summaryrefslogtreecommitdiffstats
path: root/arch/arm/crypto
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
commitace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch)
treeb2d64bc10158fdd5497876388cd68142ca374ed3 /arch/arm/crypto
parentInitial commit. (diff)
downloadlinux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz
linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/arm/crypto')
-rw-r--r--arch/arm/crypto/.gitignore5
-rw-r--r--arch/arm/crypto/Kconfig245
-rw-r--r--arch/arm/crypto/Makefile64
-rw-r--r--arch/arm/crypto/aes-ce-core.S713
-rw-r--r--arch/arm/crypto/aes-ce-glue.c730
-rw-r--r--arch/arm/crypto/aes-cipher-core.S201
-rw-r--r--arch/arm/crypto/aes-cipher-glue.c68
-rw-r--r--arch/arm/crypto/aes-neonbs-core.S1043
-rw-r--r--arch/arm/crypto/aes-neonbs-glue.c557
-rw-r--r--arch/arm/crypto/blake2b-neon-core.S347
-rw-r--r--arch/arm/crypto/blake2b-neon-glue.c105
-rw-r--r--arch/arm/crypto/blake2s-core.S306
-rw-r--r--arch/arm/crypto/blake2s-glue.c7
-rw-r--r--arch/arm/crypto/chacha-glue.c358
-rw-r--r--arch/arm/crypto/chacha-neon-core.S643
-rw-r--r--arch/arm/crypto/chacha-scalar-core.S443
-rw-r--r--arch/arm/crypto/crc32-ce-core.S306
-rw-r--r--arch/arm/crypto/crc32-ce-glue.c246
-rw-r--r--arch/arm/crypto/crct10dif-ce-core.S381
-rw-r--r--arch/arm/crypto/crct10dif-ce-glue.c88
-rw-r--r--arch/arm/crypto/curve25519-core.S2062
-rw-r--r--arch/arm/crypto/curve25519-glue.c136
-rw-r--r--arch/arm/crypto/ghash-ce-core.S695
-rw-r--r--arch/arm/crypto/ghash-ce-glue.c795
-rw-r--r--arch/arm/crypto/nh-neon-core.S116
-rw-r--r--arch/arm/crypto/nhpoly1305-neon-glue.c71
-rw-r--r--arch/arm/crypto/poly1305-armv4.pl1236
-rw-r--r--arch/arm/crypto/poly1305-glue.c273
-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.c92
-rw-r--r--arch/arm/crypto/sha1.h14
-rw-r--r--arch/arm/crypto/sha1_glue.c86
-rw-r--r--arch/arm/crypto/sha1_neon_glue.c102
-rw-r--r--arch/arm/crypto/sha2-ce-core.S123
-rw-r--r--arch/arm/crypto/sha2-ce-glue.c109
-rw-r--r--arch/arm/crypto/sha256-armv4.pl724
-rw-r--r--arch/arm/crypto/sha256_glue.c120
-rw-r--r--arch/arm/crypto/sha256_glue.h15
-rw-r--r--arch/arm/crypto/sha256_neon_glue.c92
-rw-r--r--arch/arm/crypto/sha512-armv4.pl657
-rw-r--r--arch/arm/crypto/sha512-glue.c116
-rw-r--r--arch/arm/crypto/sha512-neon-glue.c92
-rw-r--r--arch/arm/crypto/sha512.h9
45 files changed, 15855 insertions, 0 deletions
diff --git a/arch/arm/crypto/.gitignore b/arch/arm/crypto/.gitignore
new file mode 100644
index 0000000000..8d7f4bcaec
--- /dev/null
+++ b/arch/arm/crypto/.gitignore
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+aesbs-core.S
+sha256-core.S
+sha512-core.S
+poly1305-core.S
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
new file mode 100644
index 0000000000..847b7a0033
--- /dev/null
+++ b/arch/arm/crypto/Kconfig
@@ -0,0 +1,245 @@
+# SPDX-License-Identifier: GPL-2.0
+
+menu "Accelerated Cryptographic Algorithms for CPU (arm)"
+
+config CRYPTO_CURVE25519_NEON
+ tristate "Public key crypto: Curve25519 (NEON)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_LIB_CURVE25519_GENERIC
+ select CRYPTO_ARCH_HAVE_LIB_CURVE25519
+ help
+ Curve25519 algorithm
+
+ Architecture: arm with
+ - NEON (Advanced SIMD) extensions
+
+config CRYPTO_GHASH_ARM_CE
+ tristate "Hash functions: GHASH (PMULL/NEON/ARMv8 Crypto Extensions)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_AEAD
+ select CRYPTO_HASH
+ select CRYPTO_CRYPTD
+ select CRYPTO_LIB_AES
+ select CRYPTO_LIB_GF128MUL
+ help
+ GCM GHASH function (NIST SP800-38D)
+
+ Architecture: arm using
+ - PMULL (Polynomial Multiply Long) instructions
+ - NEON (Advanced SIMD) extensions
+ - ARMv8 Crypto Extensions
+
+ Use an implementation of GHASH (used by the GCM AEAD chaining mode)
+ that uses the 64x64 to 128 bit polynomial multiplication (vmull.p64)
+ that is part of the ARMv8 Crypto Extensions, or a slower variant that
+ uses the vmull.p8 instruction that is part of the basic NEON ISA.
+
+config CRYPTO_NHPOLY1305_NEON
+ tristate "Hash functions: NHPoly1305 (NEON)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_NHPOLY1305
+ help
+ NHPoly1305 hash function (Adiantum)
+
+ Architecture: arm using:
+ - NEON (Advanced SIMD) extensions
+
+config CRYPTO_POLY1305_ARM
+ tristate "Hash functions: Poly1305 (NEON)"
+ select CRYPTO_HASH
+ select CRYPTO_ARCH_HAVE_LIB_POLY1305
+ help
+ Poly1305 authenticator algorithm (RFC7539)
+
+ Architecture: arm optionally using
+ - NEON (Advanced SIMD) extensions
+
+config CRYPTO_BLAKE2S_ARM
+ bool "Hash functions: BLAKE2s"
+ select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
+ help
+ BLAKE2s cryptographic hash function (RFC 7693)
+
+ Architecture: arm
+
+ This is faster than the generic implementations of BLAKE2s and
+ BLAKE2b, but slower than the NEON implementation of BLAKE2b.
+ There is no NEON implementation of BLAKE2s, since NEON doesn't
+ really help with it.
+
+config CRYPTO_BLAKE2B_NEON
+ tristate "Hash functions: BLAKE2b (NEON)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_BLAKE2B
+ help
+ BLAKE2b cryptographic hash function (RFC 7693)
+
+ Architecture: arm using
+ - NEON (Advanced SIMD) extensions
+
+ BLAKE2b digest algorithm optimized with ARM NEON instructions.
+ On ARM processors that have NEON support but not the ARMv8
+ Crypto Extensions, typically this BLAKE2b implementation is
+ 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_SHA2_ARM_CE
+ tristate "Hash functions: SHA-224 and SHA-256 (ARMv8 Crypto Extensions)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_SHA256_ARM
+ select CRYPTO_HASH
+ help
+ SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
+
+ Architecture: arm using
+ - ARMv8 Crypto Extensions
+
+config CRYPTO_SHA256_ARM
+ tristate "Hash functions: SHA-224 and SHA-256 (NEON)"
+ select CRYPTO_HASH
+ depends on !CPU_V7M
+ help
+ SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
+
+ Architecture: arm using
+ - NEON (Advanced SIMD) 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
+ select CRYPTO_AES
+ help
+ Block ciphers: AES cipher algorithms (FIPS-197)
+
+ Architecture: arm
+
+ On ARM processors without the Crypto Extensions, this is the
+ fastest AES implementation for single blocks. For multiple
+ blocks, the NEON bit-sliced implementation is usually faster.
+
+ This implementation may be vulnerable to cache timing attacks,
+ since it uses lookup tables. However, as countermeasures it
+ disables IRQs and preloads the tables; it is hoped this makes
+ such attacks very difficult.
+
+config CRYPTO_AES_ARM_BS
+ tristate "Ciphers: AES, modes: ECB/CBC/CTR/XTS (bit-sliced NEON)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_SKCIPHER
+ select CRYPTO_LIB_AES
+ select CRYPTO_AES
+ select CRYPTO_CBC
+ select CRYPTO_SIMD
+ help
+ Length-preserving ciphers: AES cipher algorithms (FIPS-197)
+ with block cipher modes:
+ - ECB (Electronic Codebook) mode (NIST SP800-38A)
+ - CBC (Cipher Block Chaining) mode (NIST SP800-38A)
+ - CTR (Counter) mode (NIST SP800-38A)
+ - XTS (XOR Encrypt XOR with ciphertext stealing) mode (NIST SP800-38E
+ and IEEE 1619)
+
+ Bit sliced AES gives around 45% speedup on Cortex-A15 for CTR mode
+ and for XTS mode encryption, CBC and XTS mode decryption speedup is
+ around 25%. (CBC encryption speed is not affected by this driver.)
+ This implementation does not rely on any lookup tables so it is
+ believed to be invulnerable to cache timing attacks.
+
+config CRYPTO_AES_ARM_CE
+ tristate "Ciphers: AES, modes: ECB/CBC/CTS/CTR/XTS (ARMv8 Crypto Extensions)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_SKCIPHER
+ select CRYPTO_LIB_AES
+ select CRYPTO_SIMD
+ help
+ Length-preserving ciphers: AES cipher algorithms (FIPS-197)
+ with block cipher modes:
+ - ECB (Electronic Codebook) mode (NIST SP800-38A)
+ - CBC (Cipher Block Chaining) mode (NIST SP800-38A)
+ - CTR (Counter) mode (NIST SP800-38A)
+ - CTS (Cipher Text Stealing) mode (NIST SP800-38A)
+ - XTS (XOR Encrypt XOR with ciphertext stealing) mode (NIST SP800-38E
+ and IEEE 1619)
+
+ Architecture: arm using:
+ - ARMv8 Crypto Extensions
+
+config CRYPTO_CHACHA20_NEON
+ tristate "Ciphers: ChaCha20, XChaCha20, XChaCha12 (NEON)"
+ select CRYPTO_SKCIPHER
+ select CRYPTO_ARCH_HAVE_LIB_CHACHA
+ help
+ Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
+ stream cipher algorithms
+
+ Architecture: arm using:
+ - NEON (Advanced SIMD) extensions
+
+config CRYPTO_CRC32_ARM_CE
+ tristate "CRC32C and CRC32"
+ depends on KERNEL_MODE_NEON
+ depends on CRC32
+ select CRYPTO_HASH
+ help
+ CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720)
+ and CRC32 CRC algorithm (IEEE 802.3)
+
+ Architecture: arm using:
+ - CRC and/or PMULL instructions
+
+ Drivers: crc32-arm-ce and crc32c-arm-ce
+
+config CRYPTO_CRCT10DIF_ARM_CE
+ tristate "CRCT10DIF"
+ depends on KERNEL_MODE_NEON
+ depends on CRC_T10DIF
+ select CRYPTO_HASH
+ help
+ CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF)
+
+ Architecture: arm using:
+ - PMULL (Polynomial Multiply Long) instructions
+
+endmenu
+
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
new file mode 100644
index 0000000000..13e62c7c25
--- /dev/null
+++ b/arch/arm/crypto/Makefile
@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Arch-specific CryptoAPI modules.
+#
+
+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-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
+obj-$(CONFIG_CRYPTO_BLAKE2S_ARM) += libblake2s-arm.o
+obj-$(CONFIG_CRYPTO_BLAKE2B_NEON) += blake2b-neon.o
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.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-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
+obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
+obj-$(CONFIG_CRYPTO_CRC32_ARM_CE) += crc32-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
+sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
+sha256-arm-y := sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
+sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
+sha512-arm-y := sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
+libblake2s-arm-y:= blake2s-core.o blake2s-glue.o
+blake2b-neon-y := blake2b-neon-core.o blake2b-neon-glue.o
+sha1-arm-ce-y := sha1-ce-core.o sha1-ce-glue.o
+sha2-arm-ce-y := sha2-ce-core.o sha2-ce-glue.o
+aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o
+ghash-arm-ce-y := ghash-ce-core.o ghash-ce-glue.o
+crct10dif-arm-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o
+crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
+chacha-neon-y := chacha-scalar-core.o chacha-glue.o
+chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
+poly1305-arm-y := poly1305-core.o poly1305-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
+ $(call cmd,perl)
+
+clean-files += poly1305-core.S sha256-core.S sha512-core.S
+
+aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1
+
+AFLAGS_sha256-core.o += $(aflags-thumb2-y)
+AFLAGS_sha512-core.o += $(aflags-thumb2-y)
+
+# massage the perlasm code a bit so we only get the NEON routine if we need it
+poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
+poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
+AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y)
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
new file mode 100644
index 0000000000..312428d83e
--- /dev/null
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -0,0 +1,713 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * aes-ce-core.S - AES in CBC/CTR/XTS mode using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .arch armv8-a
+ .fpu crypto-neon-fp-armv8
+ .align 3
+
+ .macro enc_round, state, key
+ aese.8 \state, \key
+ aesmc.8 \state, \state
+ .endm
+
+ .macro dec_round, state, key
+ aesd.8 \state, \key
+ aesimc.8 \state, \state
+ .endm
+
+ .macro enc_dround, key1, key2
+ enc_round q0, \key1
+ enc_round q0, \key2
+ .endm
+
+ .macro dec_dround, key1, key2
+ dec_round q0, \key1
+ dec_round q0, \key2
+ .endm
+
+ .macro enc_fround, key1, key2, key3
+ enc_round q0, \key1
+ aese.8 q0, \key2
+ veor q0, q0, \key3
+ .endm
+
+ .macro dec_fround, key1, key2, key3
+ dec_round q0, \key1
+ aesd.8 q0, \key2
+ veor q0, q0, \key3
+ .endm
+
+ .macro enc_dround_4x, key1, key2
+ enc_round q0, \key1
+ enc_round q1, \key1
+ enc_round q2, \key1
+ enc_round q3, \key1
+ enc_round q0, \key2
+ enc_round q1, \key2
+ enc_round q2, \key2
+ enc_round q3, \key2
+ .endm
+
+ .macro dec_dround_4x, key1, key2
+ dec_round q0, \key1
+ dec_round q1, \key1
+ dec_round q2, \key1
+ dec_round q3, \key1
+ dec_round q0, \key2
+ dec_round q1, \key2
+ dec_round q2, \key2
+ dec_round q3, \key2
+ .endm
+
+ .macro enc_fround_4x, key1, key2, key3
+ enc_round q0, \key1
+ enc_round q1, \key1
+ enc_round q2, \key1
+ enc_round q3, \key1
+ aese.8 q0, \key2
+ aese.8 q1, \key2
+ aese.8 q2, \key2
+ aese.8 q3, \key2
+ veor q0, q0, \key3
+ veor q1, q1, \key3
+ veor q2, q2, \key3
+ veor q3, q3, \key3
+ .endm
+
+ .macro dec_fround_4x, key1, key2, key3
+ dec_round q0, \key1
+ dec_round q1, \key1
+ dec_round q2, \key1
+ dec_round q3, \key1
+ aesd.8 q0, \key2
+ aesd.8 q1, \key2
+ aesd.8 q2, \key2
+ aesd.8 q3, \key2
+ veor q0, q0, \key3
+ veor q1, q1, \key3
+ veor q2, q2, \key3
+ veor q3, q3, \key3
+ .endm
+
+ .macro do_block, dround, fround
+ cmp r3, #12 @ which key size?
+ vld1.32 {q10-q11}, [ip]!
+ \dround q8, q9
+ vld1.32 {q12-q13}, [ip]!
+ \dround q10, q11
+ vld1.32 {q10-q11}, [ip]!
+ \dround q12, q13
+ vld1.32 {q12-q13}, [ip]!
+ \dround q10, q11
+ blo 0f @ AES-128: 10 rounds
+ vld1.32 {q10-q11}, [ip]!
+ \dround q12, q13
+ beq 1f @ AES-192: 12 rounds
+ vld1.32 {q12-q13}, [ip]
+ \dround q10, q11
+0: \fround q12, q13, q14
+ bx lr
+
+1: \fround q10, q11, q14
+ bx lr
+ .endm
+
+ /*
+ * Internal, non-AAPCS compliant functions that implement the core AES
+ * transforms. These should preserve all registers except q0 - q2 and ip
+ * Arguments:
+ * q0 : first in/output block
+ * q1 : second in/output block (_4x version only)
+ * q2 : third in/output block (_4x version only)
+ * q3 : fourth in/output block (_4x version only)
+ * q8 : first round key
+ * q9 : secound round key
+ * q14 : final round key
+ * r2 : address of round key array
+ * r3 : number of rounds
+ */
+ .align 6
+aes_encrypt:
+ add ip, r2, #32 @ 3rd round key
+.Laes_encrypt_tweak:
+ do_block enc_dround, enc_fround
+ENDPROC(aes_encrypt)
+
+ .align 6
+aes_decrypt:
+ add ip, r2, #32 @ 3rd round key
+ do_block dec_dround, dec_fround
+ENDPROC(aes_decrypt)
+
+ .align 6
+aes_encrypt_4x:
+ add ip, r2, #32 @ 3rd round key
+ do_block enc_dround_4x, enc_fround_4x
+ENDPROC(aes_encrypt_4x)
+
+ .align 6
+aes_decrypt_4x:
+ add ip, r2, #32 @ 3rd round key
+ do_block dec_dround_4x, dec_fround_4x
+ENDPROC(aes_decrypt_4x)
+
+ .macro prepare_key, rk, rounds
+ add ip, \rk, \rounds, lsl #4
+ vld1.32 {q8-q9}, [\rk] @ load first 2 round keys
+ vld1.32 {q14}, [ip] @ load last round key
+ .endm
+
+ /*
+ * aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
+ * int blocks)
+ * aes_ecb_decrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
+ * int blocks)
+ */
+ENTRY(ce_aes_ecb_encrypt)
+ push {r4, lr}
+ ldr r4, [sp, #8]
+ prepare_key r2, r3
+.Lecbencloop4x:
+ subs r4, r4, #4
+ bmi .Lecbenc1x
+ vld1.8 {q0-q1}, [r1]!
+ vld1.8 {q2-q3}, [r1]!
+ bl aes_encrypt_4x
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2-q3}, [r0]!
+ b .Lecbencloop4x
+.Lecbenc1x:
+ adds r4, r4, #4
+ beq .Lecbencout
+.Lecbencloop:
+ vld1.8 {q0}, [r1]!
+ bl aes_encrypt
+ vst1.8 {q0}, [r0]!
+ subs r4, r4, #1
+ bne .Lecbencloop
+.Lecbencout:
+ pop {r4, pc}
+ENDPROC(ce_aes_ecb_encrypt)
+
+ENTRY(ce_aes_ecb_decrypt)
+ push {r4, lr}
+ ldr r4, [sp, #8]
+ prepare_key r2, r3
+.Lecbdecloop4x:
+ subs r4, r4, #4
+ bmi .Lecbdec1x
+ vld1.8 {q0-q1}, [r1]!
+ vld1.8 {q2-q3}, [r1]!
+ bl aes_decrypt_4x
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2-q3}, [r0]!
+ b .Lecbdecloop4x
+.Lecbdec1x:
+ adds r4, r4, #4
+ beq .Lecbdecout
+.Lecbdecloop:
+ vld1.8 {q0}, [r1]!
+ bl aes_decrypt
+ vst1.8 {q0}, [r0]!
+ subs r4, r4, #1
+ bne .Lecbdecloop
+.Lecbdecout:
+ pop {r4, pc}
+ENDPROC(ce_aes_ecb_decrypt)
+
+ /*
+ * aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
+ * int blocks, u8 iv[])
+ * aes_cbc_decrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
+ * int blocks, u8 iv[])
+ */
+ENTRY(ce_aes_cbc_encrypt)
+ push {r4-r6, lr}
+ ldrd r4, r5, [sp, #16]
+ vld1.8 {q0}, [r5]
+ prepare_key r2, r3
+.Lcbcencloop:
+ vld1.8 {q1}, [r1]! @ get next pt block
+ veor q0, q0, q1 @ ..and xor with iv
+ bl aes_encrypt
+ vst1.8 {q0}, [r0]!
+ subs r4, r4, #1
+ bne .Lcbcencloop
+ vst1.8 {q0}, [r5]
+ pop {r4-r6, pc}
+ENDPROC(ce_aes_cbc_encrypt)
+
+ENTRY(ce_aes_cbc_decrypt)
+ push {r4-r6, lr}
+ ldrd r4, r5, [sp, #16]
+ vld1.8 {q15}, [r5] @ keep iv in q15
+ prepare_key r2, r3
+.Lcbcdecloop4x:
+ subs r4, r4, #4
+ bmi .Lcbcdec1x
+ vld1.8 {q0-q1}, [r1]!
+ vld1.8 {q2-q3}, [r1]!
+ vmov q4, q0
+ vmov q5, q1
+ vmov q6, q2
+ vmov q7, q3
+ bl aes_decrypt_4x
+ veor q0, q0, q15
+ veor q1, q1, q4
+ veor q2, q2, q5
+ veor q3, q3, q6
+ vmov q15, q7
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2-q3}, [r0]!
+ b .Lcbcdecloop4x
+.Lcbcdec1x:
+ adds r4, r4, #4
+ beq .Lcbcdecout
+ vmov q6, q14 @ preserve last round key
+.Lcbcdecloop:
+ vld1.8 {q0}, [r1]! @ get next ct block
+ veor q14, q15, q6 @ combine prev ct with last key
+ vmov q15, q0
+ bl aes_decrypt
+ vst1.8 {q0}, [r0]!
+ subs r4, r4, #1
+ bne .Lcbcdecloop
+.Lcbcdecout:
+ vst1.8 {q15}, [r5] @ keep iv in q15
+ pop {r4-r6, pc}
+ENDPROC(ce_aes_cbc_decrypt)
+
+
+ /*
+ * ce_aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ * int rounds, int bytes, u8 const iv[])
+ * ce_aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+ * int rounds, int bytes, u8 const iv[])
+ */
+
+ENTRY(ce_aes_cbc_cts_encrypt)
+ push {r4-r6, lr}
+ ldrd r4, r5, [sp, #16]
+
+ movw ip, :lower16:.Lcts_permute_table
+ movt ip, :upper16:.Lcts_permute_table
+ sub r4, r4, #16
+ add lr, ip, #32
+ add ip, ip, r4
+ sub lr, lr, r4
+ vld1.8 {q5}, [ip]
+ vld1.8 {q6}, [lr]
+
+ add ip, r1, r4
+ vld1.8 {q0}, [r1] @ overlapping loads
+ vld1.8 {q3}, [ip]
+
+ vld1.8 {q1}, [r5] @ get iv
+ prepare_key r2, r3
+
+ veor q0, q0, q1 @ xor with iv
+ bl aes_encrypt
+
+ vtbl.8 d4, {d0-d1}, d10
+ vtbl.8 d5, {d0-d1}, d11
+ vtbl.8 d2, {d6-d7}, d12
+ vtbl.8 d3, {d6-d7}, d13
+
+ veor q0, q0, q1
+ bl aes_encrypt
+
+ add r4, r0, r4
+ vst1.8 {q2}, [r4] @ overlapping stores
+ vst1.8 {q0}, [r0]
+
+ pop {r4-r6, pc}
+ENDPROC(ce_aes_cbc_cts_encrypt)
+
+ENTRY(ce_aes_cbc_cts_decrypt)
+ push {r4-r6, lr}
+ ldrd r4, r5, [sp, #16]
+
+ movw ip, :lower16:.Lcts_permute_table
+ movt ip, :upper16:.Lcts_permute_table
+ sub r4, r4, #16
+ add lr, ip, #32
+ add ip, ip, r4
+ sub lr, lr, r4
+ vld1.8 {q5}, [ip]
+ vld1.8 {q6}, [lr]
+
+ add ip, r1, r4
+ vld1.8 {q0}, [r1] @ overlapping loads
+ vld1.8 {q1}, [ip]
+
+ vld1.8 {q3}, [r5] @ get iv
+ prepare_key r2, r3
+
+ bl aes_decrypt
+
+ vtbl.8 d4, {d0-d1}, d10
+ vtbl.8 d5, {d0-d1}, d11
+ vtbx.8 d0, {d2-d3}, d12
+ vtbx.8 d1, {d2-d3}, d13
+
+ veor q1, q1, q2
+ bl aes_decrypt
+ veor q0, q0, q3 @ xor with iv
+
+ add r4, r0, r4
+ vst1.8 {q1}, [r4] @ overlapping stores
+ vst1.8 {q0}, [r0]
+
+ pop {r4-r6, pc}
+ENDPROC(ce_aes_cbc_cts_decrypt)
+
+
+ /*
+ * aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[], int rounds,
+ * int blocks, u8 ctr[])
+ */
+ENTRY(ce_aes_ctr_encrypt)
+ push {r4-r6, lr}
+ ldrd r4, r5, [sp, #16]
+ vld1.8 {q7}, [r5] @ load ctr
+ prepare_key r2, r3
+ vmov r6, s31 @ keep swabbed ctr in r6
+ rev r6, r6
+ cmn r6, r4 @ 32 bit overflow?
+ bcs .Lctrloop
+.Lctrloop4x:
+ subs r4, r4, #4
+ bmi .Lctr1x
+
+ /*
+ * NOTE: the sequence below has been carefully tweaked to avoid
+ * a silicon erratum that exists in Cortex-A57 (#1742098) and
+ * Cortex-A72 (#1655431) cores, where AESE/AESMC instruction pairs
+ * may produce an incorrect result if they take their input from a
+ * register of which a single 32-bit lane has been updated the last
+ * time it was modified. To work around this, the lanes of registers
+ * q0-q3 below are not manipulated individually, and the different
+ * counter values are prepared by successive manipulations of q7.
+ */
+ add ip, r6, #1
+ vmov q0, q7
+ rev ip, ip
+ add lr, r6, #2
+ vmov s31, ip @ set lane 3 of q1 via q7
+ add ip, r6, #3
+ rev lr, lr
+ vmov q1, q7
+ vmov s31, lr @ set lane 3 of q2 via q7
+ rev ip, ip
+ vmov q2, q7
+ vmov s31, ip @ set lane 3 of q3 via q7
+ add r6, r6, #4
+ vmov q3, q7
+
+ vld1.8 {q4-q5}, [r1]!
+ vld1.8 {q6}, [r1]!
+ vld1.8 {q15}, [r1]!
+ bl aes_encrypt_4x
+ veor q0, q0, q4
+ veor q1, q1, q5
+ veor q2, q2, q6
+ veor q3, q3, q15
+ rev ip, r6
+ vst1.8 {q0-q1}, [r0]!
+ vst1.8 {q2-q3}, [r0]!
+ vmov s31, ip
+ b .Lctrloop4x
+.Lctr1x:
+ adds r4, r4, #4
+ beq .Lctrout
+.Lctrloop:
+ vmov q0, q7
+ bl aes_encrypt
+
+ adds r6, r6, #1 @ increment BE ctr
+ rev ip, r6
+ vmov s31, ip
+ bcs .Lctrcarry
+
+.Lctrcarrydone:
+ subs r4, r4, #1
+ bmi .Lctrtailblock @ blocks < 0 means tail block
+ vld1.8 {q3}, [r1]!
+ veor q3, q0, q3
+ vst1.8 {q3}, [r0]!
+ bne .Lctrloop
+
+.Lctrout:
+ vst1.8 {q7}, [r5] @ return next CTR value
+ pop {r4-r6, pc}
+
+.Lctrtailblock:
+ vst1.8 {q0}, [r0, :64] @ return the key stream
+ b .Lctrout
+
+.Lctrcarry:
+ .irp sreg, s30, s29, s28
+ vmov ip, \sreg @ load next word of ctr
+ rev ip, ip @ ... to handle the carry
+ adds ip, ip, #1
+ rev ip, ip
+ vmov \sreg, ip
+ bcc .Lctrcarrydone
+ .endr
+ b .Lctrcarrydone
+ENDPROC(ce_aes_ctr_encrypt)
+
+ /*
+ * aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds,
+ * int bytes, u8 iv[], u32 const rk2[], int first)
+ * aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds,
+ * int bytes, u8 iv[], u32 const rk2[], int first)
+ */
+
+ .macro next_tweak, out, in, const, tmp
+ vshr.s64 \tmp, \in, #63
+ vand \tmp, \tmp, \const
+ vadd.u64 \out, \in, \in
+ vext.8 \tmp, \tmp, \tmp, #8
+ veor \out, \out, \tmp
+ .endm
+
+ce_aes_xts_init:
+ vmov.i32 d30, #0x87 @ compose tweak mask vector
+ vmovl.u32 q15, d30
+ vshr.u64 d30, d31, #7
+
+ ldrd r4, r5, [sp, #16] @ load args
+ ldr r6, [sp, #28]
+ vld1.8 {q0}, [r5] @ load iv
+ teq r6, #1 @ start of a block?
+ bxne lr
+
+ @ Encrypt the IV in q0 with the second AES key. This should only
+ @ be done at the start of a block.
+ ldr r6, [sp, #24] @ load AES key 2
+ prepare_key r6, r3
+ add ip, r6, #32 @ 3rd round key of key 2
+ b .Laes_encrypt_tweak @ tail call
+ENDPROC(ce_aes_xts_init)
+
+ENTRY(ce_aes_xts_encrypt)
+ push {r4-r6, lr}
+
+ bl ce_aes_xts_init @ run shared prologue
+ prepare_key r2, r3
+ vmov q4, q0
+
+ teq r6, #0 @ start of a block?
+ bne .Lxtsenc4x
+
+.Lxtsencloop4x:
+ next_tweak q4, q4, q15, q10
+.Lxtsenc4x:
+ subs r4, r4, #64
+ bmi .Lxtsenc1x
+ vld1.8 {q0-q1}, [r1]! @ get 4 pt blocks
+ vld1.8 {q2-q3}, [r1]!
+ next_tweak q5, q4, q15, q10
+ veor q0, q0, q4
+ next_tweak q6, q5, q15, q10
+ veor q1, q1, q5
+ next_tweak q7, q6, q15, q10
+ veor q2, q2, q6
+ veor q3, q3, q7
+ bl aes_encrypt_4x
+ veor q0, q0, q4
+ veor q1, q1, q5
+ veor q2, q2, q6
+ veor q3, q3, q7
+ vst1.8 {q0-q1}, [r0]! @ write 4 ct blocks
+ vst1.8 {q2-q3}, [r0]!
+ vmov q4, q7
+ teq r4, #0
+ beq .Lxtsencret
+ b .Lxtsencloop4x
+.Lxtsenc1x:
+ adds r4, r4, #64
+ beq .Lxtsencout
+ subs r4, r4, #16
+ bmi .LxtsencctsNx
+.Lxtsencloop:
+ vld1.8 {q0}, [r1]!
+.Lxtsencctsout:
+ veor q0, q0, q4
+ bl aes_encrypt
+ veor q0, q0, q4
+ teq r4, #0
+ beq .Lxtsencout
+ subs r4, r4, #16
+ next_tweak q4, q4, q15, q6
+ bmi .Lxtsenccts
+ vst1.8 {q0}, [r0]!
+ b .Lxtsencloop
+.Lxtsencout:
+ vst1.8 {q0}, [r0]
+.Lxtsencret:
+ vst1.8 {q4}, [r5]
+ pop {r4-r6, pc}
+
+.LxtsencctsNx:
+ vmov q0, q3
+ sub r0, r0, #16
+.Lxtsenccts:
+ movw ip, :lower16:.Lcts_permute_table
+ movt ip, :upper16:.Lcts_permute_table
+
+ add r1, r1, r4 @ rewind input pointer
+ add r4, r4, #16 @ # bytes in final block
+ add lr, ip, #32
+ add ip, ip, r4
+ sub lr, lr, r4
+ add r4, r0, r4 @ output address of final block
+
+ vld1.8 {q1}, [r1] @ load final partial block
+ vld1.8 {q2}, [ip]
+ vld1.8 {q3}, [lr]
+
+ vtbl.8 d4, {d0-d1}, d4
+ vtbl.8 d5, {d0-d1}, d5
+ vtbx.8 d0, {d2-d3}, d6
+ vtbx.8 d1, {d2-d3}, d7
+
+ vst1.8 {q2}, [r4] @ overlapping stores
+ mov r4, #0
+ b .Lxtsencctsout
+ENDPROC(ce_aes_xts_encrypt)
+
+
+ENTRY(ce_aes_xts_decrypt)
+ push {r4-r6, lr}
+
+ bl ce_aes_xts_init @ run shared prologue
+ prepare_key r2, r3
+ vmov q4, q0
+
+ /* subtract 16 bytes if we are doing CTS */
+ tst r4, #0xf
+ subne r4, r4, #0x10
+
+ teq r6, #0 @ start of a block?
+ bne .Lxtsdec4x
+
+.Lxtsdecloop4x:
+ next_tweak q4, q4, q15, q10
+.Lxtsdec4x:
+ subs r4, r4, #64
+ bmi .Lxtsdec1x
+ vld1.8 {q0-q1}, [r1]! @ get 4 ct blocks
+ vld1.8 {q2-q3}, [r1]!
+ next_tweak q5, q4, q15, q10
+ veor q0, q0, q4
+ next_tweak q6, q5, q15, q10
+ veor q1, q1, q5
+ next_tweak q7, q6, q15, q10
+ veor q2, q2, q6
+ veor q3, q3, q7
+ bl aes_decrypt_4x
+ veor q0, q0, q4
+ veor q1, q1, q5
+ veor q2, q2, q6
+ veor q3, q3, q7
+ vst1.8 {q0-q1}, [r0]! @ write 4 pt blocks
+ vst1.8 {q2-q3}, [r0]!
+ vmov q4, q7
+ teq r4, #0
+ beq .Lxtsdecout
+ b .Lxtsdecloop4x
+.Lxtsdec1x:
+ adds r4, r4, #64
+ beq .Lxtsdecout
+ subs r4, r4, #16
+.Lxtsdecloop:
+ vld1.8 {q0}, [r1]!
+ bmi .Lxtsdeccts
+.Lxtsdecctsout:
+ veor q0, q0, q4
+ bl aes_decrypt
+ veor q0, q0, q4
+ vst1.8 {q0}, [r0]!
+ teq r4, #0
+ beq .Lxtsdecout
+ subs r4, r4, #16
+ next_tweak q4, q4, q15, q6
+ b .Lxtsdecloop
+.Lxtsdecout:
+ vst1.8 {q4}, [r5]
+ pop {r4-r6, pc}
+
+.Lxtsdeccts:
+ movw ip, :lower16:.Lcts_permute_table
+ movt ip, :upper16:.Lcts_permute_table
+
+ add r1, r1, r4 @ rewind input pointer
+ add r4, r4, #16 @ # bytes in final block
+ add lr, ip, #32
+ add ip, ip, r4
+ sub lr, lr, r4
+ add r4, r0, r4 @ output address of final block
+
+ next_tweak q5, q4, q15, q6
+
+ vld1.8 {q1}, [r1] @ load final partial block
+ vld1.8 {q2}, [ip]
+ vld1.8 {q3}, [lr]
+
+ veor q0, q0, q5
+ bl aes_decrypt
+ veor q0, q0, q5
+
+ vtbl.8 d4, {d0-d1}, d4
+ vtbl.8 d5, {d0-d1}, d5
+ vtbx.8 d0, {d2-d3}, d6
+ vtbx.8 d1, {d2-d3}, d7
+
+ vst1.8 {q2}, [r4] @ overlapping stores
+ mov r4, #0
+ b .Lxtsdecctsout
+ENDPROC(ce_aes_xts_decrypt)
+
+ /*
+ * u32 ce_aes_sub(u32 input) - use the aese instruction to perform the
+ * AES sbox substitution on each byte in
+ * 'input'
+ */
+ENTRY(ce_aes_sub)
+ vdup.32 q1, r0
+ veor q0, q0, q0
+ aese.8 q0, q1
+ vmov r0, s0
+ bx lr
+ENDPROC(ce_aes_sub)
+
+ /*
+ * void ce_aes_invert(u8 *dst, u8 *src) - perform the Inverse MixColumns
+ * operation on round key *src
+ */
+ENTRY(ce_aes_invert)
+ vld1.32 {q0}, [r1]
+ aesimc.8 q0, q0
+ vst1.32 {q0}, [r0]
+ bx lr
+ENDPROC(ce_aes_invert)
+
+ .section ".rodata", "a"
+ .align 6
+.Lcts_permute_table:
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
+ .byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
new file mode 100644
index 0000000000..b668c97663
--- /dev/null
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -0,0 +1,730 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * aes-ce-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/ctr.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/cpufeature.h>
+#include <linux/module.h>
+#include <crypto/xts.h>
+
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-ce-core.S */
+asmlinkage u32 ce_aes_sub(u32 input);
+asmlinkage void ce_aes_invert(void *dst, void *src);
+
+asmlinkage void ce_aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int blocks);
+asmlinkage void ce_aes_ecb_decrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int blocks);
+
+asmlinkage void ce_aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int blocks, u8 iv[]);
+asmlinkage void ce_aes_cbc_decrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int blocks, u8 iv[]);
+asmlinkage void ce_aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int bytes, u8 const iv[]);
+asmlinkage void ce_aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int bytes, u8 const iv[]);
+
+asmlinkage void ce_aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int blocks, u8 ctr[]);
+
+asmlinkage void ce_aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[],
+ int rounds, int bytes, u8 iv[],
+ u32 const rk2[], int first);
+asmlinkage void ce_aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[],
+ int rounds, int bytes, u8 iv[],
+ u32 const rk2[], int first);
+
+struct aes_block {
+ u8 b[AES_BLOCK_SIZE];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+ /*
+ * # of rounds specified by AES:
+ * 128 bit key 10 rounds
+ * 192 bit key 12 rounds
+ * 256 bit key 14 rounds
+ * => n byte key => 6 + (n/4) rounds
+ */
+ return 6 + ctx->key_length / 4;
+}
+
+static int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+ unsigned int key_len)
+{
+ /*
+ * The AES key schedule round constants
+ */
+ static u8 const rcon[] = {
+ 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36,
+ };
+
+ u32 kwords = key_len / sizeof(u32);
+ struct aes_block *key_enc, *key_dec;
+ int i, j;
+
+ if (key_len != AES_KEYSIZE_128 &&
+ key_len != AES_KEYSIZE_192 &&
+ key_len != AES_KEYSIZE_256)
+ return -EINVAL;
+
+ ctx->key_length = key_len;
+ for (i = 0; i < kwords; i++)
+ ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32));
+
+ kernel_neon_begin();
+ for (i = 0; i < sizeof(rcon); i++) {
+ u32 *rki = ctx->key_enc + (i * kwords);
+ u32 *rko = rki + kwords;
+
+ rko[0] = ror32(ce_aes_sub(rki[kwords - 1]), 8);
+ rko[0] = rko[0] ^ rki[0] ^ rcon[i];
+ rko[1] = rko[0] ^ rki[1];
+ rko[2] = rko[1] ^ rki[2];
+ rko[3] = rko[2] ^ rki[3];
+
+ if (key_len == AES_KEYSIZE_192) {
+ if (i >= 7)
+ break;
+ rko[4] = rko[3] ^ rki[4];
+ rko[5] = rko[4] ^ rki[5];
+ } else if (key_len == AES_KEYSIZE_256) {
+ if (i >= 6)
+ break;
+ rko[4] = ce_aes_sub(rko[3]) ^ rki[4];
+ rko[5] = rko[4] ^ rki[5];
+ rko[6] = rko[5] ^ rki[6];
+ rko[7] = rko[6] ^ rki[7];
+ }
+ }
+
+ /*
+ * Generate the decryption keys for the Equivalent Inverse Cipher.
+ * This involves reversing the order of the round keys, and applying
+ * the Inverse Mix Columns transformation on all but the first and
+ * the last one.
+ */
+ key_enc = (struct aes_block *)ctx->key_enc;
+ key_dec = (struct aes_block *)ctx->key_dec;
+ j = num_rounds(ctx);
+
+ key_dec[0] = key_enc[j];
+ for (i = 1, j--; j > 0; i++, j--)
+ ce_aes_invert(key_dec + i, key_enc + j);
+ key_dec[i] = key_enc[0];
+
+ kernel_neon_end();
+ return 0;
+}
+
+static int ce_aes_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return ce_aes_expandkey(ctx, in_key, key_len);
+}
+
+struct crypto_aes_xts_ctx {
+ struct crypto_aes_ctx key1;
+ struct crypto_aes_ctx __aligned(8) key2;
+};
+
+static int xts_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int ret;
+
+ ret = xts_verify_key(tfm, in_key, key_len);
+ if (ret)
+ return ret;
+
+ ret = ce_aes_expandkey(&ctx->key1, in_key, key_len / 2);
+ if (!ret)
+ ret = ce_aes_expandkey(&ctx->key2, &in_key[key_len / 2],
+ key_len / 2);
+ return ret;
+}
+
+static int ecb_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int blocks;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+ kernel_neon_begin();
+ ce_aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_enc, num_rounds(ctx), blocks);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static int ecb_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ unsigned int blocks;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+ kernel_neon_begin();
+ ce_aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_dec, num_rounds(ctx), blocks);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static int cbc_encrypt_walk(struct skcipher_request *req,
+ struct skcipher_walk *walk)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ unsigned int blocks;
+ int err = 0;
+
+ while ((blocks = (walk->nbytes / AES_BLOCK_SIZE))) {
+ kernel_neon_begin();
+ ce_aes_cbc_encrypt(walk->dst.virt.addr, walk->src.virt.addr,
+ ctx->key_enc, num_rounds(ctx), blocks,
+ walk->iv);
+ kernel_neon_end();
+ err = skcipher_walk_done(walk, walk->nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static int cbc_encrypt(struct skcipher_request *req)
+{
+ struct skcipher_walk walk;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+ if (err)
+ return err;
+ return cbc_encrypt_walk(req, &walk);
+}
+
+static int cbc_decrypt_walk(struct skcipher_request *req,
+ struct skcipher_walk *walk)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ unsigned int blocks;
+ int err = 0;
+
+ while ((blocks = (walk->nbytes / AES_BLOCK_SIZE))) {
+ kernel_neon_begin();
+ ce_aes_cbc_decrypt(walk->dst.virt.addr, walk->src.virt.addr,
+ ctx->key_dec, num_rounds(ctx), blocks,
+ walk->iv);
+ kernel_neon_end();
+ err = skcipher_walk_done(walk, walk->nbytes % AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+ struct skcipher_walk walk;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+ if (err)
+ return err;
+ return cbc_decrypt_walk(req, &walk);
+}
+
+static int cts_cbc_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+ struct scatterlist *src = req->src, *dst = req->dst;
+ struct scatterlist sg_src[2], sg_dst[2];
+ struct skcipher_request subreq;
+ struct skcipher_walk walk;
+ int err;
+
+ skcipher_request_set_tfm(&subreq, tfm);
+ skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+ NULL, NULL);
+
+ if (req->cryptlen <= AES_BLOCK_SIZE) {
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+ cbc_blocks = 1;
+ }
+
+ if (cbc_blocks > 0) {
+ skcipher_request_set_crypt(&subreq, req->src, req->dst,
+ cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &subreq, false) ?:
+ cbc_encrypt_walk(&subreq, &walk);
+ if (err)
+ return err;
+
+ if (req->cryptlen == AES_BLOCK_SIZE)
+ return 0;
+
+ dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+ if (req->dst != req->src)
+ dst = scatterwalk_ffwd(sg_dst, req->dst,
+ subreq.cryptlen);
+ }
+
+ /* handle ciphertext stealing */
+ skcipher_request_set_crypt(&subreq, src, dst,
+ req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &subreq, false);
+ if (err)
+ return err;
+
+ kernel_neon_begin();
+ ce_aes_cbc_cts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_enc, num_rounds(ctx), walk.nbytes,
+ walk.iv);
+ kernel_neon_end();
+
+ return skcipher_walk_done(&walk, 0);
+}
+
+static int cts_cbc_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+ struct scatterlist *src = req->src, *dst = req->dst;
+ struct scatterlist sg_src[2], sg_dst[2];
+ struct skcipher_request subreq;
+ struct skcipher_walk walk;
+ int err;
+
+ skcipher_request_set_tfm(&subreq, tfm);
+ skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+ NULL, NULL);
+
+ if (req->cryptlen <= AES_BLOCK_SIZE) {
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+ cbc_blocks = 1;
+ }
+
+ if (cbc_blocks > 0) {
+ skcipher_request_set_crypt(&subreq, req->src, req->dst,
+ cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &subreq, false) ?:
+ cbc_decrypt_walk(&subreq, &walk);
+ if (err)
+ return err;
+
+ if (req->cryptlen == AES_BLOCK_SIZE)
+ return 0;
+
+ dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+ if (req->dst != req->src)
+ dst = scatterwalk_ffwd(sg_dst, req->dst,
+ subreq.cryptlen);
+ }
+
+ /* handle ciphertext stealing */
+ skcipher_request_set_crypt(&subreq, src, dst,
+ req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &subreq, false);
+ if (err)
+ return err;
+
+ kernel_neon_begin();
+ ce_aes_cbc_cts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_dec, num_rounds(ctx), walk.nbytes,
+ walk.iv);
+ kernel_neon_end();
+
+ return skcipher_walk_done(&walk, 0);
+}
+
+static int ctr_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ int err, blocks;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+ kernel_neon_begin();
+ ce_aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_enc, num_rounds(ctx), blocks,
+ walk.iv);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+ }
+ if (walk.nbytes) {
+ u8 __aligned(8) tail[AES_BLOCK_SIZE];
+ unsigned int nbytes = walk.nbytes;
+ u8 *tdst = walk.dst.virt.addr;
+ u8 *tsrc = walk.src.virt.addr;
+
+ /*
+ * Tell aes_ctr_encrypt() to process a tail block.
+ */
+ blocks = -1;
+
+ kernel_neon_begin();
+ ce_aes_ctr_encrypt(tail, NULL, ctx->key_enc, num_rounds(ctx),
+ blocks, walk.iv);
+ kernel_neon_end();
+ crypto_xor_cpy(tdst, tsrc, tail, nbytes);
+ err = skcipher_walk_done(&walk, 0);
+ }
+ return err;
+}
+
+static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+{
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ unsigned long flags;
+
+ /*
+ * Temporarily disable interrupts to avoid races where
+ * cachelines are evicted when the CPU is interrupted
+ * to do something else.
+ */
+ local_irq_save(flags);
+ aes_encrypt(ctx, dst, src);
+ local_irq_restore(flags);
+}
+
+static int ctr_encrypt_sync(struct skcipher_request *req)
+{
+ if (!crypto_simd_usable())
+ return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
+
+ return ctr_encrypt(req);
+}
+
+static int xts_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int err, first, rounds = num_rounds(&ctx->key1);
+ int tail = req->cryptlen % AES_BLOCK_SIZE;
+ struct scatterlist sg_src[2], sg_dst[2];
+ struct skcipher_request subreq;
+ struct scatterlist *src, *dst;
+ struct skcipher_walk walk;
+
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+ int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+ AES_BLOCK_SIZE) - 2;
+
+ skcipher_walk_abort(&walk);
+
+ skcipher_request_set_tfm(&subreq, tfm);
+ skcipher_request_set_callback(&subreq,
+ skcipher_request_flags(req),
+ NULL, NULL);
+ skcipher_request_set_crypt(&subreq, req->src, req->dst,
+ xts_blocks * AES_BLOCK_SIZE,
+ req->iv);
+ req = &subreq;
+ err = skcipher_walk_virt(&walk, req, false);
+ } else {
+ tail = 0;
+ }
+
+ for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+ int nbytes = walk.nbytes;
+
+ if (walk.nbytes < walk.total)
+ nbytes &= ~(AES_BLOCK_SIZE - 1);
+
+ kernel_neon_begin();
+ ce_aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key1.key_enc, rounds, nbytes, walk.iv,
+ ctx->key2.key_enc, first);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+ }
+
+ if (err || likely(!tail))
+ return err;
+
+ dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+ if (req->dst != req->src)
+ dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+ skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, req, false);
+ if (err)
+ return err;
+
+ kernel_neon_begin();
+ ce_aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key1.key_enc, rounds, walk.nbytes, walk.iv,
+ ctx->key2.key_enc, first);
+ kernel_neon_end();
+
+ return skcipher_walk_done(&walk, 0);
+}
+
+static int xts_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int err, first, rounds = num_rounds(&ctx->key1);
+ int tail = req->cryptlen % AES_BLOCK_SIZE;
+ struct scatterlist sg_src[2], sg_dst[2];
+ struct skcipher_request subreq;
+ struct scatterlist *src, *dst;
+ struct skcipher_walk walk;
+
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+ int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+ AES_BLOCK_SIZE) - 2;
+
+ skcipher_walk_abort(&walk);
+
+ skcipher_request_set_tfm(&subreq, tfm);
+ skcipher_request_set_callback(&subreq,
+ skcipher_request_flags(req),
+ NULL, NULL);
+ skcipher_request_set_crypt(&subreq, req->src, req->dst,
+ xts_blocks * AES_BLOCK_SIZE,
+ req->iv);
+ req = &subreq;
+ err = skcipher_walk_virt(&walk, req, false);
+ } else {
+ tail = 0;
+ }
+
+ for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+ int nbytes = walk.nbytes;
+
+ if (walk.nbytes < walk.total)
+ nbytes &= ~(AES_BLOCK_SIZE - 1);
+
+ kernel_neon_begin();
+ ce_aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key1.key_dec, rounds, nbytes, walk.iv,
+ ctx->key2.key_enc, first);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+ }
+
+ if (err || likely(!tail))
+ return err;
+
+ dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+ if (req->dst != req->src)
+ dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+ skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, req, false);
+ if (err)
+ return err;
+
+ kernel_neon_begin();
+ ce_aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key1.key_dec, rounds, walk.nbytes, walk.iv,
+ ctx->key2.key_enc, first);
+ kernel_neon_end();
+
+ return skcipher_walk_done(&walk, 0);
+}
+
+static struct skcipher_alg aes_algs[] = { {
+ .base.cra_name = "__ecb(aes)",
+ .base.cra_driver_name = "__ecb-aes-ce",
+ .base.cra_priority = 300,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .setkey = ce_aes_setkey,
+ .encrypt = ecb_encrypt,
+ .decrypt = ecb_decrypt,
+}, {
+ .base.cra_name = "__cbc(aes)",
+ .base.cra_driver_name = "__cbc-aes-ce",
+ .base.cra_priority = 300,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ce_aes_setkey,
+ .encrypt = cbc_encrypt,
+ .decrypt = cbc_decrypt,
+}, {
+ .base.cra_name = "__cts(cbc(aes))",
+ .base.cra_driver_name = "__cts-cbc-aes-ce",
+ .base.cra_priority = 300,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .walksize = 2 * AES_BLOCK_SIZE,
+ .setkey = ce_aes_setkey,
+ .encrypt = cts_cbc_encrypt,
+ .decrypt = cts_cbc_decrypt,
+}, {
+ .base.cra_name = "__ctr(aes)",
+ .base.cra_driver_name = "__ctr-aes-ce",
+ .base.cra_priority = 300,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+ .setkey = ce_aes_setkey,
+ .encrypt = ctr_encrypt,
+ .decrypt = ctr_encrypt,
+}, {
+ .base.cra_name = "ctr(aes)",
+ .base.cra_driver_name = "ctr-aes-ce-sync",
+ .base.cra_priority = 300 - 1,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+ .setkey = ce_aes_setkey,
+ .encrypt = ctr_encrypt_sync,
+ .decrypt = ctr_encrypt_sync,
+}, {
+ .base.cra_name = "__xts(aes)",
+ .base.cra_driver_name = "__xts-aes-ce",
+ .base.cra_priority = 300,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct crypto_aes_xts_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .walksize = 2 * AES_BLOCK_SIZE,
+ .setkey = xts_set_key,
+ .encrypt = xts_encrypt,
+ .decrypt = xts_decrypt,
+} };
+
+static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
+
+static void aes_exit(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(aes_simd_algs) && aes_simd_algs[i]; i++)
+ simd_skcipher_free(aes_simd_algs[i]);
+
+ crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static int __init aes_init(void)
+{
+ struct simd_skcipher_alg *simd;
+ const char *basename;
+ const char *algname;
+ const char *drvname;
+ int err;
+ int i;
+
+ err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+ if (err)
+ return err;
+
+ for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+ if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
+ continue;
+
+ algname = aes_algs[i].base.cra_name + 2;
+ drvname = aes_algs[i].base.cra_driver_name + 2;
+ basename = aes_algs[i].base.cra_driver_name;
+ simd = simd_skcipher_create_compat(algname, drvname, basename);
+ err = PTR_ERR(simd);
+ if (IS_ERR(simd))
+ goto unregister_simds;
+
+ aes_simd_algs[i] = simd;
+ }
+
+ return 0;
+
+unregister_simds:
+ aes_exit();
+ return err;
+}
+
+module_cpu_feature_match(AES, aes_init);
+module_exit(aes_exit);
diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S
new file mode 100644
index 0000000000..1da3f41359
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-core.S
@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
+
+ .text
+ .align 5
+
+ rk .req r0
+ rounds .req r1
+ in .req r2
+ out .req r3
+ ttab .req ip
+
+ t0 .req lr
+ t1 .req r2
+ t2 .req r3
+
+ .macro __select, out, in, idx
+ .if __LINUX_ARM_ARCH__ < 7
+ and \out, \in, #0xff << (8 * \idx)
+ .else
+ ubfx \out, \in, #(8 * \idx), #8
+ .endif
+ .endm
+
+ .macro __load, out, in, idx, sz, op
+ .if __LINUX_ARM_ARCH__ < 7 && \idx > 0
+ ldr\op \out, [ttab, \in, lsr #(8 * \idx) - \sz]
+ .else
+ ldr\op \out, [ttab, \in, lsl #\sz]
+ .endif
+ .endm
+
+ .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc, sz, op, oldcpsr
+ __select \out0, \in0, 0
+ __select t0, \in1, 1
+ __load \out0, \out0, 0, \sz, \op
+ __load t0, t0, 1, \sz, \op
+
+ .if \enc
+ __select \out1, \in1, 0
+ __select t1, \in2, 1
+ .else
+ __select \out1, \in3, 0
+ __select t1, \in0, 1
+ .endif
+ __load \out1, \out1, 0, \sz, \op
+ __select t2, \in2, 2
+ __load t1, t1, 1, \sz, \op
+ __load t2, t2, 2, \sz, \op
+
+ eor \out0, \out0, t0, ror #24
+
+ __select t0, \in3, 3
+ .if \enc
+ __select \t3, \in3, 2
+ __select \t4, \in0, 3
+ .else
+ __select \t3, \in1, 2
+ __select \t4, \in2, 3
+ .endif
+ __load \t3, \t3, 2, \sz, \op
+ __load t0, t0, 3, \sz, \op
+ __load \t4, \t4, 3, \sz, \op
+
+ .ifnb \oldcpsr
+ /*
+ * This is the final round and we're done with all data-dependent table
+ * lookups, so we can safely re-enable interrupts.
+ */
+ restore_irqs \oldcpsr
+ .endif
+
+ eor \out1, \out1, t1, ror #24
+ eor \out0, \out0, t2, ror #16
+ ldm rk!, {t1, t2}
+ eor \out1, \out1, \t3, ror #16
+ eor \out0, \out0, t0, ror #8
+ eor \out1, \out1, \t4, ror #8
+ eor \out0, \out0, t1
+ eor \out1, \out1, t2
+ .endm
+
+ .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op, oldcpsr
+ __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op
+ __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op, \oldcpsr
+ .endm
+
+ .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op, oldcpsr
+ __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op
+ __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op, \oldcpsr
+ .endm
+
+ .macro do_crypt, round, ttab, ltab, bsz
+ push {r3-r11, lr}
+
+ // Load keys first, to reduce latency in case they're not cached yet.
+ ldm rk!, {r8-r11}
+
+ ldr r4, [in]
+ ldr r5, [in, #4]
+ ldr r6, [in, #8]
+ ldr r7, [in, #12]
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ rev_l r4, t0
+ rev_l r5, t0
+ rev_l r6, t0
+ rev_l r7, t0
+#endif
+
+ eor r4, r4, r8
+ eor r5, r5, r9
+ eor r6, r6, r10
+ eor r7, r7, r11
+
+ mov_l ttab, \ttab
+ /*
+ * Disable interrupts and prefetch the 1024-byte 'ft' or 'it' table into
+ * L1 cache, assuming cacheline size >= 32. This is a hardening measure
+ * intended to make cache-timing attacks more difficult. They may not
+ * be fully prevented, however; see the paper
+ * https://cr.yp.to/antiforgery/cachetiming-20050414.pdf
+ * ("Cache-timing attacks on AES") for a discussion of the many
+ * difficulties involved in writing truly constant-time AES software.
+ */
+ save_and_disable_irqs t0
+ .set i, 0
+ .rept 1024 / 128
+ ldr r8, [ttab, #i + 0]
+ ldr r9, [ttab, #i + 32]
+ ldr r10, [ttab, #i + 64]
+ ldr r11, [ttab, #i + 96]
+ .set i, i + 128
+ .endr
+ push {t0} // oldcpsr
+
+ tst rounds, #2
+ bne 1f
+
+0: \round r8, r9, r10, r11, r4, r5, r6, r7
+ \round r4, r5, r6, r7, r8, r9, r10, r11
+
+1: subs rounds, rounds, #4
+ \round r8, r9, r10, r11, r4, r5, r6, r7
+ bls 2f
+ \round r4, r5, r6, r7, r8, r9, r10, r11
+ b 0b
+
+2: .ifb \ltab
+ add ttab, ttab, #1
+ .else
+ mov_l ttab, \ltab
+ // Prefetch inverse S-box for final round; see explanation above
+ .set i, 0
+ .rept 256 / 64
+ ldr t0, [ttab, #i + 0]
+ ldr t1, [ttab, #i + 32]
+ .set i, i + 64
+ .endr
+ .endif
+
+ pop {rounds} // oldcpsr
+ \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b, rounds
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ rev_l r4, t0
+ rev_l r5, t0
+ rev_l r6, t0
+ rev_l r7, t0
+#endif
+
+ ldr out, [sp]
+
+ str r4, [out]
+ str r5, [out, #4]
+ str r6, [out, #8]
+ str r7, [out, #12]
+
+ pop {r3-r11, pc}
+
+ .align 3
+ .ltorg
+ .endm
+
+ENTRY(__aes_arm_encrypt)
+ do_crypt fround, crypto_ft_tab,, 2
+ENDPROC(__aes_arm_encrypt)
+
+ .align 5
+ENTRY(__aes_arm_decrypt)
+ do_crypt iround, crypto_it_tab, crypto_aes_inv_sbox, 0
+ENDPROC(__aes_arm_decrypt)
diff --git a/arch/arm/crypto/aes-cipher-glue.c b/arch/arm/crypto/aes-cipher-glue.c
new file mode 100644
index 0000000000..6dfaef2d8f
--- /dev/null
+++ b/arch/arm/crypto/aes-cipher-glue.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ */
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+
+asmlinkage void __aes_arm_encrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+asmlinkage void __aes_arm_decrypt(u32 *rk, int rounds, const u8 *in, u8 *out);
+
+static void aes_arm_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ int rounds = 6 + ctx->key_length / 4;
+
+ __aes_arm_encrypt(ctx->key_enc, rounds, in, out);
+}
+
+static void aes_arm_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ int rounds = 6 + ctx->key_length / 4;
+
+ __aes_arm_decrypt(ctx->key_dec, rounds, in, out);
+}
+
+static struct crypto_alg aes_alg = {
+ .cra_name = "aes",
+ .cra_driver_name = "aes-arm",
+ .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_cipher.cia_min_keysize = AES_MIN_KEY_SIZE,
+ .cra_cipher.cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cra_cipher.cia_setkey = crypto_aes_set_key,
+ .cra_cipher.cia_encrypt = aes_arm_encrypt,
+ .cra_cipher.cia_decrypt = aes_arm_decrypt,
+
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ .cra_alignmask = 3,
+#endif
+};
+
+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("Scalar AES cipher for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/arm/crypto/aes-neonbs-core.S b/arch/arm/crypto/aes-neonbs-core.S
new file mode 100644
index 0000000000..7b61032f29
--- /dev/null
+++ b/arch/arm/crypto/aes-neonbs-core.S
@@ -0,0 +1,1043 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Bit sliced AES using NEON instructions
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ */
+
+/*
+ * The algorithm implemented here is described in detail by the paper
+ * 'Faster and Timing-Attack Resistant AES-GCM' by Emilia Kaesper and
+ * Peter Schwabe (https://eprint.iacr.org/2009/129.pdf)
+ *
+ * This implementation is based primarily on the OpenSSL implementation
+ * for 32-bit ARM written by Andy Polyakov <appro@openssl.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .fpu neon
+
+ rounds .req ip
+ bskey .req r4
+
+ q0l .req d0
+ q0h .req d1
+ q1l .req d2
+ q1h .req d3
+ q2l .req d4
+ q2h .req d5
+ q3l .req d6
+ q3h .req d7
+ q4l .req d8
+ q4h .req d9
+ q5l .req d10
+ q5h .req d11
+ q6l .req d12
+ q6h .req d13
+ q7l .req d14
+ q7h .req d15
+ q8l .req d16
+ q8h .req d17
+ q9l .req d18
+ q9h .req d19
+ q10l .req d20
+ q10h .req d21
+ q11l .req d22
+ q11h .req d23
+ q12l .req d24
+ q12h .req d25
+ q13l .req d26
+ q13h .req d27
+ q14l .req d28
+ q14h .req d29
+ q15l .req d30
+ q15h .req d31
+
+ .macro __tbl, out, tbl, in, tmp
+ .ifc \out, \tbl
+ .ifb \tmp
+ .error __tbl needs temp register if out == tbl
+ .endif
+ vmov \tmp, \out
+ .endif
+ vtbl.8 \out\()l, {\tbl}, \in\()l
+ .ifc \out, \tbl
+ vtbl.8 \out\()h, {\tmp}, \in\()h
+ .else
+ vtbl.8 \out\()h, {\tbl}, \in\()h
+ .endif
+ .endm
+
+ .macro __ldr, out, sym
+ vldr \out\()l, \sym
+ vldr \out\()h, \sym + 8
+ .endm
+
+ .macro in_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+ veor \b2, \b2, \b1
+ veor \b5, \b5, \b6
+ veor \b3, \b3, \b0
+ veor \b6, \b6, \b2
+ veor \b5, \b5, \b0
+ veor \b6, \b6, \b3
+ veor \b3, \b3, \b7
+ veor \b7, \b7, \b5
+ veor \b3, \b3, \b4
+ veor \b4, \b4, \b5
+ veor \b2, \b2, \b7
+ veor \b3, \b3, \b1
+ veor \b1, \b1, \b5
+ .endm
+
+ .macro out_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+ veor \b0, \b0, \b6
+ veor \b1, \b1, \b4
+ veor \b4, \b4, \b6
+ veor \b2, \b2, \b0
+ veor \b6, \b6, \b1
+ veor \b1, \b1, \b5
+ veor \b5, \b5, \b3
+ veor \b3, \b3, \b7
+ veor \b7, \b7, \b5
+ veor \b2, \b2, \b5
+ veor \b4, \b4, \b7
+ .endm
+
+ .macro inv_in_bs_ch, b6, b1, b2, b4, b7, b0, b3, b5
+ veor \b1, \b1, \b7
+ veor \b4, \b4, \b7
+ veor \b7, \b7, \b5
+ veor \b1, \b1, \b3
+ veor \b2, \b2, \b5
+ veor \b3, \b3, \b7
+ veor \b6, \b6, \b1
+ veor \b2, \b2, \b0
+ veor \b5, \b5, \b3
+ veor \b4, \b4, \b6
+ veor \b0, \b0, \b6
+ veor \b1, \b1, \b4
+ .endm
+
+ .macro inv_out_bs_ch, b6, b5, b0, b3, b7, b1, b4, b2
+ veor \b1, \b1, \b5
+ veor \b2, \b2, \b7
+ veor \b3, \b3, \b1
+ veor \b4, \b4, \b5
+ veor \b7, \b7, \b5
+ veor \b3, \b3, \b4
+ veor \b5, \b5, \b0
+ veor \b3, \b3, \b7
+ veor \b6, \b6, \b2
+ veor \b2, \b2, \b1
+ veor \b6, \b6, \b3
+ veor \b3, \b3, \b0
+ veor \b5, \b5, \b6
+ .endm
+
+ .macro mul_gf4, x0, x1, y0, y1, t0, t1
+ veor \t0, \y0, \y1
+ vand \t0, \t0, \x0
+ veor \x0, \x0, \x1
+ vand \t1, \x1, \y0
+ vand \x0, \x0, \y1
+ veor \x1, \t1, \t0
+ veor \x0, \x0, \t1
+ .endm
+
+ .macro mul_gf4_n_gf4, x0, x1, y0, y1, t0, x2, x3, y2, y3, t1
+ veor \t0, \y0, \y1
+ veor \t1, \y2, \y3
+ vand \t0, \t0, \x0
+ vand \t1, \t1, \x2
+ veor \x0, \x0, \x1
+ veor \x2, \x2, \x3
+ vand \x1, \x1, \y0
+ vand \x3, \x3, \y2
+ vand \x0, \x0, \y1
+ vand \x2, \x2, \y3
+ veor \x1, \x1, \x0
+ veor \x2, \x2, \x3
+ veor \x0, \x0, \t0
+ veor \x3, \x3, \t1
+ .endm
+
+ .macro mul_gf16_2, x0, x1, x2, x3, x4, x5, x6, x7, \
+ y0, y1, y2, y3, t0, t1, t2, t3
+ veor \t0, \x0, \x2
+ veor \t1, \x1, \x3
+ mul_gf4 \x0, \x1, \y0, \y1, \t2, \t3
+ veor \y0, \y0, \y2
+ veor \y1, \y1, \y3
+ mul_gf4_n_gf4 \t0, \t1, \y0, \y1, \t3, \x2, \x3, \y2, \y3, \t2
+ veor \x0, \x0, \t0
+ veor \x2, \x2, \t0
+ veor \x1, \x1, \t1
+ veor \x3, \x3, \t1
+ veor \t0, \x4, \x6
+ veor \t1, \x5, \x7
+ mul_gf4_n_gf4 \t0, \t1, \y0, \y1, \t3, \x6, \x7, \y2, \y3, \t2
+ veor \y0, \y0, \y2
+ veor \y1, \y1, \y3
+ mul_gf4 \x4, \x5, \y0, \y1, \t2, \t3
+ veor \x4, \x4, \t0
+ veor \x6, \x6, \t0
+ veor \x5, \x5, \t1
+ veor \x7, \x7, \t1
+ .endm
+
+ .macro inv_gf256, x0, x1, x2, x3, x4, x5, x6, x7, \
+ t0, t1, t2, t3, s0, s1, s2, s3
+ veor \t3, \x4, \x6
+ veor \t0, \x5, \x7
+ veor \t1, \x1, \x3
+ veor \s1, \x7, \x6
+ veor \s0, \x0, \x2
+ veor \s3, \t3, \t0
+ vorr \t2, \t0, \t1
+ vand \s2, \t3, \s0
+ vorr \t3, \t3, \s0
+ veor \s0, \s0, \t1
+ vand \t0, \t0, \t1
+ veor \t1, \x3, \x2
+ vand \s3, \s3, \s0
+ vand \s1, \s1, \t1
+ veor \t1, \x4, \x5
+ veor \s0, \x1, \x0
+ veor \t3, \t3, \s1
+ veor \t2, \t2, \s1
+ vand \s1, \t1, \s0
+ vorr \t1, \t1, \s0
+ veor \t3, \t3, \s3
+ veor \t0, \t0, \s1
+ veor \t2, \t2, \s2
+ veor \t1, \t1, \s3
+ veor \t0, \t0, \s2
+ vand \s0, \x7, \x3
+ veor \t1, \t1, \s2
+ vand \s1, \x6, \x2
+ vand \s2, \x5, \x1
+ vorr \s3, \x4, \x0
+ veor \t3, \t3, \s0
+ veor \t1, \t1, \s2
+ veor \s0, \t0, \s3
+ veor \t2, \t2, \s1
+ vand \s2, \t3, \t1
+ veor \s1, \t2, \s2
+ veor \s3, \s0, \s2
+ vbsl \s1, \t1, \s0
+ vmvn \t0, \s0
+ vbsl \s0, \s1, \s3
+ vbsl \t0, \s1, \s3
+ vbsl \s3, \t3, \t2
+ veor \t3, \t3, \t2
+ vand \s2, \s0, \s3
+ veor \t1, \t1, \t0
+ veor \s2, \s2, \t3
+ mul_gf16_2 \x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+ \s3, \s2, \s1, \t1, \s0, \t0, \t2, \t3
+ .endm
+
+ .macro sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+ t0, t1, t2, t3, s0, s1, s2, s3
+ in_bs_ch \b0, \b1, \b2, \b3, \b4, \b5, \b6, \b7
+ inv_gf256 \b6, \b5, \b0, \b3, \b7, \b1, \b4, \b2, \
+ \t0, \t1, \t2, \t3, \s0, \s1, \s2, \s3
+ out_bs_ch \b7, \b1, \b4, \b2, \b6, \b5, \b0, \b3
+ .endm
+
+ .macro inv_sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+ t0, t1, t2, t3, s0, s1, s2, s3
+ inv_in_bs_ch \b0, \b1, \b2, \b3, \b4, \b5, \b6, \b7
+ inv_gf256 \b5, \b1, \b2, \b6, \b3, \b7, \b0, \b4, \
+ \t0, \t1, \t2, \t3, \s0, \s1, \s2, \s3
+ inv_out_bs_ch \b3, \b7, \b0, \b4, \b5, \b1, \b2, \b6
+ .endm
+
+ .macro shift_rows, x0, x1, x2, x3, x4, x5, x6, x7, \
+ t0, t1, t2, t3, mask
+ vld1.8 {\t0-\t1}, [bskey, :256]!
+ veor \t0, \t0, \x0
+ vld1.8 {\t2-\t3}, [bskey, :256]!
+ veor \t1, \t1, \x1
+ __tbl \x0, \t0, \mask
+ veor \t2, \t2, \x2
+ __tbl \x1, \t1, \mask
+ vld1.8 {\t0-\t1}, [bskey, :256]!
+ veor \t3, \t3, \x3
+ __tbl \x2, \t2, \mask
+ __tbl \x3, \t3, \mask
+ vld1.8 {\t2-\t3}, [bskey, :256]!
+ veor \t0, \t0, \x4
+ veor \t1, \t1, \x5
+ __tbl \x4, \t0, \mask
+ veor \t2, \t2, \x6
+ __tbl \x5, \t1, \mask
+ veor \t3, \t3, \x7
+ __tbl \x6, \t2, \mask
+ __tbl \x7, \t3, \mask
+ .endm
+
+ .macro inv_shift_rows, x0, x1, x2, x3, x4, x5, x6, x7, \
+ t0, t1, t2, t3, mask
+ __tbl \x0, \x0, \mask, \t0
+ __tbl \x1, \x1, \mask, \t1
+ __tbl \x2, \x2, \mask, \t2
+ __tbl \x3, \x3, \mask, \t3
+ __tbl \x4, \x4, \mask, \t0
+ __tbl \x5, \x5, \mask, \t1
+ __tbl \x6, \x6, \mask, \t2
+ __tbl \x7, \x7, \mask, \t3
+ .endm
+
+ .macro mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+ t0, t1, t2, t3, t4, t5, t6, t7, inv
+ vext.8 \t0, \x0, \x0, #12
+ vext.8 \t1, \x1, \x1, #12
+ veor \x0, \x0, \t0
+ vext.8 \t2, \x2, \x2, #12
+ veor \x1, \x1, \t1
+ vext.8 \t3, \x3, \x3, #12
+ veor \x2, \x2, \t2
+ vext.8 \t4, \x4, \x4, #12
+ veor \x3, \x3, \t3
+ vext.8 \t5, \x5, \x5, #12
+ veor \x4, \x4, \t4
+ vext.8 \t6, \x6, \x6, #12
+ veor \x5, \x5, \t5
+ vext.8 \t7, \x7, \x7, #12
+ veor \x6, \x6, \t6
+ veor \t1, \t1, \x0
+ veor.8 \x7, \x7, \t7
+ vext.8 \x0, \x0, \x0, #8
+ veor \t2, \t2, \x1
+ veor \t0, \t0, \x7
+ veor \t1, \t1, \x7
+ vext.8 \x1, \x1, \x1, #8
+ veor \t5, \t5, \x4
+ veor \x0, \x0, \t0
+ veor \t6, \t6, \x5
+ veor \x1, \x1, \t1
+ vext.8 \t0, \x4, \x4, #8
+ veor \t4, \t4, \x3
+ vext.8 \t1, \x5, \x5, #8
+ veor \t7, \t7, \x6
+ vext.8 \x4, \x3, \x3, #8
+ veor \t3, \t3, \x2
+ vext.8 \x5, \x7, \x7, #8
+ veor \t4, \t4, \x7
+ vext.8 \x3, \x6, \x6, #8
+ veor \t3, \t3, \x7
+ vext.8 \x6, \x2, \x2, #8
+ veor \x7, \t1, \t5
+ .ifb \inv
+ veor \x2, \t0, \t4
+ veor \x4, \x4, \t3
+ veor \x5, \x5, \t7
+ veor \x3, \x3, \t6
+ veor \x6, \x6, \t2
+ .else
+ veor \t3, \t3, \x4
+ veor \x5, \x5, \t7
+ veor \x2, \x3, \t6
+ veor \x3, \t0, \t4
+ veor \x4, \x6, \t2
+ vmov \x6, \t3
+ .endif
+ .endm
+
+ .macro inv_mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+ t0, t1, t2, t3, t4, t5, t6, t7
+ vld1.8 {\t0-\t1}, [bskey, :256]!
+ veor \x0, \x0, \t0
+ vld1.8 {\t2-\t3}, [bskey, :256]!
+ veor \x1, \x1, \t1
+ vld1.8 {\t4-\t5}, [bskey, :256]!
+ veor \x2, \x2, \t2
+ vld1.8 {\t6-\t7}, [bskey, :256]
+ sub bskey, bskey, #224
+ veor \x3, \x3, \t3
+ veor \x4, \x4, \t4
+ veor \x5, \x5, \t5
+ veor \x6, \x6, \t6
+ veor \x7, \x7, \t7
+ vext.8 \t0, \x0, \x0, #8
+ vext.8 \t6, \x6, \x6, #8
+ vext.8 \t7, \x7, \x7, #8
+ veor \t0, \t0, \x0
+ vext.8 \t1, \x1, \x1, #8
+ veor \t6, \t6, \x6
+ vext.8 \t2, \x2, \x2, #8
+ veor \t7, \t7, \x7
+ vext.8 \t3, \x3, \x3, #8
+ veor \t1, \t1, \x1
+ vext.8 \t4, \x4, \x4, #8
+ veor \t2, \t2, \x2
+ vext.8 \t5, \x5, \x5, #8
+ veor \t3, \t3, \x3
+ veor \t4, \t4, \x4
+ veor \t5, \t5, \x5
+ veor \x0, \x0, \t6
+ veor \x1, \x1, \t6
+ veor \x2, \x2, \t0
+ veor \x4, \x4, \t2
+ veor \x3, \x3, \t1
+ veor \x1, \x1, \t7
+ veor \x2, \x2, \t7
+ veor \x4, \x4, \t6
+ veor \x5, \x5, \t3
+ veor \x3, \x3, \t6
+ veor \x6, \x6, \t4
+ veor \x4, \x4, \t7
+ veor \x5, \x5, \t7
+ veor \x7, \x7, \t5
+ mix_cols \x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+ \t0, \t1, \t2, \t3, \t4, \t5, \t6, \t7, 1
+ .endm
+
+ .macro swapmove_2x, a0, b0, a1, b1, n, mask, t0, t1
+ vshr.u64 \t0, \b0, #\n
+ vshr.u64 \t1, \b1, #\n
+ veor \t0, \t0, \a0
+ veor \t1, \t1, \a1
+ vand \t0, \t0, \mask
+ vand \t1, \t1, \mask
+ veor \a0, \a0, \t0
+ vshl.s64 \t0, \t0, #\n
+ veor \a1, \a1, \t1
+ vshl.s64 \t1, \t1, #\n
+ veor \b0, \b0, \t0
+ veor \b1, \b1, \t1
+ .endm
+
+ .macro bitslice, x7, x6, x5, x4, x3, x2, x1, x0, t0, t1, t2, t3
+ vmov.i8 \t0, #0x55
+ vmov.i8 \t1, #0x33
+ swapmove_2x \x0, \x1, \x2, \x3, 1, \t0, \t2, \t3
+ swapmove_2x \x4, \x5, \x6, \x7, 1, \t0, \t2, \t3
+ vmov.i8 \t0, #0x0f
+ swapmove_2x \x0, \x2, \x1, \x3, 2, \t1, \t2, \t3
+ swapmove_2x \x4, \x6, \x5, \x7, 2, \t1, \t2, \t3
+ swapmove_2x \x0, \x4, \x1, \x5, 4, \t0, \t2, \t3
+ swapmove_2x \x2, \x6, \x3, \x7, 4, \t0, \t2, \t3
+ .endm
+
+ .align 4
+M0: .quad 0x02060a0e03070b0f, 0x0004080c0105090d
+
+ /*
+ * void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)
+ */
+ENTRY(aesbs_convert_key)
+ vld1.32 {q7}, [r1]! // load round 0 key
+ vld1.32 {q15}, [r1]! // load round 1 key
+
+ vmov.i8 q8, #0x01 // bit masks
+ vmov.i8 q9, #0x02
+ vmov.i8 q10, #0x04
+ vmov.i8 q11, #0x08
+ vmov.i8 q12, #0x10
+ vmov.i8 q13, #0x20
+ __ldr q14, M0
+
+ sub r2, r2, #1
+ vst1.8 {q7}, [r0, :128]! // save round 0 key
+
+.Lkey_loop:
+ __tbl q7, q15, q14
+ vmov.i8 q6, #0x40
+ vmov.i8 q15, #0x80
+
+ vtst.8 q0, q7, q8
+ vtst.8 q1, q7, q9
+ vtst.8 q2, q7, q10
+ vtst.8 q3, q7, q11
+ vtst.8 q4, q7, q12
+ vtst.8 q5, q7, q13
+ vtst.8 q6, q7, q6
+ vtst.8 q7, q7, q15
+ vld1.32 {q15}, [r1]! // load next round key
+ vmvn q0, q0
+ vmvn q1, q1
+ vmvn q5, q5
+ vmvn q6, q6
+
+ subs r2, r2, #1
+ vst1.8 {q0-q1}, [r0, :256]!
+ vst1.8 {q2-q3}, [r0, :256]!
+ vst1.8 {q4-q5}, [r0, :256]!
+ vst1.8 {q6-q7}, [r0, :256]!
+ bne .Lkey_loop
+
+ vmov.i8 q7, #0x63 // compose .L63
+ veor q15, q15, q7
+ vst1.8 {q15}, [r0, :128]
+ bx lr
+ENDPROC(aesbs_convert_key)
+
+ .align 4
+M0SR: .quad 0x0a0e02060f03070b, 0x0004080c05090d01
+
+aesbs_encrypt8:
+ vld1.8 {q9}, [bskey, :128]! // round 0 key
+ __ldr q8, M0SR
+
+ veor q10, q0, q9 // xor with round0 key
+ veor q11, q1, q9
+ __tbl q0, q10, q8
+ veor q12, q2, q9
+ __tbl q1, q11, q8
+ veor q13, q3, q9
+ __tbl q2, q12, q8
+ veor q14, q4, q9
+ __tbl q3, q13, q8
+ veor q15, q5, q9
+ __tbl q4, q14, q8
+ veor q10, q6, q9
+ __tbl q5, q15, q8
+ veor q11, q7, q9
+ __tbl q6, q10, q8
+ __tbl q7, q11, q8
+
+ bitslice q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11
+
+ sub rounds, rounds, #1
+ b .Lenc_sbox
+
+ .align 5
+SR: .quad 0x0504070600030201, 0x0f0e0d0c0a09080b
+SRM0: .quad 0x0304090e00050a0f, 0x01060b0c0207080d
+
+.Lenc_last:
+ __ldr q12, SRM0
+.Lenc_loop:
+ shift_rows q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12
+.Lenc_sbox:
+ sbox q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12, \
+ q13, q14, q15
+ subs rounds, rounds, #1
+ bcc .Lenc_done
+
+ mix_cols q0, q1, q4, q6, q3, q7, q2, q5, q8, q9, q10, q11, q12, \
+ q13, q14, q15
+
+ beq .Lenc_last
+ __ldr q12, SR
+ b .Lenc_loop
+
+.Lenc_done:
+ vld1.8 {q12}, [bskey, :128] // last round key
+
+ bitslice q0, q1, q4, q6, q3, q7, q2, q5, q8, q9, q10, q11
+
+ veor q0, q0, q12
+ veor q1, q1, q12
+ veor q4, q4, q12
+ veor q6, q6, q12
+ veor q3, q3, q12
+ veor q7, q7, q12
+ veor q2, q2, q12
+ veor q5, q5, q12
+ bx lr
+ENDPROC(aesbs_encrypt8)
+
+ .align 4
+M0ISR: .quad 0x0a0e0206070b0f03, 0x0004080c0d010509
+
+aesbs_decrypt8:
+ add bskey, bskey, rounds, lsl #7
+ sub bskey, bskey, #112
+ vld1.8 {q9}, [bskey, :128] // round 0 key
+ sub bskey, bskey, #128
+ __ldr q8, M0ISR
+
+ veor q10, q0, q9 // xor with round0 key
+ veor q11, q1, q9
+ __tbl q0, q10, q8
+ veor q12, q2, q9
+ __tbl q1, q11, q8
+ veor q13, q3, q9
+ __tbl q2, q12, q8
+ veor q14, q4, q9
+ __tbl q3, q13, q8
+ veor q15, q5, q9
+ __tbl q4, q14, q8
+ veor q10, q6, q9
+ __tbl q5, q15, q8
+ veor q11, q7, q9
+ __tbl q6, q10, q8
+ __tbl q7, q11, q8
+
+ bitslice q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11
+
+ sub rounds, rounds, #1
+ b .Ldec_sbox
+
+ .align 5
+ISR: .quad 0x0504070602010003, 0x0f0e0d0c080b0a09
+ISRM0: .quad 0x01040b0e0205080f, 0x0306090c00070a0d
+
+.Ldec_last:
+ __ldr q12, ISRM0
+.Ldec_loop:
+ inv_shift_rows q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12
+.Ldec_sbox:
+ inv_sbox q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12, \
+ q13, q14, q15
+ subs rounds, rounds, #1
+ bcc .Ldec_done
+
+ inv_mix_cols q0, q1, q6, q4, q2, q7, q3, q5, q8, q9, q10, q11, q12, \
+ q13, q14, q15
+
+ beq .Ldec_last
+ __ldr q12, ISR
+ b .Ldec_loop
+
+.Ldec_done:
+ add bskey, bskey, #112
+ vld1.8 {q12}, [bskey, :128] // last round key
+
+ bitslice q0, q1, q6, q4, q2, q7, q3, q5, q8, q9, q10, q11
+
+ veor q0, q0, q12
+ veor q1, q1, q12
+ veor q6, q6, q12
+ veor q4, q4, q12
+ veor q2, q2, q12
+ veor q7, q7, q12
+ veor q3, q3, q12
+ veor q5, q5, q12
+ bx lr
+ENDPROC(aesbs_decrypt8)
+
+ /*
+ * aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks)
+ * aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks)
+ */
+ .macro __ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+ push {r4-r6, lr}
+ ldr r5, [sp, #16] // number of blocks
+
+99: adr ip, 0f
+ and lr, r5, #7
+ cmp r5, #8
+ sub ip, ip, lr, lsl #2
+ movlt pc, ip // computed goto if blocks < 8
+
+ vld1.8 {q0}, [r1]!
+ vld1.8 {q1}, [r1]!
+ vld1.8 {q2}, [r1]!
+ vld1.8 {q3}, [r1]!
+ vld1.8 {q4}, [r1]!
+ vld1.8 {q5}, [r1]!
+ vld1.8 {q6}, [r1]!
+ vld1.8 {q7}, [r1]!
+
+0: mov bskey, r2
+ mov rounds, r3
+ bl \do8
+
+ adr ip, 1f
+ and lr, r5, #7
+ cmp r5, #8
+ sub ip, ip, lr, lsl #2
+ movlt pc, ip // computed goto if blocks < 8
+
+ vst1.8 {\o0}, [r0]!
+ vst1.8 {\o1}, [r0]!
+ vst1.8 {\o2}, [r0]!
+ vst1.8 {\o3}, [r0]!
+ vst1.8 {\o4}, [r0]!
+ vst1.8 {\o5}, [r0]!
+ vst1.8 {\o6}, [r0]!
+ vst1.8 {\o7}, [r0]!
+
+1: subs r5, r5, #8
+ bgt 99b
+
+ pop {r4-r6, pc}
+ .endm
+
+ .align 4
+ENTRY(aesbs_ecb_encrypt)
+ __ecb_crypt aesbs_encrypt8, q0, q1, q4, q6, q3, q7, q2, q5
+ENDPROC(aesbs_ecb_encrypt)
+
+ .align 4
+ENTRY(aesbs_ecb_decrypt)
+ __ecb_crypt aesbs_decrypt8, q0, q1, q6, q4, q2, q7, q3, q5
+ENDPROC(aesbs_ecb_decrypt)
+
+ /*
+ * aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ * int rounds, int blocks, u8 iv[])
+ */
+ .align 4
+ENTRY(aesbs_cbc_decrypt)
+ mov ip, sp
+ push {r4-r6, lr}
+ ldm ip, {r5-r6} // load args 4-5
+
+99: adr ip, 0f
+ and lr, r5, #7
+ cmp r5, #8
+ sub ip, ip, lr, lsl #2
+ mov lr, r1
+ movlt pc, ip // computed goto if blocks < 8
+
+ vld1.8 {q0}, [lr]!
+ vld1.8 {q1}, [lr]!
+ vld1.8 {q2}, [lr]!
+ vld1.8 {q3}, [lr]!
+ vld1.8 {q4}, [lr]!
+ vld1.8 {q5}, [lr]!
+ vld1.8 {q6}, [lr]!
+ vld1.8 {q7}, [lr]
+
+0: mov bskey, r2
+ mov rounds, r3
+ bl aesbs_decrypt8
+
+ vld1.8 {q8}, [r6]
+ vmov q9, q8
+ vmov q10, q8
+ vmov q11, q8
+ vmov q12, q8
+ vmov q13, q8
+ vmov q14, q8
+ vmov q15, q8
+
+ adr ip, 1f
+ and lr, r5, #7
+ cmp r5, #8
+ sub ip, ip, lr, lsl #2
+ movlt pc, ip // computed goto if blocks < 8
+
+ vld1.8 {q9}, [r1]!
+ vld1.8 {q10}, [r1]!
+ vld1.8 {q11}, [r1]!
+ vld1.8 {q12}, [r1]!
+ vld1.8 {q13}, [r1]!
+ vld1.8 {q14}, [r1]!
+ vld1.8 {q15}, [r1]!
+ W(nop)
+
+1: adr ip, 2f
+ sub ip, ip, lr, lsl #3
+ movlt pc, ip // computed goto if blocks < 8
+
+ veor q0, q0, q8
+ vst1.8 {q0}, [r0]!
+ veor q1, q1, q9
+ vst1.8 {q1}, [r0]!
+ veor q6, q6, q10
+ vst1.8 {q6}, [r0]!
+ veor q4, q4, q11
+ vst1.8 {q4}, [r0]!
+ veor q2, q2, q12
+ vst1.8 {q2}, [r0]!
+ veor q7, q7, q13
+ vst1.8 {q7}, [r0]!
+ veor q3, q3, q14
+ vst1.8 {q3}, [r0]!
+ veor q5, q5, q15
+ vld1.8 {q8}, [r1]! // load next round's iv
+2: vst1.8 {q5}, [r0]!
+
+ subs r5, r5, #8
+ vst1.8 {q8}, [r6] // store next round's iv
+ bgt 99b
+
+ pop {r4-r6, pc}
+ENDPROC(aesbs_cbc_decrypt)
+
+ .macro next_ctr, q
+ vmov \q\()h, r9, r10
+ adds r10, r10, #1
+ adcs r9, r9, #0
+ vmov \q\()l, r7, r8
+ adcs r8, r8, #0
+ adc r7, r7, #0
+ vrev32.8 \q, \q
+ .endm
+
+ /*
+ * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ * int rounds, int bytes, u8 ctr[])
+ */
+ENTRY(aesbs_ctr_encrypt)
+ mov ip, sp
+ push {r4-r10, lr}
+
+ ldm ip, {r5, r6} // load args 4-5
+ vld1.8 {q0}, [r6] // load counter
+ vrev32.8 q1, q0
+ vmov r9, r10, d3
+ vmov r7, r8, d2
+
+ adds r10, r10, #1
+ adcs r9, r9, #0
+ adcs r8, r8, #0
+ adc r7, r7, #0
+
+99: vmov q1, q0
+ sub lr, r5, #1
+ vmov q2, q0
+ adr ip, 0f
+ vmov q3, q0
+ and lr, lr, #112
+ vmov q4, q0
+ cmp r5, #112
+ vmov q5, q0
+ sub ip, ip, lr, lsl #1
+ vmov q6, q0
+ add ip, ip, lr, lsr #2
+ vmov q7, q0
+ movle pc, ip // computed goto if bytes < 112
+
+ next_ctr q1
+ next_ctr q2
+ next_ctr q3
+ next_ctr q4
+ next_ctr q5
+ next_ctr q6
+ next_ctr q7
+
+0: mov bskey, r2
+ mov rounds, r3
+ bl aesbs_encrypt8
+
+ adr ip, 1f
+ sub lr, r5, #1
+ cmp r5, #128
+ bic lr, lr, #15
+ ands r4, r5, #15 // preserves C flag
+ teqcs r5, r5 // set Z flag if not last iteration
+ sub ip, ip, lr, lsr #2
+ rsb r4, r4, #16
+ movcc pc, ip // computed goto if bytes < 128
+
+ vld1.8 {q8}, [r1]!
+ vld1.8 {q9}, [r1]!
+ vld1.8 {q10}, [r1]!
+ vld1.8 {q11}, [r1]!
+ vld1.8 {q12}, [r1]!
+ vld1.8 {q13}, [r1]!
+ vld1.8 {q14}, [r1]!
+1: subne r1, r1, r4
+ vld1.8 {q15}, [r1]!
+
+ add ip, ip, #2f - 1b
+
+ veor q0, q0, q8
+ veor q1, q1, q9
+ veor q4, q4, q10
+ veor q6, q6, q11
+ veor q3, q3, q12
+ veor q7, q7, q13
+ veor q2, q2, q14
+ bne 3f
+ veor q5, q5, q15
+
+ movcc pc, ip // computed goto if bytes < 128
+
+ vst1.8 {q0}, [r0]!
+ vst1.8 {q1}, [r0]!
+ vst1.8 {q4}, [r0]!
+ vst1.8 {q6}, [r0]!
+ vst1.8 {q3}, [r0]!
+ vst1.8 {q7}, [r0]!
+ vst1.8 {q2}, [r0]!
+2: subne r0, r0, r4
+ vst1.8 {q5}, [r0]!
+
+ next_ctr q0
+
+ subs r5, r5, #128
+ bgt 99b
+
+ vst1.8 {q0}, [r6]
+ pop {r4-r10, pc}
+
+3: adr lr, .Lpermute_table + 16
+ cmp r5, #16 // Z flag remains cleared
+ sub lr, lr, r4
+ vld1.8 {q8-q9}, [lr]
+ vtbl.8 d16, {q5}, d16
+ vtbl.8 d17, {q5}, d17
+ veor q5, q8, q15
+ bcc 4f // have to reload prev if R5 < 16
+ vtbx.8 d10, {q2}, d18
+ vtbx.8 d11, {q2}, d19
+ mov pc, ip // branch back to VST sequence
+
+4: sub r0, r0, r4
+ vshr.s8 q9, q9, #7 // create mask for VBIF
+ vld1.8 {q8}, [r0] // reload
+ vbif q5, q8, q9
+ vst1.8 {q5}, [r0]
+ pop {r4-r10, pc}
+ENDPROC(aesbs_ctr_encrypt)
+
+ .align 6
+.Lpermute_table:
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+ .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+
+ .macro next_tweak, out, in, const, tmp
+ vshr.s64 \tmp, \in, #63
+ vand \tmp, \tmp, \const
+ vadd.u64 \out, \in, \in
+ vext.8 \tmp, \tmp, \tmp, #8
+ veor \out, \out, \tmp
+ .endm
+
+ /*
+ * aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 iv[], int reorder_last_tweak)
+ * aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 iv[], int reorder_last_tweak)
+ */
+ .align 6
+__xts_prepare8:
+ vld1.8 {q14}, [r7] // load iv
+ vmov.i32 d30, #0x87 // compose tweak mask vector
+ vmovl.u32 q15, d30
+ vshr.u64 d30, d31, #7
+ vmov q12, q14
+
+ adr ip, 0f
+ and r4, r6, #7
+ cmp r6, #8
+ sub ip, ip, r4, lsl #5
+ mov r4, sp
+ movlt pc, ip // computed goto if blocks < 8
+
+ vld1.8 {q0}, [r1]!
+ next_tweak q12, q14, q15, q13
+ veor q0, q0, q14
+ vst1.8 {q14}, [r4, :128]!
+
+ vld1.8 {q1}, [r1]!
+ next_tweak q14, q12, q15, q13
+ veor q1, q1, q12
+ vst1.8 {q12}, [r4, :128]!
+
+ vld1.8 {q2}, [r1]!
+ next_tweak q12, q14, q15, q13
+ veor q2, q2, q14
+ vst1.8 {q14}, [r4, :128]!
+
+ vld1.8 {q3}, [r1]!
+ next_tweak q14, q12, q15, q13
+ veor q3, q3, q12
+ vst1.8 {q12}, [r4, :128]!
+
+ vld1.8 {q4}, [r1]!
+ next_tweak q12, q14, q15, q13
+ veor q4, q4, q14
+ vst1.8 {q14}, [r4, :128]!
+
+ vld1.8 {q5}, [r1]!
+ next_tweak q14, q12, q15, q13
+ veor q5, q5, q12
+ vst1.8 {q12}, [r4, :128]!
+
+ vld1.8 {q6}, [r1]!
+ next_tweak q12, q14, q15, q13
+ veor q6, q6, q14
+ vst1.8 {q14}, [r4, :128]!
+
+ vld1.8 {q7}, [r1]!
+ next_tweak q14, q12, q15, q13
+THUMB( itt le )
+ W(cmple) r8, #0
+ ble 1f
+0: veor q7, q7, q12
+ vst1.8 {q12}, [r4, :128]
+
+ vst1.8 {q14}, [r7] // store next iv
+ bx lr
+
+1: vswp q12, q14
+ b 0b
+ENDPROC(__xts_prepare8)
+
+ .macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+ push {r4-r8, lr}
+ mov r5, sp // preserve sp
+ ldrd r6, r7, [sp, #24] // get blocks and iv args
+ rsb r8, ip, #1
+ sub ip, sp, #128 // make room for 8x tweak
+ bic ip, ip, #0xf // align sp to 16 bytes
+ mov sp, ip
+
+99: bl __xts_prepare8
+
+ mov bskey, r2
+ mov rounds, r3
+ bl \do8
+
+ adr ip, 0f
+ and lr, r6, #7
+ cmp r6, #8
+ sub ip, ip, lr, lsl #2
+ mov r4, sp
+ movlt pc, ip // computed goto if blocks < 8
+
+ vld1.8 {q8}, [r4, :128]!
+ vld1.8 {q9}, [r4, :128]!
+ vld1.8 {q10}, [r4, :128]!
+ vld1.8 {q11}, [r4, :128]!
+ vld1.8 {q12}, [r4, :128]!
+ vld1.8 {q13}, [r4, :128]!
+ vld1.8 {q14}, [r4, :128]!
+ vld1.8 {q15}, [r4, :128]
+
+0: adr ip, 1f
+ sub ip, ip, lr, lsl #3
+ movlt pc, ip // computed goto if blocks < 8
+
+ veor \o0, \o0, q8
+ vst1.8 {\o0}, [r0]!
+ veor \o1, \o1, q9
+ vst1.8 {\o1}, [r0]!
+ veor \o2, \o2, q10
+ vst1.8 {\o2}, [r0]!
+ veor \o3, \o3, q11
+ vst1.8 {\o3}, [r0]!
+ veor \o4, \o4, q12
+ vst1.8 {\o4}, [r0]!
+ veor \o5, \o5, q13
+ vst1.8 {\o5}, [r0]!
+ veor \o6, \o6, q14
+ vst1.8 {\o6}, [r0]!
+ veor \o7, \o7, q15
+ vst1.8 {\o7}, [r0]!
+
+1: subs r6, r6, #8
+ bgt 99b
+
+ mov sp, r5
+ pop {r4-r8, pc}
+ .endm
+
+ENTRY(aesbs_xts_encrypt)
+ mov ip, #0 // never reorder final tweak
+ __xts_crypt aesbs_encrypt8, q0, q1, q4, q6, q3, q7, q2, q5
+ENDPROC(aesbs_xts_encrypt)
+
+ENTRY(aesbs_xts_decrypt)
+ ldr ip, [sp, #8] // reorder final tweak?
+ __xts_crypt aesbs_decrypt8, q0, q1, q6, q4, q2, q7, q3, q5
+ENDPROC(aesbs_xts_decrypt)
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
new file mode 100644
index 0000000000..f00f042ef3
--- /dev/null
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -0,0 +1,557 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Bit sliced AES using NEON instructions
+ *
+ * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/aes.h>
+#include <crypto/ctr.h>
+#include <crypto/internal/cipher.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/xts.h>
+#include <linux/module.h>
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("ecb(aes)");
+MODULE_ALIAS_CRYPTO("cbc(aes)-all");
+MODULE_ALIAS_CRYPTO("ctr(aes)");
+MODULE_ALIAS_CRYPTO("xts(aes)");
+
+MODULE_IMPORT_NS(CRYPTO_INTERNAL);
+
+asmlinkage void aesbs_convert_key(u8 out[], u32 const rk[], int rounds);
+
+asmlinkage void aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks);
+asmlinkage void aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks);
+
+asmlinkage void aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[]);
+
+asmlinkage void aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 ctr[]);
+
+asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[], int);
+asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[], int);
+
+struct aesbs_ctx {
+ int rounds;
+ u8 rk[13 * (8 * AES_BLOCK_SIZE) + 32] __aligned(AES_BLOCK_SIZE);
+};
+
+struct aesbs_cbc_ctx {
+ struct aesbs_ctx key;
+ struct crypto_skcipher *enc_tfm;
+};
+
+struct aesbs_xts_ctx {
+ struct aesbs_ctx key;
+ struct crypto_cipher *cts_tfm;
+ struct crypto_cipher *tweak_tfm;
+};
+
+struct aesbs_ctr_ctx {
+ struct aesbs_ctx key; /* must be first member */
+ struct crypto_aes_ctx fallback;
+};
+
+static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct crypto_aes_ctx rk;
+ int err;
+
+ err = aes_expandkey(&rk, in_key, key_len);
+ if (err)
+ return err;
+
+ ctx->rounds = 6 + key_len / 4;
+
+ kernel_neon_begin();
+ aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int __ecb_crypt(struct skcipher_request *req,
+ void (*fn)(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks))
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+ if (walk.nbytes < walk.total)
+ blocks = round_down(blocks,
+ walk.stride / AES_BLOCK_SIZE);
+
+ kernel_neon_begin();
+ fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
+ ctx->rounds, blocks);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk,
+ walk.nbytes - blocks * AES_BLOCK_SIZE);
+ }
+
+ return err;
+}
+
+static int ecb_encrypt(struct skcipher_request *req)
+{
+ return __ecb_crypt(req, aesbs_ecb_encrypt);
+}
+
+static int ecb_decrypt(struct skcipher_request *req)
+{
+ return __ecb_crypt(req, aesbs_ecb_decrypt);
+}
+
+static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct crypto_aes_ctx rk;
+ int err;
+
+ err = aes_expandkey(&rk, in_key, key_len);
+ if (err)
+ return err;
+
+ ctx->key.rounds = 6 + key_len / 4;
+
+ kernel_neon_begin();
+ aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
+ kernel_neon_end();
+ memzero_explicit(&rk, sizeof(rk));
+
+ return crypto_skcipher_setkey(ctx->enc_tfm, in_key, key_len);
+}
+
+static int cbc_encrypt(struct skcipher_request *req)
+{
+ struct skcipher_request *subreq = skcipher_request_ctx(req);
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ skcipher_request_set_tfm(subreq, ctx->enc_tfm);
+ skcipher_request_set_callback(subreq,
+ skcipher_request_flags(req),
+ NULL, NULL);
+ skcipher_request_set_crypt(subreq, req->src, req->dst,
+ req->cryptlen, req->iv);
+
+ return crypto_skcipher_encrypt(subreq);
+}
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+ if (walk.nbytes < walk.total)
+ blocks = round_down(blocks,
+ walk.stride / AES_BLOCK_SIZE);
+
+ kernel_neon_begin();
+ aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key.rk, ctx->key.rounds, blocks,
+ walk.iv);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk,
+ walk.nbytes - blocks * AES_BLOCK_SIZE);
+ }
+
+ return err;
+}
+
+static int cbc_init(struct crypto_skcipher *tfm)
+{
+ struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+ unsigned int reqsize;
+
+ ctx->enc_tfm = crypto_alloc_skcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC |
+ CRYPTO_ALG_NEED_FALLBACK);
+ if (IS_ERR(ctx->enc_tfm))
+ return PTR_ERR(ctx->enc_tfm);
+
+ reqsize = sizeof(struct skcipher_request);
+ reqsize += crypto_skcipher_reqsize(ctx->enc_tfm);
+ crypto_skcipher_set_reqsize(tfm, reqsize);
+
+ return 0;
+}
+
+static void cbc_exit(struct crypto_skcipher *tfm)
+{
+ struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ crypto_free_skcipher(ctx->enc_tfm);
+}
+
+static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int err;
+
+ err = aes_expandkey(&ctx->fallback, in_key, key_len);
+ if (err)
+ return err;
+
+ ctx->key.rounds = 6 + key_len / 4;
+
+ kernel_neon_begin();
+ aesbs_convert_key(ctx->key.rk, ctx->fallback.key_enc, ctx->key.rounds);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int ctr_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct skcipher_walk walk;
+ u8 buf[AES_BLOCK_SIZE];
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while (walk.nbytes > 0) {
+ const u8 *src = walk.src.virt.addr;
+ u8 *dst = walk.dst.virt.addr;
+ int bytes = walk.nbytes;
+
+ if (unlikely(bytes < AES_BLOCK_SIZE))
+ src = dst = memcpy(buf + sizeof(buf) - bytes,
+ src, bytes);
+ else if (walk.nbytes < walk.total)
+ bytes &= ~(8 * AES_BLOCK_SIZE - 1);
+
+ kernel_neon_begin();
+ aesbs_ctr_encrypt(dst, src, ctx->rk, ctx->rounds, bytes, walk.iv);
+ kernel_neon_end();
+
+ if (unlikely(bytes < AES_BLOCK_SIZE))
+ memcpy(walk.dst.virt.addr,
+ buf + sizeof(buf) - bytes, bytes);
+
+ err = skcipher_walk_done(&walk, walk.nbytes - bytes);
+ }
+
+ return err;
+}
+
+static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+{
+ struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+ unsigned long flags;
+
+ /*
+ * Temporarily disable interrupts to avoid races where
+ * cachelines are evicted when the CPU is interrupted
+ * to do something else.
+ */
+ local_irq_save(flags);
+ aes_encrypt(&ctx->fallback, dst, src);
+ local_irq_restore(flags);
+}
+
+static int ctr_encrypt_sync(struct skcipher_request *req)
+{
+ if (!crypto_simd_usable())
+ return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
+
+ return ctr_encrypt(req);
+}
+
+static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int err;
+
+ err = xts_verify_key(tfm, in_key, key_len);
+ if (err)
+ return err;
+
+ key_len /= 2;
+ err = crypto_cipher_setkey(ctx->cts_tfm, in_key, key_len);
+ if (err)
+ return err;
+ err = crypto_cipher_setkey(ctx->tweak_tfm, in_key + key_len, key_len);
+ if (err)
+ return err;
+
+ return aesbs_setkey(tfm, in_key, key_len);
+}
+
+static int xts_init(struct crypto_skcipher *tfm)
+{
+ struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ ctx->cts_tfm = crypto_alloc_cipher("aes", 0, 0);
+ if (IS_ERR(ctx->cts_tfm))
+ return PTR_ERR(ctx->cts_tfm);
+
+ ctx->tweak_tfm = crypto_alloc_cipher("aes", 0, 0);
+ if (IS_ERR(ctx->tweak_tfm))
+ crypto_free_cipher(ctx->cts_tfm);
+
+ return PTR_ERR_OR_ZERO(ctx->tweak_tfm);
+}
+
+static void xts_exit(struct crypto_skcipher *tfm)
+{
+ struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ crypto_free_cipher(ctx->tweak_tfm);
+ crypto_free_cipher(ctx->cts_tfm);
+}
+
+static int __xts_crypt(struct skcipher_request *req, bool encrypt,
+ void (*fn)(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[], int))
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int tail = req->cryptlen % AES_BLOCK_SIZE;
+ struct skcipher_request subreq;
+ u8 buf[2 * AES_BLOCK_SIZE];
+ struct skcipher_walk walk;
+ int err;
+
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+
+ if (unlikely(tail)) {
+ skcipher_request_set_tfm(&subreq, tfm);
+ skcipher_request_set_callback(&subreq,
+ skcipher_request_flags(req),
+ NULL, NULL);
+ skcipher_request_set_crypt(&subreq, req->src, req->dst,
+ req->cryptlen - tail, req->iv);
+ req = &subreq;
+ }
+
+ err = skcipher_walk_virt(&walk, req, true);
+ if (err)
+ return err;
+
+ crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+ int reorder_last_tweak = !encrypt && tail > 0;
+
+ if (walk.nbytes < walk.total) {
+ blocks = round_down(blocks,
+ walk.stride / AES_BLOCK_SIZE);
+ reorder_last_tweak = 0;
+ }
+
+ kernel_neon_begin();
+ fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk,
+ ctx->key.rounds, blocks, walk.iv, reorder_last_tweak);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk,
+ walk.nbytes - blocks * AES_BLOCK_SIZE);
+ }
+
+ if (err || likely(!tail))
+ return err;
+
+ /* handle ciphertext stealing */
+ scatterwalk_map_and_copy(buf, req->dst, req->cryptlen - AES_BLOCK_SIZE,
+ AES_BLOCK_SIZE, 0);
+ memcpy(buf + AES_BLOCK_SIZE, buf, tail);
+ scatterwalk_map_and_copy(buf, req->src, req->cryptlen, tail, 0);
+
+ crypto_xor(buf, req->iv, AES_BLOCK_SIZE);
+
+ if (encrypt)
+ crypto_cipher_encrypt_one(ctx->cts_tfm, buf, buf);
+ else
+ crypto_cipher_decrypt_one(ctx->cts_tfm, buf, buf);
+
+ crypto_xor(buf, req->iv, AES_BLOCK_SIZE);
+
+ scatterwalk_map_and_copy(buf, req->dst, req->cryptlen - AES_BLOCK_SIZE,
+ AES_BLOCK_SIZE + tail, 1);
+ return 0;
+}
+
+static int xts_encrypt(struct skcipher_request *req)
+{
+ return __xts_crypt(req, true, aesbs_xts_encrypt);
+}
+
+static int xts_decrypt(struct skcipher_request *req)
+{
+ return __xts_crypt(req, false, aesbs_xts_decrypt);
+}
+
+static struct skcipher_alg aes_algs[] = { {
+ .base.cra_name = "__ecb(aes)",
+ .base.cra_driver_name = "__ecb-aes-neonbs",
+ .base.cra_priority = 250,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct aesbs_ctx),
+ .base.cra_module = THIS_MODULE,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .walksize = 8 * AES_BLOCK_SIZE,
+ .setkey = aesbs_setkey,
+ .encrypt = ecb_encrypt,
+ .decrypt = ecb_decrypt,
+}, {
+ .base.cra_name = "__cbc(aes)",
+ .base.cra_driver_name = "__cbc-aes-neonbs",
+ .base.cra_priority = 250,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct aesbs_cbc_ctx),
+ .base.cra_module = THIS_MODULE,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL |
+ CRYPTO_ALG_NEED_FALLBACK,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .walksize = 8 * AES_BLOCK_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aesbs_cbc_setkey,
+ .encrypt = cbc_encrypt,
+ .decrypt = cbc_decrypt,
+ .init = cbc_init,
+ .exit = cbc_exit,
+}, {
+ .base.cra_name = "__ctr(aes)",
+ .base.cra_driver_name = "__ctr-aes-neonbs",
+ .base.cra_priority = 250,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct aesbs_ctx),
+ .base.cra_module = THIS_MODULE,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+ .walksize = 8 * AES_BLOCK_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aesbs_setkey,
+ .encrypt = ctr_encrypt,
+ .decrypt = ctr_encrypt,
+}, {
+ .base.cra_name = "ctr(aes)",
+ .base.cra_driver_name = "ctr-aes-neonbs-sync",
+ .base.cra_priority = 250 - 1,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct aesbs_ctr_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+ .walksize = 8 * AES_BLOCK_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aesbs_ctr_setkey_sync,
+ .encrypt = ctr_encrypt_sync,
+ .decrypt = ctr_encrypt_sync,
+}, {
+ .base.cra_name = "__xts(aes)",
+ .base.cra_driver_name = "__xts-aes-neonbs",
+ .base.cra_priority = 250,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct aesbs_xts_ctx),
+ .base.cra_module = THIS_MODULE,
+ .base.cra_flags = CRYPTO_ALG_INTERNAL,
+
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .walksize = 8 * AES_BLOCK_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = aesbs_xts_setkey,
+ .encrypt = xts_encrypt,
+ .decrypt = xts_decrypt,
+ .init = xts_init,
+ .exit = xts_exit,
+} };
+
+static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
+
+static void aes_exit(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(aes_simd_algs); i++)
+ if (aes_simd_algs[i])
+ simd_skcipher_free(aes_simd_algs[i]);
+
+ crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static int __init aes_init(void)
+{
+ struct simd_skcipher_alg *simd;
+ const char *basename;
+ const char *algname;
+ const char *drvname;
+ int err;
+ int i;
+
+ if (!(elf_hwcap & HWCAP_NEON))
+ return -ENODEV;
+
+ err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+ if (err)
+ return err;
+
+ for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+ if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
+ continue;
+
+ algname = aes_algs[i].base.cra_name + 2;
+ drvname = aes_algs[i].base.cra_driver_name + 2;
+ basename = aes_algs[i].base.cra_driver_name;
+ simd = simd_skcipher_create_compat(algname, drvname, basename);
+ err = PTR_ERR(simd);
+ if (IS_ERR(simd))
+ goto unregister_simds;
+
+ aes_simd_algs[i] = simd;
+ }
+ return 0;
+
+unregister_simds:
+ aes_exit();
+ return err;
+}
+
+late_initcall(aes_init);
+module_exit(aes_exit);
diff --git a/arch/arm/crypto/blake2b-neon-core.S b/arch/arm/crypto/blake2b-neon-core.S
new file mode 100644
index 0000000000..0406a18637
--- /dev/null
+++ b/arch/arm/crypto/blake2b-neon-core.S
@@ -0,0 +1,347 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * BLAKE2b digest algorithm, NEON accelerated
+ *
+ * Copyright 2020 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+ .text
+ .fpu neon
+
+ // The arguments to blake2b_compress_neon()
+ STATE .req r0
+ BLOCK .req r1
+ NBLOCKS .req r2
+ INC .req r3
+
+ // Pointers to the rotation tables
+ ROR24_TABLE .req r4
+ ROR16_TABLE .req r5
+
+ // The original stack pointer
+ ORIG_SP .req r6
+
+ // NEON registers which contain the message words of the current block.
+ // M_0-M_3 are occasionally used for other purposes too.
+ M_0 .req d16
+ M_1 .req d17
+ M_2 .req d18
+ M_3 .req d19
+ M_4 .req d20
+ M_5 .req d21
+ M_6 .req d22
+ M_7 .req d23
+ M_8 .req d24
+ M_9 .req d25
+ M_10 .req d26
+ M_11 .req d27
+ M_12 .req d28
+ M_13 .req d29
+ M_14 .req d30
+ M_15 .req d31
+
+ .align 4
+ // Tables for computing ror64(x, 24) and ror64(x, 16) using the vtbl.8
+ // instruction. This is the most efficient way to implement these
+ // rotation amounts with NEON. (On Cortex-A53 it's the same speed as
+ // vshr.u64 + vsli.u64, while on Cortex-A7 it's faster.)
+.Lror24_table:
+ .byte 3, 4, 5, 6, 7, 0, 1, 2
+.Lror16_table:
+ .byte 2, 3, 4, 5, 6, 7, 0, 1
+ // The BLAKE2b initialization vector
+.Lblake2b_IV:
+ .quad 0x6a09e667f3bcc908, 0xbb67ae8584caa73b
+ .quad 0x3c6ef372fe94f82b, 0xa54ff53a5f1d36f1
+ .quad 0x510e527fade682d1, 0x9b05688c2b3e6c1f
+ .quad 0x1f83d9abfb41bd6b, 0x5be0cd19137e2179
+
+// Execute one round of BLAKE2b by updating the state matrix v[0..15] in the
+// NEON registers q0-q7. The message block is in q8..q15 (M_0-M_15). The stack
+// pointer points to a 32-byte aligned buffer containing a copy of q8 and q9
+// (M_0-M_3), so that they can be reloaded if they are used as temporary
+// registers. The macro arguments s0-s15 give the order in which the message
+// words are used in this round. 'final' is 1 if this is the final round.
+.macro _blake2b_round s0, s1, s2, s3, s4, s5, s6, s7, \
+ s8, s9, s10, s11, s12, s13, s14, s15, final=0
+
+ // Mix the columns:
+ // (v[0], v[4], v[8], v[12]), (v[1], v[5], v[9], v[13]),
+ // (v[2], v[6], v[10], v[14]), and (v[3], v[7], v[11], v[15]).
+
+ // a += b + m[blake2b_sigma[r][2*i + 0]];
+ vadd.u64 q0, q0, q2
+ vadd.u64 q1, q1, q3
+ vadd.u64 d0, d0, M_\s0
+ vadd.u64 d1, d1, M_\s2
+ vadd.u64 d2, d2, M_\s4
+ vadd.u64 d3, d3, M_\s6
+
+ // d = ror64(d ^ a, 32);
+ veor q6, q6, q0
+ veor q7, q7, q1
+ vrev64.32 q6, q6
+ vrev64.32 q7, q7
+
+ // c += d;
+ vadd.u64 q4, q4, q6
+ vadd.u64 q5, q5, q7
+
+ // b = ror64(b ^ c, 24);
+ vld1.8 {M_0}, [ROR24_TABLE, :64]
+ veor q2, q2, q4
+ veor q3, q3, q5
+ vtbl.8 d4, {d4}, M_0
+ vtbl.8 d5, {d5}, M_0
+ vtbl.8 d6, {d6}, M_0
+ vtbl.8 d7, {d7}, M_0
+
+ // a += b + m[blake2b_sigma[r][2*i + 1]];
+ //
+ // M_0 got clobbered above, so we have to reload it if any of the four
+ // message words this step needs happens to be M_0. Otherwise we don't
+ // need to reload it here, as it will just get clobbered again below.
+.if \s1 == 0 || \s3 == 0 || \s5 == 0 || \s7 == 0
+ vld1.8 {M_0}, [sp, :64]
+.endif
+ vadd.u64 q0, q0, q2
+ vadd.u64 q1, q1, q3
+ vadd.u64 d0, d0, M_\s1
+ vadd.u64 d1, d1, M_\s3
+ vadd.u64 d2, d2, M_\s5
+ vadd.u64 d3, d3, M_\s7
+
+ // d = ror64(d ^ a, 16);
+ vld1.8 {M_0}, [ROR16_TABLE, :64]
+ veor q6, q6, q0
+ veor q7, q7, q1
+ vtbl.8 d12, {d12}, M_0
+ vtbl.8 d13, {d13}, M_0
+ vtbl.8 d14, {d14}, M_0
+ vtbl.8 d15, {d15}, M_0
+
+ // c += d;
+ vadd.u64 q4, q4, q6
+ vadd.u64 q5, q5, q7
+
+ // b = ror64(b ^ c, 63);
+ //
+ // This rotation amount isn't a multiple of 8, so it has to be
+ // implemented using a pair of shifts, which requires temporary
+ // registers. Use q8-q9 (M_0-M_3) for this, and reload them afterwards.
+ veor q8, q2, q4
+ veor q9, q3, q5
+ vshr.u64 q2, q8, #63
+ vshr.u64 q3, q9, #63
+ vsli.u64 q2, q8, #1
+ vsli.u64 q3, q9, #1
+ vld1.8 {q8-q9}, [sp, :256]
+
+ // Mix the diagonals:
+ // (v[0], v[5], v[10], v[15]), (v[1], v[6], v[11], v[12]),
+ // (v[2], v[7], v[8], v[13]), and (v[3], v[4], v[9], v[14]).
+ //
+ // There are two possible ways to do this: use 'vext' instructions to
+ // shift the rows of the matrix so that the diagonals become columns,
+ // and undo it afterwards; or just use 64-bit operations on 'd'
+ // registers instead of 128-bit operations on 'q' registers. We use the
+ // latter approach, as it performs much better on Cortex-A7.
+
+ // a += b + m[blake2b_sigma[r][2*i + 0]];
+ vadd.u64 d0, d0, d5
+ vadd.u64 d1, d1, d6
+ vadd.u64 d2, d2, d7
+ vadd.u64 d3, d3, d4
+ vadd.u64 d0, d0, M_\s8
+ vadd.u64 d1, d1, M_\s10
+ vadd.u64 d2, d2, M_\s12
+ vadd.u64 d3, d3, M_\s14
+
+ // d = ror64(d ^ a, 32);
+ veor d15, d15, d0
+ veor d12, d12, d1
+ veor d13, d13, d2
+ veor d14, d14, d3
+ vrev64.32 d15, d15
+ vrev64.32 d12, d12
+ vrev64.32 d13, d13
+ vrev64.32 d14, d14
+
+ // c += d;
+ vadd.u64 d10, d10, d15
+ vadd.u64 d11, d11, d12
+ vadd.u64 d8, d8, d13
+ vadd.u64 d9, d9, d14
+
+ // b = ror64(b ^ c, 24);
+ vld1.8 {M_0}, [ROR24_TABLE, :64]
+ veor d5, d5, d10
+ veor d6, d6, d11
+ veor d7, d7, d8
+ veor d4, d4, d9
+ vtbl.8 d5, {d5}, M_0
+ vtbl.8 d6, {d6}, M_0
+ vtbl.8 d7, {d7}, M_0
+ vtbl.8 d4, {d4}, M_0
+
+ // a += b + m[blake2b_sigma[r][2*i + 1]];
+.if \s9 == 0 || \s11 == 0 || \s13 == 0 || \s15 == 0
+ vld1.8 {M_0}, [sp, :64]
+.endif
+ vadd.u64 d0, d0, d5
+ vadd.u64 d1, d1, d6
+ vadd.u64 d2, d2, d7
+ vadd.u64 d3, d3, d4
+ vadd.u64 d0, d0, M_\s9
+ vadd.u64 d1, d1, M_\s11
+ vadd.u64 d2, d2, M_\s13
+ vadd.u64 d3, d3, M_\s15
+
+ // d = ror64(d ^ a, 16);
+ vld1.8 {M_0}, [ROR16_TABLE, :64]
+ veor d15, d15, d0
+ veor d12, d12, d1
+ veor d13, d13, d2
+ veor d14, d14, d3
+ vtbl.8 d12, {d12}, M_0
+ vtbl.8 d13, {d13}, M_0
+ vtbl.8 d14, {d14}, M_0
+ vtbl.8 d15, {d15}, M_0
+
+ // c += d;
+ vadd.u64 d10, d10, d15
+ vadd.u64 d11, d11, d12
+ vadd.u64 d8, d8, d13
+ vadd.u64 d9, d9, d14
+
+ // b = ror64(b ^ c, 63);
+ veor d16, d4, d9
+ veor d17, d5, d10
+ veor d18, d6, d11
+ veor d19, d7, d8
+ vshr.u64 q2, q8, #63
+ vshr.u64 q3, q9, #63
+ vsli.u64 q2, q8, #1
+ vsli.u64 q3, q9, #1
+ // Reloading q8-q9 can be skipped on the final round.
+.if ! \final
+ vld1.8 {q8-q9}, [sp, :256]
+.endif
+.endm
+
+//
+// void blake2b_compress_neon(struct blake2b_state *state,
+// const u8 *block, size_t nblocks, u32 inc);
+//
+// Only the first three fields of struct blake2b_state are used:
+// u64 h[8]; (inout)
+// u64 t[2]; (inout)
+// u64 f[2]; (in)
+//
+ .align 5
+ENTRY(blake2b_compress_neon)
+ push {r4-r10}
+
+ // Allocate a 32-byte stack buffer that is 32-byte aligned.
+ mov ORIG_SP, sp
+ sub ip, sp, #32
+ bic ip, ip, #31
+ mov sp, ip
+
+ adr ROR24_TABLE, .Lror24_table
+ adr ROR16_TABLE, .Lror16_table
+
+ mov ip, STATE
+ vld1.64 {q0-q1}, [ip]! // Load h[0..3]
+ vld1.64 {q2-q3}, [ip]! // Load h[4..7]
+.Lnext_block:
+ adr r10, .Lblake2b_IV
+ vld1.64 {q14-q15}, [ip] // Load t[0..1] and f[0..1]
+ vld1.64 {q4-q5}, [r10]! // Load IV[0..3]
+ vmov r7, r8, d28 // Copy t[0] to (r7, r8)
+ vld1.64 {q6-q7}, [r10] // Load IV[4..7]
+ adds r7, r7, INC // Increment counter
+ bcs .Lslow_inc_ctr
+ vmov.i32 d28[0], r7
+ vst1.64 {d28}, [ip] // Update t[0]
+.Linc_ctr_done:
+
+ // Load the next message block and finish initializing the state matrix
+ // 'v'. Fortunately, there are exactly enough NEON registers to fit the
+ // entire state matrix in q0-q7 and the entire message block in q8-15.
+ //
+ // However, _blake2b_round also needs some extra registers for rotates,
+ // so we have to spill some registers. It's better to spill the message
+ // registers than the state registers, as the message doesn't change.
+ // Therefore we store a copy of the first 32 bytes of the message block
+ // (q8-q9) in an aligned buffer on the stack so that they can be
+ // reloaded when needed. (We could just reload directly from the
+ // message buffer, but it's faster to use aligned loads.)
+ vld1.8 {q8-q9}, [BLOCK]!
+ veor q6, q6, q14 // v[12..13] = IV[4..5] ^ t[0..1]
+ vld1.8 {q10-q11}, [BLOCK]!
+ veor q7, q7, q15 // v[14..15] = IV[6..7] ^ f[0..1]
+ vld1.8 {q12-q13}, [BLOCK]!
+ vst1.8 {q8-q9}, [sp, :256]
+ mov ip, STATE
+ vld1.8 {q14-q15}, [BLOCK]!
+
+ // Execute the rounds. Each round is provided the order in which it
+ // needs to use the message words.
+ _blake2b_round 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+ _blake2b_round 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3
+ _blake2b_round 11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4
+ _blake2b_round 7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8
+ _blake2b_round 9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13
+ _blake2b_round 2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9
+ _blake2b_round 12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11
+ _blake2b_round 13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10
+ _blake2b_round 6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5
+ _blake2b_round 10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0
+ _blake2b_round 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+ _blake2b_round 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3 \
+ final=1
+
+ // Fold the final state matrix into the hash chaining value:
+ //
+ // for (i = 0; i < 8; i++)
+ // h[i] ^= v[i] ^ v[i + 8];
+ //
+ vld1.64 {q8-q9}, [ip]! // Load old h[0..3]
+ veor q0, q0, q4 // v[0..1] ^= v[8..9]
+ veor q1, q1, q5 // v[2..3] ^= v[10..11]
+ vld1.64 {q10-q11}, [ip] // Load old h[4..7]
+ veor q2, q2, q6 // v[4..5] ^= v[12..13]
+ veor q3, q3, q7 // v[6..7] ^= v[14..15]
+ veor q0, q0, q8 // v[0..1] ^= h[0..1]
+ veor q1, q1, q9 // v[2..3] ^= h[2..3]
+ mov ip, STATE
+ subs NBLOCKS, NBLOCKS, #1 // nblocks--
+ vst1.64 {q0-q1}, [ip]! // Store new h[0..3]
+ veor q2, q2, q10 // v[4..5] ^= h[4..5]
+ veor q3, q3, q11 // v[6..7] ^= h[6..7]
+ vst1.64 {q2-q3}, [ip]! // Store new h[4..7]
+
+ // Advance to the next block, if there is one.
+ bne .Lnext_block // nblocks != 0?
+
+ mov sp, ORIG_SP
+ pop {r4-r10}
+ mov pc, lr
+
+.Lslow_inc_ctr:
+ // Handle the case where the counter overflowed its low 32 bits, by
+ // carrying the overflow bit into the full 128-bit counter.
+ vmov r9, r10, d29
+ adcs r8, r8, #0
+ adcs r9, r9, #0
+ adc r10, r10, #0
+ vmov d28, r7, r8
+ vmov d29, r9, r10
+ vst1.64 {q14}, [ip] // Update t[0] and t[1]
+ b .Linc_ctr_done
+ENDPROC(blake2b_compress_neon)
diff --git a/arch/arm/crypto/blake2b-neon-glue.c b/arch/arm/crypto/blake2b-neon-glue.c
new file mode 100644
index 0000000000..4b59d027ba
--- /dev/null
+++ b/arch/arm/crypto/blake2b-neon-glue.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * BLAKE2b digest algorithm, NEON accelerated
+ *
+ * Copyright 2020 Google LLC
+ */
+
+#include <crypto/internal/blake2b.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+
+#include <linux/module.h>
+#include <linux/sizes.h>
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void blake2b_compress_neon(struct blake2b_state *state,
+ const u8 *block, size_t nblocks, u32 inc);
+
+static void blake2b_compress_arch(struct blake2b_state *state,
+ const u8 *block, size_t nblocks, u32 inc)
+{
+ if (!crypto_simd_usable()) {
+ blake2b_compress_generic(state, block, nblocks, inc);
+ return;
+ }
+
+ do {
+ const size_t blocks = min_t(size_t, nblocks,
+ SZ_4K / BLAKE2B_BLOCK_SIZE);
+
+ kernel_neon_begin();
+ blake2b_compress_neon(state, block, blocks, inc);
+ kernel_neon_end();
+
+ nblocks -= blocks;
+ block += blocks * BLAKE2B_BLOCK_SIZE;
+ } while (nblocks);
+}
+
+static int crypto_blake2b_update_neon(struct shash_desc *desc,
+ const u8 *in, unsigned int inlen)
+{
+ return crypto_blake2b_update(desc, in, inlen, blake2b_compress_arch);
+}
+
+static int crypto_blake2b_final_neon(struct shash_desc *desc, u8 *out)
+{
+ return crypto_blake2b_final(desc, out, blake2b_compress_arch);
+}
+
+#define BLAKE2B_ALG(name, driver_name, digest_size) \
+ { \
+ .base.cra_name = name, \
+ .base.cra_driver_name = driver_name, \
+ .base.cra_priority = 200, \
+ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY, \
+ .base.cra_blocksize = BLAKE2B_BLOCK_SIZE, \
+ .base.cra_ctxsize = sizeof(struct blake2b_tfm_ctx), \
+ .base.cra_module = THIS_MODULE, \
+ .digestsize = digest_size, \
+ .setkey = crypto_blake2b_setkey, \
+ .init = crypto_blake2b_init, \
+ .update = crypto_blake2b_update_neon, \
+ .final = crypto_blake2b_final_neon, \
+ .descsize = sizeof(struct blake2b_state), \
+ }
+
+static struct shash_alg blake2b_neon_algs[] = {
+ BLAKE2B_ALG("blake2b-160", "blake2b-160-neon", BLAKE2B_160_HASH_SIZE),
+ BLAKE2B_ALG("blake2b-256", "blake2b-256-neon", BLAKE2B_256_HASH_SIZE),
+ BLAKE2B_ALG("blake2b-384", "blake2b-384-neon", BLAKE2B_384_HASH_SIZE),
+ BLAKE2B_ALG("blake2b-512", "blake2b-512-neon", BLAKE2B_512_HASH_SIZE),
+};
+
+static int __init blake2b_neon_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_NEON))
+ return -ENODEV;
+
+ return crypto_register_shashes(blake2b_neon_algs,
+ ARRAY_SIZE(blake2b_neon_algs));
+}
+
+static void __exit blake2b_neon_mod_exit(void)
+{
+ crypto_unregister_shashes(blake2b_neon_algs,
+ ARRAY_SIZE(blake2b_neon_algs));
+}
+
+module_init(blake2b_neon_mod_init);
+module_exit(blake2b_neon_mod_exit);
+
+MODULE_DESCRIPTION("BLAKE2b digest algorithm, NEON accelerated");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("blake2b-160");
+MODULE_ALIAS_CRYPTO("blake2b-160-neon");
+MODULE_ALIAS_CRYPTO("blake2b-256");
+MODULE_ALIAS_CRYPTO("blake2b-256-neon");
+MODULE_ALIAS_CRYPTO("blake2b-384");
+MODULE_ALIAS_CRYPTO("blake2b-384-neon");
+MODULE_ALIAS_CRYPTO("blake2b-512");
+MODULE_ALIAS_CRYPTO("blake2b-512-neon");
diff --git a/arch/arm/crypto/blake2s-core.S b/arch/arm/crypto/blake2s-core.S
new file mode 100644
index 0000000000..df40e46601
--- /dev/null
+++ b/arch/arm/crypto/blake2s-core.S
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * BLAKE2s digest algorithm, ARM scalar implementation
+ *
+ * Copyright 2020 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ // Registers used to hold message words temporarily. There aren't
+ // enough ARM registers to hold the whole message block, so we have to
+ // load the words on-demand.
+ M_0 .req r12
+ M_1 .req r14
+
+// The BLAKE2s initialization vector
+.Lblake2s_IV:
+ .word 0x6A09E667, 0xBB67AE85, 0x3C6EF372, 0xA54FF53A
+ .word 0x510E527F, 0x9B05688C, 0x1F83D9AB, 0x5BE0CD19
+
+.macro __ldrd a, b, src, offset
+#if __LINUX_ARM_ARCH__ >= 6
+ ldrd \a, \b, [\src, #\offset]
+#else
+ ldr \a, [\src, #\offset]
+ ldr \b, [\src, #\offset + 4]
+#endif
+.endm
+
+.macro __strd a, b, dst, offset
+#if __LINUX_ARM_ARCH__ >= 6
+ strd \a, \b, [\dst, #\offset]
+#else
+ str \a, [\dst, #\offset]
+ str \b, [\dst, #\offset + 4]
+#endif
+.endm
+
+.macro _le32_bswap a, tmp
+#ifdef __ARMEB__
+ rev_l \a, \tmp
+#endif
+.endm
+
+.macro _le32_bswap_8x a, b, c, d, e, f, g, h, tmp
+ _le32_bswap \a, \tmp
+ _le32_bswap \b, \tmp
+ _le32_bswap \c, \tmp
+ _le32_bswap \d, \tmp
+ _le32_bswap \e, \tmp
+ _le32_bswap \f, \tmp
+ _le32_bswap \g, \tmp
+ _le32_bswap \h, \tmp
+.endm
+
+// Execute a quarter-round of BLAKE2s by mixing two columns or two diagonals.
+// (a0, b0, c0, d0) and (a1, b1, c1, d1) give the registers containing the two
+// columns/diagonals. s0-s1 are the word offsets to the message words the first
+// column/diagonal needs, and likewise s2-s3 for the second column/diagonal.
+// M_0 and M_1 are free to use, and the message block can be found at sp + 32.
+//
+// Note that to save instructions, the rotations don't happen when the
+// pseudocode says they should, but rather they are delayed until the values are
+// used. See the comment above _blake2s_round().
+.macro _blake2s_quarterround a0, b0, c0, d0, a1, b1, c1, d1, s0, s1, s2, s3
+
+ ldr M_0, [sp, #32 + 4 * \s0]
+ ldr M_1, [sp, #32 + 4 * \s2]
+
+ // a += b + m[blake2s_sigma[r][2*i + 0]];
+ add \a0, \a0, \b0, ror #brot
+ add \a1, \a1, \b1, ror #brot
+ add \a0, \a0, M_0
+ add \a1, \a1, M_1
+
+ // d = ror32(d ^ a, 16);
+ eor \d0, \a0, \d0, ror #drot
+ eor \d1, \a1, \d1, ror #drot
+
+ // c += d;
+ add \c0, \c0, \d0, ror #16
+ add \c1, \c1, \d1, ror #16
+
+ // b = ror32(b ^ c, 12);
+ eor \b0, \c0, \b0, ror #brot
+ eor \b1, \c1, \b1, ror #brot
+
+ ldr M_0, [sp, #32 + 4 * \s1]
+ ldr M_1, [sp, #32 + 4 * \s3]
+
+ // a += b + m[blake2s_sigma[r][2*i + 1]];
+ add \a0, \a0, \b0, ror #12
+ add \a1, \a1, \b1, ror #12
+ add \a0, \a0, M_0
+ add \a1, \a1, M_1
+
+ // d = ror32(d ^ a, 8);
+ eor \d0, \a0, \d0, ror#16
+ eor \d1, \a1, \d1, ror#16
+
+ // c += d;
+ add \c0, \c0, \d0, ror#8
+ add \c1, \c1, \d1, ror#8
+
+ // b = ror32(b ^ c, 7);
+ eor \b0, \c0, \b0, ror#12
+ eor \b1, \c1, \b1, ror#12
+.endm
+
+// Execute one round of BLAKE2s by updating the state matrix v[0..15]. v[0..9]
+// are in r0..r9. The stack pointer points to 8 bytes of scratch space for
+// spilling v[8..9], then to v[9..15], then to the message block. r10-r12 and
+// r14 are free to use. The macro arguments s0-s15 give the order in which the
+// message words are used in this round.
+//
+// All rotates are performed using the implicit rotate operand accepted by the
+// 'add' and 'eor' instructions. This is faster than using explicit rotate
+// instructions. To make this work, we allow the values in the second and last
+// rows of the BLAKE2s state matrix (rows 'b' and 'd') to temporarily have the
+// wrong rotation amount. The rotation amount is then fixed up just in time
+// when the values are used. 'brot' is the number of bits the values in row 'b'
+// need to be rotated right to arrive at the correct values, and 'drot'
+// similarly for row 'd'. (brot, drot) start out as (0, 0) but we make it such
+// that they end up as (7, 8) after every round.
+.macro _blake2s_round s0, s1, s2, s3, s4, s5, s6, s7, \
+ s8, s9, s10, s11, s12, s13, s14, s15
+
+ // Mix first two columns:
+ // (v[0], v[4], v[8], v[12]) and (v[1], v[5], v[9], v[13]).
+ __ldrd r10, r11, sp, 16 // load v[12] and v[13]
+ _blake2s_quarterround r0, r4, r8, r10, r1, r5, r9, r11, \
+ \s0, \s1, \s2, \s3
+ __strd r8, r9, sp, 0
+ __strd r10, r11, sp, 16
+
+ // Mix second two columns:
+ // (v[2], v[6], v[10], v[14]) and (v[3], v[7], v[11], v[15]).
+ __ldrd r8, r9, sp, 8 // load v[10] and v[11]
+ __ldrd r10, r11, sp, 24 // load v[14] and v[15]
+ _blake2s_quarterround r2, r6, r8, r10, r3, r7, r9, r11, \
+ \s4, \s5, \s6, \s7
+ str r10, [sp, #24] // store v[14]
+ // v[10], v[11], and v[15] are used below, so no need to store them yet.
+
+ .set brot, 7
+ .set drot, 8
+
+ // Mix first two diagonals:
+ // (v[0], v[5], v[10], v[15]) and (v[1], v[6], v[11], v[12]).
+ ldr r10, [sp, #16] // load v[12]
+ _blake2s_quarterround r0, r5, r8, r11, r1, r6, r9, r10, \
+ \s8, \s9, \s10, \s11
+ __strd r8, r9, sp, 8
+ str r11, [sp, #28]
+ str r10, [sp, #16]
+
+ // Mix second two diagonals:
+ // (v[2], v[7], v[8], v[13]) and (v[3], v[4], v[9], v[14]).
+ __ldrd r8, r9, sp, 0 // load v[8] and v[9]
+ __ldrd r10, r11, sp, 20 // load v[13] and v[14]
+ _blake2s_quarterround r2, r7, r8, r10, r3, r4, r9, r11, \
+ \s12, \s13, \s14, \s15
+ __strd r10, r11, sp, 20
+.endm
+
+//
+// void blake2s_compress(struct blake2s_state *state,
+// const u8 *block, size_t nblocks, u32 inc);
+//
+// Only the first three fields of struct blake2s_state are used:
+// u32 h[8]; (inout)
+// u32 t[2]; (inout)
+// u32 f[2]; (in)
+//
+ .align 5
+ENTRY(blake2s_compress)
+ push {r0-r2,r4-r11,lr} // keep this an even number
+
+.Lnext_block:
+ // r0 is 'state'
+ // r1 is 'block'
+ // r3 is 'inc'
+
+ // Load and increment the counter t[0..1].
+ __ldrd r10, r11, r0, 32
+ adds r10, r10, r3
+ adc r11, r11, #0
+ __strd r10, r11, r0, 32
+
+ // _blake2s_round is very short on registers, so copy the message block
+ // to the stack to save a register during the rounds. This also has the
+ // advantage that misalignment only needs to be dealt with in one place.
+ sub sp, sp, #64
+ mov r12, sp
+ tst r1, #3
+ bne .Lcopy_block_misaligned
+ ldmia r1!, {r2-r9}
+ _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14
+ stmia r12!, {r2-r9}
+ ldmia r1!, {r2-r9}
+ _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14
+ stmia r12, {r2-r9}
+.Lcopy_block_done:
+ str r1, [sp, #68] // Update message pointer
+
+ // Calculate v[8..15]. Push v[9..15] onto the stack, and leave space
+ // for spilling v[8..9]. Leave v[8..9] in r8-r9.
+ mov r14, r0 // r14 = state
+ adr r12, .Lblake2s_IV
+ ldmia r12!, {r8-r9} // load IV[0..1]
+ __ldrd r0, r1, r14, 40 // load f[0..1]
+ ldm r12, {r2-r7} // load IV[3..7]
+ eor r4, r4, r10 // v[12] = IV[4] ^ t[0]
+ eor r5, r5, r11 // v[13] = IV[5] ^ t[1]
+ eor r6, r6, r0 // v[14] = IV[6] ^ f[0]
+ eor r7, r7, r1 // v[15] = IV[7] ^ f[1]
+ push {r2-r7} // push v[9..15]
+ sub sp, sp, #8 // leave space for v[8..9]
+
+ // Load h[0..7] == v[0..7].
+ ldm r14, {r0-r7}
+
+ // Execute the rounds. Each round is provided the order in which it
+ // needs to use the message words.
+ .set brot, 0
+ .set drot, 0
+ _blake2s_round 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+ _blake2s_round 14, 10, 4, 8, 9, 15, 13, 6, 1, 12, 0, 2, 11, 7, 5, 3
+ _blake2s_round 11, 8, 12, 0, 5, 2, 15, 13, 10, 14, 3, 6, 7, 1, 9, 4
+ _blake2s_round 7, 9, 3, 1, 13, 12, 11, 14, 2, 6, 5, 10, 4, 0, 15, 8
+ _blake2s_round 9, 0, 5, 7, 2, 4, 10, 15, 14, 1, 11, 12, 6, 8, 3, 13
+ _blake2s_round 2, 12, 6, 10, 0, 11, 8, 3, 4, 13, 7, 5, 15, 14, 1, 9
+ _blake2s_round 12, 5, 1, 15, 14, 13, 4, 10, 0, 7, 6, 3, 9, 2, 8, 11
+ _blake2s_round 13, 11, 7, 14, 12, 1, 3, 9, 5, 0, 15, 4, 8, 6, 2, 10
+ _blake2s_round 6, 15, 14, 9, 11, 3, 0, 8, 12, 2, 13, 7, 1, 4, 10, 5
+ _blake2s_round 10, 2, 8, 4, 7, 6, 1, 5, 15, 11, 9, 14, 3, 12, 13, 0
+
+ // Fold the final state matrix into the hash chaining value:
+ //
+ // for (i = 0; i < 8; i++)
+ // h[i] ^= v[i] ^ v[i + 8];
+ //
+ ldr r14, [sp, #96] // r14 = &h[0]
+ add sp, sp, #8 // v[8..9] are already loaded.
+ pop {r10-r11} // load v[10..11]
+ eor r0, r0, r8
+ eor r1, r1, r9
+ eor r2, r2, r10
+ eor r3, r3, r11
+ ldm r14, {r8-r11} // load h[0..3]
+ eor r0, r0, r8
+ eor r1, r1, r9
+ eor r2, r2, r10
+ eor r3, r3, r11
+ stmia r14!, {r0-r3} // store new h[0..3]
+ ldm r14, {r0-r3} // load old h[4..7]
+ pop {r8-r11} // load v[12..15]
+ eor r0, r0, r4, ror #brot
+ eor r1, r1, r5, ror #brot
+ eor r2, r2, r6, ror #brot
+ eor r3, r3, r7, ror #brot
+ eor r0, r0, r8, ror #drot
+ eor r1, r1, r9, ror #drot
+ eor r2, r2, r10, ror #drot
+ eor r3, r3, r11, ror #drot
+ add sp, sp, #64 // skip copy of message block
+ stm r14, {r0-r3} // store new h[4..7]
+
+ // Advance to the next block, if there is one. Note that if there are
+ // multiple blocks, then 'inc' (the counter increment amount) must be
+ // 64. So we can simply set it to 64 without re-loading it.
+ ldm sp, {r0, r1, r2} // load (state, block, nblocks)
+ mov r3, #64 // set 'inc'
+ subs r2, r2, #1 // nblocks--
+ str r2, [sp, #8]
+ bne .Lnext_block // nblocks != 0?
+
+ pop {r0-r2,r4-r11,pc}
+
+ // The next message block (pointed to by r1) isn't 4-byte aligned, so it
+ // can't be loaded using ldmia. Copy it to the stack buffer (pointed to
+ // by r12) using an alternative method. r2-r9 are free to use.
+.Lcopy_block_misaligned:
+ mov r2, #64
+1:
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ ldr r3, [r1], #4
+ _le32_bswap r3, r4
+#else
+ ldrb r3, [r1, #0]
+ ldrb r4, [r1, #1]
+ ldrb r5, [r1, #2]
+ ldrb r6, [r1, #3]
+ add r1, r1, #4
+ orr r3, r3, r4, lsl #8
+ orr r3, r3, r5, lsl #16
+ orr r3, r3, r6, lsl #24
+#endif
+ subs r2, r2, #4
+ str r3, [r12], #4
+ bne 1b
+ b .Lcopy_block_done
+ENDPROC(blake2s_compress)
diff --git a/arch/arm/crypto/blake2s-glue.c b/arch/arm/crypto/blake2s-glue.c
new file mode 100644
index 0000000000..0238a70d95
--- /dev/null
+++ b/arch/arm/crypto/blake2s-glue.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <crypto/internal/blake2s.h>
+#include <linux/module.h>
+
+/* defined in blake2s-core.S */
+EXPORT_SYMBOL(blake2s_compress);
diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
new file mode 100644
index 0000000000..cdde8fd01f
--- /dev/null
+++ b/arch/arm/crypto/chacha-glue.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM NEON accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2016-2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/chacha.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/cputype.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+ int nrounds);
+asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
+ int nrounds, unsigned int nbytes);
+asmlinkage void hchacha_block_arm(const u32 *state, u32 *out, int nrounds);
+asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
+
+asmlinkage void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+ const u32 *state, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_neon);
+
+static inline bool neon_usable(void)
+{
+ return static_branch_likely(&use_neon) && crypto_simd_usable();
+}
+
+static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
+ unsigned int bytes, int nrounds)
+{
+ u8 buf[CHACHA_BLOCK_SIZE];
+
+ while (bytes > CHACHA_BLOCK_SIZE) {
+ unsigned int l = min(bytes, CHACHA_BLOCK_SIZE * 4U);
+
+ chacha_4block_xor_neon(state, dst, src, nrounds, l);
+ bytes -= l;
+ src += l;
+ dst += l;
+ state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
+ }
+ if (bytes) {
+ const u8 *s = src;
+ u8 *d = dst;
+
+ if (bytes != CHACHA_BLOCK_SIZE)
+ s = d = memcpy(buf, src, bytes);
+ chacha_block_xor_neon(state, d, s, nrounds);
+ if (d != dst)
+ memcpy(dst, buf, bytes);
+ state[12]++;
+ }
+}
+
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+ if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable()) {
+ hchacha_block_arm(state, stream, nrounds);
+ } else {
+ kernel_neon_begin();
+ hchacha_block_neon(state, stream, nrounds);
+ kernel_neon_end();
+ }
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+ chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+ int nrounds)
+{
+ if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable() ||
+ bytes <= CHACHA_BLOCK_SIZE) {
+ chacha_doarm(dst, src, bytes, state, nrounds);
+ state[12] += DIV_ROUND_UP(bytes, CHACHA_BLOCK_SIZE);
+ return;
+ }
+
+ do {
+ unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+ kernel_neon_begin();
+ chacha_doneon(state, dst, src, todo, nrounds);
+ kernel_neon_end();
+
+ bytes -= todo;
+ src += todo;
+ dst += todo;
+ } while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_stream_xor(struct skcipher_request *req,
+ const struct chacha_ctx *ctx, const u8 *iv,
+ bool neon)
+{
+ struct skcipher_walk walk;
+ u32 state[16];
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+
+ chacha_init_generic(state, ctx->key, iv);
+
+ while (walk.nbytes > 0) {
+ unsigned int nbytes = walk.nbytes;
+
+ if (nbytes < walk.total)
+ nbytes = round_down(nbytes, walk.stride);
+
+ if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon) {
+ chacha_doarm(walk.dst.virt.addr, walk.src.virt.addr,
+ nbytes, state, ctx->nrounds);
+ state[12] += DIV_ROUND_UP(nbytes, CHACHA_BLOCK_SIZE);
+ } else {
+ kernel_neon_begin();
+ chacha_doneon(state, walk.dst.virt.addr,
+ walk.src.virt.addr, nbytes, ctx->nrounds);
+ kernel_neon_end();
+ }
+ err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+ }
+
+ return err;
+}
+
+static int do_chacha(struct skcipher_request *req, bool neon)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return chacha_stream_xor(req, ctx, req->iv, neon);
+}
+
+static int chacha_arm(struct skcipher_request *req)
+{
+ return do_chacha(req, false);
+}
+
+static int chacha_neon(struct skcipher_request *req)
+{
+ return do_chacha(req, neon_usable());
+}
+
+static int do_xchacha(struct skcipher_request *req, bool neon)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct chacha_ctx subctx;
+ u32 state[16];
+ u8 real_iv[16];
+
+ chacha_init_generic(state, ctx->key, req->iv);
+
+ if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon) {
+ hchacha_block_arm(state, subctx.key, ctx->nrounds);
+ } else {
+ kernel_neon_begin();
+ hchacha_block_neon(state, subctx.key, ctx->nrounds);
+ kernel_neon_end();
+ }
+ subctx.nrounds = ctx->nrounds;
+
+ memcpy(&real_iv[0], req->iv + 24, 8);
+ memcpy(&real_iv[8], req->iv + 16, 8);
+ return chacha_stream_xor(req, &subctx, real_iv, neon);
+}
+
+static int xchacha_arm(struct skcipher_request *req)
+{
+ return do_xchacha(req, false);
+}
+
+static int xchacha_neon(struct skcipher_request *req)
+{
+ return do_xchacha(req, neon_usable());
+}
+
+static struct skcipher_alg arm_algs[] = {
+ {
+ .base.cra_name = "chacha20",
+ .base.cra_driver_name = "chacha20-arm",
+ .base.cra_priority = 200,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = CHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .setkey = chacha20_setkey,
+ .encrypt = chacha_arm,
+ .decrypt = chacha_arm,
+ }, {
+ .base.cra_name = "xchacha20",
+ .base.cra_driver_name = "xchacha20-arm",
+ .base.cra_priority = 200,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .setkey = chacha20_setkey,
+ .encrypt = xchacha_arm,
+ .decrypt = xchacha_arm,
+ }, {
+ .base.cra_name = "xchacha12",
+ .base.cra_driver_name = "xchacha12-arm",
+ .base.cra_priority = 200,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .setkey = chacha12_setkey,
+ .encrypt = xchacha_arm,
+ .decrypt = xchacha_arm,
+ },
+};
+
+static struct skcipher_alg neon_algs[] = {
+ {
+ .base.cra_name = "chacha20",
+ .base.cra_driver_name = "chacha20-neon",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = CHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .walksize = 4 * CHACHA_BLOCK_SIZE,
+ .setkey = chacha20_setkey,
+ .encrypt = chacha_neon,
+ .decrypt = chacha_neon,
+ }, {
+ .base.cra_name = "xchacha20",
+ .base.cra_driver_name = "xchacha20-neon",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .walksize = 4 * CHACHA_BLOCK_SIZE,
+ .setkey = chacha20_setkey,
+ .encrypt = xchacha_neon,
+ .decrypt = xchacha_neon,
+ }, {
+ .base.cra_name = "xchacha12",
+ .base.cra_driver_name = "xchacha12-neon",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .walksize = 4 * CHACHA_BLOCK_SIZE,
+ .setkey = chacha12_setkey,
+ .encrypt = xchacha_neon,
+ .decrypt = xchacha_neon,
+ }
+};
+
+static int __init chacha_simd_mod_init(void)
+{
+ int err = 0;
+
+ if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
+ err = crypto_register_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+ if (err)
+ return err;
+ }
+
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) {
+ int i;
+
+ switch (read_cpuid_part()) {
+ case ARM_CPU_PART_CORTEX_A7:
+ case ARM_CPU_PART_CORTEX_A5:
+ /*
+ * The Cortex-A7 and Cortex-A5 do not perform well with
+ * the NEON implementation but do incredibly with the
+ * scalar one and use less power.
+ */
+ for (i = 0; i < ARRAY_SIZE(neon_algs); i++)
+ neon_algs[i].base.cra_priority = 0;
+ break;
+ default:
+ static_branch_enable(&use_neon);
+ }
+
+ if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
+ err = crypto_register_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
+ if (err)
+ crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+ }
+ }
+ return err;
+}
+
+static void __exit chacha_simd_mod_fini(void)
+{
+ if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER)) {
+ crypto_unregister_skciphers(arm_algs, ARRAY_SIZE(arm_algs));
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON))
+ crypto_unregister_skciphers(neon_algs, ARRAY_SIZE(neon_algs));
+ }
+}
+
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
+
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (scalar and NEON accelerated)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-arm");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-arm");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-arm");
+#ifdef CONFIG_KERNEL_MODE_NEON
+MODULE_ALIAS_CRYPTO("chacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha12-neon");
+#endif
diff --git a/arch/arm/crypto/chacha-neon-core.S b/arch/arm/crypto/chacha-neon-core.S
new file mode 100644
index 0000000000..13d12f6726
--- /dev/null
+++ b/arch/arm/crypto/chacha-neon-core.S
@@ -0,0 +1,643 @@
+/*
+ * ChaCha/XChaCha NEON helper functions
+ *
+ * Copyright (C) 2016 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.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+ /*
+ * NEON doesn't have a rotate instruction. The alternatives are, more or less:
+ *
+ * (a) vshl.u32 + vsri.u32 (needs temporary register)
+ * (b) vshl.u32 + vshr.u32 + vorr (needs temporary register)
+ * (c) vrev32.16 (16-bit rotations only)
+ * (d) vtbl.8 + vtbl.8 (multiple of 8 bits rotations only,
+ * needs index vector)
+ *
+ * ChaCha has 16, 12, 8, and 7-bit rotations. For the 12 and 7-bit rotations,
+ * the only choices are (a) and (b). We use (a) since it takes two-thirds the
+ * cycles of (b) on both Cortex-A7 and Cortex-A53.
+ *
+ * For the 16-bit rotation, we use vrev32.16 since it's consistently fastest
+ * and doesn't need a temporary register.
+ *
+ * For the 8-bit rotation, we use vtbl.8 + vtbl.8. On Cortex-A7, this sequence
+ * is twice as fast as (a), even when doing (a) on multiple registers
+ * simultaneously to eliminate the stall between vshl and vsri. Also, it
+ * parallelizes better when temporary registers are scarce.
+ *
+ * A disadvantage is that on Cortex-A53, the vtbl sequence is the same speed as
+ * (a), so the need to load the rotation table actually makes the vtbl method
+ * slightly slower overall on that CPU (~1.3% slower ChaCha20). Still, it
+ * seems to be a good compromise to get a more significant speed boost on some
+ * CPUs, e.g. ~4.8% faster ChaCha20 on Cortex-A7.
+ */
+
+#include <linux/linkage.h>
+#include <asm/cache.h>
+
+ .text
+ .fpu neon
+ .align 5
+
+/*
+ * chacha_permute - permute one block
+ *
+ * Permute one 64-byte block where the state matrix is stored in the four NEON
+ * registers q0-q3. It performs matrix operations on four words in parallel,
+ * but requires shuffling to rearrange the words after each round.
+ *
+ * The round count is given in r3.
+ *
+ * Clobbers: r3, ip, q4-q5
+ */
+chacha_permute:
+
+ adr ip, .Lrol8_table
+ vld1.8 {d10}, [ip, :64]
+
+.Ldoubleround:
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vrev32.16 q3, q3
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #12
+ vsri.u32 q1, q4, #20
+
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vtbl.8 d6, {d6}, d10
+ vtbl.8 d7, {d7}, d10
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #7
+ vsri.u32 q1, q4, #25
+
+ // x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+ vext.8 q1, q1, q1, #4
+ // x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+ vext.8 q2, q2, q2, #8
+ // x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+ vext.8 q3, q3, q3, #12
+
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vrev32.16 q3, q3
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #12
+ vsri.u32 q1, q4, #20
+
+ // x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+ vadd.i32 q0, q0, q1
+ veor q3, q3, q0
+ vtbl.8 d6, {d6}, d10
+ vtbl.8 d7, {d7}, d10
+
+ // x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+ vadd.i32 q2, q2, q3
+ veor q4, q1, q2
+ vshl.u32 q1, q4, #7
+ vsri.u32 q1, q4, #25
+
+ // x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+ vext.8 q1, q1, q1, #12
+ // x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+ vext.8 q2, q2, q2, #8
+ // x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+ vext.8 q3, q3, q3, #4
+
+ subs r3, r3, #2
+ bne .Ldoubleround
+
+ bx lr
+ENDPROC(chacha_permute)
+
+ENTRY(chacha_block_xor_neon)
+ // r0: Input state matrix, s
+ // r1: 1 data block output, o
+ // r2: 1 data block input, i
+ // r3: nrounds
+ push {lr}
+
+ // x0..3 = s0..3
+ add ip, r0, #0x20
+ vld1.32 {q0-q1}, [r0]
+ vld1.32 {q2-q3}, [ip]
+
+ vmov q8, q0
+ vmov q9, q1
+ vmov q10, q2
+ vmov q11, q3
+
+ bl chacha_permute
+
+ add ip, r2, #0x20
+ vld1.8 {q4-q5}, [r2]
+ vld1.8 {q6-q7}, [ip]
+
+ // o0 = i0 ^ (x0 + s0)
+ vadd.i32 q0, q0, q8
+ veor q0, q0, q4
+
+ // o1 = i1 ^ (x1 + s1)
+ vadd.i32 q1, q1, q9
+ veor q1, q1, q5
+
+ // o2 = i2 ^ (x2 + s2)
+ vadd.i32 q2, q2, q10
+ veor q2, q2, q6
+
+ // o3 = i3 ^ (x3 + s3)
+ vadd.i32 q3, q3, q11
+ veor q3, q3, q7
+
+ add ip, r1, #0x20
+ vst1.8 {q0-q1}, [r1]
+ vst1.8 {q2-q3}, [ip]
+
+ pop {pc}
+ENDPROC(chacha_block_xor_neon)
+
+ENTRY(hchacha_block_neon)
+ // r0: Input state matrix, s
+ // r1: output (8 32-bit words)
+ // r2: nrounds
+ push {lr}
+
+ vld1.32 {q0-q1}, [r0]!
+ vld1.32 {q2-q3}, [r0]
+
+ mov r3, r2
+ bl chacha_permute
+
+ vst1.32 {q0}, [r1]!
+ vst1.32 {q3}, [r1]
+
+ pop {pc}
+ENDPROC(hchacha_block_neon)
+
+ .align 4
+.Lctrinc: .word 0, 1, 2, 3
+.Lrol8_table: .byte 3, 0, 1, 2, 7, 4, 5, 6
+
+ .align 5
+ENTRY(chacha_4block_xor_neon)
+ push {r4, lr}
+ mov r4, sp // preserve the stack pointer
+ sub ip, sp, #0x20 // allocate a 32 byte buffer
+ bic ip, ip, #0x1f // aligned to 32 bytes
+ mov sp, ip
+
+ // r0: Input state matrix, s
+ // r1: 4 data blocks output, o
+ // r2: 4 data blocks input, i
+ // r3: nrounds
+
+ //
+ // This function encrypts four consecutive ChaCha blocks by loading
+ // the state matrix in NEON registers four times. The algorithm performs
+ // each operation on the corresponding word of each state matrix, hence
+ // requires no word shuffling. The words are re-interleaved before the
+ // final addition of the original state and the XORing step.
+ //
+
+ // x0..15[0-3] = s0..15[0-3]
+ add ip, r0, #0x20
+ vld1.32 {q0-q1}, [r0]
+ vld1.32 {q2-q3}, [ip]
+
+ adr lr, .Lctrinc
+ vdup.32 q15, d7[1]
+ vdup.32 q14, d7[0]
+ vld1.32 {q4}, [lr, :128]
+ vdup.32 q13, d6[1]
+ vdup.32 q12, d6[0]
+ vdup.32 q11, d5[1]
+ vdup.32 q10, d5[0]
+ vadd.u32 q12, q12, q4 // x12 += counter values 0-3
+ vdup.32 q9, d4[1]
+ vdup.32 q8, d4[0]
+ vdup.32 q7, d3[1]
+ vdup.32 q6, d3[0]
+ vdup.32 q5, d2[1]
+ vdup.32 q4, d2[0]
+ vdup.32 q3, d1[1]
+ vdup.32 q2, d1[0]
+ vdup.32 q1, d0[1]
+ vdup.32 q0, d0[0]
+
+ adr ip, .Lrol8_table
+ b 1f
+
+.Ldoubleround4:
+ vld1.32 {q8-q9}, [sp, :256]
+1:
+ // x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+ // x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+ // x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+ // x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+ vadd.i32 q0, q0, q4
+ vadd.i32 q1, q1, q5
+ vadd.i32 q2, q2, q6
+ vadd.i32 q3, q3, q7
+
+ veor q12, q12, q0
+ veor q13, q13, q1
+ veor q14, q14, q2
+ veor q15, q15, q3
+
+ vrev32.16 q12, q12
+ vrev32.16 q13, q13
+ vrev32.16 q14, q14
+ vrev32.16 q15, q15
+
+ // x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+ // x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+ // x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+ // x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+ vadd.i32 q8, q8, q12
+ vadd.i32 q9, q9, q13
+ vadd.i32 q10, q10, q14
+ vadd.i32 q11, q11, q15
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q4, q8
+ veor q9, q5, q9
+ vshl.u32 q4, q8, #12
+ vshl.u32 q5, q9, #12
+ vsri.u32 q4, q8, #20
+ vsri.u32 q5, q9, #20
+
+ veor q8, q6, q10
+ veor q9, q7, q11
+ vshl.u32 q6, q8, #12
+ vshl.u32 q7, q9, #12
+ vsri.u32 q6, q8, #20
+ vsri.u32 q7, q9, #20
+
+ // x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+ // x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+ // x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+ // x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+ vld1.8 {d16}, [ip, :64]
+ vadd.i32 q0, q0, q4
+ vadd.i32 q1, q1, q5
+ vadd.i32 q2, q2, q6
+ vadd.i32 q3, q3, q7
+
+ veor q12, q12, q0
+ veor q13, q13, q1
+ veor q14, q14, q2
+ veor q15, q15, q3
+
+ vtbl.8 d24, {d24}, d16
+ vtbl.8 d25, {d25}, d16
+ vtbl.8 d26, {d26}, d16
+ vtbl.8 d27, {d27}, d16
+ vtbl.8 d28, {d28}, d16
+ vtbl.8 d29, {d29}, d16
+ vtbl.8 d30, {d30}, d16
+ vtbl.8 d31, {d31}, d16
+
+ vld1.32 {q8-q9}, [sp, :256]
+
+ // x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+ // x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+ // x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+ // x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+ vadd.i32 q8, q8, q12
+ vadd.i32 q9, q9, q13
+ vadd.i32 q10, q10, q14
+ vadd.i32 q11, q11, q15
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q4, q8
+ veor q9, q5, q9
+ vshl.u32 q4, q8, #7
+ vshl.u32 q5, q9, #7
+ vsri.u32 q4, q8, #25
+ vsri.u32 q5, q9, #25
+
+ veor q8, q6, q10
+ veor q9, q7, q11
+ vshl.u32 q6, q8, #7
+ vshl.u32 q7, q9, #7
+ vsri.u32 q6, q8, #25
+ vsri.u32 q7, q9, #25
+
+ vld1.32 {q8-q9}, [sp, :256]
+
+ // x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+ // x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+ // x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+ // x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+ vadd.i32 q0, q0, q5
+ vadd.i32 q1, q1, q6
+ vadd.i32 q2, q2, q7
+ vadd.i32 q3, q3, q4
+
+ veor q15, q15, q0
+ veor q12, q12, q1
+ veor q13, q13, q2
+ veor q14, q14, q3
+
+ vrev32.16 q15, q15
+ vrev32.16 q12, q12
+ vrev32.16 q13, q13
+ vrev32.16 q14, q14
+
+ // x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+ // x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+ // x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+ // x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+ vadd.i32 q10, q10, q15
+ vadd.i32 q11, q11, q12
+ vadd.i32 q8, q8, q13
+ vadd.i32 q9, q9, q14
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q7, q8
+ veor q9, q4, q9
+ vshl.u32 q7, q8, #12
+ vshl.u32 q4, q9, #12
+ vsri.u32 q7, q8, #20
+ vsri.u32 q4, q9, #20
+
+ veor q8, q5, q10
+ veor q9, q6, q11
+ vshl.u32 q5, q8, #12
+ vshl.u32 q6, q9, #12
+ vsri.u32 q5, q8, #20
+ vsri.u32 q6, q9, #20
+
+ // x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+ // x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+ // x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+ // x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+ vld1.8 {d16}, [ip, :64]
+ vadd.i32 q0, q0, q5
+ vadd.i32 q1, q1, q6
+ vadd.i32 q2, q2, q7
+ vadd.i32 q3, q3, q4
+
+ veor q15, q15, q0
+ veor q12, q12, q1
+ veor q13, q13, q2
+ veor q14, q14, q3
+
+ vtbl.8 d30, {d30}, d16
+ vtbl.8 d31, {d31}, d16
+ vtbl.8 d24, {d24}, d16
+ vtbl.8 d25, {d25}, d16
+ vtbl.8 d26, {d26}, d16
+ vtbl.8 d27, {d27}, d16
+ vtbl.8 d28, {d28}, d16
+ vtbl.8 d29, {d29}, d16
+
+ vld1.32 {q8-q9}, [sp, :256]
+
+ // x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+ // x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+ // x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+ // x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+ vadd.i32 q10, q10, q15
+ vadd.i32 q11, q11, q12
+ vadd.i32 q8, q8, q13
+ vadd.i32 q9, q9, q14
+
+ vst1.32 {q8-q9}, [sp, :256]
+
+ veor q8, q7, q8
+ veor q9, q4, q9
+ vshl.u32 q7, q8, #7
+ vshl.u32 q4, q9, #7
+ vsri.u32 q7, q8, #25
+ vsri.u32 q4, q9, #25
+
+ veor q8, q5, q10
+ veor q9, q6, q11
+ vshl.u32 q5, q8, #7
+ vshl.u32 q6, q9, #7
+ vsri.u32 q5, q8, #25
+ vsri.u32 q6, q9, #25
+
+ subs r3, r3, #2
+ bne .Ldoubleround4
+
+ // x0..7[0-3] are in q0-q7, x10..15[0-3] are in q10-q15.
+ // x8..9[0-3] are on the stack.
+
+ // Re-interleave the words in the first two rows of each block (x0..7).
+ // Also add the counter values 0-3 to x12[0-3].
+ vld1.32 {q8}, [lr, :128] // load counter values 0-3
+ vzip.32 q0, q1 // => (0 1 0 1) (0 1 0 1)
+ vzip.32 q2, q3 // => (2 3 2 3) (2 3 2 3)
+ vzip.32 q4, q5 // => (4 5 4 5) (4 5 4 5)
+ vzip.32 q6, q7 // => (6 7 6 7) (6 7 6 7)
+ vadd.u32 q12, q8 // x12 += counter values 0-3
+ vswp d1, d4
+ vswp d3, d6
+ vld1.32 {q8-q9}, [r0]! // load s0..7
+ vswp d9, d12
+ vswp d11, d14
+
+ // Swap q1 and q4 so that we'll free up consecutive registers (q0-q1)
+ // after XORing the first 32 bytes.
+ vswp q1, q4
+
+ // First two rows of each block are (q0 q1) (q2 q6) (q4 q5) (q3 q7)
+
+ // x0..3[0-3] += s0..3[0-3] (add orig state to 1st row of each block)
+ vadd.u32 q0, q0, q8
+ vadd.u32 q2, q2, q8
+ vadd.u32 q4, q4, q8
+ vadd.u32 q3, q3, q8
+
+ // x4..7[0-3] += s4..7[0-3] (add orig state to 2nd row of each block)
+ vadd.u32 q1, q1, q9
+ vadd.u32 q6, q6, q9
+ vadd.u32 q5, q5, q9
+ vadd.u32 q7, q7, q9
+
+ // XOR first 32 bytes using keystream from first two rows of first block
+ vld1.8 {q8-q9}, [r2]!
+ veor q8, q8, q0
+ veor q9, q9, q1
+ vst1.8 {q8-q9}, [r1]!
+
+ // Re-interleave the words in the last two rows of each block (x8..15).
+ vld1.32 {q8-q9}, [sp, :256]
+ mov sp, r4 // restore original stack pointer
+ ldr r4, [r4, #8] // load number of bytes
+ vzip.32 q12, q13 // => (12 13 12 13) (12 13 12 13)
+ vzip.32 q14, q15 // => (14 15 14 15) (14 15 14 15)
+ vzip.32 q8, q9 // => (8 9 8 9) (8 9 8 9)
+ vzip.32 q10, q11 // => (10 11 10 11) (10 11 10 11)
+ vld1.32 {q0-q1}, [r0] // load s8..15
+ vswp d25, d28
+ vswp d27, d30
+ vswp d17, d20
+ vswp d19, d22
+
+ // Last two rows of each block are (q8 q12) (q10 q14) (q9 q13) (q11 q15)
+
+ // x8..11[0-3] += s8..11[0-3] (add orig state to 3rd row of each block)
+ vadd.u32 q8, q8, q0
+ vadd.u32 q10, q10, q0
+ vadd.u32 q9, q9, q0
+ vadd.u32 q11, q11, q0
+
+ // x12..15[0-3] += s12..15[0-3] (add orig state to 4th row of each block)
+ vadd.u32 q12, q12, q1
+ vadd.u32 q14, q14, q1
+ vadd.u32 q13, q13, q1
+ vadd.u32 q15, q15, q1
+
+ // XOR the rest of the data with the keystream
+
+ vld1.8 {q0-q1}, [r2]!
+ subs r4, r4, #96
+ veor q0, q0, q8
+ veor q1, q1, q12
+ ble .Lle96
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ subs r4, r4, #32
+ veor q0, q0, q2
+ veor q1, q1, q6
+ ble .Lle128
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ subs r4, r4, #32
+ veor q0, q0, q10
+ veor q1, q1, q14
+ ble .Lle160
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ subs r4, r4, #32
+ veor q0, q0, q4
+ veor q1, q1, q5
+ ble .Lle192
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ subs r4, r4, #32
+ veor q0, q0, q9
+ veor q1, q1, q13
+ ble .Lle224
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]!
+ subs r4, r4, #32
+ veor q0, q0, q3
+ veor q1, q1, q7
+ blt .Llt256
+.Lout:
+ vst1.8 {q0-q1}, [r1]!
+
+ vld1.8 {q0-q1}, [r2]
+ veor q0, q0, q11
+ veor q1, q1, q15
+ vst1.8 {q0-q1}, [r1]
+
+ pop {r4, pc}
+
+.Lle192:
+ vmov q4, q9
+ vmov q5, q13
+
+.Lle160:
+ // nothing to do
+
+.Lfinalblock:
+ // Process the final block if processing less than 4 full blocks.
+ // Entered with 32 bytes of ChaCha cipher stream in q4-q5, and the
+ // previous 32 byte output block that still needs to be written at
+ // [r1] in q0-q1.
+ beq .Lfullblock
+
+.Lpartialblock:
+ adr lr, .Lpermute + 32
+ add r2, r2, r4
+ add lr, lr, r4
+ add r4, r4, r1
+
+ vld1.8 {q2-q3}, [lr]
+ vld1.8 {q6-q7}, [r2]
+
+ add r4, r4, #32
+
+ vtbl.8 d4, {q4-q5}, d4
+ vtbl.8 d5, {q4-q5}, d5
+ vtbl.8 d6, {q4-q5}, d6
+ vtbl.8 d7, {q4-q5}, d7
+
+ veor q6, q6, q2
+ veor q7, q7, q3
+
+ vst1.8 {q6-q7}, [r4] // overlapping stores
+ vst1.8 {q0-q1}, [r1]
+ pop {r4, pc}
+
+.Lfullblock:
+ vmov q11, q4
+ vmov q15, q5
+ b .Lout
+.Lle96:
+ vmov q4, q2
+ vmov q5, q6
+ b .Lfinalblock
+.Lle128:
+ vmov q4, q10
+ vmov q5, q14
+ b .Lfinalblock
+.Lle224:
+ vmov q4, q3
+ vmov q5, q7
+ b .Lfinalblock
+.Llt256:
+ vmov q4, q11
+ vmov q5, q15
+ b .Lpartialblock
+ENDPROC(chacha_4block_xor_neon)
+
+ .align L1_CACHE_SHIFT
+.Lpermute:
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+ .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+ .byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17
+ .byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+ .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+ .byte 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17
+ .byte 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f
diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/crypto/chacha-scalar-core.S
new file mode 100644
index 0000000000..083fe1ab96
--- /dev/null
+++ b/arch/arm/crypto/chacha-scalar-core.S
@@ -0,0 +1,443 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Google, Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Design notes:
+ *
+ * 16 registers would be needed to hold the state matrix, but only 14 are
+ * available because 'sp' and 'pc' cannot be used. So we spill the elements
+ * (x8, x9) to the stack and swap them out with (x10, x11). This adds one
+ * 'ldrd' and one 'strd' instruction per round.
+ *
+ * All rotates are performed using the implicit rotate operand accepted by the
+ * 'add' and 'eor' instructions. This is faster than using explicit rotate
+ * instructions. To make this work, we allow the values in the second and last
+ * rows of the ChaCha state matrix (rows 'b' and 'd') to temporarily have the
+ * wrong rotation amount. The rotation amount is then fixed up just in time
+ * when the values are used. 'brot' is the number of bits the values in row 'b'
+ * need to be rotated right to arrive at the correct values, and 'drot'
+ * similarly for row 'd'. (brot, drot) start out as (0, 0) but we make it such
+ * that they end up as (25, 24) after every round.
+ */
+
+ // ChaCha state registers
+ X0 .req r0
+ X1 .req r1
+ X2 .req r2
+ X3 .req r3
+ X4 .req r4
+ X5 .req r5
+ X6 .req r6
+ X7 .req r7
+ X8_X10 .req r8 // shared by x8 and x10
+ X9_X11 .req r9 // shared by x9 and x11
+ X12 .req r10
+ X13 .req r11
+ X14 .req r12
+ X15 .req r14
+
+.macro _le32_bswap_4x a, b, c, d, tmp
+#ifdef __ARMEB__
+ rev_l \a, \tmp
+ rev_l \b, \tmp
+ rev_l \c, \tmp
+ rev_l \d, \tmp
+#endif
+.endm
+
+.macro __ldrd a, b, src, offset
+#if __LINUX_ARM_ARCH__ >= 6
+ ldrd \a, \b, [\src, #\offset]
+#else
+ ldr \a, [\src, #\offset]
+ ldr \b, [\src, #\offset + 4]
+#endif
+.endm
+
+.macro __strd a, b, dst, offset
+#if __LINUX_ARM_ARCH__ >= 6
+ strd \a, \b, [\dst, #\offset]
+#else
+ str \a, [\dst, #\offset]
+ str \b, [\dst, #\offset + 4]
+#endif
+.endm
+
+.macro _halfround a1, b1, c1, d1, a2, b2, c2, d2
+
+ // a += b; d ^= a; d = rol(d, 16);
+ add \a1, \a1, \b1, ror #brot
+ add \a2, \a2, \b2, ror #brot
+ eor \d1, \a1, \d1, ror #drot
+ eor \d2, \a2, \d2, ror #drot
+ // drot == 32 - 16 == 16
+
+ // c += d; b ^= c; b = rol(b, 12);
+ add \c1, \c1, \d1, ror #16
+ add \c2, \c2, \d2, ror #16
+ eor \b1, \c1, \b1, ror #brot
+ eor \b2, \c2, \b2, ror #brot
+ // brot == 32 - 12 == 20
+
+ // a += b; d ^= a; d = rol(d, 8);
+ add \a1, \a1, \b1, ror #20
+ add \a2, \a2, \b2, ror #20
+ eor \d1, \a1, \d1, ror #16
+ eor \d2, \a2, \d2, ror #16
+ // drot == 32 - 8 == 24
+
+ // c += d; b ^= c; b = rol(b, 7);
+ add \c1, \c1, \d1, ror #24
+ add \c2, \c2, \d2, ror #24
+ eor \b1, \c1, \b1, ror #20
+ eor \b2, \c2, \b2, ror #20
+ // brot == 32 - 7 == 25
+.endm
+
+.macro _doubleround
+
+ // column round
+
+ // quarterrounds: (x0, x4, x8, x12) and (x1, x5, x9, x13)
+ _halfround X0, X4, X8_X10, X12, X1, X5, X9_X11, X13
+
+ // save (x8, x9); restore (x10, x11)
+ __strd X8_X10, X9_X11, sp, 0
+ __ldrd X8_X10, X9_X11, sp, 8
+
+ // quarterrounds: (x2, x6, x10, x14) and (x3, x7, x11, x15)
+ _halfround X2, X6, X8_X10, X14, X3, X7, X9_X11, X15
+
+ .set brot, 25
+ .set drot, 24
+
+ // diagonal round
+
+ // quarterrounds: (x0, x5, x10, x15) and (x1, x6, x11, x12)
+ _halfround X0, X5, X8_X10, X15, X1, X6, X9_X11, X12
+
+ // save (x10, x11); restore (x8, x9)
+ __strd X8_X10, X9_X11, sp, 8
+ __ldrd X8_X10, X9_X11, sp, 0
+
+ // quarterrounds: (x2, x7, x8, x13) and (x3, x4, x9, x14)
+ _halfround X2, X7, X8_X10, X13, X3, X4, X9_X11, X14
+.endm
+
+.macro _chacha_permute nrounds
+ .set brot, 0
+ .set drot, 0
+ .rept \nrounds / 2
+ _doubleround
+ .endr
+.endm
+
+.macro _chacha nrounds
+
+.Lnext_block\@:
+ // Stack: unused0-unused1 x10-x11 x0-x15 OUT IN LEN
+ // Registers contain x0-x9,x12-x15.
+
+ // Do the core ChaCha permutation to update x0-x15.
+ _chacha_permute \nrounds
+
+ add sp, #8
+ // Stack: x10-x11 orig_x0-orig_x15 OUT IN LEN
+ // Registers contain x0-x9,x12-x15.
+ // x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+ // Free up some registers (r8-r12,r14) by pushing (x8-x9,x12-x15).
+ push {X8_X10, X9_X11, X12, X13, X14, X15}
+
+ // Load (OUT, IN, LEN).
+ ldr r14, [sp, #96]
+ ldr r12, [sp, #100]
+ ldr r11, [sp, #104]
+
+ orr r10, r14, r12
+
+ // Use slow path if fewer than 64 bytes remain.
+ cmp r11, #64
+ blt .Lxor_slowpath\@
+
+ // Use slow path if IN and/or OUT isn't 4-byte aligned. Needed even on
+ // ARMv6+, since ldmia and stmia (used below) still require alignment.
+ tst r10, #3
+ bne .Lxor_slowpath\@
+
+ // Fast path: XOR 64 bytes of aligned data.
+
+ // Stack: x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+ // Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is OUT.
+ // x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+ // x0-x3
+ __ldrd r8, r9, sp, 32
+ __ldrd r10, r11, sp, 40
+ add X0, X0, r8
+ add X1, X1, r9
+ add X2, X2, r10
+ add X3, X3, r11
+ _le32_bswap_4x X0, X1, X2, X3, r8
+ ldmia r12!, {r8-r11}
+ eor X0, X0, r8
+ eor X1, X1, r9
+ eor X2, X2, r10
+ eor X3, X3, r11
+ stmia r14!, {X0-X3}
+
+ // x4-x7
+ __ldrd r8, r9, sp, 48
+ __ldrd r10, r11, sp, 56
+ add X4, r8, X4, ror #brot
+ add X5, r9, X5, ror #brot
+ ldmia r12!, {X0-X3}
+ add X6, r10, X6, ror #brot
+ add X7, r11, X7, ror #brot
+ _le32_bswap_4x X4, X5, X6, X7, r8
+ eor X4, X4, X0
+ eor X5, X5, X1
+ eor X6, X6, X2
+ eor X7, X7, X3
+ stmia r14!, {X4-X7}
+
+ // x8-x15
+ pop {r0-r7} // (x8-x9,x12-x15,x10-x11)
+ __ldrd r8, r9, sp, 32
+ __ldrd r10, r11, sp, 40
+ add r0, r0, r8 // x8
+ add r1, r1, r9 // x9
+ add r6, r6, r10 // x10
+ add r7, r7, r11 // x11
+ _le32_bswap_4x r0, r1, r6, r7, r8
+ ldmia r12!, {r8-r11}
+ eor r0, r0, r8 // x8
+ eor r1, r1, r9 // x9
+ eor r6, r6, r10 // x10
+ eor r7, r7, r11 // x11
+ stmia r14!, {r0,r1,r6,r7}
+ ldmia r12!, {r0,r1,r6,r7}
+ __ldrd r8, r9, sp, 48
+ __ldrd r10, r11, sp, 56
+ add r2, r8, r2, ror #drot // x12
+ add r3, r9, r3, ror #drot // x13
+ add r4, r10, r4, ror #drot // x14
+ add r5, r11, r5, ror #drot // x15
+ _le32_bswap_4x r2, r3, r4, r5, r9
+ ldr r9, [sp, #72] // load LEN
+ eor r2, r2, r0 // x12
+ eor r3, r3, r1 // x13
+ eor r4, r4, r6 // x14
+ eor r5, r5, r7 // x15
+ subs r9, #64 // decrement and check LEN
+ stmia r14!, {r2-r5}
+
+ beq .Ldone\@
+
+.Lprepare_for_next_block\@:
+
+ // Stack: x0-x15 OUT IN LEN
+
+ // Increment block counter (x12)
+ add r8, #1
+
+ // Store updated (OUT, IN, LEN)
+ str r14, [sp, #64]
+ str r12, [sp, #68]
+ str r9, [sp, #72]
+
+ mov r14, sp
+
+ // Store updated block counter (x12)
+ str r8, [sp, #48]
+
+ sub sp, #16
+
+ // Reload state and do next block
+ ldmia r14!, {r0-r11} // load x0-x11
+ __strd r10, r11, sp, 8 // store x10-x11 before state
+ ldmia r14, {r10-r12,r14} // load x12-x15
+ b .Lnext_block\@
+
+.Lxor_slowpath\@:
+ // Slow path: < 64 bytes remaining, or unaligned input or output buffer.
+ // We handle it by storing the 64 bytes of keystream to the stack, then
+ // XOR-ing the needed portion with the data.
+
+ // Allocate keystream buffer
+ sub sp, #64
+ mov r14, sp
+
+ // Stack: ks0-ks15 x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+ // Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is &ks0.
+ // x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+ // Save keystream for x0-x3
+ __ldrd r8, r9, sp, 96
+ __ldrd r10, r11, sp, 104
+ add X0, X0, r8
+ add X1, X1, r9
+ add X2, X2, r10
+ add X3, X3, r11
+ _le32_bswap_4x X0, X1, X2, X3, r8
+ stmia r14!, {X0-X3}
+
+ // Save keystream for x4-x7
+ __ldrd r8, r9, sp, 112
+ __ldrd r10, r11, sp, 120
+ add X4, r8, X4, ror #brot
+ add X5, r9, X5, ror #brot
+ add X6, r10, X6, ror #brot
+ add X7, r11, X7, ror #brot
+ _le32_bswap_4x X4, X5, X6, X7, r8
+ add r8, sp, #64
+ stmia r14!, {X4-X7}
+
+ // Save keystream for x8-x15
+ ldm r8, {r0-r7} // (x8-x9,x12-x15,x10-x11)
+ __ldrd r8, r9, sp, 128
+ __ldrd r10, r11, sp, 136
+ add r0, r0, r8 // x8
+ add r1, r1, r9 // x9
+ add r6, r6, r10 // x10
+ add r7, r7, r11 // x11
+ _le32_bswap_4x r0, r1, r6, r7, r8
+ stmia r14!, {r0,r1,r6,r7}
+ __ldrd r8, r9, sp, 144
+ __ldrd r10, r11, sp, 152
+ add r2, r8, r2, ror #drot // x12
+ add r3, r9, r3, ror #drot // x13
+ add r4, r10, r4, ror #drot // x14
+ add r5, r11, r5, ror #drot // x15
+ _le32_bswap_4x r2, r3, r4, r5, r9
+ stmia r14, {r2-r5}
+
+ // Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
+ // Registers: r8 is block counter, r12 is IN.
+
+ ldr r9, [sp, #168] // LEN
+ ldr r14, [sp, #160] // OUT
+ cmp r9, #64
+ mov r0, sp
+ movle r1, r9
+ movgt r1, #64
+ // r1 is number of bytes to XOR, in range [1, 64]
+
+.if __LINUX_ARM_ARCH__ < 6
+ orr r2, r12, r14
+ tst r2, #3 // IN or OUT misaligned?
+ bne .Lxor_next_byte\@
+.endif
+
+ // XOR a word at a time
+.rept 16
+ subs r1, #4
+ blt .Lxor_words_done\@
+ ldr r2, [r12], #4
+ ldr r3, [r0], #4
+ eor r2, r2, r3
+ str r2, [r14], #4
+.endr
+ b .Lxor_slowpath_done\@
+.Lxor_words_done\@:
+ ands r1, r1, #3
+ beq .Lxor_slowpath_done\@
+
+ // XOR a byte at a time
+.Lxor_next_byte\@:
+ ldrb r2, [r12], #1
+ ldrb r3, [r0], #1
+ eor r2, r2, r3
+ strb r2, [r14], #1
+ subs r1, #1
+ bne .Lxor_next_byte\@
+
+.Lxor_slowpath_done\@:
+ subs r9, #64
+ add sp, #96
+ bgt .Lprepare_for_next_block\@
+
+.Ldone\@:
+.endm // _chacha
+
+/*
+ * void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
+ * const u32 *state, int nrounds);
+ */
+ENTRY(chacha_doarm)
+ cmp r2, #0 // len == 0?
+ reteq lr
+
+ ldr ip, [sp]
+ cmp ip, #12
+
+ push {r0-r2,r4-r11,lr}
+
+ // Push state x0-x15 onto stack.
+ // Also store an extra copy of x10-x11 just before the state.
+
+ add X12, r3, #48
+ ldm X12, {X12,X13,X14,X15}
+ push {X12,X13,X14,X15}
+ sub sp, sp, #64
+
+ __ldrd X8_X10, X9_X11, r3, 40
+ __strd X8_X10, X9_X11, sp, 8
+ __strd X8_X10, X9_X11, sp, 56
+ ldm r3, {X0-X9_X11}
+ __strd X0, X1, sp, 16
+ __strd X2, X3, sp, 24
+ __strd X4, X5, sp, 32
+ __strd X6, X7, sp, 40
+ __strd X8_X10, X9_X11, sp, 48
+
+ beq 1f
+ _chacha 20
+
+0: add sp, #76
+ pop {r4-r11, pc}
+
+1: _chacha 12
+ b 0b
+ENDPROC(chacha_doarm)
+
+/*
+ * void hchacha_block_arm(const u32 state[16], u32 out[8], int nrounds);
+ */
+ENTRY(hchacha_block_arm)
+ push {r1,r4-r11,lr}
+
+ cmp r2, #12 // ChaCha12 ?
+
+ mov r14, r0
+ ldmia r14!, {r0-r11} // load x0-x11
+ push {r10-r11} // store x10-x11 to stack
+ ldm r14, {r10-r12,r14} // load x12-x15
+ sub sp, #8
+
+ beq 1f
+ _chacha_permute 20
+
+ // Skip over (unused0-unused1, x10-x11)
+0: add sp, #16
+
+ // Fix up rotations of x12-x15
+ ror X12, X12, #drot
+ ror X13, X13, #drot
+ pop {r4} // load 'out'
+ ror X14, X14, #drot
+ ror X15, X15, #drot
+
+ // Store (x0-x3,x12-x15) to 'out'
+ stm r4, {X0,X1,X2,X3,X12,X13,X14,X15}
+
+ pop {r4-r11,pc}
+
+1: _chacha_permute 12
+ b 0b
+ENDPROC(hchacha_block_arm)
diff --git a/arch/arm/crypto/crc32-ce-core.S b/arch/arm/crypto/crc32-ce-core.S
new file mode 100644
index 0000000000..3f13a76b90
--- /dev/null
+++ b/arch/arm/crypto/crc32-ce-core.S
@@ -0,0 +1,306 @@
+/*
+ * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 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.
+ */
+
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Using hardware provided PCLMULQDQ instruction to accelerate the CRC32
+ * calculation.
+ * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
+ * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
+ * at:
+ * https://www.intel.com/products/processor/manuals/
+ * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
+ * Volume 2B: Instruction Set Reference, N-Z
+ *
+ * Authors: Gregory Prestas <Gregory_Prestas@us.xyratex.com>
+ * Alexander Boyko <Alexander_Boyko@xyratex.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .align 6
+ .arch armv8-a
+ .arch_extension crc
+ .fpu crypto-neon-fp-armv8
+
+.Lcrc32_constants:
+ /*
+ * [x4*128+32 mod P(x) << 32)]' << 1 = 0x154442bd4
+ * #define CONSTANT_R1 0x154442bd4LL
+ *
+ * [(x4*128-32 mod P(x) << 32)]' << 1 = 0x1c6e41596
+ * #define CONSTANT_R2 0x1c6e41596LL
+ */
+ .quad 0x0000000154442bd4
+ .quad 0x00000001c6e41596
+
+ /*
+ * [(x128+32 mod P(x) << 32)]' << 1 = 0x1751997d0
+ * #define CONSTANT_R3 0x1751997d0LL
+ *
+ * [(x128-32 mod P(x) << 32)]' << 1 = 0x0ccaa009e
+ * #define CONSTANT_R4 0x0ccaa009eLL
+ */
+ .quad 0x00000001751997d0
+ .quad 0x00000000ccaa009e
+
+ /*
+ * [(x64 mod P(x) << 32)]' << 1 = 0x163cd6124
+ * #define CONSTANT_R5 0x163cd6124LL
+ */
+ .quad 0x0000000163cd6124
+ .quad 0x00000000FFFFFFFF
+
+ /*
+ * #define CRCPOLY_TRUE_LE_FULL 0x1DB710641LL
+ *
+ * Barrett Reduction constant (u64`) = u` = (x**64 / P(x))`
+ * = 0x1F7011641LL
+ * #define CONSTANT_RU 0x1F7011641LL
+ */
+ .quad 0x00000001DB710641
+ .quad 0x00000001F7011641
+
+.Lcrc32c_constants:
+ .quad 0x00000000740eef02
+ .quad 0x000000009e4addf8
+ .quad 0x00000000f20c0dfe
+ .quad 0x000000014cd00bd6
+ .quad 0x00000000dd45aab8
+ .quad 0x00000000FFFFFFFF
+ .quad 0x0000000105ec76f0
+ .quad 0x00000000dea713f1
+
+ dCONSTANTl .req d0
+ dCONSTANTh .req d1
+ qCONSTANT .req q0
+
+ BUF .req r0
+ LEN .req r1
+ CRC .req r2
+
+ qzr .req q9
+
+ /**
+ * Calculate crc32
+ * BUF - buffer
+ * LEN - sizeof buffer (multiple of 16 bytes), LEN should be > 63
+ * CRC - initial crc32
+ * return %eax crc32
+ * uint crc32_pmull_le(unsigned char const *buffer,
+ * size_t len, uint crc32)
+ */
+ENTRY(crc32_pmull_le)
+ adr r3, .Lcrc32_constants
+ b 0f
+
+ENTRY(crc32c_pmull_le)
+ adr r3, .Lcrc32c_constants
+
+0: bic LEN, LEN, #15
+ vld1.8 {q1-q2}, [BUF, :128]!
+ vld1.8 {q3-q4}, [BUF, :128]!
+ vmov.i8 qzr, #0
+ vmov.i8 qCONSTANT, #0
+ vmov.32 dCONSTANTl[0], CRC
+ veor.8 d2, d2, dCONSTANTl
+ sub LEN, LEN, #0x40
+ cmp LEN, #0x40
+ blt less_64
+
+ vld1.64 {qCONSTANT}, [r3]
+
+loop_64: /* 64 bytes Full cache line folding */
+ sub LEN, LEN, #0x40
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q6, d5, dCONSTANTh
+ vmull.p64 q7, d7, dCONSTANTh
+ vmull.p64 q8, d9, dCONSTANTh
+
+ vmull.p64 q1, d2, dCONSTANTl
+ vmull.p64 q2, d4, dCONSTANTl
+ vmull.p64 q3, d6, dCONSTANTl
+ vmull.p64 q4, d8, dCONSTANTl
+
+ veor.8 q1, q1, q5
+ vld1.8 {q5}, [BUF, :128]!
+ veor.8 q2, q2, q6
+ vld1.8 {q6}, [BUF, :128]!
+ veor.8 q3, q3, q7
+ vld1.8 {q7}, [BUF, :128]!
+ veor.8 q4, q4, q8
+ vld1.8 {q8}, [BUF, :128]!
+
+ veor.8 q1, q1, q5
+ veor.8 q2, q2, q6
+ veor.8 q3, q3, q7
+ veor.8 q4, q4, q8
+
+ cmp LEN, #0x40
+ bge loop_64
+
+less_64: /* Folding cache line into 128bit */
+ vldr dCONSTANTl, [r3, #16]
+ vldr dCONSTANTh, [r3, #24]
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q2
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q3
+
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q4
+
+ teq LEN, #0
+ beq fold_64
+
+loop_16: /* Folding rest buffer into 128bit */
+ subs LEN, LEN, #0x10
+
+ vld1.8 {q2}, [BUF, :128]!
+ vmull.p64 q5, d3, dCONSTANTh
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q5
+ veor.8 q1, q1, q2
+
+ bne loop_16
+
+fold_64:
+ /* perform the last 64 bit fold, also adds 32 zeroes
+ * to the input stream */
+ vmull.p64 q2, d2, dCONSTANTh
+ vext.8 q1, q1, qzr, #8
+ veor.8 q1, q1, q2
+
+ /* final 32-bit fold */
+ vldr dCONSTANTl, [r3, #32]
+ vldr d6, [r3, #40]
+ vmov.i8 d7, #0
+
+ vext.8 q2, q1, qzr, #4
+ vand.8 d2, d2, d6
+ vmull.p64 q1, d2, dCONSTANTl
+ veor.8 q1, q1, q2
+
+ /* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
+ vldr dCONSTANTl, [r3, #48]
+ vldr dCONSTANTh, [r3, #56]
+
+ vand.8 q2, q1, q3
+ vext.8 q2, qzr, q2, #8
+ vmull.p64 q2, d5, dCONSTANTh
+ vand.8 q2, q2, q3
+ vmull.p64 q2, d4, dCONSTANTl
+ veor.8 q1, q1, q2
+ vmov r0, s5
+
+ bx lr
+ENDPROC(crc32_pmull_le)
+ENDPROC(crc32c_pmull_le)
+
+ .macro __crc32, c
+ subs ip, r2, #8
+ bmi .Ltail\c
+
+ tst r1, #3
+ bne .Lunaligned\c
+
+ teq ip, #0
+.Laligned8\c:
+ ldrd r2, r3, [r1], #8
+ARM_BE8(rev r2, r2 )
+ARM_BE8(rev r3, r3 )
+ crc32\c\()w r0, r0, r2
+ crc32\c\()w r0, r0, r3
+ bxeq lr
+ subs ip, ip, #8
+ bpl .Laligned8\c
+
+.Ltail\c:
+ tst ip, #4
+ beq 2f
+ ldr r3, [r1], #4
+ARM_BE8(rev r3, r3 )
+ crc32\c\()w r0, r0, r3
+
+2: tst ip, #2
+ beq 1f
+ ldrh r3, [r1], #2
+ARM_BE8(rev16 r3, r3 )
+ crc32\c\()h r0, r0, r3
+
+1: tst ip, #1
+ bxeq lr
+ ldrb r3, [r1]
+ crc32\c\()b r0, r0, r3
+ bx lr
+
+.Lunaligned\c:
+ tst r1, #1
+ beq 2f
+ ldrb r3, [r1], #1
+ subs r2, r2, #1
+ crc32\c\()b r0, r0, r3
+
+ tst r1, #2
+ beq 0f
+2: ldrh r3, [r1], #2
+ subs r2, r2, #2
+ARM_BE8(rev16 r3, r3 )
+ crc32\c\()h r0, r0, r3
+
+0: subs ip, r2, #8
+ bpl .Laligned8\c
+ b .Ltail\c
+ .endm
+
+ .align 5
+ENTRY(crc32_armv8_le)
+ __crc32
+ENDPROC(crc32_armv8_le)
+
+ .align 5
+ENTRY(crc32c_armv8_le)
+ __crc32 c
+ENDPROC(crc32c_armv8_le)
diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c
new file mode 100644
index 0000000000..2208445808
--- /dev/null
+++ b/arch/arm/crypto/crc32-ce-glue.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/cpufeature.h>
+#include <linux/crc32.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+
+#define PMULL_MIN_LEN 64L /* minimum size of buffer
+ * for crc32_pmull_le_16 */
+#define SCALE_F 16L /* size of NEON register */
+
+asmlinkage u32 crc32_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+asmlinkage u32 crc32c_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+static u32 (*fallback_crc32)(u32 init_crc, const u8 buf[], u32 len);
+static u32 (*fallback_crc32c)(u32 init_crc, const u8 buf[], u32 len);
+
+static int crc32_cra_init(struct crypto_tfm *tfm)
+{
+ u32 *key = crypto_tfm_ctx(tfm);
+
+ *key = 0;
+ return 0;
+}
+
+static int crc32c_cra_init(struct crypto_tfm *tfm)
+{
+ u32 *key = crypto_tfm_ctx(tfm);
+
+ *key = ~0;
+ return 0;
+}
+
+static int crc32_setkey(struct crypto_shash *hash, const u8 *key,
+ unsigned int keylen)
+{
+ u32 *mctx = crypto_shash_ctx(hash);
+
+ if (keylen != sizeof(u32))
+ return -EINVAL;
+ *mctx = le32_to_cpup((__le32 *)key);
+ return 0;
+}
+
+static int crc32_init(struct shash_desc *desc)
+{
+ u32 *mctx = crypto_shash_ctx(desc->tfm);
+ u32 *crc = shash_desc_ctx(desc);
+
+ *crc = *mctx;
+ return 0;
+}
+
+static int crc32_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u32 *crc = shash_desc_ctx(desc);
+
+ *crc = crc32_armv8_le(*crc, data, length);
+ return 0;
+}
+
+static int crc32c_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u32 *crc = shash_desc_ctx(desc);
+
+ *crc = crc32c_armv8_le(*crc, data, length);
+ return 0;
+}
+
+static int crc32_final(struct shash_desc *desc, u8 *out)
+{
+ u32 *crc = shash_desc_ctx(desc);
+
+ put_unaligned_le32(*crc, out);
+ return 0;
+}
+
+static int crc32c_final(struct shash_desc *desc, u8 *out)
+{
+ u32 *crc = shash_desc_ctx(desc);
+
+ put_unaligned_le32(~*crc, out);
+ return 0;
+}
+
+static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u32 *crc = shash_desc_ctx(desc);
+ unsigned int l;
+
+ if (crypto_simd_usable()) {
+ if ((u32)data % SCALE_F) {
+ l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F));
+
+ *crc = fallback_crc32(*crc, data, l);
+
+ data += l;
+ length -= l;
+ }
+
+ if (length >= PMULL_MIN_LEN) {
+ l = round_down(length, SCALE_F);
+
+ kernel_neon_begin();
+ *crc = crc32_pmull_le(data, l, *crc);
+ kernel_neon_end();
+
+ data += l;
+ length -= l;
+ }
+ }
+
+ if (length > 0)
+ *crc = fallback_crc32(*crc, data, length);
+
+ return 0;
+}
+
+static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u32 *crc = shash_desc_ctx(desc);
+ unsigned int l;
+
+ if (crypto_simd_usable()) {
+ if ((u32)data % SCALE_F) {
+ l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F));
+
+ *crc = fallback_crc32c(*crc, data, l);
+
+ data += l;
+ length -= l;
+ }
+
+ if (length >= PMULL_MIN_LEN) {
+ l = round_down(length, SCALE_F);
+
+ kernel_neon_begin();
+ *crc = crc32c_pmull_le(data, l, *crc);
+ kernel_neon_end();
+
+ data += l;
+ length -= l;
+ }
+ }
+
+ if (length > 0)
+ *crc = fallback_crc32c(*crc, data, length);
+
+ return 0;
+}
+
+static struct shash_alg crc32_pmull_algs[] = { {
+ .setkey = crc32_setkey,
+ .init = crc32_init,
+ .update = crc32_update,
+ .final = crc32_final,
+ .descsize = sizeof(u32),
+ .digestsize = sizeof(u32),
+
+ .base.cra_ctxsize = sizeof(u32),
+ .base.cra_init = crc32_cra_init,
+ .base.cra_name = "crc32",
+ .base.cra_driver_name = "crc32-arm-ce",
+ .base.cra_priority = 200,
+ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY,
+ .base.cra_blocksize = 1,
+ .base.cra_module = THIS_MODULE,
+}, {
+ .setkey = crc32_setkey,
+ .init = crc32_init,
+ .update = crc32c_update,
+ .final = crc32c_final,
+ .descsize = sizeof(u32),
+ .digestsize = sizeof(u32),
+
+ .base.cra_ctxsize = sizeof(u32),
+ .base.cra_init = crc32c_cra_init,
+ .base.cra_name = "crc32c",
+ .base.cra_driver_name = "crc32c-arm-ce",
+ .base.cra_priority = 200,
+ .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY,
+ .base.cra_blocksize = 1,
+ .base.cra_module = THIS_MODULE,
+} };
+
+static int __init crc32_pmull_mod_init(void)
+{
+ if (elf_hwcap2 & HWCAP2_PMULL) {
+ crc32_pmull_algs[0].update = crc32_pmull_update;
+ crc32_pmull_algs[1].update = crc32c_pmull_update;
+
+ if (elf_hwcap2 & HWCAP2_CRC32) {
+ fallback_crc32 = crc32_armv8_le;
+ fallback_crc32c = crc32c_armv8_le;
+ } else {
+ fallback_crc32 = crc32_le;
+ fallback_crc32c = __crc32c_le;
+ }
+ } else if (!(elf_hwcap2 & HWCAP2_CRC32)) {
+ return -ENODEV;
+ }
+
+ return crypto_register_shashes(crc32_pmull_algs,
+ ARRAY_SIZE(crc32_pmull_algs));
+}
+
+static void __exit crc32_pmull_mod_exit(void)
+{
+ crypto_unregister_shashes(crc32_pmull_algs,
+ ARRAY_SIZE(crc32_pmull_algs));
+}
+
+static const struct cpu_feature __maybe_unused crc32_cpu_feature[] = {
+ { cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { }
+};
+MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature);
+
+module_init(crc32_pmull_mod_init);
+module_exit(crc32_pmull_mod_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32c");
diff --git a/arch/arm/crypto/crct10dif-ce-core.S b/arch/arm/crypto/crct10dif-ce-core.S
new file mode 100644
index 0000000000..46c02c518a
--- /dev/null
+++ b/arch/arm/crypto/crct10dif-ce-core.S
@@ -0,0 +1,381 @@
+//
+// Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions
+//
+// Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+// Copyright (C) 2019 Google LLC <ebiggers@google.com>
+//
+// 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.
+//
+
+// Derived from the x86 version:
+//
+// Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
+//
+// Copyright (c) 2013, Intel Corporation
+//
+// Authors:
+// Erdinc Ozturk <erdinc.ozturk@intel.com>
+// Vinodh Gopal <vinodh.gopal@intel.com>
+// James Guilford <james.guilford@intel.com>
+// Tim Chen <tim.c.chen@linux.intel.com>
+//
+// This software is available to you under a choice of one of two
+// licenses. You may choose to be licensed under the terms of the GNU
+// General Public License (GPL) Version 2, available from the file
+// COPYING in the main directory of this source tree, or the
+// OpenIB.org BSD license below:
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+// * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//
+// * Redistributions in binary form must reproduce the above copyright
+// notice, this list of conditions and the following disclaimer in the
+// documentation and/or other materials provided with the
+// distribution.
+//
+// * Neither the name of the Intel Corporation nor the names of its
+// contributors may be used to endorse or promote products derived from
+// this software without specific prior written permission.
+//
+//
+// THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
+// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
+// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+// LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+// Reference paper titled "Fast CRC Computation for Generic
+// Polynomials Using PCLMULQDQ Instruction"
+// URL: http://www.intel.com/content/dam/www/public/us/en/documents
+// /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
+//
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define CPU_LE(code...)
+#else
+#define CPU_LE(code...) code
+#endif
+
+ .text
+ .arch armv8-a
+ .fpu crypto-neon-fp-armv8
+
+ init_crc .req r0
+ buf .req r1
+ len .req r2
+
+ fold_consts_ptr .req ip
+
+ q0l .req d0
+ q0h .req d1
+ q1l .req d2
+ q1h .req d3
+ q2l .req d4
+ q2h .req d5
+ q3l .req d6
+ q3h .req d7
+ q4l .req d8
+ q4h .req d9
+ q5l .req d10
+ q5h .req d11
+ q6l .req d12
+ q6h .req d13
+ q7l .req d14
+ q7h .req d15
+ q8l .req d16
+ q8h .req d17
+ q9l .req d18
+ q9h .req d19
+ q10l .req d20
+ q10h .req d21
+ q11l .req d22
+ q11h .req d23
+ q12l .req d24
+ q12h .req d25
+
+ FOLD_CONSTS .req q10
+ FOLD_CONST_L .req q10l
+ FOLD_CONST_H .req q10h
+
+ // Fold reg1, reg2 into the next 32 data bytes, storing the result back
+ // into reg1, reg2.
+ .macro fold_32_bytes, reg1, reg2
+ vld1.64 {q11-q12}, [buf]!
+
+ vmull.p64 q8, \reg1\()h, FOLD_CONST_H
+ vmull.p64 \reg1, \reg1\()l, FOLD_CONST_L
+ vmull.p64 q9, \reg2\()h, FOLD_CONST_H
+ vmull.p64 \reg2, \reg2\()l, FOLD_CONST_L
+
+CPU_LE( vrev64.8 q11, q11 )
+CPU_LE( vrev64.8 q12, q12 )
+ vswp q11l, q11h
+ vswp q12l, q12h
+
+ veor.8 \reg1, \reg1, q8
+ veor.8 \reg2, \reg2, q9
+ veor.8 \reg1, \reg1, q11
+ veor.8 \reg2, \reg2, q12
+ .endm
+
+ // Fold src_reg into dst_reg, optionally loading the next fold constants
+ .macro fold_16_bytes, src_reg, dst_reg, load_next_consts
+ vmull.p64 q8, \src_reg\()l, FOLD_CONST_L
+ vmull.p64 \src_reg, \src_reg\()h, FOLD_CONST_H
+ .ifnb \load_next_consts
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+ .endif
+ veor.8 \dst_reg, \dst_reg, q8
+ veor.8 \dst_reg, \dst_reg, \src_reg
+ .endm
+
+ .macro __adrl, out, sym
+ movw \out, #:lower16:\sym
+ movt \out, #:upper16:\sym
+ .endm
+
+//
+// u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
+//
+// Assumes len >= 16.
+//
+ENTRY(crc_t10dif_pmull)
+
+ // For sizes less than 256 bytes, we can't fold 128 bytes at a time.
+ cmp len, #256
+ blt .Lless_than_256_bytes
+
+ __adrl fold_consts_ptr, .Lfold_across_128_bytes_consts
+
+ // Load the first 128 data bytes. Byte swapping is necessary to make
+ // the bit order match the polynomial coefficient order.
+ vld1.64 {q0-q1}, [buf]!
+ vld1.64 {q2-q3}, [buf]!
+ vld1.64 {q4-q5}, [buf]!
+ vld1.64 {q6-q7}, [buf]!
+CPU_LE( vrev64.8 q0, q0 )
+CPU_LE( vrev64.8 q1, q1 )
+CPU_LE( vrev64.8 q2, q2 )
+CPU_LE( vrev64.8 q3, q3 )
+CPU_LE( vrev64.8 q4, q4 )
+CPU_LE( vrev64.8 q5, q5 )
+CPU_LE( vrev64.8 q6, q6 )
+CPU_LE( vrev64.8 q7, q7 )
+ vswp q0l, q0h
+ vswp q1l, q1h
+ vswp q2l, q2h
+ vswp q3l, q3h
+ vswp q4l, q4h
+ vswp q5l, q5h
+ vswp q6l, q6h
+ vswp q7l, q7h
+
+ // XOR the first 16 data *bits* with the initial CRC value.
+ vmov.i8 q8h, #0
+ vmov.u16 q8h[3], init_crc
+ veor q0h, q0h, q8h
+
+ // Load the constants for folding across 128 bytes.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+
+ // Subtract 128 for the 128 data bytes just consumed. Subtract another
+ // 128 to simplify the termination condition of the following loop.
+ sub len, len, #256
+
+ // While >= 128 data bytes remain (not counting q0-q7), fold the 128
+ // bytes q0-q7 into them, storing the result back into q0-q7.
+.Lfold_128_bytes_loop:
+ fold_32_bytes q0, q1
+ fold_32_bytes q2, q3
+ fold_32_bytes q4, q5
+ fold_32_bytes q6, q7
+ subs len, len, #128
+ bge .Lfold_128_bytes_loop
+
+ // Now fold the 112 bytes in q0-q6 into the 16 bytes in q7.
+
+ // Fold across 64 bytes.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+ fold_16_bytes q0, q4
+ fold_16_bytes q1, q5
+ fold_16_bytes q2, q6
+ fold_16_bytes q3, q7, 1
+ // Fold across 32 bytes.
+ fold_16_bytes q4, q6
+ fold_16_bytes q5, q7, 1
+ // Fold across 16 bytes.
+ fold_16_bytes q6, q7
+
+ // Add 128 to get the correct number of data bytes remaining in 0...127
+ // (not counting q7), following the previous extra subtraction by 128.
+ // Then subtract 16 to simplify the termination condition of the
+ // following loop.
+ adds len, len, #(128-16)
+
+ // While >= 16 data bytes remain (not counting q7), fold the 16 bytes q7
+ // into them, storing the result back into q7.
+ blt .Lfold_16_bytes_loop_done
+.Lfold_16_bytes_loop:
+ vmull.p64 q8, q7l, FOLD_CONST_L
+ vmull.p64 q7, q7h, FOLD_CONST_H
+ veor.8 q7, q7, q8
+ vld1.64 {q0}, [buf]!
+CPU_LE( vrev64.8 q0, q0 )
+ vswp q0l, q0h
+ veor.8 q7, q7, q0
+ subs len, len, #16
+ bge .Lfold_16_bytes_loop
+
+.Lfold_16_bytes_loop_done:
+ // Add 16 to get the correct number of data bytes remaining in 0...15
+ // (not counting q7), following the previous extra subtraction by 16.
+ adds len, len, #16
+ beq .Lreduce_final_16_bytes
+
+.Lhandle_partial_segment:
+ // Reduce the last '16 + len' bytes where 1 <= len <= 15 and the first
+ // 16 bytes are in q7 and the rest are the remaining data in 'buf'. To
+ // do this without needing a fold constant for each possible 'len',
+ // redivide the bytes into a first chunk of 'len' bytes and a second
+ // chunk of 16 bytes, then fold the first chunk into the second.
+
+ // q0 = last 16 original data bytes
+ add buf, buf, len
+ sub buf, buf, #16
+ vld1.64 {q0}, [buf]
+CPU_LE( vrev64.8 q0, q0 )
+ vswp q0l, q0h
+
+ // q1 = high order part of second chunk: q7 left-shifted by 'len' bytes.
+ __adrl r3, .Lbyteshift_table + 16
+ sub r3, r3, len
+ vld1.8 {q2}, [r3]
+ vtbl.8 q1l, {q7l-q7h}, q2l
+ vtbl.8 q1h, {q7l-q7h}, q2h
+
+ // q3 = first chunk: q7 right-shifted by '16-len' bytes.
+ vmov.i8 q3, #0x80
+ veor.8 q2, q2, q3
+ vtbl.8 q3l, {q7l-q7h}, q2l
+ vtbl.8 q3h, {q7l-q7h}, q2h
+
+ // Convert to 8-bit masks: 'len' 0x00 bytes, then '16-len' 0xff bytes.
+ vshr.s8 q2, q2, #7
+
+ // q2 = second chunk: 'len' bytes from q0 (low-order bytes),
+ // then '16-len' bytes from q1 (high-order bytes).
+ vbsl.8 q2, q1, q0
+
+ // Fold the first chunk into the second chunk, storing the result in q7.
+ vmull.p64 q0, q3l, FOLD_CONST_L
+ vmull.p64 q7, q3h, FOLD_CONST_H
+ veor.8 q7, q7, q0
+ veor.8 q7, q7, q2
+
+.Lreduce_final_16_bytes:
+ // Reduce the 128-bit value M(x), stored in q7, to the final 16-bit CRC.
+
+ // Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+
+ // Fold the high 64 bits into the low 64 bits, while also multiplying by
+ // x^64. This produces a 128-bit value congruent to x^64 * M(x) and
+ // whose low 48 bits are 0.
+ vmull.p64 q0, q7h, FOLD_CONST_H // high bits * x^48 * (x^80 mod G(x))
+ veor.8 q0h, q0h, q7l // + low bits * x^64
+
+ // Fold the high 32 bits into the low 96 bits. This produces a 96-bit
+ // value congruent to x^64 * M(x) and whose low 48 bits are 0.
+ vmov.i8 q1, #0
+ vmov s4, s3 // extract high 32 bits
+ vmov s3, s5 // zero high 32 bits
+ vmull.p64 q1, q1l, FOLD_CONST_L // high 32 bits * x^48 * (x^48 mod G(x))
+ veor.8 q0, q0, q1 // + low bits
+
+ // Load G(x) and floor(x^48 / G(x)).
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]
+
+ // Use Barrett reduction to compute the final CRC value.
+ vmull.p64 q1, q0h, FOLD_CONST_H // high 32 bits * floor(x^48 / G(x))
+ vshr.u64 q1l, q1l, #32 // /= x^32
+ vmull.p64 q1, q1l, FOLD_CONST_L // *= G(x)
+ vshr.u64 q0l, q0l, #48
+ veor.8 q0l, q0l, q1l // + low 16 nonzero bits
+ // Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of q0.
+
+ vmov.u16 r0, q0l[0]
+ bx lr
+
+.Lless_than_256_bytes:
+ // Checksumming a buffer of length 16...255 bytes
+
+ __adrl fold_consts_ptr, .Lfold_across_16_bytes_consts
+
+ // Load the first 16 data bytes.
+ vld1.64 {q7}, [buf]!
+CPU_LE( vrev64.8 q7, q7 )
+ vswp q7l, q7h
+
+ // XOR the first 16 data *bits* with the initial CRC value.
+ vmov.i8 q0h, #0
+ vmov.u16 q0h[3], init_crc
+ veor.8 q7h, q7h, q0h
+
+ // Load the fold-across-16-bytes constants.
+ vld1.64 {FOLD_CONSTS}, [fold_consts_ptr, :128]!
+
+ cmp len, #16
+ beq .Lreduce_final_16_bytes // len == 16
+ subs len, len, #32
+ addlt len, len, #16
+ blt .Lhandle_partial_segment // 17 <= len <= 31
+ b .Lfold_16_bytes_loop // 32 <= len <= 255
+ENDPROC(crc_t10dif_pmull)
+
+ .section ".rodata", "a"
+ .align 4
+
+// Fold constants precomputed from the polynomial 0x18bb7
+// G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+.Lfold_across_128_bytes_consts:
+ .quad 0x0000000000006123 // x^(8*128) mod G(x)
+ .quad 0x0000000000002295 // x^(8*128+64) mod G(x)
+// .Lfold_across_64_bytes_consts:
+ .quad 0x0000000000001069 // x^(4*128) mod G(x)
+ .quad 0x000000000000dd31 // x^(4*128+64) mod G(x)
+// .Lfold_across_32_bytes_consts:
+ .quad 0x000000000000857d // x^(2*128) mod G(x)
+ .quad 0x0000000000007acc // x^(2*128+64) mod G(x)
+.Lfold_across_16_bytes_consts:
+ .quad 0x000000000000a010 // x^(1*128) mod G(x)
+ .quad 0x0000000000001faa // x^(1*128+64) mod G(x)
+// .Lfinal_fold_consts:
+ .quad 0x1368000000000000 // x^48 * (x^48 mod G(x))
+ .quad 0x2d56000000000000 // x^48 * (x^80 mod G(x))
+// .Lbarrett_reduction_consts:
+ .quad 0x0000000000018bb7 // G(x)
+ .quad 0x00000001f65a57f8 // floor(x^48 / G(x))
+
+// For 1 <= len <= 15, the 16-byte vector beginning at &byteshift_table[16 -
+// len] is the index vector to shift left by 'len' bytes, and is also {0x80,
+// ..., 0x80} XOR the index vector to shift right by '16 - len' bytes.
+.Lbyteshift_table:
+ .byte 0x0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87
+ .byte 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f
+ .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
+ .byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe , 0x0
diff --git a/arch/arm/crypto/crct10dif-ce-glue.c b/arch/arm/crypto/crct10dif-ce-glue.c
new file mode 100644
index 0000000000..e9191a8c87
--- /dev/null
+++ b/arch/arm/crypto/crct10dif-ce-glue.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/crc-t10dif.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
+
+asmlinkage u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
+
+static int crct10dif_init(struct shash_desc *desc)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *crc = 0;
+ return 0;
+}
+
+static int crct10dif_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
+ kernel_neon_begin();
+ *crc = crc_t10dif_pmull(*crc, data, length);
+ kernel_neon_end();
+ } else {
+ *crc = crc_t10dif_generic(*crc, data, length);
+ }
+
+ return 0;
+}
+
+static int crct10dif_final(struct shash_desc *desc, u8 *out)
+{
+ u16 *crc = shash_desc_ctx(desc);
+
+ *(u16 *)out = *crc;
+ return 0;
+}
+
+static struct shash_alg crc_t10dif_alg = {
+ .digestsize = CRC_T10DIF_DIGEST_SIZE,
+ .init = crct10dif_init,
+ .update = crct10dif_update,
+ .final = crct10dif_final,
+ .descsize = CRC_T10DIF_DIGEST_SIZE,
+
+ .base.cra_name = "crct10dif",
+ .base.cra_driver_name = "crct10dif-arm-ce",
+ .base.cra_priority = 200,
+ .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
+ .base.cra_module = THIS_MODULE,
+};
+
+static int __init crc_t10dif_mod_init(void)
+{
+ if (!(elf_hwcap2 & HWCAP2_PMULL))
+ return -ENODEV;
+
+ return crypto_register_shash(&crc_t10dif_alg);
+}
+
+static void __exit crc_t10dif_mod_exit(void)
+{
+ crypto_unregister_shash(&crc_t10dif_alg);
+}
+
+module_init(crc_t10dif_mod_init);
+module_exit(crc_t10dif_mod_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("crct10dif");
diff --git a/arch/arm/crypto/curve25519-core.S b/arch/arm/crypto/curve25519-core.S
new file mode 100644
index 0000000000..b697fa5d05
--- /dev/null
+++ b/arch/arm/crypto/curve25519-core.S
@@ -0,0 +1,2062 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <linux/linkage.h>
+
+.text
+.arch armv7-a
+.fpu neon
+.align 4
+
+ENTRY(curve25519_neon)
+ push {r4-r11, lr}
+ mov ip, sp
+ sub r3, sp, #704
+ and r3, r3, #0xfffffff0
+ mov sp, r3
+ movw r4, #0
+ movw r5, #254
+ vmov.i32 q0, #1
+ vshr.u64 q1, q0, #7
+ vshr.u64 q0, q0, #8
+ vmov.i32 d4, #19
+ vmov.i32 d5, #38
+ add r6, sp, #480
+ vst1.8 {d2-d3}, [r6, : 128]!
+ vst1.8 {d0-d1}, [r6, : 128]!
+ vst1.8 {d4-d5}, [r6, : 128]
+ add r6, r3, #0
+ vmov.i32 q2, #0
+ vst1.8 {d4-d5}, [r6, : 128]!
+ vst1.8 {d4-d5}, [r6, : 128]!
+ vst1.8 d4, [r6, : 64]
+ add r6, r3, #0
+ movw r7, #960
+ sub r7, r7, #2
+ neg r7, r7
+ sub r7, r7, r7, LSL #7
+ str r7, [r6]
+ add r6, sp, #672
+ vld1.8 {d4-d5}, [r1]!
+ vld1.8 {d6-d7}, [r1]
+ vst1.8 {d4-d5}, [r6, : 128]!
+ vst1.8 {d6-d7}, [r6, : 128]
+ sub r1, r6, #16
+ ldrb r6, [r1]
+ and r6, r6, #248
+ strb r6, [r1]
+ ldrb r6, [r1, #31]
+ and r6, r6, #127
+ orr r6, r6, #64
+ strb r6, [r1, #31]
+ vmov.i64 q2, #0xffffffff
+ vshr.u64 q3, q2, #7
+ vshr.u64 q2, q2, #6
+ vld1.8 {d8}, [r2]
+ vld1.8 {d10}, [r2]
+ add r2, r2, #6
+ vld1.8 {d12}, [r2]
+ vld1.8 {d14}, [r2]
+ add r2, r2, #6
+ vld1.8 {d16}, [r2]
+ add r2, r2, #4
+ vld1.8 {d18}, [r2]
+ vld1.8 {d20}, [r2]
+ add r2, r2, #6
+ vld1.8 {d22}, [r2]
+ add r2, r2, #2
+ vld1.8 {d24}, [r2]
+ vld1.8 {d26}, [r2]
+ vshr.u64 q5, q5, #26
+ vshr.u64 q6, q6, #3
+ vshr.u64 q7, q7, #29
+ vshr.u64 q8, q8, #6
+ vshr.u64 q10, q10, #25
+ vshr.u64 q11, q11, #3
+ vshr.u64 q12, q12, #12
+ vshr.u64 q13, q13, #38
+ vand q4, q4, q2
+ vand q6, q6, q2
+ vand q8, q8, q2
+ vand q10, q10, q2
+ vand q2, q12, q2
+ vand q5, q5, q3
+ vand q7, q7, q3
+ vand q9, q9, q3
+ vand q11, q11, q3
+ vand q3, q13, q3
+ add r2, r3, #48
+ vadd.i64 q12, q4, q1
+ vadd.i64 q13, q10, q1
+ vshr.s64 q12, q12, #26
+ vshr.s64 q13, q13, #26
+ vadd.i64 q5, q5, q12
+ vshl.i64 q12, q12, #26
+ vadd.i64 q14, q5, q0
+ vadd.i64 q11, q11, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q15, q11, q0
+ vsub.i64 q4, q4, q12
+ vshr.s64 q12, q14, #25
+ vsub.i64 q10, q10, q13
+ vshr.s64 q13, q15, #25
+ vadd.i64 q6, q6, q12
+ vshl.i64 q12, q12, #25
+ vadd.i64 q14, q6, q1
+ vadd.i64 q2, q2, q13
+ vsub.i64 q5, q5, q12
+ vshr.s64 q12, q14, #26
+ vshl.i64 q13, q13, #25
+ vadd.i64 q14, q2, q1
+ vadd.i64 q7, q7, q12
+ vshl.i64 q12, q12, #26
+ vadd.i64 q15, q7, q0
+ vsub.i64 q11, q11, q13
+ vshr.s64 q13, q14, #26
+ vsub.i64 q6, q6, q12
+ vshr.s64 q12, q15, #25
+ vadd.i64 q3, q3, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q14, q3, q0
+ vadd.i64 q8, q8, q12
+ vshl.i64 q12, q12, #25
+ vadd.i64 q15, q8, q1
+ add r2, r2, #8
+ vsub.i64 q2, q2, q13
+ vshr.s64 q13, q14, #25
+ vsub.i64 q7, q7, q12
+ vshr.s64 q12, q15, #26
+ vadd.i64 q14, q13, q13
+ vadd.i64 q9, q9, q12
+ vtrn.32 d12, d14
+ vshl.i64 q12, q12, #26
+ vtrn.32 d13, d15
+ vadd.i64 q0, q9, q0
+ vadd.i64 q4, q4, q14
+ vst1.8 d12, [r2, : 64]!
+ vshl.i64 q6, q13, #4
+ vsub.i64 q7, q8, q12
+ vshr.s64 q0, q0, #25
+ vadd.i64 q4, q4, q6
+ vadd.i64 q6, q10, q0
+ vshl.i64 q0, q0, #25
+ vadd.i64 q8, q6, q1
+ vadd.i64 q4, q4, q13
+ vshl.i64 q10, q13, #25
+ vadd.i64 q1, q4, q1
+ vsub.i64 q0, q9, q0
+ vshr.s64 q8, q8, #26
+ vsub.i64 q3, q3, q10
+ vtrn.32 d14, d0
+ vshr.s64 q1, q1, #26
+ vtrn.32 d15, d1
+ vadd.i64 q0, q11, q8
+ vst1.8 d14, [r2, : 64]
+ vshl.i64 q7, q8, #26
+ vadd.i64 q5, q5, q1
+ vtrn.32 d4, d6
+ vshl.i64 q1, q1, #26
+ vtrn.32 d5, d7
+ vsub.i64 q3, q6, q7
+ add r2, r2, #16
+ vsub.i64 q1, q4, q1
+ vst1.8 d4, [r2, : 64]
+ vtrn.32 d6, d0
+ vtrn.32 d7, d1
+ sub r2, r2, #8
+ vtrn.32 d2, d10
+ vtrn.32 d3, d11
+ vst1.8 d6, [r2, : 64]
+ sub r2, r2, #24
+ vst1.8 d2, [r2, : 64]
+ add r2, r3, #96
+ vmov.i32 q0, #0
+ vmov.i64 d2, #0xff
+ vmov.i64 d3, #0
+ vshr.u32 q1, q1, #7
+ vst1.8 {d2-d3}, [r2, : 128]!
+ vst1.8 {d0-d1}, [r2, : 128]!
+ vst1.8 d0, [r2, : 64]
+ add r2, r3, #144
+ vmov.i32 q0, #0
+ vst1.8 {d0-d1}, [r2, : 128]!
+ vst1.8 {d0-d1}, [r2, : 128]!
+ vst1.8 d0, [r2, : 64]
+ add r2, r3, #240
+ vmov.i32 q0, #0
+ vmov.i64 d2, #0xff
+ vmov.i64 d3, #0
+ vshr.u32 q1, q1, #7
+ vst1.8 {d2-d3}, [r2, : 128]!
+ vst1.8 {d0-d1}, [r2, : 128]!
+ vst1.8 d0, [r2, : 64]
+ add r2, r3, #48
+ add r6, r3, #192
+ vld1.8 {d0-d1}, [r2, : 128]!
+ vld1.8 {d2-d3}, [r2, : 128]!
+ vld1.8 {d4}, [r2, : 64]
+ vst1.8 {d0-d1}, [r6, : 128]!
+ vst1.8 {d2-d3}, [r6, : 128]!
+ vst1.8 d4, [r6, : 64]
+.Lmainloop:
+ mov r2, r5, LSR #3
+ and r6, r5, #7
+ ldrb r2, [r1, r2]
+ mov r2, r2, LSR r6
+ and r2, r2, #1
+ str r5, [sp, #456]
+ eor r4, r4, r2
+ str r2, [sp, #460]
+ neg r2, r4
+ add r4, r3, #96
+ add r5, r3, #192
+ add r6, r3, #144
+ vld1.8 {d8-d9}, [r4, : 128]!
+ add r7, r3, #240
+ vld1.8 {d10-d11}, [r5, : 128]!
+ veor q6, q4, q5
+ vld1.8 {d14-d15}, [r6, : 128]!
+ vdup.i32 q8, r2
+ vld1.8 {d18-d19}, [r7, : 128]!
+ veor q10, q7, q9
+ vld1.8 {d22-d23}, [r4, : 128]!
+ vand q6, q6, q8
+ vld1.8 {d24-d25}, [r5, : 128]!
+ vand q10, q10, q8
+ vld1.8 {d26-d27}, [r6, : 128]!
+ veor q4, q4, q6
+ vld1.8 {d28-d29}, [r7, : 128]!
+ veor q5, q5, q6
+ vld1.8 {d0}, [r4, : 64]
+ veor q6, q7, q10
+ vld1.8 {d2}, [r5, : 64]
+ veor q7, q9, q10
+ vld1.8 {d4}, [r6, : 64]
+ veor q9, q11, q12
+ vld1.8 {d6}, [r7, : 64]
+ veor q10, q0, q1
+ sub r2, r4, #32
+ vand q9, q9, q8
+ sub r4, r5, #32
+ vand q10, q10, q8
+ sub r5, r6, #32
+ veor q11, q11, q9
+ sub r6, r7, #32
+ veor q0, q0, q10
+ veor q9, q12, q9
+ veor q1, q1, q10
+ veor q10, q13, q14
+ veor q12, q2, q3
+ vand q10, q10, q8
+ vand q8, q12, q8
+ veor q12, q13, q10
+ veor q2, q2, q8
+ veor q10, q14, q10
+ veor q3, q3, q8
+ vadd.i32 q8, q4, q6
+ vsub.i32 q4, q4, q6
+ vst1.8 {d16-d17}, [r2, : 128]!
+ vadd.i32 q6, q11, q12
+ vst1.8 {d8-d9}, [r5, : 128]!
+ vsub.i32 q4, q11, q12
+ vst1.8 {d12-d13}, [r2, : 128]!
+ vadd.i32 q6, q0, q2
+ vst1.8 {d8-d9}, [r5, : 128]!
+ vsub.i32 q0, q0, q2
+ vst1.8 d12, [r2, : 64]
+ vadd.i32 q2, q5, q7
+ vst1.8 d0, [r5, : 64]
+ vsub.i32 q0, q5, q7
+ vst1.8 {d4-d5}, [r4, : 128]!
+ vadd.i32 q2, q9, q10
+ vst1.8 {d0-d1}, [r6, : 128]!
+ vsub.i32 q0, q9, q10
+ vst1.8 {d4-d5}, [r4, : 128]!
+ vadd.i32 q2, q1, q3
+ vst1.8 {d0-d1}, [r6, : 128]!
+ vsub.i32 q0, q1, q3
+ vst1.8 d4, [r4, : 64]
+ vst1.8 d0, [r6, : 64]
+ add r2, sp, #512
+ add r4, r3, #96
+ add r5, r3, #144
+ vld1.8 {d0-d1}, [r2, : 128]
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vld1.8 {d4-d5}, [r5, : 128]!
+ vzip.i32 q1, q2
+ vld1.8 {d6-d7}, [r4, : 128]!
+ vld1.8 {d8-d9}, [r5, : 128]!
+ vshl.i32 q5, q1, #1
+ vzip.i32 q3, q4
+ vshl.i32 q6, q2, #1
+ vld1.8 {d14}, [r4, : 64]
+ vshl.i32 q8, q3, #1
+ vld1.8 {d15}, [r5, : 64]
+ vshl.i32 q9, q4, #1
+ vmul.i32 d21, d7, d1
+ vtrn.32 d14, d15
+ vmul.i32 q11, q4, q0
+ vmul.i32 q0, q7, q0
+ vmull.s32 q12, d2, d2
+ vmlal.s32 q12, d11, d1
+ vmlal.s32 q12, d12, d0
+ vmlal.s32 q12, d13, d23
+ vmlal.s32 q12, d16, d22
+ vmlal.s32 q12, d7, d21
+ vmull.s32 q10, d2, d11
+ vmlal.s32 q10, d4, d1
+ vmlal.s32 q10, d13, d0
+ vmlal.s32 q10, d6, d23
+ vmlal.s32 q10, d17, d22
+ vmull.s32 q13, d10, d4
+ vmlal.s32 q13, d11, d3
+ vmlal.s32 q13, d13, d1
+ vmlal.s32 q13, d16, d0
+ vmlal.s32 q13, d17, d23
+ vmlal.s32 q13, d8, d22
+ vmull.s32 q1, d10, d5
+ vmlal.s32 q1, d11, d4
+ vmlal.s32 q1, d6, d1
+ vmlal.s32 q1, d17, d0
+ vmlal.s32 q1, d8, d23
+ vmull.s32 q14, d10, d6
+ vmlal.s32 q14, d11, d13
+ vmlal.s32 q14, d4, d4
+ vmlal.s32 q14, d17, d1
+ vmlal.s32 q14, d18, d0
+ vmlal.s32 q14, d9, d23
+ vmull.s32 q11, d10, d7
+ vmlal.s32 q11, d11, d6
+ vmlal.s32 q11, d12, d5
+ vmlal.s32 q11, d8, d1
+ vmlal.s32 q11, d19, d0
+ vmull.s32 q15, d10, d8
+ vmlal.s32 q15, d11, d17
+ vmlal.s32 q15, d12, d6
+ vmlal.s32 q15, d13, d5
+ vmlal.s32 q15, d19, d1
+ vmlal.s32 q15, d14, d0
+ vmull.s32 q2, d10, d9
+ vmlal.s32 q2, d11, d8
+ vmlal.s32 q2, d12, d7
+ vmlal.s32 q2, d13, d6
+ vmlal.s32 q2, d14, d1
+ vmull.s32 q0, d15, d1
+ vmlal.s32 q0, d10, d14
+ vmlal.s32 q0, d11, d19
+ vmlal.s32 q0, d12, d8
+ vmlal.s32 q0, d13, d17
+ vmlal.s32 q0, d6, d6
+ add r2, sp, #480
+ vld1.8 {d18-d19}, [r2, : 128]!
+ vmull.s32 q3, d16, d7
+ vmlal.s32 q3, d10, d15
+ vmlal.s32 q3, d11, d14
+ vmlal.s32 q3, d12, d9
+ vmlal.s32 q3, d13, d8
+ vld1.8 {d8-d9}, [r2, : 128]
+ vadd.i64 q5, q12, q9
+ vadd.i64 q6, q15, q9
+ vshr.s64 q5, q5, #26
+ vshr.s64 q6, q6, #26
+ vadd.i64 q7, q10, q5
+ vshl.i64 q5, q5, #26
+ vadd.i64 q8, q7, q4
+ vadd.i64 q2, q2, q6
+ vshl.i64 q6, q6, #26
+ vadd.i64 q10, q2, q4
+ vsub.i64 q5, q12, q5
+ vshr.s64 q8, q8, #25
+ vsub.i64 q6, q15, q6
+ vshr.s64 q10, q10, #25
+ vadd.i64 q12, q13, q8
+ vshl.i64 q8, q8, #25
+ vadd.i64 q13, q12, q9
+ vadd.i64 q0, q0, q10
+ vsub.i64 q7, q7, q8
+ vshr.s64 q8, q13, #26
+ vshl.i64 q10, q10, #25
+ vadd.i64 q13, q0, q9
+ vadd.i64 q1, q1, q8
+ vshl.i64 q8, q8, #26
+ vadd.i64 q15, q1, q4
+ vsub.i64 q2, q2, q10
+ vshr.s64 q10, q13, #26
+ vsub.i64 q8, q12, q8
+ vshr.s64 q12, q15, #25
+ vadd.i64 q3, q3, q10
+ vshl.i64 q10, q10, #26
+ vadd.i64 q13, q3, q4
+ vadd.i64 q14, q14, q12
+ add r2, r3, #288
+ vshl.i64 q12, q12, #25
+ add r4, r3, #336
+ vadd.i64 q15, q14, q9
+ add r2, r2, #8
+ vsub.i64 q0, q0, q10
+ add r4, r4, #8
+ vshr.s64 q10, q13, #25
+ vsub.i64 q1, q1, q12
+ vshr.s64 q12, q15, #26
+ vadd.i64 q13, q10, q10
+ vadd.i64 q11, q11, q12
+ vtrn.32 d16, d2
+ vshl.i64 q12, q12, #26
+ vtrn.32 d17, d3
+ vadd.i64 q1, q11, q4
+ vadd.i64 q4, q5, q13
+ vst1.8 d16, [r2, : 64]!
+ vshl.i64 q5, q10, #4
+ vst1.8 d17, [r4, : 64]!
+ vsub.i64 q8, q14, q12
+ vshr.s64 q1, q1, #25
+ vadd.i64 q4, q4, q5
+ vadd.i64 q5, q6, q1
+ vshl.i64 q1, q1, #25
+ vadd.i64 q6, q5, q9
+ vadd.i64 q4, q4, q10
+ vshl.i64 q10, q10, #25
+ vadd.i64 q9, q4, q9
+ vsub.i64 q1, q11, q1
+ vshr.s64 q6, q6, #26
+ vsub.i64 q3, q3, q10
+ vtrn.32 d16, d2
+ vshr.s64 q9, q9, #26
+ vtrn.32 d17, d3
+ vadd.i64 q1, q2, q6
+ vst1.8 d16, [r2, : 64]
+ vshl.i64 q2, q6, #26
+ vst1.8 d17, [r4, : 64]
+ vadd.i64 q6, q7, q9
+ vtrn.32 d0, d6
+ vshl.i64 q7, q9, #26
+ vtrn.32 d1, d7
+ vsub.i64 q2, q5, q2
+ add r2, r2, #16
+ vsub.i64 q3, q4, q7
+ vst1.8 d0, [r2, : 64]
+ add r4, r4, #16
+ vst1.8 d1, [r4, : 64]
+ vtrn.32 d4, d2
+ vtrn.32 d5, d3
+ sub r2, r2, #8
+ sub r4, r4, #8
+ vtrn.32 d6, d12
+ vtrn.32 d7, d13
+ vst1.8 d4, [r2, : 64]
+ vst1.8 d5, [r4, : 64]
+ sub r2, r2, #24
+ sub r4, r4, #24
+ vst1.8 d6, [r2, : 64]
+ vst1.8 d7, [r4, : 64]
+ add r2, r3, #240
+ add r4, r3, #96
+ vld1.8 {d0-d1}, [r4, : 128]!
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vld1.8 {d4}, [r4, : 64]
+ add r4, r3, #144
+ vld1.8 {d6-d7}, [r4, : 128]!
+ vtrn.32 q0, q3
+ vld1.8 {d8-d9}, [r4, : 128]!
+ vshl.i32 q5, q0, #4
+ vtrn.32 q1, q4
+ vshl.i32 q6, q3, #4
+ vadd.i32 q5, q5, q0
+ vadd.i32 q6, q6, q3
+ vshl.i32 q7, q1, #4
+ vld1.8 {d5}, [r4, : 64]
+ vshl.i32 q8, q4, #4
+ vtrn.32 d4, d5
+ vadd.i32 q7, q7, q1
+ vadd.i32 q8, q8, q4
+ vld1.8 {d18-d19}, [r2, : 128]!
+ vshl.i32 q10, q2, #4
+ vld1.8 {d22-d23}, [r2, : 128]!
+ vadd.i32 q10, q10, q2
+ vld1.8 {d24}, [r2, : 64]
+ vadd.i32 q5, q5, q0
+ add r2, r3, #192
+ vld1.8 {d26-d27}, [r2, : 128]!
+ vadd.i32 q6, q6, q3
+ vld1.8 {d28-d29}, [r2, : 128]!
+ vadd.i32 q8, q8, q4
+ vld1.8 {d25}, [r2, : 64]
+ vadd.i32 q10, q10, q2
+ vtrn.32 q9, q13
+ vadd.i32 q7, q7, q1
+ vadd.i32 q5, q5, q0
+ vtrn.32 q11, q14
+ vadd.i32 q6, q6, q3
+ add r2, sp, #528
+ vadd.i32 q10, q10, q2
+ vtrn.32 d24, d25
+ vst1.8 {d12-d13}, [r2, : 128]!
+ vshl.i32 q6, q13, #1
+ vst1.8 {d20-d21}, [r2, : 128]!
+ vshl.i32 q10, q14, #1
+ vst1.8 {d12-d13}, [r2, : 128]!
+ vshl.i32 q15, q12, #1
+ vadd.i32 q8, q8, q4
+ vext.32 d10, d31, d30, #0
+ vadd.i32 q7, q7, q1
+ vst1.8 {d16-d17}, [r2, : 128]!
+ vmull.s32 q8, d18, d5
+ vmlal.s32 q8, d26, d4
+ vmlal.s32 q8, d19, d9
+ vmlal.s32 q8, d27, d3
+ vmlal.s32 q8, d22, d8
+ vmlal.s32 q8, d28, d2
+ vmlal.s32 q8, d23, d7
+ vmlal.s32 q8, d29, d1
+ vmlal.s32 q8, d24, d6
+ vmlal.s32 q8, d25, d0
+ vst1.8 {d14-d15}, [r2, : 128]!
+ vmull.s32 q2, d18, d4
+ vmlal.s32 q2, d12, d9
+ vmlal.s32 q2, d13, d8
+ vmlal.s32 q2, d19, d3
+ vmlal.s32 q2, d22, d2
+ vmlal.s32 q2, d23, d1
+ vmlal.s32 q2, d24, d0
+ vst1.8 {d20-d21}, [r2, : 128]!
+ vmull.s32 q7, d18, d9
+ vmlal.s32 q7, d26, d3
+ vmlal.s32 q7, d19, d8
+ vmlal.s32 q7, d27, d2
+ vmlal.s32 q7, d22, d7
+ vmlal.s32 q7, d28, d1
+ vmlal.s32 q7, d23, d6
+ vmlal.s32 q7, d29, d0
+ vst1.8 {d10-d11}, [r2, : 128]!
+ vmull.s32 q5, d18, d3
+ vmlal.s32 q5, d19, d2
+ vmlal.s32 q5, d22, d1
+ vmlal.s32 q5, d23, d0
+ vmlal.s32 q5, d12, d8
+ vst1.8 {d16-d17}, [r2, : 128]
+ vmull.s32 q4, d18, d8
+ vmlal.s32 q4, d26, d2
+ vmlal.s32 q4, d19, d7
+ vmlal.s32 q4, d27, d1
+ vmlal.s32 q4, d22, d6
+ vmlal.s32 q4, d28, d0
+ vmull.s32 q8, d18, d7
+ vmlal.s32 q8, d26, d1
+ vmlal.s32 q8, d19, d6
+ vmlal.s32 q8, d27, d0
+ add r2, sp, #544
+ vld1.8 {d20-d21}, [r2, : 128]
+ vmlal.s32 q7, d24, d21
+ vmlal.s32 q7, d25, d20
+ vmlal.s32 q4, d23, d21
+ vmlal.s32 q4, d29, d20
+ vmlal.s32 q8, d22, d21
+ vmlal.s32 q8, d28, d20
+ vmlal.s32 q5, d24, d20
+ vst1.8 {d14-d15}, [r2, : 128]
+ vmull.s32 q7, d18, d6
+ vmlal.s32 q7, d26, d0
+ add r2, sp, #624
+ vld1.8 {d30-d31}, [r2, : 128]
+ vmlal.s32 q2, d30, d21
+ vmlal.s32 q7, d19, d21
+ vmlal.s32 q7, d27, d20
+ add r2, sp, #592
+ vld1.8 {d26-d27}, [r2, : 128]
+ vmlal.s32 q4, d25, d27
+ vmlal.s32 q8, d29, d27
+ vmlal.s32 q8, d25, d26
+ vmlal.s32 q7, d28, d27
+ vmlal.s32 q7, d29, d26
+ add r2, sp, #576
+ vld1.8 {d28-d29}, [r2, : 128]
+ vmlal.s32 q4, d24, d29
+ vmlal.s32 q8, d23, d29
+ vmlal.s32 q8, d24, d28
+ vmlal.s32 q7, d22, d29
+ vmlal.s32 q7, d23, d28
+ vst1.8 {d8-d9}, [r2, : 128]
+ add r2, sp, #528
+ vld1.8 {d8-d9}, [r2, : 128]
+ vmlal.s32 q7, d24, d9
+ vmlal.s32 q7, d25, d31
+ vmull.s32 q1, d18, d2
+ vmlal.s32 q1, d19, d1
+ vmlal.s32 q1, d22, d0
+ vmlal.s32 q1, d24, d27
+ vmlal.s32 q1, d23, d20
+ vmlal.s32 q1, d12, d7
+ vmlal.s32 q1, d13, d6
+ vmull.s32 q6, d18, d1
+ vmlal.s32 q6, d19, d0
+ vmlal.s32 q6, d23, d27
+ vmlal.s32 q6, d22, d20
+ vmlal.s32 q6, d24, d26
+ vmull.s32 q0, d18, d0
+ vmlal.s32 q0, d22, d27
+ vmlal.s32 q0, d23, d26
+ vmlal.s32 q0, d24, d31
+ vmlal.s32 q0, d19, d20
+ add r2, sp, #608
+ vld1.8 {d18-d19}, [r2, : 128]
+ vmlal.s32 q2, d18, d7
+ vmlal.s32 q5, d18, d6
+ vmlal.s32 q1, d18, d21
+ vmlal.s32 q0, d18, d28
+ vmlal.s32 q6, d18, d29
+ vmlal.s32 q2, d19, d6
+ vmlal.s32 q5, d19, d21
+ vmlal.s32 q1, d19, d29
+ vmlal.s32 q0, d19, d9
+ vmlal.s32 q6, d19, d28
+ add r2, sp, #560
+ vld1.8 {d18-d19}, [r2, : 128]
+ add r2, sp, #480
+ vld1.8 {d22-d23}, [r2, : 128]
+ vmlal.s32 q5, d19, d7
+ vmlal.s32 q0, d18, d21
+ vmlal.s32 q0, d19, d29
+ vmlal.s32 q6, d18, d6
+ add r2, sp, #496
+ vld1.8 {d6-d7}, [r2, : 128]
+ vmlal.s32 q6, d19, d21
+ add r2, sp, #544
+ vld1.8 {d18-d19}, [r2, : 128]
+ vmlal.s32 q0, d30, d8
+ add r2, sp, #640
+ vld1.8 {d20-d21}, [r2, : 128]
+ vmlal.s32 q5, d30, d29
+ add r2, sp, #576
+ vld1.8 {d24-d25}, [r2, : 128]
+ vmlal.s32 q1, d30, d28
+ vadd.i64 q13, q0, q11
+ vadd.i64 q14, q5, q11
+ vmlal.s32 q6, d30, d9
+ vshr.s64 q4, q13, #26
+ vshr.s64 q13, q14, #26
+ vadd.i64 q7, q7, q4
+ vshl.i64 q4, q4, #26
+ vadd.i64 q14, q7, q3
+ vadd.i64 q9, q9, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q15, q9, q3
+ vsub.i64 q0, q0, q4
+ vshr.s64 q4, q14, #25
+ vsub.i64 q5, q5, q13
+ vshr.s64 q13, q15, #25
+ vadd.i64 q6, q6, q4
+ vshl.i64 q4, q4, #25
+ vadd.i64 q14, q6, q11
+ vadd.i64 q2, q2, q13
+ vsub.i64 q4, q7, q4
+ vshr.s64 q7, q14, #26
+ vshl.i64 q13, q13, #25
+ vadd.i64 q14, q2, q11
+ vadd.i64 q8, q8, q7
+ vshl.i64 q7, q7, #26
+ vadd.i64 q15, q8, q3
+ vsub.i64 q9, q9, q13
+ vshr.s64 q13, q14, #26
+ vsub.i64 q6, q6, q7
+ vshr.s64 q7, q15, #25
+ vadd.i64 q10, q10, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q14, q10, q3
+ vadd.i64 q1, q1, q7
+ add r2, r3, #144
+ vshl.i64 q7, q7, #25
+ add r4, r3, #96
+ vadd.i64 q15, q1, q11
+ add r2, r2, #8
+ vsub.i64 q2, q2, q13
+ add r4, r4, #8
+ vshr.s64 q13, q14, #25
+ vsub.i64 q7, q8, q7
+ vshr.s64 q8, q15, #26
+ vadd.i64 q14, q13, q13
+ vadd.i64 q12, q12, q8
+ vtrn.32 d12, d14
+ vshl.i64 q8, q8, #26
+ vtrn.32 d13, d15
+ vadd.i64 q3, q12, q3
+ vadd.i64 q0, q0, q14
+ vst1.8 d12, [r2, : 64]!
+ vshl.i64 q7, q13, #4
+ vst1.8 d13, [r4, : 64]!
+ vsub.i64 q1, q1, q8
+ vshr.s64 q3, q3, #25
+ vadd.i64 q0, q0, q7
+ vadd.i64 q5, q5, q3
+ vshl.i64 q3, q3, #25
+ vadd.i64 q6, q5, q11
+ vadd.i64 q0, q0, q13
+ vshl.i64 q7, q13, #25
+ vadd.i64 q8, q0, q11
+ vsub.i64 q3, q12, q3
+ vshr.s64 q6, q6, #26
+ vsub.i64 q7, q10, q7
+ vtrn.32 d2, d6
+ vshr.s64 q8, q8, #26
+ vtrn.32 d3, d7
+ vadd.i64 q3, q9, q6
+ vst1.8 d2, [r2, : 64]
+ vshl.i64 q6, q6, #26
+ vst1.8 d3, [r4, : 64]
+ vadd.i64 q1, q4, q8
+ vtrn.32 d4, d14
+ vshl.i64 q4, q8, #26
+ vtrn.32 d5, d15
+ vsub.i64 q5, q5, q6
+ add r2, r2, #16
+ vsub.i64 q0, q0, q4
+ vst1.8 d4, [r2, : 64]
+ add r4, r4, #16
+ vst1.8 d5, [r4, : 64]
+ vtrn.32 d10, d6
+ vtrn.32 d11, d7
+ sub r2, r2, #8
+ sub r4, r4, #8
+ vtrn.32 d0, d2
+ vtrn.32 d1, d3
+ vst1.8 d10, [r2, : 64]
+ vst1.8 d11, [r4, : 64]
+ sub r2, r2, #24
+ sub r4, r4, #24
+ vst1.8 d0, [r2, : 64]
+ vst1.8 d1, [r4, : 64]
+ add r2, r3, #288
+ add r4, r3, #336
+ vld1.8 {d0-d1}, [r2, : 128]!
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vsub.i32 q0, q0, q1
+ vld1.8 {d2-d3}, [r2, : 128]!
+ vld1.8 {d4-d5}, [r4, : 128]!
+ vsub.i32 q1, q1, q2
+ add r5, r3, #240
+ vld1.8 {d4}, [r2, : 64]
+ vld1.8 {d6}, [r4, : 64]
+ vsub.i32 q2, q2, q3
+ vst1.8 {d0-d1}, [r5, : 128]!
+ vst1.8 {d2-d3}, [r5, : 128]!
+ vst1.8 d4, [r5, : 64]
+ add r2, r3, #144
+ add r4, r3, #96
+ add r5, r3, #144
+ add r6, r3, #192
+ vld1.8 {d0-d1}, [r2, : 128]!
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vsub.i32 q2, q0, q1
+ vadd.i32 q0, q0, q1
+ vld1.8 {d2-d3}, [r2, : 128]!
+ vld1.8 {d6-d7}, [r4, : 128]!
+ vsub.i32 q4, q1, q3
+ vadd.i32 q1, q1, q3
+ vld1.8 {d6}, [r2, : 64]
+ vld1.8 {d10}, [r4, : 64]
+ vsub.i32 q6, q3, q5
+ vadd.i32 q3, q3, q5
+ vst1.8 {d4-d5}, [r5, : 128]!
+ vst1.8 {d0-d1}, [r6, : 128]!
+ vst1.8 {d8-d9}, [r5, : 128]!
+ vst1.8 {d2-d3}, [r6, : 128]!
+ vst1.8 d12, [r5, : 64]
+ vst1.8 d6, [r6, : 64]
+ add r2, r3, #0
+ add r4, r3, #240
+ vld1.8 {d0-d1}, [r4, : 128]!
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vld1.8 {d4}, [r4, : 64]
+ add r4, r3, #336
+ vld1.8 {d6-d7}, [r4, : 128]!
+ vtrn.32 q0, q3
+ vld1.8 {d8-d9}, [r4, : 128]!
+ vshl.i32 q5, q0, #4
+ vtrn.32 q1, q4
+ vshl.i32 q6, q3, #4
+ vadd.i32 q5, q5, q0
+ vadd.i32 q6, q6, q3
+ vshl.i32 q7, q1, #4
+ vld1.8 {d5}, [r4, : 64]
+ vshl.i32 q8, q4, #4
+ vtrn.32 d4, d5
+ vadd.i32 q7, q7, q1
+ vadd.i32 q8, q8, q4
+ vld1.8 {d18-d19}, [r2, : 128]!
+ vshl.i32 q10, q2, #4
+ vld1.8 {d22-d23}, [r2, : 128]!
+ vadd.i32 q10, q10, q2
+ vld1.8 {d24}, [r2, : 64]
+ vadd.i32 q5, q5, q0
+ add r2, r3, #288
+ vld1.8 {d26-d27}, [r2, : 128]!
+ vadd.i32 q6, q6, q3
+ vld1.8 {d28-d29}, [r2, : 128]!
+ vadd.i32 q8, q8, q4
+ vld1.8 {d25}, [r2, : 64]
+ vadd.i32 q10, q10, q2
+ vtrn.32 q9, q13
+ vadd.i32 q7, q7, q1
+ vadd.i32 q5, q5, q0
+ vtrn.32 q11, q14
+ vadd.i32 q6, q6, q3
+ add r2, sp, #528
+ vadd.i32 q10, q10, q2
+ vtrn.32 d24, d25
+ vst1.8 {d12-d13}, [r2, : 128]!
+ vshl.i32 q6, q13, #1
+ vst1.8 {d20-d21}, [r2, : 128]!
+ vshl.i32 q10, q14, #1
+ vst1.8 {d12-d13}, [r2, : 128]!
+ vshl.i32 q15, q12, #1
+ vadd.i32 q8, q8, q4
+ vext.32 d10, d31, d30, #0
+ vadd.i32 q7, q7, q1
+ vst1.8 {d16-d17}, [r2, : 128]!
+ vmull.s32 q8, d18, d5
+ vmlal.s32 q8, d26, d4
+ vmlal.s32 q8, d19, d9
+ vmlal.s32 q8, d27, d3
+ vmlal.s32 q8, d22, d8
+ vmlal.s32 q8, d28, d2
+ vmlal.s32 q8, d23, d7
+ vmlal.s32 q8, d29, d1
+ vmlal.s32 q8, d24, d6
+ vmlal.s32 q8, d25, d0
+ vst1.8 {d14-d15}, [r2, : 128]!
+ vmull.s32 q2, d18, d4
+ vmlal.s32 q2, d12, d9
+ vmlal.s32 q2, d13, d8
+ vmlal.s32 q2, d19, d3
+ vmlal.s32 q2, d22, d2
+ vmlal.s32 q2, d23, d1
+ vmlal.s32 q2, d24, d0
+ vst1.8 {d20-d21}, [r2, : 128]!
+ vmull.s32 q7, d18, d9
+ vmlal.s32 q7, d26, d3
+ vmlal.s32 q7, d19, d8
+ vmlal.s32 q7, d27, d2
+ vmlal.s32 q7, d22, d7
+ vmlal.s32 q7, d28, d1
+ vmlal.s32 q7, d23, d6
+ vmlal.s32 q7, d29, d0
+ vst1.8 {d10-d11}, [r2, : 128]!
+ vmull.s32 q5, d18, d3
+ vmlal.s32 q5, d19, d2
+ vmlal.s32 q5, d22, d1
+ vmlal.s32 q5, d23, d0
+ vmlal.s32 q5, d12, d8
+ vst1.8 {d16-d17}, [r2, : 128]!
+ vmull.s32 q4, d18, d8
+ vmlal.s32 q4, d26, d2
+ vmlal.s32 q4, d19, d7
+ vmlal.s32 q4, d27, d1
+ vmlal.s32 q4, d22, d6
+ vmlal.s32 q4, d28, d0
+ vmull.s32 q8, d18, d7
+ vmlal.s32 q8, d26, d1
+ vmlal.s32 q8, d19, d6
+ vmlal.s32 q8, d27, d0
+ add r2, sp, #544
+ vld1.8 {d20-d21}, [r2, : 128]
+ vmlal.s32 q7, d24, d21
+ vmlal.s32 q7, d25, d20
+ vmlal.s32 q4, d23, d21
+ vmlal.s32 q4, d29, d20
+ vmlal.s32 q8, d22, d21
+ vmlal.s32 q8, d28, d20
+ vmlal.s32 q5, d24, d20
+ vst1.8 {d14-d15}, [r2, : 128]
+ vmull.s32 q7, d18, d6
+ vmlal.s32 q7, d26, d0
+ add r2, sp, #624
+ vld1.8 {d30-d31}, [r2, : 128]
+ vmlal.s32 q2, d30, d21
+ vmlal.s32 q7, d19, d21
+ vmlal.s32 q7, d27, d20
+ add r2, sp, #592
+ vld1.8 {d26-d27}, [r2, : 128]
+ vmlal.s32 q4, d25, d27
+ vmlal.s32 q8, d29, d27
+ vmlal.s32 q8, d25, d26
+ vmlal.s32 q7, d28, d27
+ vmlal.s32 q7, d29, d26
+ add r2, sp, #576
+ vld1.8 {d28-d29}, [r2, : 128]
+ vmlal.s32 q4, d24, d29
+ vmlal.s32 q8, d23, d29
+ vmlal.s32 q8, d24, d28
+ vmlal.s32 q7, d22, d29
+ vmlal.s32 q7, d23, d28
+ vst1.8 {d8-d9}, [r2, : 128]
+ add r2, sp, #528
+ vld1.8 {d8-d9}, [r2, : 128]
+ vmlal.s32 q7, d24, d9
+ vmlal.s32 q7, d25, d31
+ vmull.s32 q1, d18, d2
+ vmlal.s32 q1, d19, d1
+ vmlal.s32 q1, d22, d0
+ vmlal.s32 q1, d24, d27
+ vmlal.s32 q1, d23, d20
+ vmlal.s32 q1, d12, d7
+ vmlal.s32 q1, d13, d6
+ vmull.s32 q6, d18, d1
+ vmlal.s32 q6, d19, d0
+ vmlal.s32 q6, d23, d27
+ vmlal.s32 q6, d22, d20
+ vmlal.s32 q6, d24, d26
+ vmull.s32 q0, d18, d0
+ vmlal.s32 q0, d22, d27
+ vmlal.s32 q0, d23, d26
+ vmlal.s32 q0, d24, d31
+ vmlal.s32 q0, d19, d20
+ add r2, sp, #608
+ vld1.8 {d18-d19}, [r2, : 128]
+ vmlal.s32 q2, d18, d7
+ vmlal.s32 q5, d18, d6
+ vmlal.s32 q1, d18, d21
+ vmlal.s32 q0, d18, d28
+ vmlal.s32 q6, d18, d29
+ vmlal.s32 q2, d19, d6
+ vmlal.s32 q5, d19, d21
+ vmlal.s32 q1, d19, d29
+ vmlal.s32 q0, d19, d9
+ vmlal.s32 q6, d19, d28
+ add r2, sp, #560
+ vld1.8 {d18-d19}, [r2, : 128]
+ add r2, sp, #480
+ vld1.8 {d22-d23}, [r2, : 128]
+ vmlal.s32 q5, d19, d7
+ vmlal.s32 q0, d18, d21
+ vmlal.s32 q0, d19, d29
+ vmlal.s32 q6, d18, d6
+ add r2, sp, #496
+ vld1.8 {d6-d7}, [r2, : 128]
+ vmlal.s32 q6, d19, d21
+ add r2, sp, #544
+ vld1.8 {d18-d19}, [r2, : 128]
+ vmlal.s32 q0, d30, d8
+ add r2, sp, #640
+ vld1.8 {d20-d21}, [r2, : 128]
+ vmlal.s32 q5, d30, d29
+ add r2, sp, #576
+ vld1.8 {d24-d25}, [r2, : 128]
+ vmlal.s32 q1, d30, d28
+ vadd.i64 q13, q0, q11
+ vadd.i64 q14, q5, q11
+ vmlal.s32 q6, d30, d9
+ vshr.s64 q4, q13, #26
+ vshr.s64 q13, q14, #26
+ vadd.i64 q7, q7, q4
+ vshl.i64 q4, q4, #26
+ vadd.i64 q14, q7, q3
+ vadd.i64 q9, q9, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q15, q9, q3
+ vsub.i64 q0, q0, q4
+ vshr.s64 q4, q14, #25
+ vsub.i64 q5, q5, q13
+ vshr.s64 q13, q15, #25
+ vadd.i64 q6, q6, q4
+ vshl.i64 q4, q4, #25
+ vadd.i64 q14, q6, q11
+ vadd.i64 q2, q2, q13
+ vsub.i64 q4, q7, q4
+ vshr.s64 q7, q14, #26
+ vshl.i64 q13, q13, #25
+ vadd.i64 q14, q2, q11
+ vadd.i64 q8, q8, q7
+ vshl.i64 q7, q7, #26
+ vadd.i64 q15, q8, q3
+ vsub.i64 q9, q9, q13
+ vshr.s64 q13, q14, #26
+ vsub.i64 q6, q6, q7
+ vshr.s64 q7, q15, #25
+ vadd.i64 q10, q10, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q14, q10, q3
+ vadd.i64 q1, q1, q7
+ add r2, r3, #288
+ vshl.i64 q7, q7, #25
+ add r4, r3, #96
+ vadd.i64 q15, q1, q11
+ add r2, r2, #8
+ vsub.i64 q2, q2, q13
+ add r4, r4, #8
+ vshr.s64 q13, q14, #25
+ vsub.i64 q7, q8, q7
+ vshr.s64 q8, q15, #26
+ vadd.i64 q14, q13, q13
+ vadd.i64 q12, q12, q8
+ vtrn.32 d12, d14
+ vshl.i64 q8, q8, #26
+ vtrn.32 d13, d15
+ vadd.i64 q3, q12, q3
+ vadd.i64 q0, q0, q14
+ vst1.8 d12, [r2, : 64]!
+ vshl.i64 q7, q13, #4
+ vst1.8 d13, [r4, : 64]!
+ vsub.i64 q1, q1, q8
+ vshr.s64 q3, q3, #25
+ vadd.i64 q0, q0, q7
+ vadd.i64 q5, q5, q3
+ vshl.i64 q3, q3, #25
+ vadd.i64 q6, q5, q11
+ vadd.i64 q0, q0, q13
+ vshl.i64 q7, q13, #25
+ vadd.i64 q8, q0, q11
+ vsub.i64 q3, q12, q3
+ vshr.s64 q6, q6, #26
+ vsub.i64 q7, q10, q7
+ vtrn.32 d2, d6
+ vshr.s64 q8, q8, #26
+ vtrn.32 d3, d7
+ vadd.i64 q3, q9, q6
+ vst1.8 d2, [r2, : 64]
+ vshl.i64 q6, q6, #26
+ vst1.8 d3, [r4, : 64]
+ vadd.i64 q1, q4, q8
+ vtrn.32 d4, d14
+ vshl.i64 q4, q8, #26
+ vtrn.32 d5, d15
+ vsub.i64 q5, q5, q6
+ add r2, r2, #16
+ vsub.i64 q0, q0, q4
+ vst1.8 d4, [r2, : 64]
+ add r4, r4, #16
+ vst1.8 d5, [r4, : 64]
+ vtrn.32 d10, d6
+ vtrn.32 d11, d7
+ sub r2, r2, #8
+ sub r4, r4, #8
+ vtrn.32 d0, d2
+ vtrn.32 d1, d3
+ vst1.8 d10, [r2, : 64]
+ vst1.8 d11, [r4, : 64]
+ sub r2, r2, #24
+ sub r4, r4, #24
+ vst1.8 d0, [r2, : 64]
+ vst1.8 d1, [r4, : 64]
+ add r2, sp, #512
+ add r4, r3, #144
+ add r5, r3, #192
+ vld1.8 {d0-d1}, [r2, : 128]
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vld1.8 {d4-d5}, [r5, : 128]!
+ vzip.i32 q1, q2
+ vld1.8 {d6-d7}, [r4, : 128]!
+ vld1.8 {d8-d9}, [r5, : 128]!
+ vshl.i32 q5, q1, #1
+ vzip.i32 q3, q4
+ vshl.i32 q6, q2, #1
+ vld1.8 {d14}, [r4, : 64]
+ vshl.i32 q8, q3, #1
+ vld1.8 {d15}, [r5, : 64]
+ vshl.i32 q9, q4, #1
+ vmul.i32 d21, d7, d1
+ vtrn.32 d14, d15
+ vmul.i32 q11, q4, q0
+ vmul.i32 q0, q7, q0
+ vmull.s32 q12, d2, d2
+ vmlal.s32 q12, d11, d1
+ vmlal.s32 q12, d12, d0
+ vmlal.s32 q12, d13, d23
+ vmlal.s32 q12, d16, d22
+ vmlal.s32 q12, d7, d21
+ vmull.s32 q10, d2, d11
+ vmlal.s32 q10, d4, d1
+ vmlal.s32 q10, d13, d0
+ vmlal.s32 q10, d6, d23
+ vmlal.s32 q10, d17, d22
+ vmull.s32 q13, d10, d4
+ vmlal.s32 q13, d11, d3
+ vmlal.s32 q13, d13, d1
+ vmlal.s32 q13, d16, d0
+ vmlal.s32 q13, d17, d23
+ vmlal.s32 q13, d8, d22
+ vmull.s32 q1, d10, d5
+ vmlal.s32 q1, d11, d4
+ vmlal.s32 q1, d6, d1
+ vmlal.s32 q1, d17, d0
+ vmlal.s32 q1, d8, d23
+ vmull.s32 q14, d10, d6
+ vmlal.s32 q14, d11, d13
+ vmlal.s32 q14, d4, d4
+ vmlal.s32 q14, d17, d1
+ vmlal.s32 q14, d18, d0
+ vmlal.s32 q14, d9, d23
+ vmull.s32 q11, d10, d7
+ vmlal.s32 q11, d11, d6
+ vmlal.s32 q11, d12, d5
+ vmlal.s32 q11, d8, d1
+ vmlal.s32 q11, d19, d0
+ vmull.s32 q15, d10, d8
+ vmlal.s32 q15, d11, d17
+ vmlal.s32 q15, d12, d6
+ vmlal.s32 q15, d13, d5
+ vmlal.s32 q15, d19, d1
+ vmlal.s32 q15, d14, d0
+ vmull.s32 q2, d10, d9
+ vmlal.s32 q2, d11, d8
+ vmlal.s32 q2, d12, d7
+ vmlal.s32 q2, d13, d6
+ vmlal.s32 q2, d14, d1
+ vmull.s32 q0, d15, d1
+ vmlal.s32 q0, d10, d14
+ vmlal.s32 q0, d11, d19
+ vmlal.s32 q0, d12, d8
+ vmlal.s32 q0, d13, d17
+ vmlal.s32 q0, d6, d6
+ add r2, sp, #480
+ vld1.8 {d18-d19}, [r2, : 128]!
+ vmull.s32 q3, d16, d7
+ vmlal.s32 q3, d10, d15
+ vmlal.s32 q3, d11, d14
+ vmlal.s32 q3, d12, d9
+ vmlal.s32 q3, d13, d8
+ vld1.8 {d8-d9}, [r2, : 128]
+ vadd.i64 q5, q12, q9
+ vadd.i64 q6, q15, q9
+ vshr.s64 q5, q5, #26
+ vshr.s64 q6, q6, #26
+ vadd.i64 q7, q10, q5
+ vshl.i64 q5, q5, #26
+ vadd.i64 q8, q7, q4
+ vadd.i64 q2, q2, q6
+ vshl.i64 q6, q6, #26
+ vadd.i64 q10, q2, q4
+ vsub.i64 q5, q12, q5
+ vshr.s64 q8, q8, #25
+ vsub.i64 q6, q15, q6
+ vshr.s64 q10, q10, #25
+ vadd.i64 q12, q13, q8
+ vshl.i64 q8, q8, #25
+ vadd.i64 q13, q12, q9
+ vadd.i64 q0, q0, q10
+ vsub.i64 q7, q7, q8
+ vshr.s64 q8, q13, #26
+ vshl.i64 q10, q10, #25
+ vadd.i64 q13, q0, q9
+ vadd.i64 q1, q1, q8
+ vshl.i64 q8, q8, #26
+ vadd.i64 q15, q1, q4
+ vsub.i64 q2, q2, q10
+ vshr.s64 q10, q13, #26
+ vsub.i64 q8, q12, q8
+ vshr.s64 q12, q15, #25
+ vadd.i64 q3, q3, q10
+ vshl.i64 q10, q10, #26
+ vadd.i64 q13, q3, q4
+ vadd.i64 q14, q14, q12
+ add r2, r3, #144
+ vshl.i64 q12, q12, #25
+ add r4, r3, #192
+ vadd.i64 q15, q14, q9
+ add r2, r2, #8
+ vsub.i64 q0, q0, q10
+ add r4, r4, #8
+ vshr.s64 q10, q13, #25
+ vsub.i64 q1, q1, q12
+ vshr.s64 q12, q15, #26
+ vadd.i64 q13, q10, q10
+ vadd.i64 q11, q11, q12
+ vtrn.32 d16, d2
+ vshl.i64 q12, q12, #26
+ vtrn.32 d17, d3
+ vadd.i64 q1, q11, q4
+ vadd.i64 q4, q5, q13
+ vst1.8 d16, [r2, : 64]!
+ vshl.i64 q5, q10, #4
+ vst1.8 d17, [r4, : 64]!
+ vsub.i64 q8, q14, q12
+ vshr.s64 q1, q1, #25
+ vadd.i64 q4, q4, q5
+ vadd.i64 q5, q6, q1
+ vshl.i64 q1, q1, #25
+ vadd.i64 q6, q5, q9
+ vadd.i64 q4, q4, q10
+ vshl.i64 q10, q10, #25
+ vadd.i64 q9, q4, q9
+ vsub.i64 q1, q11, q1
+ vshr.s64 q6, q6, #26
+ vsub.i64 q3, q3, q10
+ vtrn.32 d16, d2
+ vshr.s64 q9, q9, #26
+ vtrn.32 d17, d3
+ vadd.i64 q1, q2, q6
+ vst1.8 d16, [r2, : 64]
+ vshl.i64 q2, q6, #26
+ vst1.8 d17, [r4, : 64]
+ vadd.i64 q6, q7, q9
+ vtrn.32 d0, d6
+ vshl.i64 q7, q9, #26
+ vtrn.32 d1, d7
+ vsub.i64 q2, q5, q2
+ add r2, r2, #16
+ vsub.i64 q3, q4, q7
+ vst1.8 d0, [r2, : 64]
+ add r4, r4, #16
+ vst1.8 d1, [r4, : 64]
+ vtrn.32 d4, d2
+ vtrn.32 d5, d3
+ sub r2, r2, #8
+ sub r4, r4, #8
+ vtrn.32 d6, d12
+ vtrn.32 d7, d13
+ vst1.8 d4, [r2, : 64]
+ vst1.8 d5, [r4, : 64]
+ sub r2, r2, #24
+ sub r4, r4, #24
+ vst1.8 d6, [r2, : 64]
+ vst1.8 d7, [r4, : 64]
+ add r2, r3, #336
+ add r4, r3, #288
+ vld1.8 {d0-d1}, [r2, : 128]!
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vadd.i32 q0, q0, q1
+ vld1.8 {d2-d3}, [r2, : 128]!
+ vld1.8 {d4-d5}, [r4, : 128]!
+ vadd.i32 q1, q1, q2
+ add r5, r3, #288
+ vld1.8 {d4}, [r2, : 64]
+ vld1.8 {d6}, [r4, : 64]
+ vadd.i32 q2, q2, q3
+ vst1.8 {d0-d1}, [r5, : 128]!
+ vst1.8 {d2-d3}, [r5, : 128]!
+ vst1.8 d4, [r5, : 64]
+ add r2, r3, #48
+ add r4, r3, #144
+ vld1.8 {d0-d1}, [r4, : 128]!
+ vld1.8 {d2-d3}, [r4, : 128]!
+ vld1.8 {d4}, [r4, : 64]
+ add r4, r3, #288
+ vld1.8 {d6-d7}, [r4, : 128]!
+ vtrn.32 q0, q3
+ vld1.8 {d8-d9}, [r4, : 128]!
+ vshl.i32 q5, q0, #4
+ vtrn.32 q1, q4
+ vshl.i32 q6, q3, #4
+ vadd.i32 q5, q5, q0
+ vadd.i32 q6, q6, q3
+ vshl.i32 q7, q1, #4
+ vld1.8 {d5}, [r4, : 64]
+ vshl.i32 q8, q4, #4
+ vtrn.32 d4, d5
+ vadd.i32 q7, q7, q1
+ vadd.i32 q8, q8, q4
+ vld1.8 {d18-d19}, [r2, : 128]!
+ vshl.i32 q10, q2, #4
+ vld1.8 {d22-d23}, [r2, : 128]!
+ vadd.i32 q10, q10, q2
+ vld1.8 {d24}, [r2, : 64]
+ vadd.i32 q5, q5, q0
+ add r2, r3, #240
+ vld1.8 {d26-d27}, [r2, : 128]!
+ vadd.i32 q6, q6, q3
+ vld1.8 {d28-d29}, [r2, : 128]!
+ vadd.i32 q8, q8, q4
+ vld1.8 {d25}, [r2, : 64]
+ vadd.i32 q10, q10, q2
+ vtrn.32 q9, q13
+ vadd.i32 q7, q7, q1
+ vadd.i32 q5, q5, q0
+ vtrn.32 q11, q14
+ vadd.i32 q6, q6, q3
+ add r2, sp, #528
+ vadd.i32 q10, q10, q2
+ vtrn.32 d24, d25
+ vst1.8 {d12-d13}, [r2, : 128]!
+ vshl.i32 q6, q13, #1
+ vst1.8 {d20-d21}, [r2, : 128]!
+ vshl.i32 q10, q14, #1
+ vst1.8 {d12-d13}, [r2, : 128]!
+ vshl.i32 q15, q12, #1
+ vadd.i32 q8, q8, q4
+ vext.32 d10, d31, d30, #0
+ vadd.i32 q7, q7, q1
+ vst1.8 {d16-d17}, [r2, : 128]!
+ vmull.s32 q8, d18, d5
+ vmlal.s32 q8, d26, d4
+ vmlal.s32 q8, d19, d9
+ vmlal.s32 q8, d27, d3
+ vmlal.s32 q8, d22, d8
+ vmlal.s32 q8, d28, d2
+ vmlal.s32 q8, d23, d7
+ vmlal.s32 q8, d29, d1
+ vmlal.s32 q8, d24, d6
+ vmlal.s32 q8, d25, d0
+ vst1.8 {d14-d15}, [r2, : 128]!
+ vmull.s32 q2, d18, d4
+ vmlal.s32 q2, d12, d9
+ vmlal.s32 q2, d13, d8
+ vmlal.s32 q2, d19, d3
+ vmlal.s32 q2, d22, d2
+ vmlal.s32 q2, d23, d1
+ vmlal.s32 q2, d24, d0
+ vst1.8 {d20-d21}, [r2, : 128]!
+ vmull.s32 q7, d18, d9
+ vmlal.s32 q7, d26, d3
+ vmlal.s32 q7, d19, d8
+ vmlal.s32 q7, d27, d2
+ vmlal.s32 q7, d22, d7
+ vmlal.s32 q7, d28, d1
+ vmlal.s32 q7, d23, d6
+ vmlal.s32 q7, d29, d0
+ vst1.8 {d10-d11}, [r2, : 128]!
+ vmull.s32 q5, d18, d3
+ vmlal.s32 q5, d19, d2
+ vmlal.s32 q5, d22, d1
+ vmlal.s32 q5, d23, d0
+ vmlal.s32 q5, d12, d8
+ vst1.8 {d16-d17}, [r2, : 128]!
+ vmull.s32 q4, d18, d8
+ vmlal.s32 q4, d26, d2
+ vmlal.s32 q4, d19, d7
+ vmlal.s32 q4, d27, d1
+ vmlal.s32 q4, d22, d6
+ vmlal.s32 q4, d28, d0
+ vmull.s32 q8, d18, d7
+ vmlal.s32 q8, d26, d1
+ vmlal.s32 q8, d19, d6
+ vmlal.s32 q8, d27, d0
+ add r2, sp, #544
+ vld1.8 {d20-d21}, [r2, : 128]
+ vmlal.s32 q7, d24, d21
+ vmlal.s32 q7, d25, d20
+ vmlal.s32 q4, d23, d21
+ vmlal.s32 q4, d29, d20
+ vmlal.s32 q8, d22, d21
+ vmlal.s32 q8, d28, d20
+ vmlal.s32 q5, d24, d20
+ vst1.8 {d14-d15}, [r2, : 128]
+ vmull.s32 q7, d18, d6
+ vmlal.s32 q7, d26, d0
+ add r2, sp, #624
+ vld1.8 {d30-d31}, [r2, : 128]
+ vmlal.s32 q2, d30, d21
+ vmlal.s32 q7, d19, d21
+ vmlal.s32 q7, d27, d20
+ add r2, sp, #592
+ vld1.8 {d26-d27}, [r2, : 128]
+ vmlal.s32 q4, d25, d27
+ vmlal.s32 q8, d29, d27
+ vmlal.s32 q8, d25, d26
+ vmlal.s32 q7, d28, d27
+ vmlal.s32 q7, d29, d26
+ add r2, sp, #576
+ vld1.8 {d28-d29}, [r2, : 128]
+ vmlal.s32 q4, d24, d29
+ vmlal.s32 q8, d23, d29
+ vmlal.s32 q8, d24, d28
+ vmlal.s32 q7, d22, d29
+ vmlal.s32 q7, d23, d28
+ vst1.8 {d8-d9}, [r2, : 128]
+ add r2, sp, #528
+ vld1.8 {d8-d9}, [r2, : 128]
+ vmlal.s32 q7, d24, d9
+ vmlal.s32 q7, d25, d31
+ vmull.s32 q1, d18, d2
+ vmlal.s32 q1, d19, d1
+ vmlal.s32 q1, d22, d0
+ vmlal.s32 q1, d24, d27
+ vmlal.s32 q1, d23, d20
+ vmlal.s32 q1, d12, d7
+ vmlal.s32 q1, d13, d6
+ vmull.s32 q6, d18, d1
+ vmlal.s32 q6, d19, d0
+ vmlal.s32 q6, d23, d27
+ vmlal.s32 q6, d22, d20
+ vmlal.s32 q6, d24, d26
+ vmull.s32 q0, d18, d0
+ vmlal.s32 q0, d22, d27
+ vmlal.s32 q0, d23, d26
+ vmlal.s32 q0, d24, d31
+ vmlal.s32 q0, d19, d20
+ add r2, sp, #608
+ vld1.8 {d18-d19}, [r2, : 128]
+ vmlal.s32 q2, d18, d7
+ vmlal.s32 q5, d18, d6
+ vmlal.s32 q1, d18, d21
+ vmlal.s32 q0, d18, d28
+ vmlal.s32 q6, d18, d29
+ vmlal.s32 q2, d19, d6
+ vmlal.s32 q5, d19, d21
+ vmlal.s32 q1, d19, d29
+ vmlal.s32 q0, d19, d9
+ vmlal.s32 q6, d19, d28
+ add r2, sp, #560
+ vld1.8 {d18-d19}, [r2, : 128]
+ add r2, sp, #480
+ vld1.8 {d22-d23}, [r2, : 128]
+ vmlal.s32 q5, d19, d7
+ vmlal.s32 q0, d18, d21
+ vmlal.s32 q0, d19, d29
+ vmlal.s32 q6, d18, d6
+ add r2, sp, #496
+ vld1.8 {d6-d7}, [r2, : 128]
+ vmlal.s32 q6, d19, d21
+ add r2, sp, #544
+ vld1.8 {d18-d19}, [r2, : 128]
+ vmlal.s32 q0, d30, d8
+ add r2, sp, #640
+ vld1.8 {d20-d21}, [r2, : 128]
+ vmlal.s32 q5, d30, d29
+ add r2, sp, #576
+ vld1.8 {d24-d25}, [r2, : 128]
+ vmlal.s32 q1, d30, d28
+ vadd.i64 q13, q0, q11
+ vadd.i64 q14, q5, q11
+ vmlal.s32 q6, d30, d9
+ vshr.s64 q4, q13, #26
+ vshr.s64 q13, q14, #26
+ vadd.i64 q7, q7, q4
+ vshl.i64 q4, q4, #26
+ vadd.i64 q14, q7, q3
+ vadd.i64 q9, q9, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q15, q9, q3
+ vsub.i64 q0, q0, q4
+ vshr.s64 q4, q14, #25
+ vsub.i64 q5, q5, q13
+ vshr.s64 q13, q15, #25
+ vadd.i64 q6, q6, q4
+ vshl.i64 q4, q4, #25
+ vadd.i64 q14, q6, q11
+ vadd.i64 q2, q2, q13
+ vsub.i64 q4, q7, q4
+ vshr.s64 q7, q14, #26
+ vshl.i64 q13, q13, #25
+ vadd.i64 q14, q2, q11
+ vadd.i64 q8, q8, q7
+ vshl.i64 q7, q7, #26
+ vadd.i64 q15, q8, q3
+ vsub.i64 q9, q9, q13
+ vshr.s64 q13, q14, #26
+ vsub.i64 q6, q6, q7
+ vshr.s64 q7, q15, #25
+ vadd.i64 q10, q10, q13
+ vshl.i64 q13, q13, #26
+ vadd.i64 q14, q10, q3
+ vadd.i64 q1, q1, q7
+ add r2, r3, #240
+ vshl.i64 q7, q7, #25
+ add r4, r3, #144
+ vadd.i64 q15, q1, q11
+ add r2, r2, #8
+ vsub.i64 q2, q2, q13
+ add r4, r4, #8
+ vshr.s64 q13, q14, #25
+ vsub.i64 q7, q8, q7
+ vshr.s64 q8, q15, #26
+ vadd.i64 q14, q13, q13
+ vadd.i64 q12, q12, q8
+ vtrn.32 d12, d14
+ vshl.i64 q8, q8, #26
+ vtrn.32 d13, d15
+ vadd.i64 q3, q12, q3
+ vadd.i64 q0, q0, q14
+ vst1.8 d12, [r2, : 64]!
+ vshl.i64 q7, q13, #4
+ vst1.8 d13, [r4, : 64]!
+ vsub.i64 q1, q1, q8
+ vshr.s64 q3, q3, #25
+ vadd.i64 q0, q0, q7
+ vadd.i64 q5, q5, q3
+ vshl.i64 q3, q3, #25
+ vadd.i64 q6, q5, q11
+ vadd.i64 q0, q0, q13
+ vshl.i64 q7, q13, #25
+ vadd.i64 q8, q0, q11
+ vsub.i64 q3, q12, q3
+ vshr.s64 q6, q6, #26
+ vsub.i64 q7, q10, q7
+ vtrn.32 d2, d6
+ vshr.s64 q8, q8, #26
+ vtrn.32 d3, d7
+ vadd.i64 q3, q9, q6
+ vst1.8 d2, [r2, : 64]
+ vshl.i64 q6, q6, #26
+ vst1.8 d3, [r4, : 64]
+ vadd.i64 q1, q4, q8
+ vtrn.32 d4, d14
+ vshl.i64 q4, q8, #26
+ vtrn.32 d5, d15
+ vsub.i64 q5, q5, q6
+ add r2, r2, #16
+ vsub.i64 q0, q0, q4
+ vst1.8 d4, [r2, : 64]
+ add r4, r4, #16
+ vst1.8 d5, [r4, : 64]
+ vtrn.32 d10, d6
+ vtrn.32 d11, d7
+ sub r2, r2, #8
+ sub r4, r4, #8
+ vtrn.32 d0, d2
+ vtrn.32 d1, d3
+ vst1.8 d10, [r2, : 64]
+ vst1.8 d11, [r4, : 64]
+ sub r2, r2, #24
+ sub r4, r4, #24
+ vst1.8 d0, [r2, : 64]
+ vst1.8 d1, [r4, : 64]
+ ldr r2, [sp, #456]
+ ldr r4, [sp, #460]
+ subs r5, r2, #1
+ bge .Lmainloop
+ add r1, r3, #144
+ add r2, r3, #336
+ vld1.8 {d0-d1}, [r1, : 128]!
+ vld1.8 {d2-d3}, [r1, : 128]!
+ vld1.8 {d4}, [r1, : 64]
+ vst1.8 {d0-d1}, [r2, : 128]!
+ vst1.8 {d2-d3}, [r2, : 128]!
+ vst1.8 d4, [r2, : 64]
+ movw r1, #0
+.Linvertloop:
+ add r2, r3, #144
+ movw r4, #0
+ movw r5, #2
+ cmp r1, #1
+ moveq r5, #1
+ addeq r2, r3, #336
+ addeq r4, r3, #48
+ cmp r1, #2
+ moveq r5, #1
+ addeq r2, r3, #48
+ cmp r1, #3
+ moveq r5, #5
+ addeq r4, r3, #336
+ cmp r1, #4
+ moveq r5, #10
+ cmp r1, #5
+ moveq r5, #20
+ cmp r1, #6
+ moveq r5, #10
+ addeq r2, r3, #336
+ addeq r4, r3, #336
+ cmp r1, #7
+ moveq r5, #50
+ cmp r1, #8
+ moveq r5, #100
+ cmp r1, #9
+ moveq r5, #50
+ addeq r2, r3, #336
+ cmp r1, #10
+ moveq r5, #5
+ addeq r2, r3, #48
+ cmp r1, #11
+ moveq r5, #0
+ addeq r2, r3, #96
+ add r6, r3, #144
+ add r7, r3, #288
+ vld1.8 {d0-d1}, [r6, : 128]!
+ vld1.8 {d2-d3}, [r6, : 128]!
+ vld1.8 {d4}, [r6, : 64]
+ vst1.8 {d0-d1}, [r7, : 128]!
+ vst1.8 {d2-d3}, [r7, : 128]!
+ vst1.8 d4, [r7, : 64]
+ cmp r5, #0
+ beq .Lskipsquaringloop
+.Lsquaringloop:
+ add r6, r3, #288
+ add r7, r3, #288
+ add r8, r3, #288
+ vmov.i32 q0, #19
+ vmov.i32 q1, #0
+ vmov.i32 q2, #1
+ vzip.i32 q1, q2
+ vld1.8 {d4-d5}, [r7, : 128]!
+ vld1.8 {d6-d7}, [r7, : 128]!
+ vld1.8 {d9}, [r7, : 64]
+ vld1.8 {d10-d11}, [r6, : 128]!
+ add r7, sp, #384
+ vld1.8 {d12-d13}, [r6, : 128]!
+ vmul.i32 q7, q2, q0
+ vld1.8 {d8}, [r6, : 64]
+ vext.32 d17, d11, d10, #1
+ vmul.i32 q9, q3, q0
+ vext.32 d16, d10, d8, #1
+ vshl.u32 q10, q5, q1
+ vext.32 d22, d14, d4, #1
+ vext.32 d24, d18, d6, #1
+ vshl.u32 q13, q6, q1
+ vshl.u32 d28, d8, d2
+ vrev64.i32 d22, d22
+ vmul.i32 d1, d9, d1
+ vrev64.i32 d24, d24
+ vext.32 d29, d8, d13, #1
+ vext.32 d0, d1, d9, #1
+ vrev64.i32 d0, d0
+ vext.32 d2, d9, d1, #1
+ vext.32 d23, d15, d5, #1
+ vmull.s32 q4, d20, d4
+ vrev64.i32 d23, d23
+ vmlal.s32 q4, d21, d1
+ vrev64.i32 d2, d2
+ vmlal.s32 q4, d26, d19
+ vext.32 d3, d5, d15, #1
+ vmlal.s32 q4, d27, d18
+ vrev64.i32 d3, d3
+ vmlal.s32 q4, d28, d15
+ vext.32 d14, d12, d11, #1
+ vmull.s32 q5, d16, d23
+ vext.32 d15, d13, d12, #1
+ vmlal.s32 q5, d17, d4
+ vst1.8 d8, [r7, : 64]!
+ vmlal.s32 q5, d14, d1
+ vext.32 d12, d9, d8, #0
+ vmlal.s32 q5, d15, d19
+ vmov.i64 d13, #0
+ vmlal.s32 q5, d29, d18
+ vext.32 d25, d19, d7, #1
+ vmlal.s32 q6, d20, d5
+ vrev64.i32 d25, d25
+ vmlal.s32 q6, d21, d4
+ vst1.8 d11, [r7, : 64]!
+ vmlal.s32 q6, d26, d1
+ vext.32 d9, d10, d10, #0
+ vmlal.s32 q6, d27, d19
+ vmov.i64 d8, #0
+ vmlal.s32 q6, d28, d18
+ vmlal.s32 q4, d16, d24
+ vmlal.s32 q4, d17, d5
+ vmlal.s32 q4, d14, d4
+ vst1.8 d12, [r7, : 64]!
+ vmlal.s32 q4, d15, d1
+ vext.32 d10, d13, d12, #0
+ vmlal.s32 q4, d29, d19
+ vmov.i64 d11, #0
+ vmlal.s32 q5, d20, d6
+ vmlal.s32 q5, d21, d5
+ vmlal.s32 q5, d26, d4
+ vext.32 d13, d8, d8, #0
+ vmlal.s32 q5, d27, d1
+ vmov.i64 d12, #0
+ vmlal.s32 q5, d28, d19
+ vst1.8 d9, [r7, : 64]!
+ vmlal.s32 q6, d16, d25
+ vmlal.s32 q6, d17, d6
+ vst1.8 d10, [r7, : 64]
+ vmlal.s32 q6, d14, d5
+ vext.32 d8, d11, d10, #0
+ vmlal.s32 q6, d15, d4
+ vmov.i64 d9, #0
+ vmlal.s32 q6, d29, d1
+ vmlal.s32 q4, d20, d7
+ vmlal.s32 q4, d21, d6
+ vmlal.s32 q4, d26, d5
+ vext.32 d11, d12, d12, #0
+ vmlal.s32 q4, d27, d4
+ vmov.i64 d10, #0
+ vmlal.s32 q4, d28, d1
+ vmlal.s32 q5, d16, d0
+ sub r6, r7, #32
+ vmlal.s32 q5, d17, d7
+ vmlal.s32 q5, d14, d6
+ vext.32 d30, d9, d8, #0
+ vmlal.s32 q5, d15, d5
+ vld1.8 {d31}, [r6, : 64]!
+ vmlal.s32 q5, d29, d4
+ vmlal.s32 q15, d20, d0
+ vext.32 d0, d6, d18, #1
+ vmlal.s32 q15, d21, d25
+ vrev64.i32 d0, d0
+ vmlal.s32 q15, d26, d24
+ vext.32 d1, d7, d19, #1
+ vext.32 d7, d10, d10, #0
+ vmlal.s32 q15, d27, d23
+ vrev64.i32 d1, d1
+ vld1.8 {d6}, [r6, : 64]
+ vmlal.s32 q15, d28, d22
+ vmlal.s32 q3, d16, d4
+ add r6, r6, #24
+ vmlal.s32 q3, d17, d2
+ vext.32 d4, d31, d30, #0
+ vmov d17, d11
+ vmlal.s32 q3, d14, d1
+ vext.32 d11, d13, d13, #0
+ vext.32 d13, d30, d30, #0
+ vmlal.s32 q3, d15, d0
+ vext.32 d1, d8, d8, #0
+ vmlal.s32 q3, d29, d3
+ vld1.8 {d5}, [r6, : 64]
+ sub r6, r6, #16
+ vext.32 d10, d6, d6, #0
+ vmov.i32 q1, #0xffffffff
+ vshl.i64 q4, q1, #25
+ add r7, sp, #480
+ vld1.8 {d14-d15}, [r7, : 128]
+ vadd.i64 q9, q2, q7
+ vshl.i64 q1, q1, #26
+ vshr.s64 q10, q9, #26
+ vld1.8 {d0}, [r6, : 64]!
+ vadd.i64 q5, q5, q10
+ vand q9, q9, q1
+ vld1.8 {d16}, [r6, : 64]!
+ add r6, sp, #496
+ vld1.8 {d20-d21}, [r6, : 128]
+ vadd.i64 q11, q5, q10
+ vsub.i64 q2, q2, q9
+ vshr.s64 q9, q11, #25
+ vext.32 d12, d5, d4, #0
+ vand q11, q11, q4
+ vadd.i64 q0, q0, q9
+ vmov d19, d7
+ vadd.i64 q3, q0, q7
+ vsub.i64 q5, q5, q11
+ vshr.s64 q11, q3, #26
+ vext.32 d18, d11, d10, #0
+ vand q3, q3, q1
+ vadd.i64 q8, q8, q11
+ vadd.i64 q11, q8, q10
+ vsub.i64 q0, q0, q3
+ vshr.s64 q3, q11, #25
+ vand q11, q11, q4
+ vadd.i64 q3, q6, q3
+ vadd.i64 q6, q3, q7
+ vsub.i64 q8, q8, q11
+ vshr.s64 q11, q6, #26
+ vand q6, q6, q1
+ vadd.i64 q9, q9, q11
+ vadd.i64 d25, d19, d21
+ vsub.i64 q3, q3, q6
+ vshr.s64 d23, d25, #25
+ vand q4, q12, q4
+ vadd.i64 d21, d23, d23
+ vshl.i64 d25, d23, #4
+ vadd.i64 d21, d21, d23
+ vadd.i64 d25, d25, d21
+ vadd.i64 d4, d4, d25
+ vzip.i32 q0, q8
+ vadd.i64 d12, d4, d14
+ add r6, r8, #8
+ vst1.8 d0, [r6, : 64]
+ vsub.i64 d19, d19, d9
+ add r6, r6, #16
+ vst1.8 d16, [r6, : 64]
+ vshr.s64 d22, d12, #26
+ vand q0, q6, q1
+ vadd.i64 d10, d10, d22
+ vzip.i32 q3, q9
+ vsub.i64 d4, d4, d0
+ sub r6, r6, #8
+ vst1.8 d6, [r6, : 64]
+ add r6, r6, #16
+ vst1.8 d18, [r6, : 64]
+ vzip.i32 q2, q5
+ sub r6, r6, #32
+ vst1.8 d4, [r6, : 64]
+ subs r5, r5, #1
+ bhi .Lsquaringloop
+.Lskipsquaringloop:
+ mov r2, r2
+ add r5, r3, #288
+ add r6, r3, #144
+ vmov.i32 q0, #19
+ vmov.i32 q1, #0
+ vmov.i32 q2, #1
+ vzip.i32 q1, q2
+ vld1.8 {d4-d5}, [r5, : 128]!
+ vld1.8 {d6-d7}, [r5, : 128]!
+ vld1.8 {d9}, [r5, : 64]
+ vld1.8 {d10-d11}, [r2, : 128]!
+ add r5, sp, #384
+ vld1.8 {d12-d13}, [r2, : 128]!
+ vmul.i32 q7, q2, q0
+ vld1.8 {d8}, [r2, : 64]
+ vext.32 d17, d11, d10, #1
+ vmul.i32 q9, q3, q0
+ vext.32 d16, d10, d8, #1
+ vshl.u32 q10, q5, q1
+ vext.32 d22, d14, d4, #1
+ vext.32 d24, d18, d6, #1
+ vshl.u32 q13, q6, q1
+ vshl.u32 d28, d8, d2
+ vrev64.i32 d22, d22
+ vmul.i32 d1, d9, d1
+ vrev64.i32 d24, d24
+ vext.32 d29, d8, d13, #1
+ vext.32 d0, d1, d9, #1
+ vrev64.i32 d0, d0
+ vext.32 d2, d9, d1, #1
+ vext.32 d23, d15, d5, #1
+ vmull.s32 q4, d20, d4
+ vrev64.i32 d23, d23
+ vmlal.s32 q4, d21, d1
+ vrev64.i32 d2, d2
+ vmlal.s32 q4, d26, d19
+ vext.32 d3, d5, d15, #1
+ vmlal.s32 q4, d27, d18
+ vrev64.i32 d3, d3
+ vmlal.s32 q4, d28, d15
+ vext.32 d14, d12, d11, #1
+ vmull.s32 q5, d16, d23
+ vext.32 d15, d13, d12, #1
+ vmlal.s32 q5, d17, d4
+ vst1.8 d8, [r5, : 64]!
+ vmlal.s32 q5, d14, d1
+ vext.32 d12, d9, d8, #0
+ vmlal.s32 q5, d15, d19
+ vmov.i64 d13, #0
+ vmlal.s32 q5, d29, d18
+ vext.32 d25, d19, d7, #1
+ vmlal.s32 q6, d20, d5
+ vrev64.i32 d25, d25
+ vmlal.s32 q6, d21, d4
+ vst1.8 d11, [r5, : 64]!
+ vmlal.s32 q6, d26, d1
+ vext.32 d9, d10, d10, #0
+ vmlal.s32 q6, d27, d19
+ vmov.i64 d8, #0
+ vmlal.s32 q6, d28, d18
+ vmlal.s32 q4, d16, d24
+ vmlal.s32 q4, d17, d5
+ vmlal.s32 q4, d14, d4
+ vst1.8 d12, [r5, : 64]!
+ vmlal.s32 q4, d15, d1
+ vext.32 d10, d13, d12, #0
+ vmlal.s32 q4, d29, d19
+ vmov.i64 d11, #0
+ vmlal.s32 q5, d20, d6
+ vmlal.s32 q5, d21, d5
+ vmlal.s32 q5, d26, d4
+ vext.32 d13, d8, d8, #0
+ vmlal.s32 q5, d27, d1
+ vmov.i64 d12, #0
+ vmlal.s32 q5, d28, d19
+ vst1.8 d9, [r5, : 64]!
+ vmlal.s32 q6, d16, d25
+ vmlal.s32 q6, d17, d6
+ vst1.8 d10, [r5, : 64]
+ vmlal.s32 q6, d14, d5
+ vext.32 d8, d11, d10, #0
+ vmlal.s32 q6, d15, d4
+ vmov.i64 d9, #0
+ vmlal.s32 q6, d29, d1
+ vmlal.s32 q4, d20, d7
+ vmlal.s32 q4, d21, d6
+ vmlal.s32 q4, d26, d5
+ vext.32 d11, d12, d12, #0
+ vmlal.s32 q4, d27, d4
+ vmov.i64 d10, #0
+ vmlal.s32 q4, d28, d1
+ vmlal.s32 q5, d16, d0
+ sub r2, r5, #32
+ vmlal.s32 q5, d17, d7
+ vmlal.s32 q5, d14, d6
+ vext.32 d30, d9, d8, #0
+ vmlal.s32 q5, d15, d5
+ vld1.8 {d31}, [r2, : 64]!
+ vmlal.s32 q5, d29, d4
+ vmlal.s32 q15, d20, d0
+ vext.32 d0, d6, d18, #1
+ vmlal.s32 q15, d21, d25
+ vrev64.i32 d0, d0
+ vmlal.s32 q15, d26, d24
+ vext.32 d1, d7, d19, #1
+ vext.32 d7, d10, d10, #0
+ vmlal.s32 q15, d27, d23
+ vrev64.i32 d1, d1
+ vld1.8 {d6}, [r2, : 64]
+ vmlal.s32 q15, d28, d22
+ vmlal.s32 q3, d16, d4
+ add r2, r2, #24
+ vmlal.s32 q3, d17, d2
+ vext.32 d4, d31, d30, #0
+ vmov d17, d11
+ vmlal.s32 q3, d14, d1
+ vext.32 d11, d13, d13, #0
+ vext.32 d13, d30, d30, #0
+ vmlal.s32 q3, d15, d0
+ vext.32 d1, d8, d8, #0
+ vmlal.s32 q3, d29, d3
+ vld1.8 {d5}, [r2, : 64]
+ sub r2, r2, #16
+ vext.32 d10, d6, d6, #0
+ vmov.i32 q1, #0xffffffff
+ vshl.i64 q4, q1, #25
+ add r5, sp, #480
+ vld1.8 {d14-d15}, [r5, : 128]
+ vadd.i64 q9, q2, q7
+ vshl.i64 q1, q1, #26
+ vshr.s64 q10, q9, #26
+ vld1.8 {d0}, [r2, : 64]!
+ vadd.i64 q5, q5, q10
+ vand q9, q9, q1
+ vld1.8 {d16}, [r2, : 64]!
+ add r2, sp, #496
+ vld1.8 {d20-d21}, [r2, : 128]
+ vadd.i64 q11, q5, q10
+ vsub.i64 q2, q2, q9
+ vshr.s64 q9, q11, #25
+ vext.32 d12, d5, d4, #0
+ vand q11, q11, q4
+ vadd.i64 q0, q0, q9
+ vmov d19, d7
+ vadd.i64 q3, q0, q7
+ vsub.i64 q5, q5, q11
+ vshr.s64 q11, q3, #26
+ vext.32 d18, d11, d10, #0
+ vand q3, q3, q1
+ vadd.i64 q8, q8, q11
+ vadd.i64 q11, q8, q10
+ vsub.i64 q0, q0, q3
+ vshr.s64 q3, q11, #25
+ vand q11, q11, q4
+ vadd.i64 q3, q6, q3
+ vadd.i64 q6, q3, q7
+ vsub.i64 q8, q8, q11
+ vshr.s64 q11, q6, #26
+ vand q6, q6, q1
+ vadd.i64 q9, q9, q11
+ vadd.i64 d25, d19, d21
+ vsub.i64 q3, q3, q6
+ vshr.s64 d23, d25, #25
+ vand q4, q12, q4
+ vadd.i64 d21, d23, d23
+ vshl.i64 d25, d23, #4
+ vadd.i64 d21, d21, d23
+ vadd.i64 d25, d25, d21
+ vadd.i64 d4, d4, d25
+ vzip.i32 q0, q8
+ vadd.i64 d12, d4, d14
+ add r2, r6, #8
+ vst1.8 d0, [r2, : 64]
+ vsub.i64 d19, d19, d9
+ add r2, r2, #16
+ vst1.8 d16, [r2, : 64]
+ vshr.s64 d22, d12, #26
+ vand q0, q6, q1
+ vadd.i64 d10, d10, d22
+ vzip.i32 q3, q9
+ vsub.i64 d4, d4, d0
+ sub r2, r2, #8
+ vst1.8 d6, [r2, : 64]
+ add r2, r2, #16
+ vst1.8 d18, [r2, : 64]
+ vzip.i32 q2, q5
+ sub r2, r2, #32
+ vst1.8 d4, [r2, : 64]
+ cmp r4, #0
+ beq .Lskippostcopy
+ add r2, r3, #144
+ mov r4, r4
+ vld1.8 {d0-d1}, [r2, : 128]!
+ vld1.8 {d2-d3}, [r2, : 128]!
+ vld1.8 {d4}, [r2, : 64]
+ vst1.8 {d0-d1}, [r4, : 128]!
+ vst1.8 {d2-d3}, [r4, : 128]!
+ vst1.8 d4, [r4, : 64]
+.Lskippostcopy:
+ cmp r1, #1
+ bne .Lskipfinalcopy
+ add r2, r3, #288
+ add r4, r3, #144
+ vld1.8 {d0-d1}, [r2, : 128]!
+ vld1.8 {d2-d3}, [r2, : 128]!
+ vld1.8 {d4}, [r2, : 64]
+ vst1.8 {d0-d1}, [r4, : 128]!
+ vst1.8 {d2-d3}, [r4, : 128]!
+ vst1.8 d4, [r4, : 64]
+.Lskipfinalcopy:
+ add r1, r1, #1
+ cmp r1, #12
+ blo .Linvertloop
+ add r1, r3, #144
+ ldr r2, [r1], #4
+ ldr r3, [r1], #4
+ ldr r4, [r1], #4
+ ldr r5, [r1], #4
+ ldr r6, [r1], #4
+ ldr r7, [r1], #4
+ ldr r8, [r1], #4
+ ldr r9, [r1], #4
+ ldr r10, [r1], #4
+ ldr r1, [r1]
+ add r11, r1, r1, LSL #4
+ add r11, r11, r1, LSL #1
+ add r11, r11, #16777216
+ mov r11, r11, ASR #25
+ add r11, r11, r2
+ mov r11, r11, ASR #26
+ add r11, r11, r3
+ mov r11, r11, ASR #25
+ add r11, r11, r4
+ mov r11, r11, ASR #26
+ add r11, r11, r5
+ mov r11, r11, ASR #25
+ add r11, r11, r6
+ mov r11, r11, ASR #26
+ add r11, r11, r7
+ mov r11, r11, ASR #25
+ add r11, r11, r8
+ mov r11, r11, ASR #26
+ add r11, r11, r9
+ mov r11, r11, ASR #25
+ add r11, r11, r10
+ mov r11, r11, ASR #26
+ add r11, r11, r1
+ mov r11, r11, ASR #25
+ add r2, r2, r11
+ add r2, r2, r11, LSL #1
+ add r2, r2, r11, LSL #4
+ mov r11, r2, ASR #26
+ add r3, r3, r11
+ sub r2, r2, r11, LSL #26
+ mov r11, r3, ASR #25
+ add r4, r4, r11
+ sub r3, r3, r11, LSL #25
+ mov r11, r4, ASR #26
+ add r5, r5, r11
+ sub r4, r4, r11, LSL #26
+ mov r11, r5, ASR #25
+ add r6, r6, r11
+ sub r5, r5, r11, LSL #25
+ mov r11, r6, ASR #26
+ add r7, r7, r11
+ sub r6, r6, r11, LSL #26
+ mov r11, r7, ASR #25
+ add r8, r8, r11
+ sub r7, r7, r11, LSL #25
+ mov r11, r8, ASR #26
+ add r9, r9, r11
+ sub r8, r8, r11, LSL #26
+ mov r11, r9, ASR #25
+ add r10, r10, r11
+ sub r9, r9, r11, LSL #25
+ mov r11, r10, ASR #26
+ add r1, r1, r11
+ sub r10, r10, r11, LSL #26
+ mov r11, r1, ASR #25
+ sub r1, r1, r11, LSL #25
+ add r2, r2, r3, LSL #26
+ mov r3, r3, LSR #6
+ add r3, r3, r4, LSL #19
+ mov r4, r4, LSR #13
+ add r4, r4, r5, LSL #13
+ mov r5, r5, LSR #19
+ add r5, r5, r6, LSL #6
+ add r6, r7, r8, LSL #25
+ mov r7, r8, LSR #7
+ add r7, r7, r9, LSL #19
+ mov r8, r9, LSR #13
+ add r8, r8, r10, LSL #12
+ mov r9, r10, LSR #20
+ add r1, r9, r1, LSL #6
+ str r2, [r0]
+ str r3, [r0, #4]
+ str r4, [r0, #8]
+ str r5, [r0, #12]
+ str r6, [r0, #16]
+ str r7, [r0, #20]
+ str r8, [r0, #24]
+ str r1, [r0, #28]
+ movw r0, #0
+ mov sp, ip
+ pop {r4-r11, pc}
+ENDPROC(curve25519_neon)
diff --git a/arch/arm/crypto/curve25519-glue.c b/arch/arm/crypto/curve25519-glue.c
new file mode 100644
index 0000000000..9bdafd5788
--- /dev/null
+++ b/arch/arm/crypto/curve25519-glue.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * Based on public domain code from Daniel J. Bernstein and Peter Schwabe. This
+ * began from SUPERCOP's curve25519/neon2/scalarmult.s, but has subsequently been
+ * manually reworked for use in kernel space.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/kpp.h>
+#include <crypto/internal/simd.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/scatterlist.h>
+#include <crypto/curve25519.h>
+
+asmlinkage void curve25519_neon(u8 mypublic[CURVE25519_KEY_SIZE],
+ const u8 secret[CURVE25519_KEY_SIZE],
+ const u8 basepoint[CURVE25519_KEY_SIZE]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void curve25519_arch(u8 out[CURVE25519_KEY_SIZE],
+ const u8 scalar[CURVE25519_KEY_SIZE],
+ const u8 point[CURVE25519_KEY_SIZE])
+{
+ if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
+ kernel_neon_begin();
+ curve25519_neon(out, scalar, point);
+ kernel_neon_end();
+ } else {
+ curve25519_generic(out, scalar, point);
+ }
+}
+EXPORT_SYMBOL(curve25519_arch);
+
+void curve25519_base_arch(u8 pub[CURVE25519_KEY_SIZE],
+ const u8 secret[CURVE25519_KEY_SIZE])
+{
+ return curve25519_arch(pub, secret, curve25519_base_point);
+}
+EXPORT_SYMBOL(curve25519_base_arch);
+
+static int curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+ unsigned int len)
+{
+ u8 *secret = kpp_tfm_ctx(tfm);
+
+ if (!len)
+ curve25519_generate_secret(secret);
+ else if (len == CURVE25519_KEY_SIZE &&
+ crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE))
+ memcpy(secret, buf, CURVE25519_KEY_SIZE);
+ else
+ return -EINVAL;
+ return 0;
+}
+
+static int curve25519_compute_value(struct kpp_request *req)
+{
+ struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+ const u8 *secret = kpp_tfm_ctx(tfm);
+ u8 public_key[CURVE25519_KEY_SIZE];
+ u8 buf[CURVE25519_KEY_SIZE];
+ int copied, nbytes;
+ u8 const *bp;
+
+ if (req->src) {
+ copied = sg_copy_to_buffer(req->src,
+ sg_nents_for_len(req->src,
+ CURVE25519_KEY_SIZE),
+ public_key, CURVE25519_KEY_SIZE);
+ if (copied != CURVE25519_KEY_SIZE)
+ return -EINVAL;
+ bp = public_key;
+ } else {
+ bp = curve25519_base_point;
+ }
+
+ curve25519_arch(buf, secret, bp);
+
+ /* might want less than we've got */
+ nbytes = min_t(size_t, CURVE25519_KEY_SIZE, req->dst_len);
+ copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst,
+ nbytes),
+ buf, nbytes);
+ if (copied != nbytes)
+ return -EINVAL;
+ return 0;
+}
+
+static unsigned int curve25519_max_size(struct crypto_kpp *tfm)
+{
+ return CURVE25519_KEY_SIZE;
+}
+
+static struct kpp_alg curve25519_alg = {
+ .base.cra_name = "curve25519",
+ .base.cra_driver_name = "curve25519-neon",
+ .base.cra_priority = 200,
+ .base.cra_module = THIS_MODULE,
+ .base.cra_ctxsize = CURVE25519_KEY_SIZE,
+
+ .set_secret = curve25519_set_secret,
+ .generate_public_key = curve25519_compute_value,
+ .compute_shared_secret = curve25519_compute_value,
+ .max_size = curve25519_max_size,
+};
+
+static int __init arm_curve25519_init(void)
+{
+ if (elf_hwcap & HWCAP_NEON) {
+ static_branch_enable(&have_neon);
+ return IS_REACHABLE(CONFIG_CRYPTO_KPP) ?
+ crypto_register_kpp(&curve25519_alg) : 0;
+ }
+ return 0;
+}
+
+static void __exit arm_curve25519_exit(void)
+{
+ if (IS_REACHABLE(CONFIG_CRYPTO_KPP) && elf_hwcap & HWCAP_NEON)
+ crypto_unregister_kpp(&curve25519_alg);
+}
+
+module_init(arm_curve25519_init);
+module_exit(arm_curve25519_exit);
+
+MODULE_ALIAS_CRYPTO("curve25519");
+MODULE_ALIAS_CRYPTO("curve25519-neon");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/crypto/ghash-ce-core.S b/arch/arm/crypto/ghash-ce-core.S
new file mode 100644
index 0000000000..858c0d6679
--- /dev/null
+++ b/arch/arm/crypto/ghash-ce-core.S
@@ -0,0 +1,695 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Accelerated GHASH implementation with NEON/ARMv8 vmull.p8/64 instructions.
+ *
+ * Copyright (C) 2015 - 2017 Linaro Ltd.
+ * Copyright (C) 2023 Google LLC. <ardb@google.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .arch armv8-a
+ .fpu crypto-neon-fp-armv8
+
+ SHASH .req q0
+ T1 .req q1
+ XL .req q2
+ XM .req q3
+ XH .req q4
+ IN1 .req q4
+
+ SHASH_L .req d0
+ SHASH_H .req d1
+ T1_L .req d2
+ T1_H .req d3
+ XL_L .req d4
+ XL_H .req d5
+ XM_L .req d6
+ XM_H .req d7
+ XH_L .req d8
+
+ t0l .req d10
+ t0h .req d11
+ t1l .req d12
+ t1h .req d13
+ t2l .req d14
+ t2h .req d15
+ t3l .req d16
+ t3h .req d17
+ t4l .req d18
+ t4h .req d19
+
+ t0q .req q5
+ t1q .req q6
+ t2q .req q7
+ t3q .req q8
+ t4q .req q9
+ XH2 .req q9
+
+ s1l .req d20
+ s1h .req d21
+ s2l .req d22
+ s2h .req d23
+ s3l .req d24
+ s3h .req d25
+ s4l .req d26
+ s4h .req d27
+
+ MASK .req d28
+ SHASH2_p8 .req d28
+
+ k16 .req d29
+ k32 .req d30
+ k48 .req d31
+ SHASH2_p64 .req d31
+
+ HH .req q10
+ HH3 .req q11
+ HH4 .req q12
+ HH34 .req q13
+
+ HH_L .req d20
+ HH_H .req d21
+ HH3_L .req d22
+ HH3_H .req d23
+ HH4_L .req d24
+ HH4_H .req d25
+ HH34_L .req d26
+ HH34_H .req d27
+ SHASH2_H .req d29
+
+ XL2 .req q5
+ XM2 .req q6
+ T2 .req q7
+ T3 .req q8
+
+ XL2_L .req d10
+ XL2_H .req d11
+ XM2_L .req d12
+ XM2_H .req d13
+ T3_L .req d16
+ T3_H .req d17
+
+ .text
+
+ .macro __pmull_p64, rd, rn, rm, b1, b2, b3, b4
+ vmull.p64 \rd, \rn, \rm
+ .endm
+
+ /*
+ * This implementation of 64x64 -> 128 bit polynomial multiplication
+ * using vmull.p8 instructions (8x8 -> 16) is taken from the paper
+ * "Fast Software Polynomial Multiplication on ARM Processors Using
+ * the NEON Engine" by Danilo Camara, Conrado Gouvea, Julio Lopez and
+ * Ricardo Dahab (https://hal.inria.fr/hal-01506572)
+ *
+ * It has been slightly tweaked for in-order performance, and to allow
+ * 'rq' to overlap with 'ad' or 'bd'.
+ */
+ .macro __pmull_p8, rq, ad, bd, b1=t4l, b2=t3l, b3=t4l, b4=t3l
+ vext.8 t0l, \ad, \ad, #1 @ A1
+ .ifc \b1, t4l
+ vext.8 t4l, \bd, \bd, #1 @ B1
+ .endif
+ vmull.p8 t0q, t0l, \bd @ F = A1*B
+ vext.8 t1l, \ad, \ad, #2 @ A2
+ vmull.p8 t4q, \ad, \b1 @ E = A*B1
+ .ifc \b2, t3l
+ vext.8 t3l, \bd, \bd, #2 @ B2
+ .endif
+ vmull.p8 t1q, t1l, \bd @ H = A2*B
+ vext.8 t2l, \ad, \ad, #3 @ A3
+ vmull.p8 t3q, \ad, \b2 @ G = A*B2
+ veor t0q, t0q, t4q @ L = E + F
+ .ifc \b3, t4l
+ vext.8 t4l, \bd, \bd, #3 @ B3
+ .endif
+ vmull.p8 t2q, t2l, \bd @ J = A3*B
+ veor t0l, t0l, t0h @ t0 = (L) (P0 + P1) << 8
+ veor t1q, t1q, t3q @ M = G + H
+ .ifc \b4, t3l
+ vext.8 t3l, \bd, \bd, #4 @ B4
+ .endif
+ vmull.p8 t4q, \ad, \b3 @ I = A*B3
+ veor t1l, t1l, t1h @ t1 = (M) (P2 + P3) << 16
+ vmull.p8 t3q, \ad, \b4 @ K = A*B4
+ vand t0h, t0h, k48
+ vand t1h, t1h, k32
+ veor t2q, t2q, t4q @ N = I + J
+ veor t0l, t0l, t0h
+ veor t1l, t1l, t1h
+ veor t2l, t2l, t2h @ t2 = (N) (P4 + P5) << 24
+ vand t2h, t2h, k16
+ veor t3l, t3l, t3h @ t3 = (K) (P6 + P7) << 32
+ vmov.i64 t3h, #0
+ vext.8 t0q, t0q, t0q, #15
+ veor t2l, t2l, t2h
+ vext.8 t1q, t1q, t1q, #14
+ vmull.p8 \rq, \ad, \bd @ D = A*B
+ vext.8 t2q, t2q, t2q, #13
+ vext.8 t3q, t3q, t3q, #12
+ veor t0q, t0q, t1q
+ veor t2q, t2q, t3q
+ veor \rq, \rq, t0q
+ veor \rq, \rq, t2q
+ .endm
+
+ //
+ // PMULL (64x64->128) based reduction for CPUs that can do
+ // it in a single instruction.
+ //
+ .macro __pmull_reduce_p64
+ vmull.p64 T1, XL_L, MASK
+
+ veor XH_L, XH_L, XM_H
+ vext.8 T1, T1, T1, #8
+ veor XL_H, XL_H, XM_L
+ veor T1, T1, XL
+
+ vmull.p64 XL, T1_H, MASK
+ .endm
+
+ //
+ // Alternative reduction for CPUs that lack support for the
+ // 64x64->128 PMULL instruction
+ //
+ .macro __pmull_reduce_p8
+ veor XL_H, XL_H, XM_L
+ veor XH_L, XH_L, XM_H
+
+ vshl.i64 T1, XL, #57
+ vshl.i64 T2, XL, #62
+ veor T1, T1, T2
+ vshl.i64 T2, XL, #63
+ veor T1, T1, T2
+ veor XL_H, XL_H, T1_L
+ veor XH_L, XH_L, T1_H
+
+ vshr.u64 T1, XL, #1
+ veor XH, XH, XL
+ veor XL, XL, T1
+ vshr.u64 T1, T1, #6
+ vshr.u64 XL, XL, #1
+ .endm
+
+ .macro ghash_update, pn, enc, aggregate=1, head=1
+ vld1.64 {XL}, [r1]
+
+ .if \head
+ /* do the head block first, if supplied */
+ ldr ip, [sp]
+ teq ip, #0
+ beq 0f
+ vld1.64 {T1}, [ip]
+ teq r0, #0
+ b 3f
+ .endif
+
+0: .ifc \pn, p64
+ .if \aggregate
+ tst r0, #3 // skip until #blocks is a
+ bne 2f // round multiple of 4
+
+ vld1.8 {XL2-XM2}, [r2]!
+1: vld1.8 {T2-T3}, [r2]!
+
+ .ifnb \enc
+ \enc\()_4x XL2, XM2, T2, T3
+
+ add ip, r3, #16
+ vld1.64 {HH}, [ip, :128]!
+ vld1.64 {HH3-HH4}, [ip, :128]
+
+ veor SHASH2_p64, SHASH_L, SHASH_H
+ veor SHASH2_H, HH_L, HH_H
+ veor HH34_L, HH3_L, HH3_H
+ veor HH34_H, HH4_L, HH4_H
+
+ vmov.i8 MASK, #0xe1
+ vshl.u64 MASK, MASK, #57
+ .endif
+
+ vrev64.8 XL2, XL2
+ vrev64.8 XM2, XM2
+
+ subs r0, r0, #4
+
+ vext.8 T1, XL2, XL2, #8
+ veor XL2_H, XL2_H, XL_L
+ veor XL, XL, T1
+
+ vrev64.8 T1, T3
+ vrev64.8 T3, T2
+
+ vmull.p64 XH, HH4_H, XL_H // a1 * b1
+ veor XL2_H, XL2_H, XL_H
+ vmull.p64 XL, HH4_L, XL_L // a0 * b0
+ vmull.p64 XM, HH34_H, XL2_H // (a1 + a0)(b1 + b0)
+
+ vmull.p64 XH2, HH3_H, XM2_L // a1 * b1
+ veor XM2_L, XM2_L, XM2_H
+ vmull.p64 XL2, HH3_L, XM2_H // a0 * b0
+ vmull.p64 XM2, HH34_L, XM2_L // (a1 + a0)(b1 + b0)
+
+ veor XH, XH, XH2
+ veor XL, XL, XL2
+ veor XM, XM, XM2
+
+ vmull.p64 XH2, HH_H, T3_L // a1 * b1
+ veor T3_L, T3_L, T3_H
+ vmull.p64 XL2, HH_L, T3_H // a0 * b0
+ vmull.p64 XM2, SHASH2_H, T3_L // (a1 + a0)(b1 + b0)
+
+ veor XH, XH, XH2
+ veor XL, XL, XL2
+ veor XM, XM, XM2
+
+ vmull.p64 XH2, SHASH_H, T1_L // a1 * b1
+ veor T1_L, T1_L, T1_H
+ vmull.p64 XL2, SHASH_L, T1_H // a0 * b0
+ vmull.p64 XM2, SHASH2_p64, T1_L // (a1 + a0)(b1 + b0)
+
+ veor XH, XH, XH2
+ veor XL, XL, XL2
+ veor XM, XM, XM2
+
+ beq 4f
+
+ vld1.8 {XL2-XM2}, [r2]!
+
+ veor T1, XL, XH
+ veor XM, XM, T1
+
+ __pmull_reduce_p64
+
+ veor T1, T1, XH
+ veor XL, XL, T1
+
+ b 1b
+ .endif
+ .endif
+
+2: vld1.8 {T1}, [r2]!
+
+ .ifnb \enc
+ \enc\()_1x T1
+ veor SHASH2_p64, SHASH_L, SHASH_H
+ vmov.i8 MASK, #0xe1
+ vshl.u64 MASK, MASK, #57
+ .endif
+
+ subs r0, r0, #1
+
+3: /* multiply XL by SHASH in GF(2^128) */
+ vrev64.8 T1, T1
+
+ vext.8 IN1, T1, T1, #8
+ veor T1_L, T1_L, XL_H
+ veor XL, XL, IN1
+
+ __pmull_\pn XH, XL_H, SHASH_H, s1h, s2h, s3h, s4h @ a1 * b1
+ veor T1, T1, XL
+ __pmull_\pn XL, XL_L, SHASH_L, s1l, s2l, s3l, s4l @ a0 * b0
+ __pmull_\pn XM, T1_L, SHASH2_\pn @ (a1+a0)(b1+b0)
+
+4: veor T1, XL, XH
+ veor XM, XM, T1
+
+ __pmull_reduce_\pn
+
+ veor T1, T1, XH
+ veor XL, XL, T1
+
+ bne 0b
+ .endm
+
+ /*
+ * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+ * struct ghash_key const *k, const char *head)
+ */
+ENTRY(pmull_ghash_update_p64)
+ vld1.64 {SHASH}, [r3]!
+ vld1.64 {HH}, [r3]!
+ vld1.64 {HH3-HH4}, [r3]
+
+ veor SHASH2_p64, SHASH_L, SHASH_H
+ veor SHASH2_H, HH_L, HH_H
+ veor HH34_L, HH3_L, HH3_H
+ veor HH34_H, HH4_L, HH4_H
+
+ vmov.i8 MASK, #0xe1
+ vshl.u64 MASK, MASK, #57
+
+ ghash_update p64
+ vst1.64 {XL}, [r1]
+
+ bx lr
+ENDPROC(pmull_ghash_update_p64)
+
+ENTRY(pmull_ghash_update_p8)
+ vld1.64 {SHASH}, [r3]
+ veor SHASH2_p8, SHASH_L, SHASH_H
+
+ vext.8 s1l, SHASH_L, SHASH_L, #1
+ vext.8 s2l, SHASH_L, SHASH_L, #2
+ vext.8 s3l, SHASH_L, SHASH_L, #3
+ vext.8 s4l, SHASH_L, SHASH_L, #4
+ vext.8 s1h, SHASH_H, SHASH_H, #1
+ vext.8 s2h, SHASH_H, SHASH_H, #2
+ vext.8 s3h, SHASH_H, SHASH_H, #3
+ vext.8 s4h, SHASH_H, SHASH_H, #4
+
+ vmov.i64 k16, #0xffff
+ vmov.i64 k32, #0xffffffff
+ vmov.i64 k48, #0xffffffffffff
+
+ ghash_update p8
+ vst1.64 {XL}, [r1]
+
+ bx lr
+ENDPROC(pmull_ghash_update_p8)
+
+ e0 .req q9
+ e1 .req q10
+ e2 .req q11
+ e3 .req q12
+ e0l .req d18
+ e0h .req d19
+ e2l .req d22
+ e2h .req d23
+ e3l .req d24
+ e3h .req d25
+ ctr .req q13
+ ctr0 .req d26
+ ctr1 .req d27
+
+ ek0 .req q14
+ ek1 .req q15
+
+ .macro round, rk:req, regs:vararg
+ .irp r, \regs
+ aese.8 \r, \rk
+ aesmc.8 \r, \r
+ .endr
+ .endm
+
+ .macro aes_encrypt, rkp, rounds, regs:vararg
+ vld1.8 {ek0-ek1}, [\rkp, :128]!
+ cmp \rounds, #12
+ blt .L\@ // AES-128
+
+ round ek0, \regs
+ vld1.8 {ek0}, [\rkp, :128]!
+ round ek1, \regs
+ vld1.8 {ek1}, [\rkp, :128]!
+
+ beq .L\@ // AES-192
+
+ round ek0, \regs
+ vld1.8 {ek0}, [\rkp, :128]!
+ round ek1, \regs
+ vld1.8 {ek1}, [\rkp, :128]!
+
+.L\@: .rept 4
+ round ek0, \regs
+ vld1.8 {ek0}, [\rkp, :128]!
+ round ek1, \regs
+ vld1.8 {ek1}, [\rkp, :128]!
+ .endr
+
+ round ek0, \regs
+ vld1.8 {ek0}, [\rkp, :128]
+
+ .irp r, \regs
+ aese.8 \r, ek1
+ .endr
+ .irp r, \regs
+ veor \r, \r, ek0
+ .endr
+ .endm
+
+pmull_aes_encrypt:
+ add ip, r5, #4
+ vld1.8 {ctr0}, [r5] // load 12 byte IV
+ vld1.8 {ctr1}, [ip]
+ rev r8, r7
+ vext.8 ctr1, ctr1, ctr1, #4
+ add r7, r7, #1
+ vmov.32 ctr1[1], r8
+ vmov e0, ctr
+
+ add ip, r3, #64
+ aes_encrypt ip, r6, e0
+ bx lr
+ENDPROC(pmull_aes_encrypt)
+
+pmull_aes_encrypt_4x:
+ add ip, r5, #4
+ vld1.8 {ctr0}, [r5]
+ vld1.8 {ctr1}, [ip]
+ rev r8, r7
+ vext.8 ctr1, ctr1, ctr1, #4
+ add r7, r7, #1
+ vmov.32 ctr1[1], r8
+ rev ip, r7
+ vmov e0, ctr
+ add r7, r7, #1
+ vmov.32 ctr1[1], ip
+ rev r8, r7
+ vmov e1, ctr
+ add r7, r7, #1
+ vmov.32 ctr1[1], r8
+ rev ip, r7
+ vmov e2, ctr
+ add r7, r7, #1
+ vmov.32 ctr1[1], ip
+ vmov e3, ctr
+
+ add ip, r3, #64
+ aes_encrypt ip, r6, e0, e1, e2, e3
+ bx lr
+ENDPROC(pmull_aes_encrypt_4x)
+
+pmull_aes_encrypt_final:
+ add ip, r5, #4
+ vld1.8 {ctr0}, [r5]
+ vld1.8 {ctr1}, [ip]
+ rev r8, r7
+ vext.8 ctr1, ctr1, ctr1, #4
+ mov r7, #1 << 24 // BE #1 for the tag
+ vmov.32 ctr1[1], r8
+ vmov e0, ctr
+ vmov.32 ctr1[1], r7
+ vmov e1, ctr
+
+ add ip, r3, #64
+ aes_encrypt ip, r6, e0, e1
+ bx lr
+ENDPROC(pmull_aes_encrypt_final)
+
+ .macro enc_1x, in0
+ bl pmull_aes_encrypt
+ veor \in0, \in0, e0
+ vst1.8 {\in0}, [r4]!
+ .endm
+
+ .macro dec_1x, in0
+ bl pmull_aes_encrypt
+ veor e0, e0, \in0
+ vst1.8 {e0}, [r4]!
+ .endm
+
+ .macro enc_4x, in0, in1, in2, in3
+ bl pmull_aes_encrypt_4x
+
+ veor \in0, \in0, e0
+ veor \in1, \in1, e1
+ veor \in2, \in2, e2
+ veor \in3, \in3, e3
+
+ vst1.8 {\in0-\in1}, [r4]!
+ vst1.8 {\in2-\in3}, [r4]!
+ .endm
+
+ .macro dec_4x, in0, in1, in2, in3
+ bl pmull_aes_encrypt_4x
+
+ veor e0, e0, \in0
+ veor e1, e1, \in1
+ veor e2, e2, \in2
+ veor e3, e3, \in3
+
+ vst1.8 {e0-e1}, [r4]!
+ vst1.8 {e2-e3}, [r4]!
+ .endm
+
+ /*
+ * void pmull_gcm_encrypt(int blocks, u64 dg[], const char *src,
+ * struct gcm_key const *k, char *dst,
+ * char *iv, int rounds, u32 counter)
+ */
+ENTRY(pmull_gcm_encrypt)
+ push {r4-r8, lr}
+ ldrd r4, r5, [sp, #24]
+ ldrd r6, r7, [sp, #32]
+
+ vld1.64 {SHASH}, [r3]
+
+ ghash_update p64, enc, head=0
+ vst1.64 {XL}, [r1]
+
+ pop {r4-r8, pc}
+ENDPROC(pmull_gcm_encrypt)
+
+ /*
+ * void pmull_gcm_decrypt(int blocks, u64 dg[], const char *src,
+ * struct gcm_key const *k, char *dst,
+ * char *iv, int rounds, u32 counter)
+ */
+ENTRY(pmull_gcm_decrypt)
+ push {r4-r8, lr}
+ ldrd r4, r5, [sp, #24]
+ ldrd r6, r7, [sp, #32]
+
+ vld1.64 {SHASH}, [r3]
+
+ ghash_update p64, dec, head=0
+ vst1.64 {XL}, [r1]
+
+ pop {r4-r8, pc}
+ENDPROC(pmull_gcm_decrypt)
+
+ /*
+ * void pmull_gcm_enc_final(int bytes, u64 dg[], char *tag,
+ * struct gcm_key const *k, char *head,
+ * char *iv, int rounds, u32 counter)
+ */
+ENTRY(pmull_gcm_enc_final)
+ push {r4-r8, lr}
+ ldrd r4, r5, [sp, #24]
+ ldrd r6, r7, [sp, #32]
+
+ bl pmull_aes_encrypt_final
+
+ cmp r0, #0
+ beq .Lenc_final
+
+ mov_l ip, .Lpermute
+ sub r4, r4, #16
+ add r8, ip, r0
+ add ip, ip, #32
+ add r4, r4, r0
+ sub ip, ip, r0
+
+ vld1.8 {e3}, [r8] // permute vector for key stream
+ vld1.8 {e2}, [ip] // permute vector for ghash input
+
+ vtbl.8 e3l, {e0}, e3l
+ vtbl.8 e3h, {e0}, e3h
+
+ vld1.8 {e0}, [r4] // encrypt tail block
+ veor e0, e0, e3
+ vst1.8 {e0}, [r4]
+
+ vtbl.8 T1_L, {e0}, e2l
+ vtbl.8 T1_H, {e0}, e2h
+
+ vld1.64 {XL}, [r1]
+.Lenc_final:
+ vld1.64 {SHASH}, [r3, :128]
+ vmov.i8 MASK, #0xe1
+ veor SHASH2_p64, SHASH_L, SHASH_H
+ vshl.u64 MASK, MASK, #57
+ mov r0, #1
+ bne 3f // process head block first
+ ghash_update p64, aggregate=0, head=0
+
+ vrev64.8 XL, XL
+ vext.8 XL, XL, XL, #8
+ veor XL, XL, e1
+
+ sub r2, r2, #16 // rewind src pointer
+ vst1.8 {XL}, [r2] // store tag
+
+ pop {r4-r8, pc}
+ENDPROC(pmull_gcm_enc_final)
+
+ /*
+ * int pmull_gcm_dec_final(int bytes, u64 dg[], char *tag,
+ * struct gcm_key const *k, char *head,
+ * char *iv, int rounds, u32 counter,
+ * const char *otag, int authsize)
+ */
+ENTRY(pmull_gcm_dec_final)
+ push {r4-r8, lr}
+ ldrd r4, r5, [sp, #24]
+ ldrd r6, r7, [sp, #32]
+
+ bl pmull_aes_encrypt_final
+
+ cmp r0, #0
+ beq .Ldec_final
+
+ mov_l ip, .Lpermute
+ sub r4, r4, #16
+ add r8, ip, r0
+ add ip, ip, #32
+ add r4, r4, r0
+ sub ip, ip, r0
+
+ vld1.8 {e3}, [r8] // permute vector for key stream
+ vld1.8 {e2}, [ip] // permute vector for ghash input
+
+ vtbl.8 e3l, {e0}, e3l
+ vtbl.8 e3h, {e0}, e3h
+
+ vld1.8 {e0}, [r4]
+
+ vtbl.8 T1_L, {e0}, e2l
+ vtbl.8 T1_H, {e0}, e2h
+
+ veor e0, e0, e3
+ vst1.8 {e0}, [r4]
+
+ vld1.64 {XL}, [r1]
+.Ldec_final:
+ vld1.64 {SHASH}, [r3]
+ vmov.i8 MASK, #0xe1
+ veor SHASH2_p64, SHASH_L, SHASH_H
+ vshl.u64 MASK, MASK, #57
+ mov r0, #1
+ bne 3f // process head block first
+ ghash_update p64, aggregate=0, head=0
+
+ vrev64.8 XL, XL
+ vext.8 XL, XL, XL, #8
+ veor XL, XL, e1
+
+ mov_l ip, .Lpermute
+ ldrd r2, r3, [sp, #40] // otag and authsize
+ vld1.8 {T1}, [r2]
+ add ip, ip, r3
+ vceq.i8 T1, T1, XL // compare tags
+ vmvn T1, T1 // 0 for eq, -1 for ne
+
+ vld1.8 {e0}, [ip]
+ vtbl.8 XL_L, {T1}, e0l // keep authsize bytes only
+ vtbl.8 XL_H, {T1}, e0h
+
+ vpmin.s8 XL_L, XL_L, XL_H // take the minimum s8 across the vector
+ vpmin.s8 XL_L, XL_L, XL_L
+ vmov.32 r0, XL_L[0] // fail if != 0x0
+
+ pop {r4-r8, pc}
+ENDPROC(pmull_gcm_dec_final)
+
+ .section ".rodata", "a", %progbits
+ .align 5
+.Lpermute:
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+ .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
new file mode 100644
index 0000000000..3ddf05b423
--- /dev/null
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -0,0 +1,795 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated GHASH implementation with ARMv8 vmull.p64 instructions.
+ *
+ * Copyright (C) 2015 - 2018 Linaro Ltd.
+ * Copyright (C) 2023 Google LLC.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/gcm.h>
+#include <crypto/b128ops.h>
+#include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/gf128mul.h>
+#include <crypto/scatterwalk.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/jump_label.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH hash function using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ardb@kernel.org>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("ghash");
+MODULE_ALIAS_CRYPTO("gcm(aes)");
+MODULE_ALIAS_CRYPTO("rfc4106(gcm(aes))");
+
+#define GHASH_BLOCK_SIZE 16
+#define GHASH_DIGEST_SIZE 16
+
+#define RFC4106_NONCE_SIZE 4
+
+struct ghash_key {
+ be128 k;
+ u64 h[][2];
+};
+
+struct gcm_key {
+ u64 h[4][2];
+ u32 rk[AES_MAX_KEYLENGTH_U32];
+ int rounds;
+ u8 nonce[]; // for RFC4106 nonce
+};
+
+struct ghash_desc_ctx {
+ u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+ u8 buf[GHASH_BLOCK_SIZE];
+ u32 count;
+};
+
+struct ghash_async_ctx {
+ struct cryptd_ahash *cryptd_tfm;
+};
+
+asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
+ u64 const h[][2], const char *head);
+
+asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
+ u64 const h[][2], const char *head);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_p64);
+
+static int ghash_init(struct shash_desc *desc)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ *ctx = (struct ghash_desc_ctx){};
+ return 0;
+}
+
+static void ghash_do_update(int blocks, u64 dg[], const char *src,
+ struct ghash_key *key, const char *head)
+{
+ if (likely(crypto_simd_usable())) {
+ kernel_neon_begin();
+ if (static_branch_likely(&use_p64))
+ pmull_ghash_update_p64(blocks, dg, src, key->h, head);
+ else
+ pmull_ghash_update_p8(blocks, dg, src, key->h, head);
+ kernel_neon_end();
+ } else {
+ be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
+
+ do {
+ const u8 *in = src;
+
+ if (head) {
+ in = head;
+ blocks++;
+ head = NULL;
+ } else {
+ src += GHASH_BLOCK_SIZE;
+ }
+
+ crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
+ gf128mul_lle(&dst, &key->k);
+ } while (--blocks);
+
+ dg[0] = be64_to_cpu(dst.b);
+ dg[1] = be64_to_cpu(dst.a);
+ }
+}
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+ unsigned int len)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+ ctx->count += len;
+
+ if ((partial + len) >= GHASH_BLOCK_SIZE) {
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+ int blocks;
+
+ if (partial) {
+ int p = GHASH_BLOCK_SIZE - partial;
+
+ memcpy(ctx->buf + partial, src, p);
+ src += p;
+ len -= p;
+ }
+
+ blocks = len / GHASH_BLOCK_SIZE;
+ len %= GHASH_BLOCK_SIZE;
+
+ ghash_do_update(blocks, ctx->digest, src, key,
+ partial ? ctx->buf : NULL);
+ src += blocks * GHASH_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(ctx->buf + partial, src, len);
+ return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+ if (partial) {
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+ memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+ ghash_do_update(1, ctx->digest, ctx->buf, key, NULL);
+ }
+ put_unaligned_be64(ctx->digest[1], dst);
+ put_unaligned_be64(ctx->digest[0], dst + 8);
+
+ *ctx = (struct ghash_desc_ctx){};
+ return 0;
+}
+
+static void ghash_reflect(u64 h[], const be128 *k)
+{
+ u64 carry = be64_to_cpu(k->a) >> 63;
+
+ h[0] = (be64_to_cpu(k->b) << 1) | carry;
+ h[1] = (be64_to_cpu(k->a) << 1) | (be64_to_cpu(k->b) >> 63);
+
+ if (carry)
+ h[1] ^= 0xc200000000000000UL;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+ const u8 *inkey, unsigned int keylen)
+{
+ struct ghash_key *key = crypto_shash_ctx(tfm);
+
+ if (keylen != GHASH_BLOCK_SIZE)
+ return -EINVAL;
+
+ /* needed for the fallback */
+ memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
+ ghash_reflect(key->h[0], &key->k);
+
+ if (static_branch_likely(&use_p64)) {
+ be128 h = key->k;
+
+ gf128mul_lle(&h, &key->k);
+ ghash_reflect(key->h[1], &h);
+
+ gf128mul_lle(&h, &key->k);
+ ghash_reflect(key->h[2], &h);
+
+ gf128mul_lle(&h, &key->k);
+ ghash_reflect(key->h[3], &h);
+ }
+ return 0;
+}
+
+static struct shash_alg ghash_alg = {
+ .digestsize = GHASH_DIGEST_SIZE,
+ .init = ghash_init,
+ .update = ghash_update,
+ .final = ghash_final,
+ .setkey = ghash_setkey,
+ .descsize = sizeof(struct ghash_desc_ctx),
+
+ .base.cra_name = "ghash",
+ .base.cra_driver_name = "ghash-ce-sync",
+ .base.cra_priority = 300 - 1,
+ .base.cra_blocksize = GHASH_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct ghash_key) + sizeof(u64[2]),
+ .base.cra_module = THIS_MODULE,
+};
+
+static int ghash_async_init(struct ahash_request *req)
+{
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+ struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+ desc->tfm = child;
+ return crypto_shash_init(desc);
+}
+
+static int ghash_async_update(struct ahash_request *req)
+{
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+ if (!crypto_simd_usable() ||
+ (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+ memcpy(cryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+ return crypto_ahash_update(cryptd_req);
+ } else {
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+ return shash_ahash_update(req, desc);
+ }
+}
+
+static int ghash_async_final(struct ahash_request *req)
+{
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+ if (!crypto_simd_usable() ||
+ (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+ memcpy(cryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+ return crypto_ahash_final(cryptd_req);
+ } else {
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+ return crypto_shash_final(desc, req->result);
+ }
+}
+
+static int ghash_async_digest(struct ahash_request *req)
+{
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+ if (!crypto_simd_usable() ||
+ (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+ memcpy(cryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+ return crypto_ahash_digest(cryptd_req);
+ } else {
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+ struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+ desc->tfm = child;
+ return shash_ahash_digest(req, desc);
+ }
+}
+
+static int ghash_async_import(struct ahash_request *req, const void *in)
+{
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+ desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
+
+ return crypto_shash_import(desc, in);
+}
+
+static int ghash_async_export(struct ahash_request *req, void *out)
+{
+ struct ahash_request *cryptd_req = ahash_request_ctx(req);
+ struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+ return crypto_shash_export(desc, out);
+}
+
+static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct crypto_ahash *child = &ctx->cryptd_tfm->base;
+
+ crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+ crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm)
+ & CRYPTO_TFM_REQ_MASK);
+ return crypto_ahash_setkey(child, key, keylen);
+}
+
+static int ghash_async_init_tfm(struct crypto_tfm *tfm)
+{
+ struct cryptd_ahash *cryptd_tfm;
+ struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ cryptd_tfm = cryptd_alloc_ahash("ghash-ce-sync", 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ctx->cryptd_tfm = cryptd_tfm;
+ crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+ sizeof(struct ahash_request) +
+ crypto_ahash_reqsize(&cryptd_tfm->base));
+
+ return 0;
+}
+
+static void ghash_async_exit_tfm(struct crypto_tfm *tfm)
+{
+ struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ cryptd_free_ahash(ctx->cryptd_tfm);
+}
+
+static struct ahash_alg ghash_async_alg = {
+ .init = ghash_async_init,
+ .update = ghash_async_update,
+ .final = ghash_async_final,
+ .setkey = ghash_async_setkey,
+ .digest = ghash_async_digest,
+ .import = ghash_async_import,
+ .export = ghash_async_export,
+ .halg.digestsize = GHASH_DIGEST_SIZE,
+ .halg.statesize = sizeof(struct ghash_desc_ctx),
+ .halg.base = {
+ .cra_name = "ghash",
+ .cra_driver_name = "ghash-ce",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_ASYNC,
+ .cra_blocksize = GHASH_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct ghash_async_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_init = ghash_async_init_tfm,
+ .cra_exit = ghash_async_exit_tfm,
+ },
+};
+
+
+void pmull_gcm_encrypt(int blocks, u64 dg[], const char *src,
+ struct gcm_key const *k, char *dst,
+ const char *iv, int rounds, u32 counter);
+
+void pmull_gcm_enc_final(int blocks, u64 dg[], char *tag,
+ struct gcm_key const *k, char *head,
+ const char *iv, int rounds, u32 counter);
+
+void pmull_gcm_decrypt(int bytes, u64 dg[], const char *src,
+ struct gcm_key const *k, char *dst,
+ const char *iv, int rounds, u32 counter);
+
+int pmull_gcm_dec_final(int bytes, u64 dg[], char *tag,
+ struct gcm_key const *k, char *head,
+ const char *iv, int rounds, u32 counter,
+ const char *otag, int authsize);
+
+static int gcm_aes_setkey(struct crypto_aead *tfm, const u8 *inkey,
+ unsigned int keylen)
+{
+ struct gcm_key *ctx = crypto_aead_ctx(tfm);
+ struct crypto_aes_ctx aes_ctx;
+ be128 h, k;
+ int ret;
+
+ ret = aes_expandkey(&aes_ctx, inkey, keylen);
+ if (ret)
+ return -EINVAL;
+
+ aes_encrypt(&aes_ctx, (u8 *)&k, (u8[AES_BLOCK_SIZE]){});
+
+ memcpy(ctx->rk, aes_ctx.key_enc, sizeof(ctx->rk));
+ ctx->rounds = 6 + keylen / 4;
+
+ memzero_explicit(&aes_ctx, sizeof(aes_ctx));
+
+ ghash_reflect(ctx->h[0], &k);
+
+ h = k;
+ gf128mul_lle(&h, &k);
+ ghash_reflect(ctx->h[1], &h);
+
+ gf128mul_lle(&h, &k);
+ ghash_reflect(ctx->h[2], &h);
+
+ gf128mul_lle(&h, &k);
+ ghash_reflect(ctx->h[3], &h);
+
+ return 0;
+}
+
+static int gcm_aes_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+ return crypto_gcm_check_authsize(authsize);
+}
+
+static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[],
+ int *buf_count, struct gcm_key *ctx)
+{
+ if (*buf_count > 0) {
+ int buf_added = min(count, GHASH_BLOCK_SIZE - *buf_count);
+
+ memcpy(&buf[*buf_count], src, buf_added);
+
+ *buf_count += buf_added;
+ src += buf_added;
+ count -= buf_added;
+ }
+
+ if (count >= GHASH_BLOCK_SIZE || *buf_count == GHASH_BLOCK_SIZE) {
+ int blocks = count / GHASH_BLOCK_SIZE;
+
+ pmull_ghash_update_p64(blocks, dg, src, ctx->h,
+ *buf_count ? buf : NULL);
+
+ src += blocks * GHASH_BLOCK_SIZE;
+ count %= GHASH_BLOCK_SIZE;
+ *buf_count = 0;
+ }
+
+ if (count > 0) {
+ memcpy(buf, src, count);
+ *buf_count = count;
+ }
+}
+
+static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[], u32 len)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_key *ctx = crypto_aead_ctx(aead);
+ u8 buf[GHASH_BLOCK_SIZE];
+ struct scatter_walk walk;
+ int buf_count = 0;
+
+ scatterwalk_start(&walk, req->src);
+
+ do {
+ u32 n = scatterwalk_clamp(&walk, len);
+ u8 *p;
+
+ if (!n) {
+ scatterwalk_start(&walk, sg_next(walk.sg));
+ n = scatterwalk_clamp(&walk, len);
+ }
+
+ p = scatterwalk_map(&walk);
+ gcm_update_mac(dg, p, n, buf, &buf_count, ctx);
+ scatterwalk_unmap(p);
+
+ if (unlikely(len / SZ_4K > (len - n) / SZ_4K)) {
+ kernel_neon_end();
+ kernel_neon_begin();
+ }
+
+ len -= n;
+ scatterwalk_advance(&walk, n);
+ scatterwalk_done(&walk, 0, len);
+ } while (len);
+
+ if (buf_count) {
+ memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count);
+ pmull_ghash_update_p64(1, dg, buf, ctx->h, NULL);
+ }
+}
+
+static int gcm_encrypt(struct aead_request *req, const u8 *iv, u32 assoclen)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_key *ctx = crypto_aead_ctx(aead);
+ struct skcipher_walk walk;
+ u8 buf[AES_BLOCK_SIZE];
+ u32 counter = 2;
+ u64 dg[2] = {};
+ be128 lengths;
+ const u8 *src;
+ u8 *tag, *dst;
+ int tail, err;
+
+ if (WARN_ON_ONCE(!may_use_simd()))
+ return -EBUSY;
+
+ err = skcipher_walk_aead_encrypt(&walk, req, false);
+
+ kernel_neon_begin();
+
+ if (assoclen)
+ gcm_calculate_auth_mac(req, dg, assoclen);
+
+ src = walk.src.virt.addr;
+ dst = walk.dst.virt.addr;
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ int nblocks = walk.nbytes / AES_BLOCK_SIZE;
+
+ pmull_gcm_encrypt(nblocks, dg, src, ctx, dst, iv,
+ ctx->rounds, counter);
+ counter += nblocks;
+
+ if (walk.nbytes == walk.total) {
+ src += nblocks * AES_BLOCK_SIZE;
+ dst += nblocks * AES_BLOCK_SIZE;
+ break;
+ }
+
+ kernel_neon_end();
+
+ err = skcipher_walk_done(&walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ if (err)
+ return err;
+
+ src = walk.src.virt.addr;
+ dst = walk.dst.virt.addr;
+
+ kernel_neon_begin();
+ }
+
+
+ lengths.a = cpu_to_be64(assoclen * 8);
+ lengths.b = cpu_to_be64(req->cryptlen * 8);
+
+ tag = (u8 *)&lengths;
+ tail = walk.nbytes % AES_BLOCK_SIZE;
+
+ /*
+ * Bounce via a buffer unless we are encrypting in place and src/dst
+ * are not pointing to the start of the walk buffer. In that case, we
+ * can do a NEON load/xor/store sequence in place as long as we move
+ * the plain/ciphertext and keystream to the start of the register. If
+ * not, do a memcpy() to the end of the buffer so we can reuse the same
+ * logic.
+ */
+ if (unlikely(tail && (tail == walk.nbytes || src != dst)))
+ src = memcpy(buf + sizeof(buf) - tail, src, tail);
+
+ pmull_gcm_enc_final(tail, dg, tag, ctx, (u8 *)src, iv,
+ ctx->rounds, counter);
+ kernel_neon_end();
+
+ if (unlikely(tail && src != dst))
+ memcpy(dst, src, tail);
+
+ if (walk.nbytes) {
+ err = skcipher_walk_done(&walk, 0);
+ if (err)
+ return err;
+ }
+
+ /* copy authtag to end of dst */
+ scatterwalk_map_and_copy(tag, req->dst, req->assoclen + req->cryptlen,
+ crypto_aead_authsize(aead), 1);
+
+ return 0;
+}
+
+static int gcm_decrypt(struct aead_request *req, const u8 *iv, u32 assoclen)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_key *ctx = crypto_aead_ctx(aead);
+ int authsize = crypto_aead_authsize(aead);
+ struct skcipher_walk walk;
+ u8 otag[AES_BLOCK_SIZE];
+ u8 buf[AES_BLOCK_SIZE];
+ u32 counter = 2;
+ u64 dg[2] = {};
+ be128 lengths;
+ const u8 *src;
+ u8 *tag, *dst;
+ int tail, err, ret;
+
+ if (WARN_ON_ONCE(!may_use_simd()))
+ return -EBUSY;
+
+ scatterwalk_map_and_copy(otag, req->src,
+ req->assoclen + req->cryptlen - authsize,
+ authsize, 0);
+
+ err = skcipher_walk_aead_decrypt(&walk, req, false);
+
+ kernel_neon_begin();
+
+ if (assoclen)
+ gcm_calculate_auth_mac(req, dg, assoclen);
+
+ src = walk.src.virt.addr;
+ dst = walk.dst.virt.addr;
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ int nblocks = walk.nbytes / AES_BLOCK_SIZE;
+
+ pmull_gcm_decrypt(nblocks, dg, src, ctx, dst, iv,
+ ctx->rounds, counter);
+ counter += nblocks;
+
+ if (walk.nbytes == walk.total) {
+ src += nblocks * AES_BLOCK_SIZE;
+ dst += nblocks * AES_BLOCK_SIZE;
+ break;
+ }
+
+ kernel_neon_end();
+
+ err = skcipher_walk_done(&walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ if (err)
+ return err;
+
+ src = walk.src.virt.addr;
+ dst = walk.dst.virt.addr;
+
+ kernel_neon_begin();
+ }
+
+ lengths.a = cpu_to_be64(assoclen * 8);
+ lengths.b = cpu_to_be64((req->cryptlen - authsize) * 8);
+
+ tag = (u8 *)&lengths;
+ tail = walk.nbytes % AES_BLOCK_SIZE;
+
+ if (unlikely(tail && (tail == walk.nbytes || src != dst)))
+ src = memcpy(buf + sizeof(buf) - tail, src, tail);
+
+ ret = pmull_gcm_dec_final(tail, dg, tag, ctx, (u8 *)src, iv,
+ ctx->rounds, counter, otag, authsize);
+ kernel_neon_end();
+
+ if (unlikely(tail && src != dst))
+ memcpy(dst, src, tail);
+
+ if (walk.nbytes) {
+ err = skcipher_walk_done(&walk, 0);
+ if (err)
+ return err;
+ }
+
+ return ret ? -EBADMSG : 0;
+}
+
+static int gcm_aes_encrypt(struct aead_request *req)
+{
+ return gcm_encrypt(req, req->iv, req->assoclen);
+}
+
+static int gcm_aes_decrypt(struct aead_request *req)
+{
+ return gcm_decrypt(req, req->iv, req->assoclen);
+}
+
+static int rfc4106_setkey(struct crypto_aead *tfm, const u8 *inkey,
+ unsigned int keylen)
+{
+ struct gcm_key *ctx = crypto_aead_ctx(tfm);
+ int err;
+
+ keylen -= RFC4106_NONCE_SIZE;
+ err = gcm_aes_setkey(tfm, inkey, keylen);
+ if (err)
+ return err;
+
+ memcpy(ctx->nonce, inkey + keylen, RFC4106_NONCE_SIZE);
+ return 0;
+}
+
+static int rfc4106_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+ return crypto_rfc4106_check_authsize(authsize);
+}
+
+static int rfc4106_encrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_key *ctx = crypto_aead_ctx(aead);
+ u8 iv[GCM_AES_IV_SIZE];
+
+ memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+ memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+ return crypto_ipsec_check_assoclen(req->assoclen) ?:
+ gcm_encrypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE);
+}
+
+static int rfc4106_decrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_key *ctx = crypto_aead_ctx(aead);
+ u8 iv[GCM_AES_IV_SIZE];
+
+ memcpy(iv, ctx->nonce, RFC4106_NONCE_SIZE);
+ memcpy(iv + RFC4106_NONCE_SIZE, req->iv, GCM_RFC4106_IV_SIZE);
+
+ return crypto_ipsec_check_assoclen(req->assoclen) ?:
+ gcm_decrypt(req, iv, req->assoclen - GCM_RFC4106_IV_SIZE);
+}
+
+static struct aead_alg gcm_aes_algs[] = {{
+ .ivsize = GCM_AES_IV_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+ .maxauthsize = AES_BLOCK_SIZE,
+ .setkey = gcm_aes_setkey,
+ .setauthsize = gcm_aes_setauthsize,
+ .encrypt = gcm_aes_encrypt,
+ .decrypt = gcm_aes_decrypt,
+
+ .base.cra_name = "gcm(aes)",
+ .base.cra_driver_name = "gcm-aes-ce",
+ .base.cra_priority = 400,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct gcm_key),
+ .base.cra_module = THIS_MODULE,
+}, {
+ .ivsize = GCM_RFC4106_IV_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+ .maxauthsize = AES_BLOCK_SIZE,
+ .setkey = rfc4106_setkey,
+ .setauthsize = rfc4106_setauthsize,
+ .encrypt = rfc4106_encrypt,
+ .decrypt = rfc4106_decrypt,
+
+ .base.cra_name = "rfc4106(gcm(aes))",
+ .base.cra_driver_name = "rfc4106-gcm-aes-ce",
+ .base.cra_priority = 400,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct gcm_key) + RFC4106_NONCE_SIZE,
+ .base.cra_module = THIS_MODULE,
+}};
+
+static int __init ghash_ce_mod_init(void)
+{
+ int err;
+
+ if (!(elf_hwcap & HWCAP_NEON))
+ return -ENODEV;
+
+ if (elf_hwcap2 & HWCAP2_PMULL) {
+ err = crypto_register_aeads(gcm_aes_algs,
+ ARRAY_SIZE(gcm_aes_algs));
+ if (err)
+ return err;
+ ghash_alg.base.cra_ctxsize += 3 * sizeof(u64[2]);
+ static_branch_enable(&use_p64);
+ }
+
+ err = crypto_register_shash(&ghash_alg);
+ if (err)
+ goto err_aead;
+ err = crypto_register_ahash(&ghash_async_alg);
+ if (err)
+ goto err_shash;
+
+ return 0;
+
+err_shash:
+ crypto_unregister_shash(&ghash_alg);
+err_aead:
+ if (elf_hwcap2 & HWCAP2_PMULL)
+ crypto_unregister_aeads(gcm_aes_algs,
+ ARRAY_SIZE(gcm_aes_algs));
+ return err;
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+ crypto_unregister_ahash(&ghash_async_alg);
+ crypto_unregister_shash(&ghash_alg);
+ if (elf_hwcap2 & HWCAP2_PMULL)
+ crypto_unregister_aeads(gcm_aes_algs,
+ ARRAY_SIZE(gcm_aes_algs));
+}
+
+module_init(ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm/crypto/nh-neon-core.S b/arch/arm/crypto/nh-neon-core.S
new file mode 100644
index 0000000000..01620a0782
--- /dev/null
+++ b/arch/arm/crypto/nh-neon-core.S
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NH - ε-almost-universal hash function, NEON accelerated version
+ *
+ * Copyright 2018 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+ .text
+ .fpu neon
+
+ KEY .req r0
+ MESSAGE .req r1
+ MESSAGE_LEN .req r2
+ HASH .req r3
+
+ PASS0_SUMS .req q0
+ PASS0_SUM_A .req d0
+ PASS0_SUM_B .req d1
+ PASS1_SUMS .req q1
+ PASS1_SUM_A .req d2
+ PASS1_SUM_B .req d3
+ PASS2_SUMS .req q2
+ PASS2_SUM_A .req d4
+ PASS2_SUM_B .req d5
+ PASS3_SUMS .req q3
+ PASS3_SUM_A .req d6
+ PASS3_SUM_B .req d7
+ K0 .req q4
+ K1 .req q5
+ K2 .req q6
+ K3 .req q7
+ T0 .req q8
+ T0_L .req d16
+ T0_H .req d17
+ T1 .req q9
+ T1_L .req d18
+ T1_H .req d19
+ T2 .req q10
+ T2_L .req d20
+ T2_H .req d21
+ T3 .req q11
+ T3_L .req d22
+ T3_H .req d23
+
+.macro _nh_stride k0, k1, k2, k3
+
+ // Load next message stride
+ vld1.8 {T3}, [MESSAGE]!
+
+ // Load next key stride
+ vld1.32 {\k3}, [KEY]!
+
+ // Add message words to key words
+ vadd.u32 T0, T3, \k0
+ vadd.u32 T1, T3, \k1
+ vadd.u32 T2, T3, \k2
+ vadd.u32 T3, T3, \k3
+
+ // Multiply 32x32 => 64 and accumulate
+ vmlal.u32 PASS0_SUMS, T0_L, T0_H
+ vmlal.u32 PASS1_SUMS, T1_L, T1_H
+ vmlal.u32 PASS2_SUMS, T2_L, T2_H
+ vmlal.u32 PASS3_SUMS, T3_L, T3_H
+.endm
+
+/*
+ * void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ * __le64 hash[NH_NUM_PASSES])
+ *
+ * It's guaranteed that message_len % 16 == 0.
+ */
+ENTRY(nh_neon)
+
+ vld1.32 {K0,K1}, [KEY]!
+ vmov.u64 PASS0_SUMS, #0
+ vmov.u64 PASS1_SUMS, #0
+ vld1.32 {K2}, [KEY]!
+ vmov.u64 PASS2_SUMS, #0
+ vmov.u64 PASS3_SUMS, #0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ blt .Lloop4_done
+.Lloop4:
+ _nh_stride K0, K1, K2, K3
+ _nh_stride K1, K2, K3, K0
+ _nh_stride K2, K3, K0, K1
+ _nh_stride K3, K0, K1, K2
+ subs MESSAGE_LEN, MESSAGE_LEN, #64
+ bge .Lloop4
+
+.Lloop4_done:
+ ands MESSAGE_LEN, MESSAGE_LEN, #63
+ beq .Ldone
+ _nh_stride K0, K1, K2, K3
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K1, K2, K3, K0
+
+ subs MESSAGE_LEN, MESSAGE_LEN, #16
+ beq .Ldone
+ _nh_stride K2, K3, K0, K1
+
+.Ldone:
+ // Sum the accumulators for each pass, then store the sums to 'hash'
+ vadd.u64 T0_L, PASS0_SUM_A, PASS0_SUM_B
+ vadd.u64 T0_H, PASS1_SUM_A, PASS1_SUM_B
+ vadd.u64 T1_L, PASS2_SUM_A, PASS2_SUM_B
+ vadd.u64 T1_H, PASS3_SUM_A, PASS3_SUM_B
+ vst1.8 {T0-T1}, [HASH]
+ bx lr
+ENDPROC(nh_neon)
diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c
new file mode 100644
index 0000000000..e93e41ff26
--- /dev/null
+++ b/arch/arm/crypto/nhpoly1305-neon-glue.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
+ * (NEON accelerated version)
+ *
+ * Copyright 2018 Google LLC
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/nhpoly1305.h>
+#include <linux/module.h>
+
+asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ __le64 hash[NH_NUM_PASSES]);
+
+static int nhpoly1305_neon_update(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen)
+{
+ if (srclen < 64 || !crypto_simd_usable())
+ return crypto_nhpoly1305_update(desc, src, srclen);
+
+ do {
+ unsigned int n = min_t(unsigned int, srclen, SZ_4K);
+
+ kernel_neon_begin();
+ crypto_nhpoly1305_update_helper(desc, src, n, nh_neon);
+ kernel_neon_end();
+ src += n;
+ srclen -= n;
+ } while (srclen);
+ return 0;
+}
+
+static struct shash_alg nhpoly1305_alg = {
+ .base.cra_name = "nhpoly1305",
+ .base.cra_driver_name = "nhpoly1305-neon",
+ .base.cra_priority = 200,
+ .base.cra_ctxsize = sizeof(struct nhpoly1305_key),
+ .base.cra_module = THIS_MODULE,
+ .digestsize = POLY1305_DIGEST_SIZE,
+ .init = crypto_nhpoly1305_init,
+ .update = nhpoly1305_neon_update,
+ .final = crypto_nhpoly1305_final,
+ .setkey = crypto_nhpoly1305_setkey,
+ .descsize = sizeof(struct nhpoly1305_state),
+};
+
+static int __init nhpoly1305_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_NEON))
+ return -ENODEV;
+
+ return crypto_register_shash(&nhpoly1305_alg);
+}
+
+static void __exit nhpoly1305_mod_exit(void)
+{
+ crypto_unregister_shash(&nhpoly1305_alg);
+}
+
+module_init(nhpoly1305_mod_init);
+module_exit(nhpoly1305_mod_exit);
+
+MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (NEON-accelerated)");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("nhpoly1305");
+MODULE_ALIAS_CRYPTO("nhpoly1305-neon");
diff --git a/arch/arm/crypto/poly1305-armv4.pl b/arch/arm/crypto/poly1305-armv4.pl
new file mode 100644
index 0000000000..6d79498d31
--- /dev/null
+++ b/arch/arm/crypto/poly1305-armv4.pl
@@ -0,0 +1,1236 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
+# project.
+# ====================================================================
+#
+# IALU(*)/gcc-4.4 NEON
+#
+# ARM11xx(ARMv6) 7.78/+100% -
+# Cortex-A5 6.35/+130% 3.00
+# Cortex-A8 6.25/+115% 2.36
+# Cortex-A9 5.10/+95% 2.55
+# Cortex-A15 3.85/+85% 1.25(**)
+# Snapdragon S4 5.70/+100% 1.48(**)
+#
+# (*) this is for -march=armv6, i.e. with bunch of ldrb loading data;
+# (**) these are trade-off results, they can be improved by ~8% but at
+# the cost of 15/12% regression on Cortex-A5/A7, it's even possible
+# to improve Cortex-A9 result, but then A5/A7 loose more than 20%;
+
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+ ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+ ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+ die "can't locate arm-xlate.pl";
+
+ open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+ open STDOUT,">$output";
+}
+
+($ctx,$inp,$len,$padbit)=map("r$_",(0..3));
+
+$code.=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define poly1305_init poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit poly1305_emit_arm
+.globl poly1305_blocks_neon
+#endif
+
+#if defined(__thumb2__)
+.syntax unified
+.thumb
+#else
+.code 32
+#endif
+
+.text
+
+.globl poly1305_emit
+.globl poly1305_blocks
+.globl poly1305_init
+.type poly1305_init,%function
+.align 5
+poly1305_init:
+.Lpoly1305_init:
+ stmdb sp!,{r4-r11}
+
+ eor r3,r3,r3
+ cmp $inp,#0
+ str r3,[$ctx,#0] @ zero hash value
+ str r3,[$ctx,#4]
+ str r3,[$ctx,#8]
+ str r3,[$ctx,#12]
+ str r3,[$ctx,#16]
+ str r3,[$ctx,#36] @ clear is_base2_26
+ add $ctx,$ctx,#20
+
+#ifdef __thumb2__
+ it eq
+#endif
+ moveq r0,#0
+ beq .Lno_key
+
+#if __ARM_MAX_ARCH__>=7
+ mov r3,#-1
+ str r3,[$ctx,#28] @ impossible key power value
+# ifndef __KERNEL__
+ adr r11,.Lpoly1305_init
+ ldr r12,.LOPENSSL_armcap
+# endif
+#endif
+ ldrb r4,[$inp,#0]
+ mov r10,#0x0fffffff
+ ldrb r5,[$inp,#1]
+ and r3,r10,#-4 @ 0x0ffffffc
+ ldrb r6,[$inp,#2]
+ ldrb r7,[$inp,#3]
+ orr r4,r4,r5,lsl#8
+ ldrb r5,[$inp,#4]
+ orr r4,r4,r6,lsl#16
+ ldrb r6,[$inp,#5]
+ orr r4,r4,r7,lsl#24
+ ldrb r7,[$inp,#6]
+ and r4,r4,r10
+
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+# if !defined(_WIN32)
+ ldr r12,[r11,r12] @ OPENSSL_armcap_P
+# endif
+# if defined(__APPLE__) || defined(_WIN32)
+ ldr r12,[r12]
+# endif
+#endif
+ ldrb r8,[$inp,#7]
+ orr r5,r5,r6,lsl#8
+ ldrb r6,[$inp,#8]
+ orr r5,r5,r7,lsl#16
+ ldrb r7,[$inp,#9]
+ orr r5,r5,r8,lsl#24
+ ldrb r8,[$inp,#10]
+ and r5,r5,r3
+
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ tst r12,#ARMV7_NEON @ check for NEON
+# ifdef __thumb2__
+ adr r9,.Lpoly1305_blocks_neon
+ adr r11,.Lpoly1305_blocks
+ it ne
+ movne r11,r9
+ adr r12,.Lpoly1305_emit
+ orr r11,r11,#1 @ thumb-ify addresses
+ orr r12,r12,#1
+# else
+ add r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
+ ite eq
+ addeq r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
+ addne r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
+# endif
+#endif
+ ldrb r9,[$inp,#11]
+ orr r6,r6,r7,lsl#8
+ ldrb r7,[$inp,#12]
+ orr r6,r6,r8,lsl#16
+ ldrb r8,[$inp,#13]
+ orr r6,r6,r9,lsl#24
+ ldrb r9,[$inp,#14]
+ and r6,r6,r3
+
+ ldrb r10,[$inp,#15]
+ orr r7,r7,r8,lsl#8
+ str r4,[$ctx,#0]
+ orr r7,r7,r9,lsl#16
+ str r5,[$ctx,#4]
+ orr r7,r7,r10,lsl#24
+ str r6,[$ctx,#8]
+ and r7,r7,r3
+ str r7,[$ctx,#12]
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ stmia r2,{r11,r12} @ fill functions table
+ mov r0,#1
+#else
+ mov r0,#0
+#endif
+.Lno_key:
+ ldmia sp!,{r4-r11}
+#if __ARM_ARCH__>=5
+ ret @ bx lr
+#else
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size poly1305_init,.-poly1305_init
+___
+{
+my ($h0,$h1,$h2,$h3,$h4,$r0,$r1,$r2,$r3)=map("r$_",(4..12));
+my ($s1,$s2,$s3)=($r1,$r2,$r3);
+
+$code.=<<___;
+.type poly1305_blocks,%function
+.align 5
+poly1305_blocks:
+.Lpoly1305_blocks:
+ stmdb sp!,{r3-r11,lr}
+
+ ands $len,$len,#-16
+ beq .Lno_data
+
+ add $len,$len,$inp @ end pointer
+ sub sp,sp,#32
+
+#if __ARM_ARCH__<7
+ ldmia $ctx,{$h0-$r3} @ load context
+ add $ctx,$ctx,#20
+ str $len,[sp,#16] @ offload stuff
+ str $ctx,[sp,#12]
+#else
+ ldr lr,[$ctx,#36] @ is_base2_26
+ ldmia $ctx!,{$h0-$h4} @ load hash value
+ str $len,[sp,#16] @ offload stuff
+ str $ctx,[sp,#12]
+
+ adds $r0,$h0,$h1,lsl#26 @ base 2^26 -> base 2^32
+ mov $r1,$h1,lsr#6
+ adcs $r1,$r1,$h2,lsl#20
+ mov $r2,$h2,lsr#12
+ adcs $r2,$r2,$h3,lsl#14
+ mov $r3,$h3,lsr#18
+ adcs $r3,$r3,$h4,lsl#8
+ mov $len,#0
+ teq lr,#0
+ str $len,[$ctx,#16] @ clear is_base2_26
+ adc $len,$len,$h4,lsr#24
+
+ itttt ne
+ movne $h0,$r0 @ choose between radixes
+ movne $h1,$r1
+ movne $h2,$r2
+ movne $h3,$r3
+ ldmia $ctx,{$r0-$r3} @ load key
+ it ne
+ movne $h4,$len
+#endif
+
+ mov lr,$inp
+ cmp $padbit,#0
+ str $r1,[sp,#20]
+ str $r2,[sp,#24]
+ str $r3,[sp,#28]
+ b .Loop
+
+.align 4
+.Loop:
+#if __ARM_ARCH__<7
+ ldrb r0,[lr],#16 @ load input
+# ifdef __thumb2__
+ it hi
+# endif
+ addhi $h4,$h4,#1 @ 1<<128
+ ldrb r1,[lr,#-15]
+ ldrb r2,[lr,#-14]
+ ldrb r3,[lr,#-13]
+ orr r1,r0,r1,lsl#8
+ ldrb r0,[lr,#-12]
+ orr r2,r1,r2,lsl#16
+ ldrb r1,[lr,#-11]
+ orr r3,r2,r3,lsl#24
+ ldrb r2,[lr,#-10]
+ adds $h0,$h0,r3 @ accumulate input
+
+ ldrb r3,[lr,#-9]
+ orr r1,r0,r1,lsl#8
+ ldrb r0,[lr,#-8]
+ orr r2,r1,r2,lsl#16
+ ldrb r1,[lr,#-7]
+ orr r3,r2,r3,lsl#24
+ ldrb r2,[lr,#-6]
+ adcs $h1,$h1,r3
+
+ ldrb r3,[lr,#-5]
+ orr r1,r0,r1,lsl#8
+ ldrb r0,[lr,#-4]
+ orr r2,r1,r2,lsl#16
+ ldrb r1,[lr,#-3]
+ orr r3,r2,r3,lsl#24
+ ldrb r2,[lr,#-2]
+ adcs $h2,$h2,r3
+
+ ldrb r3,[lr,#-1]
+ orr r1,r0,r1,lsl#8
+ str lr,[sp,#8] @ offload input pointer
+ orr r2,r1,r2,lsl#16
+ add $s1,$r1,$r1,lsr#2
+ orr r3,r2,r3,lsl#24
+#else
+ ldr r0,[lr],#16 @ load input
+ it hi
+ addhi $h4,$h4,#1 @ padbit
+ ldr r1,[lr,#-12]
+ ldr r2,[lr,#-8]
+ ldr r3,[lr,#-4]
+# ifdef __ARMEB__
+ rev r0,r0
+ rev r1,r1
+ rev r2,r2
+ rev r3,r3
+# endif
+ adds $h0,$h0,r0 @ accumulate input
+ str lr,[sp,#8] @ offload input pointer
+ adcs $h1,$h1,r1
+ add $s1,$r1,$r1,lsr#2
+ adcs $h2,$h2,r2
+#endif
+ add $s2,$r2,$r2,lsr#2
+ adcs $h3,$h3,r3
+ add $s3,$r3,$r3,lsr#2
+
+ umull r2,r3,$h1,$r0
+ adc $h4,$h4,#0
+ umull r0,r1,$h0,$r0
+ umlal r2,r3,$h4,$s1
+ umlal r0,r1,$h3,$s1
+ ldr $r1,[sp,#20] @ reload $r1
+ umlal r2,r3,$h2,$s3
+ umlal r0,r1,$h1,$s3
+ umlal r2,r3,$h3,$s2
+ umlal r0,r1,$h2,$s2
+ umlal r2,r3,$h0,$r1
+ str r0,[sp,#0] @ future $h0
+ mul r0,$s2,$h4
+ ldr $r2,[sp,#24] @ reload $r2
+ adds r2,r2,r1 @ d1+=d0>>32
+ eor r1,r1,r1
+ adc lr,r3,#0 @ future $h2
+ str r2,[sp,#4] @ future $h1
+
+ mul r2,$s3,$h4
+ eor r3,r3,r3
+ umlal r0,r1,$h3,$s3
+ ldr $r3,[sp,#28] @ reload $r3
+ umlal r2,r3,$h3,$r0
+ umlal r0,r1,$h2,$r0
+ umlal r2,r3,$h2,$r1
+ umlal r0,r1,$h1,$r1
+ umlal r2,r3,$h1,$r2
+ umlal r0,r1,$h0,$r2
+ umlal r2,r3,$h0,$r3
+ ldr $h0,[sp,#0]
+ mul $h4,$r0,$h4
+ ldr $h1,[sp,#4]
+
+ adds $h2,lr,r0 @ d2+=d1>>32
+ ldr lr,[sp,#8] @ reload input pointer
+ adc r1,r1,#0
+ adds $h3,r2,r1 @ d3+=d2>>32
+ ldr r0,[sp,#16] @ reload end pointer
+ adc r3,r3,#0
+ add $h4,$h4,r3 @ h4+=d3>>32
+
+ and r1,$h4,#-4
+ and $h4,$h4,#3
+ add r1,r1,r1,lsr#2 @ *=5
+ adds $h0,$h0,r1
+ adcs $h1,$h1,#0
+ adcs $h2,$h2,#0
+ adcs $h3,$h3,#0
+ adc $h4,$h4,#0
+
+ cmp r0,lr @ done yet?
+ bhi .Loop
+
+ ldr $ctx,[sp,#12]
+ add sp,sp,#32
+ stmdb $ctx,{$h0-$h4} @ store the result
+
+.Lno_data:
+#if __ARM_ARCH__>=5
+ ldmia sp!,{r3-r11,pc}
+#else
+ ldmia sp!,{r3-r11,lr}
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size poly1305_blocks,.-poly1305_blocks
+___
+}
+{
+my ($ctx,$mac,$nonce)=map("r$_",(0..2));
+my ($h0,$h1,$h2,$h3,$h4,$g0,$g1,$g2,$g3)=map("r$_",(3..11));
+my $g4=$ctx;
+
+$code.=<<___;
+.type poly1305_emit,%function
+.align 5
+poly1305_emit:
+.Lpoly1305_emit:
+ stmdb sp!,{r4-r11}
+
+ ldmia $ctx,{$h0-$h4}
+
+#if __ARM_ARCH__>=7
+ ldr ip,[$ctx,#36] @ is_base2_26
+
+ adds $g0,$h0,$h1,lsl#26 @ base 2^26 -> base 2^32
+ mov $g1,$h1,lsr#6
+ adcs $g1,$g1,$h2,lsl#20
+ mov $g2,$h2,lsr#12
+ adcs $g2,$g2,$h3,lsl#14
+ mov $g3,$h3,lsr#18
+ adcs $g3,$g3,$h4,lsl#8
+ mov $g4,#0
+ adc $g4,$g4,$h4,lsr#24
+
+ tst ip,ip
+ itttt ne
+ movne $h0,$g0
+ movne $h1,$g1
+ movne $h2,$g2
+ movne $h3,$g3
+ it ne
+ movne $h4,$g4
+#endif
+
+ adds $g0,$h0,#5 @ compare to modulus
+ adcs $g1,$h1,#0
+ adcs $g2,$h2,#0
+ adcs $g3,$h3,#0
+ adc $g4,$h4,#0
+ tst $g4,#4 @ did it carry/borrow?
+
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h0,$g0
+ ldr $g0,[$nonce,#0]
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h1,$g1
+ ldr $g1,[$nonce,#4]
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h2,$g2
+ ldr $g2,[$nonce,#8]
+#ifdef __thumb2__
+ it ne
+#endif
+ movne $h3,$g3
+ ldr $g3,[$nonce,#12]
+
+ adds $h0,$h0,$g0
+ adcs $h1,$h1,$g1
+ adcs $h2,$h2,$g2
+ adc $h3,$h3,$g3
+
+#if __ARM_ARCH__>=7
+# ifdef __ARMEB__
+ rev $h0,$h0
+ rev $h1,$h1
+ rev $h2,$h2
+ rev $h3,$h3
+# endif
+ str $h0,[$mac,#0]
+ str $h1,[$mac,#4]
+ str $h2,[$mac,#8]
+ str $h3,[$mac,#12]
+#else
+ strb $h0,[$mac,#0]
+ mov $h0,$h0,lsr#8
+ strb $h1,[$mac,#4]
+ mov $h1,$h1,lsr#8
+ strb $h2,[$mac,#8]
+ mov $h2,$h2,lsr#8
+ strb $h3,[$mac,#12]
+ mov $h3,$h3,lsr#8
+
+ strb $h0,[$mac,#1]
+ mov $h0,$h0,lsr#8
+ strb $h1,[$mac,#5]
+ mov $h1,$h1,lsr#8
+ strb $h2,[$mac,#9]
+ mov $h2,$h2,lsr#8
+ strb $h3,[$mac,#13]
+ mov $h3,$h3,lsr#8
+
+ strb $h0,[$mac,#2]
+ mov $h0,$h0,lsr#8
+ strb $h1,[$mac,#6]
+ mov $h1,$h1,lsr#8
+ strb $h2,[$mac,#10]
+ mov $h2,$h2,lsr#8
+ strb $h3,[$mac,#14]
+ mov $h3,$h3,lsr#8
+
+ strb $h0,[$mac,#3]
+ strb $h1,[$mac,#7]
+ strb $h2,[$mac,#11]
+ strb $h3,[$mac,#15]
+#endif
+ ldmia sp!,{r4-r11}
+#if __ARM_ARCH__>=5
+ ret @ bx lr
+#else
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size poly1305_emit,.-poly1305_emit
+___
+{
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("d$_",(0..9));
+my ($D0,$D1,$D2,$D3,$D4, $H0,$H1,$H2,$H3,$H4) = map("q$_",(5..14));
+my ($T0,$T1,$MASK) = map("q$_",(15,4,0));
+
+my ($in2,$zeros,$tbl0,$tbl1) = map("r$_",(4..7));
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.fpu neon
+
+.type poly1305_init_neon,%function
+.align 5
+poly1305_init_neon:
+.Lpoly1305_init_neon:
+ ldr r3,[$ctx,#48] @ first table element
+ cmp r3,#-1 @ is value impossible?
+ bne .Lno_init_neon
+
+ ldr r4,[$ctx,#20] @ load key base 2^32
+ ldr r5,[$ctx,#24]
+ ldr r6,[$ctx,#28]
+ ldr r7,[$ctx,#32]
+
+ and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
+ mov r3,r4,lsr#26
+ mov r4,r5,lsr#20
+ orr r3,r3,r5,lsl#6
+ mov r5,r6,lsr#14
+ orr r4,r4,r6,lsl#12
+ mov r6,r7,lsr#8
+ orr r5,r5,r7,lsl#18
+ and r3,r3,#0x03ffffff
+ and r4,r4,#0x03ffffff
+ and r5,r5,#0x03ffffff
+
+ vdup.32 $R0,r2 @ r^1 in both lanes
+ add r2,r3,r3,lsl#2 @ *5
+ vdup.32 $R1,r3
+ add r3,r4,r4,lsl#2
+ vdup.32 $S1,r2
+ vdup.32 $R2,r4
+ add r4,r5,r5,lsl#2
+ vdup.32 $S2,r3
+ vdup.32 $R3,r5
+ add r5,r6,r6,lsl#2
+ vdup.32 $S3,r4
+ vdup.32 $R4,r6
+ vdup.32 $S4,r5
+
+ mov $zeros,#2 @ counter
+
+.Lsquare_neon:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+ @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
+ @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
+ @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
+ @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
+
+ vmull.u32 $D0,$R0,${R0}[1]
+ vmull.u32 $D1,$R1,${R0}[1]
+ vmull.u32 $D2,$R2,${R0}[1]
+ vmull.u32 $D3,$R3,${R0}[1]
+ vmull.u32 $D4,$R4,${R0}[1]
+
+ vmlal.u32 $D0,$R4,${S1}[1]
+ vmlal.u32 $D1,$R0,${R1}[1]
+ vmlal.u32 $D2,$R1,${R1}[1]
+ vmlal.u32 $D3,$R2,${R1}[1]
+ vmlal.u32 $D4,$R3,${R1}[1]
+
+ vmlal.u32 $D0,$R3,${S2}[1]
+ vmlal.u32 $D1,$R4,${S2}[1]
+ vmlal.u32 $D3,$R1,${R2}[1]
+ vmlal.u32 $D2,$R0,${R2}[1]
+ vmlal.u32 $D4,$R2,${R2}[1]
+
+ vmlal.u32 $D0,$R2,${S3}[1]
+ vmlal.u32 $D3,$R0,${R3}[1]
+ vmlal.u32 $D1,$R3,${S3}[1]
+ vmlal.u32 $D2,$R4,${S3}[1]
+ vmlal.u32 $D4,$R1,${R3}[1]
+
+ vmlal.u32 $D3,$R4,${S4}[1]
+ vmlal.u32 $D0,$R1,${S4}[1]
+ vmlal.u32 $D1,$R2,${S4}[1]
+ vmlal.u32 $D2,$R3,${S4}[1]
+ vmlal.u32 $D4,$R0,${R4}[1]
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+ @ and P. Schwabe
+ @
+ @ H0>>+H1>>+H2>>+H3>>+H4
+ @ H3>>+H4>>*5+H0>>+H1
+ @
+ @ Trivia.
+ @
+ @ Result of multiplication of n-bit number by m-bit number is
+ @ n+m bits wide. However! Even though 2^n is a n+1-bit number,
+ @ m-bit number multiplied by 2^n is still n+m bits wide.
+ @
+ @ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
+ @ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
+ @ one is n+1 bits wide.
+ @
+ @ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
+ @ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
+ @ can be 27. However! In cases when their width exceeds 26 bits
+ @ they are limited by 2^26+2^6. This in turn means that *sum*
+ @ of the products with these values can still be viewed as sum
+ @ of 52-bit numbers as long as the amount of addends is not a
+ @ power of 2. For example,
+ @
+ @ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
+ @
+ @ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
+ @ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
+ @ 8 * (2^52) or 2^55. However, the value is then multiplied by
+ @ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
+ @ which is less than 32 * (2^52) or 2^57. And when processing
+ @ data we are looking at triple as many addends...
+ @
+ @ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
+ @ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
+ @ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
+ @ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
+ @ instruction accepts 2x32-bit input and writes 2x64-bit result.
+ @ This means that result of reduction have to be compressed upon
+ @ loop wrap-around. This can be done in the process of reduction
+ @ to minimize amount of instructions [as well as amount of
+ @ 128-bit instructions, which benefits low-end processors], but
+ @ one has to watch for H2 (which is narrower than H0) and 5*H4
+ @ not being wider than 58 bits, so that result of right shift
+ @ by 26 bits fits in 32 bits. This is also useful on x86,
+ @ because it allows to use paddd in place for paddq, which
+ @ benefits Atom, where paddq is ridiculously slow.
+
+ vshr.u64 $T0,$D3,#26
+ vmovn.i64 $D3#lo,$D3
+ vshr.u64 $T1,$D0,#26
+ vmovn.i64 $D0#lo,$D0
+ vadd.i64 $D4,$D4,$T0 @ h3 -> h4
+ vbic.i32 $D3#lo,#0xfc000000 @ &=0x03ffffff
+ vadd.i64 $D1,$D1,$T1 @ h0 -> h1
+ vbic.i32 $D0#lo,#0xfc000000
+
+ vshrn.u64 $T0#lo,$D4,#26
+ vmovn.i64 $D4#lo,$D4
+ vshr.u64 $T1,$D1,#26
+ vmovn.i64 $D1#lo,$D1
+ vadd.i64 $D2,$D2,$T1 @ h1 -> h2
+ vbic.i32 $D4#lo,#0xfc000000
+ vbic.i32 $D1#lo,#0xfc000000
+
+ vadd.i32 $D0#lo,$D0#lo,$T0#lo
+ vshl.u32 $T0#lo,$T0#lo,#2
+ vshrn.u64 $T1#lo,$D2,#26
+ vmovn.i64 $D2#lo,$D2
+ vadd.i32 $D0#lo,$D0#lo,$T0#lo @ h4 -> h0
+ vadd.i32 $D3#lo,$D3#lo,$T1#lo @ h2 -> h3
+ vbic.i32 $D2#lo,#0xfc000000
+
+ vshr.u32 $T0#lo,$D0#lo,#26
+ vbic.i32 $D0#lo,#0xfc000000
+ vshr.u32 $T1#lo,$D3#lo,#26
+ vbic.i32 $D3#lo,#0xfc000000
+ vadd.i32 $D1#lo,$D1#lo,$T0#lo @ h0 -> h1
+ vadd.i32 $D4#lo,$D4#lo,$T1#lo @ h3 -> h4
+
+ subs $zeros,$zeros,#1
+ beq .Lsquare_break_neon
+
+ add $tbl0,$ctx,#(48+0*9*4)
+ add $tbl1,$ctx,#(48+1*9*4)
+
+ vtrn.32 $R0,$D0#lo @ r^2:r^1
+ vtrn.32 $R2,$D2#lo
+ vtrn.32 $R3,$D3#lo
+ vtrn.32 $R1,$D1#lo
+ vtrn.32 $R4,$D4#lo
+
+ vshl.u32 $S2,$R2,#2 @ *5
+ vshl.u32 $S3,$R3,#2
+ vshl.u32 $S1,$R1,#2
+ vshl.u32 $S4,$R4,#2
+ vadd.i32 $S2,$S2,$R2
+ vadd.i32 $S1,$S1,$R1
+ vadd.i32 $S3,$S3,$R3
+ vadd.i32 $S4,$S4,$R4
+
+ vst4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+ vst4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+ vst4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vst4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vst1.32 {${S4}[0]},[$tbl0,:32]
+ vst1.32 {${S4}[1]},[$tbl1,:32]
+
+ b .Lsquare_neon
+
+.align 4
+.Lsquare_break_neon:
+ add $tbl0,$ctx,#(48+2*4*9)
+ add $tbl1,$ctx,#(48+3*4*9)
+
+ vmov $R0,$D0#lo @ r^4:r^3
+ vshl.u32 $S1,$D1#lo,#2 @ *5
+ vmov $R1,$D1#lo
+ vshl.u32 $S2,$D2#lo,#2
+ vmov $R2,$D2#lo
+ vshl.u32 $S3,$D3#lo,#2
+ vmov $R3,$D3#lo
+ vshl.u32 $S4,$D4#lo,#2
+ vmov $R4,$D4#lo
+ vadd.i32 $S1,$S1,$D1#lo
+ vadd.i32 $S2,$S2,$D2#lo
+ vadd.i32 $S3,$S3,$D3#lo
+ vadd.i32 $S4,$S4,$D4#lo
+
+ vst4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+ vst4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+ vst4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vst4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vst1.32 {${S4}[0]},[$tbl0]
+ vst1.32 {${S4}[1]},[$tbl1]
+
+.Lno_init_neon:
+ ret @ bx lr
+.size poly1305_init_neon,.-poly1305_init_neon
+
+.type poly1305_blocks_neon,%function
+.align 5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+ ldr ip,[$ctx,#36] @ is_base2_26
+
+ cmp $len,#64
+ blo .Lpoly1305_blocks
+
+ stmdb sp!,{r4-r7}
+ vstmdb sp!,{d8-d15} @ ABI specification says so
+
+ tst ip,ip @ is_base2_26?
+ bne .Lbase2_26_neon
+
+ stmdb sp!,{r1-r3,lr}
+ bl .Lpoly1305_init_neon
+
+ ldr r4,[$ctx,#0] @ load hash value base 2^32
+ ldr r5,[$ctx,#4]
+ ldr r6,[$ctx,#8]
+ ldr r7,[$ctx,#12]
+ ldr ip,[$ctx,#16]
+
+ and r2,r4,#0x03ffffff @ base 2^32 -> base 2^26
+ mov r3,r4,lsr#26
+ veor $D0#lo,$D0#lo,$D0#lo
+ mov r4,r5,lsr#20
+ orr r3,r3,r5,lsl#6
+ veor $D1#lo,$D1#lo,$D1#lo
+ mov r5,r6,lsr#14
+ orr r4,r4,r6,lsl#12
+ veor $D2#lo,$D2#lo,$D2#lo
+ mov r6,r7,lsr#8
+ orr r5,r5,r7,lsl#18
+ veor $D3#lo,$D3#lo,$D3#lo
+ and r3,r3,#0x03ffffff
+ orr r6,r6,ip,lsl#24
+ veor $D4#lo,$D4#lo,$D4#lo
+ and r4,r4,#0x03ffffff
+ mov r1,#1
+ and r5,r5,#0x03ffffff
+ str r1,[$ctx,#36] @ set is_base2_26
+
+ vmov.32 $D0#lo[0],r2
+ vmov.32 $D1#lo[0],r3
+ vmov.32 $D2#lo[0],r4
+ vmov.32 $D3#lo[0],r5
+ vmov.32 $D4#lo[0],r6
+ adr $zeros,.Lzeros
+
+ ldmia sp!,{r1-r3,lr}
+ b .Lhash_loaded
+
+.align 4
+.Lbase2_26_neon:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ load hash value
+
+ veor $D0#lo,$D0#lo,$D0#lo
+ veor $D1#lo,$D1#lo,$D1#lo
+ veor $D2#lo,$D2#lo,$D2#lo
+ veor $D3#lo,$D3#lo,$D3#lo
+ veor $D4#lo,$D4#lo,$D4#lo
+ vld4.32 {$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+ adr $zeros,.Lzeros
+ vld1.32 {$D4#lo[0]},[$ctx]
+ sub $ctx,$ctx,#16 @ rewind
+
+.Lhash_loaded:
+ add $in2,$inp,#32
+ mov $padbit,$padbit,lsl#24
+ tst $len,#31
+ beq .Leven
+
+ vld4.32 {$H0#lo[0],$H1#lo[0],$H2#lo[0],$H3#lo[0]},[$inp]!
+ vmov.32 $H4#lo[0],$padbit
+ sub $len,$len,#16
+ add $in2,$inp,#32
+
+# ifdef __ARMEB__
+ vrev32.8 $H0,$H0
+ vrev32.8 $H3,$H3
+ vrev32.8 $H1,$H1
+ vrev32.8 $H2,$H2
+# endif
+ vsri.u32 $H4#lo,$H3#lo,#8 @ base 2^32 -> base 2^26
+ vshl.u32 $H3#lo,$H3#lo,#18
+
+ vsri.u32 $H3#lo,$H2#lo,#14
+ vshl.u32 $H2#lo,$H2#lo,#12
+ vadd.i32 $H4#hi,$H4#lo,$D4#lo @ add hash value and move to #hi
+
+ vbic.i32 $H3#lo,#0xfc000000
+ vsri.u32 $H2#lo,$H1#lo,#20
+ vshl.u32 $H1#lo,$H1#lo,#6
+
+ vbic.i32 $H2#lo,#0xfc000000
+ vsri.u32 $H1#lo,$H0#lo,#26
+ vadd.i32 $H3#hi,$H3#lo,$D3#lo
+
+ vbic.i32 $H0#lo,#0xfc000000
+ vbic.i32 $H1#lo,#0xfc000000
+ vadd.i32 $H2#hi,$H2#lo,$D2#lo
+
+ vadd.i32 $H0#hi,$H0#lo,$D0#lo
+ vadd.i32 $H1#hi,$H1#lo,$D1#lo
+
+ mov $tbl1,$zeros
+ add $tbl0,$ctx,#48
+
+ cmp $len,$len
+ b .Long_tail
+
+.align 4
+.Leven:
+ subs $len,$len,#64
+ it lo
+ movlo $in2,$zeros
+
+ vmov.i32 $H4,#1<<24 @ padbit, yes, always
+ vld4.32 {$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp] @ inp[0:1]
+ add $inp,$inp,#64
+ vld4.32 {$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2] @ inp[2:3] (or 0)
+ add $in2,$in2,#64
+ itt hi
+ addhi $tbl1,$ctx,#(48+1*9*4)
+ addhi $tbl0,$ctx,#(48+3*9*4)
+
+# ifdef __ARMEB__
+ vrev32.8 $H0,$H0
+ vrev32.8 $H3,$H3
+ vrev32.8 $H1,$H1
+ vrev32.8 $H2,$H2
+# endif
+ vsri.u32 $H4,$H3,#8 @ base 2^32 -> base 2^26
+ vshl.u32 $H3,$H3,#18
+
+ vsri.u32 $H3,$H2,#14
+ vshl.u32 $H2,$H2,#12
+
+ vbic.i32 $H3,#0xfc000000
+ vsri.u32 $H2,$H1,#20
+ vshl.u32 $H1,$H1,#6
+
+ vbic.i32 $H2,#0xfc000000
+ vsri.u32 $H1,$H0,#26
+
+ vbic.i32 $H0,#0xfc000000
+ vbic.i32 $H1,#0xfc000000
+
+ bls .Lskip_loop
+
+ vld4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]! @ load r^2
+ vld4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]! @ load r^4
+ vld4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vld4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ b .Loop_neon
+
+.align 5
+.Loop_neon:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+ @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+ @ \___________________/
+ @ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+ @ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+ @ \___________________/ \____________________/
+ @
+ @ Note that we start with inp[2:3]*r^2. This is because it
+ @ doesn't depend on reduction in previous iteration.
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
+ @ d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
+ @ d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
+ @ d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
+ @ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ inp[2:3]*r^2
+
+ vadd.i32 $H2#lo,$H2#lo,$D2#lo @ accumulate inp[0:1]
+ vmull.u32 $D2,$H2#hi,${R0}[1]
+ vadd.i32 $H0#lo,$H0#lo,$D0#lo
+ vmull.u32 $D0,$H0#hi,${R0}[1]
+ vadd.i32 $H3#lo,$H3#lo,$D3#lo
+ vmull.u32 $D3,$H3#hi,${R0}[1]
+ vmlal.u32 $D2,$H1#hi,${R1}[1]
+ vadd.i32 $H1#lo,$H1#lo,$D1#lo
+ vmull.u32 $D1,$H1#hi,${R0}[1]
+
+ vadd.i32 $H4#lo,$H4#lo,$D4#lo
+ vmull.u32 $D4,$H4#hi,${R0}[1]
+ subs $len,$len,#64
+ vmlal.u32 $D0,$H4#hi,${S1}[1]
+ it lo
+ movlo $in2,$zeros
+ vmlal.u32 $D3,$H2#hi,${R1}[1]
+ vld1.32 ${S4}[1],[$tbl1,:32]
+ vmlal.u32 $D1,$H0#hi,${R1}[1]
+ vmlal.u32 $D4,$H3#hi,${R1}[1]
+
+ vmlal.u32 $D0,$H3#hi,${S2}[1]
+ vmlal.u32 $D3,$H1#hi,${R2}[1]
+ vmlal.u32 $D4,$H2#hi,${R2}[1]
+ vmlal.u32 $D1,$H4#hi,${S2}[1]
+ vmlal.u32 $D2,$H0#hi,${R2}[1]
+
+ vmlal.u32 $D3,$H0#hi,${R3}[1]
+ vmlal.u32 $D0,$H2#hi,${S3}[1]
+ vmlal.u32 $D4,$H1#hi,${R3}[1]
+ vmlal.u32 $D1,$H3#hi,${S3}[1]
+ vmlal.u32 $D2,$H4#hi,${S3}[1]
+
+ vmlal.u32 $D3,$H4#hi,${S4}[1]
+ vmlal.u32 $D0,$H1#hi,${S4}[1]
+ vmlal.u32 $D4,$H0#hi,${R4}[1]
+ vmlal.u32 $D1,$H2#hi,${S4}[1]
+ vmlal.u32 $D2,$H3#hi,${S4}[1]
+
+ vld4.32 {$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2] @ inp[2:3] (or 0)
+ add $in2,$in2,#64
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ (hash+inp[0:1])*r^4 and accumulate
+
+ vmlal.u32 $D3,$H3#lo,${R0}[0]
+ vmlal.u32 $D0,$H0#lo,${R0}[0]
+ vmlal.u32 $D4,$H4#lo,${R0}[0]
+ vmlal.u32 $D1,$H1#lo,${R0}[0]
+ vmlal.u32 $D2,$H2#lo,${R0}[0]
+ vld1.32 ${S4}[0],[$tbl0,:32]
+
+ vmlal.u32 $D3,$H2#lo,${R1}[0]
+ vmlal.u32 $D0,$H4#lo,${S1}[0]
+ vmlal.u32 $D4,$H3#lo,${R1}[0]
+ vmlal.u32 $D1,$H0#lo,${R1}[0]
+ vmlal.u32 $D2,$H1#lo,${R1}[0]
+
+ vmlal.u32 $D3,$H1#lo,${R2}[0]
+ vmlal.u32 $D0,$H3#lo,${S2}[0]
+ vmlal.u32 $D4,$H2#lo,${R2}[0]
+ vmlal.u32 $D1,$H4#lo,${S2}[0]
+ vmlal.u32 $D2,$H0#lo,${R2}[0]
+
+ vmlal.u32 $D3,$H0#lo,${R3}[0]
+ vmlal.u32 $D0,$H2#lo,${S3}[0]
+ vmlal.u32 $D4,$H1#lo,${R3}[0]
+ vmlal.u32 $D1,$H3#lo,${S3}[0]
+ vmlal.u32 $D3,$H4#lo,${S4}[0]
+
+ vmlal.u32 $D2,$H4#lo,${S3}[0]
+ vmlal.u32 $D0,$H1#lo,${S4}[0]
+ vmlal.u32 $D4,$H0#lo,${R4}[0]
+ vmov.i32 $H4,#1<<24 @ padbit, yes, always
+ vmlal.u32 $D1,$H2#lo,${S4}[0]
+ vmlal.u32 $D2,$H3#lo,${S4}[0]
+
+ vld4.32 {$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp] @ inp[0:1]
+ add $inp,$inp,#64
+# ifdef __ARMEB__
+ vrev32.8 $H0,$H0
+ vrev32.8 $H1,$H1
+ vrev32.8 $H2,$H2
+ vrev32.8 $H3,$H3
+# endif
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ lazy reduction interleaved with base 2^32 -> base 2^26 of
+ @ inp[0:3] previously loaded to $H0-$H3 and smashed to $H0-$H4.
+
+ vshr.u64 $T0,$D3,#26
+ vmovn.i64 $D3#lo,$D3
+ vshr.u64 $T1,$D0,#26
+ vmovn.i64 $D0#lo,$D0
+ vadd.i64 $D4,$D4,$T0 @ h3 -> h4
+ vbic.i32 $D3#lo,#0xfc000000
+ vsri.u32 $H4,$H3,#8 @ base 2^32 -> base 2^26
+ vadd.i64 $D1,$D1,$T1 @ h0 -> h1
+ vshl.u32 $H3,$H3,#18
+ vbic.i32 $D0#lo,#0xfc000000
+
+ vshrn.u64 $T0#lo,$D4,#26
+ vmovn.i64 $D4#lo,$D4
+ vshr.u64 $T1,$D1,#26
+ vmovn.i64 $D1#lo,$D1
+ vadd.i64 $D2,$D2,$T1 @ h1 -> h2
+ vsri.u32 $H3,$H2,#14
+ vbic.i32 $D4#lo,#0xfc000000
+ vshl.u32 $H2,$H2,#12
+ vbic.i32 $D1#lo,#0xfc000000
+
+ vadd.i32 $D0#lo,$D0#lo,$T0#lo
+ vshl.u32 $T0#lo,$T0#lo,#2
+ vbic.i32 $H3,#0xfc000000
+ vshrn.u64 $T1#lo,$D2,#26
+ vmovn.i64 $D2#lo,$D2
+ vaddl.u32 $D0,$D0#lo,$T0#lo @ h4 -> h0 [widen for a sec]
+ vsri.u32 $H2,$H1,#20
+ vadd.i32 $D3#lo,$D3#lo,$T1#lo @ h2 -> h3
+ vshl.u32 $H1,$H1,#6
+ vbic.i32 $D2#lo,#0xfc000000
+ vbic.i32 $H2,#0xfc000000
+
+ vshrn.u64 $T0#lo,$D0,#26 @ re-narrow
+ vmovn.i64 $D0#lo,$D0
+ vsri.u32 $H1,$H0,#26
+ vbic.i32 $H0,#0xfc000000
+ vshr.u32 $T1#lo,$D3#lo,#26
+ vbic.i32 $D3#lo,#0xfc000000
+ vbic.i32 $D0#lo,#0xfc000000
+ vadd.i32 $D1#lo,$D1#lo,$T0#lo @ h0 -> h1
+ vadd.i32 $D4#lo,$D4#lo,$T1#lo @ h3 -> h4
+ vbic.i32 $H1,#0xfc000000
+
+ bhi .Loop_neon
+
+.Lskip_loop:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+ add $tbl1,$ctx,#(48+0*9*4)
+ add $tbl0,$ctx,#(48+1*9*4)
+ adds $len,$len,#32
+ it ne
+ movne $len,#0
+ bne .Long_tail
+
+ vadd.i32 $H2#hi,$H2#lo,$D2#lo @ add hash value and move to #hi
+ vadd.i32 $H0#hi,$H0#lo,$D0#lo
+ vadd.i32 $H3#hi,$H3#lo,$D3#lo
+ vadd.i32 $H1#hi,$H1#lo,$D1#lo
+ vadd.i32 $H4#hi,$H4#lo,$D4#lo
+
+.Long_tail:
+ vld4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]! @ load r^1
+ vld4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]! @ load r^2
+
+ vadd.i32 $H2#lo,$H2#lo,$D2#lo @ can be redundant
+ vmull.u32 $D2,$H2#hi,$R0
+ vadd.i32 $H0#lo,$H0#lo,$D0#lo
+ vmull.u32 $D0,$H0#hi,$R0
+ vadd.i32 $H3#lo,$H3#lo,$D3#lo
+ vmull.u32 $D3,$H3#hi,$R0
+ vadd.i32 $H1#lo,$H1#lo,$D1#lo
+ vmull.u32 $D1,$H1#hi,$R0
+ vadd.i32 $H4#lo,$H4#lo,$D4#lo
+ vmull.u32 $D4,$H4#hi,$R0
+
+ vmlal.u32 $D0,$H4#hi,$S1
+ vld4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vmlal.u32 $D3,$H2#hi,$R1
+ vld4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vmlal.u32 $D1,$H0#hi,$R1
+ vmlal.u32 $D4,$H3#hi,$R1
+ vmlal.u32 $D2,$H1#hi,$R1
+
+ vmlal.u32 $D3,$H1#hi,$R2
+ vld1.32 ${S4}[1],[$tbl1,:32]
+ vmlal.u32 $D0,$H3#hi,$S2
+ vld1.32 ${S4}[0],[$tbl0,:32]
+ vmlal.u32 $D4,$H2#hi,$R2
+ vmlal.u32 $D1,$H4#hi,$S2
+ vmlal.u32 $D2,$H0#hi,$R2
+
+ vmlal.u32 $D3,$H0#hi,$R3
+ it ne
+ addne $tbl1,$ctx,#(48+2*9*4)
+ vmlal.u32 $D0,$H2#hi,$S3
+ it ne
+ addne $tbl0,$ctx,#(48+3*9*4)
+ vmlal.u32 $D4,$H1#hi,$R3
+ vmlal.u32 $D1,$H3#hi,$S3
+ vmlal.u32 $D2,$H4#hi,$S3
+
+ vmlal.u32 $D3,$H4#hi,$S4
+ vorn $MASK,$MASK,$MASK @ all-ones, can be redundant
+ vmlal.u32 $D0,$H1#hi,$S4
+ vshr.u64 $MASK,$MASK,#38
+ vmlal.u32 $D4,$H0#hi,$R4
+ vmlal.u32 $D1,$H2#hi,$S4
+ vmlal.u32 $D2,$H3#hi,$S4
+
+ beq .Lshort_tail
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ (hash+inp[0:1])*r^4:r^3 and accumulate
+
+ vld4.32 {${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]! @ load r^3
+ vld4.32 {${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]! @ load r^4
+
+ vmlal.u32 $D2,$H2#lo,$R0
+ vmlal.u32 $D0,$H0#lo,$R0
+ vmlal.u32 $D3,$H3#lo,$R0
+ vmlal.u32 $D1,$H1#lo,$R0
+ vmlal.u32 $D4,$H4#lo,$R0
+
+ vmlal.u32 $D0,$H4#lo,$S1
+ vld4.32 {${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+ vmlal.u32 $D3,$H2#lo,$R1
+ vld4.32 {${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+ vmlal.u32 $D1,$H0#lo,$R1
+ vmlal.u32 $D4,$H3#lo,$R1
+ vmlal.u32 $D2,$H1#lo,$R1
+
+ vmlal.u32 $D3,$H1#lo,$R2
+ vld1.32 ${S4}[1],[$tbl1,:32]
+ vmlal.u32 $D0,$H3#lo,$S2
+ vld1.32 ${S4}[0],[$tbl0,:32]
+ vmlal.u32 $D4,$H2#lo,$R2
+ vmlal.u32 $D1,$H4#lo,$S2
+ vmlal.u32 $D2,$H0#lo,$R2
+
+ vmlal.u32 $D3,$H0#lo,$R3
+ vmlal.u32 $D0,$H2#lo,$S3
+ vmlal.u32 $D4,$H1#lo,$R3
+ vmlal.u32 $D1,$H3#lo,$S3
+ vmlal.u32 $D2,$H4#lo,$S3
+
+ vmlal.u32 $D3,$H4#lo,$S4
+ vorn $MASK,$MASK,$MASK @ all-ones
+ vmlal.u32 $D0,$H1#lo,$S4
+ vshr.u64 $MASK,$MASK,#38
+ vmlal.u32 $D4,$H0#lo,$R4
+ vmlal.u32 $D1,$H2#lo,$S4
+ vmlal.u32 $D2,$H3#lo,$S4
+
+.Lshort_tail:
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ horizontal addition
+
+ vadd.i64 $D3#lo,$D3#lo,$D3#hi
+ vadd.i64 $D0#lo,$D0#lo,$D0#hi
+ vadd.i64 $D4#lo,$D4#lo,$D4#hi
+ vadd.i64 $D1#lo,$D1#lo,$D1#hi
+ vadd.i64 $D2#lo,$D2#lo,$D2#hi
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ lazy reduction, but without narrowing
+
+ vshr.u64 $T0,$D3,#26
+ vand.i64 $D3,$D3,$MASK
+ vshr.u64 $T1,$D0,#26
+ vand.i64 $D0,$D0,$MASK
+ vadd.i64 $D4,$D4,$T0 @ h3 -> h4
+ vadd.i64 $D1,$D1,$T1 @ h0 -> h1
+
+ vshr.u64 $T0,$D4,#26
+ vand.i64 $D4,$D4,$MASK
+ vshr.u64 $T1,$D1,#26
+ vand.i64 $D1,$D1,$MASK
+ vadd.i64 $D2,$D2,$T1 @ h1 -> h2
+
+ vadd.i64 $D0,$D0,$T0
+ vshl.u64 $T0,$T0,#2
+ vshr.u64 $T1,$D2,#26
+ vand.i64 $D2,$D2,$MASK
+ vadd.i64 $D0,$D0,$T0 @ h4 -> h0
+ vadd.i64 $D3,$D3,$T1 @ h2 -> h3
+
+ vshr.u64 $T0,$D0,#26
+ vand.i64 $D0,$D0,$MASK
+ vshr.u64 $T1,$D3,#26
+ vand.i64 $D3,$D3,$MASK
+ vadd.i64 $D1,$D1,$T0 @ h0 -> h1
+ vadd.i64 $D4,$D4,$T1 @ h3 -> h4
+
+ cmp $len,#0
+ bne .Leven
+
+ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+ @ store hash value
+
+ vst4.32 {$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+ vst1.32 {$D4#lo[0]},[$ctx]
+
+ vldmia sp!,{d8-d15} @ epilogue
+ ldmia sp!,{r4-r7}
+ ret @ bx lr
+.size poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align 5
+.Lzeros:
+.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+#ifndef __KERNEL__
+.LOPENSSL_armcap:
+# ifdef _WIN32
+.word OPENSSL_armcap_P
+# else
+.word OPENSSL_armcap_P-.Lpoly1305_init
+# endif
+.comm OPENSSL_armcap_P,4,4
+.hidden OPENSSL_armcap_P
+#endif
+#endif
+___
+} }
+$code.=<<___;
+.asciz "Poly1305 for ARMv4/NEON, CRYPTOGAMS by \@dot-asm"
+.align 2
+___
+
+foreach (split("\n",$code)) {
+ s/\`([^\`]*)\`/eval $1/geo;
+
+ s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo or
+ s/\bret\b/bx lr/go or
+ s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4
+
+ print $_,"\n";
+}
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
new file mode 100644
index 0000000000..c31bd8f7c0
--- /dev/null
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/jump_label.h>
+#include <linux/module.h>
+
+void poly1305_init_arm(void *state, const u8 *key);
+void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);
+void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
+void poly1305_emit_arm(void *state, u8 *digest, const u32 *nonce);
+
+void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
+{
+}
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
+{
+ poly1305_init_arm(&dctx->h, key);
+ dctx->s[0] = get_unaligned_le32(key + 16);
+ dctx->s[1] = get_unaligned_le32(key + 20);
+ dctx->s[2] = get_unaligned_le32(key + 24);
+ dctx->s[3] = get_unaligned_le32(key + 28);
+ dctx->buflen = 0;
+}
+EXPORT_SYMBOL(poly1305_init_arch);
+
+static int arm_poly1305_init(struct shash_desc *desc)
+{
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ dctx->buflen = 0;
+ dctx->rset = 0;
+ dctx->sset = false;
+
+ return 0;
+}
+
+static void arm_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
+ u32 len, u32 hibit, bool do_neon)
+{
+ if (unlikely(!dctx->sset)) {
+ if (!dctx->rset) {
+ poly1305_init_arm(&dctx->h, src);
+ src += POLY1305_BLOCK_SIZE;
+ len -= POLY1305_BLOCK_SIZE;
+ dctx->rset = 1;
+ }
+ if (len >= POLY1305_BLOCK_SIZE) {
+ dctx->s[0] = get_unaligned_le32(src + 0);
+ dctx->s[1] = get_unaligned_le32(src + 4);
+ dctx->s[2] = get_unaligned_le32(src + 8);
+ dctx->s[3] = get_unaligned_le32(src + 12);
+ src += POLY1305_BLOCK_SIZE;
+ len -= POLY1305_BLOCK_SIZE;
+ dctx->sset = true;
+ }
+ if (len < POLY1305_BLOCK_SIZE)
+ return;
+ }
+
+ len &= ~(POLY1305_BLOCK_SIZE - 1);
+
+ if (static_branch_likely(&have_neon) && likely(do_neon))
+ poly1305_blocks_neon(&dctx->h, src, len, hibit);
+ else
+ poly1305_blocks_arm(&dctx->h, src, len, hibit);
+}
+
+static void arm_poly1305_do_update(struct poly1305_desc_ctx *dctx,
+ const u8 *src, u32 len, bool do_neon)
+{
+ if (unlikely(dctx->buflen)) {
+ u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+ memcpy(dctx->buf + dctx->buflen, src, bytes);
+ src += bytes;
+ len -= bytes;
+ dctx->buflen += bytes;
+
+ if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+ arm_poly1305_blocks(dctx, dctx->buf,
+ POLY1305_BLOCK_SIZE, 1, false);
+ dctx->buflen = 0;
+ }
+ }
+
+ if (likely(len >= POLY1305_BLOCK_SIZE)) {
+ arm_poly1305_blocks(dctx, src, len, 1, do_neon);
+ src += round_down(len, POLY1305_BLOCK_SIZE);
+ len %= POLY1305_BLOCK_SIZE;
+ }
+
+ if (unlikely(len)) {
+ dctx->buflen = len;
+ memcpy(dctx->buf, src, len);
+ }
+}
+
+static int arm_poly1305_update(struct shash_desc *desc,
+ const u8 *src, unsigned int srclen)
+{
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ arm_poly1305_do_update(dctx, src, srclen, false);
+ return 0;
+}
+
+static int __maybe_unused arm_poly1305_update_neon(struct shash_desc *desc,
+ const u8 *src,
+ unsigned int srclen)
+{
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+ bool do_neon = crypto_simd_usable() && srclen > 128;
+
+ if (static_branch_likely(&have_neon) && do_neon)
+ kernel_neon_begin();
+ arm_poly1305_do_update(dctx, src, srclen, do_neon);
+ if (static_branch_likely(&have_neon) && do_neon)
+ kernel_neon_end();
+ return 0;
+}
+
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+ unsigned int nbytes)
+{
+ bool do_neon = IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+ crypto_simd_usable();
+
+ if (unlikely(dctx->buflen)) {
+ u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+ memcpy(dctx->buf + dctx->buflen, src, bytes);
+ src += bytes;
+ nbytes -= bytes;
+ dctx->buflen += bytes;
+
+ if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+ poly1305_blocks_arm(&dctx->h, dctx->buf,
+ POLY1305_BLOCK_SIZE, 1);
+ dctx->buflen = 0;
+ }
+ }
+
+ if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
+ unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
+
+ if (static_branch_likely(&have_neon) && do_neon) {
+ do {
+ unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+ kernel_neon_begin();
+ poly1305_blocks_neon(&dctx->h, src, todo, 1);
+ kernel_neon_end();
+
+ len -= todo;
+ src += todo;
+ } while (len);
+ } else {
+ poly1305_blocks_arm(&dctx->h, src, len, 1);
+ src += len;
+ }
+ nbytes %= POLY1305_BLOCK_SIZE;
+ }
+
+ if (unlikely(nbytes)) {
+ dctx->buflen = nbytes;
+ memcpy(dctx->buf, src, nbytes);
+ }
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
+{
+ if (unlikely(dctx->buflen)) {
+ dctx->buf[dctx->buflen++] = 1;
+ memset(dctx->buf + dctx->buflen, 0,
+ POLY1305_BLOCK_SIZE - dctx->buflen);
+ poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+ }
+
+ poly1305_emit_arm(&dctx->h, dst, dctx->s);
+ *dctx = (struct poly1305_desc_ctx){};
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int arm_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+ struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+ if (unlikely(!dctx->sset))
+ return -ENOKEY;
+
+ poly1305_final_arch(dctx, dst);
+ return 0;
+}
+
+static struct shash_alg arm_poly1305_algs[] = {{
+ .init = arm_poly1305_init,
+ .update = arm_poly1305_update,
+ .final = arm_poly1305_final,
+ .digestsize = POLY1305_DIGEST_SIZE,
+ .descsize = sizeof(struct poly1305_desc_ctx),
+
+ .base.cra_name = "poly1305",
+ .base.cra_driver_name = "poly1305-arm",
+ .base.cra_priority = 150,
+ .base.cra_blocksize = POLY1305_BLOCK_SIZE,
+ .base.cra_module = THIS_MODULE,
+#ifdef CONFIG_KERNEL_MODE_NEON
+}, {
+ .init = arm_poly1305_init,
+ .update = arm_poly1305_update_neon,
+ .final = arm_poly1305_final,
+ .digestsize = POLY1305_DIGEST_SIZE,
+ .descsize = sizeof(struct poly1305_desc_ctx),
+
+ .base.cra_name = "poly1305",
+ .base.cra_driver_name = "poly1305-neon",
+ .base.cra_priority = 200,
+ .base.cra_blocksize = POLY1305_BLOCK_SIZE,
+ .base.cra_module = THIS_MODULE,
+#endif
+}};
+
+static int __init arm_poly1305_mod_init(void)
+{
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+ (elf_hwcap & HWCAP_NEON))
+ static_branch_enable(&have_neon);
+ else if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
+ /* register only the first entry */
+ return crypto_register_shash(&arm_poly1305_algs[0]);
+
+ return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
+ crypto_register_shashes(arm_poly1305_algs,
+ ARRAY_SIZE(arm_poly1305_algs)) : 0;
+}
+
+static void __exit arm_poly1305_mod_exit(void)
+{
+ if (!IS_REACHABLE(CONFIG_CRYPTO_HASH))
+ return;
+ if (!static_branch_likely(&have_neon)) {
+ crypto_unregister_shash(&arm_poly1305_algs[0]);
+ return;
+ }
+ crypto_unregister_shashes(arm_poly1305_algs,
+ ARRAY_SIZE(arm_poly1305_algs));
+}
+
+module_init(arm_poly1305_mod_init);
+module_exit(arm_poly1305_mod_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-arm");
+MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
new file mode 100644
index 0000000000..1c8b685149
--- /dev/null
+++ b/arch/arm/crypto/sha1-armv4-large.S
@@ -0,0 +1,507 @@
+#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
new file mode 100644
index 0000000000..28d816a6a5
--- /dev/null
+++ b/arch/arm/crypto/sha1-armv7-neon.S
@@ -0,0 +1,634 @@
+/* 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
new file mode 100644
index 0000000000..8a702e0517
--- /dev/null
+++ b/arch/arm/crypto/sha1-ce-core.S
@@ -0,0 +1,123 @@
+/* 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
new file mode 100644
index 0000000000..de9100c67b
--- /dev/null
+++ b/arch/arm/crypto/sha1-ce-glue.c
@@ -0,0 +1,92 @@
+// 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 <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha1.h>
+#include <crypto/sha1_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+#include "sha1.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)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ if (!crypto_simd_usable() ||
+ (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
+ return sha1_update_arm(desc, data, len);
+
+ kernel_neon_begin();
+ sha1_base_do_update(desc, data, len, sha1_ce_transform);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ if (!crypto_simd_usable())
+ return sha1_finup_arm(desc, data, len, out);
+
+ kernel_neon_begin();
+ if (len)
+ sha1_base_do_update(desc, data, len, sha1_ce_transform);
+ sha1_base_do_finalize(desc, sha1_ce_transform);
+ kernel_neon_end();
+
+ return sha1_base_finish(desc, out);
+}
+
+static int sha1_ce_final(struct shash_desc *desc, u8 *out)
+{
+ return sha1_ce_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg alg = {
+ .init = sha1_base_init,
+ .update = sha1_ce_update,
+ .final = sha1_ce_final,
+ .finup = sha1_ce_finup,
+ .descsize = sizeof(struct sha1_state),
+ .digestsize = SHA1_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "sha1-ce",
+ .cra_priority = 200,
+ .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.h b/arch/arm/crypto/sha1.h
new file mode 100644
index 0000000000..b1b7e21da2
--- /dev/null
+++ b/arch/arm/crypto/sha1.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_ARM_CRYPTO_SHA1_H
+#define ASM_ARM_CRYPTO_SHA1_H
+
+#include <linux/crypto.h>
+#include <crypto/sha1.h>
+
+extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+ unsigned int len);
+
+extern int sha1_finup_arm(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out);
+
+#endif
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
new file mode 100644
index 0000000000..95a727bcd6
--- /dev/null
+++ b/arch/arm/crypto/sha1_glue.c
@@ -0,0 +1,86 @@
+// 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 <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/sha1.h>
+#include <crypto/sha1_base.h>
+#include <asm/byteorder.h>
+
+#include "sha1.h"
+
+asmlinkage void sha1_block_data_order(struct sha1_state *digest,
+ const u8 *data, int rounds);
+
+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(desc, data, len, sha1_block_data_order);
+}
+EXPORT_SYMBOL_GPL(sha1_update_arm);
+
+static int sha1_final(struct shash_desc *desc, u8 *out)
+{
+ sha1_base_do_finalize(desc, sha1_block_data_order);
+ return sha1_base_finish(desc, out);
+}
+
+int sha1_finup_arm(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ sha1_base_do_update(desc, data, len, sha1_block_data_order);
+ return sha1_final(desc, out);
+}
+EXPORT_SYMBOL_GPL(sha1_finup_arm);
+
+static struct shash_alg alg = {
+ .digestsize = SHA1_DIGEST_SIZE,
+ .init = sha1_base_init,
+ .update = sha1_update_arm,
+ .final = sha1_final,
+ .finup = sha1_finup_arm,
+ .descsize = sizeof(struct sha1_state),
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name= "sha1-asm",
+ .cra_priority = 150,
+ .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
new file mode 100644
index 0000000000..9c70b87e69
--- /dev/null
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -0,0 +1,102 @@
+// 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 <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <crypto/sha1.h>
+#include <crypto/sha1_base.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+#include "sha1.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)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ if (!crypto_simd_usable() ||
+ (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
+ return sha1_update_arm(desc, data, len);
+
+ kernel_neon_begin();
+ sha1_base_do_update(desc, data, len, sha1_transform_neon);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int sha1_neon_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ if (!crypto_simd_usable())
+ return sha1_finup_arm(desc, data, len, out);
+
+ kernel_neon_begin();
+ if (len)
+ sha1_base_do_update(desc, data, len, sha1_transform_neon);
+ sha1_base_do_finalize(desc, sha1_transform_neon);
+ kernel_neon_end();
+
+ return sha1_base_finish(desc, out);
+}
+
+static int sha1_neon_final(struct shash_desc *desc, u8 *out)
+{
+ return sha1_neon_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg alg = {
+ .digestsize = SHA1_DIGEST_SIZE,
+ .init = sha1_base_init,
+ .update = sha1_neon_update,
+ .final = sha1_neon_final,
+ .finup = sha1_neon_finup,
+ .descsize = sizeof(struct sha1_state),
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "sha1-neon",
+ .cra_priority = 250,
+ .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/sha2-ce-core.S b/arch/arm/crypto/sha2-ce-core.S
new file mode 100644
index 0000000000..b6369d2440
--- /dev/null
+++ b/arch/arm/crypto/sha2-ce-core.S
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sha2-ce-core.S - SHA-224/256 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 q7
+ k1 .req q8
+ rk .req r3
+
+ ta0 .req q9
+ ta1 .req q10
+ tb0 .req q10
+ tb1 .req q9
+
+ dga .req q11
+ dgb .req q12
+
+ dg0 .req q13
+ dg1 .req q14
+ dg2 .req q15
+
+ .macro add_only, ev, s0
+ vmov dg2, dg0
+ .ifnb \s0
+ vld1.32 {k\ev}, [rk, :128]!
+ .endif
+ sha256h.32 dg0, dg1, tb\ev
+ sha256h2.32 dg1, dg2, tb\ev
+ .ifnb \s0
+ vadd.u32 ta\ev, q\s0, k\ev
+ .endif
+ .endm
+
+ .macro add_update, ev, s0, s1, s2, s3
+ sha256su0.32 q\s0, q\s1
+ add_only \ev, \s1
+ sha256su1.32 q\s0, q\s2, q\s3
+ .endm
+
+ .align 6
+.Lsha256_rcon:
+ .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+ .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+ .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+ .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+ .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+ .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+ .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+ .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+ .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+ .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+ .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+ .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+ .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+ .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+ .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+ .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+ /*
+ * void sha2_ce_transform(struct sha256_state *sst, u8 const *src,
+ int blocks);
+ */
+ENTRY(sha2_ce_transform)
+ /* load state */
+ vld1.32 {dga-dgb}, [r0]
+
+ /* load input */
+0: vld1.32 {q0-q1}, [r1]!
+ vld1.32 {q2-q3}, [r1]!
+ subs r2, r2, #1
+
+#ifndef CONFIG_CPU_BIG_ENDIAN
+ vrev32.8 q0, q0
+ vrev32.8 q1, q1
+ vrev32.8 q2, q2
+ vrev32.8 q3, q3
+#endif
+
+ /* load first round constant */
+ adr rk, .Lsha256_rcon
+ vld1.32 {k0}, [rk, :128]!
+
+ vadd.u32 ta0, q0, k0
+ vmov dg0, dga
+ vmov dg1, dgb
+
+ add_update 1, 0, 1, 2, 3
+ add_update 0, 1, 2, 3, 0
+ add_update 1, 2, 3, 0, 1
+ add_update 0, 3, 0, 1, 2
+ add_update 1, 0, 1, 2, 3
+ add_update 0, 1, 2, 3, 0
+ add_update 1, 2, 3, 0, 1
+ add_update 0, 3, 0, 1, 2
+ add_update 1, 0, 1, 2, 3
+ add_update 0, 1, 2, 3, 0
+ add_update 1, 2, 3, 0, 1
+ add_update 0, 3, 0, 1, 2
+
+ add_only 1, 1
+ add_only 0, 2
+ add_only 1, 3
+ add_only 0
+
+ /* update state */
+ vadd.u32 dga, dga, dg0
+ vadd.u32 dgb, dgb, dg1
+ bne 0b
+
+ /* store new state */
+ vst1.32 {dga-dgb}, [r0]
+ bx lr
+ENDPROC(sha2_ce_transform)
diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
new file mode 100644
index 0000000000..c62ce89dd3
--- /dev/null
+++ b/arch/arm/crypto/sha2-ce-glue.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha2.h>
+#include <crypto/sha256_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+
+#include "sha256_glue.h"
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha2_ce_transform(struct sha256_state *sst, u8 const *src,
+ int blocks);
+
+static int sha2_ce_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ if (!crypto_simd_usable() ||
+ (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
+ return crypto_sha256_arm_update(desc, data, len);
+
+ kernel_neon_begin();
+ sha256_base_do_update(desc, data, len,
+ (sha256_block_fn *)sha2_ce_transform);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int sha2_ce_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ if (!crypto_simd_usable())
+ return crypto_sha256_arm_finup(desc, data, len, out);
+
+ kernel_neon_begin();
+ if (len)
+ sha256_base_do_update(desc, data, len,
+ (sha256_block_fn *)sha2_ce_transform);
+ sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
+ kernel_neon_end();
+
+ return sha256_base_finish(desc, out);
+}
+
+static int sha2_ce_final(struct shash_desc *desc, u8 *out)
+{
+ return sha2_ce_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg algs[] = { {
+ .init = sha224_base_init,
+ .update = sha2_ce_update,
+ .final = sha2_ce_final,
+ .finup = sha2_ce_finup,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA224_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-ce",
+ .cra_priority = 300,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .init = sha256_base_init,
+ .update = sha2_ce_update,
+ .final = sha2_ce_final,
+ .finup = sha2_ce_finup,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA256_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-ce",
+ .cra_priority = 300,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+ return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
new file mode 100644
index 0000000000..f3a2b54efd
--- /dev/null
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -0,0 +1,724 @@
+#!/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/.
+# ====================================================================
+
+# SHA256 block procedure for ARMv4. May 2007.
+
+# Performance is ~2x better than gcc 3.4 generated code and in "abso-
+# lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
+# byte [on single-issue Xscale PXA250 core].
+
+# July 2010.
+#
+# Rescheduling for dual-issue pipeline resulted in 22% improvement on
+# Cortex A8 core and ~20 cycles per processed byte.
+
+# February 2011.
+#
+# Profiler-assisted and platform-specific optimization resulted in 16%
+# improvement on Cortex A8 core and ~15.4 cycles per processed byte.
+
+# September 2013.
+#
+# Add NEON implementation. On Cortex A8 it was measured to process one
+# byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
+# S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
+# code (meaning that latter performs sub-optimally, nothing was done
+# about it).
+
+# May 2014.
+#
+# Add ARMv8 code path performing at 2.0 cpb on Apple A7.
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$ctx="r0"; $t0="r0";
+$inp="r1"; $t4="r1";
+$len="r2"; $t1="r2";
+$T1="r3"; $t3="r3";
+$A="r4";
+$B="r5";
+$C="r6";
+$D="r7";
+$E="r8";
+$F="r9";
+$G="r10";
+$H="r11";
+@V=($A,$B,$C,$D,$E,$F,$G,$H);
+$t2="r12";
+$Ktbl="r14";
+
+@Sigma0=( 2,13,22);
+@Sigma1=( 6,11,25);
+@sigma0=( 7,18, 3);
+@sigma1=(17,19,10);
+
+sub BODY_00_15 {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_;
+
+$code.=<<___ if ($i<16);
+#if __ARM_ARCH__>=7
+ @ ldr $t1,[$inp],#4 @ $i
+# if $i==15
+ str $inp,[sp,#17*4] @ make room for $t4
+# endif
+ eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
+ add $a,$a,$t2 @ h+=Maj(a,b,c) from the past
+ eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e)
+# ifndef __ARMEB__
+ rev $t1,$t1
+# endif
+#else
+ @ ldrb $t1,[$inp,#3] @ $i
+ add $a,$a,$t2 @ h+=Maj(a,b,c) from the past
+ ldrb $t2,[$inp,#2]
+ ldrb $t0,[$inp,#1]
+ orr $t1,$t1,$t2,lsl#8
+ ldrb $t2,[$inp],#4
+ orr $t1,$t1,$t0,lsl#16
+# if $i==15
+ str $inp,[sp,#17*4] @ make room for $t4
+# endif
+ eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
+ orr $t1,$t1,$t2,lsl#24
+ eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e)
+#endif
+___
+$code.=<<___;
+ ldr $t2,[$Ktbl],#4 @ *K256++
+ add $h,$h,$t1 @ h+=X[i]
+ str $t1,[sp,#`$i%16`*4]
+ eor $t1,$f,$g
+ add $h,$h,$t0,ror#$Sigma1[0] @ h+=Sigma1(e)
+ and $t1,$t1,$e
+ add $h,$h,$t2 @ h+=K256[i]
+ eor $t1,$t1,$g @ Ch(e,f,g)
+ eor $t0,$a,$a,ror#`$Sigma0[1]-$Sigma0[0]`
+ add $h,$h,$t1 @ h+=Ch(e,f,g)
+#if $i==31
+ and $t2,$t2,#0xff
+ cmp $t2,#0xf2 @ done?
+#endif
+#if $i<15
+# if __ARM_ARCH__>=7
+ ldr $t1,[$inp],#4 @ prefetch
+# else
+ ldrb $t1,[$inp,#3]
+# endif
+ eor $t2,$a,$b @ a^b, b^c in next round
+#else
+ ldr $t1,[sp,#`($i+2)%16`*4] @ from future BODY_16_xx
+ eor $t2,$a,$b @ a^b, b^c in next round
+ ldr $t4,[sp,#`($i+15)%16`*4] @ from future BODY_16_xx
+#endif
+ eor $t0,$t0,$a,ror#`$Sigma0[2]-$Sigma0[0]` @ Sigma0(a)
+ and $t3,$t3,$t2 @ (b^c)&=(a^b)
+ add $d,$d,$h @ d+=h
+ eor $t3,$t3,$b @ Maj(a,b,c)
+ add $h,$h,$t0,ror#$Sigma0[0] @ h+=Sigma0(a)
+ @ add $h,$h,$t3 @ h+=Maj(a,b,c)
+___
+ ($t2,$t3)=($t3,$t2);
+}
+
+sub BODY_16_XX {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_;
+
+$code.=<<___;
+ @ ldr $t1,[sp,#`($i+1)%16`*4] @ $i
+ @ ldr $t4,[sp,#`($i+14)%16`*4]
+ mov $t0,$t1,ror#$sigma0[0]
+ add $a,$a,$t2 @ h+=Maj(a,b,c) from the past
+ mov $t2,$t4,ror#$sigma1[0]
+ eor $t0,$t0,$t1,ror#$sigma0[1]
+ eor $t2,$t2,$t4,ror#$sigma1[1]
+ eor $t0,$t0,$t1,lsr#$sigma0[2] @ sigma0(X[i+1])
+ ldr $t1,[sp,#`($i+0)%16`*4]
+ eor $t2,$t2,$t4,lsr#$sigma1[2] @ sigma1(X[i+14])
+ ldr $t4,[sp,#`($i+9)%16`*4]
+
+ add $t2,$t2,$t0
+ eor $t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]` @ from BODY_00_15
+ add $t1,$t1,$t2
+ eor $t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]` @ Sigma1(e)
+ add $t1,$t1,$t4 @ X[i]
+___
+ &BODY_00_15(@_);
+}
+
+$code=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code 32
+#else
+.syntax unified
+# ifdef __thumb2__
+.thumb
+# else
+.code 32
+# endif
+#endif
+
+.type K256,%object
+.align 5
+K256:
+.word 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+.word 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+.word 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+.word 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+.word 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+.word 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+.word 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+.word 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+.word 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+.word 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+.word 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+.word 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+.word 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+.word 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+.word 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+.size K256,.-K256
+.word 0 @ terminator
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word OPENSSL_armcap_P-sha256_block_data_order
+#endif
+.align 5
+
+.global sha256_block_data_order
+.type sha256_block_data_order,%function
+sha256_block_data_order:
+.Lsha256_block_data_order:
+#if __ARM_ARCH__<7
+ sub r3,pc,#8 @ sha256_block_data_order
+#else
+ adr r3,.Lsha256_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+ ldr r12,.LOPENSSL_armcap
+ ldr r12,[r3,r12] @ OPENSSL_armcap_P
+ tst r12,#ARMV8_SHA256
+ bne .LARMv8
+ tst r12,#ARMV7_NEON
+ bne .LNEON
+#endif
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
+ stmdb sp!,{$ctx,$inp,$len,r4-r11,lr}
+ ldmia $ctx,{$A,$B,$C,$D,$E,$F,$G,$H}
+ sub $Ktbl,r3,#256+32 @ K256
+ sub sp,sp,#16*4 @ alloca(X[16])
+.Loop:
+# if __ARM_ARCH__>=7
+ ldr $t1,[$inp],#4
+# else
+ ldrb $t1,[$inp,#3]
+# endif
+ eor $t3,$B,$C @ magic
+ eor $t2,$t2,$t2
+___
+for($i=0;$i<16;$i++) { &BODY_00_15($i,@V); unshift(@V,pop(@V)); }
+$code.=".Lrounds_16_xx:\n";
+for (;$i<32;$i++) { &BODY_16_XX($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+#if __ARM_ARCH__>=7
+ ite eq @ Thumb2 thing, sanity check in ARM
+#endif
+ ldreq $t3,[sp,#16*4] @ pull ctx
+ bne .Lrounds_16_xx
+
+ add $A,$A,$t2 @ h+=Maj(a,b,c) from the past
+ ldr $t0,[$t3,#0]
+ ldr $t1,[$t3,#4]
+ ldr $t2,[$t3,#8]
+ add $A,$A,$t0
+ ldr $t0,[$t3,#12]
+ add $B,$B,$t1
+ ldr $t1,[$t3,#16]
+ add $C,$C,$t2
+ ldr $t2,[$t3,#20]
+ add $D,$D,$t0
+ ldr $t0,[$t3,#24]
+ add $E,$E,$t1
+ ldr $t1,[$t3,#28]
+ add $F,$F,$t2
+ ldr $inp,[sp,#17*4] @ pull inp
+ ldr $t2,[sp,#18*4] @ pull inp+len
+ add $G,$G,$t0
+ add $H,$H,$t1
+ stmia $t3,{$A,$B,$C,$D,$E,$F,$G,$H}
+ cmp $inp,$t2
+ sub $Ktbl,$Ktbl,#256 @ rewind Ktbl
+ bne .Loop
+
+ add sp,sp,#`16+3`*4 @ destroy frame
+#if __ARM_ARCH__>=5
+ ldmia sp!,{r4-r11,pc}
+#else
+ ldmia sp!,{r4-r11,lr}
+ tst lr,#1
+ moveq pc,lr @ be binary compatible with V4, yet
+ bx lr @ interoperable with Thumb ISA:-)
+#endif
+.size sha256_block_data_order,.-sha256_block_data_order
+___
+######################################################################
+# NEON stuff
+#
+{{{
+my @X=map("q$_",(0..3));
+my ($T0,$T1,$T2,$T3,$T4,$T5)=("q8","q9","q10","q11","d24","d25");
+my $Xfer=$t4;
+my $j=0;
+
+sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; }
+sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; }
+
+sub AUTOLOAD() # thunk [simplified] x86-style perlasm
+{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./;
+ my $arg = pop;
+ $arg = "#$arg" if ($arg*1 eq $arg);
+ $code .= "\t$opcode\t".join(',',@_,$arg)."\n";
+}
+
+sub Xupdate()
+{ use integer;
+ my $body = shift;
+ my @insns = (&$body,&$body,&$body,&$body);
+ my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+ &vext_8 ($T0,@X[0],@X[1],4); # X[1..4]
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vext_8 ($T1,@X[2],@X[3],4); # X[9..12]
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T2,$T0,$sigma0[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += X[9..12]
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T1,$T0,$sigma0[2]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T2,$T0,32-$sigma0[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T3,$T0,$sigma0[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T1,$T1,$T2);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T3,$T0,32-$sigma0[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T1,$T1,$T3); # sigma0(X[1..4])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T5,&Dhi(@X[3]),$sigma1[2]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (@X[0],@X[0],$T1); # X[0..3] += sigma0(X[1..4])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dhi(@X[3]),$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dhi(@X[3]),32-$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4); # sigma1(X[14..15])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (&Dlo(@X[0]),&Dlo(@X[0]),$T5);# X[0..1] += sigma1(X[14..15])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T5,&Dlo(@X[0]),$sigma1[2]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vshr_u32 ($T4,&Dlo(@X[0]),$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vld1_32 ("{$T0}","[$Ktbl,:128]!");
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vsli_32 ($T4,&Dlo(@X[0]),32-$sigma1[1]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &veor ($T5,$T5,$T4); # sigma1(X[16..17])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 (&Dhi(@X[0]),&Dhi(@X[0]),$T5);# X[2..3] += sigma1(X[16..17])
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 ($T0,$T0,@X[0]);
+ while($#insns>=2) { eval(shift(@insns)); }
+ &vst1_32 ("{$T0}","[$Xfer,:128]!");
+ eval(shift(@insns));
+ eval(shift(@insns));
+
+ push(@X,shift(@X)); # "rotate" X[]
+}
+
+sub Xpreload()
+{ use integer;
+ my $body = shift;
+ my @insns = (&$body,&$body,&$body,&$body);
+ my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vld1_32 ("{$T0}","[$Ktbl,:128]!");
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vrev32_8 (@X[0],@X[0]);
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ eval(shift(@insns));
+ &vadd_i32 ($T0,$T0,@X[0]);
+ foreach (@insns) { eval; } # remaining instructions
+ &vst1_32 ("{$T0}","[$Xfer,:128]!");
+
+ push(@X,shift(@X)); # "rotate" X[]
+}
+
+sub body_00_15 () {
+ (
+ '($a,$b,$c,$d,$e,$f,$g,$h)=@V;'.
+ '&add ($h,$h,$t1)', # h+=X[i]+K[i]
+ '&eor ($t1,$f,$g)',
+ '&eor ($t0,$e,$e,"ror#".($Sigma1[1]-$Sigma1[0]))',
+ '&add ($a,$a,$t2)', # h+=Maj(a,b,c) from the past
+ '&and ($t1,$t1,$e)',
+ '&eor ($t2,$t0,$e,"ror#".($Sigma1[2]-$Sigma1[0]))', # Sigma1(e)
+ '&eor ($t0,$a,$a,"ror#".($Sigma0[1]-$Sigma0[0]))',
+ '&eor ($t1,$t1,$g)', # Ch(e,f,g)
+ '&add ($h,$h,$t2,"ror#$Sigma1[0]")', # h+=Sigma1(e)
+ '&eor ($t2,$a,$b)', # a^b, b^c in next round
+ '&eor ($t0,$t0,$a,"ror#".($Sigma0[2]-$Sigma0[0]))', # Sigma0(a)
+ '&add ($h,$h,$t1)', # h+=Ch(e,f,g)
+ '&ldr ($t1,sprintf "[sp,#%d]",4*(($j+1)&15)) if (($j&15)!=15);'.
+ '&ldr ($t1,"[$Ktbl]") if ($j==15);'.
+ '&ldr ($t1,"[sp,#64]") if ($j==31)',
+ '&and ($t3,$t3,$t2)', # (b^c)&=(a^b)
+ '&add ($d,$d,$h)', # d+=h
+ '&add ($h,$h,$t0,"ror#$Sigma0[0]");'. # h+=Sigma0(a)
+ '&eor ($t3,$t3,$b)', # Maj(a,b,c)
+ '$j++; unshift(@V,pop(@V)); ($t2,$t3)=($t3,$t2);'
+ )
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch armv7-a
+.fpu neon
+
+.global sha256_block_data_order_neon
+.type sha256_block_data_order_neon,%function
+.align 4
+sha256_block_data_order_neon:
+.LNEON:
+ stmdb sp!,{r4-r12,lr}
+
+ sub $H,sp,#16*4+16
+ adr $Ktbl,.Lsha256_block_data_order
+ sub $Ktbl,$Ktbl,#.Lsha256_block_data_order-K256
+ bic $H,$H,#15 @ align for 128-bit stores
+ mov $t2,sp
+ mov sp,$H @ alloca
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
+
+ vld1.8 {@X[0]},[$inp]!
+ vld1.8 {@X[1]},[$inp]!
+ vld1.8 {@X[2]},[$inp]!
+ vld1.8 {@X[3]},[$inp]!
+ vld1.32 {$T0},[$Ktbl,:128]!
+ vld1.32 {$T1},[$Ktbl,:128]!
+ vld1.32 {$T2},[$Ktbl,:128]!
+ vld1.32 {$T3},[$Ktbl,:128]!
+ vrev32.8 @X[0],@X[0] @ yes, even on
+ str $ctx,[sp,#64]
+ vrev32.8 @X[1],@X[1] @ big-endian
+ str $inp,[sp,#68]
+ mov $Xfer,sp
+ vrev32.8 @X[2],@X[2]
+ str $len,[sp,#72]
+ vrev32.8 @X[3],@X[3]
+ str $t2,[sp,#76] @ save original sp
+ vadd.i32 $T0,$T0,@X[0]
+ vadd.i32 $T1,$T1,@X[1]
+ vst1.32 {$T0},[$Xfer,:128]!
+ vadd.i32 $T2,$T2,@X[2]
+ vst1.32 {$T1},[$Xfer,:128]!
+ vadd.i32 $T3,$T3,@X[3]
+ vst1.32 {$T2},[$Xfer,:128]!
+ vst1.32 {$T3},[$Xfer,:128]!
+
+ ldmia $ctx,{$A-$H}
+ sub $Xfer,$Xfer,#64
+ ldr $t1,[sp,#0]
+ eor $t2,$t2,$t2
+ eor $t3,$B,$C
+ b .L_00_48
+
+.align 4
+.L_00_48:
+___
+ &Xupdate(\&body_00_15);
+ &Xupdate(\&body_00_15);
+ &Xupdate(\&body_00_15);
+ &Xupdate(\&body_00_15);
+$code.=<<___;
+ teq $t1,#0 @ check for K256 terminator
+ ldr $t1,[sp,#0]
+ sub $Xfer,$Xfer,#64
+ bne .L_00_48
+
+ ldr $inp,[sp,#68]
+ ldr $t0,[sp,#72]
+ sub $Ktbl,$Ktbl,#256 @ rewind $Ktbl
+ teq $inp,$t0
+ it eq
+ subeq $inp,$inp,#64 @ avoid SEGV
+ vld1.8 {@X[0]},[$inp]! @ load next input block
+ vld1.8 {@X[1]},[$inp]!
+ vld1.8 {@X[2]},[$inp]!
+ vld1.8 {@X[3]},[$inp]!
+ it ne
+ strne $inp,[sp,#68]
+ mov $Xfer,sp
+___
+ &Xpreload(\&body_00_15);
+ &Xpreload(\&body_00_15);
+ &Xpreload(\&body_00_15);
+ &Xpreload(\&body_00_15);
+$code.=<<___;
+ ldr $t0,[$t1,#0]
+ add $A,$A,$t2 @ h+=Maj(a,b,c) from the past
+ ldr $t2,[$t1,#4]
+ ldr $t3,[$t1,#8]
+ ldr $t4,[$t1,#12]
+ add $A,$A,$t0 @ accumulate
+ ldr $t0,[$t1,#16]
+ add $B,$B,$t2
+ ldr $t2,[$t1,#20]
+ add $C,$C,$t3
+ ldr $t3,[$t1,#24]
+ add $D,$D,$t4
+ ldr $t4,[$t1,#28]
+ add $E,$E,$t0
+ str $A,[$t1],#4
+ add $F,$F,$t2
+ str $B,[$t1],#4
+ add $G,$G,$t3
+ str $C,[$t1],#4
+ add $H,$H,$t4
+ str $D,[$t1],#4
+ stmia $t1,{$E-$H}
+
+ ittte ne
+ movne $Xfer,sp
+ ldrne $t1,[sp,#0]
+ eorne $t2,$t2,$t2
+ ldreq sp,[sp,#76] @ restore original sp
+ itt ne
+ eorne $t3,$B,$C
+ bne .L_00_48
+
+ ldmia sp!,{r4-r12,pc}
+.size sha256_block_data_order_neon,.-sha256_block_data_order_neon
+#endif
+___
+}}}
+######################################################################
+# ARMv8 stuff
+#
+{{{
+my ($ABCD,$EFGH,$abcd)=map("q$_",(0..2));
+my @MSG=map("q$_",(8..11));
+my ($W0,$W1,$ABCD_SAVE,$EFGH_SAVE)=map("q$_",(12..15));
+my $Ktbl="r3";
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+
+# ifdef __thumb2__
+# define INST(a,b,c,d) .byte c,d|0xc,a,b
+# else
+# define INST(a,b,c,d) .byte a,b,c,d
+# endif
+
+.type sha256_block_data_order_armv8,%function
+.align 5
+sha256_block_data_order_armv8:
+.LARMv8:
+ vld1.32 {$ABCD,$EFGH},[$ctx]
+# ifdef __thumb2__
+ adr $Ktbl,.LARMv8
+ sub $Ktbl,$Ktbl,#.LARMv8-K256
+# else
+ adrl $Ktbl,K256
+# endif
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
+
+.Loop_v8:
+ vld1.8 {@MSG[0]-@MSG[1]},[$inp]!
+ vld1.8 {@MSG[2]-@MSG[3]},[$inp]!
+ vld1.32 {$W0},[$Ktbl]!
+ vrev32.8 @MSG[0],@MSG[0]
+ vrev32.8 @MSG[1],@MSG[1]
+ vrev32.8 @MSG[2],@MSG[2]
+ vrev32.8 @MSG[3],@MSG[3]
+ vmov $ABCD_SAVE,$ABCD @ offload
+ vmov $EFGH_SAVE,$EFGH
+ teq $inp,$len
+___
+for($i=0;$i<12;$i++) {
+$code.=<<___;
+ vld1.32 {$W1},[$Ktbl]!
+ vadd.i32 $W0,$W0,@MSG[0]
+ sha256su0 @MSG[0],@MSG[1]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W0
+ sha256h2 $EFGH,$abcd,$W0
+ sha256su1 @MSG[0],@MSG[2],@MSG[3]
+___
+ ($W0,$W1)=($W1,$W0); push(@MSG,shift(@MSG));
+}
+$code.=<<___;
+ vld1.32 {$W1},[$Ktbl]!
+ vadd.i32 $W0,$W0,@MSG[0]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W0
+ sha256h2 $EFGH,$abcd,$W0
+
+ vld1.32 {$W0},[$Ktbl]!
+ vadd.i32 $W1,$W1,@MSG[1]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W1
+ sha256h2 $EFGH,$abcd,$W1
+
+ vld1.32 {$W1},[$Ktbl]
+ vadd.i32 $W0,$W0,@MSG[2]
+ sub $Ktbl,$Ktbl,#256-16 @ rewind
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W0
+ sha256h2 $EFGH,$abcd,$W0
+
+ vadd.i32 $W1,$W1,@MSG[3]
+ vmov $abcd,$ABCD
+ sha256h $ABCD,$EFGH,$W1
+ sha256h2 $EFGH,$abcd,$W1
+
+ vadd.i32 $ABCD,$ABCD,$ABCD_SAVE
+ vadd.i32 $EFGH,$EFGH,$EFGH_SAVE
+ it ne
+ bne .Loop_v8
+
+ vst1.32 {$ABCD,$EFGH},[$ctx]
+
+ ret @ bx lr
+.size sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
+#endif
+___
+}}}
+$code.=<<___;
+.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align 2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm OPENSSL_armcap_P,4,4
+#endif
+___
+
+open SELF,$0;
+while(<SELF>) {
+ next if (/^#!/);
+ last if (!s/^#/@/ and !/^$/);
+ print;
+}
+close SELF;
+
+{ my %opcode = (
+ "sha256h" => 0xf3000c40, "sha256h2" => 0xf3100c40,
+ "sha256su0" => 0xf3ba03c0, "sha256su1" => 0xf3200c40 );
+
+ sub unsha256 {
+ my ($mnemonic,$arg)=@_;
+
+ if ($arg =~ m/q([0-9]+)(?:,\s*q([0-9]+))?,\s*q([0-9]+)/o) {
+ my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19)
+ |(($2&7)<<17)|(($2&8)<<4)
+ |(($3&7)<<1) |(($3&8)<<2);
+ # since ARMv7 instructions are always encoded little-endian.
+ # correct solution is to use .inst directive, but older
+ # assemblers don't implement it:-(
+ sprintf "INST(0x%02x,0x%02x,0x%02x,0x%02x)\t@ %s %s",
+ $word&0xff,($word>>8)&0xff,
+ ($word>>16)&0xff,($word>>24)&0xff,
+ $mnemonic,$arg;
+ }
+ }
+}
+
+foreach (split($/,$code)) {
+
+ s/\`([^\`]*)\`/eval $1/geo;
+
+ s/\b(sha256\w+)\s+(q.*)/unsha256($1,$2)/geo;
+
+ s/\bret\b/bx lr/go or
+ s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4
+
+ print $_,"\n";
+}
+
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
new file mode 100644
index 0000000000..433ee4ddce
--- /dev/null
+++ b/arch/arm/crypto/sha256_glue.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
+ * using optimized ARM assembler and NEON instructions.
+ *
+ * Copyright © 2015 Google Inc.
+ *
+ * This file is based on sha256_ssse3_glue.c:
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha2.h>
+#include <crypto/sha256_base.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+#include "sha256_glue.h"
+
+asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
+ unsigned int num_blks);
+
+int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ /* make sure casting to sha256_block_fn() is safe */
+ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0);
+
+ return sha256_base_do_update(desc, data, len,
+ (sha256_block_fn *)sha256_block_data_order);
+}
+EXPORT_SYMBOL(crypto_sha256_arm_update);
+
+static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out)
+{
+ sha256_base_do_finalize(desc,
+ (sha256_block_fn *)sha256_block_data_order);
+ return sha256_base_finish(desc, out);
+}
+
+int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ sha256_base_do_update(desc, data, len,
+ (sha256_block_fn *)sha256_block_data_order);
+ return crypto_sha256_arm_final(desc, out);
+}
+EXPORT_SYMBOL(crypto_sha256_arm_finup);
+
+static struct shash_alg algs[] = { {
+ .digestsize = SHA256_DIGEST_SIZE,
+ .init = sha256_base_init,
+ .update = crypto_sha256_arm_update,
+ .final = crypto_sha256_arm_final,
+ .finup = crypto_sha256_arm_finup,
+ .descsize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-asm",
+ .cra_priority = 150,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .digestsize = SHA224_DIGEST_SIZE,
+ .init = sha224_base_init,
+ .update = crypto_sha256_arm_update,
+ .final = crypto_sha256_arm_final,
+ .finup = crypto_sha256_arm_finup,
+ .descsize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-asm",
+ .cra_priority = 150,
+ .cra_blocksize = SHA224_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha256_mod_init(void)
+{
+ int res = crypto_register_shashes(algs, ARRAY_SIZE(algs));
+
+ if (res < 0)
+ return res;
+
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
+ res = crypto_register_shashes(sha256_neon_algs,
+ ARRAY_SIZE(sha256_neon_algs));
+
+ if (res < 0)
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+ }
+
+ return res;
+}
+
+static void __exit sha256_mod_fini(void)
+{
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
+ crypto_unregister_shashes(sha256_neon_algs,
+ ARRAY_SIZE(sha256_neon_algs));
+}
+
+module_init(sha256_mod_init);
+module_exit(sha256_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm (ARM), including NEON");
+
+MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/arm/crypto/sha256_glue.h b/arch/arm/crypto/sha256_glue.h
new file mode 100644
index 0000000000..9f0d578bab
--- /dev/null
+++ b/arch/arm/crypto/sha256_glue.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _CRYPTO_SHA256_GLUE_H
+#define _CRYPTO_SHA256_GLUE_H
+
+#include <linux/crypto.h>
+
+extern struct shash_alg sha256_neon_algs[2];
+
+int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len);
+
+int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *hash);
+
+#endif /* _CRYPTO_SHA256_GLUE_H */
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
new file mode 100644
index 0000000000..ccdcfff719
--- /dev/null
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
+ * using NEON instructions.
+ *
+ * Copyright © 2015 Google Inc.
+ *
+ * This file is based on sha512_neon_glue.c:
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha2.h>
+#include <crypto/sha256_base.h>
+#include <asm/byteorder.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+#include "sha256_glue.h"
+
+asmlinkage void sha256_block_data_order_neon(struct sha256_state *digest,
+ const u8 *data, int num_blks);
+
+static int crypto_sha256_neon_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ if (!crypto_simd_usable() ||
+ (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
+ return crypto_sha256_arm_update(desc, data, len);
+
+ kernel_neon_begin();
+ sha256_base_do_update(desc, data, len, sha256_block_data_order_neon);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int crypto_sha256_neon_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ if (!crypto_simd_usable())
+ return crypto_sha256_arm_finup(desc, data, len, out);
+
+ kernel_neon_begin();
+ if (len)
+ sha256_base_do_update(desc, data, len,
+ sha256_block_data_order_neon);
+ sha256_base_do_finalize(desc, sha256_block_data_order_neon);
+ kernel_neon_end();
+
+ return sha256_base_finish(desc, out);
+}
+
+static int crypto_sha256_neon_final(struct shash_desc *desc, u8 *out)
+{
+ return crypto_sha256_neon_finup(desc, NULL, 0, out);
+}
+
+struct shash_alg sha256_neon_algs[] = { {
+ .digestsize = SHA256_DIGEST_SIZE,
+ .init = sha256_base_init,
+ .update = crypto_sha256_neon_update,
+ .final = crypto_sha256_neon_final,
+ .finup = crypto_sha256_neon_finup,
+ .descsize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-neon",
+ .cra_priority = 250,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .digestsize = SHA224_DIGEST_SIZE,
+ .init = sha224_base_init,
+ .update = crypto_sha256_neon_update,
+ .final = crypto_sha256_neon_final,
+ .finup = crypto_sha256_neon_finup,
+ .descsize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-neon",
+ .cra_priority = 250,
+ .cra_blocksize = SHA224_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
new file mode 100644
index 0000000000..2fc3516912
--- /dev/null
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -0,0 +1,657 @@
+#!/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
new file mode 100644
index 0000000000..0635a65aa4
--- /dev/null
+++ b/arch/arm/crypto/sha512-glue.c
@@ -0,0 +1,116 @@
+// 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 <crypto/internal/hash.h>
+#include <crypto/sha2.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.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(u64 *state, u8 const *src, int blocks);
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ return sha512_base_do_update(desc, data, len,
+ (sha512_block_fn *)sha512_block_data_order);
+}
+
+static int sha512_arm_final(struct shash_desc *desc, u8 *out)
+{
+ sha512_base_do_finalize(desc,
+ (sha512_block_fn *)sha512_block_data_order);
+ return sha512_base_finish(desc, out);
+}
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ sha512_base_do_update(desc, data, len,
+ (sha512_block_fn *)sha512_block_data_order);
+ return sha512_arm_final(desc, out);
+}
+
+static struct shash_alg sha512_arm_algs[] = { {
+ .init = sha384_base_init,
+ .update = sha512_arm_update,
+ .final = sha512_arm_final,
+ .finup = sha512_arm_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA384_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha384",
+ .cra_driver_name = "sha384-arm",
+ .cra_priority = 250,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .init = sha512_base_init,
+ .update = sha512_arm_update,
+ .final = sha512_arm_final,
+ .finup = sha512_arm_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA512_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha512",
+ .cra_driver_name = "sha512-arm",
+ .cra_priority = 250,
+ .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
new file mode 100644
index 0000000000..c6e58fe475
--- /dev/null
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -0,0 +1,92 @@
+// 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 <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha2.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/simd.h>
+#include <asm/neon.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)
+{
+ struct sha512_state *sctx = shash_desc_ctx(desc);
+
+ if (!crypto_simd_usable() ||
+ (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
+ return sha512_arm_update(desc, data, len);
+
+ kernel_neon_begin();
+ sha512_base_do_update(desc, data, len, sha512_block_data_order_neon);
+ kernel_neon_end();
+
+ return 0;
+}
+
+static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ if (!crypto_simd_usable())
+ return sha512_arm_finup(desc, data, len, out);
+
+ kernel_neon_begin();
+ if (len)
+ sha512_base_do_update(desc, data, len,
+ sha512_block_data_order_neon);
+ sha512_base_do_finalize(desc, sha512_block_data_order_neon);
+ kernel_neon_end();
+
+ return sha512_base_finish(desc, out);
+}
+
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+ return sha512_neon_finup(desc, NULL, 0, out);
+}
+
+struct shash_alg sha512_neon_algs[] = { {
+ .init = sha384_base_init,
+ .update = sha512_neon_update,
+ .final = sha512_neon_final,
+ .finup = sha512_neon_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA384_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha384",
+ .cra_driver_name = "sha384-neon",
+ .cra_priority = 300,
+ .cra_blocksize = SHA384_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+
+ }
+}, {
+ .init = sha512_base_init,
+ .update = sha512_neon_update,
+ .final = sha512_neon_final,
+ .finup = sha512_neon_finup,
+ .descsize = sizeof(struct sha512_state),
+ .digestsize = SHA512_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha512",
+ .cra_driver_name = "sha512-neon",
+ .cra_priority = 300,
+ .cra_blocksize = SHA512_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
new file mode 100644
index 0000000000..e14572be76
--- /dev/null
+++ b/arch/arm/crypto/sha512.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len);
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out);
+
+extern struct shash_alg sha512_neon_algs[2];