Commit 1d2c3279 authored by Ard Biesheuvel's avatar Ard Biesheuvel Committed by Herbert Xu

crypto: x86/aes - drop scalar assembler implementations

The AES assembler code for x86 isn't actually faster than code
generated by the compiler from aes_generic.c, and considering
the disproportionate maintenance burden of assembler code on
x86, it is better just to drop it entirely. Modern x86 systems
will use AES-NI anyway, and given that the modules being removed
have a dependency on aes_generic already, we can remove them
without running the risk of regressions.
Signed-off-by: default avatarArd Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
parent 2c53fd11
...@@ -14,11 +14,9 @@ sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) ...@@ -14,11 +14,9 @@ sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no)
obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
...@@ -68,11 +66,9 @@ ifeq ($(avx2_supported),yes) ...@@ -68,11 +66,9 @@ ifeq ($(avx2_supported),yes)
obj-$(CONFIG_CRYPTO_MORUS1280_AVX2) += morus1280-avx2.o obj-$(CONFIG_CRYPTO_MORUS1280_AVX2) += morus1280-avx2.o
endif endif
aes-i586-y := aes-i586-asm_32.o aes_glue.o
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
......
This diff is collapsed.
/* AES (Rijndael) implementation (FIPS PUB 197) for x86_64
*
* Copyright (C) 2005 Andreas Steinmetz, <ast@domdv.de>
*
* License:
* This code can be distributed under the terms of the GNU General Public
* License (GPL) Version 2 provided that the above header down to and
* including this sentence is retained in full.
*/
.extern crypto_ft_tab
.extern crypto_it_tab
.extern crypto_fl_tab
.extern crypto_il_tab
.text
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#define R1 %rax
#define R1E %eax
#define R1X %ax
#define R1H %ah
#define R1L %al
#define R2 %rbx
#define R2E %ebx
#define R2X %bx
#define R2H %bh
#define R2L %bl
#define R3 %rcx
#define R3E %ecx
#define R3X %cx
#define R3H %ch
#define R3L %cl
#define R4 %rdx
#define R4E %edx
#define R4X %dx
#define R4H %dh
#define R4L %dl
#define R5 %rsi
#define R5E %esi
#define R6 %rdi
#define R6E %edi
#define R7 %r9 /* don't use %rbp; it breaks stack traces */
#define R7E %r9d
#define R8 %r8
#define R10 %r10
#define R11 %r11
#define prologue(FUNC,KEY,B128,B192,r1,r2,r5,r6,r7,r8,r9,r10,r11) \
ENTRY(FUNC); \
movq r1,r2; \
leaq KEY+48(r8),r9; \
movq r10,r11; \
movl (r7),r5 ## E; \
movl 4(r7),r1 ## E; \
movl 8(r7),r6 ## E; \
movl 12(r7),r7 ## E; \
movl 480(r8),r10 ## E; \
xorl -48(r9),r5 ## E; \
xorl -44(r9),r1 ## E; \
xorl -40(r9),r6 ## E; \
xorl -36(r9),r7 ## E; \
cmpl $24,r10 ## E; \
jb B128; \
leaq 32(r9),r9; \
je B192; \
leaq 32(r9),r9;
#define epilogue(FUNC,r1,r2,r5,r6,r7,r8,r9) \
movq r1,r2; \
movl r5 ## E,(r9); \
movl r6 ## E,4(r9); \
movl r7 ## E,8(r9); \
movl r8 ## E,12(r9); \
ret; \
ENDPROC(FUNC);
#define round(TAB,OFFSET,r1,r2,r3,r4,r5,r6,r7,r8,ra,rb,rc,rd) \
movzbl r2 ## H,r5 ## E; \
movzbl r2 ## L,r6 ## E; \
movl TAB+1024(,r5,4),r5 ## E;\
movw r4 ## X,r2 ## X; \
movl TAB(,r6,4),r6 ## E; \
roll $16,r2 ## E; \
shrl $16,r4 ## E; \
movzbl r4 ## L,r7 ## E; \
movzbl r4 ## H,r4 ## E; \
xorl OFFSET(r8),ra ## E; \
xorl OFFSET+4(r8),rb ## E; \
xorl TAB+3072(,r4,4),r5 ## E;\
xorl TAB+2048(,r7,4),r6 ## E;\
movzbl r1 ## L,r7 ## E; \
movzbl r1 ## H,r4 ## E; \
movl TAB+1024(,r4,4),r4 ## E;\
movw r3 ## X,r1 ## X; \
roll $16,r1 ## E; \
shrl $16,r3 ## E; \
xorl TAB(,r7,4),r5 ## E; \
movzbl r3 ## L,r7 ## E; \
movzbl r3 ## H,r3 ## E; \
xorl TAB+3072(,r3,4),r4 ## E;\
xorl TAB+2048(,r7,4),r5 ## E;\
movzbl r1 ## L,r7 ## E; \
movzbl r1 ## H,r3 ## E; \
shrl $16,r1 ## E; \
xorl TAB+3072(,r3,4),r6 ## E;\
movl TAB+2048(,r7,4),r3 ## E;\
movzbl r1 ## L,r7 ## E; \
movzbl r1 ## H,r1 ## E; \
xorl TAB+1024(,r1,4),r6 ## E;\
xorl TAB(,r7,4),r3 ## E; \
movzbl r2 ## H,r1 ## E; \
movzbl r2 ## L,r7 ## E; \
shrl $16,r2 ## E; \
xorl TAB+3072(,r1,4),r3 ## E;\
xorl TAB+2048(,r7,4),r4 ## E;\
movzbl r2 ## H,r1 ## E; \
movzbl r2 ## L,r2 ## E; \
xorl OFFSET+8(r8),rc ## E; \
xorl OFFSET+12(r8),rd ## E; \
xorl TAB+1024(,r1,4),r3 ## E;\
xorl TAB(,r2,4),r4 ## E;
#define move_regs(r1,r2,r3,r4) \
movl r3 ## E,r1 ## E; \
movl r4 ## E,r2 ## E;
#define entry(FUNC,KEY,B128,B192) \
prologue(FUNC,KEY,B128,B192,R2,R8,R1,R3,R4,R6,R10,R5,R11)
#define return(FUNC) epilogue(FUNC,R8,R2,R5,R6,R3,R4,R11)
#define encrypt_round(TAB,OFFSET) \
round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \
move_regs(R1,R2,R5,R6)
#define encrypt_final(TAB,OFFSET) \
round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4)
#define decrypt_round(TAB,OFFSET) \
round(TAB,OFFSET,R2,R1,R4,R3,R6,R5,R7,R10,R5,R6,R3,R4) \
move_regs(R1,R2,R5,R6)
#define decrypt_final(TAB,OFFSET) \
round(TAB,OFFSET,R2,R1,R4,R3,R6,R5,R7,R10,R5,R6,R3,R4)
/* void aes_enc_blk(stuct crypto_tfm *tfm, u8 *out, const u8 *in) */
entry(aes_enc_blk,0,.Le128,.Le192)
encrypt_round(crypto_ft_tab,-96)
encrypt_round(crypto_ft_tab,-80)
.Le192: encrypt_round(crypto_ft_tab,-64)
encrypt_round(crypto_ft_tab,-48)
.Le128: encrypt_round(crypto_ft_tab,-32)
encrypt_round(crypto_ft_tab,-16)
encrypt_round(crypto_ft_tab, 0)
encrypt_round(crypto_ft_tab, 16)
encrypt_round(crypto_ft_tab, 32)
encrypt_round(crypto_ft_tab, 48)
encrypt_round(crypto_ft_tab, 64)
encrypt_round(crypto_ft_tab, 80)
encrypt_round(crypto_ft_tab, 96)
encrypt_final(crypto_fl_tab,112)
return(aes_enc_blk)
/* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in) */
entry(aes_dec_blk,240,.Ld128,.Ld192)
decrypt_round(crypto_it_tab,-96)
decrypt_round(crypto_it_tab,-80)
.Ld192: decrypt_round(crypto_it_tab,-64)
decrypt_round(crypto_it_tab,-48)
.Ld128: decrypt_round(crypto_it_tab,-32)
decrypt_round(crypto_it_tab,-16)
decrypt_round(crypto_it_tab, 0)
decrypt_round(crypto_it_tab, 16)
decrypt_round(crypto_it_tab, 32)
decrypt_round(crypto_it_tab, 48)
decrypt_round(crypto_it_tab, 64)
decrypt_round(crypto_it_tab, 80)
decrypt_round(crypto_it_tab, 96)
decrypt_final(crypto_il_tab,112)
return(aes_dec_blk)
// SPDX-License-Identifier: GPL-2.0-only // SPDX-License-Identifier: GPL-2.0-only
/*
* Glue Code for the asm optimized version of the AES Cipher Algorithm
*
*/
#include <linux/module.h>
#include <crypto/aes.h>
#include <asm/crypto/aes.h>
asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in);
asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in);
void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
{
aes_enc_blk(ctx, dst, src);
}
EXPORT_SYMBOL_GPL(crypto_aes_encrypt_x86);
void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
{
aes_dec_blk(ctx, dst, src);
}
EXPORT_SYMBOL_GPL(crypto_aes_decrypt_x86);
static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
{
aes_enc_blk(crypto_tfm_ctx(tfm), dst, src);
}
static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
{
aes_dec_blk(crypto_tfm_ctx(tfm), dst, src);
}
static struct crypto_alg aes_alg = {
.cra_name = "aes",
.cra_driver_name = "aes-asm",
.cra_priority = 200,
.cra_flags = CRYPTO_ALG_TYPE_CIPHER,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
.cra_module = THIS_MODULE,
.cra_u = {
.cipher = {
.cia_min_keysize = AES_MIN_KEY_SIZE,
.cia_max_keysize = AES_MAX_KEY_SIZE,
.cia_setkey = crypto_aes_set_key,
.cia_encrypt = aes_encrypt,
.cia_decrypt = aes_decrypt
}
}
};
static int __init aes_init(void)
{
return crypto_register_alg(&aes_alg);
}
static void __exit aes_fini(void)
{
crypto_unregister_alg(&aes_alg);
}
module_init(aes_init);
module_exit(aes_fini);
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized");
MODULE_LICENSE("GPL");
MODULE_ALIAS_CRYPTO("aes");
MODULE_ALIAS_CRYPTO("aes-asm");
...@@ -1108,50 +1108,6 @@ config CRYPTO_AES_TI ...@@ -1108,50 +1108,6 @@ config CRYPTO_AES_TI
block. Interrupts are also disabled to avoid races where cachelines block. Interrupts are also disabled to avoid races where cachelines
are evicted when the CPU is interrupted to do something else. are evicted when the CPU is interrupted to do something else.
config CRYPTO_AES_586
tristate "AES cipher algorithms (i586)"
depends on (X86 || UML_X86) && !64BIT
select CRYPTO_ALGAPI
select CRYPTO_AES
help
AES cipher algorithms (FIPS-197). AES uses the Rijndael
algorithm.
Rijndael appears to be consistently a very good performer in
both hardware and software across a wide range of computing
environments regardless of its use in feedback or non-feedback
modes. Its key setup time is excellent, and its key agility is
good. Rijndael's very low memory requirements make it very well
suited for restricted-space environments, in which it also
demonstrates excellent performance. Rijndael's operations are
among the easiest to defend against power and timing attacks.
The AES specifies three key sizes: 128, 192 and 256 bits
See <http://csrc.nist.gov/encryption/aes/> for more information.
config CRYPTO_AES_X86_64
tristate "AES cipher algorithms (x86_64)"
depends on (X86 || UML_X86) && 64BIT
select CRYPTO_ALGAPI
select CRYPTO_AES
help
AES cipher algorithms (FIPS-197). AES uses the Rijndael
algorithm.
Rijndael appears to be consistently a very good performer in
both hardware and software across a wide range of computing
environments regardless of its use in feedback or non-feedback
modes. Its key setup time is excellent, and its key agility is
good. Rijndael's very low memory requirements make it very well
suited for restricted-space environments, in which it also
demonstrates excellent performance. Rijndael's operations are
among the easiest to defend against power and timing attacks.
The AES specifies three key sizes: 128, 192 and 256 bits
See <http://csrc.nist.gov/encryption/aes/> for more information.
config CRYPTO_AES_NI_INTEL config CRYPTO_AES_NI_INTEL
tristate "AES cipher algorithms (AES-NI)" tristate "AES cipher algorithms (AES-NI)"
depends on X86 depends on X86
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment