add all sorts of shit

13 files changed, 1141 insertions, 16 deletions

diff --git a/melonDS.cbp b/melonDS.cbp
index 59df311..97958f5 100644
--- a/melonDS.cbp
+++ b/melonDS.cbp
@@ -254,6 +254,15 @@
 		<Unit filename="src/pcap/sll.h" />
 		<Unit filename="src/pcap/usb.h" />
 		<Unit filename="src/pcap/vlan.h" />
+		<Unit filename="src/sha1/sha1.c">
+			<Option compilerVar="CC" />
+		</Unit>
+		<Unit filename="src/sha1/sha1.h" />
+		<Unit filename="src/tiny-AES-c/aes.c">
+			<Option compilerVar="CC" />
+		</Unit>
+		<Unit filename="src/tiny-AES-c/aes.h" />
+		<Unit filename="src/tiny-AES-c/aes.hpp" />
 		<Unit filename="src/types.h" />
 		<Unit filename="src/version.h" />
 		<Unit filename="xp.manifest" />
diff --git a/src/DSi.cpp b/src/DSi.cpp
index 6a524dd..376e6a0 100644
--- a/src/DSi.cpp
+++ b/src/DSi.cpp
@@ -15,3 +15,19 @@
     You should have received a copy of the GNU General Public License along
     with melonDS. If not, see http://www.gnu.org/licenses/.
 */
+
+#include "DSi.h"
+#include "tiny-AES-c/aes.hpp"
+#include "sha1/sha1.h"
+
+namespace DSi
+{
+
+bool LoadNAND()
+{
+    //
+
+    return true;
+}
+
+}
diff --git a/src/DSi.h b/src/DSi.h
index 6a524dd..2c71ad9 100644
--- a/src/DSi.h
+++ b/src/DSi.h
@@ -15,3 +15,17 @@
     You should have received a copy of the GNU General Public License along
     with melonDS. If not, see http://www.gnu.org/licenses/.
 */
+
+#ifndef DSI_H
+#define DSI_H
+
+#include "types.h"
+
+namespace DSi
+{
+
+bool LoadNAND();
+
+}
+
+#endif // DSI_H
diff --git a/src/DSiCrypto.h b/src/DSiCrypto.h
index 6a524dd..dc9bfe6 100644
--- a/src/DSiCrypto.h
+++ b/src/DSiCrypto.h
@@ -15,3 +15,10 @@
     You should have received a copy of the GNU General Public License along
     with melonDS. If not, see http://www.gnu.org/licenses/.
 */
+
+#ifndef DSICRYPTO_H
+#define DSICRYPTO_H
+
+//
+
+#endif // DSICRYPTO_H
diff --git a/src/NDS.cpp b/src/NDS.cpp
index ea34103..f00665e 100644
--- a/src/NDS.cpp
+++ b/src/NDS.cpp
@@ -31,6 +31,8 @@
 #include "Wifi.h"
 #include "Platform.h"
 
+#include "DSi.h"
+
 
 namespace NDS
 {
@@ -83,8 +85,8 @@ u32 SchedListMask;
 
 u32 CPUStop;
 
-u8 ARM9BIOS[0x1000];
-u8 ARM7BIOS[0x4000];
+u8 ARM9BIOS[0x10000];
+u8 ARM7BIOS[0x10000];
 
 u8 MainRAM[MAIN_RAM_SIZE];
 
@@ -387,6 +389,9 @@ void Reset()
 
     LastSysClockCycles = 0;
 
+    memset(ARM9BIOS, 0, 0x10000);
+    memset(ARM7BIOS, 0, 0x10000);
+
     f = Platform::OpenLocalFile("bios9.bin", "rb");
     if (!f)
     {
@@ -421,6 +426,8 @@ void Reset()
         fclose(f);
     }
 
+    DSi::LoadNAND();
+
     // TODO for later: configure this when emulating a DSi
     ARM9ClockShift = 1;
 
@@ -1566,9 +1573,9 @@ void debug(u32 param)
 
 u8 ARM9Read8(u32 addr)
 {
-    if ((addr & 0xFFFFF000) == 0xFFFF0000)
+    if ((addr & 0xFFFF0000) == 0xFFFF0000)
     {
-        return *(u8*)&ARM9BIOS[addr & 0xFFF];
+        return *(u8*)&ARM9BIOS[addr & 0xFFFF];
     }
 
     switch (addr & 0xFF000000)
@@ -1627,9 +1634,9 @@ u8 ARM9Read8(u32 addr)
 
 u16 ARM9Read16(u32 addr)
 {
-    if ((addr & 0xFFFFF000) == 0xFFFF0000)
+    if ((addr & 0xFFFF0000) == 0xFFFF0000)
     {
-        return *(u16*)&ARM9BIOS[addr & 0xFFF];
+        return *(u16*)&ARM9BIOS[addr & 0xFFFF];
     }
 
     switch (addr & 0xFF000000)
@@ -1688,9 +1695,9 @@ u16 ARM9Read16(u32 addr)
 
 u32 ARM9Read32(u32 addr)
 {
-    if ((addr & 0xFFFFF000) == 0xFFFF0000)
+    if ((addr & 0xFFFF0000) == 0xFFFF0000)
     {
-        return *(u32*)&ARM9BIOS[addr & 0xFFF];
+        return *(u32*)&ARM9BIOS[addr & 0xFFFF];
     }
 
     switch (addr & 0xFF000000)
@@ -1896,9 +1903,10 @@ bool ARM9GetMemRegion(u32 addr, bool write, MemRegion* region)
 
 u8 ARM7Read8(u32 addr)
 {
-    if (addr < 0x00004000)
+    if (addr < 0x00010000)
     {
-        if (ARM7->R[15] >= 0x4000)
+        // TODO: check the boundary? is it 4000 or higher on regular DS?
+        if (ARM7->R[15] >= 0x00010000)
             return 0xFF;
         if (addr < ARM7BIOSProt && ARM7->R[15] >= ARM7BIOSProt)
             return 0xFF;
@@ -1952,9 +1960,9 @@ u8 ARM7Read8(u32 addr)
 
 u16 ARM7Read16(u32 addr)
 {
-    if (addr < 0x00004000)
+    if (addr < 0x00010000)
     {
-        if (ARM7->R[15] >= 0x4000)
+        if (ARM7->R[15] >= 0x00010000)
             return 0xFFFF;
         if (addr < ARM7BIOSProt && ARM7->R[15] >= ARM7BIOSProt)
             return 0xFFFF;
@@ -2015,9 +2023,9 @@ u16 ARM7Read16(u32 addr)
 
 u32 ARM7Read32(u32 addr)
 {
-    if (addr < 0x00004000)
+    if (addr < 0x00010000)
     {
-        if (ARM7->R[15] >= 0x4000)
+        if (ARM7->R[15] >= 0x00010000)
             return 0xFFFFFFFF;
         if (addr < ARM7BIOSProt && ARM7->R[15] >= ARM7BIOSProt)
             return 0xFFFFFFFF;
diff --git a/src/NDS.h b/src/NDS.h
index 9b7a10a..e8bb44d 100644
--- a/src/NDS.h
+++ b/src/NDS.h
@@ -117,8 +117,8 @@ extern u16 ExMemCnt[2];
 extern u8 ROMSeed0[2*8];
 extern u8 ROMSeed1[2*8];
 
-extern u8 ARM9BIOS[0x1000];
-extern u8 ARM7BIOS[0x4000];
+extern u8 ARM9BIOS[0x10000];
+extern u8 ARM7BIOS[0x10000];
 
 //#define MAIN_RAM_SIZE 0x400000
 #define MAIN_RAM_SIZE 0x1000000
diff --git a/src/sha1/sha1.c b/src/sha1/sha1.c
new file mode 100644
index 0000000..2c50433
--- /dev/null
+++ b/src/sha1/sha1.c
@@ -0,0 +1,276 @@
+
+/* from valgrind tests */
+
+/* ================ sha1.c ================ */
+/*
+SHA-1 in C
+By Steve Reid <steve@edmweb.com>
+100% Public Domain
+
+Test Vectors (from FIPS PUB 180-1)
+"abc"
+  A9993E36 4706816A BA3E2571 7850C26C 9CD0D89D
+"abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq"
+  84983E44 1C3BD26E BAAE4AA1 F95129E5 E54670F1
+A million repetitions of "a"
+  34AA973C D4C4DAA4 F61EEB2B DBAD2731 6534016F
+*/
+
+/* #define LITTLE_ENDIAN * This should be #define'd already, if true. */
+/* #define SHA1HANDSOFF * Copies data before messing with it. */
+
+#define SHA1HANDSOFF
+
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>	/* for u_int*_t */
+#if defined(__sun)
+#include "solarisfixes.h"
+#endif
+#include "sha1.h"
+
+#ifndef BYTE_ORDER
+#if (BSD >= 199103)
+# include <machine/endian.h>
+#else
+#if defined(linux) || defined(__linux__)
+# include <endian.h>
+#else
+#define	LITTLE_ENDIAN	1234	/* least-significant byte first (vax, pc) */
+#define	BIG_ENDIAN	4321	/* most-significant byte first (IBM, net) */
+#define	PDP_ENDIAN	3412	/* LSB first in word, MSW first in long (pdp)*/
+
+#if defined(vax) || defined(ns32000) || defined(sun386) || defined(__i386__) || \
+    defined(MIPSEL) || defined(_MIPSEL) || defined(BIT_ZERO_ON_RIGHT) || \
+    defined(__alpha__) || defined(__alpha)
+#define BYTE_ORDER	LITTLE_ENDIAN
+#endif
+
+#if defined(sel) || defined(pyr) || defined(mc68000) || defined(sparc) || \
+    defined(is68k) || defined(tahoe) || defined(ibm032) || defined(ibm370) || \
+    defined(MIPSEB) || defined(_MIPSEB) || defined(_IBMR2) || defined(DGUX) ||\
+    defined(apollo) || defined(__convex__) || defined(_CRAY) || \
+    defined(__hppa) || defined(__hp9000) || \
+    defined(__hp9000s300) || defined(__hp9000s700) || \
+    defined (BIT_ZERO_ON_LEFT) || defined(m68k) || defined(__sparc)
+#define BYTE_ORDER	BIG_ENDIAN
+#endif
+#endif /* linux */
+#endif /* BSD */
+#endif /* BYTE_ORDER */
+
+#if defined(__BYTE_ORDER) && !defined(BYTE_ORDER)
+#if (__BYTE_ORDER == __LITTLE_ENDIAN)
+#define BYTE_ORDER LITTLE_ENDIAN
+#else
+#define BYTE_ORDER BIG_ENDIAN
+#endif
+#endif
+
+#if !defined(BYTE_ORDER) || \
+    (BYTE_ORDER != BIG_ENDIAN && BYTE_ORDER != LITTLE_ENDIAN && \
+    BYTE_ORDER != PDP_ENDIAN)
+	/* you must determine what the correct bit order is for
+	 * your compiler - the next line is an intentional error
+	 * which will force your compiles to bomb until you fix
+	 * the above macros.
+	 */
+#error "Undefined or invalid BYTE_ORDER"
+#endif
+
+#define rol(value, bits) (((value) << (bits)) | ((value) >> (32 - (bits))))
+
+/* blk0() and blk() perform the initial expand. */
+/* I got the idea of expanding during the round function from SSLeay */
+#if BYTE_ORDER == LITTLE_ENDIAN
+#define blk0(i) (block->l[i] = (rol(block->l[i],24)&0xFF00FF00) \
+    |(rol(block->l[i],8)&0x00FF00FF))
+#elif BYTE_ORDER == BIG_ENDIAN
+#define blk0(i) block->l[i]
+#else
+#error "Endianness not defined!"
+#endif
+#define blk(i) (block->l[i&15] = rol(block->l[(i+13)&15]^block->l[(i+8)&15] \
+    ^block->l[(i+2)&15]^block->l[i&15],1))
+
+/* (R0+R1), R2, R3, R4 are the different operations used in SHA1 */
+#define R0(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk0(i)+0x5A827999+rol(v,5);w=rol(w,30);
+#define R1(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk(i)+0x5A827999+rol(v,5);w=rol(w,30);
+#define R2(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0x6ED9EBA1+rol(v,5);w=rol(w,30);
+#define R3(v,w,x,y,z,i) z+=(((w|x)&y)|(w&x))+blk(i)+0x8F1BBCDC+rol(v,5);w=rol(w,30);
+#define R4(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0xCA62C1D6+rol(v,5);w=rol(w,30);
+
+
+/* Hash a single 512-bit block. This is the core of the algorithm. */
+
+void SHA1Transform(u_int32_t state[5], const unsigned char buffer[64])
+{
+u_int32_t a, b, c, d, e;
+typedef union {
+    unsigned char c[64];
+    u_int32_t l[16];
+} CHAR64LONG16;
+#ifdef SHA1HANDSOFF
+CHAR64LONG16 block[1];  /* use array to appear as a pointer */
+    memcpy(block, buffer, 64);
+#else
+    /* The following had better never be used because it causes the
+     * pointer-to-const buffer to be cast into a pointer to non-const.
+     * And the result is written through.  I threw a "const" in, hoping
+     * this will cause a diagnostic.
+     */
+CHAR64LONG16* block = (const CHAR64LONG16*)buffer;
+#endif
+    /* Copy context->state[] to working vars */
+    a = state[0];
+    b = state[1];
+    c = state[2];
+    d = state[3];
+    e = state[4];
+    /* 4 rounds of 20 operations each. Loop unrolled. */
+    R0(a,b,c,d,e, 0); R0(e,a,b,c,d, 1); R0(d,e,a,b,c, 2); R0(c,d,e,a,b, 3);
+    R0(b,c,d,e,a, 4); R0(a,b,c,d,e, 5); R0(e,a,b,c,d, 6); R0(d,e,a,b,c, 7);
+    R0(c,d,e,a,b, 8); R0(b,c,d,e,a, 9); R0(a,b,c,d,e,10); R0(e,a,b,c,d,11);
+    R0(d,e,a,b,c,12); R0(c,d,e,a,b,13); R0(b,c,d,e,a,14); R0(a,b,c,d,e,15);
+    R1(e,a,b,c,d,16); R1(d,e,a,b,c,17); R1(c,d,e,a,b,18); R1(b,c,d,e,a,19);
+    R2(a,b,c,d,e,20); R2(e,a,b,c,d,21); R2(d,e,a,b,c,22); R2(c,d,e,a,b,23);
+    R2(b,c,d,e,a,24); R2(a,b,c,d,e,25); R2(e,a,b,c,d,26); R2(d,e,a,b,c,27);
+    R2(c,d,e,a,b,28); R2(b,c,d,e,a,29); R2(a,b,c,d,e,30); R2(e,a,b,c,d,31);
+    R2(d,e,a,b,c,32); R2(c,d,e,a,b,33); R2(b,c,d,e,a,34); R2(a,b,c,d,e,35);
+    R2(e,a,b,c,d,36); R2(d,e,a,b,c,37); R2(c,d,e,a,b,38); R2(b,c,d,e,a,39);
+    R3(a,b,c,d,e,40); R3(e,a,b,c,d,41); R3(d,e,a,b,c,42); R3(c,d,e,a,b,43);
+    R3(b,c,d,e,a,44); R3(a,b,c,d,e,45); R3(e,a,b,c,d,46); R3(d,e,a,b,c,47);
+    R3(c,d,e,a,b,48); R3(b,c,d,e,a,49); R3(a,b,c,d,e,50); R3(e,a,b,c,d,51);
+    R3(d,e,a,b,c,52); R3(c,d,e,a,b,53); R3(b,c,d,e,a,54); R3(a,b,c,d,e,55);
+    R3(e,a,b,c,d,56); R3(d,e,a,b,c,57); R3(c,d,e,a,b,58); R3(b,c,d,e,a,59);
+    R4(a,b,c,d,e,60); R4(e,a,b,c,d,61); R4(d,e,a,b,c,62); R4(c,d,e,a,b,63);
+    R4(b,c,d,e,a,64); R4(a,b,c,d,e,65); R4(e,a,b,c,d,66); R4(d,e,a,b,c,67);
+    R4(c,d,e,a,b,68); R4(b,c,d,e,a,69); R4(a,b,c,d,e,70); R4(e,a,b,c,d,71);
+    R4(d,e,a,b,c,72); R4(c,d,e,a,b,73); R4(b,c,d,e,a,74); R4(a,b,c,d,e,75);
+    R4(e,a,b,c,d,76); R4(d,e,a,b,c,77); R4(c,d,e,a,b,78); R4(b,c,d,e,a,79);
+    /* Add the working vars back into context.state[] */
+    state[0] += a;
+    state[1] += b;
+    state[2] += c;
+    state[3] += d;
+    state[4] += e;
+    /* Wipe variables */
+    a = b = c = d = e = 0;
+#ifdef SHA1HANDSOFF
+    memset(block, '\0', sizeof(block));
+#endif
+}
+
+
+/* SHA1Init - Initialize new context */
+
+void SHA1Init(SHA1_CTX* context)
+{
+    /* SHA1 initialization constants */
+    context->state[0] = 0x67452301;
+    context->state[1] = 0xEFCDAB89;
+    context->state[2] = 0x98BADCFE;
+    context->state[3] = 0x10325476;
+    context->state[4] = 0xC3D2E1F0;
+    context->count[0] = context->count[1] = 0;
+}
+
+
+/* Run your data through this. */
+
+void SHA1Update(SHA1_CTX* context, const unsigned char* data, u_int32_t len)
+{
+u_int32_t i;
+u_int32_t j;
+
+    j = context->count[0];
+    if ((context->count[0] += len << 3) < j)
+	context->count[1]++;
+    context->count[1] += (len>>29);
+    j = (j >> 3) & 63;
+    if ((j + len) > 63) {
+        memcpy(&context->buffer[j], data, (i = 64-j));
+        SHA1Transform(context->state, context->buffer);
+        for ( ; i + 63 < len; i += 64) {
+            SHA1Transform(context->state, &data[i]);
+        }
+        j = 0;
+    }
+    else i = 0;
+    memcpy(&context->buffer[j], &data[i], len - i);
+}
+
+
+/* Add padding and return the message digest. */
+
+void SHA1Final(unsigned char digest[20], SHA1_CTX* context)
+{
+unsigned i;
+unsigned char finalcount[8];
+unsigned char c;
+
+#if 0	/* untested "improvement" by DHR */
+    /* Convert context->count to a sequence of bytes
+     * in finalcount.  Second element first, but
+     * big-endian order within element.
+     * But we do it all backwards.
+     */
+    unsigned char *fcp = &finalcount[8];
+
+    for (i = 0; i < 2; i++)
+    {
+	u_int32_t t = context->count[i];
+	int j;
+
+	for (j = 0; j < 4; t >>= 8, j++)
+	    *--fcp = (unsigned char) t
+    }
+#else
+    for (i = 0; i < 8; i++) {
+        finalcount[i] = (unsigned char)((context->count[(i >= 4 ? 0 : 1)]
+         >> ((3-(i & 3)) * 8) ) & 255);  /* Endian independent */
+    }
+#endif
+    c = 0200;
+    SHA1Update(context, &c, 1);
+    while ((context->count[0] & 504) != 448) {
+	c = 0000;
+        SHA1Update(context, &c, 1);
+    }
+    SHA1Update(context, finalcount, 8);  /* Should cause a SHA1Transform() */
+    for (i = 0; i < 20; i++) {
+        digest[i] = (unsigned char)
+         ((context->state[i>>2] >> ((3-(i & 3)) * 8) ) & 255);
+    }
+    /* Wipe variables */
+    memset(context, '\0', sizeof(*context));
+    memset(&finalcount, '\0', sizeof(finalcount));
+}
+/* ================ end of sha1.c ================ */
+
+#if 0
+#define BUFSIZE 4096
+
+int
+main(int argc, char **argv)
+{
+    SHA1_CTX ctx;
+    unsigned char hash[20], buf[BUFSIZE];
+    int i;
+
+    for(i=0;i<BUFSIZE;i++)
+        buf[i] = i;
+
+    SHA1Init(&ctx);
+    for(i=0;i<1000;i++)
+        SHA1Update(&ctx, buf, BUFSIZE);
+    SHA1Final(hash, &ctx);
+
+    printf("SHA1=");
+    for(i=0;i<20;i++)
+        printf("%02x", hash[i]);
+    printf("\n");
+    return 0;
+}
+
+#endif
diff --git a/src/sha1/sha1.h b/src/sha1/sha1.h
new file mode 100644
index 0000000..9d6f129
--- /dev/null
+++ b/src/sha1/sha1.h
@@ -0,0 +1,17 @@
+/* ================ sha1.h ================ */
+/*
+SHA-1 in C
+By Steve Reid <steve@edmweb.com>
+100% Public Domain
+*/
+
+typedef struct {
+    u_int32_t state[5];
+    u_int32_t count[2];
+    unsigned char buffer[64];
+} SHA1_CTX;
+
+void SHA1Transform(u_int32_t state[5], const unsigned char buffer[64]);
+void SHA1Init(SHA1_CTX* context);
+void SHA1Update(SHA1_CTX* context, const unsigned char* data, u_int32_t len);
+void SHA1Final(unsigned char digest[20], SHA1_CTX* context);
diff --git a/src/tiny-AES-c/README.md b/src/tiny-AES-c/README.md
new file mode 100644
index 0000000..e32e25e
--- /dev/null
+++ b/src/tiny-AES-c/README.md
@@ -0,0 +1,80 @@
+### Tiny AES in C
+
+This is a small and portable implementation of the AES [ECB](https://en.wikipedia.org/wiki/Block_cipher_mode_of_operation#Electronic_Codebook_.28ECB.29), [CTR](https://en.wikipedia.org/wiki/Block_cipher_mode_of_operation#Counter_.28CTR.29) and [CBC](https://en.wikipedia.org/wiki/Block_cipher_mode_of_operation#Cipher_Block_Chaining_.28CBC.29) encryption algorithms written in C.
+
+You can override the default key-size of 128 bit with 192 or 256 bit by defining the symbols AES192 or AES256 in `aes.h`.
+
+The API is very simple and looks like this (I am using C99 `<stdint.h>`-style annotated types):
+
+```C
+/* Initialize context calling one of: */
+void AES_init_ctx(struct AES_ctx* ctx, const uint8_t* key);
+void AES_init_ctx_iv(struct AES_ctx* ctx, const uint8_t* key, const uint8_t* iv);
+
+/* ... or reset IV at random point: */
+void AES_ctx_set_iv(struct AES_ctx* ctx, const uint8_t* iv);
+
+/* Then start encrypting and decrypting with the functions below: */
+void AES_ECB_encrypt(const struct AES_ctx* ctx, uint8_t* buf);
+void AES_ECB_decrypt(const struct AES_ctx* ctx, uint8_t* buf);
+
+void AES_CBC_encrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, uint32_t length);
+void AES_CBC_decrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, uint32_t length);
+
+/* Same function for encrypting as for decrypting in CTR mode */
+void AES_CTR_xcrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, uint32_t length);
+```
+
+Note: 
+ * No padding is provided so for CBC and ECB all buffers should be multiples of 16 bytes. For padding [PKCS7](https://en.wikipedia.org/wiki/Padding_(cryptography)#PKCS7) is recommendable.
+ * ECB mode is considered unsafe for most uses and is not implemented in streaming mode. If you need this mode, call the function for every block of 16 bytes you need encrypted. See [wikipedia's article on ECB](https://en.wikipedia.org/wiki/Block_cipher_mode_of_operation#Electronic_Codebook_(ECB)) for more details.
+
+You can choose to use any or all of the modes-of-operations, by defining the symbols CBC, CTR or ECB. See the header file for clarification.
+
+C++ users should `#include` [aes.hpp](https://github.com/kokke/tiny-AES-c/blob/master/aes.hpp) instead of [aes.h](https://github.com/kokke/tiny-AES-c/blob/master/aes.h)
+
+There is no built-in error checking or protection from out-of-bounds memory access errors as a result of malicious input.
+
+The module uses less than 200 bytes of RAM and 1-2K ROM when compiled for ARM, but YMMV depending on which modes are enabled.
+
+It is one of the smallest implementations in C I've seen yet, but do contact me if you know of something smaller (or have improvements to the code here). 
+
+I've successfully used the code on 64bit x86, 32bit ARM and 8 bit AVR platforms.
+
+
+GCC size output when only CTR mode is compiled for ARM:
+
+    $ arm-none-eabi-gcc -Os -DCBC=0 -DECB=0 -DCTR=1 -c aes.c
+    $ size aes.o
+       text    data     bss     dec     hex filename
+       1343       0       0    1343     53f aes.o
+
+.. and when compiling for the THUMB instruction set, we end up just below 1K in code size.
+
+    $ arm-none-eabi-gcc -Os -mthumb -DCBC=0 -DECB=0 -DCTR=1 -c aes.c
+    $ size aes.o
+       text    data     bss     dec     hex filename
+        979       0       0     979     3d3 aes.o
+
+
+I am using the Free Software Foundation, ARM GCC compiler:
+
+    $ arm-none-eabi-gcc --version
+    arm-none-eabi-gcc (GNU Tools for Arm Embedded Processors 8-2018-q4-major) 8.2.1 20181213 (release)
+    Copyright (C) 2018 Free Software Foundation, Inc.
+    This is free software; see the source for copying conditions.  There is NO
+    warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+
+
+
+This implementation is verified against the data in:
+
+[National Institute of Standards and Technology Special Publication 800-38A 2001 ED](http://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-38a.pdf) Appendix F: Example Vectors for Modes of Operation of the AES.
+
+The other appendices in the document are valuable for implementation details on e.g. padding, generation of IVs and nonces in CTR-mode etc.
+
+
+A heartfelt thank-you to all the nice people out there who have contributed to this project.
+
+
+All material in this repository is in the public domain.
diff --git a/src/tiny-AES-c/aes.c b/src/tiny-AES-c/aes.c
new file mode 100644
index 0000000..313ff71
--- /dev/null
+++ b/src/tiny-AES-c/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 <stdint.h>
+#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 };
+
+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 };
+
+// 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)])
+/*
+static uint8_t getSBoxInvert(uint8_t num)
+{
+  return rsbox[num];
+}
+*/
+#define getSBoxInvert(num) (rsbox[(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)
+// 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-1 rounds are executed in the loop below.
+  for (round = 1; round < Nr; ++round)
+  {
+    SubBytes(state);
+    ShiftRows(state);
+    MixColumns(state);
+    AddRoundKey(round, state, RoundKey);
+  }
+  
+  // The last round is given below.
+  // The MixColumns function is not here in the last round.
+  SubBytes(state);
+  ShiftRows(state);
+  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-1 rounds are executed in the loop below.
+  for (round = (Nr - 1); round > 0; --round)
+  {
+    InvShiftRows(state);
+    InvSubBytes(state);
+    AddRoundKey(round, state, RoundKey);
+    InvMixColumns(state);
+  }
+  
+  // The last round is given below.
+  // The MixColumns function is not here in the last round.
+  InvShiftRows(state);
+  InvSubBytes(state);
+  AddRoundKey(0, state, RoundKey);
+}
+#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, uint32_t length)
+{
+  uintptr_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;
+    //printf("Step %d - %d", i/16, i);
+  }
+  /* 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,  uint32_t length)
+{
+  uintptr_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, uint32_t length)
+{
+  uint8_t buffer[AES_BLOCKLEN];
+  
+  unsigned 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/src/tiny-AES-c/aes.h b/src/tiny-AES-c/aes.h
new file mode 100644
index 0000000..87f1471
--- /dev/null
+++ b/src/tiny-AES-c/aes.h
@@ -0,0 +1,90 @@
+#ifndef _AES_H_
+#define _AES_H_
+
+#include <stdint.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 1
+#endif
+
+#ifndef CTR
+  #define CTR 1
+#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, uint32_t length);
+void AES_CBC_decrypt_buffer(struct AES_ctx* ctx, uint8_t* buf, uint32_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, uint32_t length);
+
+#endif // #if defined(CTR) && (CTR == 1)
+
+
+#endif //_AES_H_
diff --git a/src/tiny-AES-c/aes.hpp b/src/tiny-AES-c/aes.hpp
new file mode 100644
index 0000000..ade1642
--- /dev/null
+++ b/src/tiny-AES-c/aes.hpp
@@ -0,0 +1,12 @@
+#ifndef _AES_HPP_
+#define _AES_HPP_
+
+#ifndef __cplusplus
+#error Do not include the hpp header in a c project!
+#endif //__cplusplus
+
+extern "C" {
+#include "aes.h"
+}
+
+#endif //_AES_HPP_
diff --git a/src/tiny-AES-c/unlicense.txt b/src/tiny-AES-c/unlicense.txt
new file mode 100644
index 0000000..68a49da
--- /dev/null
+++ b/src/tiny-AES-c/unlicense.txt
@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <http://unlicense.org/>