Merge with /home/shaggy/git/linus-clean/

26 files changed, 443 insertions, 428 deletions

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 89299f4ffe1..c442f2e7ce4 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -40,10 +40,11 @@ config CRYPTO_SHA1
 	help
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
 
-config CRYPTO_SHA1_Z990
-	tristate "SHA1 digest algorithm for IBM zSeries z990"
-	depends on CRYPTO && ARCH_S390
+config CRYPTO_SHA1_S390
+	tristate "SHA1 digest algorithm (s390)"
+	depends on CRYPTO && S390
 	help
+	  This is the s390 hardware accelerated implementation of the
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
 
 config CRYPTO_SHA256
@@ -55,6 +56,16 @@ config CRYPTO_SHA256
 	  This version of SHA implements a 256 bit hash with 128 bits of
 	  security against collision attacks.
 
+config CRYPTO_SHA256_S390
+	tristate "SHA256 digest algorithm (s390)"
+	depends on CRYPTO && S390
+	help
+	  This is the s390 hardware accelerated implementation of the
+	  SHA256 secure hash standard (DFIPS 180-2).
+
+	  This version of SHA implements a 256 bit hash with 128 bits of
+	  security against collision attacks.
+
 config CRYPTO_SHA512
 	tristate "SHA384 and SHA512 digest algorithms"
 	depends on CRYPTO
@@ -98,9 +109,9 @@ config CRYPTO_DES
 	help
 	  DES cipher algorithm (FIPS 46-2), and Triple DES EDE (FIPS 46-3).
 
-config CRYPTO_DES_Z990
-	tristate "DES and Triple DES cipher algorithms for IBM zSeries z990"
-	depends on CRYPTO && ARCH_S390
+config CRYPTO_DES_S390
+	tristate "DES and Triple DES cipher algorithms (s390)"
+	depends on CRYPTO && S390
 	help
 	  DES cipher algorithm (FIPS 46-2), and Triple DES EDE (FIPS 46-3).
 
@@ -146,7 +157,7 @@ config CRYPTO_SERPENT
 
 config CRYPTO_AES
 	tristate "AES cipher algorithms"
-	depends on CRYPTO && !(X86 || UML_X86)
+	depends on CRYPTO
 	help
 	  AES cipher algorithms (FIPS-197). AES uses the Rijndael 
 	  algorithm.
@@ -204,6 +215,26 @@ config CRYPTO_AES_X86_64
 
 	  See <http://csrc.nist.gov/encryption/aes/> for more information.
 
+config CRYPTO_AES_S390
+	tristate "AES cipher algorithms (s390)"
+	depends on CRYPTO && S390
+	help
+	  This is the s390 hardware accelerated implementation of the
+	  AES cipher algorithms (FIPS-197). AES uses the Rijndael
+	  algorithm.
+
+	  Rijndael appears to be consistently a very good performer in
+	  both hardware and software across a wide range of computing
+	  environments regardless of its use in feedback or non-feedback
+	  modes. Its key setup time is excellent, and its key agility is
+	  good. Rijndael's very low memory requirements make it very well
+	  suited for restricted-space environments, in which it also
+	  demonstrates excellent performance. Rijndael's operations are
+	  among the easiest to defend against power and timing attacks.
+
+	  On s390 the System z9-109 currently only supports the key size
+	  of 128 bit.
+
 config CRYPTO_CAST5
 	tristate "CAST5 (CAST-128) cipher algorithm"
 	depends on CRYPTO
diff --git a/crypto/aes.c b/crypto/aes.c
index 5df92888ef5..0a6a5c14368 100644
--- a/crypto/aes.c
+++ b/crypto/aes.c
@@ -73,9 +73,6 @@ byte(const u32 x, const unsigned n)
 	return x >> (n << 3);
 }
 
-#define u32_in(x) le32_to_cpu(*(const u32 *)(x))
-#define u32_out(to, from) (*(u32 *)(to) = cpu_to_le32(from))
-
 struct aes_ctx {
 	int key_length;
 	u32 E[60];
@@ -256,6 +253,7 @@ static int
 aes_set_key(void *ctx_arg, const u8 *in_key, unsigned int key_len, u32 *flags)
 {
 	struct aes_ctx *ctx = ctx_arg;
+	const __le32 *key = (const __le32 *)in_key;
 	u32 i, t, u, v, w;
 
 	if (key_len != 16 && key_len != 24 && key_len != 32) {
@@ -265,10 +263,10 @@ aes_set_key(void *ctx_arg, const u8 *in_key, unsigned int key_len, u32 *flags)
 
 	ctx->key_length = key_len;
 
-	E_KEY[0] = u32_in (in_key);
-	E_KEY[1] = u32_in (in_key + 4);
-	E_KEY[2] = u32_in (in_key + 8);
-	E_KEY[3] = u32_in (in_key + 12);
+	E_KEY[0] = le32_to_cpu(key[0]);
+	E_KEY[1] = le32_to_cpu(key[1]);
+	E_KEY[2] = le32_to_cpu(key[2]);
+	E_KEY[3] = le32_to_cpu(key[3]);
 
 	switch (key_len) {
 	case 16:
@@ -278,17 +276,17 @@ aes_set_key(void *ctx_arg, const u8 *in_key, unsigned int key_len, u32 *flags)
 		break;
 
 	case 24:
-		E_KEY[4] = u32_in (in_key + 16);
-		t = E_KEY[5] = u32_in (in_key + 20);
+		E_KEY[4] = le32_to_cpu(key[4]);
+		t = E_KEY[5] = le32_to_cpu(key[5]);
 		for (i = 0; i < 8; ++i)
 			loop6 (i);
 		break;
 
 	case 32:
-		E_KEY[4] = u32_in (in_key + 16);
-		E_KEY[5] = u32_in (in_key + 20);
-		E_KEY[6] = u32_in (in_key + 24);
-		t = E_KEY[7] = u32_in (in_key + 28);
+		E_KEY[4] = le32_to_cpu(key[4]);
+		E_KEY[5] = le32_to_cpu(key[5]);
+		E_KEY[6] = le32_to_cpu(key[6]);
+		t = E_KEY[7] = le32_to_cpu(key[7]);
 		for (i = 0; i < 7; ++i)
 			loop8 (i);
 		break;
@@ -324,13 +322,15 @@ aes_set_key(void *ctx_arg, const u8 *in_key, unsigned int key_len, u32 *flags)
 static void aes_encrypt(void *ctx_arg, u8 *out, const u8 *in)
 {
 	const struct aes_ctx *ctx = ctx_arg;
+	const __le32 *src = (const __le32 *)in;
+	__le32 *dst = (__le32 *)out;
 	u32 b0[4], b1[4];
 	const u32 *kp = E_KEY + 4;
 
-	b0[0] = u32_in (in) ^ E_KEY[0];
-	b0[1] = u32_in (in + 4) ^ E_KEY[1];
-	b0[2] = u32_in (in + 8) ^ E_KEY[2];
-	b0[3] = u32_in (in + 12) ^ E_KEY[3];
+	b0[0] = le32_to_cpu(src[0]) ^ E_KEY[0];
+	b0[1] = le32_to_cpu(src[1]) ^ E_KEY[1];
+	b0[2] = le32_to_cpu(src[2]) ^ E_KEY[2];
+	b0[3] = le32_to_cpu(src[3]) ^ E_KEY[3];
 
 	if (ctx->key_length > 24) {
 		f_nround (b1, b0, kp);
@@ -353,10 +353,10 @@ static void aes_encrypt(void *ctx_arg, u8 *out, const u8 *in)
 	f_nround (b1, b0, kp);
 	f_lround (b0, b1, kp);
 
-	u32_out (out, b0[0]);
-	u32_out (out + 4, b0[1]);
-	u32_out (out + 8, b0[2]);
-	u32_out (out + 12, b0[3]);
+	dst[0] = cpu_to_le32(b0[0]);
+	dst[1] = cpu_to_le32(b0[1]);
+	dst[2] = cpu_to_le32(b0[2]);
+	dst[3] = cpu_to_le32(b0[3]);
 }
 
 /* decrypt a block of text */
@@ -377,14 +377,16 @@ static void aes_encrypt(void *ctx_arg, u8 *out, const u8 *in)
 static void aes_decrypt(void *ctx_arg, u8 *out, const u8 *in)
 {
 	const struct aes_ctx *ctx = ctx_arg;
+	const __le32 *src = (const __le32 *)in;
+	__le32 *dst = (__le32 *)out;
 	u32 b0[4], b1[4];
 	const int key_len = ctx->key_length;
 	const u32 *kp = D_KEY + key_len + 20;
 
-	b0[0] = u32_in (in) ^ E_KEY[key_len + 24];
-	b0[1] = u32_in (in + 4) ^ E_KEY[key_len + 25];
-	b0[2] = u32_in (in + 8) ^ E_KEY[key_len + 26];
-	b0[3] = u32_in (in + 12) ^ E_KEY[key_len + 27];
+	b0[0] = le32_to_cpu(src[0]) ^ E_KEY[key_len + 24];
+	b0[1] = le32_to_cpu(src[1]) ^ E_KEY[key_len + 25];
+	b0[2] = le32_to_cpu(src[2]) ^ E_KEY[key_len + 26];
+	b0[3] = le32_to_cpu(src[3]) ^ E_KEY[key_len + 27];
 
 	if (key_len > 24) {
 		i_nround (b1, b0, kp);
@@ -407,18 +409,21 @@ static void aes_decrypt(void *ctx_arg, u8 *out, const u8 *in)
 	i_nround (b1, b0, kp);
 	i_lround (b0, b1, kp);
 
-	u32_out (out, b0[0]);
-	u32_out (out + 4, b0[1]);
-	u32_out (out + 8, b0[2]);
-	u32_out (out + 12, b0[3]);
+	dst[0] = cpu_to_le32(b0[0]);
+	dst[1] = cpu_to_le32(b0[1]);
+	dst[2] = cpu_to_le32(b0[2]);
+	dst[3] = cpu_to_le32(b0[3]);
 }
 
 
 static struct crypto_alg aes_alg = {
 	.cra_name		=	"aes",
+	.cra_driver_name	=	"aes-generic",
+	.cra_priority		=	100,
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	AES_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct aes_ctx),
+	.cra_alignmask		=	3,
 	.cra_module		=	THIS_MODULE,
 	.cra_list		=	LIST_HEAD_INIT(aes_alg.cra_list),
 	.cra_u			=	{
diff --git a/crypto/anubis.c b/crypto/anubis.c
index 3925eb0133c..2c796bdb91a 100644
--- a/crypto/anubis.c
+++ b/crypto/anubis.c
@@ -32,8 +32,10 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <asm/byteorder.h>
 #include <asm/scatterlist.h>
 #include <linux/crypto.h>
+#include <linux/types.h>
 
 #define ANUBIS_MIN_KEY_SIZE	16
 #define ANUBIS_MAX_KEY_SIZE	40
@@ -461,8 +463,8 @@ static const u32 rc[] = {
 static int anubis_setkey(void *ctx_arg, const u8 *in_key,
 			 unsigned int key_len, u32 *flags)
 {
-
-	int N, R, i, pos, r;
+	const __be32 *key = (const __be32 *)in_key;
+	int N, R, i, r;
 	u32 kappa[ANUBIS_MAX_N];
 	u32 inter[ANUBIS_MAX_N];
 
@@ -483,13 +485,8 @@ static int anubis_setkey(void *ctx_arg, const u8 *in_key,
 	ctx->R = R = 8 + N;
 
 	/* * map cipher key to initial key state (mu): */
-		for (i = 0, pos = 0; i < N; i++, pos += 4) {
-		kappa[i] =
-			(in_key[pos    ] << 24) ^
-			(in_key[pos + 1] << 16) ^
-			(in_key[pos + 2] <<  8) ^
-			(in_key[pos + 3]      );
-	}
+	for (i = 0; i < N; i++)
+		kappa[i] = be32_to_cpu(key[i]);
 
 	/*
 	 * generate R + 1 round keys:
@@ -578,7 +575,9 @@ static int anubis_setkey(void *ctx_arg, const u8 *in_key,
 static void anubis_crypt(u32 roundKey[ANUBIS_MAX_ROUNDS + 1][4],
 		u8 *ciphertext, const u8 *plaintext, const int R)
 {
-	int i, pos, r;
+	const __be32 *src = (const __be32 *)plaintext;
+	__be32 *dst = (__be32 *)ciphertext;
+	int i, r;
 	u32 state[4];
 	u32 inter[4];
 
@@ -586,14 +585,8 @@ static void anubis_crypt(u32 roundKey[ANUBIS_MAX_ROUNDS + 1][4],
 	 * map plaintext block to cipher state (mu)
 	 * and add initial round key (sigma[K^0]):
 	 */
-	for (i = 0, pos = 0; i < 4; i++, pos += 4) {
-		state[i] =
-			(plaintext[pos    ] << 24) ^
-			(plaintext[pos + 1] << 16) ^
-			(plaintext[pos + 2] <<  8) ^
-			(plaintext[pos + 3]      ) ^
-			roundKey[0][i];
-	}
+	for (i = 0; i < 4; i++)
+		state[i] = be32_to_cpu(src[i]) ^ roundKey[0][i];
 
 	/*
 	 * R - 1 full rounds:
@@ -663,13 +656,8 @@ static void anubis_crypt(u32 roundKey[ANUBIS_MAX_ROUNDS + 1][4],
 	 * map cipher state to ciphertext block (mu^{-1}):
 	 */
 
-	for (i = 0, pos = 0; i < 4; i++, pos += 4) {
-		u32 w = inter[i];
-		ciphertext[pos    ] = (u8)(w >> 24);
-		ciphertext[pos + 1] = (u8)(w >> 16);
-		ciphertext[pos + 2] = (u8)(w >>  8);
-		ciphertext[pos + 3] = (u8)(w      );
-	}
+	for (i = 0; i < 4; i++)
+		dst[i] = cpu_to_be32(inter[i]);
 }
 
 static void anubis_encrypt(void *ctx_arg, u8 *dst, const u8 *src)
@@ -689,6 +677,7 @@ static struct crypto_alg anubis_alg = {
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	ANUBIS_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof (struct anubis_ctx),
+	.cra_alignmask		=	3,
 	.cra_module		=	THIS_MODULE,
 	.cra_list		=	LIST_HEAD_INIT(anubis_alg.cra_list),
 	.cra_u			=	{ .cipher = {
diff --git a/crypto/api.c b/crypto/api.c
index 40ae42e9b6a..e26156f7183 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
  * Copyright (c) 2002 David S. Miller (davem@redhat.com)
+ * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no>
  * and Nettle, by Niels Möller.
@@ -18,9 +19,11 @@
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/kmod.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include "internal.h"
 
 LIST_HEAD(crypto_alg_list);
@@ -39,6 +42,7 @@ static inline void crypto_alg_put(struct crypto_alg *alg)
 static struct crypto_alg *crypto_alg_lookup(const char *name)
 {
 	struct crypto_alg *q, *alg = NULL;
+	int best = -1;
 
 	if (!name)
 		return NULL;
@@ -46,11 +50,23 @@ static struct crypto_alg *crypto_alg_lookup(const char *name)
 	down_read(&crypto_alg_sem);
 	
 	list_for_each_entry(q, &crypto_alg_list, cra_list) {
-		if (!(strcmp(q->cra_name, name))) {
-			if (crypto_alg_get(q))
-				alg = q;
+		int exact, fuzzy;
+
+		exact = !strcmp(q->cra_driver_name, name);
+		fuzzy = !strcmp(q->cra_name, name);
+		if (!exact && !(fuzzy && q->cra_priority > best))
+			continue;
+
+		if (unlikely(!crypto_alg_get(q)))
+			continue;
+
+		best = q->cra_priority;
+		if (alg)
+			crypto_alg_put(alg);
+		alg = q;
+
+		if (exact)
 			break;
-		}
 	}
 	
 	up_read(&crypto_alg_sem);
@@ -207,9 +223,26 @@ void crypto_free_tfm(struct crypto_tfm *tfm)
 	kfree(tfm);
 }
 
+static inline int crypto_set_driver_name(struct crypto_alg *alg)
+{
+	static const char suffix[] = "-generic";
+	char *driver_name = (char *)alg->cra_driver_name;
+	int len;
+
+	if (*driver_name)
+		return 0;
+
+	len = strlcpy(driver_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
+	if (len + sizeof(suffix) > CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	memcpy(driver_name + len, suffix, sizeof(suffix));
+	return 0;
+}
+
 int crypto_register_alg(struct crypto_alg *alg)
 {
-	int ret = 0;
+	int ret;
 	struct crypto_alg *q;
 
 	if (alg->cra_alignmask & (alg->cra_alignmask + 1))
@@ -218,13 +251,20 @@ int crypto_register_alg(struct crypto_alg *alg)
 	if (alg->cra_alignmask & alg->cra_blocksize)
 		return -EINVAL;
 
-	if (alg->cra_blocksize > PAGE_SIZE)
+	if (alg->cra_blocksize > PAGE_SIZE / 8)
+		return -EINVAL;
+
+	if (alg->cra_priority < 0)
 		return -EINVAL;
 	
+	ret = crypto_set_driver_name(alg);
+	if (unlikely(ret))
+		return ret;
+
 	down_write(&crypto_alg_sem);
 	
 	list_for_each_entry(q, &crypto_alg_list, cra_list) {
-		if (!(strcmp(q->cra_name, alg->cra_name))) {
+		if (!strcmp(q->cra_driver_name, alg->cra_driver_name)) {
 			ret = -EEXIST;
 			goto out;
 		}
diff --git a/crypto/blowfish.c b/crypto/blowfish.c
index a8b29d54e7d..7f710b201f2 100644
--- a/crypto/blowfish.c
+++ b/crypto/blowfish.c
@@ -19,8 +19,10 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <asm/byteorder.h>
 #include <asm/scatterlist.h>
 #include <linux/crypto.h>
+#include <linux/types.h>
 
 #define BF_BLOCK_SIZE 8
 #define BF_MIN_KEY_SIZE 4
@@ -451,6 +453,7 @@ static struct crypto_alg alg = {
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	BF_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct bf_ctx),
+	.cra_alignmask		=	3,
 	.cra_module		=	THIS_MODULE,
 	.cra_list		=	LIST_HEAD_INIT(alg.cra_list),
 	.cra_u			=	{ .cipher = {
diff --git a/crypto/cast5.c b/crypto/cast5.c
index bc42f42b4fe..8834c8580c0 100644
--- a/crypto/cast5.c
+++ b/crypto/cast5.c
@@ -21,11 +21,13 @@
 */
 
 
+#include <asm/byteorder.h>
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/types.h>
 
 #define CAST5_BLOCK_SIZE 8
 #define CAST5_MIN_KEY_SIZE 5
@@ -578,6 +580,8 @@ static const u32 sb8[256] = {
 static void cast5_encrypt(void *ctx, u8 * outbuf, const u8 * inbuf)
 {
 	struct cast5_ctx *c = (struct cast5_ctx *) ctx;
+	const __be32 *src = (const __be32 *)inbuf;
+	__be32 *dst = (__be32 *)outbuf;
 	u32 l, r, t;
 	u32 I;			/* used by the Fx macros */
 	u32 *Km;
@@ -589,8 +593,8 @@ static void cast5_encrypt(void *ctx, u8 * outbuf, const u8 * inbuf)
 	/* (L0,R0) <-- (m1...m64).  (Split the plaintext into left and
 	 * right 32-bit halves L0 = m1...m32 and R0 = m33...m64.)
 	 */
-	l = inbuf[0] << 24 | inbuf[1] << 16 | inbuf[2] << 8 | inbuf[3];
-	r = inbuf[4] << 24 | inbuf[5] << 16 | inbuf[6] << 8 | inbuf[7];
+	l = be32_to_cpu(src[0]);
+	r = be32_to_cpu(src[1]);
 
 	/* (16 rounds) for i from 1 to 16, compute Li and Ri as follows:
 	 *  Li = Ri-1;
@@ -634,19 +638,15 @@ static void cast5_encrypt(void *ctx, u8 * outbuf, const u8 * inbuf)
 
 	/* c1...c64 <-- (R16,L16).  (Exchange final blocks L16, R16 and
 	 *  concatenate to form the ciphertext.) */
-	outbuf[0] = (r >> 24) & 0xff;
-	outbuf[1] = (r >> 16) & 0xff;
-	outbuf[2] = (r >> 8) & 0xff;
-	outbuf[3] = r & 0xff;
-	outbuf[4] = (l >> 24) & 0xff;
-	outbuf[5] = (l >> 16) & 0xff;
-	outbuf[6] = (l >> 8) & 0xff;
-	outbuf[7] = l & 0xff;
+	dst[0] = cpu_to_be32(r);
+	dst[1] = cpu_to_be32(l);
 }
 
 static void cast5_decrypt(void *ctx, u8 * outbuf, const u8 * inbuf)
 {
 	struct cast5_ctx *c = (struct cast5_ctx *) ctx;
+	const __be32 *src = (const __be32 *)inbuf;
+	__be32 *dst = (__be32 *)outbuf;
 	u32 l, r, t;
 	u32 I;
 	u32 *Km;
@@ -655,8 +655,8 @@ static void cast5_decrypt(void *ctx, u8 * outbuf, const u8 * inbuf)
 	Km = c->Km;
 	Kr = c->Kr;
 
-	l = inbuf[0] << 24 | inbuf[1] << 16 | inbuf[2] << 8 | inbuf[3];
-	r = inbuf[4] << 24 | inbuf[5] << 16 | inbuf[6] << 8 | inbuf[7];
+	l = be32_to_cpu(src[0]);
+	r = be32_to_cpu(src[1]);
 
 	if (!(c->rr)) {
 		t = l; l = r; r = t ^ F1(r, Km[15], Kr[15]);
@@ -690,14 +690,8 @@ static void cast5_decrypt(void *ctx, u8 * outbuf, const u8 * inbuf)
 		t = l; l = r; r = t ^ F1(r, Km[0], Kr[0]);
 	}
 
-	outbuf[0] = (r >> 24) & 0xff;
-	outbuf[1] = (r >> 16) & 0xff;
-	outbuf[2] = (r >> 8) & 0xff;
-	outbuf[3] = r & 0xff;
-	outbuf[4] = (l >> 24) & 0xff;
-	outbuf[5] = (l >> 16) & 0xff;
-	outbuf[6] = (l >> 8) & 0xff;
-	outbuf[7] = l & 0xff;
+	dst[0] = cpu_to_be32(r);
+	dst[1] = cpu_to_be32(l);
 }
 
 static void key_schedule(u32 * x, u32 * z, u32 * k)
@@ -782,7 +776,7 @@ cast5_setkey(void *ctx, const u8 * key, unsigned key_len, u32 * flags)
 	u32 x[4];
 	u32 z[4];
 	u32 k[16];
-	u8 p_key[16];
+	__be32 p_key[4];
 	struct cast5_ctx *c = (struct cast5_ctx *) ctx;
 	
 	if (key_len < 5 || key_len > 16) {
@@ -796,12 +790,10 @@ cast5_setkey(void *ctx, const u8 * key, unsigned key_len, u32 * flags)
 	memcpy(p_key, key, key_len);
 
 
-	x[0] = p_key[0] << 24 | p_key[1] << 16 | p_key[2] << 8 | p_key[3];
-	x[1] = p_key[4] << 24 | p_key[5] << 16 | p_key[6] << 8 | p_key[7];
-	x[2] =
-	    p_key[8] << 24 | p_key[9] << 16 | p_key[10] << 8 | p_key[11];
-	x[3] =
-	    p_key[12] << 24 | p_key[13] << 16 | p_key[14] << 8 | p_key[15];
+	x[0] = be32_to_cpu(p_key[0]);
+	x[1] = be32_to_cpu(p_key[1]);
+	x[2] = be32_to_cpu(p_key[2]);
+	x[3] = be32_to_cpu(p_key[3]);
 
 	key_schedule(x, z, k);
 	for (i = 0; i < 16; i++)
@@ -817,6 +809,7 @@ static struct crypto_alg alg = {
 	.cra_flags 	= CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize 	= CAST5_BLOCK_SIZE,
 	.cra_ctxsize 	= sizeof(struct cast5_ctx),
+	.cra_alignmask	= 3,
 	.cra_module 	= THIS_MODULE,
 	.cra_list 	= LIST_HEAD_INIT(alg.cra_list),
 	.cra_u 		= {
diff --git a/crypto/cast6.c b/crypto/cast6.c
index 3eb08107342..9e28740ba77 100644
--- a/crypto/cast6.c
+++ b/crypto/cast6.c
@@ -18,11 +18,13 @@
  */
 
 
+#include <asm/byteorder.h>
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/types.h>
 
 #define CAST6_BLOCK_SIZE 16
 #define CAST6_MIN_KEY_SIZE 16
@@ -384,7 +386,7 @@ cast6_setkey(void *ctx, const u8 * in_key, unsigned key_len, u32 * flags)
 {
 	int i;
 	u32 key[8];
-	u8 p_key[32]; /* padded key */
+	__be32 p_key[8]; /* padded key */
 	struct cast6_ctx *c = (struct cast6_ctx *) ctx;
 
 	if (key_len < 16 || key_len > 32 || key_len % 4 != 0) {
@@ -395,14 +397,14 @@ cast6_setkey(void *ctx, const u8 * in_key, unsigned key_len, u32 * flags)
 	memset (p_key, 0, 32);
 	memcpy (p_key, in_key, key_len);
 	
-	key[0] = p_key[0] << 24 | p_key[1] << 16 | p_key[2] << 8 | p_key[3];		/* A */
-	key[1] = p_key[4] << 24 | p_key[5] << 16 | p_key[6] << 8 | p_key[7];		/* B */
-	key[2] = p_key[8] << 24 | p_key[9] << 16 | p_key[10] << 8 | p_key[11];		/* C */
-	key[3] = p_key[12] << 24 | p_key[13] << 16 | p_key[14] << 8 | p_key[15];	/* D */
-	key[4] = p_key[16] << 24 | p_key[17] << 16 | p_key[18] << 8 | p_key[19];	/* E */
-	key[5] = p_key[20] << 24 | p_key[21] << 16 | p_key[22] << 8 | p_key[23];	/* F */
-	key[6] = p_key[24] << 24 | p_key[25] << 16 | p_key[26] << 8 | p_key[27];	/* G */
-	key[7] = p_key[28] << 24 | p_key[29] << 16 | p_key[30] << 8 | p_key[31];	/* H */
+	key[0] = be32_to_cpu(p_key[0]);		/* A */
+	key[1] = be32_to_cpu(p_key[1]);		/* B */
+	key[2] = be32_to_cpu(p_key[2]);		/* C */
+	key[3] = be32_to_cpu(p_key[3]);		/* D */
+	key[4] = be32_to_cpu(p_key[4]);		/* E */
+	key[5] = be32_to_cpu(p_key[5]);		/* F */
+	key[6] = be32_to_cpu(p_key[6]);		/* G */
+	key[7] = be32_to_cpu(p_key[7]);		/* H */
 	
 
 
@@ -444,14 +446,16 @@ static inline void QBAR (u32 * block, u8 * Kr, u32 * Km) {
 
 static void cast6_encrypt (void * ctx, u8 * outbuf, const u8 * inbuf) {
 	struct cast6_ctx * c = (struct cast6_ctx *)ctx;
+	const __be32 *src = (const __be32 *)inbuf;
+	__be32 *dst = (__be32 *)outbuf;
 	u32 block[4];
 	u32 * Km; 
 	u8 * Kr;
 
-	block[0] = inbuf[0] << 24 | inbuf[1] << 16 | inbuf[2] << 8 | inbuf[3];
-	block[1] = inbuf[4] << 24 | inbuf[5] << 16 | inbuf[6] << 8 | inbuf[7];
-	block[2] = inbuf[8] << 24 | inbuf[9] << 16 | inbuf[10] << 8 | inbuf[11];
-	block[3] = inbuf[12] << 24 | inbuf[13] << 16 | inbuf[14] << 8 | inbuf[15];
+	block[0] = be32_to_cpu(src[0]);
+	block[1] = be32_to_cpu(src[1]);
+	block[2] = be32_to_cpu(src[2]);
+	block[3] = be32_to_cpu(src[3]);
 
 	Km = c->Km[0]; Kr = c->Kr[0]; Q (block, Kr, Km);
 	Km = c->Km[1]; Kr = c->Kr[1]; Q (block, Kr, Km);
@@ -465,35 +469,25 @@ static void cast6_encrypt (void * ctx, u8 * outbuf, const u8 * inbuf) {
 	Km = c->Km[9]; Kr = c->Kr[9]; QBAR (block, Kr, Km);
 	Km = c->Km[10]; Kr = c->Kr[10]; QBAR (block, Kr, Km);
 	Km = c->Km[11]; Kr = c->Kr[11]; QBAR (block, Kr, Km);
-	
-	outbuf[0] = (block[0] >> 24) & 0xff;
-	outbuf[1] = (block[0] >> 16) & 0xff;
-	outbuf[2] = (block[0] >> 8) & 0xff;
-	outbuf[3] = block[0] & 0xff;
-	outbuf[4] = (block[1] >> 24) & 0xff;
-	outbuf[5] = (block[1] >> 16) & 0xff;
-	outbuf[6] = (block[1] >> 8) & 0xff;
-	outbuf[7] = block[1] & 0xff;
-	outbuf[8] = (block[2] >> 24) & 0xff;
-	outbuf[9] = (block[2] >> 16) & 0xff;
-	outbuf[10] = (block[2] >> 8) & 0xff;
-	outbuf[11] = block[2] & 0xff;
-	outbuf[12] = (block[3] >> 24) & 0xff;
-	outbuf[13] = (block[3] >> 16) & 0xff;
-	outbuf[14] = (block[3] >> 8) & 0xff;
-	outbuf[15] = block[3] & 0xff;	
+
+	dst[0] = cpu_to_be32(block[0]);
+	dst[1] = cpu_to_be32(block[1]);
+	dst[2] = cpu_to_be32(block[2]);
+	dst[3] = cpu_to_be32(block[3]);
 }	
 
 static void cast6_decrypt (void * ctx, u8 * outbuf, const u8 * inbuf) {
 	struct cast6_ctx * c = (struct cast6_ctx *)ctx;
+	const __be32 *src = (const __be32 *)inbuf;
+	__be32 *dst = (__be32 *)outbuf;
 	u32 block[4];
 	u32 * Km; 
 	u8 * Kr;
 
-	block[0] = inbuf[0] << 24 | inbuf[1] << 16 | inbuf[2] << 8 | inbuf[3];
-	block[1] = inbuf[4] << 24 | inbuf[5] << 16 | inbuf[6] << 8 | inbuf[7];
-	block[2] = inbuf[8] << 24 | inbuf[9] << 16 | inbuf[10] << 8 | inbuf[11];
-	block[3] = inbuf[12] << 24 | inbuf[13] << 16 | inbuf[14] << 8 | inbuf[15];
+	block[0] = be32_to_cpu(src[0]);
+	block[1] = be32_to_cpu(src[1]);
+	block[2] = be32_to_cpu(src[2]);
+	block[3] = be32_to_cpu(src[3]);
 
 	Km = c->Km[11]; Kr = c->Kr[11]; Q (block, Kr, Km);
 	Km = c->Km[10]; Kr = c->Kr[10]; Q (block, Kr, Km);
@@ -508,22 +502,10 @@ static void cast6_decrypt (void * ctx, u8 * outbuf, const u8 * inbuf) {
 	Km = c->Km[1]; Kr = c->Kr[1]; QBAR (block, Kr, Km);
 	Km = c->Km[0]; Kr = c->Kr[0]; QBAR (block, Kr, Km);
 	
-	outbuf[0] = (block[0] >> 24) & 0xff;
-	outbuf[1] = (block[0] >> 16) & 0xff;
-	outbuf[2] = (block[0] >> 8) & 0xff;
-	outbuf[3] = block[0] & 0xff;
-	outbuf[4] = (block[1] >> 24) & 0xff;
-	outbuf[5] = (block[1] >> 16) & 0xff;
-	outbuf[6] = (block[1] >> 8) & 0xff;
-	outbuf[7] = block[1] & 0xff;
-	outbuf[8] = (block[2] >> 24) & 0xff;
-	outbuf[9] = (block[2] >> 16) & 0xff;
-	outbuf[10] = (block[2] >> 8) & 0xff;
-	outbuf[11] = block[2] & 0xff;
-	outbuf[12] = (block[3] >> 24) & 0xff;
-	outbuf[13] = (block[3] >> 16) & 0xff;
-	outbuf[14] = (block[3] >> 8) & 0xff;
-	outbuf[15] = block[3] & 0xff;	
+	dst[0] = cpu_to_be32(block[0]);
+	dst[1] = cpu_to_be32(block[1]);
+	dst[2] = cpu_to_be32(block[2]);
+	dst[3] = cpu_to_be32(block[3]);
 }	
 
 static struct crypto_alg alg = {
@@ -531,6 +513,7 @@ static struct crypto_alg alg = {
 	.cra_flags = CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize = CAST6_BLOCK_SIZE,
 	.cra_ctxsize = sizeof(struct cast6_ctx),
+	.cra_alignmask = 3,
 	.cra_module = THIS_MODULE,
 	.cra_list = LIST_HEAD_INIT(alg.cra_list),
 	.cra_u = {
diff --git a/crypto/cipher.c b/crypto/cipher.c
index dfd4bcfc597..65bcea0cd17 100644
--- a/crypto/cipher.c
+++ b/crypto/cipher.c
@@ -212,9 +212,10 @@ static unsigned int cbc_process_decrypt(const struct cipher_desc *desc,
 	struct crypto_tfm *tfm = desc->tfm;
 	void (*xor)(u8 *, const u8 *) = tfm->crt_u.cipher.cit_xor_block;
 	int bsize = crypto_tfm_alg_blocksize(tfm);
+	unsigned long alignmask = crypto_tfm_alg_alignmask(desc->tfm);
 
-	u8 stack[src == dst ? bsize : 0];
-	u8 *buf = stack;
+	u8 stack[src == dst ? bsize + alignmask : 0];
+	u8 *buf = (u8 *)ALIGN((unsigned long)stack, alignmask + 1);
 	u8 **dst_p = src == dst ? &buf : &dst;
 
 	void (*fn)(void *, u8 *, const u8 *) = desc->crfn;
diff --git a/crypto/crc32c.c b/crypto/crc32c.c
index 256956cd937..953362423a5 100644
--- a/crypto/crc32c.c
+++ b/crypto/crc32c.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/crypto.h>
 #include <linux/crc32c.h>
+#include <linux/types.h>
 #include <asm/byteorder.h>
 
 #define CHKSUM_BLOCK_SIZE	32
diff --git a/crypto/des.c b/crypto/des.c
index a3c863dddde..7bb548653dc 100644
--- a/crypto/des.c
+++ b/crypto/des.c
@@ -12,11 +12,13 @@
  *
  */
 
+#include <asm/byteorder.h>
 #include <linux/bitops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/crypto.h>
+#include <linux/types.h>
 
 #define DES_KEY_SIZE		8
 #define DES_EXPKEY_WORDS	32
@@ -947,6 +949,7 @@ static struct crypto_alg des_alg = {
 	.cra_blocksize		=	DES_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct des_ctx),
 	.cra_module		=	THIS_MODULE,
+	.cra_alignmask		=	3,
 	.cra_list		=	LIST_HEAD_INIT(des_alg.cra_list),
 	.cra_u			=	{ .cipher = {
 	.cia_min_keysize	=	DES_KEY_SIZE,
diff --git a/crypto/internal.h b/crypto/internal.h
index 37aa652ce5c..959e602909a 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -2,6 +2,7 @@
  * Cryptographic API.
  *
  * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -16,10 +17,15 @@
 #include <linux/highmem.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
+#include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/rwsem.h>
 #include <linux/slab.h>
 #include <asm/kmap_types.h>
 
+extern struct list_head crypto_alg_list;
+extern struct rw_semaphore crypto_alg_sem;
+
 extern enum km_type crypto_km_types[];
 
 static inline enum km_type crypto_kmap_type(int out)
diff --git a/crypto/khazad.c b/crypto/khazad.c
index 738cb0dd1e7..807f2bf4ea2 100644
--- a/crypto/khazad.c
+++ b/crypto/khazad.c
@@ -22,8 +22,10 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <asm/byteorder.h>
 #include <asm/scatterlist.h>
 #include <linux/crypto.h>
+#include <linux/types.h>
 
 #define KHAZAD_KEY_SIZE		16
 #define KHAZAD_BLOCK_SIZE	8
@@ -755,8 +757,8 @@ static const u64 c[KHAZAD_ROUNDS + 1] = {
 static int khazad_setkey(void *ctx_arg, const u8 *in_key,
                        unsigned int key_len, u32 *flags)
 {
-
 	struct khazad_ctx *ctx = ctx_arg;
+	const __be64 *key = (const __be64 *)in_key;
 	int r;
 	const u64 *S = T7;
 	u64 K2, K1;
@@ -767,22 +769,8 @@ static int khazad_setkey(void *ctx_arg, const u8 *in_key,
 		return -EINVAL;
 	}
 
-	K2 = ((u64)in_key[ 0] << 56) ^
-	     ((u64)in_key[ 1] << 48) ^
-	     ((u64)in_key[ 2] << 40) ^
-	     ((u64)in_key[ 3] << 32) ^
-	     ((u64)in_key[ 4] << 24) ^
-	     ((u64)in_key[ 5] << 16) ^
-	     ((u64)in_key[ 6] <<  8) ^