f10dc56c64
As it turns out, checking the TIF_NEED_RESCHED flag after each iteration results in a significant performance regression (~10%) when running fast algorithms (i.e., ones that use special instructions and operate in the < 4 cycles per byte range) on in-order cores with comparatively slow memory accesses such as the Cortex-A53. Given the speed of these ciphers, and the fact that the page based nature of the AEAD scatterwalk API guarantees that the core NEON transform is never invoked with more than a single page's worth of input, we can estimate the worst case duration of any resulting scheduling blackout: on a 1 GHz Cortex-A53 running with 64k pages, processing a page's worth of input at 4 cycles per byte results in a delay of ~250 us, which is a reasonable upper bound. So let's remove the yield checks from the fused AES-CCM and AES-GCM routines entirely. This reverts commit7b67ae4d5cand partially reverts commit7c50136a8a. Fixes:7c50136a8a("crypto: arm64/aes-ghash - yield NEON after every ...") Fixes:7b67ae4d5c("crypto: arm64/aes-ccm - yield NEON after every ...") Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
224 lines
5.9 KiB
ArmAsm
224 lines
5.9 KiB
ArmAsm
/*
|
|
* aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
|
|
*
|
|
* Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/assembler.h>
|
|
|
|
.text
|
|
.arch armv8-a+crypto
|
|
|
|
/*
|
|
* void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
|
|
* u32 *macp, u8 const rk[], u32 rounds);
|
|
*/
|
|
ENTRY(ce_aes_ccm_auth_data)
|
|
ldr w8, [x3] /* leftover from prev round? */
|
|
ld1 {v0.16b}, [x0] /* load mac */
|
|
cbz w8, 1f
|
|
sub w8, w8, #16
|
|
eor v1.16b, v1.16b, v1.16b
|
|
0: ldrb w7, [x1], #1 /* get 1 byte of input */
|
|
subs w2, w2, #1
|
|
add w8, w8, #1
|
|
ins v1.b[0], w7
|
|
ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */
|
|
beq 8f /* out of input? */
|
|
cbnz w8, 0b
|
|
eor v0.16b, v0.16b, v1.16b
|
|
1: ld1 {v3.4s}, [x4] /* load first round key */
|
|
prfm pldl1strm, [x1]
|
|
cmp w5, #12 /* which key size? */
|
|
add x6, x4, #16
|
|
sub w7, w5, #2 /* modified # of rounds */
|
|
bmi 2f
|
|
bne 5f
|
|
mov v5.16b, v3.16b
|
|
b 4f
|
|
2: mov v4.16b, v3.16b
|
|
ld1 {v5.4s}, [x6], #16 /* load 2nd round key */
|
|
3: aese v0.16b, v4.16b
|
|
aesmc v0.16b, v0.16b
|
|
4: ld1 {v3.4s}, [x6], #16 /* load next round key */
|
|
aese v0.16b, v5.16b
|
|
aesmc v0.16b, v0.16b
|
|
5: ld1 {v4.4s}, [x6], #16 /* load next round key */
|
|
subs w7, w7, #3
|
|
aese v0.16b, v3.16b
|
|
aesmc v0.16b, v0.16b
|
|
ld1 {v5.4s}, [x6], #16 /* load next round key */
|
|
bpl 3b
|
|
aese v0.16b, v4.16b
|
|
subs w2, w2, #16 /* last data? */
|
|
eor v0.16b, v0.16b, v5.16b /* final round */
|
|
bmi 6f
|
|
ld1 {v1.16b}, [x1], #16 /* load next input block */
|
|
eor v0.16b, v0.16b, v1.16b /* xor with mac */
|
|
bne 1b
|
|
6: st1 {v0.16b}, [x0] /* store mac */
|
|
beq 10f
|
|
adds w2, w2, #16
|
|
beq 10f
|
|
mov w8, w2
|
|
7: ldrb w7, [x1], #1
|
|
umov w6, v0.b[0]
|
|
eor w6, w6, w7
|
|
strb w6, [x0], #1
|
|
subs w2, w2, #1
|
|
beq 10f
|
|
ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */
|
|
b 7b
|
|
8: mov w7, w8
|
|
add w8, w8, #16
|
|
9: ext v1.16b, v1.16b, v1.16b, #1
|
|
adds w7, w7, #1
|
|
bne 9b
|
|
eor v0.16b, v0.16b, v1.16b
|
|
st1 {v0.16b}, [x0]
|
|
10: str w8, [x3]
|
|
ret
|
|
ENDPROC(ce_aes_ccm_auth_data)
|
|
|
|
/*
|
|
* void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
|
|
* u32 rounds);
|
|
*/
|
|
ENTRY(ce_aes_ccm_final)
|
|
ld1 {v3.4s}, [x2], #16 /* load first round key */
|
|
ld1 {v0.16b}, [x0] /* load mac */
|
|
cmp w3, #12 /* which key size? */
|
|
sub w3, w3, #2 /* modified # of rounds */
|
|
ld1 {v1.16b}, [x1] /* load 1st ctriv */
|
|
bmi 0f
|
|
bne 3f
|
|
mov v5.16b, v3.16b
|
|
b 2f
|
|
0: mov v4.16b, v3.16b
|
|
1: ld1 {v5.4s}, [x2], #16 /* load next round key */
|
|
aese v0.16b, v4.16b
|
|
aesmc v0.16b, v0.16b
|
|
aese v1.16b, v4.16b
|
|
aesmc v1.16b, v1.16b
|
|
2: ld1 {v3.4s}, [x2], #16 /* load next round key */
|
|
aese v0.16b, v5.16b
|
|
aesmc v0.16b, v0.16b
|
|
aese v1.16b, v5.16b
|
|
aesmc v1.16b, v1.16b
|
|
3: ld1 {v4.4s}, [x2], #16 /* load next round key */
|
|
subs w3, w3, #3
|
|
aese v0.16b, v3.16b
|
|
aesmc v0.16b, v0.16b
|
|
aese v1.16b, v3.16b
|
|
aesmc v1.16b, v1.16b
|
|
bpl 1b
|
|
aese v0.16b, v4.16b
|
|
aese v1.16b, v4.16b
|
|
/* final round key cancels out */
|
|
eor v0.16b, v0.16b, v1.16b /* en-/decrypt the mac */
|
|
st1 {v0.16b}, [x0] /* store result */
|
|
ret
|
|
ENDPROC(ce_aes_ccm_final)
|
|
|
|
.macro aes_ccm_do_crypt,enc
|
|
ldr x8, [x6, #8] /* load lower ctr */
|
|
ld1 {v0.16b}, [x5] /* load mac */
|
|
CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */
|
|
0: /* outer loop */
|
|
ld1 {v1.8b}, [x6] /* load upper ctr */
|
|
prfm pldl1strm, [x1]
|
|
add x8, x8, #1
|
|
rev x9, x8
|
|
cmp w4, #12 /* which key size? */
|
|
sub w7, w4, #2 /* get modified # of rounds */
|
|
ins v1.d[1], x9 /* no carry in lower ctr */
|
|
ld1 {v3.4s}, [x3] /* load first round key */
|
|
add x10, x3, #16
|
|
bmi 1f
|
|
bne 4f
|
|
mov v5.16b, v3.16b
|
|
b 3f
|
|
1: mov v4.16b, v3.16b
|
|
ld1 {v5.4s}, [x10], #16 /* load 2nd round key */
|
|
2: /* inner loop: 3 rounds, 2x interleaved */
|
|
aese v0.16b, v4.16b
|
|
aesmc v0.16b, v0.16b
|
|
aese v1.16b, v4.16b
|
|
aesmc v1.16b, v1.16b
|
|
3: ld1 {v3.4s}, [x10], #16 /* load next round key */
|
|
aese v0.16b, v5.16b
|
|
aesmc v0.16b, v0.16b
|
|
aese v1.16b, v5.16b
|
|
aesmc v1.16b, v1.16b
|
|
4: ld1 {v4.4s}, [x10], #16 /* load next round key */
|
|
subs w7, w7, #3
|
|
aese v0.16b, v3.16b
|
|
aesmc v0.16b, v0.16b
|
|
aese v1.16b, v3.16b
|
|
aesmc v1.16b, v1.16b
|
|
ld1 {v5.4s}, [x10], #16 /* load next round key */
|
|
bpl 2b
|
|
aese v0.16b, v4.16b
|
|
aese v1.16b, v4.16b
|
|
subs w2, w2, #16
|
|
bmi 6f /* partial block? */
|
|
ld1 {v2.16b}, [x1], #16 /* load next input block */
|
|
.if \enc == 1
|
|
eor v2.16b, v2.16b, v5.16b /* final round enc+mac */
|
|
eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */
|
|
.else
|
|
eor v2.16b, v2.16b, v1.16b /* xor with crypted ctr */
|
|
eor v1.16b, v2.16b, v5.16b /* final round enc */
|
|
.endif
|
|
eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */
|
|
st1 {v1.16b}, [x0], #16 /* write output block */
|
|
bne 0b
|
|
CPU_LE( rev x8, x8 )
|
|
st1 {v0.16b}, [x5] /* store mac */
|
|
str x8, [x6, #8] /* store lsb end of ctr (BE) */
|
|
5: ret
|
|
|
|
6: eor v0.16b, v0.16b, v5.16b /* final round mac */
|
|
eor v1.16b, v1.16b, v5.16b /* final round enc */
|
|
st1 {v0.16b}, [x5] /* store mac */
|
|
add w2, w2, #16 /* process partial tail block */
|
|
7: ldrb w9, [x1], #1 /* get 1 byte of input */
|
|
umov w6, v1.b[0] /* get top crypted ctr byte */
|
|
umov w7, v0.b[0] /* get top mac byte */
|
|
.if \enc == 1
|
|
eor w7, w7, w9
|
|
eor w9, w9, w6
|
|
.else
|
|
eor w9, w9, w6
|
|
eor w7, w7, w9
|
|
.endif
|
|
strb w9, [x0], #1 /* store out byte */
|
|
strb w7, [x5], #1 /* store mac byte */
|
|
subs w2, w2, #1
|
|
beq 5b
|
|
ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */
|
|
ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */
|
|
b 7b
|
|
.endm
|
|
|
|
/*
|
|
* void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
|
|
* u8 const rk[], u32 rounds, u8 mac[],
|
|
* u8 ctr[]);
|
|
* void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
|
|
* u8 const rk[], u32 rounds, u8 mac[],
|
|
* u8 ctr[]);
|
|
*/
|
|
ENTRY(ce_aes_ccm_encrypt)
|
|
aes_ccm_do_crypt 1
|
|
ENDPROC(ce_aes_ccm_encrypt)
|
|
|
|
ENTRY(ce_aes_ccm_decrypt)
|
|
aes_ccm_do_crypt 0
|
|
ENDPROC(ce_aes_ccm_decrypt)
|