commit 6719988d8d81711ecf39ce637db0815cd6c6f5e3
parent 435380f327499a97078ab9eda9340fd02432e696
Author: William Casarin <jb55@jb55.com>
Date:   Thu, 14 Apr 2022 12:35:26 -0700
encrypted dms
Signed-off-by: William Casarin <jb55@jb55.com>
Diffstat:
| M | Makefile |  |  | 4 | ++-- | 
| A | aes.c |  |  | 572 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ | 
| A | aes.h |  |  | 91 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ | 
| A | base64.c |  |  | 254 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ | 
| A | base64.h |  |  | 241 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ | 
| M | nostril.c |  |  | 188 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-------- | 
| M | random.h |  |  | 5 | ++--- | 
| M | shell.nix |  |  | 2 | +- | 
8 files changed, 1333 insertions(+), 24 deletions(-)
diff --git a/Makefile b/Makefile
@@ -1,6 +1,6 @@
 
-CFLAGS = -Wall -O2
-OBJS = sha256.o nostril.o
+CFLAGS = -Wall -Og
+OBJS = sha256.o nostril.o aes.o base64.o
 HEADERS = hex.h random.h config.h sha256.h
 
 all: nostril
diff --git a/aes.c b/aes.c
@@ -0,0 +1,572 @@
+/*
+
+This is an implementation of the AES algorithm, specifically ECB, CTR and CBC mode.
+Block size can be chosen in aes.h - available choices are AES128, AES192, AES256.
+
+The implementation is verified against the test vectors in:
+  National Institute of Standards and Technology Special Publication 800-38A 2001 ED
+
+ECB-AES128
+----------
+
+  plain-text:
+    6bc1bee22e409f96e93d7e117393172a
+    ae2d8a571e03ac9c9eb76fac45af8e51
+    30c81c46a35ce411e5fbc1191a0a52ef
+    f69f2445df4f9b17ad2b417be66c3710
+
+  key:
+    2b7e151628aed2a6abf7158809cf4f3c
+
+  resulting cipher
+    3ad77bb40d7a3660a89ecaf32466ef97
+    f5d3d58503b9699de785895a96fdbaaf
+    43b1cd7f598ece23881b00e3ed030688
+    7b0c785e27e8ad3f8223207104725dd4
+
+
+NOTE:   String length must be evenly divisible by 16byte (str_len % 16 == 0)
+        You should pad the end of the string with zeros if this is not the case.
+        For AES192/256 the key size is proportionally larger.
+
+*/
+
+
+/*****************************************************************************/
+/* Includes:                                                                 */
+/*****************************************************************************/
+#include <string.h> // CBC mode, for memset
+#include "aes.h"
+
+/*****************************************************************************/
+/* Defines:                                                                  */
+/*****************************************************************************/
+// The number of columns comprising a state in AES. This is a constant in AES. Value=4
+#define Nb 4
+
+#if defined(AES256) && (AES256 == 1)
+    #define Nk 8
+    #define Nr 14
+#elif defined(AES192) && (AES192 == 1)
+    #define Nk 6
+    #define Nr 12
+#else
+    #define Nk 4        // The number of 32 bit words in a key.
+    #define Nr 10       // The number of rounds in AES Cipher.
+#endif
+
+// jcallan@github points out that declaring Multiply as a function
+// reduces code size considerably with the Keil ARM compiler.
+// See this link for more information: https://github.com/kokke/tiny-AES-C/pull/3
+#ifndef MULTIPLY_AS_A_FUNCTION
+  #define MULTIPLY_AS_A_FUNCTION 0
+#endif
+
+
+
+
+/*****************************************************************************/
+/* Private variables:                                                        */
+/*****************************************************************************/
+// state - array holding the intermediate results during decryption.
+typedef uint8_t state_t[4][4];
+
+
+
+// The lookup-tables are marked const so they can be placed in read-only storage instead of RAM
+// The numbers below can be computed dynamically trading ROM for RAM -
+// This can be useful in (embedded) bootloader applications, where ROM is often limited.
+static const uint8_t sbox[256] = {
+  //0     1    2      3     4    5     6     7      8    9     A      B    C     D     E     F
+  0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76,
+  0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
+  0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15,
+  0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75,
+  0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84,
+  0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf,
+  0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8,
+  0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2,
+  0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73,
+  0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb,
+  0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79,
+  0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08,
+  0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a,
+  0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e,
+  0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf,
+  0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16 };
+
+#if (defined(CBC) && CBC == 1) || (defined(ECB) && ECB == 1)
+static const uint8_t rsbox[256] = {
+  0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
+  0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
+  0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
+  0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
+  0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
+  0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
+  0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
+  0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
+  0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
+  0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
+  0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
+  0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
+  0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
+  0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
+  0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
+  0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d };
+#endif
+
+// The round constant word array, Rcon[i], contains the values given by
+// x to the power (i-1) being powers of x (x is denoted as {02}) in the field GF(2^8)
+static const uint8_t Rcon[11] = {
+  0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36 };
+
+/*
+ * Jordan Goulder points out in PR #12 (https://github.com/kokke/tiny-AES-C/pull/12),
+ * that you can remove most of the elements in the Rcon array, because they are unused.
+ *
+ * From Wikipedia's article on the Rijndael key schedule @ https://en.wikipedia.org/wiki/Rijndael_key_schedule#Rcon
+ *
+ * "Only the first some of these constants are actually used – up to rcon[10] for AES-128 (as 11 round keys are needed),
+ *  up to rcon[8] for AES-192, up to rcon[7] for AES-256. rcon[0] is not used in AES algorithm."
+ */
+
+
+/*****************************************************************************/
+/* Private functions:                                                        */
+/*****************************************************************************/
+/*
+static uint8_t getSBoxValue(uint8_t num)
+{
+  return sbox[num];
+}
+*/
+#define getSBoxValue(num) (sbox[(num)])
+
+// This function produces Nb(Nr+1) round keys. The round keys are used in each round to decrypt the states.
+static void KeyExpansion(uint8_t* RoundKey, const uint8_t* Key)
+{
+  unsigned i, j, k;
+  uint8_t tempa[4]; // Used for the column/row operations
+
+  // The first round key is the key itself.
+  for (i = 0; i < Nk; ++i)
+  {
+    RoundKey[(i * 4) + 0] = Key[(i * 4) + 0];
+    RoundKey[(i * 4) + 1] = Key[(i * 4) + 1];
+    RoundKey[(i * 4) + 2] = Key[(i * 4) + 2];
+    RoundKey[(i * 4) + 3] = Key[(i * 4) + 3];
+  }
+
+  // All other round keys are found from the previous round keys.
+  for (i = Nk; i < Nb * (Nr + 1); ++i)
+  {
+    {
+      k = (i - 1) * 4;
+      tempa[0]=RoundKey[k + 0];
+      tempa[1]=RoundKey[k + 1];
+      tempa[2]=RoundKey[k + 2];
+      tempa[3]=RoundKey[k + 3];
+
+    }
+
+    if (i % Nk == 0)
+    {
+      // This function shifts the 4 bytes in a word to the left once.
+      // [a0,a1,a2,a3] becomes [a1,a2,a3,a0]
+
+      // Function RotWord()
+      {
+        const uint8_t u8tmp = tempa[0];
+        tempa[0] = tempa[1];
+        tempa[1] = tempa[2];
+        tempa[2] = tempa[3];
+        tempa[3] = u8tmp;
+      }
+
+      // SubWord() is a function that takes a four-byte input word and
+      // applies the S-box to each of the four bytes to produce an output word.
+
+      // Function Subword()
+      {
+        tempa[0] = getSBoxValue(tempa[0]);
+        tempa[1] = getSBoxValue(tempa[1]);
+        tempa[2] = getSBoxValue(tempa[2]);
+        tempa[3] = getSBoxValue(tempa[3]);
+      }
+
+      tempa[0] = tempa[0] ^ Rcon[i/Nk];
+    }
+#if defined(AES256) && (AES256 == 1)
+    if (i % Nk == 4)
+    {
+      // Function Subword()
+      {
+        tempa[0] = getSBoxValue(tempa[0]);
+        tempa[1] = getSBoxValue(tempa[1]);
+        tempa[2] = getSBoxValue(tempa[2]);
+        tempa[3] = getSBoxValue(tempa[3]);
+      }
+    }
+#endif
+    j = i * 4; k=(i - Nk) * 4;
+    RoundKey[j + 0] = RoundKey[k + 0] ^ tempa[0];
+    RoundKey[j + 1] = RoundKey[k + 1] ^ tempa[1];
+    RoundKey[j + 2] = RoundKey[k + 2] ^ tempa[2];
+    RoundKey[j + 3] = RoundKey[k + 3] ^ tempa[3];
+  }
+}
+
+void AES_init_ctx(struct AES_ctx* ctx, const uint8_t* key)
+{
+  KeyExpansion(ctx->RoundKey, key);
+}
+#if (defined(CBC) && (CBC == 1)) || (defined(CTR) && (CTR == 1))
+void AES_init_ctx_iv(struct AES_ctx* ctx, const uint8_t* key, const uint8_t* iv)
+{
+  KeyExpansion(ctx->RoundKey, key);
+  memcpy (ctx->Iv, iv, AES_BLOCKLEN);
+}
+void AES_ctx_set_iv(struct AES_ctx* ctx, const uint8_t* iv)
+{
+  memcpy (ctx->Iv, iv, AES_BLOCKLEN);
+}
+#endif
+
+// This function adds the round key to state.
+// The round key is added to the state by an XOR function.
+static void AddRoundKey(uint8_t round, state_t* state, const uint8_t* RoundKey)
+{
+  uint8_t i,j;
+  for (i = 0; i < 4; ++i)
+  {
+    for (j = 0; j < 4; ++j)
+    {
+      (*state)[i][j] ^= RoundKey[(round * Nb * 4) + (i * Nb) + j];
+    }
+  }
+}
+
+// The SubBytes Function Substitutes the values in the
+// state matrix with values in an S-box.
+static void SubBytes(state_t* state)
+{
+  uint8_t i, j;
+  for (i = 0; i < 4; ++i)
+  {
+    for (j = 0; j < 4; ++j)
+    {
+      (*state)[j][i] = getSBoxValue((*state)[j][i]);
+    }
+  }
+}
+
+// The ShiftRows() function shifts the rows in the state to the left.
+// Each row is shifted with different offset.
+// Offset = Row number. So the first row is not shifted.
+static void ShiftRows(state_t* state)
+{
+  uint8_t temp;
+
+  // Rotate first row 1 columns to left
+  temp           = (*state)[0][1];
+  (*state)[0][1] = (*state)[1][1];
+  (*state)[1][1] = (*state)[2][1];
+  (*state)[2][1] = (*state)[3][1];
+  (*state)[3][1] = temp;
+
+  // Rotate second row 2 columns to left
+  temp           = (*state)[0][2];
+  (*state)[0][2] = (*state)[2][2];
+  (*state)[2][2] = temp;
+
+  temp           = (*state)[1][2];
+  (*state)[1][2] = (*state)[3][2];
+  (*state)[3][2] = temp;
+
+  // Rotate third row 3 columns to left
+  temp           = (*state)[0][3];
+  (*state)[0][3] = (*state)[3][3];
+  (*state)[3][3] = (*state)[2][3];
+  (*state)[2][3] = (*state)[1][3];
+  (*state)[1][3] = temp;
+}
+
+static uint8_t xtime(uint8_t x)
+{
+  return ((x<<1) ^ (((x>>7) & 1) * 0x1b));
+}
+
+// MixColumns function mixes the columns of the state matrix
+static void MixColumns(state_t* state)
+{
+  uint8_t i;
+  uint8_t Tmp, Tm, t;
+  for (i = 0; i < 4; ++i)
+  {
+    t   = (*state)[i][0];
+    Tmp = (*state)[i][0] ^ (*state)[i][1] ^ (*state)[i][2] ^ (*state)[i][3] ;
+    Tm  = (*state)[i][0] ^ (*state)[i][1] ; Tm = xtime(Tm);  (*state)[i][0] ^= Tm ^ Tmp ;
+    Tm  = (*state)[i][1] ^ (*state)[i][2] ; Tm = xtime(Tm);  (*state)[i][1] ^= Tm ^ Tmp ;
+    Tm  = (*state)[i][2] ^ (*state)[i][3] ; Tm = xtime(Tm);  (*state)[i][2] ^= Tm ^ Tmp ;
+    Tm  = (*state)[i][3] ^ t ;              Tm = xtime(Tm);  (*state)[i][3] ^= Tm ^ Tmp ;
+  }
+}
+
+// Multiply is used to multiply numbers in the field GF(2^8)
+// Note: The last call to xtime() is unneeded, but often ends up generating a smaller binary
+//       The compiler seems to be able to vectorize the operation better this way.
+//       See https://github.com/kokke/tiny-AES-c/pull/34
+#if MULTIPLY_AS_A_FUNCTION
+static uint8_t Multiply(uint8_t x, uint8_t y)
+{
+  return (((y & 1) * x) ^
+       ((y>>1 & 1) * xtime(x)) ^
+       ((y>>2 & 1) * xtime(xtime(x))) ^
+       ((y>>3 & 1) * xtime(xtime(xtime(x)))) ^
+       ((y>>4 & 1) * xtime(xtime(xtime(xtime(x)))))); /* this last call to xtime() can be omitted */
+  }
+#else
+#define Multiply(x, y)                                \
+      (  ((y & 1) * x) ^                              \
+      ((y>>1 & 1) * xtime(x)) ^                       \
+      ((y>>2 & 1) * xtime(xtime(x))) ^                \
+      ((y>>3 & 1) * xtime(xtime(xtime(x)))) ^         \
+      ((y>>4 & 1) * xtime(xtime(xtime(xtime(x))))))   \
+
+#endif
+
+#if (defined(CBC) && CBC == 1) || (defined(ECB) && ECB == 1)
+/*
+static uint8_t getSBoxInvert(uint8_t num)
+{
+  return rsbox[num];
+}
+*/
+#define getSBoxInvert(num) (rsbox[(num)])
+
+// MixColumns function mixes the columns of the state matrix.
+// The method used to multiply may be difficult to understand for the inexperienced.
+// Please use the references to gain more information.
+static void InvMixColumns(state_t* state)
+{
+  int i;
+  uint8_t a, b, c, d;
+  for (i = 0; i < 4; ++i)
+  {
+    a = (*state)[i][0];
+    b = (*state)[i][1];
+    c = (*state)[i][2];
+    d = (*state)[i][3];
+
+    (*state)[i][0] = Multiply(a, 0x0e) ^ Multiply(b, 0x0b) ^ Multiply(c, 0x0d) ^ Multiply(d, 0x09);
+    (*state)[i][1] = Multiply(a, 0x09) ^ Multiply(b, 0x0e) ^ Multiply(c, 0x0b) ^ Multiply(d, 0x0d);
+    (*state)[i][2] = Multiply(a, 0x0d) ^ Multiply(b, 0x09) ^ Multiply(c, 0x0e) ^ Multiply(d, 0x0b);
+    (*state)[i][3] = Multiply(a, 0x0b) ^ Multiply(b, 0x0d) ^ Multiply(c, 0x09) ^ Multiply(d, 0x0e);
+  }
+}
+
+
+// The SubBytes Function Substitutes the values in the
+// state matrix with values in an S-box.
+static void InvSubBytes(state_t* state)
+{
+  uint8_t i, j;
+  for (i = 0; i < 4; ++i)
+  {
+    for (j = 0; j < 4; ++j)
+    {
+      (*state)[j][i] = getSBoxInvert((*state)[j][i]);
+    }
+  }
+}
+
+static void InvShiftRows(state_t* state)
+{
+  uint8_t temp;
+
+  // Rotate first row 1 columns to right
+  temp = (*state)[3][1];
+  (*state)[3][1] = (*state)[2][1];
+  (*state)[2][1] = (*state)[1][1];
+  (*state)[1][1] = (*state)[0][1];
+  (*state)[0][1] = temp;
+
+  // Rotate second row 2 columns to right
+  temp = (*state)[0][2];
+  (*state)[0][2] = (*state)[2][2];
+  (*state)[2][2] = temp;
+
+  temp = (*state)[1][2];
+  (*state)[1][2] = (*state)[3][2];
+  (*state)[3][2] = temp;
+
+  // Rotate third row 3 columns to right
+  temp = (*state)[0][3];
+  (*state)[0][3] = (*state)[1][3];
+  (*state)[1][3] = (*state)[2][3];
+  (*state)[2][3] = (*state)[3][3];
+  (*state)[3][3] = temp;
+}
+#endif // #if (defined(CBC) && CBC == 1) || (defined(ECB) && ECB == 1)
+
+// Cipher is the main function that encrypts the PlainText.
+static void Cipher(state_t* state, const uint8_t* RoundKey)
+{
+  uint8_t round = 0;
+
+  // Add the First round key to the state before starting the rounds.
+  AddRoundKey(0, state, RoundKey);
+
+  // There will be Nr rounds.
+  // The first Nr-1 rounds are identical.
+  // These Nr rounds are executed in the loop below.
+  // Last one without MixColumns()
+  for (round = 1; ; ++round)
+  {
+    SubBytes(state);
+    ShiftRows(state);
+    if (round == Nr) {
+      break;
+    }
+    MixColumns(state);
+    AddRoundKey(round, state, RoundKey);
+  }
+  // Add round key to last round
+  AddRoundKey(Nr, state, RoundKey);
+}
+
+#if (defined(CBC) && CBC == 1) || (defined(ECB) && ECB == 1)
+static void InvCipher(state_t* state, const uint8_t* RoundKey)
+{
+  uint8_t round = 0;
+
+  // Add the First round key to the state before starting the rounds.
+  AddRoundKey(Nr, state, RoundKey);
+
+  // There will be Nr rounds.
+  // The first Nr-1 rounds are identical.
+  // These Nr rounds are executed in the loop below.
+  // Last one without InvMixColumn()
+  for (round = (Nr - 1); ; --round)
+  {
+    InvShiftRows(state);
+    InvSubBytes(state);
+    AddRoundKey(round, state, RoundKey);
+    if (round == 0) {
+      break;
+    }
+    InvMixColumns(state);
+  }
+
+}
+#endif // #if (defined(CBC) && CBC == 1) || (defined(ECB) && ECB == 1)
+
+/*****************************************************************************/
+/* Public functions:                                                         */
+/*****************************************************************************/
+#if defined(ECB) && (ECB == 1)
+
+
+void AES_ECB_encrypt(const struct AES_ctx* ctx, uint8_t* buf)
+{
+  // The next function call encrypts the PlainText with the Key using AES algorithm.
+  Cipher((state_t*)buf, ctx->RoundKey);
+}
+
+void AES_ECB_decrypt(const struct AES_ctx* ctx, uint8_t* buf)
+{
+  // The next function call decrypts the PlainText with the Key using AES algorithm.
+  InvCipher((state_t*)buf, ctx->RoundKey);
+}
+
+
+#endif // #if defined(ECB) && (ECB == 1)
+
+
+
+
+
+#if defined(CBC) && (CBC == 1)
+
+
+static void XorWithIv(uint8_t* buf, const uint8_t* Iv)
+{
+  uint8_t i;
+  for (i = 0; i < AES_BLOCKLEN; ++i) // The block in AES is always 128bit no matter the key size
+  {
+    buf[i] ^= Iv[i];
+  }
+}
+
+void AES_CBC_encrypt_buffer(struct AES_ctx *ctx, uint8_t* buf, size_t length)
+{
+  size_t i;
+  uint8_t *Iv = ctx->Iv;
+  for (i = 0; i < length; i += AES_BLOCKLEN)
+  {
+    XorWithIv(buf, Iv);
+    Cipher((state_t*)buf, ctx->RoundKey);
+    Iv = buf;
+    buf += AES_BLOCKLEN;
+  }
+  /* store Iv in ctx for next call */
+  memcpy(ctx->Iv, Iv, AES_BLOCKLEN);
+}
+
+void AES_CBC_decrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, size_t length)
+{
+  size_t i;
+  uint8_t storeNextIv[AES_BLOCKLEN];
+  for (i = 0; i < length; i += AES_BLOCKLEN)
+  {
+    memcpy(storeNextIv, buf, AES_BLOCKLEN);
+    InvCipher((state_t*)buf, ctx->RoundKey);
+    XorWithIv(buf, ctx->Iv);
+    memcpy(ctx->Iv, storeNextIv, AES_BLOCKLEN);
+    buf += AES_BLOCKLEN;
+  }
+
+}
+
+#endif // #if defined(CBC) && (CBC == 1)
+
+
+
+#if defined(CTR) && (CTR == 1)
+
+/* Symmetrical operation: same function for encrypting as for decrypting. Note any IV/nonce should never be reused with the same key */
+void AES_CTR_xcrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, size_t length)
+{
+  uint8_t buffer[AES_BLOCKLEN];
+
+  size_t i;
+  int bi;
+  for (i = 0, bi = AES_BLOCKLEN; i < length; ++i, ++bi)
+  {
+    if (bi == AES_BLOCKLEN) /* we need to regen xor compliment in buffer */
+    {
+
+      memcpy(buffer, ctx->Iv, AES_BLOCKLEN);
+      Cipher((state_t*)buffer,ctx->RoundKey);
+
+      /* Increment Iv and handle overflow */
+      for (bi = (AES_BLOCKLEN - 1); bi >= 0; --bi)
+      {
+	/* inc will overflow */
+        if (ctx->Iv[bi] == 255)
+	{
+          ctx->Iv[bi] = 0;
+          continue;
+        }
+        ctx->Iv[bi] += 1;
+        break;
+      }
+      bi = 0;
+    }
+
+    buf[i] = (buf[i] ^ buffer[bi]);
+  }
+}
+
+#endif // #if defined(CTR) && (CTR == 1)
+
diff --git a/aes.h b/aes.h
@@ -0,0 +1,91 @@
+#ifndef _AES_H_
+#define _AES_H_
+
+#include <stdint.h>
+#include <stddef.h>
+
+// #define the macros below to 1/0 to enable/disable the mode of operation.
+//
+// CBC enables AES encryption in CBC-mode of operation.
+// CTR enables encryption in counter-mode.
+// ECB enables the basic ECB 16-byte block algorithm. All can be enabled simultaneously.
+
+// The #ifndef-guard allows it to be configured before #include'ing or at compile time.
+#ifndef CBC
+  #define CBC 1
+#endif
+
+#ifndef ECB
+  #define ECB 0
+#endif
+
+#ifndef CTR
+  #define CTR 0
+#endif
+
+
+//#define AES128 1
+//#define AES192 1
+#define AES256 1
+
+#define AES_BLOCKLEN 16 // Block length in bytes - AES is 128b block only
+
+#if defined(AES256) && (AES256 == 1)
+    #define AES_KEYLEN 32
+    #define AES_keyExpSize 240
+#elif defined(AES192) && (AES192 == 1)
+    #define AES_KEYLEN 24
+    #define AES_keyExpSize 208
+#else
+    #define AES_KEYLEN 16   // Key length in bytes
+    #define AES_keyExpSize 176
+#endif
+
+struct AES_ctx
+{
+  uint8_t RoundKey[AES_keyExpSize];
+#if (defined(CBC) && (CBC == 1)) || (defined(CTR) && (CTR == 1))
+  uint8_t Iv[AES_BLOCKLEN];
+#endif
+};
+
+void AES_init_ctx(struct AES_ctx* ctx, const uint8_t* key);
+#if (defined(CBC) && (CBC == 1)) || (defined(CTR) && (CTR == 1))
+void AES_init_ctx_iv(struct AES_ctx* ctx, const uint8_t* key, const uint8_t* iv);
+void AES_ctx_set_iv(struct AES_ctx* ctx, const uint8_t* iv);
+#endif
+
+#if defined(ECB) && (ECB == 1)
+// buffer size is exactly AES_BLOCKLEN bytes; 
+// you need only AES_init_ctx as IV is not used in ECB 
+// NB: ECB is considered insecure for most uses
+void AES_ECB_encrypt(const struct AES_ctx* ctx, uint8_t* buf);
+void AES_ECB_decrypt(const struct AES_ctx* ctx, uint8_t* buf);
+
+#endif // #if defined(ECB) && (ECB == !)
+
+
+#if defined(CBC) && (CBC == 1)
+// buffer size MUST be mutile of AES_BLOCKLEN;
+// Suggest https://en.wikipedia.org/wiki/Padding_(cryptography)#PKCS7 for padding scheme
+// NOTES: you need to set IV in ctx via AES_init_ctx_iv() or AES_ctx_set_iv()
+//        no IV should ever be reused with the same key 
+void AES_CBC_encrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, size_t length);
+void AES_CBC_decrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, size_t length);
+
+#endif // #if defined(CBC) && (CBC == 1)
+
+
+#if defined(CTR) && (CTR == 1)
+
+// Same function for encrypting as for decrypting. 
+// IV is incremented for every block, and used after encryption as XOR-compliment for output
+// Suggesting https://en.wikipedia.org/wiki/Padding_(cryptography)#PKCS7 for padding scheme
+// NOTES: you need to set IV in ctx with AES_init_ctx_iv() or AES_ctx_set_iv()
+//        no IV should ever be reused with the same key 
+void AES_CTR_xcrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, size_t length);
+
+#endif // #if defined(CTR) && (CTR == 1)
+
+
+#endif // _AES_H_
diff --git a/base64.c b/base64.c
@@ -0,0 +1,254 @@
+/* Licensed under BSD-MIT - see LICENSE file for details */
+#include "base64.h"
+
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <stdint.h>
+
+/**
+ * sixbit_to_b64 - maps a 6-bit value to the base64 alphabet
+ * @param map A base 64 map (see base64_init_map)
+ * @param sixbit Six-bit value to map
+ * @return a base 64 character
+ */
+static char sixbit_to_b64(const base64_maps_t *maps, const uint8_t sixbit)
+{
+	assert(sixbit <= 63);
+
+	return maps->encode_map[(unsigned char)sixbit];
+}
+
+/**
+ * sixbit_from_b64 - maps a base64-alphabet character to its 6-bit value
+ * @param maps A base 64 maps structure (see base64_init_maps)
+ * @param sixbit Six-bit value to map
+ * @return a six-bit value
+ */
+static int8_t sixbit_from_b64(const base64_maps_t *maps,
+			      const unsigned char b64letter)
+{
+	int8_t ret;
+
+	ret = maps->decode_map[(unsigned char)b64letter];
+	if (ret == (char)0xff) {
+		errno = EDOM;
+		return -1;
+	}
+
+	return ret;
+}
+
+bool base64_char_in_alphabet(const base64_maps_t *maps, const char b64char)
+{
+	return (maps->decode_map[(const unsigned char)b64char] != (char)0xff);
+}
+
+void base64_init_maps(base64_maps_t *dest, const char src[64])
+{
+	unsigned char i;
+
+	memcpy(dest->encode_map,src,64);
+	memset(dest->decode_map,0xff,256);
+	for (i=0; i<64; i++) {
+		dest->decode_map[(unsigned char)src[i]] = i;
+	}
+}
+
+size_t base64_encoded_length(size_t srclen)
+{
+	return ((srclen + 2) / 3) * 4;
+}
+
+void base64_encode_triplet_using_maps(const base64_maps_t *maps,
+				      char dest[4], const char src[3])
+{
+	char a = src[0];
+	char b = src[1];
+	char c = src[2];
+
+	dest[0] = sixbit_to_b64(maps, (a & 0xfc) >> 2);
+	dest[1] = sixbit_to_b64(maps, ((a & 0x3) << 4) | ((b & 0xf0) >> 4));
+	dest[2] = sixbit_to_b64(maps, ((c & 0xc0) >> 6) | ((b & 0xf) << 2));
+	dest[3] = sixbit_to_b64(maps, c & 0x3f);
+}
+
+void base64_encode_tail_using_maps(const base64_maps_t *maps, char dest[4],
+				   const char *src, const size_t srclen)
+{
+	char longsrc[3] = { 0 };
+
+	assert(srclen <= 3);
+
+	memcpy(longsrc, src, srclen);
+	base64_encode_triplet_using_maps(maps, dest, longsrc);
+	memset(dest+1+srclen, '=', 3-srclen);
+}
+
+ssize_t base64_encode_using_maps(const base64_maps_t *maps,
+				 char *dest, const size_t destlen,
+				 const char *src, const size_t srclen)
+{
+	size_t src_offset = 0;
+	size_t dest_offset = 0;
+
+	if (destlen < base64_encoded_length(srclen)) {
+		errno = EOVERFLOW;
+		return -1;
+	}
+
+	while (srclen - src_offset >= 3) {
+		base64_encode_triplet_using_maps(maps, &dest[dest_offset], &src[src_offset]);
+		src_offset += 3;
+		dest_offset += 4;
+	}
+
+	if (src_offset < srclen) {
+		base64_encode_tail_using_maps(maps, &dest[dest_offset], &src[src_offset], srclen-src_offset);
+		dest_offset += 4;
+	}
+
+	memset(&dest[dest_offset], '\0', destlen-dest_offset);
+
+	return dest_offset;
+}
+
+size_t base64_decoded_length(size_t srclen)
+{
+	return ((srclen+3)/4*3);
+}
+
+ssize_t base64_decode_quartet_using_maps(const base64_maps_t *maps, char dest[3],
+				     const char src[4])
+{
+	signed char a;
+	signed char b;
+	signed char c;
+	signed char d;
+
+	a = sixbit_from_b64(maps, src[0]);
+	b = sixbit_from_b64(maps, src[1]);
+	c = sixbit_from_b64(maps, src[2]);
+	d = sixbit_from_b64(maps, src[3]);
+
+	if ((a == -1) || (b == -1) || (c == -1) || (d == -1)) {
+		return -1;
+	}
+
+	dest[0] = (a << 2) | (b >> 4);
+	dest[1] = ((b & 0xf) << 4) | (c >> 2);
+	dest[2] = ((c & 0x3) << 6) | d;
+
+	return 0;
+}
+
+
+ssize_t base64_decode_tail_using_maps(const base64_maps_t *maps, char dest[3],
+				  const char * src, const size_t srclen)
+{
+	char longsrc[4];
+	int quartet_result;
+	size_t insize = srclen;
+
+	while (insize != 0 &&
+	       src[insize-1] == '=') { /* throw away padding symbols */
+		insize--;
+	}
+	if (insize == 0) {
+		return 0;
+	}
+	if (insize == 1) {
+		/* the input is malformed.... */
+		errno = EINVAL;
+		return -1;
+	}
+	memcpy(longsrc, src, insize);
+	memset(longsrc+insize, 'A', 4-insize);
+	quartet_result = base64_decode_quartet_using_maps(maps, dest, longsrc);
+	if (quartet_result == -1) {
+		return -1;
+	}
+
+	return insize - 1;
+}
+
+ssize_t base64_decode_using_maps(const base64_maps_t *maps,
+				 char *dest, const size_t destlen,
+				 const char *src, const size_t srclen)
+{
+	ssize_t dest_offset = 0;
+	ssize_t i;
+	ssize_t more;
+
+	if (destlen < base64_decoded_length(srclen)) {
+		errno = EOVERFLOW;
+		return -1;
+	}
+
+	for(i=0; srclen - i > 4; i+=4) {
+		if (base64_decode_quartet_using_maps(maps, &dest[dest_offset], &src[i]) == -1) {
+			return -1;
+		}
+		dest_offset += 3;
+	}
+
+	more = base64_decode_tail_using_maps(maps, &dest[dest_offset], &src[i], srclen - i);
+	if (more == -1) {
+		return -1;
+	}
+	dest_offset += more;
+
+	memset(&dest[dest_offset], '\0', destlen-dest_offset);
+
+	return dest_offset;
+}
+
+
+
+
+/**
+ * base64_maps_rfc4648 - pregenerated maps struct for rfc4648
+ */
+const base64_maps_t base64_maps_rfc4648 = {
+  "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/",
+
+  "\xff\xff\xff\xff\xff" /* 0 */					\
+  "\xff\xff\xff\xff\xff" /* 5 */					\
+  "\xff\xff\xff\xff\xff" /* 10 */					\
+  "\xff\xff\xff\xff\xff" /* 15 */					\
+  "\xff\xff\xff\xff\xff" /* 20 */					\
+  "\xff\xff\xff\xff\xff" /* 25 */					\
+  "\xff\xff\xff\xff\xff" /* 30 */					\
+  "\xff\xff\xff\xff\xff" /* 35 */					\
+  "\xff\xff\xff\x3e\xff" /* 40 */					\
+  "\xff\xff\x3f\x34\x35" /* 45 */					\
+  "\x36\x37\x38\x39\x3a" /* 50 */					\
+  "\x3b\x3c\x3d\xff\xff" /* 55 */					\
+  "\xff\xff\xff\xff\xff" /* 60 */					\
+  "\x00\x01\x02\x03\x04" /* 65 A */					\
+  "\x05\x06\x07\x08\x09" /* 70 */					\
+  "\x0a\x0b\x0c\x0d\x0e" /* 75 */					\
+  "\x0f\x10\x11\x12\x13" /* 80 */					\
+  "\x14\x15\x16\x17\x18" /* 85 */					\
+  "\x19\xff\xff\xff\xff" /* 90 */					\
+  "\xff\xff\x1a\x1b\x1c" /* 95 */					\
+  "\x1d\x1e\x1f\x20\x21" /* 100 */					\
+  "\x22\x23\x24\x25\x26" /* 105 */					\
+  "\x27\x28\x29\x2a\x2b" /* 110 */					\
+  "\x2c\x2d\x2e\x2f\x30" /* 115 */					\
+  "\x31\x32\x33\xff\xff" /* 120 */					\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff" /* 125 */			\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff" /* 155 */			\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff" /* 185 */			\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff" /* 215 */			\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff"				\
+  "\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff" /* 245 */
+};
+
diff --git a/base64.h b/base64.h
@@ -0,0 +1,241 @@
+/* Licensed under BSD-MIT - see LICENSE file for details */
+#ifndef CCAN_BASE64_H
+#define CCAN_BASE64_H
+
+#include <stddef.h>
+#include <stdbool.h>
+#include <sys/types.h>
+
+/**
+ * base64_maps_t - structure to hold maps for encode/decode
+ */
+typedef struct {
+	char encode_map[64];
+	signed char decode_map[256];
+} base64_maps_t;
+
+/**
+ * base64_encoded_length - Calculate encode buffer length
+ * @param srclen the size of the data to be encoded
+ * @note add 1 to this to get null-termination
+ * @return Buffer length required for encode
+ */
+size_t base64_encoded_length(size_t srclen);
+
+/**
+ * base64_decoded_length - Calculate decode buffer length
+ * @param srclen Length of the data to be decoded
+ * @note This does not return the size of the decoded data!  see base64_decode
+ * @return Minimum buffer length for safe decode
+ */
+size_t base64_decoded_length(size_t srclen);
+
+/**
+ * base64_init_maps - populate a base64_maps_t based on a supplied alphabet
+ * @param dest A base64 maps object
+ * @param src Alphabet to populate the maps from (e.g. base64_alphabet_rfc4648)
+ */
+void base64_init_maps(base64_maps_t *dest, const char src[64]);
+
+
+/**
+ * base64_encode_triplet_using_maps - encode 3 bytes into base64 using a specific alphabet
+ * @param maps Maps to use for encoding (see base64_init_maps)
+ * @param dest Buffer containing 3 bytes
+ * @param src Buffer containing 4 characters
+ */
+void base64_encode_triplet_using_maps(const base64_maps_t *maps,
+				      char dest[4], const char src[3]);
+
+/**
+ * base64_encode_tail_using_maps - encode the final bytes of a source using a specific alphabet
+ * @param maps Maps to use for encoding (see base64_init_maps)
+ * @param dest Buffer containing 4 bytes
+ * @param src Buffer containing srclen bytes
+ * @param srclen Number of bytes (<= 3) to encode in src
+ */
+void base64_encode_tail_using_maps(const base64_maps_t *maps, char dest[4],
+				   const char *src, size_t srclen);
+
+/**
+ * base64_encode_using_maps - encode a buffer into base64 using a specific alphabet
+ * @param maps Maps to use for encoding (see base64_init_maps)
+ * @param dest Buffer to encode into
+ * @param destlen Length of dest
+ * @param src Buffer to encode
+ * @param srclen Length of the data to encode
+ * @return Number of encoded bytes set in dest. -1 on error (and errno set)
+ * @note dest will be nul-padded to destlen (past any required padding)
+ * @note sets errno = EOVERFLOW if destlen is too small
+ */
+ssize_t base64_encode_using_maps(const base64_maps_t *maps,
+				 char *dest, size_t destlen,
+				 const char *src, size_t srclen);
+
+/*
+ * base64_char_in_alphabet - returns true if character can be part of an encoded string
+ * @param maps A base64 maps object (see base64_init_maps)
+ * @param b64char Character to check
+ */
+bool base64_char_in_alphabet(const base64_maps_t *maps, char b64char);
+
+/**
+ * base64_decode_using_maps - decode a base64-encoded string using a specific alphabet
+ * @param maps A base64 maps object (see base64_init_maps)
+ * @param dest Buffer to decode into
+ * @param destlen length of dest
+ * @param src the buffer to decode
+ * @param srclen the length of the data to decode
+ * @return Number of decoded bytes set in dest. -1 on error (and errno set)
+ * @note dest will be nul-padded to destlen
+ * @note sets errno = EOVERFLOW if destlen is too small
+ * @note sets errno = EDOM if src contains invalid characters
+ */
+ssize_t base64_decode_using_maps(const base64_maps_t *maps,
+				 char *dest, size_t destlen,
+				 const char *src, size_t srclen);
+
+/**
+ * base64_decode_quartet_using_maps - decode 4 bytes from base64 using a specific alphabet
+ * @param maps A base64 maps object (see base64_init_maps)
+ * @param dest Buffer containing 3 bytes
+ * @param src Buffer containing 4 bytes
+ * @return Number of decoded bytes set in dest. -1 on error (and errno set)
+ * @note sets errno = EDOM if src contains invalid characters
+ */
+ssize_t base64_decode_quartet_using_maps(const base64_maps_t *maps,
+				         char dest[3], const char src[4]);
+
+/**
+ * base64_decode_tail_using_maps - decode the final bytes of a base64 string using a specific alphabet
+ * @param maps A base64 maps object (see base64_init_maps)
+ * @param dest Buffer containing 3 bytes
+ * @param src Buffer containing 4 bytes - padded with '=' as required
+ * @param srclen Number of bytes to decode in src
+ * @return Number of decoded bytes set in dest. -1 on error (and errno set)
+ * @note sets errno = EDOM if src contains invalid characters
+ * @note sets errno = EINVAL if src is an invalid base64 tail
+ */
+ssize_t base64_decode_tail_using_maps(const base64_maps_t *maps, char *dest,
+				      const char *src, size_t srclen);
+
+
+/* the rfc4648 functions: */
+
+extern const base64_maps_t base64_maps_rfc4648;
+
+/**
+ * base64_encode - Encode a buffer into base64 according to rfc4648
+ * @param dest Buffer to encode into
+ * @param destlen Length of the destination buffer
+ * @param src Buffer to encode
+ * @param srclen Length of the data to encode
+ * @return Number of encoded bytes set in dest. -1 on error (and errno set)
+ * @note dest will be nul-padded to destlen (past any required padding)
+ * @note sets errno = EOVERFLOW if destlen is too small
+ *
+ * This function encodes src according to http://tools.ietf.org/html/rfc4648
+ *
+ * Example:
+ *	size_t encoded_length;
+ *	char dest[100];
+ *	const char *src = "This string gets encoded";
+ *	encoded_length = base64_encode(dest, sizeof(dest), src, strlen(src));
+ *	printf("Returned data of length %zd @%p\n", encoded_length, &dest);
+ */
+static inline
+ssize_t base64_encode(char *dest, size_t destlen,
+		      const char *src, size_t srclen)
+{
+	return base64_encode_using_maps(&base64_maps_rfc4648,
+					dest, destlen, src, srclen);
+}
+
+/**
+ * base64_encode_triplet - encode 3 bytes into base64 according to rfc4648
+ * @param dest Buffer containing 4 bytes
+ * @param src Buffer containing 3 bytes
+ */
+static inline
+void base64_encode_triplet(char dest[4], const char src[3])
+{
+	base64_encode_triplet_using_maps(&base64_maps_rfc4648, dest, src);
+}
+
+/**
+ * base64_encode_tail - encode the final bytes of a source according to rfc4648
+ * @param dest Buffer containing 4 bytes
+ * @param src Buffer containing srclen bytes
+ * @param srclen Number of bytes (<= 3) to encode in src
+ */
+static inline
+void base64_encode_tail(char dest[4], const char *src, size_t srclen)
+{
+	base64_encode_tail_using_maps(&base64_maps_rfc4648, dest, src, srclen);
+}
+
+
+/**
+ * base64_decode - decode An rfc4648 base64-encoded string
+ * @param dest Buffer to decode into
+ * @param destlen Length of the destination buffer
+ * @param src Buffer to decode
+ * @param srclen Length of the data to decode
+ * @return Number of decoded bytes set in dest. -1 on error (and errno set)
+ * @note dest will be nul-padded to destlen
+ * @note sets errno = EOVERFLOW if destlen is too small
+ * @note sets errno = EDOM if src contains invalid characters
+ *
+ * This function decodes the buffer according to
+ * http://tools.ietf.org/html/rfc4648
+ *
+ * Example:
+ *	size_t decoded_length;
+ *	char ret[100];
+ *	const char *src = "Zm9vYmFyYmF6";
+ *	decoded_length = base64_decode(ret, sizeof(ret), src, strlen(src));
+ *	printf("Returned data of length %zd @%p\n", decoded_length, &ret);
+ */
+static inline
+ssize_t base64_decode(char *dest, size_t destlen,
+		      const char *src, size_t srclen)
+{
+	return base64_decode_using_maps(&base64_maps_rfc4648,
+					dest, destlen, src, srclen);
+}
+
+/**
+ * base64_decode_quartet - decode the first 4 characters in src into dest
+ * @param dest Buffer containing 3 bytes
+ * @param src Buffer containing 4 characters
+ * @return Number of decoded bytes set in dest. -1 on error (and errno set)
+ * @note sets errno = EDOM if src contains invalid characters
+ */
+static inline
+ssize_t base64_decode_quartet(char dest[3], const char src[4])
+{
+	return base64_decode_quartet_using_maps(&base64_maps_rfc4648,
+						dest, src);
+}
+
+/**
+ * @brief decode the final bytes of a base64 string from src into dest
+ * @param dest Buffer containing 3 bytes
+ * @param src Buffer containing 4 bytes - padded with '=' as required
+ * @param srclen Number of bytes to decode in src
+ * @return Number of decoded bytes set in dest. -1 on error (and errno set)
+ * @note sets errno = EDOM if src contains invalid characters
+ * @note sets errno = EINVAL if src is an invalid base64 tail
+ */
+static inline
+ssize_t base64_decode_tail(char dest[3], const char *src, size_t srclen)
+{
+	return base64_decode_tail_using_maps(&base64_maps_rfc4648,
+					     dest, src, srclen);
+}
+
+/* end rfc4648 functions */
+
+
+
+#endif /* CCAN_BASE64_H */
diff --git a/nostril.c b/nostril.c
@@ -7,10 +7,13 @@
 #include <inttypes.h>
 
 #include <secp256k1.h>
+#include <secp256k1_ecdh.h>
 #include <secp256k1_schnorrsig.h>
 
 #include "cursor.h"
 #include "hex.h"
+#include "base64.h"
+#include "aes.h"
 #include "sha256.h"
 #include "random.h"
 
@@ -20,9 +23,11 @@
 #define HAS_CREATED_AT (1<<1)
 #define HAS_KIND (1<<2)
 #define HAS_ENVELOPE (1<<3)
+#define HAS_ENCRYPT (1<<4)
 
 struct key {
 	secp256k1_keypair pair;
+	unsigned char secret[32];
 	unsigned char pubkey[32];
 };
 
@@ -30,9 +35,10 @@ struct args {
 	unsigned int flags;
 	int kind;
 
+	unsigned char encrypt_to[32];
 	const char *sec;
 	const char *content;
-	
+
 	uint64_t created_at;
 };
 
@@ -184,13 +190,13 @@ static int make_sig(secp256k1_context *ctx, struct key *key,
 	return secp256k1_schnorrsig_sign(ctx, sig, id, &key->pair, aux);
 }
 
-static int create_key(secp256k1_context *ctx, struct key *key, unsigned char seckey[32])
+static int create_key(secp256k1_context *ctx, struct key *key)
 {
 	secp256k1_xonly_pubkey pubkey;
 
 	/* Try to create a keypair with a valid context, it should only
 	 * fail if the secret key is zero or out of range. */
-	if (!secp256k1_keypair_create(ctx, &key->pair, seckey))
+	if (!secp256k1_keypair_create(ctx, &key->pair, key->secret))
 		return 0;
 
 	if (!secp256k1_keypair_xonly_pub(ctx, &pubkey, NULL, &key->pair))
@@ -202,28 +208,24 @@ static int create_key(secp256k1_context *ctx, struct key *key, unsigned char sec
 
 static int decode_key(secp256k1_context *ctx, const char *secstr, struct key *key)
 {
-	unsigned char seckey[32];
-
-	if (!hex_decode(secstr, strlen(secstr), seckey, 32)) {
+	if (!hex_decode(secstr, strlen(secstr), key->secret, 32)) {
 		fprintf(stderr, "could not hex decode secret key\n");
 		return 0;
 	}
 
-	return create_key(ctx, key, seckey);
+	return create_key(ctx, key);
 }
 
 static int generate_key(secp256k1_context *ctx, struct key *key)
 {
-	unsigned char seckey[32];
-
 	/* If the secret key is zero or out of range (bigger than secp256k1's
 	 * order), we try to sample a new key. Note that the probability of this
 	 * happening is negligible. */
-	if (!fill_random(seckey, sizeof(seckey))) {
+	if (!fill_random(key->secret, sizeof(key->secret))) {
 		return 0;
 	}
 
-	return create_key(ctx, key, seckey);
+	return create_key(ctx, key);
 }
 
 
@@ -254,7 +256,7 @@ static int generate_event_id(struct nostr_event *ev)
 	}
 
 	//fprintf(stderr, "commitment: '%.*s'\n", len, buf);
-	
+
 	sha256((struct sha256*)ev->id, buf, len);
 
 	return 1;
@@ -262,10 +264,8 @@ static int generate_event_id(struct nostr_event *ev)
 
 static int sign_event(secp256k1_context *ctx, struct key *key, struct nostr_event *ev)
 {
-	if (!make_sig(ctx, key, ev->id, ev->sig)) {
-		fprintf(stderr, "Signature generation failed\n");
+	if (!make_sig(ctx, key, ev->id, ev->sig))
 		return 0;
-	}
 
 	return 1;
 }
@@ -309,7 +309,7 @@ static int print_event(struct nostr_event *ev, int envelope)
 		printf("]");
 
 	printf("\n");
-	
+
 	return 1;
 }
 
@@ -327,7 +327,7 @@ static void make_event_from_args(struct nostr_event *ev, struct args *args)
 
 static int parse_num(const char *arg, uint64_t *t)
 {
-	*t = strtol(arg, NULL, 10); 
+	*t = strtol(arg, NULL, 10);
 	return errno != EINVAL;
 }
 
@@ -363,6 +363,13 @@ static int parse_args(int argc, const char *argv[], struct args *args)
 			args->flags |= HAS_KIND;
 		} else if (!strcmp(arg, "--envelope")) {
 			args->flags |= HAS_ENVELOPE;
+		} else if (!strcmp(arg, "--dm")) {
+			arg = *argv++; argc--;
+			if (!hex_decode(arg, strlen(arg), args->encrypt_to, 32)) {
+				fprintf(stderr, "could not decode encrypt-to pubkey");
+				return 0;
+			}
+			args->flags |= HAS_ENCRYPT;
 		} else if (!strncmp(arg, "--", 2)) {
 			fprintf(stderr, "unknown argument: %s\n", arg);
 			return 0;
@@ -372,6 +379,144 @@ static int parse_args(int argc, const char *argv[], struct args *args)
 	return 1;
 }
 
+static int nostr_add_tag(struct nostr_event *ev, const char *t1, const char *t2)
+{
+	struct nostr_tag *tag;
+
+	if (ev->num_tags + 1 > MAX_TAGS)
+		return 0;
+
+	tag = &ev->tags[ev->num_tags++];
+	tag->strs[0] = t1;
+	tag->strs[1] = t2;
+	tag->num_elems = 2;
+	return 1;
+}
+
+static int aes_encrypt(unsigned char *key, unsigned char *iv,
+		unsigned char *buf, size_t buflen)
+{
+	struct AES_ctx ctx;
+	unsigned char padding;
+	int i;
+	struct cursor cur;
+
+	padding = 16 - (buflen % 16);
+	make_cursor(buf, buf + buflen + padding, &cur);
+	cur.p += buflen;
+	//fprintf(stderr, "aes_encrypt: len %ld, padding %d\n", buflen, padding);
+
+	for (i = 0; i < padding; i++) {
+		if (!cursor_push_byte(&cur, padding)) {
+			return 0;
+		}
+	}
+	assert(cur.p == cur.end);
+	assert((cur.p - cur.start) % 16 == 0);
+
+	AES_init_ctx_iv(&ctx, key, iv);
+	//fprintf(stderr, "encrypting %ld bytes: ", cur.p - cur.start);
+	//print_hex(cur.start, cur.p - cur.start);
+	AES_CBC_encrypt_buffer(&ctx, cur.start, cur.p - cur.start);
+
+	return cur.p - cur.start;
+}
+
+static int copyx(unsigned char *output, const unsigned char *x32, const unsigned char *y32, void *data) {
+	memcpy(output, x32, 32);
+	return 1;
+}
+
+static int make_encrypted_dm(secp256k1_context *ctx, struct key *key,
+		struct nostr_event *ev, unsigned char nostr_pubkey[32])
+{
+	size_t inl = strlen(ev->content);
+	int enclen = inl + 16;
+	size_t buflen = enclen * 3 + 65 * 10;
+	unsigned char *buf = malloc(buflen);
+	unsigned char shared_secret[32];
+	unsigned char iv[16];
+	unsigned char compressed_pubkey[33];
+	int content_len = strlen(ev->content);
+	unsigned char encbuf[content_len + (content_len % 16) + 1];
+	struct cursor cur;
+	secp256k1_pubkey pubkey;
+
+	compressed_pubkey[0] = 2;
+	memcpy(&compressed_pubkey[1], nostr_pubkey, 32);
+
+	make_cursor(buf, buf + buflen, &cur);
+
+        if (!secp256k1_ec_seckey_verify(ctx, key->secret)) {
+		fprintf(stderr, "make_encrypted_dm: ec_seckey_verify failed\n");
+		return 0;
+	}
+
+	if (!secp256k1_ec_pubkey_parse(ctx, &pubkey, compressed_pubkey, sizeof(compressed_pubkey))) {
+		fprintf(stderr, "make_encrypted_dm: ec_pubkey_parse failed\n");
+		return 0;
+	}
+
+	if (!secp256k1_ecdh(ctx, shared_secret, &pubkey, key->secret, copyx, NULL)) {
+		fprintf(stderr, "make_encrypted_dm: secp256k1_ecdh failed\n");
+		return 0;
+	}
+
+	if (!fill_random(iv, sizeof(iv))) {
+		fprintf(stderr, "make_encrypted_dm: fill_random failed\n");
+		return 0;
+	}
+
+	fprintf(stderr, "shared secret: ");
+	print_hex(shared_secret, 32);
+
+	memcpy(encbuf, ev->content, strlen(ev->content));
+	enclen = aes_encrypt(shared_secret, iv, encbuf, strlen(ev->content));
+	if (enclen == 0) {
+		fprintf(stderr, "make_encrypted_dm: aes_encrypt failed\n");
+		free(buf);
+		free(encbuf);
+		return 0;
+	}
+
+	if ((enclen = base64_encode((char *)buf, buflen, (const char*)encbuf, enclen)) == -1) {
+		fprintf(stderr, "make_encrypted_dm: base64 encode of encrypted fata failed\n");
+		return 0;
+	}
+	cur.p += enclen;
+
+	if (!cursor_push_str(&cur, "?iv=")) {
+		fprintf(stderr, "make_encrypted_dm: buffer too small\n");
+		return 0;
+	}
+
+	if ((enclen = base64_encode((char *)cur.p, cur.end - cur.p, (const char*)iv, 16)) == -1) {
+		fprintf(stderr, "make_encrypted_dm: base64 encode of iv failed\n");
+		return 0;
+	}
+	cur.p += enclen;
+
+	if (!cursor_push_byte(&cur, 0)) {
+		fprintf(stderr, "make_encrypted_dm: out of memory by 1 byte!\n");
+		return 0;
+	}
+
+	ev->content = (const char*)cur.start;
+	ev->kind = 4;
+
+	if (!hex_encode(nostr_pubkey, 32, (char*)cur.p, cur.end - cur.p))
+		return 0;
+
+	if (!nostr_add_tag(ev, "p", (const char*)cur.p)) {
+		fprintf(stderr, "too many tags\n");
+		return 0;
+	}
+
+	cur.p += 65;
+
+	return 1;
+}
+
 int main(int argc, const char *argv[])
 {
 	struct args args = {0};
@@ -396,11 +541,18 @@ int main(int argc, const char *argv[])
 		}
 	} else {
 		if (!generate_key(ctx, &key)) {
-			fprintf(stderr, "could not generate key");
+			fprintf(stderr, "could not generate key\n");
 			return 4;
 		}
 	}
 
+	if (args.flags & HAS_ENCRYPT) {
+		if (!make_encrypted_dm(ctx, &key, &ev, args.encrypt_to)) {
+			fprintf(stderr, "error making encrypted dm\n");
+			return 0;
+		}
+	}
+
 	// set the event's pubkey
 	memcpy(ev.pubkey, key.pubkey, 32);
 
diff --git a/random.h b/random.h
@@ -65,9 +65,8 @@ static int fill_random(unsigned char* data, size_t size) {
 
 static void print_hex(unsigned char* data, size_t size) {
     size_t i;
-    printf("0x");
     for (i = 0; i < size; i++) {
-        printf("%02x", data[i]);
+        fprintf(stderr, "%02x", data[i]);
     }
-    printf("\n");
+    fprintf(stderr, "\n");
 }
diff --git a/shell.nix b/shell.nix
@@ -1,5 +1,5 @@
 { pkgs ? import <nixpkgs> {} }:
 with pkgs;
 mkShell {
-  buildInputs = [ secp256k1 ];
+  buildInputs = [ secp256k1 openssl gdb ];
 }