From: Eric Biggers <ebiggers@kernel.org>
To: linux-crypto@vger.kernel.org
Cc: x86@kernel.org
Subject: [PATCH 4/7] crypto: x86/aes-xts - make the register aliases per-function
Date: Tue, 10 Dec 2024 15:58:31 -0800 [thread overview]
Message-ID: <20241210235834.40862-5-ebiggers@kernel.org> (raw)
In-Reply-To: <20241210235834.40862-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Since aes-xts-avx-x86_64.S contains multiple functions, move the
register aliases for the parameters and local variables of the XTS
update function into the macro that generates that function. Then add
register aliases to aes_xts_encrypt_iv() to improve readability there.
This makes aes-xts-avx-x86_64.S consistent with the GCM assembly files.
No change in the generated code.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
arch/x86/crypto/aes-xts-avx-x86_64.S | 77 +++++++++++++++-------------
1 file changed, 41 insertions(+), 36 deletions(-)
diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
index 63e5d3b3e77f5..77b3c265be30b 100644
--- a/arch/x86/crypto/aes-xts-avx-x86_64.S
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -78,26 +78,10 @@
.byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
.byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
.byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
.text
-// Function parameters
-.set KEY, %rdi // Initially points to crypto_aes_ctx, then is
- // advanced to point to 7th-from-last round key
-.set SRC, %rsi // Pointer to next source data
-.set DST, %rdx // Pointer to next destination data
-.set LEN, %ecx // Remaining length in bytes
-.set LEN8, %cl
-.set LEN64, %rcx
-.set TWEAK, %r8 // Pointer to next tweak
-
-// %rax holds the AES key length in bytes.
-.set KEYLEN, %eax
-.set KEYLEN64, %rax
-
-// %r9-r11 are available as temporaries.
-
.macro _define_Vi i
.if VL == 16
.set V\i, %xmm\i
.elseif VL == 32
.set V\i, %ymm\i
@@ -119,10 +103,26 @@
.irp i, 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
_define_Vi \i
.endr
.endif
+ // Function parameters
+ .set KEY, %rdi // Initially points to crypto_aes_ctx, then is
+ // advanced to point to 7th-from-last round key
+ .set SRC, %rsi // Pointer to next source data
+ .set DST, %rdx // Pointer to next destination data
+ .set LEN, %ecx // Remaining length in bytes
+ .set LEN8, %cl
+ .set LEN64, %rcx
+ .set TWEAK, %r8 // Pointer to next tweak
+
+ // %rax holds the AES key length in bytes.
+ .set KEYLEN, %eax
+ .set KEYLEN64, %rax
+
+ // %r9-r11 are available as temporaries.
+
// V0-V3 hold the data blocks during the main loop, or temporary values
// otherwise. V4-V5 hold temporary values.
// V6-V9 hold XTS tweaks. Each 128-bit lane holds one tweak.
.set TWEAK0_XMM, %xmm6
@@ -732,34 +732,39 @@
.endm
// void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
// u8 iv[AES_BLOCK_SIZE]);
SYM_TYPED_FUNC_START(aes_xts_encrypt_iv)
- vmovdqu (%rsi), %xmm0
- vpxor (%rdi), %xmm0, %xmm0
- movl 480(%rdi), %eax // AES key length
- lea -16(%rdi, %rax, 4), %rdi
- cmp $24, %eax
+ .set TWEAK_KEY, %rdi
+ .set IV, %rsi
+ .set KEYLEN, %eax
+ .set KEYLEN64, %rax
+
+ vmovdqu (IV), %xmm0
+ vpxor (TWEAK_KEY), %xmm0, %xmm0
+ movl 480(TWEAK_KEY), KEYLEN
+ lea -16(TWEAK_KEY, KEYLEN64, 4), TWEAK_KEY
+ cmp $24, KEYLEN
jl .Lencrypt_iv_aes128
je .Lencrypt_iv_aes192
- vaesenc -6*16(%rdi), %xmm0, %xmm0
- vaesenc -5*16(%rdi), %xmm0, %xmm0
+ vaesenc -6*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc -5*16(TWEAK_KEY), %xmm0, %xmm0
.Lencrypt_iv_aes192:
- vaesenc -4*16(%rdi), %xmm0, %xmm0
- vaesenc -3*16(%rdi), %xmm0, %xmm0
+ vaesenc -4*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc -3*16(TWEAK_KEY), %xmm0, %xmm0
.Lencrypt_iv_aes128:
- vaesenc -2*16(%rdi), %xmm0, %xmm0
- vaesenc -1*16(%rdi), %xmm0, %xmm0
- vaesenc 0*16(%rdi), %xmm0, %xmm0
- vaesenc 1*16(%rdi), %xmm0, %xmm0
- vaesenc 2*16(%rdi), %xmm0, %xmm0
- vaesenc 3*16(%rdi), %xmm0, %xmm0
- vaesenc 4*16(%rdi), %xmm0, %xmm0
- vaesenc 5*16(%rdi), %xmm0, %xmm0
- vaesenc 6*16(%rdi), %xmm0, %xmm0
- vaesenclast 7*16(%rdi), %xmm0, %xmm0
- vmovdqu %xmm0, (%rsi)
+ vaesenc -2*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc -1*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc 0*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc 1*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc 2*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc 3*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc 4*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc 5*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenc 6*16(TWEAK_KEY), %xmm0, %xmm0
+ vaesenclast 7*16(TWEAK_KEY), %xmm0, %xmm0
+ vmovdqu %xmm0, (IV)
RET
SYM_FUNC_END(aes_xts_encrypt_iv)
// Below are the actual AES-XTS encryption and decryption functions,
// instantiated from the above macro. They all have the following prototype:
--
2.47.1
next prev parent reply other threads:[~2024-12-10 23:59 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-10 23:58 [PATCH 0/7] crypto: x86 - minor optimizations and cleanup to VAES code Eric Biggers
2024-12-10 23:58 ` [PATCH 1/7] crypto: x86/aes-gcm - code size optimization Eric Biggers
2024-12-10 23:58 ` [PATCH 2/7] crypto: x86/aes-gcm - tune better for AMD CPUs Eric Biggers
2024-12-10 23:58 ` [PATCH 3/7] crypto: x86/aes-xts - use .irp when useful Eric Biggers
2024-12-10 23:58 ` Eric Biggers [this message]
2024-12-10 23:58 ` [PATCH 5/7] crypto: x86/aes-xts - improve some comments Eric Biggers
2024-12-10 23:58 ` [PATCH 6/7] crypto: x86/aes-xts - change len parameter to int Eric Biggers
2024-12-10 23:58 ` [PATCH 7/7] crypto: x86/aes-xts - more code size optimizations 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=20241210235834.40862-5-ebiggers@kernel.org \
--to=ebiggers@kernel.org \
--cc=linux-crypto@vger.kernel.org \
--cc=x86@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.