From: Eric Biggers <ebiggers@kernel.org>
To: linux-crypto@vger.kernel.org
Cc: David Howells <dhowells@redhat.com>,
Ard Biesheuvel <ardb@kernel.org>,
"Jason A . Donenfeld" <Jason@zx2c4.com>,
Eric Biggers <ebiggers@kernel.org>,
Holger Dengler <dengler@linux.ibm.com>,
Harald Freudenberger <freude@linux.ibm.com>,
Herbert Xu <herbert@gondor.apana.org.au>,
linux-arm-kernel@lists.infradead.org, linux-s390@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: [PATCH v2 08/15] crypto: arm64/sha3 - Update sha3_ce_transform() to prepare for library
Date: Sat, 25 Oct 2025 22:50:25 -0700 [thread overview]
Message-ID: <20251026055032.1413733-9-ebiggers@kernel.org> (raw)
In-Reply-To: <20251026055032.1413733-1-ebiggers@kernel.org>
- Use size_t lengths, to match the library.
- Pass the block size instead of digest size, and add support for the
block size that SHAKE128 uses. This allows the code to be used with
SHAKE128 and SHAKE256, which don't have the concept of a digest size.
SHAKE256 has the same block size as SHA3-256, but SHAKE128 has a
unique block size. Thus, there are now 5 supported block sizes.
Don't bother changing the "glue" code arm64_sha3_update() too much, as
it gets deleted when the SHA-3 code is migrated into lib/crypto/ anyway.
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
arch/arm64/crypto/sha3-ce-core.S | 67 ++++++++++++++++----------------
arch/arm64/crypto/sha3-ce-glue.c | 11 +++---
2 files changed, 39 insertions(+), 39 deletions(-)
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
index 9c77313f5a608..b62bd714839b1 100644
--- a/arch/arm64/crypto/sha3-ce-core.S
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -35,11 +35,15 @@
.macro xar, rd, rn, rm, imm6
.inst 0xce800000 | .L\rd | (.L\rn << 5) | ((\imm6) << 10) | (.L\rm << 16)
.endm
/*
- * int sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size)
+ * size_t sha3_ce_transform(struct sha3_state *state, const u8 *data,
+ * size_t nblocks, size_t block_size)
+ *
+ * block_size is assumed to be one of 72 (SHA3-512), 104 (SHA3-384), 136
+ * (SHA3-256 and SHAKE256), 144 (SHA3-224), or 168 (SHAKE128).
*/
.text
SYM_FUNC_START(sha3_ce_transform)
/* load state */
add x8, x0, #32
@@ -49,62 +53,59 @@ SYM_FUNC_START(sha3_ce_transform)
ld1 {v12.1d-v15.1d}, [x8], #32
ld1 {v16.1d-v19.1d}, [x8], #32
ld1 {v20.1d-v23.1d}, [x8], #32
ld1 {v24.1d}, [x8]
-0: sub w2, w2, #1
+0: sub x2, x2, #1
mov w8, #24
adr_l x9, .Lsha3_rcon
/* load input */
ld1 {v25.8b-v28.8b}, [x1], #32
- ld1 {v29.8b-v31.8b}, [x1], #24
+ ld1 {v29.8b}, [x1], #8
eor v0.8b, v0.8b, v25.8b
eor v1.8b, v1.8b, v26.8b
eor v2.8b, v2.8b, v27.8b
eor v3.8b, v3.8b, v28.8b
eor v4.8b, v4.8b, v29.8b
- eor v5.8b, v5.8b, v30.8b
- eor v6.8b, v6.8b, v31.8b
-
- tbnz x3, #6, 2f // SHA3-512
ld1 {v25.8b-v28.8b}, [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
next prev parent reply other threads:[~2025-10-26 5:53 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-26 5:50 [PATCH v2 00/15] SHA-3 library Eric Biggers
2025-10-26 5:50 ` [PATCH v2 01/15] crypto: s390/sha3 - Rename conflicting functions Eric Biggers
2025-10-26 5:50 ` [PATCH v2 02/15] crypto: arm64/sha3 - Rename conflicting function Eric Biggers
2025-10-26 5:50 ` [PATCH v2 03/15] lib/crypto: sha3: Add SHA-3 support Eric Biggers
2025-10-26 5:50 ` [PATCH v2 04/15] lib/crypto: sha3: Move SHA3 Iota step mapping into round function Eric Biggers
2025-10-26 5:50 ` [PATCH v2 05/15] lib/crypto: tests: Add SHA3 kunit tests Eric Biggers
2025-10-26 5:50 ` [PATCH v2 06/15] lib/crypto: tests: Add additional SHAKE tests Eric Biggers
2025-10-26 5:50 ` [PATCH v2 07/15] lib/crypto: sha3: Add FIPS cryptographic algorithm self-test Eric Biggers
2025-10-26 5:50 ` Eric Biggers [this message]
2025-10-26 5:50 ` [PATCH v2 09/15] lib/crypto: arm64/sha3: Migrate optimized code into library Eric Biggers
2025-10-26 5:50 ` [PATCH v2 10/15] lib/crypto: s390/sha3: Add optimized Keccak functions Eric Biggers
2025-10-26 5:50 ` [PATCH v2 11/15] lib/crypto: sha3: Support arch overrides of one-shot digest functions Eric Biggers
2025-10-26 5:50 ` [PATCH v2 12/15] lib/crypto: s390/sha3: Add optimized one-shot SHA-3 " Eric Biggers
2025-10-26 5:50 ` [PATCH v2 13/15] crypto: jitterentropy - Use default sha3 implementation Eric Biggers
2025-10-26 5:50 ` [PATCH v2 14/15] crypto: sha3 - Reimplement using library API Eric Biggers
2025-10-26 5:50 ` [PATCH v2 15/15] crypto: s390/sha3 - Remove superseded SHA-3 code Eric Biggers
2025-10-29 9:30 ` [PATCH v2 00/15] SHA-3 library Harald Freudenberger
2025-10-29 16:32 ` Eric Biggers
2025-10-29 20:33 ` Eric Biggers
2025-10-30 8:11 ` Heiko Carstens
2025-10-30 10:16 ` Harald Freudenberger
2025-10-30 10:10 ` Harald Freudenberger
2025-10-30 17:14 ` Eric Biggers
2025-10-31 14:29 ` Harald Freudenberger
2025-11-04 11:07 ` Harald Freudenberger
2025-11-04 18:27 ` Eric Biggers
2025-11-05 8:16 ` Harald Freudenberger
2025-11-04 11:55 ` Harald Freudenberger
2025-10-30 14:08 ` Ard Biesheuvel
2025-11-03 17:34 ` Eric Biggers
2025-11-05 15:39 ` Harald Freudenberger
2025-11-06 4:33 ` Eric Biggers
2025-11-06 7:22 ` Eric Biggers
2025-11-06 8:54 ` Harald Freudenberger
2025-11-06 19:51 ` Eric Biggers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251026055032.1413733-9-ebiggers@kernel.org \
--to=ebiggers@kernel.org \
--cc=Jason@zx2c4.com \
--cc=ardb@kernel.org \
--cc=dengler@linux.ibm.com \
--cc=dhowells@redhat.com \
--cc=freude@linux.ibm.com \
--cc=herbert@gondor.apana.org.au \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).