crypto: {arm,arm64,mips}/poly1305 - remove redundant non-reduction from emit

This appears to be some kind of copy and paste error, and is actually
dead code.

Pre: f = 0 ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[0]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst);

Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[1]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst + 4);

Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[2]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst + 8);

Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[3]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst + 12);

Therefore this sequence is redundant. And Andy's code appears to handle
misalignment acceptably.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Tested-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm/crypto/poly1305-glue.c

@@ -20,7 +20,7 @@
 
 void poly1305_init_arm(void *state, const u8 *key);
 void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);
-void poly1305_emit_arm(void *state, __le32 *digest, const u32 *nonce);
+void poly1305_emit_arm(void *state, u8 *digest, const u32 *nonce);
 
 void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
 {
@@ -179,9 +179,6 @@ EXPORT_SYMBOL(poly1305_update_arch);
 
 void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(dctx->buflen)) {
 		dctx->buf[dctx->buflen++] = 1;
 		memset(dctx->buf + dctx->buflen, 0,
@@ -189,18 +186,7 @@ void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 		poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
 	}
 
-	poly1305_emit_arm(&dctx->h, digest, dctx->s);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]);
-	put_unaligned_le32(f, dst);
-	f = (f >> 32) + le32_to_cpu(digest[1]);
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]);
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]);
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_emit_arm(&dctx->h, dst, dctx->s);
 	*dctx = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);

arch/arm64/crypto/poly1305-glue.c

@@ -21,7 +21,7 @@
 asmlinkage void poly1305_init_arm64(void *state, const u8 *key);
 asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit);
 asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit(void *state, __le32 *digest, const u32 *nonce);
+asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce);
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
 
@@ -162,9 +162,6 @@ EXPORT_SYMBOL(poly1305_update_arch);
 
 void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(dctx->buflen)) {
 		dctx->buf[dctx->buflen++] = 1;
 		memset(dctx->buf + dctx->buflen, 0,
@@ -172,18 +169,7 @@ void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 		poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
 	}
 
-	poly1305_emit(&dctx->h, digest, dctx->s);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]);
-	put_unaligned_le32(f, dst);
-	f = (f >> 32) + le32_to_cpu(digest[1]);
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]);
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]);
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_emit(&dctx->h, dst, dctx->s);
 	*dctx = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);

arch/mips/crypto/poly1305-glue.c

@@ -15,7 +15,7 @@
 
 asmlinkage void poly1305_init_mips(void *state, const u8 *key);
 asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit_mips(void *state, __le32 *digest, const u32 *nonce);
+asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce);
 
 void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
@@ -134,9 +134,6 @@ EXPORT_SYMBOL(poly1305_update_arch);
 
 void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(dctx->buflen)) {
 		dctx->buf[dctx->buflen++] = 1;
 		memset(dctx->buf + dctx->buflen, 0,
@@ -144,18 +141,7 @@ void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 		poly1305_blocks_mips(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
 	}
 
-	poly1305_emit_mips(&dctx->h, digest, dctx->s);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]);
-	put_unaligned_le32(f, dst);
-	f = (f >> 32) + le32_to_cpu(digest[1]);
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]);
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]);
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_emit_mips(&dctx->h, dst, dctx->s);
 	*dctx = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);