summaryrefslogtreecommitdiff
path: root/arch/arm/crypto
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/crypto')
-rw-r--r--arch/arm/crypto/Kconfig41
-rw-r--r--arch/arm/crypto/Makefile21
-rw-r--r--arch/arm/crypto/sha1-armv4-large.S507
-rw-r--r--arch/arm/crypto/sha1-armv7-neon.S634
-rw-r--r--arch/arm/crypto/sha1-ce-core.S123
-rw-r--r--arch/arm/crypto/sha1-ce-glue.c72
-rw-r--r--arch/arm/crypto/sha1_glue.c75
-rw-r--r--arch/arm/crypto/sha1_neon_glue.c83
-rw-r--r--arch/arm/crypto/sha512-armv4.pl657
-rw-r--r--arch/arm/crypto/sha512-glue.c110
-rw-r--r--arch/arm/crypto/sha512-neon-glue.c75
-rw-r--r--arch/arm/crypto/sha512.h3
12 files changed, 0 insertions, 2401 deletions
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 7efb9a8596e4..1e5f3cdf691c 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -62,47 +62,6 @@ config CRYPTO_BLAKE2B_NEON
much faster than the SHA-2 family and slightly faster than
SHA-1.
-config CRYPTO_SHA1_ARM
- tristate "Hash functions: SHA-1"
- select CRYPTO_SHA1
- select CRYPTO_HASH
- help
- SHA-1 secure hash algorithm (FIPS 180)
-
- Architecture: arm
-
-config CRYPTO_SHA1_ARM_NEON
- tristate "Hash functions: SHA-1 (NEON)"
- depends on KERNEL_MODE_NEON
- select CRYPTO_SHA1_ARM
- select CRYPTO_SHA1
- select CRYPTO_HASH
- help
- SHA-1 secure hash algorithm (FIPS 180)
-
- Architecture: arm using
- - NEON (Advanced SIMD) extensions
-
-config CRYPTO_SHA1_ARM_CE
- tristate "Hash functions: SHA-1 (ARMv8 Crypto Extensions)"
- depends on KERNEL_MODE_NEON
- select CRYPTO_SHA1_ARM
- select CRYPTO_HASH
- help
- SHA-1 secure hash algorithm (FIPS 180)
-
- Architecture: arm using ARMv8 Crypto Extensions
-
-config CRYPTO_SHA512_ARM
- tristate "Hash functions: SHA-384 and SHA-512 (NEON)"
- select CRYPTO_HASH
- depends on !CPU_V7M
- help
- SHA-384 and SHA-512 secure hash algorithms (FIPS 180)
-
- Architecture: arm using
- - NEON (Advanced SIMD) extensions
-
config CRYPTO_AES_ARM
tristate "Ciphers: AES"
select CRYPTO_ALGAPI
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 8479137c6e80..4f23999ae17d 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -5,38 +5,17 @@
obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
-obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
-obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
-obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
obj-$(CONFIG_CRYPTO_BLAKE2B_NEON) += blake2b-neon.o
obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
obj-$(CONFIG_CRYPTO_CURVE25519_NEON) += curve25519-neon.o
obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
aes-arm-y := aes-cipher-core.o aes-cipher-glue.o
aes-arm-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
-sha1-arm-y := sha1-armv4-large.o sha1_glue.o
-sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o
-sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
-sha512-arm-y := sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
blake2b-neon-y := blake2b-neon-core.o blake2b-neon-glue.o
-sha1-arm-ce-y := sha1-ce-core.o sha1-ce-glue.o
aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o
ghash-arm-ce-y := ghash-ce-core.o ghash-ce-glue.o
nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
curve25519-neon-y := curve25519-core.o curve25519-glue.o
-
-quiet_cmd_perl = PERL $@
- cmd_perl = $(PERL) $(<) > $(@)
-
-$(obj)/%-core.S: $(src)/%-armv4.pl
- $(call cmd,perl)
-
-clean-files += sha512-core.S
-
-aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1
-
-AFLAGS_sha512-core.o += $(aflags-thumb2-y)
diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
deleted file mode 100644
index 1c8b685149f2..000000000000
--- a/arch/arm/crypto/sha1-armv4-large.S
+++ /dev/null
@@ -1,507 +0,0 @@
-#define __ARM_ARCH__ __LINUX_ARM_ARCH__
-@ SPDX-License-Identifier: GPL-2.0
-
-@ This code is taken from the OpenSSL project but the author (Andy Polyakov)
-@ has relicensed it under the GPLv2. Therefore 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.
-@
-@ The original headers, including the original license headers, are
-@ included below for completeness.
-
-@ ====================================================================
-@ Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
-@ project. The module is, however, dual licensed under OpenSSL and
-@ CRYPTOGAMS licenses depending on where you obtain it. For further
-@ details see https://www.openssl.org/~appro/cryptogams/.
-@ ====================================================================
-
-@ sha1_block procedure for ARMv4.
-@
-@ January 2007.
-
-@ Size/performance trade-off
-@ ====================================================================
-@ impl size in bytes comp cycles[*] measured performance
-@ ====================================================================
-@ thumb 304 3212 4420
-@ armv4-small 392/+29% 1958/+64% 2250/+96%
-@ armv4-compact 740/+89% 1552/+26% 1840/+22%
-@ armv4-large 1420/+92% 1307/+19% 1370/+34%[***]
-@ full unroll ~5100/+260% ~1260/+4% ~1300/+5%
-@ ====================================================================
-@ thumb = same as 'small' but in Thumb instructions[**] and
-@ with recurring code in two private functions;
-@ small = detached Xload/update, loops are folded;
-@ compact = detached Xload/update, 5x unroll;
-@ large = interleaved Xload/update, 5x unroll;
-@ full unroll = interleaved Xload/update, full unroll, estimated[!];
-@
-@ [*] Manually counted instructions in "grand" loop body. Measured
-@ performance is affected by prologue and epilogue overhead,
-@ i-cache availability, branch penalties, etc.
-@ [**] While each Thumb instruction is twice smaller, they are not as
-@ diverse as ARM ones: e.g., there are only two arithmetic
-@ instructions with 3 arguments, no [fixed] rotate, addressing
-@ modes are limited. As result it takes more instructions to do
-@ the same job in Thumb, therefore the code is never twice as
-@ small and always slower.
-@ [***] which is also ~35% better than compiler generated code. Dual-
-@ issue Cortex A8 core was measured to process input block in
-@ ~990 cycles.
-
-@ August 2010.
-@
-@ Rescheduling for dual-issue pipeline resulted in 13% improvement on
-@ Cortex A8 core and in absolute terms ~870 cycles per input block
-@ [or 13.6 cycles per byte].
-
-@ February 2011.
-@
-@ Profiler-assisted and platform-specific optimization resulted in 10%
-@ improvement on Cortex A8 core and 12.2 cycles per byte.
-
-#include <linux/linkage.h>
-
-.text
-
-.align 2
-ENTRY(sha1_block_data_order)
- stmdb sp!,{r4-r12,lr}
- add r2,r1,r2,lsl#6 @ r2 to point at the end of r1
- ldmia r0,{r3,r4,r5,r6,r7}
-.Lloop:
- ldr r8,.LK_00_19
- mov r14,sp
- sub sp,sp,#15*4
- mov r5,r5,ror#30
- mov r6,r6,ror#30
- mov r7,r7,ror#30 @ [6]
-.L_00_15:
-#if __ARM_ARCH__<7
- ldrb r10,[r1,#2]
- ldrb r9,[r1,#3]
- ldrb r11,[r1,#1]
- add r7,r8,r7,ror#2 @ E+=K_00_19
- ldrb r12,[r1],#4
- orr r9,r9,r10,lsl#8
- eor r10,r5,r6 @ F_xx_xx
- orr r9,r9,r11,lsl#16
- add r7,r7,r3,ror#27 @ E+=ROR(A,27)
- orr r9,r9,r12,lsl#24
-#else
- ldr r9,[r1],#4 @ handles unaligned
- add r7,r8,r7,ror#2 @ E+=K_00_19
- eor r10,r5,r6 @ F_xx_xx
- add r7,r7,r3,ror#27 @ E+=ROR(A,27)
-#ifdef __ARMEL__
- rev r9,r9 @ byte swap
-#endif
-#endif
- and r10,r4,r10,ror#2
- add r7,r7,r9 @ E+=X[i]
- eor r10,r10,r6,ror#2 @ F_00_19(B,C,D)
- str r9,[r14,#-4]!
- add r7,r7,r10 @ E+=F_00_19(B,C,D)
-#if __ARM_ARCH__<7
- ldrb r10,[r1,#2]
- ldrb r9,[r1,#3]
- ldrb r11,[r1,#1]
- add r6,r8,r6,ror#2 @ E+=K_00_19
- ldrb r12,[r1],#4
- orr r9,r9,r10,lsl#8
- eor r10,r4,r5 @ F_xx_xx
- orr r9,r9,r11,lsl#16
- add r6,r6,r7,ror#27 @ E+=ROR(A,27)
- orr r9,r9,r12,lsl#24
-#else
- ldr r9,[r1],#4 @ handles unaligned
- add r6,r8,r6,ror#2 @ E+=K_00_19
- eor r10,r4,r5 @ F_xx_xx
- add r6,r6,r7,ror#27 @ E+=ROR(A,27)
-#ifdef __ARMEL__
- rev r9,r9 @ byte swap
-#endif
-#endif
- and r10,r3,r10,ror#2
- add r6,r6,r9 @ E+=X[i]
- eor r10,r10,r5,ror#2 @ F_00_19(B,C,D)
- str r9,[r14,#-4]!
- add r6,r6,r10 @ E+=F_00_19(B,C,D)
-#if __ARM_ARCH__<7
- ldrb r10,[r1,#2]
- ldrb r9,[r1,#3]
- ldrb r11,[r1,#1]
- add r5,r8,r5,ror#2 @ E+=K_00_19
- ldrb r12,[r1],#4
- orr r9,r9,r10,lsl#8
- eor r10,r3,r4 @ F_xx_xx
- orr r9,r9,r11,lsl#16
- add r5,r5,r6,ror#27 @ E+=ROR(A,27)
- orr r9,r9,r12,lsl#24
-#else
- ldr r9,[r1],#4 @ handles unaligned
- add r5,r8,r5,ror#2 @ E+=K_00_19
- eor r10,r3,r4 @ F_xx_xx
- add r5,r5,r6,ror#27 @ E+=ROR(A,27)
-#ifdef __ARMEL__
- rev r9,r9 @ byte swap
-#endif
-#endif
- and r10,r7,r10,ror#2
- add r5,r5,r9 @ E+=X[i]
- eor r10,r10,r4,ror#2 @ F_00_19(B,C,D)
- str r9,[r14,#-4]!
- add r5,r5,r10 @ E+=F_00_19(B,C,D)
-#if __ARM_ARCH__<7
- ldrb r10,[r1,#2]
- ldrb r9,[r1,#3]
- ldrb r11,[r1,#1]
- add r4,r8,r4,ror#2 @ E+=K_00_19
- ldrb r12,[r1],#4
- orr r9,r9,r10,lsl#8
- eor r10,r7,r3 @ F_xx_xx
- orr r9,r9,r11,lsl#16
- add r4,r4,r5,ror#27 @ E+=ROR(A,27)
- orr r9,r9,r12,lsl#24
-#else
- ldr r9,[r1],#4 @ handles unaligned
- add r4,r8,r4,ror#2 @ E+=K_00_19
- eor r10,r7,r3 @ F_xx_xx
- add r4,r4,r5,ror#27 @ E+=ROR(A,27)
-#ifdef __ARMEL__
- rev r9,r9 @ byte swap
-#endif
-#endif
- and r10,r6,r10,ror#2
- add r4,r4,r9 @ E+=X[i]
- eor r10,r10,r3,ror#2 @ F_00_19(B,C,D)
- str r9,[r14,#-4]!
- add r4,r4,r10 @ E+=F_00_19(B,C,D)
-#if __ARM_ARCH__<7
- ldrb r10,[r1,#2]
- ldrb r9,[r1,#3]
- ldrb r11,[r1,#1]
- add r3,r8,r3,ror#2 @ E+=K_00_19
- ldrb r12,[r1],#4
- orr r9,r9,r10,lsl#8
- eor r10,r6,r7 @ F_xx_xx
- orr r9,r9,r11,lsl#16
- add r3,r3,r4,ror#27 @ E+=ROR(A,27)
- orr r9,r9,r12,lsl#24
-#else
- ldr r9,[r1],#4 @ handles unaligned
- add r3,r8,r3,ror#2 @ E+=K_00_19
- eor r10,r6,r7 @ F_xx_xx
- add r3,r3,r4,ror#27 @ E+=ROR(A,27)
-#ifdef __ARMEL__
- rev r9,r9 @ byte swap
-#endif
-#endif
- and r10,r5,r10,ror#2
- add r3,r3,r9 @ E+=X[i]
- eor r10,r10,r7,ror#2 @ F_00_19(B,C,D)
- str r9,[r14,#-4]!
- add r3,r3,r10 @ E+=F_00_19(B,C,D)
- cmp r14,sp
- bne .L_00_15 @ [((11+4)*5+2)*3]
- sub sp,sp,#25*4
-#if __ARM_ARCH__<7
- ldrb r10,[r1,#2]
- ldrb r9,[r1,#3]
- ldrb r11,[r1,#1]
- add r7,r8,r7,ror#2 @ E+=K_00_19
- ldrb r12,[r1],#4
- orr r9,r9,r10,lsl#8
- eor r10,r5,r6 @ F_xx_xx
- orr r9,r9,r11,lsl#16
- add r7,r7,r3,ror#27 @ E+=ROR(A,27)
- orr r9,r9,r12,lsl#24
-#else
- ldr r9,[r1],#4 @ handles unaligned
- add r7,r8,r7,ror#2 @ E+=K_00_19
- eor r10,r5,r6 @ F_xx_xx
- add r7,r7,r3,ror#27 @ E+=ROR(A,27)
-#ifdef __ARMEL__
- rev r9,r9 @ byte swap
-#endif
-#endif
- and r10,r4,r10,ror#2
- add r7,r7,r9 @ E+=X[i]
- eor r10,r10,r6,ror#2 @ F_00_19(B,C,D)
- str r9,[r14,#-4]!
- add r7,r7,r10 @ E+=F_00_19(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r6,r8,r6,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r4,r5 @ F_xx_xx
- mov r9,r9,ror#31
- add r6,r6,r7,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r3,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r6,r6,r9 @ E+=X[i]
- eor r10,r10,r5,ror#2 @ F_00_19(B,C,D)
- add r6,r6,r10 @ E+=F_00_19(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r5,r8,r5,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r3,r4 @ F_xx_xx
- mov r9,r9,ror#31
- add r5,r5,r6,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r7,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r5,r5,r9 @ E+=X[i]
- eor r10,r10,r4,ror#2 @ F_00_19(B,C,D)
- add r5,r5,r10 @ E+=F_00_19(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r4,r8,r4,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r7,r3 @ F_xx_xx
- mov r9,r9,ror#31
- add r4,r4,r5,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r6,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r4,r4,r9 @ E+=X[i]
- eor r10,r10,r3,ror#2 @ F_00_19(B,C,D)
- add r4,r4,r10 @ E+=F_00_19(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r3,r8,r3,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r6,r7 @ F_xx_xx
- mov r9,r9,ror#31
- add r3,r3,r4,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r5,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r3,r3,r9 @ E+=X[i]
- eor r10,r10,r7,ror#2 @ F_00_19(B,C,D)
- add r3,r3,r10 @ E+=F_00_19(B,C,D)
-
- ldr r8,.LK_20_39 @ [+15+16*4]
- cmn sp,#0 @ [+3], clear carry to denote 20_39
-.L_20_39_or_60_79:
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r7,r8,r7,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r5,r6 @ F_xx_xx
- mov r9,r9,ror#31
- add r7,r7,r3,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- eor r10,r4,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r7,r7,r9 @ E+=X[i]
- add r7,r7,r10 @ E+=F_20_39(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r6,r8,r6,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r4,r5 @ F_xx_xx
- mov r9,r9,ror#31
- add r6,r6,r7,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- eor r10,r3,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r6,r6,r9 @ E+=X[i]
- add r6,r6,r10 @ E+=F_20_39(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r5,r8,r5,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r3,r4 @ F_xx_xx
- mov r9,r9,ror#31
- add r5,r5,r6,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- eor r10,r7,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r5,r5,r9 @ E+=X[i]
- add r5,r5,r10 @ E+=F_20_39(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r4,r8,r4,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r7,r3 @ F_xx_xx
- mov r9,r9,ror#31
- add r4,r4,r5,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- eor r10,r6,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r4,r4,r9 @ E+=X[i]
- add r4,r4,r10 @ E+=F_20_39(B,C,D)
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r3,r8,r3,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r6,r7 @ F_xx_xx
- mov r9,r9,ror#31
- add r3,r3,r4,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- eor r10,r5,r10,ror#2 @ F_xx_xx
- @ F_xx_xx
- add r3,r3,r9 @ E+=X[i]
- add r3,r3,r10 @ E+=F_20_39(B,C,D)
- ARM( teq r14,sp ) @ preserve carry
- THUMB( mov r11,sp )
- THUMB( teq r14,r11 ) @ preserve carry
- bne .L_20_39_or_60_79 @ [+((12+3)*5+2)*4]
- bcs .L_done @ [+((12+3)*5+2)*4], spare 300 bytes
-
- ldr r8,.LK_40_59
- sub sp,sp,#20*4 @ [+2]
-.L_40_59:
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r7,r8,r7,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r5,r6 @ F_xx_xx
- mov r9,r9,ror#31
- add r7,r7,r3,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r4,r10,ror#2 @ F_xx_xx
- and r11,r5,r6 @ F_xx_xx
- add r7,r7,r9 @ E+=X[i]
- add r7,r7,r10 @ E+=F_40_59(B,C,D)
- add r7,r7,r11,ror#2
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r6,r8,r6,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r4,r5 @ F_xx_xx
- mov r9,r9,ror#31
- add r6,r6,r7,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r3,r10,ror#2 @ F_xx_xx
- and r11,r4,r5 @ F_xx_xx
- add r6,r6,r9 @ E+=X[i]
- add r6,r6,r10 @ E+=F_40_59(B,C,D)
- add r6,r6,r11,ror#2
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r5,r8,r5,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r3,r4 @ F_xx_xx
- mov r9,r9,ror#31
- add r5,r5,r6,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r7,r10,ror#2 @ F_xx_xx
- and r11,r3,r4 @ F_xx_xx
- add r5,r5,r9 @ E+=X[i]
- add r5,r5,r10 @ E+=F_40_59(B,C,D)
- add r5,r5,r11,ror#2
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r4,r8,r4,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r7,r3 @ F_xx_xx
- mov r9,r9,ror#31
- add r4,r4,r5,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r6,r10,ror#2 @ F_xx_xx
- and r11,r7,r3 @ F_xx_xx
- add r4,r4,r9 @ E+=X[i]
- add r4,r4,r10 @ E+=F_40_59(B,C,D)
- add r4,r4,r11,ror#2
- ldr r9,[r14,#15*4]
- ldr r10,[r14,#13*4]
- ldr r11,[r14,#7*4]
- add r3,r8,r3,ror#2 @ E+=K_xx_xx
- ldr r12,[r14,#2*4]
- eor r9,r9,r10
- eor r11,r11,r12 @ 1 cycle stall
- eor r10,r6,r7 @ F_xx_xx
- mov r9,r9,ror#31
- add r3,r3,r4,ror#27 @ E+=ROR(A,27)
- eor r9,r9,r11,ror#31
- str r9,[r14,#-4]!
- and r10,r5,r10,ror#2 @ F_xx_xx
- and r11,r6,r7 @ F_xx_xx
- add r3,r3,r9 @ E+=X[i]
- add r3,r3,r10 @ E+=F_40_59(B,C,D)
- add r3,r3,r11,ror#2
- cmp r14,sp
- bne .L_40_59 @ [+((12+5)*5+2)*4]
-
- ldr r8,.LK_60_79
- sub sp,sp,#20*4
- cmp sp,#0 @ set carry to denote 60_79
- b .L_20_39_or_60_79 @ [+4], spare 300 bytes
-.L_done:
- add sp,sp,#80*4 @ "deallocate" stack frame
- ldmia r0,{r8,r9,r10,r11,r12}
- add r3,r8,r3
- add r4,r9,r4
- add r5,r10,r5,ror#2
- add r6,r11,r6,ror#2
- add r7,r12,r7,ror#2
- stmia r0,{r3,r4,r5,r6,r7}
- teq r1,r2
- bne .Lloop @ [+18], total 1307
-
- ldmia sp!,{r4-r12,pc}
-.align 2
-.LK_00_19: .word 0x5a827999
-.LK_20_39: .word 0x6ed9eba1
-.LK_40_59: .word 0x8f1bbcdc
-.LK_60_79: .word 0xca62c1d6
-ENDPROC(sha1_block_data_order)
-.asciz "SHA1 block transform for ARMv4, CRYPTOGAMS by <appro@openssl.org>"
-.align 2
diff --git a/arch/arm/crypto/sha1-armv7-neon.S b/arch/arm/crypto/sha1-armv7-neon.S
deleted file mode 100644
index 28d816a6a530..000000000000
--- a/arch/arm/crypto/sha1-armv7-neon.S
+++ /dev/null
@@ -1,634 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/* sha1-armv7-neon.S - ARM/NEON accelerated SHA-1 transform function
- *
- * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-.syntax unified
-.fpu neon
-
-.text
-
-
-/* Context structure */
-
-#define state_h0 0
-#define state_h1 4
-#define state_h2 8
-#define state_h3 12
-#define state_h4 16
-
-
-/* Constants */
-
-#define K1 0x5A827999
-#define K2 0x6ED9EBA1
-#define K3 0x8F1BBCDC
-#define K4 0xCA62C1D6
-.align 4
-.LK_VEC:
-.LK1: .long K1, K1, K1, K1
-.LK2: .long K2, K2, K2, K2
-.LK3: .long K3, K3, K3, K3
-.LK4: .long K4, K4, K4, K4
-
-
-/* Register macros */
-
-#define RSTATE r0
-#define RDATA r1
-#define RNBLKS r2
-#define ROLDSTACK r3
-#define RWK lr
-
-#define _a r4
-#define _b r5
-#define _c r6
-#define _d r7
-#define _e r8
-
-#define RT0 r9
-#define RT1 r10
-#define RT2 r11
-#define RT3 r12
-
-#define W0 q0
-#define W1 q7
-#define W2 q2
-#define W3 q3
-#define W4 q4
-#define W5 q6
-#define W6 q5
-#define W7 q1
-
-#define tmp0 q8
-#define tmp1 q9
-#define tmp2 q10
-#define tmp3 q11
-
-#define qK1 q12
-#define qK2 q13
-#define qK3 q14
-#define qK4 q15
-
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define ARM_LE(code...)
-#else
-#define ARM_LE(code...) code
-#endif
-
-/* Round function macros. */
-
-#define WK_offs(i) (((i) & 15) * 4)
-
-#define _R_F1(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- ldr RT3, [sp, WK_offs(i)]; \
- pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- bic RT0, d, b; \
- add e, e, a, ror #(32 - 5); \
- and RT1, c, b; \
- pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- add RT0, RT0, RT3; \
- add e, e, RT1; \
- ror b, #(32 - 30); \
- pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- add e, e, RT0;
-
-#define _R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- ldr RT3, [sp, WK_offs(i)]; \
- pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- eor RT0, d, b; \
- add e, e, a, ror #(32 - 5); \
- eor RT0, RT0, c; \
- pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- add e, e, RT3; \
- ror b, #(32 - 30); \
- pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- add e, e, RT0; \
-
-#define _R_F3(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- ldr RT3, [sp, WK_offs(i)]; \
- pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- eor RT0, b, c; \
- and RT1, b, c; \
- add e, e, a, ror #(32 - 5); \
- pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- and RT0, RT0, d; \
- add RT1, RT1, RT3; \
- add e, e, RT0; \
- ror b, #(32 - 30); \
- pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
- add e, e, RT1;
-
-#define _R_F4(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- _R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
-
-#define _R(a,b,c,d,e,f,i,pre1,pre2,pre3,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- _R_##f(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
-
-#define R(a,b,c,d,e,f,i) \
- _R_##f(a,b,c,d,e,i,dummy,dummy,dummy,i16,\
- W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
-
-#define dummy(...)
-
-
-/* Input expansion macros. */
-
-/********* Precalc macros for rounds 0-15 *************************************/
-
-#define W_PRECALC_00_15() \
- add RWK, sp, #(WK_offs(0)); \
- \
- vld1.32 {W0, W7}, [RDATA]!; \
- ARM_LE(vrev32.8 W0, W0; ) /* big => little */ \
- vld1.32 {W6, W5}, [RDATA]!; \
- vadd.u32 tmp0, W0, curK; \
- ARM_LE(vrev32.8 W7, W7; ) /* big => little */ \
- ARM_LE(vrev32.8 W6, W6; ) /* big => little */ \
- vadd.u32 tmp1, W7, curK; \
- ARM_LE(vrev32.8 W5, W5; ) /* big => little */ \
- vadd.u32 tmp2, W6, curK; \
- vst1.32 {tmp0, tmp1}, [RWK]!; \
- vadd.u32 tmp3, W5, curK; \
- vst1.32 {tmp2, tmp3}, [RWK]; \
-
-#define WPRECALC_00_15_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vld1.32 {W0, W7}, [RDATA]!; \
-
-#define WPRECALC_00_15_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- add RWK, sp, #(WK_offs(0)); \
-
-#define WPRECALC_00_15_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- ARM_LE(vrev32.8 W0, W0; ) /* big => little */ \
-
-#define WPRECALC_00_15_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vld1.32 {W6, W5}, [RDATA]!; \
-
-#define WPRECALC_00_15_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vadd.u32 tmp0, W0, curK; \
-
-#define WPRECALC_00_15_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- ARM_LE(vrev32.8 W7, W7; ) /* big => little */ \
-
-#define WPRECALC_00_15_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- ARM_LE(vrev32.8 W6, W6; ) /* big => little */ \
-
-#define WPRECALC_00_15_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vadd.u32 tmp1, W7, curK; \
-
-#define WPRECALC_00_15_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- ARM_LE(vrev32.8 W5, W5; ) /* big => little */ \
-
-#define WPRECALC_00_15_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vadd.u32 tmp2, W6, curK; \
-
-#define WPRECALC_00_15_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vst1.32 {tmp0, tmp1}, [RWK]!; \
-
-#define WPRECALC_00_15_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vadd.u32 tmp3, W5, curK; \
-
-#define WPRECALC_00_15_12(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vst1.32 {tmp2, tmp3}, [RWK]; \
-
-
-/********* Precalc macros for rounds 16-31 ************************************/
-
-#define WPRECALC_16_31_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor tmp0, tmp0; \
- vext.8 W, W_m16, W_m12, #8; \
-
-#define WPRECALC_16_31_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- add RWK, sp, #(WK_offs(i)); \
- vext.8 tmp0, W_m04, tmp0, #4; \
-
-#define WPRECALC_16_31_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor tmp0, tmp0, W_m16; \
- veor.32 W, W, W_m08; \
-
-#define WPRECALC_16_31_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor tmp1, tmp1; \
- veor W, W, tmp0; \
-
-#define WPRECALC_16_31_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vshl.u32 tmp0, W, #1; \
-
-#define WPRECALC_16_31_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vext.8 tmp1, tmp1, W, #(16-12); \
- vshr.u32 W, W, #31; \
-
-#define WPRECALC_16_31_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vorr tmp0, tmp0, W; \
- vshr.u32 W, tmp1, #30; \
-
-#define WPRECALC_16_31_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vshl.u32 tmp1, tmp1, #2; \
-
-#define WPRECALC_16_31_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor tmp0, tmp0, W; \
-
-#define WPRECALC_16_31_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor W, tmp0, tmp1; \
-
-#define WPRECALC_16_31_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vadd.u32 tmp0, W, curK; \
-
-#define WPRECALC_16_31_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vst1.32 {tmp0}, [RWK];
-
-
-/********* Precalc macros for rounds 32-79 ************************************/
-
-#define WPRECALC_32_79_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor W, W_m28; \
-
-#define WPRECALC_32_79_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vext.8 tmp0, W_m08, W_m04, #8; \
-
-#define WPRECALC_32_79_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor W, W_m16; \
-
-#define WPRECALC_32_79_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- veor W, tmp0; \
-
-#define WPRECALC_32_79_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- add RWK, sp, #(WK_offs(i&~3)); \
-
-#define WPRECALC_32_79_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vshl.u32 tmp1, W, #2; \
-
-#define WPRECALC_32_79_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vshr.u32 tmp0, W, #30; \
-
-#define WPRECALC_32_79_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vorr W, tmp0, tmp1; \
-
-#define WPRECALC_32_79_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vadd.u32 tmp0, W, curK; \
-
-#define WPRECALC_32_79_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
- vst1.32 {tmp0}, [RWK];
-
-
-/*
- * Transform nblks*64 bytes (nblks*16 32-bit words) at DATA.
- *
- * unsigned int
- * sha1_transform_neon (void *ctx, const unsigned char *data,
- * unsigned int nblks)
- */
-.align 3
-ENTRY(sha1_transform_neon)
- /* input:
- * r0: ctx, CTX
- * r1: data (64*nblks bytes)
- * r2: nblks
- */
-
- cmp RNBLKS, #0;
- beq .Ldo_nothing;
-
- push {r4-r12, lr};
- /*vpush {q4-q7};*/
-
- adr RT3, .LK_VEC;
-
- mov ROLDSTACK, sp;
-
- /* Align stack. */
- sub RT0, sp, #(16*4);
- and RT0, #(~(16-1));
- mov sp, RT0;
-
- vld1.32 {qK1-qK2}, [RT3]!; /* Load K1,K2 */
-
- /* Get the values of the chaining variables. */
- ldm RSTATE, {_a-_e};
-
- vld1.32 {qK3-qK4}, [RT3]; /* Load K3,K4 */
-
-#undef curK
-#define curK qK1
- /* Precalc 0-15. */
- W_PRECALC_00_15();
-
-.Loop:
- /* Transform 0-15 + Precalc 16-31. */
- _R( _a, _b, _c, _d, _e, F1, 0,
- WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 16,
- W4, W5, W6, W7, W0, _, _, _ );
- _R( _e, _a, _b, _c, _d, F1, 1,
- WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 16,
- W4, W5, W6, W7, W0, _, _, _ );
- _R( _d, _e, _a, _b, _c, F1, 2,
- WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 16,
- W4, W5, W6, W7, W0, _, _, _ );
- _R( _c, _d, _e, _a, _b, F1, 3,
- WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,16,
- W4, W5, W6, W7, W0, _, _, _ );
-
-#undef curK
-#define curK qK2
- _R( _b, _c, _d, _e, _a, F1, 4,
- WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 20,
- W3, W4, W5, W6, W7, _, _, _ );
- _R( _a, _b, _c, _d, _e, F1, 5,
- WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 20,
- W3, W4, W5, W6, W7, _, _, _ );
- _R( _e, _a, _b, _c, _d, F1, 6,
- WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 20,
- W3, W4, W5, W6, W7, _, _, _ );
- _R( _d, _e, _a, _b, _c, F1, 7,
- WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,20,
- W3, W4, W5, W6, W7, _, _, _ );
-
- _R( _c, _d, _e, _a, _b, F1, 8,
- WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 24,
- W2, W3, W4, W5, W6, _, _, _ );
- _R( _b, _c, _d, _e, _a, F1, 9,
- WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 24,
- W2, W3, W4, W5, W6, _, _, _ );
- _R( _a, _b, _c, _d, _e, F1, 10,
- WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 24,
- W2, W3, W4, W5, W6, _, _, _ );
- _R( _e, _a, _b, _c, _d, F1, 11,
- WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,24,
- W2, W3, W4, W5, W6, _, _, _ );
-
- _R( _d, _e, _a, _b, _c, F1, 12,
- WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 28,
- W1, W2, W3, W4, W5, _, _, _ );
- _R( _c, _d, _e, _a, _b, F1, 13,
- WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 28,
- W1, W2, W3, W4, W5, _, _, _ );
- _R( _b, _c, _d, _e, _a, F1, 14,
- WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 28,
- W1, W2, W3, W4, W5, _, _, _ );
- _R( _a, _b, _c, _d, _e, F1, 15,
- WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,28,
- W1, W2, W3, W4, W5, _, _, _ );
-
- /* Transform 16-63 + Precalc 32-79. */
- _R( _e, _a, _b, _c, _d, F1, 16,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 32,
- W0, W1, W2, W3, W4, W5, W6, W7);
- _R( _d, _e, _a, _b, _c, F1, 17,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 32,
- W0, W1, W2, W3, W4, W5, W6, W7);
- _R( _c, _d, _e, _a, _b, F1, 18,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 32,
- W0, W1, W2, W3, W4, W5, W6, W7);
- _R( _b, _c, _d, _e, _a, F1, 19,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 32,
- W0, W1, W2, W3, W4, W5, W6, W7);
-
- _R( _a, _b, _c, _d, _e, F2, 20,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 36,
- W7, W0, W1, W2, W3, W4, W5, W6);
- _R( _e, _a, _b, _c, _d, F2, 21,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 36,
- W7, W0, W1, W2, W3, W4, W5, W6);
- _R( _d, _e, _a, _b, _c, F2, 22,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 36,
- W7, W0, W1, W2, W3, W4, W5, W6);
- _R( _c, _d, _e, _a, _b, F2, 23,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 36,
- W7, W0, W1, W2, W3, W4, W5, W6);
-
-#undef curK
-#define curK qK3
- _R( _b, _c, _d, _e, _a, F2, 24,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 40,
- W6, W7, W0, W1, W2, W3, W4, W5);
- _R( _a, _b, _c, _d, _e, F2, 25,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 40,
- W6, W7, W0, W1, W2, W3, W4, W5);
- _R( _e, _a, _b, _c, _d, F2, 26,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 40,
- W6, W7, W0, W1, W2, W3, W4, W5);
- _R( _d, _e, _a, _b, _c, F2, 27,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 40,
- W6, W7, W0, W1, W2, W3, W4, W5);
-
- _R( _c, _d, _e, _a, _b, F2, 28,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 44,
- W5, W6, W7, W0, W1, W2, W3, W4);
- _R( _b, _c, _d, _e, _a, F2, 29,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 44,
- W5, W6, W7, W0, W1, W2, W3, W4);
- _R( _a, _b, _c, _d, _e, F2, 30,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 44,
- W5, W6, W7, W0, W1, W2, W3, W4);
- _R( _e, _a, _b, _c, _d, F2, 31,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 44,
- W5, W6, W7, W0, W1, W2, W3, W4);
-
- _R( _d, _e, _a, _b, _c, F2, 32,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 48,
- W4, W5, W6, W7, W0, W1, W2, W3);
- _R( _c, _d, _e, _a, _b, F2, 33,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 48,
- W4, W5, W6, W7, W0, W1, W2, W3);
- _R( _b, _c, _d, _e, _a, F2, 34,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 48,
- W4, W5, W6, W7, W0, W1, W2, W3);
- _R( _a, _b, _c, _d, _e, F2, 35,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 48,
- W4, W5, W6, W7, W0, W1, W2, W3);
-
- _R( _e, _a, _b, _c, _d, F2, 36,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 52,
- W3, W4, W5, W6, W7, W0, W1, W2);
- _R( _d, _e, _a, _b, _c, F2, 37,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 52,
- W3, W4, W5, W6, W7, W0, W1, W2);
- _R( _c, _d, _e, _a, _b, F2, 38,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 52,
- W3, W4, W5, W6, W7, W0, W1, W2);
- _R( _b, _c, _d, _e, _a, F2, 39,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 52,
- W3, W4, W5, W6, W7, W0, W1, W2);
-
- _R( _a, _b, _c, _d, _e, F3, 40,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 56,
- W2, W3, W4, W5, W6, W7, W0, W1);
- _R( _e, _a, _b, _c, _d, F3, 41,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 56,
- W2, W3, W4, W5, W6, W7, W0, W1);
- _R( _d, _e, _a, _b, _c, F3, 42,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 56,
- W2, W3, W4, W5, W6, W7, W0, W1);
- _R( _c, _d, _e, _a, _b, F3, 43,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 56,
- W2, W3, W4, W5, W6, W7, W0, W1);
-
-#undef curK
-#define curK qK4
- _R( _b, _c, _d, _e, _a, F3, 44,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 60,
- W1, W2, W3, W4, W5, W6, W7, W0);
- _R( _a, _b, _c, _d, _e, F3, 45,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 60,
- W1, W2, W3, W4, W5, W6, W7, W0);
- _R( _e, _a, _b, _c, _d, F3, 46,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 60,
- W1, W2, W3, W4, W5, W6, W7, W0);
- _R( _d, _e, _a, _b, _c, F3, 47,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 60,
- W1, W2, W3, W4, W5, W6, W7, W0);
-
- _R( _c, _d, _e, _a, _b, F3, 48,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 64,
- W0, W1, W2, W3, W4, W5, W6, W7);
- _R( _b, _c, _d, _e, _a, F3, 49,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 64,
- W0, W1, W2, W3, W4, W5, W6, W7);
- _R( _a, _b, _c, _d, _e, F3, 50,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 64,
- W0, W1, W2, W3, W4, W5, W6, W7);
- _R( _e, _a, _b, _c, _d, F3, 51,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 64,
- W0, W1, W2, W3, W4, W5, W6, W7);
-
- _R( _d, _e, _a, _b, _c, F3, 52,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 68,
- W7, W0, W1, W2, W3, W4, W5, W6);
- _R( _c, _d, _e, _a, _b, F3, 53,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 68,
- W7, W0, W1, W2, W3, W4, W5, W6);
- _R( _b, _c, _d, _e, _a, F3, 54,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 68,
- W7, W0, W1, W2, W3, W4, W5, W6);
- _R( _a, _b, _c, _d, _e, F3, 55,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 68,
- W7, W0, W1, W2, W3, W4, W5, W6);
-
- _R( _e, _a, _b, _c, _d, F3, 56,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 72,
- W6, W7, W0, W1, W2, W3, W4, W5);
- _R( _d, _e, _a, _b, _c, F3, 57,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 72,
- W6, W7, W0, W1, W2, W3, W4, W5);
- _R( _c, _d, _e, _a, _b, F3, 58,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 72,
- W6, W7, W0, W1, W2, W3, W4, W5);
- _R( _b, _c, _d, _e, _a, F3, 59,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 72,
- W6, W7, W0, W1, W2, W3, W4, W5);
-
- subs RNBLKS, #1;
-
- _R( _a, _b, _c, _d, _e, F4, 60,
- WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 76,
- W5, W6, W7, W0, W1, W2, W3, W4);
- _R( _e, _a, _b, _c, _d, F4, 61,
- WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 76,
- W5, W6, W7, W0, W1, W2, W3, W4);
- _R( _d, _e, _a, _b, _c, F4, 62,
- WPRECALC_32_79_6, dummy, WPRECALC_32_79_7, 76,
- W5, W6, W7, W0, W1, W2, W3, W4);
- _R( _c, _d, _e, _a, _b, F4, 63,
- WPRECALC_32_79_8, dummy, WPRECALC_32_79_9, 76,
- W5, W6, W7, W0, W1, W2, W3, W4);
-
- beq .Lend;
-
- /* Transform 64-79 + Precalc 0-15 of next block. */
-#undef curK
-#define curK qK1
- _R( _b, _c, _d, _e, _a, F4, 64,
- WPRECALC_00_15_0, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _a, _b, _c, _d, _e, F4, 65,
- WPRECALC_00_15_1, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _e, _a, _b, _c, _d, F4, 66,
- WPRECALC_00_15_2, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _d, _e, _a, _b, _c, F4, 67,
- WPRECALC_00_15_3, dummy, dummy, _, _, _, _, _, _, _, _, _ );
-
- _R( _c, _d, _e, _a, _b, F4, 68,
- dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _b, _c, _d, _e, _a, F4, 69,
- dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _a, _b, _c, _d, _e, F4, 70,
- WPRECALC_00_15_4, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _e, _a, _b, _c, _d, F4, 71,
- WPRECALC_00_15_5, dummy, dummy, _, _, _, _, _, _, _, _, _ );
-
- _R( _d, _e, _a, _b, _c, F4, 72,
- dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _c, _d, _e, _a, _b, F4, 73,
- dummy, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _b, _c, _d, _e, _a, F4, 74,
- WPRECALC_00_15_6, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _a, _b, _c, _d, _e, F4, 75,
- WPRECALC_00_15_7, dummy, dummy, _, _, _, _, _, _, _, _, _ );
-
- _R( _e, _a, _b, _c, _d, F4, 76,
- WPRECALC_00_15_8, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _d, _e, _a, _b, _c, F4, 77,
- WPRECALC_00_15_9, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _c, _d, _e, _a, _b, F4, 78,
- WPRECALC_00_15_10, dummy, dummy, _, _, _, _, _, _, _, _, _ );
- _R( _b, _c, _d, _e, _a, F4, 79,
- WPRECALC_00_15_11, dummy, WPRECALC_00_15_12, _, _, _, _, _, _, _, _, _ );
-
- /* Update the chaining variables. */
- ldm RSTATE, {RT0-RT3};
- add _a, RT0;
- ldr RT0, [RSTATE, #state_h4];
- add _b, RT1;
- add _c, RT2;
- add _d, RT3;
- add _e, RT0;
- stm RSTATE, {_a-_e};
-
- b .Loop;
-
-.Lend:
- /* Transform 64-79 */
- R( _b, _c, _d, _e, _a, F4, 64 );
- R( _a, _b, _c, _d, _e, F4, 65 );
- R( _e, _a, _b, _c, _d, F4, 66 );
- R( _d, _e, _a, _b, _c, F4, 67 );
- R( _c, _d, _e, _a, _b, F4, 68 );
- R( _b, _c, _d, _e, _a, F4, 69 );
- R( _a, _b, _c, _d, _e, F4, 70 );
- R( _e, _a, _b, _c, _d, F4, 71 );
- R( _d, _e, _a, _b, _c, F4, 72 );
- R( _c, _d, _e, _a, _b, F4, 73 );
- R( _b, _c, _d, _e, _a, F4, 74 );
- R( _a, _b, _c, _d, _e, F4, 75 );
- R( _e, _a, _b, _c, _d, F4, 76 );
- R( _d, _e, _a, _b, _c, F4, 77 );
- R( _c, _d, _e, _a, _b, F4, 78 );
- R( _b, _c, _d, _e, _a, F4, 79 );
-
- mov sp, ROLDSTACK;
-
- /* Update the chaining variables. */
- ldm RSTATE, {RT0-RT3};
- add _a, RT0;
- ldr RT0, [RSTATE, #state_h4];
- add _b, RT1;
- add _c, RT2;
- add _d, RT3;
- /*vpop {q4-q7};*/
- add _e, RT0;
- stm RSTATE, {_a-_e};
-
- pop {r4-r12, pc};
-
-.Ldo_nothing:
- bx lr
-ENDPROC(sha1_transform_neon)
diff --git a/arch/arm/crypto/sha1-ce-core.S b/arch/arm/crypto/sha1-ce-core.S
deleted file mode 100644
index 8a702e051738..000000000000
--- a/arch/arm/crypto/sha1-ce-core.S
+++ /dev/null
@@ -1,123 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
- *
- * Copyright (C) 2015 Linaro Ltd.
- * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
- .text
- .arch armv8-a
- .fpu crypto-neon-fp-armv8
-
- k0 .req q0
- k1 .req q1
- k2 .req q2
- k3 .req q3
-
- ta0 .req q4
- ta1 .req q5
- tb0 .req q5
- tb1 .req q4
-
- dga .req q6
- dgb .req q7
- dgbs .req s28
-
- dg0 .req q12
- dg1a0 .req q13
- dg1a1 .req q14
- dg1b0 .req q14
- dg1b1 .req q13
-
- .macro add_only, op, ev, rc, s0, dg1
- .ifnb \s0
- vadd.u32 tb\ev, q\s0, \rc
- .endif
- sha1h.32 dg1b\ev, dg0
- .ifb \dg1
- sha1\op\().32 dg0, dg1a\ev, ta\ev
- .else
- sha1\op\().32 dg0, \dg1, ta\ev
- .endif
- .endm
-
- .macro add_update, op, ev, rc, s0, s1, s2, s3, dg1
- sha1su0.32 q\s0, q\s1, q\s2
- add_only \op, \ev, \rc, \s1, \dg1
- sha1su1.32 q\s0, q\s3
- .endm
-
- .align 6
-.Lsha1_rcon:
- .word 0x5a827999, 0x5a827999, 0x5a827999, 0x5a827999
- .word 0x6ed9eba1, 0x6ed9eba1, 0x6ed9eba1, 0x6ed9eba1
- .word 0x8f1bbcdc, 0x8f1bbcdc, 0x8f1bbcdc, 0x8f1bbcdc
- .word 0xca62c1d6, 0xca62c1d6, 0xca62c1d6, 0xca62c1d6
-
- /*
- * void sha1_ce_transform(struct sha1_state *sst, u8 const *src,
- * int blocks);
- */
-ENTRY(sha1_ce_transform)
- /* load round constants */
- adr ip, .Lsha1_rcon
- vld1.32 {k0-k1}, [ip, :128]!
- vld1.32 {k2-k3}, [ip, :128]
-
- /* load state */
- vld1.32 {dga}, [r0]
- vldr dgbs, [r0, #16]
-
- /* load input */
-0: vld1.32 {q8-q9}, [r1]!
- vld1.32 {q10-q11}, [r1]!
- subs r2, r2, #1
-
-#ifndef CONFIG_CPU_BIG_ENDIAN
- vrev32.8 q8, q8
- vrev32.8 q9, q9
- vrev32.8 q10, q10
- vrev32.8 q11, q11
-#endif
-
- vadd.u32 ta0, q8, k0
- vmov dg0, dga
-
- add_update c, 0, k0, 8, 9, 10, 11, dgb
- add_update c, 1, k0, 9, 10, 11, 8
- add_update c, 0, k0, 10, 11, 8, 9
- add_update c, 1, k0, 11, 8, 9, 10
- add_update c, 0, k1, 8, 9, 10, 11
-
- add_update p, 1, k1, 9, 10, 11, 8
- add_update p, 0, k1, 10, 11, 8, 9
- add_update p, 1, k1, 11, 8, 9, 10
- add_update p, 0, k1, 8, 9, 10, 11
- add_update p, 1, k2, 9, 10, 11, 8
-
- add_update m, 0, k2, 10, 11, 8, 9
- add_update m, 1, k2, 11, 8, 9, 10
- add_update m, 0, k2, 8, 9, 10, 11
- add_update m, 1, k2, 9, 10, 11, 8
- add_update m, 0, k3, 10, 11, 8, 9
-
- add_update p, 1, k3, 11, 8, 9, 10
- add_only p, 0, k3, 9
- add_only p, 1, k3, 10
- add_only p, 0, k3, 11
- add_only p, 1
-
- /* update state */
- vadd.u32 dga, dga, dg0
- vadd.u32 dgb, dgb, dg1a0
- bne 0b
-
- /* store new state */
- vst1.32 {dga}, [r0]
- vstr dgbs, [r0, #16]
- bx lr
-ENDPROC(sha1_ce_transform)
diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c
deleted file mode 100644
index fac07a4799de..000000000000
--- a/arch/arm/crypto/sha1-ce-glue.c
+++ /dev/null
@@ -1,72 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
- *
- * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/neon.h>
-#include <crypto/internal/hash.h>
-#include <crypto/sha1.h>
-#include <crypto/sha1_base.h>
-#include <linux/cpufeature.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-
-asmlinkage void sha1_ce_transform(struct sha1_state *sst, u8 const *src,
- int blocks);
-
-static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- int remain;
-
- kernel_neon_begin();
- remain = sha1_base_do_update_blocks(desc, data, len, sha1_ce_transform);
- kernel_neon_end();
-
- return remain;
-}
-
-static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- kernel_neon_begin();
- sha1_base_do_finup(desc, data, len, sha1_ce_transform);
- kernel_neon_end();
-
- return sha1_base_finish(desc, out);
-}
-
-static struct shash_alg alg = {
- .init = sha1_base_init,
- .update = sha1_ce_update,
- .finup = sha1_ce_finup,
- .descsize = SHA1_STATE_SIZE,
- .digestsize = SHA1_DIGEST_SIZE,
- .base = {
- .cra_name = "sha1",
- .cra_driver_name = "sha1-ce",
- .cra_priority = 200,
- .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static int __init sha1_ce_mod_init(void)
-{
- return crypto_register_shash(&alg);
-}
-
-static void __exit sha1_ce_mod_fini(void)
-{
- crypto_unregister_shash(&alg);
-}
-
-module_cpu_feature_match(SHA1, sha1_ce_mod_init);
-module_exit(sha1_ce_mod_fini);
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
deleted file mode 100644
index 255da00c7d98..000000000000
--- a/arch/arm/crypto/sha1_glue.c
+++ /dev/null
@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cryptographic API.
- * Glue code for the SHA1 Secure Hash Algorithm assembler implementation
- *
- * This file is based on sha1_generic.c and sha1_ssse3_glue.c
- *
- * Copyright (c) Alan Smithee.
- * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
- * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
- * Copyright (c) Mathias Krause <minipli@googlemail.com>
- */
-
-#include <crypto/internal/hash.h>
-#include <crypto/sha1.h>
-#include <crypto/sha1_base.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-asmlinkage void sha1_block_data_order(struct sha1_state *digest,
- const u8 *data, int rounds);
-
-static int sha1_update_arm(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- /* make sure signature matches sha1_block_fn() */
- BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0);
-
- return sha1_base_do_update_blocks(desc, data, len,
- sha1_block_data_order);
-}
-
-static int sha1_finup_arm(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- sha1_base_do_finup(desc, data, len, sha1_block_data_order);
- return sha1_base_finish(desc, out);
-}
-
-static struct shash_alg alg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .init = sha1_base_init,
- .update = sha1_update_arm,
- .finup = sha1_finup_arm,
- .descsize = SHA1_STATE_SIZE,
- .base = {
- .cra_name = "sha1",
- .cra_driver_name= "sha1-asm",
- .cra_priority = 150,
- .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-
-static int __init sha1_mod_init(void)
-{
- return crypto_register_shash(&alg);
-}
-
-
-static void __exit sha1_mod_fini(void)
-{
- crypto_unregister_shash(&alg);
-}
-
-
-module_init(sha1_mod_init);
-module_exit(sha1_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm (ARM)");
-MODULE_ALIAS_CRYPTO("sha1");
-MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
deleted file mode 100644
index d321850f22a6..000000000000
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ /dev/null
@@ -1,83 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
- * ARM NEON instructions.
- *
- * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This file is based on sha1_generic.c and sha1_ssse3_glue.c:
- * Copyright (c) Alan Smithee.
- * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
- * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
- * Copyright (c) Mathias Krause <minipli@googlemail.com>
- * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
- */
-
-#include <asm/neon.h>
-#include <crypto/internal/hash.h>
-#include <crypto/sha1.h>
-#include <crypto/sha1_base.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-asmlinkage void sha1_transform_neon(struct sha1_state *state_h,
- const u8 *data, int rounds);
-
-static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- int remain;
-
- kernel_neon_begin();
- remain = sha1_base_do_update_blocks(desc, data, len,
- sha1_transform_neon);
- kernel_neon_end();
-
- return remain;
-}
-
-static int sha1_neon_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- kernel_neon_begin();
- sha1_base_do_finup(desc, data, len, sha1_transform_neon);
- kernel_neon_end();
-
- return sha1_base_finish(desc, out);
-}
-
-static struct shash_alg alg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .init = sha1_base_init,
- .update = sha1_neon_update,
- .finup = sha1_neon_finup,
- .descsize = SHA1_STATE_SIZE,
- .base = {
- .cra_name = "sha1",
- .cra_driver_name = "sha1-neon",
- .cra_priority = 250,
- .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static int __init sha1_neon_mod_init(void)
-{
- if (!cpu_has_neon())
- return -ENODEV;
-
- return crypto_register_shash(&alg);
-}
-
-static void __exit sha1_neon_mod_fini(void)
-{
- crypto_unregister_shash(&alg);
-}
-
-module_init(sha1_neon_mod_init);
-module_exit(sha1_neon_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
-MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
deleted file mode 100644
index 2fc3516912fa..000000000000
--- a/arch/arm/crypto/sha512-armv4.pl
+++ /dev/null
@@ -1,657 +0,0 @@
-#!/usr/bin/env perl
-# SPDX-License-Identifier: GPL-2.0
-
-# This code is taken from the OpenSSL project but the author (Andy Polyakov)
-# has relicensed it under the GPLv2. Therefore 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.
-#
-# The original headers, including the original license headers, are
-# included below for completeness.
-
-# ====================================================================
-# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
-# project. The module is, however, dual licensed under OpenSSL and
-# CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see https://www.openssl.org/~appro/cryptogams/.
-# ====================================================================
-
-# SHA512 block procedure for ARMv4. September 2007.
-
-# This code is ~4.5 (four and a half) times faster than code generated
-# by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
-# Xscale PXA250 core].
-#
-# July 2010.
-#
-# Rescheduling for dual-issue pipeline resulted in 6% improvement on
-# Cortex A8 core and ~40 cycles per processed byte.
-
-# February 2011.
-#
-# Profiler-assisted and platform-specific optimization resulted in 7%
-# improvement on Coxtex A8 core and ~38 cycles per byte.
-
-# March 2011.
-#
-# Add NEON implementation. On Cortex A8 it was measured to process
-# one byte in 23.3 cycles or ~60% faster than integer-only code.
-
-# August 2012.
-#
-# Improve NEON performance by 12% on Snapdragon S4. In absolute
-# terms it's 22.6 cycles per byte, which is disappointing result.
-# Technical writers asserted that 3-way S4 pipeline can sustain
-# multiple NEON instructions per cycle, but dual NEON issue could
-# not be observed, see https://www.openssl.org/~appro/Snapdragon-S4.html
-# for further details. On side note Cortex-A15 processes one byte in
-# 16 cycles.
-
-# Byte order [in]dependence. =========================================
-#
-# Originally caller was expected to maintain specific *dword* order in
-# h[0-7], namely with most significant dword at *lower* address, which
-# was reflected in below two parameters as 0 and 4. Now caller is
-# expected to maintain native byte order for whole 64-bit values.
-$hi="HI";
-$lo="LO";
-# ====================================================================
-
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
-
-$ctx="r0"; # parameter block
-$inp="r1";
-$len="r2";
-
-$Tlo="r3";
-$Thi="r4";
-$Alo="r5";
-$Ahi="r6";
-$Elo="r7";
-$Ehi="r8";
-$t0="r9";
-$t1="r10";
-$t2="r11";
-$t3="r12";
-############ r13 is stack pointer
-$Ktbl="r14";
-############ r15 is program counter
-
-$Aoff=8*0;
-$Boff=8*1;
-$Coff=8*2;
-$Doff=8*3;
-$Eoff=8*4;
-$Foff=8*5;
-$Goff=8*6;
-$Hoff=8*7;
-$Xoff=8*8;
-
-sub BODY_00_15() {
-my $magic = shift;
-$code.=<<___;
- @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
- @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
- @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
- mov $t0,$Elo,lsr#14
- str $Tlo,[sp,#$Xoff+0]
- mov $t1,$Ehi,lsr#14
- str $Thi,[sp,#$Xoff+4]
- eor $t0,$t0,$Ehi,lsl#18
- ldr $t2,[sp,#$Hoff+0] @ h.lo
- eor $t1,$t1,$Elo,lsl#18
- ldr $t3,[sp,#$Hoff+4] @ h.hi
- eor $t0,$t0,$Elo,lsr#18
- eor $t1,$t1,$Ehi,lsr#18
- eor $t0,$t0,$Ehi,lsl#14
- eor $t1,$t1,$Elo,lsl#14
- eor $t0,$t0,$Ehi,lsr#9
- eor $t1,$t1,$Elo,lsr#9
- eor $t0,$t0,$Elo,lsl#23
- eor $t1,$t1,$Ehi,lsl#23 @ Sigma1(e)
- adds $Tlo,$Tlo,$t0
- ldr $t0,[sp,#$Foff+0] @ f.lo
- adc $Thi,$Thi,$t1 @ T += Sigma1(e)
- ldr $t1,[sp,#$Foff+4] @ f.hi
- adds $Tlo,$Tlo,$t2
- ldr $t2,[sp,#$Goff+0] @ g.lo
- adc $Thi,$Thi,$t3 @ T += h
- ldr $t3,[sp,#$Goff+4] @ g.hi
-
- eor $t0,$t0,$t2
- str $Elo,[sp,#$Eoff+0]
- eor $t1,$t1,$t3
- str $Ehi,[sp,#$Eoff+4]
- and $t0,$t0,$Elo
- str $Alo,[sp,#$Aoff+0]
- and $t1,$t1,$Ehi
- str $Ahi,[sp,#$Aoff+4]
- eor $t0,$t0,$t2
- ldr $t2,[$Ktbl,#$lo] @ K[i].lo
- eor $t1,$t1,$t3 @ Ch(e,f,g)
- ldr $t3,[$Ktbl,#$hi] @ K[i].hi
-
- adds $Tlo,$Tlo,$t0
- ldr $Elo,[sp,#$Doff+0] @ d.lo
- adc $Thi,$Thi,$t1 @ T += Ch(e,f,g)
- ldr $Ehi,[sp,#$Doff+4] @ d.hi
- adds $Tlo,$Tlo,$t2
- and $t0,$t2,#0xff
- adc $Thi,$Thi,$t3 @ T += K[i]
- adds $Elo,$Elo,$Tlo
- ldr $t2,[sp,#$Boff+0] @ b.lo
- adc $Ehi,$Ehi,$Thi @ d += T
- teq $t0,#$magic
-
- ldr $t3,[sp,#$Coff+0] @ c.lo
-#if __ARM_ARCH__>=7
- it eq @ Thumb2 thing, sanity check in ARM
-#endif
- orreq $Ktbl,$Ktbl,#1
- @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
- @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
- @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
- mov $t0,$Alo,lsr#28
- mov $t1,$Ahi,lsr#28
- eor $t0,$t0,$Ahi,lsl#4
- eor $t1,$t1,$Alo,lsl#4
- eor $t0,$t0,$Ahi,lsr#2
- eor $t1,$t1,$Alo,lsr#2
- eor $t0,$t0,$Alo,lsl#30
- eor $t1,$t1,$Ahi,lsl#30
- eor $t0,$t0,$Ahi,lsr#7
- eor $t1,$t1,$Alo,lsr#7
- eor $t0,$t0,$Alo,lsl#25
- eor $t1,$t1,$Ahi,lsl#25 @ Sigma0(a)
- adds $Tlo,$Tlo,$t0
- and $t0,$Alo,$t2
- adc $Thi,$Thi,$t1 @ T += Sigma0(a)
-
- ldr $t1,[sp,#$Boff+4] @ b.hi
- orr $Alo,$Alo,$t2
- ldr $t2,[sp,#$Coff+4] @ c.hi
- and $Alo,$Alo,$t3
- and $t3,$Ahi,$t1
- orr $Ahi,$Ahi,$t1
- orr $Alo,$Alo,$t0 @ Maj(a,b,c).lo
- and $Ahi,$Ahi,$t2
- adds $Alo,$Alo,$Tlo
- orr $Ahi,$Ahi,$t3 @ Maj(a,b,c).hi
- sub sp,sp,#8
- adc $Ahi,$Ahi,$Thi @ h += T
- tst $Ktbl,#1
- add $Ktbl,$Ktbl,#8
-___
-}
-$code=<<___;
-#ifndef __KERNEL__
-# include "arm_arch.h"
-# define VFP_ABI_PUSH vstmdb sp!,{d8-d15}
-# define VFP_ABI_POP vldmia sp!,{d8-d15}
-#else
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
-# define __ARM_MAX_ARCH__ 7
-# define VFP_ABI_PUSH
-# define VFP_ABI_POP
-#endif
-
-#ifdef __ARMEL__
-# define LO 0
-# define HI 4
-# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1
-#else
-# define HI 0
-# define LO 4
-# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1
-#endif
-
-.text
-#if __ARM_ARCH__<7
-.code 32
-#else
-.syntax unified
-# ifdef __thumb2__
-.thumb
-# else
-.code 32
-# endif
-#endif
-
-.type K512,%object
-.align 5
-K512:
-WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
-WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
-WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
-WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
-WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
-WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
-WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
-WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
-WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
-WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
-WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
-WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
-WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
-WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
-WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
-WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
-WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
-WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
-WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
-WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
-WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
-WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
-WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
-WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
-WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
-WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
-WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
-WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
-WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
-WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
-WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
-WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
-WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
-WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
-WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
-WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
-WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
-WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
-WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
-WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
-.size K512,.-K512
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.LOPENSSL_armcap:
-.word OPENSSL_armcap_P-sha512_block_data_order
-.skip 32-4
-#else
-.skip 32
-#endif
-
-.global sha512_block_data_order
-.type sha512_block_data_order,%function
-sha512_block_data_order:
-.Lsha512_block_data_order:
-#if __ARM_ARCH__<7
- sub r3,pc,#8 @ sha512_block_data_order
-#else
- adr r3,.Lsha512_block_data_order
-#endif
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
- ldr r12,.LOPENSSL_armcap
- ldr r12,[r3,r12] @ OPENSSL_armcap_P
- tst r12,#1
- bne .LNEON
-#endif
- add $len,$inp,$len,lsl#7 @ len to point at the end of inp
- stmdb sp!,{r4-r12,lr}
- sub $Ktbl,r3,#672 @ K512
- sub sp,sp,#9*8
-
- ldr $Elo,[$ctx,#$Eoff+$lo]
- ldr $Ehi,[$ctx,#$Eoff+$hi]
- ldr $t0, [$ctx,#$Goff+$lo]
- ldr $t1, [$ctx,#$Goff+$hi]
- ldr $t2, [$ctx,#$Hoff+$lo]
- ldr $t3, [$ctx,#$Hoff+$hi]
-.Loop:
- str $t0, [sp,#$Goff+0]
- str $t1, [sp,#$Goff+4]
- str $t2, [sp,#$Hoff+0]
- str $t3, [sp,#$Hoff+4]
- ldr $Alo,[$ctx,#$Aoff+$lo]
- ldr $Ahi,[$ctx,#$Aoff+$hi]
- ldr $Tlo,[$ctx,#$Boff+$lo]
- ldr $Thi,[$ctx,#$Boff+$hi]
- ldr $t0, [$ctx,#$Coff+$lo]
- ldr $t1, [$ctx,#$Coff+$hi]
- ldr $t2, [$ctx,#$Doff+$lo]
- ldr $t3, [$ctx,#$Doff+$hi]
- str $Tlo,[sp,#$Boff+0]
- str $Thi,[sp,#$Boff+4]
- str $t0, [sp,#$Coff+0]
- str $t1, [sp,#$Coff+4]
- str $t2, [sp,#$Doff+0]
- str $t3, [sp,#$Doff+4]
- ldr $Tlo,[$ctx,#$Foff+$lo]
- ldr $Thi,[$ctx,#$Foff+$hi]
- str $Tlo,[sp,#$Foff+0]
- str $Thi,[sp,#$Foff+4]
-
-.L00_15:
-#if __ARM_ARCH__<7
- ldrb $Tlo,[$inp,#7]
- ldrb $t0, [$inp,#6]
- ldrb $t1, [$inp,#5]
- ldrb $t2, [$inp,#4]
- ldrb $Thi,[$inp,#3]
- ldrb $t3, [$inp,#2]
- orr $Tlo,$Tlo,$t0,lsl#8
- ldrb $t0, [$inp,#1]
- orr $Tlo,$Tlo,$t1,lsl#16
- ldrb $t1, [$inp],#8
- orr $Tlo,$Tlo,$t2,lsl#24
- orr $Thi,$Thi,$t3,lsl#8
- orr $Thi,$Thi,$t0,lsl#16
- orr $Thi,$Thi,$t1,lsl#24
-#else
- ldr $Tlo,[$inp,#4]
- ldr $Thi,[$inp],#8
-#ifdef __ARMEL__
- rev $Tlo,$Tlo
- rev $Thi,$Thi
-#endif
-#endif
-___
- &BODY_00_15(0x94);
-$code.=<<___;
- tst $Ktbl,#1
- beq .L00_15
- ldr $t0,[sp,#`$Xoff+8*(16-1)`+0]
- ldr $t1,[sp,#`$Xoff+8*(16-1)`+4]
- bic $Ktbl,$Ktbl,#1
-.L16_79:
- @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7))
- @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
- @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7
- mov $Tlo,$t0,lsr#1
- ldr $t2,[sp,#`$Xoff+8*(16-14)`+0]
- mov $Thi,$t1,lsr#1
- ldr $t3,[sp,#`$Xoff+8*(16-14)`+4]
- eor $Tlo,$Tlo,$t1,lsl#31
- eor $Thi,$Thi,$t0,lsl#31
- eor $Tlo,$Tlo,$t0,lsr#8
- eor $Thi,$Thi,$t1,lsr#8
- eor $Tlo,$Tlo,$t1,lsl#24
- eor $Thi,$Thi,$t0,lsl#24
- eor $Tlo,$Tlo,$t0,lsr#7
- eor $Thi,$Thi,$t1,lsr#7
- eor $Tlo,$Tlo,$t1,lsl#25
-
- @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
- @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
- @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
- mov $t0,$t2,lsr#19
- mov $t1,$t3,lsr#19
- eor $t0,$t0,$t3,lsl#13
- eor $t1,$t1,$t2,lsl#13
- eor $t0,$t0,$t3,lsr#29
- eor $t1,$t1,$t2,lsr#29
- eor $t0,$t0,$t2,lsl#3
- eor $t1,$t1,$t3,lsl#3
- eor $t0,$t0,$t2,lsr#6
- eor $t1,$t1,$t3,lsr#6
- ldr $t2,[sp,#`$Xoff+8*(16-9)`+0]
- eor $t0,$t0,$t3,lsl#26
-
- ldr $t3,[sp,#`$Xoff+8*(16-9)`+4]
- adds $Tlo,$Tlo,$t0
- ldr $t0,[sp,#`$Xoff+8*16`+0]
- adc $Thi,$Thi,$t1
-
- ldr $t1,[sp,#`$Xoff+8*16`+4]
- adds $Tlo,$Tlo,$t2
- adc $Thi,$Thi,$t3
- adds $Tlo,$Tlo,$t0
- adc $Thi,$Thi,$t1
-___
- &BODY_00_15(0x17);
-$code.=<<___;
-#if __ARM_ARCH__>=7
- ittt eq @ Thumb2 thing, sanity check in ARM
-#endif
- ldreq $t0,[sp,#`$Xoff+8*(16-1)`+0]
- ldreq $t1,[sp,#`$Xoff+8*(16-1)`+4]
- beq .L16_79
- bic $Ktbl,$Ktbl,#1
-
- ldr $Tlo,[sp,#$Boff+0]
- ldr $Thi,[sp,#$Boff+4]
- ldr $t0, [$ctx,#$Aoff+$lo]
- ldr $t1, [$ctx,#$Aoff+$hi]
- ldr $t2, [$ctx,#$Boff+$lo]
- ldr $t3, [$ctx,#$Boff+$hi]
- adds $t0,$Alo,$t0
- str $t0, [$ctx,#$Aoff+$lo]
- adc $t1,$Ahi,$t1
- str $t1, [$ctx,#$Aoff+$hi]
- adds $t2,$Tlo,$t2
- str $t2, [$ctx,#$Boff+$lo]
- adc $t3,$Thi,$t3
- str $t3, [$ctx,#$Boff+$hi]
-
- ldr $Alo,[sp,#$Coff+0]
- ldr $Ahi,[sp,#$Coff+4]
- ldr $Tlo,[sp,#$Doff+0]
- ldr $Thi,[sp,#$Doff+4]
- ldr $t0, [$ctx,#$Coff+$lo]
- ldr $t1, [$ctx,#$Coff+$hi]
- ldr $t2, [$ctx,#$Doff+$lo]
- ldr $t3, [$ctx,#$Doff+$hi]
- adds $t0,$Alo,$t0
- str $t0, [$ctx,#$Coff+$lo]
- adc $t1,$Ahi,$t1
- str $t1, [$ctx,#$Coff+$hi]
- adds $t2,$Tlo,$t2
- str $t2, [$ctx,#$Doff+$lo]
- adc $t3,$Thi,$t3
- str $t3, [$ctx,#$Doff+$hi]
-
- ldr $Tlo,[sp,#$Foff+0]
- ldr $Thi,[sp,#$Foff+4]
- ldr $t0, [$ctx,#$Eoff+$lo]
- ldr $t1, [$ctx,#$Eoff+$hi]
- ldr $t2, [$ctx,#$Foff+$lo]
- ldr $t3, [$ctx,#$Foff+$hi]
- adds $Elo,$Elo,$t0
- str $Elo,[$ctx,#$Eoff+$lo]
- adc $Ehi,$Ehi,$t1
- str $Ehi,[$ctx,#$Eoff+$hi]
- adds $t2,$Tlo,$t2
- str $t2, [$ctx,#$Foff+$lo]
- adc $t3,$Thi,$t3
- str $t3, [$ctx,#$Foff+$hi]
-
- ldr $Alo,[sp,#$Goff+0]
- ldr $Ahi,[sp,#$Goff+4]
- ldr $Tlo,[sp,#$Hoff+0]
- ldr $Thi,[sp,#$Hoff+4]
- ldr $t0, [$ctx,#$Goff+$lo]
- ldr $t1, [$ctx,#$Goff+$hi]
- ldr $t2, [$ctx,#$Hoff+$lo]
- ldr $t3, [$ctx,#$Hoff+$hi]
- adds $t0,$Alo,$t0
- str $t0, [$ctx,#$Goff+$lo]
- adc $t1,$Ahi,$t1
- str $t1, [$ctx,#$Goff+$hi]
- adds $t2,$Tlo,$t2
- str $t2, [$ctx,#$Hoff+$lo]
- adc $t3,$Thi,$t3
- str $t3, [$ctx,#$Hoff+$hi]
-
- add sp,sp,#640
- sub $Ktbl,$Ktbl,#640
-
- teq $inp,$len
- bne .Loop
-
- add sp,sp,#8*9 @ destroy frame
-#if __ARM_ARCH__>=5
- ldmia sp!,{r4-r12,pc}
-#else
- ldmia sp!,{r4-r12,lr}
- tst lr,#1
- moveq pc,lr @ be binary compatible with V4, yet
- bx lr @ interoperable with Thumb ISA:-)
-#endif
-.size sha512_block_data_order,.-sha512_block_data_order
-___
-
-{
-my @Sigma0=(28,34,39);
-my @Sigma1=(14,18,41);
-my @sigma0=(1, 8, 7);
-my @sigma1=(19,61,6);
-
-my $Ktbl="r3";
-my $cnt="r12"; # volatile register known as ip, intra-procedure-call scratch
-
-my @X=map("d$_",(0..15));
-my @V=($A,$B,$C,$D,$E,$F,$G,$H)=map("d$_",(16..23));
-
-sub NEON_00_15() {
-my $i=shift;
-my ($a,$b,$c,$d,$e,$f,$g,$h)=@_;
-my ($t0,$t1,$t2,$T1,$K,$Ch,$Maj)=map("d$_",(24..31)); # temps
-
-$code.=<<___ if ($i<16 || $i&1);
- vshr.u64 $t0,$e,#@Sigma1[0] @ $i
-#if $i<16
- vld1.64 {@X[$i%16]},[$inp]! @ handles unaligned
-#endif
- vshr.u64 $t1,$e,#@Sigma1[1]
-#if $i>0
- vadd.i64 $a,$Maj @ h+=Maj from the past
-#endif
- vshr.u64 $t2,$e,#@Sigma1[2]
-___
-$code.=<<___;
- vld1.64 {$K},[$Ktbl,:64]! @ K[i++]
- vsli.64 $t0,$e,#`64-@Sigma1[0]`
- vsli.64 $t1,$e,#`64-@Sigma1[1]`
- vmov $Ch,$e
- vsli.64 $t2,$e,#`64-@Sigma1[2]`
-#if $i<16 && defined(__ARMEL__)
- vrev64.8 @X[$i],@X[$i]
-#endif
- veor $t1,$t0
- vbsl $Ch,$f,$g @ Ch(e,f,g)
- vshr.u64 $t0,$a,#@Sigma0[0]
- veor $t2,$t1 @ Sigma1(e)
- vadd.i64 $T1,$Ch,$h
- vshr.u64 $t1,$a,#@Sigma0[1]
- vsli.64 $t0,$a,#`64-@Sigma0[0]`
- vadd.i64 $T1,$t2
- vshr.u64 $t2,$a,#@Sigma0[2]
- vadd.i64 $K,@X[$i%16]
- vsli.64 $t1,$a,#`64-@Sigma0[1]`
- veor $Maj,$a,$b
- vsli.64 $t2,$a,#`64-@Sigma0[2]`
- veor $h,$t0,$t1
- vadd.i64 $T1,$K
- vbsl $Maj,$c,$b @ Maj(a,b,c)
- veor $h,$t2 @ Sigma0(a)
- vadd.i64 $d,$T1
- vadd.i64 $Maj,$T1
- @ vadd.i64 $h,$Maj
-___
-}
-
-sub NEON_16_79() {
-my $i=shift;
-
-if ($i&1) { &NEON_00_15($i,@_); return; }
-
-# 2x-vectorized, therefore runs every 2nd round
-my @X=map("q$_",(0..7)); # view @X as 128-bit vector
-my ($t0,$t1,$s0,$s1) = map("q$_",(12..15)); # temps
-my ($d0,$d1,$d2) = map("d$_",(24..26)); # temps from NEON_00_15
-my $e=@_[4]; # $e from NEON_00_15
-$i /= 2;
-$code.=<<___;
- vshr.u64 $t0,@X[($i+7)%8],#@sigma1[0]
- vshr.u64 $t1,@X[($i+7)%8],#@sigma1[1]
- vadd.i64 @_[0],d30 @ h+=Maj from the past
- vshr.u64 $s1,@X[($i+7)%8],#@sigma1[2]
- vsli.64 $t0,@X[($i+7)%8],#`64-@sigma1[0]`
- vext.8 $s0,@X[$i%8],@X[($i+1)%8],#8 @ X[i+1]
- vsli.64 $t1,@X[($i+7)%8],#`64-@sigma1[1]`
- veor $s1,$t0
- vshr.u64 $t0,$s0,#@sigma0[0]
- veor $s1,$t1 @ sigma1(X[i+14])
- vshr.u64 $t1,$s0,#@sigma0[1]
- vadd.i64 @X[$i%8],$s1
- vshr.u64 $s1,$s0,#@sigma0[2]
- vsli.64 $t0,$s0,#`64-@sigma0[0]`
- vsli.64 $t1,$s0,#`64-@sigma0[1]`
- vext.8 $s0,@X[($i+4)%8],@X[($i+5)%8],#8 @ X[i+9]
- veor $s1,$t0
- vshr.u64 $d0,$e,#@Sigma1[0] @ from NEON_00_15
- vadd.i64 @X[$i%8],$s0
- vshr.u64 $d1,$e,#@Sigma1[1] @ from NEON_00_15
- veor $s1,$t1 @ sigma0(X[i+1])
- vshr.u64 $d2,$e,#@Sigma1[2] @ from NEON_00_15
- vadd.i64 @X[$i%8],$s1
-___
- &NEON_00_15(2*$i,@_);
-}
-
-$code.=<<___;
-#if __ARM_MAX_ARCH__>=7
-.arch armv7-a
-.fpu neon
-
-.global sha512_block_data_order_neon
-.type sha512_block_data_order_neon,%function
-.align 4
-sha512_block_data_order_neon:
-.LNEON:
- dmb @ errata #451034 on early Cortex A8
- add $len,$inp,$len,lsl#7 @ len to point at the end of inp
- VFP_ABI_PUSH
- adr $Ktbl,.Lsha512_block_data_order
- sub $Ktbl,$Ktbl,.Lsha512_block_data_order-K512
- vldmia $ctx,{$A-$H} @ load context
-.Loop_neon:
-___
-for($i=0;$i<16;$i++) { &NEON_00_15($i,@V); unshift(@V,pop(@V)); }
-$code.=<<___;
- mov $cnt,#4
-.L16_79_neon:
- subs $cnt,#1
-___
-for(;$i<32;$i++) { &NEON_16_79($i,@V); unshift(@V,pop(@V)); }
-$code.=<<___;
- bne .L16_79_neon
-
- vadd.i64 $A,d30 @ h+=Maj from the past
- vldmia $ctx,{d24-d31} @ load context to temp
- vadd.i64 q8,q12 @ vectorized accumulate
- vadd.i64 q9,q13
- vadd.i64 q10,q14
- vadd.i64 q11,q15
- vstmia $ctx,{$A-$H} @ save context
- teq $inp,$len
- sub $Ktbl,#640 @ rewind K512
- bne .Loop_neon
-
- VFP_ABI_POP
- ret @ bx lr
-.size sha512_block_data_order_neon,.-sha512_block_data_order_neon
-#endif
-___
-}
-$code.=<<___;
-.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>"
-.align 2
-#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
-.comm OPENSSL_armcap_P,4,4
-#endif
-___
-
-$code =~ s/\`([^\`]*)\`/eval $1/gem;
-$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm; # make it possible to compile with -march=armv4
-$code =~ s/\bret\b/bx lr/gm;
-
-open SELF,$0;
-while(<SELF>) {
- next if (/^#!/);
- last if (!s/^#/@/ and !/^$/);
- print;
-}
-close SELF;
-
-print $code;
-close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
deleted file mode 100644
index f8a6480889b1..000000000000
--- a/arch/arm/crypto/sha512-glue.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha512-glue.c - accelerated SHA-384/512 for ARM
- *
- * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <crypto/internal/hash.h>
-#include <crypto/sha2.h>
-#include <crypto/sha512_base.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include "sha512.h"
-
-MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-
-MODULE_ALIAS_CRYPTO("sha384");
-MODULE_ALIAS_CRYPTO("sha512");
-MODULE_ALIAS_CRYPTO("sha384-arm");
-MODULE_ALIAS_CRYPTO("sha512-arm");
-
-asmlinkage void sha512_block_data_order(struct sha512_state *state,
- u8 const *src, int blocks);
-
-static int sha512_arm_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha512_base_do_update_blocks(desc, data, len,
- sha512_block_data_order);
-}
-
-static int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- sha512_base_do_finup(desc, data, len, sha512_block_data_order);
- return sha512_base_finish(desc, out);
-}
-
-static struct shash_alg sha512_arm_algs[] = { {
- .init = sha384_base_init,
- .update = sha512_arm_update,
- .finup = sha512_arm_finup,
- .descsize = SHA512_STATE_SIZE,
- .digestsize = SHA384_DIGEST_SIZE,
- .base = {
- .cra_name = "sha384",
- .cra_driver_name = "sha384-arm",
- .cra_priority = 250,
- .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
- CRYPTO_AHASH_ALG_FINUP_MAX,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .init = sha512_base_init,
- .update = sha512_arm_update,
- .finup = sha512_arm_finup,
- .descsize = SHA512_STATE_SIZE,
- .digestsize = SHA512_DIGEST_SIZE,
- .base = {
- .cra_name = "sha512",
- .cra_driver_name = "sha512-arm",
- .cra_priority = 250,
- .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
- CRYPTO_AHASH_ALG_FINUP_MAX,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static int __init sha512_arm_mod_init(void)
-{
- int err;
-
- err = crypto_register_shashes(sha512_arm_algs,
- ARRAY_SIZE(sha512_arm_algs));
- if (err)
- return err;
-
- if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
- err = crypto_register_shashes(sha512_neon_algs,
- ARRAY_SIZE(sha512_neon_algs));
- if (err)
- goto err_unregister;
- }
- return 0;
-
-err_unregister:
- crypto_unregister_shashes(sha512_arm_algs,
- ARRAY_SIZE(sha512_arm_algs));
-
- return err;
-}
-
-static void __exit sha512_arm_mod_fini(void)
-{
- crypto_unregister_shashes(sha512_arm_algs,
- ARRAY_SIZE(sha512_arm_algs));
- if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
- crypto_unregister_shashes(sha512_neon_algs,
- ARRAY_SIZE(sha512_neon_algs));
-}
-
-module_init(sha512_arm_mod_init);
-module_exit(sha512_arm_mod_fini);
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
deleted file mode 100644
index bd528077fefb..000000000000
--- a/arch/arm/crypto/sha512-neon-glue.c
+++ /dev/null
@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON
- *
- * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/neon.h>
-#include <crypto/internal/hash.h>
-#include <crypto/sha2.h>
-#include <crypto/sha512_base.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include "sha512.h"
-
-MODULE_ALIAS_CRYPTO("sha384-neon");
-MODULE_ALIAS_CRYPTO("sha512-neon");
-
-asmlinkage void sha512_block_data_order_neon(struct sha512_state *state,
- const u8 *src, int blocks);
-
-static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- int remain;
-
- kernel_neon_begin();
- remain = sha512_base_do_update_blocks(desc, data, len,
- sha512_block_data_order_neon);
- kernel_neon_end();
- return remain;
-}
-
-static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- kernel_neon_begin();
- sha512_base_do_finup(desc, data, len, sha512_block_data_order_neon);
- kernel_neon_end();
- return sha512_base_finish(desc, out);
-}
-
-struct shash_alg sha512_neon_algs[] = { {
- .init = sha384_base_init,
- .update = sha512_neon_update,
- .finup = sha512_neon_finup,
- .descsize = SHA512_STATE_SIZE,
- .digestsize = SHA384_DIGEST_SIZE,
- .base = {
- .cra_name = "sha384",
- .cra_driver_name = "sha384-neon",
- .cra_priority = 300,
- .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
- CRYPTO_AHASH_ALG_FINUP_MAX,
- .cra_blocksize = SHA384_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
-
- }
-}, {
- .init = sha512_base_init,
- .update = sha512_neon_update,
- .finup = sha512_neon_finup,
- .descsize = SHA512_STATE_SIZE,
- .digestsize = SHA512_DIGEST_SIZE,
- .base = {
- .cra_name = "sha512",
- .cra_driver_name = "sha512-neon",
- .cra_priority = 300,
- .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
- CRYPTO_AHASH_ALG_FINUP_MAX,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
deleted file mode 100644
index eeaee52cda69..000000000000
--- a/arch/arm/crypto/sha512.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-extern struct shash_alg sha512_neon_algs[2];
generated by cgit (git 2.34.1) at 2025-07-29 15:39:16 +0000