Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / Atom feed
From: Ard Biesheuvel <ardb@kernel.org>
To: linux-crypto@vger.kernel.org
Cc: mark.rutland@arm.com, herbert@gondor.apana.org.au,
	Eric Biggers <ebiggers@google.com>,
	catalin.marinas@arm.com, Dave Martin <dave.martin@arm.com>,
	will@kernel.org, Ard Biesheuvel <ardb@kernel.org>,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2 7/9] crypto: arm64/aes-ce-mac - simplify NEON yield
Date: Wed,  3 Feb 2021 12:36:24 +0100
Message-ID: <20210203113626.220151-8-ardb@kernel.org> (raw)
In-Reply-To: <20210203113626.220151-1-ardb@kernel.org>

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/arm64/crypto/aes-glue.c  | 21 +++++---
 arch/arm64/crypto/aes-modes.S | 52 +++++++-------------
 2 files changed, 33 insertions(+), 40 deletions(-)

diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index e7f116d833b9..17e735931a0c 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -105,9 +105,9 @@ asmlinkage void aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[],
 				      int rounds, int blocks, u8 iv[],
 				      u32 const rk2[]);
 
-asmlinkage void aes_mac_update(u8 const in[], u32 const rk[], int rounds,
-			       int blocks, u8 dg[], int enc_before,
-			       int enc_after);
+asmlinkage int aes_mac_update(u8 const in[], u32 const rk[], int rounds,
+			      int blocks, u8 dg[], int enc_before,
+			      int enc_after);
 
 struct crypto_aes_xts_ctx {
 	struct crypto_aes_ctx key1;
@@ -856,10 +856,17 @@ static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
 	int rounds = 6 + ctx->key_length / 4;
 
 	if (crypto_simd_usable()) {
-		kernel_neon_begin();
-		aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before,
-			       enc_after);
-		kernel_neon_end();
+		int rem;
+
+		do {
+			kernel_neon_begin();
+			rem = aes_mac_update(in, ctx->key_enc, rounds, blocks,
+					     dg, enc_before, enc_after);
+			kernel_neon_end();
+			in += (blocks - rem) * AES_BLOCK_SIZE;
+			blocks = rem;
+			enc_before = 0;
+		} while (blocks);
 	} else {
 		if (enc_before)
 			aes_encrypt(ctx, dg, dg);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index 3d1f97799899..bbdb54702aa7 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -678,61 +678,47 @@ AES_FUNC_END(aes_xts_decrypt)
 	 *		  int blocks, u8 dg[], int enc_before, int enc_after)
 	 */
 AES_FUNC_START(aes_mac_update)
-	frame_push	6
-
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-	mov		x22, x3
-	mov		x23, x4
-	mov		x24, x6
-
-	ld1		{v0.16b}, [x23]			/* get dg */
+	ld1		{v0.16b}, [x4]			/* get dg */
 	enc_prepare	w2, x1, x7
 	cbz		w5, .Lmacloop4x
 
 	encrypt_block	v0, w2, x1, x7, w8
 
 .Lmacloop4x:
-	subs		w22, w22, #4
+	subs		w3, w3, #4
 	bmi		.Lmac1x
-	ld1		{v1.16b-v4.16b}, [x19], #64	/* get next pt block */
+	ld1		{v1.16b-v4.16b}, [x0], #64	/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
-	encrypt_block	v0, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	eor		v0.16b, v0.16b, v2.16b
-	encrypt_block	v0, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	eor		v0.16b, v0.16b, v3.16b
-	encrypt_block	v0, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	eor		v0.16b, v0.16b, v4.16b
-	cmp		w22, wzr
-	csinv		x5, x24, xzr, eq
+	cmp		w3, wzr
+	csinv		x5, x6, xzr, eq
 	cbz		w5, .Lmacout
-	encrypt_block	v0, w21, x20, x7, w8
-	st1		{v0.16b}, [x23]			/* return dg */
-	cond_yield_neon	.Lmacrestart
+	encrypt_block	v0, w2, x1, x7, w8
+	st1		{v0.16b}, [x4]			/* return dg */
+	cond_yield	.Lmacout, x7
 	b		.Lmacloop4x
 .Lmac1x:
-	add		w22, w22, #4
+	add		w3, w3, #4
 .Lmacloop:
-	cbz		w22, .Lmacout
-	ld1		{v1.16b}, [x19], #16		/* get next pt block */
+	cbz		w3, .Lmacout
+	ld1		{v1.16b}, [x0], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
 
-	subs		w22, w22, #1
-	csinv		x5, x24, xzr, eq
+	subs		w3, w3, #1
+	csinv		x5, x6, xzr, eq
 	cbz		w5, .Lmacout
 
 .Lmacenc:
-	encrypt_block	v0, w21, x20, x7, w8
+	encrypt_block	v0, w2, x1, x7, w8
 	b		.Lmacloop
 
 .Lmacout:
-	st1		{v0.16b}, [x23]			/* return dg */
-	frame_pop
+	st1		{v0.16b}, [x4]			/* return dg */
+	mov		w0, w3
 	ret
-
-.Lmacrestart:
-	ld1		{v0.16b}, [x23]			/* get dg */
-	enc_prepare	w21, x20, x0
-	b		.Lmacloop4x
 AES_FUNC_END(aes_mac_update)
-- 
2.30.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply index

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-03 11:36 [PATCH v2 0/9] arm64: rework NEON yielding to avoid scheduling from asm code Ard Biesheuvel
2021-02-03 11:36 ` [PATCH v2 1/9] arm64: assembler: add cond_yield macro Ard Biesheuvel
2021-02-03 11:36 ` [PATCH v2 2/9] crypto: arm64/sha1-ce - simplify NEON yield Ard Biesheuvel
2021-02-03 11:36 ` [PATCH v2 3/9] crypto: arm64/sha2-ce " Ard Biesheuvel
2021-02-03 11:36 ` [PATCH v2 4/9] crypto: arm64/sha3-ce " Ard Biesheuvel
2021-02-03 11:36 ` [PATCH v2 5/9] crypto: arm64/sha512-ce " Ard Biesheuvel
2021-02-03 11:36 ` [PATCH v2 6/9] crypto: arm64/aes-neonbs - remove NEON yield calls Ard Biesheuvel
2021-02-03 11:36 ` Ard Biesheuvel [this message]
2021-02-03 11:36 ` [PATCH v2 8/9] crypto: arm64/crc-t10dif - move NEON yield to C code Ard Biesheuvel
2021-02-03 11:36 ` [PATCH v2 9/9] arm64: assembler: remove conditional NEON yield macros Ard Biesheuvel
2021-02-03 21:31 ` (subset) Re: [PATCH v2 0/9] arm64: rework NEON yielding to avoid scheduling from asm code Will Deacon
2021-02-04  2:44   ` Herbert Xu
2021-02-04  8:29     ` Ard Biesheuvel
2021-02-04 11:10       ` Herbert Xu
2021-02-04 13:03         ` Will Deacon
2021-02-04 19:45           ` Herbert Xu
2021-02-04 10:33   ` Will Deacon
2021-02-10  7:23 ` Herbert Xu

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=20210203113626.220151-8-ardb@kernel.org \
    --to=ardb@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=dave.martin@arm.com \
    --cc=ebiggers@google.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-crypto@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=will@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

Linux-ARM-Kernel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-arm-kernel/0 linux-arm-kernel/git/0.git
	git clone --mirror https://lore.kernel.org/linux-arm-kernel/1 linux-arm-kernel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-arm-kernel linux-arm-kernel/ https://lore.kernel.org/linux-arm-kernel \
		linux-arm-kernel@lists.infradead.org
	public-inbox-index linux-arm-kernel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.infradead.lists.linux-arm-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git