linux/arch/x86/crypto/aes-x86_64-asm_64.S
Eric Biggers 9417cd1c51 crypto: x86/aes - Don't use %rbp as temporary register
When using the "aes-asm" implementation of AES (*not* the AES-NI
implementation) on an x86_64, v4.12-rc1 kernel with lockdep enabled, the
following warning was reported, along with a long unwinder dump:

	WARNING: kernel stack regs at ffffc90000643558 in kworker/u4:2:155 has bad 'bp' value 000000000000001c

The problem is that aes_enc_block() and aes_dec_block() use %rbp as a
temporary register, which breaks stack traces if an interrupt occurs.

Fix this by replacing %rbp with %r9, which was being used to hold the
saved value of %rbp.  This required rearranging the AES round macro
slightly since %r9d cannot be used as the target of a move from %ah-%dh.

Performance is essentially unchanged --- actually about 0.2% faster than
before.  Interestingly, I also measured aes-generic as being nearly 7%
faster than aes-asm, so perhaps aes-asm has outlived its usefulness...

Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2017-05-23 12:52:05 +08:00

186 lines
4.7 KiB
ArmAsm

/* 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)