0] = 0;
-    ctx->bits[1] = 0;
+  ctx->bits[0] = 0;
+  ctx->bits[1] = 0;
 }
 
 /*
  * Update context to reflect the concatenation of another buffer full
  * of bytes.
  */
-void MD5Update(struct MD5Context *ctx, unsigned char const *buf, unsigned len)
+void
+md5_update(struct md5_context *ctx, const byte *buf, uint len)
 {
-    u32 t;
+  u32 t;
 
-    /* Update bitcount */
+  /* Update bitcount */
 
-    t = ctx->bits[0];
-    if ((ctx->bits[0] = t + ((u32) len << 3)) < t)
-	ctx->bits[1]++;		/* Carry from low to high */
-    ctx->bits[1] += len >> 29;
+  t = ctx->bits[0];
+  if ((ctx->bits[0] = t + ((u32) len << 3)) < t)
+    ctx->bits[1]++;		/* Carry from low to high */
+  ctx->bits[1] += len >> 29;
 
-    t = (t >> 3) & 0x3f;	/* Bytes already in shsInfo->data */
+  t = (t >> 3) & 0x3f;	/* Bytes already in shsInfo->data */
 
-    /* Handle any leading odd-sized chunks */
+  /* Handle any leading odd-sized chunks */
+  if (t)
+  {
+    byte *p = (byte *) ctx->in + t;
 
-    if (t) {
-	unsigned char *p = (unsigned char *) ctx->in + t;
-
-	t = 64 - t;
-	if (len < t) {
-	    memcpy(p, buf, len);
-	    return;
-	}
-	memcpy(p, buf, t);
-	byteReverse(ctx->in, 16);
-	MD5Transform(ctx->buf, (u32 *) ctx->in);
-	buf += t;
-	len -= t;
-    }
-    /* Process data in 64-byte chunks */
-
-    while (len >= 64) {
-	memcpy(ctx->in, buf, 64);
-	byteReverse(ctx->in, 16);
-	MD5Transform(ctx->buf, (u32 *) ctx->in);
-	buf += 64;
-	len -= 64;
+    t = 64 - t;
+    if (len < t)
+    {
+      memcpy(p, buf, len);
+      return;
     }
-
-    /* Handle any remaining bytes of data. */
-
-    memcpy(ctx->in, buf, len);
+    memcpy(p, buf, t);
+    byteReverse(ctx->in, 16);
+    md5_transform(ctx->buf, (u32 *) ctx->in);
+    buf += t;
+    len -= t;
+  }
+
+  /* Process data in 64-byte chunks */
+  while (len >= 64)
+  {
+    memcpy(ctx->in, buf, 64);
+    byteReverse(ctx->in, 16);
+    md5_transform(ctx->buf, (u32 *) ctx->in);
+    buf += 64;
+    len -= 64;
+  }
+
+  /* Handle any remaining bytes of data. */
+  memcpy(ctx->in, buf, len);
 }
 
 /*
- * Final wrapup - pad to 64-byte boundary with the bit pattern 
+ * Final wrapup - pad to 64-byte boundary with the bit pattern
  * 1 0* (64-bit count of bits processed, MSB-first)
  */
-void MD5Final(unsigned char digest[16], struct MD5Context *ctx)
+byte *
+md5_final(struct md5_context *ctx)
 {
-    unsigned count;
-    unsigned char *p;
+  uint count;
+  byte *p;
 
-    /* Compute number of bytes mod 64 */
-    count = (ctx->bits[0] >> 3) & 0x3F;
+  /* Compute number of bytes mod 64 */
+  count = (ctx->bits[0] >> 3) & 0x3F;
 
-    /* Set the first char of padding to 0x80.  This is safe since there is
+  /* Set the first char of padding to 0x80.  This is safe since there is
        always at least one byte free */
-    p = ctx->in + count;
-    *p++ = 0x80;
-
-    /* Bytes of padding needed to make 64 bytes */
-    count = 64 - 1 - count;
-
-    /* Pad out to 56 mod 64 */
-    if (count < 8) {
-	/* Two lots of padding:  Pad the first block to 64 bytes */
-	memset(p, 0, count);
-	byteReverse(ctx->in, 16);
-	MD5Transform(ctx->buf, (u32 *) ctx->in);
-
-	/* Now fill the next block with 56 bytes */
-	memset(ctx->in, 0, 56);
-    } else {
-	/* Pad block to 56 bytes */
-	memset(p, 0, count - 8);
-    }
-    byteReverse(ctx->in, 14);
-
-    /* Append length in bits and transform */
-    ((u32 *) ctx->in)[14] = ctx->bits[0];
-    ((u32 *) ctx->in)[15] = ctx->bits[1];
+  p = ctx->in + count;
+  *p++ = 0x80;
+
+  /* Bytes of padding needed to make 64 bytes */
+  count = 64 - 1 - count;
+
+  /* Pad out to 56 mod 64 */
+  if (count < 8)
+  {
+    /* Two lots of padding:  Pad the first block to 64 bytes */
+    memset(p, 0, count);
+    byteReverse(ctx->in, 16);
+    md5_transform(ctx->buf, (u32 *) ctx->in);
+
+    /* Now fill the next block with 56 bytes */
+    memset(ctx->in, 0, 56);
+  }
+  else
+  {
+    /* Pad block to 56 bytes */
+    memset(p, 0, count - 8);
+  }
+  byteReverse(ctx->in, 14);
+
+  /* Append length in bits and transform */
+  ((u32 *) ctx->in)[14] = ctx->bits[0];
+  ((u32 *) ctx->in)[15] = ctx->bits[1];
+
+  md5_transform(ctx->buf, (u32 *) ctx->in);
+  byteReverse((byte *) ctx->buf, 4);
+
+  return (byte*) ctx->buf;
+}
 
-    MD5Transform(ctx->buf, (u32 *) ctx->in);
-    byteReverse((unsigned char *) ctx->buf, 4);
-    memcpy(digest, ctx->buf, 16);
-    memset((char *) ctx, 0, sizeof(ctx));	/* In case it's sensitive */
+/* I am a hard paranoid */
+void
+md5_erase_ctx(struct md5_context *ctx)
+{
+  memset((char *) ctx, 0, sizeof(*ctx));	/* In case it's sensitive */
 }
 
 /* The four core functions - F1 is optimized somewhat */
@@ -161,92 +166,157 @@ void MD5Final(unsigned char digest[16], struct MD5Context *ctx)
 
 /* This is the central step in the MD5 algorithm. */
 #define MD5STEP(f, w, x, y, z, data, s) \
-	( w += f(x, y, z) + data,  w = w<<s | w>>(32-s),  w += x )
+    ( w += f(x, y, z) + data,  w = w<<s | w>>(32-s),  w += x )
 
 /*
  * The core of the MD5 algorithm, this alters an existing MD5 hash to
  * reflect the addition of 16 longwords of new data.  MD5Update blocks
  * the data and converts bytes into longwords for this routine.
  */
-void MD5Transform(u32 buf[4], u32 const in[16])
+void
+md5_transform(u32 buf[4], u32 const in[16])
+{
+  register u32 a, b, c, d;
+
+  a = buf[0];
+  b = buf[1];
+  c = buf[2];
+  d = buf[3];
+
+  MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
+  MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
+  MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
+  MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
+  MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
+  MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
+  MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
+  MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
+  MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
+  MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
+  MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
+  MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
+  MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
+  MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
+  MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
+  MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
+
+  MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
+  MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
+  MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
+  MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
+  MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
+  MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
+  MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
+  MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
+  MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
+  MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
+  MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
+  MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
+  MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
+  MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
+  MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
+  MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
+
+  MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
+  MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
+  MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
+  MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
+  MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
+  MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
+  MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
+  MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
+  MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
+  MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
+  MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
+  MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
+  MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
+  MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
+  MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
+  MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
+
+  MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
+  MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
+  MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
+  MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
+  MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
+  MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
+  MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
+  MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
+  MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
+  MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
+  MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
+  MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
+  MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
+  MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
+  MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
+  MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
+
+  buf[0] += a;
+  buf[1] += b;
+  buf[2] += c;
+  buf[3] += d;
+}
+
+
+/*
+ * 	MD5-HMAC
+ */
+
+static void
+md5_hash_buffer(byte *outbuf, const byte *buffer, size_t length)
+{
+  struct md5_context hd_tmp;
+
+  md5_init(&hd_tmp);
+  md5_update(&hd_tmp, buffer, length);
+  memcpy(outbuf, md5_final(&hd_tmp), MD5_SIZE);
+}
+
+void
+md5_hmac_init(struct md5_hmac_context *ctx, const byte *key, size_t keylen)
+{
+  byte keybuf[MD5_BLOCK_SIZE], buf[MD5_BLOCK_SIZE];
+
+  /* Hash the key if necessary */
+  if (keylen <= MD5_BLOCK_SIZE)
+  {
+    memcpy(keybuf, key, keylen);
+    bzero(keybuf + keylen, MD5_BLOCK_SIZE - keylen);
+  }
+  else
+  {
+    md5_hash_buffer(keybuf, key, keylen);
+    bzero(keybuf + MD5_SIZE, MD5_BLOCK_SIZE - MD5_SIZE);
+  }
+
+  /* Initialize the inner digest */
+  md5_init(&ctx->ictx);
+  int i;
+  for (i = 0; i < MD5_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x36;
+  md5_update(&ctx->ictx, buf, MD5_BLOCK_SIZE);
+
+  /* Initialize the outer digest */
+  md5_init(&ctx->octx);
+  for (i = 0; i < MD5_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x5c;
+  md5_update(&ctx->octx, buf, MD5_BLOCK_SIZE);
+}
+
+void
+md5_hmac_update(struct md5_hmac_context *ctx, const byte *buf, size_t buflen)
 {
-    register u32 a, b, c, d;
-
-    a = buf[0];
-    b = buf[1];
-    c = buf[2];
-    d = buf[3];
-
-    MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
-    MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
-    MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
-    MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
-    MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
-    MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
-    MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
-    MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
-    MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
-    MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
-    MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
-    MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
-    MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
-    MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
-    MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
-    MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
-
-    MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
-    MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
-    MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
-    MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
-    MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
-    MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
-    MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
-    MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
-    MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
-    MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
-    MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
-    MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
-    MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
-    MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
-    MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
-    MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
-
-    MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
-    MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
-    MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
-    MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
-    MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
-    MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
-    MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
-    MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
-    MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
-    MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
-    MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
-    MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
-    MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
-    MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
-    MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
-    MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
-
-    MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
-    MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
-    MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
-    MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
-    MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
-    MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
-    MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
-    MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
-    MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
-    MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
-    MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
-    MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
-    MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
-    MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
-    MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
-    MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
-
-    buf[0] += a;
-    buf[1] += b;
-    buf[2] += c;
-    buf[3] += d;
+  /* Just update the inner digest */
+  md5_update(&ctx->ictx, buf, buflen);
+}
+
+byte *
+md5_hmac_final(struct md5_hmac_context *ctx)
+{
+  /* Finish the inner digest */
+  byte *isha = md5_final(&ctx->ictx);
+
+  /* Finish the outer digest */
+  md5_update(&ctx->octx, isha, MD5_SIZE);
+  return md5_final(&ctx->octx);
 }
diff --git a/lib/md5.h b/lib/md5.h
index 12586357..034d764c 100644
--- a/lib/md5.h
+++ b/lib/md5.h
@@ -1,16 +1,47 @@
-#ifndef MD5_H
-#define MD5_H
+/*
+ *	BIRD Library -- MD5 Hash Function and HMAC-MD5 Function
+ *
+ *	(c) 2015 CZ.NIC z.s.p.o.
+ *
+ *	Adapted for BIRD by Martin Mares <mj@ucw.cz>
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
+ */
 
-struct MD5Context {
-	u32 buf[4];
-	u32 bits[2];
-	unsigned char in[64];
+#ifndef _BIRD_MD5_H_
+#define _BIRD_MD5_H_
+
+#include "nest/bird.h"
+
+
+#define MD5_SIZE		16
+#define MD5_HEX_SIZE		33
+#define MD5_BLOCK_SIZE		64
+
+
+struct md5_context {
+  u32 buf[4];
+  u32 bits[2];
+  byte in[64];
 };
 
-void MD5Init(struct MD5Context *context);
-void MD5Update(struct MD5Context *context, unsigned char const *buf,
-	       unsigned len);
-void MD5Final(unsigned char digest[16], struct MD5Context *context);
-void MD5Transform(u32 buf[4], u32 const in[16]);
+void md5_init(struct md5_context *ctx);
+void md5_update(struct md5_context *ctx, const byte *buf, uint len);
+byte *md5_final(struct md5_context *ctx);
+
+
+/*
+ *	HMAC-MD5
+ */
+
+struct md5_hmac_context {
+  struct md5_context ictx;
+  struct md5_context octx;
+};
+
+void md5_hmac_init(struct md5_hmac_context *ctx, const byte *key, size_t keylen);
+void md5_hmac_update(struct md5_hmac_context *ctx, const byte *buf, size_t buflen);
+byte *md5_hmac_final(struct md5_hmac_context *ctx);
+
 
-#endif /* !MD5_H */
+#endif /* _BIRD_MD5_H_ */
diff --git a/lib/patmatch.c b/lib/patmatch.c
index 923e8f86..d2e1e313 100644
--- a/lib/patmatch.c
+++ b/lib/patmatch.c
@@ -16,7 +16,7 @@
 #endif
 
 int
-MATCH_FUNC_NAME(byte *p, byte *s)
+MATCH_FUNC_NAME(const byte *p, const byte *s)
 {
   while (*p)
     {
diff --git a/lib/sha1.c b/lib/sha1.c
new file mode 100644
index 00000000..73b4b280
--- /dev/null
+++ b/lib/sha1.c
@@ -0,0 +1,348 @@
+/*
+ *	BIRD Library -- SHA-1 Hash Function (FIPS 180-1, RFC 3174) and HMAC-SHA-1
+ *
+ *	(c) 2015 CZ.NIC z.s.p.o.
+ *
+ *	Based on the code from libucw-6.4
+ *	(c) 2008--2009 Martin Mares <mj@ucw.cz>
+ *
+ *	Based on the code from libgcrypt-1.2.3, which is
+ *	(c) 1998, 2001, 2002, 2003 Free Software Foundation, Inc.
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
+ */
+
+#include "lib/sha1.h"
+#include "lib/unaligned.h"
+
+
+void
+sha1_init(struct sha1_context *ctx)
+{
+  ctx->h0 = 0x67452301;
+  ctx->h1 = 0xefcdab89;
+  ctx->h2 = 0x98badcfe;
+  ctx->h3 = 0x10325476;
+  ctx->h4 = 0xc3d2e1f0;
+
+  ctx->nblocks = 0;
+  ctx->count = 0;
+}
+
+/*
+ * Transform the message X which consists of 16 32-bit-words
+ */
+static void
+sha1_transform(struct sha1_context *ctx, const byte *data)
+{
+  u32 a,b,c,d,e,tm;
+  u32 x[16];
+
+  /* Get values from the chaining vars. */
+  a = ctx->h0;
+  b = ctx->h1;
+  c = ctx->h2;
+  d = ctx->h3;
+  e = ctx->h4;
+
+#ifdef CPU_BIG_ENDIAN
+  memcpy(x, data, 64);
+#else
+  int i;
+  for (i = 0; i < 16; i++)
+    x[i] = get_u32(data+4*i);
+#endif
+
+#define K1		0x5A827999L
+#define K2		0x6ED9EBA1L
+#define K3		0x8F1BBCDCL
+#define K4  		0xCA62C1D6L
+#define F1(x,y,z)	( z ^ ( x & ( y ^ z ) ) )
+#define F2(x,y,z)	( x ^ y ^ z )
+#define F3(x,y,z)	( ( x & y ) | ( z & ( x | y ) ) )
+#define F4(x,y,z)	( x ^ y ^ z )
+
+#define M(i) (tm = x[i&0x0f] ^ x[(i-14)&0x0f] ^ x[(i-8)&0x0f] ^ x[(i-3)&0x0f], (x[i&0x0f] = ROL(tm, 1)))
+
+/* Bitwise rotation of an unsigned int to the left **/
+#define	ROL(x, bits) (((x) << (bits)) | ((uint)(x) >> (sizeof(uint)*8 - (bits))))
+
+  #define R(a, b, c, d, e, f, k, m)		\
+    do 						\
+    {						\
+      e += ROL(a, 5) + f(b, c, d) + k + m;	\
+      b = ROL(b, 30);				\
+    } while(0)
+
+  R( a, b, c, d, e, F1, K1, x[ 0] );
+  R( e, a, b, c, d, F1, K1, x[ 1] );
+  R( d, e, a, b, c, F1, K1, x[ 2] );
+  R( c, d, e, a, b, F1, K1, x[ 3] );
+  R( b, c, d, e, a, F1, K1, x[ 4] );
+  R( a, b, c, d, e, F1, K1, x[ 5] );
+  R( e, a, b, c, d, F1, K1, x[ 6] );
+  R( d, e, a, b, c, F1, K1, x[ 7] );
+  R( c, d, e, a, b, F1, K1, x[ 8] );
+  R( b, c, d, e, a, F1, K1, x[ 9] );
+  R( a, b, c, d, e, F1, K1, x[10] );
+  R( e, a, b, c, d, F1, K1, x[11] );
+  R( d, e, a, b, c, F1, K1, x[12] );
+  R( c, d, e, a, b, F1, K1, x[13] );
+  R( b, c, d, e, a, F1, K1, x[14] );
+  R( a, b, c, d, e, F1, K1, x[15] );
+  R( e, a, b, c, d, F1, K1, M(16) );
+  R( d, e, a, b, c, F1, K1, M(17) );
+  R( c, d, e, a, b, F1, K1, M(18) );
+  R( b, c, d, e, a, F1, K1, M(19) );
+  R( a, b, c, d, e, F2, K2, M(20) );
+  R( e, a, b, c, d, F2, K2, M(21) );
+  R( d, e, a, b, c, F2, K2, M(22) );
+  R( c, d, e, a, b, F2, K2, M(23) );
+  R( b, c, d, e, a, F2, K2, M(24) );
+  R( a, b, c, d, e, F2, K2, M(25) );
+  R( e, a, b, c, d, F2, K2, M(26) );
+  R( d, e, a, b, c, F2, K2, M(27) );
+  R( c, d, e, a, b, F2, K2, M(28) );
+  R( b, c, d, e, a, F2, K2, M(29) );
+  R( a, b, c, d, e, F2, K2, M(30) );
+  R( e, a, b, c, d, F2, K2, M(31) );
+  R( d, e, a, b, c, F2, K2, M(32) );
+  R( c, d, e, a, b, F2, K2, M(33) );
+  R( b, c, d, e, a, F2, K2, M(34) );
+  R( a, b, c, d, e, F2, K2, M(35) );
+  R( e, a, b, c, d, F2, K2, M(36) );
+  R( d, e, a, b, c, F2, K2, M(37) );
+  R( c, d, e, a, b, F2, K2, M(38) );
+  R( b, c, d, e, a, F2, K2, M(39) );
+  R( a, b, c, d, e, F3, K3, M(40) );
+  R( e, a, b, c, d, F3, K3, M(41) );
+  R( d, e, a, b, c, F3, K3, M(42) );
+  R( c, d, e, a, b, F3, K3, M(43) );
+  R( b, c, d, e, a, F3, K3, M(44) );
+  R( a, b, c, d, e, F3, K3, M(45) );
+  R( e, a, b, c, d, F3, K3, M(46) );
+  R( d, e, a, b, c, F3, K3, M(47) );
+  R( c, d, e, a, b, F3, K3, M(48) );
+  R( b, c, d, e, a, F3, K3, M(49) );
+  R( a, b, c, d, e, F3, K3, M(50) );
+  R( e, a, b, c, d, F3, K3, M(51) );
+  R( d, e, a, b, c, F3, K3, M(52) );
+  R( c, d, e, a, b, F3, K3, M(53) );
+  R( b, c, d, e, a, F3, K3, M(54) );
+  R( a, b, c, d, e, F3, K3, M(55) );
+  R( e, a, b, c, d, F3, K3, M(56) );
+  R( d, e, a, b, c, F3, K3, M(57) );
+  R( c, d, e, a, b, F3, K3, M(58) );
+  R( b, c, d, e, a, F3, K3, M(59) );
+  R( a, b, c, d, e, F4, K4, M(60) );
+  R( e, a, b, c, d, F4, K4, M(61) );
+  R( d, e, a, b, c, F4, K4, M(62) );
+  R( c, d, e, a, b, F4, K4, M(63) );
+  R( b, c, d, e, a, F4, K4, M(64) );
+  R( a, b, c, d, e, F4, K4, M(65) );
+  R( e, a, b, c, d, F4, K4, M(66) );
+  R( d, e, a, b, c, F4, K4, M(67) );
+  R( c, d, e, a, b, F4, K4, M(68) );
+  R( b, c, d, e, a, F4, K4, M(69) );
+  R( a, b, c, d, e, F4, K4, M(70) );
+  R( e, a, b, c, d, F4, K4, M(71) );
+  R( d, e, a, b, c, F4, K4, M(72) );
+  R( c, d, e, a, b, F4, K4, M(73) );
+  R( b, c, d, e, a, F4, K4, M(74) );
+  R( a, b, c, d, e, F4, K4, M(75) );
+  R( e, a, b, c, d, F4, K4, M(76) );
+  R( d, e, a, b, c, F4, K4, M(77) );
+  R( c, d, e, a, b, F4, K4, M(78) );
+  R( b, c, d, e, a, F4, K4, M(79) );
+
+  /* Update chaining vars. */
+  ctx->h0 += a;
+  ctx->h1 += b;
+  ctx->h2 += c;
+  ctx->h3 += d;
+  ctx->h4 += e;
+}
+
+/*
+ * Update the message digest with the contents of BUF with length LEN.
+ */
+void
+sha1_update(struct sha1_context *ctx, const byte *buf, uint len)
+{
+  if (ctx->count)
+  {
+    /* Fill rest of internal buffer */
+    for (; len && ctx->count < SHA1_BLOCK_SIZE; len--)
+      ctx->buf[ctx->count++] = *buf++;
+
+    if (ctx->count < SHA1_BLOCK_SIZE)
+      return;
+
+    /* Process data from internal buffer */
+    sha1_transform(ctx, ctx->buf);
+    ctx->nblocks++;
+    ctx->count = 0;
+  }
+
+  if (!len)
+    return;
+
+  /* Process data from input buffer */
+  while (len >= SHA1_BLOCK_SIZE)
+  {
+    sha1_transform(ctx, buf);
+    ctx->nblocks++;
+    buf += SHA1_BLOCK_SIZE;
+    len -= SHA1_BLOCK_SIZE;
+  }
+
+  /* Copy remaining data to internal buffer */
+  memcpy(ctx->buf, buf, len);
+  ctx->count = len;
+}
+
+/*
+ * The routine final terminates the computation and returns the digest. The
+ * handle is prepared for a new cycle, but adding bytes to the handle will the
+ * destroy the returned buffer.
+ *
+ * Returns: 20 bytes representing the digest.
+ */
+byte *
+sha1_final(struct sha1_context *ctx)
+{
+  u32 t, msb, lsb;
+
+  sha1_update(ctx, NULL, 0);	/* flush */
+
+  t = ctx->nblocks;
+  /* multiply by 64 to make a byte count */
+  lsb = t << 6;
+  msb = t >> 26;
+  /* add the count */
+  t = lsb;
+  if ((lsb += ctx->count) < t)
+    msb++;
+  /* multiply by 8 to make a bit count */
+  t = lsb;
+  lsb <<= 3;
+  msb <<= 3;
+  msb |= t >> 29;
+
+  if (ctx->count < 56)
+  {
+    /* enough room */
+    ctx->buf[ctx->count++] = 0x80; /* pad */
+    while (ctx->count < 56)
+      ctx->buf[ctx->count++] = 0;  /* pad */
+  }
+  else
+  {
+    /* need one extra block */
+    ctx->buf[ctx->count++] = 0x80; /* pad character */
+    while (ctx->count < 64)
+      ctx->buf[ctx->count++] = 0;
+    sha1_update(ctx, NULL, 0);	/* flush */
+    memset(ctx->buf, 0, 56); /* fill next block with zeroes */
+  }
+
+  /* append the 64 bit count */
+  ctx->buf[56] = msb >> 24;
+  ctx->buf[57] = msb >> 16;
+  ctx->buf[58] = msb >>  8;
+  ctx->buf[59] = msb;
+  ctx->buf[60] = lsb >> 24;
+  ctx->buf[61] = lsb >> 16;
+  ctx->buf[62] = lsb >>  8;
+  ctx->buf[63] = lsb;
+  sha1_transform(ctx, ctx->buf);
+
+  byte *p = ctx->buf;
+#define X(a) do { put_u32(p, ctx->h##a); p += 4; } while(0)
+  X(0);
+  X(1);
+  X(2);
+  X(3);
+  X(4);
+#undef X
+
+  return ctx->buf;
+}
+
+
+/*
+ *	SHA1-HMAC
+ */
+
+/*
+ * Shortcut function which puts the hash value of the supplied buffer
+ * into outbuf which must have a size of 20 bytes.
+ */
+void
+sha1_hash_buffer(byte *outbuf, const byte *buffer, uint length)
+{
+  struct sha1_context ctx;
+
+  sha1_init(&ctx);
+  sha1_update(&ctx, buffer, length);
+  memcpy(outbuf, sha1_final(&ctx), SHA1_SIZE);
+}
+
+void
+sha1_hmac_init(struct sha1_hmac_context *ctx, const byte *key, uint keylen)
+{
+  byte keybuf[SHA1_BLOCK_SIZE], buf[SHA1_BLOCK_SIZE];
+
+  /* Hash the key if necessary */
+  if (keylen <= SHA1_BLOCK_SIZE)
+  {
+    memcpy(keybuf, key, keylen);
+    memset(keybuf + keylen, 0, SHA1_BLOCK_SIZE - keylen);
+  }
+  else
+  {
+    sha1_hash_buffer(keybuf, key, keylen);
+    memset(keybuf + SHA1_SIZE, 0, SHA1_BLOCK_SIZE - SHA1_SIZE);
+  }
+
+  /* Initialize the inner digest */
+  sha1_init(&ctx->ictx);
+  int i;
+  for (i = 0; i < SHA1_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x36;
+  sha1_update(&ctx->ictx, buf, SHA1_BLOCK_SIZE);
+
+  /* Initialize the outer digest */
+  sha1_init(&ctx->octx);
+  for (i = 0; i < SHA1_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x5c;
+  sha1_update(&ctx->octx, buf, SHA1_BLOCK_SIZE);
+}
+
+void
+sha1_hmac_update(struct sha1_hmac_context *ctx, const byte *data, uint datalen)
+{
+  /* Just update the inner digest */
+  sha1_update(&ctx->ictx, data, datalen);
+}
+
+byte *
+sha1_hmac_final(struct sha1_hmac_context *ctx)
+{
+  /* Finish the inner digest */
+  byte *isha = sha1_final(&ctx->ictx);
+
+  /* Finish the outer digest */
+  sha1_update(&ctx->octx, isha, SHA1_SIZE);
+  return sha1_final(&ctx->octx);
+}
+
+void
+sha1_hmac(byte *outbuf, const byte *key, uint keylen, const byte *data, uint datalen)
+{
+  struct sha1_hmac_context ctx;
+
+  sha1_hmac_init(&ctx, key, keylen);
+  sha1_hmac_update(&ctx, data, datalen);
+  memcpy(outbuf, sha1_hmac_final(&ctx), SHA1_SIZE);
+}
diff --git a/lib/sha1.h b/lib/sha1.h
new file mode 100644
index 00000000..c019bb49
--- /dev/null
+++ b/lib/sha1.h
@@ -0,0 +1,86 @@
+/*
+ *	BIRD Library -- SHA-1 Hash Function (FIPS 180-1, RFC 3174) and HMAC-SHA-1
+ *
+ *	(c) 2015 CZ.NIC z.s.p.o.
+ *
+ *	Based on the code from libucw-6.4
+ *	(c) 2008--2009 Martin Mares <mj@ucw.cz>
+ *
+ *	Based on the code from libgcrypt-1.2.3, which is
+ *	(c) 1998, 2001, 2002, 2003 Free Software Foundation, Inc.
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
+ */
+
+#ifndef _BIRD_SHA1_H_
+#define _BIRD_SHA1_H_
+
+#include "nest/bird.h"
+
+
+#define SHA1_SIZE		20	/* Size of the SHA1 hash in its binary representation */
+#define SHA1_HEX_SIZE		41	/* Buffer length for a string containing SHA1 in hexadecimal format. */
+#define SHA1_BLOCK_SIZE		64	/* SHA1 splits input to blocks of this size. */
+
+
+/*
+ * Internal SHA1 state.
+ * You should use it just as an opaque handle only.
+ */
+struct sha1_context {
+  u32 h0, h1, h2, h3, h4;
+  byte buf[SHA1_BLOCK_SIZE];
+  uint nblocks;
+  uint count;
+};
+
+
+void sha1_init(struct sha1_context *ctx); /* Initialize new algorithm run in the @ctx context. **/
+/*
+ * Push another @len bytes of data pointed to by @buf onto the SHA1 hash
+ * currently in @ctx. You can call this any times you want on the same hash (and
+ * you do not need to reinitialize it by @sha1_init()). It has the same effect
+ * as concatenating all the data together and passing them at once.
+ */
+void sha1_update(struct sha1_context *ctx, const byte *buf, uint len);
+/*
+ * No more @sha1_update() calls will be done. This terminates the hash and
+ * returns a pointer to it.
+ *
+ * Note that the pointer points into data in the @ctx context. If it ceases to
+ * exist, the pointer becomes invalid.
+ */
+byte *sha1_final(struct sha1_context *ctx);
+
+/*
+ * A convenience one-shot function for SHA1 hash. It is equivalent to this
+ * snippet of code:
+ *
+ *  sha1_context ctx;
+ *  sha1_init(&ctx);
+ *  sha1_update(&ctx, buffer, length);
+ *  memcpy(outbuf, sha1_final(&ctx), SHA1_SIZE);
+ */
+void sha1_hash_buffer(byte *outbuf, const byte *buffer, uint length);
+
+/*
+ * SHA1 HMAC message authentication. If you provide @key and @data, the result
+ * will be stored in @outbuf.
+ */
+void sha1_hmac(byte *outbuf, const byte *key, uint keylen, const byte *data, uint datalen);
+
+/*
+ * The HMAC also exists in a stream version in a way analogous to the plain
+ * SHA1. Pass this as a context.
+ */
+struct sha1_hmac_context {
+  struct sha1_context ictx;
+  struct sha1_context octx;
+};
+
+void sha1_hmac_init(struct sha1_hmac_context *ctx, const byte *key, uint keylen);	/* Initialize HMAC with context @ctx and the given key. See sha1_init(). */
+void sha1_hmac_update(struct sha1_hmac_context *ctx, const byte *data, uint datalen);	/* Hash another @datalen bytes of data. See sha1_update(). */
+byte *sha1_hmac_final(struct sha1_hmac_context *ctx);					/* Terminate the HMAC and return a pointer to the allocated hash. See sha1_final(). */
+
+
+#endif /* _BIRD_SHA1_H_ */
diff --git a/lib/sha256.c b/lib/sha256.c
new file mode 100644
index 00000000..440245d5
--- /dev/null
+++ b/lib/sha256.c
@@ -0,0 +1,449 @@
+/*
+ *	BIRD Library -- SHA-256 and SHA-224 Hash Functions,
+ *			HMAC-SHA-256 and HMAC-SHA-224 Functions
+ *
+ *	(c) 2015 CZ.NIC z.s.p.o.
+ *
+ *	Based on the code from libgcrypt-1.6.0, which is
+ *	(c) 2003, 2006, 2008, 2009 Free Software Foundation, Inc.
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
+ */
+
+#include "lib/sha256.h"
+#include "lib/unaligned.h"
+
+
+// #define SHA256_UNROLLED
+
+void
+sha256_init(struct sha256_context *ctx)
+{
+  ctx->h0 = 0x6a09e667;
+  ctx->h1 = 0xbb67ae85;
+  ctx->h2 = 0x3c6ef372;
+  ctx->h3 = 0xa54ff53a;
+  ctx->h4 = 0x510e527f;
+  ctx->h5 = 0x9b05688c;
+  ctx->h6 = 0x1f83d9ab;
+  ctx->h7 = 0x5be0cd19;
+
+  ctx->nblocks = 0;
+  ctx->count = 0;
+}
+
+void
+sha224_init(struct sha224_context *ctx)
+{
+  ctx->h0 = 0xc1059ed8;
+  ctx->h1 = 0x367cd507;
+  ctx->h2 = 0x3070dd17;
+  ctx->h3 = 0xf70e5939;
+  ctx->h4 = 0xffc00b31;
+  ctx->h5 = 0x68581511;
+  ctx->h6 = 0x64f98fa7;
+  ctx->h7 = 0xbefa4fa4;
+
+  ctx->nblocks = 0;
+  ctx->count = 0;
+}
+
+/* (4.2) same as SHA-1's F1.  */
+static inline u32
+f1(u32 x, u32 y, u32 z)
+{
+  return (z ^ (x & (y ^ z)));
+}
+
+/* (4.3) same as SHA-1's F3 */
+static inline u32
+f3(u32 x, u32 y, u32 z)
+{
+  return ((x & y) | (z & (x|y)));
+}
+
+/* Bitwise rotation of an uint to the right */
+static inline u32 ror(u32 x, int n)
+{
+  return ((x >> (n&(32-1))) | (x << ((32-n)&(32-1))));
+}
+
+/* (4.4) */
+static inline u32
+sum0(u32 x)
+{
+  return (ror(x, 2) ^ ror(x, 13) ^ ror(x, 22));
+}
+
+/* (4.5) */
+static inline u32
+sum1(u32 x)
+{
+  return (ror(x, 6) ^ ror(x, 11) ^ ror(x, 25));
+}
+
+/*
+  Transform the message X which consists of 16 32-bit-words. See FIPS
+  180-2 for details.  */
+#define S0(x) (ror((x),  7) ^ ror((x), 18) ^ ((x) >>  3))	/* (4.6) */
+#define S1(x) (ror((x), 17) ^ ror((x), 19) ^ ((x) >> 10))	/* (4.7) */
+#define R(a,b,c,d,e,f,g,h,k,w)					\
+    do								\
+    {								\
+      t1 = (h) + sum1((e)) + f1((e),(f),(g)) + (k) + (w);	\
+      t2 = sum0((a)) + f3((a),(b),(c));				\
+      h = g;							\
+      g = f;							\
+      f = e;							\
+      e = d + t1;						\
+      d = c;							\
+      c = b;							\
+      b = a;							\
+      a = t1 + t2;						\
+    } while (0)
+
+/*
+    The SHA-256 core: Transform the message X which consists of 16
+    32-bit-words. See FIPS 180-2 for details.
+ */
+static uint
+sha256_transform(struct sha256_context *ctx, const byte *data)
+{
+  static const u32 K[64] = {
+      0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5,
+      0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
+      0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+      0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
+      0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc,
+      0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+      0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7,
+      0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
+      0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+      0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
+      0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3,
+      0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+      0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5,
+      0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
+      0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+      0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+  };
+
+  u32 a,b,c,d,e,f,g,h,t1,t2;
+  u32 w[64];
+  int i;
+
+  a = ctx->h0;
+  b = ctx->h1;
+  c = ctx->h2;
+  d = ctx->h3;
+  e = ctx->h4;
+  f = ctx->h5;
+  g = ctx->h6;
+  h = ctx->h7;
+
+  for (i = 0; i < 16; i++)
+    w[i] = get_u32(data + i * 4);
+
+  for (; i < 64; i++)
+    w[i] = S1(w[i-2]) + w[i-7] + S0(w[i-15]) + w[i-16];
+
+  for (i = 0; i < 64;)
+  {
+#ifndef SHA256_UNROLLED
+    R(a,b,c,d,e,f,g,h,K[i],w[i]);
+    i++;
+#else /* Unrolled */
+    t1 = h + sum1(e) + f1(e, f, g) + K[i] + w[i];
+    t2 = sum0(a) + f3(a, b, c);
+    d += t1;
+    h  = t1 + t2;
+
+    t1 = g + sum1(d) + f1(d, e, f) + K[i+1] + w[i+1];
+    t2 = sum0(h) + f3(h, a, b);
+    c += t1;
+    g  = t1 + t2;
+
+    t1 = f + sum1(c) + f1(c, d, e) + K[i+2] + w[i+2];
+    t2 = sum0(g) + f3(g, h, a);
+    b += t1;
+    f  = t1 + t2;
+
+    t1 = e + sum1(b) + f1(b, c, d) + K[i+3] + w[i+3];
+    t2 = sum0(f) + f3(f, g, h);
+    a += t1;
+    e  = t1 + t2;
+
+    t1 = d + sum1(a) + f1(a, b, c) + K[i+4] + w[i+4];
+    t2 = sum0(e) + f3(e, f, g);
+    h += t1;
+    d  = t1 + t2;
+
+    t1 = c + sum1(h) + f1(h, a, b) + K[i+5] + w[i+5];
+    t2 = sum0(d) + f3(d, e, f);
+    g += t1;
+    c  = t1 + t2;
+
+    t1 = b + sum1(g) + f1(g, h, a) + K[i+6] + w[i+6];
+    t2 = sum0(c) + f3(c, d, e);
+    f += t1;
+    b  = t1 + t2;
+
+    t1 = a + sum1(f) + f1(f, g, h) + K[i+7] + w[i+7];
+    t2 = sum0(b) + f3(b, c, d);
+    e += t1;
+    a  = t1 + t2;
+
+    i += 8;
+#endif
+  }
+
+  ctx->h0 += a;
+  ctx->h1 += b;
+  ctx->h2 += c;
+  ctx->h3 += d;
+  ctx->h4 += e;
+  ctx->h5 += f;
+  ctx->h6 += g;
+  ctx->h7 += h;
+
+  return /*burn_stack*/ 74*4+32;
+}
+#undef S0
+#undef S1
+#undef R
+
+/* Common function to write a chunk of data to the transform function
+   of a hash algorithm.  Note that the use of the term "block" does
+   not imply a fixed size block.  Note that we explicitly allow to use
+   this function after the context has been finalized; the result does
+   not have any meaning but writing after finalize is sometimes
+   helpful to mitigate timing attacks. */
+void
+sha256_update(struct sha256_context *ctx, const byte *buf, size_t len)
+{
+  if (ctx->count)
+  {
+    /* Fill rest of internal buffer */
+    for (; len && ctx->count < SHA256_BLOCK_SIZE; len--)
+      ctx->buf[ctx->count++] = *buf++;
+
+    if (ctx->count < SHA256_BLOCK_SIZE)
+      return;
+
+    /* Process data from internal buffer */
+    sha256_transform(ctx, ctx->buf);
+    ctx->nblocks++;
+    ctx->count = 0;
+  }
+
+  if (!len)
+    return;
+
+  /* Process data from input buffer */
+  while (len >= SHA256_BLOCK_SIZE)
+  {
+    sha256_transform(ctx, buf);
+    ctx->nblocks++;
+    buf += SHA256_BLOCK_SIZE;
+    len -= SHA256_BLOCK_SIZE;
+  }
+
+  /* Copy remaining data to internal buffer */
+  memcpy(ctx->buf, buf, len);
+  ctx->count = len;
+}
+
+/*
+ * The routine finally terminates the computation and returns the digest.  The
+ * handle is prepared for a new cycle, but adding bytes to the handle will the
+ * destroy the returned buffer.
+ *
+ * Returns: 32 bytes with the message the digest. 28 bytes for SHA-224.
+ */
+byte *
+sha256_final(struct sha256_context *ctx)
+{
+  u32 t, th, msb, lsb;
+
+  sha256_update(ctx, NULL, 0);	/* flush */
+
+  t = ctx->nblocks;
+  th = 0;
+
+  /* multiply by 64 to make a byte count */
+  lsb = t << 6;
+  msb = (th << 6) | (t >> 26);
+  /* add the count */
+  t = lsb;
+  if ((lsb += ctx->count) < t)
+    msb++;
+  /* multiply by 8 to make a bit count */
+  t = lsb;
+  lsb <<= 3;
+  msb <<= 3;
+  msb |= t >> 29;
+
+  if (ctx->count < 56)
+  {
+    /* enough room */
+    ctx->buf[ctx->count++] = 0x80; /* pad */
+    while (ctx->count < 56)
+      ctx->buf[ctx->count++] = 0;  /* pad */
+  }
+  else
+  {
+    /* need one extra block */
+    ctx->buf[ctx->count++] = 0x80; /* pad character */
+    while (ctx->count < 64)
+      ctx->buf[ctx->count++] = 0;
+    sha256_update(ctx, NULL, 0);  /* flush */;
+    memset(ctx->buf, 0, 56 ); /* fill next block with zeroes */
+  }
+
+  /* append the 64 bit count */
+  put_u32(ctx->buf + 56, msb);
+  put_u32(ctx->buf + 60, lsb);
+  sha256_transform(ctx, ctx->buf);
+
+  byte *p = ctx->buf;
+#define X(a) do { put_u32(p, ctx->h##a); p += 4; } while(0)
+  X(0);
+  X(1);
+  X(2);
+  X(3);
+  X(4);
+  X(5);
+  X(6);
+  X(7);
+#undef X
+
+  return ctx->buf;
+}
+
+
+/*
+ *	SHA256-HMAC
+ */
+
+static void
+sha256_hash_buffer(byte *outbuf, const byte *buffer, size_t length)
+{
+  struct sha256_context ctx;
+
+  sha256_init(&ctx);
+  sha256_update(&ctx, buffer, length);
+  memcpy(outbuf, sha256_final(&ctx), SHA256_SIZE);
+}
+
+void
+sha256_hmac_init(struct sha256_hmac_context *ctx, const byte *key, size_t keylen)
+{
+  byte keybuf[SHA256_BLOCK_SIZE], buf[SHA256_BLOCK_SIZE];
+
+  /* Hash the key if necessary */
+  if (keylen <= SHA256_BLOCK_SIZE)
+  {
+    memcpy(keybuf, key, keylen);
+    memset(keybuf + keylen, 0, SHA256_BLOCK_SIZE - keylen);
+  }
+  else
+  {
+    sha256_hash_buffer(keybuf, key, keylen);
+    memset(keybuf + SHA256_SIZE, 0, SHA256_BLOCK_SIZE - SHA256_SIZE);
+  }
+
+  /* Initialize the inner digest */
+  sha256_init(&ctx->ictx);
+  int i;
+  for (i = 0; i < SHA256_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x36;
+  sha256_update(&ctx->ictx, buf, SHA256_BLOCK_SIZE);
+
+  /* Initialize the outer digest */
+  sha256_init(&ctx->octx);
+  for (i = 0; i < SHA256_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x5c;
+  sha256_update(&ctx->octx, buf, SHA256_BLOCK_SIZE);
+}
+
+void
+sha256_hmac_update(struct sha256_hmac_context *ctx, const byte *buf, size_t buflen)
+{
+  /* Just update the inner digest */
+  sha256_update(&ctx->ictx, buf, buflen);
+}
+
+byte *
+sha256_hmac_final(struct sha256_hmac_context *ctx)
+{
+  /* Finish the inner digest */
+  byte *isha = sha256_final(&ctx->ictx);
+
+  /* Finish the outer digest */
+  sha256_update(&ctx->octx, isha, SHA256_SIZE);
+  return sha256_final(&ctx->octx);
+}
+
+
+/*
+ *	SHA224-HMAC
+ */
+
+static void
+sha224_hash_buffer(byte *outbuf, const byte *buffer, size_t length)
+{
+  struct sha224_context ctx;
+
+  sha224_init(&ctx);
+  sha224_update(&ctx, buffer, length);
+  memcpy(outbuf, sha224_final(&ctx), SHA224_SIZE);
+}
+
+void
+sha224_hmac_init(struct sha224_hmac_context *ctx, const byte *key, size_t keylen)
+{
+  byte keybuf[SHA224_BLOCK_SIZE], buf[SHA224_BLOCK_SIZE];
+
+  /* Hash the key if necessary */
+  if (keylen <= SHA224_BLOCK_SIZE)
+  {
+    memcpy(keybuf, key, keylen);
+    memset(keybuf + keylen, 0, SHA224_BLOCK_SIZE - keylen);
+  }
+  else
+  {
+    sha224_hash_buffer(keybuf, key, keylen);
+    memset(keybuf + SHA224_SIZE, 0, SHA224_BLOCK_SIZE - SHA224_SIZE);
+  }
+
+  /* Initialize the inner digest */
+  sha224_init(&ctx->ictx);
+  int i;
+  for (i = 0; i < SHA224_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x36;
+  sha224_update(&ctx->ictx, buf, SHA224_BLOCK_SIZE);
+
+  /* Initialize the outer digest */
+  sha224_init(&ctx->octx);
+  for (i = 0; i < SHA224_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x5c;
+  sha224_update(&ctx->octx, buf, SHA224_BLOCK_SIZE);
+}
+
+void
+sha224_hmac_update(struct sha224_hmac_context *ctx, const byte *buf, size_t buflen)
+{
+  /* Just update the inner digest */
+  sha256_update(&ctx->ictx, buf, buflen);
+}
+
+byte *
+sha224_hmac_final(struct sha224_hmac_context *ctx)
+{
+  /* Finish the inner digest */
+  byte *isha = sha224_final(&ctx->ictx);
+
+  /* Finish the outer digest */
+  sha224_update(&ctx->octx, isha, SHA224_SIZE);
+  return sha224_final(&ctx->octx);
+}
diff --git a/lib/sha256.h b/lib/sha256.h
new file mode 100644
index 00000000..381200a9
--- /dev/null
+++ b/lib/sha256.h
@@ -0,0 +1,73 @@
+/*
+ *	BIRD Library -- SHA-256 and SHA-224 Hash Functions,
+ *			HMAC-SHA-256 and HMAC-SHA-224 Functions
+ *
+ *	(c) 2015 CZ.NIC z.s.p.o.
+ *
+ *	Based on the code from libgcrypt-1.6.0, which is
+ *	(c) 2003, 2006, 2008, 2009 Free Software Foundation, Inc.
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
+ */
+
+#ifndef _BIRD_SHA256_H_
+#define _BIRD_SHA256_H_
+
+#include "nest/bird.h"
+
+
+#define SHA224_SIZE 		28
+#define SHA224_HEX_SIZE		57
+#define SHA224_BLOCK_SIZE 	64
+
+#define SHA256_SIZE 		32
+#define SHA256_HEX_SIZE		65
+#define SHA256_BLOCK_SIZE 	64
+
+
+struct sha256_context {
+  u32  h0, h1, h2, h3, h4, h5, h6, h7;
+  byte buf[SHA256_BLOCK_SIZE];
+  uint nblocks;
+  uint count;
+};
+
+#define sha224_context sha256_context
+
+
+void sha256_init(struct sha256_context *ctx);
+void sha224_init(struct sha224_context *ctx);
+
+void sha256_update(struct sha256_context *ctx, const byte *buf, size_t len);
+static inline void sha224_update(struct sha224_context *ctx, const byte *buf, size_t len)
+{ sha256_update(ctx, buf, len); }
+
+byte *sha256_final(struct sha256_context *ctx);
+static inline byte *sha224_final(struct sha224_context *ctx)
+{ return sha256_final(ctx); }
+
+
+/*
+ *	HMAC-SHA256, HMAC-SHA224
+ */
+
+struct sha256_hmac_context
+{
+  struct sha256_context ictx;
+  struct sha256_context octx;
+};
+
+#define sha224_hmac_context sha256_hmac_context
+
+
+void sha256_hmac_init(struct sha256_hmac_context *ctx, const byte *key, size_t keylen);
+void sha224_hmac_init(struct sha224_hmac_context *ctx, const byte *key, size_t keylen);
+
+void sha256_hmac_update(struct sha256_hmac_context *ctx, const byte *buf, size_t buflen);
+void sha224_hmac_update(struct sha224_hmac_context *ctx, const byte *buf, size_t buflen);
+
+byte *sha256_hmac_final(struct sha256_hmac_context *ctx);
+byte *sha224_hmac_final(struct sha224_hmac_context *ctx);
+
+
+#endif /* _BIRD_SHA256_H_ */
diff --git a/lib/sha512.c b/lib/sha512.c
new file mode 100644
index 00000000..37e660f7
--- /dev/null
+++ b/lib/sha512.c
@@ -0,0 +1,620 @@
+/*
+ *	BIRD Library -- SHA-512 and SHA-384 Hash Functions,
+ *			HMAC-SHA-512 and HMAC-SHA-384 Functions
+ *
+ *	(c) 2015 CZ.NIC z.s.p.o.
+ *
+ *	Based on the code from libgcrypt-1.6.0, which is
+ *	(c) 2003, 2006, 2008, 2009 Free Software Foundation, Inc.
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
+ */
+
+#include "lib/sha512.h"
+#include "lib/unaligned.h"
+
+
+// #define SHA512_UNROLLED
+
+void
+sha512_init(struct sha512_context *ctx)
+{
+  ctx->h0 = U64(0x6a09e667f3bcc908);
+  ctx->h1 = U64(0xbb67ae8584caa73b);
+  ctx->h2 = U64(0x3c6ef372fe94f82b);
+  ctx->h3 = U64(0xa54ff53a5f1d36f1);
+  ctx->h4 = U64(0x510e527fade682d1);
+  ctx->h5 = U64(0x9b05688c2b3e6c1f);
+  ctx->h6 = U64(0x1f83d9abfb41bd6b);
+  ctx->h7 = U64(0x5be0cd19137e2179);
+
+  ctx->nblocks = 0;
+  ctx->count = 0;
+}
+
+void
+sha384_init(struct sha384_context *ctx)
+{
+  ctx->h0 = U64(0xcbbb9d5dc1059ed8);
+  ctx->h1 = U64(0x629a292a367cd507);
+  ctx->h2 = U64(0x9159015a3070dd17);
+  ctx->h3 = U64(0x152fecd8f70e5939);
+  ctx->h4 = U64(0x67332667ffc00b31);
+  ctx->h5 = U64(0x8eb44a8768581511);
+  ctx->h6 = U64(0xdb0c2e0d64f98fa7);
+  ctx->h7 = U64(0x47b5481dbefa4fa4);
+
+  ctx->nblocks = 0;
+  ctx->count = 0;
+}
+
+static inline u64
+ROTR(u64 x, u64 n)
+{
+  return ((x >> n) | (x << (64 - n)));
+}
+
+static inline u64
+Ch(u64 x, u64 y, u64 z)
+{
+  return ((x & y) ^ ( ~x & z));
+}
+
+static inline u64
+Maj(u64 x, u64 y, u64 z)
+{
+  return ((x & y) ^ (x & z) ^ (y & z));
+}
+
+static inline u64
+sum0(u64 x)
+{
+  return (ROTR(x, 28) ^ ROTR(x, 34) ^ ROTR(x, 39));
+}
+
+static inline u64
+sum1(u64 x)
+{
+  return (ROTR(x, 14) ^ ROTR(x, 18) ^ ROTR(x, 41));
+}
+
+static const u64 k[] =
+{
+    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)
+};
+
+/*
+ * Transform the message W which consists of 16 64-bit-words
+ */
+static uint
+sha512_transform(struct sha512_context *ctx, const byte *data)
+{
+  u64 a, b, c, d, e, f, g, h;
+  u64 w[16];
+  uint t;
+
+  /* get values from the chaining vars */
+  a = ctx->h0;
+  b = ctx->h1;
+  c = ctx->h2;
+  d = ctx->h3;
+  e = ctx->h4;
+  f = ctx->h5;
+  g = ctx->h6;
+  h = ctx->h7;
+
+  for (t = 0; t < 16; t++)
+    w[t] = get_u64(data + t * 8);
+
+#define S0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
+#define S1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+
+  for (t = 0; t < 80 - 16; )
+  {
+    u64 t1, t2;
+
+    /* Performance on a AMD Athlon(tm) Dual Core Processor 4050e
+         with gcc 4.3.3 using gcry_md_hash_buffer of each 10000 bytes
+         initialized to 0,1,2,3...255,0,... and 1000 iterations:
+
+         Not unrolled with macros:  440ms
+         Unrolled with macros:      350ms
+         Unrolled with inline:      330ms
+     */
+#ifndef SHA512_UNROLLED
+    t1 = h + sum1(e) + Ch(e, f, g) + k[t] + w[t%16];
+    w[t%16] += S1(w[(t - 2)%16]) + w[(t - 7)%16] + S0(w[(t - 15)%16]);
+    t2 = sum0(a) + Maj(a, b, c);
+    h = g;
+    g = f;
+    f = e;
+    e = d + t1;
+    d = c;
+    c = b;
+    b = a;
+    a = t1 + t2;
+    t++;
+#else /* Unrolled */
+    t1 = h + sum1(e) + Ch(e, f, g) + k[t] + w[0];
+    w[0] += S1(w[14]) + w[9] + S0(w[1]);
+    t2 = sum0(a) + Maj(a, b, c);
+    d += t1;
+    h = t1 + t2;
+
+    t1 = g + sum1(d) + Ch(d, e, f) + k[t+1] + w[1];
+    w[1] += S1(w[15]) + w[10] + S0(w[2]);
+    t2 = sum0(h) + Maj(h, a, b);
+    c += t1;
+    g  = t1 + t2;
+
+    t1 = f + sum1(c) + Ch(c, d, e) + k[t+2] + w[2];
+    w[2] += S1(w[0]) + w[11] + S0(w[3]);
+    t2 = sum0(g) + Maj(g, h, a);
+    b += t1;
+    f  = t1 + t2;
+
+    t1 = e + sum1(b) + Ch(b, c, d) + k[t+3] + w[3];
+    w[3] += S1(w[1]) + w[12] + S0(w[4]);
+    t2 = sum0(f) + Maj(f, g, h);
+    a += t1;
+    e  = t1 + t2;
+
+    t1 = d + sum1(a) + Ch(a, b, c) + k[t+4] + w[4];
+    w[4] += S1(w[2]) + w[13] + S0(w[5]);
+    t2 = sum0(e) + Maj(e, f, g);
+    h += t1;
+    d  = t1 + t2;
+
+    t1 = c + sum1(h) + Ch(h, a, b) + k[t+5] + w[5];
+    w[5] += S1(w[3]) + w[14] + S0(w[6]);
+    t2 = sum0(d) + Maj(d, e, f);
+    g += t1;
+    c  = t1 + t2;
+
+    t1 = b + sum1(g) + Ch(g, h, a) + k[t+6] + w[6];
+    w[6] += S1(w[4]) + w[15] + S0(w[7]);
+    t2 = sum0(c) + Maj(c, d, e);
+    f += t1;
+    b  = t1 + t2;
+
+    t1 = a + sum1(f) + Ch(f, g, h) + k[t+7] + w[7];
+    w[7] += S1(w[5]) + w[0] + S0(w[8]);
+    t2 = sum0(b) + Maj(b, c, d);
+    e += t1;
+    a  = t1 + t2;
+
+    t1 = h + sum1(e) + Ch(e, f, g) + k[t+8] + w[8];
+    w[8] += S1(w[6]) + w[1] + S0(w[9]);
+    t2 = sum0(a) + Maj(a, b, c);
+    d += t1;
+    h  = t1 + t2;
+
+    t1 = g + sum1(d) + Ch(d, e, f) + k[t+9] + w[9];
+    w[9] += S1(w[7]) + w[2] + S0(w[10]);
+    t2 = sum0(h) + Maj(h, a, b);
+    c += t1;
+    g  = t1 + t2;
+
+    t1 = f + sum1(c) + Ch(c, d, e) + k[t+10] + w[10];
+    w[10] += S1(w[8]) + w[3] + S0(w[11]);
+    t2 = sum0(g) + Maj(g, h, a);
+    b += t1;
+    f  = t1 + t2;
+
+    t1 = e + sum1(b) + Ch(b, c, d) + k[t+11] + w[11];
+    w[11] += S1(w[9]) + w[4] + S0(w[12]);
+    t2 = sum0(f) + Maj(f, g, h);
+    a += t1;
+    e  = t1 + t2;
+
+    t1 = d + sum1(a) + Ch(a, b, c) + k[t+12] + w[12];
+    w[12] += S1(w[10]) + w[5] + S0(w[13]);
+    t2 = sum0(e) + Maj(e, f, g);
+    h += t1;
+    d  = t1 + t2;
+
+    t1 = c + sum1(h) + Ch(h, a, b) + k[t+13] + w[13];
+    w[13] += S1(w[11]) + w[6] + S0(w[14]);
+    t2 = sum0(d) + Maj(d, e, f);
+    g += t1;
+    c  = t1 + t2;
+
+    t1 = b + sum1(g) + Ch(g, h, a) + k[t+14] + w[14];
+    w[14] += S1(w[12]) + w[7] + S0(w[15]);
+    t2 = sum0(c) + Maj(c, d, e);
+    f += t1;
+    b  = t1 + t2;
+
+    t1 = a + sum1(f) + Ch(f, g, h) + k[t+15] + w[15];
+    w[15] += S1(w[13]) + w[8] + S0(w[0]);
+    t2 = sum0(b) + Maj(b, c, d);
+    e += t1;
+    a  = t1 + t2;
+
+    t += 16;
+#endif
+  }
+
+  for (; t < 80; )
+  {
+    u64 t1, t2;
+
+#ifndef SHA512_UNROLLED
+    t1 = h + sum1(e) + Ch(e, f, g) + k[t] + w[t%16];
+    t2 = sum0(a) + Maj(a, b, c);
+    h = g;
+    g = f;
+    f = e;
+    e = d + t1;
+    d = c;
+    c = b;
+    b = a;
+    a = t1 + t2;
+    t++;
+#else /* Unrolled */
+    t1 = h + sum1(e) + Ch(e, f, g) + k[t] + w[0];
+    t2 = sum0(a) + Maj(a, b, c);
+    d += t1;
+    h  = t1 + t2;
+
+    t1 = g + sum1(d) + Ch(d, e, f) + k[t+1] + w[1];
+    t2 = sum0(h) + Maj(h, a, b);
+    c += t1;
+    g  = t1 + t2;
+
+    t1 = f + sum1(c) + Ch(c, d, e) + k[t+2] + w[2];
+    t2 = sum0(g) + Maj(g, h, a);
+    b += t1;
+    f  = t1 + t2;
+
+    t1 = e + sum1(b) + Ch(b, c, d) + k[t+3] + w[3];
+    t2 = sum0(f) + Maj(f, g, h);
+    a += t1;
+    e  = t1 + t2;
+
+    t1 = d + sum1(a) + Ch(a, b, c) + k[t+4] + w[4];
+    t2 = sum0(e) + Maj(e, f, g);
+    h += t1;
+    d  = t1 + t2;
+
+    t1 = c + sum1(h) + Ch(h, a, b) + k[t+5] + w[5];
+    t2 = sum0(d) + Maj(d, e, f);
+    g += t1;
+    c  = t1 + t2;
+
+    t1 = b + sum1(g) + Ch(g, h, a) + k[t+6] + w[6];
+    t2 = sum0(c) + Maj(c, d, e);
+    f += t1;
+    b  = t1 + t2;
+
+    t1 = a + sum1(f) + Ch(f, g, h) + k[t+7] + w[7];
+    t2 = sum0(b) + Maj(b, c, d);
+    e += t1;
+    a  = t1 + t2;
+
+    t1 = h + sum1(e) + Ch(e, f, g) + k[t+8] + w[8];
+    t2 = sum0(a) + Maj(a, b, c);
+    d += t1;
+    h  = t1 + t2;
+
+    t1 = g + sum1(d) + Ch(d, e, f) + k[t+9] + w[9];
+    t2 = sum0(h) + Maj(h, a, b);
+    c += t1;
+    g  = t1 + t2;
+
+    t1 = f + sum1(c) + Ch(c, d, e) + k[t+10] + w[10];
+    t2 = sum0(g) + Maj(g, h, a);
+    b += t1;
+    f  = t1 + t2;
+
+    t1 = e + sum1(b) + Ch(b, c, d) + k[t+11] + w[11];
+    t2 = sum0(f) + Maj(f, g, h);
+    a += t1;
+    e  = t1 + t2;
+
+    t1 = d + sum1(a) + Ch(a, b, c) + k[t+12] + w[12];
+    t2 = sum0(e) + Maj(e, f, g);
+    h += t1;
+    d  = t1 + t2;
+
+    t1 = c + sum1(h) + Ch(h, a, b) + k[t+13] + w[13];
+    t2 = sum0(d) + Maj(d, e, f);
+    g += t1;
+    c  = t1 + t2;
+
+    t1 = b + sum1(g) + Ch(g, h, a) + k[t+14] + w[14];
+    t2 = sum0(c) + Maj(c, d, e);
+    f += t1;
+    b  = t1 + t2;
+
+    t1 = a + sum1(f) + Ch(f, g, h) + k[t+15] + w[15];
+    t2 = sum0(b) + Maj(b, c, d);
+    e += t1;
+    a  = t1 + t2;
+
+    t += 16;
+#endif
+  }
+
+  /* Update chaining vars.  */
+  ctx->h0 += a;
+  ctx->h1 += b;
+  ctx->h2 += c;
+  ctx->h3 += d;
+  ctx->h4 += e;
+  ctx->h5 += f;
+  ctx->h6 += g;
+  ctx->h7 += h;
+
+  return /* burn_stack */ (8 + 16) * sizeof(u64) + sizeof(u32) + 3 * sizeof(void*);
+}
+
+void
+sha512_update(struct sha512_context *ctx, const byte *buf, size_t len)
+{
+  if (ctx->count)
+  {
+    /* Fill rest of internal buffer */
+    for (; len && ctx->count < SHA512_BLOCK_SIZE; len--)
+      ctx->buf[ctx->count++] = *buf++;
+
+    if (ctx->count < SHA512_BLOCK_SIZE)
+      return;
+
+    /* Process data from internal buffer */
+    sha512_transform(ctx, ctx->buf);
+    ctx->nblocks++;
+    ctx->count = 0;
+  }
+
+  if (!len)
+    return;
+
+  /* Process data from input buffer */
+  while (len >= SHA512_BLOCK_SIZE)
+  {
+    sha512_transform(ctx, buf);
+    ctx->nblocks++;
+    buf += SHA512_BLOCK_SIZE;
+    len -= SHA512_BLOCK_SIZE;
+  }
+
+  /* Copy remaining data to internal buffer */
+  memcpy(ctx->buf, buf, len);
+  ctx->count = len;
+}
+
+/*
+ * The routine final terminates the computation and returns the digest. The
+ * handle is prepared for a new cycle, but adding bytes to the handle will the
+ * destroy the returned buffer.
+ *
+ * Returns: 64 bytes representing the digest. When used for sha384, we take the
+ * first 48 of those bytes.
+ */
+byte *
+sha512_final(struct sha512_context *ctx)
+{
+  u64 t, th, msb, lsb;
+
+  sha512_update(ctx, NULL, 0);	/* flush */
+
+  t = ctx->nblocks;
+  th = 0;
+
+  /* multiply by 128 to make a byte count */
+  lsb = t << 7;
+  msb = (th << 7) | (t >> 57);
+  /* add the count */
+  t = lsb;
+  if ((lsb += ctx->count) < t)
+    msb++;
+  /* multiply by 8 to make a bit count */
+  t = lsb;
+  lsb <<= 3;
+  msb <<= 3;
+  msb |= t >> 61;
+
+  if (ctx->count < 112)
+  {
+    /* enough room */
+    ctx->buf[ctx->count++] = 0x80;	/* pad */
+    while(ctx->count < 112)
+      ctx->buf[ctx->count++] = 0;	/* pad */
+  }
+  else
+  {
+    /* need one extra block */
+    ctx->buf[ctx->count++] = 0x80;	/* pad character */
+    while(ctx->count < 128)
+      ctx->buf[ctx->count++] = 0;
+    sha512_update(ctx, NULL, 0); 	/* flush */
+    memset(ctx->buf, 0, 112);		/* fill next block with zeroes */
+  }
+
+  /* append the 128 bit count */
+  put_u64(ctx->buf + 112, msb);
+  put_u64(ctx->buf + 120, lsb);
+  sha512_transform(ctx, ctx->buf);
+
+  byte *p = ctx->buf;
+#define X(a) do { put_u64(p, ctx->h##a); p += 8; } while(0)
+  X(0);
+  X(1);
+  X(2);
+  X(3);
+  X(4);
+  X(5);
+  X(6);
+  X(7);
+#undef X
+
+  return ctx->buf;
+}
+
+
+/*
+ *	SHA512-HMAC
+ */
+
+static void
+sha512_hash_buffer(byte *outbuf, const byte *buffer, size_t length)
+{
+  struct sha512_context ctx;
+
+  sha512_init(&ctx);
+  sha512_update(&ctx, buffer, length);
+  memcpy(outbuf, sha512_final(&ctx), SHA512_SIZE);
+}
+
+void
+sha512_hmac_init(struct sha512_hmac_context *ctx, const byte *key, size_t keylen)
+{
+  byte keybuf[SHA512_BLOCK_SIZE], buf[SHA512_BLOCK_SIZE];
+
+  /* Hash the key if necessary */
+  if (keylen <= SHA512_BLOCK_SIZE)
+  {
+    memcpy(keybuf, key, keylen);
+    memset(keybuf + keylen, 0, SHA512_BLOCK_SIZE - keylen);
+  }
+  else
+  {
+    sha512_hash_buffer(keybuf, key, keylen);
+    memset(keybuf + SHA512_SIZE, 0, SHA512_BLOCK_SIZE - SHA512_SIZE);
+  }
+
+  /* Initialize the inner digest */
+  sha512_init(&ctx->ictx);
+  int i;
+  for (i = 0; i < SHA512_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x36;
+  sha512_update(&ctx->ictx, buf, SHA512_BLOCK_SIZE);
+
+  /* Initialize the outer digest */
+  sha512_init(&ctx->octx);
+  for (i = 0; i < SHA512_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x5c;
+  sha512_update(&ctx->octx, buf, SHA512_BLOCK_SIZE);
+}
+
+void
+sha512_hmac_update(struct sha512_hmac_context *ctx, const byte *buf, size_t buflen)
+{
+  /* Just update the inner digest */
+  sha512_update(&ctx->ictx, buf, buflen);
+}
+
+byte *
+sha512_hmac_final(struct sha512_hmac_context *ctx)
+{
+  /* Finish the inner digest */
+  byte *isha = sha512_final(&ctx->ictx);
+
+  /* Finish the outer digest */
+  sha512_update(&ctx->octx, isha, SHA512_SIZE);
+  return sha512_final(&ctx->octx);
+}
+
+
+/*
+ *	SHA384-HMAC
+ */
+
+static void
+sha384_hash_buffer(byte *outbuf, const byte *buffer, size_t length)
+{
+  struct sha384_context ctx;
+
+  sha384_init(&ctx);
+  sha384_update(&ctx, buffer, length);
+  memcpy(outbuf, sha384_final(&ctx), SHA384_SIZE);
+}
+
+void
+sha384_hmac_init(struct sha384_hmac_context *ctx, const byte *key, size_t keylen)
+{
+  byte keybuf[SHA384_BLOCK_SIZE], buf[SHA384_BLOCK_SIZE];
+
+  /* Hash the key if necessary */
+  if (keylen <= SHA384_BLOCK_SIZE)
+  {
+    memcpy(keybuf, key, keylen);
+    memset(keybuf + keylen, 0, SHA384_BLOCK_SIZE - keylen);
+  }
+  else
+  {
+    sha384_hash_buffer(keybuf, key, keylen);
+    memset(keybuf + SHA384_SIZE, 0, SHA384_BLOCK_SIZE - SHA384_SIZE);
+  }
+
+  /* Initialize the inner digest */
+  sha384_init(&ctx->ictx);
+  int i;
+  for (i = 0; i < SHA384_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x36;
+  sha384_update(&ctx->ictx, buf, SHA384_BLOCK_SIZE);
+
+  /* Initialize the outer digest */
+  sha384_init(&ctx->octx);
+  for (i = 0; i < SHA384_BLOCK_SIZE; i++)
+    buf[i] = keybuf[i] ^ 0x5c;
+  sha384_update(&ctx->octx, buf, SHA384_BLOCK_SIZE);
+}
+
+void
+sha384_hmac_update(struct sha384_hmac_context *ctx, const byte *buf, size_t buflen)
+{
+  /* Just update the inner digest */
+  sha384_update(&ctx->ictx, buf, buflen);
+}
+
+byte *
+sha384_hmac_final(struct sha384_hmac_context *ctx)
+{
+  /* Finish the inner digest */
+  byte *isha = sha384_final(&ctx->ictx);
+
+  /* Finish the outer digest */
+  sha384_update(&ctx->octx, isha, SHA384_SIZE);
+  return sha384_final(&ctx->octx);
+}
diff --git a/lib/sha512.h b/lib/sha512.h
new file mode 100644
index 00000000..1614a3ac
--- /dev/null
+++ b/lib/sha512.h
@@ -0,0 +1,73 @@
+/*
+ *	BIRD Library -- SHA-512 and SHA-384 Hash Functions,
+ *			HMAC-SHA-512 and HMAC-SHA-384 Functions
+ *
+ *	(c) 2015 CZ.NIC z.s.p.o.
+ *
+ *	Based on the code from libgcrypt-1.6.0, which is
+ *	(c) 2003, 2006, 2008, 2009 Free Software Foundation, Inc.
+ *
+ *	Can be freely distributed and used under the terms of the GNU GPL.
+ */
+
+#ifndef _BIRD_SHA512_H_
+#define _BIRD_SHA512_H_
+
+#include "nest/bird.h"
+
+
+#define SHA384_SIZE 		48
+#define SHA384_HEX_SIZE		97
+#define SHA384_BLOCK_SIZE	128
+
+#define SHA512_SIZE 		64
+#define SHA512_HEX_SIZE		129
+#define SHA512_BLOCK_SIZE	128
+
+
+struct sha512_context {
+  u64 h0, h1, h2, h3, h4, h5, h6, h7;
+  byte buf[SHA512_BLOCK_SIZE];
+  uint nblocks;
+  uint count;
+};
+
+#define sha384_context sha512_context
+
+
+void sha512_init(struct sha512_context *ctx);
+void sha384_init(struct sha384_context *ctx);
+
+void sha512_update(struct sha512_context *ctx, const byte *buf, size_t len);
+static inline void sha384_update(struct sha384_context *ctx, const byte *buf, size_t len)
+{ sha512_update(ctx, buf, len); }
+
+byte *sha512_final(struct sha512_context *ctx);
+static inline byte *sha384_final(struct sha384_context *ctx)
+{ return sha512_final(ctx); }
+
+
+/*
+ *	HMAC-SHA512, HMAC-SHA384
+ */
+
+struct sha512_hmac_context
+{
+  struct sha512_context ictx;
+  struct sha512_context octx;
+};
+
+#define sha384_hmac_context sha512_hmac_context
+
+
+void sha512_hmac_init(struct sha512_hmac_context *ctx, const byte *key, size_t keylen);
+void sha384_hmac_init(struct sha384_hmac_context *ctx, const byte *key, size_t keylen);
+
+void sha512_hmac_update(struct sha512_hmac_context *ctx, const byte *buf, size_t buflen);
+void sha384_hmac_update(struct sha384_hmac_context *ctx, const byte *buf, size_t buflen);
+
+byte *sha512_hmac_final(struct sha512_hmac_context *ctx);
+byte *sha384_hmac_final(struct sha384_hmac_context *ctx);
+
+
+#endif /* _BIRD_SHA512_H_ */
diff --git a/lib/string.h b/lib/string.h
index 528a1a19..218f7b1c 100644
--- a/lib/string.h
+++ b/lib/string.h
@@ -22,6 +22,6 @@ int buffer_vprint(buffer *buf, const char *fmt, va_list args);
 int buffer_print(buffer *buf, const char *fmt, ...);
 void buffer_puts(buffer *buf, const char *str);
 
-int patmatch(byte *pat, byte *str);
+int patmatch(const byte *pat, const byte *str);
 
 #endif
diff --git a/lib/unaligned.h b/lib/unaligned.h
index af655204..dc777fbf 100644
--- a/lib/unaligned.h
+++ b/lib/unaligned.h
@@ -20,7 +20,7 @@
 #include "lib/string.h"
 
 static inline u16
-get_u16(void *p)
+get_u16(const void *p)
 {
   u16 x;
   memcpy(&x, p, 2);
@@ -28,13 +28,22 @@ get_u16(void *p)
 }
 
 static inline u32
-get_u32(void *p)
+get_u32(const void *p)
 {
   u32 x;
   memcpy(&x, p, 4);
   return ntohl(x);
 }
 
+static inline u64
+get_u64(const void *p)
+{
+  u32 xh, xl;
+  memcpy(&xh, p, 4);
+  memcpy(&xl, p+4, 4);
+  return (((u64) ntohl(xh)) << 32) | ntohl(xl);
+}
+
 static inline void
 put_u16(void *p, u16 x)
 {
@@ -49,4 +58,14 @@ put_u32(void *p, u32 x)
   memcpy(p, &x, 4);
 }
 
+static inline void
+put_u64(void *p, u64 x)
+{
+  u32 xh, xl;
+  xh = htonl(x >> 32);
+  xl = htonl((u32) x);
+  memcpy(p, &xh, 4);
+  memcpy(p+4, &xl, 4);
+}
+
 #endif