.8b}, [x1], #32
-	ld1	{v29.8b-v30.8b}, [x1], #16
-	eor	 v7.8b,  v7.8b, v25.8b
-	eor	 v8.8b,  v8.8b, v26.8b
-	eor	 v9.8b,  v9.8b, v27.8b
-	eor	v10.8b, v10.8b, v28.8b
-	eor	v11.8b, v11.8b, v29.8b
-	eor	v12.8b, v12.8b, v30.8b
+	eor	v5.8b, v5.8b, v25.8b
+	eor	v6.8b, v6.8b, v26.8b
+	eor	v7.8b, v7.8b, v27.8b
+	eor	v8.8b, v8.8b, v28.8b
+	cmp	x3, #72
+	b.eq	3f	/* SHA3-512 (block_size=72)? */
 
-	tbnz	x3, #4, 1f		// SHA3-384 or SHA3-224
+	ld1	{v25.8b-v28.8b}, [x1], #32
+	eor	v9.8b, v9.8b, v25.8b
+	eor	v10.8b, v10.8b, v26.8b
+	eor	v11.8b, v11.8b, v27.8b
+	eor	v12.8b, v12.8b, v28.8b
+	cmp	x3, #104
+	b.eq	3f	/* SHA3-384 (block_size=104)? */
 
-	// SHA3-256
 	ld1	{v25.8b-v28.8b}, [x1], #32
 	eor	v13.8b, v13.8b, v25.8b
 	eor	v14.8b, v14.8b, v26.8b
 	eor	v15.8b, v15.8b, v27.8b
 	eor	v16.8b, v16.8b, v28.8b
-	b	3f
-
-1:	tbz	x3, #2, 3f		// bit 2 cleared? SHA-384
+	cmp	x3, #144
+	b.lt	3f	/* SHA3-256 or SHAKE256 (block_size=136)? */
+	b.eq	2f	/* SHA3-224 (block_size=144)? */
 
-	// SHA3-224
+	/* SHAKE128 (block_size=168) */
 	ld1	{v25.8b-v28.8b}, [x1], #32
-	ld1	{v29.8b}, [x1], #8
-	eor	v13.8b, v13.8b, v25.8b
-	eor	v14.8b, v14.8b, v26.8b
-	eor	v15.8b, v15.8b, v27.8b
-	eor	v16.8b, v16.8b, v28.8b
-	eor	v17.8b, v17.8b, v29.8b
+	eor	v17.8b, v17.8b, v25.8b
+	eor	v18.8b, v18.8b, v26.8b
+	eor	v19.8b, v19.8b, v27.8b
+	eor	v20.8b, v20.8b, v28.8b
 	b	3f
-
-	// SHA3-512
-2:	ld1	{v25.8b-v26.8b}, [x1], #16
-	eor	 v7.8b,  v7.8b, v25.8b
-	eor	 v8.8b,  v8.8b, v26.8b
+2:
+	/* SHA3-224 (block_size=144) */
+	ld1	{v25.8b}, [x1], #8
+	eor	v17.8b, v17.8b, v25.8b
 
 3:	sub	w8, w8, #1
 
 	eor3	v29.16b,  v4.16b,  v9.16b, v14.16b
 	eor3	v26.16b,  v1.16b,  v6.16b, v11.16b
@@ -183,21 +184,21 @@ SYM_FUNC_START(sha3_ce_transform)
 
 	eor	 v0.16b,  v0.16b, v31.16b
 
 	cbnz	w8, 3b
 	cond_yield 4f, x8, x9
-	cbnz	w2, 0b
+	cbnz	x2, 0b
 
 	/* save state */
 4:	st1	{ v0.1d- v3.1d}, [x0], #32
 	st1	{ v4.1d- v7.1d}, [x0], #32
 	st1	{ v8.1d-v11.1d}, [x0], #32
 	st1	{v12.1d-v15.1d}, [x0], #32
 	st1	{v16.1d-v19.1d}, [x0], #32
 	st1	{v20.1d-v23.1d}, [x0], #32
 	st1	{v24.1d}, [x0]
-	mov	w0, w2
+	mov	x0, x2
 	ret
 SYM_FUNC_END(sha3_ce_transform)
 
 	.section	".rodata", "a"
 	.align		8
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
index f5c8302349337..250f4fb76b472 100644
--- a/arch/arm64/crypto/sha3-ce-glue.c
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -26,30 +26,29 @@ MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("sha3-224");
 MODULE_ALIAS_CRYPTO("sha3-256");
 MODULE_ALIAS_CRYPTO("sha3-384");
 MODULE_ALIAS_CRYPTO("sha3-512");
 
-asmlinkage int sha3_ce_transform(u64 *st, const u8 *data, int blocks,
-				 int md_len);
+asmlinkage size_t sha3_ce_transform(struct sha3_state *state, const u8 *data,
+				    size_t nblocks, size_t block_size);
 
 static int arm64_sha3_update(struct shash_desc *desc, const u8 *data,
 			     unsigned int len)
 {
 	struct sha3_state *sctx = shash_desc_ctx(desc);
 	struct crypto_shash *tfm = desc->tfm;
-	unsigned int bs, ds;
+	unsigned int bs;
 	int blocks;
 
-	ds = crypto_shash_digestsize(tfm);
 	bs = crypto_shash_blocksize(tfm);
 	blocks = len / bs;
 	len -= blocks * bs;
 	do {
 		int rem;
 
 		kernel_neon_begin();
-		rem = sha3_ce_transform(sctx->st, data, blocks, ds);
+		rem = sha3_ce_transform(sctx, data, blocks, bs);
 		kernel_neon_end();
 		data += (blocks - rem) * bs;
 		blocks = rem;
 	} while (blocks);
 	return len;
@@ -72,11 +71,11 @@ static int sha3_finup(struct shash_desc *desc, const u8 *src, unsigned int len,
 	block[len++] = 0x06;
 	memset(block + len, 0, bs - len);
 	block[bs - 1] |= 0x80;
 
 	kernel_neon_begin();
-	sha3_ce_transform(sctx->st, block, 1, ds);
+	sha3_ce_transform(sctx, block, 1, bs);
 	kernel_neon_end();
 	memzero_explicit(block , sizeof(block));
 
 	for (i = 0; i < ds / 8; i++)
 		put_unaligned_le64(sctx->st[i], digest++);
-- 
2.51.1.dirty[PATCH v2 08/15] crypto: arm64/sha3 - Update sha3_ce_transform() to prepare for libraryEric Biggers <ebiggers@kernel.org> undefinedlinux-crypto@vger.kernel.org undefined undefined undefined undefined undefined undefined undefined undefined undefined undefined