crypto: crypto4xx - use the correct LE32 format for IV and key defs

The hardware expects that the keys, IVs (and inner/outer hashes)
are in the le32 format.

This patch changes all hardware interface declarations to use
the correct LE32 data format for each field.

In order to pass __CHECK_ENDIAN__ checks, crypto4xx_memcpy_le
has to be honest about the endianness of its parameters.
The function was split and moved to the common crypto4xx_core.h
header. This allows the compiler to generate better code if the
sizes/len is a constant (various *_IV_LEN).

Please note that the hardware isn't consistent with the endiannes
of the save_digest field in the state record struct though.
The hashes produced by GHASH and CBC (for CCM) will be in LE32.
Whereas md5 and sha{1/,256,...} do not need any conversion.
Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

drivers/crypto/amcc/crypto4xx_alg.c

@@ -149,7 +149,7 @@ static int crypto4xx_setkey_aes(struct crypto_ablkcipher *cipher,
 				 SA_SEQ_MASK_OFF, SA_MC_ENABLE,
 				 SA_NOT_COPY_PAD, SA_NOT_COPY_PAYLOAD,
 				 SA_NOT_COPY_HDR);
-	crypto4xx_memcpy_le(get_dynamic_sa_key_field(sa),
+	crypto4xx_memcpy_to_le32(get_dynamic_sa_key_field(sa),
 				 key, keylen);
 	sa->sa_contents.w = SA_AES_CONTENTS | (keylen << 2);
 	sa->sa_command_1.bf.key_len = keylen >> 3;

drivers/crypto/amcc/crypto4xx_core.c

@@ -614,42 +614,6 @@ static u32 crypto4xx_pd_done(struct crypto4xx_device *dev, u32 idx)
 		return crypto4xx_ahash_done(dev, pd_uinfo);
 }
 
-/**
- * Note: Only use this function to copy items that is word aligned.
- */
-void crypto4xx_memcpy_le(unsigned int *dst,
-			 const unsigned char *buf,
-			 int len)
-{
-	u8 *tmp;
-	for (; len >= 4; buf += 4, len -= 4)
-		*dst++ = cpu_to_le32(*(unsigned int *) buf);
-
-	tmp = (u8 *)dst;
-	switch (len) {
-	case 3:
-		*tmp++ = 0;
-		*tmp++ = *(buf+2);
-		*tmp++ = *(buf+1);
-		*tmp++ = *buf;
-		break;
-	case 2:
-		*tmp++ = 0;
-		*tmp++ = 0;
-		*tmp++ = *(buf+1);
-		*tmp++ = *buf;
-		break;
-	case 1:
-		*tmp++ = 0;
-		*tmp++ = 0;
-		*tmp++ = 0;
-		*tmp++ = *buf;
-		break;
-	default:
-		break;
-	}
-}
-
 static void crypto4xx_stop_all(struct crypto4xx_core_device *core_dev)
 {
 	crypto4xx_destroy_pdr(core_dev->dev);
@@ -809,7 +773,7 @@ u32 crypto4xx_build_pd(struct crypto_async_request *req,
 			&pd_uinfo->sr_pa, 4);
 
 		if (iv_len)
-			crypto4xx_memcpy_le(pd_uinfo->sr_va->save_iv,
+			crypto4xx_memcpy_to_le32(pd_uinfo->sr_va->save_iv,
 						 iv, iv_len);
 	} else {
 		if (ctx->direction == DIR_INBOUND) {

drivers/crypto/amcc/crypto4xx_core.h

@@ -166,9 +166,7 @@ int crypto4xx_alloc_sa(struct crypto4xx_ctx *ctx, u32 size);
 void crypto4xx_free_sa(struct crypto4xx_ctx *ctx);
 void crypto4xx_free_ctx(struct crypto4xx_ctx *ctx);
 u32 crypto4xx_alloc_state_record(struct crypto4xx_ctx *ctx);
-void crypto4xx_memcpy_le(unsigned int *dst,
-			 const unsigned char *buf, int len);
-u32 crypto4xx_build_pd(struct crypto_async_request *req,
+int crypto4xx_build_pd(struct crypto_async_request *req,
 		       struct crypto4xx_ctx *ctx,
 		       struct scatterlist *src,
 		       struct scatterlist *dst,
@@ -193,4 +191,47 @@ int crypto4xx_hash_digest(struct ahash_request *req);
 int crypto4xx_hash_final(struct ahash_request *req);
 int crypto4xx_hash_update(struct ahash_request *req);
 int crypto4xx_hash_init(struct ahash_request *req);
+
+/**
+ * Note: Only use this function to copy items that is word aligned.
+ */
+static inline void crypto4xx_memcpy_swab32(u32 *dst, const void *buf,
+					   size_t len)
+{
+	for (; len >= 4; buf += 4, len -= 4)
+		*dst++ = __swab32p((u32 *) buf);
+
+	if (len) {
+		const u8 *tmp = (u8 *)buf;
+
+		switch (len) {
+		case 3:
+			*dst = (tmp[2] << 16) |
+			       (tmp[1] << 8) |
+			       tmp[0];
+			break;
+		case 2:
+			*dst = (tmp[1] << 8) |
+			       tmp[0];
+			break;
+		case 1:
+			*dst = tmp[0];
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static inline void crypto4xx_memcpy_from_le32(u32 *dst, const void *buf,
+					      size_t len)
+{
+	crypto4xx_memcpy_swab32(dst, buf, len);
+}
+
+static inline void crypto4xx_memcpy_to_le32(__le32 *dst, const void *buf,
+					    size_t len)
+{
+	crypto4xx_memcpy_swab32((u32 *)dst, buf, len);
+}
 #endif

drivers/crypto/amcc/crypto4xx_sa.h

@@ -181,9 +181,12 @@ struct dynamic_sa_ctl {
  * State Record for Security Association (SA)
  */
 struct  sa_state_record {
-	u32 save_iv[4];
-	u32 save_hash_byte_cnt[2];
-	u32 save_digest[16];
+	__le32 save_iv[4];
+	__le32 save_hash_byte_cnt[2];
+	union {
+		u32 save_digest[16]; /* for MD5/SHA */
+		__le32 save_digest_le32[16]; /* GHASH / CBC */
+	};
 } __attribute__((packed));
 
 /**
@@ -192,8 +195,8 @@ struct  sa_state_record {
  */
 struct dynamic_sa_aes128 {
 	struct dynamic_sa_ctl	ctrl;
-	u32 key[4];
-	u32 iv[4]; /* for CBC, OFC, and CFB mode */
+	__le32 key[4];
+	__le32 iv[4]; /* for CBC, OFC, and CFB mode */
 	u32 state_ptr;
 	u32 reserved;
 } __attribute__((packed));
@@ -206,8 +209,8 @@ struct dynamic_sa_aes128 {
  */
 struct dynamic_sa_aes192 {
 	struct dynamic_sa_ctl ctrl;
-	u32 key[6];
-	u32 iv[4]; /* for CBC, OFC, and CFB mode */
+	__le32 key[6];
+	__le32 iv[4]; /* for CBC, OFC, and CFB mode */
 	u32 state_ptr;
 	u32 reserved;
 } __attribute__((packed));
@@ -220,8 +223,8 @@ struct dynamic_sa_aes192 {
  */
 struct dynamic_sa_aes256 {
 	struct dynamic_sa_ctl ctrl;
-	u32 key[8];
-	u32 iv[4]; /* for CBC, OFC, and CFB mode */
+	__le32 key[8];
+	__le32 iv[4]; /* for CBC, OFC, and CFB mode */
 	u32 state_ptr;
 	u32 reserved;
 } __attribute__((packed));
@@ -235,8 +238,8 @@ struct dynamic_sa_aes256 {
  */
 struct dynamic_sa_hash160 {
 	struct dynamic_sa_ctl ctrl;
-	u32 inner_digest[5];
-	u32 outer_digest[5];
+	__le32 inner_digest[5];
+	__le32 outer_digest[5];
 	u32 state_ptr;
 	u32 reserved;
 } __attribute__((packed));
@@ -266,9 +269,9 @@ get_dynamic_sa_offset_state_ptr_field(struct dynamic_sa_ctl *cts)
 	return sizeof(struct dynamic_sa_ctl) + offset * 4;
 }
 
-static inline u32 *get_dynamic_sa_key_field(struct dynamic_sa_ctl *cts)
+static inline __le32 *get_dynamic_sa_key_field(struct dynamic_sa_ctl *cts)
 {
-	return (u32 *) ((unsigned long)cts + sizeof(struct dynamic_sa_ctl));
+	return (__le32 *) ((unsigned long)cts + sizeof(struct dynamic_sa_ctl));
 }
 
 #endif