Optimized for size over speed to (substantially) reduce generated code size.

libcrypt/md5.c

@@ -41,6 +41,14 @@
  * On April 19th, 2001 md5_crypt() was modified to make it reentrant 
  * by Erik Andersen <andersen@lineo.com>, <andersee@debian.org>
  *
+ * June 28, 2001             Manuel Novoa III
+ *
+ * "Un-inlined" code using loops and static const tables in order to
+ * reduce generated code size (on i386 from approx 4k to approx 2.5k).
+ *
+ * WARNING!!! Changed PADDING array from a staticly allocated object to
+ *            a dynamicly generated one.  Although it was declared static
+ *            and not static const, it doesn't appear that it ever changes.
  */
 
 #include <sys/types.h>
@@ -125,12 +133,6 @@ Decode (output, input, len)
 }
 #endif /* i386 */
 
-static unsigned char PADDING[64] = {
-  0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-};
-
 /* F, G, H and I are basic MD5 functions. */
 #define F(x, y, z) (((x) & (y)) | ((~x) & (z)))
 #define G(x, y, z) (((x) & (z)) | ((y) & (~z)))
@@ -169,7 +171,6 @@ static unsigned char PADDING[64] = {
 
 void MD5Init (MD5_CTX *context)
 {
-
 	context->count[0] = context->count[1] = 0;
 
 	/* Load magic initialization constants.  */
@@ -223,11 +224,29 @@ void MD5Update ( MD5_CTX *context, const unsigned char *input, unsigned int inpu
  * MD5 padding. Adds padding followed by original length.
  */
 
+#define STATIC_PADDING 0
+#if STATIC_PADDING
+static unsigned char PADDING[64] = {
+  0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+#endif
+
 void MD5Pad ( MD5_CTX *context)
 {
 	unsigned char bits[8];
 	unsigned int index, padLen;
 
+#if !STATIC_PADDING
+	unsigned char PADDING[64];
+
+	for (index = 0 ; index < sizeof(PADDING) ; index++) {
+		PADDING[index] = 0;
+	}
+	PADDING[0] = 0x80;
+#endif
+
 	/* Save number of bits */
 	Encode (bits, context->count, 8);
 
@@ -264,97 +283,76 @@ MD5Transform (state, block)
 	u_int32_t state[4];
 	const unsigned char block[64];
 {
-	u_int32_t a = state[0], b = state[1], c = state[2], d = state[3], x[16];
+	u_int32_t a, b, c, d, x[16], temp;
+	int i;
+
+	static const int S1[] = { 7, 12, 17, 22 };
+	static const u_int32_t C1[] = {
+		0xd76aa478, 0xe8c7b756, 0x242070db, 0xc1bdceee,
+		0xf57c0faf, 0x4787c62a, 0xa8304613, 0xfd469501,
+		0x698098d8, 0x8b44f7af, 0xffff5bb1, 0x895cd7be,
+		0x6b901122, 0xfd987193, 0xa679438e, 0x49b40821
+	};
+
+	static const int p2[] = {
+		1, 6, 11, 0, 5, 10, 15, 4, 9, 14, 3, 8, 13, 2, 7, 12
+	};
+	static const int S2[] = { 5, 9, 14, 20 };
+	static const u_int32_t C2[] = {
+		0xf61e2562, 0xc040b340, 0x265e5a51, 0xe9b6c7aa,
+		0xd62f105d, 0x2441453,  0xd8a1e681, 0xe7d3fbc8,
+		0x21e1cde6, 0xc33707d6, 0xf4d50d87, 0x455a14ed,
+		0xa9e3e905, 0xfcefa3f8, 0x676f02d9, 0x8d2a4c8a
+	};
+	
+	static const int p3[] = {
+		5, 8, 11, 14, 1, 4, 7, 10, 13, 0, 3, 6, 9, 12, 15, 2
+	};
+	static const int S3[] = { 4, 11, 16, 23 };
+	static const u_int32_t C3[] = {
+		0xfffa3942, 0x8771f681, 0x6d9d6122, 0xfde5380c,
+		0xa4beea44, 0x4bdecfa9, 0xf6bb4b60, 0xbebfbc70,
+		0x289b7ec6, 0xeaa127fa, 0xd4ef3085, 0x4881d05,
+		0xd9d4d039, 0xe6db99e5, 0x1fa27cf8, 0xc4ac5665
+	};
+
+	static const int p4[] = {
+		0, 7, 14, 5, 12, 3, 10, 1, 8, 15, 6, 13, 4, 11, 2, 9
+	};
+	static const int S4[] = { 6, 10, 15, 21 };
+	static const u_int32_t C4[] = {
+		0xf4292244, 0x432aff97, 0xab9423a7, 0xfc93a039,
+		0x655b59c3, 0x8f0ccc92, 0xffeff47d, 0x85845dd1,
+		0x6fa87e4f, 0xfe2ce6e0, 0xa3014314, 0x4e0811a1,
+		0xf7537e82, 0xbd3af235, 0x2ad7d2bb, 0xeb86d391
+	};
 
 	Decode (x, block, 64);
 
+	a = state[0]; b = state[1]; c = state[2]; d = state[3]; 
+
 	/* Round 1 */
-#define S11 7
-#define S12 12
-#define S13 17
-#define S14 22
-	FF (a, b, c, d, x[ 0], S11, 0xd76aa478); /* 1 */
-	FF (d, a, b, c, x[ 1], S12, 0xe8c7b756); /* 2 */
-	FF (c, d, a, b, x[ 2], S13, 0x242070db); /* 3 */
-	FF (b, c, d, a, x[ 3], S14, 0xc1bdceee); /* 4 */
-	FF (a, b, c, d, x[ 4], S11, 0xf57c0faf); /* 5 */
-	FF (d, a, b, c, x[ 5], S12, 0x4787c62a); /* 6 */
-	FF (c, d, a, b, x[ 6], S13, 0xa8304613); /* 7 */
-	FF (b, c, d, a, x[ 7], S14, 0xfd469501); /* 8 */
-	FF (a, b, c, d, x[ 8], S11, 0x698098d8); /* 9 */
-	FF (d, a, b, c, x[ 9], S12, 0x8b44f7af); /* 10 */
-	FF (c, d, a, b, x[10], S13, 0xffff5bb1); /* 11 */
-	FF (b, c, d, a, x[11], S14, 0x895cd7be); /* 12 */
-	FF (a, b, c, d, x[12], S11, 0x6b901122); /* 13 */
-	FF (d, a, b, c, x[13], S12, 0xfd987193); /* 14 */
-	FF (c, d, a, b, x[14], S13, 0xa679438e); /* 15 */
-	FF (b, c, d, a, x[15], S14, 0x49b40821); /* 16 */
+	for ( i = 0 ; i < 16 ; i++ ) {
+		FF (a, b, c, d, x[i], S1[i&3], C1[i]);
+		temp = d; d= c; c = b; b = a; a = temp;
+	}
 
 	/* Round 2 */
-#define S21 5
-#define S22 9
-#define S23 14
-#define S24 20
-	GG (a, b, c, d, x[ 1], S21, 0xf61e2562); /* 17 */
-	GG (d, a, b, c, x[ 6], S22, 0xc040b340); /* 18 */
-	GG (c, d, a, b, x[11], S23, 0x265e5a51); /* 19 */
-	GG (b, c, d, a, x[ 0], S24, 0xe9b6c7aa); /* 20 */
-	GG (a, b, c, d, x[ 5], S21, 0xd62f105d); /* 21 */
-	GG (d, a, b, c, x[10], S22,  0x2441453); /* 22 */
-	GG (c, d, a, b, x[15], S23, 0xd8a1e681); /* 23 */
-	GG (b, c, d, a, x[ 4], S24, 0xe7d3fbc8); /* 24 */
-	GG (a, b, c, d, x[ 9], S21, 0x21e1cde6); /* 25 */
-	GG (d, a, b, c, x[14], S22, 0xc33707d6); /* 26 */
-	GG (c, d, a, b, x[ 3], S23, 0xf4d50d87); /* 27 */
-	GG (b, c, d, a, x[ 8], S24, 0x455a14ed); /* 28 */
-	GG (a, b, c, d, x[13], S21, 0xa9e3e905); /* 29 */
-	GG (d, a, b, c, x[ 2], S22, 0xfcefa3f8); /* 30 */
-	GG (c, d, a, b, x[ 7], S23, 0x676f02d9); /* 31 */
-	GG (b, c, d, a, x[12], S24, 0x8d2a4c8a); /* 32 */
-
+	for ( i = 0 ; i < 16 ; i++ ) {
+		GG (a, b, c, d, x[p2[i]], S2[i&3], C2[i]);
+		temp = d; d= c; c = b; b = a; a = temp;
+	}
 	/* Round 3 */
-#define S31 4
-#define S32 11
-#define S33 16
-#define S34 23
-	HH (a, b, c, d, x[ 5], S31, 0xfffa3942); /* 33 */
-	HH (d, a, b, c, x[ 8], S32, 0x8771f681); /* 34 */
-	HH (c, d, a, b, x[11], S33, 0x6d9d6122); /* 35 */
-	HH (b, c, d, a, x[14], S34, 0xfde5380c); /* 36 */
-	HH (a, b, c, d, x[ 1], S31, 0xa4beea44); /* 37 */
-	HH (d, a, b, c, x[ 4], S32, 0x4bdecfa9); /* 38 */
-	HH (c, d, a, b, x[ 7], S33, 0xf6bb4b60); /* 39 */
-	HH (b, c, d, a, x[10], S34, 0xbebfbc70); /* 40 */
-	HH (a, b, c, d, x[13], S31, 0x289b7ec6); /* 41 */
-	HH (d, a, b, c, x[ 0], S32, 0xeaa127fa); /* 42 */
-	HH (c, d, a, b, x[ 3], S33, 0xd4ef3085); /* 43 */
-	HH (b, c, d, a, x[ 6], S34,  0x4881d05); /* 44 */
-	HH (a, b, c, d, x[ 9], S31, 0xd9d4d039); /* 45 */
-	HH (d, a, b, c, x[12], S32, 0xe6db99e5); /* 46 */
-	HH (c, d, a, b, x[15], S33, 0x1fa27cf8); /* 47 */
-	HH (b, c, d, a, x[ 2], S34, 0xc4ac5665); /* 48 */
+	for ( i = 0 ; i < 16 ; i++ ) {
+		HH (a, b, c, d, x[p3[i]], S3[i&3], C3[i]);
+		temp = d; d= c; c = b; b = a; a = temp;
+	}
 
 	/* Round 4 */
-#define S41 6
-#define S42 10
-#define S43 15
-#define S44 21
-	II (a, b, c, d, x[ 0], S41, 0xf4292244); /* 49 */
-	II (d, a, b, c, x[ 7], S42, 0x432aff97); /* 50 */
-	II (c, d, a, b, x[14], S43, 0xab9423a7); /* 51 */
-	II (b, c, d, a, x[ 5], S44, 0xfc93a039); /* 52 */
-	II (a, b, c, d, x[12], S41, 0x655b59c3); /* 53 */
-	II (d, a, b, c, x[ 3], S42, 0x8f0ccc92); /* 54 */
-	II (c, d, a, b, x[10], S43, 0xffeff47d); /* 55 */
-	II (b, c, d, a, x[ 1], S44, 0x85845dd1); /* 56 */
-	II (a, b, c, d, x[ 8], S41, 0x6fa87e4f); /* 57 */
-	II (d, a, b, c, x[15], S42, 0xfe2ce6e0); /* 58 */
-	II (c, d, a, b, x[ 6], S43, 0xa3014314); /* 59 */
-	II (b, c, d, a, x[13], S44, 0x4e0811a1); /* 60 */
-	II (a, b, c, d, x[ 4], S41, 0xf7537e82); /* 61 */
-	II (d, a, b, c, x[11], S42, 0xbd3af235); /* 62 */
-	II (c, d, a, b, x[ 2], S43, 0x2ad7d2bb); /* 63 */
-	II (b, c, d, a, x[ 9], S44, 0xeb86d391); /* 64 */
+	for ( i = 0 ; i < 16 ; i++ ) {
+		II (a, b, c, d, x[p4[i]], S4[i&3], C4[i]);
+		temp = d; d= c; c = b; b = a; a = temp;
+	}
 
 	state[0] += a;
 	state[1] += b;
@@ -386,8 +384,8 @@ char * md5_crypt_r( const char *pw, const char *salt, struct crypt_data * data)
 	const char *sp = data->sp;
 	const char *ep = data->ep;
 	char *passwd = *data->KS;
-	unsigned char	final[16];
-	int sl,pl,i;
+	unsigned char	final[17];	/* final[16] exists only to aid in looping */
+	int sl,pl,i,md5_magic_len,pw_len;
 	MD5_CTX	ctx,ctx1;
 	unsigned long l;
 
@@ -395,8 +393,9 @@ char * md5_crypt_r( const char *pw, const char *salt, struct crypt_data * data)
 	sp = salt;
 
 	/* If it starts with the magic string, then skip that */
-	if(!strncmp(sp,md5_magic,strlen(md5_magic)))
-		sp += strlen(md5_magic);
+	md5_magic_len = strlen(md5_magic);
+	if(!strncmp(sp,md5_magic,md5_magic_len))
+		sp += md5_magic_len;
 
 	/* It stops at the first '$', max 8 chars */
 	for(ep=sp;*ep && *ep != '$' && ep < (sp+8);ep++)
@@ -408,32 +407,31 @@ char * md5_crypt_r( const char *pw, const char *salt, struct crypt_data * data)
 	MD5Init(&ctx);
 
 	/* The password first, since that is what is most unknown */
-	MD5Update(&ctx,pw,strlen(pw));
+	pw_len = strlen(pw);
+	MD5Update(&ctx,pw,pw_len);
 
 	/* Then our magic string */
-	MD5Update(&ctx,md5_magic,strlen(md5_magic));
+	MD5Update(&ctx,md5_magic,md5_magic_len);
 
 	/* Then the raw salt */
 	MD5Update(&ctx,sp,sl);
 
 	/* Then just as many characters of the MD5(pw,salt,pw) */
 	MD5Init(&ctx1);
-	MD5Update(&ctx1,pw,strlen(pw));
+	MD5Update(&ctx1,pw,pw_len);
 	MD5Update(&ctx1,sp,sl);
-	MD5Update(&ctx1,pw,strlen(pw));
+	MD5Update(&ctx1,pw,pw_len);
 	MD5Final(final,&ctx1);
-	for(pl = strlen(pw); pl > 0; pl -= 16)
+	for(pl = pw_len; pl > 0; pl -= 16)
 		MD5Update(&ctx,final,pl>16 ? 16 : pl);
 
 	/* Don't leave anything around in vm they could use. */
 	memset(final,0,sizeof final);
 
 	/* Then something really weird... */
-	for (i = strlen(pw); i ; i >>= 1)
-		if(i&1)
-		    MD5Update(&ctx, final, 1);
-		else
-		    MD5Update(&ctx, pw, 1);
+	for (i = pw_len; i ; i >>= 1) {
+		MD5Update(&ctx, ((i&1) ? final : (const unsigned char *) pw), 1);
+	}
 
 	/* Now make the output string */
 	strcpy(passwd,md5_magic);
@@ -450,7 +448,7 @@ char * md5_crypt_r( const char *pw, const char *salt, struct crypt_data * data)
 	for(i=0;i<1000;i++) {
 		MD5Init(&ctx1);
 		if(i & 1)
-			MD5Update(&ctx1,pw,strlen(pw));
+			MD5Update(&ctx1,pw,pw_len);
 		else
 			MD5Update(&ctx1,final,16);
 
@@ -458,23 +456,24 @@ char * md5_crypt_r( const char *pw, const char *salt, struct crypt_data * data)
 			MD5Update(&ctx1,sp,sl);
 
 		if(i % 7)
-			MD5Update(&ctx1,pw,strlen(pw));
+			MD5Update(&ctx1,pw,pw_len);
 
 		if(i & 1)
 			MD5Update(&ctx1,final,16);
 		else
-			MD5Update(&ctx1,pw,strlen(pw));
+			MD5Update(&ctx1,pw,pw_len);
 		MD5Final(final,&ctx1);
 	}
 
 	p = passwd + strlen(passwd);
 
-	l = (final[ 0]<<16) | (final[ 6]<<8) | final[12]; to64(p,l,4); p += 4;
-	l = (final[ 1]<<16) | (final[ 7]<<8) | final[13]; to64(p,l,4); p += 4;
-	l = (final[ 2]<<16) | (final[ 8]<<8) | final[14]; to64(p,l,4); p += 4;
-	l = (final[ 3]<<16) | (final[ 9]<<8) | final[15]; to64(p,l,4); p += 4;
-	l = (final[ 4]<<16) | (final[10]<<8) | final[ 5]; to64(p,l,4); p += 4;
-	l =                    final[11]                ; to64(p,l,2); p += 2;
+	final[16] = final[5];
+	for ( i=0 ; i < 5 ; i++ ) {
+		l = (final[i]<<16) | (final[i+6]<<8) | final[i+12];
+		to64(p,l,4); p += 4;
+	}
+	l = final[11];
+	to64(p,l,2); p += 2;
 	*p = '\0';
 
 	/* Don't leave anything around in vm they could use. */